{"current_steps": 5, "total_steps": 40000, "loss": 2.1246, "lr": 4.999999876629946e-05, "epoch": 0.00022635188664297517, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "13:09:47", "throughput": 1544.86, "total_tokens": 9152} {"current_steps": 10, "total_steps": 40000, "loss": 2.5796, "lr": 4.999999375439123e-05, "epoch": 0.00045270377328595035, "percentage": 0.03, "elapsed_time": "0:00:09", "remaining_time": "10:02:10", "throughput": 1898.39, "total_tokens": 17152} {"current_steps": 15, "total_steps": 40000, "loss": 2.2741, "lr": 4.9999984887169785e-05, "epoch": 0.0006790556599289255, "percentage": 0.04, "elapsed_time": "0:00:12", "remaining_time": "9:03:19", "throughput": 2072.38, "total_tokens": 25344} {"current_steps": 20, "total_steps": 40000, "loss": 2.1236, "lr": 4.9999972164636506e-05, "epoch": 0.0009054075465719007, "percentage": 0.05, "elapsed_time": "0:00:15", "remaining_time": "8:38:02", "throughput": 2191.75, "total_tokens": 34080} {"current_steps": 25, "total_steps": 40000, "loss": 2.369, "lr": 4.999995558679334e-05, "epoch": 0.0011317594332148758, "percentage": 0.06, "elapsed_time": "0:00:18", "remaining_time": "8:15:53", "throughput": 2225.29, "total_tokens": 41408} {"current_steps": 30, "total_steps": 40000, "loss": 2.346, "lr": 4.999993515364287e-05, "epoch": 0.001358111319857851, "percentage": 0.07, "elapsed_time": "0:00:21", "remaining_time": "8:05:34", "throughput": 2281.38, "total_tokens": 49888} {"current_steps": 35, "total_steps": 40000, "loss": 2.4199, "lr": 4.999991086518822e-05, "epoch": 0.0015844632065008261, "percentage": 0.09, "elapsed_time": "0:00:25", "remaining_time": "7:56:27", "throughput": 2317.32, "total_tokens": 58016} {"current_steps": 40, "total_steps": 40000, "loss": 2.2586, "lr": 4.999988272143315e-05, "epoch": 0.0018108150931438014, "percentage": 0.1, "elapsed_time": "0:00:28", "remaining_time": "7:49:09", "throughput": 2339.42, "total_tokens": 65920} {"current_steps": 45, "total_steps": 40000, "loss": 2.4836, "lr": 4.999985072238199e-05, "epoch": 0.0020371669797867764, "percentage": 0.11, "elapsed_time": "0:00:31", "remaining_time": "7:44:10", "throughput": 2353.53, "total_tokens": 73824} {"current_steps": 50, "total_steps": 40000, "loss": 1.7353, "lr": 4.999981486803969e-05, "epoch": 0.0022635188664297517, "percentage": 0.12, "elapsed_time": "0:00:34", "remaining_time": "7:41:12", "throughput": 2388.38, "total_tokens": 82720} {"current_steps": 55, "total_steps": 40000, "loss": 1.2899, "lr": 4.999977515841176e-05, "epoch": 0.002489870753072727, "percentage": 0.14, "elapsed_time": "0:00:37", "remaining_time": "7:36:46", "throughput": 2394.72, "total_tokens": 90368} {"current_steps": 60, "total_steps": 40000, "loss": 1.2832, "lr": 4.9999731593504344e-05, "epoch": 0.002716222639715702, "percentage": 0.15, "elapsed_time": "0:00:40", "remaining_time": "7:32:46", "throughput": 2400.12, "total_tokens": 97952} {"current_steps": 65, "total_steps": 40000, "loss": 1.0173, "lr": 4.999968417332415e-05, "epoch": 0.002942574526358677, "percentage": 0.16, "elapsed_time": "0:00:43", "remaining_time": "7:28:59", "throughput": 2402.45, "total_tokens": 105344} {"current_steps": 70, "total_steps": 40000, "loss": 0.722, "lr": 4.999963289787848e-05, "epoch": 0.0031689264130016523, "percentage": 0.18, "elapsed_time": "0:00:47", "remaining_time": "7:26:56", "throughput": 2410.3, "total_tokens": 113312} {"current_steps": 75, "total_steps": 40000, "loss": 0.8752, "lr": 4.999957776717526e-05, "epoch": 0.0033952782996446275, "percentage": 0.19, "elapsed_time": "0:00:50", "remaining_time": "7:24:52", "throughput": 2414.28, "total_tokens": 121056} {"current_steps": 80, "total_steps": 40000, "loss": 0.6573, "lr": 4.9999518781222984e-05, "epoch": 0.0036216301862876028, "percentage": 0.2, "elapsed_time": "0:00:53", "remaining_time": "7:22:43", "throughput": 2419.57, "total_tokens": 128800} {"current_steps": 85, "total_steps": 40000, "loss": 0.6734, "lr": 4.9999455940030746e-05, "epoch": 0.003847982072930578, "percentage": 0.21, "elapsed_time": "0:00:56", "remaining_time": "7:22:39", "throughput": 2439.04, "total_tokens": 137952} {"current_steps": 90, "total_steps": 40000, "loss": 0.5341, "lr": 4.999938924360824e-05, "epoch": 0.004074333959573553, "percentage": 0.22, "elapsed_time": "0:00:59", "remaining_time": "7:21:10", "throughput": 2441.82, "total_tokens": 145760} {"current_steps": 95, "total_steps": 40000, "loss": 0.5605, "lr": 4.999931869196575e-05, "epoch": 0.0043006858462165285, "percentage": 0.24, "elapsed_time": "0:01:02", "remaining_time": "7:19:56", "throughput": 2446.33, "total_tokens": 153728} {"current_steps": 100, "total_steps": 40000, "loss": 0.4603, "lr": 4.999924428511416e-05, "epoch": 0.004527037732859503, "percentage": 0.25, "elapsed_time": "0:01:05", "remaining_time": "7:18:43", "throughput": 2452.85, "total_tokens": 161824} {"current_steps": 105, "total_steps": 40000, "loss": 0.3978, "lr": 4.999916602306494e-05, "epoch": 0.004753389619502478, "percentage": 0.26, "elapsed_time": "0:01:09", "remaining_time": "7:17:31", "throughput": 2454.21, "total_tokens": 169568} {"current_steps": 110, "total_steps": 40000, "loss": 0.2952, "lr": 4.999908390583016e-05, "epoch": 0.004979741506145454, "percentage": 0.27, "elapsed_time": "0:01:12", "remaining_time": "7:16:29", "throughput": 2459.12, "total_tokens": 177600} {"current_steps": 115, "total_steps": 40000, "loss": 0.3797, "lr": 4.999899793342247e-05, "epoch": 0.005206093392788429, "percentage": 0.29, "elapsed_time": "0:01:15", "remaining_time": "7:15:55", "throughput": 2465.32, "total_tokens": 185920} {"current_steps": 120, "total_steps": 40000, "loss": 0.6056, "lr": 4.999890810585516e-05, "epoch": 0.005432445279431404, "percentage": 0.3, "elapsed_time": "0:01:18", "remaining_time": "7:15:09", "throughput": 2468.35, "total_tokens": 193920} {"current_steps": 125, "total_steps": 40000, "loss": 0.5774, "lr": 4.999881442314206e-05, "epoch": 0.005658797166074379, "percentage": 0.31, "elapsed_time": "0:01:21", "remaining_time": "7:14:12", "throughput": 2468.07, "total_tokens": 201568} {"current_steps": 130, "total_steps": 40000, "loss": 0.4443, "lr": 4.9998716885297617e-05, "epoch": 0.005885149052717354, "percentage": 0.33, "elapsed_time": "0:01:24", "remaining_time": "7:13:32", "throughput": 2469.38, "total_tokens": 209440} {"current_steps": 135, "total_steps": 40000, "loss": 0.417, "lr": 4.999861549233688e-05, "epoch": 0.00611150093936033, "percentage": 0.34, "elapsed_time": "0:01:27", "remaining_time": "7:12:59", "throughput": 2474.08, "total_tokens": 217664} {"current_steps": 140, "total_steps": 40000, "loss": 0.2993, "lr": 4.999851024427548e-05, "epoch": 0.0063378528260033045, "percentage": 0.35, "elapsed_time": "0:01:31", "remaining_time": "7:12:14", "throughput": 2476.32, "total_tokens": 225568} {"current_steps": 145, "total_steps": 40000, "loss": 0.3689, "lr": 4.999840114112965e-05, "epoch": 0.00656420471264628, "percentage": 0.36, "elapsed_time": "0:01:34", "remaining_time": "7:12:59", "throughput": 2484.65, "total_tokens": 234848} {"current_steps": 150, "total_steps": 40000, "loss": 0.4545, "lr": 4.999828818291621e-05, "epoch": 0.006790556599289255, "percentage": 0.38, "elapsed_time": "0:01:37", "remaining_time": "7:12:28", "throughput": 2488.31, "total_tokens": 243040} {"current_steps": 155, "total_steps": 40000, "loss": 0.3115, "lr": 4.999817136965259e-05, "epoch": 0.00701690848593223, "percentage": 0.39, "elapsed_time": "0:01:40", "remaining_time": "7:11:51", "throughput": 2490.21, "total_tokens": 251008} {"current_steps": 160, "total_steps": 40000, "loss": 0.2772, "lr": 4.9998050701356794e-05, "epoch": 0.0072432603725752056, "percentage": 0.4, "elapsed_time": "0:01:43", "remaining_time": "7:11:30", "throughput": 2493.13, "total_tokens": 259232} {"current_steps": 165, "total_steps": 40000, "loss": 0.4504, "lr": 4.999792617804744e-05, "epoch": 0.00746961225921818, "percentage": 0.41, "elapsed_time": "0:01:47", "remaining_time": "7:11:02", "throughput": 2494.32, "total_tokens": 267200} {"current_steps": 170, "total_steps": 40000, "loss": 0.3514, "lr": 4.9997797799743724e-05, "epoch": 0.007695964145861156, "percentage": 0.43, "elapsed_time": "0:01:50", "remaining_time": "7:11:24", "throughput": 2498.81, "total_tokens": 276064} {"current_steps": 175, "total_steps": 40000, "loss": 0.4366, "lr": 4.999766556646545e-05, "epoch": 0.007922316032504132, "percentage": 0.44, "elapsed_time": "0:01:53", "remaining_time": "7:10:57", "throughput": 2497.51, "total_tokens": 283776} {"current_steps": 180, "total_steps": 40000, "loss": 0.402, "lr": 4.9997529478232996e-05, "epoch": 0.008148667919147106, "percentage": 0.45, "elapsed_time": "0:01:56", "remaining_time": "7:10:38", "throughput": 2500.59, "total_tokens": 292064} {"current_steps": 185, "total_steps": 40000, "loss": 0.3653, "lr": 4.9997389535067365e-05, "epoch": 0.008375019805790081, "percentage": 0.46, "elapsed_time": "0:01:59", "remaining_time": "7:10:20", "throughput": 2501.61, "total_tokens": 300128} {"current_steps": 190, "total_steps": 40000, "loss": 0.3906, "lr": 4.999724573699012e-05, "epoch": 0.008601371692433057, "percentage": 0.47, "elapsed_time": "0:02:03", "remaining_time": "7:10:20", "throughput": 2505.1, "total_tokens": 308704} {"current_steps": 195, "total_steps": 40000, "loss": 0.4125, "lr": 4.9997098084023457e-05, "epoch": 0.008827723579076031, "percentage": 0.49, "elapsed_time": "0:02:06", "remaining_time": "7:09:41", "throughput": 2505.23, "total_tokens": 316416} {"current_steps": 200, "total_steps": 40000, "loss": 0.3032, "lr": 4.999694657619013e-05, "epoch": 0.009054075465719007, "percentage": 0.5, "elapsed_time": "0:02:09", "remaining_time": "7:09:29", "throughput": 2505.53, "total_tokens": 324448} {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.3444136083126068, "epoch": 0.009054075465719007, "percentage": 0.5, "elapsed_time": "0:09:51", "remaining_time": "1 day, 8:43:11", "throughput": 548.13, "total_tokens": 324448} {"current_steps": 205, "total_steps": 40000, "loss": 0.3287, "lr": 4.999679121351352e-05, "epoch": 0.009280427352361982, "percentage": 0.51, "elapsed_time": "0:09:56", "remaining_time": "1 day, 8:08:24", "throughput": 559.26, "total_tokens": 333344} {"current_steps": 210, "total_steps": 40000, "loss": 0.3015, "lr": 4.9996631996017565e-05, "epoch": 0.009506779239004956, "percentage": 0.53, "elapsed_time": "0:09:59", "remaining_time": "1 day, 7:33:04", "throughput": 571.39, "total_tokens": 342528} {"current_steps": 215, "total_steps": 40000, "loss": 0.5199, "lr": 4.9996468923726835e-05, "epoch": 0.009733131125647932, "percentage": 0.54, "elapsed_time": "0:10:02", "remaining_time": "1 day, 6:58:36", "throughput": 581.97, "total_tokens": 350720} {"current_steps": 220, "total_steps": 40000, "loss": 0.3087, "lr": 4.999630199666647e-05, "epoch": 0.009959483012290908, "percentage": 0.55, "elapsed_time": "0:10:05", "remaining_time": "1 day, 6:26:05", "throughput": 593.54, "total_tokens": 359648} {"current_steps": 225, "total_steps": 40000, "loss": 0.3944, "lr": 4.999613121486222e-05, "epoch": 0.010185834898933883, "percentage": 0.56, "elapsed_time": "0:10:09", "remaining_time": "1 day, 5:54:30", "throughput": 603.73, "total_tokens": 367712} {"current_steps": 230, "total_steps": 40000, "loss": 0.2192, "lr": 4.999595657834041e-05, "epoch": 0.010412186785576857, "percentage": 0.57, "elapsed_time": "0:10:12", "remaining_time": "1 day, 5:24:02", "throughput": 613.01, "total_tokens": 375232} {"current_steps": 235, "total_steps": 40000, "loss": 0.2915, "lr": 4.999577808712798e-05, "epoch": 0.010638538672219833, "percentage": 0.59, "elapsed_time": "0:10:15", "remaining_time": "1 day, 4:55:12", "throughput": 622.91, "total_tokens": 383264} {"current_steps": 240, "total_steps": 40000, "loss": 0.362, "lr": 4.999559574125244e-05, "epoch": 0.010864890558862809, "percentage": 0.6, "elapsed_time": "0:10:18", "remaining_time": "1 day, 4:27:27", "throughput": 632.61, "total_tokens": 391200} {"current_steps": 245, "total_steps": 40000, "loss": 0.2475, "lr": 4.9995409540741934e-05, "epoch": 0.011091242445505783, "percentage": 0.61, "elapsed_time": "0:10:21", "remaining_time": "1 day, 4:01:06", "throughput": 643.13, "total_tokens": 399776} {"current_steps": 250, "total_steps": 40000, "loss": 0.2546, "lr": 4.999521948562516e-05, "epoch": 0.011317594332148758, "percentage": 0.62, "elapsed_time": "0:10:24", "remaining_time": "1 day, 3:35:34", "throughput": 652.56, "total_tokens": 407680} {"current_steps": 255, "total_steps": 40000, "loss": 0.2477, "lr": 4.999502557593143e-05, "epoch": 0.011543946218791734, "percentage": 0.64, "elapsed_time": "0:10:27", "remaining_time": "1 day, 3:11:03", "throughput": 661.88, "total_tokens": 415584} {"current_steps": 260, "total_steps": 40000, "loss": 0.2742, "lr": 4.999482781169066e-05, "epoch": 0.011770298105434708, "percentage": 0.65, "elapsed_time": "0:10:31", "remaining_time": "1 day, 2:47:43", "throughput": 671.62, "total_tokens": 423872} {"current_steps": 265, "total_steps": 40000, "loss": 0.2898, "lr": 4.9994626192933324e-05, "epoch": 0.011996649992077684, "percentage": 0.66, "elapsed_time": "0:10:34", "remaining_time": "1 day, 2:25:04", "throughput": 680.69, "total_tokens": 431744} {"current_steps": 270, "total_steps": 40000, "loss": 0.3186, "lr": 4.999442071969054e-05, "epoch": 0.01222300187872066, "percentage": 0.68, "elapsed_time": "0:10:37", "remaining_time": "1 day, 2:03:26", "throughput": 689.95, "total_tokens": 439840} {"current_steps": 275, "total_steps": 40000, "loss": 0.2708, "lr": 4.999421139199397e-05, "epoch": 0.012449353765363635, "percentage": 0.69, "elapsed_time": "0:10:40", "remaining_time": "1 day, 1:42:20", "throughput": 698.77, "total_tokens": 447648} {"current_steps": 280, "total_steps": 40000, "loss": 0.3127, "lr": 4.999399820987592e-05, "epoch": 0.012675705652006609, "percentage": 0.7, "elapsed_time": "0:10:43", "remaining_time": "1 day, 1:22:02", "throughput": 707.69, "total_tokens": 455584} {"current_steps": 285, "total_steps": 40000, "loss": 0.2249, "lr": 4.999378117336924e-05, "epoch": 0.012902057538649585, "percentage": 0.71, "elapsed_time": "0:10:46", "remaining_time": "1 day, 1:02:28", "throughput": 716.65, "total_tokens": 463616} {"current_steps": 290, "total_steps": 40000, "loss": 0.295, "lr": 4.9993560282507415e-05, "epoch": 0.01312840942529256, "percentage": 0.73, "elapsed_time": "0:10:50", "remaining_time": "1 day, 0:43:38", "throughput": 725.6, "total_tokens": 471712} {"current_steps": 295, "total_steps": 40000, "loss": 0.3044, "lr": 4.9993335537324495e-05, "epoch": 0.013354761311935534, "percentage": 0.74, "elapsed_time": "0:10:53", "remaining_time": "1 day, 0:25:27", "throughput": 734.41, "total_tokens": 479776} {"current_steps": 300, "total_steps": 40000, "loss": 0.2751, "lr": 4.999310693785516e-05, "epoch": 0.01358111319857851, "percentage": 0.75, "elapsed_time": "0:10:56", "remaining_time": "1 day, 0:07:57", "throughput": 743.62, "total_tokens": 488192} {"current_steps": 305, "total_steps": 40000, "loss": 0.36, "lr": 4.9992874484134653e-05, "epoch": 0.013807465085221486, "percentage": 0.76, "elapsed_time": "0:10:59", "remaining_time": "23:50:39", "throughput": 751.34, "total_tokens": 495552} {"current_steps": 310, "total_steps": 40000, "loss": 0.284, "lr": 4.999263817619882e-05, "epoch": 0.01403381697186446, "percentage": 0.78, "elapsed_time": "0:11:02", "remaining_time": "23:34:08", "throughput": 760.18, "total_tokens": 503776} {"current_steps": 315, "total_steps": 40000, "loss": 0.2809, "lr": 4.9992398014084105e-05, "epoch": 0.014260168858507435, "percentage": 0.79, "elapsed_time": "0:11:05", "remaining_time": "23:17:58", "throughput": 768.15, "total_tokens": 511424} {"current_steps": 320, "total_steps": 40000, "loss": 0.3891, "lr": 4.999215399782754e-05, "epoch": 0.014486520745150411, "percentage": 0.8, "elapsed_time": "0:11:08", "remaining_time": "23:02:20", "throughput": 775.85, "total_tokens": 518944} {"current_steps": 325, "total_steps": 40000, "loss": 0.274, "lr": 4.999190612746675e-05, "epoch": 0.014712872631793387, "percentage": 0.81, "elapsed_time": "0:11:12", "remaining_time": "22:47:17", "throughput": 784.18, "total_tokens": 526976} {"current_steps": 330, "total_steps": 40000, "loss": 0.3165, "lr": 4.999165440303998e-05, "epoch": 0.01493922451843636, "percentage": 0.83, "elapsed_time": "0:11:15", "remaining_time": "22:32:34", "throughput": 791.97, "total_tokens": 534656} {"current_steps": 335, "total_steps": 40000, "loss": 0.2743, "lr": 4.999139882458603e-05, "epoch": 0.015165576405079336, "percentage": 0.84, "elapsed_time": "0:11:18", "remaining_time": "22:18:39", "throughput": 800.19, "total_tokens": 542816} {"current_steps": 340, "total_steps": 40000, "loss": 0.2484, "lr": 4.9991139392144314e-05, "epoch": 0.015391928291722312, "percentage": 0.85, "elapsed_time": "0:11:21", "remaining_time": "22:05:00", "throughput": 808.51, "total_tokens": 551040} {"current_steps": 345, "total_steps": 40000, "loss": 0.3007, "lr": 4.999087610575485e-05, "epoch": 0.015618280178365286, "percentage": 0.86, "elapsed_time": "0:11:24", "remaining_time": "21:51:42", "throughput": 816.32, "total_tokens": 558944} {"current_steps": 350, "total_steps": 40000, "loss": 0.2921, "lr": 4.999060896545824e-05, "epoch": 0.015844632065008264, "percentage": 0.88, "elapsed_time": "0:11:27", "remaining_time": "21:38:40", "throughput": 824.21, "total_tokens": 566912} {"current_steps": 355, "total_steps": 40000, "loss": 0.2645, "lr": 4.999033797129568e-05, "epoch": 0.016070983951651237, "percentage": 0.89, "elapsed_time": "0:11:30", "remaining_time": "21:26:01", "throughput": 832.11, "total_tokens": 574944} {"current_steps": 360, "total_steps": 40000, "loss": 0.2858, "lr": 4.999006312330894e-05, "epoch": 0.01629733583829421, "percentage": 0.9, "elapsed_time": "0:11:34", "remaining_time": "21:13:51", "throughput": 840.28, "total_tokens": 583264} {"current_steps": 365, "total_steps": 40000, "loss": 0.1831, "lr": 4.998978442154043e-05, "epoch": 0.01652368772493719, "percentage": 0.91, "elapsed_time": "0:11:37", "remaining_time": "21:02:05", "throughput": 848.51, "total_tokens": 591712} {"current_steps": 370, "total_steps": 40000, "loss": 0.2181, "lr": 4.9989501866033125e-05, "epoch": 0.016750039611580163, "percentage": 0.92, "elapsed_time": "0:11:40", "remaining_time": "20:50:33", "throughput": 856.3, "total_tokens": 599872} {"current_steps": 375, "total_steps": 40000, "loss": 0.2681, "lr": 4.998921545683059e-05, "epoch": 0.016976391498223137, "percentage": 0.94, "elapsed_time": "0:11:43", "remaining_time": "20:39:24", "throughput": 864.65, "total_tokens": 608512} {"current_steps": 380, "total_steps": 40000, "loss": 0.2525, "lr": 4.9988925193976996e-05, "epoch": 0.017202743384866114, "percentage": 0.95, "elapsed_time": "0:11:46", "remaining_time": "20:28:32", "throughput": 872.17, "total_tokens": 616608} {"current_steps": 385, "total_steps": 40000, "loss": 0.2949, "lr": 4.998863107751711e-05, "epoch": 0.017429095271509088, "percentage": 0.96, "elapsed_time": "0:11:50", "remaining_time": "20:17:42", "throughput": 879.11, "total_tokens": 624224} {"current_steps": 390, "total_steps": 40000, "loss": 0.2989, "lr": 4.998833310749629e-05, "epoch": 0.017655447158152062, "percentage": 0.97, "elapsed_time": "0:11:53", "remaining_time": "20:07:30", "throughput": 887.31, "total_tokens": 632960} {"current_steps": 395, "total_steps": 40000, "loss": 0.2405, "lr": 4.998803128396047e-05, "epoch": 0.01788179904479504, "percentage": 0.99, "elapsed_time": "0:11:56", "remaining_time": "19:57:21", "throughput": 894.74, "total_tokens": 641088} {"current_steps": 400, "total_steps": 40000, "loss": 0.2352, "lr": 4.9987725606956215e-05, "epoch": 0.018108150931438013, "percentage": 1.0, "elapsed_time": "0:11:59", "remaining_time": "19:47:25", "throughput": 901.77, "total_tokens": 648960} {"current_steps": 400, "total_steps": 40000, "eval_loss": 0.2627139091491699, "epoch": 0.018108150931438013, "percentage": 1.0, "elapsed_time": "0:19:42", "remaining_time": "1 day, 8:30:34", "throughput": 548.96, "total_tokens": 648960} {"current_steps": 405, "total_steps": 40000, "loss": 0.2094, "lr": 4.998741607653066e-05, "epoch": 0.018334502818080987, "percentage": 1.01, "elapsed_time": "0:19:46", "remaining_time": "1 day, 8:12:56", "throughput": 554.26, "total_tokens": 657504} {"current_steps": 410, "total_steps": 40000, "loss": 0.2851, "lr": 4.9987102692731523e-05, "epoch": 0.018560854704723965, "percentage": 1.03, "elapsed_time": "0:19:49", "remaining_time": "1 day, 7:54:30", "throughput": 560.23, "total_tokens": 666464} {"current_steps": 415, "total_steps": 40000, "loss": 0.2283, "lr": 4.9986785455607157e-05, "epoch": 0.01878720659136694, "percentage": 1.04, "elapsed_time": "0:19:52", "remaining_time": "1 day, 7:36:17", "throughput": 565.55, "total_tokens": 674592} {"current_steps": 420, "total_steps": 40000, "loss": 0.2862, "lr": 4.9986464365206456e-05, "epoch": 0.019013558478009913, "percentage": 1.05, "elapsed_time": "0:19:55", "remaining_time": "1 day, 7:18:17", "throughput": 570.3, "total_tokens": 682016} {"current_steps": 425, "total_steps": 40000, "loss": 0.2072, "lr": 4.9986139421578956e-05, "epoch": 0.01923991036465289, "percentage": 1.06, "elapsed_time": "0:19:58", "remaining_time": "1 day, 7:00:46", "throughput": 575.23, "total_tokens": 689696} {"current_steps": 430, "total_steps": 40000, "loss": 0.2082, "lr": 4.998581062477477e-05, "epoch": 0.019466262251295864, "percentage": 1.07, "elapsed_time": "0:20:02", "remaining_time": "1 day, 6:43:52", "throughput": 580.92, "total_tokens": 698400} {"current_steps": 435, "total_steps": 40000, "loss": 0.277, "lr": 4.998547797484458e-05, "epoch": 0.019692614137938838, "percentage": 1.09, "elapsed_time": "0:20:05", "remaining_time": "1 day, 6:27:16", "throughput": 586.29, "total_tokens": 706720} {"current_steps": 440, "total_steps": 40000, "loss": 0.2225, "lr": 4.9985141471839706e-05, "epoch": 0.019918966024581816, "percentage": 1.1, "elapsed_time": "0:20:08", "remaining_time": "1 day, 6:10:59", "throughput": 591.57, "total_tokens": 714944} {"current_steps": 445, "total_steps": 40000, "loss": 0.2049, "lr": 4.998480111581203e-05, "epoch": 0.02014531791122479, "percentage": 1.11, "elapsed_time": "0:20:11", "remaining_time": "1 day, 5:55:08", "throughput": 596.85, "total_tokens": 723232} {"current_steps": 450, "total_steps": 40000, "loss": 0.2464, "lr": 4.998445690681405e-05, "epoch": 0.020371669797867767, "percentage": 1.12, "elapsed_time": "0:20:14", "remaining_time": "1 day, 5:39:43", "throughput": 602.3, "total_tokens": 731776} {"current_steps": 455, "total_steps": 40000, "loss": 0.3425, "lr": 4.9984108844898834e-05, "epoch": 0.02059802168451074, "percentage": 1.14, "elapsed_time": "0:20:18", "remaining_time": "1 day, 5:24:28", "throughput": 607.32, "total_tokens": 739776} {"current_steps": 460, "total_steps": 40000, "loss": 0.2692, "lr": 4.9983756930120076e-05, "epoch": 0.020824373571153715, "percentage": 1.15, "elapsed_time": "0:20:21", "remaining_time": "1 day, 5:09:58", "throughput": 613.0, "total_tokens": 748800} {"current_steps": 465, "total_steps": 40000, "loss": 0.2803, "lr": 4.9983401162532025e-05, "epoch": 0.021050725457796692, "percentage": 1.16, "elapsed_time": "0:20:24", "remaining_time": "1 day, 4:55:29", "throughput": 618.24, "total_tokens": 757184} {"current_steps": 470, "total_steps": 40000, "loss": 0.2333, "lr": 4.998304154218955e-05, "epoch": 0.021277077344439666, "percentage": 1.18, "elapsed_time": "0:20:27", "remaining_time": "1 day, 4:41:16", "throughput": 623.41, "total_tokens": 765504} {"current_steps": 475, "total_steps": 40000, "loss": 0.2127, "lr": 4.998267806914812e-05, "epoch": 0.02150342923108264, "percentage": 1.19, "elapsed_time": "0:20:31", "remaining_time": "1 day, 4:27:18", "throughput": 628.21, "total_tokens": 773376} {"current_steps": 480, "total_steps": 40000, "loss": 0.2443, "lr": 4.998231074346378e-05, "epoch": 0.021729781117725618, "percentage": 1.2, "elapsed_time": "0:20:34", "remaining_time": "1 day, 4:13:40", "throughput": 633.25, "total_tokens": 781600} {"current_steps": 485, "total_steps": 40000, "loss": 0.2447, "lr": 4.998193956519317e-05, "epoch": 0.02195613300436859, "percentage": 1.21, "elapsed_time": "0:20:37", "remaining_time": "1 day, 4:00:17", "throughput": 638.11, "total_tokens": 789600} {"current_steps": 490, "total_steps": 40000, "loss": 0.2555, "lr": 4.9981564534393545e-05, "epoch": 0.022182484891011565, "percentage": 1.23, "elapsed_time": "0:20:40", "remaining_time": "1 day, 3:47:29", "throughput": 643.61, "total_tokens": 798592} {"current_steps": 495, "total_steps": 40000, "loss": 0.202, "lr": 4.998118565112272e-05, "epoch": 0.022408836777654543, "percentage": 1.24, "elapsed_time": "0:20:44", "remaining_time": "1 day, 3:34:44", "throughput": 648.67, "total_tokens": 806976} {"current_steps": 500, "total_steps": 40000, "loss": 0.301, "lr": 4.998080291543914e-05, "epoch": 0.022635188664297517, "percentage": 1.25, "elapsed_time": "0:20:47", "remaining_time": "1 day, 3:22:06", "throughput": 653.13, "total_tokens": 814560} {"current_steps": 505, "total_steps": 40000, "loss": 0.2295, "lr": 4.9980416327401826e-05, "epoch": 0.02286154055094049, "percentage": 1.26, "elapsed_time": "0:20:50", "remaining_time": "1 day, 3:09:55", "throughput": 658.37, "total_tokens": 823264} {"current_steps": 510, "total_steps": 40000, "loss": 0.2703, "lr": 4.998002588707038e-05, "epoch": 0.023087892437583468, "percentage": 1.27, "elapsed_time": "0:20:53", "remaining_time": "1 day, 2:57:58", "throughput": 663.47, "total_tokens": 831808} {"current_steps": 515, "total_steps": 40000, "loss": 0.2875, "lr": 4.997963159450503e-05, "epoch": 0.023314244324226442, "percentage": 1.29, "elapsed_time": "0:20:56", "remaining_time": "1 day, 2:46:13", "throughput": 668.64, "total_tokens": 840480} {"current_steps": 520, "total_steps": 40000, "loss": 0.3891, "lr": 4.9979233449766575e-05, "epoch": 0.023540596210869416, "percentage": 1.3, "elapsed_time": "0:21:00", "remaining_time": "1 day, 2:34:26", "throughput": 673.04, "total_tokens": 848064} {"current_steps": 525, "total_steps": 40000, "loss": 0.2298, "lr": 4.997883145291641e-05, "epoch": 0.023766948097512394, "percentage": 1.31, "elapsed_time": "0:21:03", "remaining_time": "1 day, 2:23:03", "throughput": 677.88, "total_tokens": 856320} {"current_steps": 530, "total_steps": 40000, "loss": 0.23, "lr": 4.9978425604016536e-05, "epoch": 0.023993299984155367, "percentage": 1.32, "elapsed_time": "0:21:06", "remaining_time": "1 day, 2:12:00", "throughput": 682.94, "total_tokens": 864960} {"current_steps": 535, "total_steps": 40000, "loss": 0.2486, "lr": 4.9978015903129536e-05, "epoch": 0.02421965187079834, "percentage": 1.34, "elapsed_time": "0:21:09", "remaining_time": "1 day, 2:00:56", "throughput": 687.34, "total_tokens": 872672} {"current_steps": 540, "total_steps": 40000, "loss": 0.2491, "lr": 4.997760235031859e-05, "epoch": 0.02444600375744132, "percentage": 1.35, "elapsed_time": "0:21:12", "remaining_time": "1 day, 1:50:08", "throughput": 692.07, "total_tokens": 880864} {"current_steps": 545, "total_steps": 40000, "loss": 0.2823, "lr": 4.9977184945647473e-05, "epoch": 0.024672355644084293, "percentage": 1.36, "elapsed_time": "0:21:16", "remaining_time": "1 day, 1:39:36", "throughput": 696.89, "total_tokens": 889248} {"current_steps": 550, "total_steps": 40000, "loss": 0.262, "lr": 4.997676368918055e-05, "epoch": 0.02489870753072727, "percentage": 1.38, "elapsed_time": "0:21:19", "remaining_time": "1 day, 1:29:09", "throughput": 701.35, "total_tokens": 897120} {"current_steps": 555, "total_steps": 40000, "loss": 0.2074, "lr": 4.9976338580982794e-05, "epoch": 0.025125059417370244, "percentage": 1.39, "elapsed_time": "0:21:22", "remaining_time": "1 day, 1:18:49", "throughput": 705.78, "total_tokens": 904960} {"current_steps": 560, "total_steps": 40000, "loss": 0.2237, "lr": 4.9975909621119755e-05, "epoch": 0.025351411304013218, "percentage": 1.4, "elapsed_time": "0:21:25", "remaining_time": "1 day, 1:08:48", "throughput": 710.48, "total_tokens": 913248} {"current_steps": 565, "total_steps": 40000, "loss": 0.2224, "lr": 4.997547680965758e-05, "epoch": 0.025577763190656196, "percentage": 1.41, "elapsed_time": "0:21:28", "remaining_time": "1 day, 0:59:00", "throughput": 715.29, "total_tokens": 921728} {"current_steps": 570, "total_steps": 40000, "loss": 0.2338, "lr": 4.997504014666302e-05, "epoch": 0.02580411507729917, "percentage": 1.43, "elapsed_time": "0:21:31", "remaining_time": "1 day, 0:49:31", "throughput": 720.08, "total_tokens": 930304} {"current_steps": 575, "total_steps": 40000, "loss": 0.2343, "lr": 4.997459963220342e-05, "epoch": 0.026030466963942143, "percentage": 1.44, "elapsed_time": "0:21:35", "remaining_time": "1 day, 0:39:59", "throughput": 724.67, "total_tokens": 938528} {"current_steps": 580, "total_steps": 40000, "loss": 0.1884, "lr": 4.997415526634671e-05, "epoch": 0.02625681885058512, "percentage": 1.45, "elapsed_time": "0:21:38", "remaining_time": "1 day, 0:30:31", "throughput": 728.8, "total_tokens": 946112} {"current_steps": 585, "total_steps": 40000, "loss": 0.2214, "lr": 4.99737070491614e-05, "epoch": 0.026483170737228095, "percentage": 1.46, "elapsed_time": "0:21:41", "remaining_time": "1 day, 0:21:26", "throughput": 733.56, "total_tokens": 954688} {"current_steps": 590, "total_steps": 40000, "loss": 0.2693, "lr": 4.997325498071663e-05, "epoch": 0.02670952262387107, "percentage": 1.47, "elapsed_time": "0:21:44", "remaining_time": "1 day, 0:12:23", "throughput": 737.79, "total_tokens": 962528} {"current_steps": 595, "total_steps": 40000, "loss": 0.2597, "lr": 4.997279906108211e-05, "epoch": 0.026935874510514046, "percentage": 1.49, "elapsed_time": "0:21:47", "remaining_time": "1 day, 0:03:25", "throughput": 742.02, "total_tokens": 970336} {"current_steps": 600, "total_steps": 40000, "loss": 0.224, "lr": 4.9972339290328155e-05, "epoch": 0.02716222639715702, "percentage": 1.5, "elapsed_time": "0:21:50", "remaining_time": "23:54:39", "throughput": 746.28, "total_tokens": 978272} {"current_steps": 600, "total_steps": 40000, "eval_loss": 0.241190105676651, "epoch": 0.02716222639715702, "percentage": 1.5, "elapsed_time": "0:29:33", "remaining_time": "1 day, 8:20:47", "throughput": 551.66, "total_tokens": 978272} {"current_steps": 605, "total_steps": 40000, "loss": 0.2438, "lr": 4.9971875668525646e-05, "epoch": 0.027388578283799994, "percentage": 1.51, "elapsed_time": "0:29:37", "remaining_time": "1 day, 8:09:05", "throughput": 554.76, "total_tokens": 986112} {"current_steps": 610, "total_steps": 40000, "loss": 0.1812, "lr": 4.997140819574609e-05, "epoch": 0.02761493017044297, "percentage": 1.52, "elapsed_time": "0:29:40", "remaining_time": "1 day, 7:56:40", "throughput": 558.11, "total_tokens": 993952} {"current_steps": 615, "total_steps": 40000, "loss": 0.2887, "lr": 4.997093687206159e-05, "epoch": 0.027841282057085946, "percentage": 1.54, "elapsed_time": "0:29:44", "remaining_time": "1 day, 7:44:10", "throughput": 561.37, "total_tokens": 1001504} {"current_steps": 620, "total_steps": 40000, "loss": 0.2703, "lr": 4.997046169754482e-05, "epoch": 0.02806763394372892, "percentage": 1.55, "elapsed_time": "0:29:47", "remaining_time": "1 day, 7:31:58", "throughput": 565.11, "total_tokens": 1009984} {"current_steps": 625, "total_steps": 40000, "loss": 0.2293, "lr": 4.996998267226905e-05, "epoch": 0.028293985830371897, "percentage": 1.56, "elapsed_time": "0:29:50", "remaining_time": "1 day, 7:19:50", "throughput": 568.51, "total_tokens": 1017824} {"current_steps": 630, "total_steps": 40000, "loss": 0.2159, "lr": 4.996949979630817e-05, "epoch": 0.02852033771701487, "percentage": 1.57, "elapsed_time": "0:29:53", "remaining_time": "1 day, 7:08:07", "throughput": 572.3, "total_tokens": 1026496} {"current_steps": 635, "total_steps": 40000, "loss": 0.2268, "lr": 4.996901306973663e-05, "epoch": 0.028746689603657845, "percentage": 1.59, "elapsed_time": "0:29:56", "remaining_time": "1 day, 6:56:26", "throughput": 575.69, "total_tokens": 1034400} {"current_steps": 640, "total_steps": 40000, "loss": 0.2864, "lr": 4.996852249262949e-05, "epoch": 0.028973041490300822, "percentage": 1.6, "elapsed_time": "0:29:59", "remaining_time": "1 day, 6:44:56", "throughput": 579.04, "total_tokens": 1042240} {"current_steps": 645, "total_steps": 40000, "loss": 0.1731, "lr": 4.996802806506241e-05, "epoch": 0.029199393376943796, "percentage": 1.61, "elapsed_time": "0:30:03", "remaining_time": "1 day, 6:33:33", "throughput": 582.43, "total_tokens": 1050144} {"current_steps": 650, "total_steps": 40000, "loss": 0.2153, "lr": 4.996752978711164e-05, "epoch": 0.029425745263586774, "percentage": 1.62, "elapsed_time": "0:30:06", "remaining_time": "1 day, 6:22:30", "throughput": 586.07, "total_tokens": 1058624} {"current_steps": 655, "total_steps": 40000, "loss": 0.228, "lr": 4.996702765885401e-05, "epoch": 0.029652097150229748, "percentage": 1.64, "elapsed_time": "0:30:09", "remaining_time": "1 day, 6:11:33", "throughput": 589.62, "total_tokens": 1066912} {"current_steps": 660, "total_steps": 40000, "loss": 0.2661, "lr": 4.9966521680366964e-05, "epoch": 0.02987844903687272, "percentage": 1.65, "elapsed_time": "0:30:12", "remaining_time": "1 day, 6:00:43", "throughput": 593.03, "total_tokens": 1074944} {"current_steps": 665, "total_steps": 40000, "loss": 0.2313, "lr": 4.9966011851728524e-05, "epoch": 0.0301048009235157, "percentage": 1.66, "elapsed_time": "0:30:15", "remaining_time": "1 day, 5:50:03", "throughput": 596.48, "total_tokens": 1083072} {"current_steps": 670, "total_steps": 40000, "loss": 0.2107, "lr": 4.996549817301731e-05, "epoch": 0.030331152810158673, "percentage": 1.68, "elapsed_time": "0:30:18", "remaining_time": "1 day, 5:39:33", "throughput": 599.77, "total_tokens": 1090944} {"current_steps": 675, "total_steps": 40000, "loss": 0.1851, "lr": 4.9964980644312544e-05, "epoch": 0.030557504696801647, "percentage": 1.69, "elapsed_time": "0:30:22", "remaining_time": "1 day, 5:29:25", "throughput": 603.72, "total_tokens": 1100160} {"current_steps": 680, "total_steps": 40000, "loss": 0.2187, "lr": 4.996445926569403e-05, "epoch": 0.030783856583444624, "percentage": 1.7, "elapsed_time": "0:30:25", "remaining_time": "1 day, 5:19:14", "throughput": 607.09, "total_tokens": 1108224} {"current_steps": 685, "total_steps": 40000, "loss": 0.2801, "lr": 4.996393403724218e-05, "epoch": 0.031010208470087598, "percentage": 1.71, "elapsed_time": "0:30:28", "remaining_time": "1 day, 5:09:10", "throughput": 610.22, "total_tokens": 1115840} {"current_steps": 690, "total_steps": 40000, "loss": 0.2187, "lr": 4.9963404959037985e-05, "epoch": 0.031236560356730572, "percentage": 1.73, "elapsed_time": "0:30:31", "remaining_time": "1 day, 4:59:19", "throughput": 613.64, "total_tokens": 1124064} {"current_steps": 695, "total_steps": 40000, "loss": 0.2618, "lr": 4.996287203116303e-05, "epoch": 0.031462912243373546, "percentage": 1.74, "elapsed_time": "0:30:34", "remaining_time": "1 day, 4:49:31", "throughput": 616.84, "total_tokens": 1131840} {"current_steps": 700, "total_steps": 40000, "loss": 0.2223, "lr": 4.996233525369951e-05, "epoch": 0.03168926413001653, "percentage": 1.75, "elapsed_time": "0:30:38", "remaining_time": "1 day, 4:39:55", "throughput": 620.26, "total_tokens": 1140096} {"current_steps": 705, "total_steps": 40000, "loss": 0.2403, "lr": 4.99617946267302e-05, "epoch": 0.0319156160166595, "percentage": 1.76, "elapsed_time": "0:30:41", "remaining_time": "1 day, 4:30:31", "throughput": 623.82, "total_tokens": 1148672} {"current_steps": 710, "total_steps": 40000, "loss": 0.1993, "lr": 4.996125015033846e-05, "epoch": 0.032141967903302475, "percentage": 1.77, "elapsed_time": "0:30:44", "remaining_time": "1 day, 4:21:04", "throughput": 626.85, "total_tokens": 1156160} {"current_steps": 715, "total_steps": 40000, "loss": 0.2424, "lr": 4.996070182460827e-05, "epoch": 0.03236831978994545, "percentage": 1.79, "elapsed_time": "0:30:47", "remaining_time": "1 day, 4:11:47", "throughput": 629.89, "total_tokens": 1163712} {"current_steps": 720, "total_steps": 40000, "loss": 0.2844, "lr": 4.996014964962418e-05, "epoch": 0.03259467167658842, "percentage": 1.8, "elapsed_time": "0:30:50", "remaining_time": "1 day, 4:02:44", "throughput": 633.33, "total_tokens": 1172096} {"current_steps": 725, "total_steps": 40000, "loss": 0.2138, "lr": 4.9959593625471344e-05, "epoch": 0.0328210235632314, "percentage": 1.81, "elapsed_time": "0:30:53", "remaining_time": "1 day, 3:53:49", "throughput": 636.69, "total_tokens": 1180352} {"current_steps": 730, "total_steps": 40000, "loss": 0.2479, "lr": 4.995903375223552e-05, "epoch": 0.03304737544987438, "percentage": 1.82, "elapsed_time": "0:30:57", "remaining_time": "1 day, 3:44:59", "throughput": 640.0, "total_tokens": 1188512} {"current_steps": 735, "total_steps": 40000, "loss": 0.236, "lr": 4.995847003000302e-05, "epoch": 0.03327372733651735, "percentage": 1.84, "elapsed_time": "0:31:00", "remaining_time": "1 day, 3:36:22", "throughput": 643.5, "total_tokens": 1197120} {"current_steps": 740, "total_steps": 40000, "loss": 0.2108, "lr": 4.9957902458860804e-05, "epoch": 0.033500079223160326, "percentage": 1.85, "elapsed_time": "0:31:03", "remaining_time": "1 day, 3:27:44", "throughput": 646.69, "total_tokens": 1205088} {"current_steps": 745, "total_steps": 40000, "loss": 0.2928, "lr": 4.995733103889639e-05, "epoch": 0.0337264311098033, "percentage": 1.86, "elapsed_time": "0:31:06", "remaining_time": "1 day, 3:19:15", "throughput": 649.79, "total_tokens": 1212928} {"current_steps": 750, "total_steps": 40000, "loss": 0.2838, "lr": 4.99567557701979e-05, "epoch": 0.033952782996446274, "percentage": 1.88, "elapsed_time": "0:31:09", "remaining_time": "1 day, 3:10:56", "throughput": 653.19, "total_tokens": 1221376} {"current_steps": 755, "total_steps": 40000, "loss": 0.2348, "lr": 4.995617665285403e-05, "epoch": 0.03417913488308925, "percentage": 1.89, "elapsed_time": "0:31:13", "remaining_time": "1 day, 3:02:43", "throughput": 656.61, "total_tokens": 1229888} {"current_steps": 760, "total_steps": 40000, "loss": 0.1972, "lr": 4.99555936869541e-05, "epoch": 0.03440548676973223, "percentage": 1.9, "elapsed_time": "0:31:16", "remaining_time": "1 day, 2:54:32", "throughput": 659.66, "total_tokens": 1237664} {"current_steps": 765, "total_steps": 40000, "loss": 0.2011, "lr": 4.995500687258803e-05, "epoch": 0.0346318386563752, "percentage": 1.91, "elapsed_time": "0:31:19", "remaining_time": "1 day, 2:46:27", "throughput": 662.9, "total_tokens": 1245824} {"current_steps": 770, "total_steps": 40000, "loss": 0.2659, "lr": 4.995441620984628e-05, "epoch": 0.034858190543018176, "percentage": 1.93, "elapsed_time": "0:31:22", "remaining_time": "1 day, 2:38:29", "throughput": 665.98, "total_tokens": 1253696} {"current_steps": 775, "total_steps": 40000, "loss": 0.1811, "lr": 4.995382169881996e-05, "epoch": 0.03508454242966115, "percentage": 1.94, "elapsed_time": "0:31:25", "remaining_time": "1 day, 2:30:40", "throughput": 669.26, "total_tokens": 1262016} {"current_steps": 780, "total_steps": 40000, "loss": 0.2871, "lr": 4.9953223339600755e-05, "epoch": 0.035310894316304124, "percentage": 1.95, "elapsed_time": "0:31:28", "remaining_time": "1 day, 2:23:02", "throughput": 672.63, "total_tokens": 1270592} {"current_steps": 785, "total_steps": 40000, "loss": 0.2291, "lr": 4.995262113228091e-05, "epoch": 0.0355372462029471, "percentage": 1.96, "elapsed_time": "0:31:32", "remaining_time": "1 day, 2:15:23", "throughput": 675.85, "total_tokens": 1278816} {"current_steps": 790, "total_steps": 40000, "loss": 0.2437, "lr": 4.995201507695332e-05, "epoch": 0.03576359808959008, "percentage": 1.98, "elapsed_time": "0:31:35", "remaining_time": "1 day, 2:07:56", "throughput": 679.24, "total_tokens": 1287456} {"current_steps": 795, "total_steps": 40000, "loss": 0.2542, "lr": 4.995140517371144e-05, "epoch": 0.03598994997623305, "percentage": 1.99, "elapsed_time": "0:31:38", "remaining_time": "1 day, 2:00:32", "throughput": 682.46, "total_tokens": 1295776} {"current_steps": 800, "total_steps": 40000, "loss": 0.2823, "lr": 4.995079142264932e-05, "epoch": 0.03621630186287603, "percentage": 2.0, "elapsed_time": "0:31:41", "remaining_time": "1 day, 1:53:15", "throughput": 685.9, "total_tokens": 1304544} {"current_steps": 800, "total_steps": 40000, "eval_loss": 0.2285599410533905, "epoch": 0.03621630186287603, "percentage": 2.0, "elapsed_time": "0:39:24", "remaining_time": "1 day, 8:11:02", "throughput": 551.71, "total_tokens": 1304544} {"current_steps": 805, "total_steps": 40000, "loss": 0.2075, "lr": 4.995017382386162e-05, "epoch": 0.036442653749519, "percentage": 2.01, "elapsed_time": "0:39:28", "remaining_time": "1 day, 8:01:57", "throughput": 554.25, "total_tokens": 1312704} {"current_steps": 810, "total_steps": 40000, "loss": 0.2817, "lr": 4.994955237744356e-05, "epoch": 0.036669005636161975, "percentage": 2.02, "elapsed_time": "0:39:31", "remaining_time": "1 day, 7:52:23", "throughput": 556.87, "total_tokens": 1320672} {"current_steps": 815, "total_steps": 40000, "loss": 0.222, "lr": 4.994892708349101e-05, "epoch": 0.036895357522804956, "percentage": 2.04, "elapsed_time": "0:39:34", "remaining_time": "1 day, 7:42:57", "throughput": 559.58, "total_tokens": 1328864} {"current_steps": 820, "total_steps": 40000, "loss": 0.2259, "lr": 4.994829794210035e-05, "epoch": 0.03712170940944793, "percentage": 2.05, "elapsed_time": "0:39:37", "remaining_time": "1 day, 7:33:39", "throughput": 562.32, "total_tokens": 1337152} {"current_steps": 825, "total_steps": 40000, "loss": 0.1932, "lr": 4.994766495336864e-05, "epoch": 0.037348061296090904, "percentage": 2.06, "elapsed_time": "0:39:41", "remaining_time": "1 day, 7:24:24", "throughput": 564.9, "total_tokens": 1345056} {"current_steps": 830, "total_steps": 40000, "loss": 0.2293, "lr": 4.994702811739348e-05, "epoch": 0.03757441318273388, "percentage": 2.08, "elapsed_time": "0:39:44", "remaining_time": "1 day, 7:15:21", "throughput": 567.68, "total_tokens": 1353504} {"current_steps": 835, "total_steps": 40000, "loss": 0.2256, "lr": 4.994638743427308e-05, "epoch": 0.03780076506937685, "percentage": 2.09, "elapsed_time": "0:39:47", "remaining_time": "1 day, 7:06:21", "throughput": 570.27, "total_tokens": 1361504} {"current_steps": 840, "total_steps": 40000, "loss": 0.2443, "lr": 4.994574290410624e-05, "epoch": 0.038027116956019825, "percentage": 2.1, "elapsed_time": "0:39:50", "remaining_time": "1 day, 6:57:40", "throughput": 573.25, "total_tokens": 1370560} {"current_steps": 845, "total_steps": 40000, "loss": 0.237, "lr": 4.9945094526992364e-05, "epoch": 0.038253468842662806, "percentage": 2.11, "elapsed_time": "0:39:54", "remaining_time": "1 day, 6:49:02", "throughput": 576.26, "total_tokens": 1379712} {"current_steps": 850, "total_steps": 40000, "loss": 0.272, "lr": 4.994444230303142e-05, "epoch": 0.03847982072930578, "percentage": 2.12, "elapsed_time": "0:39:57", "remaining_time": "1 day, 6:40:19", "throughput": 578.77, "total_tokens": 1387520} {"current_steps": 855, "total_steps": 40000, "loss": 0.1884, "lr": 4.994378623232402e-05, "epoch": 0.038706172615948754, "percentage": 2.14, "elapsed_time": "0:40:00", "remaining_time": "1 day, 6:31:42", "throughput": 581.22, "total_tokens": 1395200} {"current_steps": 860, "total_steps": 40000, "loss": 0.2206, "lr": 4.99431263149713e-05, "epoch": 0.03893252450259173, "percentage": 2.15, "elapsed_time": "0:40:03", "remaining_time": "1 day, 6:23:11", "throughput": 583.75, "total_tokens": 1403104} {"current_steps": 865, "total_steps": 40000, "loss": 0.1519, "lr": 4.9942462551075056e-05, "epoch": 0.0391588763892347, "percentage": 2.16, "elapsed_time": "0:40:06", "remaining_time": "1 day, 6:14:44", "throughput": 586.13, "total_tokens": 1410624} {"current_steps": 870, "total_steps": 40000, "loss": 0.1567, "lr": 4.994179494073764e-05, "epoch": 0.039385228275877676, "percentage": 2.17, "elapsed_time": "0:40:09", "remaining_time": "1 day, 6:06:27", "throughput": 588.85, "total_tokens": 1419040} {"current_steps": 875, "total_steps": 40000, "loss": 0.2307, "lr": 4.9941123484062e-05, "epoch": 0.03961158016252066, "percentage": 2.19, "elapsed_time": "0:40:13", "remaining_time": "1 day, 5:58:17", "throughput": 591.49, "total_tokens": 1427296} {"current_steps": 880, "total_steps": 40000, "loss": 0.2807, "lr": 4.99404481811517e-05, "epoch": 0.03983793204916363, "percentage": 2.2, "elapsed_time": "0:40:16", "remaining_time": "1 day, 5:50:17", "throughput": 594.29, "total_tokens": 1436000} {"current_steps": 885, "total_steps": 40000, "loss": 0.2602, "lr": 4.9939769032110864e-05, "epoch": 0.040064283935806605, "percentage": 2.21, "elapsed_time": "0:40:19", "remaining_time": "1 day, 5:42:14", "throughput": 596.72, "total_tokens": 1443744} {"current_steps": 890, "total_steps": 40000, "loss": 0.1901, "lr": 4.993908603704423e-05, "epoch": 0.04029063582244958, "percentage": 2.23, "elapsed_time": "0:40:22", "remaining_time": "1 day, 5:34:24", "throughput": 599.4, "total_tokens": 1452192} {"current_steps": 895, "total_steps": 40000, "loss": 0.2576, "lr": 4.9938399196057126e-05, "epoch": 0.04051698770909255, "percentage": 2.24, "elapsed_time": "0:40:26", "remaining_time": "1 day, 5:26:38", "throughput": 602.05, "total_tokens": 1460576} {"current_steps": 900, "total_steps": 40000, "loss": 0.2498, "lr": 4.993770850925547e-05, "epoch": 0.040743339595735534, "percentage": 2.25, "elapsed_time": "0:40:29", "remaining_time": "1 day, 5:18:53", "throughput": 604.52, "total_tokens": 1468480} {"current_steps": 905, "total_steps": 40000, "loss": 0.2537, "lr": 4.993701397674577e-05, "epoch": 0.04096969148237851, "percentage": 2.26, "elapsed_time": "0:40:32", "remaining_time": "1 day, 5:11:14", "throughput": 607.05, "total_tokens": 1476544} {"current_steps": 910, "total_steps": 40000, "loss": 0.1758, "lr": 4.993631559863515e-05, "epoch": 0.04119604336902148, "percentage": 2.27, "elapsed_time": "0:40:35", "remaining_time": "1 day, 5:03:46", "throughput": 609.88, "total_tokens": 1485472} {"current_steps": 915, "total_steps": 40000, "loss": 0.2285, "lr": 4.9935613375031283e-05, "epoch": 0.041422395255664456, "percentage": 2.29, "elapsed_time": "0:40:38", "remaining_time": "1 day, 4:56:17", "throughput": 612.47, "total_tokens": 1493728} {"current_steps": 920, "total_steps": 40000, "loss": 0.1813, "lr": 4.993490730604248e-05, "epoch": 0.04164874714230743, "percentage": 2.3, "elapsed_time": "0:40:42", "remaining_time": "1 day, 4:48:52", "throughput": 614.99, "total_tokens": 1501824} {"current_steps": 925, "total_steps": 40000, "loss": 0.222, "lr": 4.993419739177761e-05, "epoch": 0.041875099028950404, "percentage": 2.31, "elapsed_time": "0:40:45", "remaining_time": "1 day, 4:41:34", "throughput": 617.62, "total_tokens": 1510208} {"current_steps": 930, "total_steps": 40000, "loss": 0.2482, "lr": 4.9933483632346164e-05, "epoch": 0.042101450915593384, "percentage": 2.33, "elapsed_time": "0:40:48", "remaining_time": "1 day, 4:34:17", "throughput": 620.04, "total_tokens": 1518080} {"current_steps": 935, "total_steps": 40000, "loss": 0.1742, "lr": 4.993276602785821e-05, "epoch": 0.04232780280223636, "percentage": 2.34, "elapsed_time": "0:40:51", "remaining_time": "1 day, 4:27:09", "throughput": 622.6, "total_tokens": 1526368} {"current_steps": 940, "total_steps": 40000, "loss": 0.2021, "lr": 4.993204457842441e-05, "epoch": 0.04255415468887933, "percentage": 2.35, "elapsed_time": "0:40:54", "remaining_time": "1 day, 4:19:59", "throughput": 624.99, "total_tokens": 1534144} {"current_steps": 945, "total_steps": 40000, "loss": 0.2601, "lr": 4.993131928415602e-05, "epoch": 0.042780506575522306, "percentage": 2.36, "elapsed_time": "0:40:57", "remaining_time": "1 day, 4:12:57", "throughput": 627.45, "total_tokens": 1542176} {"current_steps": 950, "total_steps": 40000, "loss": 0.2562, "lr": 4.993059014516489e-05, "epoch": 0.04300685846216528, "percentage": 2.38, "elapsed_time": "0:41:01", "remaining_time": "1 day, 4:06:01", "throughput": 629.98, "total_tokens": 1550400} {"current_steps": 955, "total_steps": 40000, "loss": 0.2196, "lr": 4.9929857161563464e-05, "epoch": 0.043233210348808254, "percentage": 2.39, "elapsed_time": "0:41:04", "remaining_time": "1 day, 3:59:05", "throughput": 632.43, "total_tokens": 1558400} {"current_steps": 960, "total_steps": 40000, "loss": 0.2053, "lr": 4.992912033346477e-05, "epoch": 0.043459562235451235, "percentage": 2.4, "elapsed_time": "0:41:07", "remaining_time": "1 day, 3:52:17", "throughput": 634.95, "total_tokens": 1566624} {"current_steps": 965, "total_steps": 40000, "loss": 0.1982, "lr": 4.992837966098245e-05, "epoch": 0.04368591412209421, "percentage": 2.41, "elapsed_time": "0:41:10", "remaining_time": "1 day, 3:45:34", "throughput": 637.43, "total_tokens": 1574784} {"current_steps": 970, "total_steps": 40000, "loss": 0.2309, "lr": 4.992763514423071e-05, "epoch": 0.04391226600873718, "percentage": 2.43, "elapsed_time": "0:41:13", "remaining_time": "1 day, 3:38:57", "throughput": 640.17, "total_tokens": 1583648} {"current_steps": 975, "total_steps": 40000, "loss": 0.2351, "lr": 4.992688678332437e-05, "epoch": 0.04413861789538016, "percentage": 2.44, "elapsed_time": "0:41:16", "remaining_time": "1 day, 3:32:20", "throughput": 642.6, "total_tokens": 1591680} {"current_steps": 980, "total_steps": 40000, "loss": 0.2496, "lr": 4.992613457837884e-05, "epoch": 0.04436496978202313, "percentage": 2.45, "elapsed_time": "0:41:20", "remaining_time": "1 day, 3:25:49", "throughput": 645.13, "total_tokens": 1600000} {"current_steps": 985, "total_steps": 40000, "loss": 0.189, "lr": 4.992537852951011e-05, "epoch": 0.04459132166866611, "percentage": 2.46, "elapsed_time": "0:41:23", "remaining_time": "1 day, 3:19:22", "throughput": 647.68, "total_tokens": 1608416} {"current_steps": 990, "total_steps": 40000, "loss": 0.2244, "lr": 4.9924618636834785e-05, "epoch": 0.044817673555309086, "percentage": 2.48, "elapsed_time": "0:41:26", "remaining_time": "1 day, 3:12:58", "throughput": 650.05, "total_tokens": 1616352} {"current_steps": 995, "total_steps": 40000, "loss": 0.1957, "lr": 4.9923854900470046e-05, "epoch": 0.04504402544195206, "percentage": 2.49, "elapsed_time": "0:41:29", "remaining_time": "1 day, 3:06:39", "throughput": 652.49, "total_tokens": 1624512} {"current_steps": 1000, "total_steps": 40000, "loss": 0.2385, "lr": 4.992308732053367e-05, "epoch": 0.045270377328595034, "percentage": 2.5, "elapsed_time": "0:41:32", "remaining_time": "1 day, 3:00:20", "throughput": 654.81, "total_tokens": 1632320} {"current_steps": 1000, "total_steps": 40000, "eval_loss": 0.2194906771183014, "epoch": 0.045270377328595034, "percentage": 2.5, "elapsed_time": "0:49:15", "remaining_time": "1 day, 8:01:03", "throughput": 552.3, "total_tokens": 1632320} {"current_steps": 1005, "total_steps": 40000, "loss": 0.2481, "lr": 4.992231589714402e-05, "epoch": 0.04549672921523801, "percentage": 2.51, "elapsed_time": "0:49:19", "remaining_time": "1 day, 7:53:45", "throughput": 554.37, "total_tokens": 1640576} {"current_steps": 1010, "total_steps": 40000, "loss": 0.2535, "lr": 4.992154063042007e-05, "epoch": 0.04572308110188098, "percentage": 2.53, "elapsed_time": "0:49:22", "remaining_time": "1 day, 7:46:00", "throughput": 556.36, "total_tokens": 1648160} {"current_steps": 1015, "total_steps": 40000, "loss": 0.2288, "lr": 4.992076152048136e-05, "epoch": 0.04594943298852396, "percentage": 2.54, "elapsed_time": "0:49:25", "remaining_time": "1 day, 7:38:26", "throughput": 558.5, "total_tokens": 1656288} {"current_steps": 1020, "total_steps": 40000, "loss": 0.2031, "lr": 4.991997856744807e-05, "epoch": 0.046175784875166936, "percentage": 2.55, "elapsed_time": "0:49:28", "remaining_time": "1 day, 7:30:56", "throughput": 560.7, "total_tokens": 1664640} {"current_steps": 1025, "total_steps": 40000, "loss": 0.231, "lr": 4.9919191771440905e-05, "epoch": 0.04640213676180991, "percentage": 2.56, "elapsed_time": "0:49:32", "remaining_time": "1 day, 7:23:29", "throughput": 562.88, "total_tokens": 1672896} {"current_steps": 1030, "total_steps": 40000, "loss": 0.2521, "lr": 4.991840113258122e-05, "epoch": 0.046628488648452884, "percentage": 2.57, "elapsed_time": "0:49:35", "remaining_time": "1 day, 7:16:11", "throughput": 565.31, "total_tokens": 1681984} {"current_steps": 1035, "total_steps": 40000, "loss": 0.2258, "lr": 4.9917606650990933e-05, "epoch": 0.04685484053509586, "percentage": 2.59, "elapsed_time": "0:49:38", "remaining_time": "1 day, 7:08:49", "throughput": 567.27, "total_tokens": 1689568} {"current_steps": 1040, "total_steps": 40000, "loss": 0.1872, "lr": 4.9916808326792566e-05, "epoch": 0.04708119242173883, "percentage": 2.6, "elapsed_time": "0:49:41", "remaining_time": "1 day, 7:01:35", "throughput": 569.49, "total_tokens": 1697984} {"current_steps": 1045, "total_steps": 40000, "loss": 0.2187, "lr": 4.9916006160109235e-05, "epoch": 0.04730754430838181, "percentage": 2.61, "elapsed_time": "0:49:44", "remaining_time": "1 day, 6:54:23", "throughput": 571.47, "total_tokens": 1705696} {"current_steps": 1050, "total_steps": 40000, "loss": 0.2388, "lr": 4.991520015106464e-05, "epoch": 0.04753389619502479, "percentage": 2.62, "elapsed_time": "0:49:47", "remaining_time": "1 day, 6:47:15", "throughput": 573.57, "total_tokens": 1713760} {"current_steps": 1055, "total_steps": 40000, "loss": 0.2871, "lr": 4.991439029978308e-05, "epoch": 0.04776024808166776, "percentage": 2.64, "elapsed_time": "0:49:51", "remaining_time": "1 day, 6:40:13", "throughput": 575.73, "total_tokens": 1722048} {"current_steps": 1060, "total_steps": 40000, "loss": 0.2432, "lr": 4.9913576606389434e-05, "epoch": 0.047986599968310735, "percentage": 2.65, "elapsed_time": "0:49:54", "remaining_time": "1 day, 6:33:15", "throughput": 577.85, "total_tokens": 1730208} {"current_steps": 1065, "total_steps": 40000, "loss": 0.2074, "lr": 4.991275907100919e-05, "epoch": 0.04821295185495371, "percentage": 2.66, "elapsed_time": "0:49:57", "remaining_time": "1 day, 6:26:17", "throughput": 579.83, "total_tokens": 1737920} {"current_steps": 1070, "total_steps": 40000, "loss": 0.1709, "lr": 4.9911937693768434e-05, "epoch": 0.04843930374159668, "percentage": 2.67, "elapsed_time": "0:50:00", "remaining_time": "1 day, 6:19:32", "throughput": 582.13, "total_tokens": 1746752} {"current_steps": 1075, "total_steps": 40000, "loss": 0.2073, "lr": 4.991111247479382e-05, "epoch": 0.048665655628239664, "percentage": 2.69, "elapsed_time": "0:50:03", "remaining_time": "1 day, 6:12:46", "throughput": 584.3, "total_tokens": 1755136} {"current_steps": 1080, "total_steps": 40000, "loss": 0.2355, "lr": 4.9910283414212605e-05, "epoch": 0.04889200751488264, "percentage": 2.7, "elapsed_time": "0:50:06", "remaining_time": "1 day, 6:05:58", "throughput": 586.2, "total_tokens": 1762624} {"current_steps": 1085, "total_steps": 40000, "loss": 0.2103, "lr": 4.990945051215265e-05, "epoch": 0.04911835940152561, "percentage": 2.71, "elapsed_time": "0:50:09", "remaining_time": "1 day, 5:59:17", "throughput": 588.25, "total_tokens": 1770624} {"current_steps": 1090, "total_steps": 40000, "loss": 0.1821, "lr": 4.99086137687424e-05, "epoch": 0.049344711288168586, "percentage": 2.73, "elapsed_time": "0:50:13", "remaining_time": "1 day, 5:52:38", "throughput": 590.21, "total_tokens": 1778368} {"current_steps": 1095, "total_steps": 40000, "loss": 0.1922, "lr": 4.9907773184110874e-05, "epoch": 0.04957106317481156, "percentage": 2.74, "elapsed_time": "0:50:16", "remaining_time": "1 day, 5:46:07", "throughput": 592.28, "total_tokens": 1786496} {"current_steps": 1100, "total_steps": 40000, "loss": 0.1898, "lr": 4.9906928758387715e-05, "epoch": 0.04979741506145454, "percentage": 2.75, "elapsed_time": "0:50:19", "remaining_time": "1 day, 5:39:37", "throughput": 594.24, "total_tokens": 1794272} {"current_steps": 1105, "total_steps": 40000, "loss": 0.1931, "lr": 4.9906080491703146e-05, "epoch": 0.050023766948097514, "percentage": 2.76, "elapsed_time": "0:50:22", "remaining_time": "1 day, 5:33:13", "throughput": 596.49, "total_tokens": 1802976} {"current_steps": 1110, "total_steps": 40000, "loss": 0.197, "lr": 4.990522838418797e-05, "epoch": 0.05025011883474049, "percentage": 2.77, "elapsed_time": "0:50:26", "remaining_time": "1 day, 5:27:02", "throughput": 598.88, "total_tokens": 1812288} {"current_steps": 1115, "total_steps": 40000, "loss": 0.1992, "lr": 4.9904372435973604e-05, "epoch": 0.05047647072138346, "percentage": 2.79, "elapsed_time": "0:50:29", "remaining_time": "1 day, 5:20:47", "throughput": 601.09, "total_tokens": 1820928} {"current_steps": 1120, "total_steps": 40000, "loss": 0.2402, "lr": 4.990351264719203e-05, "epoch": 0.050702822608026436, "percentage": 2.8, "elapsed_time": "0:50:32", "remaining_time": "1 day, 5:14:36", "throughput": 603.3, "total_tokens": 1829600} {"current_steps": 1125, "total_steps": 40000, "loss": 0.2336, "lr": 4.990264901797586e-05, "epoch": 0.05092917449466941, "percentage": 2.81, "elapsed_time": "0:50:35", "remaining_time": "1 day, 5:08:27", "throughput": 605.47, "total_tokens": 1838144} {"current_steps": 1130, "total_steps": 40000, "loss": 0.1939, "lr": 4.990178154845826e-05, "epoch": 0.05115552638131239, "percentage": 2.83, "elapsed_time": "0:50:39", "remaining_time": "1 day, 5:02:22", "throughput": 607.68, "total_tokens": 1846848} {"current_steps": 1135, "total_steps": 40000, "loss": 0.1908, "lr": 4.9900910238773014e-05, "epoch": 0.051381878267955365, "percentage": 2.84, "elapsed_time": "0:50:42", "remaining_time": "1 day, 4:56:18", "throughput": 609.62, "total_tokens": 1854688} {"current_steps": 1140, "total_steps": 40000, "loss": 0.2075, "lr": 4.990003508905448e-05, "epoch": 0.05160823015459834, "percentage": 2.85, "elapsed_time": "0:50:45", "remaining_time": "1 day, 4:50:17", "throughput": 611.77, "total_tokens": 1863200} {"current_steps": 1145, "total_steps": 40000, "loss": 0.2364, "lr": 4.989915609943763e-05, "epoch": 0.05183458204124131, "percentage": 2.86, "elapsed_time": "0:50:48", "remaining_time": "1 day, 4:44:20", "throughput": 613.88, "total_tokens": 1871616} {"current_steps": 1150, "total_steps": 40000, "loss": 0.1802, "lr": 4.9898273270058e-05, "epoch": 0.05206093392788429, "percentage": 2.88, "elapsed_time": "0:50:51", "remaining_time": "1 day, 4:38:21", "throughput": 615.74, "total_tokens": 1879168} {"current_steps": 1155, "total_steps": 40000, "loss": 0.3025, "lr": 4.989738660105174e-05, "epoch": 0.05228728581452726, "percentage": 2.89, "elapsed_time": "0:50:55", "remaining_time": "1 day, 4:32:28", "throughput": 617.79, "total_tokens": 1887392} {"current_steps": 1160, "total_steps": 40000, "loss": 0.2481, "lr": 4.989649609255559e-05, "epoch": 0.05251363770117024, "percentage": 2.9, "elapsed_time": "0:50:58", "remaining_time": "1 day, 4:26:40", "throughput": 619.88, "total_tokens": 1895776} {"current_steps": 1165, "total_steps": 40000, "loss": 0.2547, "lr": 4.989560174470687e-05, "epoch": 0.052739989587813216, "percentage": 2.91, "elapsed_time": "0:51:01", "remaining_time": "1 day, 4:20:51", "throughput": 621.76, "total_tokens": 1903456} {"current_steps": 1170, "total_steps": 40000, "loss": 0.2011, "lr": 4.989470355764351e-05, "epoch": 0.05296634147445619, "percentage": 2.93, "elapsed_time": "0:51:04", "remaining_time": "1 day, 4:15:04", "throughput": 623.62, "total_tokens": 1911072} {"current_steps": 1175, "total_steps": 40000, "loss": 0.2099, "lr": 4.9893801531504e-05, "epoch": 0.053192693361099164, "percentage": 2.94, "elapsed_time": "0:51:07", "remaining_time": "1 day, 4:09:23", "throughput": 625.69, "total_tokens": 1919392} {"current_steps": 1180, "total_steps": 40000, "loss": 0.1997, "lr": 4.9892895666427475e-05, "epoch": 0.05341904524774214, "percentage": 2.95, "elapsed_time": "0:51:10", "remaining_time": "1 day, 4:03:45", "throughput": 627.7, "total_tokens": 1927552} {"current_steps": 1185, "total_steps": 40000, "loss": 0.2214, "lr": 4.9891985962553606e-05, "epoch": 0.05364539713438512, "percentage": 2.96, "elapsed_time": "0:51:13", "remaining_time": "1 day, 3:58:08", "throughput": 629.65, "total_tokens": 1935520} {"current_steps": 1190, "total_steps": 40000, "loss": 0.2241, "lr": 4.989107242002269e-05, "epoch": 0.05387174902102809, "percentage": 2.97, "elapsed_time": "0:51:17", "remaining_time": "1 day, 3:52:37", "throughput": 631.72, "total_tokens": 1943936} {"current_steps": 1195, "total_steps": 40000, "loss": 0.2092, "lr": 4.989015503897561e-05, "epoch": 0.054098100907671066, "percentage": 2.99, "elapsed_time": "0:51:20", "remaining_time": "1 day, 3:47:07", "throughput": 633.64, "total_tokens": 1951840} {"current_steps": 1200, "total_steps": 40000, "loss": 0.2736, "lr": 4.988923381955383e-05, "epoch": 0.05432445279431404, "percentage": 3.0, "elapsed_time": "0:51:23", "remaining_time": "1 day, 3:41:45", "throughput": 635.81, "total_tokens": 1960640} {"current_steps": 1200, "total_steps": 40000, "eval_loss": 0.21299625933170319, "epoch": 0.05432445279431404, "percentage": 3.0, "elapsed_time": "0:59:06", "remaining_time": "1 day, 7:51:04", "throughput": 552.87, "total_tokens": 1960640} {"current_steps": 1205, "total_steps": 40000, "loss": 0.2228, "lr": 4.988830876189942e-05, "epoch": 0.054550804680957014, "percentage": 3.01, "elapsed_time": "0:59:10", "remaining_time": "1 day, 7:44:55", "throughput": 554.43, "total_tokens": 1968288} {"current_steps": 1210, "total_steps": 40000, "loss": 0.2345, "lr": 4.988737986615503e-05, "epoch": 0.05477715656759999, "percentage": 3.02, "elapsed_time": "0:59:13", "remaining_time": "1 day, 7:38:30", "throughput": 556.2, "total_tokens": 1976352} {"current_steps": 1215, "total_steps": 40000, "loss": 0.2152, "lr": 4.988644713246391e-05, "epoch": 0.05500350845424297, "percentage": 3.04, "elapsed_time": "0:59:16", "remaining_time": "1 day, 7:32:07", "throughput": 557.97, "total_tokens": 1984384} {"current_steps": 1220, "total_steps": 40000, "loss": 0.2553, "lr": 4.988551056096991e-05, "epoch": 0.05522986034088594, "percentage": 3.05, "elapsed_time": "0:59:19", "remaining_time": "1 day, 7:25:47", "throughput": 559.75, "total_tokens": 1992480} {"current_steps": 1225, "total_steps": 40000, "loss": 0.1712, "lr": 4.988457015181743e-05, "epoch": 0.05545621222752892, "percentage": 3.06, "elapsed_time": "0:59:22", "remaining_time": "1 day, 7:19:37", "throughput": 561.7, "total_tokens": 2001280} {"current_steps": 1230, "total_steps": 40000, "loss": 0.2333, "lr": 4.988362590515153e-05, "epoch": 0.05568256411417189, "percentage": 3.08, "elapsed_time": "0:59:26", "remaining_time": "1 day, 7:13:26", "throughput": 563.6, "total_tokens": 2009888} {"current_steps": 1235, "total_steps": 40000, "loss": 0.2753, "lr": 4.9882677821117805e-05, "epoch": 0.055908916000814865, "percentage": 3.09, "elapsed_time": "0:59:29", "remaining_time": "1 day, 7:07:16", "throughput": 565.42, "total_tokens": 2018176} {"current_steps": 1240, "total_steps": 40000, "loss": 0.2692, "lr": 4.988172589986246e-05, "epoch": 0.05613526788745784, "percentage": 3.1, "elapsed_time": "0:59:32", "remaining_time": "1 day, 7:01:07", "throughput": 567.1, "total_tokens": 2025920} {"current_steps": 1245, "total_steps": 40000, "loss": 0.1749, "lr": 4.9880770141532304e-05, "epoch": 0.05636161977410082, "percentage": 3.11, "elapsed_time": "0:59:35", "remaining_time": "1 day, 6:55:04", "throughput": 568.96, "total_tokens": 2034400} {"current_steps": 1250, "total_steps": 40000, "loss": 0.1962, "lr": 4.987981054627472e-05, "epoch": 0.056587971660743794, "percentage": 3.12, "elapsed_time": "0:59:39", "remaining_time": "1 day, 6:49:11", "throughput": 570.71, "total_tokens": 2042624} {"current_steps": 1255, "total_steps": 40000, "loss": 0.217, "lr": 4.987884711423769e-05, "epoch": 0.05681432354738677, "percentage": 3.14, "elapsed_time": "0:59:42", "remaining_time": "1 day, 6:43:13", "throughput": 572.51, "total_tokens": 2050880} {"current_steps": 1260, "total_steps": 40000, "loss": 0.2, "lr": 4.9877879845569784e-05, "epoch": 0.05704067543402974, "percentage": 3.15, "elapsed_time": "0:59:45", "remaining_time": "1 day, 6:37:21", "throughput": 574.41, "total_tokens": 2059584} {"current_steps": 1265, "total_steps": 40000, "loss": 0.1781, "lr": 4.9876908740420175e-05, "epoch": 0.057267027320672716, "percentage": 3.16, "elapsed_time": "0:59:48", "remaining_time": "1 day, 6:31:28", "throughput": 576.08, "total_tokens": 2067392} {"current_steps": 1270, "total_steps": 40000, "loss": 0.2329, "lr": 4.987593379893861e-05, "epoch": 0.05749337920731569, "percentage": 3.17, "elapsed_time": "0:59:51", "remaining_time": "1 day, 6:25:36", "throughput": 577.77, "total_tokens": 2075264} {"current_steps": 1275, "total_steps": 40000, "loss": 0.2331, "lr": 4.987495502127545e-05, "epoch": 0.05771973109395867, "percentage": 3.19, "elapsed_time": "0:59:55", "remaining_time": "1 day, 6:19:50", "throughput": 579.6, "total_tokens": 2083680} {"current_steps": 1280, "total_steps": 40000, "loss": 0.2228, "lr": 4.987397240758162e-05, "epoch": 0.057946082980601644, "percentage": 3.2, "elapsed_time": "0:59:58", "remaining_time": "1 day, 6:14:08", "throughput": 581.46, "total_tokens": 2092256} {"current_steps": 1285, "total_steps": 40000, "loss": 0.2705, "lr": 4.9872985958008664e-05, "epoch": 0.05817243486724462, "percentage": 3.21, "elapsed_time": "1:00:01", "remaining_time": "1 day, 6:08:32", "throughput": 583.36, "total_tokens": 2101056} {"current_steps": 1290, "total_steps": 40000, "loss": 0.159, "lr": 4.987199567270871e-05, "epoch": 0.05839878675388759, "percentage": 3.23, "elapsed_time": "1:00:04", "remaining_time": "1 day, 6:02:52", "throughput": 585.09, "total_tokens": 2109152} {"current_steps": 1295, "total_steps": 40000, "loss": 0.2134, "lr": 4.9871001551834444e-05, "epoch": 0.058625138640530566, "percentage": 3.24, "elapsed_time": "1:00:07", "remaining_time": "1 day, 5:57:14", "throughput": 586.81, "total_tokens": 2117184} {"current_steps": 1300, "total_steps": 40000, "loss": 0.175, "lr": 4.98700035955392e-05, "epoch": 0.05885149052717355, "percentage": 3.25, "elapsed_time": "1:00:11", "remaining_time": "1 day, 5:51:40", "throughput": 588.59, "total_tokens": 2125472} {"current_steps": 1305, "total_steps": 40000, "loss": 0.2233, "lr": 4.986900180397686e-05, "epoch": 0.05907784241381652, "percentage": 3.26, "elapsed_time": "1:00:14", "remaining_time": "1 day, 5:46:05", "throughput": 590.21, "total_tokens": 2133120} {"current_steps": 1310, "total_steps": 40000, "loss": 0.1626, "lr": 4.9867996177301926e-05, "epoch": 0.059304194300459495, "percentage": 3.28, "elapsed_time": "1:00:17", "remaining_time": "1 day, 5:40:35", "throughput": 591.94, "total_tokens": 2141248} {"current_steps": 1315, "total_steps": 40000, "loss": 0.2019, "lr": 4.9866986715669464e-05, "epoch": 0.05953054618710247, "percentage": 3.29, "elapsed_time": "1:00:20", "remaining_time": "1 day, 5:35:07", "throughput": 593.62, "total_tokens": 2149184} {"current_steps": 1320, "total_steps": 40000, "loss": 0.2064, "lr": 4.9865973419235155e-05, "epoch": 0.05975689807374544, "percentage": 3.3, "elapsed_time": "1:00:23", "remaining_time": "1 day, 5:29:44", "throughput": 595.41, "total_tokens": 2157568} {"current_steps": 1325, "total_steps": 40000, "loss": 0.2314, "lr": 4.986495628815526e-05, "epoch": 0.05998324996038842, "percentage": 3.31, "elapsed_time": "1:00:26", "remaining_time": "1 day, 5:24:20", "throughput": 597.04, "total_tokens": 2165344} {"current_steps": 1330, "total_steps": 40000, "loss": 0.2251, "lr": 4.986393532258663e-05, "epoch": 0.0602096018470314, "percentage": 3.33, "elapsed_time": "1:00:29", "remaining_time": "1 day, 5:19:00", "throughput": 598.71, "total_tokens": 2173248} {"current_steps": 1335, "total_steps": 40000, "loss": 0.1619, "lr": 4.986291052268671e-05, "epoch": 0.06043595373367437, "percentage": 3.34, "elapsed_time": "1:00:33", "remaining_time": "1 day, 5:13:41", "throughput": 600.38, "total_tokens": 2181184} {"current_steps": 1340, "total_steps": 40000, "loss": 0.2545, "lr": 4.986188188861355e-05, "epoch": 0.060662305620317346, "percentage": 3.35, "elapsed_time": "1:00:36", "remaining_time": "1 day, 5:08:26", "throughput": 602.1, "total_tokens": 2189344} {"current_steps": 1345, "total_steps": 40000, "loss": 0.1954, "lr": 4.9860849420525766e-05, "epoch": 0.06088865750696032, "percentage": 3.36, "elapsed_time": "1:00:39", "remaining_time": "1 day, 5:03:11", "throughput": 603.73, "total_tokens": 2197120} {"current_steps": 1350, "total_steps": 40000, "loss": 0.249, "lr": 4.9859813118582575e-05, "epoch": 0.061115009393603294, "percentage": 3.38, "elapsed_time": "1:00:42", "remaining_time": "1 day, 4:58:01", "throughput": 605.45, "total_tokens": 2205312} {"current_steps": 1355, "total_steps": 40000, "loss": 0.2129, "lr": 4.98587729829438e-05, "epoch": 0.06134136128024627, "percentage": 3.39, "elapsed_time": "1:00:45", "remaining_time": "1 day, 4:52:50", "throughput": 607.09, "total_tokens": 2213152} {"current_steps": 1360, "total_steps": 40000, "loss": 0.1853, "lr": 4.985772901376983e-05, "epoch": 0.06156771316688925, "percentage": 3.4, "elapsed_time": "1:00:48", "remaining_time": "1 day, 4:47:49", "throughput": 608.89, "total_tokens": 2221728} {"current_steps": 1365, "total_steps": 40000, "loss": 0.2237, "lr": 4.9856681211221666e-05, "epoch": 0.06179406505353222, "percentage": 3.41, "elapsed_time": "1:00:51", "remaining_time": "1 day, 4:42:46", "throughput": 610.56, "total_tokens": 2229760} {"current_steps": 1370, "total_steps": 40000, "loss": 0.2083, "lr": 4.985562957546089e-05, "epoch": 0.062020416940175196, "percentage": 3.43, "elapsed_time": "1:00:55", "remaining_time": "1 day, 4:37:44", "throughput": 612.21, "total_tokens": 2237696} {"current_steps": 1375, "total_steps": 40000, "loss": 0.261, "lr": 4.9854574106649686e-05, "epoch": 0.06224676882681817, "percentage": 3.44, "elapsed_time": "1:00:58", "remaining_time": "1 day, 4:32:45", "throughput": 613.86, "total_tokens": 2245696} {"current_steps": 1380, "total_steps": 40000, "loss": 0.2047, "lr": 4.985351480495081e-05, "epoch": 0.062473120713461144, "percentage": 3.45, "elapsed_time": "1:01:01", "remaining_time": "1 day, 4:27:49", "throughput": 615.58, "total_tokens": 2253952} {"current_steps": 1385, "total_steps": 40000, "loss": 0.1889, "lr": 4.985245167052762e-05, "epoch": 0.06269947260010413, "percentage": 3.46, "elapsed_time": "1:01:04", "remaining_time": "1 day, 4:22:53", "throughput": 617.2, "total_tokens": 2261824} {"current_steps": 1390, "total_steps": 40000, "loss": 0.1832, "lr": 4.9851384703544066e-05, "epoch": 0.06292582448674709, "percentage": 3.48, "elapsed_time": "1:01:07", "remaining_time": "1 day, 4:17:58", "throughput": 618.86, "total_tokens": 2269824} {"current_steps": 1395, "total_steps": 40000, "loss": 0.2501, "lr": 4.985031390416469e-05, "epoch": 0.06315217637339007, "percentage": 3.49, "elapsed_time": "1:01:10", "remaining_time": "1 day, 4:13:05", "throughput": 620.34, "total_tokens": 2277152} {"current_steps": 1400, "total_steps": 40000, "loss": 0.1934, "lr": 4.984923927255461e-05, "epoch": 0.06337852826003305, "percentage": 3.5, "elapsed_time": "1:01:14", "remaining_time": "1 day, 4:08:20", "throughput": 622.09, "total_tokens": 2285632} {"current_steps": 1400, "total_steps": 40000, "eval_loss": 0.20683465898036957, "epoch": 0.06337852826003305, "percentage": 3.5, "elapsed_time": "1:08:56", "remaining_time": "1 day, 7:40:52", "throughput": 552.53, "total_tokens": 2285632} {"current_steps": 1405, "total_steps": 40000, "loss": 0.193, "lr": 4.984816080887958e-05, "epoch": 0.06360488014667602, "percentage": 3.51, "elapsed_time": "1:09:00", "remaining_time": "1 day, 7:35:42", "throughput": 554.25, "total_tokens": 2294976} {"current_steps": 1410, "total_steps": 40000, "loss": 0.2223, "lr": 4.9847078513305875e-05, "epoch": 0.063831232033319, "percentage": 3.52, "elapsed_time": "1:09:03", "remaining_time": "1 day, 7:30:13", "throughput": 555.9, "total_tokens": 2303616} {"current_steps": 1415, "total_steps": 40000, "loss": 0.2148, "lr": 4.984599238600043e-05, "epoch": 0.06405758391996197, "percentage": 3.54, "elapsed_time": "1:09:07", "remaining_time": "1 day, 7:24:50", "throughput": 557.56, "total_tokens": 2312384} {"current_steps": 1420, "total_steps": 40000, "loss": 0.1817, "lr": 4.9844902427130716e-05, "epoch": 0.06428393580660495, "percentage": 3.55, "elapsed_time": "1:09:10", "remaining_time": "1 day, 7:19:24", "throughput": 559.06, "total_tokens": 2320384} {"current_steps": 1425, "total_steps": 40000, "loss": 0.1969, "lr": 4.984380863686482e-05, "epoch": 0.06451028769324792, "percentage": 3.56, "elapsed_time": "1:09:13", "remaining_time": "1 day, 7:14:01", "throughput": 560.67, "total_tokens": 2328832} {"current_steps": 1430, "total_steps": 40000, "loss": 0.1591, "lr": 4.984271101537143e-05, "epoch": 0.0647366395798909, "percentage": 3.57, "elapsed_time": "1:09:16", "remaining_time": "1 day, 7:08:40", "throughput": 562.22, "total_tokens": 2337088} {"current_steps": 1435, "total_steps": 40000, "loss": 0.2294, "lr": 4.9841609562819816e-05, "epoch": 0.06496299146653388, "percentage": 3.59, "elapsed_time": "1:09:20", "remaining_time": "1 day, 7:03:19", "throughput": 563.7, "total_tokens": 2345024} {"current_steps": 1440, "total_steps": 40000, "loss": 0.2104, "lr": 4.984050427937983e-05, "epoch": 0.06518934335317685, "percentage": 3.6, "elapsed_time": "1:09:23", "remaining_time": "1 day, 6:58:06", "throughput": 565.45, "total_tokens": 2354208} {"current_steps": 1445, "total_steps": 40000, "loss": 0.2228, "lr": 4.983939516522191e-05, "epoch": 0.06541569523981983, "percentage": 3.61, "elapsed_time": "1:09:26", "remaining_time": "1 day, 6:52:52", "throughput": 567.09, "total_tokens": 2362848} {"current_steps": 1450, "total_steps": 40000, "loss": 0.2093, "lr": 4.983828222051711e-05, "epoch": 0.0656420471264628, "percentage": 3.62, "elapsed_time": "1:09:29", "remaining_time": "1 day, 6:47:38", "throughput": 568.55, "total_tokens": 2370720} {"current_steps": 1455, "total_steps": 40000, "loss": 0.2834, "lr": 4.983716544543705e-05, "epoch": 0.06586839901310577, "percentage": 3.64, "elapsed_time": "1:09:32", "remaining_time": "1 day, 6:42:24", "throughput": 569.98, "total_tokens": 2378432} {"current_steps": 1460, "total_steps": 40000, "loss": 0.2521, "lr": 4.983604484015395e-05, "epoch": 0.06609475089974876, "percentage": 3.65, "elapsed_time": "1:09:36", "remaining_time": "1 day, 6:37:20", "throughput": 571.67, "total_tokens": 2387424} {"current_steps": 1465, "total_steps": 40000, "loss": 0.188, "lr": 4.983492040484064e-05, "epoch": 0.06632110278639172, "percentage": 3.66, "elapsed_time": "1:09:39", "remaining_time": "1 day, 6:32:12", "throughput": 573.21, "total_tokens": 2395648} {"current_steps": 1470, "total_steps": 40000, "loss": 0.1996, "lr": 4.98337921396705e-05, "epoch": 0.0665474546730347, "percentage": 3.67, "elapsed_time": "1:09:42", "remaining_time": "1 day, 6:27:05", "throughput": 574.6, "total_tokens": 2403232} {"current_steps": 1475, "total_steps": 40000, "loss": 0.2143, "lr": 4.983266004481753e-05, "epoch": 0.06677380655967767, "percentage": 3.69, "elapsed_time": "1:09:45", "remaining_time": "1 day, 6:22:03", "throughput": 576.16, "total_tokens": 2411616} {"current_steps": 1480, "total_steps": 40000, "loss": 0.1931, "lr": 4.9831524120456316e-05, "epoch": 0.06700015844632065, "percentage": 3.7, "elapsed_time": "1:09:48", "remaining_time": "1 day, 6:17:01", "throughput": 577.61, "total_tokens": 2419488} {"current_steps": 1485, "total_steps": 40000, "loss": 0.2409, "lr": 4.9830384366762026e-05, "epoch": 0.06722651033296363, "percentage": 3.71, "elapsed_time": "1:09:52", "remaining_time": "1 day, 6:12:04", "throughput": 579.16, "total_tokens": 2427840} {"current_steps": 1490, "total_steps": 40000, "loss": 0.2031, "lr": 4.9829240783910436e-05, "epoch": 0.0674528622196066, "percentage": 3.72, "elapsed_time": "1:09:55", "remaining_time": "1 day, 6:07:07", "throughput": 580.69, "total_tokens": 2436128} {"current_steps": 1495, "total_steps": 40000, "loss": 0.1948, "lr": 4.982809337207789e-05, "epoch": 0.06767921410624958, "percentage": 3.74, "elapsed_time": "1:09:58", "remaining_time": "1 day, 6:02:17", "throughput": 582.4, "total_tokens": 2445248} {"current_steps": 1500, "total_steps": 40000, "loss": 0.2131, "lr": 4.9826942131441337e-05, "epoch": 0.06790556599289255, "percentage": 3.75, "elapsed_time": "1:10:01", "remaining_time": "1 day, 5:57:24", "throughput": 583.9, "total_tokens": 2453408} {"current_steps": 1505, "total_steps": 40000, "loss": 0.1963, "lr": 4.9825787062178315e-05, "epoch": 0.06813191787953553, "percentage": 3.76, "elapsed_time": "1:10:04", "remaining_time": "1 day, 5:52:32", "throughput": 585.39, "total_tokens": 2461472} {"current_steps": 1510, "total_steps": 40000, "loss": 0.1702, "lr": 4.9824628164466945e-05, "epoch": 0.0683582697661785, "percentage": 3.77, "elapsed_time": "1:10:08", "remaining_time": "1 day, 5:47:46", "throughput": 587.11, "total_tokens": 2470688} {"current_steps": 1515, "total_steps": 40000, "loss": 0.1964, "lr": 4.982346543848595e-05, "epoch": 0.06858462165282148, "percentage": 3.79, "elapsed_time": "1:10:11", "remaining_time": "1 day, 5:43:00", "throughput": 588.61, "total_tokens": 2478880} {"current_steps": 1520, "total_steps": 40000, "loss": 0.28, "lr": 4.9822298884414626e-05, "epoch": 0.06881097353946446, "percentage": 3.8, "elapsed_time": "1:10:14", "remaining_time": "1 day, 5:38:14", "throughput": 590.1, "total_tokens": 2487008} {"current_steps": 1525, "total_steps": 40000, "loss": 0.1511, "lr": 4.982112850243288e-05, "epoch": 0.06903732542610742, "percentage": 3.81, "elapsed_time": "1:10:17", "remaining_time": "1 day, 5:33:30", "throughput": 591.48, "total_tokens": 2494688} {"current_steps": 1530, "total_steps": 40000, "loss": 0.2165, "lr": 4.98199542927212e-05, "epoch": 0.0692636773127504, "percentage": 3.82, "elapsed_time": "1:10:20", "remaining_time": "1 day, 5:28:48", "throughput": 592.98, "total_tokens": 2502912} {"current_steps": 1535, "total_steps": 40000, "loss": 0.1859, "lr": 4.981877625546066e-05, "epoch": 0.06949002919939337, "percentage": 3.84, "elapsed_time": "1:10:24", "remaining_time": "1 day, 5:24:08", "throughput": 594.48, "total_tokens": 2511104} {"current_steps": 1540, "total_steps": 40000, "loss": 0.1301, "lr": 4.981759439083293e-05, "epoch": 0.06971638108603635, "percentage": 3.85, "elapsed_time": "1:10:27", "remaining_time": "1 day, 5:19:30", "throughput": 595.98, "total_tokens": 2519328} {"current_steps": 1545, "total_steps": 40000, "loss": 0.1908, "lr": 4.981640869902027e-05, "epoch": 0.06994273297267933, "percentage": 3.86, "elapsed_time": "1:10:30", "remaining_time": "1 day, 5:14:54", "throughput": 597.41, "total_tokens": 2527296} {"current_steps": 1550, "total_steps": 40000, "loss": 0.1759, "lr": 4.9815219180205517e-05, "epoch": 0.0701690848593223, "percentage": 3.88, "elapsed_time": "1:10:33", "remaining_time": "1 day, 5:10:19", "throughput": 598.9, "total_tokens": 2535456} {"current_steps": 1555, "total_steps": 40000, "loss": 0.2207, "lr": 4.9814025834572126e-05, "epoch": 0.07039543674596528, "percentage": 3.89, "elapsed_time": "1:10:36", "remaining_time": "1 day, 5:05:49", "throughput": 600.48, "total_tokens": 2544128} {"current_steps": 1560, "total_steps": 40000, "loss": 0.1947, "lr": 4.981282866230411e-05, "epoch": 0.07062178863260825, "percentage": 3.9, "elapsed_time": "1:10:40", "remaining_time": "1 day, 5:01:18", "throughput": 601.98, "total_tokens": 2552416} {"current_steps": 1565, "total_steps": 40000, "loss": 0.1911, "lr": 4.981162766358611e-05, "epoch": 0.07084814051925123, "percentage": 3.91, "elapsed_time": "1:10:43", "remaining_time": "1 day, 4:56:50", "throughput": 603.48, "total_tokens": 2560704} {"current_steps": 1570, "total_steps": 40000, "loss": 0.1644, "lr": 4.9810422838603316e-05, "epoch": 0.0710744924058942, "percentage": 3.92, "elapsed_time": "1:10:46", "remaining_time": "1 day, 4:52:22", "throughput": 604.97, "total_tokens": 2568960} {"current_steps": 1575, "total_steps": 40000, "loss": 0.239, "lr": 4.9809214187541533e-05, "epoch": 0.07130084429253718, "percentage": 3.94, "elapsed_time": "1:10:49", "remaining_time": "1 day, 4:47:56", "throughput": 606.43, "total_tokens": 2577088} {"current_steps": 1580, "total_steps": 40000, "loss": 0.1938, "lr": 4.980800171058715e-05, "epoch": 0.07152719617918016, "percentage": 3.95, "elapsed_time": "1:10:52", "remaining_time": "1 day, 4:43:31", "throughput": 607.81, "total_tokens": 2584864} {"current_steps": 1585, "total_steps": 40000, "loss": 0.2684, "lr": 4.980678540792715e-05, "epoch": 0.07175354806582313, "percentage": 3.96, "elapsed_time": "1:10:55", "remaining_time": "1 day, 4:39:07", "throughput": 609.25, "total_tokens": 2592896} {"current_steps": 1590, "total_steps": 40000, "loss": 0.1535, "lr": 4.980556527974909e-05, "epoch": 0.0719798999524661, "percentage": 3.98, "elapsed_time": "1:10:59", "remaining_time": "1 day, 4:34:51", "throughput": 610.81, "total_tokens": 2601600} {"current_steps": 1595, "total_steps": 40000, "loss": 0.2019, "lr": 4.980434132624114e-05, "epoch": 0.07220625183910907, "percentage": 3.99, "elapsed_time": "1:11:02", "remaining_time": "1 day, 4:30:36", "throughput": 612.43, "total_tokens": 2610528} {"current_steps": 1600, "total_steps": 40000, "loss": 0.1414, "lr": 4.980311354759205e-05, "epoch": 0.07243260372575205, "percentage": 4.0, "elapsed_time": "1:11:05", "remaining_time": "1 day, 4:26:17", "throughput": 613.84, "total_tokens": 2618496} {"current_steps": 1600, "total_steps": 40000, "eval_loss": 0.20075473189353943, "epoch": 0.07243260372575205, "percentage": 4.0, "elapsed_time": "1:18:48", "remaining_time": "1 day, 7:31:22", "throughput": 553.78, "total_tokens": 2618496} {"current_steps": 1605, "total_steps": 40000, "loss": 0.2071, "lr": 4.980188194399116e-05, "epoch": 0.07265895561239503, "percentage": 4.01, "elapsed_time": "1:18:52", "remaining_time": "1 day, 7:26:46", "throughput": 555.07, "total_tokens": 2626752} {"current_steps": 1610, "total_steps": 40000, "loss": 0.1727, "lr": 4.9800646515628384e-05, "epoch": 0.072885307499038, "percentage": 4.03, "elapsed_time": "1:18:55", "remaining_time": "1 day, 7:21:56", "throughput": 556.4, "total_tokens": 2634816} {"current_steps": 1615, "total_steps": 40000, "loss": 0.191, "lr": 4.979940726269426e-05, "epoch": 0.07311165938568098, "percentage": 4.04, "elapsed_time": "1:18:58", "remaining_time": "1 day, 7:17:05", "throughput": 557.72, "total_tokens": 2642784} {"current_steps": 1620, "total_steps": 40000, "loss": 0.1846, "lr": 4.979816418537988e-05, "epoch": 0.07333801127232395, "percentage": 4.05, "elapsed_time": "1:19:01", "remaining_time": "1 day, 7:12:19", "throughput": 559.12, "total_tokens": 2651232} {"current_steps": 1625, "total_steps": 40000, "loss": 0.1793, "lr": 4.979691728387696e-05, "epoch": 0.07356436315896693, "percentage": 4.06, "elapsed_time": "1:19:04", "remaining_time": "1 day, 7:07:33", "throughput": 560.47, "total_tokens": 2659392} {"current_steps": 1630, "total_steps": 40000, "loss": 0.1913, "lr": 4.979566655837776e-05, "epoch": 0.07379071504560991, "percentage": 4.08, "elapsed_time": "1:19:08", "remaining_time": "1 day, 7:02:53", "throughput": 561.93, "total_tokens": 2668192} {"current_steps": 1635, "total_steps": 40000, "loss": 0.2184, "lr": 4.9794412009075184e-05, "epoch": 0.07401706693225288, "percentage": 4.09, "elapsed_time": "1:19:11", "remaining_time": "1 day, 6:58:11", "throughput": 563.25, "total_tokens": 2676256} {"current_steps": 1640, "total_steps": 40000, "loss": 0.1859, "lr": 4.979315363616269e-05, "epoch": 0.07424341881889586, "percentage": 4.1, "elapsed_time": "1:19:14", "remaining_time": "1 day, 6:53:30", "throughput": 564.54, "total_tokens": 2684160} {"current_steps": 1645, "total_steps": 40000, "loss": 0.1955, "lr": 4.979189143983434e-05, "epoch": 0.07446977070553883, "percentage": 4.11, "elapsed_time": "1:19:17", "remaining_time": "1 day, 6:48:53", "throughput": 565.94, "total_tokens": 2692608} {"current_steps": 1650, "total_steps": 40000, "loss": 0.2007, "lr": 4.979062542028478e-05, "epoch": 0.07469612259218181, "percentage": 4.12, "elapsed_time": "1:19:20", "remaining_time": "1 day, 6:44:15", "throughput": 567.2, "total_tokens": 2700416} {"current_steps": 1655, "total_steps": 40000, "loss": 0.2069, "lr": 4.978935557770923e-05, "epoch": 0.07492247447882477, "percentage": 4.14, "elapsed_time": "1:19:24", "remaining_time": "1 day, 6:39:40", "throughput": 568.58, "total_tokens": 2708768} {"current_steps": 1660, "total_steps": 40000, "loss": 0.1977, "lr": 4.978808191230353e-05, "epoch": 0.07514882636546776, "percentage": 4.15, "elapsed_time": "1:19:27", "remaining_time": "1 day, 6:35:05", "throughput": 569.86, "total_tokens": 2716640} {"current_steps": 1665, "total_steps": 40000, "loss": 0.2055, "lr": 4.9786804424264085e-05, "epoch": 0.07537517825211074, "percentage": 4.16, "elapsed_time": "1:19:30", "remaining_time": "1 day, 6:30:34", "throughput": 571.19, "total_tokens": 2724832} {"current_steps": 1670, "total_steps": 40000, "loss": 0.1587, "lr": 4.978552311378792e-05, "epoch": 0.0756015301387537, "percentage": 4.17, "elapsed_time": "1:19:33", "remaining_time": "1 day, 6:26:03", "throughput": 572.5, "total_tokens": 2732896} {"current_steps": 1675, "total_steps": 40000, "loss": 0.2039, "lr": 4.978423798107261e-05, "epoch": 0.07582788202539668, "percentage": 4.19, "elapsed_time": "1:19:36", "remaining_time": "1 day, 6:21:34", "throughput": 573.84, "total_tokens": 2741088} {"current_steps": 1680, "total_steps": 40000, "loss": 0.2185, "lr": 4.978294902631635e-05, "epoch": 0.07605423391203965, "percentage": 4.2, "elapsed_time": "1:19:39", "remaining_time": "1 day, 6:17:08", "throughput": 575.16, "total_tokens": 2749216} {"current_steps": 1685, "total_steps": 40000, "loss": 0.1414, "lr": 4.9781656249717914e-05, "epoch": 0.07628058579868263, "percentage": 4.21, "elapsed_time": "1:19:43", "remaining_time": "1 day, 6:12:43", "throughput": 576.51, "total_tokens": 2757536} {"current_steps": 1690, "total_steps": 40000, "loss": 0.2169, "lr": 4.9780359651476645e-05, "epoch": 0.07650693768532561, "percentage": 4.23, "elapsed_time": "1:19:46", "remaining_time": "1 day, 6:08:19", "throughput": 577.86, "total_tokens": 2765824} {"current_steps": 1695, "total_steps": 40000, "loss": 0.1915, "lr": 4.977905923179251e-05, "epoch": 0.07673328957196858, "percentage": 4.24, "elapsed_time": "1:19:49", "remaining_time": "1 day, 6:03:56", "throughput": 579.12, "total_tokens": 2773664} {"current_steps": 1700, "total_steps": 40000, "loss": 0.229, "lr": 4.977775499086606e-05, "epoch": 0.07695964145861156, "percentage": 4.25, "elapsed_time": "1:19:52", "remaining_time": "1 day, 5:59:37", "throughput": 580.53, "total_tokens": 2782304} {"current_steps": 1705, "total_steps": 40000, "loss": 0.2058, "lr": 4.97764469288984e-05, "epoch": 0.07718599334525453, "percentage": 4.26, "elapsed_time": "1:19:55", "remaining_time": "1 day, 5:55:17", "throughput": 581.8, "total_tokens": 2790272} {"current_steps": 1710, "total_steps": 40000, "loss": 0.2265, "lr": 4.977513504609127e-05, "epoch": 0.07741234523189751, "percentage": 4.28, "elapsed_time": "1:19:59", "remaining_time": "1 day, 5:51:00", "throughput": 583.21, "total_tokens": 2798880} {"current_steps": 1715, "total_steps": 40000, "loss": 0.2382, "lr": 4.9773819342646965e-05, "epoch": 0.07763869711854049, "percentage": 4.29, "elapsed_time": "1:20:02", "remaining_time": "1 day, 5:46:43", "throughput": 584.47, "total_tokens": 2806784} {"current_steps": 1720, "total_steps": 40000, "loss": 0.205, "lr": 4.97724998187684e-05, "epoch": 0.07786504900518346, "percentage": 4.3, "elapsed_time": "1:20:05", "remaining_time": "1 day, 5:42:31", "throughput": 585.9, "total_tokens": 2815552} {"current_steps": 1725, "total_steps": 40000, "loss": 0.1972, "lr": 4.9771176474659045e-05, "epoch": 0.07809140089182644, "percentage": 4.31, "elapsed_time": "1:20:08", "remaining_time": "1 day, 5:38:17", "throughput": 587.13, "total_tokens": 2823328} {"current_steps": 1730, "total_steps": 40000, "loss": 0.1713, "lr": 4.976984931052299e-05, "epoch": 0.0783177527784694, "percentage": 4.32, "elapsed_time": "1:20:11", "remaining_time": "1 day, 5:34:06", "throughput": 588.49, "total_tokens": 2831744} {"current_steps": 1735, "total_steps": 40000, "loss": 0.2082, "lr": 4.976851832656489e-05, "epoch": 0.07854410466511239, "percentage": 4.34, "elapsed_time": "1:20:14", "remaining_time": "1 day, 5:29:53", "throughput": 589.78, "total_tokens": 2839776} {"current_steps": 1740, "total_steps": 40000, "loss": 0.1472, "lr": 4.9767183522990004e-05, "epoch": 0.07877045655175535, "percentage": 4.35, "elapsed_time": "1:20:18", "remaining_time": "1 day, 5:25:44", "throughput": 591.03, "total_tokens": 2847712} {"current_steps": 1745, "total_steps": 40000, "loss": 0.2581, "lr": 4.9765844900004176e-05, "epoch": 0.07899680843839833, "percentage": 4.36, "elapsed_time": "1:20:21", "remaining_time": "1 day, 5:21:36", "throughput": 592.32, "total_tokens": 2855744} {"current_steps": 1750, "total_steps": 40000, "loss": 0.1599, "lr": 4.9764502457813834e-05, "epoch": 0.07922316032504131, "percentage": 4.38, "elapsed_time": "1:20:24", "remaining_time": "1 day, 5:17:27", "throughput": 593.52, "total_tokens": 2863392} {"current_steps": 1755, "total_steps": 40000, "loss": 0.1791, "lr": 4.9763156196626005e-05, "epoch": 0.07944951221168428, "percentage": 4.39, "elapsed_time": "1:20:27", "remaining_time": "1 day, 5:13:21", "throughput": 594.75, "total_tokens": 2871168} {"current_steps": 1760, "total_steps": 40000, "loss": 0.2263, "lr": 4.97618061166483e-05, "epoch": 0.07967586409832726, "percentage": 4.4, "elapsed_time": "1:20:30", "remaining_time": "1 day, 5:09:18", "throughput": 596.07, "total_tokens": 2879456} {"current_steps": 1765, "total_steps": 40000, "loss": 0.3452, "lr": 4.9760452218088915e-05, "epoch": 0.07990221598497023, "percentage": 4.41, "elapsed_time": "1:20:33", "remaining_time": "1 day, 5:05:14", "throughput": 597.25, "total_tokens": 2886976} {"current_steps": 1770, "total_steps": 40000, "loss": 0.2043, "lr": 4.975909450115663e-05, "epoch": 0.08012856787161321, "percentage": 4.42, "elapsed_time": "1:20:36", "remaining_time": "1 day, 5:01:11", "throughput": 598.47, "total_tokens": 2894752} {"current_steps": 1775, "total_steps": 40000, "loss": 0.1288, "lr": 4.975773296606084e-05, "epoch": 0.08035491975825619, "percentage": 4.44, "elapsed_time": "1:20:40", "remaining_time": "1 day, 4:57:15", "throughput": 599.88, "total_tokens": 2903552} {"current_steps": 1780, "total_steps": 40000, "loss": 0.241, "lr": 4.97563676130115e-05, "epoch": 0.08058127164489916, "percentage": 4.45, "elapsed_time": "1:20:43", "remaining_time": "1 day, 4:53:19", "throughput": 601.31, "total_tokens": 2912448} {"current_steps": 1785, "total_steps": 40000, "loss": 0.213, "lr": 4.9754998442219166e-05, "epoch": 0.08080762353154214, "percentage": 4.46, "elapsed_time": "1:20:46", "remaining_time": "1 day, 4:49:20", "throughput": 602.45, "total_tokens": 2919840} {"current_steps": 1790, "total_steps": 40000, "loss": 0.1776, "lr": 4.9753625453894984e-05, "epoch": 0.0810339754181851, "percentage": 4.47, "elapsed_time": "1:20:49", "remaining_time": "1 day, 4:45:25", "throughput": 603.67, "total_tokens": 2927680} {"current_steps": 1795, "total_steps": 40000, "loss": 0.1876, "lr": 4.975224864825068e-05, "epoch": 0.08126032730482809, "percentage": 4.49, "elapsed_time": "1:20:52", "remaining_time": "1 day, 4:41:30", "throughput": 604.96, "total_tokens": 2935840} {"current_steps": 1800, "total_steps": 40000, "loss": 0.1758, "lr": 4.9750868025498576e-05, "epoch": 0.08148667919147107, "percentage": 4.5, "elapsed_time": "1:20:56", "remaining_time": "1 day, 4:37:37", "throughput": 606.25, "total_tokens": 2944032} {"current_steps": 1800, "total_steps": 40000, "eval_loss": 0.1969570815563202, "epoch": 0.08148667919147107, "percentage": 4.5, "elapsed_time": "1:28:38", "remaining_time": "1 day, 7:21:13", "throughput": 553.53, "total_tokens": 2944032} {"current_steps": 1805, "total_steps": 40000, "loss": 0.1954, "lr": 4.974948358585158e-05, "epoch": 0.08171303107811403, "percentage": 4.51, "elapsed_time": "1:28:42", "remaining_time": "1 day, 7:17:15", "throughput": 554.7, "total_tokens": 2952576} {"current_steps": 1810, "total_steps": 40000, "loss": 0.2387, "lr": 4.9748095329523205e-05, "epoch": 0.08193938296475702, "percentage": 4.52, "elapsed_time": "1:28:46", "remaining_time": "1 day, 7:12:55", "throughput": 555.9, "total_tokens": 2960736} {"current_steps": 1815, "total_steps": 40000, "loss": 0.1686, "lr": 4.974670325672752e-05, "epoch": 0.08216573485139998, "percentage": 4.54, "elapsed_time": "1:28:49", "remaining_time": "1 day, 7:08:37", "throughput": 557.03, "total_tokens": 2968480} {"current_steps": 1820, "total_steps": 40000, "loss": 0.2222, "lr": 4.974530736767921e-05, "epoch": 0.08239208673804296, "percentage": 4.55, "elapsed_time": "1:28:52", "remaining_time": "1 day, 7:04:21", "throughput": 558.26, "total_tokens": 2976832} {"current_steps": 1825, "total_steps": 40000, "loss": 0.2021, "lr": 4.9743907662593524e-05, "epoch": 0.08261843862468593, "percentage": 4.56, "elapsed_time": "1:28:55", "remaining_time": "1 day, 7:00:05", "throughput": 559.43, "total_tokens": 2984832} {"current_steps": 1830, "total_steps": 40000, "loss": 0.2297, "lr": 4.974250414168633e-05, "epoch": 0.08284479051132891, "percentage": 4.58, "elapsed_time": "1:28:58", "remaining_time": "1 day, 6:55:55", "throughput": 560.74, "total_tokens": 2993664} {"current_steps": 1835, "total_steps": 40000, "loss": 0.2181, "lr": 4.974109680517407e-05, "epoch": 0.08307114239797189, "percentage": 4.59, "elapsed_time": "1:29:01", "remaining_time": "1 day, 6:51:43", "throughput": 561.98, "total_tokens": 3002048} {"current_steps": 1840, "total_steps": 40000, "loss": 0.2132, "lr": 4.973968565327376e-05, "epoch": 0.08329749428461486, "percentage": 4.6, "elapsed_time": "1:29:05", "remaining_time": "1 day, 6:47:37", "throughput": 563.3, "total_tokens": 3011008} {"current_steps": 1845, "total_steps": 40000, "loss": 0.1656, "lr": 4.973827068620303e-05, "epoch": 0.08352384617125784, "percentage": 4.61, "elapsed_time": "1:29:08", "remaining_time": "1 day, 6:43:28", "throughput": 564.52, "total_tokens": 3019360} {"current_steps": 1850, "total_steps": 40000, "loss": 0.2757, "lr": 4.973685190418008e-05, "epoch": 0.08375019805790081, "percentage": 4.62, "elapsed_time": "1:29:11", "remaining_time": "1 day, 6:39:21", "throughput": 565.74, "total_tokens": 3027680} {"current_steps": 1855, "total_steps": 40000, "loss": 0.2447, "lr": 4.97354293074237e-05, "epoch": 0.08397654994454379, "percentage": 4.64, "elapsed_time": "1:29:14", "remaining_time": "1 day, 6:35:14", "throughput": 566.93, "total_tokens": 3035872} {"current_steps": 1860, "total_steps": 40000, "loss": 0.1731, "lr": 4.9734002896153276e-05, "epoch": 0.08420290183118677, "percentage": 4.65, "elapsed_time": "1:29:18", "remaining_time": "1 day, 6:31:08", "throughput": 568.08, "total_tokens": 3043808} {"current_steps": 1865, "total_steps": 40000, "loss": 0.208, "lr": 4.973257267058877e-05, "epoch": 0.08442925371782974, "percentage": 4.66, "elapsed_time": "1:29:21", "remaining_time": "1 day, 6:27:07", "throughput": 569.43, "total_tokens": 3052928} {"current_steps": 1870, "total_steps": 40000, "loss": 0.2432, "lr": 4.973113863095076e-05, "epoch": 0.08465560560447272, "percentage": 4.67, "elapsed_time": "1:29:24", "remaining_time": "1 day, 6:23:04", "throughput": 570.55, "total_tokens": 3060704} {"current_steps": 1875, "total_steps": 40000, "loss": 0.1842, "lr": 4.9729700777460384e-05, "epoch": 0.08488195749111568, "percentage": 4.69, "elapsed_time": "1:29:27", "remaining_time": "1 day, 6:19:00", "throughput": 571.61, "total_tokens": 3068128} {"current_steps": 1880, "total_steps": 40000, "loss": 0.2254, "lr": 4.972825911033937e-05, "epoch": 0.08510830937775866, "percentage": 4.7, "elapsed_time": "1:29:30", "remaining_time": "1 day, 6:14:59", "throughput": 572.75, "total_tokens": 3076096} {"current_steps": 1885, "total_steps": 40000, "loss": 0.2179, "lr": 4.9726813629810056e-05, "epoch": 0.08533466126440165, "percentage": 4.71, "elapsed_time": "1:29:34", "remaining_time": "1 day, 6:11:06", "throughput": 574.01, "total_tokens": 3084864} {"current_steps": 1890, "total_steps": 40000, "loss": 0.1862, "lr": 4.9725364336095326e-05, "epoch": 0.08556101315104461, "percentage": 4.72, "elapsed_time": "1:29:37", "remaining_time": "1 day, 6:07:07", "throughput": 575.07, "total_tokens": 3092320} {"current_steps": 1895, "total_steps": 40000, "loss": 0.2078, "lr": 4.972391122941871e-05, "epoch": 0.0857873650376876, "percentage": 4.74, "elapsed_time": "1:29:40", "remaining_time": "1 day, 6:03:13", "throughput": 576.3, "total_tokens": 3100800} {"current_steps": 1900, "total_steps": 40000, "loss": 0.1737, "lr": 4.972245431000428e-05, "epoch": 0.08601371692433056, "percentage": 4.75, "elapsed_time": "1:29:43", "remaining_time": "1 day, 5:59:19", "throughput": 577.55, "total_tokens": 3109440} {"current_steps": 1905, "total_steps": 40000, "loss": 0.2027, "lr": 4.972099357807671e-05, "epoch": 0.08624006881097354, "percentage": 4.76, "elapsed_time": "1:29:46", "remaining_time": "1 day, 5:55:25", "throughput": 578.68, "total_tokens": 3117312} {"current_steps": 1910, "total_steps": 40000, "loss": 0.2066, "lr": 4.971952903386127e-05, "epoch": 0.08646642069761651, "percentage": 4.78, "elapsed_time": "1:29:50", "remaining_time": "1 day, 5:51:31", "throughput": 579.79, "total_tokens": 3125152} {"current_steps": 1915, "total_steps": 40000, "loss": 0.2173, "lr": 4.971806067758381e-05, "epoch": 0.08669277258425949, "percentage": 4.79, "elapsed_time": "1:29:53", "remaining_time": "1 day, 5:47:41", "throughput": 581.01, "total_tokens": 3133568} {"current_steps": 1920, "total_steps": 40000, "loss": 0.1628, "lr": 4.971658850947076e-05, "epoch": 0.08691912447090247, "percentage": 4.8, "elapsed_time": "1:29:56", "remaining_time": "1 day, 5:43:50", "throughput": 582.14, "total_tokens": 3141504} {"current_steps": 1925, "total_steps": 40000, "loss": 0.2191, "lr": 4.9715112529749165e-05, "epoch": 0.08714547635754544, "percentage": 4.81, "elapsed_time": "1:29:59", "remaining_time": "1 day, 5:39:59", "throughput": 583.26, "total_tokens": 3149376} {"current_steps": 1930, "total_steps": 40000, "loss": 0.1732, "lr": 4.9713632738646624e-05, "epoch": 0.08737182824418842, "percentage": 4.83, "elapsed_time": "1:30:02", "remaining_time": "1 day, 5:36:13", "throughput": 584.51, "total_tokens": 3158016} {"current_steps": 1935, "total_steps": 40000, "loss": 0.2246, "lr": 4.971214913639134e-05, "epoch": 0.08759818013083139, "percentage": 4.84, "elapsed_time": "1:30:06", "remaining_time": "1 day, 5:32:26", "throughput": 585.61, "total_tokens": 3165824} {"current_steps": 1940, "total_steps": 40000, "loss": 0.1639, "lr": 4.9710661723212104e-05, "epoch": 0.08782453201747437, "percentage": 4.85, "elapsed_time": "1:30:09", "remaining_time": "1 day, 5:28:41", "throughput": 586.78, "total_tokens": 3174048} {"current_steps": 1945, "total_steps": 40000, "loss": 0.1852, "lr": 4.9709170499338295e-05, "epoch": 0.08805088390411735, "percentage": 4.86, "elapsed_time": "1:30:12", "remaining_time": "1 day, 5:24:55", "throughput": 587.9, "total_tokens": 3181952} {"current_steps": 1950, "total_steps": 40000, "loss": 0.2037, "lr": 4.9707675464999895e-05, "epoch": 0.08827723579076031, "percentage": 4.88, "elapsed_time": "1:30:15", "remaining_time": "1 day, 5:21:11", "throughput": 589.04, "total_tokens": 3189952} {"current_steps": 1955, "total_steps": 40000, "loss": 0.189, "lr": 4.970617662042743e-05, "epoch": 0.0885035876774033, "percentage": 4.89, "elapsed_time": "1:30:18", "remaining_time": "1 day, 5:17:30", "throughput": 590.25, "total_tokens": 3198400} {"current_steps": 1960, "total_steps": 40000, "loss": 0.1895, "lr": 4.970467396585206e-05, "epoch": 0.08872993956404626, "percentage": 4.9, "elapsed_time": "1:30:21", "remaining_time": "1 day, 5:13:50", "throughput": 591.43, "total_tokens": 3206752} {"current_steps": 1965, "total_steps": 40000, "loss": 0.1846, "lr": 4.97031675015055e-05, "epoch": 0.08895629145068924, "percentage": 4.91, "elapsed_time": "1:30:25", "remaining_time": "1 day, 5:10:12", "throughput": 592.66, "total_tokens": 3215328} {"current_steps": 1970, "total_steps": 40000, "loss": 0.171, "lr": 4.9701657227620075e-05, "epoch": 0.08918264333733222, "percentage": 4.92, "elapsed_time": "1:30:28", "remaining_time": "1 day, 5:06:34", "throughput": 593.91, "total_tokens": 3224000} {"current_steps": 1975, "total_steps": 40000, "loss": 0.2121, "lr": 4.9700143144428685e-05, "epoch": 0.08940899522397519, "percentage": 4.94, "elapsed_time": "1:30:31", "remaining_time": "1 day, 5:02:56", "throughput": 595.02, "total_tokens": 3231968} {"current_steps": 1980, "total_steps": 40000, "loss": 0.1917, "lr": 4.969862525216482e-05, "epoch": 0.08963534711061817, "percentage": 4.95, "elapsed_time": "1:30:34", "remaining_time": "1 day, 4:59:21", "throughput": 596.21, "total_tokens": 3240320} {"current_steps": 1985, "total_steps": 40000, "loss": 0.1918, "lr": 4.9697103551062556e-05, "epoch": 0.08986169899726114, "percentage": 4.96, "elapsed_time": "1:30:38", "remaining_time": "1 day, 4:55:43", "throughput": 597.3, "total_tokens": 3248096} {"current_steps": 1990, "total_steps": 40000, "loss": 0.2521, "lr": 4.9695578041356565e-05, "epoch": 0.09008805088390412, "percentage": 4.98, "elapsed_time": "1:30:41", "remaining_time": "1 day, 4:52:08", "throughput": 598.37, "total_tokens": 3255776} {"current_steps": 1995, "total_steps": 40000, "loss": 0.1862, "lr": 4.969404872328209e-05, "epoch": 0.09031440277054709, "percentage": 4.99, "elapsed_time": "1:30:44", "remaining_time": "1 day, 4:48:33", "throughput": 599.52, "total_tokens": 3263936} {"current_steps": 2000, "total_steps": 40000, "loss": 0.1925, "lr": 4.969251559707498e-05, "epoch": 0.09054075465719007, "percentage": 5.0, "elapsed_time": "1:30:47", "remaining_time": "1 day, 4:45:00", "throughput": 600.65, "total_tokens": 3272000} {"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.19327212870121002, "epoch": 0.09054075465719007, "percentage": 5.0, "elapsed_time": "1:38:30", "remaining_time": "1 day, 7:11:30", "throughput": 553.64, "total_tokens": 3272000} {"current_steps": 2005, "total_steps": 40000, "loss": 0.1872, "lr": 4.9690978662971674e-05, "epoch": 0.09076710654383305, "percentage": 5.01, "elapsed_time": "1:38:33", "remaining_time": "1 day, 7:07:45", "throughput": 554.54, "total_tokens": 3279360} {"current_steps": 2010, "total_steps": 40000, "loss": 0.1929, "lr": 4.968943792120916e-05, "epoch": 0.09099345843047602, "percentage": 5.03, "elapsed_time": "1:38:36", "remaining_time": "1 day, 7:03:51", "throughput": 555.59, "total_tokens": 3287328} {"current_steps": 2015, "total_steps": 40000, "loss": 0.2271, "lr": 4.9687893372025046e-05, "epoch": 0.091219810317119, "percentage": 5.04, "elapsed_time": "1:38:40", "remaining_time": "1 day, 7:00:00", "throughput": 556.76, "total_tokens": 3296064} {"current_steps": 2020, "total_steps": 40000, "loss": 0.1571, "lr": 4.9686345015657535e-05, "epoch": 0.09144616220376196, "percentage": 5.05, "elapsed_time": "1:38:43", "remaining_time": "1 day, 6:56:09", "throughput": 557.83, "total_tokens": 3304192} {"current_steps": 2025, "total_steps": 40000, "loss": 0.1866, "lr": 4.968479285234538e-05, "epoch": 0.09167251409040494, "percentage": 5.06, "elapsed_time": "1:38:46", "remaining_time": "1 day, 6:52:19", "throughput": 558.93, "total_tokens": 3312512} {"current_steps": 2030, "total_steps": 40000, "loss": 0.1649, "lr": 4.9683236882327974e-05, "epoch": 0.09189886597704792, "percentage": 5.08, "elapsed_time": "1:38:49", "remaining_time": "1 day, 6:48:30", "throughput": 560.0, "total_tokens": 3320608} {"current_steps": 2035, "total_steps": 40000, "loss": 0.1683, "lr": 4.968167710584526e-05, "epoch": 0.09212521786369089, "percentage": 5.09, "elapsed_time": "1:38:52", "remaining_time": "1 day, 6:44:42", "throughput": 561.08, "total_tokens": 3328800} {"current_steps": 2040, "total_steps": 40000, "loss": 0.1538, "lr": 4.968011352313775e-05, "epoch": 0.09235156975033387, "percentage": 5.1, "elapsed_time": "1:38:55", "remaining_time": "1 day, 6:40:55", "throughput": 562.12, "total_tokens": 3336704} {"current_steps": 2045, "total_steps": 40000, "loss": 0.2096, "lr": 4.967854613444659e-05, "epoch": 0.09257792163697684, "percentage": 5.11, "elapsed_time": "1:38:59", "remaining_time": "1 day, 6:37:11", "throughput": 563.28, "total_tokens": 3345472} {"current_steps": 2050, "total_steps": 40000, "loss": 0.1816, "lr": 4.967697494001349e-05, "epoch": 0.09280427352361982, "percentage": 5.12, "elapsed_time": "1:39:02", "remaining_time": "1 day, 6:33:26", "throughput": 564.32, "total_tokens": 3353376} {"current_steps": 2055, "total_steps": 40000, "loss": 0.1558, "lr": 4.9675399940080736e-05, "epoch": 0.09303062541026279, "percentage": 5.14, "elapsed_time": "1:39:05", "remaining_time": "1 day, 6:29:42", "throughput": 565.42, "total_tokens": 3361760} {"current_steps": 2060, "total_steps": 40000, "loss": 0.1929, "lr": 4.9673821134891226e-05, "epoch": 0.09325697729690577, "percentage": 5.15, "elapsed_time": "1:39:08", "remaining_time": "1 day, 6:26:00", "throughput": 566.49, "total_tokens": 3369920} {"current_steps": 2065, "total_steps": 40000, "loss": 0.193, "lr": 4.967223852468842e-05, "epoch": 0.09348332918354875, "percentage": 5.16, "elapsed_time": "1:39:11", "remaining_time": "1 day, 6:22:19", "throughput": 567.57, "total_tokens": 3378112} {"current_steps": 2070, "total_steps": 40000, "loss": 0.1505, "lr": 4.967065210971639e-05, "epoch": 0.09370968107019172, "percentage": 5.17, "elapsed_time": "1:39:15", "remaining_time": "1 day, 6:18:39", "throughput": 568.62, "total_tokens": 3386176} {"current_steps": 2075, "total_steps": 40000, "loss": 0.1716, "lr": 4.966906189021977e-05, "epoch": 0.0939360329568347, "percentage": 5.19, "elapsed_time": "1:39:18", "remaining_time": "1 day, 6:14:59", "throughput": 569.67, "total_tokens": 3394240} {"current_steps": 2080, "total_steps": 40000, "loss": 0.1505, "lr": 4.966746786644379e-05, "epoch": 0.09416238484347766, "percentage": 5.2, "elapsed_time": "1:39:21", "remaining_time": "1 day, 6:11:19", "throughput": 570.65, "total_tokens": 3401824} {"current_steps": 2085, "total_steps": 40000, "loss": 0.1843, "lr": 4.966587003863429e-05, "epoch": 0.09438873673012065, "percentage": 5.21, "elapsed_time": "1:39:24", "remaining_time": "1 day, 6:07:44", "throughput": 571.77, "total_tokens": 3410400} {"current_steps": 2090, "total_steps": 40000, "loss": 0.1745, "lr": 4.966426840703765e-05, "epoch": 0.09461508861676363, "percentage": 5.22, "elapsed_time": "1:39:27", "remaining_time": "1 day, 6:04:06", "throughput": 572.76, "total_tokens": 3418048} {"current_steps": 2095, "total_steps": 40000, "loss": 0.2226, "lr": 4.9662662971900875e-05, "epoch": 0.0948414405034066, "percentage": 5.24, "elapsed_time": "1:39:30", "remaining_time": "1 day, 6:00:30", "throughput": 573.75, "total_tokens": 3425760} {"current_steps": 2100, "total_steps": 40000, "loss": 0.1917, "lr": 4.9661053733471534e-05, "epoch": 0.09506779239004957, "percentage": 5.25, "elapsed_time": "1:39:33", "remaining_time": "1 day, 5:56:56", "throughput": 574.84, "total_tokens": 3434112} {"current_steps": 2105, "total_steps": 40000, "loss": 0.1854, "lr": 4.965944069199781e-05, "epoch": 0.09529414427669254, "percentage": 5.26, "elapsed_time": "1:39:37", "remaining_time": "1 day, 5:53:22", "throughput": 575.85, "total_tokens": 3441920} {"current_steps": 2110, "total_steps": 40000, "loss": 0.1544, "lr": 4.965782384772842e-05, "epoch": 0.09552049616333552, "percentage": 5.27, "elapsed_time": "1:39:40", "remaining_time": "1 day, 5:49:49", "throughput": 576.86, "total_tokens": 3449792} {"current_steps": 2115, "total_steps": 40000, "loss": 0.1928, "lr": 4.9656203200912734e-05, "epoch": 0.0957468480499785, "percentage": 5.29, "elapsed_time": "1:39:43", "remaining_time": "1 day, 5:46:19", "throughput": 577.94, "total_tokens": 3458080} {"current_steps": 2120, "total_steps": 40000, "loss": 0.1624, "lr": 4.965457875180067e-05, "epoch": 0.09597319993662147, "percentage": 5.3, "elapsed_time": "1:39:46", "remaining_time": "1 day, 5:42:48", "throughput": 578.97, "total_tokens": 3466048} {"current_steps": 2125, "total_steps": 40000, "loss": 0.198, "lr": 4.9652950500642724e-05, "epoch": 0.09619955182326445, "percentage": 5.31, "elapsed_time": "1:39:49", "remaining_time": "1 day, 5:39:21", "throughput": 580.12, "total_tokens": 3474880} {"current_steps": 2130, "total_steps": 40000, "loss": 0.2346, "lr": 4.965131844769001e-05, "epoch": 0.09642590370990742, "percentage": 5.33, "elapsed_time": "1:39:53", "remaining_time": "1 day, 5:35:52", "throughput": 581.11, "total_tokens": 3482624} {"current_steps": 2135, "total_steps": 40000, "loss": 0.1814, "lr": 4.96496825931942e-05, "epoch": 0.0966522555965504, "percentage": 5.34, "elapsed_time": "1:39:56", "remaining_time": "1 day, 5:32:25", "throughput": 582.09, "total_tokens": 3490368} {"current_steps": 2140, "total_steps": 40000, "loss": 0.1353, "lr": 4.9648042937407566e-05, "epoch": 0.09687860748319337, "percentage": 5.35, "elapsed_time": "1:39:59", "remaining_time": "1 day, 5:29:03", "throughput": 583.39, "total_tokens": 3500128} {"current_steps": 2145, "total_steps": 40000, "loss": 0.1931, "lr": 4.964639948058297e-05, "epoch": 0.09710495936983635, "percentage": 5.36, "elapsed_time": "1:40:02", "remaining_time": "1 day, 5:25:38", "throughput": 584.44, "total_tokens": 3508320} {"current_steps": 2150, "total_steps": 40000, "loss": 0.1943, "lr": 4.9644752222973846e-05, "epoch": 0.09733131125647933, "percentage": 5.38, "elapsed_time": "1:40:06", "remaining_time": "1 day, 5:22:14", "throughput": 585.52, "total_tokens": 3516672} {"current_steps": 2155, "total_steps": 40000, "loss": 0.1779, "lr": 4.964310116483422e-05, "epoch": 0.0975576631431223, "percentage": 5.39, "elapsed_time": "1:40:09", "remaining_time": "1 day, 5:18:49", "throughput": 586.52, "total_tokens": 3524512} {"current_steps": 2160, "total_steps": 40000, "loss": 0.1768, "lr": 4.964144630641872e-05, "epoch": 0.09778401502976528, "percentage": 5.4, "elapsed_time": "1:40:12", "remaining_time": "1 day, 5:15:27", "throughput": 587.57, "total_tokens": 3532672} {"current_steps": 2165, "total_steps": 40000, "loss": 0.2429, "lr": 4.9639787647982525e-05, "epoch": 0.09801036691640824, "percentage": 5.41, "elapsed_time": "1:40:15", "remaining_time": "1 day, 5:12:04", "throughput": 588.56, "total_tokens": 3540448} {"current_steps": 2170, "total_steps": 40000, "loss": 0.1531, "lr": 4.963812518978143e-05, "epoch": 0.09823671880305122, "percentage": 5.42, "elapsed_time": "1:40:18", "remaining_time": "1 day, 5:08:42", "throughput": 589.6, "total_tokens": 3548576} {"current_steps": 2175, "total_steps": 40000, "loss": 0.2536, "lr": 4.963645893207182e-05, "epoch": 0.0984630706896942, "percentage": 5.44, "elapsed_time": "1:40:21", "remaining_time": "1 day, 5:05:21", "throughput": 590.59, "total_tokens": 3556352} {"current_steps": 2180, "total_steps": 40000, "loss": 0.2393, "lr": 4.963478887511063e-05, "epoch": 0.09868942257633717, "percentage": 5.45, "elapsed_time": "1:40:24", "remaining_time": "1 day, 5:02:02", "throughput": 591.61, "total_tokens": 3564352} {"current_steps": 2185, "total_steps": 40000, "loss": 0.157, "lr": 4.963311501915542e-05, "epoch": 0.09891577446298015, "percentage": 5.46, "elapsed_time": "1:40:27", "remaining_time": "1 day, 4:58:42", "throughput": 592.65, "total_tokens": 3572448} {"current_steps": 2190, "total_steps": 40000, "loss": 0.1154, "lr": 4.963143736446432e-05, "epoch": 0.09914212634962312, "percentage": 5.47, "elapsed_time": "1:40:31", "remaining_time": "1 day, 4:55:27", "throughput": 593.79, "total_tokens": 3581280} {"current_steps": 2195, "total_steps": 40000, "loss": 0.1737, "lr": 4.962975591129603e-05, "epoch": 0.0993684782362661, "percentage": 5.49, "elapsed_time": "1:40:34", "remaining_time": "1 day, 4:52:11", "throughput": 594.86, "total_tokens": 3589600} {"current_steps": 2200, "total_steps": 40000, "loss": 0.1826, "lr": 4.962807065990986e-05, "epoch": 0.09959483012290908, "percentage": 5.5, "elapsed_time": "1:40:37", "remaining_time": "1 day, 4:48:55", "throughput": 595.85, "total_tokens": 3597472} {"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.19075937569141388, "epoch": 0.09959483012290908, "percentage": 5.5, "elapsed_time": "1:48:20", "remaining_time": "1 day, 7:01:24", "throughput": 553.44, "total_tokens": 3597472} {"current_steps": 2205, "total_steps": 40000, "loss": 0.1743, "lr": 4.9626381610565714e-05, "epoch": 0.09982118200955205, "percentage": 5.51, "elapsed_time": "1:48:24", "remaining_time": "1 day, 6:58:12", "throughput": 554.32, "total_tokens": 3605632} {"current_steps": 2210, "total_steps": 40000, "loss": 0.197, "lr": 4.9624688763524043e-05, "epoch": 0.10004753389619503, "percentage": 5.53, "elapsed_time": "1:48:27", "remaining_time": "1 day, 6:54:39", "throughput": 555.32, "total_tokens": 3613856} {"current_steps": 2215, "total_steps": 40000, "loss": 0.2079, "lr": 4.962299211904591e-05, "epoch": 0.100273885782838, "percentage": 5.54, "elapsed_time": "1:48:31", "remaining_time": "1 day, 6:51:09", "throughput": 556.38, "total_tokens": 3622592} {"current_steps": 2220, "total_steps": 40000, "loss": 0.1532, "lr": 4.962129167739296e-05, "epoch": 0.10050023766948098, "percentage": 5.55, "elapsed_time": "1:48:34", "remaining_time": "1 day, 6:47:37", "throughput": 557.33, "total_tokens": 3630496} {"current_steps": 2225, "total_steps": 40000, "loss": 0.2133, "lr": 4.961958743882742e-05, "epoch": 0.10072658955612394, "percentage": 5.56, "elapsed_time": "1:48:37", "remaining_time": "1 day, 6:44:07", "throughput": 558.3, "total_tokens": 3638592} {"current_steps": 2230, "total_steps": 40000, "loss": 0.153, "lr": 4.961787940361211e-05, "epoch": 0.10095294144276692, "percentage": 5.58, "elapsed_time": "1:48:40", "remaining_time": "1 day, 6:40:39", "throughput": 559.33, "total_tokens": 3647136} {"current_steps": 2235, "total_steps": 40000, "loss": 0.2031, "lr": 4.961616757201043e-05, "epoch": 0.1011792933294099, "percentage": 5.59, "elapsed_time": "1:48:43", "remaining_time": "1 day, 6:37:12", "throughput": 560.33, "total_tokens": 3655456} {"current_steps": 2240, "total_steps": 40000, "loss": 0.1475, "lr": 4.961445194428637e-05, "epoch": 0.10140564521605287, "percentage": 5.6, "elapsed_time": "1:48:46", "remaining_time": "1 day, 6:33:45", "throughput": 561.31, "total_tokens": 3663648} {"current_steps": 2245, "total_steps": 40000, "loss": 0.182, "lr": 4.9612732520704486e-05, "epoch": 0.10163199710269585, "percentage": 5.61, "elapsed_time": "1:48:50", "remaining_time": "1 day, 6:30:18", "throughput": 562.27, "total_tokens": 3671680} {"current_steps": 2250, "total_steps": 40000, "loss": 0.1652, "lr": 4.961100930152994e-05, "epoch": 0.10185834898933882, "percentage": 5.62, "elapsed_time": "1:48:53", "remaining_time": "1 day, 6:26:51", "throughput": 563.19, "total_tokens": 3679424} {"current_steps": 2255, "total_steps": 40000, "loss": 0.2338, "lr": 4.960928228702849e-05, "epoch": 0.1020847008759818, "percentage": 5.64, "elapsed_time": "1:48:56", "remaining_time": "1 day, 6:23:30", "throughput": 564.29, "total_tokens": 3688512} {"current_steps": 2260, "total_steps": 40000, "loss": 0.2046, "lr": 4.960755147746645e-05, "epoch": 0.10231105276262478, "percentage": 5.65, "elapsed_time": "1:48:59", "remaining_time": "1 day, 6:20:06", "throughput": 565.24, "total_tokens": 3696480} {"current_steps": 2265, "total_steps": 40000, "loss": 0.1857, "lr": 4.9605816873110736e-05, "epoch": 0.10253740464926775, "percentage": 5.66, "elapsed_time": "1:49:02", "remaining_time": "1 day, 6:16:43", "throughput": 566.21, "total_tokens": 3704576} {"current_steps": 2270, "total_steps": 40000, "loss": 0.1965, "lr": 4.960407847422883e-05, "epoch": 0.10276375653591073, "percentage": 5.67, "elapsed_time": "1:49:05", "remaining_time": "1 day, 6:13:21", "throughput": 567.14, "total_tokens": 3712480} {"current_steps": 2275, "total_steps": 40000, "loss": 0.1209, "lr": 4.960233628108885e-05, "epoch": 0.1029901084225537, "percentage": 5.69, "elapsed_time": "1:49:09", "remaining_time": "1 day, 6:10:00", "throughput": 568.13, "total_tokens": 3720736} {"current_steps": 2280, "total_steps": 40000, "loss": 0.1965, "lr": 4.960059029395942e-05, "epoch": 0.10321646030919668, "percentage": 5.7, "elapsed_time": "1:49:12", "remaining_time": "1 day, 6:06:41", "throughput": 569.14, "total_tokens": 3729184} {"current_steps": 2285, "total_steps": 40000, "loss": 0.1619, "lr": 4.959884051310983e-05, "epoch": 0.10344281219583966, "percentage": 5.71, "elapsed_time": "1:49:15", "remaining_time": "1 day, 6:03:21", "throughput": 570.09, "total_tokens": 3737184} {"current_steps": 2290, "total_steps": 40000, "loss": 0.1685, "lr": 4.959708693880991e-05, "epoch": 0.10366916408248263, "percentage": 5.73, "elapsed_time": "1:49:18", "remaining_time": "1 day, 6:00:08", "throughput": 571.26, "total_tokens": 3746880} {"current_steps": 2295, "total_steps": 40000, "loss": 0.1887, "lr": 4.9595329571330074e-05, "epoch": 0.1038955159691256, "percentage": 5.74, "elapsed_time": "1:49:22", "remaining_time": "1 day, 5:56:55", "throughput": 572.31, "total_tokens": 3755744} {"current_steps": 2300, "total_steps": 40000, "loss": 0.2029, "lr": 4.9593568410941326e-05, "epoch": 0.10412186785576857, "percentage": 5.75, "elapsed_time": "1:49:25", "remaining_time": "1 day, 5:53:38", "throughput": 573.26, "total_tokens": 3763744} {"current_steps": 2305, "total_steps": 40000, "loss": 0.1615, "lr": 4.959180345791528e-05, "epoch": 0.10434821974241155, "percentage": 5.76, "elapsed_time": "1:49:28", "remaining_time": "1 day, 5:50:21", "throughput": 574.17, "total_tokens": 3771584} {"current_steps": 2310, "total_steps": 40000, "loss": 0.1288, "lr": 4.9590034712524086e-05, "epoch": 0.10457457162905452, "percentage": 5.78, "elapsed_time": "1:49:31", "remaining_time": "1 day, 5:47:07", "throughput": 575.13, "total_tokens": 3779712} {"current_steps": 2315, "total_steps": 40000, "loss": 0.1815, "lr": 4.958826217504053e-05, "epoch": 0.1048009235156975, "percentage": 5.79, "elapsed_time": "1:49:34", "remaining_time": "1 day, 5:43:51", "throughput": 576.08, "total_tokens": 3787744} {"current_steps": 2320, "total_steps": 40000, "loss": 0.1752, "lr": 4.958648584573795e-05, "epoch": 0.10502727540234048, "percentage": 5.8, "elapsed_time": "1:49:38", "remaining_time": "1 day, 5:40:39", "throughput": 577.06, "total_tokens": 3796000} {"current_steps": 2325, "total_steps": 40000, "loss": 0.2208, "lr": 4.958470572489028e-05, "epoch": 0.10525362728898345, "percentage": 5.81, "elapsed_time": "1:49:41", "remaining_time": "1 day, 5:37:26", "throughput": 578.0, "total_tokens": 3804064} {"current_steps": 2330, "total_steps": 40000, "loss": 0.1639, "lr": 4.958292181277203e-05, "epoch": 0.10547997917562643, "percentage": 5.83, "elapsed_time": "1:49:44", "remaining_time": "1 day, 5:34:13", "throughput": 578.88, "total_tokens": 3811584} {"current_steps": 2335, "total_steps": 40000, "loss": 0.1928, "lr": 4.958113410965832e-05, "epoch": 0.1057063310622694, "percentage": 5.84, "elapsed_time": "1:49:47", "remaining_time": "1 day, 5:31:02", "throughput": 579.83, "total_tokens": 3819712} {"current_steps": 2340, "total_steps": 40000, "loss": 0.1317, "lr": 4.957934261582481e-05, "epoch": 0.10593268294891238, "percentage": 5.85, "elapsed_time": "1:49:50", "remaining_time": "1 day, 5:27:52", "throughput": 580.8, "total_tokens": 3827936} {"current_steps": 2345, "total_steps": 40000, "loss": 0.1983, "lr": 4.95775473315478e-05, "epoch": 0.10615903483555536, "percentage": 5.86, "elapsed_time": "1:49:53", "remaining_time": "1 day, 5:24:43", "throughput": 581.77, "total_tokens": 3836192} {"current_steps": 2350, "total_steps": 40000, "loss": 0.1693, "lr": 4.9575748257104124e-05, "epoch": 0.10638538672219833, "percentage": 5.88, "elapsed_time": "1:49:57", "remaining_time": "1 day, 5:21:35", "throughput": 582.8, "total_tokens": 3844864} {"current_steps": 2355, "total_steps": 40000, "loss": 0.2248, "lr": 4.9573945392771224e-05, "epoch": 0.10661173860884131, "percentage": 5.89, "elapsed_time": "1:50:00", "remaining_time": "1 day, 5:18:28", "throughput": 583.75, "total_tokens": 3852992} {"current_steps": 2360, "total_steps": 40000, "loss": 0.1944, "lr": 4.9572138738827134e-05, "epoch": 0.10683809049548428, "percentage": 5.9, "elapsed_time": "1:50:03", "remaining_time": "1 day, 5:15:20", "throughput": 584.69, "total_tokens": 3861056} {"current_steps": 2365, "total_steps": 40000, "loss": 0.1579, "lr": 4.957032829555046e-05, "epoch": 0.10706444238212726, "percentage": 5.91, "elapsed_time": "1:50:06", "remaining_time": "1 day, 5:12:15", "throughput": 585.68, "total_tokens": 3869472} {"current_steps": 2370, "total_steps": 40000, "loss": 0.1511, "lr": 4.956851406322039e-05, "epoch": 0.10729079426877024, "percentage": 5.92, "elapsed_time": "1:50:09", "remaining_time": "1 day, 5:09:10", "throughput": 586.62, "total_tokens": 3877504} {"current_steps": 2375, "total_steps": 40000, "loss": 0.1522, "lr": 4.9566696042116704e-05, "epoch": 0.1075171461554132, "percentage": 5.94, "elapsed_time": "1:50:13", "remaining_time": "1 day, 5:06:05", "throughput": 587.56, "total_tokens": 3885600} {"current_steps": 2380, "total_steps": 40000, "loss": 0.1459, "lr": 4.9564874232519766e-05, "epoch": 0.10774349804205618, "percentage": 5.95, "elapsed_time": "1:50:16", "remaining_time": "1 day, 5:03:00", "throughput": 588.5, "total_tokens": 3893632} {"current_steps": 2385, "total_steps": 40000, "loss": 0.1879, "lr": 4.9563048634710516e-05, "epoch": 0.10796984992869915, "percentage": 5.96, "elapsed_time": "1:50:19", "remaining_time": "1 day, 4:59:59", "throughput": 589.51, "total_tokens": 3902272} {"current_steps": 2390, "total_steps": 40000, "loss": 0.1527, "lr": 4.956121924897049e-05, "epoch": 0.10819620181534213, "percentage": 5.97, "elapsed_time": "1:50:22", "remaining_time": "1 day, 4:56:57", "throughput": 590.48, "total_tokens": 3910560} {"current_steps": 2395, "total_steps": 40000, "loss": 0.1398, "lr": 4.955938607558181e-05, "epoch": 0.1084225537019851, "percentage": 5.99, "elapsed_time": "1:50:25", "remaining_time": "1 day, 4:53:56", "throughput": 591.44, "total_tokens": 3918816} {"current_steps": 2400, "total_steps": 40000, "loss": 0.1573, "lr": 4.955754911482715e-05, "epoch": 0.10864890558862808, "percentage": 6.0, "elapsed_time": "1:50:29", "remaining_time": "1 day, 4:50:56", "throughput": 592.41, "total_tokens": 3927168} {"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.18641383945941925, "epoch": 0.10864890558862808, "percentage": 6.0, "elapsed_time": "1:58:11", "remaining_time": "1 day, 6:51:47", "throughput": 553.75, "total_tokens": 3927168} {"current_steps": 2405, "total_steps": 40000, "loss": 0.1853, "lr": 4.9555708366989804e-05, "epoch": 0.10887525747527106, "percentage": 6.01, "elapsed_time": "1:58:16", "remaining_time": "1 day, 6:48:46", "throughput": 554.63, "total_tokens": 3935712} {"current_steps": 2410, "total_steps": 40000, "loss": 0.2087, "lr": 4.9553863832353655e-05, "epoch": 0.10910160936191403, "percentage": 6.02, "elapsed_time": "1:58:19", "remaining_time": "1 day, 6:45:31", "throughput": 555.54, "total_tokens": 3943904} {"current_steps": 2415, "total_steps": 40000, "loss": 0.1774, "lr": 4.955201551120313e-05, "epoch": 0.10932796124855701, "percentage": 6.04, "elapsed_time": "1:58:22", "remaining_time": "1 day, 6:42:15", "throughput": 556.38, "total_tokens": 3951648} {"current_steps": 2420, "total_steps": 40000, "loss": 0.1208, "lr": 4.955016340382328e-05, "epoch": 0.10955431313519998, "percentage": 6.05, "elapsed_time": "1:58:25", "remaining_time": "1 day, 6:39:01", "throughput": 557.25, "total_tokens": 3959552} {"current_steps": 2425, "total_steps": 40000, "loss": 0.133, "lr": 4.954830751049972e-05, "epoch": 0.10978066502184296, "percentage": 6.06, "elapsed_time": "1:58:28", "remaining_time": "1 day, 6:35:46", "throughput": 558.1, "total_tokens": 3967296} {"current_steps": 2430, "total_steps": 40000, "loss": 0.188, "lr": 4.954644783151864e-05, "epoch": 0.11000701690848594, "percentage": 6.08, "elapsed_time": "1:58:31", "remaining_time": "1 day, 6:32:33", "throughput": 558.97, "total_tokens": 3975232} {"current_steps": 2435, "total_steps": 40000, "loss": 0.1981, "lr": 4.954458436716684e-05, "epoch": 0.1102333687951289, "percentage": 6.09, "elapsed_time": "1:58:34", "remaining_time": "1 day, 6:29:21", "throughput": 559.85, "total_tokens": 3983232} {"current_steps": 2440, "total_steps": 40000, "loss": 0.1518, "lr": 4.954271711773168e-05, "epoch": 0.11045972068177189, "percentage": 6.1, "elapsed_time": "1:58:38", "remaining_time": "1 day, 6:26:12", "throughput": 560.78, "total_tokens": 3991680} {"current_steps": 2445, "total_steps": 40000, "loss": 0.2076, "lr": 4.9540846083501115e-05, "epoch": 0.11068607256841485, "percentage": 6.11, "elapsed_time": "1:58:41", "remaining_time": "1 day, 6:23:01", "throughput": 561.64, "total_tokens": 3999616} {"current_steps": 2450, "total_steps": 40000, "loss": 0.1683, "lr": 4.953897126476369e-05, "epoch": 0.11091242445505783, "percentage": 6.12, "elapsed_time": "1:58:44", "remaining_time": "1 day, 6:19:53", "throughput": 562.62, "total_tokens": 4008352} {"current_steps": 2455, "total_steps": 40000, "loss": 0.1126, "lr": 4.9537092661808514e-05, "epoch": 0.1111387763417008, "percentage": 6.14, "elapsed_time": "1:58:47", "remaining_time": "1 day, 6:16:46", "throughput": 563.55, "total_tokens": 4016864} {"current_steps": 2460, "total_steps": 40000, "loss": 0.1786, "lr": 4.9535210274925306e-05, "epoch": 0.11136512822834378, "percentage": 6.15, "elapsed_time": "1:58:50", "remaining_time": "1 day, 6:13:40", "throughput": 564.49, "total_tokens": 4025376} {"current_steps": 2465, "total_steps": 40000, "loss": 0.1953, "lr": 4.953332410440435e-05, "epoch": 0.11159148011498676, "percentage": 6.16, "elapsed_time": "1:58:54", "remaining_time": "1 day, 6:10:33", "throughput": 565.39, "total_tokens": 4033600} {"current_steps": 2470, "total_steps": 40000, "loss": 0.1879, "lr": 4.9531434150536496e-05, "epoch": 0.11181783200162973, "percentage": 6.17, "elapsed_time": "1:58:57", "remaining_time": "1 day, 6:07:27", "throughput": 566.31, "total_tokens": 4041952} {"current_steps": 2475, "total_steps": 40000, "loss": 0.1856, "lr": 4.952954041361322e-05, "epoch": 0.11204418388827271, "percentage": 6.19, "elapsed_time": "1:59:00", "remaining_time": "1 day, 6:04:22", "throughput": 567.19, "total_tokens": 4050048} {"current_steps": 2480, "total_steps": 40000, "loss": 0.1566, "lr": 4.952764289392655e-05, "epoch": 0.11227053577491568, "percentage": 6.2, "elapsed_time": "1:59:03", "remaining_time": "1 day, 6:01:17", "throughput": 568.08, "total_tokens": 4058240} {"current_steps": 2485, "total_steps": 40000, "loss": 0.1901, "lr": 4.952574159176912e-05, "epoch": 0.11249688766155866, "percentage": 6.21, "elapsed_time": "1:59:06", "remaining_time": "1 day, 5:58:13", "throughput": 568.95, "total_tokens": 4066208} {"current_steps": 2490, "total_steps": 40000, "loss": 0.1914, "lr": 4.952383650743413e-05, "epoch": 0.11272323954820164, "percentage": 6.22, "elapsed_time": "1:59:10", "remaining_time": "1 day, 5:55:12", "throughput": 569.94, "total_tokens": 4075168} {"current_steps": 2495, "total_steps": 40000, "loss": 0.1744, "lr": 4.952192764121536e-05, "epoch": 0.1129495914348446, "percentage": 6.24, "elapsed_time": "1:59:13", "remaining_time": "1 day, 5:52:11", "throughput": 570.87, "total_tokens": 4083680} {"current_steps": 2500, "total_steps": 40000, "loss": 0.1918, "lr": 4.9520014993407185e-05, "epoch": 0.11317594332148759, "percentage": 6.25, "elapsed_time": "1:59:16", "remaining_time": "1 day, 5:49:09", "throughput": 571.74, "total_tokens": 4091744} {"current_steps": 2505, "total_steps": 40000, "loss": 0.1551, "lr": 4.951809856430456e-05, "epoch": 0.11340229520813055, "percentage": 6.26, "elapsed_time": "1:59:19", "remaining_time": "1 day, 5:46:10", "throughput": 572.7, "total_tokens": 4100480} {"current_steps": 2510, "total_steps": 40000, "loss": 0.2031, "lr": 4.951617835420303e-05, "epoch": 0.11362864709477354, "percentage": 6.28, "elapsed_time": "1:59:23", "remaining_time": "1 day, 5:43:09", "throughput": 573.56, "total_tokens": 4108448} {"current_steps": 2515, "total_steps": 40000, "loss": 0.1704, "lr": 4.951425436339869e-05, "epoch": 0.11385499898141652, "percentage": 6.29, "elapsed_time": "1:59:26", "remaining_time": "1 day, 5:40:10", "throughput": 574.46, "total_tokens": 4116704} {"current_steps": 2520, "total_steps": 40000, "loss": 0.1629, "lr": 4.9512326592188274e-05, "epoch": 0.11408135086805948, "percentage": 6.3, "elapsed_time": "1:59:29", "remaining_time": "1 day, 5:37:13", "throughput": 575.45, "total_tokens": 4125792} {"current_steps": 2525, "total_steps": 40000, "loss": 0.1735, "lr": 4.9510395040869054e-05, "epoch": 0.11430770275470246, "percentage": 6.31, "elapsed_time": "1:59:33", "remaining_time": "1 day, 5:34:21", "throughput": 576.4, "total_tokens": 4134656} {"current_steps": 2530, "total_steps": 40000, "loss": 0.1998, "lr": 4.9508459709738905e-05, "epoch": 0.11453405464134543, "percentage": 6.33, "elapsed_time": "1:59:36", "remaining_time": "1 day, 5:31:21", "throughput": 577.17, "total_tokens": 4141888} {"current_steps": 2535, "total_steps": 40000, "loss": 0.18, "lr": 4.950652059909627e-05, "epoch": 0.11476040652798841, "percentage": 6.34, "elapsed_time": "1:59:39", "remaining_time": "1 day, 5:28:24", "throughput": 578.03, "total_tokens": 4149920} {"current_steps": 2540, "total_steps": 40000, "loss": 0.1829, "lr": 4.95045777092402e-05, "epoch": 0.11498675841463138, "percentage": 6.35, "elapsed_time": "1:59:42", "remaining_time": "1 day, 5:25:27", "throughput": 578.83, "total_tokens": 4157440} {"current_steps": 2545, "total_steps": 40000, "loss": 0.1748, "lr": 4.950263104047031e-05, "epoch": 0.11521311030127436, "percentage": 6.36, "elapsed_time": "1:59:45", "remaining_time": "1 day, 5:22:32", "throughput": 579.78, "total_tokens": 4166112} {"current_steps": 2550, "total_steps": 40000, "loss": 0.2164, "lr": 4.9500680593086775e-05, "epoch": 0.11543946218791734, "percentage": 6.38, "elapsed_time": "1:59:48", "remaining_time": "1 day, 5:19:37", "throughput": 580.62, "total_tokens": 4173984} {"current_steps": 2555, "total_steps": 40000, "loss": 0.2394, "lr": 4.94987263673904e-05, "epoch": 0.11566581407456031, "percentage": 6.39, "elapsed_time": "1:59:51", "remaining_time": "1 day, 5:16:42", "throughput": 581.45, "total_tokens": 4181728} {"current_steps": 2560, "total_steps": 40000, "loss": 0.124, "lr": 4.949676836368256e-05, "epoch": 0.11589216596120329, "percentage": 6.4, "elapsed_time": "1:59:55", "remaining_time": "1 day, 5:13:48", "throughput": 582.3, "total_tokens": 4189696} {"current_steps": 2565, "total_steps": 40000, "loss": 0.1449, "lr": 4.949480658226518e-05, "epoch": 0.11611851784784626, "percentage": 6.41, "elapsed_time": "1:59:58", "remaining_time": "1 day, 5:10:57", "throughput": 583.27, "total_tokens": 4198656} {"current_steps": 2570, "total_steps": 40000, "loss": 0.1838, "lr": 4.949284102344082e-05, "epoch": 0.11634486973448924, "percentage": 6.42, "elapsed_time": "2:00:01", "remaining_time": "1 day, 5:08:05", "throughput": 584.12, "total_tokens": 4206592} {"current_steps": 2575, "total_steps": 40000, "loss": 0.1521, "lr": 4.9490871687512565e-05, "epoch": 0.11657122162113222, "percentage": 6.44, "elapsed_time": "2:00:04", "remaining_time": "1 day, 5:05:15", "throughput": 585.06, "total_tokens": 4215296} {"current_steps": 2580, "total_steps": 40000, "loss": 0.1518, "lr": 4.948889857478413e-05, "epoch": 0.11679757350777518, "percentage": 6.45, "elapsed_time": "2:00:07", "remaining_time": "1 day, 5:02:23", "throughput": 585.92, "total_tokens": 4223328} {"current_steps": 2585, "total_steps": 40000, "loss": 0.1633, "lr": 4.948692168555978e-05, "epoch": 0.11702392539441817, "percentage": 6.46, "elapsed_time": "2:00:11", "remaining_time": "1 day, 4:59:33", "throughput": 586.84, "total_tokens": 4231840} {"current_steps": 2590, "total_steps": 40000, "loss": 0.1576, "lr": 4.94849410201444e-05, "epoch": 0.11725027728106113, "percentage": 6.48, "elapsed_time": "2:00:14", "remaining_time": "1 day, 4:56:42", "throughput": 587.6, "total_tokens": 4239072} {"current_steps": 2595, "total_steps": 40000, "loss": 0.1717, "lr": 4.948295657884341e-05, "epoch": 0.11747662916770411, "percentage": 6.49, "elapsed_time": "2:00:17", "remaining_time": "1 day, 4:53:54", "throughput": 588.48, "total_tokens": 4247328} {"current_steps": 2600, "total_steps": 40000, "loss": 0.112, "lr": 4.9480968361962835e-05, "epoch": 0.1177029810543471, "percentage": 6.5, "elapsed_time": "2:00:20", "remaining_time": "1 day, 4:51:05", "throughput": 589.37, "total_tokens": 4255584} {"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.18631435930728912, "epoch": 0.1177029810543471, "percentage": 6.5, "elapsed_time": "2:08:03", "remaining_time": "1 day, 6:42:02", "throughput": 553.87, "total_tokens": 4255584} {"current_steps": 2605, "total_steps": 40000, "loss": 0.2173, "lr": 4.9478976369809305e-05, "epoch": 0.11792933294099006, "percentage": 6.51, "elapsed_time": "2:08:07", "remaining_time": "1 day, 6:39:11", "throughput": 554.69, "total_tokens": 4264064} {"current_steps": 2610, "total_steps": 40000, "loss": 0.2295, "lr": 4.947698060268999e-05, "epoch": 0.11815568482763304, "percentage": 6.53, "elapsed_time": "2:08:10", "remaining_time": "1 day, 6:36:10", "throughput": 555.49, "total_tokens": 4271968} {"current_steps": 2615, "total_steps": 40000, "loss": 0.1782, "lr": 4.9474981060912665e-05, "epoch": 0.11838203671427601, "percentage": 6.54, "elapsed_time": "2:08:13", "remaining_time": "1 day, 6:33:11", "throughput": 556.36, "total_tokens": 4280416} {"current_steps": 2620, "total_steps": 40000, "loss": 0.2013, "lr": 4.94729777447857e-05, "epoch": 0.11860838860091899, "percentage": 6.55, "elapsed_time": "2:08:16", "remaining_time": "1 day, 6:30:11", "throughput": 557.16, "total_tokens": 4288352} {"current_steps": 2625, "total_steps": 40000, "loss": 0.1875, "lr": 4.947097065461801e-05, "epoch": 0.11883474048756196, "percentage": 6.56, "elapsed_time": "2:08:20", "remaining_time": "1 day, 6:27:14", "throughput": 558.07, "total_tokens": 4297216} {"current_steps": 2630, "total_steps": 40000, "loss": 0.1302, "lr": 4.9468959790719125e-05, "epoch": 0.11906109237420494, "percentage": 6.58, "elapsed_time": "2:08:23", "remaining_time": "1 day, 6:24:16", "throughput": 558.9, "total_tokens": 4305344} {"current_steps": 2635, "total_steps": 40000, "loss": 0.2428, "lr": 4.9466945153399146e-05, "epoch": 0.11928744426084792, "percentage": 6.59, "elapsed_time": "2:08:26", "remaining_time": "1 day, 6:21:17", "throughput": 559.69, "total_tokens": 4313120} {"current_steps": 2640, "total_steps": 40000, "loss": 0.1572, "lr": 4.9464926742968755e-05, "epoch": 0.11951379614749089, "percentage": 6.6, "elapsed_time": "2:08:29", "remaining_time": "1 day, 6:18:20", "throughput": 560.51, "total_tokens": 4321184} {"current_steps": 2645, "total_steps": 40000, "loss": 0.2364, "lr": 4.946290455973921e-05, "epoch": 0.11974014803413387, "percentage": 6.61, "elapsed_time": "2:08:32", "remaining_time": "1 day, 6:15:24", "throughput": 561.32, "total_tokens": 4329248} {"current_steps": 2650, "total_steps": 40000, "loss": 0.1892, "lr": 4.9460878604022365e-05, "epoch": 0.11996649992077683, "percentage": 6.62, "elapsed_time": "2:08:35", "remaining_time": "1 day, 6:12:30", "throughput": 562.2, "total_tokens": 4337856} {"current_steps": 2655, "total_steps": 40000, "loss": 0.1197, "lr": 4.945884887613065e-05, "epoch": 0.12019285180741981, "percentage": 6.64, "elapsed_time": "2:08:39", "remaining_time": "1 day, 6:09:35", "throughput": 563.03, "total_tokens": 4346048} {"current_steps": 2660, "total_steps": 40000, "loss": 0.1687, "lr": 4.9456815376377055e-05, "epoch": 0.1204192036940628, "percentage": 6.65, "elapsed_time": "2:08:42", "remaining_time": "1 day, 6:06:41", "throughput": 563.84, "total_tokens": 4354112} {"current_steps": 2665, "total_steps": 40000, "loss": 0.1881, "lr": 4.9454778105075195e-05, "epoch": 0.12064555558070576, "percentage": 6.66, "elapsed_time": "2:08:45", "remaining_time": "1 day, 6:03:48", "throughput": 564.69, "total_tokens": 4362464} {"current_steps": 2670, "total_steps": 40000, "loss": 0.1557, "lr": 4.945273706253924e-05, "epoch": 0.12087190746734874, "percentage": 6.68, "elapsed_time": "2:08:48", "remaining_time": "1 day, 6:00:58", "throughput": 565.61, "total_tokens": 4371456} {"current_steps": 2675, "total_steps": 40000, "loss": 0.1396, "lr": 4.9450692249083925e-05, "epoch": 0.12109825935399171, "percentage": 6.69, "elapsed_time": "2:08:52", "remaining_time": "1 day, 5:58:08", "throughput": 566.56, "total_tokens": 4380736} {"current_steps": 2680, "total_steps": 40000, "loss": 0.1719, "lr": 4.9448643665024605e-05, "epoch": 0.12132461124063469, "percentage": 6.7, "elapsed_time": "2:08:55", "remaining_time": "1 day, 5:55:17", "throughput": 567.38, "total_tokens": 4388864} {"current_steps": 2685, "total_steps": 40000, "loss": 0.1524, "lr": 4.944659131067719e-05, "epoch": 0.12155096312727767, "percentage": 6.71, "elapsed_time": "2:08:58", "remaining_time": "1 day, 5:52:25", "throughput": 568.18, "total_tokens": 4396832} {"current_steps": 2690, "total_steps": 40000, "loss": 0.1683, "lr": 4.944453518635818e-05, "epoch": 0.12177731501392064, "percentage": 6.73, "elapsed_time": "2:09:01", "remaining_time": "1 day, 5:49:34", "throughput": 568.96, "total_tokens": 4404640} {"current_steps": 2695, "total_steps": 40000, "loss": 0.2147, "lr": 4.944247529238465e-05, "epoch": 0.12200366690056362, "percentage": 6.74, "elapsed_time": "2:09:04", "remaining_time": "1 day, 5:46:43", "throughput": 569.74, "total_tokens": 4412384} {"current_steps": 2700, "total_steps": 40000, "loss": 0.1349, "lr": 4.944041162907427e-05, "epoch": 0.12223001878720659, "percentage": 6.75, "elapsed_time": "2:09:07", "remaining_time": "1 day, 5:43:54", "throughput": 570.55, "total_tokens": 4420480} {"current_steps": 2705, "total_steps": 40000, "loss": 0.1624, "lr": 4.943834419674529e-05, "epoch": 0.12245637067384957, "percentage": 6.76, "elapsed_time": "2:09:10", "remaining_time": "1 day, 5:41:05", "throughput": 571.35, "total_tokens": 4428512} {"current_steps": 2710, "total_steps": 40000, "loss": 0.2099, "lr": 4.9436272995716506e-05, "epoch": 0.12268272256049254, "percentage": 6.78, "elapsed_time": "2:09:14", "remaining_time": "1 day, 5:38:18", "throughput": 572.21, "total_tokens": 4437024} {"current_steps": 2715, "total_steps": 40000, "loss": 0.1652, "lr": 4.943419802630735e-05, "epoch": 0.12290907444713552, "percentage": 6.79, "elapsed_time": "2:09:17", "remaining_time": "1 day, 5:35:30", "throughput": 573.0, "total_tokens": 4444960} {"current_steps": 2720, "total_steps": 40000, "loss": 0.2058, "lr": 4.94321192888378e-05, "epoch": 0.1231354263337785, "percentage": 6.8, "elapsed_time": "2:09:20", "remaining_time": "1 day, 5:32:44", "throughput": 573.87, "total_tokens": 4453504} {"current_steps": 2725, "total_steps": 40000, "loss": 0.1691, "lr": 4.943003678362842e-05, "epoch": 0.12336177822042146, "percentage": 6.81, "elapsed_time": "2:09:23", "remaining_time": "1 day, 5:30:01", "throughput": 574.77, "total_tokens": 4462432} {"current_steps": 2730, "total_steps": 40000, "loss": 0.1367, "lr": 4.942795051100036e-05, "epoch": 0.12358813010706445, "percentage": 6.83, "elapsed_time": "2:09:26", "remaining_time": "1 day, 5:27:15", "throughput": 575.53, "total_tokens": 4470144} {"current_steps": 2735, "total_steps": 40000, "loss": 0.1713, "lr": 4.942586047127536e-05, "epoch": 0.12381448199370741, "percentage": 6.84, "elapsed_time": "2:09:30", "remaining_time": "1 day, 5:24:30", "throughput": 576.32, "total_tokens": 4478112} {"current_steps": 2740, "total_steps": 40000, "loss": 0.1941, "lr": 4.942376666477571e-05, "epoch": 0.12404083388035039, "percentage": 6.85, "elapsed_time": "2:09:33", "remaining_time": "1 day, 5:21:46", "throughput": 577.15, "total_tokens": 4486400} {"current_steps": 2745, "total_steps": 40000, "loss": 0.2002, "lr": 4.9421669091824304e-05, "epoch": 0.12426718576699337, "percentage": 6.86, "elapsed_time": "2:09:36", "remaining_time": "1 day, 5:19:02", "throughput": 577.93, "total_tokens": 4494272} {"current_steps": 2750, "total_steps": 40000, "loss": 0.1719, "lr": 4.9419567752744634e-05, "epoch": 0.12449353765363634, "percentage": 6.88, "elapsed_time": "2:09:39", "remaining_time": "1 day, 5:16:18", "throughput": 578.69, "total_tokens": 4501984} {"current_steps": 2755, "total_steps": 40000, "loss": 0.1658, "lr": 4.941746264786074e-05, "epoch": 0.12471988954027932, "percentage": 6.89, "elapsed_time": "2:09:42", "remaining_time": "1 day, 5:13:37", "throughput": 579.56, "total_tokens": 4510688} {"current_steps": 2760, "total_steps": 40000, "loss": 0.2194, "lr": 4.9415353777497254e-05, "epoch": 0.12494624142692229, "percentage": 6.9, "elapsed_time": "2:09:46", "remaining_time": "1 day, 5:10:56", "throughput": 580.43, "total_tokens": 4519296} {"current_steps": 2765, "total_steps": 40000, "loss": 0.1399, "lr": 4.9413241141979394e-05, "epoch": 0.12517259331356526, "percentage": 6.91, "elapsed_time": "2:09:49", "remaining_time": "1 day, 5:08:16", "throughput": 581.3, "total_tokens": 4527968} {"current_steps": 2770, "total_steps": 40000, "loss": 0.1636, "lr": 4.9411124741632956e-05, "epoch": 0.12539894520020825, "percentage": 6.93, "elapsed_time": "2:09:52", "remaining_time": "1 day, 5:05:36", "throughput": 582.14, "total_tokens": 4536352} {"current_steps": 2775, "total_steps": 40000, "loss": 0.1669, "lr": 4.940900457678431e-05, "epoch": 0.12562529708685122, "percentage": 6.94, "elapsed_time": "2:09:55", "remaining_time": "1 day, 5:02:54", "throughput": 582.9, "total_tokens": 4544128} {"current_steps": 2780, "total_steps": 40000, "loss": 0.2742, "lr": 4.9406880647760425e-05, "epoch": 0.12585164897349418, "percentage": 6.95, "elapsed_time": "2:09:58", "remaining_time": "1 day, 5:00:14", "throughput": 583.64, "total_tokens": 4551680} {"current_steps": 2785, "total_steps": 40000, "loss": 0.1676, "lr": 4.9404752954888824e-05, "epoch": 0.12607800086013718, "percentage": 6.96, "elapsed_time": "2:10:01", "remaining_time": "1 day, 4:57:34", "throughput": 584.46, "total_tokens": 4559904} {"current_steps": 2790, "total_steps": 40000, "loss": 0.1456, "lr": 4.940262149849762e-05, "epoch": 0.12630435274678015, "percentage": 6.98, "elapsed_time": "2:10:05", "remaining_time": "1 day, 4:54:55", "throughput": 585.26, "total_tokens": 4568000} {"current_steps": 2795, "total_steps": 40000, "loss": 0.1927, "lr": 4.9400486278915526e-05, "epoch": 0.1265307046334231, "percentage": 6.99, "elapsed_time": "2:10:08", "remaining_time": "1 day, 4:52:17", "throughput": 586.03, "total_tokens": 4575840} {"current_steps": 2800, "total_steps": 40000, "loss": 0.1453, "lr": 4.939834729647181e-05, "epoch": 0.1267570565200661, "percentage": 7.0, "elapsed_time": "2:10:11", "remaining_time": "1 day, 4:49:40", "throughput": 586.87, "total_tokens": 4584288} {"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.1804143786430359, "epoch": 0.1267570565200661, "percentage": 7.0, "elapsed_time": "2:17:54", "remaining_time": "1 day, 6:32:07", "throughput": 554.05, "total_tokens": 4584288} {"current_steps": 2805, "total_steps": 40000, "loss": 0.1828, "lr": 4.9396204551496326e-05, "epoch": 0.12698340840670908, "percentage": 7.01, "elapsed_time": "2:17:58", "remaining_time": "1 day, 6:29:30", "throughput": 554.76, "total_tokens": 4592352} {"current_steps": 2810, "total_steps": 40000, "loss": 0.1625, "lr": 4.939405804431952e-05, "epoch": 0.12720976029335204, "percentage": 7.03, "elapsed_time": "2:18:01", "remaining_time": "1 day, 6:26:41", "throughput": 555.53, "total_tokens": 4600480} {"current_steps": 2815, "total_steps": 40000, "loss": 0.1857, "lr": 4.9391907775272414e-05, "epoch": 0.127436112179995, "percentage": 7.04, "elapsed_time": "2:18:04", "remaining_time": "1 day, 6:23:53", "throughput": 556.26, "total_tokens": 4608320} {"current_steps": 2820, "total_steps": 40000, "loss": 0.1343, "lr": 4.9389753744686604e-05, "epoch": 0.127662464066638, "percentage": 7.05, "elapsed_time": "2:18:07", "remaining_time": "1 day, 6:21:05", "throughput": 556.98, "total_tokens": 4615968} {"current_steps": 2825, "total_steps": 40000, "loss": 0.2295, "lr": 4.938759595289426e-05, "epoch": 0.12788881595328097, "percentage": 7.06, "elapsed_time": "2:18:10", "remaining_time": "1 day, 6:18:20", "throughput": 557.8, "total_tokens": 4624544} {"current_steps": 2830, "total_steps": 40000, "loss": 0.2094, "lr": 4.938543440022815e-05, "epoch": 0.12811516783992394, "percentage": 7.07, "elapsed_time": "2:18:13", "remaining_time": "1 day, 6:15:34", "throughput": 558.59, "total_tokens": 4632864} {"current_steps": 2835, "total_steps": 40000, "loss": 0.1844, "lr": 4.938326908702161e-05, "epoch": 0.12834151972656693, "percentage": 7.09, "elapsed_time": "2:18:17", "remaining_time": "1 day, 6:12:48", "throughput": 559.3, "total_tokens": 4640512} {"current_steps": 2840, "total_steps": 40000, "loss": 0.1687, "lr": 4.9381100013608554e-05, "epoch": 0.1285678716132099, "percentage": 7.1, "elapsed_time": "2:18:20", "remaining_time": "1 day, 6:10:02", "throughput": 560.01, "total_tokens": 4648128} {"current_steps": 2845, "total_steps": 40000, "loss": 0.1678, "lr": 4.9378927180323485e-05, "epoch": 0.12879422349985287, "percentage": 7.11, "elapsed_time": "2:18:23", "remaining_time": "1 day, 6:07:19", "throughput": 560.81, "total_tokens": 4656544} {"current_steps": 2850, "total_steps": 40000, "loss": 0.1815, "lr": 4.937675058750148e-05, "epoch": 0.12902057538649583, "percentage": 7.12, "elapsed_time": "2:18:26", "remaining_time": "1 day, 6:04:35", "throughput": 561.55, "total_tokens": 4664512} {"current_steps": 2855, "total_steps": 40000, "loss": 0.1867, "lr": 4.937457023547819e-05, "epoch": 0.12924692727313883, "percentage": 7.14, "elapsed_time": "2:18:29", "remaining_time": "1 day, 6:01:54", "throughput": 562.42, "total_tokens": 4673568} {"current_steps": 2860, "total_steps": 40000, "loss": 0.1939, "lr": 4.9372386124589876e-05, "epoch": 0.1294732791597818, "percentage": 7.15, "elapsed_time": "2:18:32", "remaining_time": "1 day, 5:59:11", "throughput": 563.17, "total_tokens": 4681568} {"current_steps": 2865, "total_steps": 40000, "loss": 0.1755, "lr": 4.937019825517333e-05, "epoch": 0.12969963104642476, "percentage": 7.16, "elapsed_time": "2:18:35", "remaining_time": "1 day, 5:56:28", "throughput": 563.89, "total_tokens": 4689312} {"current_steps": 2870, "total_steps": 40000, "loss": 0.1594, "lr": 4.9368006627565954e-05, "epoch": 0.12992598293306776, "percentage": 7.17, "elapsed_time": "2:18:39", "remaining_time": "1 day, 5:53:47", "throughput": 564.65, "total_tokens": 4697472} {"current_steps": 2875, "total_steps": 40000, "loss": 0.1564, "lr": 4.936581124210573e-05, "epoch": 0.13015233481971072, "percentage": 7.19, "elapsed_time": "2:18:42", "remaining_time": "1 day, 5:51:06", "throughput": 565.38, "total_tokens": 4705280} {"current_steps": 2880, "total_steps": 40000, "loss": 0.1995, "lr": 4.9363612099131216e-05, "epoch": 0.1303786867063537, "percentage": 7.2, "elapsed_time": "2:18:45", "remaining_time": "1 day, 5:48:26", "throughput": 566.13, "total_tokens": 4713344} {"current_steps": 2885, "total_steps": 40000, "loss": 0.1653, "lr": 4.936140919898155e-05, "epoch": 0.1306050385929967, "percentage": 7.21, "elapsed_time": "2:18:48", "remaining_time": "1 day, 5:45:47", "throughput": 566.93, "total_tokens": 4721824} {"current_steps": 2890, "total_steps": 40000, "loss": 0.1497, "lr": 4.9359202541996426e-05, "epoch": 0.13083139047963965, "percentage": 7.22, "elapsed_time": "2:18:51", "remaining_time": "1 day, 5:43:08", "throughput": 567.7, "total_tokens": 4730016} {"current_steps": 2895, "total_steps": 40000, "loss": 0.19, "lr": 4.935699212851616e-05, "epoch": 0.13105774236628262, "percentage": 7.24, "elapsed_time": "2:18:54", "remaining_time": "1 day, 5:40:29", "throughput": 568.4, "total_tokens": 4737600} {"current_steps": 2900, "total_steps": 40000, "loss": 0.191, "lr": 4.935477795888162e-05, "epoch": 0.1312840942529256, "percentage": 7.25, "elapsed_time": "2:18:58", "remaining_time": "1 day, 5:37:50", "throughput": 569.13, "total_tokens": 4745472} {"current_steps": 2905, "total_steps": 40000, "loss": 0.1916, "lr": 4.935256003343426e-05, "epoch": 0.13151044613956858, "percentage": 7.26, "elapsed_time": "2:19:01", "remaining_time": "1 day, 5:35:13", "throughput": 569.91, "total_tokens": 4753792} {"current_steps": 2910, "total_steps": 40000, "loss": 0.223, "lr": 4.93503383525161e-05, "epoch": 0.13173679802621155, "percentage": 7.27, "elapsed_time": "2:19:04", "remaining_time": "1 day, 5:32:36", "throughput": 570.64, "total_tokens": 4761696} {"current_steps": 2915, "total_steps": 40000, "loss": 0.1721, "lr": 4.934811291646977e-05, "epoch": 0.13196314991285452, "percentage": 7.29, "elapsed_time": "2:19:07", "remaining_time": "1 day, 5:30:00", "throughput": 571.45, "total_tokens": 4770304} {"current_steps": 2920, "total_steps": 40000, "loss": 0.1561, "lr": 4.934588372563845e-05, "epoch": 0.1321895017994975, "percentage": 7.3, "elapsed_time": "2:19:10", "remaining_time": "1 day, 5:27:25", "throughput": 572.2, "total_tokens": 4778432} {"current_steps": 2925, "total_steps": 40000, "loss": 0.1696, "lr": 4.93436507803659e-05, "epoch": 0.13241585368614048, "percentage": 7.31, "elapsed_time": "2:19:14", "remaining_time": "1 day, 5:24:51", "throughput": 573.03, "total_tokens": 4787264} {"current_steps": 2930, "total_steps": 40000, "loss": 0.1533, "lr": 4.934141408099649e-05, "epoch": 0.13264220557278344, "percentage": 7.32, "elapsed_time": "2:19:17", "remaining_time": "1 day, 5:22:16", "throughput": 573.73, "total_tokens": 4794848} {"current_steps": 2935, "total_steps": 40000, "loss": 0.2072, "lr": 4.9339173627875135e-05, "epoch": 0.1328685574594264, "percentage": 7.34, "elapsed_time": "2:19:20", "remaining_time": "1 day, 5:19:41", "throughput": 574.48, "total_tokens": 4802944} {"current_steps": 2940, "total_steps": 40000, "loss": 0.1615, "lr": 4.9336929421347335e-05, "epoch": 0.1330949093460694, "percentage": 7.35, "elapsed_time": "2:19:23", "remaining_time": "1 day, 5:17:08", "throughput": 575.26, "total_tokens": 4811328} {"current_steps": 2945, "total_steps": 40000, "loss": 0.1833, "lr": 4.933468146175918e-05, "epoch": 0.13332126123271237, "percentage": 7.36, "elapsed_time": "2:19:26", "remaining_time": "1 day, 5:14:36", "throughput": 576.04, "total_tokens": 4819712} {"current_steps": 2950, "total_steps": 40000, "loss": 0.168, "lr": 4.933242974945734e-05, "epoch": 0.13354761311935534, "percentage": 7.38, "elapsed_time": "2:19:30", "remaining_time": "1 day, 5:12:03", "throughput": 576.79, "total_tokens": 4827776} {"current_steps": 2955, "total_steps": 40000, "loss": 0.1891, "lr": 4.933017428478906e-05, "epoch": 0.13377396500599834, "percentage": 7.39, "elapsed_time": "2:19:33", "remaining_time": "1 day, 5:09:31", "throughput": 577.55, "total_tokens": 4836032} {"current_steps": 2960, "total_steps": 40000, "loss": 0.2368, "lr": 4.932791506810214e-05, "epoch": 0.1340003168926413, "percentage": 7.4, "elapsed_time": "2:19:36", "remaining_time": "1 day, 5:07:02", "throughput": 578.37, "total_tokens": 4844800} {"current_steps": 2965, "total_steps": 40000, "loss": 0.2137, "lr": 4.932565209974499e-05, "epoch": 0.13422666877928427, "percentage": 7.41, "elapsed_time": "2:19:40", "remaining_time": "1 day, 5:04:33", "throughput": 579.21, "total_tokens": 4853888} {"current_steps": 2970, "total_steps": 40000, "loss": 0.147, "lr": 4.93233853800666e-05, "epoch": 0.13445302066592726, "percentage": 7.42, "elapsed_time": "2:19:43", "remaining_time": "1 day, 5:02:02", "throughput": 579.95, "total_tokens": 4861856} {"current_steps": 2975, "total_steps": 40000, "loss": 0.1786, "lr": 4.932111490941651e-05, "epoch": 0.13467937255257023, "percentage": 7.44, "elapsed_time": "2:19:46", "remaining_time": "1 day, 4:59:31", "throughput": 580.62, "total_tokens": 4869312} {"current_steps": 2980, "total_steps": 40000, "loss": 0.1691, "lr": 4.9318840688144876e-05, "epoch": 0.1349057244392132, "percentage": 7.45, "elapsed_time": "2:19:49", "remaining_time": "1 day, 4:57:02", "throughput": 581.4, "total_tokens": 4877696} {"current_steps": 2985, "total_steps": 40000, "loss": 0.1449, "lr": 4.9316562716602387e-05, "epoch": 0.13513207632585617, "percentage": 7.46, "elapsed_time": "2:19:52", "remaining_time": "1 day, 4:54:33", "throughput": 582.14, "total_tokens": 4885824} {"current_steps": 2990, "total_steps": 40000, "loss": 0.1643, "lr": 4.9314280995140346e-05, "epoch": 0.13535842821249916, "percentage": 7.47, "elapsed_time": "2:19:55", "remaining_time": "1 day, 4:52:04", "throughput": 582.87, "total_tokens": 4893760} {"current_steps": 2995, "total_steps": 40000, "loss": 0.1386, "lr": 4.931199552411063e-05, "epoch": 0.13558478009914213, "percentage": 7.49, "elapsed_time": "2:19:59", "remaining_time": "1 day, 4:49:35", "throughput": 583.57, "total_tokens": 4901440} {"current_steps": 3000, "total_steps": 40000, "loss": 0.1463, "lr": 4.930970630386568e-05, "epoch": 0.1358111319857851, "percentage": 7.5, "elapsed_time": "2:20:02", "remaining_time": "1 day, 4:47:08", "throughput": 584.35, "total_tokens": 4909888} {"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.17821675539016724, "epoch": 0.1358111319857851, "percentage": 7.5, "elapsed_time": "2:27:44", "remaining_time": "1 day, 6:22:13", "throughput": 553.86, "total_tokens": 4909888} {"current_steps": 3005, "total_steps": 40000, "loss": 0.144, "lr": 4.9307413334758524e-05, "epoch": 0.1360374838724281, "percentage": 7.51, "elapsed_time": "2:27:48", "remaining_time": "1 day, 6:19:45", "throughput": 554.57, "total_tokens": 4918400} {"current_steps": 3010, "total_steps": 40000, "loss": 0.1579, "lr": 4.930511661714276e-05, "epoch": 0.13626383575907106, "percentage": 7.52, "elapsed_time": "2:27:52", "remaining_time": "1 day, 6:17:09", "throughput": 555.3, "total_tokens": 4926688} {"current_steps": 3015, "total_steps": 40000, "loss": 0.1715, "lr": 4.9302816151372576e-05, "epoch": 0.13649018764571402, "percentage": 7.54, "elapsed_time": "2:27:55", "remaining_time": "1 day, 6:14:33", "throughput": 556.04, "total_tokens": 4935008} {"current_steps": 3020, "total_steps": 40000, "loss": 0.2154, "lr": 4.930051193780274e-05, "epoch": 0.136716539532357, "percentage": 7.55, "elapsed_time": "2:27:58", "remaining_time": "1 day, 6:11:57", "throughput": 556.77, "total_tokens": 4943296} {"current_steps": 3025, "total_steps": 40000, "loss": 0.1842, "lr": 4.929820397678858e-05, "epoch": 0.13694289141899998, "percentage": 7.56, "elapsed_time": "2:28:01", "remaining_time": "1 day, 6:09:20", "throughput": 557.45, "total_tokens": 4951040} {"current_steps": 3030, "total_steps": 40000, "loss": 0.1935, "lr": 4.9295892268686015e-05, "epoch": 0.13716924330564295, "percentage": 7.58, "elapsed_time": "2:28:04", "remaining_time": "1 day, 6:06:47", "throughput": 558.24, "total_tokens": 4959904} {"current_steps": 3035, "total_steps": 40000, "loss": 0.2238, "lr": 4.9293576813851536e-05, "epoch": 0.13739559519228592, "percentage": 7.59, "elapsed_time": "2:28:08", "remaining_time": "1 day, 6:04:15", "throughput": 559.04, "total_tokens": 4968896} {"current_steps": 3040, "total_steps": 40000, "loss": 0.139, "lr": 4.929125761264223e-05, "epoch": 0.1376219470789289, "percentage": 7.6, "elapsed_time": "2:28:11", "remaining_time": "1 day, 6:01:43", "throughput": 559.84, "total_tokens": 4977824} {"current_steps": 3045, "total_steps": 40000, "loss": 0.1472, "lr": 4.928893466541573e-05, "epoch": 0.13784829896557188, "percentage": 7.61, "elapsed_time": "2:28:14", "remaining_time": "1 day, 5:59:08", "throughput": 560.53, "total_tokens": 4985760} {"current_steps": 3050, "total_steps": 40000, "loss": 0.1972, "lr": 4.928660797253027e-05, "epoch": 0.13807465085221485, "percentage": 7.62, "elapsed_time": "2:28:18", "remaining_time": "1 day, 5:56:37", "throughput": 561.3, "total_tokens": 4994496} {"current_steps": 3055, "total_steps": 40000, "loss": 0.1606, "lr": 4.928427753434467e-05, "epoch": 0.13830100273885784, "percentage": 7.64, "elapsed_time": "2:28:21", "remaining_time": "1 day, 5:54:04", "throughput": 561.99, "total_tokens": 5002400} {"current_steps": 3060, "total_steps": 40000, "loss": 0.171, "lr": 4.9281943351218286e-05, "epoch": 0.1385273546255008, "percentage": 7.65, "elapsed_time": "2:28:24", "remaining_time": "1 day, 5:51:33", "throughput": 562.74, "total_tokens": 5010848} {"current_steps": 3065, "total_steps": 40000, "loss": 0.1283, "lr": 4.9279605423511095e-05, "epoch": 0.13875370651214378, "percentage": 7.66, "elapsed_time": "2:28:27", "remaining_time": "1 day, 5:49:01", "throughput": 563.48, "total_tokens": 5019296} {"current_steps": 3070, "total_steps": 40000, "loss": 0.1891, "lr": 4.927726375158363e-05, "epoch": 0.13898005839878674, "percentage": 7.67, "elapsed_time": "2:28:30", "remaining_time": "1 day, 5:46:30", "throughput": 564.17, "total_tokens": 5027168} {"current_steps": 3075, "total_steps": 40000, "loss": 0.1604, "lr": 4.9274918335797004e-05, "epoch": 0.13920641028542974, "percentage": 7.69, "elapsed_time": "2:28:33", "remaining_time": "1 day, 5:43:59", "throughput": 564.9, "total_tokens": 5035488} {"current_steps": 3080, "total_steps": 40000, "loss": 0.1941, "lr": 4.927256917651292e-05, "epoch": 0.1394327621720727, "percentage": 7.7, "elapsed_time": "2:28:37", "remaining_time": "1 day, 5:41:30", "throughput": 565.68, "total_tokens": 5044320} {"current_steps": 3085, "total_steps": 40000, "loss": 0.1981, "lr": 4.927021627409364e-05, "epoch": 0.13965911405871567, "percentage": 7.71, "elapsed_time": "2:28:40", "remaining_time": "1 day, 5:38:59", "throughput": 566.34, "total_tokens": 5051936} {"current_steps": 3090, "total_steps": 40000, "loss": 0.1853, "lr": 4.9267859628902005e-05, "epoch": 0.13988546594535867, "percentage": 7.72, "elapsed_time": "2:28:43", "remaining_time": "1 day, 5:36:31", "throughput": 567.08, "total_tokens": 5060352} {"current_steps": 3095, "total_steps": 40000, "loss": 0.1475, "lr": 4.9265499241301454e-05, "epoch": 0.14011181783200163, "percentage": 7.74, "elapsed_time": "2:28:46", "remaining_time": "1 day, 5:34:02", "throughput": 567.78, "total_tokens": 5068352} {"current_steps": 3100, "total_steps": 40000, "loss": 0.197, "lr": 4.926313511165598e-05, "epoch": 0.1403381697186446, "percentage": 7.75, "elapsed_time": "2:28:49", "remaining_time": "1 day, 5:31:33", "throughput": 568.48, "total_tokens": 5076448} {"current_steps": 3105, "total_steps": 40000, "loss": 0.1945, "lr": 4.926076724033016e-05, "epoch": 0.14056452160528757, "percentage": 7.76, "elapsed_time": "2:28:53", "remaining_time": "1 day, 5:29:06", "throughput": 569.19, "total_tokens": 5084608} {"current_steps": 3110, "total_steps": 40000, "loss": 0.1768, "lr": 4.9258395627689146e-05, "epoch": 0.14079087349193056, "percentage": 7.78, "elapsed_time": "2:28:56", "remaining_time": "1 day, 5:26:38", "throughput": 569.85, "total_tokens": 5092288} {"current_steps": 3115, "total_steps": 40000, "loss": 0.1307, "lr": 4.925602027409868e-05, "epoch": 0.14101722537857353, "percentage": 7.79, "elapsed_time": "2:28:59", "remaining_time": "1 day, 5:24:10", "throughput": 570.49, "total_tokens": 5099776} {"current_steps": 3120, "total_steps": 40000, "loss": 0.1638, "lr": 4.925364117992507e-05, "epoch": 0.1412435772652165, "percentage": 7.8, "elapsed_time": "2:29:02", "remaining_time": "1 day, 5:21:43", "throughput": 571.19, "total_tokens": 5107808} {"current_steps": 3125, "total_steps": 40000, "loss": 0.1595, "lr": 4.92512583455352e-05, "epoch": 0.1414699291518595, "percentage": 7.81, "elapsed_time": "2:29:05", "remaining_time": "1 day, 5:19:18", "throughput": 571.96, "total_tokens": 5116544} {"current_steps": 3130, "total_steps": 40000, "loss": 0.1599, "lr": 4.9248871771296536e-05, "epoch": 0.14169628103850246, "percentage": 7.83, "elapsed_time": "2:29:08", "remaining_time": "1 day, 5:16:52", "throughput": 572.65, "total_tokens": 5124512} {"current_steps": 3135, "total_steps": 40000, "loss": 0.1246, "lr": 4.924648145757711e-05, "epoch": 0.14192263292514543, "percentage": 7.84, "elapsed_time": "2:29:11", "remaining_time": "1 day, 5:14:27", "throughput": 573.32, "total_tokens": 5132320} {"current_steps": 3140, "total_steps": 40000, "loss": 0.19, "lr": 4.924408740474554e-05, "epoch": 0.1421489848117884, "percentage": 7.85, "elapsed_time": "2:29:15", "remaining_time": "1 day, 5:12:02", "throughput": 574.03, "total_tokens": 5140512} {"current_steps": 3145, "total_steps": 40000, "loss": 0.1748, "lr": 4.924168961317103e-05, "epoch": 0.1423753366984314, "percentage": 7.86, "elapsed_time": "2:29:18", "remaining_time": "1 day, 5:09:37", "throughput": 574.68, "total_tokens": 5148096} {"current_steps": 3150, "total_steps": 40000, "loss": 0.1753, "lr": 4.9239288083223334e-05, "epoch": 0.14260168858507435, "percentage": 7.88, "elapsed_time": "2:29:21", "remaining_time": "1 day, 5:07:13", "throughput": 575.38, "total_tokens": 5156192} {"current_steps": 3155, "total_steps": 40000, "loss": 0.1435, "lr": 4.9236882815272803e-05, "epoch": 0.14282804047171732, "percentage": 7.89, "elapsed_time": "2:29:24", "remaining_time": "1 day, 5:04:54", "throughput": 576.15, "total_tokens": 5165120} {"current_steps": 3160, "total_steps": 40000, "loss": 0.1548, "lr": 4.9234473809690365e-05, "epoch": 0.14305439235836032, "percentage": 7.9, "elapsed_time": "2:29:27", "remaining_time": "1 day, 5:02:30", "throughput": 576.8, "total_tokens": 5172768} {"current_steps": 3165, "total_steps": 40000, "loss": 0.1315, "lr": 4.923206106684752e-05, "epoch": 0.14328074424500328, "percentage": 7.91, "elapsed_time": "2:29:31", "remaining_time": "1 day, 5:00:08", "throughput": 577.5, "total_tokens": 5180864} {"current_steps": 3170, "total_steps": 40000, "loss": 0.193, "lr": 4.922964458711634e-05, "epoch": 0.14350709613164625, "percentage": 7.92, "elapsed_time": "2:29:34", "remaining_time": "1 day, 4:57:46", "throughput": 578.21, "total_tokens": 5189056} {"current_steps": 3175, "total_steps": 40000, "loss": 0.1427, "lr": 4.9227224370869474e-05, "epoch": 0.14373344801828924, "percentage": 7.94, "elapsed_time": "2:29:37", "remaining_time": "1 day, 4:55:25", "throughput": 578.97, "total_tokens": 5197760} {"current_steps": 3180, "total_steps": 40000, "loss": 0.1601, "lr": 4.9224800418480155e-05, "epoch": 0.1439597999049322, "percentage": 7.95, "elapsed_time": "2:29:40", "remaining_time": "1 day, 4:53:03", "throughput": 579.64, "total_tokens": 5205568} {"current_steps": 3185, "total_steps": 40000, "loss": 0.1531, "lr": 4.9222372730322176e-05, "epoch": 0.14418615179157518, "percentage": 7.96, "elapsed_time": "2:29:43", "remaining_time": "1 day, 4:50:43", "throughput": 580.34, "total_tokens": 5213696} {"current_steps": 3190, "total_steps": 40000, "loss": 0.1806, "lr": 4.921994130676993e-05, "epoch": 0.14441250367821815, "percentage": 7.98, "elapsed_time": "2:29:46", "remaining_time": "1 day, 4:48:21", "throughput": 581.0, "total_tokens": 5221440} {"current_steps": 3195, "total_steps": 40000, "loss": 0.1246, "lr": 4.9217506148198366e-05, "epoch": 0.14463885556486114, "percentage": 7.99, "elapsed_time": "2:29:50", "remaining_time": "1 day, 4:46:02", "throughput": 581.74, "total_tokens": 5229920} {"current_steps": 3200, "total_steps": 40000, "loss": 0.1461, "lr": 4.921506725498302e-05, "epoch": 0.1448652074515041, "percentage": 8.0, "elapsed_time": "2:29:53", "remaining_time": "1 day, 4:43:43", "throughput": 582.45, "total_tokens": 5238176} {"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.17492890357971191, "epoch": 0.1448652074515041, "percentage": 8.0, "elapsed_time": "2:37:35", "remaining_time": "1 day, 6:12:23", "throughput": 553.95, "total_tokens": 5238176} {"current_steps": 3205, "total_steps": 40000, "loss": 0.2002, "lr": 4.9212624627499994e-05, "epoch": 0.14509155933814707, "percentage": 8.01, "elapsed_time": "2:37:39", "remaining_time": "1 day, 6:10:03", "throughput": 554.56, "total_tokens": 5246048} {"current_steps": 3210, "total_steps": 40000, "loss": 0.201, "lr": 4.921017826612597e-05, "epoch": 0.14531791122479007, "percentage": 8.03, "elapsed_time": "2:37:43", "remaining_time": "1 day, 6:07:36", "throughput": 555.24, "total_tokens": 5254304} {"current_steps": 3215, "total_steps": 40000, "loss": 0.1985, "lr": 4.9207728171238223e-05, "epoch": 0.14554426311143304, "percentage": 8.04, "elapsed_time": "2:37:46", "remaining_time": "1 day, 6:05:09", "throughput": 555.94, "total_tokens": 5262624} {"current_steps": 3220, "total_steps": 40000, "loss": 0.2095, "lr": 4.920527434321458e-05, "epoch": 0.145770614998076, "percentage": 8.05, "elapsed_time": "2:37:49", "remaining_time": "1 day, 6:02:43", "throughput": 556.62, "total_tokens": 5270880} {"current_steps": 3225, "total_steps": 40000, "loss": 0.1676, "lr": 4.920281678243345e-05, "epoch": 0.14599696688471897, "percentage": 8.06, "elapsed_time": "2:37:52", "remaining_time": "1 day, 6:00:16", "throughput": 557.26, "total_tokens": 5278656} {"current_steps": 3230, "total_steps": 40000, "loss": 0.2038, "lr": 4.920035548927381e-05, "epoch": 0.14622331877136197, "percentage": 8.08, "elapsed_time": "2:37:55", "remaining_time": "1 day, 5:57:49", "throughput": 557.87, "total_tokens": 5286208} {"current_steps": 3235, "total_steps": 40000, "loss": 0.1541, "lr": 4.919789046411525e-05, "epoch": 0.14644967065800493, "percentage": 8.09, "elapsed_time": "2:37:58", "remaining_time": "1 day, 5:55:24", "throughput": 558.56, "total_tokens": 5294528} {"current_steps": 3240, "total_steps": 40000, "loss": 0.1808, "lr": 4.919542170733787e-05, "epoch": 0.1466760225446479, "percentage": 8.1, "elapsed_time": "2:38:01", "remaining_time": "1 day, 5:52:59", "throughput": 559.19, "total_tokens": 5302208} {"current_steps": 3245, "total_steps": 40000, "loss": 0.1672, "lr": 4.919294921932242e-05, "epoch": 0.1469023744312909, "percentage": 8.11, "elapsed_time": "2:38:05", "remaining_time": "1 day, 5:50:38", "throughput": 559.97, "total_tokens": 5311520} {"current_steps": 3250, "total_steps": 40000, "loss": 0.1442, "lr": 4.919047300045016e-05, "epoch": 0.14712872631793386, "percentage": 8.12, "elapsed_time": "2:38:08", "remaining_time": "1 day, 5:48:13", "throughput": 560.59, "total_tokens": 5319136} {"current_steps": 3255, "total_steps": 40000, "loss": 0.1197, "lr": 4.918799305110299e-05, "epoch": 0.14735507820457683, "percentage": 8.14, "elapsed_time": "2:38:11", "remaining_time": "1 day, 5:45:50", "throughput": 561.28, "total_tokens": 5327552} {"current_steps": 3260, "total_steps": 40000, "loss": 0.1392, "lr": 4.918550937166331e-05, "epoch": 0.14758143009121982, "percentage": 8.15, "elapsed_time": "2:38:14", "remaining_time": "1 day, 5:43:26", "throughput": 561.96, "total_tokens": 5335712} {"current_steps": 3265, "total_steps": 40000, "loss": 0.1631, "lr": 4.918302196251415e-05, "epoch": 0.1478077819778628, "percentage": 8.16, "elapsed_time": "2:38:17", "remaining_time": "1 day, 5:41:03", "throughput": 562.58, "total_tokens": 5343360} {"current_steps": 3270, "total_steps": 40000, "loss": 0.2018, "lr": 4.91805308240391e-05, "epoch": 0.14803413386450576, "percentage": 8.18, "elapsed_time": "2:38:21", "remaining_time": "1 day, 5:38:42", "throughput": 563.32, "total_tokens": 5352256} {"current_steps": 3275, "total_steps": 40000, "loss": 0.1947, "lr": 4.9178035956622326e-05, "epoch": 0.14826048575114872, "percentage": 8.19, "elapsed_time": "2:38:24", "remaining_time": "1 day, 5:36:20", "throughput": 564.03, "total_tokens": 5360800} {"current_steps": 3280, "total_steps": 40000, "loss": 0.191, "lr": 4.917553736064857e-05, "epoch": 0.14848683763779172, "percentage": 8.2, "elapsed_time": "2:38:27", "remaining_time": "1 day, 5:33:59", "throughput": 564.71, "total_tokens": 5369024} {"current_steps": 3285, "total_steps": 40000, "loss": 0.1809, "lr": 4.917303503650314e-05, "epoch": 0.14871318952443469, "percentage": 8.21, "elapsed_time": "2:38:30", "remaining_time": "1 day, 5:31:38", "throughput": 565.41, "total_tokens": 5377504} {"current_steps": 3290, "total_steps": 40000, "loss": 0.1942, "lr": 4.917052898457194e-05, "epoch": 0.14893954141107765, "percentage": 8.22, "elapsed_time": "2:38:34", "remaining_time": "1 day, 5:29:18", "throughput": 566.11, "total_tokens": 5386016} {"current_steps": 3295, "total_steps": 40000, "loss": 0.1517, "lr": 4.916801920524141e-05, "epoch": 0.14916589329772065, "percentage": 8.24, "elapsed_time": "2:38:37", "remaining_time": "1 day, 5:26:59", "throughput": 566.79, "total_tokens": 5394368} {"current_steps": 3300, "total_steps": 40000, "loss": 0.1368, "lr": 4.916550569889862e-05, "epoch": 0.14939224518436361, "percentage": 8.25, "elapsed_time": "2:38:40", "remaining_time": "1 day, 5:24:39", "throughput": 567.44, "total_tokens": 5402304} {"current_steps": 3305, "total_steps": 40000, "loss": 0.1887, "lr": 4.916298846593116e-05, "epoch": 0.14961859707100658, "percentage": 8.26, "elapsed_time": "2:38:43", "remaining_time": "1 day, 5:22:20", "throughput": 568.15, "total_tokens": 5410912} {"current_steps": 3310, "total_steps": 40000, "loss": 0.1436, "lr": 4.916046750672722e-05, "epoch": 0.14984494895764955, "percentage": 8.28, "elapsed_time": "2:38:46", "remaining_time": "1 day, 5:20:00", "throughput": 568.77, "total_tokens": 5418560} {"current_steps": 3315, "total_steps": 40000, "loss": 0.1549, "lr": 4.915794282167559e-05, "epoch": 0.15007130084429254, "percentage": 8.29, "elapsed_time": "2:38:50", "remaining_time": "1 day, 5:17:42", "throughput": 569.43, "total_tokens": 5426688} {"current_steps": 3320, "total_steps": 40000, "loss": 0.2009, "lr": 4.915541441116558e-05, "epoch": 0.1502976527309355, "percentage": 8.3, "elapsed_time": "2:38:53", "remaining_time": "1 day, 5:15:25", "throughput": 570.14, "total_tokens": 5435264} {"current_steps": 3325, "total_steps": 40000, "loss": 0.161, "lr": 4.915288227558711e-05, "epoch": 0.15052400461757848, "percentage": 8.31, "elapsed_time": "2:38:56", "remaining_time": "1 day, 5:13:07", "throughput": 570.83, "total_tokens": 5443712} {"current_steps": 3330, "total_steps": 40000, "loss": 0.1907, "lr": 4.915034641533066e-05, "epoch": 0.15075035650422147, "percentage": 8.33, "elapsed_time": "2:38:59", "remaining_time": "1 day, 5:10:49", "throughput": 571.45, "total_tokens": 5451424} {"current_steps": 3335, "total_steps": 40000, "loss": 0.2268, "lr": 4.914780683078731e-05, "epoch": 0.15097670839086444, "percentage": 8.34, "elapsed_time": "2:39:02", "remaining_time": "1 day, 5:08:33", "throughput": 572.13, "total_tokens": 5459776} {"current_steps": 3340, "total_steps": 40000, "loss": 0.171, "lr": 4.9145263522348695e-05, "epoch": 0.1512030602775074, "percentage": 8.35, "elapsed_time": "2:39:06", "remaining_time": "1 day, 5:06:17", "throughput": 572.81, "total_tokens": 5468000} {"current_steps": 3345, "total_steps": 40000, "loss": 0.1513, "lr": 4.9142716490407e-05, "epoch": 0.1514294121641504, "percentage": 8.36, "elapsed_time": "2:39:09", "remaining_time": "1 day, 5:04:01", "throughput": 573.44, "total_tokens": 5475904} {"current_steps": 3350, "total_steps": 40000, "loss": 0.1194, "lr": 4.914016573535504e-05, "epoch": 0.15165576405079337, "percentage": 8.38, "elapsed_time": "2:39:12", "remaining_time": "1 day, 5:01:44", "throughput": 574.08, "total_tokens": 5483776} {"current_steps": 3355, "total_steps": 40000, "loss": 0.2255, "lr": 4.9137611257586154e-05, "epoch": 0.15188211593743633, "percentage": 8.39, "elapsed_time": "2:39:15", "remaining_time": "1 day, 4:59:29", "throughput": 574.73, "total_tokens": 5491776} {"current_steps": 3360, "total_steps": 40000, "loss": 0.1924, "lr": 4.9135053057494274e-05, "epoch": 0.1521084678240793, "percentage": 8.4, "elapsed_time": "2:39:18", "remaining_time": "1 day, 4:57:12", "throughput": 575.31, "total_tokens": 5499104} {"current_steps": 3365, "total_steps": 40000, "loss": 0.2192, "lr": 4.913249113547392e-05, "epoch": 0.1523348197107223, "percentage": 8.41, "elapsed_time": "2:39:21", "remaining_time": "1 day, 4:54:58", "throughput": 575.97, "total_tokens": 5507200} {"current_steps": 3370, "total_steps": 40000, "loss": 0.2107, "lr": 4.912992549192016e-05, "epoch": 0.15256117159736526, "percentage": 8.43, "elapsed_time": "2:39:24", "remaining_time": "1 day, 4:52:43", "throughput": 576.62, "total_tokens": 5515264} {"current_steps": 3375, "total_steps": 40000, "loss": 0.1491, "lr": 4.9127356127228665e-05, "epoch": 0.15278752348400823, "percentage": 8.44, "elapsed_time": "2:39:27", "remaining_time": "1 day, 4:50:29", "throughput": 577.31, "total_tokens": 5523680} {"current_steps": 3380, "total_steps": 40000, "loss": 0.1508, "lr": 4.912478304179564e-05, "epoch": 0.15301387537065123, "percentage": 8.45, "elapsed_time": "2:39:31", "remaining_time": "1 day, 4:48:16", "throughput": 577.96, "total_tokens": 5531744} {"current_steps": 3385, "total_steps": 40000, "loss": 0.1941, "lr": 4.9122206236017896e-05, "epoch": 0.1532402272572942, "percentage": 8.46, "elapsed_time": "2:39:34", "remaining_time": "1 day, 4:46:03", "throughput": 578.67, "total_tokens": 5540384} {"current_steps": 3390, "total_steps": 40000, "loss": 0.1741, "lr": 4.911962571029282e-05, "epoch": 0.15346657914393716, "percentage": 8.48, "elapsed_time": "2:39:37", "remaining_time": "1 day, 4:43:50", "throughput": 579.31, "total_tokens": 5548288} {"current_steps": 3395, "total_steps": 40000, "loss": 0.1263, "lr": 4.9117041465018353e-05, "epoch": 0.15369293103058013, "percentage": 8.49, "elapsed_time": "2:39:40", "remaining_time": "1 day, 4:41:39", "throughput": 579.99, "total_tokens": 5556704} {"current_steps": 3400, "total_steps": 40000, "loss": 0.1924, "lr": 4.911445350059302e-05, "epoch": 0.15391928291722312, "percentage": 8.5, "elapsed_time": "2:39:43", "remaining_time": "1 day, 4:39:28", "throughput": 580.7, "total_tokens": 5565344} {"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.17381219565868378, "epoch": 0.15391928291722312, "percentage": 8.5, "elapsed_time": "2:47:26", "remaining_time": "1 day, 6:02:28", "throughput": 553.95, "total_tokens": 5565344} {"current_steps": 3405, "total_steps": 40000, "loss": 0.1942, "lr": 4.9111861817415905e-05, "epoch": 0.1541456348038661, "percentage": 8.51, "elapsed_time": "2:47:30", "remaining_time": "1 day, 6:00:19", "throughput": 554.5, "total_tokens": 5573120} {"current_steps": 3410, "total_steps": 40000, "loss": 0.1785, "lr": 4.91092664158867e-05, "epoch": 0.15437198669050906, "percentage": 8.53, "elapsed_time": "2:47:33", "remaining_time": "1 day, 5:58:00", "throughput": 555.16, "total_tokens": 5581504} {"current_steps": 3415, "total_steps": 40000, "loss": 0.1201, "lr": 4.910666729640563e-05, "epoch": 0.15459833857715205, "percentage": 8.54, "elapsed_time": "2:47:37", "remaining_time": "1 day, 5:55:41", "throughput": 555.75, "total_tokens": 5589152} {"current_steps": 3420, "total_steps": 40000, "loss": 0.1357, "lr": 4.910406445937353e-05, "epoch": 0.15482469046379502, "percentage": 8.55, "elapsed_time": "2:47:40", "remaining_time": "1 day, 5:53:22", "throughput": 556.37, "total_tokens": 5597184} {"current_steps": 3425, "total_steps": 40000, "loss": 0.1856, "lr": 4.9101457905191774e-05, "epoch": 0.15505104235043798, "percentage": 8.56, "elapsed_time": "2:47:43", "remaining_time": "1 day, 5:51:06", "throughput": 557.06, "total_tokens": 5605920} {"current_steps": 3430, "total_steps": 40000, "loss": 0.1494, "lr": 4.909884763426233e-05, "epoch": 0.15527739423708098, "percentage": 8.58, "elapsed_time": "2:47:46", "remaining_time": "1 day, 5:48:49", "throughput": 557.7, "total_tokens": 5614208} {"current_steps": 3435, "total_steps": 40000, "loss": 0.2076, "lr": 4.9096233646987736e-05, "epoch": 0.15550374612372395, "percentage": 8.59, "elapsed_time": "2:47:49", "remaining_time": "1 day, 5:46:31", "throughput": 558.31, "total_tokens": 5622112} {"current_steps": 3440, "total_steps": 40000, "loss": 0.2184, "lr": 4.9093615943771104e-05, "epoch": 0.1557300980103669, "percentage": 8.6, "elapsed_time": "2:47:53", "remaining_time": "1 day, 5:44:17", "throughput": 559.01, "total_tokens": 5631040} {"current_steps": 3445, "total_steps": 40000, "loss": 0.1404, "lr": 4.909099452501611e-05, "epoch": 0.15595644989700988, "percentage": 8.61, "elapsed_time": "2:47:56", "remaining_time": "1 day, 5:42:00", "throughput": 559.66, "total_tokens": 5639328} {"current_steps": 3450, "total_steps": 40000, "loss": 0.1886, "lr": 4.908836939112702e-05, "epoch": 0.15618280178365287, "percentage": 8.62, "elapsed_time": "2:47:59", "remaining_time": "1 day, 5:39:44", "throughput": 560.28, "total_tokens": 5647392} {"current_steps": 3455, "total_steps": 40000, "loss": 0.1951, "lr": 4.908574054250865e-05, "epoch": 0.15640915367029584, "percentage": 8.64, "elapsed_time": "2:48:02", "remaining_time": "1 day, 5:37:30", "throughput": 560.95, "total_tokens": 5655904} {"current_steps": 3460, "total_steps": 40000, "loss": 0.1355, "lr": 4.9083107979566414e-05, "epoch": 0.1566355055569388, "percentage": 8.65, "elapsed_time": "2:48:05", "remaining_time": "1 day, 5:35:15", "throughput": 561.59, "total_tokens": 5664160} {"current_steps": 3465, "total_steps": 40000, "loss": 0.1363, "lr": 4.908047170270628e-05, "epoch": 0.1568618574435818, "percentage": 8.66, "elapsed_time": "2:48:09", "remaining_time": "1 day, 5:33:00", "throughput": 562.18, "total_tokens": 5671968} {"current_steps": 3470, "total_steps": 40000, "loss": 0.1542, "lr": 4.9077831712334784e-05, "epoch": 0.15708820933022477, "percentage": 8.67, "elapsed_time": "2:48:12", "remaining_time": "1 day, 5:30:46", "throughput": 562.86, "total_tokens": 5680544} {"current_steps": 3475, "total_steps": 40000, "loss": 0.1386, "lr": 4.907518800885907e-05, "epoch": 0.15731456121686774, "percentage": 8.69, "elapsed_time": "2:48:15", "remaining_time": "1 day, 5:28:31", "throughput": 563.43, "total_tokens": 5688064} {"current_steps": 3480, "total_steps": 40000, "loss": 0.1739, "lr": 4.907254059268681e-05, "epoch": 0.1575409131035107, "percentage": 8.7, "elapsed_time": "2:48:18", "remaining_time": "1 day, 5:26:17", "throughput": 564.03, "total_tokens": 5695872} {"current_steps": 3485, "total_steps": 40000, "loss": 0.148, "lr": 4.906988946422628e-05, "epoch": 0.1577672649901537, "percentage": 8.71, "elapsed_time": "2:48:21", "remaining_time": "1 day, 5:24:03", "throughput": 564.65, "total_tokens": 5703904} {"current_steps": 3490, "total_steps": 40000, "loss": 0.1405, "lr": 4.9067234623886315e-05, "epoch": 0.15799361687679667, "percentage": 8.72, "elapsed_time": "2:48:24", "remaining_time": "1 day, 5:21:50", "throughput": 565.28, "total_tokens": 5712128} {"current_steps": 3495, "total_steps": 40000, "loss": 0.155, "lr": 4.9064576072076316e-05, "epoch": 0.15821996876343963, "percentage": 8.74, "elapsed_time": "2:48:28", "remaining_time": "1 day, 5:19:39", "throughput": 565.96, "total_tokens": 5720864} {"current_steps": 3500, "total_steps": 40000, "loss": 0.2064, "lr": 4.906191380920628e-05, "epoch": 0.15844632065008263, "percentage": 8.75, "elapsed_time": "2:48:31", "remaining_time": "1 day, 5:17:27", "throughput": 566.58, "total_tokens": 5728928} {"current_steps": 3505, "total_steps": 40000, "loss": 0.1316, "lr": 4.905924783568675e-05, "epoch": 0.1586726725367256, "percentage": 8.76, "elapsed_time": "2:48:34", "remaining_time": "1 day, 5:15:19", "throughput": 567.36, "total_tokens": 5738752} {"current_steps": 3510, "total_steps": 40000, "loss": 0.1647, "lr": 4.905657815192886e-05, "epoch": 0.15889902442336856, "percentage": 8.77, "elapsed_time": "2:48:37", "remaining_time": "1 day, 5:13:06", "throughput": 567.94, "total_tokens": 5746368} {"current_steps": 3515, "total_steps": 40000, "loss": 0.141, "lr": 4.90539047583443e-05, "epoch": 0.15912537631001156, "percentage": 8.79, "elapsed_time": "2:48:41", "remaining_time": "1 day, 5:10:55", "throughput": 568.53, "total_tokens": 5754208} {"current_steps": 3520, "total_steps": 40000, "loss": 0.1663, "lr": 4.905122765534534e-05, "epoch": 0.15935172819665452, "percentage": 8.8, "elapsed_time": "2:48:44", "remaining_time": "1 day, 5:08:43", "throughput": 569.11, "total_tokens": 5761792} {"current_steps": 3525, "total_steps": 40000, "loss": 0.1666, "lr": 4.9048546843344846e-05, "epoch": 0.1595780800832975, "percentage": 8.81, "elapsed_time": "2:48:47", "remaining_time": "1 day, 5:06:33", "throughput": 569.72, "total_tokens": 5769824} {"current_steps": 3530, "total_steps": 40000, "loss": 0.1948, "lr": 4.9045862322756206e-05, "epoch": 0.15980443196994046, "percentage": 8.82, "elapsed_time": "2:48:50", "remaining_time": "1 day, 5:04:23", "throughput": 570.33, "total_tokens": 5777760} {"current_steps": 3535, "total_steps": 40000, "loss": 0.1838, "lr": 4.904317409399342e-05, "epoch": 0.16003078385658345, "percentage": 8.84, "elapsed_time": "2:48:53", "remaining_time": "1 day, 5:02:12", "throughput": 570.9, "total_tokens": 5785344} {"current_steps": 3540, "total_steps": 40000, "loss": 0.1471, "lr": 4.904048215747104e-05, "epoch": 0.16025713574322642, "percentage": 8.85, "elapsed_time": "2:48:57", "remaining_time": "1 day, 5:00:06", "throughput": 571.61, "total_tokens": 5794496} {"current_steps": 3545, "total_steps": 40000, "loss": 0.1971, "lr": 4.90377865136042e-05, "epoch": 0.1604834876298694, "percentage": 8.86, "elapsed_time": "2:49:00", "remaining_time": "1 day, 4:57:57", "throughput": 572.26, "total_tokens": 5802912} {"current_steps": 3550, "total_steps": 40000, "loss": 0.1519, "lr": 4.90350871628086e-05, "epoch": 0.16070983951651238, "percentage": 8.88, "elapsed_time": "2:49:03", "remaining_time": "1 day, 4:55:48", "throughput": 572.87, "total_tokens": 5810816} {"current_steps": 3555, "total_steps": 40000, "loss": 0.1396, "lr": 4.903238410550052e-05, "epoch": 0.16093619140315535, "percentage": 8.89, "elapsed_time": "2:49:06", "remaining_time": "1 day, 4:53:41", "throughput": 573.52, "total_tokens": 5819360} {"current_steps": 3560, "total_steps": 40000, "loss": 0.182, "lr": 4.90296773420968e-05, "epoch": 0.16116254328979832, "percentage": 8.9, "elapsed_time": "2:49:09", "remaining_time": "1 day, 4:51:34", "throughput": 574.22, "total_tokens": 5828256} {"current_steps": 3565, "total_steps": 40000, "loss": 0.1127, "lr": 4.902696687301486e-05, "epoch": 0.16138889517644128, "percentage": 8.91, "elapsed_time": "2:49:13", "remaining_time": "1 day, 4:49:28", "throughput": 574.9, "total_tokens": 5837088} {"current_steps": 3570, "total_steps": 40000, "loss": 0.1088, "lr": 4.902425269867268e-05, "epoch": 0.16161524706308428, "percentage": 8.92, "elapsed_time": "2:49:16", "remaining_time": "1 day, 4:47:21", "throughput": 575.5, "total_tokens": 5845024} {"current_steps": 3575, "total_steps": 40000, "loss": 0.1492, "lr": 4.902153481948883e-05, "epoch": 0.16184159894972724, "percentage": 8.94, "elapsed_time": "2:49:19", "remaining_time": "1 day, 4:45:14", "throughput": 576.14, "total_tokens": 5853408} {"current_steps": 3580, "total_steps": 40000, "loss": 0.1915, "lr": 4.901881323588244e-05, "epoch": 0.1620679508363702, "percentage": 8.95, "elapsed_time": "2:49:22", "remaining_time": "1 day, 4:43:08", "throughput": 576.76, "total_tokens": 5861504} {"current_steps": 3585, "total_steps": 40000, "loss": 0.1513, "lr": 4.90160879482732e-05, "epoch": 0.1622943027230132, "percentage": 8.96, "elapsed_time": "2:49:26", "remaining_time": "1 day, 4:41:04", "throughput": 577.48, "total_tokens": 5870752} {"current_steps": 3590, "total_steps": 40000, "loss": 0.2048, "lr": 4.9013358957081405e-05, "epoch": 0.16252065460965617, "percentage": 8.97, "elapsed_time": "2:49:29", "remaining_time": "1 day, 4:38:58", "throughput": 578.06, "total_tokens": 5878528} {"current_steps": 3595, "total_steps": 40000, "loss": 0.1382, "lr": 4.901062626272789e-05, "epoch": 0.16274700649629914, "percentage": 8.99, "elapsed_time": "2:49:32", "remaining_time": "1 day, 4:36:52", "throughput": 578.68, "total_tokens": 5886624} {"current_steps": 3600, "total_steps": 40000, "loss": 0.1914, "lr": 4.900788986563406e-05, "epoch": 0.16297335838294214, "percentage": 9.0, "elapsed_time": "2:49:35", "remaining_time": "1 day, 4:34:47", "throughput": 579.3, "total_tokens": 5894816} {"current_steps": 3600, "total_steps": 40000, "eval_loss": 0.17068035900592804, "epoch": 0.16297335838294214, "percentage": 9.0, "elapsed_time": "2:57:18", "remaining_time": "1 day, 5:52:45", "throughput": 554.11, "total_tokens": 5894816} {"current_steps": 3605, "total_steps": 40000, "loss": 0.1685, "lr": 4.9005149766221915e-05, "epoch": 0.1631997102695851, "percentage": 9.01, "elapsed_time": "2:57:22", "remaining_time": "1 day, 5:50:43", "throughput": 554.74, "total_tokens": 5903840} {"current_steps": 3610, "total_steps": 40000, "loss": 0.1354, "lr": 4.9002405964914e-05, "epoch": 0.16342606215622807, "percentage": 9.03, "elapsed_time": "2:57:25", "remaining_time": "1 day, 5:48:30", "throughput": 555.29, "total_tokens": 5911360} {"current_steps": 3615, "total_steps": 40000, "loss": 0.2022, "lr": 4.899965846213346e-05, "epoch": 0.16365241404287104, "percentage": 9.04, "elapsed_time": "2:57:28", "remaining_time": "1 day, 5:46:18", "throughput": 555.83, "total_tokens": 5918880} {"current_steps": 3620, "total_steps": 40000, "loss": 0.1463, "lr": 4.899690725830399e-05, "epoch": 0.16387876592951403, "percentage": 9.05, "elapsed_time": "2:57:31", "remaining_time": "1 day, 5:44:09", "throughput": 556.46, "total_tokens": 5927424} {"current_steps": 3625, "total_steps": 40000, "loss": 0.1161, "lr": 4.899415235384985e-05, "epoch": 0.164105117816157, "percentage": 9.06, "elapsed_time": "2:57:35", "remaining_time": "1 day, 5:41:58", "throughput": 557.08, "total_tokens": 5935776} {"current_steps": 3630, "total_steps": 40000, "loss": 0.1364, "lr": 4.899139374919589e-05, "epoch": 0.16433146970279996, "percentage": 9.07, "elapsed_time": "2:57:38", "remaining_time": "1 day, 5:39:48", "throughput": 557.69, "total_tokens": 5944000} {"current_steps": 3635, "total_steps": 40000, "loss": 0.1767, "lr": 4.898863144476752e-05, "epoch": 0.16455782158944296, "percentage": 9.09, "elapsed_time": "2:57:41", "remaining_time": "1 day, 5:37:37", "throughput": 558.28, "total_tokens": 5952000} {"current_steps": 3640, "total_steps": 40000, "loss": 0.2057, "lr": 4.898586544099072e-05, "epoch": 0.16478417347608593, "percentage": 9.1, "elapsed_time": "2:57:44", "remaining_time": "1 day, 5:35:27", "throughput": 558.85, "total_tokens": 5959808} {"current_steps": 3645, "total_steps": 40000, "loss": 0.1873, "lr": 4.898309573829204e-05, "epoch": 0.1650105253627289, "percentage": 9.11, "elapsed_time": "2:57:47", "remaining_time": "1 day, 5:33:18", "throughput": 559.42, "total_tokens": 5967744} {"current_steps": 3650, "total_steps": 40000, "loss": 0.1944, "lr": 4.898032233709862e-05, "epoch": 0.16523687724937186, "percentage": 9.12, "elapsed_time": "2:57:50", "remaining_time": "1 day, 5:31:10", "throughput": 560.04, "total_tokens": 5976128} {"current_steps": 3655, "total_steps": 40000, "loss": 0.146, "lr": 4.8977545237838123e-05, "epoch": 0.16546322913601486, "percentage": 9.14, "elapsed_time": "2:57:53", "remaining_time": "1 day, 5:29:00", "throughput": 560.59, "total_tokens": 5983744} {"current_steps": 3660, "total_steps": 40000, "loss": 0.2212, "lr": 4.8974764440938836e-05, "epoch": 0.16568958102265782, "percentage": 9.15, "elapsed_time": "2:57:57", "remaining_time": "1 day, 5:26:52", "throughput": 561.17, "total_tokens": 5991616} {"current_steps": 3665, "total_steps": 40000, "loss": 0.1687, "lr": 4.897197994682959e-05, "epoch": 0.1659159329093008, "percentage": 9.16, "elapsed_time": "2:58:00", "remaining_time": "1 day, 5:24:44", "throughput": 561.75, "total_tokens": 5999584} {"current_steps": 3670, "total_steps": 40000, "loss": 0.1452, "lr": 4.8969191755939786e-05, "epoch": 0.16614228479594378, "percentage": 9.18, "elapsed_time": "2:58:03", "remaining_time": "1 day, 5:22:36", "throughput": 562.31, "total_tokens": 6007392} {"current_steps": 3675, "total_steps": 40000, "loss": 0.2451, "lr": 4.8966399868699396e-05, "epoch": 0.16636863668258675, "percentage": 9.19, "elapsed_time": "2:58:06", "remaining_time": "1 day, 5:20:28", "throughput": 562.86, "total_tokens": 6014944} {"current_steps": 3680, "total_steps": 40000, "loss": 0.1376, "lr": 4.8963604285538965e-05, "epoch": 0.16659498856922972, "percentage": 9.2, "elapsed_time": "2:58:09", "remaining_time": "1 day, 5:18:21", "throughput": 563.46, "total_tokens": 6023104} {"current_steps": 3685, "total_steps": 40000, "loss": 0.1517, "lr": 4.8960805006889604e-05, "epoch": 0.1668213404558727, "percentage": 9.21, "elapsed_time": "2:58:12", "remaining_time": "1 day, 5:16:14", "throughput": 564.02, "total_tokens": 6030912} {"current_steps": 3690, "total_steps": 40000, "loss": 0.1977, "lr": 4.8958002033183004e-05, "epoch": 0.16704769234251568, "percentage": 9.22, "elapsed_time": "2:58:15", "remaining_time": "1 day, 5:14:08", "throughput": 564.61, "total_tokens": 6039040} {"current_steps": 3695, "total_steps": 40000, "loss": 0.1231, "lr": 4.8955195364851414e-05, "epoch": 0.16727404422915865, "percentage": 9.24, "elapsed_time": "2:58:19", "remaining_time": "1 day, 5:12:02", "throughput": 565.22, "total_tokens": 6047296} {"current_steps": 3700, "total_steps": 40000, "loss": 0.1918, "lr": 4.895238500232766e-05, "epoch": 0.16750039611580161, "percentage": 9.25, "elapsed_time": "2:58:22", "remaining_time": "1 day, 5:09:57", "throughput": 565.82, "total_tokens": 6055520} {"current_steps": 3705, "total_steps": 40000, "loss": 0.2066, "lr": 4.8949570946045143e-05, "epoch": 0.1677267480024446, "percentage": 9.26, "elapsed_time": "2:58:25", "remaining_time": "1 day, 5:07:52", "throughput": 566.4, "total_tokens": 6063584} {"current_steps": 3710, "total_steps": 40000, "loss": 0.2384, "lr": 4.89467531964378e-05, "epoch": 0.16795309988908758, "percentage": 9.28, "elapsed_time": "2:58:28", "remaining_time": "1 day, 5:05:48", "throughput": 566.99, "total_tokens": 6071680} {"current_steps": 3715, "total_steps": 40000, "loss": 0.184, "lr": 4.894393175394019e-05, "epoch": 0.16817945177573054, "percentage": 9.29, "elapsed_time": "2:58:31", "remaining_time": "1 day, 5:03:44", "throughput": 567.6, "total_tokens": 6080064} {"current_steps": 3720, "total_steps": 40000, "loss": 0.2458, "lr": 4.8941106618987406e-05, "epoch": 0.16840580366237354, "percentage": 9.3, "elapsed_time": "2:58:35", "remaining_time": "1 day, 5:01:41", "throughput": 568.22, "total_tokens": 6088576} {"current_steps": 3725, "total_steps": 40000, "loss": 0.193, "lr": 4.893827779201512e-05, "epoch": 0.1686321555490165, "percentage": 9.31, "elapsed_time": "2:58:38", "remaining_time": "1 day, 4:59:37", "throughput": 568.82, "total_tokens": 6096800} {"current_steps": 3730, "total_steps": 40000, "loss": 0.1275, "lr": 4.893544527345957e-05, "epoch": 0.16885850743565947, "percentage": 9.32, "elapsed_time": "2:58:41", "remaining_time": "1 day, 4:57:32", "throughput": 569.34, "total_tokens": 6104128} {"current_steps": 3735, "total_steps": 40000, "loss": 0.1807, "lr": 4.8932609063757563e-05, "epoch": 0.16908485932230244, "percentage": 9.34, "elapsed_time": "2:58:44", "remaining_time": "1 day, 4:55:29", "throughput": 569.94, "total_tokens": 6112352} {"current_steps": 3740, "total_steps": 40000, "loss": 0.1318, "lr": 4.8929769163346484e-05, "epoch": 0.16931121120894543, "percentage": 9.35, "elapsed_time": "2:58:47", "remaining_time": "1 day, 4:53:27", "throughput": 570.54, "total_tokens": 6120640} {"current_steps": 3745, "total_steps": 40000, "loss": 0.1789, "lr": 4.892692557266429e-05, "epoch": 0.1695375630955884, "percentage": 9.36, "elapsed_time": "2:58:50", "remaining_time": "1 day, 4:51:25", "throughput": 571.16, "total_tokens": 6129152} {"current_steps": 3750, "total_steps": 40000, "loss": 0.1913, "lr": 4.8924078292149464e-05, "epoch": 0.16976391498223137, "percentage": 9.38, "elapsed_time": "2:58:54", "remaining_time": "1 day, 4:49:23", "throughput": 571.79, "total_tokens": 6137728} {"current_steps": 3755, "total_steps": 40000, "loss": 0.1976, "lr": 4.892122732224114e-05, "epoch": 0.16999026686887436, "percentage": 9.39, "elapsed_time": "2:58:57", "remaining_time": "1 day, 4:47:22", "throughput": 572.41, "total_tokens": 6146240} {"current_steps": 3760, "total_steps": 40000, "loss": 0.1999, "lr": 4.8918372663378944e-05, "epoch": 0.17021661875551733, "percentage": 9.4, "elapsed_time": "2:59:00", "remaining_time": "1 day, 4:45:21", "throughput": 573.01, "total_tokens": 6154528} {"current_steps": 3765, "total_steps": 40000, "loss": 0.1526, "lr": 4.89155143160031e-05, "epoch": 0.1704429706421603, "percentage": 9.41, "elapsed_time": "2:59:03", "remaining_time": "1 day, 4:43:20", "throughput": 573.65, "total_tokens": 6163168} {"current_steps": 3770, "total_steps": 40000, "loss": 0.1659, "lr": 4.891265228055441e-05, "epoch": 0.1706693225288033, "percentage": 9.43, "elapsed_time": "2:59:07", "remaining_time": "1 day, 4:41:20", "throughput": 574.26, "total_tokens": 6171648} {"current_steps": 3775, "total_steps": 40000, "loss": 0.1682, "lr": 4.890978655747424e-05, "epoch": 0.17089567441544626, "percentage": 9.44, "elapsed_time": "2:59:10", "remaining_time": "1 day, 4:39:19", "throughput": 574.85, "total_tokens": 6179744} {"current_steps": 3780, "total_steps": 40000, "loss": 0.2004, "lr": 4.89069171472045e-05, "epoch": 0.17112202630208923, "percentage": 9.45, "elapsed_time": "2:59:13", "remaining_time": "1 day, 4:37:18", "throughput": 575.39, "total_tokens": 6187328} {"current_steps": 3785, "total_steps": 40000, "loss": 0.138, "lr": 4.890404405018772e-05, "epoch": 0.1713483781887322, "percentage": 9.46, "elapsed_time": "2:59:16", "remaining_time": "1 day, 4:35:19", "throughput": 576.03, "total_tokens": 6196064} {"current_steps": 3790, "total_steps": 40000, "loss": 0.1569, "lr": 4.8901167266866934e-05, "epoch": 0.1715747300753752, "percentage": 9.47, "elapsed_time": "2:59:19", "remaining_time": "1 day, 4:33:21", "throughput": 576.62, "total_tokens": 6204384} {"current_steps": 3795, "total_steps": 40000, "loss": 0.1462, "lr": 4.88982867976858e-05, "epoch": 0.17180108196201815, "percentage": 9.49, "elapsed_time": "2:59:23", "remaining_time": "1 day, 4:31:23", "throughput": 577.24, "total_tokens": 6212960} {"current_steps": 3800, "total_steps": 40000, "loss": 0.2461, "lr": 4.889540264308852e-05, "epoch": 0.17202743384866112, "percentage": 9.5, "elapsed_time": "2:59:26", "remaining_time": "1 day, 4:29:24", "throughput": 577.89, "total_tokens": 6221824} {"current_steps": 3800, "total_steps": 40000, "eval_loss": 0.1688394993543625, "epoch": 0.17202743384866112, "percentage": 9.5, "elapsed_time": "3:07:09", "remaining_time": "1 day, 5:42:52", "throughput": 554.08, "total_tokens": 6221824} {"current_steps": 3805, "total_steps": 40000, "loss": 0.1774, "lr": 4.889251480351986e-05, "epoch": 0.17225378573530412, "percentage": 9.51, "elapsed_time": "3:07:14", "remaining_time": "1 day, 5:41:06", "throughput": 554.5, "total_tokens": 6229440} {"current_steps": 3810, "total_steps": 40000, "loss": 0.1486, "lr": 4.888962327942517e-05, "epoch": 0.17248013762194708, "percentage": 9.53, "elapsed_time": "3:07:17", "remaining_time": "1 day, 5:39:01", "throughput": 555.07, "total_tokens": 6237568} {"current_steps": 3815, "total_steps": 40000, "loss": 0.1311, "lr": 4.8886728071250356e-05, "epoch": 0.17270648950859005, "percentage": 9.54, "elapsed_time": "3:07:20", "remaining_time": "1 day, 5:36:56", "throughput": 555.64, "total_tokens": 6245728} {"current_steps": 3820, "total_steps": 40000, "loss": 0.1797, "lr": 4.8883829179441884e-05, "epoch": 0.17293284139523302, "percentage": 9.55, "elapsed_time": "3:07:23", "remaining_time": "1 day, 5:34:52", "throughput": 556.22, "total_tokens": 6254048} {"current_steps": 3825, "total_steps": 40000, "loss": 0.1376, "lr": 4.888092660444682e-05, "epoch": 0.173159193281876, "percentage": 9.56, "elapsed_time": "3:07:27", "remaining_time": "1 day, 5:32:49", "throughput": 556.81, "total_tokens": 6262528} {"current_steps": 3830, "total_steps": 40000, "loss": 0.1719, "lr": 4.887802034671276e-05, "epoch": 0.17338554516851898, "percentage": 9.57, "elapsed_time": "3:07:30", "remaining_time": "1 day, 5:30:45", "throughput": 557.34, "total_tokens": 6270144} {"current_steps": 3835, "total_steps": 40000, "loss": 0.2119, "lr": 4.88751104066879e-05, "epoch": 0.17361189705516195, "percentage": 9.59, "elapsed_time": "3:07:33", "remaining_time": "1 day, 5:28:41", "throughput": 557.91, "total_tokens": 6278304} {"current_steps": 3840, "total_steps": 40000, "loss": 0.188, "lr": 4.887219678482098e-05, "epoch": 0.17383824894180494, "percentage": 9.6, "elapsed_time": "3:07:36", "remaining_time": "1 day, 5:26:38", "throughput": 558.45, "total_tokens": 6286112} {"current_steps": 3845, "total_steps": 40000, "loss": 0.1164, "lr": 4.8869279481561316e-05, "epoch": 0.1740646008284479, "percentage": 9.61, "elapsed_time": "3:07:39", "remaining_time": "1 day, 5:24:35", "throughput": 559.01, "total_tokens": 6294272} {"current_steps": 3850, "total_steps": 40000, "loss": 0.1946, "lr": 4.88663584973588e-05, "epoch": 0.17429095271509087, "percentage": 9.62, "elapsed_time": "3:07:42", "remaining_time": "1 day, 5:22:34", "throughput": 559.62, "total_tokens": 6302944} {"current_steps": 3855, "total_steps": 40000, "loss": 0.1617, "lr": 4.8863433832663874e-05, "epoch": 0.17451730460173387, "percentage": 9.64, "elapsed_time": "3:07:46", "remaining_time": "1 day, 5:20:32", "throughput": 560.19, "total_tokens": 6311168} {"current_steps": 3860, "total_steps": 40000, "loss": 0.195, "lr": 4.886050548792757e-05, "epoch": 0.17474365648837684, "percentage": 9.65, "elapsed_time": "3:07:49", "remaining_time": "1 day, 5:18:30", "throughput": 560.73, "total_tokens": 6319040} {"current_steps": 3865, "total_steps": 40000, "loss": 0.1479, "lr": 4.8857573463601465e-05, "epoch": 0.1749700083750198, "percentage": 9.66, "elapsed_time": "3:07:52", "remaining_time": "1 day, 5:16:28", "throughput": 561.29, "total_tokens": 6327072} {"current_steps": 3870, "total_steps": 40000, "loss": 0.1369, "lr": 4.885463776013772e-05, "epoch": 0.17519636026166277, "percentage": 9.68, "elapsed_time": "3:07:55", "remaining_time": "1 day, 5:14:28", "throughput": 561.88, "total_tokens": 6335616} {"current_steps": 3875, "total_steps": 40000, "loss": 0.1443, "lr": 4.8851698377989056e-05, "epoch": 0.17542271214830576, "percentage": 9.69, "elapsed_time": "3:07:58", "remaining_time": "1 day, 5:12:28", "throughput": 562.45, "total_tokens": 6343808} {"current_steps": 3880, "total_steps": 40000, "loss": 0.1462, "lr": 4.884875531760876e-05, "epoch": 0.17564906403494873, "percentage": 9.7, "elapsed_time": "3:08:01", "remaining_time": "1 day, 5:10:27", "throughput": 563.0, "total_tokens": 6351712} {"current_steps": 3885, "total_steps": 40000, "loss": 0.1493, "lr": 4.88458085794507e-05, "epoch": 0.1758754159215917, "percentage": 9.71, "elapsed_time": "3:08:05", "remaining_time": "1 day, 5:08:26", "throughput": 563.55, "total_tokens": 6359680} {"current_steps": 3890, "total_steps": 40000, "loss": 0.1704, "lr": 4.884285816396929e-05, "epoch": 0.1761017678082347, "percentage": 9.72, "elapsed_time": "3:08:08", "remaining_time": "1 day, 5:06:27", "throughput": 564.14, "total_tokens": 6368160} {"current_steps": 3895, "total_steps": 40000, "loss": 0.1459, "lr": 4.8839904071619526e-05, "epoch": 0.17632811969487766, "percentage": 9.74, "elapsed_time": "3:08:11", "remaining_time": "1 day, 5:04:28", "throughput": 564.71, "total_tokens": 6376512} {"current_steps": 3900, "total_steps": 40000, "loss": 0.1567, "lr": 4.8836946302856955e-05, "epoch": 0.17655447158152063, "percentage": 9.75, "elapsed_time": "3:08:14", "remaining_time": "1 day, 5:02:28", "throughput": 565.24, "total_tokens": 6384160} {"current_steps": 3905, "total_steps": 40000, "loss": 0.1557, "lr": 4.8833984858137715e-05, "epoch": 0.1767808234681636, "percentage": 9.76, "elapsed_time": "3:08:17", "remaining_time": "1 day, 5:00:28", "throughput": 565.8, "total_tokens": 6392288} {"current_steps": 3910, "total_steps": 40000, "loss": 0.1626, "lr": 4.8831019737918494e-05, "epoch": 0.1770071753548066, "percentage": 9.78, "elapsed_time": "3:08:21", "remaining_time": "1 day, 4:58:30", "throughput": 566.39, "total_tokens": 6400768} {"current_steps": 3915, "total_steps": 40000, "loss": 0.1364, "lr": 4.882805094265655e-05, "epoch": 0.17723352724144956, "percentage": 9.79, "elapsed_time": "3:08:24", "remaining_time": "1 day, 4:56:33", "throughput": 566.99, "total_tokens": 6409472} {"current_steps": 3920, "total_steps": 40000, "loss": 0.1674, "lr": 4.8825078472809706e-05, "epoch": 0.17745987912809252, "percentage": 9.8, "elapsed_time": "3:08:27", "remaining_time": "1 day, 4:54:33", "throughput": 567.49, "total_tokens": 6416832} {"current_steps": 3925, "total_steps": 40000, "loss": 0.1797, "lr": 4.882210232883635e-05, "epoch": 0.17768623101473552, "percentage": 9.81, "elapsed_time": "3:08:30", "remaining_time": "1 day, 4:52:37", "throughput": 568.1, "total_tokens": 6425536} {"current_steps": 3930, "total_steps": 40000, "loss": 0.1821, "lr": 4.881912251119546e-05, "epoch": 0.17791258290137849, "percentage": 9.83, "elapsed_time": "3:08:33", "remaining_time": "1 day, 4:50:39", "throughput": 568.66, "total_tokens": 6433728} {"current_steps": 3935, "total_steps": 40000, "loss": 0.1603, "lr": 4.881613902034654e-05, "epoch": 0.17813893478802145, "percentage": 9.84, "elapsed_time": "3:08:37", "remaining_time": "1 day, 4:48:43", "throughput": 569.26, "total_tokens": 6442400} {"current_steps": 3940, "total_steps": 40000, "loss": 0.2251, "lr": 4.88131518567497e-05, "epoch": 0.17836528667466445, "percentage": 9.85, "elapsed_time": "3:08:40", "remaining_time": "1 day, 4:46:46", "throughput": 569.8, "total_tokens": 6450240} {"current_steps": 3945, "total_steps": 40000, "loss": 0.1746, "lr": 4.881016102086558e-05, "epoch": 0.17859163856130741, "percentage": 9.86, "elapsed_time": "3:08:43", "remaining_time": "1 day, 4:44:50", "throughput": 570.37, "total_tokens": 6458592} {"current_steps": 3950, "total_steps": 40000, "loss": 0.165, "lr": 4.8807166513155425e-05, "epoch": 0.17881799044795038, "percentage": 9.88, "elapsed_time": "3:08:46", "remaining_time": "1 day, 4:42:54", "throughput": 570.98, "total_tokens": 6467360} {"current_steps": 3955, "total_steps": 40000, "loss": 0.155, "lr": 4.8804168334081004e-05, "epoch": 0.17904434233459335, "percentage": 9.89, "elapsed_time": "3:08:49", "remaining_time": "1 day, 4:40:58", "throughput": 571.53, "total_tokens": 6475360} {"current_steps": 3960, "total_steps": 40000, "loss": 0.1615, "lr": 4.880116648410468e-05, "epoch": 0.17927069422123634, "percentage": 9.9, "elapsed_time": "3:08:53", "remaining_time": "1 day, 4:39:02", "throughput": 572.06, "total_tokens": 6483232} {"current_steps": 3965, "total_steps": 40000, "loss": 0.1833, "lr": 4.879816096368939e-05, "epoch": 0.1794970461078793, "percentage": 9.91, "elapsed_time": "3:08:56", "remaining_time": "1 day, 4:37:05", "throughput": 572.58, "total_tokens": 6490848} {"current_steps": 3970, "total_steps": 40000, "loss": 0.1235, "lr": 4.879515177329861e-05, "epoch": 0.17972339799452228, "percentage": 9.93, "elapsed_time": "3:08:59", "remaining_time": "1 day, 4:35:10", "throughput": 573.12, "total_tokens": 6498752} {"current_steps": 3975, "total_steps": 40000, "loss": 0.1745, "lr": 4.8792138913396394e-05, "epoch": 0.17994974988116527, "percentage": 9.94, "elapsed_time": "3:09:02", "remaining_time": "1 day, 4:33:15", "throughput": 573.68, "total_tokens": 6506944} {"current_steps": 3980, "total_steps": 40000, "loss": 0.1302, "lr": 4.8789122384447374e-05, "epoch": 0.18017610176780824, "percentage": 9.95, "elapsed_time": "3:09:05", "remaining_time": "1 day, 4:31:20", "throughput": 574.23, "total_tokens": 6514912} {"current_steps": 3985, "total_steps": 40000, "loss": 0.1931, "lr": 4.878610218691673e-05, "epoch": 0.1804024536544512, "percentage": 9.96, "elapsed_time": "3:09:08", "remaining_time": "1 day, 4:29:26", "throughput": 574.82, "total_tokens": 6523520} {"current_steps": 3990, "total_steps": 40000, "loss": 0.2006, "lr": 4.87830783212702e-05, "epoch": 0.18062880554109417, "percentage": 9.98, "elapsed_time": "3:09:12", "remaining_time": "1 day, 4:27:32", "throughput": 575.36, "total_tokens": 6531520} {"current_steps": 3995, "total_steps": 40000, "loss": 0.1375, "lr": 4.878005078797413e-05, "epoch": 0.18085515742773717, "percentage": 9.99, "elapsed_time": "3:09:15", "remaining_time": "1 day, 4:25:40", "throughput": 575.98, "total_tokens": 6540416} {"current_steps": 4000, "total_steps": 40000, "loss": 0.1189, "lr": 4.877701958749539e-05, "epoch": 0.18108150931438013, "percentage": 10.0, "elapsed_time": "3:09:18", "remaining_time": "1 day, 4:23:47", "throughput": 576.6, "total_tokens": 6549344} {"current_steps": 4000, "total_steps": 40000, "eval_loss": 0.1670093983411789, "epoch": 0.18108150931438013, "percentage": 10.0, "elapsed_time": "3:17:01", "remaining_time": "1 day, 5:33:11", "throughput": 554.03, "total_tokens": 6549344} {"current_steps": 4005, "total_steps": 40000, "loss": 0.1909, "lr": 4.877398472030142e-05, "epoch": 0.1813078612010231, "percentage": 10.01, "elapsed_time": "3:17:05", "remaining_time": "1 day, 5:31:21", "throughput": 554.56, "total_tokens": 6557952} {"current_steps": 4010, "total_steps": 40000, "loss": 0.1483, "lr": 4.877094618686024e-05, "epoch": 0.1815342130876661, "percentage": 10.03, "elapsed_time": "3:17:08", "remaining_time": "1 day, 5:29:23", "throughput": 555.13, "total_tokens": 6566400} {"current_steps": 4015, "total_steps": 40000, "loss": 0.1394, "lr": 4.876790398764045e-05, "epoch": 0.18176056497430906, "percentage": 10.04, "elapsed_time": "3:17:11", "remaining_time": "1 day, 5:27:24", "throughput": 555.67, "total_tokens": 6574560} {"current_steps": 4020, "total_steps": 40000, "loss": 0.2385, "lr": 4.8764858123111167e-05, "epoch": 0.18198691686095203, "percentage": 10.05, "elapsed_time": "3:17:15", "remaining_time": "1 day, 5:25:27", "throughput": 556.23, "total_tokens": 6583008} {"current_steps": 4025, "total_steps": 40000, "loss": 0.1717, "lr": 4.876180859374212e-05, "epoch": 0.182213268747595, "percentage": 10.06, "elapsed_time": "3:17:18", "remaining_time": "1 day, 5:23:29", "throughput": 556.74, "total_tokens": 6590848} {"current_steps": 4030, "total_steps": 40000, "loss": 0.1446, "lr": 4.875875540000357e-05, "epoch": 0.182439620634238, "percentage": 10.08, "elapsed_time": "3:17:21", "remaining_time": "1 day, 5:21:31", "throughput": 557.28, "total_tokens": 6599040} {"current_steps": 4035, "total_steps": 40000, "loss": 0.1561, "lr": 4.8755698542366376e-05, "epoch": 0.18266597252088096, "percentage": 10.09, "elapsed_time": "3:17:24", "remaining_time": "1 day, 5:19:35", "throughput": 557.86, "total_tokens": 6607744} {"current_steps": 4040, "total_steps": 40000, "loss": 0.1593, "lr": 4.875263802130193e-05, "epoch": 0.18289232440752393, "percentage": 10.1, "elapsed_time": "3:17:28", "remaining_time": "1 day, 5:17:39", "throughput": 558.42, "total_tokens": 6616128} {"current_steps": 4045, "total_steps": 40000, "loss": 0.1633, "lr": 4.8749573837282207e-05, "epoch": 0.18311867629416692, "percentage": 10.11, "elapsed_time": "3:17:31", "remaining_time": "1 day, 5:15:42", "throughput": 558.93, "total_tokens": 6623936} {"current_steps": 4050, "total_steps": 40000, "loss": 0.1942, "lr": 4.874650599077974e-05, "epoch": 0.1833450281808099, "percentage": 10.12, "elapsed_time": "3:17:34", "remaining_time": "1 day, 5:13:44", "throughput": 559.42, "total_tokens": 6631488} {"current_steps": 4055, "total_steps": 40000, "loss": 0.2043, "lr": 4.874343448226764e-05, "epoch": 0.18357138006745286, "percentage": 10.14, "elapsed_time": "3:17:37", "remaining_time": "1 day, 5:11:48", "throughput": 559.98, "total_tokens": 6639872} {"current_steps": 4060, "total_steps": 40000, "loss": 0.2027, "lr": 4.874035931221955e-05, "epoch": 0.18379773195409585, "percentage": 10.15, "elapsed_time": "3:17:40", "remaining_time": "1 day, 5:09:52", "throughput": 560.52, "total_tokens": 6648128} {"current_steps": 4065, "total_steps": 40000, "loss": 0.1398, "lr": 4.8737280481109724e-05, "epoch": 0.18402408384073882, "percentage": 10.16, "elapsed_time": "3:17:43", "remaining_time": "1 day, 5:07:57", "throughput": 561.11, "total_tokens": 6656864} {"current_steps": 4070, "total_steps": 40000, "loss": 0.1601, "lr": 4.873419798941294e-05, "epoch": 0.18425043572738178, "percentage": 10.17, "elapsed_time": "3:17:47", "remaining_time": "1 day, 5:06:02", "throughput": 561.65, "total_tokens": 6665184} {"current_steps": 4075, "total_steps": 40000, "loss": 0.1648, "lr": 4.873111183760458e-05, "epoch": 0.18447678761402475, "percentage": 10.19, "elapsed_time": "3:17:50", "remaining_time": "1 day, 5:04:08", "throughput": 562.21, "total_tokens": 6673664} {"current_steps": 4080, "total_steps": 40000, "loss": 0.1614, "lr": 4.8728022026160537e-05, "epoch": 0.18470313950066775, "percentage": 10.2, "elapsed_time": "3:17:53", "remaining_time": "1 day, 5:02:13", "throughput": 562.75, "total_tokens": 6681824} {"current_steps": 4085, "total_steps": 40000, "loss": 0.1354, "lr": 4.872492855555732e-05, "epoch": 0.1849294913873107, "percentage": 10.21, "elapsed_time": "3:17:56", "remaining_time": "1 day, 5:00:19", "throughput": 563.28, "total_tokens": 6689952} {"current_steps": 4090, "total_steps": 40000, "loss": 0.1991, "lr": 4.8721831426271956e-05, "epoch": 0.18515584327395368, "percentage": 10.22, "elapsed_time": "3:17:59", "remaining_time": "1 day, 4:58:24", "throughput": 563.74, "total_tokens": 6697152} {"current_steps": 4095, "total_steps": 40000, "loss": 0.1544, "lr": 4.87187306387821e-05, "epoch": 0.18538219516059667, "percentage": 10.24, "elapsed_time": "3:18:02", "remaining_time": "1 day, 4:56:30", "throughput": 564.27, "total_tokens": 6705216} {"current_steps": 4100, "total_steps": 40000, "loss": 0.1735, "lr": 4.87156261935659e-05, "epoch": 0.18560854704723964, "percentage": 10.25, "elapsed_time": "3:18:06", "remaining_time": "1 day, 4:54:35", "throughput": 564.75, "total_tokens": 6712640} {"current_steps": 4105, "total_steps": 40000, "loss": 0.1618, "lr": 4.871251809110211e-05, "epoch": 0.1858348989338826, "percentage": 10.26, "elapsed_time": "3:18:09", "remaining_time": "1 day, 4:52:43", "throughput": 565.34, "total_tokens": 6721536} {"current_steps": 4110, "total_steps": 40000, "loss": 0.1364, "lr": 4.8709406331870044e-05, "epoch": 0.18606125082052558, "percentage": 10.27, "elapsed_time": "3:18:12", "remaining_time": "1 day, 4:50:49", "throughput": 565.82, "total_tokens": 6729088} {"current_steps": 4115, "total_steps": 40000, "loss": 0.1522, "lr": 4.8706290916349574e-05, "epoch": 0.18628760270716857, "percentage": 10.29, "elapsed_time": "3:18:15", "remaining_time": "1 day, 4:48:57", "throughput": 566.38, "total_tokens": 6737472} {"current_steps": 4120, "total_steps": 40000, "loss": 0.1667, "lr": 4.8703171845021134e-05, "epoch": 0.18651395459381154, "percentage": 10.3, "elapsed_time": "3:18:19", "remaining_time": "1 day, 4:47:05", "throughput": 566.94, "total_tokens": 6745984} {"current_steps": 4125, "total_steps": 40000, "loss": 0.1617, "lr": 4.870004911836572e-05, "epoch": 0.1867403064804545, "percentage": 10.31, "elapsed_time": "3:18:22", "remaining_time": "1 day, 4:45:12", "throughput": 567.45, "total_tokens": 6753824} {"current_steps": 4130, "total_steps": 40000, "loss": 0.2285, "lr": 4.869692273686489e-05, "epoch": 0.1869666583670975, "percentage": 10.32, "elapsed_time": "3:18:25", "remaining_time": "1 day, 4:43:20", "throughput": 567.98, "total_tokens": 6762048} {"current_steps": 4135, "total_steps": 40000, "loss": 0.144, "lr": 4.869379270100079e-05, "epoch": 0.18719301025374047, "percentage": 10.34, "elapsed_time": "3:18:28", "remaining_time": "1 day, 4:41:29", "throughput": 568.54, "total_tokens": 6770496} {"current_steps": 4140, "total_steps": 40000, "loss": 0.1196, "lr": 4.86906590112561e-05, "epoch": 0.18741936214038343, "percentage": 10.35, "elapsed_time": "3:18:31", "remaining_time": "1 day, 4:39:37", "throughput": 569.06, "total_tokens": 6778432} {"current_steps": 4145, "total_steps": 40000, "loss": 0.2189, "lr": 4.8687521668114064e-05, "epoch": 0.18764571402702643, "percentage": 10.36, "elapsed_time": "3:18:34", "remaining_time": "1 day, 4:37:45", "throughput": 569.59, "total_tokens": 6786624} {"current_steps": 4150, "total_steps": 40000, "loss": 0.2044, "lr": 4.868438067205853e-05, "epoch": 0.1878720659136694, "percentage": 10.38, "elapsed_time": "3:18:38", "remaining_time": "1 day, 4:35:55", "throughput": 570.17, "total_tokens": 6795392} {"current_steps": 4155, "total_steps": 40000, "loss": 0.1395, "lr": 4.8681236023573844e-05, "epoch": 0.18809841780031236, "percentage": 10.39, "elapsed_time": "3:18:41", "remaining_time": "1 day, 4:34:04", "throughput": 570.7, "total_tokens": 6803488} {"current_steps": 4160, "total_steps": 40000, "loss": 0.1542, "lr": 4.867808772314497e-05, "epoch": 0.18832476968695533, "percentage": 10.4, "elapsed_time": "3:18:44", "remaining_time": "1 day, 4:32:15", "throughput": 571.29, "total_tokens": 6812384} {"current_steps": 4165, "total_steps": 40000, "loss": 0.1558, "lr": 4.867493577125741e-05, "epoch": 0.18855112157359832, "percentage": 10.41, "elapsed_time": "3:18:47", "remaining_time": "1 day, 4:30:24", "throughput": 571.81, "total_tokens": 6820480} {"current_steps": 4170, "total_steps": 40000, "loss": 0.1732, "lr": 4.867178016839725e-05, "epoch": 0.1887774734602413, "percentage": 10.42, "elapsed_time": "3:18:50", "remaining_time": "1 day, 4:28:34", "throughput": 572.3, "total_tokens": 6828064} {"current_steps": 4175, "total_steps": 40000, "loss": 0.2316, "lr": 4.8668620915051094e-05, "epoch": 0.18900382534688426, "percentage": 10.44, "elapsed_time": "3:18:54", "remaining_time": "1 day, 4:26:44", "throughput": 572.85, "total_tokens": 6836448} {"current_steps": 4180, "total_steps": 40000, "loss": 0.1651, "lr": 4.866545801170616e-05, "epoch": 0.18923017723352725, "percentage": 10.45, "elapsed_time": "3:18:57", "remaining_time": "1 day, 4:24:55", "throughput": 573.4, "total_tokens": 6844832} {"current_steps": 4185, "total_steps": 40000, "loss": 0.1451, "lr": 4.86622914588502e-05, "epoch": 0.18945652912017022, "percentage": 10.46, "elapsed_time": "3:19:00", "remaining_time": "1 day, 4:23:07", "throughput": 573.97, "total_tokens": 6853600} {"current_steps": 4190, "total_steps": 40000, "loss": 0.1575, "lr": 4.865912125697154e-05, "epoch": 0.1896828810068132, "percentage": 10.47, "elapsed_time": "3:19:03", "remaining_time": "1 day, 4:21:18", "throughput": 574.52, "total_tokens": 6861952} {"current_steps": 4195, "total_steps": 40000, "loss": 0.1758, "lr": 4.865594740655907e-05, "epoch": 0.18990923289345615, "percentage": 10.49, "elapsed_time": "3:19:06", "remaining_time": "1 day, 4:19:28", "throughput": 575.0, "total_tokens": 6869472} {"current_steps": 4200, "total_steps": 40000, "loss": 0.1342, "lr": 4.865276990810222e-05, "epoch": 0.19013558478009915, "percentage": 10.5, "elapsed_time": "3:19:10", "remaining_time": "1 day, 4:17:40", "throughput": 575.54, "total_tokens": 6877728} {"current_steps": 4200, "total_steps": 40000, "eval_loss": 0.1662140041589737, "epoch": 0.19013558478009915, "percentage": 10.5, "elapsed_time": "3:26:52", "remaining_time": "1 day, 5:23:24", "throughput": 554.08, "total_tokens": 6877728} {"current_steps": 4205, "total_steps": 40000, "loss": 0.1391, "lr": 4.8649588762091016e-05, "epoch": 0.19036193666674212, "percentage": 10.51, "elapsed_time": "3:26:57", "remaining_time": "1 day, 5:21:44", "throughput": 554.53, "total_tokens": 6885888} {"current_steps": 4210, "total_steps": 40000, "loss": 0.1664, "lr": 4.8646403969016016e-05, "epoch": 0.19058828855338508, "percentage": 10.53, "elapsed_time": "3:27:00", "remaining_time": "1 day, 5:19:50", "throughput": 554.99, "total_tokens": 6893312} {"current_steps": 4215, "total_steps": 40000, "loss": 0.2039, "lr": 4.864321552936838e-05, "epoch": 0.19081464044002808, "percentage": 10.54, "elapsed_time": "3:27:03", "remaining_time": "1 day, 5:17:56", "throughput": 555.47, "total_tokens": 6901024} {"current_steps": 4220, "total_steps": 40000, "loss": 0.1414, "lr": 4.864002344363978e-05, "epoch": 0.19104099232667104, "percentage": 10.55, "elapsed_time": "3:27:06", "remaining_time": "1 day, 5:16:03", "throughput": 555.98, "total_tokens": 6909120} {"current_steps": 4225, "total_steps": 40000, "loss": 0.188, "lr": 4.863682771232248e-05, "epoch": 0.191267344213314, "percentage": 10.56, "elapsed_time": "3:27:10", "remaining_time": "1 day, 5:14:11", "throughput": 556.51, "total_tokens": 6917504} {"current_steps": 4230, "total_steps": 40000, "loss": 0.1903, "lr": 4.8633628335909324e-05, "epoch": 0.191493696099957, "percentage": 10.57, "elapsed_time": "3:27:13", "remaining_time": "1 day, 5:12:19", "throughput": 557.03, "total_tokens": 6925728} {"current_steps": 4235, "total_steps": 40000, "loss": 0.2068, "lr": 4.8630425314893676e-05, "epoch": 0.19172004798659997, "percentage": 10.59, "elapsed_time": "3:27:16", "remaining_time": "1 day, 5:10:27", "throughput": 557.56, "total_tokens": 6934048} {"current_steps": 4240, "total_steps": 40000, "loss": 0.1428, "lr": 4.862721864976948e-05, "epoch": 0.19194639987324294, "percentage": 10.6, "elapsed_time": "3:27:19", "remaining_time": "1 day, 5:08:34", "throughput": 558.05, "total_tokens": 6941952} {"current_steps": 4245, "total_steps": 40000, "loss": 0.1489, "lr": 4.862400834103125e-05, "epoch": 0.1921727517598859, "percentage": 10.61, "elapsed_time": "3:27:22", "remaining_time": "1 day, 5:06:43", "throughput": 558.56, "total_tokens": 6950048} {"current_steps": 4250, "total_steps": 40000, "loss": 0.2106, "lr": 4.862079438917406e-05, "epoch": 0.1923991036465289, "percentage": 10.62, "elapsed_time": "3:27:25", "remaining_time": "1 day, 5:04:52", "throughput": 559.1, "total_tokens": 6958496} {"current_steps": 4255, "total_steps": 40000, "loss": 0.1921, "lr": 4.8617576794693536e-05, "epoch": 0.19262545553317187, "percentage": 10.64, "elapsed_time": "3:27:29", "remaining_time": "1 day, 5:03:01", "throughput": 559.6, "total_tokens": 6966560} {"current_steps": 4260, "total_steps": 40000, "loss": 0.1415, "lr": 4.8614355558085875e-05, "epoch": 0.19285180741981484, "percentage": 10.65, "elapsed_time": "3:27:32", "remaining_time": "1 day, 5:01:09", "throughput": 560.11, "total_tokens": 6974560} {"current_steps": 4265, "total_steps": 40000, "loss": 0.1761, "lr": 4.861113067984783e-05, "epoch": 0.19307815930645783, "percentage": 10.66, "elapsed_time": "3:27:35", "remaining_time": "1 day, 4:59:19", "throughput": 560.62, "total_tokens": 6982784} {"current_steps": 4270, "total_steps": 40000, "loss": 0.1303, "lr": 4.860790216047671e-05, "epoch": 0.1933045111931008, "percentage": 10.67, "elapsed_time": "3:27:38", "remaining_time": "1 day, 4:57:30", "throughput": 561.19, "total_tokens": 6991648} {"current_steps": 4275, "total_steps": 40000, "loss": 0.1766, "lr": 4.860467000047041e-05, "epoch": 0.19353086307974376, "percentage": 10.69, "elapsed_time": "3:27:41", "remaining_time": "1 day, 4:55:40", "throughput": 561.72, "total_tokens": 7000032} {"current_steps": 4280, "total_steps": 40000, "loss": 0.1407, "lr": 4.860143420032737e-05, "epoch": 0.19375721496638673, "percentage": 10.7, "elapsed_time": "3:27:44", "remaining_time": "1 day, 4:53:50", "throughput": 562.19, "total_tokens": 7007744} {"current_steps": 4285, "total_steps": 40000, "loss": 0.1304, "lr": 4.859819476054657e-05, "epoch": 0.19398356685302973, "percentage": 10.71, "elapsed_time": "3:27:48", "remaining_time": "1 day, 4:52:00", "throughput": 562.7, "total_tokens": 7015872} {"current_steps": 4290, "total_steps": 40000, "loss": 0.146, "lr": 4.859495168162758e-05, "epoch": 0.1942099187396727, "percentage": 10.72, "elapsed_time": "3:27:51", "remaining_time": "1 day, 4:50:11", "throughput": 563.23, "total_tokens": 7024224} {"current_steps": 4295, "total_steps": 40000, "loss": 0.1693, "lr": 4.859170496407054e-05, "epoch": 0.19443627062631566, "percentage": 10.74, "elapsed_time": "3:27:54", "remaining_time": "1 day, 4:48:22", "throughput": 563.76, "total_tokens": 7032640} {"current_steps": 4300, "total_steps": 40000, "loss": 0.1834, "lr": 4.8588454608376114e-05, "epoch": 0.19466262251295866, "percentage": 10.75, "elapsed_time": "3:27:57", "remaining_time": "1 day, 4:46:34", "throughput": 564.26, "total_tokens": 7040704} {"current_steps": 4305, "total_steps": 40000, "loss": 0.2614, "lr": 4.8585200615045555e-05, "epoch": 0.19488897439960162, "percentage": 10.76, "elapsed_time": "3:28:00", "remaining_time": "1 day, 4:44:46", "throughput": 564.76, "total_tokens": 7048736} {"current_steps": 4310, "total_steps": 40000, "loss": 0.1197, "lr": 4.8581942984580674e-05, "epoch": 0.1951153262862446, "percentage": 10.78, "elapsed_time": "3:28:04", "remaining_time": "1 day, 4:42:58", "throughput": 565.27, "total_tokens": 7056960} {"current_steps": 4315, "total_steps": 40000, "loss": 0.1436, "lr": 4.857868171748384e-05, "epoch": 0.19534167817288758, "percentage": 10.79, "elapsed_time": "3:28:07", "remaining_time": "1 day, 4:41:10", "throughput": 565.77, "total_tokens": 7064928} {"current_steps": 4320, "total_steps": 40000, "loss": 0.144, "lr": 4.8575416814257976e-05, "epoch": 0.19556803005953055, "percentage": 10.8, "elapsed_time": "3:28:10", "remaining_time": "1 day, 4:39:22", "throughput": 566.24, "total_tokens": 7072640} {"current_steps": 4325, "total_steps": 40000, "loss": 0.1705, "lr": 4.857214827540657e-05, "epoch": 0.19579438194617352, "percentage": 10.81, "elapsed_time": "3:28:13", "remaining_time": "1 day, 4:37:35", "throughput": 566.76, "total_tokens": 7080960} {"current_steps": 4330, "total_steps": 40000, "loss": 0.1155, "lr": 4.856887610143367e-05, "epoch": 0.19602073383281648, "percentage": 10.82, "elapsed_time": "3:28:16", "remaining_time": "1 day, 4:35:48", "throughput": 567.31, "total_tokens": 7089696} {"current_steps": 4335, "total_steps": 40000, "loss": 0.1916, "lr": 4.8565600292843896e-05, "epoch": 0.19624708571945948, "percentage": 10.84, "elapsed_time": "3:28:20", "remaining_time": "1 day, 4:34:02", "throughput": 567.83, "total_tokens": 7098048} {"current_steps": 4340, "total_steps": 40000, "loss": 0.136, "lr": 4.856232085014241e-05, "epoch": 0.19647343760610245, "percentage": 10.85, "elapsed_time": "3:28:23", "remaining_time": "1 day, 4:32:15", "throughput": 568.35, "total_tokens": 7106400} {"current_steps": 4345, "total_steps": 40000, "loss": 0.1778, "lr": 4.855903777383495e-05, "epoch": 0.1966997894927454, "percentage": 10.86, "elapsed_time": "3:28:26", "remaining_time": "1 day, 4:30:28", "throughput": 568.84, "total_tokens": 7114208} {"current_steps": 4350, "total_steps": 40000, "loss": 0.1542, "lr": 4.85557510644278e-05, "epoch": 0.1969261413793884, "percentage": 10.88, "elapsed_time": "3:28:29", "remaining_time": "1 day, 4:28:42", "throughput": 569.33, "total_tokens": 7122112} {"current_steps": 4355, "total_steps": 40000, "loss": 0.1957, "lr": 4.855246072242782e-05, "epoch": 0.19715249326603138, "percentage": 10.89, "elapsed_time": "3:28:33", "remaining_time": "1 day, 4:26:57", "throughput": 569.87, "total_tokens": 7130848} {"current_steps": 4360, "total_steps": 40000, "loss": 0.1795, "lr": 4.8549166748342414e-05, "epoch": 0.19737884515267434, "percentage": 10.9, "elapsed_time": "3:28:36", "remaining_time": "1 day, 4:25:11", "throughput": 570.37, "total_tokens": 7138848} {"current_steps": 4365, "total_steps": 40000, "loss": 0.1332, "lr": 4.8545869142679556e-05, "epoch": 0.1976051970393173, "percentage": 10.91, "elapsed_time": "3:28:39", "remaining_time": "1 day, 4:23:25", "throughput": 570.89, "total_tokens": 7147136} {"current_steps": 4370, "total_steps": 40000, "loss": 0.1119, "lr": 4.8542567905947776e-05, "epoch": 0.1978315489259603, "percentage": 10.93, "elapsed_time": "3:28:43", "remaining_time": "1 day, 4:21:45", "throughput": 571.59, "total_tokens": 7158144} {"current_steps": 4375, "total_steps": 40000, "loss": 0.1674, "lr": 4.853926303865618e-05, "epoch": 0.19805790081260327, "percentage": 10.94, "elapsed_time": "3:28:46", "remaining_time": "1 day, 4:20:00", "throughput": 572.1, "total_tokens": 7166400} {"current_steps": 4380, "total_steps": 40000, "loss": 0.172, "lr": 4.853595454131441e-05, "epoch": 0.19828425269924624, "percentage": 10.95, "elapsed_time": "3:28:49", "remaining_time": "1 day, 4:18:16", "throughput": 572.64, "total_tokens": 7175040} {"current_steps": 4385, "total_steps": 40000, "loss": 0.135, "lr": 4.8532642414432674e-05, "epoch": 0.19851060458588923, "percentage": 10.96, "elapsed_time": "3:28:52", "remaining_time": "1 day, 4:16:31", "throughput": 573.14, "total_tokens": 7183008} {"current_steps": 4390, "total_steps": 40000, "loss": 0.183, "lr": 4.8529326658521754e-05, "epoch": 0.1987369564725322, "percentage": 10.97, "elapsed_time": "3:28:55", "remaining_time": "1 day, 4:14:47", "throughput": 573.64, "total_tokens": 7191104} {"current_steps": 4395, "total_steps": 40000, "loss": 0.1544, "lr": 4.8526007274092965e-05, "epoch": 0.19896330835917517, "percentage": 10.99, "elapsed_time": "3:28:59", "remaining_time": "1 day, 4:13:03", "throughput": 574.19, "total_tokens": 7199904} {"current_steps": 4400, "total_steps": 40000, "loss": 0.1281, "lr": 4.852268426165822e-05, "epoch": 0.19918966024581816, "percentage": 11.0, "elapsed_time": "3:29:02", "remaining_time": "1 day, 4:11:20", "throughput": 574.72, "total_tokens": 7208416} {"current_steps": 4400, "total_steps": 40000, "eval_loss": 0.1651245355606079, "epoch": 0.19918966024581816, "percentage": 11.0, "elapsed_time": "3:36:45", "remaining_time": "1 day, 5:13:45", "throughput": 554.26, "total_tokens": 7208416} {"current_steps": 4405, "total_steps": 40000, "loss": 0.1599, "lr": 4.851935762172995e-05, "epoch": 0.19941601213246113, "percentage": 11.01, "elapsed_time": "3:36:49", "remaining_time": "1 day, 5:12:04", "throughput": 554.72, "total_tokens": 7216640} {"current_steps": 4410, "total_steps": 40000, "loss": 0.12, "lr": 4.8516027354821175e-05, "epoch": 0.1996423640191041, "percentage": 11.03, "elapsed_time": "3:36:52", "remaining_time": "1 day, 5:10:16", "throughput": 555.22, "total_tokens": 7224864} {"current_steps": 4415, "total_steps": 40000, "loss": 0.1698, "lr": 4.851269346144546e-05, "epoch": 0.19986871590574706, "percentage": 11.04, "elapsed_time": "3:36:55", "remaining_time": "1 day, 5:08:28", "throughput": 555.71, "total_tokens": 7233088} {"current_steps": 4420, "total_steps": 40000, "loss": 0.2138, "lr": 4.850935594211693e-05, "epoch": 0.20009506779239006, "percentage": 11.05, "elapsed_time": "3:36:59", "remaining_time": "1 day, 5:06:40", "throughput": 556.2, "total_tokens": 7241216} {"current_steps": 4425, "total_steps": 40000, "loss": 0.1925, "lr": 4.850601479735029e-05, "epoch": 0.20032141967903302, "percentage": 11.06, "elapsed_time": "3:37:02", "remaining_time": "1 day, 5:04:52", "throughput": 556.7, "total_tokens": 7249440} {"current_steps": 4430, "total_steps": 40000, "loss": 0.134, "lr": 4.850267002766076e-05, "epoch": 0.200547771565676, "percentage": 11.07, "elapsed_time": "3:37:05", "remaining_time": "1 day, 5:03:07", "throughput": 557.16, "total_tokens": 7257376} {"current_steps": 4435, "total_steps": 40000, "loss": 0.1815, "lr": 4.849932163356417e-05, "epoch": 0.200774123452319, "percentage": 11.09, "elapsed_time": "3:37:08", "remaining_time": "1 day, 5:01:21", "throughput": 557.7, "total_tokens": 7266304} {"current_steps": 4440, "total_steps": 40000, "loss": 0.1434, "lr": 4.8495969615576864e-05, "epoch": 0.20100047533896195, "percentage": 11.1, "elapsed_time": "3:37:12", "remaining_time": "1 day, 4:59:34", "throughput": 558.15, "total_tokens": 7273824} {"current_steps": 4445, "total_steps": 40000, "loss": 0.2391, "lr": 4.849261397421577e-05, "epoch": 0.20122682722560492, "percentage": 11.11, "elapsed_time": "3:37:15", "remaining_time": "1 day, 4:57:47", "throughput": 558.63, "total_tokens": 7281888} {"current_steps": 4450, "total_steps": 40000, "loss": 0.1339, "lr": 4.848925470999839e-05, "epoch": 0.2014531791122479, "percentage": 11.12, "elapsed_time": "3:37:18", "remaining_time": "1 day, 4:56:00", "throughput": 559.09, "total_tokens": 7289664} {"current_steps": 4455, "total_steps": 40000, "loss": 0.1392, "lr": 4.848589182344273e-05, "epoch": 0.20167953099889088, "percentage": 11.14, "elapsed_time": "3:37:21", "remaining_time": "1 day, 4:54:13", "throughput": 559.57, "total_tokens": 7297664} {"current_steps": 4460, "total_steps": 40000, "loss": 0.1805, "lr": 4.848252531506742e-05, "epoch": 0.20190588288553385, "percentage": 11.15, "elapsed_time": "3:37:24", "remaining_time": "1 day, 4:52:28", "throughput": 560.08, "total_tokens": 7306112} {"current_steps": 4465, "total_steps": 40000, "loss": 0.1662, "lr": 4.847915518539161e-05, "epoch": 0.20213223477217682, "percentage": 11.16, "elapsed_time": "3:37:27", "remaining_time": "1 day, 4:50:43", "throughput": 560.6, "total_tokens": 7314720} {"current_steps": 4470, "total_steps": 40000, "loss": 0.1841, "lr": 4.847578143493501e-05, "epoch": 0.2023585866588198, "percentage": 11.18, "elapsed_time": "3:37:31", "remaining_time": "1 day, 4:48:58", "throughput": 561.11, "total_tokens": 7323136} {"current_steps": 4475, "total_steps": 40000, "loss": 0.1234, "lr": 4.847240406421789e-05, "epoch": 0.20258493854546278, "percentage": 11.19, "elapsed_time": "3:37:34", "remaining_time": "1 day, 4:47:12", "throughput": 561.56, "total_tokens": 7330784} {"current_steps": 4480, "total_steps": 40000, "loss": 0.1223, "lr": 4.84690230737611e-05, "epoch": 0.20281129043210575, "percentage": 11.2, "elapsed_time": "3:37:37", "remaining_time": "1 day, 4:45:27", "throughput": 562.05, "total_tokens": 7338912} {"current_steps": 4485, "total_steps": 40000, "loss": 0.1815, "lr": 4.846563846408602e-05, "epoch": 0.20303764231874874, "percentage": 11.21, "elapsed_time": "3:37:40", "remaining_time": "1 day, 4:43:41", "throughput": 562.51, "total_tokens": 7346784} {"current_steps": 4490, "total_steps": 40000, "loss": 0.1506, "lr": 4.84622502357146e-05, "epoch": 0.2032639942053917, "percentage": 11.22, "elapsed_time": "3:37:43", "remaining_time": "1 day, 4:41:57", "throughput": 562.98, "total_tokens": 7354624} {"current_steps": 4495, "total_steps": 40000, "loss": 0.1874, "lr": 4.8458858389169345e-05, "epoch": 0.20349034609203467, "percentage": 11.24, "elapsed_time": "3:37:46", "remaining_time": "1 day, 4:40:12", "throughput": 563.46, "total_tokens": 7362688} {"current_steps": 4500, "total_steps": 40000, "loss": 0.1646, "lr": 4.8455462924973334e-05, "epoch": 0.20371669797867764, "percentage": 11.25, "elapsed_time": "3:37:50", "remaining_time": "1 day, 4:38:28", "throughput": 563.93, "total_tokens": 7370624} {"current_steps": 4505, "total_steps": 40000, "loss": 0.1589, "lr": 4.845206384365018e-05, "epoch": 0.20394304986532064, "percentage": 11.26, "elapsed_time": "3:37:53", "remaining_time": "1 day, 4:36:44", "throughput": 564.43, "total_tokens": 7378880} {"current_steps": 4510, "total_steps": 40000, "loss": 0.209, "lr": 4.844866114572405e-05, "epoch": 0.2041694017519636, "percentage": 11.28, "elapsed_time": "3:37:56", "remaining_time": "1 day, 4:35:00", "throughput": 564.9, "total_tokens": 7386880} {"current_steps": 4515, "total_steps": 40000, "loss": 0.197, "lr": 4.8445254831719706e-05, "epoch": 0.20439575363860657, "percentage": 11.29, "elapsed_time": "3:37:59", "remaining_time": "1 day, 4:33:17", "throughput": 565.39, "total_tokens": 7395104} {"current_steps": 4520, "total_steps": 40000, "loss": 0.1329, "lr": 4.8441844902162434e-05, "epoch": 0.20462210552524956, "percentage": 11.3, "elapsed_time": "3:38:02", "remaining_time": "1 day, 4:31:33", "throughput": 565.89, "total_tokens": 7403328} {"current_steps": 4525, "total_steps": 40000, "loss": 0.1655, "lr": 4.843843135757809e-05, "epoch": 0.20484845741189253, "percentage": 11.31, "elapsed_time": "3:38:05", "remaining_time": "1 day, 4:29:49", "throughput": 566.35, "total_tokens": 7411104} {"current_steps": 4530, "total_steps": 40000, "loss": 0.1411, "lr": 4.843501419849308e-05, "epoch": 0.2050748092985355, "percentage": 11.33, "elapsed_time": "3:38:09", "remaining_time": "1 day, 4:28:07", "throughput": 566.84, "total_tokens": 7419392} {"current_steps": 4535, "total_steps": 40000, "loss": 0.1076, "lr": 4.8431593425434386e-05, "epoch": 0.20530116118517847, "percentage": 11.34, "elapsed_time": "3:38:12", "remaining_time": "1 day, 4:26:25", "throughput": 567.33, "total_tokens": 7427680} {"current_steps": 4540, "total_steps": 40000, "loss": 0.1419, "lr": 4.8428169038929526e-05, "epoch": 0.20552751307182146, "percentage": 11.35, "elapsed_time": "3:38:15", "remaining_time": "1 day, 4:24:44", "throughput": 567.9, "total_tokens": 7437088} {"current_steps": 4545, "total_steps": 40000, "loss": 0.1353, "lr": 4.8424741039506575e-05, "epoch": 0.20575386495846443, "percentage": 11.36, "elapsed_time": "3:38:18", "remaining_time": "1 day, 4:23:02", "throughput": 568.41, "total_tokens": 7445536} {"current_steps": 4550, "total_steps": 40000, "loss": 0.1677, "lr": 4.842130942769419e-05, "epoch": 0.2059802168451074, "percentage": 11.38, "elapsed_time": "3:38:22", "remaining_time": "1 day, 4:21:20", "throughput": 568.91, "total_tokens": 7453952} {"current_steps": 4555, "total_steps": 40000, "loss": 0.2168, "lr": 4.841787420402156e-05, "epoch": 0.2062065687317504, "percentage": 11.39, "elapsed_time": "3:38:25", "remaining_time": "1 day, 4:19:39", "throughput": 569.41, "total_tokens": 7462304} {"current_steps": 4560, "total_steps": 40000, "loss": 0.1723, "lr": 4.841443536901844e-05, "epoch": 0.20643292061839336, "percentage": 11.4, "elapsed_time": "3:38:28", "remaining_time": "1 day, 4:17:58", "throughput": 569.93, "total_tokens": 7470880} {"current_steps": 4565, "total_steps": 40000, "loss": 0.2097, "lr": 4.841099292321514e-05, "epoch": 0.20665927250503632, "percentage": 11.41, "elapsed_time": "3:38:31", "remaining_time": "1 day, 4:16:16", "throughput": 570.37, "total_tokens": 7478464} {"current_steps": 4570, "total_steps": 40000, "loss": 0.1408, "lr": 4.8407546867142525e-05, "epoch": 0.20688562439167932, "percentage": 11.43, "elapsed_time": "3:38:34", "remaining_time": "1 day, 4:14:35", "throughput": 570.87, "total_tokens": 7486848} {"current_steps": 4575, "total_steps": 40000, "loss": 0.1332, "lr": 4.840409720133203e-05, "epoch": 0.20711197627832229, "percentage": 11.44, "elapsed_time": "3:38:37", "remaining_time": "1 day, 4:12:53", "throughput": 571.33, "total_tokens": 7494656} {"current_steps": 4580, "total_steps": 40000, "loss": 0.1762, "lr": 4.8400643926315634e-05, "epoch": 0.20733832816496525, "percentage": 11.45, "elapsed_time": "3:38:41", "remaining_time": "1 day, 4:11:13", "throughput": 571.83, "total_tokens": 7503040} {"current_steps": 4585, "total_steps": 40000, "loss": 0.1692, "lr": 4.839718704262587e-05, "epoch": 0.20756468005160822, "percentage": 11.46, "elapsed_time": "3:38:44", "remaining_time": "1 day, 4:09:32", "throughput": 572.29, "total_tokens": 7510816} {"current_steps": 4590, "total_steps": 40000, "loss": 0.1322, "lr": 4.839372655079585e-05, "epoch": 0.2077910319382512, "percentage": 11.47, "elapsed_time": "3:38:47", "remaining_time": "1 day, 4:07:52", "throughput": 572.77, "total_tokens": 7519040} {"current_steps": 4595, "total_steps": 40000, "loss": 0.1392, "lr": 4.83902624513592e-05, "epoch": 0.20801738382489418, "percentage": 11.49, "elapsed_time": "3:38:50", "remaining_time": "1 day, 4:06:12", "throughput": 573.24, "total_tokens": 7526944} {"current_steps": 4600, "total_steps": 40000, "loss": 0.1202, "lr": 4.838679474485014e-05, "epoch": 0.20824373571153715, "percentage": 11.5, "elapsed_time": "3:38:53", "remaining_time": "1 day, 4:04:32", "throughput": 573.7, "total_tokens": 7534752} {"current_steps": 4600, "total_steps": 40000, "eval_loss": 0.1634376347064972, "epoch": 0.20824373571153715, "percentage": 11.5, "elapsed_time": "3:46:36", "remaining_time": "1 day, 5:03:52", "throughput": 554.18, "total_tokens": 7534752} {"current_steps": 4605, "total_steps": 40000, "loss": 0.1514, "lr": 4.838332343180343e-05, "epoch": 0.20847008759818014, "percentage": 11.51, "elapsed_time": "3:46:40", "remaining_time": "1 day, 5:02:12", "throughput": 554.6, "total_tokens": 7542624} {"current_steps": 4610, "total_steps": 40000, "loss": 0.1868, "lr": 4.83798485127544e-05, "epoch": 0.2086964394848231, "percentage": 11.53, "elapsed_time": "3:46:43", "remaining_time": "1 day, 5:00:29", "throughput": 555.07, "total_tokens": 7550784} {"current_steps": 4615, "total_steps": 40000, "loss": 0.1495, "lr": 4.837636998823892e-05, "epoch": 0.20892279137146608, "percentage": 11.54, "elapsed_time": "3:46:46", "remaining_time": "1 day, 4:58:45", "throughput": 555.53, "total_tokens": 7558784} {"current_steps": 4620, "total_steps": 40000, "loss": 0.1896, "lr": 4.8372887858793414e-05, "epoch": 0.20914914325810904, "percentage": 11.55, "elapsed_time": "3:46:49", "remaining_time": "1 day, 4:57:01", "throughput": 555.97, "total_tokens": 7566560} {"current_steps": 4625, "total_steps": 40000, "loss": 0.1336, "lr": 4.836940212495489e-05, "epoch": 0.20937549514475204, "percentage": 11.56, "elapsed_time": "3:46:52", "remaining_time": "1 day, 4:55:18", "throughput": 556.42, "total_tokens": 7574272} {"current_steps": 4630, "total_steps": 40000, "loss": 0.157, "lr": 4.836591278726087e-05, "epoch": 0.209601847031395, "percentage": 11.58, "elapsed_time": "3:46:55", "remaining_time": "1 day, 4:53:35", "throughput": 556.91, "total_tokens": 7582816} {"current_steps": 4635, "total_steps": 40000, "loss": 0.2376, "lr": 4.836241984624947e-05, "epoch": 0.20982819891803797, "percentage": 11.59, "elapsed_time": "3:46:58", "remaining_time": "1 day, 4:51:52", "throughput": 557.35, "total_tokens": 7590496} {"current_steps": 4640, "total_steps": 40000, "loss": 0.1408, "lr": 4.8358923302459336e-05, "epoch": 0.21005455080468097, "percentage": 11.6, "elapsed_time": "3:47:02", "remaining_time": "1 day, 4:50:09", "throughput": 557.77, "total_tokens": 7597952} {"current_steps": 4645, "total_steps": 40000, "loss": 0.2034, "lr": 4.835542315642968e-05, "epoch": 0.21028090269132393, "percentage": 11.61, "elapsed_time": "3:47:05", "remaining_time": "1 day, 4:48:27", "throughput": 558.28, "total_tokens": 7606688} {"current_steps": 4650, "total_steps": 40000, "loss": 0.1321, "lr": 4.8351919408700274e-05, "epoch": 0.2105072545779669, "percentage": 11.62, "elapsed_time": "3:47:08", "remaining_time": "1 day, 4:46:45", "throughput": 558.72, "total_tokens": 7614400} {"current_steps": 4655, "total_steps": 40000, "loss": 0.1581, "lr": 4.834841205981144e-05, "epoch": 0.2107336064646099, "percentage": 11.64, "elapsed_time": "3:47:11", "remaining_time": "1 day, 4:45:03", "throughput": 559.19, "total_tokens": 7622688} {"current_steps": 4660, "total_steps": 40000, "loss": 0.1113, "lr": 4.8344901110304054e-05, "epoch": 0.21095995835125286, "percentage": 11.65, "elapsed_time": "3:47:14", "remaining_time": "1 day, 4:43:22", "throughput": 559.67, "total_tokens": 7630944} {"current_steps": 4665, "total_steps": 40000, "loss": 0.2131, "lr": 4.8341386560719534e-05, "epoch": 0.21118631023789583, "percentage": 11.66, "elapsed_time": "3:47:17", "remaining_time": "1 day, 4:41:39", "throughput": 560.1, "total_tokens": 7638624} {"current_steps": 4670, "total_steps": 40000, "loss": 0.1691, "lr": 4.833786841159989e-05, "epoch": 0.2114126621245388, "percentage": 11.68, "elapsed_time": "3:47:21", "remaining_time": "1 day, 4:40:00", "throughput": 560.62, "total_tokens": 7647552} {"current_steps": 4675, "total_steps": 40000, "loss": 0.1118, "lr": 4.833434666348765e-05, "epoch": 0.2116390140111818, "percentage": 11.69, "elapsed_time": "3:47:24", "remaining_time": "1 day, 4:38:20", "throughput": 561.12, "total_tokens": 7656160} {"current_steps": 4680, "total_steps": 40000, "loss": 0.1668, "lr": 4.833082131692592e-05, "epoch": 0.21186536589782476, "percentage": 11.7, "elapsed_time": "3:47:27", "remaining_time": "1 day, 4:36:39", "throughput": 561.61, "total_tokens": 7664672} {"current_steps": 4685, "total_steps": 40000, "loss": 0.2043, "lr": 4.832729237245835e-05, "epoch": 0.21209171778446773, "percentage": 11.71, "elapsed_time": "3:47:30", "remaining_time": "1 day, 4:34:59", "throughput": 562.08, "total_tokens": 7672960} {"current_steps": 4690, "total_steps": 40000, "loss": 0.1367, "lr": 4.8323759830629145e-05, "epoch": 0.21231806967111072, "percentage": 11.72, "elapsed_time": "3:47:34", "remaining_time": "1 day, 4:33:18", "throughput": 562.53, "total_tokens": 7680864} {"current_steps": 4695, "total_steps": 40000, "loss": 0.1998, "lr": 4.8320223691983066e-05, "epoch": 0.2125444215577537, "percentage": 11.74, "elapsed_time": "3:47:37", "remaining_time": "1 day, 4:31:38", "throughput": 562.99, "total_tokens": 7688832} {"current_steps": 4700, "total_steps": 40000, "loss": 0.1367, "lr": 4.831668395706544e-05, "epoch": 0.21277077344439665, "percentage": 11.75, "elapsed_time": "3:47:40", "remaining_time": "1 day, 4:29:58", "throughput": 563.45, "total_tokens": 7696928} {"current_steps": 4705, "total_steps": 40000, "loss": 0.1694, "lr": 4.8313140626422125e-05, "epoch": 0.21299712533103962, "percentage": 11.76, "elapsed_time": "3:47:43", "remaining_time": "1 day, 4:28:18", "throughput": 563.91, "total_tokens": 7704960} {"current_steps": 4710, "total_steps": 40000, "loss": 0.1307, "lr": 4.830959370059956e-05, "epoch": 0.21322347721768262, "percentage": 11.77, "elapsed_time": "3:47:46", "remaining_time": "1 day, 4:26:38", "throughput": 564.38, "total_tokens": 7713280} {"current_steps": 4715, "total_steps": 40000, "loss": 0.1852, "lr": 4.830604318014472e-05, "epoch": 0.21344982910432558, "percentage": 11.79, "elapsed_time": "3:47:49", "remaining_time": "1 day, 4:24:59", "throughput": 564.87, "total_tokens": 7721664} {"current_steps": 4720, "total_steps": 40000, "loss": 0.1742, "lr": 4.830248906560514e-05, "epoch": 0.21367618099096855, "percentage": 11.8, "elapsed_time": "3:47:53", "remaining_time": "1 day, 4:23:21", "throughput": 565.38, "total_tokens": 7730560} {"current_steps": 4725, "total_steps": 40000, "loss": 0.1479, "lr": 4.829893135752891e-05, "epoch": 0.21390253287761155, "percentage": 11.81, "elapsed_time": "3:47:56", "remaining_time": "1 day, 4:21:42", "throughput": 565.83, "total_tokens": 7738464} {"current_steps": 4730, "total_steps": 40000, "loss": 0.1229, "lr": 4.829537005646466e-05, "epoch": 0.2141288847642545, "percentage": 11.82, "elapsed_time": "3:47:59", "remaining_time": "1 day, 4:20:03", "throughput": 566.28, "total_tokens": 7746464} {"current_steps": 4735, "total_steps": 40000, "loss": 0.1481, "lr": 4.8291805162961615e-05, "epoch": 0.21435523665089748, "percentage": 11.84, "elapsed_time": "3:48:02", "remaining_time": "1 day, 4:18:25", "throughput": 566.79, "total_tokens": 7755296} {"current_steps": 4740, "total_steps": 40000, "loss": 0.1676, "lr": 4.82882366775695e-05, "epoch": 0.21458158853754047, "percentage": 11.85, "elapsed_time": "3:48:05", "remaining_time": "1 day, 4:16:47", "throughput": 567.25, "total_tokens": 7763328} {"current_steps": 4745, "total_steps": 40000, "loss": 0.1442, "lr": 4.828466460083864e-05, "epoch": 0.21480794042418344, "percentage": 11.86, "elapsed_time": "3:48:08", "remaining_time": "1 day, 4:15:08", "throughput": 567.68, "total_tokens": 7770976} {"current_steps": 4750, "total_steps": 40000, "loss": 0.1663, "lr": 4.8281088933319877e-05, "epoch": 0.2150342923108264, "percentage": 11.88, "elapsed_time": "3:48:12", "remaining_time": "1 day, 4:13:29", "throughput": 568.13, "total_tokens": 7778976} {"current_steps": 4755, "total_steps": 40000, "loss": 0.1309, "lr": 4.827750967556464e-05, "epoch": 0.21526064419746938, "percentage": 11.89, "elapsed_time": "3:48:15", "remaining_time": "1 day, 4:11:51", "throughput": 568.56, "total_tokens": 7786496} {"current_steps": 4760, "total_steps": 40000, "loss": 0.1238, "lr": 4.827392682812488e-05, "epoch": 0.21548699608411237, "percentage": 11.9, "elapsed_time": "3:48:18", "remaining_time": "1 day, 4:10:15", "throughput": 569.07, "total_tokens": 7795392} {"current_steps": 4765, "total_steps": 40000, "loss": 0.1651, "lr": 4.827034039155312e-05, "epoch": 0.21571334797075534, "percentage": 11.91, "elapsed_time": "3:48:21", "remaining_time": "1 day, 4:08:39", "throughput": 569.6, "total_tokens": 7804672} {"current_steps": 4770, "total_steps": 40000, "loss": 0.1345, "lr": 4.8266750366402445e-05, "epoch": 0.2159396998573983, "percentage": 11.92, "elapsed_time": "3:48:25", "remaining_time": "1 day, 4:07:02", "throughput": 570.03, "total_tokens": 7812320} {"current_steps": 4775, "total_steps": 40000, "loss": 0.1984, "lr": 4.8263156753226476e-05, "epoch": 0.2161660517440413, "percentage": 11.94, "elapsed_time": "3:48:28", "remaining_time": "1 day, 4:05:25", "throughput": 570.5, "total_tokens": 7820544} {"current_steps": 4780, "total_steps": 40000, "loss": 0.1417, "lr": 4.8259559552579394e-05, "epoch": 0.21639240363068427, "percentage": 11.95, "elapsed_time": "3:48:31", "remaining_time": "1 day, 4:03:47", "throughput": 570.93, "total_tokens": 7828256} {"current_steps": 4785, "total_steps": 40000, "loss": 0.1327, "lr": 4.825595876501593e-05, "epoch": 0.21661875551732723, "percentage": 11.96, "elapsed_time": "3:48:34", "remaining_time": "1 day, 4:02:11", "throughput": 571.39, "total_tokens": 7836288} {"current_steps": 4790, "total_steps": 40000, "loss": 0.1389, "lr": 4.825235439109137e-05, "epoch": 0.2168451074039702, "percentage": 11.97, "elapsed_time": "3:48:37", "remaining_time": "1 day, 4:00:34", "throughput": 571.87, "total_tokens": 7844768} {"current_steps": 4795, "total_steps": 40000, "loss": 0.1129, "lr": 4.824874643136156e-05, "epoch": 0.2170714592906132, "percentage": 11.99, "elapsed_time": "3:48:40", "remaining_time": "1 day, 3:58:58", "throughput": 572.33, "total_tokens": 7852768} {"current_steps": 4800, "total_steps": 40000, "loss": 0.1502, "lr": 4.824513488638288e-05, "epoch": 0.21729781117725616, "percentage": 12.0, "elapsed_time": "3:48:43", "remaining_time": "1 day, 3:57:22", "throughput": 572.78, "total_tokens": 7860736} {"current_steps": 4800, "total_steps": 40000, "eval_loss": 0.16260091960430145, "epoch": 0.21729781117725616, "percentage": 12.0, "elapsed_time": "3:56:26", "remaining_time": "1 day, 4:53:55", "throughput": 554.09, "total_tokens": 7860736} {"current_steps": 4805, "total_steps": 40000, "loss": 0.1662, "lr": 4.8241519756712293e-05, "epoch": 0.21752416306389913, "percentage": 12.01, "elapsed_time": "3:56:31", "remaining_time": "1 day, 4:52:29", "throughput": 554.44, "total_tokens": 7868384} {"current_steps": 4810, "total_steps": 40000, "loss": 0.1573, "lr": 4.8237901042907285e-05, "epoch": 0.21775051495054212, "percentage": 12.03, "elapsed_time": "3:56:34", "remaining_time": "1 day, 4:50:49", "throughput": 554.9, "total_tokens": 7876672} {"current_steps": 4815, "total_steps": 40000, "loss": 0.1846, "lr": 4.823427874552591e-05, "epoch": 0.2179768668371851, "percentage": 12.04, "elapsed_time": "3:56:38", "remaining_time": "1 day, 4:49:10", "throughput": 555.37, "total_tokens": 7885152} {"current_steps": 4820, "total_steps": 40000, "loss": 0.1844, "lr": 4.823065286512677e-05, "epoch": 0.21820321872382806, "percentage": 12.05, "elapsed_time": "3:56:41", "remaining_time": "1 day, 4:47:31", "throughput": 555.82, "total_tokens": 7893344} {"current_steps": 4825, "total_steps": 40000, "loss": 0.1898, "lr": 4.8227023402269025e-05, "epoch": 0.21842957061047102, "percentage": 12.06, "elapsed_time": "3:56:44", "remaining_time": "1 day, 4:45:52", "throughput": 556.26, "total_tokens": 7901312} {"current_steps": 4830, "total_steps": 40000, "loss": 0.169, "lr": 4.822339035751239e-05, "epoch": 0.21865592249711402, "percentage": 12.07, "elapsed_time": "3:56:47", "remaining_time": "1 day, 4:44:13", "throughput": 556.71, "total_tokens": 7909504} {"current_steps": 4835, "total_steps": 40000, "loss": 0.1922, "lr": 4.8219753731417104e-05, "epoch": 0.218882274383757, "percentage": 12.09, "elapsed_time": "3:56:50", "remaining_time": "1 day, 4:42:35", "throughput": 557.19, "total_tokens": 7918048} {"current_steps": 4840, "total_steps": 40000, "loss": 0.1646, "lr": 4.821611352454401e-05, "epoch": 0.21910862627039995, "percentage": 12.1, "elapsed_time": "3:56:53", "remaining_time": "1 day, 4:40:56", "throughput": 557.61, "total_tokens": 7925792} {"current_steps": 4845, "total_steps": 40000, "loss": 0.1689, "lr": 4.8212469737454444e-05, "epoch": 0.21933497815704295, "percentage": 12.11, "elapsed_time": "3:56:57", "remaining_time": "1 day, 4:39:18", "throughput": 558.06, "total_tokens": 7934048} {"current_steps": 4850, "total_steps": 40000, "loss": 0.1904, "lr": 4.820882237071035e-05, "epoch": 0.21956133004368591, "percentage": 12.12, "elapsed_time": "3:57:00", "remaining_time": "1 day, 4:37:41", "throughput": 558.53, "total_tokens": 7942592} {"current_steps": 4855, "total_steps": 40000, "loss": 0.1501, "lr": 4.820517142487417e-05, "epoch": 0.21978768193032888, "percentage": 12.14, "elapsed_time": "3:57:03", "remaining_time": "1 day, 4:36:03", "throughput": 558.97, "total_tokens": 7950560} {"current_steps": 4860, "total_steps": 40000, "loss": 0.1397, "lr": 4.8201516900508956e-05, "epoch": 0.22001403381697188, "percentage": 12.15, "elapsed_time": "3:57:06", "remaining_time": "1 day, 4:34:25", "throughput": 559.41, "total_tokens": 7958528} {"current_steps": 4865, "total_steps": 40000, "loss": 0.1521, "lr": 4.819785879817827e-05, "epoch": 0.22024038570361484, "percentage": 12.16, "elapsed_time": "3:57:09", "remaining_time": "1 day, 4:32:47", "throughput": 559.85, "total_tokens": 7966592} {"current_steps": 4870, "total_steps": 40000, "loss": 0.1741, "lr": 4.8194197118446226e-05, "epoch": 0.2204667375902578, "percentage": 12.17, "elapsed_time": "3:57:12", "remaining_time": "1 day, 4:31:10", "throughput": 560.31, "total_tokens": 7974816} {"current_steps": 4875, "total_steps": 40000, "loss": 0.1608, "lr": 4.819053186187752e-05, "epoch": 0.22069308947690078, "percentage": 12.19, "elapsed_time": "3:57:16", "remaining_time": "1 day, 4:29:33", "throughput": 560.73, "total_tokens": 7982656} {"current_steps": 4880, "total_steps": 40000, "loss": 0.194, "lr": 4.818686302903736e-05, "epoch": 0.22091944136354377, "percentage": 12.2, "elapsed_time": "3:57:19", "remaining_time": "1 day, 4:27:56", "throughput": 561.18, "total_tokens": 7990816} {"current_steps": 4885, "total_steps": 40000, "loss": 0.1527, "lr": 4.818319062049154e-05, "epoch": 0.22114579325018674, "percentage": 12.21, "elapsed_time": "3:57:22", "remaining_time": "1 day, 4:26:20", "throughput": 561.67, "total_tokens": 7999552} {"current_steps": 4890, "total_steps": 40000, "loss": 0.1619, "lr": 4.817951463680639e-05, "epoch": 0.2213721451368297, "percentage": 12.22, "elapsed_time": "3:57:26", "remaining_time": "1 day, 4:24:45", "throughput": 562.18, "total_tokens": 8008800} {"current_steps": 4895, "total_steps": 40000, "loss": 0.1337, "lr": 4.817583507854879e-05, "epoch": 0.2215984970234727, "percentage": 12.24, "elapsed_time": "3:57:29", "remaining_time": "1 day, 4:23:09", "throughput": 562.63, "total_tokens": 8017056} {"current_steps": 4900, "total_steps": 40000, "loss": 0.1438, "lr": 4.817215194628617e-05, "epoch": 0.22182484891011567, "percentage": 12.25, "elapsed_time": "3:57:32", "remaining_time": "1 day, 4:21:33", "throughput": 563.04, "total_tokens": 8024640} {"current_steps": 4905, "total_steps": 40000, "loss": 0.1185, "lr": 4.816846524058653e-05, "epoch": 0.22205120079675864, "percentage": 12.26, "elapsed_time": "3:57:35", "remaining_time": "1 day, 4:19:57", "throughput": 563.46, "total_tokens": 8032448} {"current_steps": 4910, "total_steps": 40000, "loss": 0.185, "lr": 4.816477496201839e-05, "epoch": 0.2222775526834016, "percentage": 12.28, "elapsed_time": "3:57:38", "remaining_time": "1 day, 4:18:21", "throughput": 563.9, "total_tokens": 8040416} {"current_steps": 4915, "total_steps": 40000, "loss": 0.1777, "lr": 4.8161081111150845e-05, "epoch": 0.2225039045700446, "percentage": 12.29, "elapsed_time": "3:57:41", "remaining_time": "1 day, 4:16:45", "throughput": 564.33, "total_tokens": 8048256} {"current_steps": 4920, "total_steps": 40000, "loss": 0.224, "lr": 4.815738368855354e-05, "epoch": 0.22273025645668756, "percentage": 12.3, "elapsed_time": "3:57:44", "remaining_time": "1 day, 4:15:09", "throughput": 564.74, "total_tokens": 8055872} {"current_steps": 4925, "total_steps": 40000, "loss": 0.202, "lr": 4.815368269479664e-05, "epoch": 0.22295660834333053, "percentage": 12.31, "elapsed_time": "3:57:47", "remaining_time": "1 day, 4:13:33", "throughput": 565.17, "total_tokens": 8063808} {"current_steps": 4930, "total_steps": 40000, "loss": 0.1177, "lr": 4.814997813045092e-05, "epoch": 0.22318296022997353, "percentage": 12.32, "elapsed_time": "3:57:51", "remaining_time": "1 day, 4:11:59", "throughput": 565.65, "total_tokens": 8072576} {"current_steps": 4935, "total_steps": 40000, "loss": 0.1176, "lr": 4.814626999608764e-05, "epoch": 0.2234093121166165, "percentage": 12.34, "elapsed_time": "3:57:54", "remaining_time": "1 day, 4:10:25", "throughput": 566.11, "total_tokens": 8080864} {"current_steps": 4940, "total_steps": 40000, "loss": 0.179, "lr": 4.814255829227865e-05, "epoch": 0.22363566400325946, "percentage": 12.35, "elapsed_time": "3:57:57", "remaining_time": "1 day, 4:08:51", "throughput": 566.57, "total_tokens": 8089248} {"current_steps": 4945, "total_steps": 40000, "loss": 0.1414, "lr": 4.813884301959635e-05, "epoch": 0.22386201588990245, "percentage": 12.36, "elapsed_time": "3:58:00", "remaining_time": "1 day, 4:07:16", "throughput": 567.0, "total_tokens": 8097184} {"current_steps": 4950, "total_steps": 40000, "loss": 0.1549, "lr": 4.813512417861368e-05, "epoch": 0.22408836777654542, "percentage": 12.38, "elapsed_time": "3:58:03", "remaining_time": "1 day, 4:05:42", "throughput": 567.45, "total_tokens": 8105408} {"current_steps": 4955, "total_steps": 40000, "loss": 0.1194, "lr": 4.813140176990411e-05, "epoch": 0.2243147196631884, "percentage": 12.39, "elapsed_time": "3:58:07", "remaining_time": "1 day, 4:04:07", "throughput": 567.89, "total_tokens": 8113536} {"current_steps": 4960, "total_steps": 40000, "loss": 0.1501, "lr": 4.8127675794041714e-05, "epoch": 0.22454107154983136, "percentage": 12.4, "elapsed_time": "3:58:10", "remaining_time": "1 day, 4:02:34", "throughput": 568.34, "total_tokens": 8121728} {"current_steps": 4965, "total_steps": 40000, "loss": 0.2141, "lr": 4.812394625160107e-05, "epoch": 0.22476742343647435, "percentage": 12.41, "elapsed_time": "3:58:13", "remaining_time": "1 day, 4:01:01", "throughput": 568.85, "total_tokens": 8130912} {"current_steps": 4970, "total_steps": 40000, "loss": 0.1548, "lr": 4.812021314315732e-05, "epoch": 0.22499377532311732, "percentage": 12.43, "elapsed_time": "3:58:16", "remaining_time": "1 day, 3:59:27", "throughput": 569.26, "total_tokens": 8138592} {"current_steps": 4975, "total_steps": 40000, "loss": 0.1608, "lr": 4.811647646928616e-05, "epoch": 0.22522012720976028, "percentage": 12.44, "elapsed_time": "3:58:20", "remaining_time": "1 day, 3:57:56", "throughput": 569.76, "total_tokens": 8147648} {"current_steps": 4980, "total_steps": 40000, "loss": 0.1852, "lr": 4.8112736230563814e-05, "epoch": 0.22544647909640328, "percentage": 12.45, "elapsed_time": "3:58:23", "remaining_time": "1 day, 3:56:23", "throughput": 570.21, "total_tokens": 8155968} {"current_steps": 4985, "total_steps": 40000, "loss": 0.1145, "lr": 4.81089924275671e-05, "epoch": 0.22567283098304625, "percentage": 12.46, "elapsed_time": "3:58:26", "remaining_time": "1 day, 3:54:50", "throughput": 570.62, "total_tokens": 8163584} {"current_steps": 4990, "total_steps": 40000, "loss": 0.1475, "lr": 4.810524506087335e-05, "epoch": 0.2258991828696892, "percentage": 12.47, "elapsed_time": "3:58:29", "remaining_time": "1 day, 3:53:17", "throughput": 571.03, "total_tokens": 8171296} {"current_steps": 4995, "total_steps": 40000, "loss": 0.1582, "lr": 4.810149413106044e-05, "epoch": 0.22612553475633218, "percentage": 12.49, "elapsed_time": "3:58:32", "remaining_time": "1 day, 3:51:43", "throughput": 571.44, "total_tokens": 8178912} {"current_steps": 5000, "total_steps": 40000, "loss": 0.1593, "lr": 4.809773963870684e-05, "epoch": 0.22635188664297518, "percentage": 12.5, "elapsed_time": "3:58:36", "remaining_time": "1 day, 3:50:12", "throughput": 571.96, "total_tokens": 8188256} {"current_steps": 5000, "total_steps": 40000, "eval_loss": 0.1597670018672943, "epoch": 0.22635188664297518, "percentage": 12.5, "elapsed_time": "4:06:18", "remaining_time": "1 day, 4:44:12", "throughput": 554.05, "total_tokens": 8188256} {"current_steps": 5005, "total_steps": 40000, "loss": 0.1946, "lr": 4.809398158439151e-05, "epoch": 0.22657823852961814, "percentage": 12.51, "elapsed_time": "4:06:22", "remaining_time": "1 day, 4:42:42", "throughput": 554.41, "total_tokens": 8195840} {"current_steps": 5010, "total_steps": 40000, "loss": 0.1229, "lr": 4.8090219968694005e-05, "epoch": 0.2268045904162611, "percentage": 12.53, "elapsed_time": "4:06:26", "remaining_time": "1 day, 4:41:06", "throughput": 554.83, "total_tokens": 8203808} {"current_steps": 5015, "total_steps": 40000, "loss": 0.1259, "lr": 4.808645479219442e-05, "epoch": 0.2270309423029041, "percentage": 12.54, "elapsed_time": "4:06:29", "remaining_time": "1 day, 4:39:31", "throughput": 555.28, "total_tokens": 8212224} {"current_steps": 5020, "total_steps": 40000, "loss": 0.1613, "lr": 4.8082686055473375e-05, "epoch": 0.22725729418954707, "percentage": 12.55, "elapsed_time": "4:06:32", "remaining_time": "1 day, 4:37:55", "throughput": 555.7, "total_tokens": 8220192} {"current_steps": 5025, "total_steps": 40000, "loss": 0.1798, "lr": 4.8078913759112066e-05, "epoch": 0.22748364607619004, "percentage": 12.56, "elapsed_time": "4:06:35", "remaining_time": "1 day, 4:36:20", "throughput": 556.12, "total_tokens": 8228128} {"current_steps": 5030, "total_steps": 40000, "loss": 0.2023, "lr": 4.807513790369223e-05, "epoch": 0.22770999796283303, "percentage": 12.57, "elapsed_time": "4:06:38", "remaining_time": "1 day, 4:34:45", "throughput": 556.56, "total_tokens": 8236416} {"current_steps": 5035, "total_steps": 40000, "loss": 0.1328, "lr": 4.8071358489796145e-05, "epoch": 0.227936349849476, "percentage": 12.59, "elapsed_time": "4:06:41", "remaining_time": "1 day, 4:33:09", "throughput": 556.97, "total_tokens": 8244192} {"current_steps": 5040, "total_steps": 40000, "loss": 0.1871, "lr": 4.806757551800665e-05, "epoch": 0.22816270173611897, "percentage": 12.6, "elapsed_time": "4:06:44", "remaining_time": "1 day, 4:31:34", "throughput": 557.37, "total_tokens": 8251872} {"current_steps": 5045, "total_steps": 40000, "loss": 0.1847, "lr": 4.806378898890713e-05, "epoch": 0.22838905362276193, "percentage": 12.61, "elapsed_time": "4:06:48", "remaining_time": "1 day, 4:30:00", "throughput": 557.82, "total_tokens": 8260288} {"current_steps": 5050, "total_steps": 40000, "loss": 0.1187, "lr": 4.80599989030815e-05, "epoch": 0.22861540550940493, "percentage": 12.62, "elapsed_time": "4:06:51", "remaining_time": "1 day, 4:28:25", "throughput": 558.23, "total_tokens": 8268128} {"current_steps": 5055, "total_steps": 40000, "loss": 0.1964, "lr": 4.805620526111426e-05, "epoch": 0.2288417573960479, "percentage": 12.64, "elapsed_time": "4:06:54", "remaining_time": "1 day, 4:26:51", "throughput": 558.67, "total_tokens": 8276448} {"current_steps": 5060, "total_steps": 40000, "loss": 0.1355, "lr": 4.805240806359042e-05, "epoch": 0.22906810928269086, "percentage": 12.65, "elapsed_time": "4:06:57", "remaining_time": "1 day, 4:25:19", "throughput": 559.07, "total_tokens": 8284128} {"current_steps": 5065, "total_steps": 40000, "loss": 0.1918, "lr": 4.804860731109557e-05, "epoch": 0.22929446116933386, "percentage": 12.66, "elapsed_time": "4:07:01", "remaining_time": "1 day, 4:23:45", "throughput": 559.53, "total_tokens": 8292800} {"current_steps": 5070, "total_steps": 40000, "loss": 0.1312, "lr": 4.804480300421581e-05, "epoch": 0.22952081305597682, "percentage": 12.68, "elapsed_time": "4:07:04", "remaining_time": "1 day, 4:22:11", "throughput": 559.93, "total_tokens": 8300448} {"current_steps": 5075, "total_steps": 40000, "loss": 0.1752, "lr": 4.804099514353784e-05, "epoch": 0.2297471649426198, "percentage": 12.69, "elapsed_time": "4:07:07", "remaining_time": "1 day, 4:20:38", "throughput": 560.35, "total_tokens": 8308544} {"current_steps": 5080, "total_steps": 40000, "loss": 0.1424, "lr": 4.8037183729648867e-05, "epoch": 0.22997351682926276, "percentage": 12.7, "elapsed_time": "4:07:10", "remaining_time": "1 day, 4:19:05", "throughput": 560.79, "total_tokens": 8316800} {"current_steps": 5085, "total_steps": 40000, "loss": 0.1252, "lr": 4.803336876313666e-05, "epoch": 0.23019986871590575, "percentage": 12.71, "elapsed_time": "4:07:13", "remaining_time": "1 day, 4:17:33", "throughput": 561.27, "total_tokens": 8325792} {"current_steps": 5090, "total_steps": 40000, "loss": 0.1681, "lr": 4.802955024458953e-05, "epoch": 0.23042622060254872, "percentage": 12.72, "elapsed_time": "4:07:16", "remaining_time": "1 day, 4:16:00", "throughput": 561.68, "total_tokens": 8333600} {"current_steps": 5095, "total_steps": 40000, "loss": 0.1657, "lr": 4.802572817459634e-05, "epoch": 0.2306525724891917, "percentage": 12.74, "elapsed_time": "4:07:20", "remaining_time": "1 day, 4:14:27", "throughput": 562.08, "total_tokens": 8341344} {"current_steps": 5100, "total_steps": 40000, "loss": 0.1728, "lr": 4.802190255374651e-05, "epoch": 0.23087892437583468, "percentage": 12.75, "elapsed_time": "4:07:23", "remaining_time": "1 day, 4:12:54", "throughput": 562.49, "total_tokens": 8349248} {"current_steps": 5105, "total_steps": 40000, "loss": 0.1524, "lr": 4.801807338263e-05, "epoch": 0.23110527626247765, "percentage": 12.76, "elapsed_time": "4:07:26", "remaining_time": "1 day, 4:11:23", "throughput": 562.97, "total_tokens": 8358144} {"current_steps": 5110, "total_steps": 40000, "loss": 0.1126, "lr": 4.8014240661837306e-05, "epoch": 0.23133162814912062, "percentage": 12.78, "elapsed_time": "4:07:29", "remaining_time": "1 day, 4:09:51", "throughput": 563.4, "total_tokens": 8366464} {"current_steps": 5115, "total_steps": 40000, "loss": 0.1476, "lr": 4.80104043919595e-05, "epoch": 0.2315579800357636, "percentage": 12.79, "elapsed_time": "4:07:33", "remaining_time": "1 day, 4:08:19", "throughput": 563.86, "total_tokens": 8375104} {"current_steps": 5120, "total_steps": 40000, "loss": 0.1696, "lr": 4.800656457358815e-05, "epoch": 0.23178433192240658, "percentage": 12.8, "elapsed_time": "4:07:36", "remaining_time": "1 day, 4:06:48", "throughput": 564.3, "total_tokens": 8383424} {"current_steps": 5125, "total_steps": 40000, "loss": 0.1744, "lr": 4.800272120731544e-05, "epoch": 0.23201068380904954, "percentage": 12.81, "elapsed_time": "4:07:39", "remaining_time": "1 day, 4:05:15", "throughput": 564.68, "total_tokens": 8390784} {"current_steps": 5130, "total_steps": 40000, "loss": 0.176, "lr": 4.799887429373404e-05, "epoch": 0.2322370356956925, "percentage": 12.83, "elapsed_time": "4:07:42", "remaining_time": "1 day, 4:03:43", "throughput": 565.08, "total_tokens": 8398368} {"current_steps": 5135, "total_steps": 40000, "loss": 0.1815, "lr": 4.79950238334372e-05, "epoch": 0.2324633875823355, "percentage": 12.84, "elapsed_time": "4:07:45", "remaining_time": "1 day, 4:02:11", "throughput": 565.49, "total_tokens": 8406272} {"current_steps": 5140, "total_steps": 40000, "loss": 0.2061, "lr": 4.799116982701872e-05, "epoch": 0.23268973946897847, "percentage": 12.85, "elapsed_time": "4:07:48", "remaining_time": "1 day, 4:00:41", "throughput": 565.96, "total_tokens": 8415104} {"current_steps": 5145, "total_steps": 40000, "loss": 0.1761, "lr": 4.7987312275072926e-05, "epoch": 0.23291609135562144, "percentage": 12.86, "elapsed_time": "4:07:52", "remaining_time": "1 day, 3:59:11", "throughput": 566.39, "total_tokens": 8423360} {"current_steps": 5150, "total_steps": 40000, "loss": 0.1741, "lr": 4.79834511781947e-05, "epoch": 0.23314244324226444, "percentage": 12.88, "elapsed_time": "4:07:55", "remaining_time": "1 day, 3:57:40", "throughput": 566.81, "total_tokens": 8431328} {"current_steps": 5155, "total_steps": 40000, "loss": 0.1328, "lr": 4.797958653697947e-05, "epoch": 0.2333687951289074, "percentage": 12.89, "elapsed_time": "4:07:58", "remaining_time": "1 day, 3:56:09", "throughput": 567.23, "total_tokens": 8439360} {"current_steps": 5160, "total_steps": 40000, "loss": 0.1136, "lr": 4.7975718352023225e-05, "epoch": 0.23359514701555037, "percentage": 12.9, "elapsed_time": "4:08:01", "remaining_time": "1 day, 3:54:39", "throughput": 567.66, "total_tokens": 8447712} {"current_steps": 5165, "total_steps": 40000, "loss": 0.1396, "lr": 4.7971846623922476e-05, "epoch": 0.23382149890219334, "percentage": 12.91, "elapsed_time": "4:08:04", "remaining_time": "1 day, 3:53:08", "throughput": 568.09, "total_tokens": 8455904} {"current_steps": 5170, "total_steps": 40000, "loss": 0.1319, "lr": 4.7967971353274294e-05, "epoch": 0.23404785078883633, "percentage": 12.93, "elapsed_time": "4:08:07", "remaining_time": "1 day, 3:51:38", "throughput": 568.5, "total_tokens": 8463808} {"current_steps": 5175, "total_steps": 40000, "loss": 0.1255, "lr": 4.79640925406763e-05, "epoch": 0.2342742026754793, "percentage": 12.94, "elapsed_time": "4:08:10", "remaining_time": "1 day, 3:50:08", "throughput": 568.91, "total_tokens": 8471584} {"current_steps": 5180, "total_steps": 40000, "loss": 0.1917, "lr": 4.796021018672664e-05, "epoch": 0.23450055456212227, "percentage": 12.95, "elapsed_time": "4:08:14", "remaining_time": "1 day, 3:48:38", "throughput": 569.34, "total_tokens": 8479808} {"current_steps": 5185, "total_steps": 40000, "loss": 0.1425, "lr": 4.795632429202405e-05, "epoch": 0.23472690644876526, "percentage": 12.96, "elapsed_time": "4:08:17", "remaining_time": "1 day, 3:47:08", "throughput": 569.74, "total_tokens": 8487616} {"current_steps": 5190, "total_steps": 40000, "loss": 0.1551, "lr": 4.795243485716775e-05, "epoch": 0.23495325833540823, "percentage": 12.97, "elapsed_time": "4:08:20", "remaining_time": "1 day, 3:45:39", "throughput": 570.18, "total_tokens": 8495904} {"current_steps": 5195, "total_steps": 40000, "loss": 0.1452, "lr": 4.794854188275757e-05, "epoch": 0.2351796102220512, "percentage": 12.99, "elapsed_time": "4:08:23", "remaining_time": "1 day, 3:44:10", "throughput": 570.61, "total_tokens": 8504160} {"current_steps": 5200, "total_steps": 40000, "loss": 0.1524, "lr": 4.794464536939384e-05, "epoch": 0.2354059621086942, "percentage": 13.0, "elapsed_time": "4:08:26", "remaining_time": "1 day, 3:42:40", "throughput": 570.99, "total_tokens": 8511680} {"current_steps": 5200, "total_steps": 40000, "eval_loss": 0.15864159166812897, "epoch": 0.2354059621086942, "percentage": 13.0, "elapsed_time": "4:16:09", "remaining_time": "1 day, 4:34:16", "throughput": 553.81, "total_tokens": 8511680} {"current_steps": 5205, "total_steps": 40000, "loss": 0.1871, "lr": 4.794074531767745e-05, "epoch": 0.23563231399533716, "percentage": 13.01, "elapsed_time": "4:16:13", "remaining_time": "1 day, 4:32:50", "throughput": 554.17, "total_tokens": 8519552} {"current_steps": 5210, "total_steps": 40000, "loss": 0.152, "lr": 4.7936841728209834e-05, "epoch": 0.23585866588198012, "percentage": 13.03, "elapsed_time": "4:16:16", "remaining_time": "1 day, 4:31:19", "throughput": 554.62, "total_tokens": 8528288} {"current_steps": 5215, "total_steps": 40000, "loss": 0.1719, "lr": 4.7932934601593e-05, "epoch": 0.2360850177686231, "percentage": 13.04, "elapsed_time": "4:16:20", "remaining_time": "1 day, 4:29:47", "throughput": 555.02, "total_tokens": 8536192} {"current_steps": 5220, "total_steps": 40000, "loss": 0.1227, "lr": 4.792902393842943e-05, "epoch": 0.23631136965526608, "percentage": 13.05, "elapsed_time": "4:16:23", "remaining_time": "1 day, 4:28:14", "throughput": 555.39, "total_tokens": 8543520} {"current_steps": 5225, "total_steps": 40000, "loss": 0.1798, "lr": 4.792510973932225e-05, "epoch": 0.23653772154190905, "percentage": 13.06, "elapsed_time": "4:16:26", "remaining_time": "1 day, 4:26:42", "throughput": 555.78, "total_tokens": 8551264} {"current_steps": 5230, "total_steps": 40000, "loss": 0.1851, "lr": 4.7921192004875036e-05, "epoch": 0.23676407342855202, "percentage": 13.08, "elapsed_time": "4:16:29", "remaining_time": "1 day, 4:25:11", "throughput": 556.18, "total_tokens": 8559296} {"current_steps": 5235, "total_steps": 40000, "loss": 0.1487, "lr": 4.791727073569198e-05, "epoch": 0.236990425315195, "percentage": 13.09, "elapsed_time": "4:16:32", "remaining_time": "1 day, 4:23:40", "throughput": 556.62, "total_tokens": 8567808} {"current_steps": 5240, "total_steps": 40000, "loss": 0.1505, "lr": 4.7913345932377775e-05, "epoch": 0.23721677720183798, "percentage": 13.1, "elapsed_time": "4:16:35", "remaining_time": "1 day, 4:22:09", "throughput": 557.03, "total_tokens": 8575936} {"current_steps": 5245, "total_steps": 40000, "loss": 0.1433, "lr": 4.790941759553769e-05, "epoch": 0.23744312908848095, "percentage": 13.11, "elapsed_time": "4:16:39", "remaining_time": "1 day, 4:20:38", "throughput": 557.46, "total_tokens": 8584256} {"current_steps": 5250, "total_steps": 40000, "loss": 0.1249, "lr": 4.79054857257775e-05, "epoch": 0.23766948097512391, "percentage": 13.12, "elapsed_time": "4:16:42", "remaining_time": "1 day, 4:19:08", "throughput": 557.9, "total_tokens": 8592928} {"current_steps": 5255, "total_steps": 40000, "loss": 0.1527, "lr": 4.790155032370357e-05, "epoch": 0.2378958328617669, "percentage": 13.14, "elapsed_time": "4:16:45", "remaining_time": "1 day, 4:17:37", "throughput": 558.29, "total_tokens": 8600672} {"current_steps": 5260, "total_steps": 40000, "loss": 0.1304, "lr": 4.789761138992278e-05, "epoch": 0.23812218474840988, "percentage": 13.15, "elapsed_time": "4:16:48", "remaining_time": "1 day, 4:16:06", "throughput": 558.7, "total_tokens": 8608832} {"current_steps": 5265, "total_steps": 40000, "loss": 0.1653, "lr": 4.7893668925042565e-05, "epoch": 0.23834853663505284, "percentage": 13.16, "elapsed_time": "4:16:51", "remaining_time": "1 day, 4:14:36", "throughput": 559.09, "total_tokens": 8616480} {"current_steps": 5270, "total_steps": 40000, "loss": 0.0866, "lr": 4.78897229296709e-05, "epoch": 0.23857488852169584, "percentage": 13.18, "elapsed_time": "4:16:54", "remaining_time": "1 day, 4:13:05", "throughput": 559.5, "total_tokens": 8624544} {"current_steps": 5275, "total_steps": 40000, "loss": 0.1699, "lr": 4.7885773404416315e-05, "epoch": 0.2388012404083388, "percentage": 13.19, "elapsed_time": "4:16:57", "remaining_time": "1 day, 4:11:35", "throughput": 559.91, "total_tokens": 8632672} {"current_steps": 5280, "total_steps": 40000, "loss": 0.1054, "lr": 4.788182034988786e-05, "epoch": 0.23902759229498177, "percentage": 13.2, "elapsed_time": "4:17:01", "remaining_time": "1 day, 4:10:05", "throughput": 560.32, "total_tokens": 8640704} {"current_steps": 5285, "total_steps": 40000, "loss": 0.1407, "lr": 4.787786376669516e-05, "epoch": 0.23925394418162477, "percentage": 13.21, "elapsed_time": "4:17:04", "remaining_time": "1 day, 4:08:35", "throughput": 560.71, "total_tokens": 8648544} {"current_steps": 5290, "total_steps": 40000, "loss": 0.1691, "lr": 4.787390365544837e-05, "epoch": 0.23948029606826773, "percentage": 13.23, "elapsed_time": "4:17:07", "remaining_time": "1 day, 4:07:06", "throughput": 561.12, "total_tokens": 8656608} {"current_steps": 5295, "total_steps": 40000, "loss": 0.1735, "lr": 4.786994001675818e-05, "epoch": 0.2397066479549107, "percentage": 13.24, "elapsed_time": "4:17:10", "remaining_time": "1 day, 4:05:37", "throughput": 561.57, "total_tokens": 8665408} {"current_steps": 5300, "total_steps": 40000, "loss": 0.1872, "lr": 4.786597285123584e-05, "epoch": 0.23993299984155367, "percentage": 13.25, "elapsed_time": "4:17:13", "remaining_time": "1 day, 4:04:09", "throughput": 561.99, "total_tokens": 8673792} {"current_steps": 5305, "total_steps": 40000, "loss": 0.1757, "lr": 4.7862002159493135e-05, "epoch": 0.24015935172819666, "percentage": 13.26, "elapsed_time": "4:17:17", "remaining_time": "1 day, 4:02:39", "throughput": 562.38, "total_tokens": 8681536} {"current_steps": 5310, "total_steps": 40000, "loss": 0.1411, "lr": 4.785802794214239e-05, "epoch": 0.24038570361483963, "percentage": 13.28, "elapsed_time": "4:17:20", "remaining_time": "1 day, 4:01:11", "throughput": 562.81, "total_tokens": 8690048} {"current_steps": 5315, "total_steps": 40000, "loss": 0.122, "lr": 4.7854050199796495e-05, "epoch": 0.2406120555014826, "percentage": 13.29, "elapsed_time": "4:17:23", "remaining_time": "1 day, 3:59:42", "throughput": 563.25, "total_tokens": 8698528} {"current_steps": 5320, "total_steps": 40000, "loss": 0.1991, "lr": 4.7850068933068845e-05, "epoch": 0.2408384073881256, "percentage": 13.3, "elapsed_time": "4:17:26", "remaining_time": "1 day, 3:58:13", "throughput": 563.63, "total_tokens": 8706208} {"current_steps": 5325, "total_steps": 40000, "loss": 0.1522, "lr": 4.7846084142573425e-05, "epoch": 0.24106475927476856, "percentage": 13.31, "elapsed_time": "4:17:29", "remaining_time": "1 day, 3:56:45", "throughput": 564.01, "total_tokens": 8713856} {"current_steps": 5330, "total_steps": 40000, "loss": 0.1804, "lr": 4.7842095828924725e-05, "epoch": 0.24129111116141153, "percentage": 13.33, "elapsed_time": "4:17:32", "remaining_time": "1 day, 3:55:16", "throughput": 564.41, "total_tokens": 8721760} {"current_steps": 5335, "total_steps": 40000, "loss": 0.1235, "lr": 4.783810399273779e-05, "epoch": 0.2415174630480545, "percentage": 13.34, "elapsed_time": "4:17:36", "remaining_time": "1 day, 3:53:49", "throughput": 564.86, "total_tokens": 8730656} {"current_steps": 5340, "total_steps": 40000, "loss": 0.1547, "lr": 4.7834108634628226e-05, "epoch": 0.2417438149346975, "percentage": 13.35, "elapsed_time": "4:17:39", "remaining_time": "1 day, 3:52:21", "throughput": 565.23, "total_tokens": 8738176} {"current_steps": 5345, "total_steps": 40000, "loss": 0.1793, "lr": 4.783010975521216e-05, "epoch": 0.24197016682134045, "percentage": 13.36, "elapsed_time": "4:17:42", "remaining_time": "1 day, 3:50:53", "throughput": 565.65, "total_tokens": 8746432} {"current_steps": 5350, "total_steps": 40000, "loss": 0.1531, "lr": 4.782610735510626e-05, "epoch": 0.24219651870798342, "percentage": 13.38, "elapsed_time": "4:17:45", "remaining_time": "1 day, 3:49:26", "throughput": 566.07, "total_tokens": 8754784} {"current_steps": 5355, "total_steps": 40000, "loss": 0.1662, "lr": 4.782210143492776e-05, "epoch": 0.24242287059462642, "percentage": 13.39, "elapsed_time": "4:17:48", "remaining_time": "1 day, 3:47:58", "throughput": 566.51, "total_tokens": 8763264} {"current_steps": 5360, "total_steps": 40000, "loss": 0.1632, "lr": 4.781809199529442e-05, "epoch": 0.24264922248126938, "percentage": 13.4, "elapsed_time": "4:17:52", "remaining_time": "1 day, 3:46:31", "throughput": 566.91, "total_tokens": 8771296} {"current_steps": 5365, "total_steps": 40000, "loss": 0.1494, "lr": 4.781407903682454e-05, "epoch": 0.24287557436791235, "percentage": 13.41, "elapsed_time": "4:17:55", "remaining_time": "1 day, 3:45:05", "throughput": 567.36, "total_tokens": 8780128} {"current_steps": 5370, "total_steps": 40000, "loss": 0.1526, "lr": 4.781006256013698e-05, "epoch": 0.24310192625455534, "percentage": 13.43, "elapsed_time": "4:17:58", "remaining_time": "1 day, 3:43:38", "throughput": 567.79, "total_tokens": 8788608} {"current_steps": 5375, "total_steps": 40000, "loss": 0.1238, "lr": 4.7806042565851115e-05, "epoch": 0.2433282781411983, "percentage": 13.44, "elapsed_time": "4:18:01", "remaining_time": "1 day, 3:42:12", "throughput": 568.2, "total_tokens": 8796832} {"current_steps": 5380, "total_steps": 40000, "loss": 0.1637, "lr": 4.7802019054586895e-05, "epoch": 0.24355463002784128, "percentage": 13.45, "elapsed_time": "4:18:04", "remaining_time": "1 day, 3:40:45", "throughput": 568.58, "total_tokens": 8804480} {"current_steps": 5385, "total_steps": 40000, "loss": 0.1685, "lr": 4.779799202696479e-05, "epoch": 0.24378098191448425, "percentage": 13.46, "elapsed_time": "4:18:08", "remaining_time": "1 day, 3:39:18", "throughput": 568.99, "total_tokens": 8812608} {"current_steps": 5390, "total_steps": 40000, "loss": 0.2228, "lr": 4.779396148360581e-05, "epoch": 0.24400733380112724, "percentage": 13.48, "elapsed_time": "4:18:11", "remaining_time": "1 day, 3:37:52", "throughput": 569.43, "total_tokens": 8821312} {"current_steps": 5395, "total_steps": 40000, "loss": 0.1051, "lr": 4.7789927425131517e-05, "epoch": 0.2442336856877702, "percentage": 13.49, "elapsed_time": "4:18:14", "remaining_time": "1 day, 3:36:26", "throughput": 569.84, "total_tokens": 8829408} {"current_steps": 5400, "total_steps": 40000, "loss": 0.1504, "lr": 4.778588985216403e-05, "epoch": 0.24446003757441317, "percentage": 13.5, "elapsed_time": "4:18:17", "remaining_time": "1 day, 3:35:00", "throughput": 570.25, "total_tokens": 8837568} {"current_steps": 5400, "total_steps": 40000, "eval_loss": 0.15712136030197144, "epoch": 0.24446003757441317, "percentage": 13.5, "elapsed_time": "4:26:00", "remaining_time": "1 day, 4:24:25", "throughput": 553.71, "total_tokens": 8837568} {"current_steps": 5405, "total_steps": 40000, "loss": 0.1702, "lr": 4.778184876532598e-05, "epoch": 0.24468638946105617, "percentage": 13.51, "elapsed_time": "4:26:04", "remaining_time": "1 day, 4:23:02", "throughput": 554.05, "total_tokens": 8845152} {"current_steps": 5410, "total_steps": 40000, "loss": 0.1705, "lr": 4.7777804165240556e-05, "epoch": 0.24491274134769914, "percentage": 13.53, "elapsed_time": "4:26:07", "remaining_time": "1 day, 4:21:33", "throughput": 554.45, "total_tokens": 8853280} {"current_steps": 5415, "total_steps": 40000, "loss": 0.1509, "lr": 4.7773756052531485e-05, "epoch": 0.2451390932343421, "percentage": 13.54, "elapsed_time": "4:26:11", "remaining_time": "1 day, 4:20:05", "throughput": 554.87, "total_tokens": 8861888} {"current_steps": 5420, "total_steps": 40000, "loss": 0.1658, "lr": 4.7769704427823035e-05, "epoch": 0.24536544512098507, "percentage": 13.55, "elapsed_time": "4:26:14", "remaining_time": "1 day, 4:18:38", "throughput": 555.35, "total_tokens": 8871360} {"current_steps": 5425, "total_steps": 40000, "loss": 0.2046, "lr": 4.776564929174003e-05, "epoch": 0.24559179700762807, "percentage": 13.56, "elapsed_time": "4:26:17", "remaining_time": "1 day, 4:17:09", "throughput": 555.73, "total_tokens": 8879168} {"current_steps": 5430, "total_steps": 40000, "loss": 0.1232, "lr": 4.7761590644907806e-05, "epoch": 0.24581814889427103, "percentage": 13.58, "elapsed_time": "4:26:20", "remaining_time": "1 day, 4:15:41", "throughput": 556.12, "total_tokens": 8887296} {"current_steps": 5435, "total_steps": 40000, "loss": 0.1919, "lr": 4.7757528487952263e-05, "epoch": 0.246044500780914, "percentage": 13.59, "elapsed_time": "4:26:23", "remaining_time": "1 day, 4:14:13", "throughput": 556.51, "total_tokens": 8895264} {"current_steps": 5440, "total_steps": 40000, "loss": 0.1287, "lr": 4.7753462821499836e-05, "epoch": 0.246270852667557, "percentage": 13.6, "elapsed_time": "4:26:27", "remaining_time": "1 day, 4:12:45", "throughput": 556.92, "total_tokens": 8903488} {"current_steps": 5445, "total_steps": 40000, "loss": 0.1539, "lr": 4.774939364617751e-05, "epoch": 0.24649720455419996, "percentage": 13.61, "elapsed_time": "4:26:30", "remaining_time": "1 day, 4:11:17", "throughput": 557.3, "total_tokens": 8911360} {"current_steps": 5450, "total_steps": 40000, "loss": 0.2255, "lr": 4.7745320962612795e-05, "epoch": 0.24672355644084293, "percentage": 13.63, "elapsed_time": "4:26:33", "remaining_time": "1 day, 4:09:48", "throughput": 557.65, "total_tokens": 8918688} {"current_steps": 5455, "total_steps": 40000, "loss": 0.1433, "lr": 4.7741244771433756e-05, "epoch": 0.24694990832748592, "percentage": 13.64, "elapsed_time": "4:26:36", "remaining_time": "1 day, 4:08:21", "throughput": 558.05, "total_tokens": 8926784} {"current_steps": 5460, "total_steps": 40000, "loss": 0.1337, "lr": 4.7737165073268985e-05, "epoch": 0.2471762602141289, "percentage": 13.65, "elapsed_time": "4:26:39", "remaining_time": "1 day, 4:06:53", "throughput": 558.42, "total_tokens": 8934528} {"current_steps": 5465, "total_steps": 40000, "loss": 0.1413, "lr": 4.7733081868747626e-05, "epoch": 0.24740261210077186, "percentage": 13.66, "elapsed_time": "4:26:42", "remaining_time": "1 day, 4:05:25", "throughput": 558.82, "total_tokens": 8942560} {"current_steps": 5470, "total_steps": 40000, "loss": 0.1599, "lr": 4.772899515849936e-05, "epoch": 0.24762896398741482, "percentage": 13.68, "elapsed_time": "4:26:45", "remaining_time": "1 day, 4:03:58", "throughput": 559.22, "total_tokens": 8950848} {"current_steps": 5475, "total_steps": 40000, "loss": 0.1973, "lr": 4.7724904943154414e-05, "epoch": 0.24785531587405782, "percentage": 13.69, "elapsed_time": "4:26:48", "remaining_time": "1 day, 4:02:31", "throughput": 559.59, "total_tokens": 8958528} {"current_steps": 5480, "total_steps": 40000, "loss": 0.2326, "lr": 4.772081122334354e-05, "epoch": 0.24808166776070079, "percentage": 13.7, "elapsed_time": "4:26:52", "remaining_time": "1 day, 4:01:05", "throughput": 559.99, "total_tokens": 8966624} {"current_steps": 5485, "total_steps": 40000, "loss": 0.0948, "lr": 4.771671399969806e-05, "epoch": 0.24830801964734375, "percentage": 13.71, "elapsed_time": "4:26:55", "remaining_time": "1 day, 3:59:38", "throughput": 560.37, "total_tokens": 8974560} {"current_steps": 5490, "total_steps": 40000, "loss": 0.1629, "lr": 4.7712613272849794e-05, "epoch": 0.24853437153398675, "percentage": 13.73, "elapsed_time": "4:26:58", "remaining_time": "1 day, 3:58:12", "throughput": 560.79, "total_tokens": 8983040} {"current_steps": 5495, "total_steps": 40000, "loss": 0.1498, "lr": 4.770850904343114e-05, "epoch": 0.24876072342062971, "percentage": 13.74, "elapsed_time": "4:27:01", "remaining_time": "1 day, 3:56:46", "throughput": 561.16, "total_tokens": 8990688} {"current_steps": 5500, "total_steps": 40000, "loss": 0.111, "lr": 4.770440131207502e-05, "epoch": 0.24898707530727268, "percentage": 13.75, "elapsed_time": "4:27:04", "remaining_time": "1 day, 3:55:19", "throughput": 561.54, "total_tokens": 8998624} {"current_steps": 5505, "total_steps": 40000, "loss": 0.195, "lr": 4.7700290079414896e-05, "epoch": 0.24921342719391565, "percentage": 13.76, "elapsed_time": "4:27:08", "remaining_time": "1 day, 3:53:53", "throughput": 561.91, "total_tokens": 9006368} {"current_steps": 5510, "total_steps": 40000, "loss": 0.1595, "lr": 4.769617534608477e-05, "epoch": 0.24943977908055864, "percentage": 13.78, "elapsed_time": "4:27:11", "remaining_time": "1 day, 3:52:27", "throughput": 562.29, "total_tokens": 9014112} {"current_steps": 5515, "total_steps": 40000, "loss": 0.1462, "lr": 4.7692057112719193e-05, "epoch": 0.2496661309672016, "percentage": 13.79, "elapsed_time": "4:27:14", "remaining_time": "1 day, 3:51:01", "throughput": 562.67, "total_tokens": 9022080} {"current_steps": 5520, "total_steps": 40000, "loss": 0.1209, "lr": 4.7687935379953234e-05, "epoch": 0.24989248285384458, "percentage": 13.8, "elapsed_time": "4:27:17", "remaining_time": "1 day, 3:49:36", "throughput": 563.08, "total_tokens": 9030400} {"current_steps": 5525, "total_steps": 40000, "loss": 0.1532, "lr": 4.7683810148422534e-05, "epoch": 0.2501188347404876, "percentage": 13.81, "elapsed_time": "4:27:20", "remaining_time": "1 day, 3:48:11", "throughput": 563.49, "total_tokens": 9038752} {"current_steps": 5530, "total_steps": 40000, "loss": 0.1356, "lr": 4.767968141876324e-05, "epoch": 0.2503451866271305, "percentage": 13.83, "elapsed_time": "4:27:23", "remaining_time": "1 day, 3:46:46", "throughput": 563.91, "total_tokens": 9047360} {"current_steps": 5535, "total_steps": 40000, "loss": 0.1722, "lr": 4.767554919161207e-05, "epoch": 0.2505715385137735, "percentage": 13.84, "elapsed_time": "4:27:27", "remaining_time": "1 day, 3:45:21", "throughput": 564.31, "total_tokens": 9055456} {"current_steps": 5540, "total_steps": 40000, "loss": 0.229, "lr": 4.767141346760624e-05, "epoch": 0.2507978904004165, "percentage": 13.85, "elapsed_time": "4:27:30", "remaining_time": "1 day, 3:43:56", "throughput": 564.7, "total_tokens": 9063616} {"current_steps": 5545, "total_steps": 40000, "loss": 0.139, "lr": 4.766727424738356e-05, "epoch": 0.25102424228705944, "percentage": 13.86, "elapsed_time": "4:27:33", "remaining_time": "1 day, 3:42:30", "throughput": 565.06, "total_tokens": 9071072} {"current_steps": 5550, "total_steps": 40000, "loss": 0.1501, "lr": 4.7663131531582325e-05, "epoch": 0.25125059417370244, "percentage": 13.88, "elapsed_time": "4:27:36", "remaining_time": "1 day, 3:41:06", "throughput": 565.44, "total_tokens": 9078912} {"current_steps": 5555, "total_steps": 40000, "loss": 0.1379, "lr": 4.765898532084142e-05, "epoch": 0.25147694606034543, "percentage": 13.89, "elapsed_time": "4:27:39", "remaining_time": "1 day, 3:39:41", "throughput": 565.8, "total_tokens": 9086528} {"current_steps": 5560, "total_steps": 40000, "loss": 0.1661, "lr": 4.765483561580022e-05, "epoch": 0.25170329794698837, "percentage": 13.9, "elapsed_time": "4:27:42", "remaining_time": "1 day, 3:38:16", "throughput": 566.18, "total_tokens": 9094336} {"current_steps": 5565, "total_steps": 40000, "loss": 0.1748, "lr": 4.7650682417098666e-05, "epoch": 0.25192964983363136, "percentage": 13.91, "elapsed_time": "4:27:45", "remaining_time": "1 day, 3:36:52", "throughput": 566.58, "total_tokens": 9102656} {"current_steps": 5570, "total_steps": 40000, "loss": 0.195, "lr": 4.7646525725377244e-05, "epoch": 0.25215600172027436, "percentage": 13.93, "elapsed_time": "4:27:49", "remaining_time": "1 day, 3:35:28", "throughput": 567.0, "total_tokens": 9111136} {"current_steps": 5575, "total_steps": 40000, "loss": 0.2103, "lr": 4.764236554127696e-05, "epoch": 0.2523823536069173, "percentage": 13.94, "elapsed_time": "4:27:52", "remaining_time": "1 day, 3:34:04", "throughput": 567.39, "total_tokens": 9119232} {"current_steps": 5580, "total_steps": 40000, "loss": 0.1689, "lr": 4.7638201865439356e-05, "epoch": 0.2526087054935603, "percentage": 13.95, "elapsed_time": "4:27:55", "remaining_time": "1 day, 3:32:41", "throughput": 567.79, "total_tokens": 9127520} {"current_steps": 5585, "total_steps": 40000, "loss": 0.1662, "lr": 4.7634034698506545e-05, "epoch": 0.2528350573802033, "percentage": 13.96, "elapsed_time": "4:27:58", "remaining_time": "1 day, 3:31:17", "throughput": 568.15, "total_tokens": 9135104} {"current_steps": 5590, "total_steps": 40000, "loss": 0.1532, "lr": 4.762986404112115e-05, "epoch": 0.2530614092668462, "percentage": 13.98, "elapsed_time": "4:28:01", "remaining_time": "1 day, 3:29:53", "throughput": 568.54, "total_tokens": 9143200} {"current_steps": 5595, "total_steps": 40000, "loss": 0.1467, "lr": 4.762568989392633e-05, "epoch": 0.2532877611534892, "percentage": 13.99, "elapsed_time": "4:28:05", "remaining_time": "1 day, 3:28:30", "throughput": 568.96, "total_tokens": 9151680} {"current_steps": 5600, "total_steps": 40000, "loss": 0.1704, "lr": 4.76215122575658e-05, "epoch": 0.2535141130401322, "percentage": 14.0, "elapsed_time": "4:28:08", "remaining_time": "1 day, 3:27:08", "throughput": 569.36, "total_tokens": 9160064} {"current_steps": 5600, "total_steps": 40000, "eval_loss": 0.15573719143867493, "epoch": 0.2535141130401322, "percentage": 14.0, "elapsed_time": "4:35:51", "remaining_time": "1 day, 4:14:30", "throughput": 553.44, "total_tokens": 9160064} {"current_steps": 5605, "total_steps": 40000, "loss": 0.1814, "lr": 4.7617331132683795e-05, "epoch": 0.25374046492677516, "percentage": 14.01, "elapsed_time": "4:35:55", "remaining_time": "1 day, 4:13:10", "throughput": 553.8, "total_tokens": 9168192} {"current_steps": 5610, "total_steps": 40000, "loss": 0.199, "lr": 4.7613146519925105e-05, "epoch": 0.25396681681341815, "percentage": 14.03, "elapsed_time": "4:35:58", "remaining_time": "1 day, 4:11:44", "throughput": 554.18, "total_tokens": 9176288} {"current_steps": 5615, "total_steps": 40000, "loss": 0.1658, "lr": 4.7608958419935045e-05, "epoch": 0.2541931687000611, "percentage": 14.04, "elapsed_time": "4:36:01", "remaining_time": "1 day, 4:10:19", "throughput": 554.57, "total_tokens": 9184576} {"current_steps": 5620, "total_steps": 40000, "loss": 0.1303, "lr": 4.760476683335948e-05, "epoch": 0.2544195205867041, "percentage": 14.05, "elapsed_time": "4:36:04", "remaining_time": "1 day, 4:08:54", "throughput": 554.97, "total_tokens": 9193056} {"current_steps": 5625, "total_steps": 40000, "loss": 0.1548, "lr": 4.760057176084479e-05, "epoch": 0.2546458724733471, "percentage": 14.06, "elapsed_time": "4:36:08", "remaining_time": "1 day, 4:07:29", "throughput": 555.38, "total_tokens": 9201664} {"current_steps": 5630, "total_steps": 40000, "loss": 0.1454, "lr": 4.759637320303793e-05, "epoch": 0.25487222435999, "percentage": 14.07, "elapsed_time": "4:36:11", "remaining_time": "1 day, 4:06:04", "throughput": 555.79, "total_tokens": 9210208} {"current_steps": 5635, "total_steps": 40000, "loss": 0.1229, "lr": 4.759217116058635e-05, "epoch": 0.255098576246633, "percentage": 14.09, "elapsed_time": "4:36:14", "remaining_time": "1 day, 4:04:39", "throughput": 556.19, "total_tokens": 9218496} {"current_steps": 5640, "total_steps": 40000, "loss": 0.151, "lr": 4.758796563413807e-05, "epoch": 0.255324928133276, "percentage": 14.1, "elapsed_time": "4:36:17", "remaining_time": "1 day, 4:03:13", "throughput": 556.55, "total_tokens": 9226208} {"current_steps": 5645, "total_steps": 40000, "loss": 0.137, "lr": 4.758375662434163e-05, "epoch": 0.25555128001991895, "percentage": 14.11, "elapsed_time": "4:36:20", "remaining_time": "1 day, 4:01:49", "throughput": 556.94, "total_tokens": 9234496} {"current_steps": 5650, "total_steps": 40000, "loss": 0.0843, "lr": 4.7579544131846114e-05, "epoch": 0.25577763190656194, "percentage": 14.12, "elapsed_time": "4:36:24", "remaining_time": "1 day, 4:00:25", "throughput": 557.35, "total_tokens": 9243072} {"current_steps": 5655, "total_steps": 40000, "loss": 0.1313, "lr": 4.757532815730114e-05, "epoch": 0.25600398379320494, "percentage": 14.14, "elapsed_time": "4:36:27", "remaining_time": "1 day, 3:59:00", "throughput": 557.7, "total_tokens": 9250720} {"current_steps": 5660, "total_steps": 40000, "loss": 0.1671, "lr": 4.7571108701356865e-05, "epoch": 0.2562303356798479, "percentage": 14.15, "elapsed_time": "4:36:30", "remaining_time": "1 day, 3:57:35", "throughput": 558.1, "total_tokens": 9259008} {"current_steps": 5665, "total_steps": 40000, "loss": 0.1185, "lr": 4.756688576466398e-05, "epoch": 0.25645668756649087, "percentage": 14.16, "elapsed_time": "4:36:33", "remaining_time": "1 day, 3:56:10", "throughput": 558.45, "total_tokens": 9266496} {"current_steps": 5670, "total_steps": 40000, "loss": 0.1168, "lr": 4.756265934787372e-05, "epoch": 0.25668303945313387, "percentage": 14.17, "elapsed_time": "4:36:36", "remaining_time": "1 day, 3:54:46", "throughput": 558.81, "total_tokens": 9274368} {"current_steps": 5675, "total_steps": 40000, "loss": 0.1349, "lr": 4.755842945163785e-05, "epoch": 0.2569093913397768, "percentage": 14.19, "elapsed_time": "4:36:39", "remaining_time": "1 day, 3:53:22", "throughput": 559.18, "total_tokens": 9282144} {"current_steps": 5680, "total_steps": 40000, "loss": 0.1415, "lr": 4.755419607660867e-05, "epoch": 0.2571357432264198, "percentage": 14.2, "elapsed_time": "4:36:42", "remaining_time": "1 day, 3:51:58", "throughput": 559.57, "total_tokens": 9290464} {"current_steps": 5685, "total_steps": 40000, "loss": 0.1768, "lr": 4.7549959223439016e-05, "epoch": 0.2573620951130628, "percentage": 14.21, "elapsed_time": "4:36:45", "remaining_time": "1 day, 3:50:34", "throughput": 559.94, "total_tokens": 9298336} {"current_steps": 5690, "total_steps": 40000, "loss": 0.1493, "lr": 4.754571889278228e-05, "epoch": 0.25758844699970573, "percentage": 14.22, "elapsed_time": "4:36:49", "remaining_time": "1 day, 3:49:11", "throughput": 560.33, "total_tokens": 9306560} {"current_steps": 5695, "total_steps": 40000, "loss": 0.1675, "lr": 4.754147508529235e-05, "epoch": 0.25781479888634873, "percentage": 14.24, "elapsed_time": "4:36:52", "remaining_time": "1 day, 3:47:48", "throughput": 560.75, "total_tokens": 9315392} {"current_steps": 5700, "total_steps": 40000, "loss": 0.0994, "lr": 4.75372278016237e-05, "epoch": 0.25804115077299167, "percentage": 14.25, "elapsed_time": "4:36:55", "remaining_time": "1 day, 3:46:26", "throughput": 561.16, "total_tokens": 9324096} {"current_steps": 5705, "total_steps": 40000, "loss": 0.155, "lr": 4.753297704243129e-05, "epoch": 0.25826750265963466, "percentage": 14.26, "elapsed_time": "4:36:59", "remaining_time": "1 day, 3:45:04", "throughput": 561.53, "total_tokens": 9332096} {"current_steps": 5710, "total_steps": 40000, "loss": 0.193, "lr": 4.752872280837066e-05, "epoch": 0.25849385454627766, "percentage": 14.27, "elapsed_time": "4:37:02", "remaining_time": "1 day, 3:43:41", "throughput": 561.92, "total_tokens": 9340384} {"current_steps": 5715, "total_steps": 40000, "loss": 0.1618, "lr": 4.752446510009786e-05, "epoch": 0.2587202064329206, "percentage": 14.29, "elapsed_time": "4:37:05", "remaining_time": "1 day, 3:42:18", "throughput": 562.3, "total_tokens": 9348576} {"current_steps": 5720, "total_steps": 40000, "loss": 0.1354, "lr": 4.7520203918269476e-05, "epoch": 0.2589465583195636, "percentage": 14.3, "elapsed_time": "4:37:08", "remaining_time": "1 day, 3:40:55", "throughput": 562.69, "total_tokens": 9356736} {"current_steps": 5725, "total_steps": 40000, "loss": 0.1971, "lr": 4.751593926354265e-05, "epoch": 0.2591729102062066, "percentage": 14.31, "elapsed_time": "4:37:11", "remaining_time": "1 day, 3:39:33", "throughput": 563.08, "total_tokens": 9365088} {"current_steps": 5730, "total_steps": 40000, "loss": 0.1319, "lr": 4.751167113657503e-05, "epoch": 0.2593992620928495, "percentage": 14.32, "elapsed_time": "4:37:15", "remaining_time": "1 day, 3:38:10", "throughput": 563.43, "total_tokens": 9372736} {"current_steps": 5735, "total_steps": 40000, "loss": 0.1981, "lr": 4.7507399538024834e-05, "epoch": 0.2596256139794925, "percentage": 14.34, "elapsed_time": "4:37:18", "remaining_time": "1 day, 3:36:48", "throughput": 563.83, "total_tokens": 9381056} {"current_steps": 5740, "total_steps": 40000, "loss": 0.1626, "lr": 4.750312446855077e-05, "epoch": 0.2598519658661355, "percentage": 14.35, "elapsed_time": "4:37:21", "remaining_time": "1 day, 3:35:26", "throughput": 564.22, "total_tokens": 9389472} {"current_steps": 5745, "total_steps": 40000, "loss": 0.1698, "lr": 4.749884592881212e-05, "epoch": 0.26007831775277845, "percentage": 14.36, "elapsed_time": "4:37:24", "remaining_time": "1 day, 3:34:04", "throughput": 564.59, "total_tokens": 9397312} {"current_steps": 5750, "total_steps": 40000, "loss": 0.1575, "lr": 4.74945639194687e-05, "epoch": 0.26030466963942145, "percentage": 14.37, "elapsed_time": "4:37:27", "remaining_time": "1 day, 3:32:42", "throughput": 564.95, "total_tokens": 9405120} {"current_steps": 5755, "total_steps": 40000, "loss": 0.1223, "lr": 4.749027844118083e-05, "epoch": 0.26053102152606444, "percentage": 14.39, "elapsed_time": "4:37:30", "remaining_time": "1 day, 3:31:20", "throughput": 565.31, "total_tokens": 9412960} {"current_steps": 5760, "total_steps": 40000, "loss": 0.1643, "lr": 4.7485989494609395e-05, "epoch": 0.2607573734127074, "percentage": 14.4, "elapsed_time": "4:37:34", "remaining_time": "1 day, 3:29:59", "throughput": 565.73, "total_tokens": 9421792} {"current_steps": 5765, "total_steps": 40000, "loss": 0.1886, "lr": 4.748169708041581e-05, "epoch": 0.2609837252993504, "percentage": 14.41, "elapsed_time": "4:37:37", "remaining_time": "1 day, 3:28:38", "throughput": 566.11, "total_tokens": 9429920} {"current_steps": 5770, "total_steps": 40000, "loss": 0.1035, "lr": 4.7477401199262004e-05, "epoch": 0.2612100771859934, "percentage": 14.42, "elapsed_time": "4:37:40", "remaining_time": "1 day, 3:27:17", "throughput": 566.49, "total_tokens": 9438080} {"current_steps": 5775, "total_steps": 40000, "loss": 0.1296, "lr": 4.747310185181048e-05, "epoch": 0.2614364290726363, "percentage": 14.44, "elapsed_time": "4:37:43", "remaining_time": "1 day, 3:25:55", "throughput": 566.88, "total_tokens": 9446240} {"current_steps": 5780, "total_steps": 40000, "loss": 0.1902, "lr": 4.746879903872422e-05, "epoch": 0.2616627809592793, "percentage": 14.45, "elapsed_time": "4:37:46", "remaining_time": "1 day, 3:24:35", "throughput": 567.28, "total_tokens": 9454752} {"current_steps": 5785, "total_steps": 40000, "loss": 0.1943, "lr": 4.746449276066679e-05, "epoch": 0.26188913284592225, "percentage": 14.46, "elapsed_time": "4:37:50", "remaining_time": "1 day, 3:23:13", "throughput": 567.63, "total_tokens": 9462368} {"current_steps": 5790, "total_steps": 40000, "loss": 0.1438, "lr": 4.746018301830227e-05, "epoch": 0.26211548473256524, "percentage": 14.47, "elapsed_time": "4:37:53", "remaining_time": "1 day, 3:21:53", "throughput": 568.02, "total_tokens": 9470752} {"current_steps": 5795, "total_steps": 40000, "loss": 0.2134, "lr": 4.7455869812295275e-05, "epoch": 0.26234183661920824, "percentage": 14.49, "elapsed_time": "4:37:56", "remaining_time": "1 day, 3:20:33", "throughput": 568.4, "total_tokens": 9478944} {"current_steps": 5800, "total_steps": 40000, "loss": 0.153, "lr": 4.7451553143310964e-05, "epoch": 0.2625681885058512, "percentage": 14.5, "elapsed_time": "4:37:59", "remaining_time": "1 day, 3:19:12", "throughput": 568.79, "total_tokens": 9487296} {"current_steps": 5800, "total_steps": 40000, "eval_loss": 0.15430735051631927, "epoch": 0.2625681885058512, "percentage": 14.5, "elapsed_time": "4:45:42", "remaining_time": "1 day, 4:04:41", "throughput": 553.44, "total_tokens": 9487296} {"current_steps": 5805, "total_steps": 40000, "loss": 0.1131, "lr": 4.744723301201501e-05, "epoch": 0.26279454039249417, "percentage": 14.51, "elapsed_time": "4:45:46", "remaining_time": "1 day, 4:03:23", "throughput": 553.76, "total_tokens": 9495040} {"current_steps": 5810, "total_steps": 40000, "loss": 0.1846, "lr": 4.744290941907364e-05, "epoch": 0.26302089227913716, "percentage": 14.52, "elapsed_time": "4:45:49", "remaining_time": "1 day, 4:02:00", "throughput": 554.1, "total_tokens": 9502592} {"current_steps": 5815, "total_steps": 40000, "loss": 0.1364, "lr": 4.7438582365153594e-05, "epoch": 0.2632472441657801, "percentage": 14.54, "elapsed_time": "4:45:52", "remaining_time": "1 day, 4:00:37", "throughput": 554.47, "total_tokens": 9510656} {"current_steps": 5820, "total_steps": 40000, "loss": 0.1697, "lr": 4.743425185092217e-05, "epoch": 0.2634735960524231, "percentage": 14.55, "elapsed_time": "4:45:55", "remaining_time": "1 day, 3:59:14", "throughput": 554.83, "total_tokens": 9518592} {"current_steps": 5825, "total_steps": 40000, "loss": 0.1793, "lr": 4.742991787704719e-05, "epoch": 0.2636999479390661, "percentage": 14.56, "elapsed_time": "4:45:59", "remaining_time": "1 day, 3:57:51", "throughput": 555.2, "total_tokens": 9526752} {"current_steps": 5830, "total_steps": 40000, "loss": 0.1798, "lr": 4.7425580444196994e-05, "epoch": 0.26392629982570903, "percentage": 14.57, "elapsed_time": "4:46:02", "remaining_time": "1 day, 3:56:28", "throughput": 555.57, "total_tokens": 9534880} {"current_steps": 5835, "total_steps": 40000, "loss": 0.1143, "lr": 4.742123955304048e-05, "epoch": 0.264152651712352, "percentage": 14.59, "elapsed_time": "4:46:05", "remaining_time": "1 day, 3:55:06", "throughput": 555.95, "total_tokens": 9543072} {"current_steps": 5840, "total_steps": 40000, "loss": 0.119, "lr": 4.741689520424706e-05, "epoch": 0.264379003598995, "percentage": 14.6, "elapsed_time": "4:46:08", "remaining_time": "1 day, 3:53:44", "throughput": 556.33, "total_tokens": 9551456} {"current_steps": 5845, "total_steps": 40000, "loss": 0.1159, "lr": 4.741254739848669e-05, "epoch": 0.26460535548563796, "percentage": 14.61, "elapsed_time": "4:46:11", "remaining_time": "1 day, 3:52:23", "throughput": 556.73, "total_tokens": 9560128} {"current_steps": 5850, "total_steps": 40000, "loss": 0.1146, "lr": 4.740819613642987e-05, "epoch": 0.26483170737228096, "percentage": 14.62, "elapsed_time": "4:46:15", "remaining_time": "1 day, 3:51:01", "throughput": 557.12, "total_tokens": 9568512} {"current_steps": 5855, "total_steps": 40000, "loss": 0.1297, "lr": 4.74038414187476e-05, "epoch": 0.26505805925892395, "percentage": 14.64, "elapsed_time": "4:46:18", "remaining_time": "1 day, 3:49:40", "throughput": 557.5, "total_tokens": 9577024} {"current_steps": 5860, "total_steps": 40000, "loss": 0.1526, "lr": 4.739948324611144e-05, "epoch": 0.2652844111455669, "percentage": 14.65, "elapsed_time": "4:46:21", "remaining_time": "1 day, 3:48:19", "throughput": 557.89, "total_tokens": 9585472} {"current_steps": 5865, "total_steps": 40000, "loss": 0.188, "lr": 4.7395121619193465e-05, "epoch": 0.2655107630322099, "percentage": 14.66, "elapsed_time": "4:46:24", "remaining_time": "1 day, 3:46:57", "throughput": 558.25, "total_tokens": 9593376} {"current_steps": 5870, "total_steps": 40000, "loss": 0.1748, "lr": 4.7390756538666313e-05, "epoch": 0.2657371149188528, "percentage": 14.67, "elapsed_time": "4:46:27", "remaining_time": "1 day, 3:45:36", "throughput": 558.61, "total_tokens": 9601344} {"current_steps": 5875, "total_steps": 40000, "loss": 0.1358, "lr": 4.738638800520311e-05, "epoch": 0.2659634668054958, "percentage": 14.69, "elapsed_time": "4:46:31", "remaining_time": "1 day, 3:44:14", "throughput": 558.92, "total_tokens": 9608448} {"current_steps": 5880, "total_steps": 40000, "loss": 0.1562, "lr": 4.738201601947757e-05, "epoch": 0.2661898186921388, "percentage": 14.7, "elapsed_time": "4:46:34", "remaining_time": "1 day, 3:42:52", "throughput": 559.28, "total_tokens": 9616416} {"current_steps": 5885, "total_steps": 40000, "loss": 0.2548, "lr": 4.7377640582163876e-05, "epoch": 0.26641617057878175, "percentage": 14.71, "elapsed_time": "4:46:37", "remaining_time": "1 day, 3:41:31", "throughput": 559.63, "total_tokens": 9624160} {"current_steps": 5890, "total_steps": 40000, "loss": 0.1599, "lr": 4.7373261693936786e-05, "epoch": 0.26664252246542475, "percentage": 14.72, "elapsed_time": "4:46:40", "remaining_time": "1 day, 3:40:11", "throughput": 560.03, "total_tokens": 9632736} {"current_steps": 5895, "total_steps": 40000, "loss": 0.1132, "lr": 4.7368879355471595e-05, "epoch": 0.26686887435206774, "percentage": 14.74, "elapsed_time": "4:46:43", "remaining_time": "1 day, 3:38:50", "throughput": 560.37, "total_tokens": 9640448} {"current_steps": 5900, "total_steps": 40000, "loss": 0.1541, "lr": 4.736449356744409e-05, "epoch": 0.2670952262387107, "percentage": 14.75, "elapsed_time": "4:46:46", "remaining_time": "1 day, 3:37:29", "throughput": 560.75, "total_tokens": 9648672} {"current_steps": 5905, "total_steps": 40000, "loss": 0.1525, "lr": 4.736010433053064e-05, "epoch": 0.2673215781253537, "percentage": 14.76, "elapsed_time": "4:46:50", "remaining_time": "1 day, 3:36:09", "throughput": 561.13, "total_tokens": 9657152} {"current_steps": 5910, "total_steps": 40000, "loss": 0.1098, "lr": 4.73557116454081e-05, "epoch": 0.26754793001199667, "percentage": 14.77, "elapsed_time": "4:46:53", "remaining_time": "1 day, 3:34:49", "throughput": 561.5, "total_tokens": 9665216} {"current_steps": 5915, "total_steps": 40000, "loss": 0.1896, "lr": 4.735131551275389e-05, "epoch": 0.2677742818986396, "percentage": 14.79, "elapsed_time": "4:46:56", "remaining_time": "1 day, 3:33:29", "throughput": 561.88, "total_tokens": 9673632} {"current_steps": 5920, "total_steps": 40000, "loss": 0.1301, "lr": 4.734691593324594e-05, "epoch": 0.2680006337852826, "percentage": 14.8, "elapsed_time": "4:46:59", "remaining_time": "1 day, 3:32:08", "throughput": 562.24, "total_tokens": 9681440} {"current_steps": 5925, "total_steps": 40000, "loss": 0.1191, "lr": 4.734251290756272e-05, "epoch": 0.2682269856719256, "percentage": 14.81, "elapsed_time": "4:47:02", "remaining_time": "1 day, 3:30:48", "throughput": 562.57, "total_tokens": 9688864} {"current_steps": 5930, "total_steps": 40000, "loss": 0.1673, "lr": 4.7338106436383246e-05, "epoch": 0.26845333755856854, "percentage": 14.82, "elapsed_time": "4:47:05", "remaining_time": "1 day, 3:29:28", "throughput": 562.92, "total_tokens": 9696672} {"current_steps": 5935, "total_steps": 40000, "loss": 0.1264, "lr": 4.733369652038703e-05, "epoch": 0.26867968944521153, "percentage": 14.84, "elapsed_time": "4:47:08", "remaining_time": "1 day, 3:28:08", "throughput": 563.32, "total_tokens": 9705376} {"current_steps": 5940, "total_steps": 40000, "loss": 0.1283, "lr": 4.7329283160254156e-05, "epoch": 0.26890604133185453, "percentage": 14.85, "elapsed_time": "4:47:12", "remaining_time": "1 day, 3:26:49", "throughput": 563.67, "total_tokens": 9713216} {"current_steps": 5945, "total_steps": 40000, "loss": 0.1627, "lr": 4.732486635666521e-05, "epoch": 0.26913239321849747, "percentage": 14.86, "elapsed_time": "4:47:15", "remaining_time": "1 day, 3:25:29", "throughput": 564.03, "total_tokens": 9721184} {"current_steps": 5950, "total_steps": 40000, "loss": 0.1046, "lr": 4.732044611030132e-05, "epoch": 0.26935874510514046, "percentage": 14.88, "elapsed_time": "4:47:18", "remaining_time": "1 day, 3:24:09", "throughput": 564.38, "total_tokens": 9729088} {"current_steps": 5955, "total_steps": 40000, "loss": 0.1341, "lr": 4.731602242184414e-05, "epoch": 0.2695850969917834, "percentage": 14.89, "elapsed_time": "4:47:21", "remaining_time": "1 day, 3:22:50", "throughput": 564.77, "total_tokens": 9737440} {"current_steps": 5960, "total_steps": 40000, "loss": 0.1794, "lr": 4.7311595291975864e-05, "epoch": 0.2698114488784264, "percentage": 14.9, "elapsed_time": "4:47:24", "remaining_time": "1 day, 3:21:31", "throughput": 565.12, "total_tokens": 9745408} {"current_steps": 5965, "total_steps": 40000, "loss": 0.1323, "lr": 4.7307164721379216e-05, "epoch": 0.2700378007650694, "percentage": 14.91, "elapsed_time": "4:47:27", "remaining_time": "1 day, 3:20:12", "throughput": 565.49, "total_tokens": 9753504} {"current_steps": 5970, "total_steps": 40000, "loss": 0.1794, "lr": 4.730273071073743e-05, "epoch": 0.27026415265171233, "percentage": 14.92, "elapsed_time": "4:47:31", "remaining_time": "1 day, 3:18:54", "throughput": 565.88, "total_tokens": 9762048} {"current_steps": 5975, "total_steps": 40000, "loss": 0.1539, "lr": 4.729829326073429e-05, "epoch": 0.2704905045383553, "percentage": 14.94, "elapsed_time": "4:47:34", "remaining_time": "1 day, 3:17:35", "throughput": 566.24, "total_tokens": 9770144} {"current_steps": 5980, "total_steps": 40000, "loss": 0.1199, "lr": 4.7293852372054126e-05, "epoch": 0.2707168564249983, "percentage": 14.95, "elapsed_time": "4:47:37", "remaining_time": "1 day, 3:16:16", "throughput": 566.61, "total_tokens": 9778144} {"current_steps": 5985, "total_steps": 40000, "loss": 0.2123, "lr": 4.728940804538176e-05, "epoch": 0.27094320831164126, "percentage": 14.96, "elapsed_time": "4:47:40", "remaining_time": "1 day, 3:14:58", "throughput": 566.97, "total_tokens": 9786304} {"current_steps": 5990, "total_steps": 40000, "loss": 0.1034, "lr": 4.7284960281402556e-05, "epoch": 0.27116956019828425, "percentage": 14.97, "elapsed_time": "4:47:43", "remaining_time": "1 day, 3:13:40", "throughput": 567.36, "total_tokens": 9794848} {"current_steps": 5995, "total_steps": 40000, "loss": 0.0827, "lr": 4.728050908080244e-05, "epoch": 0.27139591208492725, "percentage": 14.99, "elapsed_time": "4:47:47", "remaining_time": "1 day, 3:12:22", "throughput": 567.76, "total_tokens": 9803648} {"current_steps": 6000, "total_steps": 40000, "loss": 0.1463, "lr": 4.727605444426782e-05, "epoch": 0.2716222639715702, "percentage": 15.0, "elapsed_time": "4:47:50", "remaining_time": "1 day, 3:11:04", "throughput": 568.13, "total_tokens": 9811712} {"current_steps": 6000, "total_steps": 40000, "eval_loss": 0.1532072126865387, "epoch": 0.2716222639715702, "percentage": 15.0, "elapsed_time": "4:55:32", "remaining_time": "1 day, 3:54:46", "throughput": 553.3, "total_tokens": 9811712} {"current_steps": 6005, "total_steps": 40000, "loss": 0.1314, "lr": 4.727159637248567e-05, "epoch": 0.2718486158582132, "percentage": 15.01, "elapsed_time": "4:55:37", "remaining_time": "1 day, 3:53:31", "throughput": 553.61, "total_tokens": 9819424} {"current_steps": 6010, "total_steps": 40000, "loss": 0.1856, "lr": 4.7267134866143474e-05, "epoch": 0.2720749677448562, "percentage": 15.02, "elapsed_time": "4:55:40", "remaining_time": "1 day, 3:52:10", "throughput": 553.98, "total_tokens": 9827680} {"current_steps": 6015, "total_steps": 40000, "loss": 0.1231, "lr": 4.726266992592926e-05, "epoch": 0.2723013196314991, "percentage": 15.04, "elapsed_time": "4:55:43", "remaining_time": "1 day, 3:50:50", "throughput": 554.35, "total_tokens": 9836000} {"current_steps": 6020, "total_steps": 40000, "loss": 0.1367, "lr": 4.725820155253157e-05, "epoch": 0.2725276715181421, "percentage": 15.05, "elapsed_time": "4:55:46", "remaining_time": "1 day, 3:49:30", "throughput": 554.71, "total_tokens": 9844192} {"current_steps": 6025, "total_steps": 40000, "loss": 0.1554, "lr": 4.725372974663948e-05, "epoch": 0.2727540234047851, "percentage": 15.06, "elapsed_time": "4:55:49", "remaining_time": "1 day, 3:48:10", "throughput": 555.06, "total_tokens": 9852160} {"current_steps": 6030, "total_steps": 40000, "loss": 0.0974, "lr": 4.724925450894262e-05, "epoch": 0.27298037529142805, "percentage": 15.07, "elapsed_time": "4:55:52", "remaining_time": "1 day, 3:46:50", "throughput": 555.38, "total_tokens": 9859584} {"current_steps": 6035, "total_steps": 40000, "loss": 0.1365, "lr": 4.72447758401311e-05, "epoch": 0.27320672717807104, "percentage": 15.09, "elapsed_time": "4:55:55", "remaining_time": "1 day, 3:45:30", "throughput": 555.74, "total_tokens": 9867712} {"current_steps": 6040, "total_steps": 40000, "loss": 0.1435, "lr": 4.7240293740895616e-05, "epoch": 0.273433079064714, "percentage": 15.1, "elapsed_time": "4:55:59", "remaining_time": "1 day, 3:44:10", "throughput": 556.1, "total_tokens": 9875776} {"current_steps": 6045, "total_steps": 40000, "loss": 0.1407, "lr": 4.723580821192733e-05, "epoch": 0.273659430951357, "percentage": 15.11, "elapsed_time": "4:56:02", "remaining_time": "1 day, 3:42:52", "throughput": 556.5, "total_tokens": 9884736} {"current_steps": 6050, "total_steps": 40000, "loss": 0.1073, "lr": 4.7231319253917996e-05, "epoch": 0.27388578283799997, "percentage": 15.12, "elapsed_time": "4:56:05", "remaining_time": "1 day, 3:41:32", "throughput": 556.86, "total_tokens": 9892864} {"current_steps": 6055, "total_steps": 40000, "loss": 0.1652, "lr": 4.722682686755986e-05, "epoch": 0.2741121347246429, "percentage": 15.14, "elapsed_time": "4:56:08", "remaining_time": "1 day, 3:40:13", "throughput": 557.22, "total_tokens": 9901088} {"current_steps": 6060, "total_steps": 40000, "loss": 0.169, "lr": 4.722233105354569e-05, "epoch": 0.2743384866112859, "percentage": 15.15, "elapsed_time": "4:56:11", "remaining_time": "1 day, 3:38:54", "throughput": 557.6, "total_tokens": 9909632} {"current_steps": 6065, "total_steps": 40000, "loss": 0.1328, "lr": 4.7217831812568815e-05, "epoch": 0.2745648384979289, "percentage": 15.16, "elapsed_time": "4:56:15", "remaining_time": "1 day, 3:37:36", "throughput": 557.99, "total_tokens": 9918464} {"current_steps": 6070, "total_steps": 40000, "loss": 0.1554, "lr": 4.721332914532307e-05, "epoch": 0.27479119038457184, "percentage": 15.17, "elapsed_time": "4:56:18", "remaining_time": "1 day, 3:36:17", "throughput": 558.36, "total_tokens": 9926688} {"current_steps": 6075, "total_steps": 40000, "loss": 0.178, "lr": 4.720882305250281e-05, "epoch": 0.27501754227121483, "percentage": 15.19, "elapsed_time": "4:56:21", "remaining_time": "1 day, 3:34:58", "throughput": 558.73, "total_tokens": 9935040} {"current_steps": 6080, "total_steps": 40000, "loss": 0.168, "lr": 4.720431353480295e-05, "epoch": 0.2752438941578578, "percentage": 15.2, "elapsed_time": "4:56:24", "remaining_time": "1 day, 3:33:39", "throughput": 559.08, "total_tokens": 9942976} {"current_steps": 6085, "total_steps": 40000, "loss": 0.152, "lr": 4.719980059291891e-05, "epoch": 0.27547024604450077, "percentage": 15.21, "elapsed_time": "4:56:27", "remaining_time": "1 day, 3:32:21", "throughput": 559.45, "total_tokens": 9951424} {"current_steps": 6090, "total_steps": 40000, "loss": 0.1746, "lr": 4.7195284227546634e-05, "epoch": 0.27569659793114376, "percentage": 15.22, "elapsed_time": "4:56:31", "remaining_time": "1 day, 3:31:03", "throughput": 559.81, "total_tokens": 9959552} {"current_steps": 6095, "total_steps": 40000, "loss": 0.1142, "lr": 4.7190764439382604e-05, "epoch": 0.27592294981778676, "percentage": 15.24, "elapsed_time": "4:56:34", "remaining_time": "1 day, 3:29:44", "throughput": 560.14, "total_tokens": 9967232} {"current_steps": 6100, "total_steps": 40000, "loss": 0.0669, "lr": 4.7186241229123826e-05, "epoch": 0.2761493017044297, "percentage": 15.25, "elapsed_time": "4:56:37", "remaining_time": "1 day, 3:28:25", "throughput": 560.47, "total_tokens": 9974816} {"current_steps": 6105, "total_steps": 40000, "loss": 0.12, "lr": 4.718171459746785e-05, "epoch": 0.2763756535910727, "percentage": 15.26, "elapsed_time": "4:56:40", "remaining_time": "1 day, 3:27:08", "throughput": 560.83, "total_tokens": 9982944} {"current_steps": 6110, "total_steps": 40000, "loss": 0.1169, "lr": 4.717718454511273e-05, "epoch": 0.2766020054777157, "percentage": 15.28, "elapsed_time": "4:56:43", "remaining_time": "1 day, 3:25:49", "throughput": 561.15, "total_tokens": 9990400} {"current_steps": 6115, "total_steps": 40000, "loss": 0.1491, "lr": 4.7172651072757056e-05, "epoch": 0.2768283573643586, "percentage": 15.29, "elapsed_time": "4:56:46", "remaining_time": "1 day, 3:24:32", "throughput": 561.5, "total_tokens": 9998432} {"current_steps": 6120, "total_steps": 40000, "loss": 0.1389, "lr": 4.7168114181099945e-05, "epoch": 0.2770547092510016, "percentage": 15.3, "elapsed_time": "4:56:49", "remaining_time": "1 day, 3:23:14", "throughput": 561.89, "total_tokens": 10007168} {"current_steps": 6125, "total_steps": 40000, "loss": 0.1387, "lr": 4.716357387084105e-05, "epoch": 0.27728106113764456, "percentage": 15.31, "elapsed_time": "4:56:53", "remaining_time": "1 day, 3:21:56", "throughput": 562.2, "total_tokens": 10014496} {"current_steps": 6130, "total_steps": 40000, "loss": 0.1416, "lr": 4.715903014268054e-05, "epoch": 0.27750741302428755, "percentage": 15.32, "elapsed_time": "4:56:56", "remaining_time": "1 day, 3:20:38", "throughput": 562.52, "total_tokens": 10021920} {"current_steps": 6135, "total_steps": 40000, "loss": 0.1719, "lr": 4.715448299731911e-05, "epoch": 0.27773376491093055, "percentage": 15.34, "elapsed_time": "4:56:59", "remaining_time": "1 day, 3:19:21", "throughput": 562.84, "total_tokens": 10029376} {"current_steps": 6140, "total_steps": 40000, "loss": 0.0924, "lr": 4.7149932435457986e-05, "epoch": 0.2779601167975735, "percentage": 15.35, "elapsed_time": "4:57:02", "remaining_time": "1 day, 3:18:05", "throughput": 563.26, "total_tokens": 10038816} {"current_steps": 6145, "total_steps": 40000, "loss": 0.1637, "lr": 4.714537845779894e-05, "epoch": 0.2781864686842165, "percentage": 15.36, "elapsed_time": "4:57:05", "remaining_time": "1 day, 3:16:48", "throughput": 563.64, "total_tokens": 10047264} {"current_steps": 6150, "total_steps": 40000, "loss": 0.1107, "lr": 4.714082106504423e-05, "epoch": 0.2784128205708595, "percentage": 15.38, "elapsed_time": "4:57:08", "remaining_time": "1 day, 3:15:31", "throughput": 563.97, "total_tokens": 10055072} {"current_steps": 6155, "total_steps": 40000, "loss": 0.1024, "lr": 4.713626025789667e-05, "epoch": 0.2786391724575024, "percentage": 15.39, "elapsed_time": "4:57:12", "remaining_time": "1 day, 3:14:14", "throughput": 564.33, "total_tokens": 10063104} {"current_steps": 6160, "total_steps": 40000, "loss": 0.1425, "lr": 4.7131696037059606e-05, "epoch": 0.2788655243441454, "percentage": 15.4, "elapsed_time": "4:57:15", "remaining_time": "1 day, 3:12:57", "throughput": 564.68, "total_tokens": 10071168} {"current_steps": 6165, "total_steps": 40000, "loss": 0.1435, "lr": 4.712712840323689e-05, "epoch": 0.2790918762307884, "percentage": 15.41, "elapsed_time": "4:57:18", "remaining_time": "1 day, 3:11:41", "throughput": 565.05, "total_tokens": 10079680} {"current_steps": 6170, "total_steps": 40000, "loss": 0.1848, "lr": 4.71225573571329e-05, "epoch": 0.27931822811743134, "percentage": 15.43, "elapsed_time": "4:57:21", "remaining_time": "1 day, 3:10:25", "throughput": 565.4, "total_tokens": 10087648} {"current_steps": 6175, "total_steps": 40000, "loss": 0.1448, "lr": 4.711798289945256e-05, "epoch": 0.27954458000407434, "percentage": 15.44, "elapsed_time": "4:57:24", "remaining_time": "1 day, 3:09:08", "throughput": 565.75, "total_tokens": 10095680} {"current_steps": 6180, "total_steps": 40000, "loss": 0.1945, "lr": 4.71134050309013e-05, "epoch": 0.27977093189071733, "percentage": 15.45, "elapsed_time": "4:57:28", "remaining_time": "1 day, 3:07:53", "throughput": 566.13, "total_tokens": 10104288} {"current_steps": 6185, "total_steps": 40000, "loss": 0.1507, "lr": 4.710882375218509e-05, "epoch": 0.2799972837773603, "percentage": 15.46, "elapsed_time": "4:57:31", "remaining_time": "1 day, 3:06:36", "throughput": 566.46, "total_tokens": 10112032} {"current_steps": 6190, "total_steps": 40000, "loss": 0.0957, "lr": 4.7104239064010424e-05, "epoch": 0.28022363566400327, "percentage": 15.47, "elapsed_time": "4:57:34", "remaining_time": "1 day, 3:05:20", "throughput": 566.83, "total_tokens": 10120416} {"current_steps": 6195, "total_steps": 40000, "loss": 0.1313, "lr": 4.709965096708432e-05, "epoch": 0.2804499875506462, "percentage": 15.49, "elapsed_time": "4:57:37", "remaining_time": "1 day, 3:04:05", "throughput": 567.19, "total_tokens": 10128608} {"current_steps": 6200, "total_steps": 40000, "loss": 0.1254, "lr": 4.709505946211431e-05, "epoch": 0.2806763394372892, "percentage": 15.5, "elapsed_time": "4:57:40", "remaining_time": "1 day, 3:02:49", "throughput": 567.56, "total_tokens": 10136992} {"current_steps": 6200, "total_steps": 40000, "eval_loss": 0.15248726308345795, "epoch": 0.2806763394372892, "percentage": 15.5, "elapsed_time": "5:05:23", "remaining_time": "1 day, 3:44:52", "throughput": 553.22, "total_tokens": 10136992} {"current_steps": 6205, "total_steps": 40000, "loss": 0.1266, "lr": 4.709046454980846e-05, "epoch": 0.2809026913239322, "percentage": 15.51, "elapsed_time": "5:05:27", "remaining_time": "1 day, 3:43:38", "throughput": 553.52, "total_tokens": 10144512} {"current_steps": 6210, "total_steps": 40000, "loss": 0.1227, "lr": 4.708586623087538e-05, "epoch": 0.28112904321057514, "percentage": 15.53, "elapsed_time": "5:05:30", "remaining_time": "1 day, 3:42:20", "throughput": 553.85, "total_tokens": 10152256} {"current_steps": 6215, "total_steps": 40000, "loss": 0.1645, "lr": 4.708126450602418e-05, "epoch": 0.28135539509721813, "percentage": 15.54, "elapsed_time": "5:05:33", "remaining_time": "1 day, 3:41:02", "throughput": 554.21, "total_tokens": 10160640} {"current_steps": 6220, "total_steps": 40000, "loss": 0.1291, "lr": 4.7076659375964495e-05, "epoch": 0.2815817469838611, "percentage": 15.55, "elapsed_time": "5:05:36", "remaining_time": "1 day, 3:39:44", "throughput": 554.55, "total_tokens": 10168576} {"current_steps": 6225, "total_steps": 40000, "loss": 0.1145, "lr": 4.707205084140651e-05, "epoch": 0.28180809887050406, "percentage": 15.56, "elapsed_time": "5:05:39", "remaining_time": "1 day, 3:38:26", "throughput": 554.88, "total_tokens": 10176384} {"current_steps": 6230, "total_steps": 40000, "loss": 0.175, "lr": 4.7067438903060904e-05, "epoch": 0.28203445075714706, "percentage": 15.57, "elapsed_time": "5:05:43", "remaining_time": "1 day, 3:37:09", "throughput": 555.24, "total_tokens": 10184800} {"current_steps": 6235, "total_steps": 40000, "loss": 0.1494, "lr": 4.70628235616389e-05, "epoch": 0.28226080264379005, "percentage": 15.59, "elapsed_time": "5:05:46", "remaining_time": "1 day, 3:35:52", "throughput": 555.58, "total_tokens": 10192800} {"current_steps": 6240, "total_steps": 40000, "loss": 0.2341, "lr": 4.7058204817852256e-05, "epoch": 0.282487154530433, "percentage": 15.6, "elapsed_time": "5:05:49", "remaining_time": "1 day, 3:34:35", "throughput": 555.94, "total_tokens": 10201120} {"current_steps": 6245, "total_steps": 40000, "loss": 0.136, "lr": 4.705358267241322e-05, "epoch": 0.282713506417076, "percentage": 15.61, "elapsed_time": "5:05:52", "remaining_time": "1 day, 3:33:17", "throughput": 556.27, "total_tokens": 10208960} {"current_steps": 6250, "total_steps": 40000, "loss": 0.1072, "lr": 4.704895712603459e-05, "epoch": 0.282939858303719, "percentage": 15.62, "elapsed_time": "5:05:55", "remaining_time": "1 day, 3:32:00", "throughput": 556.61, "total_tokens": 10216864} {"current_steps": 6255, "total_steps": 40000, "loss": 0.1076, "lr": 4.704432817942969e-05, "epoch": 0.2831662101903619, "percentage": 15.64, "elapsed_time": "5:05:58", "remaining_time": "1 day, 3:30:44", "throughput": 556.97, "total_tokens": 10225472} {"current_steps": 6260, "total_steps": 40000, "loss": 0.1385, "lr": 4.703969583331236e-05, "epoch": 0.2833925620770049, "percentage": 15.65, "elapsed_time": "5:06:02", "remaining_time": "1 day, 3:29:27", "throughput": 557.31, "total_tokens": 10233408} {"current_steps": 6265, "total_steps": 40000, "loss": 0.1433, "lr": 4.7035060088396965e-05, "epoch": 0.2836189139636479, "percentage": 15.66, "elapsed_time": "5:06:05", "remaining_time": "1 day, 3:28:11", "throughput": 557.67, "total_tokens": 10241792} {"current_steps": 6270, "total_steps": 40000, "loss": 0.1225, "lr": 4.703042094539839e-05, "epoch": 0.28384526585029085, "percentage": 15.68, "elapsed_time": "5:06:08", "remaining_time": "1 day, 3:26:55", "throughput": 558.02, "total_tokens": 10249952} {"current_steps": 6275, "total_steps": 40000, "loss": 0.1151, "lr": 4.702577840503206e-05, "epoch": 0.28407161773693385, "percentage": 15.69, "elapsed_time": "5:06:11", "remaining_time": "1 day, 3:25:38", "throughput": 558.35, "total_tokens": 10257792} {"current_steps": 6280, "total_steps": 40000, "loss": 0.121, "lr": 4.70211324680139e-05, "epoch": 0.2842979696235768, "percentage": 15.7, "elapsed_time": "5:06:14", "remaining_time": "1 day, 3:24:22", "throughput": 558.69, "total_tokens": 10265888} {"current_steps": 6285, "total_steps": 40000, "loss": 0.1593, "lr": 4.7016483135060386e-05, "epoch": 0.2845243215102198, "percentage": 15.71, "elapsed_time": "5:06:17", "remaining_time": "1 day, 3:23:05", "throughput": 559.04, "total_tokens": 10274048} {"current_steps": 6290, "total_steps": 40000, "loss": 0.1289, "lr": 4.701183040688849e-05, "epoch": 0.2847506733968628, "percentage": 15.72, "elapsed_time": "5:06:21", "remaining_time": "1 day, 3:21:50", "throughput": 559.41, "total_tokens": 10282624} {"current_steps": 6295, "total_steps": 40000, "loss": 0.1578, "lr": 4.700717428421573e-05, "epoch": 0.2849770252835057, "percentage": 15.74, "elapsed_time": "5:06:24", "remaining_time": "1 day, 3:20:34", "throughput": 559.76, "total_tokens": 10290848} {"current_steps": 6300, "total_steps": 40000, "loss": 0.1296, "lr": 4.700251476776014e-05, "epoch": 0.2852033771701487, "percentage": 15.75, "elapsed_time": "5:06:27", "remaining_time": "1 day, 3:19:19", "throughput": 560.13, "total_tokens": 10299424} {"current_steps": 6305, "total_steps": 40000, "loss": 0.1329, "lr": 4.699785185824026e-05, "epoch": 0.2854297290567917, "percentage": 15.76, "elapsed_time": "5:06:30", "remaining_time": "1 day, 3:18:03", "throughput": 560.49, "total_tokens": 10307904} {"current_steps": 6310, "total_steps": 40000, "loss": 0.118, "lr": 4.699318555637519e-05, "epoch": 0.28565608094343464, "percentage": 15.78, "elapsed_time": "5:06:33", "remaining_time": "1 day, 3:16:48", "throughput": 560.82, "total_tokens": 10315680} {"current_steps": 6315, "total_steps": 40000, "loss": 0.1454, "lr": 4.6988515862884525e-05, "epoch": 0.28588243283007764, "percentage": 15.79, "elapsed_time": "5:06:37", "remaining_time": "1 day, 3:15:32", "throughput": 561.16, "total_tokens": 10323776} {"current_steps": 6320, "total_steps": 40000, "loss": 0.1905, "lr": 4.698384277848838e-05, "epoch": 0.28610878471672063, "percentage": 15.8, "elapsed_time": "5:06:40", "remaining_time": "1 day, 3:14:17", "throughput": 561.48, "total_tokens": 10331456} {"current_steps": 6325, "total_steps": 40000, "loss": 0.2111, "lr": 4.6979166303907425e-05, "epoch": 0.28633513660336357, "percentage": 15.81, "elapsed_time": "5:06:43", "remaining_time": "1 day, 3:13:01", "throughput": 561.8, "total_tokens": 10338944} {"current_steps": 6330, "total_steps": 40000, "loss": 0.1628, "lr": 4.697448643986281e-05, "epoch": 0.28656148849000657, "percentage": 15.82, "elapsed_time": "5:06:46", "remaining_time": "1 day, 3:11:46", "throughput": 562.15, "total_tokens": 10347200} {"current_steps": 6335, "total_steps": 40000, "loss": 0.1233, "lr": 4.696980318707624e-05, "epoch": 0.28678784037664956, "percentage": 15.84, "elapsed_time": "5:06:49", "remaining_time": "1 day, 3:10:31", "throughput": 562.45, "total_tokens": 10354624} {"current_steps": 6340, "total_steps": 40000, "loss": 0.1406, "lr": 4.6965116546269924e-05, "epoch": 0.2870141922632925, "percentage": 15.85, "elapsed_time": "5:06:52", "remaining_time": "1 day, 3:09:16", "throughput": 562.78, "total_tokens": 10362464} {"current_steps": 6345, "total_steps": 40000, "loss": 0.151, "lr": 4.6960426518166615e-05, "epoch": 0.2872405441499355, "percentage": 15.86, "elapsed_time": "5:06:56", "remaining_time": "1 day, 3:08:01", "throughput": 563.11, "total_tokens": 10370272} {"current_steps": 6350, "total_steps": 40000, "loss": 0.2075, "lr": 4.6955733103489556e-05, "epoch": 0.2874668960365785, "percentage": 15.88, "elapsed_time": "5:06:59", "remaining_time": "1 day, 3:06:48", "throughput": 563.51, "total_tokens": 10379552} {"current_steps": 6355, "total_steps": 40000, "loss": 0.1696, "lr": 4.695103630296255e-05, "epoch": 0.28769324792322143, "percentage": 15.89, "elapsed_time": "5:07:02", "remaining_time": "1 day, 3:05:33", "throughput": 563.84, "total_tokens": 10387424} {"current_steps": 6360, "total_steps": 40000, "loss": 0.1642, "lr": 4.694633611730988e-05, "epoch": 0.2879195998098644, "percentage": 15.9, "elapsed_time": "5:07:05", "remaining_time": "1 day, 3:04:19", "throughput": 564.2, "total_tokens": 10395840} {"current_steps": 6365, "total_steps": 40000, "loss": 0.1339, "lr": 4.694163254725639e-05, "epoch": 0.28814595169650736, "percentage": 15.91, "elapsed_time": "5:07:08", "remaining_time": "1 day, 3:03:05", "throughput": 564.55, "total_tokens": 10404128} {"current_steps": 6370, "total_steps": 40000, "loss": 0.1185, "lr": 4.693692559352743e-05, "epoch": 0.28837230358315036, "percentage": 15.93, "elapsed_time": "5:07:11", "remaining_time": "1 day, 3:01:50", "throughput": 564.88, "total_tokens": 10411840} {"current_steps": 6375, "total_steps": 40000, "loss": 0.0955, "lr": 4.693221525684886e-05, "epoch": 0.28859865546979335, "percentage": 15.94, "elapsed_time": "5:07:15", "remaining_time": "1 day, 3:00:35", "throughput": 565.21, "total_tokens": 10419616} {"current_steps": 6380, "total_steps": 40000, "loss": 0.1822, "lr": 4.6927501537947084e-05, "epoch": 0.2888250073564363, "percentage": 15.95, "elapsed_time": "5:07:18", "remaining_time": "1 day, 2:59:21", "throughput": 565.54, "total_tokens": 10427488} {"current_steps": 6385, "total_steps": 40000, "loss": 0.1375, "lr": 4.692278443754901e-05, "epoch": 0.2890513592430793, "percentage": 15.96, "elapsed_time": "5:07:21", "remaining_time": "1 day, 2:58:08", "throughput": 565.91, "total_tokens": 10436128} {"current_steps": 6390, "total_steps": 40000, "loss": 0.1161, "lr": 4.691806395638208e-05, "epoch": 0.2892777111297223, "percentage": 15.97, "elapsed_time": "5:07:24", "remaining_time": "1 day, 2:56:55", "throughput": 566.29, "total_tokens": 10445024} {"current_steps": 6395, "total_steps": 40000, "loss": 0.1377, "lr": 4.6913340095174255e-05, "epoch": 0.2895040630163652, "percentage": 15.99, "elapsed_time": "5:07:28", "remaining_time": "1 day, 2:55:42", "throughput": 566.67, "total_tokens": 10453920} {"current_steps": 6400, "total_steps": 40000, "loss": 0.1758, "lr": 4.690861285465399e-05, "epoch": 0.2897304149030082, "percentage": 16.0, "elapsed_time": "5:07:31", "remaining_time": "1 day, 2:54:29", "throughput": 567.02, "total_tokens": 10462272} {"current_steps": 6400, "total_steps": 40000, "eval_loss": 0.1511060744524002, "epoch": 0.2897304149030082, "percentage": 16.0, "elapsed_time": "5:15:14", "remaining_time": "1 day, 3:34:59", "throughput": 553.15, "total_tokens": 10462272} {"current_steps": 6405, "total_steps": 40000, "loss": 0.1798, "lr": 4.690388223555031e-05, "epoch": 0.2899567667896512, "percentage": 16.01, "elapsed_time": "5:15:18", "remaining_time": "1 day, 3:33:50", "throughput": 553.48, "total_tokens": 10471104} {"current_steps": 6410, "total_steps": 40000, "loss": 0.1177, "lr": 4.689914823859273e-05, "epoch": 0.29018311867629415, "percentage": 16.02, "elapsed_time": "5:15:21", "remaining_time": "1 day, 3:32:35", "throughput": 553.86, "total_tokens": 10480000} {"current_steps": 6415, "total_steps": 40000, "loss": 0.1155, "lr": 4.689441086451129e-05, "epoch": 0.29040947056293714, "percentage": 16.04, "elapsed_time": "5:15:25", "remaining_time": "1 day, 3:31:20", "throughput": 554.21, "total_tokens": 10488448} {"current_steps": 6420, "total_steps": 40000, "loss": 0.2233, "lr": 4.688967011403655e-05, "epoch": 0.29063582244958014, "percentage": 16.05, "elapsed_time": "5:15:28", "remaining_time": "1 day, 3:30:05", "throughput": 554.57, "total_tokens": 10497120} {"current_steps": 6425, "total_steps": 40000, "loss": 0.2306, "lr": 4.68849259878996e-05, "epoch": 0.2908621743362231, "percentage": 16.06, "elapsed_time": "5:15:31", "remaining_time": "1 day, 3:28:50", "throughput": 554.92, "total_tokens": 10505440} {"current_steps": 6430, "total_steps": 40000, "loss": 0.1128, "lr": 4.6880178486832036e-05, "epoch": 0.2910885262228661, "percentage": 16.07, "elapsed_time": "5:15:34", "remaining_time": "1 day, 3:27:35", "throughput": 555.24, "total_tokens": 10513216} {"current_steps": 6435, "total_steps": 40000, "loss": 0.2161, "lr": 4.687542761156598e-05, "epoch": 0.29131487810950907, "percentage": 16.09, "elapsed_time": "5:15:37", "remaining_time": "1 day, 3:26:19", "throughput": 555.55, "total_tokens": 10520864} {"current_steps": 6440, "total_steps": 40000, "loss": 0.1571, "lr": 4.6870673362834096e-05, "epoch": 0.291541229996152, "percentage": 16.1, "elapsed_time": "5:15:40", "remaining_time": "1 day, 3:25:04", "throughput": 555.86, "total_tokens": 10528576} {"current_steps": 6445, "total_steps": 40000, "loss": 0.1605, "lr": 4.6865915741369526e-05, "epoch": 0.291767581882795, "percentage": 16.11, "elapsed_time": "5:15:44", "remaining_time": "1 day, 3:23:49", "throughput": 556.18, "total_tokens": 10536288} {"current_steps": 6450, "total_steps": 40000, "loss": 0.1978, "lr": 4.686115474790597e-05, "epoch": 0.29199393376943794, "percentage": 16.12, "elapsed_time": "5:15:47", "remaining_time": "1 day, 3:22:34", "throughput": 556.52, "total_tokens": 10544480} {"current_steps": 6455, "total_steps": 40000, "loss": 0.1526, "lr": 4.685639038317762e-05, "epoch": 0.29222028565608094, "percentage": 16.14, "elapsed_time": "5:15:50", "remaining_time": "1 day, 3:21:19", "throughput": 556.85, "total_tokens": 10552448} {"current_steps": 6460, "total_steps": 40000, "loss": 0.1719, "lr": 4.685162264791921e-05, "epoch": 0.29244663754272393, "percentage": 16.15, "elapsed_time": "5:15:53", "remaining_time": "1 day, 3:20:06", "throughput": 557.22, "total_tokens": 10561248} {"current_steps": 6465, "total_steps": 40000, "loss": 0.1262, "lr": 4.684685154286599e-05, "epoch": 0.29267298942936687, "percentage": 16.16, "elapsed_time": "5:15:56", "remaining_time": "1 day, 3:18:51", "throughput": 557.56, "total_tokens": 10569440} {"current_steps": 6470, "total_steps": 40000, "loss": 0.1268, "lr": 4.684207706875371e-05, "epoch": 0.29289934131600986, "percentage": 16.18, "elapsed_time": "5:15:59", "remaining_time": "1 day, 3:17:37", "throughput": 557.87, "total_tokens": 10577088} {"current_steps": 6475, "total_steps": 40000, "loss": 0.1445, "lr": 4.683729922631866e-05, "epoch": 0.29312569320265286, "percentage": 16.19, "elapsed_time": "5:16:02", "remaining_time": "1 day, 3:16:22", "throughput": 558.2, "total_tokens": 10585152} {"current_steps": 6480, "total_steps": 40000, "loss": 0.1716, "lr": 4.683251801629765e-05, "epoch": 0.2933520450892958, "percentage": 16.2, "elapsed_time": "5:16:06", "remaining_time": "1 day, 3:15:09", "throughput": 558.52, "total_tokens": 10593024} {"current_steps": 6485, "total_steps": 40000, "loss": 0.158, "lr": 4.6827733439428e-05, "epoch": 0.2935783969759388, "percentage": 16.21, "elapsed_time": "5:16:09", "remaining_time": "1 day, 3:13:55", "throughput": 558.83, "total_tokens": 10600608} {"current_steps": 6490, "total_steps": 40000, "loss": 0.1523, "lr": 4.682294549644754e-05, "epoch": 0.2938047488625818, "percentage": 16.23, "elapsed_time": "5:16:12", "remaining_time": "1 day, 3:12:41", "throughput": 559.17, "total_tokens": 10608832} {"current_steps": 6495, "total_steps": 40000, "loss": 0.1147, "lr": 4.681815418809464e-05, "epoch": 0.2940311007492247, "percentage": 16.24, "elapsed_time": "5:16:15", "remaining_time": "1 day, 3:11:28", "throughput": 559.52, "total_tokens": 10617376} {"current_steps": 6500, "total_steps": 40000, "loss": 0.1604, "lr": 4.681335951510819e-05, "epoch": 0.2942574526358677, "percentage": 16.25, "elapsed_time": "5:16:18", "remaining_time": "1 day, 3:10:14", "throughput": 559.85, "total_tokens": 10625312} {"current_steps": 6505, "total_steps": 40000, "loss": 0.1629, "lr": 4.6808561478227576e-05, "epoch": 0.2944838045225107, "percentage": 16.26, "elapsed_time": "5:16:22", "remaining_time": "1 day, 3:09:01", "throughput": 560.21, "total_tokens": 10634048} {"current_steps": 6510, "total_steps": 40000, "loss": 0.1441, "lr": 4.680376007819271e-05, "epoch": 0.29471015640915366, "percentage": 16.28, "elapsed_time": "5:16:25", "remaining_time": "1 day, 3:07:48", "throughput": 560.55, "total_tokens": 10642336} {"current_steps": 6515, "total_steps": 40000, "loss": 0.1419, "lr": 4.679895531574405e-05, "epoch": 0.29493650829579665, "percentage": 16.29, "elapsed_time": "5:16:28", "remaining_time": "1 day, 3:06:35", "throughput": 560.9, "total_tokens": 10650720} {"current_steps": 6520, "total_steps": 40000, "loss": 0.1347, "lr": 4.679414719162253e-05, "epoch": 0.29516286018243965, "percentage": 16.3, "elapsed_time": "5:16:31", "remaining_time": "1 day, 3:05:21", "throughput": 561.21, "total_tokens": 10658368} {"current_steps": 6525, "total_steps": 40000, "loss": 0.1135, "lr": 4.6789335706569635e-05, "epoch": 0.2953892120690826, "percentage": 16.31, "elapsed_time": "5:16:34", "remaining_time": "1 day, 3:04:08", "throughput": 561.55, "total_tokens": 10666592} {"current_steps": 6530, "total_steps": 40000, "loss": 0.152, "lr": 4.678452086132734e-05, "epoch": 0.2956155639557256, "percentage": 16.32, "elapsed_time": "5:16:37", "remaining_time": "1 day, 3:02:55", "throughput": 561.85, "total_tokens": 10674048} {"current_steps": 6535, "total_steps": 40000, "loss": 0.1639, "lr": 4.677970265663818e-05, "epoch": 0.2958419158423685, "percentage": 16.34, "elapsed_time": "5:16:41", "remaining_time": "1 day, 3:01:42", "throughput": 562.2, "total_tokens": 10682528} {"current_steps": 6540, "total_steps": 40000, "loss": 0.1928, "lr": 4.677488109324517e-05, "epoch": 0.2960682677290115, "percentage": 16.35, "elapsed_time": "5:16:44", "remaining_time": "1 day, 3:00:29", "throughput": 562.53, "total_tokens": 10690464} {"current_steps": 6545, "total_steps": 40000, "loss": 0.1406, "lr": 4.6770056171891846e-05, "epoch": 0.2962946196156545, "percentage": 16.36, "elapsed_time": "5:16:47", "remaining_time": "1 day, 2:59:17", "throughput": 562.84, "total_tokens": 10698176} {"current_steps": 6550, "total_steps": 40000, "loss": 0.0925, "lr": 4.6765227893322286e-05, "epoch": 0.29652097150229745, "percentage": 16.38, "elapsed_time": "5:16:50", "remaining_time": "1 day, 2:58:04", "throughput": 563.17, "total_tokens": 10706208} {"current_steps": 6555, "total_steps": 40000, "loss": 0.1453, "lr": 4.676039625828107e-05, "epoch": 0.29674732338894044, "percentage": 16.39, "elapsed_time": "5:16:53", "remaining_time": "1 day, 2:56:52", "throughput": 563.51, "total_tokens": 10714528} {"current_steps": 6560, "total_steps": 40000, "loss": 0.1401, "lr": 4.675556126751328e-05, "epoch": 0.29697367527558344, "percentage": 16.4, "elapsed_time": "5:16:57", "remaining_time": "1 day, 2:55:40", "throughput": 563.86, "total_tokens": 10723072} {"current_steps": 6565, "total_steps": 40000, "loss": 0.2338, "lr": 4.6750722921764556e-05, "epoch": 0.2972000271622264, "percentage": 16.41, "elapsed_time": "5:17:00", "remaining_time": "1 day, 2:54:29", "throughput": 564.22, "total_tokens": 10731744} {"current_steps": 6570, "total_steps": 40000, "loss": 0.1238, "lr": 4.674588122178102e-05, "epoch": 0.29742637904886937, "percentage": 16.43, "elapsed_time": "5:17:03", "remaining_time": "1 day, 2:53:17", "throughput": 564.58, "total_tokens": 10740256} {"current_steps": 6575, "total_steps": 40000, "loss": 0.1458, "lr": 4.674103616830931e-05, "epoch": 0.29765273093551237, "percentage": 16.44, "elapsed_time": "5:17:06", "remaining_time": "1 day, 2:52:05", "throughput": 564.94, "total_tokens": 10749024} {"current_steps": 6580, "total_steps": 40000, "loss": 0.1732, "lr": 4.673618776209663e-05, "epoch": 0.2978790828221553, "percentage": 16.45, "elapsed_time": "5:17:10", "remaining_time": "1 day, 2:50:54", "throughput": 565.29, "total_tokens": 10757600} {"current_steps": 6585, "total_steps": 40000, "loss": 0.1114, "lr": 4.673133600389063e-05, "epoch": 0.2981054347087983, "percentage": 16.46, "elapsed_time": "5:17:13", "remaining_time": "1 day, 2:49:42", "throughput": 565.6, "total_tokens": 10765280} {"current_steps": 6590, "total_steps": 40000, "loss": 0.1167, "lr": 4.672648089443953e-05, "epoch": 0.2983317865954413, "percentage": 16.48, "elapsed_time": "5:17:16", "remaining_time": "1 day, 2:48:31", "throughput": 565.93, "total_tokens": 10773312} {"current_steps": 6595, "total_steps": 40000, "loss": 0.1368, "lr": 4.672162243449204e-05, "epoch": 0.29855813848208423, "percentage": 16.49, "elapsed_time": "5:17:19", "remaining_time": "1 day, 2:47:20", "throughput": 566.29, "total_tokens": 10781952} {"current_steps": 6600, "total_steps": 40000, "loss": 0.1006, "lr": 4.67167606247974e-05, "epoch": 0.29878449036872723, "percentage": 16.5, "elapsed_time": "5:17:22", "remaining_time": "1 day, 2:46:08", "throughput": 566.6, "total_tokens": 10789600} {"current_steps": 6600, "total_steps": 40000, "eval_loss": 0.15165938436985016, "epoch": 0.29878449036872723, "percentage": 16.5, "elapsed_time": "5:25:05", "remaining_time": "1 day, 3:25:09", "throughput": 553.16, "total_tokens": 10789600} {"current_steps": 6605, "total_steps": 40000, "loss": 0.1399, "lr": 4.671189546610536e-05, "epoch": 0.2990108422553702, "percentage": 16.51, "elapsed_time": "5:25:09", "remaining_time": "1 day, 3:23:59", "throughput": 553.46, "total_tokens": 10797632} {"current_steps": 6610, "total_steps": 40000, "loss": 0.1374, "lr": 4.67070269591662e-05, "epoch": 0.29923719414201316, "percentage": 16.53, "elapsed_time": "5:25:12", "remaining_time": "1 day, 3:22:46", "throughput": 553.8, "total_tokens": 10806112} {"current_steps": 6615, "total_steps": 40000, "loss": 0.1718, "lr": 4.670215510473068e-05, "epoch": 0.29946354602865616, "percentage": 16.54, "elapsed_time": "5:25:15", "remaining_time": "1 day, 3:21:33", "throughput": 554.14, "total_tokens": 10814464} {"current_steps": 6620, "total_steps": 40000, "loss": 0.1834, "lr": 4.669727990355013e-05, "epoch": 0.2996898979152991, "percentage": 16.55, "elapsed_time": "5:25:18", "remaining_time": "1 day, 3:20:20", "throughput": 554.43, "total_tokens": 10821888} {"current_steps": 6625, "total_steps": 40000, "loss": 0.1221, "lr": 4.669240135637635e-05, "epoch": 0.2999162498019421, "percentage": 16.56, "elapsed_time": "5:25:22", "remaining_time": "1 day, 3:19:07", "throughput": 554.76, "total_tokens": 10830080} {"current_steps": 6630, "total_steps": 40000, "loss": 0.1496, "lr": 4.6687519463961675e-05, "epoch": 0.3001426016885851, "percentage": 16.57, "elapsed_time": "5:25:25", "remaining_time": "1 day, 3:17:54", "throughput": 555.08, "total_tokens": 10838176} {"current_steps": 6635, "total_steps": 40000, "loss": 0.1448, "lr": 4.668263422705896e-05, "epoch": 0.300368953575228, "percentage": 16.59, "elapsed_time": "5:25:28", "remaining_time": "1 day, 3:16:41", "throughput": 555.4, "total_tokens": 10846176} {"current_steps": 6640, "total_steps": 40000, "loss": 0.1637, "lr": 4.667774564642156e-05, "epoch": 0.300595305461871, "percentage": 16.6, "elapsed_time": "5:25:31", "remaining_time": "1 day, 3:15:28", "throughput": 555.71, "total_tokens": 10853856} {"current_steps": 6645, "total_steps": 40000, "loss": 0.0786, "lr": 4.6672853722803365e-05, "epoch": 0.300821657348514, "percentage": 16.61, "elapsed_time": "5:25:34", "remaining_time": "1 day, 3:14:15", "throughput": 556.02, "total_tokens": 10861760} {"current_steps": 6650, "total_steps": 40000, "loss": 0.1291, "lr": 4.666795845695877e-05, "epoch": 0.30104800923515695, "percentage": 16.62, "elapsed_time": "5:25:37", "remaining_time": "1 day, 3:13:02", "throughput": 556.33, "total_tokens": 10869440} {"current_steps": 6655, "total_steps": 40000, "loss": 0.1402, "lr": 4.666305984964269e-05, "epoch": 0.30127436112179995, "percentage": 16.64, "elapsed_time": "5:25:41", "remaining_time": "1 day, 3:11:51", "throughput": 556.69, "total_tokens": 10878240} {"current_steps": 6660, "total_steps": 40000, "loss": 0.189, "lr": 4.6658157901610535e-05, "epoch": 0.30150071300844294, "percentage": 16.65, "elapsed_time": "5:25:44", "remaining_time": "1 day, 3:10:39", "throughput": 557.04, "total_tokens": 10886976} {"current_steps": 6665, "total_steps": 40000, "loss": 0.1392, "lr": 4.665325261361826e-05, "epoch": 0.3017270648950859, "percentage": 16.66, "elapsed_time": "5:25:47", "remaining_time": "1 day, 3:09:27", "throughput": 557.37, "total_tokens": 10895296} {"current_steps": 6670, "total_steps": 40000, "loss": 0.1744, "lr": 4.664834398642232e-05, "epoch": 0.3019534167817289, "percentage": 16.68, "elapsed_time": "5:25:50", "remaining_time": "1 day, 3:08:15", "throughput": 557.72, "total_tokens": 10903840} {"current_steps": 6675, "total_steps": 40000, "loss": 0.1436, "lr": 4.6643432020779686e-05, "epoch": 0.3021797686683719, "percentage": 16.69, "elapsed_time": "5:25:53", "remaining_time": "1 day, 3:07:03", "throughput": 558.02, "total_tokens": 10911424} {"current_steps": 6680, "total_steps": 40000, "loss": 0.1327, "lr": 4.663851671744786e-05, "epoch": 0.3024061205550148, "percentage": 16.7, "elapsed_time": "5:25:57", "remaining_time": "1 day, 3:05:50", "throughput": 558.33, "total_tokens": 10919232} {"current_steps": 6685, "total_steps": 40000, "loss": 0.1066, "lr": 4.6633598077184815e-05, "epoch": 0.3026324724416578, "percentage": 16.71, "elapsed_time": "5:26:00", "remaining_time": "1 day, 3:04:39", "throughput": 558.65, "total_tokens": 10927264} {"current_steps": 6690, "total_steps": 40000, "loss": 0.1531, "lr": 4.662867610074908e-05, "epoch": 0.3028588243283008, "percentage": 16.73, "elapsed_time": "5:26:03", "remaining_time": "1 day, 3:03:27", "throughput": 558.97, "total_tokens": 10935232} {"current_steps": 6695, "total_steps": 40000, "loss": 0.153, "lr": 4.6623750788899696e-05, "epoch": 0.30308517621494374, "percentage": 16.74, "elapsed_time": "5:26:06", "remaining_time": "1 day, 3:02:15", "throughput": 559.29, "total_tokens": 10943360} {"current_steps": 6700, "total_steps": 40000, "loss": 0.15, "lr": 4.6618822142396195e-05, "epoch": 0.30331152810158674, "percentage": 16.75, "elapsed_time": "5:26:09", "remaining_time": "1 day, 3:01:04", "throughput": 559.62, "total_tokens": 10951584} {"current_steps": 6705, "total_steps": 40000, "loss": 0.1412, "lr": 4.661389016199864e-05, "epoch": 0.3035378799882297, "percentage": 16.76, "elapsed_time": "5:26:12", "remaining_time": "1 day, 2:59:52", "throughput": 559.92, "total_tokens": 10959136} {"current_steps": 6710, "total_steps": 40000, "loss": 0.2214, "lr": 4.660895484846761e-05, "epoch": 0.30376423187487267, "percentage": 16.78, "elapsed_time": "5:26:16", "remaining_time": "1 day, 2:58:41", "throughput": 560.26, "total_tokens": 10967776} {"current_steps": 6715, "total_steps": 40000, "loss": 0.1517, "lr": 4.660401620256418e-05, "epoch": 0.30399058376151566, "percentage": 16.79, "elapsed_time": "5:26:19", "remaining_time": "1 day, 2:57:30", "throughput": 560.6, "total_tokens": 10976128} {"current_steps": 6720, "total_steps": 40000, "loss": 0.1136, "lr": 4.659907422504997e-05, "epoch": 0.3042169356481586, "percentage": 16.8, "elapsed_time": "5:26:22", "remaining_time": "1 day, 2:56:19", "throughput": 560.92, "total_tokens": 10984192} {"current_steps": 6725, "total_steps": 40000, "loss": 0.1383, "lr": 4.6594128916687074e-05, "epoch": 0.3044432875348016, "percentage": 16.81, "elapsed_time": "5:26:25", "remaining_time": "1 day, 2:55:08", "throughput": 561.25, "total_tokens": 10992320} {"current_steps": 6730, "total_steps": 40000, "loss": 0.1243, "lr": 4.658918027823813e-05, "epoch": 0.3046696394214446, "percentage": 16.83, "elapsed_time": "5:26:28", "remaining_time": "1 day, 2:53:57", "throughput": 561.53, "total_tokens": 10999616} {"current_steps": 6735, "total_steps": 40000, "loss": 0.1192, "lr": 4.658422831046628e-05, "epoch": 0.30489599130808753, "percentage": 16.84, "elapsed_time": "5:26:31", "remaining_time": "1 day, 2:52:46", "throughput": 561.85, "total_tokens": 11007648} {"current_steps": 6740, "total_steps": 40000, "loss": 0.1521, "lr": 4.657927301413518e-05, "epoch": 0.3051223431947305, "percentage": 16.85, "elapsed_time": "5:26:34", "remaining_time": "1 day, 2:51:35", "throughput": 562.17, "total_tokens": 11015648} {"current_steps": 6745, "total_steps": 40000, "loss": 0.1121, "lr": 4.657431439000901e-05, "epoch": 0.3053486950813735, "percentage": 16.86, "elapsed_time": "5:26:38", "remaining_time": "1 day, 2:50:25", "throughput": 562.5, "total_tokens": 11023968} {"current_steps": 6750, "total_steps": 40000, "loss": 0.1683, "lr": 4.656935243885243e-05, "epoch": 0.30557504696801646, "percentage": 16.88, "elapsed_time": "5:26:41", "remaining_time": "1 day, 2:49:15", "throughput": 562.82, "total_tokens": 11032096} {"current_steps": 6755, "total_steps": 40000, "loss": 0.1169, "lr": 4.656438716143066e-05, "epoch": 0.30580139885465946, "percentage": 16.89, "elapsed_time": "5:26:44", "remaining_time": "1 day, 2:48:05", "throughput": 563.17, "total_tokens": 11040704} {"current_steps": 6760, "total_steps": 40000, "loss": 0.1467, "lr": 4.6559418558509384e-05, "epoch": 0.30602775074130245, "percentage": 16.9, "elapsed_time": "5:26:47", "remaining_time": "1 day, 2:46:55", "throughput": 563.5, "total_tokens": 11049088} {"current_steps": 6765, "total_steps": 40000, "loss": 0.1231, "lr": 4.6554446630854833e-05, "epoch": 0.3062541026279454, "percentage": 16.91, "elapsed_time": "5:26:50", "remaining_time": "1 day, 2:45:44", "throughput": 563.8, "total_tokens": 11056736} {"current_steps": 6770, "total_steps": 40000, "loss": 0.1823, "lr": 4.654947137923374e-05, "epoch": 0.3064804545145884, "percentage": 16.93, "elapsed_time": "5:26:54", "remaining_time": "1 day, 2:44:34", "throughput": 564.11, "total_tokens": 11064544} {"current_steps": 6775, "total_steps": 40000, "loss": 0.1714, "lr": 4.654449280441335e-05, "epoch": 0.3067068064012314, "percentage": 16.94, "elapsed_time": "5:26:57", "remaining_time": "1 day, 2:43:24", "throughput": 564.45, "total_tokens": 11072992} {"current_steps": 6780, "total_steps": 40000, "loss": 0.1234, "lr": 4.653951090716143e-05, "epoch": 0.3069331582878743, "percentage": 16.95, "elapsed_time": "5:27:00", "remaining_time": "1 day, 2:42:14", "throughput": 564.79, "total_tokens": 11081504} {"current_steps": 6785, "total_steps": 40000, "loss": 0.1473, "lr": 4.653452568824625e-05, "epoch": 0.3071595101745173, "percentage": 16.96, "elapsed_time": "5:27:03", "remaining_time": "1 day, 2:41:05", "throughput": 565.12, "total_tokens": 11089760} {"current_steps": 6790, "total_steps": 40000, "loss": 0.1852, "lr": 4.6529537148436585e-05, "epoch": 0.30738586206116025, "percentage": 16.98, "elapsed_time": "5:27:06", "remaining_time": "1 day, 2:39:54", "throughput": 565.42, "total_tokens": 11097472} {"current_steps": 6795, "total_steps": 40000, "loss": 0.1302, "lr": 4.6524545288501734e-05, "epoch": 0.30761221394780325, "percentage": 16.99, "elapsed_time": "5:27:09", "remaining_time": "1 day, 2:38:45", "throughput": 565.74, "total_tokens": 11105376} {"current_steps": 6800, "total_steps": 40000, "loss": 0.1458, "lr": 4.6519550109211506e-05, "epoch": 0.30783856583444624, "percentage": 17.0, "elapsed_time": "5:27:13", "remaining_time": "1 day, 2:37:35", "throughput": 566.08, "total_tokens": 11113952} {"current_steps": 6800, "total_steps": 40000, "eval_loss": 0.1519087553024292, "epoch": 0.30783856583444624, "percentage": 17.0, "elapsed_time": "5:34:55", "remaining_time": "1 day, 3:15:14", "throughput": 553.05, "total_tokens": 11113952} {"current_steps": 6805, "total_steps": 40000, "loss": 0.1587, "lr": 4.651455161133622e-05, "epoch": 0.3080649177210892, "percentage": 17.01, "elapsed_time": "5:34:59", "remaining_time": "1 day, 3:14:06", "throughput": 553.34, "total_tokens": 11122016} {"current_steps": 6810, "total_steps": 40000, "loss": 0.1394, "lr": 4.6509549795646704e-05, "epoch": 0.3082912696077322, "percentage": 17.03, "elapsed_time": "5:35:02", "remaining_time": "1 day, 3:12:55", "throughput": 553.65, "total_tokens": 11129952} {"current_steps": 6815, "total_steps": 40000, "loss": 0.155, "lr": 4.6504544662914306e-05, "epoch": 0.30851762149437517, "percentage": 17.04, "elapsed_time": "5:35:06", "remaining_time": "1 day, 3:11:44", "throughput": 553.96, "total_tokens": 11137952} {"current_steps": 6820, "total_steps": 40000, "loss": 0.1053, "lr": 4.6499536213910876e-05, "epoch": 0.3087439733810181, "percentage": 17.05, "elapsed_time": "5:35:09", "remaining_time": "1 day, 3:10:33", "throughput": 554.27, "total_tokens": 11145792} {"current_steps": 6825, "total_steps": 40000, "loss": 0.0986, "lr": 4.6494524449408786e-05, "epoch": 0.3089703252676611, "percentage": 17.06, "elapsed_time": "5:35:12", "remaining_time": "1 day, 3:09:21", "throughput": 554.56, "total_tokens": 11153440} {"current_steps": 6830, "total_steps": 40000, "loss": 0.1154, "lr": 4.6489509370180903e-05, "epoch": 0.3091966771543041, "percentage": 17.08, "elapsed_time": "5:35:15", "remaining_time": "1 day, 3:08:10", "throughput": 554.86, "total_tokens": 11161216} {"current_steps": 6835, "total_steps": 40000, "loss": 0.1577, "lr": 4.648449097700063e-05, "epoch": 0.30942302904094704, "percentage": 17.09, "elapsed_time": "5:35:18", "remaining_time": "1 day, 3:06:59", "throughput": 555.16, "total_tokens": 11168928} {"current_steps": 6840, "total_steps": 40000, "loss": 0.1981, "lr": 4.647946927064185e-05, "epoch": 0.30964938092759003, "percentage": 17.1, "elapsed_time": "5:35:21", "remaining_time": "1 day, 3:05:49", "throughput": 555.49, "total_tokens": 11177312} {"current_steps": 6845, "total_steps": 40000, "loss": 0.1664, "lr": 4.647444425187898e-05, "epoch": 0.30987573281423303, "percentage": 17.11, "elapsed_time": "5:35:24", "remaining_time": "1 day, 3:04:38", "throughput": 555.82, "total_tokens": 11185760} {"current_steps": 6850, "total_steps": 40000, "loss": 0.2307, "lr": 4.646941592148695e-05, "epoch": 0.31010208470087597, "percentage": 17.12, "elapsed_time": "5:35:28", "remaining_time": "1 day, 3:03:28", "throughput": 556.13, "total_tokens": 11193792} {"current_steps": 6855, "total_steps": 40000, "loss": 0.1666, "lr": 4.646438428024117e-05, "epoch": 0.31032843658751896, "percentage": 17.14, "elapsed_time": "5:35:31", "remaining_time": "1 day, 3:02:18", "throughput": 556.46, "total_tokens": 11202272} {"current_steps": 6860, "total_steps": 40000, "loss": 0.1081, "lr": 4.64593493289176e-05, "epoch": 0.31055478847416196, "percentage": 17.15, "elapsed_time": "5:35:34", "remaining_time": "1 day, 3:01:07", "throughput": 556.79, "total_tokens": 11210624} {"current_steps": 6865, "total_steps": 40000, "loss": 0.1788, "lr": 4.64543110682927e-05, "epoch": 0.3107811403608049, "percentage": 17.16, "elapsed_time": "5:35:37", "remaining_time": "1 day, 2:59:57", "throughput": 557.1, "total_tokens": 11218752} {"current_steps": 6870, "total_steps": 40000, "loss": 0.14, "lr": 4.644926949914341e-05, "epoch": 0.3110074922474479, "percentage": 17.18, "elapsed_time": "5:35:40", "remaining_time": "1 day, 2:58:47", "throughput": 557.43, "total_tokens": 11227040} {"current_steps": 6875, "total_steps": 40000, "loss": 0.171, "lr": 4.644422462224722e-05, "epoch": 0.31123384413409083, "percentage": 17.19, "elapsed_time": "5:35:44", "remaining_time": "1 day, 2:57:39", "throughput": 557.82, "total_tokens": 11236896} {"current_steps": 6880, "total_steps": 40000, "loss": 0.1264, "lr": 4.643917643838211e-05, "epoch": 0.3114601960207338, "percentage": 17.2, "elapsed_time": "5:35:47", "remaining_time": "1 day, 2:56:28", "throughput": 558.12, "total_tokens": 11244640} {"current_steps": 6885, "total_steps": 40000, "loss": 0.1287, "lr": 4.6434124948326564e-05, "epoch": 0.3116865479073768, "percentage": 17.21, "elapsed_time": "5:35:50", "remaining_time": "1 day, 2:55:19", "throughput": 558.43, "total_tokens": 11252704} {"current_steps": 6890, "total_steps": 40000, "loss": 0.1266, "lr": 4.6429070152859594e-05, "epoch": 0.31191289979401976, "percentage": 17.22, "elapsed_time": "5:35:53", "remaining_time": "1 day, 2:54:09", "throughput": 558.75, "total_tokens": 11261056} {"current_steps": 6895, "total_steps": 40000, "loss": 0.1385, "lr": 4.6424012052760714e-05, "epoch": 0.31213925168066275, "percentage": 17.24, "elapsed_time": "5:35:57", "remaining_time": "1 day, 2:53:00", "throughput": 559.1, "total_tokens": 11269792} {"current_steps": 6900, "total_steps": 40000, "loss": 0.1773, "lr": 4.6418950648809945e-05, "epoch": 0.31236560356730575, "percentage": 17.25, "elapsed_time": "5:36:00", "remaining_time": "1 day, 2:51:51", "throughput": 559.41, "total_tokens": 11277792} {"current_steps": 6905, "total_steps": 40000, "loss": 0.1072, "lr": 4.641388594178782e-05, "epoch": 0.3125919554539487, "percentage": 17.26, "elapsed_time": "5:36:03", "remaining_time": "1 day, 2:50:41", "throughput": 559.71, "total_tokens": 11285632} {"current_steps": 6910, "total_steps": 40000, "loss": 0.1788, "lr": 4.640881793247538e-05, "epoch": 0.3128183073405917, "percentage": 17.27, "elapsed_time": "5:36:06", "remaining_time": "1 day, 2:49:32", "throughput": 560.03, "total_tokens": 11293888} {"current_steps": 6915, "total_steps": 40000, "loss": 0.1201, "lr": 4.6403746621654173e-05, "epoch": 0.3130446592272347, "percentage": 17.29, "elapsed_time": "5:36:09", "remaining_time": "1 day, 2:48:22", "throughput": 560.34, "total_tokens": 11301856} {"current_steps": 6920, "total_steps": 40000, "loss": 0.1365, "lr": 4.639867201010626e-05, "epoch": 0.3132710111138776, "percentage": 17.3, "elapsed_time": "5:36:12", "remaining_time": "1 day, 2:47:13", "throughput": 560.67, "total_tokens": 11310304} {"current_steps": 6925, "total_steps": 40000, "loss": 0.1499, "lr": 4.6393594098614204e-05, "epoch": 0.3134973630005206, "percentage": 17.31, "elapsed_time": "5:36:16", "remaining_time": "1 day, 2:46:05", "throughput": 561.0, "total_tokens": 11318784} {"current_steps": 6930, "total_steps": 40000, "loss": 0.1179, "lr": 4.63885128879611e-05, "epoch": 0.3137237148871636, "percentage": 17.32, "elapsed_time": "5:36:19", "remaining_time": "1 day, 2:44:56", "throughput": 561.31, "total_tokens": 11326976} {"current_steps": 6935, "total_steps": 40000, "loss": 0.1633, "lr": 4.638342837893052e-05, "epoch": 0.31395006677380655, "percentage": 17.34, "elapsed_time": "5:36:22", "remaining_time": "1 day, 2:43:47", "throughput": 561.6, "total_tokens": 11334528} {"current_steps": 6940, "total_steps": 40000, "loss": 0.0835, "lr": 4.6378340572306565e-05, "epoch": 0.31417641866044954, "percentage": 17.35, "elapsed_time": "5:36:25", "remaining_time": "1 day, 2:42:38", "throughput": 561.92, "total_tokens": 11342688} {"current_steps": 6945, "total_steps": 40000, "loss": 0.1387, "lr": 4.6373249468873833e-05, "epoch": 0.31440277054709254, "percentage": 17.36, "elapsed_time": "5:36:28", "remaining_time": "1 day, 2:41:29", "throughput": 562.22, "total_tokens": 11350624} {"current_steps": 6950, "total_steps": 40000, "loss": 0.1396, "lr": 4.636815506941744e-05, "epoch": 0.3146291224337355, "percentage": 17.38, "elapsed_time": "5:36:31", "remaining_time": "1 day, 2:40:20", "throughput": 562.52, "total_tokens": 11358336} {"current_steps": 6955, "total_steps": 40000, "loss": 0.1491, "lr": 4.6363057374723004e-05, "epoch": 0.31485547432037847, "percentage": 17.39, "elapsed_time": "5:36:35", "remaining_time": "1 day, 2:39:11", "throughput": 562.82, "total_tokens": 11366144} {"current_steps": 6960, "total_steps": 40000, "loss": 0.1648, "lr": 4.635795638557666e-05, "epoch": 0.3150818262070214, "percentage": 17.4, "elapsed_time": "5:36:38", "remaining_time": "1 day, 2:38:04", "throughput": 563.16, "total_tokens": 11375008} {"current_steps": 6965, "total_steps": 40000, "loss": 0.1034, "lr": 4.635285210276504e-05, "epoch": 0.3153081780936644, "percentage": 17.41, "elapsed_time": "5:36:41", "remaining_time": "1 day, 2:36:57", "throughput": 563.48, "total_tokens": 11383360} {"current_steps": 6970, "total_steps": 40000, "loss": 0.0859, "lr": 4.6347744527075295e-05, "epoch": 0.3155345299803074, "percentage": 17.42, "elapsed_time": "5:36:45", "remaining_time": "1 day, 2:35:49", "throughput": 563.81, "total_tokens": 11391872} {"current_steps": 6975, "total_steps": 40000, "loss": 0.1852, "lr": 4.634263365929506e-05, "epoch": 0.31576088186695034, "percentage": 17.44, "elapsed_time": "5:36:48", "remaining_time": "1 day, 2:34:41", "throughput": 564.14, "total_tokens": 11400288} {"current_steps": 6980, "total_steps": 40000, "loss": 0.1421, "lr": 4.6337519500212515e-05, "epoch": 0.31598723375359333, "percentage": 17.45, "elapsed_time": "5:36:51", "remaining_time": "1 day, 2:33:34", "throughput": 564.46, "total_tokens": 11408640} {"current_steps": 6985, "total_steps": 40000, "loss": 0.1675, "lr": 4.633240205061632e-05, "epoch": 0.3162135856402363, "percentage": 17.46, "elapsed_time": "5:36:55", "remaining_time": "1 day, 2:32:27", "throughput": 564.82, "total_tokens": 11417920} {"current_steps": 6990, "total_steps": 40000, "loss": 0.1034, "lr": 4.632728131129565e-05, "epoch": 0.31643993752687927, "percentage": 17.47, "elapsed_time": "5:36:58", "remaining_time": "1 day, 2:31:19", "throughput": 565.11, "total_tokens": 11425536} {"current_steps": 6995, "total_steps": 40000, "loss": 0.0771, "lr": 4.632215728304018e-05, "epoch": 0.31666628941352226, "percentage": 17.49, "elapsed_time": "5:37:01", "remaining_time": "1 day, 2:30:11", "throughput": 565.41, "total_tokens": 11433216} {"current_steps": 7000, "total_steps": 40000, "loss": 0.1425, "lr": 4.63170299666401e-05, "epoch": 0.31689264130016526, "percentage": 17.5, "elapsed_time": "5:37:04", "remaining_time": "1 day, 2:29:03", "throughput": 565.71, "total_tokens": 11441248} {"current_steps": 7000, "total_steps": 40000, "eval_loss": 0.1486380696296692, "epoch": 0.31689264130016526, "percentage": 17.5, "elapsed_time": "5:44:47", "remaining_time": "1 day, 3:05:25", "throughput": 553.06, "total_tokens": 11441248} {"current_steps": 7005, "total_steps": 40000, "loss": 0.1827, "lr": 4.631189936288612e-05, "epoch": 0.3171189931868082, "percentage": 17.51, "elapsed_time": "5:44:51", "remaining_time": "1 day, 3:04:20", "throughput": 553.36, "total_tokens": 11449632} {"current_steps": 7010, "total_steps": 40000, "loss": 0.1524, "lr": 4.630676547256944e-05, "epoch": 0.3173453450734512, "percentage": 17.52, "elapsed_time": "5:44:54", "remaining_time": "1 day, 3:03:10", "throughput": 553.65, "total_tokens": 11457568} {"current_steps": 7015, "total_steps": 40000, "loss": 0.1788, "lr": 4.630162829648176e-05, "epoch": 0.3175716969600942, "percentage": 17.54, "elapsed_time": "5:44:57", "remaining_time": "1 day, 3:02:01", "throughput": 553.98, "total_tokens": 11466048} {"current_steps": 7020, "total_steps": 40000, "loss": 0.153, "lr": 4.629648783541531e-05, "epoch": 0.3177980488467371, "percentage": 17.55, "elapsed_time": "5:45:00", "remaining_time": "1 day, 3:00:52", "throughput": 554.3, "total_tokens": 11474496} {"current_steps": 7025, "total_steps": 40000, "loss": 0.1189, "lr": 4.6291344090162804e-05, "epoch": 0.3180244007333801, "percentage": 17.56, "elapsed_time": "5:45:04", "remaining_time": "1 day, 2:59:43", "throughput": 554.62, "total_tokens": 11482912} {"current_steps": 7030, "total_steps": 40000, "loss": 0.147, "lr": 4.628619706151748e-05, "epoch": 0.3182507526200231, "percentage": 17.57, "elapsed_time": "5:45:07", "remaining_time": "1 day, 2:58:35", "throughput": 554.95, "total_tokens": 11491424} {"current_steps": 7035, "total_steps": 40000, "loss": 0.1329, "lr": 4.628104675027306e-05, "epoch": 0.31847710450666605, "percentage": 17.59, "elapsed_time": "5:45:10", "remaining_time": "1 day, 2:57:26", "throughput": 555.27, "total_tokens": 11499904} {"current_steps": 7040, "total_steps": 40000, "loss": 0.1254, "lr": 4.6275893157223805e-05, "epoch": 0.31870345639330905, "percentage": 17.6, "elapsed_time": "5:45:13", "remaining_time": "1 day, 2:56:17", "throughput": 555.6, "total_tokens": 11508608} {"current_steps": 7045, "total_steps": 40000, "loss": 0.0778, "lr": 4.627073628316445e-05, "epoch": 0.318929808279952, "percentage": 17.61, "elapsed_time": "5:45:16", "remaining_time": "1 day, 2:55:09", "throughput": 555.92, "total_tokens": 11516928} {"current_steps": 7050, "total_steps": 40000, "loss": 0.1258, "lr": 4.626557612889026e-05, "epoch": 0.319156160166595, "percentage": 17.62, "elapsed_time": "5:45:20", "remaining_time": "1 day, 2:54:00", "throughput": 556.21, "total_tokens": 11524736} {"current_steps": 7055, "total_steps": 40000, "loss": 0.1683, "lr": 4.626041269519699e-05, "epoch": 0.319382512053238, "percentage": 17.64, "elapsed_time": "5:45:23", "remaining_time": "1 day, 2:52:51", "throughput": 556.49, "total_tokens": 11532352} {"current_steps": 7060, "total_steps": 40000, "loss": 0.1171, "lr": 4.6255245982880905e-05, "epoch": 0.3196088639398809, "percentage": 17.65, "elapsed_time": "5:45:26", "remaining_time": "1 day, 2:51:43", "throughput": 556.8, "total_tokens": 11540480} {"current_steps": 7065, "total_steps": 40000, "loss": 0.1234, "lr": 4.625007599273879e-05, "epoch": 0.3198352158265239, "percentage": 17.66, "elapsed_time": "5:45:29", "remaining_time": "1 day, 2:50:35", "throughput": 557.11, "total_tokens": 11548640} {"current_steps": 7070, "total_steps": 40000, "loss": 0.1545, "lr": 4.6244902725567895e-05, "epoch": 0.3200615677131669, "percentage": 17.68, "elapsed_time": "5:45:32", "remaining_time": "1 day, 2:49:26", "throughput": 557.41, "total_tokens": 11556608} {"current_steps": 7075, "total_steps": 40000, "loss": 0.1338, "lr": 4.6239726182166024e-05, "epoch": 0.32028791959980984, "percentage": 17.69, "elapsed_time": "5:45:35", "remaining_time": "1 day, 2:48:18", "throughput": 557.68, "total_tokens": 11564032} {"current_steps": 7080, "total_steps": 40000, "loss": 0.1967, "lr": 4.623454636333147e-05, "epoch": 0.32051427148645284, "percentage": 17.7, "elapsed_time": "5:45:38", "remaining_time": "1 day, 2:47:09", "throughput": 557.96, "total_tokens": 11571424} {"current_steps": 7085, "total_steps": 40000, "loss": 0.1134, "lr": 4.622936326986301e-05, "epoch": 0.32074062337309583, "percentage": 17.71, "elapsed_time": "5:45:42", "remaining_time": "1 day, 2:46:02", "throughput": 558.27, "total_tokens": 11579776} {"current_steps": 7090, "total_steps": 40000, "loss": 0.1675, "lr": 4.6224176902559946e-05, "epoch": 0.3209669752597388, "percentage": 17.72, "elapsed_time": "5:45:45", "remaining_time": "1 day, 2:44:54", "throughput": 558.58, "total_tokens": 11587872} {"current_steps": 7095, "total_steps": 40000, "loss": 0.1721, "lr": 4.621898726222209e-05, "epoch": 0.32119332714638177, "percentage": 17.74, "elapsed_time": "5:45:48", "remaining_time": "1 day, 2:43:47", "throughput": 558.92, "total_tokens": 11596768} {"current_steps": 7100, "total_steps": 40000, "loss": 0.1253, "lr": 4.6213794349649744e-05, "epoch": 0.32141967903302476, "percentage": 17.75, "elapsed_time": "5:45:51", "remaining_time": "1 day, 2:42:40", "throughput": 559.25, "total_tokens": 11605408} {"current_steps": 7105, "total_steps": 40000, "loss": 0.1332, "lr": 4.6208598165643715e-05, "epoch": 0.3216460309196677, "percentage": 17.76, "elapsed_time": "5:45:54", "remaining_time": "1 day, 2:41:32", "throughput": 559.55, "total_tokens": 11613376} {"current_steps": 7110, "total_steps": 40000, "loss": 0.1436, "lr": 4.620339871100533e-05, "epoch": 0.3218723828063107, "percentage": 17.77, "elapsed_time": "5:45:58", "remaining_time": "1 day, 2:40:24", "throughput": 559.85, "total_tokens": 11621344} {"current_steps": 7115, "total_steps": 40000, "loss": 0.1557, "lr": 4.6198195986536394e-05, "epoch": 0.3220987346929537, "percentage": 17.79, "elapsed_time": "5:46:01", "remaining_time": "1 day, 2:39:16", "throughput": 560.14, "total_tokens": 11629152} {"current_steps": 7120, "total_steps": 40000, "loss": 0.1413, "lr": 4.619298999303926e-05, "epoch": 0.32232508657959663, "percentage": 17.8, "elapsed_time": "5:46:04", "remaining_time": "1 day, 2:38:09", "throughput": 560.45, "total_tokens": 11637504} {"current_steps": 7125, "total_steps": 40000, "loss": 0.2019, "lr": 4.618778073131673e-05, "epoch": 0.3225514384662396, "percentage": 17.81, "elapsed_time": "5:46:07", "remaining_time": "1 day, 2:37:02", "throughput": 560.75, "total_tokens": 11645472} {"current_steps": 7130, "total_steps": 40000, "loss": 0.1411, "lr": 4.618256820217215e-05, "epoch": 0.32277779035288257, "percentage": 17.82, "elapsed_time": "5:46:10", "remaining_time": "1 day, 2:35:54", "throughput": 561.03, "total_tokens": 11652992} {"current_steps": 7135, "total_steps": 40000, "loss": 0.1352, "lr": 4.617735240640936e-05, "epoch": 0.32300414223952556, "percentage": 17.84, "elapsed_time": "5:46:13", "remaining_time": "1 day, 2:34:48", "throughput": 561.36, "total_tokens": 11661664} {"current_steps": 7140, "total_steps": 40000, "loss": 0.1616, "lr": 4.6172133344832705e-05, "epoch": 0.32323049412616855, "percentage": 17.85, "elapsed_time": "5:46:17", "remaining_time": "1 day, 2:33:41", "throughput": 561.67, "total_tokens": 11669984} {"current_steps": 7145, "total_steps": 40000, "loss": 0.155, "lr": 4.6166911018247004e-05, "epoch": 0.3234568460128115, "percentage": 17.86, "elapsed_time": "5:46:20", "remaining_time": "1 day, 2:32:35", "throughput": 562.01, "total_tokens": 11678816} {"current_steps": 7150, "total_steps": 40000, "loss": 0.1755, "lr": 4.616168542745764e-05, "epoch": 0.3236831978994545, "percentage": 17.88, "elapsed_time": "5:46:23", "remaining_time": "1 day, 2:31:28", "throughput": 562.3, "total_tokens": 11686624} {"current_steps": 7155, "total_steps": 40000, "loss": 0.1388, "lr": 4.6156456573270446e-05, "epoch": 0.3239095497860975, "percentage": 17.89, "elapsed_time": "5:46:26", "remaining_time": "1 day, 2:30:21", "throughput": 562.61, "total_tokens": 11694752} {"current_steps": 7160, "total_steps": 40000, "loss": 0.1441, "lr": 4.615122445649177e-05, "epoch": 0.3241359016727404, "percentage": 17.9, "elapsed_time": "5:46:30", "remaining_time": "1 day, 2:29:16", "throughput": 562.97, "total_tokens": 11704224} {"current_steps": 7165, "total_steps": 40000, "loss": 0.1327, "lr": 4.6145989077928486e-05, "epoch": 0.3243622535593834, "percentage": 17.91, "elapsed_time": "5:46:33", "remaining_time": "1 day, 2:28:10", "throughput": 563.3, "total_tokens": 11712928} {"current_steps": 7170, "total_steps": 40000, "loss": 0.1617, "lr": 4.6140750438387953e-05, "epoch": 0.3245886054460264, "percentage": 17.93, "elapsed_time": "5:46:36", "remaining_time": "1 day, 2:27:04", "throughput": 563.61, "total_tokens": 11721184} {"current_steps": 7175, "total_steps": 40000, "loss": 0.1637, "lr": 4.613550853867803e-05, "epoch": 0.32481495733266935, "percentage": 17.94, "elapsed_time": "5:46:40", "remaining_time": "1 day, 2:25:59", "throughput": 563.99, "total_tokens": 11731168} {"current_steps": 7180, "total_steps": 40000, "loss": 0.1709, "lr": 4.613026337960708e-05, "epoch": 0.32504130921931235, "percentage": 17.95, "elapsed_time": "5:46:43", "remaining_time": "1 day, 2:24:52", "throughput": 564.3, "total_tokens": 11739360} {"current_steps": 7185, "total_steps": 40000, "loss": 0.1433, "lr": 4.612501496198398e-05, "epoch": 0.32526766110595534, "percentage": 17.96, "elapsed_time": "5:46:46", "remaining_time": "1 day, 2:23:46", "throughput": 564.61, "total_tokens": 11747616} {"current_steps": 7190, "total_steps": 40000, "loss": 0.1508, "lr": 4.61197632866181e-05, "epoch": 0.3254940129925983, "percentage": 17.97, "elapsed_time": "5:46:49", "remaining_time": "1 day, 2:22:40", "throughput": 564.9, "total_tokens": 11755360} {"current_steps": 7195, "total_steps": 40000, "loss": 0.1722, "lr": 4.611450835431931e-05, "epoch": 0.3257203648792413, "percentage": 17.99, "elapsed_time": "5:46:52", "remaining_time": "1 day, 2:21:34", "throughput": 565.2, "total_tokens": 11763392} {"current_steps": 7200, "total_steps": 40000, "loss": 0.0777, "lr": 4.6109250165898e-05, "epoch": 0.32594671676588427, "percentage": 18.0, "elapsed_time": "5:46:56", "remaining_time": "1 day, 2:20:28", "throughput": 565.51, "total_tokens": 11771744} {"current_steps": 7200, "total_steps": 40000, "eval_loss": 0.14836011826992035, "epoch": 0.32594671676588427, "percentage": 18.0, "elapsed_time": "5:54:38", "remaining_time": "1 day, 2:55:36", "throughput": 553.22, "total_tokens": 11771744} {"current_steps": 7205, "total_steps": 40000, "loss": 0.1244, "lr": 4.610398872216503e-05, "epoch": 0.3261730686525272, "percentage": 18.01, "elapsed_time": "5:54:42", "remaining_time": "1 day, 2:54:33", "throughput": 553.48, "total_tokens": 11779712} {"current_steps": 7210, "total_steps": 40000, "loss": 0.1192, "lr": 4.6098724023931796e-05, "epoch": 0.3263994205391702, "percentage": 18.02, "elapsed_time": "5:54:45", "remaining_time": "1 day, 2:53:25", "throughput": 553.76, "total_tokens": 11787360} {"current_steps": 7215, "total_steps": 40000, "loss": 0.1566, "lr": 4.609345607201017e-05, "epoch": 0.32662577242581314, "percentage": 18.04, "elapsed_time": "5:54:49", "remaining_time": "1 day, 2:52:17", "throughput": 554.05, "total_tokens": 11795296} {"current_steps": 7220, "total_steps": 40000, "loss": 0.1279, "lr": 4.608818486721254e-05, "epoch": 0.32685212431245614, "percentage": 18.05, "elapsed_time": "5:54:52", "remaining_time": "1 day, 2:51:10", "throughput": 554.34, "total_tokens": 11803072} {"current_steps": 7225, "total_steps": 40000, "loss": 0.2216, "lr": 4.608291041035179e-05, "epoch": 0.32707847619909913, "percentage": 18.06, "elapsed_time": "5:54:55", "remaining_time": "1 day, 2:50:03", "throughput": 554.64, "total_tokens": 11811360} {"current_steps": 7230, "total_steps": 40000, "loss": 0.1223, "lr": 4.607763270224132e-05, "epoch": 0.32730482808574207, "percentage": 18.07, "elapsed_time": "5:54:58", "remaining_time": "1 day, 2:48:56", "throughput": 554.94, "total_tokens": 11819488} {"current_steps": 7235, "total_steps": 40000, "loss": 0.1518, "lr": 4.6072351743695e-05, "epoch": 0.32753117997238507, "percentage": 18.09, "elapsed_time": "5:55:01", "remaining_time": "1 day, 2:47:49", "throughput": 555.22, "total_tokens": 11827168} {"current_steps": 7240, "total_steps": 40000, "loss": 0.1155, "lr": 4.606706753552723e-05, "epoch": 0.32775753185902806, "percentage": 18.1, "elapsed_time": "5:55:04", "remaining_time": "1 day, 2:46:41", "throughput": 555.51, "total_tokens": 11835136} {"current_steps": 7245, "total_steps": 40000, "loss": 0.1034, "lr": 4.6061780078552906e-05, "epoch": 0.327983883745671, "percentage": 18.11, "elapsed_time": "5:55:08", "remaining_time": "1 day, 2:45:34", "throughput": 555.81, "total_tokens": 11843232} {"current_steps": 7250, "total_steps": 40000, "loss": 0.1482, "lr": 4.605648937358742e-05, "epoch": 0.328210235632314, "percentage": 18.12, "elapsed_time": "5:55:11", "remaining_time": "1 day, 2:44:28", "throughput": 556.12, "total_tokens": 11851616} {"current_steps": 7255, "total_steps": 40000, "loss": 0.1329, "lr": 4.605119542144665e-05, "epoch": 0.328436587518957, "percentage": 18.14, "elapsed_time": "5:55:14", "remaining_time": "1 day, 2:43:21", "throughput": 556.44, "total_tokens": 11860160} {"current_steps": 7260, "total_steps": 40000, "loss": 0.1843, "lr": 4.604589822294701e-05, "epoch": 0.32866293940559993, "percentage": 18.15, "elapsed_time": "5:55:17", "remaining_time": "1 day, 2:42:14", "throughput": 556.73, "total_tokens": 11868160} {"current_steps": 7265, "total_steps": 40000, "loss": 0.126, "lr": 4.604059777890537e-05, "epoch": 0.3288892912922429, "percentage": 18.16, "elapsed_time": "5:55:20", "remaining_time": "1 day, 2:41:08", "throughput": 557.03, "total_tokens": 11876320} {"current_steps": 7270, "total_steps": 40000, "loss": 0.1849, "lr": 4.6035294090139145e-05, "epoch": 0.3291156431788859, "percentage": 18.18, "elapsed_time": "5:55:23", "remaining_time": "1 day, 2:40:01", "throughput": 557.31, "total_tokens": 11884128} {"current_steps": 7275, "total_steps": 40000, "loss": 0.1049, "lr": 4.6029987157466226e-05, "epoch": 0.32934199506552886, "percentage": 18.19, "elapsed_time": "5:55:27", "remaining_time": "1 day, 2:38:55", "throughput": 557.6, "total_tokens": 11892064} {"current_steps": 7280, "total_steps": 40000, "loss": 0.1115, "lr": 4.602467698170502e-05, "epoch": 0.32956834695217185, "percentage": 18.2, "elapsed_time": "5:55:30", "remaining_time": "1 day, 2:37:48", "throughput": 557.9, "total_tokens": 11900224} {"current_steps": 7285, "total_steps": 40000, "loss": 0.2107, "lr": 4.601936356367439e-05, "epoch": 0.32979469883881485, "percentage": 18.21, "elapsed_time": "5:55:33", "remaining_time": "1 day, 2:36:42", "throughput": 558.18, "total_tokens": 11907904} {"current_steps": 7290, "total_steps": 40000, "loss": 0.1029, "lr": 4.601404690419377e-05, "epoch": 0.3300210507254578, "percentage": 18.22, "elapsed_time": "5:55:36", "remaining_time": "1 day, 2:35:36", "throughput": 558.49, "total_tokens": 11916256} {"current_steps": 7295, "total_steps": 40000, "loss": 0.1612, "lr": 4.600872700408303e-05, "epoch": 0.3302474026121008, "percentage": 18.24, "elapsed_time": "5:55:39", "remaining_time": "1 day, 2:34:29", "throughput": 558.77, "total_tokens": 11923808} {"current_steps": 7300, "total_steps": 40000, "loss": 0.1805, "lr": 4.600340386416258e-05, "epoch": 0.3304737544987437, "percentage": 18.25, "elapsed_time": "5:55:42", "remaining_time": "1 day, 2:33:23", "throughput": 559.08, "total_tokens": 11932288} {"current_steps": 7305, "total_steps": 40000, "loss": 0.1263, "lr": 4.5998077485253296e-05, "epoch": 0.3307001063853867, "percentage": 18.26, "elapsed_time": "5:55:45", "remaining_time": "1 day, 2:32:18", "throughput": 559.38, "total_tokens": 11940480} {"current_steps": 7310, "total_steps": 40000, "loss": 0.1655, "lr": 4.59927478681766e-05, "epoch": 0.3309264582720297, "percentage": 18.27, "elapsed_time": "5:55:49", "remaining_time": "1 day, 2:31:12", "throughput": 559.67, "total_tokens": 11948512} {"current_steps": 7315, "total_steps": 40000, "loss": 0.1081, "lr": 4.5987415013754366e-05, "epoch": 0.33115281015867265, "percentage": 18.29, "elapsed_time": "5:55:52", "remaining_time": "1 day, 2:30:06", "throughput": 559.98, "total_tokens": 11956896} {"current_steps": 7320, "total_steps": 40000, "loss": 0.1622, "lr": 4.598207892280899e-05, "epoch": 0.33137916204531565, "percentage": 18.3, "elapsed_time": "5:55:55", "remaining_time": "1 day, 2:29:00", "throughput": 560.28, "total_tokens": 11964960} {"current_steps": 7325, "total_steps": 40000, "loss": 0.2402, "lr": 4.597673959616337e-05, "epoch": 0.33160551393195864, "percentage": 18.31, "elapsed_time": "5:55:58", "remaining_time": "1 day, 2:27:55", "throughput": 560.59, "total_tokens": 11973408} {"current_steps": 7330, "total_steps": 40000, "loss": 0.1118, "lr": 4.597139703464089e-05, "epoch": 0.3318318658186016, "percentage": 18.32, "elapsed_time": "5:56:01", "remaining_time": "1 day, 2:26:50", "throughput": 560.89, "total_tokens": 11981504} {"current_steps": 7335, "total_steps": 40000, "loss": 0.1377, "lr": 4.596605123906545e-05, "epoch": 0.3320582177052446, "percentage": 18.34, "elapsed_time": "5:56:04", "remaining_time": "1 day, 2:25:44", "throughput": 561.19, "total_tokens": 11989792} {"current_steps": 7340, "total_steps": 40000, "loss": 0.1463, "lr": 4.596070221026143e-05, "epoch": 0.33228456959188757, "percentage": 18.35, "elapsed_time": "5:56:08", "remaining_time": "1 day, 2:24:39", "throughput": 561.49, "total_tokens": 11997920} {"current_steps": 7345, "total_steps": 40000, "loss": 0.1709, "lr": 4.595534994905372e-05, "epoch": 0.3325109214785305, "percentage": 18.36, "elapsed_time": "5:56:11", "remaining_time": "1 day, 2:23:34", "throughput": 561.78, "total_tokens": 12005952} {"current_steps": 7350, "total_steps": 40000, "loss": 0.104, "lr": 4.594999445626771e-05, "epoch": 0.3327372733651735, "percentage": 18.38, "elapsed_time": "5:56:14", "remaining_time": "1 day, 2:22:29", "throughput": 562.08, "total_tokens": 12014144} {"current_steps": 7355, "total_steps": 40000, "loss": 0.1116, "lr": 4.5944635732729276e-05, "epoch": 0.3329636252518165, "percentage": 18.39, "elapsed_time": "5:56:17", "remaining_time": "1 day, 2:21:24", "throughput": 562.39, "total_tokens": 12022688} {"current_steps": 7360, "total_steps": 40000, "loss": 0.1787, "lr": 4.5939273779264804e-05, "epoch": 0.33318997713845944, "percentage": 18.4, "elapsed_time": "5:56:20", "remaining_time": "1 day, 2:20:19", "throughput": 562.69, "total_tokens": 12030848} {"current_steps": 7365, "total_steps": 40000, "loss": 0.1331, "lr": 4.593390859670118e-05, "epoch": 0.33341632902510243, "percentage": 18.41, "elapsed_time": "5:56:24", "remaining_time": "1 day, 2:19:15", "throughput": 562.98, "total_tokens": 12038880} {"current_steps": 7370, "total_steps": 40000, "loss": 0.1275, "lr": 4.5928540185865776e-05, "epoch": 0.3336426809117454, "percentage": 18.43, "elapsed_time": "5:56:27", "remaining_time": "1 day, 2:18:10", "throughput": 563.28, "total_tokens": 12047040} {"current_steps": 7375, "total_steps": 40000, "loss": 0.1361, "lr": 4.592316854758648e-05, "epoch": 0.33386903279838837, "percentage": 18.44, "elapsed_time": "5:56:30", "remaining_time": "1 day, 2:17:05", "throughput": 563.55, "total_tokens": 12054624} {"current_steps": 7380, "total_steps": 40000, "loss": 0.2126, "lr": 4.5917793682691646e-05, "epoch": 0.33409538468503136, "percentage": 18.45, "elapsed_time": "5:56:33", "remaining_time": "1 day, 2:16:00", "throughput": 563.84, "total_tokens": 12062656} {"current_steps": 7385, "total_steps": 40000, "loss": 0.1693, "lr": 4.5912415592010164e-05, "epoch": 0.3343217365716743, "percentage": 18.46, "elapsed_time": "5:56:36", "remaining_time": "1 day, 2:14:56", "throughput": 564.13, "total_tokens": 12070432} {"current_steps": 7390, "total_steps": 40000, "loss": 0.1596, "lr": 4.5907034276371386e-05, "epoch": 0.3345480884583173, "percentage": 18.48, "elapsed_time": "5:56:39", "remaining_time": "1 day, 2:13:52", "throughput": 564.43, "total_tokens": 12078784} {"current_steps": 7395, "total_steps": 40000, "loss": 0.1348, "lr": 4.5901649736605196e-05, "epoch": 0.3347744403449603, "percentage": 18.49, "elapsed_time": "5:56:43", "remaining_time": "1 day, 2:12:47", "throughput": 564.72, "total_tokens": 12086720} {"current_steps": 7400, "total_steps": 40000, "loss": 0.172, "lr": 4.589626197354195e-05, "epoch": 0.33500079223160323, "percentage": 18.5, "elapsed_time": "5:56:46", "remaining_time": "1 day, 2:11:43", "throughput": 564.99, "total_tokens": 12094400} {"current_steps": 7400, "total_steps": 40000, "eval_loss": 0.14723092317581177, "epoch": 0.33500079223160323, "percentage": 18.5, "elapsed_time": "6:04:28", "remaining_time": "1 day, 2:45:41", "throughput": 553.04, "total_tokens": 12094400} {"current_steps": 7405, "total_steps": 40000, "loss": 0.1551, "lr": 4.5890870988012504e-05, "epoch": 0.3352271441182462, "percentage": 18.51, "elapsed_time": "6:04:32", "remaining_time": "1 day, 2:44:38", "throughput": 553.3, "total_tokens": 12102304} {"current_steps": 7410, "total_steps": 40000, "loss": 0.1408, "lr": 4.5885476780848226e-05, "epoch": 0.3354534960048892, "percentage": 18.52, "elapsed_time": "6:04:35", "remaining_time": "1 day, 2:43:32", "throughput": 553.6, "total_tokens": 12110464} {"current_steps": 7415, "total_steps": 40000, "loss": 0.1612, "lr": 4.5880079352880964e-05, "epoch": 0.33567984789153216, "percentage": 18.54, "elapsed_time": "6:04:39", "remaining_time": "1 day, 2:42:26", "throughput": 553.89, "total_tokens": 12118624} {"current_steps": 7420, "total_steps": 40000, "loss": 0.1687, "lr": 4.5874678704943065e-05, "epoch": 0.33590619977817515, "percentage": 18.55, "elapsed_time": "6:04:42", "remaining_time": "1 day, 2:41:21", "throughput": 554.17, "total_tokens": 12126560} {"current_steps": 7425, "total_steps": 40000, "loss": 0.1359, "lr": 4.5869274837867394e-05, "epoch": 0.33613255166481815, "percentage": 18.56, "elapsed_time": "6:04:45", "remaining_time": "1 day, 2:40:15", "throughput": 554.49, "total_tokens": 12135168} {"current_steps": 7430, "total_steps": 40000, "loss": 0.1406, "lr": 4.5863867752487275e-05, "epoch": 0.3363589035514611, "percentage": 18.57, "elapsed_time": "6:04:48", "remaining_time": "1 day, 2:39:10", "throughput": 554.76, "total_tokens": 12142848} {"current_steps": 7435, "total_steps": 40000, "loss": 0.1265, "lr": 4.5858457449636554e-05, "epoch": 0.3365852554381041, "percentage": 18.59, "elapsed_time": "6:04:51", "remaining_time": "1 day, 2:38:04", "throughput": 555.04, "total_tokens": 12150848} {"current_steps": 7440, "total_steps": 40000, "loss": 0.1209, "lr": 4.5853043930149574e-05, "epoch": 0.3368116073247471, "percentage": 18.6, "elapsed_time": "6:04:54", "remaining_time": "1 day, 2:36:59", "throughput": 555.34, "total_tokens": 12159040} {"current_steps": 7445, "total_steps": 40000, "loss": 0.1619, "lr": 4.584762719486117e-05, "epoch": 0.33703795921139, "percentage": 18.61, "elapsed_time": "6:04:58", "remaining_time": "1 day, 2:35:54", "throughput": 555.61, "total_tokens": 12166752} {"current_steps": 7450, "total_steps": 40000, "loss": 0.0886, "lr": 4.584220724460665e-05, "epoch": 0.337264311098033, "percentage": 18.62, "elapsed_time": "6:05:01", "remaining_time": "1 day, 2:34:48", "throughput": 555.89, "total_tokens": 12174560} {"current_steps": 7455, "total_steps": 40000, "loss": 0.0953, "lr": 4.5836784080221865e-05, "epoch": 0.337490662984676, "percentage": 18.64, "elapsed_time": "6:05:04", "remaining_time": "1 day, 2:33:44", "throughput": 556.2, "total_tokens": 12183296} {"current_steps": 7460, "total_steps": 40000, "loss": 0.1582, "lr": 4.583135770254312e-05, "epoch": 0.33771701487131894, "percentage": 18.65, "elapsed_time": "6:05:07", "remaining_time": "1 day, 2:32:39", "throughput": 556.51, "total_tokens": 12191904} {"current_steps": 7465, "total_steps": 40000, "loss": 0.2045, "lr": 4.5825928112407236e-05, "epoch": 0.33794336675796194, "percentage": 18.66, "elapsed_time": "6:05:10", "remaining_time": "1 day, 2:31:34", "throughput": 556.78, "total_tokens": 12199456} {"current_steps": 7470, "total_steps": 40000, "loss": 0.0981, "lr": 4.582049531065152e-05, "epoch": 0.3381697186446049, "percentage": 18.68, "elapsed_time": "6:05:13", "remaining_time": "1 day, 2:30:29", "throughput": 557.07, "total_tokens": 12207584} {"current_steps": 7475, "total_steps": 40000, "loss": 0.1472, "lr": 4.5815059298113783e-05, "epoch": 0.3383960705312479, "percentage": 18.69, "elapsed_time": "6:05:17", "remaining_time": "1 day, 2:29:24", "throughput": 557.35, "total_tokens": 12215424} {"current_steps": 7480, "total_steps": 40000, "loss": 0.1442, "lr": 4.580962007563232e-05, "epoch": 0.33862242241789087, "percentage": 18.7, "elapsed_time": "6:05:20", "remaining_time": "1 day, 2:28:20", "throughput": 557.67, "total_tokens": 12224320} {"current_steps": 7485, "total_steps": 40000, "loss": 0.1304, "lr": 4.5804177644045935e-05, "epoch": 0.3388487743045338, "percentage": 18.71, "elapsed_time": "6:05:23", "remaining_time": "1 day, 2:27:15", "throughput": 557.95, "total_tokens": 12232224} {"current_steps": 7490, "total_steps": 40000, "loss": 0.1194, "lr": 4.579873200419391e-05, "epoch": 0.3390751261911768, "percentage": 18.73, "elapsed_time": "6:05:26", "remaining_time": "1 day, 2:26:11", "throughput": 558.23, "total_tokens": 12240064} {"current_steps": 7495, "total_steps": 40000, "loss": 0.1332, "lr": 4.5793283156916046e-05, "epoch": 0.3393014780778198, "percentage": 18.74, "elapsed_time": "6:05:29", "remaining_time": "1 day, 2:25:06", "throughput": 558.5, "total_tokens": 12247808} {"current_steps": 7500, "total_steps": 40000, "loss": 0.1224, "lr": 4.578783110305261e-05, "epoch": 0.33952782996446274, "percentage": 18.75, "elapsed_time": "6:05:32", "remaining_time": "1 day, 2:24:02", "throughput": 558.78, "total_tokens": 12255648} {"current_steps": 7505, "total_steps": 40000, "loss": 0.1359, "lr": 4.578237584344438e-05, "epoch": 0.33975418185110573, "percentage": 18.76, "elapsed_time": "6:05:35", "remaining_time": "1 day, 2:22:57", "throughput": 559.07, "total_tokens": 12263744} {"current_steps": 7510, "total_steps": 40000, "loss": 0.1729, "lr": 4.577691737893263e-05, "epoch": 0.3399805337377487, "percentage": 18.77, "elapsed_time": "6:05:39", "remaining_time": "1 day, 2:21:53", "throughput": 559.34, "total_tokens": 12271360} {"current_steps": 7515, "total_steps": 40000, "loss": 0.1307, "lr": 4.577145571035912e-05, "epoch": 0.34020688562439166, "percentage": 18.79, "elapsed_time": "6:05:42", "remaining_time": "1 day, 2:20:48", "throughput": 559.61, "total_tokens": 12279008} {"current_steps": 7520, "total_steps": 40000, "loss": 0.1444, "lr": 4.576599083856611e-05, "epoch": 0.34043323751103466, "percentage": 18.8, "elapsed_time": "6:05:45", "remaining_time": "1 day, 2:19:45", "throughput": 559.93, "total_tokens": 12287872} {"current_steps": 7525, "total_steps": 40000, "loss": 0.1423, "lr": 4.576052276439635e-05, "epoch": 0.34065958939767765, "percentage": 18.81, "elapsed_time": "6:05:48", "remaining_time": "1 day, 2:18:41", "throughput": 560.2, "total_tokens": 12295584} {"current_steps": 7530, "total_steps": 40000, "loss": 0.1285, "lr": 4.575505148869308e-05, "epoch": 0.3408859412843206, "percentage": 18.82, "elapsed_time": "6:05:51", "remaining_time": "1 day, 2:17:37", "throughput": 560.47, "total_tokens": 12303392} {"current_steps": 7535, "total_steps": 40000, "loss": 0.1541, "lr": 4.574957701230006e-05, "epoch": 0.3411122931709636, "percentage": 18.84, "elapsed_time": "6:05:54", "remaining_time": "1 day, 2:16:34", "throughput": 560.77, "total_tokens": 12311584} {"current_steps": 7540, "total_steps": 40000, "loss": 0.1346, "lr": 4.57440993360615e-05, "epoch": 0.3413386450576066, "percentage": 18.85, "elapsed_time": "6:05:58", "remaining_time": "1 day, 2:15:30", "throughput": 561.04, "total_tokens": 12319392} {"current_steps": 7545, "total_steps": 40000, "loss": 0.1977, "lr": 4.5738618460822134e-05, "epoch": 0.3415649969442495, "percentage": 18.86, "elapsed_time": "6:06:01", "remaining_time": "1 day, 2:14:26", "throughput": 561.31, "total_tokens": 12327104} {"current_steps": 7550, "total_steps": 40000, "loss": 0.2449, "lr": 4.573313438742719e-05, "epoch": 0.3417913488308925, "percentage": 18.88, "elapsed_time": "6:06:04", "remaining_time": "1 day, 2:13:23", "throughput": 561.62, "total_tokens": 12335680} {"current_steps": 7555, "total_steps": 40000, "loss": 0.1271, "lr": 4.5727647116722374e-05, "epoch": 0.34201770071753546, "percentage": 18.89, "elapsed_time": "6:06:07", "remaining_time": "1 day, 2:12:20", "throughput": 561.93, "total_tokens": 12344224} {"current_steps": 7560, "total_steps": 40000, "loss": 0.1474, "lr": 4.5722156649553884e-05, "epoch": 0.34224405260417845, "percentage": 18.9, "elapsed_time": "6:06:10", "remaining_time": "1 day, 2:11:17", "throughput": 562.22, "total_tokens": 12352448} {"current_steps": 7565, "total_steps": 40000, "loss": 0.172, "lr": 4.571666298676843e-05, "epoch": 0.34247040449082145, "percentage": 18.91, "elapsed_time": "6:06:14", "remaining_time": "1 day, 2:10:13", "throughput": 562.5, "total_tokens": 12360448} {"current_steps": 7570, "total_steps": 40000, "loss": 0.0823, "lr": 4.571116612921321e-05, "epoch": 0.3426967563774644, "percentage": 18.93, "elapsed_time": "6:06:17", "remaining_time": "1 day, 2:09:10", "throughput": 562.76, "total_tokens": 12367904} {"current_steps": 7575, "total_steps": 40000, "loss": 0.1916, "lr": 4.57056660777359e-05, "epoch": 0.3429231082641074, "percentage": 18.94, "elapsed_time": "6:06:20", "remaining_time": "1 day, 2:08:07", "throughput": 563.05, "total_tokens": 12376096} {"current_steps": 7580, "total_steps": 40000, "loss": 0.1298, "lr": 4.5700162833184666e-05, "epoch": 0.3431494601507504, "percentage": 18.95, "elapsed_time": "6:06:23", "remaining_time": "1 day, 2:07:04", "throughput": 563.35, "total_tokens": 12384288} {"current_steps": 7585, "total_steps": 40000, "loss": 0.1305, "lr": 4.5694656396408195e-05, "epoch": 0.3433758120373933, "percentage": 18.96, "elapsed_time": "6:06:26", "remaining_time": "1 day, 2:06:00", "throughput": 563.61, "total_tokens": 12391744} {"current_steps": 7590, "total_steps": 40000, "loss": 0.1425, "lr": 4.5689146768255646e-05, "epoch": 0.3436021639240363, "percentage": 18.98, "elapsed_time": "6:06:29", "remaining_time": "1 day, 2:04:58", "throughput": 563.91, "total_tokens": 12400224} {"current_steps": 7595, "total_steps": 40000, "loss": 0.1446, "lr": 4.568363394957667e-05, "epoch": 0.3438285158106793, "percentage": 18.99, "elapsed_time": "6:06:33", "remaining_time": "1 day, 2:03:55", "throughput": 564.2, "total_tokens": 12408544} {"current_steps": 7600, "total_steps": 40000, "loss": 0.1172, "lr": 4.567811794122141e-05, "epoch": 0.34405486769732224, "percentage": 19.0, "elapsed_time": "6:06:36", "remaining_time": "1 day, 2:02:53", "throughput": 564.5, "total_tokens": 12416992} {"current_steps": 7600, "total_steps": 40000, "eval_loss": 0.1460707038640976, "epoch": 0.34405486769732224, "percentage": 19.0, "elapsed_time": "6:14:18", "remaining_time": "1 day, 2:35:45", "throughput": 552.88, "total_tokens": 12416992} {"current_steps": 7605, "total_steps": 40000, "loss": 0.2004, "lr": 4.56725987440405e-05, "epoch": 0.34428121958396524, "percentage": 19.01, "elapsed_time": "6:14:23", "remaining_time": "1 day, 2:34:46", "throughput": 553.14, "total_tokens": 12425152} {"current_steps": 7610, "total_steps": 40000, "loss": 0.1268, "lr": 4.566707635888508e-05, "epoch": 0.34450757147060823, "percentage": 19.02, "elapsed_time": "6:14:26", "remaining_time": "1 day, 2:33:41", "throughput": 553.41, "total_tokens": 12433152} {"current_steps": 7615, "total_steps": 40000, "loss": 0.1295, "lr": 4.566155078660677e-05, "epoch": 0.34473392335725117, "percentage": 19.04, "elapsed_time": "6:14:29", "remaining_time": "1 day, 2:32:38", "throughput": 553.73, "total_tokens": 12442016} {"current_steps": 7620, "total_steps": 40000, "loss": 0.1551, "lr": 4.565602202805768e-05, "epoch": 0.34496027524389417, "percentage": 19.05, "elapsed_time": "6:14:32", "remaining_time": "1 day, 2:31:34", "throughput": 554.03, "total_tokens": 12450528} {"current_steps": 7625, "total_steps": 40000, "loss": 0.1087, "lr": 4.56504900840904e-05, "epoch": 0.34518662713053716, "percentage": 19.06, "elapsed_time": "6:14:35", "remaining_time": "1 day, 2:30:30", "throughput": 554.31, "total_tokens": 12458720} {"current_steps": 7630, "total_steps": 40000, "loss": 0.1366, "lr": 4.564495495555805e-05, "epoch": 0.3454129790171801, "percentage": 19.07, "elapsed_time": "6:14:39", "remaining_time": "1 day, 2:29:26", "throughput": 554.56, "total_tokens": 12466080} {"current_steps": 7635, "total_steps": 40000, "loss": 0.1365, "lr": 4.5639416643314204e-05, "epoch": 0.3456393309038231, "percentage": 19.09, "elapsed_time": "6:14:42", "remaining_time": "1 day, 2:28:23", "throughput": 554.86, "total_tokens": 12474560} {"current_steps": 7640, "total_steps": 40000, "loss": 0.1338, "lr": 4.5633875148212946e-05, "epoch": 0.34586568279046603, "percentage": 19.1, "elapsed_time": "6:14:45", "remaining_time": "1 day, 2:27:19", "throughput": 555.12, "total_tokens": 12482016} {"current_steps": 7645, "total_steps": 40000, "loss": 0.1181, "lr": 4.562833047110883e-05, "epoch": 0.34609203467710903, "percentage": 19.11, "elapsed_time": "6:14:48", "remaining_time": "1 day, 2:26:15", "throughput": 555.39, "total_tokens": 12489952} {"current_steps": 7650, "total_steps": 40000, "loss": 0.104, "lr": 4.5622782612856923e-05, "epoch": 0.346318386563752, "percentage": 19.12, "elapsed_time": "6:14:51", "remaining_time": "1 day, 2:25:11", "throughput": 555.66, "total_tokens": 12497728} {"current_steps": 7655, "total_steps": 40000, "loss": 0.126, "lr": 4.561723157431278e-05, "epoch": 0.34654473845039496, "percentage": 19.14, "elapsed_time": "6:14:54", "remaining_time": "1 day, 2:24:08", "throughput": 555.95, "total_tokens": 12505952} {"current_steps": 7660, "total_steps": 40000, "loss": 0.151, "lr": 4.5611677356332435e-05, "epoch": 0.34677109033703796, "percentage": 19.15, "elapsed_time": "6:14:57", "remaining_time": "1 day, 2:23:04", "throughput": 556.24, "total_tokens": 12514144} {"current_steps": 7665, "total_steps": 40000, "loss": 0.1022, "lr": 4.560611995977242e-05, "epoch": 0.34699744222368095, "percentage": 19.16, "elapsed_time": "6:15:01", "remaining_time": "1 day, 2:22:01", "throughput": 556.52, "total_tokens": 12522304} {"current_steps": 7670, "total_steps": 40000, "loss": 0.1401, "lr": 4.560055938548975e-05, "epoch": 0.3472237941103239, "percentage": 19.18, "elapsed_time": "6:15:04", "remaining_time": "1 day, 2:20:58", "throughput": 556.8, "total_tokens": 12530464} {"current_steps": 7675, "total_steps": 40000, "loss": 0.1849, "lr": 4.5594995634341944e-05, "epoch": 0.3474501459969669, "percentage": 19.19, "elapsed_time": "6:15:07", "remaining_time": "1 day, 2:19:55", "throughput": 557.09, "total_tokens": 12538784} {"current_steps": 7680, "total_steps": 40000, "loss": 0.0789, "lr": 4.5589428707187e-05, "epoch": 0.3476764978836099, "percentage": 19.2, "elapsed_time": "6:15:10", "remaining_time": "1 day, 2:18:52", "throughput": 557.36, "total_tokens": 12546592} {"current_steps": 7685, "total_steps": 40000, "loss": 0.1132, "lr": 4.55838586048834e-05, "epoch": 0.3479028497702528, "percentage": 19.21, "elapsed_time": "6:15:13", "remaining_time": "1 day, 2:17:49", "throughput": 557.65, "total_tokens": 12554784} {"current_steps": 7690, "total_steps": 40000, "loss": 0.2459, "lr": 4.557828532829013e-05, "epoch": 0.3481292016568958, "percentage": 19.23, "elapsed_time": "6:15:17", "remaining_time": "1 day, 2:16:46", "throughput": 557.95, "total_tokens": 12563360} {"current_steps": 7695, "total_steps": 40000, "loss": 0.1283, "lr": 4.557270887826667e-05, "epoch": 0.3483555535435388, "percentage": 19.24, "elapsed_time": "6:15:20", "remaining_time": "1 day, 2:15:43", "throughput": 558.23, "total_tokens": 12571392} {"current_steps": 7700, "total_steps": 40000, "loss": 0.1586, "lr": 4.556712925567296e-05, "epoch": 0.34858190543018175, "percentage": 19.25, "elapsed_time": "6:15:23", "remaining_time": "1 day, 2:14:40", "throughput": 558.51, "total_tokens": 12579424} {"current_steps": 7705, "total_steps": 40000, "loss": 0.1055, "lr": 4.5561546461369454e-05, "epoch": 0.34880825731682474, "percentage": 19.26, "elapsed_time": "6:15:26", "remaining_time": "1 day, 2:13:38", "throughput": 558.8, "total_tokens": 12587808} {"current_steps": 7710, "total_steps": 40000, "loss": 0.126, "lr": 4.55559604962171e-05, "epoch": 0.34903460920346774, "percentage": 19.28, "elapsed_time": "6:15:29", "remaining_time": "1 day, 2:12:35", "throughput": 559.06, "total_tokens": 12595456} {"current_steps": 7715, "total_steps": 40000, "loss": 0.115, "lr": 4.55503713610773e-05, "epoch": 0.3492609610901107, "percentage": 19.29, "elapsed_time": "6:15:32", "remaining_time": "1 day, 2:11:33", "throughput": 559.35, "total_tokens": 12603680} {"current_steps": 7720, "total_steps": 40000, "loss": 0.1338, "lr": 4.5544779056812e-05, "epoch": 0.3494873129767537, "percentage": 19.3, "elapsed_time": "6:15:35", "remaining_time": "1 day, 2:10:30", "throughput": 559.62, "total_tokens": 12611680} {"current_steps": 7725, "total_steps": 40000, "loss": 0.1469, "lr": 4.553918358428358e-05, "epoch": 0.3497136648633966, "percentage": 19.31, "elapsed_time": "6:15:39", "remaining_time": "1 day, 2:09:28", "throughput": 559.92, "total_tokens": 12620064} {"current_steps": 7730, "total_steps": 40000, "loss": 0.1626, "lr": 4.553358494435494e-05, "epoch": 0.3499400167500396, "percentage": 19.32, "elapsed_time": "6:15:42", "remaining_time": "1 day, 2:08:26", "throughput": 560.22, "total_tokens": 12628704} {"current_steps": 7735, "total_steps": 40000, "loss": 0.1559, "lr": 4.5527983137889464e-05, "epoch": 0.3501663686366826, "percentage": 19.34, "elapsed_time": "6:15:45", "remaining_time": "1 day, 2:07:25", "throughput": 560.54, "total_tokens": 12637984} {"current_steps": 7740, "total_steps": 40000, "loss": 0.1495, "lr": 4.5522378165751015e-05, "epoch": 0.35039272052332554, "percentage": 19.35, "elapsed_time": "6:15:49", "remaining_time": "1 day, 2:06:23", "throughput": 560.83, "total_tokens": 12646176} {"current_steps": 7745, "total_steps": 40000, "loss": 0.1478, "lr": 4.5516770028803954e-05, "epoch": 0.35061907240996854, "percentage": 19.36, "elapsed_time": "6:15:52", "remaining_time": "1 day, 2:05:21", "throughput": 561.11, "total_tokens": 12654240} {"current_steps": 7750, "total_steps": 40000, "loss": 0.2021, "lr": 4.5511158727913116e-05, "epoch": 0.35084542429661153, "percentage": 19.38, "elapsed_time": "6:15:55", "remaining_time": "1 day, 2:04:19", "throughput": 561.38, "total_tokens": 12662112} {"current_steps": 7755, "total_steps": 40000, "loss": 0.1422, "lr": 4.5505544263943856e-05, "epoch": 0.35107177618325447, "percentage": 19.39, "elapsed_time": "6:15:58", "remaining_time": "1 day, 2:03:17", "throughput": 561.67, "total_tokens": 12670560} {"current_steps": 7760, "total_steps": 40000, "loss": 0.1362, "lr": 4.549992663776197e-05, "epoch": 0.35129812806989746, "percentage": 19.4, "elapsed_time": "6:16:01", "remaining_time": "1 day, 2:02:15", "throughput": 561.94, "total_tokens": 12678368} {"current_steps": 7765, "total_steps": 40000, "loss": 0.1741, "lr": 4.5494305850233786e-05, "epoch": 0.35152447995654046, "percentage": 19.41, "elapsed_time": "6:16:04", "remaining_time": "1 day, 2:01:13", "throughput": 562.23, "total_tokens": 12686560} {"current_steps": 7770, "total_steps": 40000, "loss": 0.1464, "lr": 4.5488681902226094e-05, "epoch": 0.3517508318431834, "percentage": 19.43, "elapsed_time": "6:16:08", "remaining_time": "1 day, 2:00:12", "throughput": 562.51, "total_tokens": 12694752} {"current_steps": 7775, "total_steps": 40000, "loss": 0.1329, "lr": 4.5483054794606174e-05, "epoch": 0.3519771837298264, "percentage": 19.44, "elapsed_time": "6:16:11", "remaining_time": "1 day, 1:59:10", "throughput": 562.8, "total_tokens": 12703072} {"current_steps": 7780, "total_steps": 40000, "loss": 0.1666, "lr": 4.547742452824179e-05, "epoch": 0.3522035356164694, "percentage": 19.45, "elapsed_time": "6:16:14", "remaining_time": "1 day, 1:58:09", "throughput": 563.05, "total_tokens": 12710496} {"current_steps": 7785, "total_steps": 40000, "loss": 0.1417, "lr": 4.5471791104001215e-05, "epoch": 0.3524298875031123, "percentage": 19.46, "elapsed_time": "6:16:17", "remaining_time": "1 day, 1:57:07", "throughput": 563.32, "total_tokens": 12718400} {"current_steps": 7790, "total_steps": 40000, "loss": 0.1474, "lr": 4.546615452275319e-05, "epoch": 0.3526562393897553, "percentage": 19.48, "elapsed_time": "6:16:20", "remaining_time": "1 day, 1:56:06", "throughput": 563.6, "total_tokens": 12726496} {"current_steps": 7795, "total_steps": 40000, "loss": 0.1485, "lr": 4.5460514785366944e-05, "epoch": 0.3528825912763983, "percentage": 19.49, "elapsed_time": "6:16:23", "remaining_time": "1 day, 1:55:05", "throughput": 563.89, "total_tokens": 12734912} {"current_steps": 7800, "total_steps": 40000, "loss": 0.1068, "lr": 4.545487189271219e-05, "epoch": 0.35310894316304126, "percentage": 19.5, "elapsed_time": "6:16:27", "remaining_time": "1 day, 1:54:04", "throughput": 564.19, "total_tokens": 12743488} {"current_steps": 7800, "total_steps": 40000, "eval_loss": 0.14605003595352173, "epoch": 0.35310894316304126, "percentage": 19.5, "elapsed_time": "6:24:09", "remaining_time": "1 day, 2:25:54", "throughput": 552.87, "total_tokens": 12743488} {"current_steps": 7805, "total_steps": 40000, "loss": 0.1927, "lr": 4.544922584565914e-05, "epoch": 0.35333529504968425, "percentage": 19.51, "elapsed_time": "6:24:14", "remaining_time": "1 day, 2:24:56", "throughput": 553.14, "total_tokens": 12752064} {"current_steps": 7810, "total_steps": 40000, "loss": 0.0771, "lr": 4.544357664507848e-05, "epoch": 0.3535616469363272, "percentage": 19.53, "elapsed_time": "6:24:17", "remaining_time": "1 day, 2:23:53", "throughput": 553.42, "total_tokens": 12760288} {"current_steps": 7815, "total_steps": 40000, "loss": 0.1498, "lr": 4.54379242918414e-05, "epoch": 0.3537879988229702, "percentage": 19.54, "elapsed_time": "6:24:20", "remaining_time": "1 day, 2:22:52", "throughput": 553.72, "total_tokens": 12769216} {"current_steps": 7820, "total_steps": 40000, "loss": 0.1749, "lr": 4.543226878681955e-05, "epoch": 0.3540143507096132, "percentage": 19.55, "elapsed_time": "6:24:23", "remaining_time": "1 day, 2:21:49", "throughput": 553.99, "total_tokens": 12777088} {"current_steps": 7825, "total_steps": 40000, "loss": 0.087, "lr": 4.5426610130885087e-05, "epoch": 0.3542407025962561, "percentage": 19.56, "elapsed_time": "6:24:26", "remaining_time": "1 day, 2:20:47", "throughput": 554.25, "total_tokens": 12784864} {"current_steps": 7830, "total_steps": 40000, "loss": 0.0905, "lr": 4.542094832491064e-05, "epoch": 0.3544670544828991, "percentage": 19.57, "elapsed_time": "6:24:30", "remaining_time": "1 day, 2:19:45", "throughput": 554.57, "total_tokens": 12794016} {"current_steps": 7835, "total_steps": 40000, "loss": 0.1712, "lr": 4.541528336976934e-05, "epoch": 0.3546934063695421, "percentage": 19.59, "elapsed_time": "6:24:33", "remaining_time": "1 day, 2:18:43", "throughput": 554.83, "total_tokens": 12801888} {"current_steps": 7840, "total_steps": 40000, "loss": 0.1198, "lr": 4.540961526633479e-05, "epoch": 0.35491975825618505, "percentage": 19.6, "elapsed_time": "6:24:36", "remaining_time": "1 day, 2:17:41", "throughput": 555.12, "total_tokens": 12810400} {"current_steps": 7845, "total_steps": 40000, "loss": 0.128, "lr": 4.540394401548108e-05, "epoch": 0.35514611014282804, "percentage": 19.61, "elapsed_time": "6:24:39", "remaining_time": "1 day, 2:16:39", "throughput": 555.39, "total_tokens": 12818208} {"current_steps": 7850, "total_steps": 40000, "loss": 0.18, "lr": 4.539826961808279e-05, "epoch": 0.35537246202947104, "percentage": 19.62, "elapsed_time": "6:24:42", "remaining_time": "1 day, 2:15:37", "throughput": 555.65, "total_tokens": 12826080} {"current_steps": 7855, "total_steps": 40000, "loss": 0.1438, "lr": 4.5392592075014994e-05, "epoch": 0.355598813916114, "percentage": 19.64, "elapsed_time": "6:24:46", "remaining_time": "1 day, 2:14:35", "throughput": 555.93, "total_tokens": 12834336} {"current_steps": 7860, "total_steps": 40000, "loss": 0.1137, "lr": 4.538691138715322e-05, "epoch": 0.35582516580275697, "percentage": 19.65, "elapsed_time": "6:24:49", "remaining_time": "1 day, 2:13:33", "throughput": 556.22, "total_tokens": 12842688} {"current_steps": 7865, "total_steps": 40000, "loss": 0.1445, "lr": 4.5381227555373516e-05, "epoch": 0.35605151768939997, "percentage": 19.66, "elapsed_time": "6:24:52", "remaining_time": "1 day, 2:12:31", "throughput": 556.49, "total_tokens": 12850720} {"current_steps": 7870, "total_steps": 40000, "loss": 0.1559, "lr": 4.537554058055239e-05, "epoch": 0.3562778695760429, "percentage": 19.68, "elapsed_time": "6:24:55", "remaining_time": "1 day, 2:11:29", "throughput": 556.75, "total_tokens": 12858592} {"current_steps": 7875, "total_steps": 40000, "loss": 0.1468, "lr": 4.5369850463566865e-05, "epoch": 0.3565042214626859, "percentage": 19.69, "elapsed_time": "6:24:58", "remaining_time": "1 day, 2:10:28", "throughput": 557.01, "total_tokens": 12866304} {"current_steps": 7880, "total_steps": 40000, "loss": 0.1872, "lr": 4.5364157205294404e-05, "epoch": 0.3567305733493289, "percentage": 19.7, "elapsed_time": "6:25:02", "remaining_time": "1 day, 2:09:27", "throughput": 557.3, "total_tokens": 12874720} {"current_steps": 7885, "total_steps": 40000, "loss": 0.1747, "lr": 4.5358460806612996e-05, "epoch": 0.35695692523597183, "percentage": 19.71, "elapsed_time": "6:25:05", "remaining_time": "1 day, 2:08:25", "throughput": 557.56, "total_tokens": 12882400} {"current_steps": 7890, "total_steps": 40000, "loss": 0.1774, "lr": 4.535276126840109e-05, "epoch": 0.35718327712261483, "percentage": 19.73, "elapsed_time": "6:25:08", "remaining_time": "1 day, 2:07:23", "throughput": 557.83, "total_tokens": 12890368} {"current_steps": 7895, "total_steps": 40000, "loss": 0.1319, "lr": 4.5347058591537626e-05, "epoch": 0.35740962900925777, "percentage": 19.74, "elapsed_time": "6:25:11", "remaining_time": "1 day, 2:06:22", "throughput": 558.1, "total_tokens": 12898496} {"current_steps": 7900, "total_steps": 40000, "loss": 0.1487, "lr": 4.534135277690203e-05, "epoch": 0.35763598089590076, "percentage": 19.75, "elapsed_time": "6:25:14", "remaining_time": "1 day, 2:05:20", "throughput": 558.34, "total_tokens": 12905696} {"current_steps": 7905, "total_steps": 40000, "loss": 0.101, "lr": 4.533564382537421e-05, "epoch": 0.35786233278254376, "percentage": 19.76, "elapsed_time": "6:25:17", "remaining_time": "1 day, 2:04:19", "throughput": 558.58, "total_tokens": 12913088} {"current_steps": 7910, "total_steps": 40000, "loss": 0.1792, "lr": 4.532993173783456e-05, "epoch": 0.3580886846691867, "percentage": 19.78, "elapsed_time": "6:25:20", "remaining_time": "1 day, 2:03:18", "throughput": 558.87, "total_tokens": 12921408} {"current_steps": 7915, "total_steps": 40000, "loss": 0.1295, "lr": 4.5324216515163954e-05, "epoch": 0.3583150365558297, "percentage": 19.79, "elapsed_time": "6:25:23", "remaining_time": "1 day, 2:02:17", "throughput": 559.15, "total_tokens": 12929760} {"current_steps": 7920, "total_steps": 40000, "loss": 0.1279, "lr": 4.531849815824375e-05, "epoch": 0.3585413884424727, "percentage": 19.8, "elapsed_time": "6:25:27", "remaining_time": "1 day, 2:01:16", "throughput": 559.4, "total_tokens": 12937184} {"current_steps": 7925, "total_steps": 40000, "loss": 0.1517, "lr": 4.5312776667955795e-05, "epoch": 0.3587677403291156, "percentage": 19.81, "elapsed_time": "6:25:30", "remaining_time": "1 day, 2:00:15", "throughput": 559.67, "total_tokens": 12945184} {"current_steps": 7930, "total_steps": 40000, "loss": 0.1009, "lr": 4.5307052045182405e-05, "epoch": 0.3589940922157586, "percentage": 19.82, "elapsed_time": "6:25:33", "remaining_time": "1 day, 1:59:14", "throughput": 559.94, "total_tokens": 12953248} {"current_steps": 7935, "total_steps": 40000, "loss": 0.123, "lr": 4.53013242908064e-05, "epoch": 0.3592204441024016, "percentage": 19.84, "elapsed_time": "6:25:36", "remaining_time": "1 day, 1:58:13", "throughput": 560.21, "total_tokens": 12961344} {"current_steps": 7940, "total_steps": 40000, "loss": 0.1147, "lr": 4.529559340571107e-05, "epoch": 0.35944679598904455, "percentage": 19.85, "elapsed_time": "6:25:39", "remaining_time": "1 day, 1:57:13", "throughput": 560.5, "total_tokens": 12969952} {"current_steps": 7945, "total_steps": 40000, "loss": 0.1192, "lr": 4.528985939078018e-05, "epoch": 0.35967314787568755, "percentage": 19.86, "elapsed_time": "6:25:42", "remaining_time": "1 day, 1:56:13", "throughput": 560.79, "total_tokens": 12978336} {"current_steps": 7950, "total_steps": 40000, "loss": 0.1842, "lr": 4.5284122246898e-05, "epoch": 0.35989949976233054, "percentage": 19.88, "elapsed_time": "6:25:46", "remaining_time": "1 day, 1:55:12", "throughput": 561.05, "total_tokens": 12986016} {"current_steps": 7955, "total_steps": 40000, "loss": 0.1243, "lr": 4.527838197494926e-05, "epoch": 0.3601258516489735, "percentage": 19.89, "elapsed_time": "6:25:49", "remaining_time": "1 day, 1:54:11", "throughput": 561.32, "total_tokens": 12994048} {"current_steps": 7960, "total_steps": 40000, "loss": 0.1332, "lr": 4.527263857581918e-05, "epoch": 0.3603522035356165, "percentage": 19.9, "elapsed_time": "6:25:52", "remaining_time": "1 day, 1:53:11", "throughput": 561.59, "total_tokens": 13002144} {"current_steps": 7965, "total_steps": 40000, "loss": 0.1479, "lr": 4.526689205039347e-05, "epoch": 0.3605785554222594, "percentage": 19.91, "elapsed_time": "6:25:55", "remaining_time": "1 day, 1:52:10", "throughput": 561.85, "total_tokens": 13009856} {"current_steps": 7970, "total_steps": 40000, "loss": 0.1181, "lr": 4.5261142399558324e-05, "epoch": 0.3608049073089024, "percentage": 19.93, "elapsed_time": "6:25:58", "remaining_time": "1 day, 1:51:11", "throughput": 562.13, "total_tokens": 13018144} {"current_steps": 7975, "total_steps": 40000, "loss": 0.0941, "lr": 4.525538962420041e-05, "epoch": 0.3610312591955454, "percentage": 19.94, "elapsed_time": "6:26:01", "remaining_time": "1 day, 1:50:10", "throughput": 562.38, "total_tokens": 13025696} {"current_steps": 7980, "total_steps": 40000, "loss": 0.1864, "lr": 4.524963372520685e-05, "epoch": 0.36125761108218835, "percentage": 19.95, "elapsed_time": "6:26:04", "remaining_time": "1 day, 1:49:10", "throughput": 562.64, "total_tokens": 13033504} {"current_steps": 7985, "total_steps": 40000, "loss": 0.1397, "lr": 4.524387470346531e-05, "epoch": 0.36148396296883134, "percentage": 19.96, "elapsed_time": "6:26:08", "remaining_time": "1 day, 1:48:10", "throughput": 562.94, "total_tokens": 13042240} {"current_steps": 7990, "total_steps": 40000, "loss": 0.1347, "lr": 4.5238112559863885e-05, "epoch": 0.36171031485547434, "percentage": 19.98, "elapsed_time": "6:26:11", "remaining_time": "1 day, 1:47:11", "throughput": 563.25, "total_tokens": 13051456} {"current_steps": 7995, "total_steps": 40000, "loss": 0.1568, "lr": 4.5232347295291175e-05, "epoch": 0.3619366667421173, "percentage": 19.99, "elapsed_time": "6:26:14", "remaining_time": "1 day, 1:46:11", "throughput": 563.52, "total_tokens": 13059488} {"current_steps": 8000, "total_steps": 40000, "loss": 0.1615, "lr": 4.522657891063626e-05, "epoch": 0.36216301862876027, "percentage": 20.0, "elapsed_time": "6:26:17", "remaining_time": "1 day, 1:45:11", "throughput": 563.8, "total_tokens": 13067648} {"current_steps": 8000, "total_steps": 40000, "eval_loss": 0.14601759612560272, "epoch": 0.36216301862876027, "percentage": 20.0, "elapsed_time": "6:34:00", "remaining_time": "1 day, 2:16:02", "throughput": 552.76, "total_tokens": 13067648} {"current_steps": 8005, "total_steps": 40000, "loss": 0.1304, "lr": 4.52208074067887e-05, "epoch": 0.36238937051540326, "percentage": 20.01, "elapsed_time": "6:34:04", "remaining_time": "1 day, 2:15:04", "throughput": 553.02, "total_tokens": 13075936} {"current_steps": 8010, "total_steps": 40000, "loss": 0.1853, "lr": 4.5215032784638516e-05, "epoch": 0.3626157224020462, "percentage": 20.03, "elapsed_time": "6:34:07", "remaining_time": "1 day, 2:14:03", "throughput": 553.31, "total_tokens": 13084512} {"current_steps": 8015, "total_steps": 40000, "loss": 0.1435, "lr": 4.5209255045076245e-05, "epoch": 0.3628420742886892, "percentage": 20.04, "elapsed_time": "6:34:11", "remaining_time": "1 day, 2:13:02", "throughput": 553.6, "total_tokens": 13093216} {"current_steps": 8020, "total_steps": 40000, "loss": 0.1584, "lr": 4.5203474188992875e-05, "epoch": 0.3630684261753322, "percentage": 20.05, "elapsed_time": "6:34:14", "remaining_time": "1 day, 2:12:01", "throughput": 553.86, "total_tokens": 13101216} {"current_steps": 8025, "total_steps": 40000, "loss": 0.1371, "lr": 4.51976902172799e-05, "epoch": 0.36329477806197513, "percentage": 20.06, "elapsed_time": "6:34:17", "remaining_time": "1 day, 2:11:01", "throughput": 554.14, "total_tokens": 13109664} {"current_steps": 8030, "total_steps": 40000, "loss": 0.1629, "lr": 4.519190313082927e-05, "epoch": 0.3635211299486181, "percentage": 20.08, "elapsed_time": "6:34:20", "remaining_time": "1 day, 2:10:00", "throughput": 554.4, "total_tokens": 13117536} {"current_steps": 8035, "total_steps": 40000, "loss": 0.1587, "lr": 4.518611293053343e-05, "epoch": 0.3637474818352611, "percentage": 20.09, "elapsed_time": "6:34:23", "remaining_time": "1 day, 2:08:59", "throughput": 554.65, "total_tokens": 13125120} {"current_steps": 8040, "total_steps": 40000, "loss": 0.1715, "lr": 4.51803196172853e-05, "epoch": 0.36397383372190406, "percentage": 20.1, "elapsed_time": "6:34:27", "remaining_time": "1 day, 2:07:59", "throughput": 554.95, "total_tokens": 13133952} {"current_steps": 8045, "total_steps": 40000, "loss": 0.1156, "lr": 4.517452319197828e-05, "epoch": 0.36420018560854706, "percentage": 20.11, "elapsed_time": "6:34:30", "remaining_time": "1 day, 2:06:59", "throughput": 555.24, "total_tokens": 13142560} {"current_steps": 8050, "total_steps": 40000, "loss": 0.1497, "lr": 4.5168723655506265e-05, "epoch": 0.36442653749519, "percentage": 20.12, "elapsed_time": "6:34:33", "remaining_time": "1 day, 2:05:58", "throughput": 555.52, "total_tokens": 13151136} {"current_steps": 8055, "total_steps": 40000, "loss": 0.1876, "lr": 4.51629210087636e-05, "epoch": 0.364652889381833, "percentage": 20.14, "elapsed_time": "6:34:36", "remaining_time": "1 day, 2:04:58", "throughput": 555.79, "total_tokens": 13159360} {"current_steps": 8060, "total_steps": 40000, "loss": 0.1261, "lr": 4.515711525264513e-05, "epoch": 0.364879241268476, "percentage": 20.15, "elapsed_time": "6:34:39", "remaining_time": "1 day, 2:03:58", "throughput": 556.08, "total_tokens": 13168032} {"current_steps": 8065, "total_steps": 40000, "loss": 0.1172, "lr": 4.5151306388046175e-05, "epoch": 0.3651055931551189, "percentage": 20.16, "elapsed_time": "6:34:43", "remaining_time": "1 day, 2:02:58", "throughput": 556.36, "total_tokens": 13176384} {"current_steps": 8070, "total_steps": 40000, "loss": 0.175, "lr": 4.514549441586255e-05, "epoch": 0.3653319450417619, "percentage": 20.18, "elapsed_time": "6:34:46", "remaining_time": "1 day, 2:01:58", "throughput": 556.63, "total_tokens": 13184512} {"current_steps": 8075, "total_steps": 40000, "loss": 0.0926, "lr": 4.513967933699051e-05, "epoch": 0.3655582969284049, "percentage": 20.19, "elapsed_time": "6:34:49", "remaining_time": "1 day, 2:00:57", "throughput": 556.87, "total_tokens": 13191904} {"current_steps": 8080, "total_steps": 40000, "loss": 0.0963, "lr": 4.513386115232684e-05, "epoch": 0.36578464881504785, "percentage": 20.2, "elapsed_time": "6:34:52", "remaining_time": "1 day, 1:59:57", "throughput": 557.15, "total_tokens": 13200352} {"current_steps": 8085, "total_steps": 40000, "loss": 0.1205, "lr": 4.5128039862768745e-05, "epoch": 0.36601100070169085, "percentage": 20.21, "elapsed_time": "6:34:55", "remaining_time": "1 day, 1:58:57", "throughput": 557.41, "total_tokens": 13208256} {"current_steps": 8090, "total_steps": 40000, "loss": 0.1115, "lr": 4.512221546921397e-05, "epoch": 0.36623735258833384, "percentage": 20.23, "elapsed_time": "6:34:58", "remaining_time": "1 day, 1:57:57", "throughput": 557.69, "total_tokens": 13216768} {"current_steps": 8095, "total_steps": 40000, "loss": 0.1139, "lr": 4.5116387972560694e-05, "epoch": 0.3664637044749768, "percentage": 20.24, "elapsed_time": "6:35:02", "remaining_time": "1 day, 1:56:57", "throughput": 557.95, "total_tokens": 13224544} {"current_steps": 8100, "total_steps": 40000, "loss": 0.1676, "lr": 4.511055737370759e-05, "epoch": 0.3666900563616198, "percentage": 20.25, "elapsed_time": "6:35:05", "remaining_time": "1 day, 1:55:58", "throughput": 558.23, "total_tokens": 13233056} {"current_steps": 8105, "total_steps": 40000, "loss": 0.1542, "lr": 4.510472367355383e-05, "epoch": 0.36691640824826277, "percentage": 20.26, "elapsed_time": "6:35:08", "remaining_time": "1 day, 1:54:58", "throughput": 558.5, "total_tokens": 13241184} {"current_steps": 8110, "total_steps": 40000, "loss": 0.0949, "lr": 4.509888687299901e-05, "epoch": 0.3671427601349057, "percentage": 20.28, "elapsed_time": "6:35:11", "remaining_time": "1 day, 1:53:59", "throughput": 558.8, "total_tokens": 13250112} {"current_steps": 8115, "total_steps": 40000, "loss": 0.1788, "lr": 4.5093046972943266e-05, "epoch": 0.3673691120215487, "percentage": 20.29, "elapsed_time": "6:35:14", "remaining_time": "1 day, 1:52:59", "throughput": 559.06, "total_tokens": 13258208} {"current_steps": 8120, "total_steps": 40000, "loss": 0.1257, "lr": 4.508720397428717e-05, "epoch": 0.3675954639081917, "percentage": 20.3, "elapsed_time": "6:35:18", "remaining_time": "1 day, 1:51:59", "throughput": 559.32, "total_tokens": 13265984} {"current_steps": 8125, "total_steps": 40000, "loss": 0.1522, "lr": 4.508135787793178e-05, "epoch": 0.36782181579483464, "percentage": 20.31, "elapsed_time": "6:35:21", "remaining_time": "1 day, 1:51:00", "throughput": 559.61, "total_tokens": 13274720} {"current_steps": 8130, "total_steps": 40000, "loss": 0.1325, "lr": 4.5075508684778664e-05, "epoch": 0.36804816768147763, "percentage": 20.32, "elapsed_time": "6:35:24", "remaining_time": "1 day, 1:50:01", "throughput": 559.87, "total_tokens": 13282560} {"current_steps": 8135, "total_steps": 40000, "loss": 0.2131, "lr": 4.506965639572982e-05, "epoch": 0.3682745195681206, "percentage": 20.34, "elapsed_time": "6:35:27", "remaining_time": "1 day, 1:49:02", "throughput": 560.15, "total_tokens": 13291008} {"current_steps": 8140, "total_steps": 40000, "loss": 0.1337, "lr": 4.506380101168774e-05, "epoch": 0.36850087145476357, "percentage": 20.35, "elapsed_time": "6:35:30", "remaining_time": "1 day, 1:48:02", "throughput": 560.4, "total_tokens": 13298688} {"current_steps": 8145, "total_steps": 40000, "loss": 0.112, "lr": 4.505794253355542e-05, "epoch": 0.36872722334140656, "percentage": 20.36, "elapsed_time": "6:35:34", "remaining_time": "1 day, 1:47:03", "throughput": 560.67, "total_tokens": 13307072} {"current_steps": 8150, "total_steps": 40000, "loss": 0.1676, "lr": 4.5052080962236286e-05, "epoch": 0.3689535752280495, "percentage": 20.38, "elapsed_time": "6:35:37", "remaining_time": "1 day, 1:46:05", "throughput": 560.95, "total_tokens": 13315424} {"current_steps": 8155, "total_steps": 40000, "loss": 0.1917, "lr": 4.504621629863428e-05, "epoch": 0.3691799271146925, "percentage": 20.39, "elapsed_time": "6:35:40", "remaining_time": "1 day, 1:45:05", "throughput": 561.21, "total_tokens": 13323360} {"current_steps": 8160, "total_steps": 40000, "loss": 0.1813, "lr": 4.504034854365381e-05, "epoch": 0.3694062790013355, "percentage": 20.4, "elapsed_time": "6:35:43", "remaining_time": "1 day, 1:44:06", "throughput": 561.46, "total_tokens": 13331200} {"current_steps": 8165, "total_steps": 40000, "loss": 0.1277, "lr": 4.503447769819974e-05, "epoch": 0.36963263088797843, "percentage": 20.41, "elapsed_time": "6:35:46", "remaining_time": "1 day, 1:43:07", "throughput": 561.73, "total_tokens": 13339232} {"current_steps": 8170, "total_steps": 40000, "loss": 0.1655, "lr": 4.502860376317745e-05, "epoch": 0.3698589827746214, "percentage": 20.42, "elapsed_time": "6:35:49", "remaining_time": "1 day, 1:42:08", "throughput": 561.97, "total_tokens": 13346816} {"current_steps": 8175, "total_steps": 40000, "loss": 0.1464, "lr": 4.502272673949276e-05, "epoch": 0.3700853346612644, "percentage": 20.44, "elapsed_time": "6:35:52", "remaining_time": "1 day, 1:41:09", "throughput": 562.23, "total_tokens": 13354624} {"current_steps": 8180, "total_steps": 40000, "loss": 0.1267, "lr": 4.501684662805199e-05, "epoch": 0.37031168654790736, "percentage": 20.45, "elapsed_time": "6:35:56", "remaining_time": "1 day, 1:40:10", "throughput": 562.49, "total_tokens": 13362688} {"current_steps": 8185, "total_steps": 40000, "loss": 0.1346, "lr": 4.5010963429761924e-05, "epoch": 0.37053803843455035, "percentage": 20.46, "elapsed_time": "6:35:59", "remaining_time": "1 day, 1:39:11", "throughput": 562.74, "total_tokens": 13370336} {"current_steps": 8190, "total_steps": 40000, "loss": 0.1404, "lr": 4.500507714552982e-05, "epoch": 0.37076439032119335, "percentage": 20.47, "elapsed_time": "6:36:02", "remaining_time": "1 day, 1:38:13", "throughput": 563.01, "total_tokens": 13378464} {"current_steps": 8195, "total_steps": 40000, "loss": 0.1819, "lr": 4.499918777626342e-05, "epoch": 0.3709907422078363, "percentage": 20.49, "elapsed_time": "6:36:05", "remaining_time": "1 day, 1:37:14", "throughput": 563.28, "total_tokens": 13386656} {"current_steps": 8200, "total_steps": 40000, "loss": 0.1746, "lr": 4.499329532287093e-05, "epoch": 0.3712170940944793, "percentage": 20.5, "elapsed_time": "6:36:08", "remaining_time": "1 day, 1:36:16", "throughput": 563.53, "total_tokens": 13394336} {"current_steps": 8200, "total_steps": 40000, "eval_loss": 0.14410221576690674, "epoch": 0.3712170940944793, "percentage": 20.5, "elapsed_time": "6:43:51", "remaining_time": "1 day, 2:06:10", "throughput": 552.77, "total_tokens": 13394336} {"current_steps": 8205, "total_steps": 40000, "loss": 0.1513, "lr": 4.4987399786261064e-05, "epoch": 0.3714434459811223, "percentage": 20.51, "elapsed_time": "6:43:55", "remaining_time": "1 day, 2:05:13", "throughput": 553.0, "total_tokens": 13402080} {"current_steps": 8210, "total_steps": 40000, "loss": 0.1821, "lr": 4.498150116734297e-05, "epoch": 0.3716697978677652, "percentage": 20.52, "elapsed_time": "6:43:58", "remaining_time": "1 day, 2:04:13", "throughput": 553.24, "total_tokens": 13409696} {"current_steps": 8215, "total_steps": 40000, "loss": 0.1829, "lr": 4.4975599467026294e-05, "epoch": 0.3718961497544082, "percentage": 20.54, "elapsed_time": "6:44:01", "remaining_time": "1 day, 2:03:14", "throughput": 553.53, "total_tokens": 13418496} {"current_steps": 8220, "total_steps": 40000, "loss": 0.1319, "lr": 4.496969468622114e-05, "epoch": 0.37212250164105115, "percentage": 20.55, "elapsed_time": "6:44:04", "remaining_time": "1 day, 2:02:14", "throughput": 553.78, "total_tokens": 13426144} {"current_steps": 8225, "total_steps": 40000, "loss": 0.0937, "lr": 4.496378682583813e-05, "epoch": 0.37234885352769415, "percentage": 20.56, "elapsed_time": "6:44:08", "remaining_time": "1 day, 2:01:15", "throughput": 554.08, "total_tokens": 13435360} {"current_steps": 8230, "total_steps": 40000, "loss": 0.1308, "lr": 4.495787588678829e-05, "epoch": 0.37257520541433714, "percentage": 20.57, "elapsed_time": "6:44:11", "remaining_time": "1 day, 2:00:16", "throughput": 554.36, "total_tokens": 13443936} {"current_steps": 8235, "total_steps": 40000, "loss": 0.146, "lr": 4.4951961869983196e-05, "epoch": 0.3728015573009801, "percentage": 20.59, "elapsed_time": "6:44:14", "remaining_time": "1 day, 1:59:17", "throughput": 554.63, "total_tokens": 13452224} {"current_steps": 8240, "total_steps": 40000, "loss": 0.1264, "lr": 4.494604477633485e-05, "epoch": 0.3730279091876231, "percentage": 20.6, "elapsed_time": "6:44:17", "remaining_time": "1 day, 1:58:18", "throughput": 554.89, "total_tokens": 13460320} {"current_steps": 8245, "total_steps": 40000, "loss": 0.1185, "lr": 4.4940124606755734e-05, "epoch": 0.37325426107426607, "percentage": 20.61, "elapsed_time": "6:44:21", "remaining_time": "1 day, 1:57:20", "throughput": 555.16, "total_tokens": 13468800} {"current_steps": 8250, "total_steps": 40000, "loss": 0.1101, "lr": 4.493420136215882e-05, "epoch": 0.373480612960909, "percentage": 20.62, "elapsed_time": "6:44:24", "remaining_time": "1 day, 1:56:20", "throughput": 555.41, "total_tokens": 13476640} {"current_steps": 8255, "total_steps": 40000, "loss": 0.0721, "lr": 4.492827504345756e-05, "epoch": 0.373706964847552, "percentage": 20.64, "elapsed_time": "6:44:27", "remaining_time": "1 day, 1:55:21", "throughput": 555.66, "total_tokens": 13484512} {"current_steps": 8260, "total_steps": 40000, "loss": 0.1471, "lr": 4.492234565156584e-05, "epoch": 0.373933316734195, "percentage": 20.65, "elapsed_time": "6:44:30", "remaining_time": "1 day, 1:54:22", "throughput": 555.92, "total_tokens": 13492480} {"current_steps": 8265, "total_steps": 40000, "loss": 0.0949, "lr": 4.491641318739807e-05, "epoch": 0.37415966862083794, "percentage": 20.66, "elapsed_time": "6:44:33", "remaining_time": "1 day, 1:53:23", "throughput": 556.18, "total_tokens": 13500448} {"current_steps": 8270, "total_steps": 40000, "loss": 0.1174, "lr": 4.4910477651869096e-05, "epoch": 0.37438602050748093, "percentage": 20.67, "elapsed_time": "6:44:36", "remaining_time": "1 day, 1:52:24", "throughput": 556.45, "total_tokens": 13509024} {"current_steps": 8275, "total_steps": 40000, "loss": 0.0888, "lr": 4.4904539045894254e-05, "epoch": 0.3746123723941239, "percentage": 20.69, "elapsed_time": "6:44:40", "remaining_time": "1 day, 1:51:26", "throughput": 556.72, "total_tokens": 13517184} {"current_steps": 8280, "total_steps": 40000, "loss": 0.1366, "lr": 4.4898597370389364e-05, "epoch": 0.37483872428076687, "percentage": 20.7, "elapsed_time": "6:44:43", "remaining_time": "1 day, 1:50:27", "throughput": 557.0, "total_tokens": 13525696} {"current_steps": 8285, "total_steps": 40000, "loss": 0.1272, "lr": 4.489265262627069e-05, "epoch": 0.37506507616740986, "percentage": 20.71, "elapsed_time": "6:44:46", "remaining_time": "1 day, 1:49:28", "throughput": 557.24, "total_tokens": 13533344} {"current_steps": 8290, "total_steps": 40000, "loss": 0.1915, "lr": 4.488670481445499e-05, "epoch": 0.37529142805405286, "percentage": 20.72, "elapsed_time": "6:44:49", "remaining_time": "1 day, 1:48:30", "throughput": 557.54, "total_tokens": 13542560} {"current_steps": 8295, "total_steps": 40000, "loss": 0.1689, "lr": 4.488075393585951e-05, "epoch": 0.3755177799406958, "percentage": 20.74, "elapsed_time": "6:44:52", "remaining_time": "1 day, 1:47:32", "throughput": 557.81, "total_tokens": 13550816} {"current_steps": 8300, "total_steps": 40000, "loss": 0.1465, "lr": 4.487479999140193e-05, "epoch": 0.3757441318273388, "percentage": 20.75, "elapsed_time": "6:44:56", "remaining_time": "1 day, 1:46:33", "throughput": 558.06, "total_tokens": 13558624} {"current_steps": 8305, "total_steps": 40000, "loss": 0.1261, "lr": 4.4868842982000425e-05, "epoch": 0.37597048371398173, "percentage": 20.76, "elapsed_time": "6:44:59", "remaining_time": "1 day, 1:45:35", "throughput": 558.33, "total_tokens": 13566912} {"current_steps": 8310, "total_steps": 40000, "loss": 0.1898, "lr": 4.486288290857365e-05, "epoch": 0.3761968356006247, "percentage": 20.77, "elapsed_time": "6:45:02", "remaining_time": "1 day, 1:44:36", "throughput": 558.57, "total_tokens": 13574656} {"current_steps": 8315, "total_steps": 40000, "loss": 0.0981, "lr": 4.4856919772040715e-05, "epoch": 0.3764231874872677, "percentage": 20.79, "elapsed_time": "6:45:05", "remaining_time": "1 day, 1:43:38", "throughput": 558.83, "total_tokens": 13582592} {"current_steps": 8320, "total_steps": 40000, "loss": 0.1512, "lr": 4.485095357332122e-05, "epoch": 0.37664953937391066, "percentage": 20.8, "elapsed_time": "6:45:08", "remaining_time": "1 day, 1:42:39", "throughput": 559.1, "total_tokens": 13590880} {"current_steps": 8325, "total_steps": 40000, "loss": 0.1282, "lr": 4.484498431333521e-05, "epoch": 0.37687589126055365, "percentage": 20.81, "elapsed_time": "6:45:11", "remaining_time": "1 day, 1:41:41", "throughput": 559.35, "total_tokens": 13598912} {"current_steps": 8330, "total_steps": 40000, "loss": 0.1429, "lr": 4.4839011993003245e-05, "epoch": 0.37710224314719665, "percentage": 20.82, "elapsed_time": "6:45:14", "remaining_time": "1 day, 1:40:43", "throughput": 559.61, "total_tokens": 13606848} {"current_steps": 8335, "total_steps": 40000, "loss": 0.1614, "lr": 4.4833036613246305e-05, "epoch": 0.3773285950338396, "percentage": 20.84, "elapsed_time": "6:45:18", "remaining_time": "1 day, 1:39:45", "throughput": 559.88, "total_tokens": 13615168} {"current_steps": 8340, "total_steps": 40000, "loss": 0.1159, "lr": 4.482705817498589e-05, "epoch": 0.3775549469204826, "percentage": 20.85, "elapsed_time": "6:45:21", "remaining_time": "1 day, 1:38:47", "throughput": 560.13, "total_tokens": 13623040} {"current_steps": 8345, "total_steps": 40000, "loss": 0.1455, "lr": 4.4821076679143934e-05, "epoch": 0.3777812988071256, "percentage": 20.86, "elapsed_time": "6:45:24", "remaining_time": "1 day, 1:37:49", "throughput": 560.41, "total_tokens": 13631744} {"current_steps": 8350, "total_steps": 40000, "loss": 0.1363, "lr": 4.481509212664288e-05, "epoch": 0.3780076506937685, "percentage": 20.88, "elapsed_time": "6:45:27", "remaining_time": "1 day, 1:36:52", "throughput": 560.67, "total_tokens": 13639776} {"current_steps": 8355, "total_steps": 40000, "loss": 0.142, "lr": 4.480910451840559e-05, "epoch": 0.3782340025804115, "percentage": 20.89, "elapsed_time": "6:45:30", "remaining_time": "1 day, 1:35:54", "throughput": 560.92, "total_tokens": 13647744} {"current_steps": 8360, "total_steps": 40000, "loss": 0.1029, "lr": 4.480311385535546e-05, "epoch": 0.3784603544670545, "percentage": 20.9, "elapsed_time": "6:45:34", "remaining_time": "1 day, 1:34:56", "throughput": 561.18, "total_tokens": 13655680} {"current_steps": 8365, "total_steps": 40000, "loss": 0.1646, "lr": 4.47971201384163e-05, "epoch": 0.37868670635369744, "percentage": 20.91, "elapsed_time": "6:45:37", "remaining_time": "1 day, 1:33:59", "throughput": 561.46, "total_tokens": 13664320} {"current_steps": 8370, "total_steps": 40000, "loss": 0.1004, "lr": 4.4791123368512446e-05, "epoch": 0.37891305824034044, "percentage": 20.93, "elapsed_time": "6:45:40", "remaining_time": "1 day, 1:33:01", "throughput": 561.73, "total_tokens": 13672800} {"current_steps": 8375, "total_steps": 40000, "loss": 0.1461, "lr": 4.478512354656864e-05, "epoch": 0.37913941012698343, "percentage": 20.94, "elapsed_time": "6:45:43", "remaining_time": "1 day, 1:32:04", "throughput": 561.98, "total_tokens": 13680576} {"current_steps": 8380, "total_steps": 40000, "loss": 0.1026, "lr": 4.477912067351016e-05, "epoch": 0.3793657620136264, "percentage": 20.95, "elapsed_time": "6:45:46", "remaining_time": "1 day, 1:31:06", "throughput": 562.24, "total_tokens": 13688800} {"current_steps": 8385, "total_steps": 40000, "loss": 0.1028, "lr": 4.477311475026271e-05, "epoch": 0.37959211390026937, "percentage": 20.96, "elapsed_time": "6:45:49", "remaining_time": "1 day, 1:30:09", "throughput": 562.5, "total_tokens": 13696768} {"current_steps": 8390, "total_steps": 40000, "loss": 0.1646, "lr": 4.476710577775248e-05, "epoch": 0.3798184657869123, "percentage": 20.97, "elapsed_time": "6:45:53", "remaining_time": "1 day, 1:29:12", "throughput": 562.76, "total_tokens": 13704800} {"current_steps": 8395, "total_steps": 40000, "loss": 0.1226, "lr": 4.476109375690612e-05, "epoch": 0.3800448176735553, "percentage": 20.99, "elapsed_time": "6:45:56", "remaining_time": "1 day, 1:28:15", "throughput": 563.03, "total_tokens": 13713216} {"current_steps": 8400, "total_steps": 40000, "loss": 0.1477, "lr": 4.4755078688650784e-05, "epoch": 0.3802711695601983, "percentage": 21.0, "elapsed_time": "6:45:59", "remaining_time": "1 day, 1:27:17", "throughput": 563.28, "total_tokens": 13721024} {"current_steps": 8400, "total_steps": 40000, "eval_loss": 0.1466756910085678, "epoch": 0.3802711695601983, "percentage": 21.0, "elapsed_time": "6:53:42", "remaining_time": "1 day, 1:56:18", "throughput": 552.77, "total_tokens": 13721024} {"current_steps": 8405, "total_steps": 40000, "loss": 0.1507, "lr": 4.474906057391406e-05, "epoch": 0.38049752144684124, "percentage": 21.01, "elapsed_time": "6:53:46", "remaining_time": "1 day, 1:55:22", "throughput": 553.01, "total_tokens": 13728992} {"current_steps": 8410, "total_steps": 40000, "loss": 0.1325, "lr": 4.4743039413624e-05, "epoch": 0.38072387333348423, "percentage": 21.02, "elapsed_time": "6:53:49", "remaining_time": "1 day, 1:54:24", "throughput": 553.27, "total_tokens": 13737120} {"current_steps": 8415, "total_steps": 40000, "loss": 0.1296, "lr": 4.473701520870916e-05, "epoch": 0.3809502252201272, "percentage": 21.04, "elapsed_time": "6:53:52", "remaining_time": "1 day, 1:53:25", "throughput": 553.51, "total_tokens": 13745024} {"current_steps": 8420, "total_steps": 40000, "loss": 0.1114, "lr": 4.4730987960098544e-05, "epoch": 0.38117657710677016, "percentage": 21.05, "elapsed_time": "6:53:55", "remaining_time": "1 day, 1:52:28", "throughput": 553.79, "total_tokens": 13753696} {"current_steps": 8425, "total_steps": 40000, "loss": 0.1574, "lr": 4.4724957668721635e-05, "epoch": 0.38140292899341316, "percentage": 21.06, "elapsed_time": "6:53:58", "remaining_time": "1 day, 1:51:30", "throughput": 554.05, "total_tokens": 13761920} {"current_steps": 8430, "total_steps": 40000, "loss": 0.1482, "lr": 4.471892433550836e-05, "epoch": 0.38162928088005615, "percentage": 21.07, "elapsed_time": "6:54:02", "remaining_time": "1 day, 1:50:32", "throughput": 554.33, "total_tokens": 13770688} {"current_steps": 8435, "total_steps": 40000, "loss": 0.1128, "lr": 4.471288796138916e-05, "epoch": 0.3818556327666991, "percentage": 21.09, "elapsed_time": "6:54:05", "remaining_time": "1 day, 1:49:34", "throughput": 554.59, "total_tokens": 13778912} {"current_steps": 8440, "total_steps": 40000, "loss": 0.1453, "lr": 4.470684854729491e-05, "epoch": 0.3820819846533421, "percentage": 21.1, "elapsed_time": "6:54:08", "remaining_time": "1 day, 1:48:37", "throughput": 554.85, "total_tokens": 13787296} {"current_steps": 8445, "total_steps": 40000, "loss": 0.1424, "lr": 4.4700806094156955e-05, "epoch": 0.3823083365399851, "percentage": 21.11, "elapsed_time": "6:54:11", "remaining_time": "1 day, 1:47:38", "throughput": 555.08, "total_tokens": 13794720} {"current_steps": 8450, "total_steps": 40000, "loss": 0.1783, "lr": 4.469476060290713e-05, "epoch": 0.382534688426628, "percentage": 21.12, "elapsed_time": "6:54:14", "remaining_time": "1 day, 1:46:41", "throughput": 555.36, "total_tokens": 13803264} {"current_steps": 8455, "total_steps": 40000, "loss": 0.1192, "lr": 4.468871207447772e-05, "epoch": 0.382761040313271, "percentage": 21.14, "elapsed_time": "6:54:17", "remaining_time": "1 day, 1:45:43", "throughput": 555.59, "total_tokens": 13810880} {"current_steps": 8460, "total_steps": 40000, "loss": 0.1252, "lr": 4.4682660509801486e-05, "epoch": 0.382987392199914, "percentage": 21.15, "elapsed_time": "6:54:21", "remaining_time": "1 day, 1:44:45", "throughput": 555.88, "total_tokens": 13819744} {"current_steps": 8465, "total_steps": 40000, "loss": 0.1456, "lr": 4.467660590981165e-05, "epoch": 0.38321374408655695, "percentage": 21.16, "elapsed_time": "6:54:24", "remaining_time": "1 day, 1:43:48", "throughput": 556.12, "total_tokens": 13827680} {"current_steps": 8470, "total_steps": 40000, "loss": 0.1497, "lr": 4.467054827544191e-05, "epoch": 0.38344009597319995, "percentage": 21.18, "elapsed_time": "6:54:27", "remaining_time": "1 day, 1:42:50", "throughput": 556.38, "total_tokens": 13835840} {"current_steps": 8475, "total_steps": 40000, "loss": 0.1828, "lr": 4.4664487607626434e-05, "epoch": 0.3836664478598429, "percentage": 21.19, "elapsed_time": "6:54:30", "remaining_time": "1 day, 1:41:53", "throughput": 556.64, "total_tokens": 13844032} {"current_steps": 8480, "total_steps": 40000, "loss": 0.112, "lr": 4.4658423907299845e-05, "epoch": 0.3838927997464859, "percentage": 21.2, "elapsed_time": "6:54:34", "remaining_time": "1 day, 1:40:56", "throughput": 556.92, "total_tokens": 13852832} {"current_steps": 8485, "total_steps": 40000, "loss": 0.0919, "lr": 4.465235717539725e-05, "epoch": 0.3841191516331289, "percentage": 21.21, "elapsed_time": "6:54:37", "remaining_time": "1 day, 1:39:59", "throughput": 557.17, "total_tokens": 13860736} {"current_steps": 8490, "total_steps": 40000, "loss": 0.126, "lr": 4.464628741285421e-05, "epoch": 0.3843455035197718, "percentage": 21.22, "elapsed_time": "6:54:40", "remaining_time": "1 day, 1:39:01", "throughput": 557.43, "total_tokens": 13869024} {"current_steps": 8495, "total_steps": 40000, "loss": 0.1108, "lr": 4.4640214620606754e-05, "epoch": 0.3845718554064148, "percentage": 21.24, "elapsed_time": "6:54:43", "remaining_time": "1 day, 1:38:05", "throughput": 557.72, "total_tokens": 13878304} {"current_steps": 8500, "total_steps": 40000, "loss": 0.0924, "lr": 4.46341387995914e-05, "epoch": 0.3847982072930578, "percentage": 21.25, "elapsed_time": "6:54:47", "remaining_time": "1 day, 1:37:08", "throughput": 557.98, "total_tokens": 13886560} {"current_steps": 8505, "total_steps": 40000, "loss": 0.153, "lr": 4.4628059950745106e-05, "epoch": 0.38502455917970074, "percentage": 21.26, "elapsed_time": "6:54:50", "remaining_time": "1 day, 1:36:11", "throughput": 558.24, "total_tokens": 13894560} {"current_steps": 8510, "total_steps": 40000, "loss": 0.1682, "lr": 4.4621978075005297e-05, "epoch": 0.38525091106634374, "percentage": 21.27, "elapsed_time": "6:54:53", "remaining_time": "1 day, 1:35:14", "throughput": 558.49, "total_tokens": 13902688} {"current_steps": 8515, "total_steps": 40000, "loss": 0.0816, "lr": 4.461589317330989e-05, "epoch": 0.38547726295298673, "percentage": 21.29, "elapsed_time": "6:54:56", "remaining_time": "1 day, 1:34:17", "throughput": 558.75, "total_tokens": 13910848} {"current_steps": 8520, "total_steps": 40000, "loss": 0.0956, "lr": 4.460980524659724e-05, "epoch": 0.38570361483962967, "percentage": 21.3, "elapsed_time": "6:54:59", "remaining_time": "1 day, 1:33:20", "throughput": 559.02, "total_tokens": 13919328} {"current_steps": 8525, "total_steps": 40000, "loss": 0.1633, "lr": 4.46037142958062e-05, "epoch": 0.38592996672627267, "percentage": 21.31, "elapsed_time": "6:55:02", "remaining_time": "1 day, 1:32:23", "throughput": 559.27, "total_tokens": 13927360} {"current_steps": 8530, "total_steps": 40000, "loss": 0.1266, "lr": 4.4597620321876046e-05, "epoch": 0.38615631861291566, "percentage": 21.32, "elapsed_time": "6:55:06", "remaining_time": "1 day, 1:31:26", "throughput": 559.53, "total_tokens": 13935744} {"current_steps": 8535, "total_steps": 40000, "loss": 0.1317, "lr": 4.459152332574656e-05, "epoch": 0.3863826704995586, "percentage": 21.34, "elapsed_time": "6:55:09", "remaining_time": "1 day, 1:30:30", "throughput": 559.79, "total_tokens": 13944096} {"current_steps": 8540, "total_steps": 40000, "loss": 0.1755, "lr": 4.4585423308357985e-05, "epoch": 0.3866090223862016, "percentage": 21.35, "elapsed_time": "6:55:12", "remaining_time": "1 day, 1:29:33", "throughput": 560.06, "total_tokens": 13952384} {"current_steps": 8545, "total_steps": 40000, "loss": 0.0991, "lr": 4.457932027065102e-05, "epoch": 0.3868353742728446, "percentage": 21.36, "elapsed_time": "6:55:15", "remaining_time": "1 day, 1:28:37", "throughput": 560.33, "total_tokens": 13961088} {"current_steps": 8550, "total_steps": 40000, "loss": 0.1223, "lr": 4.45732142135668e-05, "epoch": 0.38706172615948753, "percentage": 21.38, "elapsed_time": "6:55:18", "remaining_time": "1 day, 1:27:40", "throughput": 560.57, "total_tokens": 13968832} {"current_steps": 8555, "total_steps": 40000, "loss": 0.1224, "lr": 4.4567105138046986e-05, "epoch": 0.3872880780461305, "percentage": 21.39, "elapsed_time": "6:55:22", "remaining_time": "1 day, 1:26:44", "throughput": 560.85, "total_tokens": 13977472} {"current_steps": 8560, "total_steps": 40000, "loss": 0.1375, "lr": 4.456099304503365e-05, "epoch": 0.38751442993277346, "percentage": 21.4, "elapsed_time": "6:55:25", "remaining_time": "1 day, 1:25:49", "throughput": 561.14, "total_tokens": 13986720} {"current_steps": 8565, "total_steps": 40000, "loss": 0.1449, "lr": 4.455487793546939e-05, "epoch": 0.38774078181941646, "percentage": 21.41, "elapsed_time": "6:55:28", "remaining_time": "1 day, 1:24:52", "throughput": 561.4, "total_tokens": 13995008} {"current_steps": 8570, "total_steps": 40000, "loss": 0.0909, "lr": 4.454875981029719e-05, "epoch": 0.38796713370605945, "percentage": 21.43, "elapsed_time": "6:55:31", "remaining_time": "1 day, 1:23:56", "throughput": 561.66, "total_tokens": 14003200} {"current_steps": 8575, "total_steps": 40000, "loss": 0.0972, "lr": 4.454263867046057e-05, "epoch": 0.3881934855927024, "percentage": 21.44, "elapsed_time": "6:55:35", "remaining_time": "1 day, 1:23:00", "throughput": 561.91, "total_tokens": 14011232} {"current_steps": 8580, "total_steps": 40000, "loss": 0.111, "lr": 4.4536514516903484e-05, "epoch": 0.3884198374793454, "percentage": 21.45, "elapsed_time": "6:55:38", "remaining_time": "1 day, 1:22:03", "throughput": 562.15, "total_tokens": 14019008} {"current_steps": 8585, "total_steps": 40000, "loss": 0.1437, "lr": 4.453038735057034e-05, "epoch": 0.3886461893659884, "percentage": 21.46, "elapsed_time": "6:55:41", "remaining_time": "1 day, 1:21:07", "throughput": 562.41, "total_tokens": 14027392} {"current_steps": 8590, "total_steps": 40000, "loss": 0.0885, "lr": 4.4524257172406034e-05, "epoch": 0.3888725412526313, "percentage": 21.48, "elapsed_time": "6:55:44", "remaining_time": "1 day, 1:20:11", "throughput": 562.65, "total_tokens": 14035008} {"current_steps": 8595, "total_steps": 40000, "loss": 0.1417, "lr": 4.451812398335592e-05, "epoch": 0.3890988931392743, "percentage": 21.49, "elapsed_time": "6:55:47", "remaining_time": "1 day, 1:19:15", "throughput": 562.9, "total_tokens": 14043200} {"current_steps": 8600, "total_steps": 40000, "loss": 0.0784, "lr": 4.4511987784365805e-05, "epoch": 0.3893252450259173, "percentage": 21.5, "elapsed_time": "6:55:50", "remaining_time": "1 day, 1:18:19", "throughput": 563.16, "total_tokens": 14051424} {"current_steps": 8600, "total_steps": 40000, "eval_loss": 0.14305701851844788, "epoch": 0.3893252450259173, "percentage": 21.5, "elapsed_time": "7:03:33", "remaining_time": "1 day, 1:46:29", "throughput": 552.91, "total_tokens": 14051424} {"current_steps": 8605, "total_steps": 40000, "loss": 0.1329, "lr": 4.450584857638197e-05, "epoch": 0.38955159691256025, "percentage": 21.51, "elapsed_time": "7:03:39", "remaining_time": "1 day, 1:45:43", "throughput": 553.09, "total_tokens": 14059456} {"current_steps": 8610, "total_steps": 40000, "loss": 0.1356, "lr": 4.449970636035116e-05, "epoch": 0.38977794879920324, "percentage": 21.52, "elapsed_time": "7:03:43", "remaining_time": "1 day, 1:44:46", "throughput": 553.33, "total_tokens": 14067392} {"current_steps": 8615, "total_steps": 40000, "loss": 0.1396, "lr": 4.4493561137220574e-05, "epoch": 0.39000430068584624, "percentage": 21.54, "elapsed_time": "7:03:46", "remaining_time": "1 day, 1:43:49", "throughput": 553.57, "total_tokens": 14075296} {"current_steps": 8620, "total_steps": 40000, "loss": 0.134, "lr": 4.44874129079379e-05, "epoch": 0.3902306525724892, "percentage": 21.55, "elapsed_time": "7:03:49", "remaining_time": "1 day, 1:42:52", "throughput": 553.84, "total_tokens": 14083744} {"current_steps": 8625, "total_steps": 40000, "loss": 0.1772, "lr": 4.4481261673451255e-05, "epoch": 0.3904570044591322, "percentage": 21.56, "elapsed_time": "7:03:52", "remaining_time": "1 day, 1:41:56", "throughput": 554.13, "total_tokens": 14093088} {"current_steps": 8630, "total_steps": 40000, "loss": 0.1056, "lr": 4.4475107434709245e-05, "epoch": 0.39068335634577517, "percentage": 21.57, "elapsed_time": "7:03:56", "remaining_time": "1 day, 1:40:59", "throughput": 554.38, "total_tokens": 14101152} {"current_steps": 8635, "total_steps": 40000, "loss": 0.1384, "lr": 4.446895019266093e-05, "epoch": 0.3909097082324181, "percentage": 21.59, "elapsed_time": "7:03:59", "remaining_time": "1 day, 1:40:02", "throughput": 554.61, "total_tokens": 14108800} {"current_steps": 8640, "total_steps": 40000, "loss": 0.1157, "lr": 4.446278994825583e-05, "epoch": 0.3911360601190611, "percentage": 21.6, "elapsed_time": "7:04:02", "remaining_time": "1 day, 1:39:06", "throughput": 554.89, "total_tokens": 14117632} {"current_steps": 8645, "total_steps": 40000, "loss": 0.1799, "lr": 4.445662670244394e-05, "epoch": 0.39136241200570404, "percentage": 21.61, "elapsed_time": "7:04:05", "remaining_time": "1 day, 1:38:09", "throughput": 555.14, "total_tokens": 14125792} {"current_steps": 8650, "total_steps": 40000, "loss": 0.1081, "lr": 4.44504604561757e-05, "epoch": 0.39158876389234704, "percentage": 21.62, "elapsed_time": "7:04:08", "remaining_time": "1 day, 1:37:13", "throughput": 555.39, "total_tokens": 14134144} {"current_steps": 8655, "total_steps": 40000, "loss": 0.1099, "lr": 4.4444291210402035e-05, "epoch": 0.39181511577899003, "percentage": 21.64, "elapsed_time": "7:04:12", "remaining_time": "1 day, 1:36:17", "throughput": 555.65, "total_tokens": 14142368} {"current_steps": 8660, "total_steps": 40000, "loss": 0.1635, "lr": 4.443811896607431e-05, "epoch": 0.39204146766563297, "percentage": 21.65, "elapsed_time": "7:04:15", "remaining_time": "1 day, 1:35:21", "throughput": 555.91, "total_tokens": 14150944} {"current_steps": 8665, "total_steps": 40000, "loss": 0.1234, "lr": 4.443194372414436e-05, "epoch": 0.39226781955227596, "percentage": 21.66, "elapsed_time": "7:04:18", "remaining_time": "1 day, 1:34:25", "throughput": 556.18, "total_tokens": 14159424} {"current_steps": 8670, "total_steps": 40000, "loss": 0.1351, "lr": 4.442576548556449e-05, "epoch": 0.39249417143891896, "percentage": 21.68, "elapsed_time": "7:04:21", "remaining_time": "1 day, 1:33:28", "throughput": 556.43, "total_tokens": 14167552} {"current_steps": 8675, "total_steps": 40000, "loss": 0.0969, "lr": 4.441958425128747e-05, "epoch": 0.3927205233255619, "percentage": 21.69, "elapsed_time": "7:04:24", "remaining_time": "1 day, 1:32:32", "throughput": 556.67, "total_tokens": 14175424} {"current_steps": 8680, "total_steps": 40000, "loss": 0.1842, "lr": 4.4413400022266515e-05, "epoch": 0.3929468752122049, "percentage": 21.7, "elapsed_time": "7:04:28", "remaining_time": "1 day, 1:31:36", "throughput": 556.93, "total_tokens": 14183840} {"current_steps": 8685, "total_steps": 40000, "loss": 0.1655, "lr": 4.4407212799455313e-05, "epoch": 0.3931732270988479, "percentage": 21.71, "elapsed_time": "7:04:31", "remaining_time": "1 day, 1:30:40", "throughput": 557.19, "total_tokens": 14192480} {"current_steps": 8690, "total_steps": 40000, "loss": 0.177, "lr": 4.4401022583808003e-05, "epoch": 0.3933995789854908, "percentage": 21.73, "elapsed_time": "7:04:34", "remaining_time": "1 day, 1:29:44", "throughput": 557.44, "total_tokens": 14200448} {"current_steps": 8695, "total_steps": 40000, "loss": 0.236, "lr": 4.439482937627921e-05, "epoch": 0.3936259308721338, "percentage": 21.74, "elapsed_time": "7:04:37", "remaining_time": "1 day, 1:28:48", "throughput": 557.69, "total_tokens": 14208576} {"current_steps": 8700, "total_steps": 40000, "loss": 0.0919, "lr": 4.4388633177824004e-05, "epoch": 0.3938522827587768, "percentage": 21.75, "elapsed_time": "7:04:40", "remaining_time": "1 day, 1:27:52", "throughput": 557.95, "total_tokens": 14216992} {"current_steps": 8705, "total_steps": 40000, "loss": 0.094, "lr": 4.4382433989397895e-05, "epoch": 0.39407863464541976, "percentage": 21.76, "elapsed_time": "7:04:43", "remaining_time": "1 day, 1:26:56", "throughput": 558.2, "total_tokens": 14225152} {"current_steps": 8710, "total_steps": 40000, "loss": 0.1063, "lr": 4.4376231811956895e-05, "epoch": 0.39430498653206275, "percentage": 21.77, "elapsed_time": "7:04:47", "remaining_time": "1 day, 1:26:00", "throughput": 558.45, "total_tokens": 14233280} {"current_steps": 8715, "total_steps": 40000, "loss": 0.1303, "lr": 4.437002664645745e-05, "epoch": 0.39453133841870575, "percentage": 21.79, "elapsed_time": "7:04:50", "remaining_time": "1 day, 1:25:04", "throughput": 558.68, "total_tokens": 14240960} {"current_steps": 8720, "total_steps": 40000, "loss": 0.0841, "lr": 4.436381849385649e-05, "epoch": 0.3947576903053487, "percentage": 21.8, "elapsed_time": "7:04:53", "remaining_time": "1 day, 1:24:08", "throughput": 558.92, "total_tokens": 14248672} {"current_steps": 8725, "total_steps": 40000, "loss": 0.1558, "lr": 4.435760735511136e-05, "epoch": 0.3949840421919917, "percentage": 21.81, "elapsed_time": "7:04:56", "remaining_time": "1 day, 1:23:13", "throughput": 559.18, "total_tokens": 14257280} {"current_steps": 8730, "total_steps": 40000, "loss": 0.0861, "lr": 4.435139323117992e-05, "epoch": 0.3952103940786346, "percentage": 21.82, "elapsed_time": "7:04:59", "remaining_time": "1 day, 1:22:17", "throughput": 559.43, "total_tokens": 14265440} {"current_steps": 8735, "total_steps": 40000, "loss": 0.1105, "lr": 4.434517612302046e-05, "epoch": 0.3954367459652776, "percentage": 21.84, "elapsed_time": "7:05:02", "remaining_time": "1 day, 1:21:22", "throughput": 559.68, "total_tokens": 14273472} {"current_steps": 8740, "total_steps": 40000, "loss": 0.1468, "lr": 4.433895603159174e-05, "epoch": 0.3956630978519206, "percentage": 21.85, "elapsed_time": "7:05:06", "remaining_time": "1 day, 1:20:26", "throughput": 559.92, "total_tokens": 14281504} {"current_steps": 8745, "total_steps": 40000, "loss": 0.1329, "lr": 4.433273295785296e-05, "epoch": 0.39588944973856355, "percentage": 21.86, "elapsed_time": "7:05:09", "remaining_time": "1 day, 1:19:31", "throughput": 560.15, "total_tokens": 14289056} {"current_steps": 8750, "total_steps": 40000, "loss": 0.1267, "lr": 4.432650690276382e-05, "epoch": 0.39611580162520654, "percentage": 21.88, "elapsed_time": "7:05:12", "remaining_time": "1 day, 1:18:35", "throughput": 560.4, "total_tokens": 14297024} {"current_steps": 8755, "total_steps": 40000, "loss": 0.1683, "lr": 4.4320277867284435e-05, "epoch": 0.39634215351184954, "percentage": 21.89, "elapsed_time": "7:05:15", "remaining_time": "1 day, 1:17:40", "throughput": 560.64, "total_tokens": 14305088} {"current_steps": 8760, "total_steps": 40000, "loss": 0.1669, "lr": 4.431404585237541e-05, "epoch": 0.3965685053984925, "percentage": 21.9, "elapsed_time": "7:05:18", "remaining_time": "1 day, 1:16:44", "throughput": 560.88, "total_tokens": 14313024} {"current_steps": 8765, "total_steps": 40000, "loss": 0.1113, "lr": 4.43078108589978e-05, "epoch": 0.39679485728513547, "percentage": 21.91, "elapsed_time": "7:05:21", "remaining_time": "1 day, 1:15:49", "throughput": 561.12, "total_tokens": 14320832} {"current_steps": 8770, "total_steps": 40000, "loss": 0.1155, "lr": 4.4301572888113116e-05, "epoch": 0.39702120917177847, "percentage": 21.93, "elapsed_time": "7:05:25", "remaining_time": "1 day, 1:14:54", "throughput": 561.39, "total_tokens": 14329408} {"current_steps": 8775, "total_steps": 40000, "loss": 0.143, "lr": 4.4295331940683337e-05, "epoch": 0.3972475610584214, "percentage": 21.94, "elapsed_time": "7:05:28", "remaining_time": "1 day, 1:13:59", "throughput": 561.64, "total_tokens": 14337536} {"current_steps": 8780, "total_steps": 40000, "loss": 0.1666, "lr": 4.428908801767089e-05, "epoch": 0.3974739129450644, "percentage": 21.95, "elapsed_time": "7:05:31", "remaining_time": "1 day, 1:13:04", "throughput": 561.89, "total_tokens": 14345696} {"current_steps": 8785, "total_steps": 40000, "loss": 0.1329, "lr": 4.428284112003868e-05, "epoch": 0.3977002648317074, "percentage": 21.96, "elapsed_time": "7:05:34", "remaining_time": "1 day, 1:12:09", "throughput": 562.12, "total_tokens": 14353536} {"current_steps": 8790, "total_steps": 40000, "loss": 0.1724, "lr": 4.4276591248750033e-05, "epoch": 0.39792661671835033, "percentage": 21.98, "elapsed_time": "7:05:37", "remaining_time": "1 day, 1:11:14", "throughput": 562.37, "total_tokens": 14361600} {"current_steps": 8795, "total_steps": 40000, "loss": 0.1482, "lr": 4.4270338404768774e-05, "epoch": 0.39815296860499333, "percentage": 21.99, "elapsed_time": "7:05:40", "remaining_time": "1 day, 1:10:19", "throughput": 562.6, "total_tokens": 14369312} {"current_steps": 8800, "total_steps": 40000, "loss": 0.1506, "lr": 4.426408258905917e-05, "epoch": 0.3983793204916363, "percentage": 22.0, "elapsed_time": "7:05:43", "remaining_time": "1 day, 1:09:24", "throughput": 562.83, "total_tokens": 14376864} {"current_steps": 8800, "total_steps": 40000, "eval_loss": 0.1423497349023819, "epoch": 0.3983793204916363, "percentage": 22.0, "elapsed_time": "7:13:26", "remaining_time": "1 day, 1:36:44", "throughput": 552.82, "total_tokens": 14376864} {"current_steps": 8805, "total_steps": 40000, "loss": 0.1263, "lr": 4.425782380258594e-05, "epoch": 0.39860567237827926, "percentage": 22.01, "elapsed_time": "7:13:30", "remaining_time": "1 day, 1:35:52", "throughput": 553.03, "total_tokens": 14384544} {"current_steps": 8810, "total_steps": 40000, "loss": 0.135, "lr": 4.425156204631427e-05, "epoch": 0.39883202426492226, "percentage": 22.02, "elapsed_time": "7:13:33", "remaining_time": "1 day, 1:34:56", "throughput": 553.26, "total_tokens": 14392416} {"current_steps": 8815, "total_steps": 40000, "loss": 0.1047, "lr": 4.424529732120981e-05, "epoch": 0.3990583761515652, "percentage": 22.04, "elapsed_time": "7:13:36", "remaining_time": "1 day, 1:34:00", "throughput": 553.51, "total_tokens": 14400672} {"current_steps": 8820, "total_steps": 40000, "loss": 0.1687, "lr": 4.423902962823864e-05, "epoch": 0.3992847280382082, "percentage": 22.05, "elapsed_time": "7:13:39", "remaining_time": "1 day, 1:33:04", "throughput": 553.74, "total_tokens": 14408288} {"current_steps": 8825, "total_steps": 40000, "loss": 0.102, "lr": 4.423275896836733e-05, "epoch": 0.3995110799248512, "percentage": 22.06, "elapsed_time": "7:13:43", "remaining_time": "1 day, 1:32:08", "throughput": 553.98, "total_tokens": 14416384} {"current_steps": 8830, "total_steps": 40000, "loss": 0.1462, "lr": 4.42264853425629e-05, "epoch": 0.3997374318114941, "percentage": 22.07, "elapsed_time": "7:13:46", "remaining_time": "1 day, 1:31:13", "throughput": 554.22, "total_tokens": 14424320} {"current_steps": 8835, "total_steps": 40000, "loss": 0.1014, "lr": 4.4220208751792816e-05, "epoch": 0.3999637836981371, "percentage": 22.09, "elapsed_time": "7:13:49", "remaining_time": "1 day, 1:30:17", "throughput": 554.46, "total_tokens": 14432352} {"current_steps": 8840, "total_steps": 40000, "loss": 0.1317, "lr": 4.421392919702499e-05, "epoch": 0.4001901355847801, "percentage": 22.1, "elapsed_time": "7:13:52", "remaining_time": "1 day, 1:29:22", "throughput": 554.7, "total_tokens": 14440256} {"current_steps": 8845, "total_steps": 40000, "loss": 0.1105, "lr": 4.4207646679227846e-05, "epoch": 0.40041648747142305, "percentage": 22.11, "elapsed_time": "7:13:55", "remaining_time": "1 day, 1:28:27", "throughput": 554.97, "total_tokens": 14449248} {"current_steps": 8850, "total_steps": 40000, "loss": 0.1654, "lr": 4.42013611993702e-05, "epoch": 0.40064283935806605, "percentage": 22.12, "elapsed_time": "7:13:59", "remaining_time": "1 day, 1:27:31", "throughput": 555.22, "total_tokens": 14457472} {"current_steps": 8855, "total_steps": 40000, "loss": 0.1437, "lr": 4.419507275842135e-05, "epoch": 0.40086919124470904, "percentage": 22.14, "elapsed_time": "7:14:02", "remaining_time": "1 day, 1:26:36", "throughput": 555.46, "total_tokens": 14465376} {"current_steps": 8860, "total_steps": 40000, "loss": 0.1388, "lr": 4.418878135735106e-05, "epoch": 0.401095543131352, "percentage": 22.15, "elapsed_time": "7:14:05", "remaining_time": "1 day, 1:25:41", "throughput": 555.71, "total_tokens": 14473664} {"current_steps": 8865, "total_steps": 40000, "loss": 0.1342, "lr": 4.418248699712955e-05, "epoch": 0.401321895017995, "percentage": 22.16, "elapsed_time": "7:14:08", "remaining_time": "1 day, 1:24:46", "throughput": 555.96, "total_tokens": 14481920} {"current_steps": 8870, "total_steps": 40000, "loss": 0.1409, "lr": 4.417618967872748e-05, "epoch": 0.401548246904638, "percentage": 22.18, "elapsed_time": "7:14:11", "remaining_time": "1 day, 1:23:51", "throughput": 556.21, "total_tokens": 14490208} {"current_steps": 8875, "total_steps": 40000, "loss": 0.1684, "lr": 4.4169889403115985e-05, "epoch": 0.4017745987912809, "percentage": 22.19, "elapsed_time": "7:14:14", "remaining_time": "1 day, 1:22:55", "throughput": 556.44, "total_tokens": 14497952} {"current_steps": 8880, "total_steps": 40000, "loss": 0.1351, "lr": 4.4163586171266627e-05, "epoch": 0.4020009506779239, "percentage": 22.2, "elapsed_time": "7:14:18", "remaining_time": "1 day, 1:22:01", "throughput": 556.68, "total_tokens": 14506112} {"current_steps": 8885, "total_steps": 40000, "loss": 0.0843, "lr": 4.415727998415147e-05, "epoch": 0.4022273025645669, "percentage": 22.21, "elapsed_time": "7:14:21", "remaining_time": "1 day, 1:21:06", "throughput": 556.92, "total_tokens": 14514176} {"current_steps": 8890, "total_steps": 40000, "loss": 0.1387, "lr": 4.4150970842742985e-05, "epoch": 0.40245365445120984, "percentage": 22.23, "elapsed_time": "7:14:24", "remaining_time": "1 day, 1:20:11", "throughput": 557.15, "total_tokens": 14521984} {"current_steps": 8895, "total_steps": 40000, "loss": 0.15, "lr": 4.4144658748014134e-05, "epoch": 0.40268000633785284, "percentage": 22.24, "elapsed_time": "7:14:27", "remaining_time": "1 day, 1:19:17", "throughput": 557.4, "total_tokens": 14530272} {"current_steps": 8900, "total_steps": 40000, "loss": 0.1474, "lr": 4.413834370093831e-05, "epoch": 0.4029063582244958, "percentage": 22.25, "elapsed_time": "7:14:31", "remaining_time": "1 day, 1:18:22", "throughput": 557.65, "total_tokens": 14538528} {"current_steps": 8905, "total_steps": 40000, "loss": 0.1107, "lr": 4.413202570248939e-05, "epoch": 0.40313271011113877, "percentage": 22.26, "elapsed_time": "7:14:34", "remaining_time": "1 day, 1:17:27", "throughput": 557.88, "total_tokens": 14546240} {"current_steps": 8910, "total_steps": 40000, "loss": 0.133, "lr": 4.412570475364167e-05, "epoch": 0.40335906199778176, "percentage": 22.27, "elapsed_time": "7:14:37", "remaining_time": "1 day, 1:16:33", "throughput": 558.14, "total_tokens": 14554848} {"current_steps": 8915, "total_steps": 40000, "loss": 0.1411, "lr": 4.411938085536994e-05, "epoch": 0.4035854138844247, "percentage": 22.29, "elapsed_time": "7:14:40", "remaining_time": "1 day, 1:15:38", "throughput": 558.42, "total_tokens": 14564096} {"current_steps": 8920, "total_steps": 40000, "loss": 0.1675, "lr": 4.41130540086494e-05, "epoch": 0.4038117657710677, "percentage": 22.3, "elapsed_time": "7:14:43", "remaining_time": "1 day, 1:14:44", "throughput": 558.67, "total_tokens": 14572256} {"current_steps": 8925, "total_steps": 40000, "loss": 0.1392, "lr": 4.4106724214455754e-05, "epoch": 0.4040381176577107, "percentage": 22.31, "elapsed_time": "7:14:47", "remaining_time": "1 day, 1:13:49", "throughput": 558.91, "total_tokens": 14580288} {"current_steps": 8930, "total_steps": 40000, "loss": 0.1232, "lr": 4.4100391473765115e-05, "epoch": 0.40426446954435363, "percentage": 22.32, "elapsed_time": "7:14:50", "remaining_time": "1 day, 1:12:55", "throughput": 559.14, "total_tokens": 14588096} {"current_steps": 8935, "total_steps": 40000, "loss": 0.1202, "lr": 4.409405578755408e-05, "epoch": 0.4044908214309966, "percentage": 22.34, "elapsed_time": "7:14:53", "remaining_time": "1 day, 1:12:00", "throughput": 559.38, "total_tokens": 14596224} {"current_steps": 8940, "total_steps": 40000, "loss": 0.1209, "lr": 4.4087717156799705e-05, "epoch": 0.4047171733176396, "percentage": 22.35, "elapsed_time": "7:14:56", "remaining_time": "1 day, 1:11:06", "throughput": 559.64, "total_tokens": 14604576} {"current_steps": 8945, "total_steps": 40000, "loss": 0.1359, "lr": 4.408137558247946e-05, "epoch": 0.40494352520428256, "percentage": 22.36, "elapsed_time": "7:14:59", "remaining_time": "1 day, 1:10:12", "throughput": 559.86, "total_tokens": 14612032} {"current_steps": 8950, "total_steps": 40000, "loss": 0.1317, "lr": 4.4075031065571306e-05, "epoch": 0.40516987709092556, "percentage": 22.38, "elapsed_time": "7:15:02", "remaining_time": "1 day, 1:09:17", "throughput": 560.11, "total_tokens": 14620576} {"current_steps": 8955, "total_steps": 40000, "loss": 0.1455, "lr": 4.406868360705366e-05, "epoch": 0.40539622897756855, "percentage": 22.39, "elapsed_time": "7:15:06", "remaining_time": "1 day, 1:08:24", "throughput": 560.37, "total_tokens": 14629088} {"current_steps": 8960, "total_steps": 40000, "loss": 0.1137, "lr": 4.406233320790536e-05, "epoch": 0.4056225808642115, "percentage": 22.4, "elapsed_time": "7:15:09", "remaining_time": "1 day, 1:07:29", "throughput": 560.62, "total_tokens": 14637248} {"current_steps": 8965, "total_steps": 40000, "loss": 0.1006, "lr": 4.4055979869105734e-05, "epoch": 0.4058489327508545, "percentage": 22.41, "elapsed_time": "7:15:12", "remaining_time": "1 day, 1:06:36", "throughput": 560.86, "total_tokens": 14645536} {"current_steps": 8970, "total_steps": 40000, "loss": 0.1312, "lr": 4.404962359163454e-05, "epoch": 0.4060752846374975, "percentage": 22.43, "elapsed_time": "7:15:15", "remaining_time": "1 day, 1:05:42", "throughput": 561.11, "total_tokens": 14653856} {"current_steps": 8975, "total_steps": 40000, "loss": 0.1321, "lr": 4.404326437647199e-05, "epoch": 0.4063016365241404, "percentage": 22.44, "elapsed_time": "7:15:18", "remaining_time": "1 day, 1:04:48", "throughput": 561.35, "total_tokens": 14661792} {"current_steps": 8980, "total_steps": 40000, "loss": 0.1358, "lr": 4.403690222459877e-05, "epoch": 0.4065279884107834, "percentage": 22.45, "elapsed_time": "7:15:21", "remaining_time": "1 day, 1:03:53", "throughput": 561.57, "total_tokens": 14669376} {"current_steps": 8985, "total_steps": 40000, "loss": 0.1354, "lr": 4.4030537136995984e-05, "epoch": 0.40675434029742635, "percentage": 22.46, "elapsed_time": "7:15:25", "remaining_time": "1 day, 1:03:00", "throughput": 561.83, "total_tokens": 14677856} {"current_steps": 8990, "total_steps": 40000, "loss": 0.1618, "lr": 4.402416911464523e-05, "epoch": 0.40698069218406935, "percentage": 22.48, "elapsed_time": "7:15:28", "remaining_time": "1 day, 1:02:07", "throughput": 562.1, "total_tokens": 14686784} {"current_steps": 8995, "total_steps": 40000, "loss": 0.1212, "lr": 4.4017798158528516e-05, "epoch": 0.40720704407071234, "percentage": 22.49, "elapsed_time": "7:15:31", "remaining_time": "1 day, 1:01:13", "throughput": 562.35, "total_tokens": 14695040} {"current_steps": 9000, "total_steps": 40000, "loss": 0.0779, "lr": 4.401142426962834e-05, "epoch": 0.4074333959573553, "percentage": 22.5, "elapsed_time": "7:15:34", "remaining_time": "1 day, 1:00:20", "throughput": 562.59, "total_tokens": 14703264} {"current_steps": 9000, "total_steps": 40000, "eval_loss": 0.14277665317058563, "epoch": 0.4074333959573553, "percentage": 22.5, "elapsed_time": "7:23:17", "remaining_time": "1 day, 1:26:54", "throughput": 552.8, "total_tokens": 14703264} {"current_steps": 9005, "total_steps": 40000, "loss": 0.1532, "lr": 4.400504744892763e-05, "epoch": 0.4076597478439983, "percentage": 22.51, "elapsed_time": "7:23:23", "remaining_time": "1 day, 1:26:07", "throughput": 553.02, "total_tokens": 14711936} {"current_steps": 9010, "total_steps": 40000, "loss": 0.1581, "lr": 4.399866769740975e-05, "epoch": 0.40788609973064127, "percentage": 22.53, "elapsed_time": "7:23:26", "remaining_time": "1 day, 1:25:12", "throughput": 553.25, "total_tokens": 14719904} {"current_steps": 9015, "total_steps": 40000, "loss": 0.1163, "lr": 4.399228501605859e-05, "epoch": 0.4081124516172842, "percentage": 22.54, "elapsed_time": "7:23:29", "remaining_time": "1 day, 1:24:17", "throughput": 553.49, "total_tokens": 14728128} {"current_steps": 9020, "total_steps": 40000, "loss": 0.1363, "lr": 4.398589940585839e-05, "epoch": 0.4083388035039272, "percentage": 22.55, "elapsed_time": "7:23:32", "remaining_time": "1 day, 1:23:23", "throughput": 553.73, "total_tokens": 14736256} {"current_steps": 9025, "total_steps": 40000, "loss": 0.1036, "lr": 4.3979510867793917e-05, "epoch": 0.4085651553905702, "percentage": 22.56, "elapsed_time": "7:23:35", "remaining_time": "1 day, 1:22:28", "throughput": 553.96, "total_tokens": 14744032} {"current_steps": 9030, "total_steps": 40000, "loss": 0.1719, "lr": 4.3973119402850346e-05, "epoch": 0.40879150727721314, "percentage": 22.57, "elapsed_time": "7:23:38", "remaining_time": "1 day, 1:21:34", "throughput": 554.19, "total_tokens": 14751840} {"current_steps": 9035, "total_steps": 40000, "loss": 0.124, "lr": 4.396672501201334e-05, "epoch": 0.40901785916385613, "percentage": 22.59, "elapsed_time": "7:23:42", "remaining_time": "1 day, 1:20:39", "throughput": 554.43, "total_tokens": 14760000} {"current_steps": 9040, "total_steps": 40000, "loss": 0.1188, "lr": 4.396032769626899e-05, "epoch": 0.40924421105049913, "percentage": 22.6, "elapsed_time": "7:23:45", "remaining_time": "1 day, 1:19:45", "throughput": 554.65, "total_tokens": 14767680} {"current_steps": 9045, "total_steps": 40000, "loss": 0.161, "lr": 4.395392745660384e-05, "epoch": 0.40947056293714207, "percentage": 22.61, "elapsed_time": "7:23:48", "remaining_time": "1 day, 1:18:50", "throughput": 554.88, "total_tokens": 14775488} {"current_steps": 9050, "total_steps": 40000, "loss": 0.167, "lr": 4.394752429400488e-05, "epoch": 0.40969691482378506, "percentage": 22.62, "elapsed_time": "7:23:51", "remaining_time": "1 day, 1:17:56", "throughput": 555.1, "total_tokens": 14782976} {"current_steps": 9055, "total_steps": 40000, "loss": 0.1145, "lr": 4.394111820945957e-05, "epoch": 0.40992326671042806, "percentage": 22.64, "elapsed_time": "7:23:54", "remaining_time": "1 day, 1:17:02", "throughput": 555.36, "total_tokens": 14791712} {"current_steps": 9060, "total_steps": 40000, "loss": 0.14, "lr": 4.393470920395579e-05, "epoch": 0.410149618597071, "percentage": 22.65, "elapsed_time": "7:23:57", "remaining_time": "1 day, 1:16:08", "throughput": 555.61, "total_tokens": 14800288} {"current_steps": 9065, "total_steps": 40000, "loss": 0.1819, "lr": 4.392829727848192e-05, "epoch": 0.410375970483714, "percentage": 22.66, "elapsed_time": "7:24:01", "remaining_time": "1 day, 1:15:15", "throughput": 555.86, "total_tokens": 14808768} {"current_steps": 9070, "total_steps": 40000, "loss": 0.0994, "lr": 4.392188243402673e-05, "epoch": 0.41060232237035693, "percentage": 22.68, "elapsed_time": "7:24:04", "remaining_time": "1 day, 1:14:21", "throughput": 556.1, "total_tokens": 14816992} {"current_steps": 9075, "total_steps": 40000, "loss": 0.1226, "lr": 4.391546467157949e-05, "epoch": 0.4108286742569999, "percentage": 22.69, "elapsed_time": "7:24:07", "remaining_time": "1 day, 1:13:27", "throughput": 556.36, "total_tokens": 14825600} {"current_steps": 9080, "total_steps": 40000, "loss": 0.1667, "lr": 4.390904399212988e-05, "epoch": 0.4110550261436429, "percentage": 22.7, "elapsed_time": "7:24:10", "remaining_time": "1 day, 1:12:33", "throughput": 556.6, "total_tokens": 14833952} {"current_steps": 9085, "total_steps": 40000, "loss": 0.1832, "lr": 4.390262039666807e-05, "epoch": 0.41128137803028586, "percentage": 22.71, "elapsed_time": "7:24:13", "remaining_time": "1 day, 1:11:39", "throughput": 556.84, "total_tokens": 14842080} {"current_steps": 9090, "total_steps": 40000, "loss": 0.1758, "lr": 4.389619388618464e-05, "epoch": 0.41150772991692885, "percentage": 22.73, "elapsed_time": "7:24:17", "remaining_time": "1 day, 1:10:45", "throughput": 557.07, "total_tokens": 14849728} {"current_steps": 9095, "total_steps": 40000, "loss": 0.1404, "lr": 4.3889764461670655e-05, "epoch": 0.41173408180357185, "percentage": 22.74, "elapsed_time": "7:24:20", "remaining_time": "1 day, 1:09:52", "throughput": 557.31, "total_tokens": 14857888} {"current_steps": 9100, "total_steps": 40000, "loss": 0.1076, "lr": 4.38833321241176e-05, "epoch": 0.4119604336902148, "percentage": 22.75, "elapsed_time": "7:24:23", "remaining_time": "1 day, 1:08:58", "throughput": 557.51, "total_tokens": 14865152} {"current_steps": 9105, "total_steps": 40000, "loss": 0.1653, "lr": 4.3876896874517434e-05, "epoch": 0.4121867855768578, "percentage": 22.76, "elapsed_time": "7:24:26", "remaining_time": "1 day, 1:08:04", "throughput": 557.75, "total_tokens": 14873248} {"current_steps": 9110, "total_steps": 40000, "loss": 0.1667, "lr": 4.3870458713862554e-05, "epoch": 0.4124131374635008, "percentage": 22.78, "elapsed_time": "7:24:29", "remaining_time": "1 day, 1:07:10", "throughput": 557.99, "total_tokens": 14881344} {"current_steps": 9115, "total_steps": 40000, "loss": 0.1503, "lr": 4.386401764314579e-05, "epoch": 0.4126394893501437, "percentage": 22.79, "elapsed_time": "7:24:32", "remaining_time": "1 day, 1:06:17", "throughput": 558.22, "total_tokens": 14889184} {"current_steps": 9120, "total_steps": 40000, "loss": 0.1623, "lr": 4.385757366336045e-05, "epoch": 0.4128658412367867, "percentage": 22.8, "elapsed_time": "7:24:36", "remaining_time": "1 day, 1:05:24", "throughput": 558.46, "total_tokens": 14897568} {"current_steps": 9125, "total_steps": 40000, "loss": 0.1339, "lr": 4.385112677550027e-05, "epoch": 0.4130921931234297, "percentage": 22.81, "elapsed_time": "7:24:39", "remaining_time": "1 day, 1:04:31", "throughput": 558.72, "total_tokens": 14906240} {"current_steps": 9130, "total_steps": 40000, "loss": 0.1309, "lr": 4.384467698055945e-05, "epoch": 0.41331854501007265, "percentage": 22.82, "elapsed_time": "7:24:42", "remaining_time": "1 day, 1:03:37", "throughput": 558.96, "total_tokens": 14914304} {"current_steps": 9135, "total_steps": 40000, "loss": 0.0936, "lr": 4.383822427953261e-05, "epoch": 0.41354489689671564, "percentage": 22.84, "elapsed_time": "7:24:45", "remaining_time": "1 day, 1:02:44", "throughput": 559.2, "total_tokens": 14922560} {"current_steps": 9140, "total_steps": 40000, "loss": 0.1636, "lr": 4.3831768673414864e-05, "epoch": 0.41377124878335864, "percentage": 22.85, "elapsed_time": "7:24:48", "remaining_time": "1 day, 1:01:51", "throughput": 559.45, "total_tokens": 14931040} {"current_steps": 9145, "total_steps": 40000, "loss": 0.162, "lr": 4.382531016320173e-05, "epoch": 0.4139976006700016, "percentage": 22.86, "elapsed_time": "7:24:51", "remaining_time": "1 day, 1:00:58", "throughput": 559.67, "total_tokens": 14938592} {"current_steps": 9150, "total_steps": 40000, "loss": 0.1284, "lr": 4.3818848749889184e-05, "epoch": 0.41422395255664457, "percentage": 22.88, "elapsed_time": "7:24:55", "remaining_time": "1 day, 1:00:05", "throughput": 559.92, "total_tokens": 14947104} {"current_steps": 9155, "total_steps": 40000, "loss": 0.1693, "lr": 4.381238443447368e-05, "epoch": 0.4144503044432875, "percentage": 22.89, "elapsed_time": "7:24:58", "remaining_time": "1 day, 0:59:12", "throughput": 560.18, "total_tokens": 14956000} {"current_steps": 9160, "total_steps": 40000, "loss": 0.1566, "lr": 4.380591721795208e-05, "epoch": 0.4146766563299305, "percentage": 22.9, "elapsed_time": "7:25:01", "remaining_time": "1 day, 0:58:19", "throughput": 560.41, "total_tokens": 14964000} {"current_steps": 9165, "total_steps": 40000, "loss": 0.0998, "lr": 4.3799447101321723e-05, "epoch": 0.4149030082165735, "percentage": 22.91, "elapsed_time": "7:25:04", "remaining_time": "1 day, 0:57:26", "throughput": 560.67, "total_tokens": 14972544} {"current_steps": 9170, "total_steps": 40000, "loss": 0.1548, "lr": 4.379297408558036e-05, "epoch": 0.41512936010321644, "percentage": 22.93, "elapsed_time": "7:25:08", "remaining_time": "1 day, 0:56:34", "throughput": 560.91, "total_tokens": 14980960} {"current_steps": 9175, "total_steps": 40000, "loss": 0.1262, "lr": 4.378649817172624e-05, "epoch": 0.41535571198985943, "percentage": 22.94, "elapsed_time": "7:25:11", "remaining_time": "1 day, 0:55:41", "throughput": 561.15, "total_tokens": 14988960} {"current_steps": 9180, "total_steps": 40000, "loss": 0.1845, "lr": 4.378001936075801e-05, "epoch": 0.4155820638765024, "percentage": 22.95, "elapsed_time": "7:25:14", "remaining_time": "1 day, 0:54:48", "throughput": 561.37, "total_tokens": 14996768} {"current_steps": 9185, "total_steps": 40000, "loss": 0.1964, "lr": 4.377353765367479e-05, "epoch": 0.41580841576314537, "percentage": 22.96, "elapsed_time": "7:25:17", "remaining_time": "1 day, 0:53:55", "throughput": 561.61, "total_tokens": 15004832} {"current_steps": 9190, "total_steps": 40000, "loss": 0.1361, "lr": 4.376705305147614e-05, "epoch": 0.41603476764978836, "percentage": 22.98, "elapsed_time": "7:25:20", "remaining_time": "1 day, 0:53:03", "throughput": 561.86, "total_tokens": 15013248} {"current_steps": 9195, "total_steps": 40000, "loss": 0.1153, "lr": 4.376056555516206e-05, "epoch": 0.41626111953643136, "percentage": 22.99, "elapsed_time": "7:25:24", "remaining_time": "1 day, 0:52:10", "throughput": 562.1, "total_tokens": 15021696} {"current_steps": 9200, "total_steps": 40000, "loss": 0.165, "lr": 4.375407516573302e-05, "epoch": 0.4164874714230743, "percentage": 23.0, "elapsed_time": "7:25:27", "remaining_time": "1 day, 0:51:18", "throughput": 562.34, "total_tokens": 15029760} {"current_steps": 9200, "total_steps": 40000, "eval_loss": 0.14271527528762817, "epoch": 0.4164874714230743, "percentage": 23.0, "elapsed_time": "7:33:09", "remaining_time": "1 day, 1:17:07", "throughput": 552.77, "total_tokens": 15029760} {"current_steps": 9205, "total_steps": 40000, "loss": 0.1334, "lr": 4.3747581884189913e-05, "epoch": 0.4167138233097173, "percentage": 23.01, "elapsed_time": "7:33:13", "remaining_time": "1 day, 1:16:16", "throughput": 552.99, "total_tokens": 15037984} {"current_steps": 9210, "total_steps": 40000, "loss": 0.1546, "lr": 4.374108571153408e-05, "epoch": 0.4169401751963603, "percentage": 23.03, "elapsed_time": "7:33:17", "remaining_time": "1 day, 1:15:22", "throughput": 553.24, "total_tokens": 15046432} {"current_steps": 9215, "total_steps": 40000, "loss": 0.177, "lr": 4.3734586648767316e-05, "epoch": 0.4171665270830032, "percentage": 23.04, "elapsed_time": "7:33:20", "remaining_time": "1 day, 1:14:29", "throughput": 553.49, "total_tokens": 15055040} {"current_steps": 9220, "total_steps": 40000, "loss": 0.1573, "lr": 4.372808469689186e-05, "epoch": 0.4173928789696462, "percentage": 23.05, "elapsed_time": "7:33:23", "remaining_time": "1 day, 1:13:36", "throughput": 553.72, "total_tokens": 15063296} {"current_steps": 9225, "total_steps": 40000, "loss": 0.1669, "lr": 4.372157985691039e-05, "epoch": 0.4176192308562892, "percentage": 23.06, "elapsed_time": "7:33:26", "remaining_time": "1 day, 1:12:43", "throughput": 553.96, "total_tokens": 15071520} {"current_steps": 9230, "total_steps": 40000, "loss": 0.0705, "lr": 4.371507212982603e-05, "epoch": 0.41784558274293215, "percentage": 23.08, "elapsed_time": "7:33:30", "remaining_time": "1 day, 1:11:50", "throughput": 554.2, "total_tokens": 15079904} {"current_steps": 9235, "total_steps": 40000, "loss": 0.1099, "lr": 4.370856151664236e-05, "epoch": 0.41807193462957515, "percentage": 23.09, "elapsed_time": "7:33:33", "remaining_time": "1 day, 1:10:56", "throughput": 554.44, "total_tokens": 15088128} {"current_steps": 9240, "total_steps": 40000, "loss": 0.1394, "lr": 4.3702048018363404e-05, "epoch": 0.4182982865162181, "percentage": 23.1, "elapsed_time": "7:33:36", "remaining_time": "1 day, 1:10:03", "throughput": 554.68, "total_tokens": 15096512} {"current_steps": 9245, "total_steps": 40000, "loss": 0.1728, "lr": 4.369553163599362e-05, "epoch": 0.4185246384028611, "percentage": 23.11, "elapsed_time": "7:33:39", "remaining_time": "1 day, 1:09:10", "throughput": 554.92, "total_tokens": 15104736} {"current_steps": 9250, "total_steps": 40000, "loss": 0.2099, "lr": 4.3689012370537904e-05, "epoch": 0.4187509902895041, "percentage": 23.12, "elapsed_time": "7:33:43", "remaining_time": "1 day, 1:08:18", "throughput": 555.18, "total_tokens": 15113824} {"current_steps": 9255, "total_steps": 40000, "loss": 0.1258, "lr": 4.368249022300164e-05, "epoch": 0.418977342176147, "percentage": 23.14, "elapsed_time": "7:33:46", "remaining_time": "1 day, 1:07:25", "throughput": 555.43, "total_tokens": 15122464} {"current_steps": 9260, "total_steps": 40000, "loss": 0.198, "lr": 4.367596519439059e-05, "epoch": 0.41920369406279, "percentage": 23.15, "elapsed_time": "7:33:49", "remaining_time": "1 day, 1:06:32", "throughput": 555.66, "total_tokens": 15130368} {"current_steps": 9265, "total_steps": 40000, "loss": 0.1434, "lr": 4.366943728571101e-05, "epoch": 0.419430045949433, "percentage": 23.16, "elapsed_time": "7:33:52", "remaining_time": "1 day, 1:05:40", "throughput": 555.9, "total_tokens": 15138816} {"current_steps": 9270, "total_steps": 40000, "loss": 0.1276, "lr": 4.366290649796959e-05, "epoch": 0.41965639783607595, "percentage": 23.18, "elapsed_time": "7:33:55", "remaining_time": "1 day, 1:04:47", "throughput": 556.14, "total_tokens": 15146976} {"current_steps": 9275, "total_steps": 40000, "loss": 0.189, "lr": 4.3656372832173456e-05, "epoch": 0.41988274972271894, "percentage": 23.19, "elapsed_time": "7:33:59", "remaining_time": "1 day, 1:03:54", "throughput": 556.38, "total_tokens": 15155264} {"current_steps": 9280, "total_steps": 40000, "loss": 0.1704, "lr": 4.364983628933017e-05, "epoch": 0.42010910160936193, "percentage": 23.2, "elapsed_time": "7:34:02", "remaining_time": "1 day, 1:03:02", "throughput": 556.64, "total_tokens": 15164320} {"current_steps": 9285, "total_steps": 40000, "loss": 0.1471, "lr": 4.364329687044777e-05, "epoch": 0.4203354534960049, "percentage": 23.21, "elapsed_time": "7:34:05", "remaining_time": "1 day, 1:02:09", "throughput": 556.88, "total_tokens": 15172512} {"current_steps": 9290, "total_steps": 40000, "loss": 0.1517, "lr": 4.36367545765347e-05, "epoch": 0.42056180538264787, "percentage": 23.23, "elapsed_time": "7:34:08", "remaining_time": "1 day, 1:01:16", "throughput": 557.12, "total_tokens": 15180864} {"current_steps": 9295, "total_steps": 40000, "loss": 0.1207, "lr": 4.363020940859988e-05, "epoch": 0.42078815726929086, "percentage": 23.24, "elapsed_time": "7:34:12", "remaining_time": "1 day, 1:00:24", "throughput": 557.34, "total_tokens": 15188800} {"current_steps": 9300, "total_steps": 40000, "loss": 0.1067, "lr": 4.362366136765263e-05, "epoch": 0.4210145091559338, "percentage": 23.25, "elapsed_time": "7:34:15", "remaining_time": "1 day, 0:59:31", "throughput": 557.56, "total_tokens": 15196480} {"current_steps": 9305, "total_steps": 40000, "loss": 0.1435, "lr": 4.361711045470278e-05, "epoch": 0.4212408610425768, "percentage": 23.26, "elapsed_time": "7:34:18", "remaining_time": "1 day, 0:58:38", "throughput": 557.8, "total_tokens": 15204768} {"current_steps": 9310, "total_steps": 40000, "loss": 0.1534, "lr": 4.3610556670760524e-05, "epoch": 0.4214672129292198, "percentage": 23.28, "elapsed_time": "7:34:21", "remaining_time": "1 day, 0:57:46", "throughput": 558.02, "total_tokens": 15212448} {"current_steps": 9315, "total_steps": 40000, "loss": 0.1315, "lr": 4.360400001683657e-05, "epoch": 0.42169356481586273, "percentage": 23.29, "elapsed_time": "7:34:24", "remaining_time": "1 day, 0:56:53", "throughput": 558.24, "total_tokens": 15220320} {"current_steps": 9320, "total_steps": 40000, "loss": 0.1019, "lr": 4.3597440493942e-05, "epoch": 0.4219199167025057, "percentage": 23.3, "elapsed_time": "7:34:27", "remaining_time": "1 day, 0:56:01", "throughput": 558.48, "total_tokens": 15228544} {"current_steps": 9325, "total_steps": 40000, "loss": 0.1369, "lr": 4.3590878103088405e-05, "epoch": 0.42214626858914867, "percentage": 23.31, "elapsed_time": "7:34:30", "remaining_time": "1 day, 0:55:09", "throughput": 558.71, "total_tokens": 15236640} {"current_steps": 9330, "total_steps": 40000, "loss": 0.1167, "lr": 4.358431284528779e-05, "epoch": 0.42237262047579166, "percentage": 23.33, "elapsed_time": "7:34:34", "remaining_time": "1 day, 0:54:16", "throughput": 558.96, "total_tokens": 15245152} {"current_steps": 9335, "total_steps": 40000, "loss": 0.1329, "lr": 4.357774472155257e-05, "epoch": 0.42259897236243466, "percentage": 23.34, "elapsed_time": "7:34:37", "remaining_time": "1 day, 0:53:25", "throughput": 559.2, "total_tokens": 15253664} {"current_steps": 9340, "total_steps": 40000, "loss": 0.1334, "lr": 4.3571173732895664e-05, "epoch": 0.4228253242490776, "percentage": 23.35, "elapsed_time": "7:34:40", "remaining_time": "1 day, 0:52:33", "throughput": 559.44, "total_tokens": 15261920} {"current_steps": 9345, "total_steps": 40000, "loss": 0.182, "lr": 4.356459988033039e-05, "epoch": 0.4230516761357206, "percentage": 23.36, "elapsed_time": "7:34:43", "remaining_time": "1 day, 0:51:40", "throughput": 559.67, "total_tokens": 15270016} {"current_steps": 9350, "total_steps": 40000, "loss": 0.1934, "lr": 4.355802316487051e-05, "epoch": 0.4232780280223636, "percentage": 23.38, "elapsed_time": "7:34:47", "remaining_time": "1 day, 0:50:48", "throughput": 559.92, "total_tokens": 15278496} {"current_steps": 9355, "total_steps": 40000, "loss": 0.1674, "lr": 4.355144358753025e-05, "epoch": 0.4235043799090065, "percentage": 23.39, "elapsed_time": "7:34:50", "remaining_time": "1 day, 0:49:57", "throughput": 560.17, "total_tokens": 15287264} {"current_steps": 9360, "total_steps": 40000, "loss": 0.1362, "lr": 4.354486114932425e-05, "epoch": 0.4237307317956495, "percentage": 23.4, "elapsed_time": "7:34:53", "remaining_time": "1 day, 0:49:05", "throughput": 560.41, "total_tokens": 15295552} {"current_steps": 9365, "total_steps": 40000, "loss": 0.1192, "lr": 4.353827585126762e-05, "epoch": 0.4239570836822925, "percentage": 23.41, "elapsed_time": "7:34:56", "remaining_time": "1 day, 0:48:14", "throughput": 560.67, "total_tokens": 15304640} {"current_steps": 9370, "total_steps": 40000, "loss": 0.148, "lr": 4.353168769437588e-05, "epoch": 0.42418343556893545, "percentage": 23.43, "elapsed_time": "7:35:00", "remaining_time": "1 day, 0:47:22", "throughput": 560.92, "total_tokens": 15313152} {"current_steps": 9375, "total_steps": 40000, "loss": 0.1247, "lr": 4.3525096679665014e-05, "epoch": 0.42440978745557845, "percentage": 23.44, "elapsed_time": "7:35:03", "remaining_time": "1 day, 0:46:30", "throughput": 561.15, "total_tokens": 15321216} {"current_steps": 9380, "total_steps": 40000, "loss": 0.0863, "lr": 4.351850280815144e-05, "epoch": 0.42463613934222144, "percentage": 23.45, "elapsed_time": "7:35:06", "remaining_time": "1 day, 0:45:39", "throughput": 561.39, "total_tokens": 15329504} {"current_steps": 9385, "total_steps": 40000, "loss": 0.2325, "lr": 4.3511906080852014e-05, "epoch": 0.4248624912288644, "percentage": 23.46, "elapsed_time": "7:35:09", "remaining_time": "1 day, 0:44:47", "throughput": 561.62, "total_tokens": 15337632} {"current_steps": 9390, "total_steps": 40000, "loss": 0.158, "lr": 4.350530649878404e-05, "epoch": 0.4250888431155074, "percentage": 23.47, "elapsed_time": "7:35:12", "remaining_time": "1 day, 0:43:55", "throughput": 561.82, "total_tokens": 15344864} {"current_steps": 9395, "total_steps": 40000, "loss": 0.1176, "lr": 4.3498704062965246e-05, "epoch": 0.42531519500215037, "percentage": 23.49, "elapsed_time": "7:35:16", "remaining_time": "1 day, 0:43:04", "throughput": 562.07, "total_tokens": 15353536} {"current_steps": 9400, "total_steps": 40000, "loss": 0.1242, "lr": 4.3492098774413815e-05, "epoch": 0.4255415468887933, "percentage": 23.5, "elapsed_time": "7:35:19", "remaining_time": "1 day, 0:42:13", "throughput": 562.31, "total_tokens": 15361920} {"current_steps": 9400, "total_steps": 40000, "eval_loss": 0.1405814290046692, "epoch": 0.4255415468887933, "percentage": 23.5, "elapsed_time": "7:43:02", "remaining_time": "1 day, 1:07:19", "throughput": 552.95, "total_tokens": 15361920} {"current_steps": 9405, "total_steps": 40000, "loss": 0.1584, "lr": 4.3485490634148375e-05, "epoch": 0.4257678987754363, "percentage": 23.51, "elapsed_time": "7:43:06", "remaining_time": "1 day, 1:06:29", "throughput": 553.15, "total_tokens": 15369760} {"current_steps": 9410, "total_steps": 40000, "loss": 0.0834, "lr": 4.347887964318797e-05, "epoch": 0.42599425066207924, "percentage": 23.52, "elapsed_time": "7:43:09", "remaining_time": "1 day, 1:05:37", "throughput": 553.38, "total_tokens": 15378016} {"current_steps": 9415, "total_steps": 40000, "loss": 0.1351, "lr": 4.34722658025521e-05, "epoch": 0.42622060254872224, "percentage": 23.54, "elapsed_time": "7:43:12", "remaining_time": "1 day, 1:04:44", "throughput": 553.6, "total_tokens": 15385792} {"current_steps": 9420, "total_steps": 40000, "loss": 0.1435, "lr": 4.346564911326071e-05, "epoch": 0.42644695443536523, "percentage": 23.55, "elapsed_time": "7:43:15", "remaining_time": "1 day, 1:03:52", "throughput": 553.83, "total_tokens": 15394080} {"current_steps": 9425, "total_steps": 40000, "loss": 0.1225, "lr": 4.345902957633418e-05, "epoch": 0.4266733063220082, "percentage": 23.56, "elapsed_time": "7:43:18", "remaining_time": "1 day, 1:02:59", "throughput": 554.05, "total_tokens": 15401984} {"current_steps": 9430, "total_steps": 40000, "loss": 0.1556, "lr": 4.345240719279331e-05, "epoch": 0.42689965820865117, "percentage": 23.57, "elapsed_time": "7:43:21", "remaining_time": "1 day, 1:02:07", "throughput": 554.26, "total_tokens": 15409536} {"current_steps": 9435, "total_steps": 40000, "loss": 0.0864, "lr": 4.3445781963659374e-05, "epoch": 0.42712601009529416, "percentage": 23.59, "elapsed_time": "7:43:24", "remaining_time": "1 day, 1:01:14", "throughput": 554.48, "total_tokens": 15417152} {"current_steps": 9440, "total_steps": 40000, "loss": 0.1739, "lr": 4.3439153889954045e-05, "epoch": 0.4273523619819371, "percentage": 23.6, "elapsed_time": "7:43:27", "remaining_time": "1 day, 1:00:22", "throughput": 554.69, "total_tokens": 15424896} {"current_steps": 9445, "total_steps": 40000, "loss": 0.1333, "lr": 4.343252297269946e-05, "epoch": 0.4275787138685801, "percentage": 23.61, "elapsed_time": "7:43:31", "remaining_time": "1 day, 0:59:30", "throughput": 554.93, "total_tokens": 15433344} {"current_steps": 9450, "total_steps": 40000, "loss": 0.139, "lr": 4.342588921291821e-05, "epoch": 0.4278050657552231, "percentage": 23.62, "elapsed_time": "7:43:34", "remaining_time": "1 day, 0:58:38", "throughput": 555.14, "total_tokens": 15440864} {"current_steps": 9455, "total_steps": 40000, "loss": 0.1658, "lr": 4.341925261163328e-05, "epoch": 0.42803141764186603, "percentage": 23.64, "elapsed_time": "7:43:37", "remaining_time": "1 day, 0:57:45", "throughput": 555.36, "total_tokens": 15448544} {"current_steps": 9460, "total_steps": 40000, "loss": 0.1137, "lr": 4.341261316986813e-05, "epoch": 0.428257769528509, "percentage": 23.65, "elapsed_time": "7:43:40", "remaining_time": "1 day, 0:56:53", "throughput": 555.59, "total_tokens": 15456832} {"current_steps": 9465, "total_steps": 40000, "loss": 0.141, "lr": 4.340597088864664e-05, "epoch": 0.428484121415152, "percentage": 23.66, "elapsed_time": "7:43:43", "remaining_time": "1 day, 0:56:02", "throughput": 555.82, "total_tokens": 15465088} {"current_steps": 9470, "total_steps": 40000, "loss": 0.0966, "lr": 4.339932576899313e-05, "epoch": 0.42871047330179496, "percentage": 23.67, "elapsed_time": "7:43:46", "remaining_time": "1 day, 0:55:10", "throughput": 556.05, "total_tokens": 15473056} {"current_steps": 9475, "total_steps": 40000, "loss": 0.1339, "lr": 4.3392677811932375e-05, "epoch": 0.42893682518843795, "percentage": 23.69, "elapsed_time": "7:43:50", "remaining_time": "1 day, 0:54:18", "throughput": 556.28, "total_tokens": 15481216} {"current_steps": 9480, "total_steps": 40000, "loss": 0.157, "lr": 4.338602701848956e-05, "epoch": 0.42916317707508095, "percentage": 23.7, "elapsed_time": "7:43:53", "remaining_time": "1 day, 0:53:27", "throughput": 556.51, "total_tokens": 15489696} {"current_steps": 9485, "total_steps": 40000, "loss": 0.1355, "lr": 4.337937338969033e-05, "epoch": 0.4293895289617239, "percentage": 23.71, "elapsed_time": "7:43:56", "remaining_time": "1 day, 0:52:35", "throughput": 556.74, "total_tokens": 15497824} {"current_steps": 9490, "total_steps": 40000, "loss": 0.1749, "lr": 4.337271692656075e-05, "epoch": 0.4296158808483669, "percentage": 23.72, "elapsed_time": "7:43:59", "remaining_time": "1 day, 0:51:43", "throughput": 556.96, "total_tokens": 15505664} {"current_steps": 9495, "total_steps": 40000, "loss": 0.117, "lr": 4.336605763012733e-05, "epoch": 0.4298422327350098, "percentage": 23.74, "elapsed_time": "7:44:02", "remaining_time": "1 day, 0:50:51", "throughput": 557.18, "total_tokens": 15513472} {"current_steps": 9500, "total_steps": 40000, "loss": 0.1335, "lr": 4.3359395501417026e-05, "epoch": 0.4300685846216528, "percentage": 23.75, "elapsed_time": "7:44:06", "remaining_time": "1 day, 0:50:00", "throughput": 557.42, "total_tokens": 15521856} {"current_steps": 9505, "total_steps": 40000, "loss": 0.099, "lr": 4.335273054145722e-05, "epoch": 0.4302949365082958, "percentage": 23.76, "elapsed_time": "7:44:09", "remaining_time": "1 day, 0:49:08", "throughput": 557.63, "total_tokens": 15529568} {"current_steps": 9510, "total_steps": 40000, "loss": 0.1249, "lr": 4.334606275127572e-05, "epoch": 0.43052128839493875, "percentage": 23.77, "elapsed_time": "7:44:12", "remaining_time": "1 day, 0:48:17", "throughput": 557.84, "total_tokens": 15537248} {"current_steps": 9515, "total_steps": 40000, "loss": 0.1687, "lr": 4.33393921319008e-05, "epoch": 0.43074764028158175, "percentage": 23.79, "elapsed_time": "7:44:15", "remaining_time": "1 day, 0:47:26", "throughput": 558.05, "total_tokens": 15544960} {"current_steps": 9520, "total_steps": 40000, "loss": 0.195, "lr": 4.3332718684361146e-05, "epoch": 0.43097399216822474, "percentage": 23.8, "elapsed_time": "7:44:18", "remaining_time": "1 day, 0:46:34", "throughput": 558.27, "total_tokens": 15552672} {"current_steps": 9525, "total_steps": 40000, "loss": 0.0985, "lr": 4.332604240968588e-05, "epoch": 0.4312003440548677, "percentage": 23.81, "elapsed_time": "7:44:21", "remaining_time": "1 day, 0:45:43", "throughput": 558.5, "total_tokens": 15560928} {"current_steps": 9530, "total_steps": 40000, "loss": 0.1444, "lr": 4.331936330890459e-05, "epoch": 0.4314266959415107, "percentage": 23.82, "elapsed_time": "7:44:25", "remaining_time": "1 day, 0:44:52", "throughput": 558.75, "total_tokens": 15569600} {"current_steps": 9535, "total_steps": 40000, "loss": 0.1768, "lr": 4.331268138304725e-05, "epoch": 0.43165304782815367, "percentage": 23.84, "elapsed_time": "7:44:28", "remaining_time": "1 day, 0:44:02", "throughput": 559.0, "total_tokens": 15578688} {"current_steps": 9540, "total_steps": 40000, "loss": 0.1569, "lr": 4.330599663314431e-05, "epoch": 0.4318793997147966, "percentage": 23.85, "elapsed_time": "7:44:31", "remaining_time": "1 day, 0:43:11", "throughput": 559.23, "total_tokens": 15586752} {"current_steps": 9545, "total_steps": 40000, "loss": 0.1352, "lr": 4.329930906022665e-05, "epoch": 0.4321057516014396, "percentage": 23.86, "elapsed_time": "7:44:35", "remaining_time": "1 day, 0:42:20", "throughput": 559.45, "total_tokens": 15594688} {"current_steps": 9550, "total_steps": 40000, "loss": 0.1461, "lr": 4.3292618665325564e-05, "epoch": 0.4323321034880826, "percentage": 23.88, "elapsed_time": "7:44:38", "remaining_time": "1 day, 0:41:28", "throughput": 559.65, "total_tokens": 15602048} {"current_steps": 9555, "total_steps": 40000, "loss": 0.1374, "lr": 4.3285925449472796e-05, "epoch": 0.43255845537472554, "percentage": 23.89, "elapsed_time": "7:44:41", "remaining_time": "1 day, 0:40:37", "throughput": 559.87, "total_tokens": 15609792} {"current_steps": 9560, "total_steps": 40000, "loss": 0.1122, "lr": 4.327922941370054e-05, "epoch": 0.43278480726136853, "percentage": 23.9, "elapsed_time": "7:44:44", "remaining_time": "1 day, 0:39:46", "throughput": 560.1, "total_tokens": 15618016} {"current_steps": 9565, "total_steps": 40000, "loss": 0.0937, "lr": 4.3272530559041384e-05, "epoch": 0.4330111591480115, "percentage": 23.91, "elapsed_time": "7:44:47", "remaining_time": "1 day, 0:38:55", "throughput": 560.32, "total_tokens": 15625824} {"current_steps": 9570, "total_steps": 40000, "loss": 0.1549, "lr": 4.32658288865284e-05, "epoch": 0.43323751103465447, "percentage": 23.93, "elapsed_time": "7:44:50", "remaining_time": "1 day, 0:38:04", "throughput": 560.54, "total_tokens": 15633696} {"current_steps": 9575, "total_steps": 40000, "loss": 0.148, "lr": 4.325912439719505e-05, "epoch": 0.43346386292129746, "percentage": 23.94, "elapsed_time": "7:44:53", "remaining_time": "1 day, 0:37:13", "throughput": 560.76, "total_tokens": 15641728} {"current_steps": 9580, "total_steps": 40000, "loss": 0.1112, "lr": 4.3252417092075266e-05, "epoch": 0.4336902148079404, "percentage": 23.95, "elapsed_time": "7:44:56", "remaining_time": "1 day, 0:36:22", "throughput": 560.98, "total_tokens": 15649696} {"current_steps": 9585, "total_steps": 40000, "loss": 0.1235, "lr": 4.3245706972203385e-05, "epoch": 0.4339165666945834, "percentage": 23.96, "elapsed_time": "7:44:59", "remaining_time": "1 day, 0:35:31", "throughput": 561.2, "total_tokens": 15657472} {"current_steps": 9590, "total_steps": 40000, "loss": 0.1589, "lr": 4.323899403861421e-05, "epoch": 0.4341429185812264, "percentage": 23.97, "elapsed_time": "7:45:03", "remaining_time": "1 day, 0:34:41", "throughput": 561.44, "total_tokens": 15665888} {"current_steps": 9595, "total_steps": 40000, "loss": 0.1699, "lr": 4.3232278292342935e-05, "epoch": 0.43436927046786933, "percentage": 23.99, "elapsed_time": "7:45:06", "remaining_time": "1 day, 0:33:50", "throughput": 561.66, "total_tokens": 15673760} {"current_steps": 9600, "total_steps": 40000, "loss": 0.0981, "lr": 4.322555973442524e-05, "epoch": 0.4345956223545123, "percentage": 24.0, "elapsed_time": "7:45:09", "remaining_time": "1 day, 0:33:00", "throughput": 561.92, "total_tokens": 15682912} {"current_steps": 9600, "total_steps": 40000, "eval_loss": 0.13993994891643524, "epoch": 0.4345956223545123, "percentage": 24.0, "elapsed_time": "7:52:52", "remaining_time": "1 day, 0:57:25", "throughput": 552.75, "total_tokens": 15682912} {"current_steps": 9605, "total_steps": 40000, "loss": 0.1294, "lr": 4.3218838365897184e-05, "epoch": 0.4348219742411553, "percentage": 24.01, "elapsed_time": "7:52:56", "remaining_time": "1 day, 0:56:36", "throughput": 552.97, "total_tokens": 15691104} {"current_steps": 9610, "total_steps": 40000, "loss": 0.177, "lr": 4.3212114187795306e-05, "epoch": 0.43504832612779826, "percentage": 24.02, "elapsed_time": "7:52:59", "remaining_time": "1 day, 0:55:44", "throughput": 553.18, "total_tokens": 15698944} {"current_steps": 9615, "total_steps": 40000, "loss": 0.1333, "lr": 4.320538720115656e-05, "epoch": 0.43527467801444125, "percentage": 24.04, "elapsed_time": "7:53:02", "remaining_time": "1 day, 0:54:53", "throughput": 553.41, "total_tokens": 15707136} {"current_steps": 9620, "total_steps": 40000, "loss": 0.1473, "lr": 4.319865740701831e-05, "epoch": 0.43550102990108425, "percentage": 24.05, "elapsed_time": "7:53:05", "remaining_time": "1 day, 0:54:01", "throughput": 553.62, "total_tokens": 15714784} {"current_steps": 9625, "total_steps": 40000, "loss": 0.1331, "lr": 4.3191924806418396e-05, "epoch": 0.4357273817877272, "percentage": 24.06, "elapsed_time": "7:53:08", "remaining_time": "1 day, 0:53:10", "throughput": 553.84, "total_tokens": 15722848} {"current_steps": 9630, "total_steps": 40000, "loss": 0.1152, "lr": 4.318518940039507e-05, "epoch": 0.4359537336743702, "percentage": 24.07, "elapsed_time": "7:53:11", "remaining_time": "1 day, 0:52:19", "throughput": 554.07, "total_tokens": 15731136} {"current_steps": 9635, "total_steps": 40000, "loss": 0.1429, "lr": 4.3178451189987e-05, "epoch": 0.4361800855610132, "percentage": 24.09, "elapsed_time": "7:53:15", "remaining_time": "1 day, 0:51:28", "throughput": 554.29, "total_tokens": 15739136} {"current_steps": 9640, "total_steps": 40000, "loss": 0.1186, "lr": 4.3171710176233315e-05, "epoch": 0.4364064374476561, "percentage": 24.1, "elapsed_time": "7:53:18", "remaining_time": "1 day, 0:50:36", "throughput": 554.51, "total_tokens": 15747136} {"current_steps": 9645, "total_steps": 40000, "loss": 0.1273, "lr": 4.316496636017355e-05, "epoch": 0.4366327893342991, "percentage": 24.11, "elapsed_time": "7:53:21", "remaining_time": "1 day, 0:49:45", "throughput": 554.73, "total_tokens": 15755136} {"current_steps": 9650, "total_steps": 40000, "loss": 0.1523, "lr": 4.315821974284771e-05, "epoch": 0.43685914122094205, "percentage": 24.12, "elapsed_time": "7:53:24", "remaining_time": "1 day, 0:48:54", "throughput": 554.95, "total_tokens": 15763200} {"current_steps": 9655, "total_steps": 40000, "loss": 0.1017, "lr": 4.315147032529619e-05, "epoch": 0.43708549310758504, "percentage": 24.14, "elapsed_time": "7:53:27", "remaining_time": "1 day, 0:48:03", "throughput": 555.18, "total_tokens": 15771424} {"current_steps": 9660, "total_steps": 40000, "loss": 0.1149, "lr": 4.3144718108559845e-05, "epoch": 0.43731184499422804, "percentage": 24.15, "elapsed_time": "7:53:30", "remaining_time": "1 day, 0:47:12", "throughput": 555.4, "total_tokens": 15779360} {"current_steps": 9665, "total_steps": 40000, "loss": 0.1012, "lr": 4.3137963093679945e-05, "epoch": 0.437538196880871, "percentage": 24.16, "elapsed_time": "7:53:34", "remaining_time": "1 day, 0:46:21", "throughput": 555.62, "total_tokens": 15787360} {"current_steps": 9670, "total_steps": 40000, "loss": 0.1356, "lr": 4.31312052816982e-05, "epoch": 0.437764548767514, "percentage": 24.18, "elapsed_time": "7:53:37", "remaining_time": "1 day, 0:45:31", "throughput": 555.85, "total_tokens": 15795776} {"current_steps": 9675, "total_steps": 40000, "loss": 0.1514, "lr": 4.312444467365675e-05, "epoch": 0.43799090065415697, "percentage": 24.19, "elapsed_time": "7:53:40", "remaining_time": "1 day, 0:44:40", "throughput": 556.07, "total_tokens": 15803840} {"current_steps": 9680, "total_steps": 40000, "loss": 0.1074, "lr": 4.311768127059816e-05, "epoch": 0.4382172525407999, "percentage": 24.2, "elapsed_time": "7:53:43", "remaining_time": "1 day, 0:43:50", "throughput": 556.32, "total_tokens": 15812896} {"current_steps": 9685, "total_steps": 40000, "loss": 0.1782, "lr": 4.3110915073565444e-05, "epoch": 0.4384436044274429, "percentage": 24.21, "elapsed_time": "7:53:47", "remaining_time": "1 day, 0:42:59", "throughput": 556.55, "total_tokens": 15821152} {"current_steps": 9690, "total_steps": 40000, "loss": 0.1392, "lr": 4.310414608360203e-05, "epoch": 0.4386699563140859, "percentage": 24.22, "elapsed_time": "7:53:50", "remaining_time": "1 day, 0:42:08", "throughput": 556.77, "total_tokens": 15829216} {"current_steps": 9695, "total_steps": 40000, "loss": 0.1302, "lr": 4.309737430175177e-05, "epoch": 0.43889630820072884, "percentage": 24.24, "elapsed_time": "7:53:53", "remaining_time": "1 day, 0:41:18", "throughput": 557.01, "total_tokens": 15837728} {"current_steps": 9700, "total_steps": 40000, "loss": 0.124, "lr": 4.309059972905897e-05, "epoch": 0.43912266008737183, "percentage": 24.25, "elapsed_time": "7:53:56", "remaining_time": "1 day, 0:40:28", "throughput": 557.24, "total_tokens": 15845920} {"current_steps": 9705, "total_steps": 40000, "loss": 0.1565, "lr": 4.308382236656836e-05, "epoch": 0.4393490119740148, "percentage": 24.26, "elapsed_time": "7:53:59", "remaining_time": "1 day, 0:39:37", "throughput": 557.46, "total_tokens": 15854112} {"current_steps": 9710, "total_steps": 40000, "loss": 0.1126, "lr": 4.307704221532507e-05, "epoch": 0.43957536386065776, "percentage": 24.27, "elapsed_time": "7:54:02", "remaining_time": "1 day, 0:38:46", "throughput": 557.67, "total_tokens": 15861888} {"current_steps": 9715, "total_steps": 40000, "loss": 0.1321, "lr": 4.307025927637471e-05, "epoch": 0.43980171574730076, "percentage": 24.29, "elapsed_time": "7:54:06", "remaining_time": "1 day, 0:37:56", "throughput": 557.89, "total_tokens": 15869760} {"current_steps": 9720, "total_steps": 40000, "loss": 0.1904, "lr": 4.306347355076328e-05, "epoch": 0.44002806763394375, "percentage": 24.3, "elapsed_time": "7:54:09", "remaining_time": "1 day, 0:37:05", "throughput": 558.11, "total_tokens": 15877760} {"current_steps": 9725, "total_steps": 40000, "loss": 0.1517, "lr": 4.305668503953724e-05, "epoch": 0.4402544195205867, "percentage": 24.31, "elapsed_time": "7:54:12", "remaining_time": "1 day, 0:36:15", "throughput": 558.33, "total_tokens": 15885920} {"current_steps": 9730, "total_steps": 40000, "loss": 0.1656, "lr": 4.3049893743743436e-05, "epoch": 0.4404807714072297, "percentage": 24.32, "elapsed_time": "7:54:15", "remaining_time": "1 day, 0:35:25", "throughput": 558.56, "total_tokens": 15894176} {"current_steps": 9735, "total_steps": 40000, "loss": 0.1505, "lr": 4.304309966442919e-05, "epoch": 0.4407071232938726, "percentage": 24.34, "elapsed_time": "7:54:18", "remaining_time": "1 day, 0:34:35", "throughput": 558.78, "total_tokens": 15902208} {"current_steps": 9740, "total_steps": 40000, "loss": 0.1892, "lr": 4.303630280264224e-05, "epoch": 0.4409334751805156, "percentage": 24.35, "elapsed_time": "7:54:21", "remaining_time": "1 day, 0:33:44", "throughput": 559.0, "total_tokens": 15910272} {"current_steps": 9745, "total_steps": 40000, "loss": 0.1365, "lr": 4.302950315943074e-05, "epoch": 0.4411598270671586, "percentage": 24.36, "elapsed_time": "7:54:25", "remaining_time": "1 day, 0:32:54", "throughput": 559.22, "total_tokens": 15918272} {"current_steps": 9750, "total_steps": 40000, "loss": 0.1474, "lr": 4.3022700735843275e-05, "epoch": 0.44138617895380156, "percentage": 24.38, "elapsed_time": "7:54:28", "remaining_time": "1 day, 0:32:04", "throughput": 559.44, "total_tokens": 15926240} {"current_steps": 9755, "total_steps": 40000, "loss": 0.0807, "lr": 4.301589553292887e-05, "epoch": 0.44161253084044455, "percentage": 24.39, "elapsed_time": "7:54:31", "remaining_time": "1 day, 0:31:14", "throughput": 559.67, "total_tokens": 15934464} {"current_steps": 9760, "total_steps": 40000, "loss": 0.1215, "lr": 4.300908755173697e-05, "epoch": 0.44183888272708755, "percentage": 24.4, "elapsed_time": "7:54:34", "remaining_time": "1 day, 0:30:24", "throughput": 559.89, "total_tokens": 15942720} {"current_steps": 9765, "total_steps": 40000, "loss": 0.1611, "lr": 4.300227679331745e-05, "epoch": 0.4420652346137305, "percentage": 24.41, "elapsed_time": "7:54:38", "remaining_time": "1 day, 0:29:35", "throughput": 560.16, "total_tokens": 15952352} {"current_steps": 9770, "total_steps": 40000, "loss": 0.1623, "lr": 4.299546325872063e-05, "epoch": 0.4422915865003735, "percentage": 24.43, "elapsed_time": "7:54:41", "remaining_time": "1 day, 0:28:45", "throughput": 560.4, "total_tokens": 15960864} {"current_steps": 9775, "total_steps": 40000, "loss": 0.147, "lr": 4.2988646948997225e-05, "epoch": 0.4425179383870165, "percentage": 24.44, "elapsed_time": "7:54:44", "remaining_time": "1 day, 0:27:56", "throughput": 560.63, "total_tokens": 15969376} {"current_steps": 9780, "total_steps": 40000, "loss": 0.1333, "lr": 4.29818278651984e-05, "epoch": 0.4427442902736594, "percentage": 24.45, "elapsed_time": "7:54:47", "remaining_time": "1 day, 0:27:06", "throughput": 560.85, "total_tokens": 15977280} {"current_steps": 9785, "total_steps": 40000, "loss": 0.1297, "lr": 4.297500600837574e-05, "epoch": 0.4429706421603024, "percentage": 24.46, "elapsed_time": "7:54:50", "remaining_time": "1 day, 0:26:16", "throughput": 561.08, "total_tokens": 15985696} {"current_steps": 9790, "total_steps": 40000, "loss": 0.1696, "lr": 4.2968181379581276e-05, "epoch": 0.4431969940469454, "percentage": 24.47, "elapsed_time": "7:54:54", "remaining_time": "1 day, 0:25:26", "throughput": 561.3, "total_tokens": 15993568} {"current_steps": 9795, "total_steps": 40000, "loss": 0.1322, "lr": 4.296135397986743e-05, "epoch": 0.44342334593358834, "percentage": 24.49, "elapsed_time": "7:54:57", "remaining_time": "1 day, 0:24:37", "throughput": 561.52, "total_tokens": 16001856} {"current_steps": 9800, "total_steps": 40000, "loss": 0.1451, "lr": 4.295452381028709e-05, "epoch": 0.44364969782023134, "percentage": 24.5, "elapsed_time": "7:55:00", "remaining_time": "1 day, 0:23:47", "throughput": 561.75, "total_tokens": 16010208} {"current_steps": 9800, "total_steps": 40000, "eval_loss": 0.13963530957698822, "epoch": 0.44364969782023134, "percentage": 24.5, "elapsed_time": "8:02:43", "remaining_time": "1 day, 0:47:33", "throughput": 552.78, "total_tokens": 16010208} {"current_steps": 9805, "total_steps": 40000, "loss": 0.1184, "lr": 4.294769087189354e-05, "epoch": 0.44387604970687433, "percentage": 24.51, "elapsed_time": "8:02:47", "remaining_time": "1 day, 0:46:45", "throughput": 553.01, "total_tokens": 16019136} {"current_steps": 9810, "total_steps": 40000, "loss": 0.092, "lr": 4.294085516574052e-05, "epoch": 0.44410240159351727, "percentage": 24.52, "elapsed_time": "8:02:50", "remaining_time": "1 day, 0:45:55", "throughput": 553.24, "total_tokens": 16027552} {"current_steps": 9815, "total_steps": 40000, "loss": 0.1381, "lr": 4.2934016692882176e-05, "epoch": 0.44432875348016027, "percentage": 24.54, "elapsed_time": "8:02:53", "remaining_time": "1 day, 0:45:05", "throughput": 553.46, "total_tokens": 16035680} {"current_steps": 9820, "total_steps": 40000, "loss": 0.1048, "lr": 4.292717545437308e-05, "epoch": 0.4445551053668032, "percentage": 24.55, "elapsed_time": "8:02:56", "remaining_time": "1 day, 0:44:14", "throughput": 553.66, "total_tokens": 16043232} {"current_steps": 9825, "total_steps": 40000, "loss": 0.1453, "lr": 4.292033145126825e-05, "epoch": 0.4447814572534462, "percentage": 24.56, "elapsed_time": "8:02:59", "remaining_time": "1 day, 0:43:24", "throughput": 553.87, "total_tokens": 16051168} {"current_steps": 9830, "total_steps": 40000, "loss": 0.1289, "lr": 4.29134846846231e-05, "epoch": 0.4450078091400892, "percentage": 24.57, "elapsed_time": "8:03:02", "remaining_time": "1 day, 0:42:33", "throughput": 554.1, "total_tokens": 16059328} {"current_steps": 9835, "total_steps": 40000, "loss": 0.1254, "lr": 4.29066351554935e-05, "epoch": 0.44523416102673213, "percentage": 24.59, "elapsed_time": "8:03:06", "remaining_time": "1 day, 0:41:43", "throughput": 554.31, "total_tokens": 16067232} {"current_steps": 9840, "total_steps": 40000, "loss": 0.1651, "lr": 4.289978286493574e-05, "epoch": 0.44546051291337513, "percentage": 24.6, "elapsed_time": "8:03:09", "remaining_time": "1 day, 0:40:53", "throughput": 554.52, "total_tokens": 16075104} {"current_steps": 9845, "total_steps": 40000, "loss": 0.1528, "lr": 4.28929278140065e-05, "epoch": 0.4456868648000181, "percentage": 24.61, "elapsed_time": "8:03:12", "remaining_time": "1 day, 0:40:02", "throughput": 554.73, "total_tokens": 16083072} {"current_steps": 9850, "total_steps": 40000, "loss": 0.1461, "lr": 4.288607000376295e-05, "epoch": 0.44591321668666106, "percentage": 24.62, "elapsed_time": "8:03:15", "remaining_time": "1 day, 0:39:12", "throughput": 554.95, "total_tokens": 16091136} {"current_steps": 9855, "total_steps": 40000, "loss": 0.1164, "lr": 4.2879209435262624e-05, "epoch": 0.44613956857330406, "percentage": 24.64, "elapsed_time": "8:03:18", "remaining_time": "1 day, 0:38:22", "throughput": 555.18, "total_tokens": 16099360} {"current_steps": 9860, "total_steps": 40000, "loss": 0.1331, "lr": 4.287234610956353e-05, "epoch": 0.44636592045994705, "percentage": 24.65, "elapsed_time": "8:03:21", "remaining_time": "1 day, 0:37:32", "throughput": 555.4, "total_tokens": 16107744} {"current_steps": 9865, "total_steps": 40000, "loss": 0.1397, "lr": 4.2865480027724056e-05, "epoch": 0.44659227234659, "percentage": 24.66, "elapsed_time": "8:03:25", "remaining_time": "1 day, 0:36:43", "throughput": 555.62, "total_tokens": 16115872} {"current_steps": 9870, "total_steps": 40000, "loss": 0.1627, "lr": 4.285861119080306e-05, "epoch": 0.446818624233233, "percentage": 24.68, "elapsed_time": "8:03:28", "remaining_time": "1 day, 0:35:53", "throughput": 555.83, "total_tokens": 16123712} {"current_steps": 9875, "total_steps": 40000, "loss": 0.1272, "lr": 4.2851739599859784e-05, "epoch": 0.447044976119876, "percentage": 24.69, "elapsed_time": "8:03:31", "remaining_time": "1 day, 0:35:03", "throughput": 556.04, "total_tokens": 16131648} {"current_steps": 9880, "total_steps": 40000, "loss": 0.1807, "lr": 4.2844865255953934e-05, "epoch": 0.4472713280065189, "percentage": 24.7, "elapsed_time": "8:03:34", "remaining_time": "1 day, 0:34:13", "throughput": 556.27, "total_tokens": 16140096} {"current_steps": 9885, "total_steps": 40000, "loss": 0.1737, "lr": 4.2837988160145605e-05, "epoch": 0.4474976798931619, "percentage": 24.71, "elapsed_time": "8:03:37", "remaining_time": "1 day, 0:33:23", "throughput": 556.49, "total_tokens": 16148160} {"current_steps": 9890, "total_steps": 40000, "loss": 0.0967, "lr": 4.2831108313495336e-05, "epoch": 0.4477240317798049, "percentage": 24.73, "elapsed_time": "8:03:40", "remaining_time": "1 day, 0:32:34", "throughput": 556.7, "total_tokens": 16155968} {"current_steps": 9895, "total_steps": 40000, "loss": 0.1258, "lr": 4.282422571706408e-05, "epoch": 0.44795038366644785, "percentage": 24.74, "elapsed_time": "8:03:44", "remaining_time": "1 day, 0:31:44", "throughput": 556.91, "total_tokens": 16163840} {"current_steps": 9900, "total_steps": 40000, "loss": 0.1135, "lr": 4.281734037191323e-05, "epoch": 0.44817673555309084, "percentage": 24.75, "elapsed_time": "8:03:47", "remaining_time": "1 day, 0:30:54", "throughput": 557.12, "total_tokens": 16171648} {"current_steps": 9905, "total_steps": 40000, "loss": 0.1419, "lr": 4.281045227910459e-05, "epoch": 0.4484030874397338, "percentage": 24.76, "elapsed_time": "8:03:50", "remaining_time": "1 day, 0:30:05", "throughput": 557.36, "total_tokens": 16180384} {"current_steps": 9910, "total_steps": 40000, "loss": 0.1392, "lr": 4.280356143970038e-05, "epoch": 0.4486294393263768, "percentage": 24.77, "elapsed_time": "8:03:53", "remaining_time": "1 day, 0:29:15", "throughput": 557.59, "total_tokens": 16188768} {"current_steps": 9915, "total_steps": 40000, "loss": 0.1107, "lr": 4.279666785476327e-05, "epoch": 0.4488557912130198, "percentage": 24.79, "elapsed_time": "8:03:56", "remaining_time": "1 day, 0:28:26", "throughput": 557.81, "total_tokens": 16197184} {"current_steps": 9920, "total_steps": 40000, "loss": 0.1725, "lr": 4.2789771525356325e-05, "epoch": 0.4490821430996627, "percentage": 24.8, "elapsed_time": "8:04:00", "remaining_time": "1 day, 0:27:37", "throughput": 558.06, "total_tokens": 16206208} {"current_steps": 9925, "total_steps": 40000, "loss": 0.1487, "lr": 4.2782872452543056e-05, "epoch": 0.4493084949863057, "percentage": 24.81, "elapsed_time": "8:04:03", "remaining_time": "1 day, 0:26:48", "throughput": 558.26, "total_tokens": 16213888} {"current_steps": 9930, "total_steps": 40000, "loss": 0.1318, "lr": 4.2775970637387376e-05, "epoch": 0.4495348468729487, "percentage": 24.82, "elapsed_time": "8:04:06", "remaining_time": "1 day, 0:25:58", "throughput": 558.47, "total_tokens": 16221568} {"current_steps": 9935, "total_steps": 40000, "loss": 0.1468, "lr": 4.276906608095363e-05, "epoch": 0.44976119875959164, "percentage": 24.84, "elapsed_time": "8:04:09", "remaining_time": "1 day, 0:25:09", "throughput": 558.68, "total_tokens": 16229408} {"current_steps": 9940, "total_steps": 40000, "loss": 0.1347, "lr": 4.276215878430661e-05, "epoch": 0.44998755064623464, "percentage": 24.85, "elapsed_time": "8:04:12", "remaining_time": "1 day, 0:24:19", "throughput": 558.89, "total_tokens": 16237216} {"current_steps": 9945, "total_steps": 40000, "loss": 0.1451, "lr": 4.275524874851149e-05, "epoch": 0.45021390253287763, "percentage": 24.86, "elapsed_time": "8:04:16", "remaining_time": "1 day, 0:23:30", "throughput": 559.12, "total_tokens": 16245952} {"current_steps": 9950, "total_steps": 40000, "loss": 0.1636, "lr": 4.274833597463388e-05, "epoch": 0.45044025441952057, "percentage": 24.88, "elapsed_time": "8:04:19", "remaining_time": "1 day, 0:22:41", "throughput": 559.34, "total_tokens": 16253984} {"current_steps": 9955, "total_steps": 40000, "loss": 0.1267, "lr": 4.2741420463739824e-05, "epoch": 0.45066660630616356, "percentage": 24.89, "elapsed_time": "8:04:22", "remaining_time": "1 day, 0:21:52", "throughput": 559.57, "total_tokens": 16262336} {"current_steps": 9960, "total_steps": 40000, "loss": 0.1696, "lr": 4.273450221689578e-05, "epoch": 0.45089295819280656, "percentage": 24.9, "elapsed_time": "8:04:25", "remaining_time": "1 day, 0:21:03", "throughput": 559.78, "total_tokens": 16270496} {"current_steps": 9965, "total_steps": 40000, "loss": 0.1039, "lr": 4.272758123516863e-05, "epoch": 0.4511193100794495, "percentage": 24.91, "elapsed_time": "8:04:28", "remaining_time": "1 day, 0:20:14", "throughput": 560.0, "total_tokens": 16278528} {"current_steps": 9970, "total_steps": 40000, "loss": 0.114, "lr": 4.272065751962567e-05, "epoch": 0.4513456619660925, "percentage": 24.93, "elapsed_time": "8:04:31", "remaining_time": "1 day, 0:19:25", "throughput": 560.21, "total_tokens": 16286496} {"current_steps": 9975, "total_steps": 40000, "loss": 0.1302, "lr": 4.271373107133464e-05, "epoch": 0.4515720138527355, "percentage": 24.94, "elapsed_time": "8:04:35", "remaining_time": "1 day, 0:18:38", "throughput": 560.48, "total_tokens": 16296256} {"current_steps": 9980, "total_steps": 40000, "loss": 0.1993, "lr": 4.270680189136366e-05, "epoch": 0.4517983657393784, "percentage": 24.95, "elapsed_time": "8:04:38", "remaining_time": "1 day, 0:17:49", "throughput": 560.7, "total_tokens": 16304320} {"current_steps": 9985, "total_steps": 40000, "loss": 0.1392, "lr": 4.269986998078132e-05, "epoch": 0.4520247176260214, "percentage": 24.96, "elapsed_time": "8:04:41", "remaining_time": "1 day, 0:17:00", "throughput": 560.93, "total_tokens": 16312992} {"current_steps": 9990, "total_steps": 40000, "loss": 0.125, "lr": 4.2692935340656595e-05, "epoch": 0.45225106951266436, "percentage": 24.98, "elapsed_time": "8:04:45", "remaining_time": "1 day, 0:16:11", "throughput": 561.15, "total_tokens": 16320960} {"current_steps": 9995, "total_steps": 40000, "loss": 0.1975, "lr": 4.26859979720589e-05, "epoch": 0.45247742139930736, "percentage": 24.99, "elapsed_time": "8:04:48", "remaining_time": "1 day, 0:15:23", "throughput": 561.36, "total_tokens": 16329120} {"current_steps": 10000, "total_steps": 40000, "loss": 0.1045, "lr": 4.267905787605806e-05, "epoch": 0.45270377328595035, "percentage": 25.0, "elapsed_time": "8:04:51", "remaining_time": "1 day, 0:14:34", "throughput": 561.59, "total_tokens": 16337472} {"current_steps": 10000, "total_steps": 40000, "eval_loss": 0.1394030600786209, "epoch": 0.45270377328595035, "percentage": 25.0, "elapsed_time": "8:12:34", "remaining_time": "1 day, 0:37:42", "throughput": 552.8, "total_tokens": 16337472} {"current_steps": 10005, "total_steps": 40000, "loss": 0.152, "lr": 4.267211505372433e-05, "epoch": 0.4529301251725933, "percentage": 25.01, "elapsed_time": "8:12:38", "remaining_time": "1 day, 0:36:56", "throughput": 553.0, "total_tokens": 16345824} {"current_steps": 10010, "total_steps": 40000, "loss": 0.1529, "lr": 4.266516950612837e-05, "epoch": 0.4531564770592363, "percentage": 25.02, "elapsed_time": "8:12:41", "remaining_time": "1 day, 0:36:06", "throughput": 553.19, "total_tokens": 16353216} {"current_steps": 10015, "total_steps": 40000, "loss": 0.1154, "lr": 4.265822123434128e-05, "epoch": 0.4533828289458793, "percentage": 25.04, "elapsed_time": "8:12:44", "remaining_time": "1 day, 0:35:16", "throughput": 553.4, "total_tokens": 16361024} {"current_steps": 10020, "total_steps": 40000, "loss": 0.1255, "lr": 4.265127023943457e-05, "epoch": 0.4536091808325222, "percentage": 25.05, "elapsed_time": "8:12:47", "remaining_time": "1 day, 0:34:26", "throughput": 553.61, "total_tokens": 16369024} {"current_steps": 10025, "total_steps": 40000, "loss": 0.1475, "lr": 4.2644316522480176e-05, "epoch": 0.4538355327191652, "percentage": 25.06, "elapsed_time": "8:12:50", "remaining_time": "1 day, 0:33:37", "throughput": 553.84, "total_tokens": 16377536} {"current_steps": 10030, "total_steps": 40000, "loss": 0.103, "lr": 4.263736008455044e-05, "epoch": 0.4540618846058082, "percentage": 25.07, "elapsed_time": "8:12:54", "remaining_time": "1 day, 0:32:48", "throughput": 554.06, "total_tokens": 16385856} {"current_steps": 10035, "total_steps": 40000, "loss": 0.1266, "lr": 4.2630400926718125e-05, "epoch": 0.45428823649245115, "percentage": 25.09, "elapsed_time": "8:12:57", "remaining_time": "1 day, 0:31:59", "throughput": 554.29, "total_tokens": 16394464} {"current_steps": 10040, "total_steps": 40000, "loss": 0.0983, "lr": 4.262343905005644e-05, "epoch": 0.45451458837909414, "percentage": 25.1, "elapsed_time": "8:13:00", "remaining_time": "1 day, 0:31:10", "throughput": 554.51, "total_tokens": 16402784} {"current_steps": 10045, "total_steps": 40000, "loss": 0.1052, "lr": 4.261647445563897e-05, "epoch": 0.45474094026573714, "percentage": 25.11, "elapsed_time": "8:13:03", "remaining_time": "1 day, 0:30:20", "throughput": 554.71, "total_tokens": 16410432} {"current_steps": 10050, "total_steps": 40000, "loss": 0.1017, "lr": 4.260950714453976e-05, "epoch": 0.4549672921523801, "percentage": 25.12, "elapsed_time": "8:13:06", "remaining_time": "1 day, 0:29:31", "throughput": 554.93, "total_tokens": 16418592} {"current_steps": 10055, "total_steps": 40000, "loss": 0.1853, "lr": 4.2602537117833266e-05, "epoch": 0.45519364403902307, "percentage": 25.14, "elapsed_time": "8:13:10", "remaining_time": "1 day, 0:28:42", "throughput": 555.15, "total_tokens": 16426816} {"current_steps": 10060, "total_steps": 40000, "loss": 0.1426, "lr": 4.259556437659433e-05, "epoch": 0.45541999592566607, "percentage": 25.15, "elapsed_time": "8:13:13", "remaining_time": "1 day, 0:27:53", "throughput": 555.36, "total_tokens": 16434912} {"current_steps": 10065, "total_steps": 40000, "loss": 0.1489, "lr": 4.258858892189825e-05, "epoch": 0.455646347812309, "percentage": 25.16, "elapsed_time": "8:13:16", "remaining_time": "1 day, 0:27:04", "throughput": 555.55, "total_tokens": 16442336} {"current_steps": 10070, "total_steps": 40000, "loss": 0.1665, "lr": 4.2581610754820725e-05, "epoch": 0.455872699698952, "percentage": 25.17, "elapsed_time": "8:13:19", "remaining_time": "1 day, 0:26:15", "throughput": 555.78, "total_tokens": 16450816} {"current_steps": 10075, "total_steps": 40000, "loss": 0.1332, "lr": 4.2574629876437876e-05, "epoch": 0.45609905158559494, "percentage": 25.19, "elapsed_time": "8:13:22", "remaining_time": "1 day, 0:25:26", "throughput": 556.01, "total_tokens": 16459360} {"current_steps": 10080, "total_steps": 40000, "loss": 0.1382, "lr": 4.256764628782625e-05, "epoch": 0.45632540347223793, "percentage": 25.2, "elapsed_time": "8:13:25", "remaining_time": "1 day, 0:24:37", "throughput": 556.23, "total_tokens": 16467776} {"current_steps": 10085, "total_steps": 40000, "loss": 0.1524, "lr": 4.256065999006279e-05, "epoch": 0.45655175535888093, "percentage": 25.21, "elapsed_time": "8:13:29", "remaining_time": "1 day, 0:23:48", "throughput": 556.43, "total_tokens": 16475392} {"current_steps": 10090, "total_steps": 40000, "loss": 0.1581, "lr": 4.2553670984224885e-05, "epoch": 0.45677810724552387, "percentage": 25.22, "elapsed_time": "8:13:32", "remaining_time": "1 day, 0:23:00", "throughput": 556.65, "total_tokens": 16483488} {"current_steps": 10095, "total_steps": 40000, "loss": 0.1528, "lr": 4.254667927139032e-05, "epoch": 0.45700445913216686, "percentage": 25.24, "elapsed_time": "8:13:35", "remaining_time": "1 day, 0:22:11", "throughput": 556.85, "total_tokens": 16491424} {"current_steps": 10100, "total_steps": 40000, "loss": 0.1623, "lr": 4.2539684852637295e-05, "epoch": 0.45723081101880986, "percentage": 25.25, "elapsed_time": "8:13:38", "remaining_time": "1 day, 0:21:22", "throughput": 557.08, "total_tokens": 16499872} {"current_steps": 10105, "total_steps": 40000, "loss": 0.1755, "lr": 4.253268772904446e-05, "epoch": 0.4574571629054528, "percentage": 25.26, "elapsed_time": "8:13:41", "remaining_time": "1 day, 0:20:34", "throughput": 557.3, "total_tokens": 16508128} {"current_steps": 10110, "total_steps": 40000, "loss": 0.1577, "lr": 4.252568790169085e-05, "epoch": 0.4576835147920958, "percentage": 25.27, "elapsed_time": "8:13:44", "remaining_time": "1 day, 0:19:45", "throughput": 557.51, "total_tokens": 16516160} {"current_steps": 10115, "total_steps": 40000, "loss": 0.1454, "lr": 4.251868537165592e-05, "epoch": 0.4579098666787388, "percentage": 25.29, "elapsed_time": "8:13:48", "remaining_time": "1 day, 0:18:57", "throughput": 557.73, "total_tokens": 16524512} {"current_steps": 10120, "total_steps": 40000, "loss": 0.1566, "lr": 4.251168014001955e-05, "epoch": 0.4581362185653817, "percentage": 25.3, "elapsed_time": "8:13:51", "remaining_time": "1 day, 0:18:08", "throughput": 557.94, "total_tokens": 16532608} {"current_steps": 10125, "total_steps": 40000, "loss": 0.1896, "lr": 4.250467220786204e-05, "epoch": 0.4583625704520247, "percentage": 25.31, "elapsed_time": "8:13:54", "remaining_time": "1 day, 0:17:19", "throughput": 558.15, "total_tokens": 16540384} {"current_steps": 10130, "total_steps": 40000, "loss": 0.1564, "lr": 4.249766157626409e-05, "epoch": 0.4585889223386677, "percentage": 25.32, "elapsed_time": "8:13:57", "remaining_time": "1 day, 0:16:31", "throughput": 558.35, "total_tokens": 16548224} {"current_steps": 10135, "total_steps": 40000, "loss": 0.1496, "lr": 4.249064824630684e-05, "epoch": 0.45881527422531065, "percentage": 25.34, "elapsed_time": "8:14:00", "remaining_time": "1 day, 0:15:42", "throughput": 558.57, "total_tokens": 16556384} {"current_steps": 10140, "total_steps": 40000, "loss": 0.1285, "lr": 4.248363221907183e-05, "epoch": 0.45904162611195365, "percentage": 25.35, "elapsed_time": "8:14:04", "remaining_time": "1 day, 0:14:55", "throughput": 558.8, "total_tokens": 16565120} {"current_steps": 10145, "total_steps": 40000, "loss": 0.1249, "lr": 4.2476613495641026e-05, "epoch": 0.45926797799859664, "percentage": 25.36, "elapsed_time": "8:14:07", "remaining_time": "1 day, 0:14:06", "throughput": 559.02, "total_tokens": 16573344} {"current_steps": 10150, "total_steps": 40000, "loss": 0.1755, "lr": 4.246959207709679e-05, "epoch": 0.4594943298852396, "percentage": 25.37, "elapsed_time": "8:14:10", "remaining_time": "1 day, 0:13:19", "throughput": 559.25, "total_tokens": 16581952} {"current_steps": 10155, "total_steps": 40000, "loss": 0.2152, "lr": 4.246256796452192e-05, "epoch": 0.4597206817718826, "percentage": 25.39, "elapsed_time": "8:14:13", "remaining_time": "1 day, 0:12:31", "throughput": 559.45, "total_tokens": 16590048} {"current_steps": 10160, "total_steps": 40000, "loss": 0.1213, "lr": 4.245554115899962e-05, "epoch": 0.4599470336585255, "percentage": 25.4, "elapsed_time": "8:14:17", "remaining_time": "1 day, 0:11:43", "throughput": 559.67, "total_tokens": 16598240} {"current_steps": 10165, "total_steps": 40000, "loss": 0.1451, "lr": 4.2448511661613514e-05, "epoch": 0.4601733855451685, "percentage": 25.41, "elapsed_time": "8:14:20", "remaining_time": "1 day, 0:10:55", "throughput": 559.9, "total_tokens": 16606816} {"current_steps": 10170, "total_steps": 40000, "loss": 0.0964, "lr": 4.2441479473447635e-05, "epoch": 0.4603997374318115, "percentage": 25.42, "elapsed_time": "8:14:23", "remaining_time": "1 day, 0:10:07", "throughput": 560.12, "total_tokens": 16615360} {"current_steps": 10175, "total_steps": 40000, "loss": 0.1345, "lr": 4.243444459558644e-05, "epoch": 0.46062608931845445, "percentage": 25.44, "elapsed_time": "8:14:26", "remaining_time": "1 day, 0:09:19", "throughput": 560.34, "total_tokens": 16623488} {"current_steps": 10180, "total_steps": 40000, "loss": 0.1079, "lr": 4.24274070291148e-05, "epoch": 0.46085244120509744, "percentage": 25.45, "elapsed_time": "8:14:29", "remaining_time": "1 day, 0:08:31", "throughput": 560.55, "total_tokens": 16631392} {"current_steps": 10185, "total_steps": 40000, "loss": 0.1629, "lr": 4.242036677511798e-05, "epoch": 0.46107879309174044, "percentage": 25.46, "elapsed_time": "8:14:33", "remaining_time": "1 day, 0:07:43", "throughput": 560.78, "total_tokens": 16640160} {"current_steps": 10190, "total_steps": 40000, "loss": 0.1515, "lr": 4.241332383468169e-05, "epoch": 0.4613051449783834, "percentage": 25.47, "elapsed_time": "8:14:36", "remaining_time": "1 day, 0:06:55", "throughput": 561.0, "total_tokens": 16648384} {"current_steps": 10195, "total_steps": 40000, "loss": 0.1378, "lr": 4.2406278208892034e-05, "epoch": 0.46153149686502637, "percentage": 25.49, "elapsed_time": "8:14:39", "remaining_time": "1 day, 0:06:07", "throughput": 561.19, "total_tokens": 16655936} {"current_steps": 10200, "total_steps": 40000, "loss": 0.1355, "lr": 4.2399229898835536e-05, "epoch": 0.46175784875166936, "percentage": 25.5, "elapsed_time": "8:14:43", "remaining_time": "1 day, 0:05:20", "throughput": 561.44, "total_tokens": 16665216} {"current_steps": 10200, "total_steps": 40000, "eval_loss": 0.1393870711326599, "epoch": 0.46175784875166936, "percentage": 25.5, "elapsed_time": "8:22:25", "remaining_time": "1 day, 0:27:52", "throughput": 552.82, "total_tokens": 16665216} {"current_steps": 10205, "total_steps": 40000, "loss": 0.1285, "lr": 4.239217890559914e-05, "epoch": 0.4619842006383123, "percentage": 25.51, "elapsed_time": "8:22:29", "remaining_time": "1 day, 0:27:06", "throughput": 553.03, "total_tokens": 16673760} {"current_steps": 10210, "total_steps": 40000, "loss": 0.1032, "lr": 4.238512523027019e-05, "epoch": 0.4622105525249553, "percentage": 25.52, "elapsed_time": "8:22:32", "remaining_time": "1 day, 0:26:18", "throughput": 553.25, "total_tokens": 16682112} {"current_steps": 10215, "total_steps": 40000, "loss": 0.0752, "lr": 4.237806887393645e-05, "epoch": 0.4624369044115983, "percentage": 25.54, "elapsed_time": "8:22:36", "remaining_time": "1 day, 0:25:29", "throughput": 553.47, "total_tokens": 16690464} {"current_steps": 10220, "total_steps": 40000, "loss": 0.0708, "lr": 4.237100983768611e-05, "epoch": 0.46266325629824123, "percentage": 25.55, "elapsed_time": "8:22:39", "remaining_time": "1 day, 0:24:41", "throughput": 553.68, "total_tokens": 16698688} {"current_steps": 10225, "total_steps": 40000, "loss": 0.1772, "lr": 4.2363948122607756e-05, "epoch": 0.4628896081848842, "percentage": 25.56, "elapsed_time": "8:22:42", "remaining_time": "1 day, 0:23:52", "throughput": 553.9, "total_tokens": 16706976} {"current_steps": 10230, "total_steps": 40000, "loss": 0.0793, "lr": 4.235688372979039e-05, "epoch": 0.4631159600715272, "percentage": 25.57, "elapsed_time": "8:22:45", "remaining_time": "1 day, 0:23:04", "throughput": 554.11, "total_tokens": 16715072} {"current_steps": 10235, "total_steps": 40000, "loss": 0.152, "lr": 4.234981666032343e-05, "epoch": 0.46334231195817016, "percentage": 25.59, "elapsed_time": "8:22:48", "remaining_time": "1 day, 0:22:15", "throughput": 554.33, "total_tokens": 16723552} {"current_steps": 10240, "total_steps": 40000, "loss": 0.1132, "lr": 4.2342746915296704e-05, "epoch": 0.46356866384481316, "percentage": 25.6, "elapsed_time": "8:22:52", "remaining_time": "1 day, 0:21:27", "throughput": 554.53, "total_tokens": 16731424} {"current_steps": 10245, "total_steps": 40000, "loss": 0.1194, "lr": 4.233567449580047e-05, "epoch": 0.4637950157314561, "percentage": 25.61, "elapsed_time": "8:22:55", "remaining_time": "1 day, 0:20:39", "throughput": 554.74, "total_tokens": 16739520} {"current_steps": 10250, "total_steps": 40000, "loss": 0.1294, "lr": 4.232859940292537e-05, "epoch": 0.4640213676180991, "percentage": 25.62, "elapsed_time": "8:22:58", "remaining_time": "1 day, 0:19:51", "throughput": 554.97, "total_tokens": 16748064} {"current_steps": 10255, "total_steps": 40000, "loss": 0.1258, "lr": 4.232152163776248e-05, "epoch": 0.4642477195047421, "percentage": 25.64, "elapsed_time": "8:23:01", "remaining_time": "1 day, 0:19:02", "throughput": 555.17, "total_tokens": 16755936} {"current_steps": 10260, "total_steps": 40000, "loss": 0.1334, "lr": 4.231444120140328e-05, "epoch": 0.464474071391385, "percentage": 25.65, "elapsed_time": "8:23:04", "remaining_time": "1 day, 0:18:14", "throughput": 555.39, "total_tokens": 16764224} {"current_steps": 10265, "total_steps": 40000, "loss": 0.1481, "lr": 4.230735809493967e-05, "epoch": 0.464700423278028, "percentage": 25.66, "elapsed_time": "8:23:07", "remaining_time": "1 day, 0:17:26", "throughput": 555.6, "total_tokens": 16772544} {"current_steps": 10270, "total_steps": 40000, "loss": 0.1258, "lr": 4.2300272319463926e-05, "epoch": 0.464926775164671, "percentage": 25.67, "elapsed_time": "8:23:11", "remaining_time": "1 day, 0:16:38", "throughput": 555.81, "total_tokens": 16780480} {"current_steps": 10275, "total_steps": 40000, "loss": 0.2122, "lr": 4.2293183876068786e-05, "epoch": 0.46515312705131395, "percentage": 25.69, "elapsed_time": "8:23:14", "remaining_time": "1 day, 0:15:50", "throughput": 556.03, "total_tokens": 16789056} {"current_steps": 10280, "total_steps": 40000, "loss": 0.1479, "lr": 4.228609276584737e-05, "epoch": 0.46537947893795695, "percentage": 25.7, "elapsed_time": "8:23:17", "remaining_time": "1 day, 0:15:02", "throughput": 556.26, "total_tokens": 16797696} {"current_steps": 10285, "total_steps": 40000, "loss": 0.1848, "lr": 4.227899898989323e-05, "epoch": 0.46560583082459994, "percentage": 25.71, "elapsed_time": "8:23:20", "remaining_time": "1 day, 0:14:15", "throughput": 556.48, "total_tokens": 16806208} {"current_steps": 10290, "total_steps": 40000, "loss": 0.1185, "lr": 4.2271902549300293e-05, "epoch": 0.4658321827112429, "percentage": 25.72, "elapsed_time": "8:23:24", "remaining_time": "1 day, 0:13:27", "throughput": 556.69, "total_tokens": 16814144} {"current_steps": 10295, "total_steps": 40000, "loss": 0.1307, "lr": 4.226480344516294e-05, "epoch": 0.4660585345978859, "percentage": 25.74, "elapsed_time": "8:23:27", "remaining_time": "1 day, 0:12:39", "throughput": 556.89, "total_tokens": 16822080} {"current_steps": 10300, "total_steps": 40000, "loss": 0.1025, "lr": 4.2257701678575925e-05, "epoch": 0.46628488648452887, "percentage": 25.75, "elapsed_time": "8:23:30", "remaining_time": "1 day, 0:11:51", "throughput": 557.1, "total_tokens": 16830176} {"current_steps": 10305, "total_steps": 40000, "loss": 0.1144, "lr": 4.225059725063444e-05, "epoch": 0.4665112383711718, "percentage": 25.76, "elapsed_time": "8:23:33", "remaining_time": "1 day, 0:11:03", "throughput": 557.3, "total_tokens": 16837888} {"current_steps": 10310, "total_steps": 40000, "loss": 0.1229, "lr": 4.2243490162434074e-05, "epoch": 0.4667375902578148, "percentage": 25.77, "elapsed_time": "8:23:36", "remaining_time": "1 day, 0:10:15", "throughput": 557.49, "total_tokens": 16845536} {"current_steps": 10315, "total_steps": 40000, "loss": 0.1256, "lr": 4.223638041507083e-05, "epoch": 0.4669639421444578, "percentage": 25.79, "elapsed_time": "8:23:39", "remaining_time": "1 day, 0:09:27", "throughput": 557.72, "total_tokens": 16854240} {"current_steps": 10320, "total_steps": 40000, "loss": 0.1311, "lr": 4.2229268009641124e-05, "epoch": 0.46719029403110074, "percentage": 25.8, "elapsed_time": "8:23:43", "remaining_time": "1 day, 0:08:40", "throughput": 557.95, "total_tokens": 16863008} {"current_steps": 10325, "total_steps": 40000, "loss": 0.0771, "lr": 4.222215294724177e-05, "epoch": 0.46741664591774373, "percentage": 25.81, "elapsed_time": "8:23:46", "remaining_time": "1 day, 0:07:53", "throughput": 558.18, "total_tokens": 16871552} {"current_steps": 10330, "total_steps": 40000, "loss": 0.1338, "lr": 4.2215035228970005e-05, "epoch": 0.4676429978043867, "percentage": 25.82, "elapsed_time": "8:23:49", "remaining_time": "1 day, 0:07:05", "throughput": 558.39, "total_tokens": 16879744} {"current_steps": 10335, "total_steps": 40000, "loss": 0.1083, "lr": 4.2207914855923464e-05, "epoch": 0.46786934969102967, "percentage": 25.84, "elapsed_time": "8:23:52", "remaining_time": "1 day, 0:06:18", "throughput": 558.62, "total_tokens": 16888480} {"current_steps": 10340, "total_steps": 40000, "loss": 0.124, "lr": 4.220079182920021e-05, "epoch": 0.46809570157767266, "percentage": 25.85, "elapsed_time": "8:23:55", "remaining_time": "1 day, 0:05:30", "throughput": 558.83, "total_tokens": 16896736} {"current_steps": 10345, "total_steps": 40000, "loss": 0.1562, "lr": 4.2193666149898705e-05, "epoch": 0.4683220534643156, "percentage": 25.86, "elapsed_time": "8:23:59", "remaining_time": "1 day, 0:04:44", "throughput": 559.08, "total_tokens": 16906272} {"current_steps": 10350, "total_steps": 40000, "loss": 0.083, "lr": 4.21865378191178e-05, "epoch": 0.4685484053509586, "percentage": 25.87, "elapsed_time": "8:24:02", "remaining_time": "1 day, 0:03:57", "throughput": 559.3, "total_tokens": 16914752} {"current_steps": 10355, "total_steps": 40000, "loss": 0.1319, "lr": 4.217940683795678e-05, "epoch": 0.4687747572376016, "percentage": 25.89, "elapsed_time": "8:24:05", "remaining_time": "1 day, 0:03:09", "throughput": 559.52, "total_tokens": 16923136} {"current_steps": 10360, "total_steps": 40000, "loss": 0.1636, "lr": 4.217227320751534e-05, "epoch": 0.46900110912424453, "percentage": 25.9, "elapsed_time": "8:24:09", "remaining_time": "1 day, 0:02:22", "throughput": 559.73, "total_tokens": 16931232} {"current_steps": 10365, "total_steps": 40000, "loss": 0.0903, "lr": 4.216513692889358e-05, "epoch": 0.4692274610108875, "percentage": 25.91, "elapsed_time": "8:24:12", "remaining_time": "1 day, 0:01:35", "throughput": 559.94, "total_tokens": 16939424} {"current_steps": 10370, "total_steps": 40000, "loss": 0.1236, "lr": 4.215799800319199e-05, "epoch": 0.4694538128975305, "percentage": 25.92, "elapsed_time": "8:24:15", "remaining_time": "1 day, 0:00:48", "throughput": 560.17, "total_tokens": 16948192} {"current_steps": 10375, "total_steps": 40000, "loss": 0.1617, "lr": 4.2150856431511485e-05, "epoch": 0.46968016478417346, "percentage": 25.94, "elapsed_time": "8:24:18", "remaining_time": "1 day, 0:00:01", "throughput": 560.38, "total_tokens": 16956512} {"current_steps": 10380, "total_steps": 40000, "loss": 0.0941, "lr": 4.214371221495339e-05, "epoch": 0.46990651667081645, "percentage": 25.95, "elapsed_time": "8:24:22", "remaining_time": "23:59:14", "throughput": 560.62, "total_tokens": 16965472} {"current_steps": 10385, "total_steps": 40000, "loss": 0.1231, "lr": 4.213656535461942e-05, "epoch": 0.47013286855745945, "percentage": 25.96, "elapsed_time": "8:24:25", "remaining_time": "23:58:27", "throughput": 560.83, "total_tokens": 16973664} {"current_steps": 10390, "total_steps": 40000, "loss": 0.1514, "lr": 4.2129415851611734e-05, "epoch": 0.4703592204441024, "percentage": 25.97, "elapsed_time": "8:24:28", "remaining_time": "23:57:40", "throughput": 561.04, "total_tokens": 16981888} {"current_steps": 10395, "total_steps": 40000, "loss": 0.0987, "lr": 4.2122263707032855e-05, "epoch": 0.4705855723307454, "percentage": 25.99, "elapsed_time": "8:24:31", "remaining_time": "23:56:54", "throughput": 561.27, "total_tokens": 16990720} {"current_steps": 10400, "total_steps": 40000, "loss": 0.1504, "lr": 4.211510892198574e-05, "epoch": 0.4708119242173884, "percentage": 26.0, "elapsed_time": "8:24:34", "remaining_time": "23:56:07", "throughput": 561.48, "total_tokens": 16998848} {"current_steps": 10400, "total_steps": 40000, "eval_loss": 0.13937310874462128, "epoch": 0.4708119242173884, "percentage": 26.0, "elapsed_time": "8:32:17", "remaining_time": "1 day, 0:18:04", "throughput": 553.03, "total_tokens": 16998848} {"current_steps": 10405, "total_steps": 40000, "loss": 0.1675, "lr": 4.210795149757375e-05, "epoch": 0.4710382761040313, "percentage": 26.01, "elapsed_time": "8:32:21", "remaining_time": "1 day, 0:17:18", "throughput": 553.23, "total_tokens": 17007136} {"current_steps": 10410, "total_steps": 40000, "loss": 0.1431, "lr": 4.210079143490065e-05, "epoch": 0.4712646279906743, "percentage": 26.02, "elapsed_time": "8:32:24", "remaining_time": "1 day, 0:16:30", "throughput": 553.43, "total_tokens": 17014976} {"current_steps": 10415, "total_steps": 40000, "loss": 0.1568, "lr": 4.2093628735070604e-05, "epoch": 0.47149097987731725, "percentage": 26.04, "elapsed_time": "8:32:28", "remaining_time": "1 day, 0:15:43", "throughput": 553.65, "total_tokens": 17023712} {"current_steps": 10420, "total_steps": 40000, "loss": 0.0998, "lr": 4.208646339918819e-05, "epoch": 0.47171733176396025, "percentage": 26.05, "elapsed_time": "8:32:31", "remaining_time": "1 day, 0:14:55", "throughput": 553.86, "total_tokens": 17032000} {"current_steps": 10425, "total_steps": 40000, "loss": 0.1023, "lr": 4.2079295428358414e-05, "epoch": 0.47194368365060324, "percentage": 26.06, "elapsed_time": "8:32:34", "remaining_time": "1 day, 0:14:07", "throughput": 554.04, "total_tokens": 17039136} {"current_steps": 10430, "total_steps": 40000, "loss": 0.1252, "lr": 4.207212482368664e-05, "epoch": 0.4721700355372462, "percentage": 26.07, "elapsed_time": "8:32:37", "remaining_time": "1 day, 0:13:20", "throughput": 554.26, "total_tokens": 17047552} {"current_steps": 10435, "total_steps": 40000, "loss": 0.0896, "lr": 4.206495158627867e-05, "epoch": 0.4723963874238892, "percentage": 26.09, "elapsed_time": "8:32:40", "remaining_time": "1 day, 0:12:32", "throughput": 554.46, "total_tokens": 17055520} {"current_steps": 10440, "total_steps": 40000, "loss": 0.1254, "lr": 4.205777571724073e-05, "epoch": 0.47262273931053217, "percentage": 26.1, "elapsed_time": "8:32:43", "remaining_time": "1 day, 0:11:45", "throughput": 554.66, "total_tokens": 17063488} {"current_steps": 10445, "total_steps": 40000, "loss": 0.1877, "lr": 4.20505972176794e-05, "epoch": 0.4728490911971751, "percentage": 26.11, "elapsed_time": "8:32:47", "remaining_time": "1 day, 0:10:57", "throughput": 554.87, "total_tokens": 17071712} {"current_steps": 10450, "total_steps": 40000, "loss": 0.172, "lr": 4.204341608870171e-05, "epoch": 0.4730754430838181, "percentage": 26.12, "elapsed_time": "8:32:50", "remaining_time": "1 day, 0:10:10", "throughput": 555.06, "total_tokens": 17079360} {"current_steps": 10455, "total_steps": 40000, "loss": 0.1234, "lr": 4.203623233141508e-05, "epoch": 0.4733017949704611, "percentage": 26.14, "elapsed_time": "8:32:53", "remaining_time": "1 day, 0:09:22", "throughput": 555.26, "total_tokens": 17087328} {"current_steps": 10460, "total_steps": 40000, "loss": 0.1123, "lr": 4.2029045946927334e-05, "epoch": 0.47352814685710404, "percentage": 26.15, "elapsed_time": "8:32:56", "remaining_time": "1 day, 0:08:35", "throughput": 555.48, "total_tokens": 17095680} {"current_steps": 10465, "total_steps": 40000, "loss": 0.1424, "lr": 4.20218569363467e-05, "epoch": 0.47375449874374703, "percentage": 26.16, "elapsed_time": "8:32:59", "remaining_time": "1 day, 0:07:48", "throughput": 555.7, "total_tokens": 17104384} {"current_steps": 10470, "total_steps": 40000, "loss": 0.1628, "lr": 4.2014665300781834e-05, "epoch": 0.47398085063039, "percentage": 26.17, "elapsed_time": "8:33:02", "remaining_time": "1 day, 0:07:01", "throughput": 555.9, "total_tokens": 17112032} {"current_steps": 10475, "total_steps": 40000, "loss": 0.122, "lr": 4.200747104134174e-05, "epoch": 0.47420720251703297, "percentage": 26.19, "elapsed_time": "8:33:06", "remaining_time": "1 day, 0:06:14", "throughput": 556.11, "total_tokens": 17120416} {"current_steps": 10480, "total_steps": 40000, "loss": 0.1193, "lr": 4.200027415913588e-05, "epoch": 0.47443355440367596, "percentage": 26.2, "elapsed_time": "8:33:09", "remaining_time": "1 day, 0:05:26", "throughput": 556.32, "total_tokens": 17128544} {"current_steps": 10485, "total_steps": 40000, "loss": 0.1598, "lr": 4.1993074655274126e-05, "epoch": 0.47465990629031896, "percentage": 26.21, "elapsed_time": "8:33:12", "remaining_time": "1 day, 0:04:39", "throughput": 556.53, "total_tokens": 17137024} {"current_steps": 10490, "total_steps": 40000, "loss": 0.1054, "lr": 4.198587253086669e-05, "epoch": 0.4748862581769619, "percentage": 26.22, "elapsed_time": "8:33:15", "remaining_time": "1 day, 0:03:52", "throughput": 556.72, "total_tokens": 17144576} {"current_steps": 10495, "total_steps": 40000, "loss": 0.1083, "lr": 4.197866778702426e-05, "epoch": 0.4751126100636049, "percentage": 26.24, "elapsed_time": "8:33:18", "remaining_time": "1 day, 0:03:05", "throughput": 556.93, "total_tokens": 17152864} {"current_steps": 10500, "total_steps": 40000, "loss": 0.1291, "lr": 4.197146042485789e-05, "epoch": 0.47533896195024783, "percentage": 26.25, "elapsed_time": "8:33:21", "remaining_time": "1 day, 0:02:18", "throughput": 557.13, "total_tokens": 17160672} {"current_steps": 10505, "total_steps": 40000, "loss": 0.137, "lr": 4.1964250445479046e-05, "epoch": 0.4755653138368908, "percentage": 26.26, "elapsed_time": "8:33:25", "remaining_time": "1 day, 0:01:31", "throughput": 557.36, "total_tokens": 17169664} {"current_steps": 10510, "total_steps": 40000, "loss": 0.1304, "lr": 4.19570378499996e-05, "epoch": 0.4757916657235338, "percentage": 26.27, "elapsed_time": "8:33:28", "remaining_time": "1 day, 0:00:45", "throughput": 557.58, "total_tokens": 17177984} {"current_steps": 10515, "total_steps": 40000, "loss": 0.1335, "lr": 4.194982263953182e-05, "epoch": 0.47601801761017676, "percentage": 26.29, "elapsed_time": "8:33:31", "remaining_time": "23:59:58", "throughput": 557.77, "total_tokens": 17185824} {"current_steps": 10520, "total_steps": 40000, "loss": 0.0819, "lr": 4.194260481518838e-05, "epoch": 0.47624436949681975, "percentage": 26.3, "elapsed_time": "8:33:34", "remaining_time": "23:59:11", "throughput": 557.97, "total_tokens": 17193792} {"current_steps": 10525, "total_steps": 40000, "loss": 0.107, "lr": 4.1935384378082366e-05, "epoch": 0.47647072138346275, "percentage": 26.31, "elapsed_time": "8:33:37", "remaining_time": "23:58:24", "throughput": 558.18, "total_tokens": 17202048} {"current_steps": 10530, "total_steps": 40000, "loss": 0.1357, "lr": 4.1928161329327267e-05, "epoch": 0.4766970732701057, "percentage": 26.32, "elapsed_time": "8:33:40", "remaining_time": "23:57:37", "throughput": 558.37, "total_tokens": 17209600} {"current_steps": 10535, "total_steps": 40000, "loss": 0.1382, "lr": 4.1920935670036945e-05, "epoch": 0.4769234251567487, "percentage": 26.34, "elapsed_time": "8:33:43", "remaining_time": "23:56:50", "throughput": 558.55, "total_tokens": 17216800} {"current_steps": 10540, "total_steps": 40000, "loss": 0.1345, "lr": 4.1913707401325705e-05, "epoch": 0.4771497770433917, "percentage": 26.35, "elapsed_time": "8:33:47", "remaining_time": "23:56:04", "throughput": 558.77, "total_tokens": 17225184} {"current_steps": 10545, "total_steps": 40000, "loss": 0.1392, "lr": 4.1906476524308235e-05, "epoch": 0.4773761289300346, "percentage": 26.36, "elapsed_time": "8:33:50", "remaining_time": "23:55:17", "throughput": 558.95, "total_tokens": 17232736} {"current_steps": 10550, "total_steps": 40000, "loss": 0.102, "lr": 4.189924304009962e-05, "epoch": 0.4776024808166776, "percentage": 26.38, "elapsed_time": "8:33:53", "remaining_time": "23:54:30", "throughput": 559.16, "total_tokens": 17240928} {"current_steps": 10555, "total_steps": 40000, "loss": 0.1322, "lr": 4.189200694981537e-05, "epoch": 0.4778288327033206, "percentage": 26.39, "elapsed_time": "8:33:56", "remaining_time": "23:53:44", "throughput": 559.37, "total_tokens": 17248960} {"current_steps": 10560, "total_steps": 40000, "loss": 0.1214, "lr": 4.188476825457136e-05, "epoch": 0.47805518458996354, "percentage": 26.4, "elapsed_time": "8:33:59", "remaining_time": "23:52:57", "throughput": 559.57, "total_tokens": 17257056} {"current_steps": 10565, "total_steps": 40000, "loss": 0.0986, "lr": 4.18775269554839e-05, "epoch": 0.47828153647660654, "percentage": 26.41, "elapsed_time": "8:34:03", "remaining_time": "23:52:11", "throughput": 559.79, "total_tokens": 17265696} {"current_steps": 10570, "total_steps": 40000, "loss": 0.1043, "lr": 4.187028305366969e-05, "epoch": 0.47850788836324953, "percentage": 26.42, "elapsed_time": "8:34:06", "remaining_time": "23:51:25", "throughput": 560.02, "total_tokens": 17274656} {"current_steps": 10575, "total_steps": 40000, "loss": 0.1137, "lr": 4.1863036550245824e-05, "epoch": 0.4787342402498925, "percentage": 26.44, "elapsed_time": "8:34:09", "remaining_time": "23:50:39", "throughput": 560.23, "total_tokens": 17282816} {"current_steps": 10580, "total_steps": 40000, "loss": 0.1965, "lr": 4.1855787446329806e-05, "epoch": 0.47896059213653547, "percentage": 26.45, "elapsed_time": "8:34:12", "remaining_time": "23:49:52", "throughput": 560.44, "total_tokens": 17290944} {"current_steps": 10585, "total_steps": 40000, "loss": 0.1154, "lr": 4.184853574303955e-05, "epoch": 0.4791869440231784, "percentage": 26.46, "elapsed_time": "8:34:15", "remaining_time": "23:49:06", "throughput": 560.65, "total_tokens": 17299328} {"current_steps": 10590, "total_steps": 40000, "loss": 0.2029, "lr": 4.184128144149334e-05, "epoch": 0.4794132959098214, "percentage": 26.47, "elapsed_time": "8:34:19", "remaining_time": "23:48:20", "throughput": 560.87, "total_tokens": 17308128} {"current_steps": 10595, "total_steps": 40000, "loss": 0.1328, "lr": 4.1834024542809896e-05, "epoch": 0.4796396477964644, "percentage": 26.49, "elapsed_time": "8:34:22", "remaining_time": "23:47:34", "throughput": 561.07, "total_tokens": 17316032} {"current_steps": 10600, "total_steps": 40000, "loss": 0.1616, "lr": 4.1826765048108315e-05, "epoch": 0.47986599968310734, "percentage": 26.5, "elapsed_time": "8:34:25", "remaining_time": "23:46:48", "throughput": 561.27, "total_tokens": 17323904} {"current_steps": 10600, "total_steps": 40000, "eval_loss": 0.13843144476413727, "epoch": 0.47986599968310734, "percentage": 26.5, "elapsed_time": "8:42:08", "remaining_time": "1 day, 0:08:11", "throughput": 552.98, "total_tokens": 17323904} {"current_steps": 10605, "total_steps": 40000, "loss": 0.1386, "lr": 4.181950295850811e-05, "epoch": 0.48009235156975033, "percentage": 26.51, "elapsed_time": "8:42:13", "remaining_time": "1 day, 0:07:30", "throughput": 553.17, "total_tokens": 17332800} {"current_steps": 10610, "total_steps": 40000, "loss": 0.1432, "lr": 4.181223827512918e-05, "epoch": 0.4803187034563933, "percentage": 26.52, "elapsed_time": "8:42:16", "remaining_time": "1 day, 0:06:44", "throughput": 553.38, "total_tokens": 17341184} {"current_steps": 10615, "total_steps": 40000, "loss": 0.1135, "lr": 4.180497099909183e-05, "epoch": 0.48054505534303626, "percentage": 26.54, "elapsed_time": "8:42:19", "remaining_time": "1 day, 0:05:56", "throughput": 553.57, "total_tokens": 17348928} {"current_steps": 10620, "total_steps": 40000, "loss": 0.1102, "lr": 4.179770113151677e-05, "epoch": 0.48077140722967926, "percentage": 26.55, "elapsed_time": "8:42:23", "remaining_time": "1 day, 0:05:10", "throughput": 553.78, "total_tokens": 17357312} {"current_steps": 10625, "total_steps": 40000, "loss": 0.1731, "lr": 4.179042867352511e-05, "epoch": 0.48099775911632225, "percentage": 26.56, "elapsed_time": "8:42:26", "remaining_time": "1 day, 0:04:23", "throughput": 554.0, "total_tokens": 17365856} {"current_steps": 10630, "total_steps": 40000, "loss": 0.1274, "lr": 4.1783153626238334e-05, "epoch": 0.4812241110029652, "percentage": 26.57, "elapsed_time": "8:42:29", "remaining_time": "1 day, 0:03:36", "throughput": 554.2, "total_tokens": 17373920} {"current_steps": 10635, "total_steps": 40000, "loss": 0.1655, "lr": 4.177587599077836e-05, "epoch": 0.4814504628896082, "percentage": 26.59, "elapsed_time": "8:42:32", "remaining_time": "1 day, 0:02:50", "throughput": 554.4, "total_tokens": 17381952} {"current_steps": 10640, "total_steps": 40000, "loss": 0.1383, "lr": 4.1768595768267494e-05, "epoch": 0.4816768147762512, "percentage": 26.6, "elapsed_time": "8:42:35", "remaining_time": "1 day, 0:02:03", "throughput": 554.6, "total_tokens": 17390144} {"current_steps": 10645, "total_steps": 40000, "loss": 0.1264, "lr": 4.176131295982843e-05, "epoch": 0.4819031666628941, "percentage": 26.61, "elapsed_time": "8:42:39", "remaining_time": "1 day, 0:01:17", "throughput": 554.82, "total_tokens": 17398560} {"current_steps": 10650, "total_steps": 40000, "loss": 0.1416, "lr": 4.1754027566584276e-05, "epoch": 0.4821295185495371, "percentage": 26.62, "elapsed_time": "8:42:42", "remaining_time": "1 day, 0:00:30", "throughput": 555.04, "total_tokens": 17407296} {"current_steps": 10655, "total_steps": 40000, "loss": 0.1587, "lr": 4.174673958965852e-05, "epoch": 0.4823558704361801, "percentage": 26.64, "elapsed_time": "8:42:45", "remaining_time": "23:59:44", "throughput": 555.24, "total_tokens": 17415328} {"current_steps": 10660, "total_steps": 40000, "loss": 0.14, "lr": 4.173944903017507e-05, "epoch": 0.48258222232282305, "percentage": 26.65, "elapsed_time": "8:42:48", "remaining_time": "23:58:57", "throughput": 555.43, "total_tokens": 17423136} {"current_steps": 10665, "total_steps": 40000, "loss": 0.1735, "lr": 4.173215588925822e-05, "epoch": 0.48280857420946605, "percentage": 26.66, "elapsed_time": "8:42:51", "remaining_time": "23:58:10", "throughput": 555.63, "total_tokens": 17431264} {"current_steps": 10670, "total_steps": 40000, "loss": 0.1349, "lr": 4.172486016803266e-05, "epoch": 0.483034926096109, "percentage": 26.67, "elapsed_time": "8:42:55", "remaining_time": "23:57:24", "throughput": 555.83, "total_tokens": 17439296} {"current_steps": 10675, "total_steps": 40000, "loss": 0.1644, "lr": 4.171756186762349e-05, "epoch": 0.483261277982752, "percentage": 26.69, "elapsed_time": "8:42:58", "remaining_time": "23:56:38", "throughput": 556.05, "total_tokens": 17447936} {"current_steps": 10680, "total_steps": 40000, "loss": 0.094, "lr": 4.171026098915619e-05, "epoch": 0.483487629869395, "percentage": 26.7, "elapsed_time": "8:43:01", "remaining_time": "23:55:51", "throughput": 556.23, "total_tokens": 17455296} {"current_steps": 10685, "total_steps": 40000, "loss": 0.1134, "lr": 4.170295753375665e-05, "epoch": 0.4837139817560379, "percentage": 26.71, "elapsed_time": "8:43:04", "remaining_time": "23:55:05", "throughput": 556.44, "total_tokens": 17463552} {"current_steps": 10690, "total_steps": 40000, "loss": 0.096, "lr": 4.169565150255117e-05, "epoch": 0.4839403336426809, "percentage": 26.72, "elapsed_time": "8:43:07", "remaining_time": "23:54:19", "throughput": 556.65, "total_tokens": 17472128} {"current_steps": 10695, "total_steps": 40000, "loss": 0.1351, "lr": 4.16883428966664e-05, "epoch": 0.4841666855293239, "percentage": 26.74, "elapsed_time": "8:43:10", "remaining_time": "23:53:32", "throughput": 556.85, "total_tokens": 17479936} {"current_steps": 10700, "total_steps": 40000, "loss": 0.134, "lr": 4.168103171722944e-05, "epoch": 0.48439303741596684, "percentage": 26.75, "elapsed_time": "8:43:14", "remaining_time": "23:52:46", "throughput": 557.04, "total_tokens": 17487872} {"current_steps": 10705, "total_steps": 40000, "loss": 0.1354, "lr": 4.167371796536777e-05, "epoch": 0.48461938930260984, "percentage": 26.76, "elapsed_time": "8:43:17", "remaining_time": "23:52:00", "throughput": 557.27, "total_tokens": 17496768} {"current_steps": 10710, "total_steps": 40000, "loss": 0.1033, "lr": 4.166640164220924e-05, "epoch": 0.48484574118925283, "percentage": 26.77, "elapsed_time": "8:43:20", "remaining_time": "23:51:14", "throughput": 557.47, "total_tokens": 17504928} {"current_steps": 10715, "total_steps": 40000, "loss": 0.147, "lr": 4.1659082748882144e-05, "epoch": 0.48507209307589577, "percentage": 26.79, "elapsed_time": "8:43:23", "remaining_time": "23:50:28", "throughput": 557.66, "total_tokens": 17512544} {"current_steps": 10720, "total_steps": 40000, "loss": 0.1287, "lr": 4.1651761286515135e-05, "epoch": 0.48529844496253877, "percentage": 26.8, "elapsed_time": "8:43:26", "remaining_time": "23:49:42", "throughput": 557.87, "total_tokens": 17520960} {"current_steps": 10725, "total_steps": 40000, "loss": 0.1628, "lr": 4.164443725623728e-05, "epoch": 0.48552479684918176, "percentage": 26.81, "elapsed_time": "8:43:30", "remaining_time": "23:48:57", "throughput": 558.08, "total_tokens": 17529376} {"current_steps": 10730, "total_steps": 40000, "loss": 0.149, "lr": 4.163711065917802e-05, "epoch": 0.4857511487358247, "percentage": 26.82, "elapsed_time": "8:43:33", "remaining_time": "23:48:10", "throughput": 558.26, "total_tokens": 17536736} {"current_steps": 10735, "total_steps": 40000, "loss": 0.1658, "lr": 4.1629781496467234e-05, "epoch": 0.4859775006224677, "percentage": 26.84, "elapsed_time": "8:43:36", "remaining_time": "23:47:24", "throughput": 558.46, "total_tokens": 17544800} {"current_steps": 10740, "total_steps": 40000, "loss": 0.1008, "lr": 4.1622449769235164e-05, "epoch": 0.4862038525091107, "percentage": 26.85, "elapsed_time": "8:43:39", "remaining_time": "23:46:38", "throughput": 558.64, "total_tokens": 17552256} {"current_steps": 10745, "total_steps": 40000, "loss": 0.1283, "lr": 4.161511547861243e-05, "epoch": 0.48643020439575363, "percentage": 26.86, "elapsed_time": "8:43:42", "remaining_time": "23:45:52", "throughput": 558.84, "total_tokens": 17560160} {"current_steps": 10750, "total_steps": 40000, "loss": 0.1147, "lr": 4.1607778625730104e-05, "epoch": 0.4866565562823966, "percentage": 26.88, "elapsed_time": "8:43:45", "remaining_time": "23:45:07", "throughput": 559.03, "total_tokens": 17568000} {"current_steps": 10755, "total_steps": 40000, "loss": 0.1459, "lr": 4.160043921171961e-05, "epoch": 0.48688290816903956, "percentage": 26.89, "elapsed_time": "8:43:48", "remaining_time": "23:44:21", "throughput": 559.25, "total_tokens": 17576576} {"current_steps": 10760, "total_steps": 40000, "loss": 0.1386, "lr": 4.159309723771276e-05, "epoch": 0.48710926005568256, "percentage": 26.9, "elapsed_time": "8:43:52", "remaining_time": "23:43:35", "throughput": 559.44, "total_tokens": 17584448} {"current_steps": 10765, "total_steps": 40000, "loss": 0.0831, "lr": 4.158575270484181e-05, "epoch": 0.48733561194232555, "percentage": 26.91, "elapsed_time": "8:43:55", "remaining_time": "23:42:50", "throughput": 559.65, "total_tokens": 17592736} {"current_steps": 10770, "total_steps": 40000, "loss": 0.1324, "lr": 4.157840561423936e-05, "epoch": 0.4875619638289685, "percentage": 26.92, "elapsed_time": "8:43:58", "remaining_time": "23:42:04", "throughput": 559.84, "total_tokens": 17600352} {"current_steps": 10775, "total_steps": 40000, "loss": 0.1048, "lr": 4.1571055967038416e-05, "epoch": 0.4877883157156115, "percentage": 26.94, "elapsed_time": "8:44:01", "remaining_time": "23:41:18", "throughput": 560.04, "total_tokens": 17608480} {"current_steps": 10780, "total_steps": 40000, "loss": 0.1153, "lr": 4.156370376437241e-05, "epoch": 0.4880146676022545, "percentage": 26.95, "elapsed_time": "8:44:04", "remaining_time": "23:40:33", "throughput": 560.26, "total_tokens": 17617184} {"current_steps": 10785, "total_steps": 40000, "loss": 0.1272, "lr": 4.155634900737513e-05, "epoch": 0.4882410194888974, "percentage": 26.96, "elapsed_time": "8:44:08", "remaining_time": "23:39:48", "throughput": 560.46, "total_tokens": 17625376} {"current_steps": 10790, "total_steps": 40000, "loss": 0.1361, "lr": 4.1548991697180764e-05, "epoch": 0.4884673713755404, "percentage": 26.97, "elapsed_time": "8:44:11", "remaining_time": "23:39:03", "throughput": 560.67, "total_tokens": 17634048} {"current_steps": 10795, "total_steps": 40000, "loss": 0.1848, "lr": 4.1541631834923914e-05, "epoch": 0.4886937232621834, "percentage": 26.99, "elapsed_time": "8:44:14", "remaining_time": "23:38:18", "throughput": 560.88, "total_tokens": 17642464} {"current_steps": 10800, "total_steps": 40000, "loss": 0.1605, "lr": 4.153426942173956e-05, "epoch": 0.48892007514882635, "percentage": 27.0, "elapsed_time": "8:44:17", "remaining_time": "23:37:32", "throughput": 561.09, "total_tokens": 17650528} {"current_steps": 10800, "total_steps": 40000, "eval_loss": 0.137339249253273, "epoch": 0.48892007514882635, "percentage": 27.0, "elapsed_time": "8:52:00", "remaining_time": "23:58:23", "throughput": 552.95, "total_tokens": 17650528} {"current_steps": 10805, "total_steps": 40000, "loss": 0.0861, "lr": 4.152690445876308e-05, "epoch": 0.48914642703546934, "percentage": 27.01, "elapsed_time": "8:52:04", "remaining_time": "23:57:39", "throughput": 553.15, "total_tokens": 17658848} {"current_steps": 10810, "total_steps": 40000, "loss": 0.0875, "lr": 4.1519536947130245e-05, "epoch": 0.48937277892211234, "percentage": 27.02, "elapsed_time": "8:52:07", "remaining_time": "23:56:53", "throughput": 553.37, "total_tokens": 17667744} {"current_steps": 10815, "total_steps": 40000, "loss": 0.0941, "lr": 4.151216688797722e-05, "epoch": 0.4895991308087553, "percentage": 27.04, "elapsed_time": "8:52:10", "remaining_time": "23:56:07", "throughput": 553.55, "total_tokens": 17675296} {"current_steps": 10820, "total_steps": 40000, "loss": 0.1618, "lr": 4.150479428244054e-05, "epoch": 0.4898254826953983, "percentage": 27.05, "elapsed_time": "8:52:13", "remaining_time": "23:55:21", "throughput": 553.75, "total_tokens": 17683360} {"current_steps": 10825, "total_steps": 40000, "loss": 0.1111, "lr": 4.1497419131657176e-05, "epoch": 0.49005183458204127, "percentage": 27.06, "elapsed_time": "8:52:17", "remaining_time": "23:54:35", "throughput": 553.93, "total_tokens": 17690912} {"current_steps": 10830, "total_steps": 40000, "loss": 0.1742, "lr": 4.149004143676447e-05, "epoch": 0.4902781864686842, "percentage": 27.07, "elapsed_time": "8:52:20", "remaining_time": "23:53:49", "throughput": 554.13, "total_tokens": 17698880} {"current_steps": 10835, "total_steps": 40000, "loss": 0.1668, "lr": 4.148266119890015e-05, "epoch": 0.4905045383553272, "percentage": 27.09, "elapsed_time": "8:52:23", "remaining_time": "23:53:03", "throughput": 554.32, "total_tokens": 17707040} {"current_steps": 10840, "total_steps": 40000, "loss": 0.1154, "lr": 4.1475278419202324e-05, "epoch": 0.49073089024197014, "percentage": 27.1, "elapsed_time": "8:52:26", "remaining_time": "23:52:17", "throughput": 554.53, "total_tokens": 17715520} {"current_steps": 10845, "total_steps": 40000, "loss": 0.1427, "lr": 4.146789309880953e-05, "epoch": 0.49095724212861314, "percentage": 27.11, "elapsed_time": "8:52:29", "remaining_time": "23:51:32", "throughput": 554.74, "total_tokens": 17723808} {"current_steps": 10850, "total_steps": 40000, "loss": 0.2276, "lr": 4.146050523886068e-05, "epoch": 0.49118359401525613, "percentage": 27.12, "elapsed_time": "8:52:33", "remaining_time": "23:50:46", "throughput": 554.94, "total_tokens": 17731968} {"current_steps": 10855, "total_steps": 40000, "loss": 0.1747, "lr": 4.1453114840495055e-05, "epoch": 0.49140994590189907, "percentage": 27.14, "elapsed_time": "8:52:36", "remaining_time": "23:50:00", "throughput": 555.15, "total_tokens": 17740480} {"current_steps": 10860, "total_steps": 40000, "loss": 0.1332, "lr": 4.1445721904852364e-05, "epoch": 0.49163629778854206, "percentage": 27.15, "elapsed_time": "8:52:39", "remaining_time": "23:49:15", "throughput": 555.35, "total_tokens": 17748800} {"current_steps": 10865, "total_steps": 40000, "loss": 0.1353, "lr": 4.143832643307269e-05, "epoch": 0.49186264967518506, "percentage": 27.16, "elapsed_time": "8:52:42", "remaining_time": "23:48:30", "throughput": 555.59, "total_tokens": 17758240} {"current_steps": 10870, "total_steps": 40000, "loss": 0.1149, "lr": 4.1430928426296503e-05, "epoch": 0.492089001561828, "percentage": 27.18, "elapsed_time": "8:52:46", "remaining_time": "23:47:44", "throughput": 555.78, "total_tokens": 17766112} {"current_steps": 10875, "total_steps": 40000, "loss": 0.1512, "lr": 4.142352788566466e-05, "epoch": 0.492315353448471, "percentage": 27.19, "elapsed_time": "8:52:49", "remaining_time": "23:46:58", "throughput": 555.96, "total_tokens": 17773760} {"current_steps": 10880, "total_steps": 40000, "loss": 0.1062, "lr": 4.1416124812318424e-05, "epoch": 0.492541705335114, "percentage": 27.2, "elapsed_time": "8:52:52", "remaining_time": "23:46:13", "throughput": 556.16, "total_tokens": 17781824} {"current_steps": 10885, "total_steps": 40000, "loss": 0.1227, "lr": 4.1408719207399453e-05, "epoch": 0.4927680572217569, "percentage": 27.21, "elapsed_time": "8:52:55", "remaining_time": "23:45:28", "throughput": 556.39, "total_tokens": 17790912} {"current_steps": 10890, "total_steps": 40000, "loss": 0.1315, "lr": 4.140131107204978e-05, "epoch": 0.4929944091083999, "percentage": 27.22, "elapsed_time": "8:52:59", "remaining_time": "23:44:42", "throughput": 556.6, "total_tokens": 17799488} {"current_steps": 10895, "total_steps": 40000, "loss": 0.1398, "lr": 4.139390040741182e-05, "epoch": 0.4932207609950429, "percentage": 27.24, "elapsed_time": "8:53:02", "remaining_time": "23:43:57", "throughput": 556.79, "total_tokens": 17807232} {"current_steps": 10900, "total_steps": 40000, "loss": 0.11, "lr": 4.1386487214628396e-05, "epoch": 0.49344711288168586, "percentage": 27.25, "elapsed_time": "8:53:05", "remaining_time": "23:43:11", "throughput": 556.97, "total_tokens": 17815008} {"current_steps": 10905, "total_steps": 40000, "loss": 0.1208, "lr": 4.137907149484272e-05, "epoch": 0.49367346476832885, "percentage": 27.26, "elapsed_time": "8:53:08", "remaining_time": "23:42:26", "throughput": 557.2, "total_tokens": 17823904} {"current_steps": 10910, "total_steps": 40000, "loss": 0.1248, "lr": 4.137165324919839e-05, "epoch": 0.49389981665497185, "percentage": 27.27, "elapsed_time": "8:53:11", "remaining_time": "23:41:41", "throughput": 557.38, "total_tokens": 17831680} {"current_steps": 10915, "total_steps": 40000, "loss": 0.1812, "lr": 4.136423247883939e-05, "epoch": 0.4941261685416148, "percentage": 27.29, "elapsed_time": "8:53:14", "remaining_time": "23:40:56", "throughput": 557.57, "total_tokens": 17839520} {"current_steps": 10920, "total_steps": 40000, "loss": 0.1655, "lr": 4.135680918491009e-05, "epoch": 0.4943525204282578, "percentage": 27.3, "elapsed_time": "8:53:17", "remaining_time": "23:40:10", "throughput": 557.76, "total_tokens": 17847328} {"current_steps": 10925, "total_steps": 40000, "loss": 0.1112, "lr": 4.1349383368555265e-05, "epoch": 0.4945788723149007, "percentage": 27.31, "elapsed_time": "8:53:21", "remaining_time": "23:39:25", "throughput": 557.98, "total_tokens": 17856128} {"current_steps": 10930, "total_steps": 40000, "loss": 0.1591, "lr": 4.1341955030920065e-05, "epoch": 0.4948052242015437, "percentage": 27.32, "elapsed_time": "8:53:24", "remaining_time": "23:38:40", "throughput": 558.18, "total_tokens": 17864288} {"current_steps": 10935, "total_steps": 40000, "loss": 0.1187, "lr": 4.1334524173150036e-05, "epoch": 0.4950315760881867, "percentage": 27.34, "elapsed_time": "8:53:27", "remaining_time": "23:37:55", "throughput": 558.39, "total_tokens": 17872928} {"current_steps": 10940, "total_steps": 40000, "loss": 0.1467, "lr": 4.13270907963911e-05, "epoch": 0.49525792797482965, "percentage": 27.35, "elapsed_time": "8:53:30", "remaining_time": "23:37:10", "throughput": 558.59, "total_tokens": 17880864} {"current_steps": 10945, "total_steps": 40000, "loss": 0.1184, "lr": 4.131965490178959e-05, "epoch": 0.49548427986147264, "percentage": 27.36, "elapsed_time": "8:53:34", "remaining_time": "23:36:25", "throughput": 558.79, "total_tokens": 17889280} {"current_steps": 10950, "total_steps": 40000, "loss": 0.1506, "lr": 4.131221649049222e-05, "epoch": 0.49571063174811564, "percentage": 27.38, "elapsed_time": "8:53:37", "remaining_time": "23:35:40", "throughput": 558.99, "total_tokens": 17897376} {"current_steps": 10955, "total_steps": 40000, "loss": 0.1856, "lr": 4.130477556364606e-05, "epoch": 0.4959369836347586, "percentage": 27.39, "elapsed_time": "8:53:40", "remaining_time": "23:34:55", "throughput": 559.18, "total_tokens": 17905280} {"current_steps": 10960, "total_steps": 40000, "loss": 0.1291, "lr": 4.129733212239861e-05, "epoch": 0.49616333552140157, "percentage": 27.4, "elapsed_time": "8:53:43", "remaining_time": "23:34:10", "throughput": 559.38, "total_tokens": 17913376} {"current_steps": 10965, "total_steps": 40000, "loss": 0.1644, "lr": 4.128988616789774e-05, "epoch": 0.49638968740804457, "percentage": 27.41, "elapsed_time": "8:53:46", "remaining_time": "23:33:26", "throughput": 559.61, "total_tokens": 17922560} {"current_steps": 10970, "total_steps": 40000, "loss": 0.1098, "lr": 4.1282437701291724e-05, "epoch": 0.4966160392946875, "percentage": 27.43, "elapsed_time": "8:53:50", "remaining_time": "23:32:41", "throughput": 559.79, "total_tokens": 17930240} {"current_steps": 10975, "total_steps": 40000, "loss": 0.1037, "lr": 4.1274986723729184e-05, "epoch": 0.4968423911813305, "percentage": 27.44, "elapsed_time": "8:53:53", "remaining_time": "23:31:56", "throughput": 559.98, "total_tokens": 17938016} {"current_steps": 10980, "total_steps": 40000, "loss": 0.1483, "lr": 4.126753323635917e-05, "epoch": 0.4970687430679735, "percentage": 27.45, "elapsed_time": "8:53:56", "remaining_time": "23:31:11", "throughput": 560.2, "total_tokens": 17946688} {"current_steps": 10985, "total_steps": 40000, "loss": 0.1797, "lr": 4.12600772403311e-05, "epoch": 0.49729509495461643, "percentage": 27.46, "elapsed_time": "8:53:59", "remaining_time": "23:30:27", "throughput": 560.42, "total_tokens": 17955776} {"current_steps": 10990, "total_steps": 40000, "loss": 0.1767, "lr": 4.125261873679479e-05, "epoch": 0.49752144684125943, "percentage": 27.47, "elapsed_time": "8:54:02", "remaining_time": "23:29:42", "throughput": 560.61, "total_tokens": 17963584} {"current_steps": 10995, "total_steps": 40000, "loss": 0.1521, "lr": 4.124515772690042e-05, "epoch": 0.4977477987279024, "percentage": 27.49, "elapsed_time": "8:54:06", "remaining_time": "23:28:58", "throughput": 560.82, "total_tokens": 17971968} {"current_steps": 11000, "total_steps": 40000, "loss": 0.1311, "lr": 4.123769421179858e-05, "epoch": 0.49797415061454536, "percentage": 27.5, "elapsed_time": "8:54:09", "remaining_time": "23:28:13", "throughput": 561.03, "total_tokens": 17980544} {"current_steps": 11000, "total_steps": 40000, "eval_loss": 0.1371595412492752, "epoch": 0.49797415061454536, "percentage": 27.5, "elapsed_time": "9:01:52", "remaining_time": "23:48:34", "throughput": 553.04, "total_tokens": 17980544} {"current_steps": 11005, "total_steps": 40000, "loss": 0.1734, "lr": 4.1230228192640236e-05, "epoch": 0.49820050250118836, "percentage": 27.51, "elapsed_time": "9:01:56", "remaining_time": "23:47:50", "throughput": 553.24, "total_tokens": 17989248} {"current_steps": 11010, "total_steps": 40000, "loss": 0.1224, "lr": 4.122275967057675e-05, "epoch": 0.4984268543878313, "percentage": 27.52, "elapsed_time": "9:01:59", "remaining_time": "23:47:05", "throughput": 553.45, "total_tokens": 17997760} {"current_steps": 11015, "total_steps": 40000, "loss": 0.1145, "lr": 4.1215288646759846e-05, "epoch": 0.4986532062744743, "percentage": 27.54, "elapsed_time": "9:02:02", "remaining_time": "23:46:20", "throughput": 553.63, "total_tokens": 18005472} {"current_steps": 11020, "total_steps": 40000, "loss": 0.1495, "lr": 4.120781512234166e-05, "epoch": 0.4988795581611173, "percentage": 27.55, "elapsed_time": "9:02:05", "remaining_time": "23:45:34", "throughput": 553.82, "total_tokens": 18013440} {"current_steps": 11025, "total_steps": 40000, "loss": 0.0864, "lr": 4.120033909847471e-05, "epoch": 0.4991059100477602, "percentage": 27.56, "elapsed_time": "9:02:08", "remaining_time": "23:44:49", "throughput": 554.01, "total_tokens": 18021216} {"current_steps": 11030, "total_steps": 40000, "loss": 0.2103, "lr": 4.119286057631187e-05, "epoch": 0.4993322619344032, "percentage": 27.57, "elapsed_time": "9:02:11", "remaining_time": "23:44:04", "throughput": 554.19, "total_tokens": 18028736} {"current_steps": 11035, "total_steps": 40000, "loss": 0.1803, "lr": 4.118537955700646e-05, "epoch": 0.4995586138210462, "percentage": 27.59, "elapsed_time": "9:02:15", "remaining_time": "23:43:19", "throughput": 554.39, "total_tokens": 18037216} {"current_steps": 11040, "total_steps": 40000, "loss": 0.1433, "lr": 4.11778960417121e-05, "epoch": 0.49978496570768915, "percentage": 27.6, "elapsed_time": "9:02:18", "remaining_time": "23:42:34", "throughput": 554.59, "total_tokens": 18045536} {"current_steps": 11045, "total_steps": 40000, "loss": 0.1317, "lr": 4.117041003158288e-05, "epoch": 0.5000113175943321, "percentage": 27.61, "elapsed_time": "9:02:21", "remaining_time": "23:41:49", "throughput": 554.79, "total_tokens": 18053536} {"current_steps": 11050, "total_steps": 40000, "loss": 0.1465, "lr": 4.1162921527773215e-05, "epoch": 0.5002376694809751, "percentage": 27.62, "elapsed_time": "9:02:24", "remaining_time": "23:41:03", "throughput": 554.97, "total_tokens": 18061280} {"current_steps": 11055, "total_steps": 40000, "loss": 0.1257, "lr": 4.115543053143794e-05, "epoch": 0.5004640213676181, "percentage": 27.64, "elapsed_time": "9:02:27", "remaining_time": "23:40:18", "throughput": 555.16, "total_tokens": 18069152} {"current_steps": 11060, "total_steps": 40000, "loss": 0.1448, "lr": 4.114793704373226e-05, "epoch": 0.500690373254261, "percentage": 27.65, "elapsed_time": "9:02:30", "remaining_time": "23:39:34", "throughput": 555.37, "total_tokens": 18077696} {"current_steps": 11065, "total_steps": 40000, "loss": 0.1232, "lr": 4.114044106581175e-05, "epoch": 0.500916725140904, "percentage": 27.66, "elapsed_time": "9:02:34", "remaining_time": "23:38:49", "throughput": 555.59, "total_tokens": 18086784} {"current_steps": 11070, "total_steps": 40000, "loss": 0.1422, "lr": 4.11329425988324e-05, "epoch": 0.501143077027547, "percentage": 27.68, "elapsed_time": "9:02:37", "remaining_time": "23:38:05", "throughput": 555.8, "total_tokens": 18095424} {"current_steps": 11075, "total_steps": 40000, "loss": 0.1224, "lr": 4.112544164395056e-05, "epoch": 0.50136942891419, "percentage": 27.69, "elapsed_time": "9:02:40", "remaining_time": "23:37:20", "throughput": 556.01, "total_tokens": 18104256} {"current_steps": 11080, "total_steps": 40000, "loss": 0.1571, "lr": 4.111793820232297e-05, "epoch": 0.501595780800833, "percentage": 27.7, "elapsed_time": "9:02:44", "remaining_time": "23:36:35", "throughput": 556.21, "total_tokens": 18112416} {"current_steps": 11085, "total_steps": 40000, "loss": 0.1435, "lr": 4.1110432275106767e-05, "epoch": 0.501822132687476, "percentage": 27.71, "elapsed_time": "9:02:47", "remaining_time": "23:35:50", "throughput": 556.39, "total_tokens": 18120224} {"current_steps": 11090, "total_steps": 40000, "loss": 0.1331, "lr": 4.110292386345944e-05, "epoch": 0.5020484845741189, "percentage": 27.73, "elapsed_time": "9:02:50", "remaining_time": "23:35:06", "throughput": 556.59, "total_tokens": 18128448} {"current_steps": 11095, "total_steps": 40000, "loss": 0.1314, "lr": 4.109541296853891e-05, "epoch": 0.5022748364607619, "percentage": 27.74, "elapsed_time": "9:02:53", "remaining_time": "23:34:21", "throughput": 556.8, "total_tokens": 18137120} {"current_steps": 11100, "total_steps": 40000, "loss": 0.1579, "lr": 4.108789959150341e-05, "epoch": 0.5025011883474049, "percentage": 27.75, "elapsed_time": "9:02:56", "remaining_time": "23:33:37", "throughput": 557.01, "total_tokens": 18145760} {"current_steps": 11105, "total_steps": 40000, "loss": 0.1396, "lr": 4.108038373351163e-05, "epoch": 0.5027275402340479, "percentage": 27.76, "elapsed_time": "9:03:00", "remaining_time": "23:32:53", "throughput": 557.22, "total_tokens": 18154336} {"current_steps": 11110, "total_steps": 40000, "loss": 0.0991, "lr": 4.10728653957226e-05, "epoch": 0.5029538921206909, "percentage": 27.77, "elapsed_time": "9:03:03", "remaining_time": "23:32:08", "throughput": 557.4, "total_tokens": 18161984} {"current_steps": 11115, "total_steps": 40000, "loss": 0.1307, "lr": 4.106534457929575e-05, "epoch": 0.5031802440073339, "percentage": 27.79, "elapsed_time": "9:03:06", "remaining_time": "23:31:23", "throughput": 557.59, "total_tokens": 18170016} {"current_steps": 11120, "total_steps": 40000, "loss": 0.1071, "lr": 4.105782128539086e-05, "epoch": 0.5034065958939767, "percentage": 27.8, "elapsed_time": "9:03:09", "remaining_time": "23:30:39", "throughput": 557.79, "total_tokens": 18178272} {"current_steps": 11125, "total_steps": 40000, "loss": 0.1226, "lr": 4.1050295515168144e-05, "epoch": 0.5036329477806197, "percentage": 27.81, "elapsed_time": "9:03:12", "remaining_time": "23:29:55", "throughput": 558.0, "total_tokens": 18187008} {"current_steps": 11130, "total_steps": 40000, "loss": 0.1493, "lr": 4.1042767269788155e-05, "epoch": 0.5038592996672627, "percentage": 27.82, "elapsed_time": "9:03:16", "remaining_time": "23:29:10", "throughput": 558.21, "total_tokens": 18195456} {"current_steps": 11135, "total_steps": 40000, "loss": 0.1169, "lr": 4.103523655041185e-05, "epoch": 0.5040856515539057, "percentage": 27.84, "elapsed_time": "9:03:19", "remaining_time": "23:28:26", "throughput": 558.41, "total_tokens": 18203808} {"current_steps": 11140, "total_steps": 40000, "loss": 0.1221, "lr": 4.102770335820055e-05, "epoch": 0.5043120034405487, "percentage": 27.85, "elapsed_time": "9:03:22", "remaining_time": "23:27:42", "throughput": 558.62, "total_tokens": 18212384} {"current_steps": 11145, "total_steps": 40000, "loss": 0.1927, "lr": 4.1020167694315984e-05, "epoch": 0.5045383553271916, "percentage": 27.86, "elapsed_time": "9:03:25", "remaining_time": "23:26:58", "throughput": 558.81, "total_tokens": 18220480} {"current_steps": 11150, "total_steps": 40000, "loss": 0.1367, "lr": 4.101262955992023e-05, "epoch": 0.5047647072138346, "percentage": 27.88, "elapsed_time": "9:03:29", "remaining_time": "23:26:14", "throughput": 559.01, "total_tokens": 18228928} {"current_steps": 11155, "total_steps": 40000, "loss": 0.1805, "lr": 4.100508895617578e-05, "epoch": 0.5049910591004776, "percentage": 27.89, "elapsed_time": "9:03:32", "remaining_time": "23:25:29", "throughput": 559.2, "total_tokens": 18236640} {"current_steps": 11160, "total_steps": 40000, "loss": 0.1406, "lr": 4.099754588424547e-05, "epoch": 0.5052174109871206, "percentage": 27.9, "elapsed_time": "9:03:35", "remaining_time": "23:24:45", "throughput": 559.37, "total_tokens": 18243968} {"current_steps": 11165, "total_steps": 40000, "loss": 0.1768, "lr": 4.0990000345292546e-05, "epoch": 0.5054437628737636, "percentage": 27.91, "elapsed_time": "9:03:38", "remaining_time": "23:24:01", "throughput": 559.56, "total_tokens": 18252064} {"current_steps": 11170, "total_steps": 40000, "loss": 0.1211, "lr": 4.098245234048064e-05, "epoch": 0.5056701147604066, "percentage": 27.93, "elapsed_time": "9:03:41", "remaining_time": "23:23:16", "throughput": 559.75, "total_tokens": 18259936} {"current_steps": 11175, "total_steps": 40000, "loss": 0.1324, "lr": 4.0974901870973726e-05, "epoch": 0.5058964666470495, "percentage": 27.94, "elapsed_time": "9:03:44", "remaining_time": "23:22:32", "throughput": 559.93, "total_tokens": 18267520} {"current_steps": 11180, "total_steps": 40000, "loss": 0.1073, "lr": 4.096734893793619e-05, "epoch": 0.5061228185336925, "percentage": 27.95, "elapsed_time": "9:03:47", "remaining_time": "23:21:48", "throughput": 560.13, "total_tokens": 18275776} {"current_steps": 11185, "total_steps": 40000, "loss": 0.115, "lr": 4.095979354253279e-05, "epoch": 0.5063491704203354, "percentage": 27.96, "elapsed_time": "9:03:50", "remaining_time": "23:21:04", "throughput": 560.33, "total_tokens": 18283968} {"current_steps": 11190, "total_steps": 40000, "loss": 0.1134, "lr": 4.0952235685928656e-05, "epoch": 0.5065755223069784, "percentage": 27.98, "elapsed_time": "9:03:54", "remaining_time": "23:20:20", "throughput": 560.52, "total_tokens": 18292192} {"current_steps": 11195, "total_steps": 40000, "loss": 0.1373, "lr": 4.094467536928932e-05, "epoch": 0.5068018741936214, "percentage": 27.99, "elapsed_time": "9:03:57", "remaining_time": "23:19:36", "throughput": 560.72, "total_tokens": 18300384} {"current_steps": 11200, "total_steps": 40000, "loss": 0.1381, "lr": 4.093711259378067e-05, "epoch": 0.5070282260802644, "percentage": 28.0, "elapsed_time": "9:04:00", "remaining_time": "23:18:53", "throughput": 560.93, "total_tokens": 18309024} {"current_steps": 11200, "total_steps": 40000, "eval_loss": 0.1378224641084671, "epoch": 0.5070282260802644, "percentage": 28.0, "elapsed_time": "9:11:43", "remaining_time": "23:38:42", "throughput": 553.09, "total_tokens": 18309024} {"current_steps": 11205, "total_steps": 40000, "loss": 0.1536, "lr": 4.092954736056897e-05, "epoch": 0.5072545779669073, "percentage": 28.01, "elapsed_time": "9:11:47", "remaining_time": "23:38:00", "throughput": 553.28, "total_tokens": 18317472} {"current_steps": 11210, "total_steps": 40000, "loss": 0.1316, "lr": 4.09219796708209e-05, "epoch": 0.5074809298535503, "percentage": 28.02, "elapsed_time": "9:11:50", "remaining_time": "23:37:15", "throughput": 553.45, "total_tokens": 18325056} {"current_steps": 11215, "total_steps": 40000, "loss": 0.1198, "lr": 4.0914409525703464e-05, "epoch": 0.5077072817401933, "percentage": 28.04, "elapsed_time": "9:11:53", "remaining_time": "23:36:30", "throughput": 553.65, "total_tokens": 18333216} {"current_steps": 11220, "total_steps": 40000, "loss": 0.1789, "lr": 4.090683692638408e-05, "epoch": 0.5079336336268363, "percentage": 28.05, "elapsed_time": "9:11:56", "remaining_time": "23:35:46", "throughput": 553.84, "total_tokens": 18341248} {"current_steps": 11225, "total_steps": 40000, "loss": 0.1429, "lr": 4.089926187403056e-05, "epoch": 0.5081599855134793, "percentage": 28.06, "elapsed_time": "9:11:59", "remaining_time": "23:35:01", "throughput": 554.02, "total_tokens": 18349120} {"current_steps": 11230, "total_steps": 40000, "loss": 0.1006, "lr": 4.0891684369811044e-05, "epoch": 0.5083863374001222, "percentage": 28.07, "elapsed_time": "9:12:03", "remaining_time": "23:34:17", "throughput": 554.23, "total_tokens": 18357664} {"current_steps": 11235, "total_steps": 40000, "loss": 0.1034, "lr": 4.0884104414894107e-05, "epoch": 0.5086126892867652, "percentage": 28.09, "elapsed_time": "9:12:06", "remaining_time": "23:33:33", "throughput": 554.41, "total_tokens": 18365568} {"current_steps": 11240, "total_steps": 40000, "loss": 0.2135, "lr": 4.087652201044864e-05, "epoch": 0.5088390411734082, "percentage": 28.1, "elapsed_time": "9:12:09", "remaining_time": "23:32:48", "throughput": 554.6, "total_tokens": 18373600} {"current_steps": 11245, "total_steps": 40000, "loss": 0.1506, "lr": 4.086893715764397e-05, "epoch": 0.5090653930600512, "percentage": 28.11, "elapsed_time": "9:12:12", "remaining_time": "23:32:04", "throughput": 554.79, "total_tokens": 18381696} {"current_steps": 11250, "total_steps": 40000, "loss": 0.1419, "lr": 4.086134985764977e-05, "epoch": 0.5092917449466942, "percentage": 28.12, "elapsed_time": "9:12:15", "remaining_time": "23:31:20", "throughput": 554.99, "total_tokens": 18390080} {"current_steps": 11255, "total_steps": 40000, "loss": 0.1553, "lr": 4.0853760111636085e-05, "epoch": 0.5095180968333372, "percentage": 28.14, "elapsed_time": "9:12:18", "remaining_time": "23:30:36", "throughput": 555.2, "total_tokens": 18398784} {"current_steps": 11260, "total_steps": 40000, "loss": 0.1497, "lr": 4.084616792077337e-05, "epoch": 0.50974444871998, "percentage": 28.15, "elapsed_time": "9:12:22", "remaining_time": "23:29:52", "throughput": 555.41, "total_tokens": 18407392} {"current_steps": 11265, "total_steps": 40000, "loss": 0.1317, "lr": 4.083857328623243e-05, "epoch": 0.509970800606623, "percentage": 28.16, "elapsed_time": "9:12:25", "remaining_time": "23:29:07", "throughput": 555.59, "total_tokens": 18415136} {"current_steps": 11270, "total_steps": 40000, "loss": 0.1482, "lr": 4.083097620918444e-05, "epoch": 0.510197152493266, "percentage": 28.18, "elapsed_time": "9:12:28", "remaining_time": "23:28:23", "throughput": 555.78, "total_tokens": 18423392} {"current_steps": 11275, "total_steps": 40000, "loss": 0.1803, "lr": 4.082337669080097e-05, "epoch": 0.510423504379909, "percentage": 28.19, "elapsed_time": "9:12:31", "remaining_time": "23:27:39", "throughput": 555.98, "total_tokens": 18431552} {"current_steps": 11280, "total_steps": 40000, "loss": 0.1023, "lr": 4.081577473225398e-05, "epoch": 0.510649856266552, "percentage": 28.2, "elapsed_time": "9:12:34", "remaining_time": "23:26:55", "throughput": 556.16, "total_tokens": 18439456} {"current_steps": 11285, "total_steps": 40000, "loss": 0.178, "lr": 4.080817033471577e-05, "epoch": 0.510876208153195, "percentage": 28.21, "elapsed_time": "9:12:38", "remaining_time": "23:26:11", "throughput": 556.35, "total_tokens": 18447616} {"current_steps": 11290, "total_steps": 40000, "loss": 0.1071, "lr": 4.080056349935903e-05, "epoch": 0.5111025600398379, "percentage": 28.23, "elapsed_time": "9:12:41", "remaining_time": "23:25:27", "throughput": 556.55, "total_tokens": 18455904} {"current_steps": 11295, "total_steps": 40000, "loss": 0.1252, "lr": 4.079295422735684e-05, "epoch": 0.5113289119264809, "percentage": 28.24, "elapsed_time": "9:12:44", "remaining_time": "23:24:43", "throughput": 556.74, "total_tokens": 18464000} {"current_steps": 11300, "total_steps": 40000, "loss": 0.1904, "lr": 4.078534251988264e-05, "epoch": 0.5115552638131239, "percentage": 28.25, "elapsed_time": "9:12:47", "remaining_time": "23:23:59", "throughput": 556.93, "total_tokens": 18471904} {"current_steps": 11305, "total_steps": 40000, "loss": 0.1026, "lr": 4.077772837811025e-05, "epoch": 0.5117816156997669, "percentage": 28.26, "elapsed_time": "9:12:50", "remaining_time": "23:23:15", "throughput": 557.13, "total_tokens": 18480384} {"current_steps": 11310, "total_steps": 40000, "loss": 0.1255, "lr": 4.0770111803213874e-05, "epoch": 0.5120079675864099, "percentage": 28.27, "elapsed_time": "9:12:54", "remaining_time": "23:22:32", "throughput": 557.33, "total_tokens": 18488736} {"current_steps": 11315, "total_steps": 40000, "loss": 0.1292, "lr": 4.076249279636807e-05, "epoch": 0.5122343194730528, "percentage": 28.29, "elapsed_time": "9:12:57", "remaining_time": "23:21:48", "throughput": 557.53, "total_tokens": 18497216} {"current_steps": 11320, "total_steps": 40000, "loss": 0.1346, "lr": 4.075487135874781e-05, "epoch": 0.5124606713596958, "percentage": 28.3, "elapsed_time": "9:13:00", "remaining_time": "23:21:04", "throughput": 557.71, "total_tokens": 18505024} {"current_steps": 11325, "total_steps": 40000, "loss": 0.1727, "lr": 4.074724749152837e-05, "epoch": 0.5126870232463387, "percentage": 28.31, "elapsed_time": "9:13:03", "remaining_time": "23:20:21", "throughput": 557.91, "total_tokens": 18513504} {"current_steps": 11330, "total_steps": 40000, "loss": 0.1319, "lr": 4.07396211958855e-05, "epoch": 0.5129133751329817, "percentage": 28.32, "elapsed_time": "9:13:06", "remaining_time": "23:19:37", "throughput": 558.11, "total_tokens": 18522112} {"current_steps": 11335, "total_steps": 40000, "loss": 0.2017, "lr": 4.073199247299523e-05, "epoch": 0.5131397270196247, "percentage": 28.34, "elapsed_time": "9:13:10", "remaining_time": "23:18:54", "throughput": 558.29, "total_tokens": 18529824} {"current_steps": 11340, "total_steps": 40000, "loss": 0.1238, "lr": 4.072436132403403e-05, "epoch": 0.5133660789062677, "percentage": 28.35, "elapsed_time": "9:13:13", "remaining_time": "23:18:10", "throughput": 558.47, "total_tokens": 18537568} {"current_steps": 11345, "total_steps": 40000, "loss": 0.1798, "lr": 4.0716727750178704e-05, "epoch": 0.5135924307929106, "percentage": 28.36, "elapsed_time": "9:13:16", "remaining_time": "23:17:26", "throughput": 558.66, "total_tokens": 18545440} {"current_steps": 11350, "total_steps": 40000, "loss": 0.1503, "lr": 4.0709091752606455e-05, "epoch": 0.5138187826795536, "percentage": 28.38, "elapsed_time": "9:13:19", "remaining_time": "23:16:43", "throughput": 558.86, "total_tokens": 18553824} {"current_steps": 11355, "total_steps": 40000, "loss": 0.1373, "lr": 4.070145333249484e-05, "epoch": 0.5140451345661966, "percentage": 28.39, "elapsed_time": "9:13:22", "remaining_time": "23:15:59", "throughput": 559.06, "total_tokens": 18562240} {"current_steps": 11360, "total_steps": 40000, "loss": 0.1515, "lr": 4.069381249102181e-05, "epoch": 0.5142714864528396, "percentage": 28.4, "elapsed_time": "9:13:25", "remaining_time": "23:15:16", "throughput": 559.25, "total_tokens": 18570400} {"current_steps": 11365, "total_steps": 40000, "loss": 0.1303, "lr": 4.0686169229365665e-05, "epoch": 0.5144978383394826, "percentage": 28.41, "elapsed_time": "9:13:29", "remaining_time": "23:14:32", "throughput": 559.43, "total_tokens": 18578016} {"current_steps": 11370, "total_steps": 40000, "loss": 0.1352, "lr": 4.067852354870511e-05, "epoch": 0.5147241902261256, "percentage": 28.43, "elapsed_time": "9:13:32", "remaining_time": "23:13:49", "throughput": 559.61, "total_tokens": 18585856} {"current_steps": 11375, "total_steps": 40000, "loss": 0.1203, "lr": 4.067087545021919e-05, "epoch": 0.5149505421127685, "percentage": 28.44, "elapsed_time": "9:13:35", "remaining_time": "23:13:05", "throughput": 559.8, "total_tokens": 18593888} {"current_steps": 11380, "total_steps": 40000, "loss": 0.1777, "lr": 4.066322493508734e-05, "epoch": 0.5151768939994115, "percentage": 28.45, "elapsed_time": "9:13:38", "remaining_time": "23:12:22", "throughput": 559.98, "total_tokens": 18601536} {"current_steps": 11385, "total_steps": 40000, "loss": 0.1291, "lr": 4.065557200448937e-05, "epoch": 0.5154032458860545, "percentage": 28.46, "elapsed_time": "9:13:41", "remaining_time": "23:11:39", "throughput": 560.18, "total_tokens": 18609984} {"current_steps": 11390, "total_steps": 40000, "loss": 0.1174, "lr": 4.064791665960546e-05, "epoch": 0.5156295977726975, "percentage": 28.48, "elapsed_time": "9:13:44", "remaining_time": "23:10:55", "throughput": 560.36, "total_tokens": 18617888} {"current_steps": 11395, "total_steps": 40000, "loss": 0.1206, "lr": 4.064025890161615e-05, "epoch": 0.5158559496593405, "percentage": 28.49, "elapsed_time": "9:13:48", "remaining_time": "23:10:13", "throughput": 560.57, "total_tokens": 18626688} {"current_steps": 11400, "total_steps": 40000, "loss": 0.1316, "lr": 4.0632598731702373e-05, "epoch": 0.5160823015459833, "percentage": 28.5, "elapsed_time": "9:13:51", "remaining_time": "23:09:29", "throughput": 560.75, "total_tokens": 18634272} {"current_steps": 11400, "total_steps": 40000, "eval_loss": 0.137192040681839, "epoch": 0.5160823015459833, "percentage": 28.5, "elapsed_time": "9:21:33", "remaining_time": "23:28:50", "throughput": 553.05, "total_tokens": 18634272} {"current_steps": 11405, "total_steps": 40000, "loss": 0.1598, "lr": 4.0624936151045426e-05, "epoch": 0.5163086534326263, "percentage": 28.51, "elapsed_time": "9:21:37", "remaining_time": "23:28:07", "throughput": 553.21, "total_tokens": 18642016} {"current_steps": 11410, "total_steps": 40000, "loss": 0.0836, "lr": 4.061727116082696e-05, "epoch": 0.5165350053192693, "percentage": 28.52, "elapsed_time": "9:21:40", "remaining_time": "23:27:24", "throughput": 553.4, "total_tokens": 18650016} {"current_steps": 11415, "total_steps": 40000, "loss": 0.1493, "lr": 4.060960376222903e-05, "epoch": 0.5167613572059123, "percentage": 28.54, "elapsed_time": "9:21:44", "remaining_time": "23:26:40", "throughput": 553.59, "total_tokens": 18658208} {"current_steps": 11420, "total_steps": 40000, "loss": 0.1546, "lr": 4.0601933956434034e-05, "epoch": 0.5169877090925553, "percentage": 28.55, "elapsed_time": "9:21:47", "remaining_time": "23:25:57", "throughput": 553.78, "total_tokens": 18666496} {"current_steps": 11425, "total_steps": 40000, "loss": 0.1166, "lr": 4.059426174462476e-05, "epoch": 0.5172140609791983, "percentage": 28.56, "elapsed_time": "9:21:50", "remaining_time": "23:25:13", "throughput": 553.98, "total_tokens": 18675200} {"current_steps": 11430, "total_steps": 40000, "loss": 0.1134, "lr": 4.058658712798435e-05, "epoch": 0.5174404128658412, "percentage": 28.57, "elapsed_time": "9:21:53", "remaining_time": "23:24:30", "throughput": 554.18, "total_tokens": 18683520} {"current_steps": 11435, "total_steps": 40000, "loss": 0.1585, "lr": 4.0578910107696336e-05, "epoch": 0.5176667647524842, "percentage": 28.59, "elapsed_time": "9:21:57", "remaining_time": "23:23:46", "throughput": 554.37, "total_tokens": 18691872} {"current_steps": 11440, "total_steps": 40000, "loss": 0.1272, "lr": 4.05712306849446e-05, "epoch": 0.5178931166391272, "percentage": 28.6, "elapsed_time": "9:22:00", "remaining_time": "23:23:03", "throughput": 554.57, "total_tokens": 18700448} {"current_steps": 11445, "total_steps": 40000, "loss": 0.132, "lr": 4.0563548860913415e-05, "epoch": 0.5181194685257702, "percentage": 28.61, "elapsed_time": "9:22:03", "remaining_time": "23:22:19", "throughput": 554.77, "total_tokens": 18708960} {"current_steps": 11450, "total_steps": 40000, "loss": 0.1449, "lr": 4.0555864636787414e-05, "epoch": 0.5183458204124132, "percentage": 28.62, "elapsed_time": "9:22:06", "remaining_time": "23:21:36", "throughput": 554.97, "total_tokens": 18717344} {"current_steps": 11455, "total_steps": 40000, "loss": 0.1273, "lr": 4.054817801375159e-05, "epoch": 0.5185721722990562, "percentage": 28.64, "elapsed_time": "9:22:10", "remaining_time": "23:20:53", "throughput": 555.18, "total_tokens": 18726432} {"current_steps": 11460, "total_steps": 40000, "loss": 0.0991, "lr": 4.054048899299134e-05, "epoch": 0.518798524185699, "percentage": 28.65, "elapsed_time": "9:22:13", "remaining_time": "23:20:10", "throughput": 555.36, "total_tokens": 18734368} {"current_steps": 11465, "total_steps": 40000, "loss": 0.1602, "lr": 4.0532797575692385e-05, "epoch": 0.519024876072342, "percentage": 28.66, "elapsed_time": "9:22:16", "remaining_time": "23:19:26", "throughput": 555.55, "total_tokens": 18742560} {"current_steps": 11470, "total_steps": 40000, "loss": 0.1347, "lr": 4.052510376304085e-05, "epoch": 0.519251227958985, "percentage": 28.68, "elapsed_time": "9:22:19", "remaining_time": "23:18:43", "throughput": 555.74, "total_tokens": 18750592} {"current_steps": 11475, "total_steps": 40000, "loss": 0.1621, "lr": 4.051740755622321e-05, "epoch": 0.519477579845628, "percentage": 28.69, "elapsed_time": "9:22:22", "remaining_time": "23:17:59", "throughput": 555.92, "total_tokens": 18758496} {"current_steps": 11480, "total_steps": 40000, "loss": 0.1169, "lr": 4.050970895642632e-05, "epoch": 0.519703931732271, "percentage": 28.7, "elapsed_time": "9:22:26", "remaining_time": "23:17:16", "throughput": 556.13, "total_tokens": 18767200} {"current_steps": 11485, "total_steps": 40000, "loss": 0.1253, "lr": 4.050200796483741e-05, "epoch": 0.5199302836189139, "percentage": 28.71, "elapsed_time": "9:22:29", "remaining_time": "23:16:33", "throughput": 556.32, "total_tokens": 18775424} {"current_steps": 11490, "total_steps": 40000, "loss": 0.1147, "lr": 4.049430458264405e-05, "epoch": 0.5201566355055569, "percentage": 28.73, "elapsed_time": "9:22:32", "remaining_time": "23:15:50", "throughput": 556.52, "total_tokens": 18784064} {"current_steps": 11495, "total_steps": 40000, "loss": 0.1171, "lr": 4.048659881103422e-05, "epoch": 0.5203829873921999, "percentage": 28.74, "elapsed_time": "9:22:35", "remaining_time": "23:15:06", "throughput": 556.7, "total_tokens": 18791936} {"current_steps": 11500, "total_steps": 40000, "loss": 0.1516, "lr": 4.0478890651196235e-05, "epoch": 0.5206093392788429, "percentage": 28.75, "elapsed_time": "9:22:38", "remaining_time": "23:14:23", "throughput": 556.88, "total_tokens": 18799552} {"current_steps": 11505, "total_steps": 40000, "loss": 0.1349, "lr": 4.047118010431879e-05, "epoch": 0.5208356911654859, "percentage": 28.76, "elapsed_time": "9:22:42", "remaining_time": "23:13:40", "throughput": 557.07, "total_tokens": 18807904} {"current_steps": 11510, "total_steps": 40000, "loss": 0.1443, "lr": 4.046346717159094e-05, "epoch": 0.5210620430521289, "percentage": 28.78, "elapsed_time": "9:22:45", "remaining_time": "23:12:57", "throughput": 557.27, "total_tokens": 18816256} {"current_steps": 11515, "total_steps": 40000, "loss": 0.1292, "lr": 4.045575185420214e-05, "epoch": 0.5212883949387718, "percentage": 28.79, "elapsed_time": "9:22:48", "remaining_time": "23:12:14", "throughput": 557.46, "total_tokens": 18824544} {"current_steps": 11520, "total_steps": 40000, "loss": 0.147, "lr": 4.0448034153342165e-05, "epoch": 0.5215147468254148, "percentage": 28.8, "elapsed_time": "9:22:51", "remaining_time": "23:11:31", "throughput": 557.65, "total_tokens": 18832608} {"current_steps": 11525, "total_steps": 40000, "loss": 0.1583, "lr": 4.0440314070201194e-05, "epoch": 0.5217410987120578, "percentage": 28.81, "elapsed_time": "9:22:54", "remaining_time": "23:10:47", "throughput": 557.82, "total_tokens": 18840224} {"current_steps": 11530, "total_steps": 40000, "loss": 0.1042, "lr": 4.043259160596976e-05, "epoch": 0.5219674505987008, "percentage": 28.82, "elapsed_time": "9:22:57", "remaining_time": "23:10:04", "throughput": 557.99, "total_tokens": 18847840} {"current_steps": 11535, "total_steps": 40000, "loss": 0.1168, "lr": 4.0424866761838767e-05, "epoch": 0.5221938024853437, "percentage": 28.84, "elapsed_time": "9:23:00", "remaining_time": "23:09:21", "throughput": 558.18, "total_tokens": 18856032} {"current_steps": 11540, "total_steps": 40000, "loss": 0.1378, "lr": 4.041713953899948e-05, "epoch": 0.5224201543719867, "percentage": 28.85, "elapsed_time": "9:23:04", "remaining_time": "23:08:38", "throughput": 558.35, "total_tokens": 18863424} {"current_steps": 11545, "total_steps": 40000, "loss": 0.1454, "lr": 4.0409409938643515e-05, "epoch": 0.5226465062586296, "percentage": 28.86, "elapsed_time": "9:23:07", "remaining_time": "23:07:55", "throughput": 558.54, "total_tokens": 18871392} {"current_steps": 11550, "total_steps": 40000, "loss": 0.115, "lr": 4.0401677961962904e-05, "epoch": 0.5228728581452726, "percentage": 28.88, "elapsed_time": "9:23:10", "remaining_time": "23:07:12", "throughput": 558.72, "total_tokens": 18879392} {"current_steps": 11555, "total_steps": 40000, "loss": 0.1758, "lr": 4.039394361015001e-05, "epoch": 0.5230992100319156, "percentage": 28.89, "elapsed_time": "9:23:13", "remaining_time": "23:06:30", "throughput": 558.93, "total_tokens": 18888320} {"current_steps": 11560, "total_steps": 40000, "loss": 0.1491, "lr": 4.038620688439755e-05, "epoch": 0.5233255619185586, "percentage": 28.9, "elapsed_time": "9:23:16", "remaining_time": "23:05:47", "throughput": 559.11, "total_tokens": 18896224} {"current_steps": 11565, "total_steps": 40000, "loss": 0.1389, "lr": 4.037846778589862e-05, "epoch": 0.5235519138052016, "percentage": 28.91, "elapsed_time": "9:23:20", "remaining_time": "23:05:04", "throughput": 559.31, "total_tokens": 18904704} {"current_steps": 11570, "total_steps": 40000, "loss": 0.1153, "lr": 4.0370726315846715e-05, "epoch": 0.5237782656918445, "percentage": 28.93, "elapsed_time": "9:23:23", "remaining_time": "23:04:22", "throughput": 559.49, "total_tokens": 18912768} {"current_steps": 11575, "total_steps": 40000, "loss": 0.0971, "lr": 4.036298247543565e-05, "epoch": 0.5240046175784875, "percentage": 28.94, "elapsed_time": "9:23:26", "remaining_time": "23:03:39", "throughput": 559.69, "total_tokens": 18921024} {"current_steps": 11580, "total_steps": 40000, "loss": 0.1605, "lr": 4.035523626585962e-05, "epoch": 0.5242309694651305, "percentage": 28.95, "elapsed_time": "9:23:29", "remaining_time": "23:02:56", "throughput": 559.89, "total_tokens": 18929728} {"current_steps": 11585, "total_steps": 40000, "loss": 0.1081, "lr": 4.0347487688313194e-05, "epoch": 0.5244573213517735, "percentage": 28.96, "elapsed_time": "9:23:32", "remaining_time": "23:02:14", "throughput": 560.09, "total_tokens": 18938112} {"current_steps": 11590, "total_steps": 40000, "loss": 0.122, "lr": 4.0339736743991296e-05, "epoch": 0.5246836732384165, "percentage": 28.98, "elapsed_time": "9:23:36", "remaining_time": "23:01:31", "throughput": 560.26, "total_tokens": 18945760} {"current_steps": 11595, "total_steps": 40000, "loss": 0.1219, "lr": 4.0331983434089227e-05, "epoch": 0.5249100251250595, "percentage": 28.99, "elapsed_time": "9:23:39", "remaining_time": "23:00:48", "throughput": 560.44, "total_tokens": 18953568} {"current_steps": 11600, "total_steps": 40000, "loss": 0.1468, "lr": 4.032422775980264e-05, "epoch": 0.5251363770117023, "percentage": 29.0, "elapsed_time": "9:23:42", "remaining_time": "23:00:06", "throughput": 560.67, "total_tokens": 18963136} {"current_steps": 11600, "total_steps": 40000, "eval_loss": 0.1359906941652298, "epoch": 0.5251363770117023, "percentage": 29.0, "elapsed_time": "9:31:25", "remaining_time": "23:18:59", "throughput": 553.1, "total_tokens": 18963136} {"current_steps": 11605, "total_steps": 40000, "loss": 0.0849, "lr": 4.031646972232754e-05, "epoch": 0.5253627288983453, "percentage": 29.01, "elapsed_time": "9:31:29", "remaining_time": "23:18:18", "throughput": 553.27, "total_tokens": 18971296} {"current_steps": 11610, "total_steps": 40000, "loss": 0.1257, "lr": 4.0308709322860344e-05, "epoch": 0.5255890807849883, "percentage": 29.03, "elapsed_time": "9:31:32", "remaining_time": "23:17:35", "throughput": 553.46, "total_tokens": 18979328} {"current_steps": 11615, "total_steps": 40000, "loss": 0.1166, "lr": 4.0300946562597784e-05, "epoch": 0.5258154326716313, "percentage": 29.04, "elapsed_time": "9:31:35", "remaining_time": "23:16:52", "throughput": 553.64, "total_tokens": 18987264} {"current_steps": 11620, "total_steps": 40000, "loss": 0.139, "lr": 4.029318144273698e-05, "epoch": 0.5260417845582743, "percentage": 29.05, "elapsed_time": "9:31:38", "remaining_time": "23:16:09", "throughput": 553.83, "total_tokens": 18995712} {"current_steps": 11625, "total_steps": 40000, "loss": 0.1314, "lr": 4.0285413964475415e-05, "epoch": 0.5262681364449173, "percentage": 29.06, "elapsed_time": "9:31:41", "remaining_time": "23:15:26", "throughput": 554.01, "total_tokens": 19003744} {"current_steps": 11630, "total_steps": 40000, "loss": 0.1345, "lr": 4.0277644129010927e-05, "epoch": 0.5264944883315602, "percentage": 29.07, "elapsed_time": "9:31:45", "remaining_time": "23:14:43", "throughput": 554.2, "total_tokens": 19011936} {"current_steps": 11635, "total_steps": 40000, "loss": 0.1026, "lr": 4.0269871937541724e-05, "epoch": 0.5267208402182032, "percentage": 29.09, "elapsed_time": "9:31:48", "remaining_time": "23:14:00", "throughput": 554.4, "total_tokens": 19020576} {"current_steps": 11640, "total_steps": 40000, "loss": 0.0848, "lr": 4.026209739126637e-05, "epoch": 0.5269471921048462, "percentage": 29.1, "elapsed_time": "9:31:51", "remaining_time": "23:13:17", "throughput": 554.59, "total_tokens": 19028672} {"current_steps": 11645, "total_steps": 40000, "loss": 0.1232, "lr": 4.025432049138381e-05, "epoch": 0.5271735439914892, "percentage": 29.11, "elapsed_time": "9:31:54", "remaining_time": "23:12:34", "throughput": 554.77, "total_tokens": 19036768} {"current_steps": 11650, "total_steps": 40000, "loss": 0.1311, "lr": 4.0246541239093325e-05, "epoch": 0.5273998958781322, "percentage": 29.12, "elapsed_time": "9:31:57", "remaining_time": "23:11:51", "throughput": 554.96, "total_tokens": 19044832} {"current_steps": 11655, "total_steps": 40000, "loss": 0.1497, "lr": 4.023875963559459e-05, "epoch": 0.5276262477647751, "percentage": 29.14, "elapsed_time": "9:32:00", "remaining_time": "23:11:08", "throughput": 555.12, "total_tokens": 19052352} {"current_steps": 11660, "total_steps": 40000, "loss": 0.1187, "lr": 4.023097568208761e-05, "epoch": 0.5278525996514181, "percentage": 29.15, "elapsed_time": "9:32:04", "remaining_time": "23:10:25", "throughput": 555.32, "total_tokens": 19060864} {"current_steps": 11665, "total_steps": 40000, "loss": 0.1472, "lr": 4.022318937977277e-05, "epoch": 0.5280789515380611, "percentage": 29.16, "elapsed_time": "9:32:07", "remaining_time": "23:09:42", "throughput": 555.5, "total_tokens": 19068640} {"current_steps": 11670, "total_steps": 40000, "loss": 0.159, "lr": 4.021540072985084e-05, "epoch": 0.528305303424704, "percentage": 29.18, "elapsed_time": "9:32:10", "remaining_time": "23:09:00", "throughput": 555.7, "total_tokens": 19077472} {"current_steps": 11675, "total_steps": 40000, "loss": 0.1795, "lr": 4.020760973352289e-05, "epoch": 0.528531655311347, "percentage": 29.19, "elapsed_time": "9:32:13", "remaining_time": "23:08:17", "throughput": 555.88, "total_tokens": 19085216} {"current_steps": 11680, "total_steps": 40000, "loss": 0.1607, "lr": 4.019981639199042e-05, "epoch": 0.52875800719799, "percentage": 29.2, "elapsed_time": "9:32:16", "remaining_time": "23:07:34", "throughput": 556.06, "total_tokens": 19093280} {"current_steps": 11685, "total_steps": 40000, "loss": 0.109, "lr": 4.0192020706455245e-05, "epoch": 0.5289843590846329, "percentage": 29.21, "elapsed_time": "9:32:19", "remaining_time": "23:06:52", "throughput": 556.24, "total_tokens": 19101216} {"current_steps": 11690, "total_steps": 40000, "loss": 0.1305, "lr": 4.018422267811956e-05, "epoch": 0.5292107109712759, "percentage": 29.23, "elapsed_time": "9:32:23", "remaining_time": "23:06:09", "throughput": 556.42, "total_tokens": 19109248} {"current_steps": 11695, "total_steps": 40000, "loss": 0.1368, "lr": 4.017642230818592e-05, "epoch": 0.5294370628579189, "percentage": 29.24, "elapsed_time": "9:32:26", "remaining_time": "23:05:27", "throughput": 556.62, "total_tokens": 19117984} {"current_steps": 11700, "total_steps": 40000, "loss": 0.1398, "lr": 4.0168619597857246e-05, "epoch": 0.5296634147445619, "percentage": 29.25, "elapsed_time": "9:32:29", "remaining_time": "23:04:45", "throughput": 556.82, "total_tokens": 19126720} {"current_steps": 11705, "total_steps": 40000, "loss": 0.1172, "lr": 4.016081454833681e-05, "epoch": 0.5298897666312049, "percentage": 29.26, "elapsed_time": "9:32:32", "remaining_time": "23:04:02", "throughput": 557.0, "total_tokens": 19134400} {"current_steps": 11710, "total_steps": 40000, "loss": 0.1711, "lr": 4.0153007160828245e-05, "epoch": 0.5301161185178479, "percentage": 29.28, "elapsed_time": "9:32:35", "remaining_time": "23:03:19", "throughput": 557.17, "total_tokens": 19142144} {"current_steps": 11715, "total_steps": 40000, "loss": 0.1312, "lr": 4.0145197436535555e-05, "epoch": 0.5303424704044908, "percentage": 29.29, "elapsed_time": "9:32:39", "remaining_time": "23:02:37", "throughput": 557.36, "total_tokens": 19150304} {"current_steps": 11720, "total_steps": 40000, "loss": 0.1738, "lr": 4.0137385376663095e-05, "epoch": 0.5305688222911338, "percentage": 29.3, "elapsed_time": "9:32:42", "remaining_time": "23:01:55", "throughput": 557.56, "total_tokens": 19159008} {"current_steps": 11725, "total_steps": 40000, "loss": 0.0714, "lr": 4.012957098241558e-05, "epoch": 0.5307951741777768, "percentage": 29.31, "elapsed_time": "9:32:45", "remaining_time": "23:01:12", "throughput": 557.74, "total_tokens": 19166976} {"current_steps": 11730, "total_steps": 40000, "loss": 0.175, "lr": 4.0121754254998076e-05, "epoch": 0.5310215260644198, "percentage": 29.33, "elapsed_time": "9:32:48", "remaining_time": "23:00:30", "throughput": 557.95, "total_tokens": 19175936} {"current_steps": 11735, "total_steps": 40000, "loss": 0.0878, "lr": 4.011393519561606e-05, "epoch": 0.5312478779510628, "percentage": 29.34, "elapsed_time": "9:32:52", "remaining_time": "22:59:48", "throughput": 558.14, "total_tokens": 19184384} {"current_steps": 11740, "total_steps": 40000, "loss": 0.1555, "lr": 4.010611380547529e-05, "epoch": 0.5314742298377056, "percentage": 29.35, "elapsed_time": "9:32:55", "remaining_time": "22:59:06", "throughput": 558.33, "total_tokens": 19192768} {"current_steps": 11745, "total_steps": 40000, "loss": 0.133, "lr": 4.009829008578192e-05, "epoch": 0.5317005817243486, "percentage": 29.36, "elapsed_time": "9:32:58", "remaining_time": "22:58:24", "throughput": 558.51, "total_tokens": 19200608} {"current_steps": 11750, "total_steps": 40000, "loss": 0.1112, "lr": 4.00904640377425e-05, "epoch": 0.5319269336109916, "percentage": 29.38, "elapsed_time": "9:33:01", "remaining_time": "22:57:42", "throughput": 558.71, "total_tokens": 19209504} {"current_steps": 11755, "total_steps": 40000, "loss": 0.1512, "lr": 4.0082635662563886e-05, "epoch": 0.5321532854976346, "percentage": 29.39, "elapsed_time": "9:33:04", "remaining_time": "22:57:00", "throughput": 558.88, "total_tokens": 19217024} {"current_steps": 11760, "total_steps": 40000, "loss": 0.1104, "lr": 4.007480496145331e-05, "epoch": 0.5323796373842776, "percentage": 29.4, "elapsed_time": "9:33:08", "remaining_time": "22:56:18", "throughput": 559.09, "total_tokens": 19226208} {"current_steps": 11765, "total_steps": 40000, "loss": 0.1589, "lr": 4.006697193561837e-05, "epoch": 0.5326059892709206, "percentage": 29.41, "elapsed_time": "9:33:11", "remaining_time": "22:55:36", "throughput": 559.27, "total_tokens": 19234112} {"current_steps": 11770, "total_steps": 40000, "loss": 0.114, "lr": 4.005913658626701e-05, "epoch": 0.5328323411575635, "percentage": 29.43, "elapsed_time": "9:33:14", "remaining_time": "22:54:54", "throughput": 559.45, "total_tokens": 19242144} {"current_steps": 11775, "total_steps": 40000, "loss": 0.2064, "lr": 4.005129891460754e-05, "epoch": 0.5330586930442065, "percentage": 29.44, "elapsed_time": "9:33:17", "remaining_time": "22:54:12", "throughput": 559.65, "total_tokens": 19250656} {"current_steps": 11780, "total_steps": 40000, "loss": 0.1536, "lr": 4.004345892184864e-05, "epoch": 0.5332850449308495, "percentage": 29.45, "elapsed_time": "9:33:20", "remaining_time": "22:53:30", "throughput": 559.84, "total_tokens": 19258976} {"current_steps": 11785, "total_steps": 40000, "loss": 0.1177, "lr": 4.003561660919932e-05, "epoch": 0.5335113968174925, "percentage": 29.46, "elapsed_time": "9:33:23", "remaining_time": "22:52:48", "throughput": 560.01, "total_tokens": 19266560} {"current_steps": 11790, "total_steps": 40000, "loss": 0.1112, "lr": 4.002777197786897e-05, "epoch": 0.5337377487041355, "percentage": 29.48, "elapsed_time": "9:33:27", "remaining_time": "22:52:06", "throughput": 560.18, "total_tokens": 19274208} {"current_steps": 11795, "total_steps": 40000, "loss": 0.1518, "lr": 4.0019925029067326e-05, "epoch": 0.5339641005907785, "percentage": 29.49, "elapsed_time": "9:33:30", "remaining_time": "22:51:24", "throughput": 560.37, "total_tokens": 19282624} {"current_steps": 11800, "total_steps": 40000, "loss": 0.1778, "lr": 4.0012075764004495e-05, "epoch": 0.5341904524774214, "percentage": 29.5, "elapsed_time": "9:33:33", "remaining_time": "22:50:42", "throughput": 560.56, "total_tokens": 19290912} {"current_steps": 11800, "total_steps": 40000, "eval_loss": 0.13634829223155975, "epoch": 0.5341904524774214, "percentage": 29.5, "elapsed_time": "9:41:16", "remaining_time": "23:09:08", "throughput": 553.12, "total_tokens": 19290912} {"current_steps": 11805, "total_steps": 40000, "loss": 0.1619, "lr": 4.000422418389094e-05, "epoch": 0.5344168043640644, "percentage": 29.51, "elapsed_time": "9:41:26", "remaining_time": "23:08:42", "throughput": 553.18, "total_tokens": 19298560} {"current_steps": 11810, "total_steps": 40000, "loss": 0.1481, "lr": 3.999637028993744e-05, "epoch": 0.5346431562507074, "percentage": 29.53, "elapsed_time": "9:41:29", "remaining_time": "23:08:00", "throughput": 553.36, "total_tokens": 19306464} {"current_steps": 11815, "total_steps": 40000, "loss": 0.1299, "lr": 3.99885140833552e-05, "epoch": 0.5348695081373503, "percentage": 29.54, "elapsed_time": "9:41:32", "remaining_time": "23:07:17", "throughput": 553.54, "total_tokens": 19314464} {"current_steps": 11820, "total_steps": 40000, "loss": 0.0969, "lr": 3.998065556535572e-05, "epoch": 0.5350958600239933, "percentage": 29.55, "elapsed_time": "9:41:36", "remaining_time": "23:06:35", "throughput": 553.72, "total_tokens": 19322464} {"current_steps": 11825, "total_steps": 40000, "loss": 0.1278, "lr": 3.9972794737150895e-05, "epoch": 0.5353222119106362, "percentage": 29.56, "elapsed_time": "9:41:39", "remaining_time": "23:05:52", "throughput": 553.89, "total_tokens": 19330208} {"current_steps": 11830, "total_steps": 40000, "loss": 0.1424, "lr": 3.996493159995297e-05, "epoch": 0.5355485637972792, "percentage": 29.58, "elapsed_time": "9:41:42", "remaining_time": "23:05:10", "throughput": 554.06, "total_tokens": 19337984} {"current_steps": 11835, "total_steps": 40000, "loss": 0.1657, "lr": 3.995706615497453e-05, "epoch": 0.5357749156839222, "percentage": 29.59, "elapsed_time": "9:41:45", "remaining_time": "23:04:28", "throughput": 554.24, "total_tokens": 19346048} {"current_steps": 11840, "total_steps": 40000, "loss": 0.17, "lr": 3.994919840342852e-05, "epoch": 0.5360012675705652, "percentage": 29.6, "elapsed_time": "9:41:48", "remaining_time": "23:03:45", "throughput": 554.42, "total_tokens": 19353984} {"current_steps": 11845, "total_steps": 40000, "loss": 0.2223, "lr": 3.994132834652825e-05, "epoch": 0.5362276194572082, "percentage": 29.61, "elapsed_time": "9:41:51", "remaining_time": "23:03:03", "throughput": 554.59, "total_tokens": 19361760} {"current_steps": 11850, "total_steps": 40000, "loss": 0.0707, "lr": 3.99334559854874e-05, "epoch": 0.5364539713438512, "percentage": 29.62, "elapsed_time": "9:41:54", "remaining_time": "23:02:21", "throughput": 554.77, "total_tokens": 19369856} {"current_steps": 11855, "total_steps": 40000, "loss": 0.1784, "lr": 3.9925581321519955e-05, "epoch": 0.5366803232304941, "percentage": 29.64, "elapsed_time": "9:41:57", "remaining_time": "23:01:38", "throughput": 554.95, "total_tokens": 19377792} {"current_steps": 11860, "total_steps": 40000, "loss": 0.1101, "lr": 3.991770435584031e-05, "epoch": 0.5369066751171371, "percentage": 29.65, "elapsed_time": "9:42:01", "remaining_time": "23:00:56", "throughput": 555.12, "total_tokens": 19385472} {"current_steps": 11865, "total_steps": 40000, "loss": 0.1372, "lr": 3.990982508966319e-05, "epoch": 0.5371330270037801, "percentage": 29.66, "elapsed_time": "9:42:04", "remaining_time": "23:00:14", "throughput": 555.31, "total_tokens": 19393632} {"current_steps": 11870, "total_steps": 40000, "loss": 0.1502, "lr": 3.990194352420367e-05, "epoch": 0.5373593788904231, "percentage": 29.68, "elapsed_time": "9:42:07", "remaining_time": "22:59:32", "throughput": 555.48, "total_tokens": 19401344} {"current_steps": 11875, "total_steps": 40000, "loss": 0.1049, "lr": 3.9894059660677184e-05, "epoch": 0.5375857307770661, "percentage": 29.69, "elapsed_time": "9:42:10", "remaining_time": "22:58:50", "throughput": 555.65, "total_tokens": 19409248} {"current_steps": 11880, "total_steps": 40000, "loss": 0.138, "lr": 3.9886173500299526e-05, "epoch": 0.5378120826637091, "percentage": 29.7, "elapsed_time": "9:42:13", "remaining_time": "22:58:08", "throughput": 555.83, "total_tokens": 19417120} {"current_steps": 11885, "total_steps": 40000, "loss": 0.0874, "lr": 3.987828504428685e-05, "epoch": 0.5380384345503519, "percentage": 29.71, "elapsed_time": "9:42:16", "remaining_time": "22:57:26", "throughput": 556.02, "total_tokens": 19425728} {"current_steps": 11890, "total_steps": 40000, "loss": 0.1198, "lr": 3.987039429385565e-05, "epoch": 0.5382647864369949, "percentage": 29.73, "elapsed_time": "9:42:20", "remaining_time": "22:56:44", "throughput": 556.2, "total_tokens": 19433696} {"current_steps": 11895, "total_steps": 40000, "loss": 0.1638, "lr": 3.986250125022277e-05, "epoch": 0.5384911383236379, "percentage": 29.74, "elapsed_time": "9:42:23", "remaining_time": "22:56:02", "throughput": 556.39, "total_tokens": 19441888} {"current_steps": 11900, "total_steps": 40000, "loss": 0.1369, "lr": 3.985460591460544e-05, "epoch": 0.5387174902102809, "percentage": 29.75, "elapsed_time": "9:42:26", "remaining_time": "22:55:20", "throughput": 556.56, "total_tokens": 19449792} {"current_steps": 11905, "total_steps": 40000, "loss": 0.1023, "lr": 3.984670828822118e-05, "epoch": 0.5389438420969239, "percentage": 29.76, "elapsed_time": "9:42:29", "remaining_time": "22:54:38", "throughput": 556.75, "total_tokens": 19458112} {"current_steps": 11910, "total_steps": 40000, "loss": 0.1496, "lr": 3.983880837228794e-05, "epoch": 0.5391701939835668, "percentage": 29.78, "elapsed_time": "9:42:32", "remaining_time": "22:53:56", "throughput": 556.92, "total_tokens": 19465824} {"current_steps": 11915, "total_steps": 40000, "loss": 0.1162, "lr": 3.983090616802396e-05, "epoch": 0.5393965458702098, "percentage": 29.79, "elapsed_time": "9:42:35", "remaining_time": "22:53:15", "throughput": 557.11, "total_tokens": 19474432} {"current_steps": 11920, "total_steps": 40000, "loss": 0.157, "lr": 3.982300167664788e-05, "epoch": 0.5396228977568528, "percentage": 29.8, "elapsed_time": "9:42:39", "remaining_time": "22:52:33", "throughput": 557.31, "total_tokens": 19483008} {"current_steps": 11925, "total_steps": 40000, "loss": 0.1865, "lr": 3.981509489937868e-05, "epoch": 0.5398492496434958, "percentage": 29.81, "elapsed_time": "9:42:42", "remaining_time": "22:51:51", "throughput": 557.48, "total_tokens": 19490784} {"current_steps": 11930, "total_steps": 40000, "loss": 0.1015, "lr": 3.9807185837435643e-05, "epoch": 0.5400756015301388, "percentage": 29.83, "elapsed_time": "9:42:45", "remaining_time": "22:51:10", "throughput": 557.66, "total_tokens": 19498816} {"current_steps": 11935, "total_steps": 40000, "loss": 0.0938, "lr": 3.9799274492038484e-05, "epoch": 0.5403019534167818, "percentage": 29.84, "elapsed_time": "9:42:48", "remaining_time": "22:50:28", "throughput": 557.84, "total_tokens": 19507072} {"current_steps": 11940, "total_steps": 40000, "loss": 0.1161, "lr": 3.979136086440722e-05, "epoch": 0.5405283053034247, "percentage": 29.85, "elapsed_time": "9:42:51", "remaining_time": "22:49:46", "throughput": 558.02, "total_tokens": 19514976} {"current_steps": 11945, "total_steps": 40000, "loss": 0.1839, "lr": 3.9783444955762226e-05, "epoch": 0.5407546571900677, "percentage": 29.86, "elapsed_time": "9:42:55", "remaining_time": "22:49:05", "throughput": 558.21, "total_tokens": 19523328} {"current_steps": 11950, "total_steps": 40000, "loss": 0.1471, "lr": 3.977552676732424e-05, "epoch": 0.5409810090767107, "percentage": 29.88, "elapsed_time": "9:42:58", "remaining_time": "22:48:23", "throughput": 558.38, "total_tokens": 19531008} {"current_steps": 11955, "total_steps": 40000, "loss": 0.1503, "lr": 3.976760630031435e-05, "epoch": 0.5412073609633536, "percentage": 29.89, "elapsed_time": "9:43:01", "remaining_time": "22:47:42", "throughput": 558.57, "total_tokens": 19539456} {"current_steps": 11960, "total_steps": 40000, "loss": 0.186, "lr": 3.975968355595398e-05, "epoch": 0.5414337128499966, "percentage": 29.9, "elapsed_time": "9:43:04", "remaining_time": "22:47:00", "throughput": 558.75, "total_tokens": 19547456} {"current_steps": 11965, "total_steps": 40000, "loss": 0.1233, "lr": 3.9751758535464935e-05, "epoch": 0.5416600647366396, "percentage": 29.91, "elapsed_time": "9:43:07", "remaining_time": "22:46:18", "throughput": 558.92, "total_tokens": 19555360} {"current_steps": 11970, "total_steps": 40000, "loss": 0.1687, "lr": 3.9743831240069326e-05, "epoch": 0.5418864166232825, "percentage": 29.93, "elapsed_time": "9:43:10", "remaining_time": "22:45:37", "throughput": 559.11, "total_tokens": 19563648} {"current_steps": 11975, "total_steps": 40000, "loss": 0.1331, "lr": 3.9735901670989675e-05, "epoch": 0.5421127685099255, "percentage": 29.94, "elapsed_time": "9:43:14", "remaining_time": "22:44:56", "throughput": 559.29, "total_tokens": 19571936} {"current_steps": 11980, "total_steps": 40000, "loss": 0.1804, "lr": 3.97279698294488e-05, "epoch": 0.5423391203965685, "percentage": 29.95, "elapsed_time": "9:43:17", "remaining_time": "22:44:14", "throughput": 559.48, "total_tokens": 19580320} {"current_steps": 11985, "total_steps": 40000, "loss": 0.1686, "lr": 3.9720035716669876e-05, "epoch": 0.5425654722832115, "percentage": 29.96, "elapsed_time": "9:43:20", "remaining_time": "22:43:33", "throughput": 559.65, "total_tokens": 19587936} {"current_steps": 11990, "total_steps": 40000, "loss": 0.1344, "lr": 3.9712099333876474e-05, "epoch": 0.5427918241698545, "percentage": 29.98, "elapsed_time": "9:43:23", "remaining_time": "22:42:52", "throughput": 559.83, "total_tokens": 19596160} {"current_steps": 11995, "total_steps": 40000, "loss": 0.1291, "lr": 3.9704160682292475e-05, "epoch": 0.5430181760564974, "percentage": 29.99, "elapsed_time": "9:43:26", "remaining_time": "22:42:10", "throughput": 560.01, "total_tokens": 19604192} {"current_steps": 12000, "total_steps": 40000, "loss": 0.1219, "lr": 3.9696219763142106e-05, "epoch": 0.5432445279431404, "percentage": 30.0, "elapsed_time": "9:43:29", "remaining_time": "22:41:29", "throughput": 560.21, "total_tokens": 19612800} {"current_steps": 12000, "total_steps": 40000, "eval_loss": 0.13534048199653625, "epoch": 0.5432445279431404, "percentage": 30.0, "elapsed_time": "9:51:12", "remaining_time": "22:59:29", "throughput": 552.9, "total_tokens": 19612800} {"current_steps": 12005, "total_steps": 40000, "loss": 0.1684, "lr": 3.968827657764997e-05, "epoch": 0.5434708798297834, "percentage": 30.01, "elapsed_time": "9:51:16", "remaining_time": "22:58:49", "throughput": 553.06, "total_tokens": 19620640} {"current_steps": 12010, "total_steps": 40000, "loss": 0.1303, "lr": 3.9680331127041e-05, "epoch": 0.5436972317164264, "percentage": 30.03, "elapsed_time": "9:51:19", "remaining_time": "22:58:07", "throughput": 553.22, "total_tokens": 19628128} {"current_steps": 12015, "total_steps": 40000, "loss": 0.1581, "lr": 3.9672383412540495e-05, "epoch": 0.5439235836030694, "percentage": 30.04, "elapsed_time": "9:51:22", "remaining_time": "22:57:25", "throughput": 553.41, "total_tokens": 19636416} {"current_steps": 12020, "total_steps": 40000, "loss": 0.1441, "lr": 3.966443343537407e-05, "epoch": 0.5441499354897124, "percentage": 30.05, "elapsed_time": "9:51:25", "remaining_time": "22:56:43", "throughput": 553.59, "total_tokens": 19644704} {"current_steps": 12025, "total_steps": 40000, "loss": 0.135, "lr": 3.965648119676772e-05, "epoch": 0.5443762873763552, "percentage": 30.06, "elapsed_time": "9:51:29", "remaining_time": "22:56:02", "throughput": 553.77, "total_tokens": 19652992} {"current_steps": 12030, "total_steps": 40000, "loss": 0.1235, "lr": 3.96485266979478e-05, "epoch": 0.5446026392629982, "percentage": 30.08, "elapsed_time": "9:51:32", "remaining_time": "22:55:20", "throughput": 553.96, "total_tokens": 19661344} {"current_steps": 12035, "total_steps": 40000, "loss": 0.174, "lr": 3.9640569940140974e-05, "epoch": 0.5448289911496412, "percentage": 30.09, "elapsed_time": "9:51:35", "remaining_time": "22:54:39", "throughput": 554.14, "total_tokens": 19669568} {"current_steps": 12040, "total_steps": 40000, "loss": 0.1455, "lr": 3.963261092457428e-05, "epoch": 0.5450553430362842, "percentage": 30.1, "elapsed_time": "9:51:38", "remaining_time": "22:53:57", "throughput": 554.32, "total_tokens": 19677728} {"current_steps": 12045, "total_steps": 40000, "loss": 0.1255, "lr": 3.962464965247509e-05, "epoch": 0.5452816949229272, "percentage": 30.11, "elapsed_time": "9:51:41", "remaining_time": "22:53:15", "throughput": 554.51, "total_tokens": 19686112} {"current_steps": 12050, "total_steps": 40000, "loss": 0.1926, "lr": 3.9616686125071135e-05, "epoch": 0.5455080468095702, "percentage": 30.12, "elapsed_time": "9:51:45", "remaining_time": "22:52:34", "throughput": 554.68, "total_tokens": 19693984} {"current_steps": 12055, "total_steps": 40000, "loss": 0.1221, "lr": 3.9608720343590506e-05, "epoch": 0.5457343986962131, "percentage": 30.14, "elapsed_time": "9:51:48", "remaining_time": "22:51:53", "throughput": 554.85, "total_tokens": 19701920} {"current_steps": 12060, "total_steps": 40000, "loss": 0.1601, "lr": 3.960075230926161e-05, "epoch": 0.5459607505828561, "percentage": 30.15, "elapsed_time": "9:51:51", "remaining_time": "22:51:11", "throughput": 555.03, "total_tokens": 19709952} {"current_steps": 12065, "total_steps": 40000, "loss": 0.1389, "lr": 3.959278202331322e-05, "epoch": 0.5461871024694991, "percentage": 30.16, "elapsed_time": "9:51:54", "remaining_time": "22:50:30", "throughput": 555.22, "total_tokens": 19718656} {"current_steps": 12070, "total_steps": 40000, "loss": 0.1171, "lr": 3.958480948697446e-05, "epoch": 0.5464134543561421, "percentage": 30.18, "elapsed_time": "9:51:58", "remaining_time": "22:49:49", "throughput": 555.41, "total_tokens": 19727200} {"current_steps": 12075, "total_steps": 40000, "loss": 0.1476, "lr": 3.95768347014748e-05, "epoch": 0.5466398062427851, "percentage": 30.19, "elapsed_time": "9:52:01", "remaining_time": "22:49:07", "throughput": 555.6, "total_tokens": 19735552} {"current_steps": 12080, "total_steps": 40000, "loss": 0.1402, "lr": 3.956885766804404e-05, "epoch": 0.546866158129428, "percentage": 30.2, "elapsed_time": "9:52:04", "remaining_time": "22:48:26", "throughput": 555.77, "total_tokens": 19743616} {"current_steps": 12085, "total_steps": 40000, "loss": 0.1952, "lr": 3.956087838791235e-05, "epoch": 0.547092510016071, "percentage": 30.21, "elapsed_time": "9:52:07", "remaining_time": "22:47:45", "throughput": 555.95, "total_tokens": 19751744} {"current_steps": 12090, "total_steps": 40000, "loss": 0.1214, "lr": 3.955289686231022e-05, "epoch": 0.547318861902714, "percentage": 30.23, "elapsed_time": "9:52:10", "remaining_time": "22:47:03", "throughput": 556.14, "total_tokens": 19760192} {"current_steps": 12095, "total_steps": 40000, "loss": 0.1129, "lr": 3.9544913092468504e-05, "epoch": 0.5475452137893569, "percentage": 30.24, "elapsed_time": "9:52:14", "remaining_time": "22:46:22", "throughput": 556.32, "total_tokens": 19768288} {"current_steps": 12100, "total_steps": 40000, "loss": 0.1704, "lr": 3.9536927079618425e-05, "epoch": 0.5477715656759999, "percentage": 30.25, "elapsed_time": "9:52:17", "remaining_time": "22:45:41", "throughput": 556.49, "total_tokens": 19776064} {"current_steps": 12105, "total_steps": 40000, "loss": 0.1874, "lr": 3.9528938824991494e-05, "epoch": 0.5479979175626429, "percentage": 30.26, "elapsed_time": "9:52:20", "remaining_time": "22:45:00", "throughput": 556.66, "total_tokens": 19783872} {"current_steps": 12110, "total_steps": 40000, "loss": 0.0937, "lr": 3.952094832981962e-05, "epoch": 0.5482242694492858, "percentage": 30.28, "elapsed_time": "9:52:23", "remaining_time": "22:44:18", "throughput": 556.83, "total_tokens": 19791616} {"current_steps": 12115, "total_steps": 40000, "loss": 0.1221, "lr": 3.951295559533503e-05, "epoch": 0.5484506213359288, "percentage": 30.29, "elapsed_time": "9:52:26", "remaining_time": "22:43:37", "throughput": 557.01, "total_tokens": 19799840} {"current_steps": 12120, "total_steps": 40000, "loss": 0.145, "lr": 3.95049606227703e-05, "epoch": 0.5486769732225718, "percentage": 30.3, "elapsed_time": "9:52:29", "remaining_time": "22:42:56", "throughput": 557.18, "total_tokens": 19807680} {"current_steps": 12125, "total_steps": 40000, "loss": 0.1452, "lr": 3.949696341335838e-05, "epoch": 0.5489033251092148, "percentage": 30.31, "elapsed_time": "9:52:33", "remaining_time": "22:42:15", "throughput": 557.36, "total_tokens": 19815872} {"current_steps": 12130, "total_steps": 40000, "loss": 0.1348, "lr": 3.9488963968332503e-05, "epoch": 0.5491296769958578, "percentage": 30.33, "elapsed_time": "9:52:36", "remaining_time": "22:41:34", "throughput": 557.55, "total_tokens": 19824448} {"current_steps": 12135, "total_steps": 40000, "loss": 0.1494, "lr": 3.948096228892631e-05, "epoch": 0.5493560288825008, "percentage": 30.34, "elapsed_time": "9:52:39", "remaining_time": "22:40:53", "throughput": 557.73, "total_tokens": 19832576} {"current_steps": 12140, "total_steps": 40000, "loss": 0.0926, "lr": 3.947295837637375e-05, "epoch": 0.5495823807691437, "percentage": 30.35, "elapsed_time": "9:52:42", "remaining_time": "22:40:12", "throughput": 557.91, "total_tokens": 19840896} {"current_steps": 12145, "total_steps": 40000, "loss": 0.1388, "lr": 3.9464952231909135e-05, "epoch": 0.5498087326557867, "percentage": 30.36, "elapsed_time": "9:52:46", "remaining_time": "22:39:32", "throughput": 558.11, "total_tokens": 19849888} {"current_steps": 12150, "total_steps": 40000, "loss": 0.0774, "lr": 3.945694385676711e-05, "epoch": 0.5500350845424297, "percentage": 30.38, "elapsed_time": "9:52:49", "remaining_time": "22:38:50", "throughput": 558.27, "total_tokens": 19857216} {"current_steps": 12155, "total_steps": 40000, "loss": 0.1483, "lr": 3.944893325218265e-05, "epoch": 0.5502614364290727, "percentage": 30.39, "elapsed_time": "9:52:52", "remaining_time": "22:38:09", "throughput": 558.44, "total_tokens": 19865120} {"current_steps": 12160, "total_steps": 40000, "loss": 0.0944, "lr": 3.944092041939112e-05, "epoch": 0.5504877883157157, "percentage": 30.4, "elapsed_time": "9:52:55", "remaining_time": "22:37:29", "throughput": 558.65, "total_tokens": 19874208} {"current_steps": 12165, "total_steps": 40000, "loss": 0.0827, "lr": 3.943290535962818e-05, "epoch": 0.5507141402023585, "percentage": 30.41, "elapsed_time": "9:52:58", "remaining_time": "22:36:48", "throughput": 558.84, "total_tokens": 19883072} {"current_steps": 12170, "total_steps": 40000, "loss": 0.1423, "lr": 3.942488807412985e-05, "epoch": 0.5509404920890015, "percentage": 30.43, "elapsed_time": "9:53:02", "remaining_time": "22:36:08", "throughput": 559.03, "total_tokens": 19891296} {"current_steps": 12175, "total_steps": 40000, "loss": 0.1384, "lr": 3.941686856413251e-05, "epoch": 0.5511668439756445, "percentage": 30.44, "elapsed_time": "9:53:05", "remaining_time": "22:35:27", "throughput": 559.19, "total_tokens": 19899008} {"current_steps": 12180, "total_steps": 40000, "loss": 0.1122, "lr": 3.9408846830872874e-05, "epoch": 0.5513931958622875, "percentage": 30.45, "elapsed_time": "9:53:08", "remaining_time": "22:34:46", "throughput": 559.37, "total_tokens": 19906880} {"current_steps": 12185, "total_steps": 40000, "loss": 0.1105, "lr": 3.940082287558798e-05, "epoch": 0.5516195477489305, "percentage": 30.46, "elapsed_time": "9:53:11", "remaining_time": "22:34:05", "throughput": 559.55, "total_tokens": 19915328} {"current_steps": 12190, "total_steps": 40000, "loss": 0.1159, "lr": 3.939279669951522e-05, "epoch": 0.5518458996355735, "percentage": 30.48, "elapsed_time": "9:53:14", "remaining_time": "22:33:25", "throughput": 559.75, "total_tokens": 19924096} {"current_steps": 12195, "total_steps": 40000, "loss": 0.157, "lr": 3.938476830389234e-05, "epoch": 0.5520722515222164, "percentage": 30.49, "elapsed_time": "9:53:18", "remaining_time": "22:32:44", "throughput": 559.96, "total_tokens": 19933408} {"current_steps": 12200, "total_steps": 40000, "loss": 0.1358, "lr": 3.937673768995742e-05, "epoch": 0.5522986034088594, "percentage": 30.5, "elapsed_time": "9:53:21", "remaining_time": "22:32:04", "throughput": 560.13, "total_tokens": 19941216} {"current_steps": 12200, "total_steps": 40000, "eval_loss": 0.13425643742084503, "epoch": 0.5522986034088594, "percentage": 30.5, "elapsed_time": "10:01:03", "remaining_time": "22:49:38", "throughput": 552.94, "total_tokens": 19941216} {"current_steps": 12205, "total_steps": 40000, "loss": 0.1285, "lr": 3.936870485894888e-05, "epoch": 0.5525249552955024, "percentage": 30.51, "elapsed_time": "10:01:09", "remaining_time": "22:49:01", "throughput": 553.09, "total_tokens": 19949440} {"current_steps": 12210, "total_steps": 40000, "loss": 0.1193, "lr": 3.9360669812105475e-05, "epoch": 0.5527513071821454, "percentage": 30.53, "elapsed_time": "10:01:12", "remaining_time": "22:48:20", "throughput": 553.26, "total_tokens": 19957216} {"current_steps": 12215, "total_steps": 40000, "loss": 0.1588, "lr": 3.9352632550666325e-05, "epoch": 0.5529776590687884, "percentage": 30.54, "elapsed_time": "10:01:15", "remaining_time": "22:47:39", "throughput": 553.44, "total_tokens": 19965664} {"current_steps": 12220, "total_steps": 40000, "loss": 0.1229, "lr": 3.9344593075870866e-05, "epoch": 0.5532040109554314, "percentage": 30.55, "elapsed_time": "10:01:18", "remaining_time": "22:46:58", "throughput": 553.62, "total_tokens": 19973792} {"current_steps": 12225, "total_steps": 40000, "loss": 0.1104, "lr": 3.933655138895889e-05, "epoch": 0.5534303628420743, "percentage": 30.56, "elapsed_time": "10:01:21", "remaining_time": "22:46:17", "throughput": 553.8, "total_tokens": 19982176} {"current_steps": 12230, "total_steps": 40000, "loss": 0.1477, "lr": 3.932850749117053e-05, "epoch": 0.5536567147287172, "percentage": 30.58, "elapsed_time": "10:01:25", "remaining_time": "22:45:36", "throughput": 553.99, "total_tokens": 19990592} {"current_steps": 12235, "total_steps": 40000, "loss": 0.1123, "lr": 3.932046138374624e-05, "epoch": 0.5538830666153602, "percentage": 30.59, "elapsed_time": "10:01:28", "remaining_time": "22:44:55", "throughput": 554.16, "total_tokens": 19998688} {"current_steps": 12240, "total_steps": 40000, "loss": 0.0983, "lr": 3.9312413067926854e-05, "epoch": 0.5541094185020032, "percentage": 30.6, "elapsed_time": "10:01:31", "remaining_time": "22:44:14", "throughput": 554.33, "total_tokens": 20006528} {"current_steps": 12245, "total_steps": 40000, "loss": 0.1314, "lr": 3.9304362544953506e-05, "epoch": 0.5543357703886462, "percentage": 30.61, "elapsed_time": "10:01:34", "remaining_time": "22:43:33", "throughput": 554.51, "total_tokens": 20014656} {"current_steps": 12250, "total_steps": 40000, "loss": 0.124, "lr": 3.929630981606769e-05, "epoch": 0.5545621222752891, "percentage": 30.63, "elapsed_time": "10:01:37", "remaining_time": "22:42:52", "throughput": 554.68, "total_tokens": 20022528} {"current_steps": 12255, "total_steps": 40000, "loss": 0.0936, "lr": 3.928825488251124e-05, "epoch": 0.5547884741619321, "percentage": 30.64, "elapsed_time": "10:01:40", "remaining_time": "22:42:11", "throughput": 554.85, "total_tokens": 20030496} {"current_steps": 12260, "total_steps": 40000, "loss": 0.1624, "lr": 3.9280197745526344e-05, "epoch": 0.5550148260485751, "percentage": 30.65, "elapsed_time": "10:01:43", "remaining_time": "22:41:30", "throughput": 555.02, "total_tokens": 20038304} {"current_steps": 12265, "total_steps": 40000, "loss": 0.1302, "lr": 3.9272138406355495e-05, "epoch": 0.5552411779352181, "percentage": 30.66, "elapsed_time": "10:01:47", "remaining_time": "22:40:49", "throughput": 555.21, "total_tokens": 20047232} {"current_steps": 12270, "total_steps": 40000, "loss": 0.1357, "lr": 3.926407686624154e-05, "epoch": 0.5554675298218611, "percentage": 30.68, "elapsed_time": "10:01:50", "remaining_time": "22:40:08", "throughput": 555.39, "total_tokens": 20055328} {"current_steps": 12275, "total_steps": 40000, "loss": 0.1529, "lr": 3.9256013126427684e-05, "epoch": 0.5556938817085041, "percentage": 30.69, "elapsed_time": "10:01:53", "remaining_time": "22:39:28", "throughput": 555.57, "total_tokens": 20063616} {"current_steps": 12280, "total_steps": 40000, "loss": 0.1534, "lr": 3.9247947188157455e-05, "epoch": 0.555920233595147, "percentage": 30.7, "elapsed_time": "10:01:56", "remaining_time": "22:38:47", "throughput": 555.75, "total_tokens": 20071840} {"current_steps": 12285, "total_steps": 40000, "loss": 0.11, "lr": 3.9239879052674715e-05, "epoch": 0.55614658548179, "percentage": 30.71, "elapsed_time": "10:01:59", "remaining_time": "22:38:06", "throughput": 555.93, "total_tokens": 20080224} {"current_steps": 12290, "total_steps": 40000, "loss": 0.1152, "lr": 3.9231808721223673e-05, "epoch": 0.556372937368433, "percentage": 30.73, "elapsed_time": "10:02:03", "remaining_time": "22:37:26", "throughput": 556.11, "total_tokens": 20088512} {"current_steps": 12295, "total_steps": 40000, "loss": 0.1494, "lr": 3.9223736195048886e-05, "epoch": 0.556599289255076, "percentage": 30.74, "elapsed_time": "10:02:06", "remaining_time": "22:36:45", "throughput": 556.28, "total_tokens": 20096192} {"current_steps": 12300, "total_steps": 40000, "loss": 0.1173, "lr": 3.921566147539523e-05, "epoch": 0.556825641141719, "percentage": 30.75, "elapsed_time": "10:02:09", "remaining_time": "22:36:04", "throughput": 556.45, "total_tokens": 20104096} {"current_steps": 12305, "total_steps": 40000, "loss": 0.145, "lr": 3.920758456350792e-05, "epoch": 0.5570519930283618, "percentage": 30.76, "elapsed_time": "10:02:12", "remaining_time": "22:35:23", "throughput": 556.62, "total_tokens": 20112064} {"current_steps": 12310, "total_steps": 40000, "loss": 0.1347, "lr": 3.919950546063253e-05, "epoch": 0.5572783449150048, "percentage": 30.78, "elapsed_time": "10:02:15", "remaining_time": "22:34:43", "throughput": 556.79, "total_tokens": 20119808} {"current_steps": 12315, "total_steps": 40000, "loss": 0.191, "lr": 3.919142416801496e-05, "epoch": 0.5575046968016478, "percentage": 30.79, "elapsed_time": "10:02:18", "remaining_time": "22:34:02", "throughput": 556.97, "total_tokens": 20128256} {"current_steps": 12320, "total_steps": 40000, "loss": 0.1537, "lr": 3.918334068690144e-05, "epoch": 0.5577310486882908, "percentage": 30.8, "elapsed_time": "10:02:22", "remaining_time": "22:33:22", "throughput": 557.15, "total_tokens": 20136608} {"current_steps": 12325, "total_steps": 40000, "loss": 0.1056, "lr": 3.917525501853855e-05, "epoch": 0.5579574005749338, "percentage": 30.81, "elapsed_time": "10:02:25", "remaining_time": "22:32:41", "throughput": 557.33, "total_tokens": 20144768} {"current_steps": 12330, "total_steps": 40000, "loss": 0.1412, "lr": 3.916716716417319e-05, "epoch": 0.5581837524615768, "percentage": 30.83, "elapsed_time": "10:02:28", "remaining_time": "22:32:01", "throughput": 557.49, "total_tokens": 20152256} {"current_steps": 12335, "total_steps": 40000, "loss": 0.1651, "lr": 3.915907712505263e-05, "epoch": 0.5584101043482197, "percentage": 30.84, "elapsed_time": "10:02:31", "remaining_time": "22:31:20", "throughput": 557.66, "total_tokens": 20160256} {"current_steps": 12340, "total_steps": 40000, "loss": 0.0933, "lr": 3.915098490242444e-05, "epoch": 0.5586364562348627, "percentage": 30.85, "elapsed_time": "10:02:34", "remaining_time": "22:30:40", "throughput": 557.83, "total_tokens": 20168224} {"current_steps": 12345, "total_steps": 40000, "loss": 0.0931, "lr": 3.914289049753654e-05, "epoch": 0.5588628081215057, "percentage": 30.86, "elapsed_time": "10:02:37", "remaining_time": "22:29:59", "throughput": 558.0, "total_tokens": 20176128} {"current_steps": 12350, "total_steps": 40000, "loss": 0.1332, "lr": 3.913479391163719e-05, "epoch": 0.5590891600081487, "percentage": 30.88, "elapsed_time": "10:02:41", "remaining_time": "22:29:19", "throughput": 558.18, "total_tokens": 20184384} {"current_steps": 12355, "total_steps": 40000, "loss": 0.1278, "lr": 3.9126695145975e-05, "epoch": 0.5593155118947917, "percentage": 30.89, "elapsed_time": "10:02:44", "remaining_time": "22:28:39", "throughput": 558.36, "total_tokens": 20192640} {"current_steps": 12360, "total_steps": 40000, "loss": 0.16, "lr": 3.911859420179889e-05, "epoch": 0.5595418637814347, "percentage": 30.9, "elapsed_time": "10:02:47", "remaining_time": "22:27:59", "throughput": 558.53, "total_tokens": 20200448} {"current_steps": 12365, "total_steps": 40000, "loss": 0.133, "lr": 3.911049108035813e-05, "epoch": 0.5597682156680776, "percentage": 30.91, "elapsed_time": "10:02:50", "remaining_time": "22:27:18", "throughput": 558.69, "total_tokens": 20208224} {"current_steps": 12370, "total_steps": 40000, "loss": 0.1329, "lr": 3.910238578290232e-05, "epoch": 0.5599945675547205, "percentage": 30.93, "elapsed_time": "10:02:53", "remaining_time": "22:26:38", "throughput": 558.86, "total_tokens": 20216032} {"current_steps": 12375, "total_steps": 40000, "loss": 0.1437, "lr": 3.90942783106814e-05, "epoch": 0.5602209194413635, "percentage": 30.94, "elapsed_time": "10:02:56", "remaining_time": "22:25:58", "throughput": 559.04, "total_tokens": 20224320} {"current_steps": 12380, "total_steps": 40000, "loss": 0.1344, "lr": 3.908616866494564e-05, "epoch": 0.5604472713280065, "percentage": 30.95, "elapsed_time": "10:02:59", "remaining_time": "22:25:18", "throughput": 559.22, "total_tokens": 20232672} {"current_steps": 12385, "total_steps": 40000, "loss": 0.1425, "lr": 3.907805684694566e-05, "epoch": 0.5606736232146495, "percentage": 30.96, "elapsed_time": "10:03:03", "remaining_time": "22:24:37", "throughput": 559.38, "total_tokens": 20240096} {"current_steps": 12390, "total_steps": 40000, "loss": 0.1525, "lr": 3.90699428579324e-05, "epoch": 0.5608999751012924, "percentage": 30.98, "elapsed_time": "10:03:06", "remaining_time": "22:23:57", "throughput": 559.55, "total_tokens": 20248032} {"current_steps": 12395, "total_steps": 40000, "loss": 0.1159, "lr": 3.906182669915713e-05, "epoch": 0.5611263269879354, "percentage": 30.99, "elapsed_time": "10:03:09", "remaining_time": "22:23:17", "throughput": 559.73, "total_tokens": 20256352} {"current_steps": 12400, "total_steps": 40000, "loss": 0.1107, "lr": 3.9053708371871476e-05, "epoch": 0.5613526788745784, "percentage": 31.0, "elapsed_time": "10:03:12", "remaining_time": "22:22:37", "throughput": 559.91, "total_tokens": 20264608} {"current_steps": 12400, "total_steps": 40000, "eval_loss": 0.134205162525177, "epoch": 0.5613526788745784, "percentage": 31.0, "elapsed_time": "10:10:55", "remaining_time": "22:39:47", "throughput": 552.84, "total_tokens": 20264608} {"current_steps": 12405, "total_steps": 40000, "loss": 0.1111, "lr": 3.904558787732738e-05, "epoch": 0.5615790307612214, "percentage": 31.01, "elapsed_time": "10:10:59", "remaining_time": "22:39:08", "throughput": 553.01, "total_tokens": 20272928} {"current_steps": 12410, "total_steps": 40000, "loss": 0.1602, "lr": 3.9037465216777135e-05, "epoch": 0.5618053826478644, "percentage": 31.03, "elapsed_time": "10:11:02", "remaining_time": "22:38:27", "throughput": 553.18, "total_tokens": 20280928} {"current_steps": 12415, "total_steps": 40000, "loss": 0.1662, "lr": 3.902934039147334e-05, "epoch": 0.5620317345345074, "percentage": 31.04, "elapsed_time": "10:11:05", "remaining_time": "22:37:47", "throughput": 553.35, "total_tokens": 20288896} {"current_steps": 12420, "total_steps": 40000, "loss": 0.1225, "lr": 3.902121340266894e-05, "epoch": 0.5622580864211503, "percentage": 31.05, "elapsed_time": "10:11:08", "remaining_time": "22:37:06", "throughput": 553.53, "total_tokens": 20297216} {"current_steps": 12425, "total_steps": 40000, "loss": 0.1689, "lr": 3.9013084251617246e-05, "epoch": 0.5624844383077933, "percentage": 31.06, "elapsed_time": "10:11:12", "remaining_time": "22:36:26", "throughput": 553.72, "total_tokens": 20306080} {"current_steps": 12430, "total_steps": 40000, "loss": 0.1546, "lr": 3.9004952939571865e-05, "epoch": 0.5627107901944363, "percentage": 31.08, "elapsed_time": "10:11:15", "remaining_time": "22:35:46", "throughput": 553.89, "total_tokens": 20314080} {"current_steps": 12435, "total_steps": 40000, "loss": 0.1144, "lr": 3.899681946778673e-05, "epoch": 0.5629371420810793, "percentage": 31.09, "elapsed_time": "10:11:18", "remaining_time": "22:35:06", "throughput": 554.08, "total_tokens": 20322720} {"current_steps": 12440, "total_steps": 40000, "loss": 0.1213, "lr": 3.898868383751615e-05, "epoch": 0.5631634939677223, "percentage": 31.1, "elapsed_time": "10:11:21", "remaining_time": "22:34:25", "throughput": 554.25, "total_tokens": 20330784} {"current_steps": 12445, "total_steps": 40000, "loss": 0.152, "lr": 3.8980546050014724e-05, "epoch": 0.5633898458543652, "percentage": 31.11, "elapsed_time": "10:11:24", "remaining_time": "22:33:45", "throughput": 554.42, "total_tokens": 20338624} {"current_steps": 12450, "total_steps": 40000, "loss": 0.0859, "lr": 3.897240610653741e-05, "epoch": 0.5636161977410081, "percentage": 31.13, "elapsed_time": "10:11:27", "remaining_time": "22:33:04", "throughput": 554.59, "total_tokens": 20346784} {"current_steps": 12455, "total_steps": 40000, "loss": 0.1312, "lr": 3.896426400833948e-05, "epoch": 0.5638425496276511, "percentage": 31.14, "elapsed_time": "10:11:31", "remaining_time": "22:32:24", "throughput": 554.75, "total_tokens": 20354464} {"current_steps": 12460, "total_steps": 40000, "loss": 0.1557, "lr": 3.895611975667656e-05, "epoch": 0.5640689015142941, "percentage": 31.15, "elapsed_time": "10:11:34", "remaining_time": "22:31:44", "throughput": 554.92, "total_tokens": 20362208} {"current_steps": 12465, "total_steps": 40000, "loss": 0.1234, "lr": 3.8947973352804584e-05, "epoch": 0.5642952534009371, "percentage": 31.16, "elapsed_time": "10:11:37", "remaining_time": "22:31:03", "throughput": 555.08, "total_tokens": 20369792} {"current_steps": 12470, "total_steps": 40000, "loss": 0.1683, "lr": 3.893982479797984e-05, "epoch": 0.5645216052875801, "percentage": 31.18, "elapsed_time": "10:11:40", "remaining_time": "22:30:23", "throughput": 555.25, "total_tokens": 20377952} {"current_steps": 12475, "total_steps": 40000, "loss": 0.0975, "lr": 3.8931674093458926e-05, "epoch": 0.564747957174223, "percentage": 31.19, "elapsed_time": "10:11:43", "remaining_time": "22:29:43", "throughput": 555.41, "total_tokens": 20385376} {"current_steps": 12480, "total_steps": 40000, "loss": 0.1028, "lr": 3.89235212404988e-05, "epoch": 0.564974309060866, "percentage": 31.2, "elapsed_time": "10:11:46", "remaining_time": "22:29:02", "throughput": 555.58, "total_tokens": 20393376} {"current_steps": 12485, "total_steps": 40000, "loss": 0.1696, "lr": 3.891536624035672e-05, "epoch": 0.565200660947509, "percentage": 31.21, "elapsed_time": "10:11:49", "remaining_time": "22:28:22", "throughput": 555.75, "total_tokens": 20401600} {"current_steps": 12490, "total_steps": 40000, "loss": 0.1142, "lr": 3.8907209094290295e-05, "epoch": 0.565427012834152, "percentage": 31.23, "elapsed_time": "10:11:53", "remaining_time": "22:27:42", "throughput": 555.94, "total_tokens": 20410240} {"current_steps": 12495, "total_steps": 40000, "loss": 0.1258, "lr": 3.8899049803557466e-05, "epoch": 0.565653364720795, "percentage": 31.24, "elapsed_time": "10:11:56", "remaining_time": "22:27:03", "throughput": 556.14, "total_tokens": 20419360} {"current_steps": 12500, "total_steps": 40000, "loss": 0.1203, "lr": 3.889088836941648e-05, "epoch": 0.565879716607438, "percentage": 31.25, "elapsed_time": "10:11:59", "remaining_time": "22:26:22", "throughput": 556.3, "total_tokens": 20427200} {"current_steps": 12505, "total_steps": 40000, "loss": 0.1221, "lr": 3.8882724793125946e-05, "epoch": 0.5661060684940808, "percentage": 31.26, "elapsed_time": "10:12:02", "remaining_time": "22:25:43", "throughput": 556.49, "total_tokens": 20435744} {"current_steps": 12510, "total_steps": 40000, "loss": 0.1151, "lr": 3.8874559075944794e-05, "epoch": 0.5663324203807238, "percentage": 31.27, "elapsed_time": "10:12:06", "remaining_time": "22:25:03", "throughput": 556.66, "total_tokens": 20444096} {"current_steps": 12515, "total_steps": 40000, "loss": 0.1219, "lr": 3.886639121913227e-05, "epoch": 0.5665587722673668, "percentage": 31.29, "elapsed_time": "10:12:09", "remaining_time": "22:24:23", "throughput": 556.83, "total_tokens": 20451872} {"current_steps": 12520, "total_steps": 40000, "loss": 0.1434, "lr": 3.885822122394797e-05, "epoch": 0.5667851241540098, "percentage": 31.3, "elapsed_time": "10:12:12", "remaining_time": "22:23:43", "throughput": 556.98, "total_tokens": 20459264} {"current_steps": 12525, "total_steps": 40000, "loss": 0.1662, "lr": 3.8850049091651794e-05, "epoch": 0.5670114760406528, "percentage": 31.31, "elapsed_time": "10:12:15", "remaining_time": "22:23:03", "throughput": 557.16, "total_tokens": 20467552} {"current_steps": 12530, "total_steps": 40000, "loss": 0.1169, "lr": 3.8841874823504e-05, "epoch": 0.5672378279272958, "percentage": 31.32, "elapsed_time": "10:12:18", "remaining_time": "22:22:24", "throughput": 557.35, "total_tokens": 20476288} {"current_steps": 12535, "total_steps": 40000, "loss": 0.1332, "lr": 3.8833698420765157e-05, "epoch": 0.5674641798139387, "percentage": 31.34, "elapsed_time": "10:12:22", "remaining_time": "22:21:44", "throughput": 557.52, "total_tokens": 20484608} {"current_steps": 12540, "total_steps": 40000, "loss": 0.1269, "lr": 3.882551988469618e-05, "epoch": 0.5676905317005817, "percentage": 31.35, "elapsed_time": "10:12:25", "remaining_time": "22:21:04", "throughput": 557.7, "total_tokens": 20492832} {"current_steps": 12545, "total_steps": 40000, "loss": 0.1466, "lr": 3.881733921655829e-05, "epoch": 0.5679168835872247, "percentage": 31.36, "elapsed_time": "10:12:28", "remaining_time": "22:20:24", "throughput": 557.87, "total_tokens": 20500896} {"current_steps": 12550, "total_steps": 40000, "loss": 0.1083, "lr": 3.8809156417613054e-05, "epoch": 0.5681432354738677, "percentage": 31.37, "elapsed_time": "10:12:31", "remaining_time": "22:19:45", "throughput": 558.05, "total_tokens": 20509280} {"current_steps": 12555, "total_steps": 40000, "loss": 0.1272, "lr": 3.8800971489122364e-05, "epoch": 0.5683695873605107, "percentage": 31.39, "elapsed_time": "10:12:34", "remaining_time": "22:19:05", "throughput": 558.22, "total_tokens": 20517440} {"current_steps": 12560, "total_steps": 40000, "loss": 0.1133, "lr": 3.8792784432348434e-05, "epoch": 0.5685959392471536, "percentage": 31.4, "elapsed_time": "10:12:37", "remaining_time": "22:18:25", "throughput": 558.39, "total_tokens": 20525152} {"current_steps": 12565, "total_steps": 40000, "loss": 0.1506, "lr": 3.878459524855381e-05, "epoch": 0.5688222911337966, "percentage": 31.41, "elapsed_time": "10:12:40", "remaining_time": "22:17:45", "throughput": 558.54, "total_tokens": 20532480} {"current_steps": 12570, "total_steps": 40000, "loss": 0.073, "lr": 3.8776403939001384e-05, "epoch": 0.5690486430204396, "percentage": 31.42, "elapsed_time": "10:12:44", "remaining_time": "22:17:05", "throughput": 558.72, "total_tokens": 20540704} {"current_steps": 12575, "total_steps": 40000, "loss": 0.1459, "lr": 3.876821050495433e-05, "epoch": 0.5692749949070826, "percentage": 31.44, "elapsed_time": "10:12:47", "remaining_time": "22:16:26", "throughput": 558.88, "total_tokens": 20548512} {"current_steps": 12580, "total_steps": 40000, "loss": 0.0801, "lr": 3.87600149476762e-05, "epoch": 0.5695013467937255, "percentage": 31.45, "elapsed_time": "10:12:50", "remaining_time": "22:15:46", "throughput": 559.05, "total_tokens": 20556288} {"current_steps": 12585, "total_steps": 40000, "loss": 0.1611, "lr": 3.8751817268430843e-05, "epoch": 0.5697276986803685, "percentage": 31.46, "elapsed_time": "10:12:53", "remaining_time": "22:15:06", "throughput": 559.21, "total_tokens": 20564224} {"current_steps": 12590, "total_steps": 40000, "loss": 0.1118, "lr": 3.8743617468482464e-05, "epoch": 0.5699540505670114, "percentage": 31.47, "elapsed_time": "10:12:56", "remaining_time": "22:14:27", "throughput": 559.38, "total_tokens": 20572288} {"current_steps": 12595, "total_steps": 40000, "loss": 0.1625, "lr": 3.8735415549095535e-05, "epoch": 0.5701804024536544, "percentage": 31.49, "elapsed_time": "10:12:59", "remaining_time": "22:13:48", "throughput": 559.56, "total_tokens": 20580480} {"current_steps": 12600, "total_steps": 40000, "loss": 0.122, "lr": 3.8727211511534934e-05, "epoch": 0.5704067543402974, "percentage": 31.5, "elapsed_time": "10:13:03", "remaining_time": "22:13:08", "throughput": 559.75, "total_tokens": 20589280} {"current_steps": 12600, "total_steps": 40000, "eval_loss": 0.13378699123859406, "epoch": 0.5704067543402974, "percentage": 31.5, "elapsed_time": "10:20:45", "remaining_time": "22:29:55", "throughput": 552.79, "total_tokens": 20589280} {"current_steps": 12605, "total_steps": 40000, "loss": 0.1826, "lr": 3.8719005357065804e-05, "epoch": 0.5706331062269404, "percentage": 31.51, "elapsed_time": "10:20:50", "remaining_time": "22:29:17", "throughput": 552.95, "total_tokens": 20597728} {"current_steps": 12610, "total_steps": 40000, "loss": 0.0884, "lr": 3.8710797086953645e-05, "epoch": 0.5708594581135834, "percentage": 31.52, "elapsed_time": "10:20:53", "remaining_time": "22:28:37", "throughput": 553.12, "total_tokens": 20605696} {"current_steps": 12615, "total_steps": 40000, "loss": 0.114, "lr": 3.870258670246427e-05, "epoch": 0.5710858100002264, "percentage": 31.54, "elapsed_time": "10:20:56", "remaining_time": "22:27:57", "throughput": 553.29, "total_tokens": 20613920} {"current_steps": 12620, "total_steps": 40000, "loss": 0.126, "lr": 3.869437420486384e-05, "epoch": 0.5713121618868693, "percentage": 31.55, "elapsed_time": "10:20:59", "remaining_time": "22:27:17", "throughput": 553.47, "total_tokens": 20622144} {"current_steps": 12625, "total_steps": 40000, "loss": 0.1439, "lr": 3.8686159595418805e-05, "epoch": 0.5715385137735123, "percentage": 31.56, "elapsed_time": "10:21:03", "remaining_time": "22:26:38", "throughput": 553.66, "total_tokens": 20631200} {"current_steps": 12630, "total_steps": 40000, "loss": 0.1596, "lr": 3.867794287539597e-05, "epoch": 0.5717648656601553, "percentage": 31.57, "elapsed_time": "10:21:06", "remaining_time": "22:25:58", "throughput": 553.83, "total_tokens": 20639200} {"current_steps": 12635, "total_steps": 40000, "loss": 0.1013, "lr": 3.866972404606245e-05, "epoch": 0.5719912175467983, "percentage": 31.59, "elapsed_time": "10:21:09", "remaining_time": "22:25:18", "throughput": 554.0, "total_tokens": 20647328} {"current_steps": 12640, "total_steps": 40000, "loss": 0.1524, "lr": 3.866150310868571e-05, "epoch": 0.5722175694334413, "percentage": 31.6, "elapsed_time": "10:21:12", "remaining_time": "22:24:38", "throughput": 554.18, "total_tokens": 20655648} {"current_steps": 12645, "total_steps": 40000, "loss": 0.104, "lr": 3.8653280064533506e-05, "epoch": 0.5724439213200841, "percentage": 31.61, "elapsed_time": "10:21:15", "remaining_time": "22:23:58", "throughput": 554.34, "total_tokens": 20663424} {"current_steps": 12650, "total_steps": 40000, "loss": 0.1576, "lr": 3.864505491487394e-05, "epoch": 0.5726702732067271, "percentage": 31.62, "elapsed_time": "10:21:19", "remaining_time": "22:23:19", "throughput": 554.52, "total_tokens": 20672064} {"current_steps": 12655, "total_steps": 40000, "loss": 0.1854, "lr": 3.8636827660975414e-05, "epoch": 0.5728966250933701, "percentage": 31.64, "elapsed_time": "10:21:22", "remaining_time": "22:22:40", "throughput": 554.71, "total_tokens": 20680928} {"current_steps": 12660, "total_steps": 40000, "loss": 0.0813, "lr": 3.862859830410671e-05, "epoch": 0.5731229769800131, "percentage": 31.65, "elapsed_time": "10:21:25", "remaining_time": "22:22:00", "throughput": 554.89, "total_tokens": 20689408} {"current_steps": 12665, "total_steps": 40000, "loss": 0.1596, "lr": 3.862036684553688e-05, "epoch": 0.5733493288666561, "percentage": 31.66, "elapsed_time": "10:21:28", "remaining_time": "22:21:20", "throughput": 555.07, "total_tokens": 20697792} {"current_steps": 12670, "total_steps": 40000, "loss": 0.1029, "lr": 3.8612133286535314e-05, "epoch": 0.5735756807532991, "percentage": 31.67, "elapsed_time": "10:21:32", "remaining_time": "22:20:41", "throughput": 555.24, "total_tokens": 20705984} {"current_steps": 12675, "total_steps": 40000, "loss": 0.1246, "lr": 3.860389762837173e-05, "epoch": 0.573802032639942, "percentage": 31.69, "elapsed_time": "10:21:35", "remaining_time": "22:20:01", "throughput": 555.41, "total_tokens": 20714336} {"current_steps": 12680, "total_steps": 40000, "loss": 0.1324, "lr": 3.859565987231618e-05, "epoch": 0.574028384526585, "percentage": 31.7, "elapsed_time": "10:21:38", "remaining_time": "22:19:22", "throughput": 555.59, "total_tokens": 20722656} {"current_steps": 12685, "total_steps": 40000, "loss": 0.2051, "lr": 3.858742001963902e-05, "epoch": 0.574254736413228, "percentage": 31.71, "elapsed_time": "10:21:41", "remaining_time": "22:18:42", "throughput": 555.76, "total_tokens": 20730816} {"current_steps": 12690, "total_steps": 40000, "loss": 0.1258, "lr": 3.857917807161094e-05, "epoch": 0.574481088299871, "percentage": 31.72, "elapsed_time": "10:21:44", "remaining_time": "22:18:03", "throughput": 555.91, "total_tokens": 20738112} {"current_steps": 12695, "total_steps": 40000, "loss": 0.1035, "lr": 3.857093402950296e-05, "epoch": 0.574707440186514, "percentage": 31.74, "elapsed_time": "10:21:48", "remaining_time": "22:17:23", "throughput": 556.07, "total_tokens": 20746080} {"current_steps": 12700, "total_steps": 40000, "loss": 0.1514, "lr": 3.8562687894586414e-05, "epoch": 0.574933792073157, "percentage": 31.75, "elapsed_time": "10:21:51", "remaining_time": "22:16:44", "throughput": 556.23, "total_tokens": 20753696} {"current_steps": 12705, "total_steps": 40000, "loss": 0.1541, "lr": 3.8554439668132946e-05, "epoch": 0.5751601439597999, "percentage": 31.76, "elapsed_time": "10:21:54", "remaining_time": "22:16:04", "throughput": 556.39, "total_tokens": 20761472} {"current_steps": 12710, "total_steps": 40000, "loss": 0.149, "lr": 3.854618935141455e-05, "epoch": 0.5753864958464429, "percentage": 31.77, "elapsed_time": "10:21:57", "remaining_time": "22:15:25", "throughput": 556.56, "total_tokens": 20769536} {"current_steps": 12715, "total_steps": 40000, "loss": 0.138, "lr": 3.8537936945703525e-05, "epoch": 0.5756128477330859, "percentage": 31.79, "elapsed_time": "10:22:00", "remaining_time": "22:14:45", "throughput": 556.72, "total_tokens": 20777088} {"current_steps": 12720, "total_steps": 40000, "loss": 0.101, "lr": 3.852968245227249e-05, "epoch": 0.5758391996197288, "percentage": 31.8, "elapsed_time": "10:22:03", "remaining_time": "22:14:06", "throughput": 556.89, "total_tokens": 20785312} {"current_steps": 12725, "total_steps": 40000, "loss": 0.1133, "lr": 3.85214258723944e-05, "epoch": 0.5760655515063718, "percentage": 31.81, "elapsed_time": "10:22:06", "remaining_time": "22:13:27", "throughput": 557.07, "total_tokens": 20793856} {"current_steps": 12730, "total_steps": 40000, "loss": 0.136, "lr": 3.8513167207342524e-05, "epoch": 0.5762919033930147, "percentage": 31.82, "elapsed_time": "10:22:10", "remaining_time": "22:12:48", "throughput": 557.26, "total_tokens": 20802752} {"current_steps": 12735, "total_steps": 40000, "loss": 0.1358, "lr": 3.850490645839044e-05, "epoch": 0.5765182552796577, "percentage": 31.84, "elapsed_time": "10:22:13", "remaining_time": "22:12:08", "throughput": 557.42, "total_tokens": 20810528} {"current_steps": 12740, "total_steps": 40000, "loss": 0.1234, "lr": 3.849664362681207e-05, "epoch": 0.5767446071663007, "percentage": 31.85, "elapsed_time": "10:22:16", "remaining_time": "22:11:29", "throughput": 557.59, "total_tokens": 20818464} {"current_steps": 12745, "total_steps": 40000, "loss": 0.1188, "lr": 3.848837871388165e-05, "epoch": 0.5769709590529437, "percentage": 31.86, "elapsed_time": "10:22:19", "remaining_time": "22:10:50", "throughput": 557.77, "total_tokens": 20826912} {"current_steps": 12750, "total_steps": 40000, "loss": 0.1215, "lr": 3.848011172087371e-05, "epoch": 0.5771973109395867, "percentage": 31.87, "elapsed_time": "10:22:23", "remaining_time": "22:10:11", "throughput": 557.95, "total_tokens": 20835392} {"current_steps": 12755, "total_steps": 40000, "loss": 0.0799, "lr": 3.847184264906315e-05, "epoch": 0.5774236628262297, "percentage": 31.89, "elapsed_time": "10:22:26", "remaining_time": "22:09:32", "throughput": 558.11, "total_tokens": 20843232} {"current_steps": 12760, "total_steps": 40000, "loss": 0.1691, "lr": 3.846357149972516e-05, "epoch": 0.5776500147128726, "percentage": 31.9, "elapsed_time": "10:22:29", "remaining_time": "22:08:53", "throughput": 558.27, "total_tokens": 20850848} {"current_steps": 12765, "total_steps": 40000, "loss": 0.14, "lr": 3.8455298274135246e-05, "epoch": 0.5778763665995156, "percentage": 31.91, "elapsed_time": "10:22:32", "remaining_time": "22:08:13", "throughput": 558.43, "total_tokens": 20858656} {"current_steps": 12770, "total_steps": 40000, "loss": 0.1503, "lr": 3.8447022973569254e-05, "epoch": 0.5781027184861586, "percentage": 31.92, "elapsed_time": "10:22:35", "remaining_time": "22:07:34", "throughput": 558.59, "total_tokens": 20866400} {"current_steps": 12775, "total_steps": 40000, "loss": 0.1074, "lr": 3.843874559930332e-05, "epoch": 0.5783290703728016, "percentage": 31.94, "elapsed_time": "10:22:38", "remaining_time": "22:06:55", "throughput": 558.77, "total_tokens": 20874880} {"current_steps": 12780, "total_steps": 40000, "loss": 0.1334, "lr": 3.843046615261394e-05, "epoch": 0.5785554222594446, "percentage": 31.95, "elapsed_time": "10:22:41", "remaining_time": "22:06:16", "throughput": 558.94, "total_tokens": 20883264} {"current_steps": 12785, "total_steps": 40000, "loss": 0.1467, "lr": 3.842218463477791e-05, "epoch": 0.5787817741460876, "percentage": 31.96, "elapsed_time": "10:22:45", "remaining_time": "22:05:37", "throughput": 559.11, "total_tokens": 20891168} {"current_steps": 12790, "total_steps": 40000, "loss": 0.1405, "lr": 3.841390104707233e-05, "epoch": 0.5790081260327304, "percentage": 31.97, "elapsed_time": "10:22:48", "remaining_time": "22:04:58", "throughput": 559.28, "total_tokens": 20899232} {"current_steps": 12795, "total_steps": 40000, "loss": 0.1268, "lr": 3.8405615390774643e-05, "epoch": 0.5792344779193734, "percentage": 31.99, "elapsed_time": "10:22:51", "remaining_time": "22:04:20", "throughput": 559.47, "total_tokens": 20908352} {"current_steps": 12800, "total_steps": 40000, "loss": 0.0929, "lr": 3.839732766716259e-05, "epoch": 0.5794608298060164, "percentage": 32.0, "elapsed_time": "10:22:54", "remaining_time": "22:03:41", "throughput": 559.64, "total_tokens": 20916288} {"current_steps": 12800, "total_steps": 40000, "eval_loss": 0.13354167342185974, "epoch": 0.5794608298060164, "percentage": 32.0, "elapsed_time": "10:30:37", "remaining_time": "22:20:04", "throughput": 552.79, "total_tokens": 20916288} {"current_steps": 12805, "total_steps": 40000, "loss": 0.1236, "lr": 3.838903787751425e-05, "epoch": 0.5796871816926594, "percentage": 32.01, "elapsed_time": "10:30:41", "remaining_time": "22:19:26", "throughput": 552.95, "total_tokens": 20924512} {"current_steps": 12810, "total_steps": 40000, "loss": 0.1052, "lr": 3.838074602310802e-05, "epoch": 0.5799135335793024, "percentage": 32.02, "elapsed_time": "10:30:44", "remaining_time": "22:18:47", "throughput": 553.12, "total_tokens": 20932800} {"current_steps": 12815, "total_steps": 40000, "loss": 0.1322, "lr": 3.837245210522258e-05, "epoch": 0.5801398854659453, "percentage": 32.04, "elapsed_time": "10:30:47", "remaining_time": "22:18:08", "throughput": 553.29, "total_tokens": 20940864} {"current_steps": 12820, "total_steps": 40000, "loss": 0.1377, "lr": 3.8364156125136996e-05, "epoch": 0.5803662373525883, "percentage": 32.05, "elapsed_time": "10:30:51", "remaining_time": "22:17:28", "throughput": 553.46, "total_tokens": 20949120} {"current_steps": 12825, "total_steps": 40000, "loss": 0.1304, "lr": 3.835585808413059e-05, "epoch": 0.5805925892392313, "percentage": 32.06, "elapsed_time": "10:30:54", "remaining_time": "22:16:49", "throughput": 553.63, "total_tokens": 20957248} {"current_steps": 12830, "total_steps": 40000, "loss": 0.138, "lr": 3.8347557983483024e-05, "epoch": 0.5808189411258743, "percentage": 32.07, "elapsed_time": "10:30:57", "remaining_time": "22:16:10", "throughput": 553.79, "total_tokens": 20964992} {"current_steps": 12835, "total_steps": 40000, "loss": 0.1524, "lr": 3.833925582447428e-05, "epoch": 0.5810452930125173, "percentage": 32.09, "elapsed_time": "10:31:00", "remaining_time": "22:15:30", "throughput": 553.95, "total_tokens": 20972800} {"current_steps": 12840, "total_steps": 40000, "loss": 0.1209, "lr": 3.8330951608384656e-05, "epoch": 0.5812716448991603, "percentage": 32.1, "elapsed_time": "10:31:03", "remaining_time": "22:14:51", "throughput": 554.12, "total_tokens": 20981184} {"current_steps": 12845, "total_steps": 40000, "loss": 0.1173, "lr": 3.832264533649477e-05, "epoch": 0.5814979967858032, "percentage": 32.11, "elapsed_time": "10:31:06", "remaining_time": "22:14:12", "throughput": 554.3, "total_tokens": 20989408} {"current_steps": 12850, "total_steps": 40000, "loss": 0.1197, "lr": 3.8314337010085555e-05, "epoch": 0.5817243486724462, "percentage": 32.12, "elapsed_time": "10:31:10", "remaining_time": "22:13:33", "throughput": 554.48, "total_tokens": 20998208} {"current_steps": 12855, "total_steps": 40000, "loss": 0.1808, "lr": 3.830602663043824e-05, "epoch": 0.5819507005590892, "percentage": 32.14, "elapsed_time": "10:31:13", "remaining_time": "22:12:54", "throughput": 554.65, "total_tokens": 21006304} {"current_steps": 12860, "total_steps": 40000, "loss": 0.0981, "lr": 3.8297714198834414e-05, "epoch": 0.5821770524457321, "percentage": 32.15, "elapsed_time": "10:31:16", "remaining_time": "22:12:15", "throughput": 554.81, "total_tokens": 21014240} {"current_steps": 12865, "total_steps": 40000, "loss": 0.115, "lr": 3.828939971655595e-05, "epoch": 0.5824034043323751, "percentage": 32.16, "elapsed_time": "10:31:19", "remaining_time": "22:11:36", "throughput": 554.98, "total_tokens": 21022368} {"current_steps": 12870, "total_steps": 40000, "loss": 0.1415, "lr": 3.828108318488505e-05, "epoch": 0.5826297562190181, "percentage": 32.17, "elapsed_time": "10:31:22", "remaining_time": "22:10:57", "throughput": 555.14, "total_tokens": 21030400} {"current_steps": 12875, "total_steps": 40000, "loss": 0.1435, "lr": 3.8272764605104216e-05, "epoch": 0.582856108105661, "percentage": 32.19, "elapsed_time": "10:31:25", "remaining_time": "22:10:17", "throughput": 555.3, "total_tokens": 21038240} {"current_steps": 12880, "total_steps": 40000, "loss": 0.163, "lr": 3.826444397849628e-05, "epoch": 0.583082459992304, "percentage": 32.2, "elapsed_time": "10:31:29", "remaining_time": "22:09:39", "throughput": 555.48, "total_tokens": 21046592} {"current_steps": 12885, "total_steps": 40000, "loss": 0.1169, "lr": 3.825612130634439e-05, "epoch": 0.583308811878947, "percentage": 32.21, "elapsed_time": "10:31:32", "remaining_time": "22:09:00", "throughput": 555.65, "total_tokens": 21054848} {"current_steps": 12890, "total_steps": 40000, "loss": 0.0925, "lr": 3.824779658993202e-05, "epoch": 0.58353516376559, "percentage": 32.23, "elapsed_time": "10:31:35", "remaining_time": "22:08:21", "throughput": 555.81, "total_tokens": 21062912} {"current_steps": 12895, "total_steps": 40000, "loss": 0.109, "lr": 3.823946983054292e-05, "epoch": 0.583761515652233, "percentage": 32.24, "elapsed_time": "10:31:38", "remaining_time": "22:07:42", "throughput": 555.99, "total_tokens": 21071392} {"current_steps": 12900, "total_steps": 40000, "loss": 0.1276, "lr": 3.82311410294612e-05, "epoch": 0.5839878675388759, "percentage": 32.25, "elapsed_time": "10:31:41", "remaining_time": "22:07:03", "throughput": 556.15, "total_tokens": 21079232} {"current_steps": 12905, "total_steps": 40000, "loss": 0.1484, "lr": 3.822281018797127e-05, "epoch": 0.5842142194255189, "percentage": 32.26, "elapsed_time": "10:31:45", "remaining_time": "22:06:24", "throughput": 556.32, "total_tokens": 21087264} {"current_steps": 12910, "total_steps": 40000, "loss": 0.1828, "lr": 3.821447730735783e-05, "epoch": 0.5844405713121619, "percentage": 32.27, "elapsed_time": "10:31:48", "remaining_time": "22:05:45", "throughput": 556.49, "total_tokens": 21095520} {"current_steps": 12915, "total_steps": 40000, "loss": 0.1729, "lr": 3.820614238890592e-05, "epoch": 0.5846669231988049, "percentage": 32.29, "elapsed_time": "10:31:51", "remaining_time": "22:05:06", "throughput": 556.67, "total_tokens": 21104160} {"current_steps": 12920, "total_steps": 40000, "loss": 0.1176, "lr": 3.819780543390091e-05, "epoch": 0.5848932750854479, "percentage": 32.3, "elapsed_time": "10:31:54", "remaining_time": "22:04:28", "throughput": 556.82, "total_tokens": 21111776} {"current_steps": 12925, "total_steps": 40000, "loss": 0.142, "lr": 3.818946644362844e-05, "epoch": 0.5851196269720909, "percentage": 32.31, "elapsed_time": "10:31:57", "remaining_time": "22:03:49", "throughput": 557.0, "total_tokens": 21120032} {"current_steps": 12930, "total_steps": 40000, "loss": 0.1114, "lr": 3.81811254193745e-05, "epoch": 0.5853459788587337, "percentage": 32.32, "elapsed_time": "10:32:00", "remaining_time": "22:03:10", "throughput": 557.16, "total_tokens": 21127904} {"current_steps": 12935, "total_steps": 40000, "loss": 0.1231, "lr": 3.8172782362425366e-05, "epoch": 0.5855723307453767, "percentage": 32.34, "elapsed_time": "10:32:04", "remaining_time": "22:02:31", "throughput": 557.32, "total_tokens": 21135776} {"current_steps": 12940, "total_steps": 40000, "loss": 0.1153, "lr": 3.816443727406765e-05, "epoch": 0.5857986826320197, "percentage": 32.35, "elapsed_time": "10:32:07", "remaining_time": "22:01:53", "throughput": 557.5, "total_tokens": 21144352} {"current_steps": 12945, "total_steps": 40000, "loss": 0.1159, "lr": 3.815609015558829e-05, "epoch": 0.5860250345186627, "percentage": 32.36, "elapsed_time": "10:32:10", "remaining_time": "22:01:14", "throughput": 557.69, "total_tokens": 21153344} {"current_steps": 12950, "total_steps": 40000, "loss": 0.1011, "lr": 3.814774100827448e-05, "epoch": 0.5862513864053057, "percentage": 32.38, "elapsed_time": "10:32:13", "remaining_time": "22:00:36", "throughput": 557.85, "total_tokens": 21161472} {"current_steps": 12955, "total_steps": 40000, "loss": 0.1405, "lr": 3.813938983341379e-05, "epoch": 0.5864777382919487, "percentage": 32.39, "elapsed_time": "10:32:16", "remaining_time": "21:59:57", "throughput": 558.02, "total_tokens": 21169760} {"current_steps": 12960, "total_steps": 40000, "loss": 0.1095, "lr": 3.813103663229407e-05, "epoch": 0.5867040901785916, "percentage": 32.4, "elapsed_time": "10:32:20", "remaining_time": "21:59:18", "throughput": 558.19, "total_tokens": 21177856} {"current_steps": 12965, "total_steps": 40000, "loss": 0.1543, "lr": 3.812268140620349e-05, "epoch": 0.5869304420652346, "percentage": 32.41, "elapsed_time": "10:32:23", "remaining_time": "21:58:40", "throughput": 558.37, "total_tokens": 21186368} {"current_steps": 12970, "total_steps": 40000, "loss": 0.0826, "lr": 3.811432415643051e-05, "epoch": 0.5871567939518776, "percentage": 32.42, "elapsed_time": "10:32:26", "remaining_time": "21:58:01", "throughput": 558.53, "total_tokens": 21194240} {"current_steps": 12975, "total_steps": 40000, "loss": 0.0923, "lr": 3.8105964884263954e-05, "epoch": 0.5873831458385206, "percentage": 32.44, "elapsed_time": "10:32:29", "remaining_time": "21:57:23", "throughput": 558.7, "total_tokens": 21202432} {"current_steps": 12980, "total_steps": 40000, "loss": 0.1281, "lr": 3.809760359099291e-05, "epoch": 0.5876094977251636, "percentage": 32.45, "elapsed_time": "10:32:32", "remaining_time": "21:56:44", "throughput": 558.87, "total_tokens": 21210688} {"current_steps": 12985, "total_steps": 40000, "loss": 0.1635, "lr": 3.8089240277906804e-05, "epoch": 0.5878358496118065, "percentage": 32.46, "elapsed_time": "10:32:35", "remaining_time": "21:56:06", "throughput": 559.03, "total_tokens": 21218528} {"current_steps": 12990, "total_steps": 40000, "loss": 0.1179, "lr": 3.808087494629535e-05, "epoch": 0.5880622014984495, "percentage": 32.48, "elapsed_time": "10:32:39", "remaining_time": "21:55:28", "throughput": 559.2, "total_tokens": 21226848} {"current_steps": 12995, "total_steps": 40000, "loss": 0.0942, "lr": 3.8072507597448595e-05, "epoch": 0.5882885533850924, "percentage": 32.49, "elapsed_time": "10:32:42", "remaining_time": "21:54:49", "throughput": 559.36, "total_tokens": 21234624} {"current_steps": 13000, "total_steps": 40000, "loss": 0.0914, "lr": 3.806413823265689e-05, "epoch": 0.5885149052717354, "percentage": 32.5, "elapsed_time": "10:32:45", "remaining_time": "21:54:11", "throughput": 559.55, "total_tokens": 21243456} {"current_steps": 13000, "total_steps": 40000, "eval_loss": 0.13459685444831848, "epoch": 0.5885149052717354, "percentage": 32.5, "elapsed_time": "10:40:28", "remaining_time": "22:10:12", "throughput": 552.81, "total_tokens": 21243456} {"current_steps": 13005, "total_steps": 40000, "loss": 0.1352, "lr": 3.805576685321089e-05, "epoch": 0.5887412571583784, "percentage": 32.51, "elapsed_time": "10:40:32", "remaining_time": "22:09:36", "throughput": 552.96, "total_tokens": 21251840} {"current_steps": 13010, "total_steps": 40000, "loss": 0.0833, "lr": 3.804739346040158e-05, "epoch": 0.5889676090450214, "percentage": 32.52, "elapsed_time": "10:40:35", "remaining_time": "22:08:57", "throughput": 553.12, "total_tokens": 21259456} {"current_steps": 13015, "total_steps": 40000, "loss": 0.1405, "lr": 3.8039018055520234e-05, "epoch": 0.5891939609316643, "percentage": 32.54, "elapsed_time": "10:40:38", "remaining_time": "22:08:18", "throughput": 553.27, "total_tokens": 21267040} {"current_steps": 13020, "total_steps": 40000, "loss": 0.09, "lr": 3.803064063985844e-05, "epoch": 0.5894203128183073, "percentage": 32.55, "elapsed_time": "10:40:41", "remaining_time": "22:07:39", "throughput": 553.43, "total_tokens": 21274848} {"current_steps": 13025, "total_steps": 40000, "loss": 0.1567, "lr": 3.802226121470811e-05, "epoch": 0.5896466647049503, "percentage": 32.56, "elapsed_time": "10:40:45", "remaining_time": "22:07:00", "throughput": 553.59, "total_tokens": 21282624} {"current_steps": 13030, "total_steps": 40000, "loss": 0.1754, "lr": 3.801387978136145e-05, "epoch": 0.5898730165915933, "percentage": 32.57, "elapsed_time": "10:40:48", "remaining_time": "22:06:21", "throughput": 553.74, "total_tokens": 21290304} {"current_steps": 13035, "total_steps": 40000, "loss": 0.1559, "lr": 3.800549634111099e-05, "epoch": 0.5900993684782363, "percentage": 32.59, "elapsed_time": "10:40:51", "remaining_time": "22:05:42", "throughput": 553.89, "total_tokens": 21297888} {"current_steps": 13040, "total_steps": 40000, "loss": 0.1867, "lr": 3.799711089524955e-05, "epoch": 0.5903257203648793, "percentage": 32.6, "elapsed_time": "10:40:54", "remaining_time": "22:05:04", "throughput": 554.08, "total_tokens": 21306752} {"current_steps": 13045, "total_steps": 40000, "loss": 0.1547, "lr": 3.7988723445070285e-05, "epoch": 0.5905520722515222, "percentage": 32.61, "elapsed_time": "10:40:57", "remaining_time": "22:04:25", "throughput": 554.24, "total_tokens": 21314784} {"current_steps": 13050, "total_steps": 40000, "loss": 0.1017, "lr": 3.798033399186663e-05, "epoch": 0.5907784241381652, "percentage": 32.62, "elapsed_time": "10:41:01", "remaining_time": "22:03:47", "throughput": 554.42, "total_tokens": 21323584} {"current_steps": 13055, "total_steps": 40000, "loss": 0.0946, "lr": 3.797194253693237e-05, "epoch": 0.5910047760248082, "percentage": 32.64, "elapsed_time": "10:41:04", "remaining_time": "22:03:08", "throughput": 554.58, "total_tokens": 21331584} {"current_steps": 13060, "total_steps": 40000, "loss": 0.156, "lr": 3.796354908156153e-05, "epoch": 0.5912311279114512, "percentage": 32.65, "elapsed_time": "10:41:07", "remaining_time": "22:02:29", "throughput": 554.75, "total_tokens": 21339648} {"current_steps": 13065, "total_steps": 40000, "loss": 0.1298, "lr": 3.795515362704853e-05, "epoch": 0.5914574797980942, "percentage": 32.66, "elapsed_time": "10:41:10", "remaining_time": "22:01:51", "throughput": 554.91, "total_tokens": 21347744} {"current_steps": 13070, "total_steps": 40000, "loss": 0.1827, "lr": 3.794675617468803e-05, "epoch": 0.591683831684737, "percentage": 32.67, "elapsed_time": "10:41:13", "remaining_time": "22:01:12", "throughput": 555.07, "total_tokens": 21355360} {"current_steps": 13075, "total_steps": 40000, "loss": 0.1103, "lr": 3.793835672577503e-05, "epoch": 0.59191018357138, "percentage": 32.69, "elapsed_time": "10:41:16", "remaining_time": "22:00:34", "throughput": 555.23, "total_tokens": 21363488} {"current_steps": 13080, "total_steps": 40000, "loss": 0.0982, "lr": 3.7929955281604826e-05, "epoch": 0.592136535458023, "percentage": 32.7, "elapsed_time": "10:41:19", "remaining_time": "21:59:55", "throughput": 555.39, "total_tokens": 21371168} {"current_steps": 13085, "total_steps": 40000, "loss": 0.1094, "lr": 3.7921551843473036e-05, "epoch": 0.592362887344666, "percentage": 32.71, "elapsed_time": "10:41:23", "remaining_time": "21:59:17", "throughput": 555.55, "total_tokens": 21379168} {"current_steps": 13090, "total_steps": 40000, "loss": 0.1033, "lr": 3.791314641267557e-05, "epoch": 0.592589239231309, "percentage": 32.73, "elapsed_time": "10:41:26", "remaining_time": "21:58:38", "throughput": 555.7, "total_tokens": 21386912} {"current_steps": 13095, "total_steps": 40000, "loss": 0.1534, "lr": 3.790473899050864e-05, "epoch": 0.592815591117952, "percentage": 32.74, "elapsed_time": "10:41:29", "remaining_time": "21:58:00", "throughput": 555.87, "total_tokens": 21394912} {"current_steps": 13100, "total_steps": 40000, "loss": 0.2389, "lr": 3.7896329578268794e-05, "epoch": 0.5930419430045949, "percentage": 32.75, "elapsed_time": "10:41:32", "remaining_time": "21:57:21", "throughput": 556.03, "total_tokens": 21403008} {"current_steps": 13105, "total_steps": 40000, "loss": 0.1754, "lr": 3.7887918177252855e-05, "epoch": 0.5932682948912379, "percentage": 32.76, "elapsed_time": "10:41:35", "remaining_time": "21:56:43", "throughput": 556.21, "total_tokens": 21411648} {"current_steps": 13110, "total_steps": 40000, "loss": 0.1697, "lr": 3.787950478875798e-05, "epoch": 0.5934946467778809, "percentage": 32.77, "elapsed_time": "10:41:39", "remaining_time": "21:56:05", "throughput": 556.38, "total_tokens": 21420224} {"current_steps": 13115, "total_steps": 40000, "loss": 0.0805, "lr": 3.787108941408162e-05, "epoch": 0.5937209986645239, "percentage": 32.79, "elapsed_time": "10:41:42", "remaining_time": "21:55:27", "throughput": 556.55, "total_tokens": 21428608} {"current_steps": 13120, "total_steps": 40000, "loss": 0.0921, "lr": 3.786267205452151e-05, "epoch": 0.5939473505511669, "percentage": 32.8, "elapsed_time": "10:41:45", "remaining_time": "21:54:49", "throughput": 556.73, "total_tokens": 21437088} {"current_steps": 13125, "total_steps": 40000, "loss": 0.1327, "lr": 3.785425271137573e-05, "epoch": 0.5941737024378099, "percentage": 32.81, "elapsed_time": "10:41:48", "remaining_time": "21:54:11", "throughput": 556.89, "total_tokens": 21444928} {"current_steps": 13130, "total_steps": 40000, "loss": 0.0908, "lr": 3.7845831385942655e-05, "epoch": 0.5944000543244528, "percentage": 32.82, "elapsed_time": "10:41:51", "remaining_time": "21:53:32", "throughput": 557.05, "total_tokens": 21452896} {"current_steps": 13135, "total_steps": 40000, "loss": 0.0685, "lr": 3.7837408079520944e-05, "epoch": 0.5946264062110957, "percentage": 32.84, "elapsed_time": "10:41:55", "remaining_time": "21:52:54", "throughput": 557.23, "total_tokens": 21461632} {"current_steps": 13140, "total_steps": 40000, "loss": 0.1304, "lr": 3.782898279340957e-05, "epoch": 0.5948527580977387, "percentage": 32.85, "elapsed_time": "10:41:58", "remaining_time": "21:52:16", "throughput": 557.4, "total_tokens": 21470112} {"current_steps": 13145, "total_steps": 40000, "loss": 0.0946, "lr": 3.782055552890784e-05, "epoch": 0.5950791099843817, "percentage": 32.86, "elapsed_time": "10:42:01", "remaining_time": "21:51:38", "throughput": 557.57, "total_tokens": 21478304} {"current_steps": 13150, "total_steps": 40000, "loss": 0.1558, "lr": 3.781212628731534e-05, "epoch": 0.5953054618710247, "percentage": 32.88, "elapsed_time": "10:42:04", "remaining_time": "21:51:00", "throughput": 557.72, "total_tokens": 21486016} {"current_steps": 13155, "total_steps": 40000, "loss": 0.1624, "lr": 3.7803695069931946e-05, "epoch": 0.5955318137576676, "percentage": 32.89, "elapsed_time": "10:42:07", "remaining_time": "21:50:22", "throughput": 557.88, "total_tokens": 21494080} {"current_steps": 13160, "total_steps": 40000, "loss": 0.1537, "lr": 3.779526187805789e-05, "epoch": 0.5957581656443106, "percentage": 32.9, "elapsed_time": "10:42:10", "remaining_time": "21:49:44", "throughput": 558.04, "total_tokens": 21501824} {"current_steps": 13165, "total_steps": 40000, "loss": 0.1337, "lr": 3.778682671299364e-05, "epoch": 0.5959845175309536, "percentage": 32.91, "elapsed_time": "10:42:14", "remaining_time": "21:49:06", "throughput": 558.21, "total_tokens": 21510144} {"current_steps": 13170, "total_steps": 40000, "loss": 0.1037, "lr": 3.777838957604003e-05, "epoch": 0.5962108694175966, "percentage": 32.92, "elapsed_time": "10:42:17", "remaining_time": "21:48:28", "throughput": 558.4, "total_tokens": 21519264} {"current_steps": 13175, "total_steps": 40000, "loss": 0.0968, "lr": 3.776995046849816e-05, "epoch": 0.5964372213042396, "percentage": 32.94, "elapsed_time": "10:42:20", "remaining_time": "21:47:50", "throughput": 558.56, "total_tokens": 21527200} {"current_steps": 13180, "total_steps": 40000, "loss": 0.1607, "lr": 3.776150939166945e-05, "epoch": 0.5966635731908826, "percentage": 32.95, "elapsed_time": "10:42:23", "remaining_time": "21:47:12", "throughput": 558.72, "total_tokens": 21535072} {"current_steps": 13185, "total_steps": 40000, "loss": 0.1433, "lr": 3.775306634685562e-05, "epoch": 0.5968899250775255, "percentage": 32.96, "elapsed_time": "10:42:26", "remaining_time": "21:46:34", "throughput": 558.87, "total_tokens": 21542848} {"current_steps": 13190, "total_steps": 40000, "loss": 0.1315, "lr": 3.7744621335358696e-05, "epoch": 0.5971162769641685, "percentage": 32.98, "elapsed_time": "10:42:30", "remaining_time": "21:45:56", "throughput": 559.03, "total_tokens": 21550720} {"current_steps": 13195, "total_steps": 40000, "loss": 0.1402, "lr": 3.7736174358481e-05, "epoch": 0.5973426288508115, "percentage": 32.99, "elapsed_time": "10:42:33", "remaining_time": "21:45:19", "throughput": 559.21, "total_tokens": 21559424} {"current_steps": 13200, "total_steps": 40000, "loss": 0.1268, "lr": 3.7727725417525175e-05, "epoch": 0.5975689807374545, "percentage": 33.0, "elapsed_time": "10:42:36", "remaining_time": "21:44:41", "throughput": 559.36, "total_tokens": 21567008} {"current_steps": 13200, "total_steps": 40000, "eval_loss": 0.13301336765289307, "epoch": 0.5975689807374545, "percentage": 33.0, "elapsed_time": "10:50:19", "remaining_time": "22:00:20", "throughput": 552.73, "total_tokens": 21567008} {"current_steps": 13205, "total_steps": 40000, "loss": 0.1261, "lr": 3.771927451379414e-05, "epoch": 0.5977953326240975, "percentage": 33.01, "elapsed_time": "10:50:23", "remaining_time": "21:59:44", "throughput": 552.89, "total_tokens": 21575616} {"current_steps": 13210, "total_steps": 40000, "loss": 0.1379, "lr": 3.7710821648591135e-05, "epoch": 0.5980216845107404, "percentage": 33.02, "elapsed_time": "10:50:26", "remaining_time": "21:59:05", "throughput": 553.06, "total_tokens": 21583776} {"current_steps": 13215, "total_steps": 40000, "loss": 0.1604, "lr": 3.7702366823219694e-05, "epoch": 0.5982480363973833, "percentage": 33.04, "elapsed_time": "10:50:29", "remaining_time": "21:58:27", "throughput": 553.22, "total_tokens": 21592128} {"current_steps": 13220, "total_steps": 40000, "loss": 0.1433, "lr": 3.769391003898366e-05, "epoch": 0.5984743882840263, "percentage": 33.05, "elapsed_time": "10:50:32", "remaining_time": "21:57:49", "throughput": 553.39, "total_tokens": 21600480} {"current_steps": 13225, "total_steps": 40000, "loss": 0.1713, "lr": 3.768545129718718e-05, "epoch": 0.5987007401706693, "percentage": 33.06, "elapsed_time": "10:50:36", "remaining_time": "21:57:11", "throughput": 553.55, "total_tokens": 21608544} {"current_steps": 13230, "total_steps": 40000, "loss": 0.1584, "lr": 3.7676990599134686e-05, "epoch": 0.5989270920573123, "percentage": 33.07, "elapsed_time": "10:50:39", "remaining_time": "21:56:33", "throughput": 553.72, "total_tokens": 21616736} {"current_steps": 13235, "total_steps": 40000, "loss": 0.1758, "lr": 3.766852794613095e-05, "epoch": 0.5991534439439553, "percentage": 33.09, "elapsed_time": "10:50:42", "remaining_time": "21:55:54", "throughput": 553.88, "total_tokens": 21624800} {"current_steps": 13240, "total_steps": 40000, "loss": 0.1105, "lr": 3.766006333948099e-05, "epoch": 0.5993797958305982, "percentage": 33.1, "elapsed_time": "10:50:45", "remaining_time": "21:55:16", "throughput": 554.04, "total_tokens": 21632736} {"current_steps": 13245, "total_steps": 40000, "loss": 0.1271, "lr": 3.765159678049017e-05, "epoch": 0.5996061477172412, "percentage": 33.11, "elapsed_time": "10:50:48", "remaining_time": "21:54:38", "throughput": 554.2, "total_tokens": 21640896} {"current_steps": 13250, "total_steps": 40000, "loss": 0.1177, "lr": 3.7643128270464134e-05, "epoch": 0.5998324996038842, "percentage": 33.12, "elapsed_time": "10:50:51", "remaining_time": "21:54:00", "throughput": 554.36, "total_tokens": 21648864} {"current_steps": 13255, "total_steps": 40000, "loss": 0.1222, "lr": 3.763465781070884e-05, "epoch": 0.6000588514905272, "percentage": 33.14, "elapsed_time": "10:50:54", "remaining_time": "21:53:22", "throughput": 554.52, "total_tokens": 21656704} {"current_steps": 13260, "total_steps": 40000, "loss": 0.134, "lr": 3.762618540253052e-05, "epoch": 0.6002852033771702, "percentage": 33.15, "elapsed_time": "10:50:58", "remaining_time": "21:52:44", "throughput": 554.69, "total_tokens": 21664896} {"current_steps": 13265, "total_steps": 40000, "loss": 0.1802, "lr": 3.761771104723576e-05, "epoch": 0.6005115552638132, "percentage": 33.16, "elapsed_time": "10:51:01", "remaining_time": "21:52:05", "throughput": 554.84, "total_tokens": 21672672} {"current_steps": 13270, "total_steps": 40000, "loss": 0.1365, "lr": 3.7609234746131386e-05, "epoch": 0.600737907150456, "percentage": 33.17, "elapsed_time": "10:51:04", "remaining_time": "21:51:27", "throughput": 555.0, "total_tokens": 21680544} {"current_steps": 13275, "total_steps": 40000, "loss": 0.0992, "lr": 3.7600756500524556e-05, "epoch": 0.600964259037099, "percentage": 33.19, "elapsed_time": "10:51:07", "remaining_time": "21:50:49", "throughput": 555.16, "total_tokens": 21688480} {"current_steps": 13280, "total_steps": 40000, "loss": 0.1581, "lr": 3.759227631172271e-05, "epoch": 0.601190610923742, "percentage": 33.2, "elapsed_time": "10:51:10", "remaining_time": "21:50:11", "throughput": 555.33, "total_tokens": 21697024} {"current_steps": 13285, "total_steps": 40000, "loss": 0.0938, "lr": 3.758379418103363e-05, "epoch": 0.601416962810385, "percentage": 33.21, "elapsed_time": "10:51:13", "remaining_time": "21:49:33", "throughput": 555.49, "total_tokens": 21704928} {"current_steps": 13290, "total_steps": 40000, "loss": 0.1024, "lr": 3.757531010976534e-05, "epoch": 0.601643314697028, "percentage": 33.23, "elapsed_time": "10:51:16", "remaining_time": "21:48:55", "throughput": 555.65, "total_tokens": 21713184} {"current_steps": 13295, "total_steps": 40000, "loss": 0.1356, "lr": 3.75668240992262e-05, "epoch": 0.601869666583671, "percentage": 33.24, "elapsed_time": "10:51:20", "remaining_time": "21:48:18", "throughput": 555.82, "total_tokens": 21721504} {"current_steps": 13300, "total_steps": 40000, "loss": 0.1168, "lr": 3.7558336150724865e-05, "epoch": 0.6020960184703139, "percentage": 33.25, "elapsed_time": "10:51:23", "remaining_time": "21:47:40", "throughput": 556.01, "total_tokens": 21730912} {"current_steps": 13305, "total_steps": 40000, "loss": 0.1127, "lr": 3.754984626557028e-05, "epoch": 0.6023223703569569, "percentage": 33.26, "elapsed_time": "10:51:26", "remaining_time": "21:47:02", "throughput": 556.17, "total_tokens": 21738944} {"current_steps": 13310, "total_steps": 40000, "loss": 0.163, "lr": 3.754135444507168e-05, "epoch": 0.6025487222435999, "percentage": 33.27, "elapsed_time": "10:51:29", "remaining_time": "21:46:25", "throughput": 556.33, "total_tokens": 21746880} {"current_steps": 13315, "total_steps": 40000, "loss": 0.1863, "lr": 3.753286069053863e-05, "epoch": 0.6027750741302429, "percentage": 33.29, "elapsed_time": "10:51:32", "remaining_time": "21:45:47", "throughput": 556.49, "total_tokens": 21754880} {"current_steps": 13320, "total_steps": 40000, "loss": 0.1499, "lr": 3.7524365003280945e-05, "epoch": 0.6030014260168859, "percentage": 33.3, "elapsed_time": "10:51:36", "remaining_time": "21:45:09", "throughput": 556.65, "total_tokens": 21762880} {"current_steps": 13325, "total_steps": 40000, "loss": 0.1715, "lr": 3.75158673846088e-05, "epoch": 0.6032277779035288, "percentage": 33.31, "elapsed_time": "10:51:39", "remaining_time": "21:44:31", "throughput": 556.8, "total_tokens": 21770464} {"current_steps": 13330, "total_steps": 40000, "loss": 0.1071, "lr": 3.750736783583262e-05, "epoch": 0.6034541297901718, "percentage": 33.32, "elapsed_time": "10:51:42", "remaining_time": "21:43:54", "throughput": 556.97, "total_tokens": 21778656} {"current_steps": 13335, "total_steps": 40000, "loss": 0.085, "lr": 3.7498866358263144e-05, "epoch": 0.6036804816768148, "percentage": 33.34, "elapsed_time": "10:51:45", "remaining_time": "21:43:16", "throughput": 557.12, "total_tokens": 21786688} {"current_steps": 13340, "total_steps": 40000, "loss": 0.1726, "lr": 3.74903629532114e-05, "epoch": 0.6039068335634578, "percentage": 33.35, "elapsed_time": "10:51:48", "remaining_time": "21:42:39", "throughput": 557.27, "total_tokens": 21794336} {"current_steps": 13345, "total_steps": 40000, "loss": 0.1699, "lr": 3.748185762198873e-05, "epoch": 0.6041331854501008, "percentage": 33.36, "elapsed_time": "10:51:51", "remaining_time": "21:42:01", "throughput": 557.42, "total_tokens": 21801952} {"current_steps": 13350, "total_steps": 40000, "loss": 0.1054, "lr": 3.747335036590676e-05, "epoch": 0.6043595373367437, "percentage": 33.38, "elapsed_time": "10:51:55", "remaining_time": "21:41:23", "throughput": 557.58, "total_tokens": 21809920} {"current_steps": 13355, "total_steps": 40000, "loss": 0.1171, "lr": 3.7464841186277405e-05, "epoch": 0.6045858892233866, "percentage": 33.39, "elapsed_time": "10:51:58", "remaining_time": "21:40:46", "throughput": 557.75, "total_tokens": 21818080} {"current_steps": 13360, "total_steps": 40000, "loss": 0.1428, "lr": 3.7456330084412896e-05, "epoch": 0.6048122411100296, "percentage": 33.4, "elapsed_time": "10:52:01", "remaining_time": "21:40:08", "throughput": 557.92, "total_tokens": 21826528} {"current_steps": 13365, "total_steps": 40000, "loss": 0.1561, "lr": 3.744781706162576e-05, "epoch": 0.6050385929966726, "percentage": 33.41, "elapsed_time": "10:52:04", "remaining_time": "21:39:31", "throughput": 558.09, "total_tokens": 21835168} {"current_steps": 13370, "total_steps": 40000, "loss": 0.091, "lr": 3.743930211922879e-05, "epoch": 0.6052649448833156, "percentage": 33.42, "elapsed_time": "10:52:07", "remaining_time": "21:38:53", "throughput": 558.25, "total_tokens": 21843104} {"current_steps": 13375, "total_steps": 40000, "loss": 0.1598, "lr": 3.743078525853513e-05, "epoch": 0.6054912967699586, "percentage": 33.44, "elapsed_time": "10:52:10", "remaining_time": "21:38:16", "throughput": 558.41, "total_tokens": 21851296} {"current_steps": 13380, "total_steps": 40000, "loss": 0.1424, "lr": 3.7422266480858154e-05, "epoch": 0.6057176486566016, "percentage": 33.45, "elapsed_time": "10:52:14", "remaining_time": "21:37:38", "throughput": 558.56, "total_tokens": 21858880} {"current_steps": 13385, "total_steps": 40000, "loss": 0.1411, "lr": 3.741374578751158e-05, "epoch": 0.6059440005432445, "percentage": 33.46, "elapsed_time": "10:52:17", "remaining_time": "21:37:01", "throughput": 558.74, "total_tokens": 21867552} {"current_steps": 13390, "total_steps": 40000, "loss": 0.1516, "lr": 3.740522317980941e-05, "epoch": 0.6061703524298875, "percentage": 33.48, "elapsed_time": "10:52:20", "remaining_time": "21:36:23", "throughput": 558.9, "total_tokens": 21875456} {"current_steps": 13395, "total_steps": 40000, "loss": 0.1504, "lr": 3.739669865906593e-05, "epoch": 0.6063967043165305, "percentage": 33.49, "elapsed_time": "10:52:23", "remaining_time": "21:35:46", "throughput": 559.05, "total_tokens": 21883424} {"current_steps": 13400, "total_steps": 40000, "loss": 0.1056, "lr": 3.738817222659573e-05, "epoch": 0.6066230562031735, "percentage": 33.5, "elapsed_time": "10:52:26", "remaining_time": "21:35:09", "throughput": 559.22, "total_tokens": 21891776} {"current_steps": 13400, "total_steps": 40000, "eval_loss": 0.1323808878660202, "epoch": 0.6066230562031735, "percentage": 33.5, "elapsed_time": "11:00:09", "remaining_time": "21:50:28", "throughput": 552.69, "total_tokens": 21891776} {"current_steps": 13405, "total_steps": 40000, "loss": 0.119, "lr": 3.73796438837137e-05, "epoch": 0.6068494080898165, "percentage": 33.51, "elapsed_time": "11:00:13", "remaining_time": "21:49:51", "throughput": 552.83, "total_tokens": 21899680} {"current_steps": 13410, "total_steps": 40000, "loss": 0.165, "lr": 3.7371113631735e-05, "epoch": 0.6070757599764594, "percentage": 33.52, "elapsed_time": "11:00:16", "remaining_time": "21:49:14", "throughput": 553.0, "total_tokens": 21908192} {"current_steps": 13415, "total_steps": 40000, "loss": 0.1415, "lr": 3.736258147197512e-05, "epoch": 0.6073021118631023, "percentage": 33.54, "elapsed_time": "11:00:19", "remaining_time": "21:48:36", "throughput": 553.15, "total_tokens": 21915904} {"current_steps": 13420, "total_steps": 40000, "loss": 0.1292, "lr": 3.735404740574981e-05, "epoch": 0.6075284637497453, "percentage": 33.55, "elapsed_time": "11:00:23", "remaining_time": "21:47:58", "throughput": 553.31, "total_tokens": 21923680} {"current_steps": 13425, "total_steps": 40000, "loss": 0.1713, "lr": 3.7345511434375145e-05, "epoch": 0.6077548156363883, "percentage": 33.56, "elapsed_time": "11:00:26", "remaining_time": "21:47:20", "throughput": 553.46, "total_tokens": 21931552} {"current_steps": 13430, "total_steps": 40000, "loss": 0.1143, "lr": 3.733697355916748e-05, "epoch": 0.6079811675230313, "percentage": 33.58, "elapsed_time": "11:00:29", "remaining_time": "21:46:42", "throughput": 553.63, "total_tokens": 21939808} {"current_steps": 13435, "total_steps": 40000, "loss": 0.1959, "lr": 3.732843378144345e-05, "epoch": 0.6082075194096743, "percentage": 33.59, "elapsed_time": "11:00:32", "remaining_time": "21:46:05", "throughput": 553.77, "total_tokens": 21947264} {"current_steps": 13440, "total_steps": 40000, "loss": 0.1018, "lr": 3.7319892102519995e-05, "epoch": 0.6084338712963172, "percentage": 33.6, "elapsed_time": "11:00:35", "remaining_time": "21:45:27", "throughput": 553.93, "total_tokens": 21955360} {"current_steps": 13445, "total_steps": 40000, "loss": 0.1683, "lr": 3.731134852371436e-05, "epoch": 0.6086602231829602, "percentage": 33.61, "elapsed_time": "11:00:38", "remaining_time": "21:44:49", "throughput": 554.1, "total_tokens": 21963968} {"current_steps": 13450, "total_steps": 40000, "loss": 0.1423, "lr": 3.730280304634408e-05, "epoch": 0.6088865750696032, "percentage": 33.62, "elapsed_time": "11:00:41", "remaining_time": "21:44:12", "throughput": 554.25, "total_tokens": 21971328} {"current_steps": 13455, "total_steps": 40000, "loss": 0.1027, "lr": 3.729425567172696e-05, "epoch": 0.6091129269562462, "percentage": 33.64, "elapsed_time": "11:00:45", "remaining_time": "21:43:34", "throughput": 554.41, "total_tokens": 21979776} {"current_steps": 13460, "total_steps": 40000, "loss": 0.1543, "lr": 3.728570640118111e-05, "epoch": 0.6093392788428892, "percentage": 33.65, "elapsed_time": "11:00:48", "remaining_time": "21:42:57", "throughput": 554.6, "total_tokens": 21989184} {"current_steps": 13465, "total_steps": 40000, "loss": 0.0905, "lr": 3.727715523602494e-05, "epoch": 0.6095656307295322, "percentage": 33.66, "elapsed_time": "11:00:51", "remaining_time": "21:42:20", "throughput": 554.76, "total_tokens": 21997088} {"current_steps": 13470, "total_steps": 40000, "loss": 0.1454, "lr": 3.726860217757715e-05, "epoch": 0.6097919826161751, "percentage": 33.67, "elapsed_time": "11:00:54", "remaining_time": "21:41:42", "throughput": 554.91, "total_tokens": 22004800} {"current_steps": 13475, "total_steps": 40000, "loss": 0.0902, "lr": 3.726004722715673e-05, "epoch": 0.6100183345028181, "percentage": 33.69, "elapsed_time": "11:00:57", "remaining_time": "21:41:04", "throughput": 555.07, "total_tokens": 22012864} {"current_steps": 13480, "total_steps": 40000, "loss": 0.1003, "lr": 3.725149038608296e-05, "epoch": 0.610244686389461, "percentage": 33.7, "elapsed_time": "11:01:00", "remaining_time": "21:40:27", "throughput": 555.23, "total_tokens": 22021056} {"current_steps": 13485, "total_steps": 40000, "loss": 0.1661, "lr": 3.7242931655675404e-05, "epoch": 0.610471038276104, "percentage": 33.71, "elapsed_time": "11:01:04", "remaining_time": "21:39:49", "throughput": 555.39, "total_tokens": 22028928} {"current_steps": 13490, "total_steps": 40000, "loss": 0.1239, "lr": 3.7234371037253937e-05, "epoch": 0.610697390162747, "percentage": 33.73, "elapsed_time": "11:01:07", "remaining_time": "21:39:12", "throughput": 555.54, "total_tokens": 22036896} {"current_steps": 13495, "total_steps": 40000, "loss": 0.0937, "lr": 3.7225808532138705e-05, "epoch": 0.6109237420493899, "percentage": 33.74, "elapsed_time": "11:01:10", "remaining_time": "21:38:35", "throughput": 555.72, "total_tokens": 22045760} {"current_steps": 13500, "total_steps": 40000, "loss": 0.1573, "lr": 3.721724414165016e-05, "epoch": 0.6111500939360329, "percentage": 33.75, "elapsed_time": "11:01:13", "remaining_time": "21:37:57", "throughput": 555.87, "total_tokens": 22053216} {"current_steps": 13505, "total_steps": 40000, "loss": 0.1388, "lr": 3.720867786710904e-05, "epoch": 0.6113764458226759, "percentage": 33.76, "elapsed_time": "11:01:16", "remaining_time": "21:37:20", "throughput": 556.03, "total_tokens": 22061312} {"current_steps": 13510, "total_steps": 40000, "loss": 0.0869, "lr": 3.7200109709836366e-05, "epoch": 0.6116027977093189, "percentage": 33.77, "elapsed_time": "11:01:19", "remaining_time": "21:36:43", "throughput": 556.19, "total_tokens": 22069632} {"current_steps": 13515, "total_steps": 40000, "loss": 0.1289, "lr": 3.7191539671153465e-05, "epoch": 0.6118291495959619, "percentage": 33.79, "elapsed_time": "11:01:23", "remaining_time": "21:36:06", "throughput": 556.35, "total_tokens": 22077888} {"current_steps": 13520, "total_steps": 40000, "loss": 0.1706, "lr": 3.718296775238193e-05, "epoch": 0.6120555014826049, "percentage": 33.8, "elapsed_time": "11:01:26", "remaining_time": "21:35:28", "throughput": 556.52, "total_tokens": 22086368} {"current_steps": 13525, "total_steps": 40000, "loss": 0.1281, "lr": 3.7174393954843675e-05, "epoch": 0.6122818533692478, "percentage": 33.81, "elapsed_time": "11:01:29", "remaining_time": "21:34:51", "throughput": 556.67, "total_tokens": 22094112} {"current_steps": 13530, "total_steps": 40000, "loss": 0.0918, "lr": 3.716581827986087e-05, "epoch": 0.6125082052558908, "percentage": 33.83, "elapsed_time": "11:01:32", "remaining_time": "21:34:14", "throughput": 556.84, "total_tokens": 22102368} {"current_steps": 13535, "total_steps": 40000, "loss": 0.1476, "lr": 3.7157240728756004e-05, "epoch": 0.6127345571425338, "percentage": 33.84, "elapsed_time": "11:01:35", "remaining_time": "21:33:37", "throughput": 556.99, "total_tokens": 22110304} {"current_steps": 13540, "total_steps": 40000, "loss": 0.1962, "lr": 3.714866130285184e-05, "epoch": 0.6129609090291768, "percentage": 33.85, "elapsed_time": "11:01:39", "remaining_time": "21:33:00", "throughput": 557.16, "total_tokens": 22118848} {"current_steps": 13545, "total_steps": 40000, "loss": 0.132, "lr": 3.714008000347143e-05, "epoch": 0.6131872609158198, "percentage": 33.86, "elapsed_time": "11:01:42", "remaining_time": "21:32:23", "throughput": 557.33, "total_tokens": 22127200} {"current_steps": 13550, "total_steps": 40000, "loss": 0.1035, "lr": 3.7131496831938126e-05, "epoch": 0.6134136128024628, "percentage": 33.88, "elapsed_time": "11:01:45", "remaining_time": "21:31:46", "throughput": 557.48, "total_tokens": 22135136} {"current_steps": 13555, "total_steps": 40000, "loss": 0.1427, "lr": 3.7122911789575565e-05, "epoch": 0.6136399646891056, "percentage": 33.89, "elapsed_time": "11:01:48", "remaining_time": "21:31:09", "throughput": 557.65, "total_tokens": 22143424} {"current_steps": 13560, "total_steps": 40000, "loss": 0.1466, "lr": 3.711432487770765e-05, "epoch": 0.6138663165757486, "percentage": 33.9, "elapsed_time": "11:01:51", "remaining_time": "21:30:32", "throughput": 557.81, "total_tokens": 22151744} {"current_steps": 13565, "total_steps": 40000, "loss": 0.095, "lr": 3.710573609765861e-05, "epoch": 0.6140926684623916, "percentage": 33.91, "elapsed_time": "11:01:54", "remaining_time": "21:29:54", "throughput": 557.97, "total_tokens": 22159648} {"current_steps": 13570, "total_steps": 40000, "loss": 0.1587, "lr": 3.709714545075292e-05, "epoch": 0.6143190203490346, "percentage": 33.92, "elapsed_time": "11:01:57", "remaining_time": "21:29:17", "throughput": 558.13, "total_tokens": 22167616} {"current_steps": 13575, "total_steps": 40000, "loss": 0.1347, "lr": 3.708855293831538e-05, "epoch": 0.6145453722356776, "percentage": 33.94, "elapsed_time": "11:02:01", "remaining_time": "21:28:41", "throughput": 558.3, "total_tokens": 22176224} {"current_steps": 13580, "total_steps": 40000, "loss": 0.1246, "lr": 3.707995856167107e-05, "epoch": 0.6147717241223205, "percentage": 33.95, "elapsed_time": "11:02:04", "remaining_time": "21:28:04", "throughput": 558.45, "total_tokens": 22184288} {"current_steps": 13585, "total_steps": 40000, "loss": 0.1462, "lr": 3.707136232214534e-05, "epoch": 0.6149980760089635, "percentage": 33.96, "elapsed_time": "11:02:07", "remaining_time": "21:27:27", "throughput": 558.61, "total_tokens": 22192320} {"current_steps": 13590, "total_steps": 40000, "loss": 0.1177, "lr": 3.7062764221063844e-05, "epoch": 0.6152244278956065, "percentage": 33.98, "elapsed_time": "11:02:10", "remaining_time": "21:26:50", "throughput": 558.78, "total_tokens": 22200736} {"current_steps": 13595, "total_steps": 40000, "loss": 0.1507, "lr": 3.705416425975252e-05, "epoch": 0.6154507797822495, "percentage": 33.99, "elapsed_time": "11:02:13", "remaining_time": "21:26:13", "throughput": 558.93, "total_tokens": 22208480} {"current_steps": 13600, "total_steps": 40000, "loss": 0.1738, "lr": 3.704556243953758e-05, "epoch": 0.6156771316688925, "percentage": 34.0, "elapsed_time": "11:02:17", "remaining_time": "21:25:36", "throughput": 559.09, "total_tokens": 22216544} {"current_steps": 13600, "total_steps": 40000, "eval_loss": 0.1322459727525711, "epoch": 0.6156771316688925, "percentage": 34.0, "elapsed_time": "11:09:59", "remaining_time": "21:40:34", "throughput": 552.65, "total_tokens": 22216544} {"current_steps": 13605, "total_steps": 40000, "loss": 0.0905, "lr": 3.7036958761745535e-05, "epoch": 0.6159034835555355, "percentage": 34.01, "elapsed_time": "11:10:03", "remaining_time": "21:39:59", "throughput": 552.81, "total_tokens": 22225120} {"current_steps": 13610, "total_steps": 40000, "loss": 0.1315, "lr": 3.702835322770318e-05, "epoch": 0.6161298354421784, "percentage": 34.02, "elapsed_time": "11:10:06", "remaining_time": "21:39:21", "throughput": 552.96, "total_tokens": 22232992} {"current_steps": 13615, "total_steps": 40000, "loss": 0.1252, "lr": 3.701974583873761e-05, "epoch": 0.6163561873288214, "percentage": 34.04, "elapsed_time": "11:10:10", "remaining_time": "21:38:44", "throughput": 553.13, "total_tokens": 22241664} {"current_steps": 13620, "total_steps": 40000, "loss": 0.1329, "lr": 3.701113659617618e-05, "epoch": 0.6165825392154644, "percentage": 34.05, "elapsed_time": "11:10:13", "remaining_time": "21:38:07", "throughput": 553.29, "total_tokens": 22249568} {"current_steps": 13625, "total_steps": 40000, "loss": 0.0924, "lr": 3.7002525501346535e-05, "epoch": 0.6168088911021073, "percentage": 34.06, "elapsed_time": "11:10:16", "remaining_time": "21:37:30", "throughput": 553.44, "total_tokens": 22257472} {"current_steps": 13630, "total_steps": 40000, "loss": 0.1263, "lr": 3.699391255557664e-05, "epoch": 0.6170352429887503, "percentage": 34.08, "elapsed_time": "11:10:19", "remaining_time": "21:36:53", "throughput": 553.61, "total_tokens": 22266272} {"current_steps": 13635, "total_steps": 40000, "loss": 0.1487, "lr": 3.69852977601947e-05, "epoch": 0.6172615948753933, "percentage": 34.09, "elapsed_time": "11:10:23", "remaining_time": "21:36:16", "throughput": 553.78, "total_tokens": 22274816} {"current_steps": 13640, "total_steps": 40000, "loss": 0.1323, "lr": 3.697668111652922e-05, "epoch": 0.6174879467620362, "percentage": 34.1, "elapsed_time": "11:10:26", "remaining_time": "21:35:39", "throughput": 553.93, "total_tokens": 22282464} {"current_steps": 13645, "total_steps": 40000, "loss": 0.1336, "lr": 3.6968062625909005e-05, "epoch": 0.6177142986486792, "percentage": 34.11, "elapsed_time": "11:10:29", "remaining_time": "21:35:01", "throughput": 554.09, "total_tokens": 22290592} {"current_steps": 13650, "total_steps": 40000, "loss": 0.1634, "lr": 3.6959442289663135e-05, "epoch": 0.6179406505353222, "percentage": 34.12, "elapsed_time": "11:10:32", "remaining_time": "21:34:25", "throughput": 554.27, "total_tokens": 22299552} {"current_steps": 13655, "total_steps": 40000, "loss": 0.1538, "lr": 3.695082010912098e-05, "epoch": 0.6181670024219652, "percentage": 34.14, "elapsed_time": "11:10:35", "remaining_time": "21:33:47", "throughput": 554.41, "total_tokens": 22307168} {"current_steps": 13660, "total_steps": 40000, "loss": 0.1364, "lr": 3.694219608561217e-05, "epoch": 0.6183933543086082, "percentage": 34.15, "elapsed_time": "11:10:38", "remaining_time": "21:33:10", "throughput": 554.58, "total_tokens": 22315616} {"current_steps": 13665, "total_steps": 40000, "loss": 0.1553, "lr": 3.693357022046665e-05, "epoch": 0.6186197061952511, "percentage": 34.16, "elapsed_time": "11:10:42", "remaining_time": "21:32:34", "throughput": 554.75, "total_tokens": 22324160} {"current_steps": 13670, "total_steps": 40000, "loss": 0.1399, "lr": 3.6924942515014644e-05, "epoch": 0.6188460580818941, "percentage": 34.17, "elapsed_time": "11:10:45", "remaining_time": "21:31:57", "throughput": 554.91, "total_tokens": 22332320} {"current_steps": 13675, "total_steps": 40000, "loss": 0.1015, "lr": 3.691631297058664e-05, "epoch": 0.6190724099685371, "percentage": 34.19, "elapsed_time": "11:10:48", "remaining_time": "21:31:20", "throughput": 555.08, "total_tokens": 22341152} {"current_steps": 13680, "total_steps": 40000, "loss": 0.0969, "lr": 3.6907681588513424e-05, "epoch": 0.6192987618551801, "percentage": 34.2, "elapsed_time": "11:10:51", "remaining_time": "21:30:43", "throughput": 555.22, "total_tokens": 22348736} {"current_steps": 13685, "total_steps": 40000, "loss": 0.1663, "lr": 3.689904837012606e-05, "epoch": 0.6195251137418231, "percentage": 34.21, "elapsed_time": "11:10:54", "remaining_time": "21:30:06", "throughput": 555.39, "total_tokens": 22357024} {"current_steps": 13690, "total_steps": 40000, "loss": 0.1041, "lr": 3.689041331675591e-05, "epoch": 0.6197514656284661, "percentage": 34.23, "elapsed_time": "11:10:58", "remaining_time": "21:29:29", "throughput": 555.54, "total_tokens": 22365024} {"current_steps": 13695, "total_steps": 40000, "loss": 0.1371, "lr": 3.688177642973461e-05, "epoch": 0.6199778175151089, "percentage": 34.24, "elapsed_time": "11:11:01", "remaining_time": "21:28:53", "throughput": 555.72, "total_tokens": 22374016} {"current_steps": 13700, "total_steps": 40000, "loss": 0.1166, "lr": 3.687313771039406e-05, "epoch": 0.6202041694017519, "percentage": 34.25, "elapsed_time": "11:11:04", "remaining_time": "21:28:16", "throughput": 555.89, "total_tokens": 22382688} {"current_steps": 13705, "total_steps": 40000, "loss": 0.1217, "lr": 3.686449716006647e-05, "epoch": 0.6204305212883949, "percentage": 34.26, "elapsed_time": "11:11:07", "remaining_time": "21:27:39", "throughput": 556.05, "total_tokens": 22391104} {"current_steps": 13710, "total_steps": 40000, "loss": 0.118, "lr": 3.685585478008432e-05, "epoch": 0.6206568731750379, "percentage": 34.27, "elapsed_time": "11:11:11", "remaining_time": "21:27:03", "throughput": 556.24, "total_tokens": 22400352} {"current_steps": 13715, "total_steps": 40000, "loss": 0.1436, "lr": 3.6847210571780364e-05, "epoch": 0.6208832250616809, "percentage": 34.29, "elapsed_time": "11:11:14", "remaining_time": "21:26:26", "throughput": 556.38, "total_tokens": 22408064} {"current_steps": 13720, "total_steps": 40000, "loss": 0.1798, "lr": 3.683856453648767e-05, "epoch": 0.6211095769483239, "percentage": 34.3, "elapsed_time": "11:11:17", "remaining_time": "21:25:49", "throughput": 556.54, "total_tokens": 22416256} {"current_steps": 13725, "total_steps": 40000, "loss": 0.1346, "lr": 3.682991667553954e-05, "epoch": 0.6213359288349668, "percentage": 34.31, "elapsed_time": "11:11:20", "remaining_time": "21:25:13", "throughput": 556.71, "total_tokens": 22424832} {"current_steps": 13730, "total_steps": 40000, "loss": 0.0862, "lr": 3.6821266990269606e-05, "epoch": 0.6215622807216098, "percentage": 34.33, "elapsed_time": "11:11:24", "remaining_time": "21:24:36", "throughput": 556.87, "total_tokens": 22433184} {"current_steps": 13735, "total_steps": 40000, "loss": 0.1481, "lr": 3.681261548201174e-05, "epoch": 0.6217886326082528, "percentage": 34.34, "elapsed_time": "11:11:27", "remaining_time": "21:24:00", "throughput": 557.04, "total_tokens": 22441536} {"current_steps": 13740, "total_steps": 40000, "loss": 0.1248, "lr": 3.6803962152100125e-05, "epoch": 0.6220149844948958, "percentage": 34.35, "elapsed_time": "11:11:30", "remaining_time": "21:23:23", "throughput": 557.19, "total_tokens": 22449440} {"current_steps": 13745, "total_steps": 40000, "loss": 0.1574, "lr": 3.67953070018692e-05, "epoch": 0.6222413363815388, "percentage": 34.36, "elapsed_time": "11:11:33", "remaining_time": "21:22:46", "throughput": 557.34, "total_tokens": 22457408} {"current_steps": 13750, "total_steps": 40000, "loss": 0.1678, "lr": 3.678665003265371e-05, "epoch": 0.6224676882681817, "percentage": 34.38, "elapsed_time": "11:11:36", "remaining_time": "21:22:10", "throughput": 557.5, "total_tokens": 22465536} {"current_steps": 13755, "total_steps": 40000, "loss": 0.0765, "lr": 3.677799124578867e-05, "epoch": 0.6226940401548247, "percentage": 34.39, "elapsed_time": "11:11:39", "remaining_time": "21:21:33", "throughput": 557.65, "total_tokens": 22473280} {"current_steps": 13760, "total_steps": 40000, "loss": 0.107, "lr": 3.676933064260937e-05, "epoch": 0.6229203920414677, "percentage": 34.4, "elapsed_time": "11:11:43", "remaining_time": "21:20:57", "throughput": 557.81, "total_tokens": 22481600} {"current_steps": 13765, "total_steps": 40000, "loss": 0.1, "lr": 3.6760668224451365e-05, "epoch": 0.6231467439281106, "percentage": 34.41, "elapsed_time": "11:11:46", "remaining_time": "21:20:20", "throughput": 557.97, "total_tokens": 22489728} {"current_steps": 13770, "total_steps": 40000, "loss": 0.117, "lr": 3.675200399265054e-05, "epoch": 0.6233730958147536, "percentage": 34.42, "elapsed_time": "11:11:49", "remaining_time": "21:19:44", "throughput": 558.14, "total_tokens": 22498336} {"current_steps": 13775, "total_steps": 40000, "loss": 0.1148, "lr": 3.6743337948543014e-05, "epoch": 0.6235994477013966, "percentage": 34.44, "elapsed_time": "11:11:52", "remaining_time": "21:19:08", "throughput": 558.31, "total_tokens": 22507104} {"current_steps": 13780, "total_steps": 40000, "loss": 0.1546, "lr": 3.6734670093465204e-05, "epoch": 0.6238257995880395, "percentage": 34.45, "elapsed_time": "11:11:56", "remaining_time": "21:18:31", "throughput": 558.47, "total_tokens": 22515488} {"current_steps": 13785, "total_steps": 40000, "loss": 0.1095, "lr": 3.672600042875379e-05, "epoch": 0.6240521514746825, "percentage": 34.46, "elapsed_time": "11:11:59", "remaining_time": "21:17:55", "throughput": 558.63, "total_tokens": 22523584} {"current_steps": 13790, "total_steps": 40000, "loss": 0.1573, "lr": 3.671732895574575e-05, "epoch": 0.6242785033613255, "percentage": 34.48, "elapsed_time": "11:12:02", "remaining_time": "21:17:19", "throughput": 558.82, "total_tokens": 22533248} {"current_steps": 13795, "total_steps": 40000, "loss": 0.1027, "lr": 3.670865567577834e-05, "epoch": 0.6245048552479685, "percentage": 34.49, "elapsed_time": "11:12:06", "remaining_time": "21:16:43", "throughput": 559.0, "total_tokens": 22542208} {"current_steps": 13800, "total_steps": 40000, "loss": 0.1048, "lr": 3.669998059018909e-05, "epoch": 0.6247312071346115, "percentage": 34.5, "elapsed_time": "11:12:09", "remaining_time": "21:16:07", "throughput": 559.15, "total_tokens": 22549952} {"current_steps": 13800, "total_steps": 40000, "eval_loss": 0.134722501039505, "epoch": 0.6247312071346115, "percentage": 34.5, "elapsed_time": "11:19:52", "remaining_time": "21:30:46", "throughput": 552.79, "total_tokens": 22549952} {"current_steps": 13805, "total_steps": 40000, "loss": 0.1165, "lr": 3.6691303700315796e-05, "epoch": 0.6249575590212545, "percentage": 34.51, "elapsed_time": "11:19:57", "remaining_time": "21:30:12", "throughput": 552.93, "total_tokens": 22557984} {"current_steps": 13810, "total_steps": 40000, "loss": 0.1468, "lr": 3.668262500749655e-05, "epoch": 0.6251839109078974, "percentage": 34.52, "elapsed_time": "11:20:00", "remaining_time": "21:29:35", "throughput": 553.09, "total_tokens": 22565984} {"current_steps": 13815, "total_steps": 40000, "loss": 0.1474, "lr": 3.667394451306971e-05, "epoch": 0.6254102627945404, "percentage": 34.54, "elapsed_time": "11:20:03", "remaining_time": "21:28:58", "throughput": 553.25, "total_tokens": 22574368} {"current_steps": 13820, "total_steps": 40000, "loss": 0.1911, "lr": 3.666526221837393e-05, "epoch": 0.6256366146811834, "percentage": 34.55, "elapsed_time": "11:20:06", "remaining_time": "21:28:21", "throughput": 553.39, "total_tokens": 22581856} {"current_steps": 13825, "total_steps": 40000, "loss": 0.1578, "lr": 3.665657812474812e-05, "epoch": 0.6258629665678264, "percentage": 34.56, "elapsed_time": "11:20:09", "remaining_time": "21:27:45", "throughput": 553.54, "total_tokens": 22589824} {"current_steps": 13830, "total_steps": 40000, "loss": 0.1233, "lr": 3.664789223353147e-05, "epoch": 0.6260893184544694, "percentage": 34.58, "elapsed_time": "11:20:12", "remaining_time": "21:27:08", "throughput": 553.7, "total_tokens": 22597984} {"current_steps": 13835, "total_steps": 40000, "loss": 0.1077, "lr": 3.663920454606347e-05, "epoch": 0.6263156703411122, "percentage": 34.59, "elapsed_time": "11:20:15", "remaining_time": "21:26:31", "throughput": 553.85, "total_tokens": 22605760} {"current_steps": 13840, "total_steps": 40000, "loss": 0.1789, "lr": 3.6630515063683856e-05, "epoch": 0.6265420222277552, "percentage": 34.6, "elapsed_time": "11:20:19", "remaining_time": "21:25:55", "throughput": 554.01, "total_tokens": 22613984} {"current_steps": 13845, "total_steps": 40000, "loss": 0.1117, "lr": 3.662182378773267e-05, "epoch": 0.6267683741143982, "percentage": 34.61, "elapsed_time": "11:20:22", "remaining_time": "21:25:18", "throughput": 554.16, "total_tokens": 22621920} {"current_steps": 13850, "total_steps": 40000, "loss": 0.1238, "lr": 3.66131307195502e-05, "epoch": 0.6269947260010412, "percentage": 34.62, "elapsed_time": "11:20:25", "remaining_time": "21:24:41", "throughput": 554.31, "total_tokens": 22629696} {"current_steps": 13855, "total_steps": 40000, "loss": 0.1304, "lr": 3.6604435860477034e-05, "epoch": 0.6272210778876842, "percentage": 34.64, "elapsed_time": "11:20:28", "remaining_time": "21:24:04", "throughput": 554.44, "total_tokens": 22637024} {"current_steps": 13860, "total_steps": 40000, "loss": 0.1322, "lr": 3.6595739211854025e-05, "epoch": 0.6274474297743272, "percentage": 34.65, "elapsed_time": "11:20:31", "remaining_time": "21:23:28", "throughput": 554.6, "total_tokens": 22645312} {"current_steps": 13865, "total_steps": 40000, "loss": 0.1732, "lr": 3.658704077502231e-05, "epoch": 0.6276737816609701, "percentage": 34.66, "elapsed_time": "11:20:34", "remaining_time": "21:22:52", "throughput": 554.78, "total_tokens": 22654624} {"current_steps": 13870, "total_steps": 40000, "loss": 0.1249, "lr": 3.65783405513233e-05, "epoch": 0.6279001335476131, "percentage": 34.67, "elapsed_time": "11:20:38", "remaining_time": "21:22:15", "throughput": 554.95, "total_tokens": 22662944} {"current_steps": 13875, "total_steps": 40000, "loss": 0.1557, "lr": 3.656963854209867e-05, "epoch": 0.6281264854342561, "percentage": 34.69, "elapsed_time": "11:20:41", "remaining_time": "21:21:39", "throughput": 555.11, "total_tokens": 22671328} {"current_steps": 13880, "total_steps": 40000, "loss": 0.0947, "lr": 3.656093474869038e-05, "epoch": 0.6283528373208991, "percentage": 34.7, "elapsed_time": "11:20:44", "remaining_time": "21:21:02", "throughput": 555.24, "total_tokens": 22678560} {"current_steps": 13885, "total_steps": 40000, "loss": 0.1071, "lr": 3.655222917244068e-05, "epoch": 0.6285791892075421, "percentage": 34.71, "elapsed_time": "11:20:47", "remaining_time": "21:20:26", "throughput": 555.4, "total_tokens": 22686752} {"current_steps": 13890, "total_steps": 40000, "loss": 0.1059, "lr": 3.6543521814692054e-05, "epoch": 0.6288055410941851, "percentage": 34.73, "elapsed_time": "11:20:50", "remaining_time": "21:19:50", "throughput": 555.56, "total_tokens": 22694976} {"current_steps": 13895, "total_steps": 40000, "loss": 0.1536, "lr": 3.653481267678731e-05, "epoch": 0.629031892980828, "percentage": 34.74, "elapsed_time": "11:20:54", "remaining_time": "21:19:13", "throughput": 555.72, "total_tokens": 22703328} {"current_steps": 13900, "total_steps": 40000, "loss": 0.1221, "lr": 3.652610176006949e-05, "epoch": 0.629258244867471, "percentage": 34.75, "elapsed_time": "11:20:57", "remaining_time": "21:18:37", "throughput": 555.87, "total_tokens": 22711424} {"current_steps": 13905, "total_steps": 40000, "loss": 0.1205, "lr": 3.6517389065881925e-05, "epoch": 0.629484596754114, "percentage": 34.76, "elapsed_time": "11:21:00", "remaining_time": "21:18:01", "throughput": 556.03, "total_tokens": 22719552} {"current_steps": 13910, "total_steps": 40000, "loss": 0.1588, "lr": 3.650867459556824e-05, "epoch": 0.6297109486407569, "percentage": 34.77, "elapsed_time": "11:21:03", "remaining_time": "21:17:24", "throughput": 556.17, "total_tokens": 22727264} {"current_steps": 13915, "total_steps": 40000, "loss": 0.1019, "lr": 3.64999583504723e-05, "epoch": 0.6299373005273999, "percentage": 34.79, "elapsed_time": "11:21:06", "remaining_time": "21:16:49", "throughput": 556.35, "total_tokens": 22736480} {"current_steps": 13920, "total_steps": 40000, "loss": 0.156, "lr": 3.649124033193827e-05, "epoch": 0.6301636524140428, "percentage": 34.8, "elapsed_time": "11:21:10", "remaining_time": "21:16:12", "throughput": 556.5, "total_tokens": 22744064} {"current_steps": 13925, "total_steps": 40000, "loss": 0.1584, "lr": 3.648252054131057e-05, "epoch": 0.6303900043006858, "percentage": 34.81, "elapsed_time": "11:21:13", "remaining_time": "21:15:36", "throughput": 556.66, "total_tokens": 22752352} {"current_steps": 13930, "total_steps": 40000, "loss": 0.1175, "lr": 3.647379897993391e-05, "epoch": 0.6306163561873288, "percentage": 34.83, "elapsed_time": "11:21:16", "remaining_time": "21:15:00", "throughput": 556.81, "total_tokens": 22760512} {"current_steps": 13935, "total_steps": 40000, "loss": 0.1568, "lr": 3.646507564915325e-05, "epoch": 0.6308427080739718, "percentage": 34.84, "elapsed_time": "11:21:19", "remaining_time": "21:14:23", "throughput": 556.96, "total_tokens": 22768288} {"current_steps": 13940, "total_steps": 40000, "loss": 0.1347, "lr": 3.645635055031385e-05, "epoch": 0.6310690599606148, "percentage": 34.85, "elapsed_time": "11:21:22", "remaining_time": "21:13:47", "throughput": 557.12, "total_tokens": 22776384} {"current_steps": 13945, "total_steps": 40000, "loss": 0.152, "lr": 3.6447623684761224e-05, "epoch": 0.6312954118472578, "percentage": 34.86, "elapsed_time": "11:21:25", "remaining_time": "21:13:11", "throughput": 557.28, "total_tokens": 22784736} {"current_steps": 13950, "total_steps": 40000, "loss": 0.1368, "lr": 3.643889505384117e-05, "epoch": 0.6315217637339007, "percentage": 34.88, "elapsed_time": "11:21:29", "remaining_time": "21:12:35", "throughput": 557.43, "total_tokens": 22792960} {"current_steps": 13955, "total_steps": 40000, "loss": 0.1078, "lr": 3.6430164658899744e-05, "epoch": 0.6317481156205437, "percentage": 34.89, "elapsed_time": "11:21:32", "remaining_time": "21:11:59", "throughput": 557.58, "total_tokens": 22800448} {"current_steps": 13960, "total_steps": 40000, "loss": 0.116, "lr": 3.642143250128329e-05, "epoch": 0.6319744675071867, "percentage": 34.9, "elapsed_time": "11:21:35", "remaining_time": "21:11:23", "throughput": 557.72, "total_tokens": 22808224} {"current_steps": 13965, "total_steps": 40000, "loss": 0.1109, "lr": 3.641269858233841e-05, "epoch": 0.6322008193938297, "percentage": 34.91, "elapsed_time": "11:21:38", "remaining_time": "21:10:47", "throughput": 557.88, "total_tokens": 22816384} {"current_steps": 13970, "total_steps": 40000, "loss": 0.1409, "lr": 3.640396290341199e-05, "epoch": 0.6324271712804727, "percentage": 34.92, "elapsed_time": "11:21:41", "remaining_time": "21:10:11", "throughput": 558.04, "total_tokens": 22824768} {"current_steps": 13975, "total_steps": 40000, "loss": 0.1054, "lr": 3.639522546585118e-05, "epoch": 0.6326535231671157, "percentage": 34.94, "elapsed_time": "11:21:45", "remaining_time": "21:09:35", "throughput": 558.2, "total_tokens": 22832992} {"current_steps": 13980, "total_steps": 40000, "loss": 0.1094, "lr": 3.6386486271003404e-05, "epoch": 0.6328798750537585, "percentage": 34.95, "elapsed_time": "11:21:48", "remaining_time": "21:08:59", "throughput": 558.34, "total_tokens": 22840544} {"current_steps": 13985, "total_steps": 40000, "loss": 0.0976, "lr": 3.6377745320216346e-05, "epoch": 0.6331062269404015, "percentage": 34.96, "elapsed_time": "11:21:51", "remaining_time": "21:08:23", "throughput": 558.5, "total_tokens": 22848928} {"current_steps": 13990, "total_steps": 40000, "loss": 0.117, "lr": 3.636900261483798e-05, "epoch": 0.6333325788270445, "percentage": 34.98, "elapsed_time": "11:21:54", "remaining_time": "21:07:47", "throughput": 558.67, "total_tokens": 22857696} {"current_steps": 13995, "total_steps": 40000, "loss": 0.0744, "lr": 3.636025815621654e-05, "epoch": 0.6335589307136875, "percentage": 34.99, "elapsed_time": "11:21:57", "remaining_time": "21:07:11", "throughput": 558.82, "total_tokens": 22865568} {"current_steps": 14000, "total_steps": 40000, "loss": 0.1093, "lr": 3.635151194570054e-05, "epoch": 0.6337852826003305, "percentage": 35.0, "elapsed_time": "11:22:00", "remaining_time": "21:06:35", "throughput": 558.97, "total_tokens": 22873376} {"current_steps": 14000, "total_steps": 40000, "eval_loss": 0.13168329000473022, "epoch": 0.6337852826003305, "percentage": 35.0, "elapsed_time": "11:29:43", "remaining_time": "21:20:55", "throughput": 552.72, "total_tokens": 22873376} {"current_steps": 14005, "total_steps": 40000, "loss": 0.1079, "lr": 3.634276398463873e-05, "epoch": 0.6340116344869734, "percentage": 35.01, "elapsed_time": "11:29:47", "remaining_time": "21:20:20", "throughput": 552.86, "total_tokens": 22881472} {"current_steps": 14010, "total_steps": 40000, "loss": 0.1225, "lr": 3.633401427438018e-05, "epoch": 0.6342379863736164, "percentage": 35.02, "elapsed_time": "11:29:50", "remaining_time": "21:19:44", "throughput": 553.0, "total_tokens": 22889056} {"current_steps": 14015, "total_steps": 40000, "loss": 0.1686, "lr": 3.63252628162742e-05, "epoch": 0.6344643382602594, "percentage": 35.04, "elapsed_time": "11:29:53", "remaining_time": "21:19:07", "throughput": 553.13, "total_tokens": 22896320} {"current_steps": 14020, "total_steps": 40000, "loss": 0.1317, "lr": 3.6316509611670364e-05, "epoch": 0.6346906901469024, "percentage": 35.05, "elapsed_time": "11:29:57", "remaining_time": "21:18:31", "throughput": 553.31, "total_tokens": 22905280} {"current_steps": 14025, "total_steps": 40000, "loss": 0.1281, "lr": 3.630775466191854e-05, "epoch": 0.6349170420335454, "percentage": 35.06, "elapsed_time": "11:30:00", "remaining_time": "21:17:55", "throughput": 553.45, "total_tokens": 22913056} {"current_steps": 14030, "total_steps": 40000, "loss": 0.1801, "lr": 3.629899796836884e-05, "epoch": 0.6351433939201884, "percentage": 35.08, "elapsed_time": "11:30:03", "remaining_time": "21:17:19", "throughput": 553.61, "total_tokens": 22921344} {"current_steps": 14035, "total_steps": 40000, "loss": 0.1635, "lr": 3.6290239532371666e-05, "epoch": 0.6353697458068313, "percentage": 35.09, "elapsed_time": "11:30:06", "remaining_time": "21:16:43", "throughput": 553.76, "total_tokens": 22929440} {"current_steps": 14040, "total_steps": 40000, "loss": 0.0672, "lr": 3.628147935527767e-05, "epoch": 0.6355960976934742, "percentage": 35.1, "elapsed_time": "11:30:09", "remaining_time": "21:16:06", "throughput": 553.91, "total_tokens": 22937184} {"current_steps": 14045, "total_steps": 40000, "loss": 0.0916, "lr": 3.627271743843779e-05, "epoch": 0.6358224495801172, "percentage": 35.11, "elapsed_time": "11:30:13", "remaining_time": "21:15:30", "throughput": 554.07, "total_tokens": 22945568} {"current_steps": 14050, "total_steps": 40000, "loss": 0.1339, "lr": 3.626395378320321e-05, "epoch": 0.6360488014667602, "percentage": 35.12, "elapsed_time": "11:30:16", "remaining_time": "21:14:54", "throughput": 554.22, "total_tokens": 22953856} {"current_steps": 14055, "total_steps": 40000, "loss": 0.0819, "lr": 3.625518839092541e-05, "epoch": 0.6362751533534032, "percentage": 35.14, "elapsed_time": "11:30:19", "remaining_time": "21:14:18", "throughput": 554.37, "total_tokens": 22961600} {"current_steps": 14060, "total_steps": 40000, "loss": 0.1108, "lr": 3.624642126295612e-05, "epoch": 0.6365015052400462, "percentage": 35.15, "elapsed_time": "11:30:22", "remaining_time": "21:13:42", "throughput": 554.52, "total_tokens": 22969728} {"current_steps": 14065, "total_steps": 40000, "loss": 0.1461, "lr": 3.6237652400647345e-05, "epoch": 0.6367278571266891, "percentage": 35.16, "elapsed_time": "11:30:25", "remaining_time": "21:13:06", "throughput": 554.69, "total_tokens": 22978528} {"current_steps": 14070, "total_steps": 40000, "loss": 0.1012, "lr": 3.622888180535134e-05, "epoch": 0.6369542090133321, "percentage": 35.17, "elapsed_time": "11:30:28", "remaining_time": "21:12:30", "throughput": 554.85, "total_tokens": 22986592} {"current_steps": 14075, "total_steps": 40000, "loss": 0.0717, "lr": 3.6220109478420655e-05, "epoch": 0.6371805608999751, "percentage": 35.19, "elapsed_time": "11:30:31", "remaining_time": "21:11:54", "throughput": 555.0, "total_tokens": 22994560} {"current_steps": 14080, "total_steps": 40000, "loss": 0.1106, "lr": 3.6211335421208084e-05, "epoch": 0.6374069127866181, "percentage": 35.2, "elapsed_time": "11:30:35", "remaining_time": "21:11:18", "throughput": 555.15, "total_tokens": 23002752} {"current_steps": 14085, "total_steps": 40000, "loss": 0.1159, "lr": 3.62025596350667e-05, "epoch": 0.6376332646732611, "percentage": 35.21, "elapsed_time": "11:30:38", "remaining_time": "21:10:42", "throughput": 555.29, "total_tokens": 23010272} {"current_steps": 14090, "total_steps": 40000, "loss": 0.0903, "lr": 3.619378212134984e-05, "epoch": 0.637859616559904, "percentage": 35.23, "elapsed_time": "11:30:41", "remaining_time": "21:10:06", "throughput": 555.45, "total_tokens": 23018432} {"current_steps": 14095, "total_steps": 40000, "loss": 0.2012, "lr": 3.618500288141111e-05, "epoch": 0.638085968446547, "percentage": 35.24, "elapsed_time": "11:30:44", "remaining_time": "21:09:30", "throughput": 555.6, "total_tokens": 23026656} {"current_steps": 14100, "total_steps": 40000, "loss": 0.0981, "lr": 3.617622191660438e-05, "epoch": 0.63831232033319, "percentage": 35.25, "elapsed_time": "11:30:47", "remaining_time": "21:08:54", "throughput": 555.76, "total_tokens": 23034880} {"current_steps": 14105, "total_steps": 40000, "loss": 0.1608, "lr": 3.616743922828377e-05, "epoch": 0.638538672219833, "percentage": 35.26, "elapsed_time": "11:30:50", "remaining_time": "21:08:18", "throughput": 555.9, "total_tokens": 23042720} {"current_steps": 14110, "total_steps": 40000, "loss": 0.1185, "lr": 3.615865481780371e-05, "epoch": 0.638765024106476, "percentage": 35.27, "elapsed_time": "11:30:54", "remaining_time": "21:07:42", "throughput": 556.06, "total_tokens": 23050912} {"current_steps": 14115, "total_steps": 40000, "loss": 0.1281, "lr": 3.614986868651883e-05, "epoch": 0.638991375993119, "percentage": 35.29, "elapsed_time": "11:30:57", "remaining_time": "21:07:06", "throughput": 556.2, "total_tokens": 23058496} {"current_steps": 14120, "total_steps": 40000, "loss": 0.1701, "lr": 3.614108083578409e-05, "epoch": 0.6392177278797618, "percentage": 35.3, "elapsed_time": "11:31:00", "remaining_time": "21:06:31", "throughput": 556.36, "total_tokens": 23066752} {"current_steps": 14125, "total_steps": 40000, "loss": 0.1032, "lr": 3.613229126695467e-05, "epoch": 0.6394440797664048, "percentage": 35.31, "elapsed_time": "11:31:03", "remaining_time": "21:05:55", "throughput": 556.5, "total_tokens": 23074592} {"current_steps": 14130, "total_steps": 40000, "loss": 0.1434, "lr": 3.612349998138605e-05, "epoch": 0.6396704316530478, "percentage": 35.33, "elapsed_time": "11:31:06", "remaining_time": "21:05:19", "throughput": 556.66, "total_tokens": 23083008} {"current_steps": 14135, "total_steps": 40000, "loss": 0.141, "lr": 3.6114706980433946e-05, "epoch": 0.6398967835396908, "percentage": 35.34, "elapsed_time": "11:31:09", "remaining_time": "21:04:43", "throughput": 556.81, "total_tokens": 23090944} {"current_steps": 14140, "total_steps": 40000, "loss": 0.1392, "lr": 3.610591226545435e-05, "epoch": 0.6401231354263338, "percentage": 35.35, "elapsed_time": "11:31:12", "remaining_time": "21:04:07", "throughput": 556.96, "total_tokens": 23098912} {"current_steps": 14145, "total_steps": 40000, "loss": 0.1308, "lr": 3.6097115837803505e-05, "epoch": 0.6403494873129768, "percentage": 35.36, "elapsed_time": "11:31:16", "remaining_time": "21:03:32", "throughput": 557.11, "total_tokens": 23106592} {"current_steps": 14150, "total_steps": 40000, "loss": 0.1582, "lr": 3.608831769883795e-05, "epoch": 0.6405758391996197, "percentage": 35.38, "elapsed_time": "11:31:19", "remaining_time": "21:02:56", "throughput": 557.28, "total_tokens": 23115456} {"current_steps": 14155, "total_steps": 40000, "loss": 0.1324, "lr": 3.607951784991446e-05, "epoch": 0.6408021910862627, "percentage": 35.39, "elapsed_time": "11:31:22", "remaining_time": "21:02:21", "throughput": 557.44, "total_tokens": 23123808} {"current_steps": 14160, "total_steps": 40000, "loss": 0.0964, "lr": 3.6070716292390085e-05, "epoch": 0.6410285429729057, "percentage": 35.4, "elapsed_time": "11:31:25", "remaining_time": "21:01:45", "throughput": 557.6, "total_tokens": 23132544} {"current_steps": 14165, "total_steps": 40000, "loss": 0.1674, "lr": 3.606191302762213e-05, "epoch": 0.6412548948595487, "percentage": 35.41, "elapsed_time": "11:31:29", "remaining_time": "21:01:10", "throughput": 557.77, "total_tokens": 23141184} {"current_steps": 14170, "total_steps": 40000, "loss": 0.1398, "lr": 3.605310805696818e-05, "epoch": 0.6414812467461917, "percentage": 35.43, "elapsed_time": "11:31:32", "remaining_time": "21:00:34", "throughput": 557.93, "total_tokens": 23149952} {"current_steps": 14175, "total_steps": 40000, "loss": 0.1411, "lr": 3.6044301381786067e-05, "epoch": 0.6417075986328346, "percentage": 35.44, "elapsed_time": "11:31:35", "remaining_time": "20:59:59", "throughput": 558.09, "total_tokens": 23158240} {"current_steps": 14180, "total_steps": 40000, "loss": 0.1319, "lr": 3.6035493003433883e-05, "epoch": 0.6419339505194775, "percentage": 35.45, "elapsed_time": "11:31:38", "remaining_time": "20:59:23", "throughput": 558.24, "total_tokens": 23166112} {"current_steps": 14185, "total_steps": 40000, "loss": 0.1634, "lr": 3.6026682923269994e-05, "epoch": 0.6421603024061205, "percentage": 35.46, "elapsed_time": "11:31:41", "remaining_time": "20:58:48", "throughput": 558.39, "total_tokens": 23173952} {"current_steps": 14190, "total_steps": 40000, "loss": 0.0938, "lr": 3.6017871142653034e-05, "epoch": 0.6423866542927635, "percentage": 35.48, "elapsed_time": "11:31:44", "remaining_time": "20:58:12", "throughput": 558.54, "total_tokens": 23181920} {"current_steps": 14195, "total_steps": 40000, "loss": 0.1238, "lr": 3.600905766294189e-05, "epoch": 0.6426130061794065, "percentage": 35.49, "elapsed_time": "11:31:47", "remaining_time": "20:57:37", "throughput": 558.69, "total_tokens": 23189984} {"current_steps": 14200, "total_steps": 40000, "loss": 0.1237, "lr": 3.60002424854957e-05, "epoch": 0.6428393580660495, "percentage": 35.5, "elapsed_time": "11:31:51", "remaining_time": "20:57:01", "throughput": 558.84, "total_tokens": 23198016} {"current_steps": 14200, "total_steps": 40000, "eval_loss": 0.13198459148406982, "epoch": 0.6428393580660495, "percentage": 35.5, "elapsed_time": "11:39:33", "remaining_time": "21:11:02", "throughput": 552.68, "total_tokens": 23198016} {"current_steps": 14205, "total_steps": 40000, "loss": 0.1863, "lr": 3.5991425611673876e-05, "epoch": 0.6430657099526924, "percentage": 35.51, "elapsed_time": "11:39:37", "remaining_time": "21:10:27", "throughput": 552.82, "total_tokens": 23206304} {"current_steps": 14210, "total_steps": 40000, "loss": 0.1661, "lr": 3.5982607042836105e-05, "epoch": 0.6432920618393354, "percentage": 35.52, "elapsed_time": "11:39:41", "remaining_time": "21:09:52", "throughput": 552.98, "total_tokens": 23214752} {"current_steps": 14215, "total_steps": 40000, "loss": 0.1425, "lr": 3.597378678034231e-05, "epoch": 0.6435184137259784, "percentage": 35.54, "elapsed_time": "11:39:44", "remaining_time": "21:09:16", "throughput": 553.13, "total_tokens": 23222720} {"current_steps": 14220, "total_steps": 40000, "loss": 0.1652, "lr": 3.596496482555269e-05, "epoch": 0.6437447656126214, "percentage": 35.55, "elapsed_time": "11:39:47", "remaining_time": "21:08:40", "throughput": 553.3, "total_tokens": 23231648} {"current_steps": 14225, "total_steps": 40000, "loss": 0.1374, "lr": 3.595614117982769e-05, "epoch": 0.6439711174992644, "percentage": 35.56, "elapsed_time": "11:39:50", "remaining_time": "21:08:05", "throughput": 553.45, "total_tokens": 23239936} {"current_steps": 14230, "total_steps": 40000, "loss": 0.1366, "lr": 3.594731584452805e-05, "epoch": 0.6441974693859074, "percentage": 35.58, "elapsed_time": "11:39:53", "remaining_time": "21:07:29", "throughput": 553.61, "total_tokens": 23248416} {"current_steps": 14235, "total_steps": 40000, "loss": 0.1548, "lr": 3.593848882101472e-05, "epoch": 0.6444238212725503, "percentage": 35.59, "elapsed_time": "11:39:57", "remaining_time": "21:06:53", "throughput": 553.77, "total_tokens": 23256960} {"current_steps": 14240, "total_steps": 40000, "loss": 0.1131, "lr": 3.592966011064896e-05, "epoch": 0.6446501731591933, "percentage": 35.6, "elapsed_time": "11:40:00", "remaining_time": "21:06:18", "throughput": 553.91, "total_tokens": 23264416} {"current_steps": 14245, "total_steps": 40000, "loss": 0.127, "lr": 3.592082971479226e-05, "epoch": 0.6448765250458363, "percentage": 35.61, "elapsed_time": "11:40:03", "remaining_time": "21:05:42", "throughput": 554.09, "total_tokens": 23273728} {"current_steps": 14250, "total_steps": 40000, "loss": 0.1362, "lr": 3.5911997634806385e-05, "epoch": 0.6451028769324793, "percentage": 35.62, "elapsed_time": "11:40:07", "remaining_time": "21:05:07", "throughput": 554.25, "total_tokens": 23282304} {"current_steps": 14255, "total_steps": 40000, "loss": 0.1336, "lr": 3.5903163872053336e-05, "epoch": 0.6453292288191222, "percentage": 35.64, "elapsed_time": "11:40:10", "remaining_time": "21:04:32", "throughput": 554.43, "total_tokens": 23291904} {"current_steps": 14260, "total_steps": 40000, "loss": 0.1216, "lr": 3.58943284278954e-05, "epoch": 0.6455555807057651, "percentage": 35.65, "elapsed_time": "11:40:13", "remaining_time": "21:03:56", "throughput": 554.58, "total_tokens": 23299744} {"current_steps": 14265, "total_steps": 40000, "loss": 0.0916, "lr": 3.588549130369512e-05, "epoch": 0.6457819325924081, "percentage": 35.66, "elapsed_time": "11:40:16", "remaining_time": "21:03:20", "throughput": 554.73, "total_tokens": 23307808} {"current_steps": 14270, "total_steps": 40000, "loss": 0.0954, "lr": 3.5876652500815274e-05, "epoch": 0.6460082844790511, "percentage": 35.68, "elapsed_time": "11:40:19", "remaining_time": "21:02:45", "throughput": 554.87, "total_tokens": 23315712} {"current_steps": 14275, "total_steps": 40000, "loss": 0.0774, "lr": 3.586781202061894e-05, "epoch": 0.6462346363656941, "percentage": 35.69, "elapsed_time": "11:40:22", "remaining_time": "21:02:09", "throughput": 555.02, "total_tokens": 23323456} {"current_steps": 14280, "total_steps": 40000, "loss": 0.1326, "lr": 3.585896986446942e-05, "epoch": 0.6464609882523371, "percentage": 35.7, "elapsed_time": "11:40:25", "remaining_time": "21:01:33", "throughput": 555.16, "total_tokens": 23331040} {"current_steps": 14285, "total_steps": 40000, "loss": 0.1466, "lr": 3.585012603373028e-05, "epoch": 0.6466873401389801, "percentage": 35.71, "elapsed_time": "11:40:29", "remaining_time": "21:00:58", "throughput": 555.31, "total_tokens": 23339136} {"current_steps": 14290, "total_steps": 40000, "loss": 0.1103, "lr": 3.584128052976535e-05, "epoch": 0.646913692025623, "percentage": 35.73, "elapsed_time": "11:40:32", "remaining_time": "21:00:22", "throughput": 555.45, "total_tokens": 23346912} {"current_steps": 14295, "total_steps": 40000, "loss": 0.0968, "lr": 3.5832433353938724e-05, "epoch": 0.647140043912266, "percentage": 35.74, "elapsed_time": "11:40:35", "remaining_time": "20:59:47", "throughput": 555.6, "total_tokens": 23354816} {"current_steps": 14300, "total_steps": 40000, "loss": 0.1328, "lr": 3.5823584507614746e-05, "epoch": 0.647366395798909, "percentage": 35.75, "elapsed_time": "11:40:38", "remaining_time": "20:59:11", "throughput": 555.75, "total_tokens": 23362848} {"current_steps": 14305, "total_steps": 40000, "loss": 0.1331, "lr": 3.581473399215802e-05, "epoch": 0.647592747685552, "percentage": 35.76, "elapsed_time": "11:40:41", "remaining_time": "20:58:36", "throughput": 555.9, "total_tokens": 23370816} {"current_steps": 14310, "total_steps": 40000, "loss": 0.0985, "lr": 3.580588180893341e-05, "epoch": 0.647819099572195, "percentage": 35.77, "elapsed_time": "11:40:44", "remaining_time": "20:58:01", "throughput": 556.06, "total_tokens": 23379424} {"current_steps": 14315, "total_steps": 40000, "loss": 0.1042, "lr": 3.579702795930602e-05, "epoch": 0.648045451458838, "percentage": 35.79, "elapsed_time": "11:40:48", "remaining_time": "20:57:25", "throughput": 556.21, "total_tokens": 23387520} {"current_steps": 14320, "total_steps": 40000, "loss": 0.1218, "lr": 3.578817244464125e-05, "epoch": 0.6482718033454808, "percentage": 35.8, "elapsed_time": "11:40:51", "remaining_time": "20:56:50", "throughput": 556.35, "total_tokens": 23395200} {"current_steps": 14325, "total_steps": 40000, "loss": 0.1216, "lr": 3.577931526630471e-05, "epoch": 0.6484981552321238, "percentage": 35.81, "elapsed_time": "11:40:54", "remaining_time": "20:56:14", "throughput": 556.5, "total_tokens": 23403296} {"current_steps": 14330, "total_steps": 40000, "loss": 0.1107, "lr": 3.577045642566229e-05, "epoch": 0.6487245071187668, "percentage": 35.83, "elapsed_time": "11:40:57", "remaining_time": "20:55:39", "throughput": 556.64, "total_tokens": 23411008} {"current_steps": 14335, "total_steps": 40000, "loss": 0.1489, "lr": 3.576159592408014e-05, "epoch": 0.6489508590054098, "percentage": 35.84, "elapsed_time": "11:41:00", "remaining_time": "20:55:04", "throughput": 556.79, "total_tokens": 23419104} {"current_steps": 14340, "total_steps": 40000, "loss": 0.1549, "lr": 3.575273376292466e-05, "epoch": 0.6491772108920528, "percentage": 35.85, "elapsed_time": "11:41:03", "remaining_time": "20:54:29", "throughput": 556.95, "total_tokens": 23427712} {"current_steps": 14345, "total_steps": 40000, "loss": 0.1503, "lr": 3.574386994356251e-05, "epoch": 0.6494035627786957, "percentage": 35.86, "elapsed_time": "11:41:07", "remaining_time": "20:53:53", "throughput": 557.1, "total_tokens": 23435552} {"current_steps": 14350, "total_steps": 40000, "loss": 0.1704, "lr": 3.573500446736059e-05, "epoch": 0.6496299146653387, "percentage": 35.88, "elapsed_time": "11:41:10", "remaining_time": "20:53:18", "throughput": 557.26, "total_tokens": 23443872} {"current_steps": 14355, "total_steps": 40000, "loss": 0.1093, "lr": 3.5726137335686094e-05, "epoch": 0.6498562665519817, "percentage": 35.89, "elapsed_time": "11:41:13", "remaining_time": "20:52:43", "throughput": 557.4, "total_tokens": 23451552} {"current_steps": 14360, "total_steps": 40000, "loss": 0.1219, "lr": 3.571726854990642e-05, "epoch": 0.6500826184386247, "percentage": 35.9, "elapsed_time": "11:41:16", "remaining_time": "20:52:08", "throughput": 557.54, "total_tokens": 23459264} {"current_steps": 14365, "total_steps": 40000, "loss": 0.1003, "lr": 3.570839811138925e-05, "epoch": 0.6503089703252677, "percentage": 35.91, "elapsed_time": "11:41:19", "remaining_time": "20:51:32", "throughput": 557.68, "total_tokens": 23466784} {"current_steps": 14370, "total_steps": 40000, "loss": 0.1349, "lr": 3.569952602150252e-05, "epoch": 0.6505353222119107, "percentage": 35.93, "elapsed_time": "11:41:22", "remaining_time": "20:50:57", "throughput": 557.84, "total_tokens": 23475360} {"current_steps": 14375, "total_steps": 40000, "loss": 0.1015, "lr": 3.569065228161442e-05, "epoch": 0.6507616740985536, "percentage": 35.94, "elapsed_time": "11:41:25", "remaining_time": "20:50:22", "throughput": 557.99, "total_tokens": 23483648} {"current_steps": 14380, "total_steps": 40000, "loss": 0.1469, "lr": 3.5681776893093395e-05, "epoch": 0.6509880259851966, "percentage": 35.95, "elapsed_time": "11:41:29", "remaining_time": "20:49:47", "throughput": 558.15, "total_tokens": 23491936} {"current_steps": 14385, "total_steps": 40000, "loss": 0.1287, "lr": 3.5672899857308134e-05, "epoch": 0.6512143778718396, "percentage": 35.96, "elapsed_time": "11:41:32", "remaining_time": "20:49:12", "throughput": 558.3, "total_tokens": 23500032} {"current_steps": 14390, "total_steps": 40000, "loss": 0.0871, "lr": 3.566402117562759e-05, "epoch": 0.6514407297584826, "percentage": 35.98, "elapsed_time": "11:41:35", "remaining_time": "20:48:37", "throughput": 558.44, "total_tokens": 23507776} {"current_steps": 14395, "total_steps": 40000, "loss": 0.211, "lr": 3.565514084942097e-05, "epoch": 0.6516670816451255, "percentage": 35.99, "elapsed_time": "11:41:38", "remaining_time": "20:48:02", "throughput": 558.6, "total_tokens": 23516256} {"current_steps": 14400, "total_steps": 40000, "loss": 0.1476, "lr": 3.564625888005773e-05, "epoch": 0.6518934335317685, "percentage": 36.0, "elapsed_time": "11:41:41", "remaining_time": "20:47:27", "throughput": 558.75, "total_tokens": 23524256} {"current_steps": 14400, "total_steps": 40000, "eval_loss": 0.13244511187076569, "epoch": 0.6518934335317685, "percentage": 36.0, "elapsed_time": "11:49:24", "remaining_time": "21:01:09", "throughput": 552.68, "total_tokens": 23524256} {"current_steps": 14405, "total_steps": 40000, "loss": 0.1515, "lr": 3.563737526890759e-05, "epoch": 0.6521197854184114, "percentage": 36.01, "elapsed_time": "11:49:28", "remaining_time": "21:00:35", "throughput": 552.82, "total_tokens": 23532448} {"current_steps": 14410, "total_steps": 40000, "loss": 0.1435, "lr": 3.562849001734049e-05, "epoch": 0.6523461373050544, "percentage": 36.02, "elapsed_time": "11:49:31", "remaining_time": "21:00:00", "throughput": 552.97, "total_tokens": 23540608} {"current_steps": 14415, "total_steps": 40000, "loss": 0.114, "lr": 3.561960312672667e-05, "epoch": 0.6525724891916974, "percentage": 36.04, "elapsed_time": "11:49:34", "remaining_time": "20:59:25", "throughput": 553.12, "total_tokens": 23548928} {"current_steps": 14420, "total_steps": 40000, "loss": 0.093, "lr": 3.5610714598436596e-05, "epoch": 0.6527988410783404, "percentage": 36.05, "elapsed_time": "11:49:37", "remaining_time": "20:58:49", "throughput": 553.27, "total_tokens": 23557024} {"current_steps": 14425, "total_steps": 40000, "loss": 0.0985, "lr": 3.5601824433840986e-05, "epoch": 0.6530251929649834, "percentage": 36.06, "elapsed_time": "11:49:40", "remaining_time": "20:58:14", "throughput": 553.42, "total_tokens": 23565056} {"current_steps": 14430, "total_steps": 40000, "loss": 0.1296, "lr": 3.559293263431082e-05, "epoch": 0.6532515448516263, "percentage": 36.08, "elapsed_time": "11:49:44", "remaining_time": "20:57:39", "throughput": 553.57, "total_tokens": 23573120} {"current_steps": 14435, "total_steps": 40000, "loss": 0.0719, "lr": 3.558403920121732e-05, "epoch": 0.6534778967382693, "percentage": 36.09, "elapsed_time": "11:49:47", "remaining_time": "20:57:03", "throughput": 553.72, "total_tokens": 23581280} {"current_steps": 14440, "total_steps": 40000, "loss": 0.1434, "lr": 3.557514413593197e-05, "epoch": 0.6537042486249123, "percentage": 36.1, "elapsed_time": "11:49:50", "remaining_time": "20:56:28", "throughput": 553.88, "total_tokens": 23589856} {"current_steps": 14445, "total_steps": 40000, "loss": 0.1156, "lr": 3.55662474398265e-05, "epoch": 0.6539306005115553, "percentage": 36.11, "elapsed_time": "11:49:53", "remaining_time": "20:55:53", "throughput": 554.02, "total_tokens": 23597728} {"current_steps": 14450, "total_steps": 40000, "loss": 0.1155, "lr": 3.555734911427288e-05, "epoch": 0.6541569523981983, "percentage": 36.12, "elapsed_time": "11:49:56", "remaining_time": "20:55:18", "throughput": 554.17, "total_tokens": 23605696} {"current_steps": 14455, "total_steps": 40000, "loss": 0.1314, "lr": 3.5548449160643363e-05, "epoch": 0.6543833042848413, "percentage": 36.14, "elapsed_time": "11:49:59", "remaining_time": "20:54:42", "throughput": 554.31, "total_tokens": 23613472} {"current_steps": 14460, "total_steps": 40000, "loss": 0.1342, "lr": 3.553954758031043e-05, "epoch": 0.6546096561714841, "percentage": 36.15, "elapsed_time": "11:50:03", "remaining_time": "20:54:07", "throughput": 554.47, "total_tokens": 23622144} {"current_steps": 14465, "total_steps": 40000, "loss": 0.1403, "lr": 3.5530644374646815e-05, "epoch": 0.6548360080581271, "percentage": 36.16, "elapsed_time": "11:50:06", "remaining_time": "20:53:32", "throughput": 554.63, "total_tokens": 23630944} {"current_steps": 14470, "total_steps": 40000, "loss": 0.1134, "lr": 3.552173954502549e-05, "epoch": 0.6550623599447701, "percentage": 36.18, "elapsed_time": "11:50:09", "remaining_time": "20:52:57", "throughput": 554.79, "total_tokens": 23639200} {"current_steps": 14475, "total_steps": 40000, "loss": 0.0992, "lr": 3.55128330928197e-05, "epoch": 0.6552887118314131, "percentage": 36.19, "elapsed_time": "11:50:12", "remaining_time": "20:52:22", "throughput": 554.93, "total_tokens": 23647072} {"current_steps": 14480, "total_steps": 40000, "loss": 0.0877, "lr": 3.550392501940294e-05, "epoch": 0.6555150637180561, "percentage": 36.2, "elapsed_time": "11:50:15", "remaining_time": "20:51:47", "throughput": 555.08, "total_tokens": 23654976} {"current_steps": 14485, "total_steps": 40000, "loss": 0.0863, "lr": 3.5495015326148945e-05, "epoch": 0.6557414156046991, "percentage": 36.21, "elapsed_time": "11:50:18", "remaining_time": "20:51:12", "throughput": 555.22, "total_tokens": 23663008} {"current_steps": 14490, "total_steps": 40000, "loss": 0.1547, "lr": 3.548610401443169e-05, "epoch": 0.655967767491342, "percentage": 36.23, "elapsed_time": "11:50:22", "remaining_time": "20:50:37", "throughput": 555.38, "total_tokens": 23671552} {"current_steps": 14495, "total_steps": 40000, "loss": 0.1009, "lr": 3.547719108562543e-05, "epoch": 0.656194119377985, "percentage": 36.24, "elapsed_time": "11:50:25", "remaining_time": "20:50:02", "throughput": 555.55, "total_tokens": 23680448} {"current_steps": 14500, "total_steps": 40000, "loss": 0.1173, "lr": 3.546827654110464e-05, "epoch": 0.656420471264628, "percentage": 36.25, "elapsed_time": "11:50:28", "remaining_time": "20:49:27", "throughput": 555.69, "total_tokens": 23688512} {"current_steps": 14505, "total_steps": 40000, "loss": 0.1082, "lr": 3.545936038224405e-05, "epoch": 0.656646823151271, "percentage": 36.26, "elapsed_time": "11:50:31", "remaining_time": "20:48:52", "throughput": 555.83, "total_tokens": 23696192} {"current_steps": 14510, "total_steps": 40000, "loss": 0.0904, "lr": 3.545044261041864e-05, "epoch": 0.656873175037914, "percentage": 36.27, "elapsed_time": "11:50:34", "remaining_time": "20:48:17", "throughput": 555.98, "total_tokens": 23704384} {"current_steps": 14515, "total_steps": 40000, "loss": 0.1655, "lr": 3.5441523227003657e-05, "epoch": 0.6570995269245569, "percentage": 36.29, "elapsed_time": "11:50:38", "remaining_time": "20:47:43", "throughput": 556.15, "total_tokens": 23713088} {"current_steps": 14520, "total_steps": 40000, "loss": 0.1107, "lr": 3.543260223337459e-05, "epoch": 0.6573258788111999, "percentage": 36.3, "elapsed_time": "11:50:41", "remaining_time": "20:47:08", "throughput": 556.29, "total_tokens": 23720864} {"current_steps": 14525, "total_steps": 40000, "loss": 0.132, "lr": 3.542367963090714e-05, "epoch": 0.6575522306978429, "percentage": 36.31, "elapsed_time": "11:50:44", "remaining_time": "20:46:33", "throughput": 556.44, "total_tokens": 23728960} {"current_steps": 14530, "total_steps": 40000, "loss": 0.1276, "lr": 3.5414755420977295e-05, "epoch": 0.6577785825844858, "percentage": 36.33, "elapsed_time": "11:50:47", "remaining_time": "20:45:58", "throughput": 556.61, "total_tokens": 23738240} {"current_steps": 14535, "total_steps": 40000, "loss": 0.0816, "lr": 3.54058296049613e-05, "epoch": 0.6580049344711288, "percentage": 36.34, "elapsed_time": "11:50:51", "remaining_time": "20:45:23", "throughput": 556.75, "total_tokens": 23745920} {"current_steps": 14540, "total_steps": 40000, "loss": 0.1288, "lr": 3.53969021842356e-05, "epoch": 0.6582312863577718, "percentage": 36.35, "elapsed_time": "11:50:54", "remaining_time": "20:44:48", "throughput": 556.9, "total_tokens": 23753952} {"current_steps": 14545, "total_steps": 40000, "loss": 0.1358, "lr": 3.5387973160176926e-05, "epoch": 0.6584576382444147, "percentage": 36.36, "elapsed_time": "11:50:57", "remaining_time": "20:44:13", "throughput": 557.04, "total_tokens": 23761792} {"current_steps": 14550, "total_steps": 40000, "loss": 0.1182, "lr": 3.537904253416224e-05, "epoch": 0.6586839901310577, "percentage": 36.38, "elapsed_time": "11:51:00", "remaining_time": "20:43:39", "throughput": 557.18, "total_tokens": 23769536} {"current_steps": 14555, "total_steps": 40000, "loss": 0.2038, "lr": 3.537011030756878e-05, "epoch": 0.6589103420177007, "percentage": 36.39, "elapsed_time": "11:51:03", "remaining_time": "20:43:04", "throughput": 557.33, "total_tokens": 23777824} {"current_steps": 14560, "total_steps": 40000, "loss": 0.108, "lr": 3.536117648177399e-05, "epoch": 0.6591366939043437, "percentage": 36.4, "elapsed_time": "11:51:06", "remaining_time": "20:42:29", "throughput": 557.48, "total_tokens": 23786016} {"current_steps": 14565, "total_steps": 40000, "loss": 0.194, "lr": 3.535224105815558e-05, "epoch": 0.6593630457909867, "percentage": 36.41, "elapsed_time": "11:51:10", "remaining_time": "20:41:55", "throughput": 557.64, "total_tokens": 23794720} {"current_steps": 14570, "total_steps": 40000, "loss": 0.0848, "lr": 3.5343304038091494e-05, "epoch": 0.6595893976776297, "percentage": 36.43, "elapsed_time": "11:51:13", "remaining_time": "20:41:20", "throughput": 557.79, "total_tokens": 23802560} {"current_steps": 14575, "total_steps": 40000, "loss": 0.1082, "lr": 3.5334365422959955e-05, "epoch": 0.6598157495642726, "percentage": 36.44, "elapsed_time": "11:51:16", "remaining_time": "20:40:45", "throughput": 557.94, "total_tokens": 23810848} {"current_steps": 14580, "total_steps": 40000, "loss": 0.0889, "lr": 3.5325425214139396e-05, "epoch": 0.6600421014509156, "percentage": 36.45, "elapsed_time": "11:51:19", "remaining_time": "20:40:11", "throughput": 558.1, "total_tokens": 23819488} {"current_steps": 14585, "total_steps": 40000, "loss": 0.1305, "lr": 3.531648341300851e-05, "epoch": 0.6602684533375586, "percentage": 36.46, "elapsed_time": "11:51:22", "remaining_time": "20:39:36", "throughput": 558.25, "total_tokens": 23827776} {"current_steps": 14590, "total_steps": 40000, "loss": 0.0917, "lr": 3.530754002094623e-05, "epoch": 0.6604948052242016, "percentage": 36.48, "elapsed_time": "11:51:26", "remaining_time": "20:39:02", "throughput": 558.4, "total_tokens": 23835872} {"current_steps": 14595, "total_steps": 40000, "loss": 0.1766, "lr": 3.529859503933175e-05, "epoch": 0.6607211571108446, "percentage": 36.49, "elapsed_time": "11:51:29", "remaining_time": "20:38:27", "throughput": 558.55, "total_tokens": 23844000} {"current_steps": 14600, "total_steps": 40000, "loss": 0.1182, "lr": 3.52896484695445e-05, "epoch": 0.6609475089974874, "percentage": 36.5, "elapsed_time": "11:51:32", "remaining_time": "20:37:53", "throughput": 558.69, "total_tokens": 23851808} {"current_steps": 14600, "total_steps": 40000, "eval_loss": 0.13203474879264832, "epoch": 0.6609475089974874, "percentage": 36.5, "elapsed_time": "11:59:15", "remaining_time": "20:51:17", "throughput": 552.7, "total_tokens": 23851808} {"current_steps": 14605, "total_steps": 40000, "loss": 0.13, "lr": 3.528070031296414e-05, "epoch": 0.6611738608841304, "percentage": 36.51, "elapsed_time": "11:59:19", "remaining_time": "20:50:44", "throughput": 552.83, "total_tokens": 23859488} {"current_steps": 14610, "total_steps": 40000, "loss": 0.1646, "lr": 3.5271750570970605e-05, "epoch": 0.6614002127707734, "percentage": 36.52, "elapsed_time": "11:59:22", "remaining_time": "20:50:09", "throughput": 552.98, "total_tokens": 23868000} {"current_steps": 14615, "total_steps": 40000, "loss": 0.0989, "lr": 3.526279924494405e-05, "epoch": 0.6616265646574164, "percentage": 36.54, "elapsed_time": "11:59:25", "remaining_time": "20:49:34", "throughput": 553.13, "total_tokens": 23875968} {"current_steps": 14620, "total_steps": 40000, "loss": 0.1371, "lr": 3.5253846336264874e-05, "epoch": 0.6618529165440594, "percentage": 36.55, "elapsed_time": "11:59:28", "remaining_time": "20:49:00", "throughput": 553.29, "total_tokens": 23885088} {"current_steps": 14625, "total_steps": 40000, "loss": 0.1738, "lr": 3.5244891846313736e-05, "epoch": 0.6620792684307024, "percentage": 36.56, "elapsed_time": "11:59:31", "remaining_time": "20:48:25", "throughput": 553.44, "total_tokens": 23892992} {"current_steps": 14630, "total_steps": 40000, "loss": 0.1318, "lr": 3.5235935776471527e-05, "epoch": 0.6623056203173453, "percentage": 36.58, "elapsed_time": "11:59:35", "remaining_time": "20:47:50", "throughput": 553.58, "total_tokens": 23900736} {"current_steps": 14635, "total_steps": 40000, "loss": 0.1409, "lr": 3.522697812811939e-05, "epoch": 0.6625319722039883, "percentage": 36.59, "elapsed_time": "11:59:38", "remaining_time": "20:47:15", "throughput": 553.72, "total_tokens": 23908768} {"current_steps": 14640, "total_steps": 40000, "loss": 0.1276, "lr": 3.521801890263871e-05, "epoch": 0.6627583240906313, "percentage": 36.6, "elapsed_time": "11:59:41", "remaining_time": "20:46:40", "throughput": 553.87, "total_tokens": 23917088} {"current_steps": 14645, "total_steps": 40000, "loss": 0.2057, "lr": 3.5209058101411114e-05, "epoch": 0.6629846759772743, "percentage": 36.61, "elapsed_time": "11:59:44", "remaining_time": "20:46:05", "throughput": 554.01, "total_tokens": 23924544} {"current_steps": 14650, "total_steps": 40000, "loss": 0.1816, "lr": 3.520009572581845e-05, "epoch": 0.6632110278639173, "percentage": 36.62, "elapsed_time": "11:59:47", "remaining_time": "20:45:31", "throughput": 554.17, "total_tokens": 23933568} {"current_steps": 14655, "total_steps": 40000, "loss": 0.1506, "lr": 3.519113177724285e-05, "epoch": 0.6634373797505603, "percentage": 36.64, "elapsed_time": "11:59:50", "remaining_time": "20:44:56", "throughput": 554.31, "total_tokens": 23941376} {"current_steps": 14660, "total_steps": 40000, "loss": 0.1414, "lr": 3.5182166257066656e-05, "epoch": 0.6636637316372032, "percentage": 36.65, "elapsed_time": "11:59:54", "remaining_time": "20:44:21", "throughput": 554.45, "total_tokens": 23949056} {"current_steps": 14665, "total_steps": 40000, "loss": 0.1598, "lr": 3.517319916667247e-05, "epoch": 0.6638900835238462, "percentage": 36.66, "elapsed_time": "11:59:57", "remaining_time": "20:43:46", "throughput": 554.6, "total_tokens": 23957344} {"current_steps": 14670, "total_steps": 40000, "loss": 0.1209, "lr": 3.516423050744313e-05, "epoch": 0.6641164354104891, "percentage": 36.68, "elapsed_time": "12:00:00", "remaining_time": "20:43:12", "throughput": 554.76, "total_tokens": 23965728} {"current_steps": 14675, "total_steps": 40000, "loss": 0.1139, "lr": 3.5155260280761704e-05, "epoch": 0.6643427872971321, "percentage": 36.69, "elapsed_time": "12:00:03", "remaining_time": "20:42:37", "throughput": 554.91, "total_tokens": 23974272} {"current_steps": 14680, "total_steps": 40000, "loss": 0.0903, "lr": 3.514628848801154e-05, "epoch": 0.6645691391837751, "percentage": 36.7, "elapsed_time": "12:00:06", "remaining_time": "20:42:02", "throughput": 555.05, "total_tokens": 23982080} {"current_steps": 14685, "total_steps": 40000, "loss": 0.1174, "lr": 3.5137315130576174e-05, "epoch": 0.664795491070418, "percentage": 36.71, "elapsed_time": "12:00:09", "remaining_time": "20:41:28", "throughput": 555.2, "total_tokens": 23990080} {"current_steps": 14690, "total_steps": 40000, "loss": 0.1246, "lr": 3.512834020983942e-05, "epoch": 0.665021842957061, "percentage": 36.73, "elapsed_time": "12:00:13", "remaining_time": "20:40:53", "throughput": 555.35, "total_tokens": 23998592} {"current_steps": 14695, "total_steps": 40000, "loss": 0.1607, "lr": 3.5119363727185334e-05, "epoch": 0.665248194843704, "percentage": 36.74, "elapsed_time": "12:00:16", "remaining_time": "20:40:19", "throughput": 555.52, "total_tokens": 24007552} {"current_steps": 14700, "total_steps": 40000, "loss": 0.1128, "lr": 3.511038568399819e-05, "epoch": 0.665474546730347, "percentage": 36.75, "elapsed_time": "12:00:19", "remaining_time": "20:39:45", "throughput": 555.68, "total_tokens": 24016256} {"current_steps": 14705, "total_steps": 40000, "loss": 0.1116, "lr": 3.510140608166251e-05, "epoch": 0.66570089861699, "percentage": 36.76, "elapsed_time": "12:00:22", "remaining_time": "20:39:10", "throughput": 555.82, "total_tokens": 24024320} {"current_steps": 14710, "total_steps": 40000, "loss": 0.1364, "lr": 3.509242492156308e-05, "epoch": 0.665927250503633, "percentage": 36.78, "elapsed_time": "12:00:26", "remaining_time": "20:38:36", "throughput": 555.98, "total_tokens": 24032800} {"current_steps": 14715, "total_steps": 40000, "loss": 0.1634, "lr": 3.5083442205084896e-05, "epoch": 0.6661536023902759, "percentage": 36.79, "elapsed_time": "12:00:29", "remaining_time": "20:38:01", "throughput": 556.12, "total_tokens": 24040608} {"current_steps": 14720, "total_steps": 40000, "loss": 0.1312, "lr": 3.507445793361321e-05, "epoch": 0.6663799542769189, "percentage": 36.8, "elapsed_time": "12:00:32", "remaining_time": "20:37:26", "throughput": 556.26, "total_tokens": 24048480} {"current_steps": 14725, "total_steps": 40000, "loss": 0.1558, "lr": 3.5065472108533505e-05, "epoch": 0.6666063061635619, "percentage": 36.81, "elapsed_time": "12:00:35", "remaining_time": "20:36:52", "throughput": 556.41, "total_tokens": 24056800} {"current_steps": 14730, "total_steps": 40000, "loss": 0.1234, "lr": 3.5056484731231504e-05, "epoch": 0.6668326580502049, "percentage": 36.83, "elapsed_time": "12:00:38", "remaining_time": "20:36:18", "throughput": 556.57, "total_tokens": 24065376} {"current_steps": 14735, "total_steps": 40000, "loss": 0.127, "lr": 3.504749580309319e-05, "epoch": 0.6670590099368479, "percentage": 36.84, "elapsed_time": "12:00:42", "remaining_time": "20:35:43", "throughput": 556.72, "total_tokens": 24073728} {"current_steps": 14740, "total_steps": 40000, "loss": 0.1229, "lr": 3.5038505325504753e-05, "epoch": 0.6672853618234909, "percentage": 36.85, "elapsed_time": "12:00:45", "remaining_time": "20:35:09", "throughput": 556.87, "total_tokens": 24082112} {"current_steps": 14745, "total_steps": 40000, "loss": 0.1261, "lr": 3.502951329985264e-05, "epoch": 0.6675117137101337, "percentage": 36.86, "elapsed_time": "12:00:48", "remaining_time": "20:34:35", "throughput": 557.02, "total_tokens": 24090208} {"current_steps": 14750, "total_steps": 40000, "loss": 0.1627, "lr": 3.502051972752354e-05, "epoch": 0.6677380655967767, "percentage": 36.88, "elapsed_time": "12:00:51", "remaining_time": "20:34:01", "throughput": 557.16, "total_tokens": 24098304} {"current_steps": 14755, "total_steps": 40000, "loss": 0.1333, "lr": 3.5011524609904374e-05, "epoch": 0.6679644174834197, "percentage": 36.89, "elapsed_time": "12:00:54", "remaining_time": "20:33:26", "throughput": 557.31, "total_tokens": 24106592} {"current_steps": 14760, "total_steps": 40000, "loss": 0.0966, "lr": 3.50025279483823e-05, "epoch": 0.6681907693700627, "percentage": 36.9, "elapsed_time": "12:00:57", "remaining_time": "20:32:52", "throughput": 557.45, "total_tokens": 24114080} {"current_steps": 14765, "total_steps": 40000, "loss": 0.1348, "lr": 3.499352974434472e-05, "epoch": 0.6684171212567057, "percentage": 36.91, "elapsed_time": "12:01:01", "remaining_time": "20:32:18", "throughput": 557.59, "total_tokens": 24122016} {"current_steps": 14770, "total_steps": 40000, "loss": 0.104, "lr": 3.498452999917926e-05, "epoch": 0.6686434731433486, "percentage": 36.93, "elapsed_time": "12:01:04", "remaining_time": "20:31:43", "throughput": 557.73, "total_tokens": 24129952} {"current_steps": 14775, "total_steps": 40000, "loss": 0.1159, "lr": 3.4975528714273795e-05, "epoch": 0.6688698250299916, "percentage": 36.94, "elapsed_time": "12:01:07", "remaining_time": "20:31:09", "throughput": 557.87, "total_tokens": 24137760} {"current_steps": 14780, "total_steps": 40000, "loss": 0.1297, "lr": 3.4966525891016454e-05, "epoch": 0.6690961769166346, "percentage": 36.95, "elapsed_time": "12:01:10", "remaining_time": "20:30:35", "throughput": 558.03, "total_tokens": 24146080} {"current_steps": 14785, "total_steps": 40000, "loss": 0.119, "lr": 3.495752153079557e-05, "epoch": 0.6693225288032776, "percentage": 36.96, "elapsed_time": "12:01:13", "remaining_time": "20:30:01", "throughput": 558.18, "total_tokens": 24154400} {"current_steps": 14790, "total_steps": 40000, "loss": 0.0724, "lr": 3.494851563499974e-05, "epoch": 0.6695488806899206, "percentage": 36.98, "elapsed_time": "12:01:16", "remaining_time": "20:29:26", "throughput": 558.33, "total_tokens": 24162688} {"current_steps": 14795, "total_steps": 40000, "loss": 0.1436, "lr": 3.493950820501777e-05, "epoch": 0.6697752325765636, "percentage": 36.99, "elapsed_time": "12:01:20", "remaining_time": "20:28:52", "throughput": 558.47, "total_tokens": 24170880} {"current_steps": 14800, "total_steps": 40000, "loss": 0.1321, "lr": 3.493049924223872e-05, "epoch": 0.6700015844632065, "percentage": 37.0, "elapsed_time": "12:01:23", "remaining_time": "20:28:18", "throughput": 558.62, "total_tokens": 24178976} {"current_steps": 14800, "total_steps": 40000, "eval_loss": 0.13117986917495728, "epoch": 0.6700015844632065, "percentage": 37.0, "elapsed_time": "12:09:06", "remaining_time": "20:41:26", "throughput": 552.71, "total_tokens": 24178976} {"current_steps": 14805, "total_steps": 40000, "loss": 0.0969, "lr": 3.49214887480519e-05, "epoch": 0.6702279363498495, "percentage": 37.01, "elapsed_time": "12:09:10", "remaining_time": "20:40:53", "throughput": 552.84, "total_tokens": 24187072} {"current_steps": 14810, "total_steps": 40000, "loss": 0.1765, "lr": 3.4912476723846834e-05, "epoch": 0.6704542882364924, "percentage": 37.03, "elapsed_time": "12:09:13", "remaining_time": "20:40:19", "throughput": 553.0, "total_tokens": 24195424} {"current_steps": 14815, "total_steps": 40000, "loss": 0.1662, "lr": 3.490346317101328e-05, "epoch": 0.6706806401231354, "percentage": 37.04, "elapsed_time": "12:09:16", "remaining_time": "20:39:44", "throughput": 553.13, "total_tokens": 24202976} {"current_steps": 14820, "total_steps": 40000, "loss": 0.1461, "lr": 3.4894448090941266e-05, "epoch": 0.6709069920097784, "percentage": 37.05, "elapsed_time": "12:09:19", "remaining_time": "20:39:09", "throughput": 553.27, "total_tokens": 24210752} {"current_steps": 14825, "total_steps": 40000, "loss": 0.1873, "lr": 3.488543148502101e-05, "epoch": 0.6711333438964214, "percentage": 37.06, "elapsed_time": "12:09:22", "remaining_time": "20:38:35", "throughput": 553.42, "total_tokens": 24219296} {"current_steps": 14830, "total_steps": 40000, "loss": 0.1181, "lr": 3.487641335464299e-05, "epoch": 0.6713596957830643, "percentage": 37.08, "elapsed_time": "12:09:25", "remaining_time": "20:38:01", "throughput": 553.56, "total_tokens": 24226848} {"current_steps": 14835, "total_steps": 40000, "loss": 0.1138, "lr": 3.4867393701197914e-05, "epoch": 0.6715860476697073, "percentage": 37.09, "elapsed_time": "12:09:29", "remaining_time": "20:37:26", "throughput": 553.7, "total_tokens": 24235008} {"current_steps": 14840, "total_steps": 40000, "loss": 0.1195, "lr": 3.485837252607673e-05, "epoch": 0.6718123995563503, "percentage": 37.1, "elapsed_time": "12:09:32", "remaining_time": "20:36:52", "throughput": 553.85, "total_tokens": 24243200} {"current_steps": 14845, "total_steps": 40000, "loss": 0.1268, "lr": 3.4849349830670615e-05, "epoch": 0.6720387514429933, "percentage": 37.11, "elapsed_time": "12:09:35", "remaining_time": "20:36:17", "throughput": 553.98, "total_tokens": 24250912} {"current_steps": 14850, "total_steps": 40000, "loss": 0.1239, "lr": 3.4840325616370976e-05, "epoch": 0.6722651033296363, "percentage": 37.12, "elapsed_time": "12:09:38", "remaining_time": "20:35:43", "throughput": 554.13, "total_tokens": 24258912} {"current_steps": 14855, "total_steps": 40000, "loss": 0.1347, "lr": 3.483129988456947e-05, "epoch": 0.6724914552162792, "percentage": 37.14, "elapsed_time": "12:09:41", "remaining_time": "20:35:09", "throughput": 554.28, "total_tokens": 24267296} {"current_steps": 14860, "total_steps": 40000, "loss": 0.1798, "lr": 3.482227263665797e-05, "epoch": 0.6727178071029222, "percentage": 37.15, "elapsed_time": "12:09:44", "remaining_time": "20:34:34", "throughput": 554.43, "total_tokens": 24275584} {"current_steps": 14865, "total_steps": 40000, "loss": 0.0933, "lr": 3.48132438740286e-05, "epoch": 0.6729441589895652, "percentage": 37.16, "elapsed_time": "12:09:48", "remaining_time": "20:34:00", "throughput": 554.57, "total_tokens": 24283680} {"current_steps": 14870, "total_steps": 40000, "loss": 0.1621, "lr": 3.48042135980737e-05, "epoch": 0.6731705108762082, "percentage": 37.18, "elapsed_time": "12:09:51", "remaining_time": "20:33:26", "throughput": 554.73, "total_tokens": 24292416} {"current_steps": 14875, "total_steps": 40000, "loss": 0.2003, "lr": 3.479518181018586e-05, "epoch": 0.6733968627628512, "percentage": 37.19, "elapsed_time": "12:09:54", "remaining_time": "20:32:52", "throughput": 554.89, "total_tokens": 24301056} {"current_steps": 14880, "total_steps": 40000, "loss": 0.1001, "lr": 3.4786148511757886e-05, "epoch": 0.6736232146494942, "percentage": 37.2, "elapsed_time": "12:09:57", "remaining_time": "20:32:18", "throughput": 555.03, "total_tokens": 24309152} {"current_steps": 14885, "total_steps": 40000, "loss": 0.1508, "lr": 3.477711370418284e-05, "epoch": 0.673849566536137, "percentage": 37.21, "elapsed_time": "12:10:01", "remaining_time": "20:31:44", "throughput": 555.18, "total_tokens": 24317664} {"current_steps": 14890, "total_steps": 40000, "loss": 0.1199, "lr": 3.476807738885399e-05, "epoch": 0.67407591842278, "percentage": 37.23, "elapsed_time": "12:10:04", "remaining_time": "20:31:10", "throughput": 555.34, "total_tokens": 24326336} {"current_steps": 14895, "total_steps": 40000, "loss": 0.1196, "lr": 3.475903956716485e-05, "epoch": 0.674302270309423, "percentage": 37.24, "elapsed_time": "12:10:07", "remaining_time": "20:30:36", "throughput": 555.49, "total_tokens": 24334432} {"current_steps": 14900, "total_steps": 40000, "loss": 0.1329, "lr": 3.475000024050917e-05, "epoch": 0.674528622196066, "percentage": 37.25, "elapsed_time": "12:10:10", "remaining_time": "20:30:01", "throughput": 555.64, "total_tokens": 24342912} {"current_steps": 14905, "total_steps": 40000, "loss": 0.1737, "lr": 3.4740959410280926e-05, "epoch": 0.674754974082709, "percentage": 37.26, "elapsed_time": "12:10:13", "remaining_time": "20:29:27", "throughput": 555.78, "total_tokens": 24350784} {"current_steps": 14910, "total_steps": 40000, "loss": 0.1363, "lr": 3.4731917077874324e-05, "epoch": 0.674981325969352, "percentage": 37.28, "elapsed_time": "12:10:17", "remaining_time": "20:28:53", "throughput": 555.93, "total_tokens": 24359264} {"current_steps": 14915, "total_steps": 40000, "loss": 0.1449, "lr": 3.4722873244683816e-05, "epoch": 0.6752076778559949, "percentage": 37.29, "elapsed_time": "12:10:20", "remaining_time": "20:28:19", "throughput": 556.07, "total_tokens": 24366976} {"current_steps": 14920, "total_steps": 40000, "loss": 0.1347, "lr": 3.4713827912104065e-05, "epoch": 0.6754340297426379, "percentage": 37.3, "elapsed_time": "12:10:23", "remaining_time": "20:27:45", "throughput": 556.21, "total_tokens": 24374848} {"current_steps": 14925, "total_steps": 40000, "loss": 0.1039, "lr": 3.470478108152998e-05, "epoch": 0.6756603816292809, "percentage": 37.31, "elapsed_time": "12:10:26", "remaining_time": "20:27:11", "throughput": 556.36, "total_tokens": 24383424} {"current_steps": 14930, "total_steps": 40000, "loss": 0.0911, "lr": 3.4695732754356695e-05, "epoch": 0.6758867335159239, "percentage": 37.33, "elapsed_time": "12:10:30", "remaining_time": "20:26:38", "throughput": 556.51, "total_tokens": 24392000} {"current_steps": 14935, "total_steps": 40000, "loss": 0.0853, "lr": 3.4686682931979576e-05, "epoch": 0.6761130854025669, "percentage": 37.34, "elapsed_time": "12:10:33", "remaining_time": "20:26:04", "throughput": 556.67, "total_tokens": 24400800} {"current_steps": 14940, "total_steps": 40000, "loss": 0.0986, "lr": 3.467763161579422e-05, "epoch": 0.6763394372892098, "percentage": 37.35, "elapsed_time": "12:10:36", "remaining_time": "20:25:30", "throughput": 556.81, "total_tokens": 24408704} {"current_steps": 14945, "total_steps": 40000, "loss": 0.1135, "lr": 3.466857880719645e-05, "epoch": 0.6765657891758527, "percentage": 37.36, "elapsed_time": "12:10:39", "remaining_time": "20:24:56", "throughput": 556.96, "total_tokens": 24416768} {"current_steps": 14950, "total_steps": 40000, "loss": 0.1291, "lr": 3.465952450758233e-05, "epoch": 0.6767921410624957, "percentage": 37.38, "elapsed_time": "12:10:42", "remaining_time": "20:24:22", "throughput": 557.11, "total_tokens": 24425120} {"current_steps": 14955, "total_steps": 40000, "loss": 0.1074, "lr": 3.4650468718348126e-05, "epoch": 0.6770184929491387, "percentage": 37.39, "elapsed_time": "12:10:45", "remaining_time": "20:23:48", "throughput": 557.25, "total_tokens": 24433280} {"current_steps": 14960, "total_steps": 40000, "loss": 0.1416, "lr": 3.464141144089038e-05, "epoch": 0.6772448448357817, "percentage": 37.4, "elapsed_time": "12:10:49", "remaining_time": "20:23:14", "throughput": 557.39, "total_tokens": 24441184} {"current_steps": 14965, "total_steps": 40000, "loss": 0.1603, "lr": 3.463235267660583e-05, "epoch": 0.6774711967224247, "percentage": 37.41, "elapsed_time": "12:10:52", "remaining_time": "20:22:40", "throughput": 557.53, "total_tokens": 24448832} {"current_steps": 14970, "total_steps": 40000, "loss": 0.2094, "lr": 3.462329242689145e-05, "epoch": 0.6776975486090676, "percentage": 37.43, "elapsed_time": "12:10:55", "remaining_time": "20:22:06", "throughput": 557.67, "total_tokens": 24456768} {"current_steps": 14975, "total_steps": 40000, "loss": 0.1291, "lr": 3.461423069314444e-05, "epoch": 0.6779239004957106, "percentage": 37.44, "elapsed_time": "12:10:58", "remaining_time": "20:21:32", "throughput": 557.82, "total_tokens": 24464960} {"current_steps": 14980, "total_steps": 40000, "loss": 0.1285, "lr": 3.460516747676224e-05, "epoch": 0.6781502523823536, "percentage": 37.45, "elapsed_time": "12:11:01", "remaining_time": "20:20:58", "throughput": 557.96, "total_tokens": 24472864} {"current_steps": 14985, "total_steps": 40000, "loss": 0.1359, "lr": 3.459610277914251e-05, "epoch": 0.6783766042689966, "percentage": 37.46, "elapsed_time": "12:11:04", "remaining_time": "20:20:25", "throughput": 558.1, "total_tokens": 24480896} {"current_steps": 14990, "total_steps": 40000, "loss": 0.1362, "lr": 3.458703660168314e-05, "epoch": 0.6786029561556396, "percentage": 37.48, "elapsed_time": "12:11:08", "remaining_time": "20:19:51", "throughput": 558.25, "total_tokens": 24489568} {"current_steps": 14995, "total_steps": 40000, "loss": 0.1221, "lr": 3.457796894578224e-05, "epoch": 0.6788293080422826, "percentage": 37.49, "elapsed_time": "12:11:11", "remaining_time": "20:19:18", "throughput": 558.41, "total_tokens": 24498176} {"current_steps": 15000, "total_steps": 40000, "loss": 0.1284, "lr": 3.456889981283817e-05, "epoch": 0.6790556599289255, "percentage": 37.5, "elapsed_time": "12:11:14", "remaining_time": "20:18:44", "throughput": 558.55, "total_tokens": 24506336} {"current_steps": 15000, "total_steps": 40000, "eval_loss": 0.13028113543987274, "epoch": 0.6790556599289255, "percentage": 37.5, "elapsed_time": "12:18:57", "remaining_time": "20:31:35", "throughput": 552.73, "total_tokens": 24506336} {"current_steps": 15005, "total_steps": 40000, "loss": 0.1651, "lr": 3.45598292042495e-05, "epoch": 0.6792820118155685, "percentage": 37.51, "elapsed_time": "12:19:01", "remaining_time": "20:31:02", "throughput": 552.86, "total_tokens": 24514432} {"current_steps": 15010, "total_steps": 40000, "loss": 0.1419, "lr": 3.4550757121415035e-05, "epoch": 0.6795083637022115, "percentage": 37.52, "elapsed_time": "12:19:04", "remaining_time": "20:30:28", "throughput": 553.0, "total_tokens": 24522592} {"current_steps": 15015, "total_steps": 40000, "loss": 0.1535, "lr": 3.454168356573378e-05, "epoch": 0.6797347155888545, "percentage": 37.54, "elapsed_time": "12:19:07", "remaining_time": "20:29:54", "throughput": 553.14, "total_tokens": 24530592} {"current_steps": 15020, "total_steps": 40000, "loss": 0.1432, "lr": 3.453260853860503e-05, "epoch": 0.6799610674754974, "percentage": 37.55, "elapsed_time": "12:19:10", "remaining_time": "20:29:20", "throughput": 553.28, "total_tokens": 24538496} {"current_steps": 15025, "total_steps": 40000, "loss": 0.1818, "lr": 3.452353204142824e-05, "epoch": 0.6801874193621403, "percentage": 37.56, "elapsed_time": "12:19:13", "remaining_time": "20:28:46", "throughput": 553.42, "total_tokens": 24546304} {"current_steps": 15030, "total_steps": 40000, "loss": 0.137, "lr": 3.4514454075603136e-05, "epoch": 0.6804137712487833, "percentage": 37.57, "elapsed_time": "12:19:16", "remaining_time": "20:28:12", "throughput": 553.56, "total_tokens": 24554272} {"current_steps": 15035, "total_steps": 40000, "loss": 0.1128, "lr": 3.450537464252964e-05, "epoch": 0.6806401231354263, "percentage": 37.59, "elapsed_time": "12:19:20", "remaining_time": "20:27:38", "throughput": 553.72, "total_tokens": 24562912} {"current_steps": 15040, "total_steps": 40000, "loss": 0.1342, "lr": 3.4496293743607925e-05, "epoch": 0.6808664750220693, "percentage": 37.6, "elapsed_time": "12:19:23", "remaining_time": "20:27:04", "throughput": 553.86, "total_tokens": 24571072} {"current_steps": 15045, "total_steps": 40000, "loss": 0.095, "lr": 3.448721138023838e-05, "epoch": 0.6810928269087123, "percentage": 37.61, "elapsed_time": "12:19:26", "remaining_time": "20:26:30", "throughput": 553.99, "total_tokens": 24578816} {"current_steps": 15050, "total_steps": 40000, "loss": 0.1223, "lr": 3.447812755382162e-05, "epoch": 0.6813191787953553, "percentage": 37.62, "elapsed_time": "12:19:29", "remaining_time": "20:25:56", "throughput": 554.14, "total_tokens": 24586944} {"current_steps": 15055, "total_steps": 40000, "loss": 0.0998, "lr": 3.446904226575847e-05, "epoch": 0.6815455306819982, "percentage": 37.64, "elapsed_time": "12:19:32", "remaining_time": "20:25:22", "throughput": 554.28, "total_tokens": 24594976} {"current_steps": 15060, "total_steps": 40000, "loss": 0.19, "lr": 3.445995551745002e-05, "epoch": 0.6817718825686412, "percentage": 37.65, "elapsed_time": "12:19:36", "remaining_time": "20:24:48", "throughput": 554.42, "total_tokens": 24603040} {"current_steps": 15065, "total_steps": 40000, "loss": 0.1326, "lr": 3.445086731029753e-05, "epoch": 0.6819982344552842, "percentage": 37.66, "elapsed_time": "12:19:39", "remaining_time": "20:24:14", "throughput": 554.57, "total_tokens": 24611328} {"current_steps": 15070, "total_steps": 40000, "loss": 0.1361, "lr": 3.444177764570255e-05, "epoch": 0.6822245863419272, "percentage": 37.67, "elapsed_time": "12:19:42", "remaining_time": "20:23:40", "throughput": 554.71, "total_tokens": 24619264} {"current_steps": 15075, "total_steps": 40000, "loss": 0.1851, "lr": 3.44326865250668e-05, "epoch": 0.6824509382285702, "percentage": 37.69, "elapsed_time": "12:19:45", "remaining_time": "20:23:06", "throughput": 554.85, "total_tokens": 24627072} {"current_steps": 15080, "total_steps": 40000, "loss": 0.1145, "lr": 3.442359394979225e-05, "epoch": 0.6826772901152132, "percentage": 37.7, "elapsed_time": "12:19:48", "remaining_time": "20:22:33", "throughput": 554.99, "total_tokens": 24635488} {"current_steps": 15085, "total_steps": 40000, "loss": 0.0871, "lr": 3.441449992128108e-05, "epoch": 0.682903642001856, "percentage": 37.71, "elapsed_time": "12:19:51", "remaining_time": "20:21:59", "throughput": 555.14, "total_tokens": 24643840} {"current_steps": 15090, "total_steps": 40000, "loss": 0.1812, "lr": 3.440540444093573e-05, "epoch": 0.683129993888499, "percentage": 37.72, "elapsed_time": "12:19:55", "remaining_time": "20:21:25", "throughput": 555.29, "total_tokens": 24652096} {"current_steps": 15095, "total_steps": 40000, "loss": 0.1304, "lr": 3.43963075101588e-05, "epoch": 0.683356345775142, "percentage": 37.74, "elapsed_time": "12:19:58", "remaining_time": "20:20:52", "throughput": 555.42, "total_tokens": 24659936} {"current_steps": 15100, "total_steps": 40000, "loss": 0.1115, "lr": 3.438720913035318e-05, "epoch": 0.683582697661785, "percentage": 37.75, "elapsed_time": "12:20:01", "remaining_time": "20:20:18", "throughput": 555.56, "total_tokens": 24667776} {"current_steps": 15105, "total_steps": 40000, "loss": 0.1007, "lr": 3.437810930292195e-05, "epoch": 0.683809049548428, "percentage": 37.76, "elapsed_time": "12:20:04", "remaining_time": "20:19:44", "throughput": 555.72, "total_tokens": 24676384} {"current_steps": 15110, "total_steps": 40000, "loss": 0.1353, "lr": 3.43690080292684e-05, "epoch": 0.6840354014350709, "percentage": 37.77, "elapsed_time": "12:20:07", "remaining_time": "20:19:10", "throughput": 555.86, "total_tokens": 24684544} {"current_steps": 15115, "total_steps": 40000, "loss": 0.0801, "lr": 3.435990531079608e-05, "epoch": 0.6842617533217139, "percentage": 37.79, "elapsed_time": "12:20:10", "remaining_time": "20:18:37", "throughput": 555.99, "total_tokens": 24692224} {"current_steps": 15120, "total_steps": 40000, "loss": 0.1108, "lr": 3.435080114890874e-05, "epoch": 0.6844881052083569, "percentage": 37.8, "elapsed_time": "12:20:13", "remaining_time": "20:18:03", "throughput": 556.12, "total_tokens": 24699712} {"current_steps": 15125, "total_steps": 40000, "loss": 0.1451, "lr": 3.434169554501035e-05, "epoch": 0.6847144570949999, "percentage": 37.81, "elapsed_time": "12:20:17", "remaining_time": "20:17:29", "throughput": 556.27, "total_tokens": 24707840} {"current_steps": 15130, "total_steps": 40000, "loss": 0.0796, "lr": 3.433258850050511e-05, "epoch": 0.6849408089816429, "percentage": 37.82, "elapsed_time": "12:20:20", "remaining_time": "20:16:56", "throughput": 556.41, "total_tokens": 24716000} {"current_steps": 15135, "total_steps": 40000, "loss": 0.0833, "lr": 3.4323480016797446e-05, "epoch": 0.6851671608682859, "percentage": 37.84, "elapsed_time": "12:20:23", "remaining_time": "20:16:22", "throughput": 556.55, "total_tokens": 24723808} {"current_steps": 15140, "total_steps": 40000, "loss": 0.1223, "lr": 3.4314370095291995e-05, "epoch": 0.6853935127549288, "percentage": 37.85, "elapsed_time": "12:20:26", "remaining_time": "20:15:48", "throughput": 556.69, "total_tokens": 24732000} {"current_steps": 15145, "total_steps": 40000, "loss": 0.1143, "lr": 3.430525873739363e-05, "epoch": 0.6856198646415718, "percentage": 37.86, "elapsed_time": "12:20:29", "remaining_time": "20:15:15", "throughput": 556.84, "total_tokens": 24740416} {"current_steps": 15150, "total_steps": 40000, "loss": 0.1052, "lr": 3.429614594450743e-05, "epoch": 0.6858462165282148, "percentage": 37.88, "elapsed_time": "12:20:33", "remaining_time": "20:14:41", "throughput": 556.98, "total_tokens": 24748512} {"current_steps": 15155, "total_steps": 40000, "loss": 0.1058, "lr": 3.428703171803869e-05, "epoch": 0.6860725684148578, "percentage": 37.89, "elapsed_time": "12:20:36", "remaining_time": "20:14:08", "throughput": 557.12, "total_tokens": 24756384} {"current_steps": 15160, "total_steps": 40000, "loss": 0.1098, "lr": 3.4277916059392964e-05, "epoch": 0.6862989203015007, "percentage": 37.9, "elapsed_time": "12:20:39", "remaining_time": "20:13:34", "throughput": 557.26, "total_tokens": 24764064} {"current_steps": 15165, "total_steps": 40000, "loss": 0.1235, "lr": 3.426879896997598e-05, "epoch": 0.6865252721881437, "percentage": 37.91, "elapsed_time": "12:20:42", "remaining_time": "20:13:01", "throughput": 557.39, "total_tokens": 24771840} {"current_steps": 15170, "total_steps": 40000, "loss": 0.1622, "lr": 3.425968045119372e-05, "epoch": 0.6867516240747866, "percentage": 37.92, "elapsed_time": "12:20:45", "remaining_time": "20:12:27", "throughput": 557.53, "total_tokens": 24779552} {"current_steps": 15175, "total_steps": 40000, "loss": 0.1567, "lr": 3.425056050445237e-05, "epoch": 0.6869779759614296, "percentage": 37.94, "elapsed_time": "12:20:48", "remaining_time": "20:11:54", "throughput": 557.67, "total_tokens": 24787840} {"current_steps": 15180, "total_steps": 40000, "loss": 0.1454, "lr": 3.4241439131158336e-05, "epoch": 0.6872043278480726, "percentage": 37.95, "elapsed_time": "12:20:51", "remaining_time": "20:11:20", "throughput": 557.82, "total_tokens": 24796288} {"current_steps": 15185, "total_steps": 40000, "loss": 0.1016, "lr": 3.423231633271825e-05, "epoch": 0.6874306797347156, "percentage": 37.96, "elapsed_time": "12:20:55", "remaining_time": "20:10:47", "throughput": 557.97, "total_tokens": 24804640} {"current_steps": 15190, "total_steps": 40000, "loss": 0.0694, "lr": 3.4223192110538985e-05, "epoch": 0.6876570316213586, "percentage": 37.97, "elapsed_time": "12:20:58", "remaining_time": "20:10:14", "throughput": 558.11, "total_tokens": 24812544} {"current_steps": 15195, "total_steps": 40000, "loss": 0.1331, "lr": 3.4214066466027575e-05, "epoch": 0.6878833835080015, "percentage": 37.99, "elapsed_time": "12:21:01", "remaining_time": "20:09:41", "throughput": 558.27, "total_tokens": 24821600} {"current_steps": 15200, "total_steps": 40000, "loss": 0.0974, "lr": 3.4204939400591325e-05, "epoch": 0.6881097353946445, "percentage": 38.0, "elapsed_time": "12:21:04", "remaining_time": "20:09:07", "throughput": 558.41, "total_tokens": 24829472} {"current_steps": 15200, "total_steps": 40000, "eval_loss": 0.13006596267223358, "epoch": 0.6881097353946445, "percentage": 38.0, "elapsed_time": "12:28:47", "remaining_time": "20:21:42", "throughput": 552.66, "total_tokens": 24829472} {"current_steps": 15205, "total_steps": 40000, "loss": 0.1324, "lr": 3.419581091563775e-05, "epoch": 0.6883360872812875, "percentage": 38.01, "elapsed_time": "12:28:51", "remaining_time": "20:21:10", "throughput": 552.8, "total_tokens": 24837984} {"current_steps": 15210, "total_steps": 40000, "loss": 0.1384, "lr": 3.418668101257456e-05, "epoch": 0.6885624391679305, "percentage": 38.02, "elapsed_time": "12:28:54", "remaining_time": "20:20:36", "throughput": 552.96, "total_tokens": 24847008} {"current_steps": 15215, "total_steps": 40000, "loss": 0.1158, "lr": 3.417754969280971e-05, "epoch": 0.6887887910545735, "percentage": 38.04, "elapsed_time": "12:28:57", "remaining_time": "20:20:02", "throughput": 553.09, "total_tokens": 24854784} {"current_steps": 15220, "total_steps": 40000, "loss": 0.072, "lr": 3.416841695775137e-05, "epoch": 0.6890151429412165, "percentage": 38.05, "elapsed_time": "12:29:01", "remaining_time": "20:19:29", "throughput": 553.24, "total_tokens": 24863232} {"current_steps": 15225, "total_steps": 40000, "loss": 0.1432, "lr": 3.415928280880792e-05, "epoch": 0.6892414948278593, "percentage": 38.06, "elapsed_time": "12:29:04", "remaining_time": "20:18:55", "throughput": 553.38, "total_tokens": 24871360} {"current_steps": 15230, "total_steps": 40000, "loss": 0.1381, "lr": 3.4150147247387965e-05, "epoch": 0.6894678467145023, "percentage": 38.07, "elapsed_time": "12:29:07", "remaining_time": "20:18:22", "throughput": 553.52, "total_tokens": 24879232} {"current_steps": 15235, "total_steps": 40000, "loss": 0.1025, "lr": 3.4141010274900306e-05, "epoch": 0.6896941986011453, "percentage": 38.09, "elapsed_time": "12:29:10", "remaining_time": "20:17:48", "throughput": 553.67, "total_tokens": 24887616} {"current_steps": 15240, "total_steps": 40000, "loss": 0.0863, "lr": 3.413187189275399e-05, "epoch": 0.6899205504877883, "percentage": 38.1, "elapsed_time": "12:29:13", "remaining_time": "20:17:14", "throughput": 553.8, "total_tokens": 24895488} {"current_steps": 15245, "total_steps": 40000, "loss": 0.0846, "lr": 3.4122732102358265e-05, "epoch": 0.6901469023744313, "percentage": 38.11, "elapsed_time": "12:29:17", "remaining_time": "20:16:41", "throughput": 553.94, "total_tokens": 24903392} {"current_steps": 15250, "total_steps": 40000, "loss": 0.1383, "lr": 3.411359090512261e-05, "epoch": 0.6903732542610743, "percentage": 38.12, "elapsed_time": "12:29:20", "remaining_time": "20:16:08", "throughput": 554.07, "total_tokens": 24911264} {"current_steps": 15255, "total_steps": 40000, "loss": 0.1464, "lr": 3.410444830245672e-05, "epoch": 0.6905996061477172, "percentage": 38.14, "elapsed_time": "12:29:23", "remaining_time": "20:15:34", "throughput": 554.21, "total_tokens": 24919232} {"current_steps": 15260, "total_steps": 40000, "loss": 0.132, "lr": 3.409530429577048e-05, "epoch": 0.6908259580343602, "percentage": 38.15, "elapsed_time": "12:29:26", "remaining_time": "20:15:01", "throughput": 554.35, "total_tokens": 24927360} {"current_steps": 15265, "total_steps": 40000, "loss": 0.1097, "lr": 3.408615888647402e-05, "epoch": 0.6910523099210032, "percentage": 38.16, "elapsed_time": "12:29:29", "remaining_time": "20:14:27", "throughput": 554.5, "total_tokens": 24935648} {"current_steps": 15270, "total_steps": 40000, "loss": 0.1151, "lr": 3.4077012075977675e-05, "epoch": 0.6912786618076462, "percentage": 38.17, "elapsed_time": "12:29:32", "remaining_time": "20:13:54", "throughput": 554.64, "total_tokens": 24943744} {"current_steps": 15275, "total_steps": 40000, "loss": 0.1577, "lr": 3.4067863865692e-05, "epoch": 0.6915050136942892, "percentage": 38.19, "elapsed_time": "12:29:36", "remaining_time": "20:13:20", "throughput": 554.79, "total_tokens": 24952448} {"current_steps": 15280, "total_steps": 40000, "loss": 0.1022, "lr": 3.4058714257027755e-05, "epoch": 0.6917313655809321, "percentage": 38.2, "elapsed_time": "12:29:39", "remaining_time": "20:12:47", "throughput": 554.93, "total_tokens": 24960384} {"current_steps": 15285, "total_steps": 40000, "loss": 0.1332, "lr": 3.404956325139594e-05, "epoch": 0.6919577174675751, "percentage": 38.21, "elapsed_time": "12:29:42", "remaining_time": "20:12:13", "throughput": 555.06, "total_tokens": 24968096} {"current_steps": 15290, "total_steps": 40000, "loss": 0.1534, "lr": 3.404041085020775e-05, "epoch": 0.6921840693542181, "percentage": 38.22, "elapsed_time": "12:29:45", "remaining_time": "20:11:41", "throughput": 555.23, "total_tokens": 24977472} {"current_steps": 15295, "total_steps": 40000, "loss": 0.1507, "lr": 3.403125705487459e-05, "epoch": 0.692410421240861, "percentage": 38.24, "elapsed_time": "12:29:49", "remaining_time": "20:11:07", "throughput": 555.37, "total_tokens": 24985664} {"current_steps": 15300, "total_steps": 40000, "loss": 0.1619, "lr": 3.402210186680811e-05, "epoch": 0.692636773127504, "percentage": 38.25, "elapsed_time": "12:29:52", "remaining_time": "20:10:34", "throughput": 555.52, "total_tokens": 24994112} {"current_steps": 15305, "total_steps": 40000, "loss": 0.1075, "lr": 3.4012945287420137e-05, "epoch": 0.692863125014147, "percentage": 38.26, "elapsed_time": "12:29:55", "remaining_time": "20:10:01", "throughput": 555.65, "total_tokens": 25001632} {"current_steps": 15310, "total_steps": 40000, "loss": 0.1831, "lr": 3.400378731812274e-05, "epoch": 0.6930894769007899, "percentage": 38.27, "elapsed_time": "12:29:58", "remaining_time": "20:09:27", "throughput": 555.8, "total_tokens": 25010144} {"current_steps": 15315, "total_steps": 40000, "loss": 0.1489, "lr": 3.399462796032817e-05, "epoch": 0.6933158287874329, "percentage": 38.29, "elapsed_time": "12:30:01", "remaining_time": "20:08:54", "throughput": 555.93, "total_tokens": 25017824} {"current_steps": 15320, "total_steps": 40000, "loss": 0.135, "lr": 3.3985467215448954e-05, "epoch": 0.6935421806740759, "percentage": 38.3, "elapsed_time": "12:30:04", "remaining_time": "20:08:21", "throughput": 556.07, "total_tokens": 25025696} {"current_steps": 15325, "total_steps": 40000, "loss": 0.1618, "lr": 3.3976305084897776e-05, "epoch": 0.6937685325607189, "percentage": 38.31, "elapsed_time": "12:30:07", "remaining_time": "20:07:47", "throughput": 556.21, "total_tokens": 25033920} {"current_steps": 15330, "total_steps": 40000, "loss": 0.0774, "lr": 3.3967141570087544e-05, "epoch": 0.6939948844473619, "percentage": 38.32, "elapsed_time": "12:30:11", "remaining_time": "20:07:14", "throughput": 556.35, "total_tokens": 25041856} {"current_steps": 15335, "total_steps": 40000, "loss": 0.1195, "lr": 3.39579766724314e-05, "epoch": 0.6942212363340049, "percentage": 38.34, "elapsed_time": "12:30:14", "remaining_time": "20:06:41", "throughput": 556.49, "total_tokens": 25049952} {"current_steps": 15340, "total_steps": 40000, "loss": 0.1556, "lr": 3.3948810393342677e-05, "epoch": 0.6944475882206478, "percentage": 38.35, "elapsed_time": "12:30:17", "remaining_time": "20:06:08", "throughput": 556.64, "total_tokens": 25058432} {"current_steps": 15345, "total_steps": 40000, "loss": 0.1232, "lr": 3.3939642734234936e-05, "epoch": 0.6946739401072908, "percentage": 38.36, "elapsed_time": "12:30:20", "remaining_time": "20:05:35", "throughput": 556.79, "total_tokens": 25067264} {"current_steps": 15350, "total_steps": 40000, "loss": 0.1319, "lr": 3.393047369652194e-05, "epoch": 0.6949002919939338, "percentage": 38.38, "elapsed_time": "12:30:23", "remaining_time": "20:05:02", "throughput": 556.93, "total_tokens": 25075040} {"current_steps": 15355, "total_steps": 40000, "loss": 0.0905, "lr": 3.3921303281617664e-05, "epoch": 0.6951266438805768, "percentage": 38.39, "elapsed_time": "12:30:27", "remaining_time": "20:04:29", "throughput": 557.08, "total_tokens": 25083456} {"current_steps": 15360, "total_steps": 40000, "loss": 0.101, "lr": 3.391213149093632e-05, "epoch": 0.6953529957672198, "percentage": 38.4, "elapsed_time": "12:30:30", "remaining_time": "20:03:56", "throughput": 557.22, "total_tokens": 25091904} {"current_steps": 15365, "total_steps": 40000, "loss": 0.1214, "lr": 3.3902958325892303e-05, "epoch": 0.6955793476538626, "percentage": 38.41, "elapsed_time": "12:30:33", "remaining_time": "20:03:22", "throughput": 557.36, "total_tokens": 25100064} {"current_steps": 15370, "total_steps": 40000, "loss": 0.1657, "lr": 3.389378378790023e-05, "epoch": 0.6958056995405056, "percentage": 38.42, "elapsed_time": "12:30:36", "remaining_time": "20:02:49", "throughput": 557.51, "total_tokens": 25108384} {"current_steps": 15375, "total_steps": 40000, "loss": 0.1877, "lr": 3.388460787837493e-05, "epoch": 0.6960320514271486, "percentage": 38.44, "elapsed_time": "12:30:39", "remaining_time": "20:02:16", "throughput": 557.65, "total_tokens": 25116352} {"current_steps": 15380, "total_steps": 40000, "loss": 0.1359, "lr": 3.387543059873145e-05, "epoch": 0.6962584033137916, "percentage": 38.45, "elapsed_time": "12:30:42", "remaining_time": "20:01:43", "throughput": 557.79, "total_tokens": 25124640} {"current_steps": 15385, "total_steps": 40000, "loss": 0.1123, "lr": 3.386625195038503e-05, "epoch": 0.6964847552004346, "percentage": 38.46, "elapsed_time": "12:30:46", "remaining_time": "20:01:10", "throughput": 557.94, "total_tokens": 25133184} {"current_steps": 15390, "total_steps": 40000, "loss": 0.1142, "lr": 3.3857071934751136e-05, "epoch": 0.6967111070870776, "percentage": 38.48, "elapsed_time": "12:30:49", "remaining_time": "20:00:38", "throughput": 558.09, "total_tokens": 25141472} {"current_steps": 15395, "total_steps": 40000, "loss": 0.1669, "lr": 3.384789055324544e-05, "epoch": 0.6969374589737205, "percentage": 38.49, "elapsed_time": "12:30:52", "remaining_time": "20:00:05", "throughput": 558.23, "total_tokens": 25149696} {"current_steps": 15400, "total_steps": 40000, "loss": 0.0863, "lr": 3.3838707807283843e-05, "epoch": 0.6971638108603635, "percentage": 38.5, "elapsed_time": "12:30:55", "remaining_time": "19:59:32", "throughput": 558.36, "total_tokens": 25157504} {"current_steps": 15400, "total_steps": 40000, "eval_loss": 0.13148054480552673, "epoch": 0.6971638108603635, "percentage": 38.5, "elapsed_time": "12:38:38", "remaining_time": "20:11:51", "throughput": 552.69, "total_tokens": 25157504} {"current_steps": 15405, "total_steps": 40000, "loss": 0.1279, "lr": 3.382952369828243e-05, "epoch": 0.6973901627470065, "percentage": 38.51, "elapsed_time": "12:38:43", "remaining_time": "20:11:21", "throughput": 552.8, "total_tokens": 25165440} {"current_steps": 15410, "total_steps": 40000, "loss": 0.132, "lr": 3.38203382276575e-05, "epoch": 0.6976165146336495, "percentage": 38.52, "elapsed_time": "12:38:46", "remaining_time": "20:10:47", "throughput": 552.95, "total_tokens": 25173824} {"current_steps": 15415, "total_steps": 40000, "loss": 0.1176, "lr": 3.381115139682557e-05, "epoch": 0.6978428665202925, "percentage": 38.54, "elapsed_time": "12:38:50", "remaining_time": "20:10:14", "throughput": 553.08, "total_tokens": 25181952} {"current_steps": 15420, "total_steps": 40000, "loss": 0.1149, "lr": 3.3801963207203366e-05, "epoch": 0.6980692184069355, "percentage": 38.55, "elapsed_time": "12:38:53", "remaining_time": "20:09:41", "throughput": 553.23, "total_tokens": 25190304} {"current_steps": 15425, "total_steps": 40000, "loss": 0.1992, "lr": 3.379277366020782e-05, "epoch": 0.6982955702935784, "percentage": 38.56, "elapsed_time": "12:38:56", "remaining_time": "20:09:08", "throughput": 553.38, "total_tokens": 25198752} {"current_steps": 15430, "total_steps": 40000, "loss": 0.1439, "lr": 3.3783582757256085e-05, "epoch": 0.6985219221802214, "percentage": 38.57, "elapsed_time": "12:38:59", "remaining_time": "20:08:35", "throughput": 553.51, "total_tokens": 25206752} {"current_steps": 15435, "total_steps": 40000, "loss": 0.1264, "lr": 3.3774390499765504e-05, "epoch": 0.6987482740668643, "percentage": 38.59, "elapsed_time": "12:39:02", "remaining_time": "20:08:01", "throughput": 553.65, "total_tokens": 25214592} {"current_steps": 15440, "total_steps": 40000, "loss": 0.1446, "lr": 3.376519688915364e-05, "epoch": 0.6989746259535073, "percentage": 38.6, "elapsed_time": "12:39:06", "remaining_time": "20:07:28", "throughput": 553.79, "total_tokens": 25223104} {"current_steps": 15445, "total_steps": 40000, "loss": 0.1452, "lr": 3.3756001926838273e-05, "epoch": 0.6992009778401503, "percentage": 38.61, "elapsed_time": "12:39:09", "remaining_time": "20:06:55", "throughput": 553.93, "total_tokens": 25231104} {"current_steps": 15450, "total_steps": 40000, "loss": 0.1208, "lr": 3.374680561423737e-05, "epoch": 0.6994273297267932, "percentage": 38.62, "elapsed_time": "12:39:12", "remaining_time": "20:06:22", "throughput": 554.08, "total_tokens": 25239552} {"current_steps": 15455, "total_steps": 40000, "loss": 0.1419, "lr": 3.373760795276912e-05, "epoch": 0.6996536816134362, "percentage": 38.64, "elapsed_time": "12:39:15", "remaining_time": "20:05:49", "throughput": 554.22, "total_tokens": 25247648} {"current_steps": 15460, "total_steps": 40000, "loss": 0.1111, "lr": 3.372840894385192e-05, "epoch": 0.6998800335000792, "percentage": 38.65, "elapsed_time": "12:39:18", "remaining_time": "20:05:16", "throughput": 554.35, "total_tokens": 25255392} {"current_steps": 15465, "total_steps": 40000, "loss": 0.1712, "lr": 3.3719208588904375e-05, "epoch": 0.7001063853867222, "percentage": 38.66, "elapsed_time": "12:39:21", "remaining_time": "20:04:43", "throughput": 554.48, "total_tokens": 25263232} {"current_steps": 15470, "total_steps": 40000, "loss": 0.0887, "lr": 3.371000688934529e-05, "epoch": 0.7003327372733652, "percentage": 38.67, "elapsed_time": "12:39:24", "remaining_time": "20:04:10", "throughput": 554.62, "total_tokens": 25271456} {"current_steps": 15475, "total_steps": 40000, "loss": 0.0911, "lr": 3.370080384659369e-05, "epoch": 0.7005590891600082, "percentage": 38.69, "elapsed_time": "12:39:28", "remaining_time": "20:03:37", "throughput": 554.77, "total_tokens": 25279744} {"current_steps": 15480, "total_steps": 40000, "loss": 0.1405, "lr": 3.36915994620688e-05, "epoch": 0.7007854410466511, "percentage": 38.7, "elapsed_time": "12:39:31", "remaining_time": "20:03:04", "throughput": 554.9, "total_tokens": 25287488} {"current_steps": 15485, "total_steps": 40000, "loss": 0.1303, "lr": 3.3682393737190035e-05, "epoch": 0.7010117929332941, "percentage": 38.71, "elapsed_time": "12:39:34", "remaining_time": "20:02:31", "throughput": 555.05, "total_tokens": 25296064} {"current_steps": 15490, "total_steps": 40000, "loss": 0.1226, "lr": 3.3673186673377054e-05, "epoch": 0.7012381448199371, "percentage": 38.73, "elapsed_time": "12:39:37", "remaining_time": "20:01:58", "throughput": 555.19, "total_tokens": 25304096} {"current_steps": 15495, "total_steps": 40000, "loss": 0.1073, "lr": 3.366397827204969e-05, "epoch": 0.7014644967065801, "percentage": 38.74, "elapsed_time": "12:39:40", "remaining_time": "20:01:25", "throughput": 555.32, "total_tokens": 25312032} {"current_steps": 15500, "total_steps": 40000, "loss": 0.1513, "lr": 3.3654768534628e-05, "epoch": 0.7016908485932231, "percentage": 38.75, "elapsed_time": "12:39:44", "remaining_time": "20:00:52", "throughput": 555.47, "total_tokens": 25320512} {"current_steps": 15505, "total_steps": 40000, "loss": 0.1302, "lr": 3.3645557462532245e-05, "epoch": 0.701917200479866, "percentage": 38.76, "elapsed_time": "12:39:47", "remaining_time": "20:00:19", "throughput": 555.61, "total_tokens": 25328576} {"current_steps": 15510, "total_steps": 40000, "loss": 0.1555, "lr": 3.363634505718288e-05, "epoch": 0.7021435523665089, "percentage": 38.77, "elapsed_time": "12:39:50", "remaining_time": "19:59:46", "throughput": 555.74, "total_tokens": 25336192} {"current_steps": 15515, "total_steps": 40000, "loss": 0.1476, "lr": 3.362713132000057e-05, "epoch": 0.7023699042531519, "percentage": 38.79, "elapsed_time": "12:39:53", "remaining_time": "19:59:13", "throughput": 555.87, "total_tokens": 25343968} {"current_steps": 15520, "total_steps": 40000, "loss": 0.1436, "lr": 3.36179162524062e-05, "epoch": 0.7025962561397949, "percentage": 38.8, "elapsed_time": "12:39:56", "remaining_time": "19:58:40", "throughput": 556.0, "total_tokens": 25351776} {"current_steps": 15525, "total_steps": 40000, "loss": 0.1463, "lr": 3.3608699855820846e-05, "epoch": 0.7028226080264379, "percentage": 38.81, "elapsed_time": "12:39:59", "remaining_time": "19:58:07", "throughput": 556.15, "total_tokens": 25360192} {"current_steps": 15530, "total_steps": 40000, "loss": 0.097, "lr": 3.359948213166578e-05, "epoch": 0.7030489599130809, "percentage": 38.82, "elapsed_time": "12:40:03", "remaining_time": "19:57:34", "throughput": 556.29, "total_tokens": 25368736} {"current_steps": 15535, "total_steps": 40000, "loss": 0.1404, "lr": 3.359026308136252e-05, "epoch": 0.7032753117997238, "percentage": 38.84, "elapsed_time": "12:40:06", "remaining_time": "19:57:02", "throughput": 556.43, "total_tokens": 25376544} {"current_steps": 15540, "total_steps": 40000, "loss": 0.1111, "lr": 3.358104270633272e-05, "epoch": 0.7035016636863668, "percentage": 38.85, "elapsed_time": "12:40:09", "remaining_time": "19:56:29", "throughput": 556.56, "total_tokens": 25384416} {"current_steps": 15545, "total_steps": 40000, "loss": 0.0992, "lr": 3.357182100799831e-05, "epoch": 0.7037280155730098, "percentage": 38.86, "elapsed_time": "12:40:12", "remaining_time": "19:55:56", "throughput": 556.72, "total_tokens": 25393344} {"current_steps": 15550, "total_steps": 40000, "loss": 0.0931, "lr": 3.3562597987781384e-05, "epoch": 0.7039543674596528, "percentage": 38.88, "elapsed_time": "12:40:15", "remaining_time": "19:55:23", "throughput": 556.86, "total_tokens": 25401760} {"current_steps": 15555, "total_steps": 40000, "loss": 0.1152, "lr": 3.355337364710424e-05, "epoch": 0.7041807193462958, "percentage": 38.89, "elapsed_time": "12:40:19", "remaining_time": "19:54:51", "throughput": 557.01, "total_tokens": 25410208} {"current_steps": 15560, "total_steps": 40000, "loss": 0.1225, "lr": 3.354414798738939e-05, "epoch": 0.7044070712329388, "percentage": 38.9, "elapsed_time": "12:40:22", "remaining_time": "19:54:18", "throughput": 557.14, "total_tokens": 25417888} {"current_steps": 15565, "total_steps": 40000, "loss": 0.1231, "lr": 3.353492101005955e-05, "epoch": 0.7046334231195817, "percentage": 38.91, "elapsed_time": "12:40:25", "remaining_time": "19:53:45", "throughput": 557.28, "total_tokens": 25425984} {"current_steps": 15570, "total_steps": 40000, "loss": 0.0882, "lr": 3.352569271653763e-05, "epoch": 0.7048597750062247, "percentage": 38.92, "elapsed_time": "12:40:28", "remaining_time": "19:53:13", "throughput": 557.44, "total_tokens": 25435296} {"current_steps": 15575, "total_steps": 40000, "loss": 0.1121, "lr": 3.351646310824675e-05, "epoch": 0.7050861268928676, "percentage": 38.94, "elapsed_time": "12:40:31", "remaining_time": "19:52:40", "throughput": 557.57, "total_tokens": 25442816} {"current_steps": 15580, "total_steps": 40000, "loss": 0.1629, "lr": 3.350723218661023e-05, "epoch": 0.7053124787795106, "percentage": 38.95, "elapsed_time": "12:40:34", "remaining_time": "19:52:07", "throughput": 557.7, "total_tokens": 25450688} {"current_steps": 15585, "total_steps": 40000, "loss": 0.133, "lr": 3.349799995305162e-05, "epoch": 0.7055388306661536, "percentage": 38.96, "elapsed_time": "12:40:38", "remaining_time": "19:51:35", "throughput": 557.85, "total_tokens": 25459072} {"current_steps": 15590, "total_steps": 40000, "loss": 0.1151, "lr": 3.348876640899461e-05, "epoch": 0.7057651825527966, "percentage": 38.98, "elapsed_time": "12:40:41", "remaining_time": "19:51:02", "throughput": 557.99, "total_tokens": 25467328} {"current_steps": 15595, "total_steps": 40000, "loss": 0.1041, "lr": 3.3479531555863144e-05, "epoch": 0.7059915344394395, "percentage": 38.99, "elapsed_time": "12:40:44", "remaining_time": "19:50:30", "throughput": 558.12, "total_tokens": 25475232} {"current_steps": 15600, "total_steps": 40000, "loss": 0.14, "lr": 3.3470295395081344e-05, "epoch": 0.7062178863260825, "percentage": 39.0, "elapsed_time": "12:40:47", "remaining_time": "19:49:57", "throughput": 558.26, "total_tokens": 25483232} {"current_steps": 15600, "total_steps": 40000, "eval_loss": 0.12968161702156067, "epoch": 0.7062178863260825, "percentage": 39.0, "elapsed_time": "12:48:30", "remaining_time": "20:02:01", "throughput": 552.66, "total_tokens": 25483232} {"current_steps": 15605, "total_steps": 40000, "loss": 0.1287, "lr": 3.3461057928073556e-05, "epoch": 0.7064442382127255, "percentage": 39.01, "elapsed_time": "12:48:34", "remaining_time": "20:01:29", "throughput": 552.77, "total_tokens": 25490784} {"current_steps": 15610, "total_steps": 40000, "loss": 0.1188, "lr": 3.345181915626431e-05, "epoch": 0.7066705900993685, "percentage": 39.02, "elapsed_time": "12:48:37", "remaining_time": "20:00:56", "throughput": 552.91, "total_tokens": 25498688} {"current_steps": 15615, "total_steps": 40000, "loss": 0.1479, "lr": 3.344257908107834e-05, "epoch": 0.7068969419860115, "percentage": 39.04, "elapsed_time": "12:48:40", "remaining_time": "20:00:23", "throughput": 553.05, "total_tokens": 25506784} {"current_steps": 15620, "total_steps": 40000, "loss": 0.1298, "lr": 3.343333770394058e-05, "epoch": 0.7071232938726544, "percentage": 39.05, "elapsed_time": "12:48:44", "remaining_time": "19:59:51", "throughput": 553.21, "total_tokens": 25516160} {"current_steps": 15625, "total_steps": 40000, "loss": 0.099, "lr": 3.342409502627616e-05, "epoch": 0.7073496457592974, "percentage": 39.06, "elapsed_time": "12:48:47", "remaining_time": "19:59:18", "throughput": 553.34, "total_tokens": 25523840} {"current_steps": 15630, "total_steps": 40000, "loss": 0.133, "lr": 3.341485104951043e-05, "epoch": 0.7075759976459404, "percentage": 39.07, "elapsed_time": "12:48:50", "remaining_time": "19:58:45", "throughput": 553.47, "total_tokens": 25531776} {"current_steps": 15635, "total_steps": 40000, "loss": 0.1129, "lr": 3.340560577506892e-05, "epoch": 0.7078023495325834, "percentage": 39.09, "elapsed_time": "12:48:53", "remaining_time": "19:58:12", "throughput": 553.6, "total_tokens": 25539360} {"current_steps": 15640, "total_steps": 40000, "loss": 0.1298, "lr": 3.339635920437735e-05, "epoch": 0.7080287014192264, "percentage": 39.1, "elapsed_time": "12:48:56", "remaining_time": "19:57:39", "throughput": 553.74, "total_tokens": 25547584} {"current_steps": 15645, "total_steps": 40000, "loss": 0.1113, "lr": 3.338711133886169e-05, "epoch": 0.7082550533058694, "percentage": 39.11, "elapsed_time": "12:48:59", "remaining_time": "19:57:07", "throughput": 553.87, "total_tokens": 25555328} {"current_steps": 15650, "total_steps": 40000, "loss": 0.1242, "lr": 3.3377862179948064e-05, "epoch": 0.7084814051925122, "percentage": 39.12, "elapsed_time": "12:49:02", "remaining_time": "19:56:34", "throughput": 554.0, "total_tokens": 25563360} {"current_steps": 15655, "total_steps": 40000, "loss": 0.0832, "lr": 3.336861172906281e-05, "epoch": 0.7087077570791552, "percentage": 39.14, "elapsed_time": "12:49:06", "remaining_time": "19:56:01", "throughput": 554.14, "total_tokens": 25571136} {"current_steps": 15660, "total_steps": 40000, "loss": 0.1611, "lr": 3.335935998763245e-05, "epoch": 0.7089341089657982, "percentage": 39.15, "elapsed_time": "12:49:09", "remaining_time": "19:55:28", "throughput": 554.28, "total_tokens": 25579776} {"current_steps": 15665, "total_steps": 40000, "loss": 0.1468, "lr": 3.3350106957083744e-05, "epoch": 0.7091604608524412, "percentage": 39.16, "elapsed_time": "12:49:12", "remaining_time": "19:54:56", "throughput": 554.42, "total_tokens": 25588000} {"current_steps": 15670, "total_steps": 40000, "loss": 0.1424, "lr": 3.33408526388436e-05, "epoch": 0.7093868127390842, "percentage": 39.17, "elapsed_time": "12:49:15", "remaining_time": "19:54:23", "throughput": 554.58, "total_tokens": 25596992} {"current_steps": 15675, "total_steps": 40000, "loss": 0.1198, "lr": 3.3331597034339166e-05, "epoch": 0.7096131646257272, "percentage": 39.19, "elapsed_time": "12:49:18", "remaining_time": "19:53:51", "throughput": 554.72, "total_tokens": 25605088} {"current_steps": 15680, "total_steps": 40000, "loss": 0.1439, "lr": 3.3322340144997764e-05, "epoch": 0.7098395165123701, "percentage": 39.2, "elapsed_time": "12:49:22", "remaining_time": "19:53:18", "throughput": 554.86, "total_tokens": 25613440} {"current_steps": 15685, "total_steps": 40000, "loss": 0.0927, "lr": 3.331308197224693e-05, "epoch": 0.7100658683990131, "percentage": 39.21, "elapsed_time": "12:49:25", "remaining_time": "19:52:46", "throughput": 555.01, "total_tokens": 25622208} {"current_steps": 15690, "total_steps": 40000, "loss": 0.1391, "lr": 3.330382251751438e-05, "epoch": 0.7102922202856561, "percentage": 39.23, "elapsed_time": "12:49:28", "remaining_time": "19:52:13", "throughput": 555.14, "total_tokens": 25629856} {"current_steps": 15695, "total_steps": 40000, "loss": 0.1096, "lr": 3.3294561782228054e-05, "epoch": 0.7105185721722991, "percentage": 39.24, "elapsed_time": "12:49:31", "remaining_time": "19:51:40", "throughput": 555.26, "total_tokens": 25637472} {"current_steps": 15700, "total_steps": 40000, "loss": 0.2066, "lr": 3.328529976781607e-05, "epoch": 0.7107449240589421, "percentage": 39.25, "elapsed_time": "12:49:34", "remaining_time": "19:51:08", "throughput": 555.41, "total_tokens": 25646016} {"current_steps": 15705, "total_steps": 40000, "loss": 0.1663, "lr": 3.327603647570673e-05, "epoch": 0.710971275945585, "percentage": 39.26, "elapsed_time": "12:49:38", "remaining_time": "19:50:35", "throughput": 555.55, "total_tokens": 25654496} {"current_steps": 15710, "total_steps": 40000, "loss": 0.1192, "lr": 3.326677190732857e-05, "epoch": 0.711197627832228, "percentage": 39.27, "elapsed_time": "12:49:41", "remaining_time": "19:50:03", "throughput": 555.7, "total_tokens": 25662944} {"current_steps": 15715, "total_steps": 40000, "loss": 0.1369, "lr": 3.325750606411029e-05, "epoch": 0.711423979718871, "percentage": 39.29, "elapsed_time": "12:49:44", "remaining_time": "19:49:30", "throughput": 555.83, "total_tokens": 25670944} {"current_steps": 15720, "total_steps": 40000, "loss": 0.1192, "lr": 3.3248238947480804e-05, "epoch": 0.7116503316055139, "percentage": 39.3, "elapsed_time": "12:49:47", "remaining_time": "19:48:58", "throughput": 555.96, "total_tokens": 25678336} {"current_steps": 15725, "total_steps": 40000, "loss": 0.1324, "lr": 3.323897055886922e-05, "epoch": 0.7118766834921569, "percentage": 39.31, "elapsed_time": "12:49:50", "remaining_time": "19:48:25", "throughput": 556.08, "total_tokens": 25685920} {"current_steps": 15730, "total_steps": 40000, "loss": 0.1408, "lr": 3.322970089970484e-05, "epoch": 0.7121030353787999, "percentage": 39.32, "elapsed_time": "12:49:53", "remaining_time": "19:47:53", "throughput": 556.22, "total_tokens": 25694016} {"current_steps": 15735, "total_steps": 40000, "loss": 0.1443, "lr": 3.3220429971417165e-05, "epoch": 0.7123293872654428, "percentage": 39.34, "elapsed_time": "12:49:57", "remaining_time": "19:47:20", "throughput": 556.36, "total_tokens": 25702016} {"current_steps": 15740, "total_steps": 40000, "loss": 0.156, "lr": 3.321115777543588e-05, "epoch": 0.7125557391520858, "percentage": 39.35, "elapsed_time": "12:50:00", "remaining_time": "19:46:48", "throughput": 556.51, "total_tokens": 25711232} {"current_steps": 15745, "total_steps": 40000, "loss": 0.1324, "lr": 3.320188431319088e-05, "epoch": 0.7127820910387288, "percentage": 39.36, "elapsed_time": "12:50:03", "remaining_time": "19:46:16", "throughput": 556.65, "total_tokens": 25719136} {"current_steps": 15750, "total_steps": 40000, "loss": 0.1141, "lr": 3.319260958611224e-05, "epoch": 0.7130084429253718, "percentage": 39.38, "elapsed_time": "12:50:06", "remaining_time": "19:45:43", "throughput": 556.78, "total_tokens": 25727040} {"current_steps": 15755, "total_steps": 40000, "loss": 0.0887, "lr": 3.3183333595630256e-05, "epoch": 0.7132347948120148, "percentage": 39.39, "elapsed_time": "12:50:09", "remaining_time": "19:45:11", "throughput": 556.91, "total_tokens": 25734656} {"current_steps": 15760, "total_steps": 40000, "loss": 0.1112, "lr": 3.317405634317538e-05, "epoch": 0.7134611466986578, "percentage": 39.4, "elapsed_time": "12:50:12", "remaining_time": "19:44:38", "throughput": 557.05, "total_tokens": 25742944} {"current_steps": 15765, "total_steps": 40000, "loss": 0.1185, "lr": 3.3164777830178315e-05, "epoch": 0.7136874985853007, "percentage": 39.41, "elapsed_time": "12:50:16", "remaining_time": "19:44:06", "throughput": 557.19, "total_tokens": 25751392} {"current_steps": 15770, "total_steps": 40000, "loss": 0.1173, "lr": 3.315549805806989e-05, "epoch": 0.7139138504719437, "percentage": 39.42, "elapsed_time": "12:50:19", "remaining_time": "19:43:34", "throughput": 557.34, "total_tokens": 25760064} {"current_steps": 15775, "total_steps": 40000, "loss": 0.1418, "lr": 3.314621702828118e-05, "epoch": 0.7141402023585867, "percentage": 39.44, "elapsed_time": "12:50:22", "remaining_time": "19:43:02", "throughput": 557.48, "total_tokens": 25768096} {"current_steps": 15780, "total_steps": 40000, "loss": 0.1045, "lr": 3.313693474224342e-05, "epoch": 0.7143665542452297, "percentage": 39.45, "elapsed_time": "12:50:25", "remaining_time": "19:42:29", "throughput": 557.62, "total_tokens": 25776256} {"current_steps": 15785, "total_steps": 40000, "loss": 0.073, "lr": 3.312765120138809e-05, "epoch": 0.7145929061318727, "percentage": 39.46, "elapsed_time": "12:50:28", "remaining_time": "19:41:57", "throughput": 557.74, "total_tokens": 25783712} {"current_steps": 15790, "total_steps": 40000, "loss": 0.0963, "lr": 3.311836640714679e-05, "epoch": 0.7148192580185155, "percentage": 39.48, "elapsed_time": "12:50:31", "remaining_time": "19:41:25", "throughput": 557.88, "total_tokens": 25791744} {"current_steps": 15795, "total_steps": 40000, "loss": 0.1163, "lr": 3.310908036095137e-05, "epoch": 0.7150456099051585, "percentage": 39.49, "elapsed_time": "12:50:35", "remaining_time": "19:40:53", "throughput": 558.03, "total_tokens": 25800416} {"current_steps": 15800, "total_steps": 40000, "loss": 0.0902, "lr": 3.309979306423386e-05, "epoch": 0.7152719617918015, "percentage": 39.5, "elapsed_time": "12:50:38", "remaining_time": "19:40:20", "throughput": 558.16, "total_tokens": 25808352} {"current_steps": 15800, "total_steps": 40000, "eval_loss": 0.13028807938098907, "epoch": 0.7152719617918015, "percentage": 39.5, "elapsed_time": "12:58:21", "remaining_time": "19:52:09", "throughput": 552.63, "total_tokens": 25808352} {"current_steps": 15805, "total_steps": 40000, "loss": 0.1126, "lr": 3.309050451842647e-05, "epoch": 0.7154983136784445, "percentage": 39.51, "elapsed_time": "12:58:25", "remaining_time": "19:51:38", "throughput": 552.77, "total_tokens": 25817344} {"current_steps": 15810, "total_steps": 40000, "loss": 0.1295, "lr": 3.3081214724961604e-05, "epoch": 0.7157246655650875, "percentage": 39.52, "elapsed_time": "12:58:28", "remaining_time": "19:51:05", "throughput": 552.9, "total_tokens": 25825056} {"current_steps": 15815, "total_steps": 40000, "loss": 0.1288, "lr": 3.307192368527188e-05, "epoch": 0.7159510174517305, "percentage": 39.54, "elapsed_time": "12:58:31", "remaining_time": "19:50:33", "throughput": 553.04, "total_tokens": 25833376} {"current_steps": 15820, "total_steps": 40000, "loss": 0.1434, "lr": 3.306263140079008e-05, "epoch": 0.7161773693383734, "percentage": 39.55, "elapsed_time": "12:58:34", "remaining_time": "19:50:00", "throughput": 553.18, "total_tokens": 25841824} {"current_steps": 15825, "total_steps": 40000, "loss": 0.1439, "lr": 3.30533378729492e-05, "epoch": 0.7164037212250164, "percentage": 39.56, "elapsed_time": "12:58:37", "remaining_time": "19:49:28", "throughput": 553.32, "total_tokens": 25849920} {"current_steps": 15830, "total_steps": 40000, "loss": 0.1002, "lr": 3.304404310318242e-05, "epoch": 0.7166300731116594, "percentage": 39.57, "elapsed_time": "12:58:41", "remaining_time": "19:48:56", "throughput": 553.45, "total_tokens": 25857856} {"current_steps": 15835, "total_steps": 40000, "loss": 0.1361, "lr": 3.3034747092923105e-05, "epoch": 0.7168564249983024, "percentage": 39.59, "elapsed_time": "12:58:44", "remaining_time": "19:48:23", "throughput": 553.59, "total_tokens": 25865856} {"current_steps": 15840, "total_steps": 40000, "loss": 0.1308, "lr": 3.3025449843604806e-05, "epoch": 0.7170827768849454, "percentage": 39.6, "elapsed_time": "12:58:47", "remaining_time": "19:47:51", "throughput": 553.73, "total_tokens": 25874176} {"current_steps": 15845, "total_steps": 40000, "loss": 0.0973, "lr": 3.30161513566613e-05, "epoch": 0.7173091287715883, "percentage": 39.61, "elapsed_time": "12:58:50", "remaining_time": "19:47:18", "throughput": 553.86, "total_tokens": 25882400} {"current_steps": 15850, "total_steps": 40000, "loss": 0.1094, "lr": 3.3006851633526506e-05, "epoch": 0.7175354806582313, "percentage": 39.62, "elapsed_time": "12:58:53", "remaining_time": "19:46:46", "throughput": 554.0, "total_tokens": 25890432} {"current_steps": 15855, "total_steps": 40000, "loss": 0.1075, "lr": 3.2997550675634584e-05, "epoch": 0.7177618325448742, "percentage": 39.64, "elapsed_time": "12:58:57", "remaining_time": "19:46:14", "throughput": 554.14, "total_tokens": 25899072} {"current_steps": 15860, "total_steps": 40000, "loss": 0.1386, "lr": 3.2988248484419825e-05, "epoch": 0.7179881844315172, "percentage": 39.65, "elapsed_time": "12:59:00", "remaining_time": "19:45:41", "throughput": 554.26, "total_tokens": 25906368} {"current_steps": 15865, "total_steps": 40000, "loss": 0.1274, "lr": 3.2978945061316776e-05, "epoch": 0.7182145363181602, "percentage": 39.66, "elapsed_time": "12:59:03", "remaining_time": "19:45:09", "throughput": 554.4, "total_tokens": 25914464} {"current_steps": 15870, "total_steps": 40000, "loss": 0.1585, "lr": 3.296964040776013e-05, "epoch": 0.7184408882048032, "percentage": 39.67, "elapsed_time": "12:59:06", "remaining_time": "19:44:37", "throughput": 554.54, "total_tokens": 25922912} {"current_steps": 15875, "total_steps": 40000, "loss": 0.1013, "lr": 3.296033452518478e-05, "epoch": 0.7186672400914461, "percentage": 39.69, "elapsed_time": "12:59:09", "remaining_time": "19:44:04", "throughput": 554.68, "total_tokens": 25930944} {"current_steps": 15880, "total_steps": 40000, "loss": 0.1421, "lr": 3.2951027415025806e-05, "epoch": 0.7188935919780891, "percentage": 39.7, "elapsed_time": "12:59:12", "remaining_time": "19:43:32", "throughput": 554.81, "total_tokens": 25939040} {"current_steps": 15885, "total_steps": 40000, "loss": 0.1538, "lr": 3.294171907871849e-05, "epoch": 0.7191199438647321, "percentage": 39.71, "elapsed_time": "12:59:16", "remaining_time": "19:43:00", "throughput": 554.95, "total_tokens": 25947392} {"current_steps": 15890, "total_steps": 40000, "loss": 0.1134, "lr": 3.293240951769828e-05, "epoch": 0.7193462957513751, "percentage": 39.73, "elapsed_time": "12:59:19", "remaining_time": "19:42:28", "throughput": 555.09, "total_tokens": 25955520} {"current_steps": 15895, "total_steps": 40000, "loss": 0.1458, "lr": 3.2923098733400846e-05, "epoch": 0.7195726476380181, "percentage": 39.74, "elapsed_time": "12:59:22", "remaining_time": "19:41:56", "throughput": 555.23, "total_tokens": 25964192} {"current_steps": 15900, "total_steps": 40000, "loss": 0.1632, "lr": 3.291378672726202e-05, "epoch": 0.7197989995246611, "percentage": 39.75, "elapsed_time": "12:59:25", "remaining_time": "19:41:24", "throughput": 555.36, "total_tokens": 25972032} {"current_steps": 15905, "total_steps": 40000, "loss": 0.16, "lr": 3.2904473500717824e-05, "epoch": 0.720025351411304, "percentage": 39.76, "elapsed_time": "12:59:29", "remaining_time": "19:40:51", "throughput": 555.5, "total_tokens": 25980320} {"current_steps": 15910, "total_steps": 40000, "loss": 0.1634, "lr": 3.289515905520449e-05, "epoch": 0.720251703297947, "percentage": 39.77, "elapsed_time": "12:59:32", "remaining_time": "19:40:19", "throughput": 555.65, "total_tokens": 25988960} {"current_steps": 15915, "total_steps": 40000, "loss": 0.1044, "lr": 3.288584339215841e-05, "epoch": 0.72047805518459, "percentage": 39.79, "elapsed_time": "12:59:35", "remaining_time": "19:39:47", "throughput": 555.79, "total_tokens": 25997344} {"current_steps": 15920, "total_steps": 40000, "loss": 0.1088, "lr": 3.287652651301617e-05, "epoch": 0.720704407071233, "percentage": 39.8, "elapsed_time": "12:59:38", "remaining_time": "19:39:15", "throughput": 555.94, "total_tokens": 26006208} {"current_steps": 15925, "total_steps": 40000, "loss": 0.1663, "lr": 3.286720841921457e-05, "epoch": 0.720930758957876, "percentage": 39.81, "elapsed_time": "12:59:41", "remaining_time": "19:38:43", "throughput": 556.07, "total_tokens": 26014080} {"current_steps": 15930, "total_steps": 40000, "loss": 0.1355, "lr": 3.285788911219056e-05, "epoch": 0.7211571108445188, "percentage": 39.83, "elapsed_time": "12:59:45", "remaining_time": "19:38:11", "throughput": 556.22, "total_tokens": 26022816} {"current_steps": 15935, "total_steps": 40000, "loss": 0.1365, "lr": 3.284856859338131e-05, "epoch": 0.7213834627311618, "percentage": 39.84, "elapsed_time": "12:59:48", "remaining_time": "19:37:39", "throughput": 556.35, "total_tokens": 26030528} {"current_steps": 15940, "total_steps": 40000, "loss": 0.1132, "lr": 3.283924686422414e-05, "epoch": 0.7216098146178048, "percentage": 39.85, "elapsed_time": "12:59:51", "remaining_time": "19:37:07", "throughput": 556.5, "total_tokens": 26039648} {"current_steps": 15945, "total_steps": 40000, "loss": 0.1361, "lr": 3.282992392615659e-05, "epoch": 0.7218361665044478, "percentage": 39.86, "elapsed_time": "12:59:54", "remaining_time": "19:36:35", "throughput": 556.65, "total_tokens": 26048320} {"current_steps": 15950, "total_steps": 40000, "loss": 0.1352, "lr": 3.282059978061638e-05, "epoch": 0.7220625183910908, "percentage": 39.88, "elapsed_time": "12:59:58", "remaining_time": "19:36:03", "throughput": 556.78, "total_tokens": 26056160} {"current_steps": 15955, "total_steps": 40000, "loss": 0.0756, "lr": 3.28112744290414e-05, "epoch": 0.7222888702777338, "percentage": 39.89, "elapsed_time": "13:00:01", "remaining_time": "19:35:31", "throughput": 556.92, "total_tokens": 26064608} {"current_steps": 15960, "total_steps": 40000, "loss": 0.1235, "lr": 3.280194787286974e-05, "epoch": 0.7225152221643767, "percentage": 39.9, "elapsed_time": "13:00:04", "remaining_time": "19:35:00", "throughput": 557.07, "total_tokens": 26073472} {"current_steps": 15965, "total_steps": 40000, "loss": 0.1347, "lr": 3.2792620113539674e-05, "epoch": 0.7227415740510197, "percentage": 39.91, "elapsed_time": "13:00:07", "remaining_time": "19:34:28", "throughput": 557.21, "total_tokens": 26081920} {"current_steps": 15970, "total_steps": 40000, "loss": 0.129, "lr": 3.278329115248966e-05, "epoch": 0.7229679259376627, "percentage": 39.92, "elapsed_time": "13:00:10", "remaining_time": "19:33:56", "throughput": 557.35, "total_tokens": 26090016} {"current_steps": 15975, "total_steps": 40000, "loss": 0.1055, "lr": 3.277396099115834e-05, "epoch": 0.7231942778243057, "percentage": 39.94, "elapsed_time": "13:00:14", "remaining_time": "19:33:24", "throughput": 557.49, "total_tokens": 26098624} {"current_steps": 15980, "total_steps": 40000, "loss": 0.127, "lr": 3.276462963098454e-05, "epoch": 0.7234206297109487, "percentage": 39.95, "elapsed_time": "13:00:17", "remaining_time": "19:32:52", "throughput": 557.64, "total_tokens": 26107040} {"current_steps": 15985, "total_steps": 40000, "loss": 0.1257, "lr": 3.275529707340728e-05, "epoch": 0.7236469815975917, "percentage": 39.96, "elapsed_time": "13:00:20", "remaining_time": "19:32:20", "throughput": 557.78, "total_tokens": 26115840} {"current_steps": 15990, "total_steps": 40000, "loss": 0.1108, "lr": 3.274596331986574e-05, "epoch": 0.7238733334842345, "percentage": 39.98, "elapsed_time": "13:00:23", "remaining_time": "19:31:49", "throughput": 557.92, "total_tokens": 26124192} {"current_steps": 15995, "total_steps": 40000, "loss": 0.1044, "lr": 3.273662837179932e-05, "epoch": 0.7240996853708775, "percentage": 39.99, "elapsed_time": "13:00:27", "remaining_time": "19:31:17", "throughput": 558.06, "total_tokens": 26132096} {"current_steps": 16000, "total_steps": 40000, "loss": 0.1352, "lr": 3.272729223064758e-05, "epoch": 0.7243260372575205, "percentage": 40.0, "elapsed_time": "13:00:30", "remaining_time": "19:30:45", "throughput": 558.19, "total_tokens": 26140320} {"current_steps": 16000, "total_steps": 40000, "eval_loss": 0.12960092723369598, "epoch": 0.7243260372575205, "percentage": 40.0, "elapsed_time": "13:08:12", "remaining_time": "19:42:19", "throughput": 552.73, "total_tokens": 26140320} {"current_steps": 16005, "total_steps": 40000, "loss": 0.0881, "lr": 3.2717954897850264e-05, "epoch": 0.7245523891441635, "percentage": 40.01, "elapsed_time": "13:08:19", "remaining_time": "19:41:51", "throughput": 552.83, "total_tokens": 26148544} {"current_steps": 16010, "total_steps": 40000, "loss": 0.1148, "lr": 3.270861637484733e-05, "epoch": 0.7247787410308065, "percentage": 40.02, "elapsed_time": "13:08:22", "remaining_time": "19:41:19", "throughput": 552.96, "total_tokens": 26156224} {"current_steps": 16015, "total_steps": 40000, "loss": 0.1347, "lr": 3.2699276663078867e-05, "epoch": 0.7250050929174494, "percentage": 40.04, "elapsed_time": "13:08:25", "remaining_time": "19:40:47", "throughput": 553.09, "total_tokens": 26164352} {"current_steps": 16020, "total_steps": 40000, "loss": 0.1265, "lr": 3.268993576398519e-05, "epoch": 0.7252314448040924, "percentage": 40.05, "elapsed_time": "13:08:28", "remaining_time": "19:40:15", "throughput": 553.22, "total_tokens": 26172160} {"current_steps": 16025, "total_steps": 40000, "loss": 0.1158, "lr": 3.268059367900678e-05, "epoch": 0.7254577966907354, "percentage": 40.06, "elapsed_time": "13:08:31", "remaining_time": "19:39:42", "throughput": 553.35, "total_tokens": 26179648} {"current_steps": 16030, "total_steps": 40000, "loss": 0.0789, "lr": 3.26712504095843e-05, "epoch": 0.7256841485773784, "percentage": 40.08, "elapsed_time": "13:08:34", "remaining_time": "19:39:10", "throughput": 553.49, "total_tokens": 26188544} {"current_steps": 16035, "total_steps": 40000, "loss": 0.0909, "lr": 3.2661905957158615e-05, "epoch": 0.7259105004640214, "percentage": 40.09, "elapsed_time": "13:08:38", "remaining_time": "19:38:38", "throughput": 553.63, "total_tokens": 26196512} {"current_steps": 16040, "total_steps": 40000, "loss": 0.152, "lr": 3.2652560323170734e-05, "epoch": 0.7261368523506644, "percentage": 40.1, "elapsed_time": "13:08:41", "remaining_time": "19:38:06", "throughput": 553.77, "total_tokens": 26204960} {"current_steps": 16045, "total_steps": 40000, "loss": 0.1327, "lr": 3.264321350906189e-05, "epoch": 0.7263632042373073, "percentage": 40.11, "elapsed_time": "13:08:44", "remaining_time": "19:37:34", "throughput": 553.91, "total_tokens": 26213472} {"current_steps": 16050, "total_steps": 40000, "loss": 0.1033, "lr": 3.263386551627346e-05, "epoch": 0.7265895561239503, "percentage": 40.12, "elapsed_time": "13:08:47", "remaining_time": "19:37:02", "throughput": 554.04, "total_tokens": 26221440} {"current_steps": 16055, "total_steps": 40000, "loss": 0.1782, "lr": 3.2624516346247055e-05, "epoch": 0.7268159080105933, "percentage": 40.14, "elapsed_time": "13:08:50", "remaining_time": "19:36:30", "throughput": 554.19, "total_tokens": 26230240} {"current_steps": 16060, "total_steps": 40000, "loss": 0.1295, "lr": 3.2615166000424404e-05, "epoch": 0.7270422598972363, "percentage": 40.15, "elapsed_time": "13:08:54", "remaining_time": "19:35:58", "throughput": 554.33, "total_tokens": 26238528} {"current_steps": 16065, "total_steps": 40000, "loss": 0.1495, "lr": 3.260581448024745e-05, "epoch": 0.7272686117838792, "percentage": 40.16, "elapsed_time": "13:08:57", "remaining_time": "19:35:27", "throughput": 554.46, "total_tokens": 26246752} {"current_steps": 16070, "total_steps": 40000, "loss": 0.1326, "lr": 3.2596461787158335e-05, "epoch": 0.7274949636705222, "percentage": 40.17, "elapsed_time": "13:09:00", "remaining_time": "19:34:55", "throughput": 554.6, "total_tokens": 26254912} {"current_steps": 16075, "total_steps": 40000, "loss": 0.0996, "lr": 3.258710792259934e-05, "epoch": 0.7277213155571651, "percentage": 40.19, "elapsed_time": "13:09:03", "remaining_time": "19:34:23", "throughput": 554.73, "total_tokens": 26262656} {"current_steps": 16080, "total_steps": 40000, "loss": 0.101, "lr": 3.257775288801296e-05, "epoch": 0.7279476674438081, "percentage": 40.2, "elapsed_time": "13:09:06", "remaining_time": "19:33:51", "throughput": 554.87, "total_tokens": 26271136} {"current_steps": 16085, "total_steps": 40000, "loss": 0.1375, "lr": 3.256839668484186e-05, "epoch": 0.7281740193304511, "percentage": 40.21, "elapsed_time": "13:09:09", "remaining_time": "19:33:19", "throughput": 555.0, "total_tokens": 26279232} {"current_steps": 16090, "total_steps": 40000, "loss": 0.1229, "lr": 3.255903931452888e-05, "epoch": 0.7284003712170941, "percentage": 40.23, "elapsed_time": "13:09:13", "remaining_time": "19:32:47", "throughput": 555.14, "total_tokens": 26287616} {"current_steps": 16095, "total_steps": 40000, "loss": 0.1266, "lr": 3.2549680778517045e-05, "epoch": 0.7286267231037371, "percentage": 40.24, "elapsed_time": "13:09:16", "remaining_time": "19:32:15", "throughput": 555.27, "total_tokens": 26295680} {"current_steps": 16100, "total_steps": 40000, "loss": 0.1321, "lr": 3.2540321078249556e-05, "epoch": 0.72885307499038, "percentage": 40.25, "elapsed_time": "13:09:19", "remaining_time": "19:31:43", "throughput": 555.41, "total_tokens": 26303872} {"current_steps": 16105, "total_steps": 40000, "loss": 0.1682, "lr": 3.2530960215169795e-05, "epoch": 0.729079426877023, "percentage": 40.26, "elapsed_time": "13:09:22", "remaining_time": "19:31:12", "throughput": 555.55, "total_tokens": 26312416} {"current_steps": 16110, "total_steps": 40000, "loss": 0.1448, "lr": 3.2521598190721345e-05, "epoch": 0.729305778763666, "percentage": 40.27, "elapsed_time": "13:09:25", "remaining_time": "19:30:40", "throughput": 555.68, "total_tokens": 26320480} {"current_steps": 16115, "total_steps": 40000, "loss": 0.1472, "lr": 3.251223500634792e-05, "epoch": 0.729532130650309, "percentage": 40.29, "elapsed_time": "13:09:29", "remaining_time": "19:30:08", "throughput": 555.81, "total_tokens": 26328192} {"current_steps": 16120, "total_steps": 40000, "loss": 0.1297, "lr": 3.2502870663493445e-05, "epoch": 0.729758482536952, "percentage": 40.3, "elapsed_time": "13:09:32", "remaining_time": "19:29:36", "throughput": 555.94, "total_tokens": 26335872} {"current_steps": 16125, "total_steps": 40000, "loss": 0.1035, "lr": 3.249350516360203e-05, "epoch": 0.729984834423595, "percentage": 40.31, "elapsed_time": "13:09:35", "remaining_time": "19:29:04", "throughput": 556.07, "total_tokens": 26344192} {"current_steps": 16130, "total_steps": 40000, "loss": 0.1415, "lr": 3.248413850811797e-05, "epoch": 0.7302111863102378, "percentage": 40.33, "elapsed_time": "13:09:38", "remaining_time": "19:28:33", "throughput": 556.21, "total_tokens": 26352160} {"current_steps": 16135, "total_steps": 40000, "loss": 0.1792, "lr": 3.2474770698485677e-05, "epoch": 0.7304375381968808, "percentage": 40.34, "elapsed_time": "13:09:41", "remaining_time": "19:28:01", "throughput": 556.35, "total_tokens": 26360736} {"current_steps": 16140, "total_steps": 40000, "loss": 0.1173, "lr": 3.246540173614983e-05, "epoch": 0.7306638900835238, "percentage": 40.35, "elapsed_time": "13:09:44", "remaining_time": "19:27:29", "throughput": 556.49, "total_tokens": 26369120} {"current_steps": 16145, "total_steps": 40000, "loss": 0.0942, "lr": 3.2456031622555197e-05, "epoch": 0.7308902419701668, "percentage": 40.36, "elapsed_time": "13:09:48", "remaining_time": "19:26:58", "throughput": 556.62, "total_tokens": 26377152} {"current_steps": 16150, "total_steps": 40000, "loss": 0.1772, "lr": 3.2446660359146794e-05, "epoch": 0.7311165938568098, "percentage": 40.38, "elapsed_time": "13:09:51", "remaining_time": "19:26:26", "throughput": 556.75, "total_tokens": 26385312} {"current_steps": 16155, "total_steps": 40000, "loss": 0.1259, "lr": 3.2437287947369786e-05, "epoch": 0.7313429457434528, "percentage": 40.39, "elapsed_time": "13:09:54", "remaining_time": "19:25:54", "throughput": 556.89, "total_tokens": 26393472} {"current_steps": 16160, "total_steps": 40000, "loss": 0.1287, "lr": 3.2427914388669525e-05, "epoch": 0.7315692976300957, "percentage": 40.4, "elapsed_time": "13:09:57", "remaining_time": "19:25:23", "throughput": 557.02, "total_tokens": 26401152} {"current_steps": 16165, "total_steps": 40000, "loss": 0.1148, "lr": 3.241853968449151e-05, "epoch": 0.7317956495167387, "percentage": 40.41, "elapsed_time": "13:10:00", "remaining_time": "19:24:51", "throughput": 557.16, "total_tokens": 26409888} {"current_steps": 16170, "total_steps": 40000, "loss": 0.104, "lr": 3.240916383628144e-05, "epoch": 0.7320220014033817, "percentage": 40.42, "elapsed_time": "13:10:04", "remaining_time": "19:24:20", "throughput": 557.31, "total_tokens": 26418592} {"current_steps": 16175, "total_steps": 40000, "loss": 0.18, "lr": 3.239978684548521e-05, "epoch": 0.7322483532900247, "percentage": 40.44, "elapsed_time": "13:10:07", "remaining_time": "19:23:48", "throughput": 557.44, "total_tokens": 26426688} {"current_steps": 16180, "total_steps": 40000, "loss": 0.1259, "lr": 3.239040871354885e-05, "epoch": 0.7324747051766677, "percentage": 40.45, "elapsed_time": "13:10:10", "remaining_time": "19:23:17", "throughput": 557.58, "total_tokens": 26435104} {"current_steps": 16185, "total_steps": 40000, "loss": 0.0805, "lr": 3.2381029441918596e-05, "epoch": 0.7327010570633106, "percentage": 40.46, "elapsed_time": "13:10:13", "remaining_time": "19:22:45", "throughput": 557.71, "total_tokens": 26442784} {"current_steps": 16190, "total_steps": 40000, "loss": 0.1276, "lr": 3.2371649032040845e-05, "epoch": 0.7329274089499536, "percentage": 40.48, "elapsed_time": "13:10:16", "remaining_time": "19:22:14", "throughput": 557.85, "total_tokens": 26451264} {"current_steps": 16195, "total_steps": 40000, "loss": 0.1258, "lr": 3.2362267485362174e-05, "epoch": 0.7331537608365966, "percentage": 40.49, "elapsed_time": "13:10:19", "remaining_time": "19:21:42", "throughput": 557.97, "total_tokens": 26459008} {"current_steps": 16200, "total_steps": 40000, "loss": 0.1089, "lr": 3.235288480332934e-05, "epoch": 0.7333801127232396, "percentage": 40.5, "elapsed_time": "13:10:23", "remaining_time": "19:21:11", "throughput": 558.13, "total_tokens": 26468320} {"current_steps": 16200, "total_steps": 40000, "eval_loss": 0.13035468757152557, "epoch": 0.7333801127232396, "percentage": 40.5, "elapsed_time": "13:18:05", "remaining_time": "19:32:30", "throughput": 552.74, "total_tokens": 26468320} {"current_steps": 16205, "total_steps": 40000, "loss": 0.1402, "lr": 3.234350098738927e-05, "epoch": 0.7336064646098825, "percentage": 40.51, "elapsed_time": "13:18:09", "remaining_time": "19:32:00", "throughput": 552.86, "total_tokens": 26476416} {"current_steps": 16210, "total_steps": 40000, "loss": 0.124, "lr": 3.233411603898906e-05, "epoch": 0.7338328164965255, "percentage": 40.52, "elapsed_time": "13:18:12", "remaining_time": "19:31:28", "throughput": 552.99, "total_tokens": 26484320} {"current_steps": 16215, "total_steps": 40000, "loss": 0.0941, "lr": 3.232472995957599e-05, "epoch": 0.7340591683831684, "percentage": 40.54, "elapsed_time": "13:18:16", "remaining_time": "19:30:56", "throughput": 553.12, "total_tokens": 26492448} {"current_steps": 16220, "total_steps": 40000, "loss": 0.1636, "lr": 3.231534275059751e-05, "epoch": 0.7342855202698114, "percentage": 40.55, "elapsed_time": "13:18:19", "remaining_time": "19:30:24", "throughput": 553.25, "total_tokens": 26500320} {"current_steps": 16225, "total_steps": 40000, "loss": 0.0832, "lr": 3.230595441350125e-05, "epoch": 0.7345118721564544, "percentage": 40.56, "elapsed_time": "13:18:22", "remaining_time": "19:29:52", "throughput": 553.38, "total_tokens": 26508096} {"current_steps": 16230, "total_steps": 40000, "loss": 0.1186, "lr": 3.2296564949735e-05, "epoch": 0.7347382240430974, "percentage": 40.58, "elapsed_time": "13:18:25", "remaining_time": "19:29:20", "throughput": 553.5, "total_tokens": 26515456} {"current_steps": 16235, "total_steps": 40000, "loss": 0.1385, "lr": 3.228717436074675e-05, "epoch": 0.7349645759297404, "percentage": 40.59, "elapsed_time": "13:18:28", "remaining_time": "19:28:49", "throughput": 553.63, "total_tokens": 26523584} {"current_steps": 16240, "total_steps": 40000, "loss": 0.1157, "lr": 3.227778264798463e-05, "epoch": 0.7351909278163834, "percentage": 40.6, "elapsed_time": "13:18:31", "remaining_time": "19:28:17", "throughput": 553.77, "total_tokens": 26531936} {"current_steps": 16245, "total_steps": 40000, "loss": 0.1056, "lr": 3.226838981289698e-05, "epoch": 0.7354172797030263, "percentage": 40.61, "elapsed_time": "13:18:34", "remaining_time": "19:27:45", "throughput": 553.91, "total_tokens": 26540384} {"current_steps": 16250, "total_steps": 40000, "loss": 0.1401, "lr": 3.225899585693227e-05, "epoch": 0.7356436315896693, "percentage": 40.62, "elapsed_time": "13:18:38", "remaining_time": "19:27:14", "throughput": 554.04, "total_tokens": 26548544} {"current_steps": 16255, "total_steps": 40000, "loss": 0.0934, "lr": 3.224960078153918e-05, "epoch": 0.7358699834763123, "percentage": 40.64, "elapsed_time": "13:18:41", "remaining_time": "19:26:42", "throughput": 554.19, "total_tokens": 26557536} {"current_steps": 16260, "total_steps": 40000, "loss": 0.1013, "lr": 3.224020458816655e-05, "epoch": 0.7360963353629553, "percentage": 40.65, "elapsed_time": "13:18:44", "remaining_time": "19:26:11", "throughput": 554.32, "total_tokens": 26565728} {"current_steps": 16265, "total_steps": 40000, "loss": 0.2073, "lr": 3.223080727826337e-05, "epoch": 0.7363226872495983, "percentage": 40.66, "elapsed_time": "13:18:47", "remaining_time": "19:25:39", "throughput": 554.46, "total_tokens": 26573920} {"current_steps": 16270, "total_steps": 40000, "loss": 0.1134, "lr": 3.222140885327885e-05, "epoch": 0.7365490391362411, "percentage": 40.67, "elapsed_time": "13:18:50", "remaining_time": "19:25:07", "throughput": 554.6, "total_tokens": 26582368} {"current_steps": 16275, "total_steps": 40000, "loss": 0.1346, "lr": 3.221200931466234e-05, "epoch": 0.7367753910228841, "percentage": 40.69, "elapsed_time": "13:18:54", "remaining_time": "19:24:36", "throughput": 554.73, "total_tokens": 26590592} {"current_steps": 16280, "total_steps": 40000, "loss": 0.1344, "lr": 3.220260866386336e-05, "epoch": 0.7370017429095271, "percentage": 40.7, "elapsed_time": "13:18:57", "remaining_time": "19:24:04", "throughput": 554.86, "total_tokens": 26598336} {"current_steps": 16285, "total_steps": 40000, "loss": 0.0992, "lr": 3.21932069023316e-05, "epoch": 0.7372280947961701, "percentage": 40.71, "elapsed_time": "13:19:00", "remaining_time": "19:23:33", "throughput": 554.99, "total_tokens": 26606432} {"current_steps": 16290, "total_steps": 40000, "loss": 0.0737, "lr": 3.218380403151695e-05, "epoch": 0.7374544466828131, "percentage": 40.73, "elapsed_time": "13:19:03", "remaining_time": "19:23:01", "throughput": 555.13, "total_tokens": 26615072} {"current_steps": 16295, "total_steps": 40000, "loss": 0.1366, "lr": 3.217440005286943e-05, "epoch": 0.7376807985694561, "percentage": 40.74, "elapsed_time": "13:19:06", "remaining_time": "19:22:30", "throughput": 555.26, "total_tokens": 26622880} {"current_steps": 16300, "total_steps": 40000, "loss": 0.1087, "lr": 3.216499496783928e-05, "epoch": 0.737907150456099, "percentage": 40.75, "elapsed_time": "13:19:09", "remaining_time": "19:21:58", "throughput": 555.39, "total_tokens": 26631168} {"current_steps": 16305, "total_steps": 40000, "loss": 0.0925, "lr": 3.2155588777876856e-05, "epoch": 0.738133502342742, "percentage": 40.76, "elapsed_time": "13:19:13", "remaining_time": "19:21:27", "throughput": 555.53, "total_tokens": 26639264} {"current_steps": 16310, "total_steps": 40000, "loss": 0.0866, "lr": 3.214618148443273e-05, "epoch": 0.738359854229385, "percentage": 40.77, "elapsed_time": "13:19:16", "remaining_time": "19:20:55", "throughput": 555.66, "total_tokens": 26647264} {"current_steps": 16315, "total_steps": 40000, "loss": 0.1485, "lr": 3.2136773088957595e-05, "epoch": 0.738586206116028, "percentage": 40.79, "elapsed_time": "13:19:19", "remaining_time": "19:20:24", "throughput": 555.78, "total_tokens": 26654816} {"current_steps": 16320, "total_steps": 40000, "loss": 0.1275, "lr": 3.2127363592902374e-05, "epoch": 0.738812558002671, "percentage": 40.8, "elapsed_time": "13:19:22", "remaining_time": "19:19:52", "throughput": 555.92, "total_tokens": 26663392} {"current_steps": 16325, "total_steps": 40000, "loss": 0.1857, "lr": 3.211795299771812e-05, "epoch": 0.739038909889314, "percentage": 40.81, "elapsed_time": "13:19:25", "remaining_time": "19:19:21", "throughput": 556.05, "total_tokens": 26671296} {"current_steps": 16330, "total_steps": 40000, "loss": 0.1494, "lr": 3.210854130485605e-05, "epoch": 0.7392652617759569, "percentage": 40.83, "elapsed_time": "13:19:29", "remaining_time": "19:18:50", "throughput": 556.2, "total_tokens": 26680192} {"current_steps": 16335, "total_steps": 40000, "loss": 0.1527, "lr": 3.209912851576759e-05, "epoch": 0.7394916136625999, "percentage": 40.84, "elapsed_time": "13:19:32", "remaining_time": "19:18:18", "throughput": 556.32, "total_tokens": 26688000} {"current_steps": 16340, "total_steps": 40000, "loss": 0.1147, "lr": 3.208971463190431e-05, "epoch": 0.7397179655492429, "percentage": 40.85, "elapsed_time": "13:19:35", "remaining_time": "19:17:47", "throughput": 556.45, "total_tokens": 26695936} {"current_steps": 16345, "total_steps": 40000, "loss": 0.0933, "lr": 3.208029965471793e-05, "epoch": 0.7399443174358858, "percentage": 40.86, "elapsed_time": "13:19:38", "remaining_time": "19:17:15", "throughput": 556.58, "total_tokens": 26703904} {"current_steps": 16350, "total_steps": 40000, "loss": 0.17, "lr": 3.2070883585660364e-05, "epoch": 0.7401706693225288, "percentage": 40.88, "elapsed_time": "13:19:41", "remaining_time": "19:16:44", "throughput": 556.71, "total_tokens": 26712096} {"current_steps": 16355, "total_steps": 40000, "loss": 0.1152, "lr": 3.20614664261837e-05, "epoch": 0.7403970212091717, "percentage": 40.89, "elapsed_time": "13:19:44", "remaining_time": "19:16:13", "throughput": 556.85, "total_tokens": 26720256} {"current_steps": 16360, "total_steps": 40000, "loss": 0.1311, "lr": 3.205204817774016e-05, "epoch": 0.7406233730958147, "percentage": 40.9, "elapsed_time": "13:19:47", "remaining_time": "19:15:42", "throughput": 556.99, "total_tokens": 26728608} {"current_steps": 16365, "total_steps": 40000, "loss": 0.1227, "lr": 3.204262884178218e-05, "epoch": 0.7408497249824577, "percentage": 40.91, "elapsed_time": "13:19:51", "remaining_time": "19:15:10", "throughput": 557.11, "total_tokens": 26736480} {"current_steps": 16370, "total_steps": 40000, "loss": 0.1151, "lr": 3.2033208419762314e-05, "epoch": 0.7410760768691007, "percentage": 40.92, "elapsed_time": "13:19:54", "remaining_time": "19:14:39", "throughput": 557.23, "total_tokens": 26744032} {"current_steps": 16375, "total_steps": 40000, "loss": 0.142, "lr": 3.2023786913133344e-05, "epoch": 0.7413024287557437, "percentage": 40.94, "elapsed_time": "13:19:57", "remaining_time": "19:14:08", "throughput": 557.36, "total_tokens": 26751872} {"current_steps": 16380, "total_steps": 40000, "loss": 0.1024, "lr": 3.201436432334816e-05, "epoch": 0.7415287806423867, "percentage": 40.95, "elapsed_time": "13:20:00", "remaining_time": "19:13:36", "throughput": 557.49, "total_tokens": 26759776} {"current_steps": 16385, "total_steps": 40000, "loss": 0.1382, "lr": 3.2004940651859844e-05, "epoch": 0.7417551325290296, "percentage": 40.96, "elapsed_time": "13:20:03", "remaining_time": "19:13:05", "throughput": 557.63, "total_tokens": 26768128} {"current_steps": 16390, "total_steps": 40000, "loss": 0.131, "lr": 3.1995515900121655e-05, "epoch": 0.7419814844156726, "percentage": 40.98, "elapsed_time": "13:20:06", "remaining_time": "19:12:34", "throughput": 557.75, "total_tokens": 26776000} {"current_steps": 16395, "total_steps": 40000, "loss": 0.157, "lr": 3.1986090069587e-05, "epoch": 0.7422078363023156, "percentage": 40.99, "elapsed_time": "13:20:10", "remaining_time": "19:12:03", "throughput": 557.89, "total_tokens": 26784096} {"current_steps": 16400, "total_steps": 40000, "loss": 0.1688, "lr": 3.1976663161709466e-05, "epoch": 0.7424341881889586, "percentage": 41.0, "elapsed_time": "13:20:13", "remaining_time": "19:11:32", "throughput": 558.03, "total_tokens": 26792800} {"current_steps": 16400, "total_steps": 40000, "eval_loss": 0.1299797147512436, "epoch": 0.7424341881889586, "percentage": 41.0, "elapsed_time": "13:27:56", "remaining_time": "19:22:38", "throughput": 552.7, "total_tokens": 26792800} {"current_steps": 16405, "total_steps": 40000, "loss": 0.1355, "lr": 3.196723517794279e-05, "epoch": 0.7426605400756016, "percentage": 41.01, "elapsed_time": "13:27:59", "remaining_time": "19:22:07", "throughput": 552.82, "total_tokens": 26800704} {"current_steps": 16410, "total_steps": 40000, "loss": 0.0996, "lr": 3.19578061197409e-05, "epoch": 0.7428868919622446, "percentage": 41.02, "elapsed_time": "13:28:03", "remaining_time": "19:21:36", "throughput": 552.95, "total_tokens": 26808640} {"current_steps": 16415, "total_steps": 40000, "loss": 0.1517, "lr": 3.194837598855787e-05, "epoch": 0.7431132438488874, "percentage": 41.04, "elapsed_time": "13:28:06", "remaining_time": "19:21:04", "throughput": 553.07, "total_tokens": 26816448} {"current_steps": 16420, "total_steps": 40000, "loss": 0.127, "lr": 3.193894478584794e-05, "epoch": 0.7433395957355304, "percentage": 41.05, "elapsed_time": "13:28:09", "remaining_time": "19:20:33", "throughput": 553.21, "total_tokens": 26825024} {"current_steps": 16425, "total_steps": 40000, "loss": 0.0995, "lr": 3.192951251306553e-05, "epoch": 0.7435659476221734, "percentage": 41.06, "elapsed_time": "13:28:12", "remaining_time": "19:20:02", "throughput": 553.35, "total_tokens": 26833248} {"current_steps": 16430, "total_steps": 40000, "loss": 0.1508, "lr": 3.192007917166521e-05, "epoch": 0.7437922995088164, "percentage": 41.08, "elapsed_time": "13:28:15", "remaining_time": "19:19:30", "throughput": 553.48, "total_tokens": 26841312} {"current_steps": 16435, "total_steps": 40000, "loss": 0.1141, "lr": 3.191064476310171e-05, "epoch": 0.7440186513954594, "percentage": 41.09, "elapsed_time": "13:28:19", "remaining_time": "19:18:59", "throughput": 553.61, "total_tokens": 26849440} {"current_steps": 16440, "total_steps": 40000, "loss": 0.1011, "lr": 3.1901209288829944e-05, "epoch": 0.7442450032821023, "percentage": 41.1, "elapsed_time": "13:28:22", "remaining_time": "19:18:27", "throughput": 553.74, "total_tokens": 26857568} {"current_steps": 16445, "total_steps": 40000, "loss": 0.1188, "lr": 3.1891772750304985e-05, "epoch": 0.7444713551687453, "percentage": 41.11, "elapsed_time": "13:28:25", "remaining_time": "19:17:56", "throughput": 553.88, "total_tokens": 26866016} {"current_steps": 16450, "total_steps": 40000, "loss": 0.0933, "lr": 3.188233514898206e-05, "epoch": 0.7446977070553883, "percentage": 41.12, "elapsed_time": "13:28:28", "remaining_time": "19:17:25", "throughput": 554.0, "total_tokens": 26873824} {"current_steps": 16455, "total_steps": 40000, "loss": 0.1436, "lr": 3.187289648631657e-05, "epoch": 0.7449240589420313, "percentage": 41.14, "elapsed_time": "13:28:31", "remaining_time": "19:16:53", "throughput": 554.13, "total_tokens": 26881504} {"current_steps": 16460, "total_steps": 40000, "loss": 0.1136, "lr": 3.186345676376406e-05, "epoch": 0.7451504108286743, "percentage": 41.15, "elapsed_time": "13:28:34", "remaining_time": "19:16:22", "throughput": 554.25, "total_tokens": 26889472} {"current_steps": 16465, "total_steps": 40000, "loss": 0.1187, "lr": 3.1854015982780275e-05, "epoch": 0.7453767627153173, "percentage": 41.16, "elapsed_time": "13:28:37", "remaining_time": "19:15:51", "throughput": 554.38, "total_tokens": 26897312} {"current_steps": 16470, "total_steps": 40000, "loss": 0.1594, "lr": 3.1844574144821084e-05, "epoch": 0.7456031146019602, "percentage": 41.17, "elapsed_time": "13:28:41", "remaining_time": "19:15:20", "throughput": 554.52, "total_tokens": 26906016} {"current_steps": 16475, "total_steps": 40000, "loss": 0.1439, "lr": 3.1835131251342554e-05, "epoch": 0.7458294664886032, "percentage": 41.19, "elapsed_time": "13:28:44", "remaining_time": "19:14:48", "throughput": 554.65, "total_tokens": 26914016} {"current_steps": 16480, "total_steps": 40000, "loss": 0.1386, "lr": 3.182568730380089e-05, "epoch": 0.7460558183752461, "percentage": 41.2, "elapsed_time": "13:28:47", "remaining_time": "19:14:17", "throughput": 554.79, "total_tokens": 26922496} {"current_steps": 16485, "total_steps": 40000, "loss": 0.1432, "lr": 3.181624230365245e-05, "epoch": 0.7462821702618891, "percentage": 41.21, "elapsed_time": "13:28:50", "remaining_time": "19:13:46", "throughput": 554.92, "total_tokens": 26930528} {"current_steps": 16490, "total_steps": 40000, "loss": 0.1146, "lr": 3.180679625235381e-05, "epoch": 0.7465085221485321, "percentage": 41.23, "elapsed_time": "13:28:53", "remaining_time": "19:13:15", "throughput": 555.05, "total_tokens": 26938912} {"current_steps": 16495, "total_steps": 40000, "loss": 0.0964, "lr": 3.1797349151361646e-05, "epoch": 0.7467348740351751, "percentage": 41.24, "elapsed_time": "13:28:57", "remaining_time": "19:12:44", "throughput": 555.19, "total_tokens": 26947168} {"current_steps": 16500, "total_steps": 40000, "loss": 0.1324, "lr": 3.178790100213281e-05, "epoch": 0.746961225921818, "percentage": 41.25, "elapsed_time": "13:29:00", "remaining_time": "19:12:13", "throughput": 555.33, "total_tokens": 26955968} {"current_steps": 16505, "total_steps": 40000, "loss": 0.0941, "lr": 3.1778451806124346e-05, "epoch": 0.747187577808461, "percentage": 41.26, "elapsed_time": "13:29:03", "remaining_time": "19:11:42", "throughput": 555.46, "total_tokens": 26964000} {"current_steps": 16510, "total_steps": 40000, "loss": 0.1156, "lr": 3.176900156479342e-05, "epoch": 0.747413929695104, "percentage": 41.27, "elapsed_time": "13:29:06", "remaining_time": "19:11:11", "throughput": 555.59, "total_tokens": 26972192} {"current_steps": 16515, "total_steps": 40000, "loss": 0.0874, "lr": 3.17595502795974e-05, "epoch": 0.747640281581747, "percentage": 41.29, "elapsed_time": "13:29:09", "remaining_time": "19:10:39", "throughput": 555.72, "total_tokens": 26980160} {"current_steps": 16520, "total_steps": 40000, "loss": 0.1388, "lr": 3.175009795199377e-05, "epoch": 0.74786663346839, "percentage": 41.3, "elapsed_time": "13:29:13", "remaining_time": "19:10:09", "throughput": 555.84, "total_tokens": 26988064} {"current_steps": 16525, "total_steps": 40000, "loss": 0.1283, "lr": 3.1740644583440224e-05, "epoch": 0.7480929853550329, "percentage": 41.31, "elapsed_time": "13:29:16", "remaining_time": "19:09:38", "throughput": 555.98, "total_tokens": 26996480} {"current_steps": 16530, "total_steps": 40000, "loss": 0.099, "lr": 3.173119017539457e-05, "epoch": 0.7483193372416759, "percentage": 41.33, "elapsed_time": "13:29:19", "remaining_time": "19:09:07", "throughput": 556.11, "total_tokens": 27004672} {"current_steps": 16535, "total_steps": 40000, "loss": 0.1464, "lr": 3.172173472931479e-05, "epoch": 0.7485456891283189, "percentage": 41.34, "elapsed_time": "13:29:22", "remaining_time": "19:08:36", "throughput": 556.24, "total_tokens": 27012672} {"current_steps": 16540, "total_steps": 40000, "loss": 0.1599, "lr": 3.1712278246659055e-05, "epoch": 0.7487720410149619, "percentage": 41.35, "elapsed_time": "13:29:26", "remaining_time": "19:08:05", "throughput": 556.38, "total_tokens": 27020960} {"current_steps": 16545, "total_steps": 40000, "loss": 0.0883, "lr": 3.170282072888566e-05, "epoch": 0.7489983929016049, "percentage": 41.36, "elapsed_time": "13:29:29", "remaining_time": "19:07:33", "throughput": 556.5, "total_tokens": 27028736} {"current_steps": 16550, "total_steps": 40000, "loss": 0.1129, "lr": 3.169336217745307e-05, "epoch": 0.7492247447882479, "percentage": 41.38, "elapsed_time": "13:29:32", "remaining_time": "19:07:02", "throughput": 556.63, "total_tokens": 27036736} {"current_steps": 16555, "total_steps": 40000, "loss": 0.1262, "lr": 3.1683902593819924e-05, "epoch": 0.7494510966748907, "percentage": 41.39, "elapsed_time": "13:29:35", "remaining_time": "19:06:31", "throughput": 556.75, "total_tokens": 27044416} {"current_steps": 16560, "total_steps": 40000, "loss": 0.1097, "lr": 3.1674441979445e-05, "epoch": 0.7496774485615337, "percentage": 41.4, "elapsed_time": "13:29:38", "remaining_time": "19:06:00", "throughput": 556.88, "total_tokens": 27052544} {"current_steps": 16565, "total_steps": 40000, "loss": 0.1092, "lr": 3.166498033578725e-05, "epoch": 0.7499038004481767, "percentage": 41.41, "elapsed_time": "13:29:41", "remaining_time": "19:05:29", "throughput": 557.0, "total_tokens": 27060192} {"current_steps": 16570, "total_steps": 40000, "loss": 0.124, "lr": 3.165551766430578e-05, "epoch": 0.7501301523348197, "percentage": 41.42, "elapsed_time": "13:29:44", "remaining_time": "19:04:58", "throughput": 557.12, "total_tokens": 27067712} {"current_steps": 16575, "total_steps": 40000, "loss": 0.105, "lr": 3.164605396645984e-05, "epoch": 0.7503565042214627, "percentage": 41.44, "elapsed_time": "13:29:47", "remaining_time": "19:04:27", "throughput": 557.24, "total_tokens": 27074944} {"current_steps": 16580, "total_steps": 40000, "loss": 0.1142, "lr": 3.163658924370886e-05, "epoch": 0.7505828561081057, "percentage": 41.45, "elapsed_time": "13:29:50", "remaining_time": "19:03:56", "throughput": 557.36, "total_tokens": 27082624} {"current_steps": 16585, "total_steps": 40000, "loss": 0.1416, "lr": 3.1627123497512415e-05, "epoch": 0.7508092079947486, "percentage": 41.46, "elapsed_time": "13:29:54", "remaining_time": "19:03:25", "throughput": 557.48, "total_tokens": 27090144} {"current_steps": 16590, "total_steps": 40000, "loss": 0.0963, "lr": 3.1617656729330245e-05, "epoch": 0.7510355598813916, "percentage": 41.48, "elapsed_time": "13:29:57", "remaining_time": "19:02:54", "throughput": 557.6, "total_tokens": 27097504} {"current_steps": 16595, "total_steps": 40000, "loss": 0.1413, "lr": 3.1608188940622255e-05, "epoch": 0.7512619117680346, "percentage": 41.49, "elapsed_time": "13:30:00", "remaining_time": "19:02:23", "throughput": 557.72, "total_tokens": 27105280} {"current_steps": 16600, "total_steps": 40000, "loss": 0.1423, "lr": 3.159872013284847e-05, "epoch": 0.7514882636546776, "percentage": 41.5, "elapsed_time": "13:30:03", "remaining_time": "19:01:53", "throughput": 557.85, "total_tokens": 27113248} {"current_steps": 16600, "total_steps": 40000, "eval_loss": 0.1294419765472412, "epoch": 0.7514882636546776, "percentage": 41.5, "elapsed_time": "13:37:46", "remaining_time": "19:12:45", "throughput": 552.59, "total_tokens": 27113248} {"current_steps": 16605, "total_steps": 40000, "loss": 0.1256, "lr": 3.1589250307469134e-05, "epoch": 0.7517146155413206, "percentage": 41.51, "elapsed_time": "13:37:50", "remaining_time": "19:12:15", "throughput": 552.71, "total_tokens": 27121504} {"current_steps": 16610, "total_steps": 40000, "loss": 0.1167, "lr": 3.1579779465944586e-05, "epoch": 0.7519409674279635, "percentage": 41.52, "elapsed_time": "13:37:53", "remaining_time": "19:11:44", "throughput": 552.84, "total_tokens": 27129952} {"current_steps": 16615, "total_steps": 40000, "loss": 0.1076, "lr": 3.1570307609735363e-05, "epoch": 0.7521673193146065, "percentage": 41.54, "elapsed_time": "13:37:56", "remaining_time": "19:11:13", "throughput": 552.98, "total_tokens": 27138464} {"current_steps": 16620, "total_steps": 40000, "loss": 0.157, "lr": 3.156083474030213e-05, "epoch": 0.7523936712012494, "percentage": 41.55, "elapsed_time": "13:37:59", "remaining_time": "19:10:42", "throughput": 553.1, "total_tokens": 27146240} {"current_steps": 16625, "total_steps": 40000, "loss": 0.1344, "lr": 3.155136085910573e-05, "epoch": 0.7526200230878924, "percentage": 41.56, "elapsed_time": "13:38:02", "remaining_time": "19:10:11", "throughput": 553.22, "total_tokens": 27153696} {"current_steps": 16630, "total_steps": 40000, "loss": 0.122, "lr": 3.154188596760717e-05, "epoch": 0.7528463749745354, "percentage": 41.58, "elapsed_time": "13:38:06", "remaining_time": "19:09:40", "throughput": 553.38, "total_tokens": 27163136} {"current_steps": 16635, "total_steps": 40000, "loss": 0.1133, "lr": 3.153241006726757e-05, "epoch": 0.7530727268611784, "percentage": 41.59, "elapsed_time": "13:38:09", "remaining_time": "19:09:09", "throughput": 553.5, "total_tokens": 27170784} {"current_steps": 16640, "total_steps": 40000, "loss": 0.12, "lr": 3.152293315954825e-05, "epoch": 0.7532990787478213, "percentage": 41.6, "elapsed_time": "13:38:12", "remaining_time": "19:08:38", "throughput": 553.62, "total_tokens": 27178400} {"current_steps": 16645, "total_steps": 40000, "loss": 0.1403, "lr": 3.1513455245910666e-05, "epoch": 0.7535254306344643, "percentage": 41.61, "elapsed_time": "13:38:15", "remaining_time": "19:08:07", "throughput": 553.75, "total_tokens": 27186496} {"current_steps": 16650, "total_steps": 40000, "loss": 0.114, "lr": 3.150397632781643e-05, "epoch": 0.7537517825211073, "percentage": 41.62, "elapsed_time": "13:38:18", "remaining_time": "19:07:36", "throughput": 553.87, "total_tokens": 27194560} {"current_steps": 16655, "total_steps": 40000, "loss": 0.1284, "lr": 3.149449640672731e-05, "epoch": 0.7539781344077503, "percentage": 41.64, "elapsed_time": "13:38:21", "remaining_time": "19:07:05", "throughput": 554.0, "total_tokens": 27202400} {"current_steps": 16660, "total_steps": 40000, "loss": 0.1193, "lr": 3.148501548410523e-05, "epoch": 0.7542044862943933, "percentage": 41.65, "elapsed_time": "13:38:25", "remaining_time": "19:06:34", "throughput": 554.13, "total_tokens": 27210400} {"current_steps": 16665, "total_steps": 40000, "loss": 0.147, "lr": 3.1475533561412256e-05, "epoch": 0.7544308381810363, "percentage": 41.66, "elapsed_time": "13:38:28", "remaining_time": "19:06:03", "throughput": 554.26, "total_tokens": 27218720} {"current_steps": 16670, "total_steps": 40000, "loss": 0.1344, "lr": 3.146605064011065e-05, "epoch": 0.7546571900676792, "percentage": 41.68, "elapsed_time": "13:38:31", "remaining_time": "19:05:32", "throughput": 554.4, "total_tokens": 27227360} {"current_steps": 16675, "total_steps": 40000, "loss": 0.1123, "lr": 3.145656672166277e-05, "epoch": 0.7548835419543222, "percentage": 41.69, "elapsed_time": "13:38:34", "remaining_time": "19:05:01", "throughput": 554.54, "total_tokens": 27236288} {"current_steps": 16680, "total_steps": 40000, "loss": 0.1265, "lr": 3.144708180753116e-05, "epoch": 0.7551098938409652, "percentage": 41.7, "elapsed_time": "13:38:37", "remaining_time": "19:04:30", "throughput": 554.67, "total_tokens": 27244256} {"current_steps": 16685, "total_steps": 40000, "loss": 0.1145, "lr": 3.143759589917851e-05, "epoch": 0.7553362457276082, "percentage": 41.71, "elapsed_time": "13:38:41", "remaining_time": "19:03:59", "throughput": 554.8, "total_tokens": 27252224} {"current_steps": 16690, "total_steps": 40000, "loss": 0.1347, "lr": 3.142810899806768e-05, "epoch": 0.7555625976142512, "percentage": 41.73, "elapsed_time": "13:38:44", "remaining_time": "19:03:29", "throughput": 554.93, "total_tokens": 27260256} {"current_steps": 16695, "total_steps": 40000, "loss": 0.1115, "lr": 3.141862110566166e-05, "epoch": 0.755788949500894, "percentage": 41.74, "elapsed_time": "13:38:47", "remaining_time": "19:02:58", "throughput": 555.05, "total_tokens": 27268192} {"current_steps": 16700, "total_steps": 40000, "loss": 0.0819, "lr": 3.1409132223423606e-05, "epoch": 0.756015301387537, "percentage": 41.75, "elapsed_time": "13:38:50", "remaining_time": "19:02:27", "throughput": 555.19, "total_tokens": 27276672} {"current_steps": 16705, "total_steps": 40000, "loss": 0.1233, "lr": 3.139964235281682e-05, "epoch": 0.75624165327418, "percentage": 41.76, "elapsed_time": "13:38:53", "remaining_time": "19:01:56", "throughput": 555.32, "total_tokens": 27285216} {"current_steps": 16710, "total_steps": 40000, "loss": 0.1491, "lr": 3.139015149530476e-05, "epoch": 0.756468005160823, "percentage": 41.77, "elapsed_time": "13:38:57", "remaining_time": "19:01:25", "throughput": 555.45, "total_tokens": 27293344} {"current_steps": 16715, "total_steps": 40000, "loss": 0.1198, "lr": 3.1380659652351034e-05, "epoch": 0.756694357047466, "percentage": 41.79, "elapsed_time": "13:39:00", "remaining_time": "19:00:55", "throughput": 555.59, "total_tokens": 27302080} {"current_steps": 16720, "total_steps": 40000, "loss": 0.1722, "lr": 3.137116682541941e-05, "epoch": 0.756920708934109, "percentage": 41.8, "elapsed_time": "13:39:03", "remaining_time": "19:00:24", "throughput": 555.71, "total_tokens": 27309664} {"current_steps": 16725, "total_steps": 40000, "loss": 0.1443, "lr": 3.136167301597379e-05, "epoch": 0.7571470608207519, "percentage": 41.81, "elapsed_time": "13:39:06", "remaining_time": "18:59:53", "throughput": 555.84, "total_tokens": 27317760} {"current_steps": 16730, "total_steps": 40000, "loss": 0.1322, "lr": 3.1352178225478254e-05, "epoch": 0.7573734127073949, "percentage": 41.83, "elapsed_time": "13:39:09", "remaining_time": "18:59:23", "throughput": 555.98, "total_tokens": 27326144} {"current_steps": 16735, "total_steps": 40000, "loss": 0.0886, "lr": 3.1342682455396996e-05, "epoch": 0.7575997645940379, "percentage": 41.84, "elapsed_time": "13:39:12", "remaining_time": "18:58:52", "throughput": 556.11, "total_tokens": 27334432} {"current_steps": 16740, "total_steps": 40000, "loss": 0.1108, "lr": 3.133318570719441e-05, "epoch": 0.7578261164806809, "percentage": 41.85, "elapsed_time": "13:39:16", "remaining_time": "18:58:21", "throughput": 556.25, "total_tokens": 27342912} {"current_steps": 16745, "total_steps": 40000, "loss": 0.1067, "lr": 3.132368798233499e-05, "epoch": 0.7580524683673239, "percentage": 41.86, "elapsed_time": "13:39:19", "remaining_time": "18:57:51", "throughput": 556.38, "total_tokens": 27351552} {"current_steps": 16750, "total_steps": 40000, "loss": 0.1526, "lr": 3.131418928228342e-05, "epoch": 0.7582788202539669, "percentage": 41.88, "elapsed_time": "13:39:22", "remaining_time": "18:57:20", "throughput": 556.51, "total_tokens": 27359616} {"current_steps": 16755, "total_steps": 40000, "loss": 0.1568, "lr": 3.1304689608504514e-05, "epoch": 0.7585051721406098, "percentage": 41.89, "elapsed_time": "13:39:25", "remaining_time": "18:56:50", "throughput": 556.65, "total_tokens": 27368320} {"current_steps": 16760, "total_steps": 40000, "loss": 0.1566, "lr": 3.129518896246324e-05, "epoch": 0.7587315240272527, "percentage": 41.9, "elapsed_time": "13:39:29", "remaining_time": "18:56:19", "throughput": 556.81, "total_tokens": 27378080} {"current_steps": 16765, "total_steps": 40000, "loss": 0.1231, "lr": 3.128568734562472e-05, "epoch": 0.7589578759138957, "percentage": 41.91, "elapsed_time": "13:39:32", "remaining_time": "18:55:49", "throughput": 556.94, "total_tokens": 27386400} {"current_steps": 16770, "total_steps": 40000, "loss": 0.1663, "lr": 3.127618475945421e-05, "epoch": 0.7591842278005387, "percentage": 41.93, "elapsed_time": "13:39:35", "remaining_time": "18:55:18", "throughput": 557.07, "total_tokens": 27394432} {"current_steps": 16775, "total_steps": 40000, "loss": 0.1448, "lr": 3.126668120541715e-05, "epoch": 0.7594105796871817, "percentage": 41.94, "elapsed_time": "13:39:38", "remaining_time": "18:54:48", "throughput": 557.2, "total_tokens": 27402464} {"current_steps": 16780, "total_steps": 40000, "loss": 0.0871, "lr": 3.1257176684979096e-05, "epoch": 0.7596369315738246, "percentage": 41.95, "elapsed_time": "13:39:42", "remaining_time": "18:54:17", "throughput": 557.33, "total_tokens": 27410688} {"current_steps": 16785, "total_steps": 40000, "loss": 0.1249, "lr": 3.124767119960576e-05, "epoch": 0.7598632834604676, "percentage": 41.96, "elapsed_time": "13:39:45", "remaining_time": "18:53:47", "throughput": 557.46, "total_tokens": 27418848} {"current_steps": 16790, "total_steps": 40000, "loss": 0.1148, "lr": 3.123816475076301e-05, "epoch": 0.7600896353471106, "percentage": 41.98, "elapsed_time": "13:39:48", "remaining_time": "18:53:16", "throughput": 557.58, "total_tokens": 27426560} {"current_steps": 16795, "total_steps": 40000, "loss": 0.1144, "lr": 3.122865733991687e-05, "epoch": 0.7603159872337536, "percentage": 41.99, "elapsed_time": "13:39:51", "remaining_time": "18:52:46", "throughput": 557.7, "total_tokens": 27434368} {"current_steps": 16800, "total_steps": 40000, "loss": 0.1579, "lr": 3.1219148968533486e-05, "epoch": 0.7605423391203966, "percentage": 42.0, "elapsed_time": "13:39:54", "remaining_time": "18:52:15", "throughput": 557.83, "total_tokens": 27442048} {"current_steps": 16800, "total_steps": 40000, "eval_loss": 0.1284809708595276, "epoch": 0.7605423391203966, "percentage": 42.0, "elapsed_time": "13:47:37", "remaining_time": "19:02:54", "throughput": 552.63, "total_tokens": 27442048} {"current_steps": 16805, "total_steps": 40000, "loss": 0.1059, "lr": 3.120963963807918e-05, "epoch": 0.7607686910070396, "percentage": 42.01, "elapsed_time": "13:47:41", "remaining_time": "19:02:25", "throughput": 552.74, "total_tokens": 27450176} {"current_steps": 16810, "total_steps": 40000, "loss": 0.1252, "lr": 3.12001293500204e-05, "epoch": 0.7609950428936825, "percentage": 42.02, "elapsed_time": "13:47:44", "remaining_time": "19:01:54", "throughput": 552.88, "total_tokens": 27458880} {"current_steps": 16815, "total_steps": 40000, "loss": 0.122, "lr": 3.1190618105823765e-05, "epoch": 0.7612213947803255, "percentage": 42.04, "elapsed_time": "13:47:48", "remaining_time": "19:01:23", "throughput": 553.01, "total_tokens": 27466944} {"current_steps": 16820, "total_steps": 40000, "loss": 0.1244, "lr": 3.118110590695603e-05, "epoch": 0.7614477466669685, "percentage": 42.05, "elapsed_time": "13:47:51", "remaining_time": "19:00:52", "throughput": 553.13, "total_tokens": 27474496} {"current_steps": 16825, "total_steps": 40000, "loss": 0.0782, "lr": 3.117159275488407e-05, "epoch": 0.7616740985536115, "percentage": 42.06, "elapsed_time": "13:47:54", "remaining_time": "19:00:22", "throughput": 553.28, "total_tokens": 27483776} {"current_steps": 16830, "total_steps": 40000, "loss": 0.0886, "lr": 3.1162078651074956e-05, "epoch": 0.7619004504402545, "percentage": 42.08, "elapsed_time": "13:47:57", "remaining_time": "18:59:51", "throughput": 553.4, "total_tokens": 27491360} {"current_steps": 16835, "total_steps": 40000, "loss": 0.1401, "lr": 3.1152563596995885e-05, "epoch": 0.7621268023268974, "percentage": 42.09, "elapsed_time": "13:48:00", "remaining_time": "18:59:21", "throughput": 553.54, "total_tokens": 27500352} {"current_steps": 16840, "total_steps": 40000, "loss": 0.1291, "lr": 3.1143047594114186e-05, "epoch": 0.7623531542135403, "percentage": 42.1, "elapsed_time": "13:48:04", "remaining_time": "18:58:50", "throughput": 553.67, "total_tokens": 27508576} {"current_steps": 16845, "total_steps": 40000, "loss": 0.1078, "lr": 3.113353064389734e-05, "epoch": 0.7625795061001833, "percentage": 42.11, "elapsed_time": "13:48:07", "remaining_time": "18:58:19", "throughput": 553.79, "total_tokens": 27516448} {"current_steps": 16850, "total_steps": 40000, "loss": 0.1349, "lr": 3.1124012747812993e-05, "epoch": 0.7628058579868263, "percentage": 42.12, "elapsed_time": "13:48:10", "remaining_time": "18:57:48", "throughput": 553.92, "total_tokens": 27524512} {"current_steps": 16855, "total_steps": 40000, "loss": 0.1739, "lr": 3.1114493907328936e-05, "epoch": 0.7630322098734693, "percentage": 42.14, "elapsed_time": "13:48:13", "remaining_time": "18:57:18", "throughput": 554.04, "total_tokens": 27532320} {"current_steps": 16860, "total_steps": 40000, "loss": 0.0948, "lr": 3.110497412391306e-05, "epoch": 0.7632585617601123, "percentage": 42.15, "elapsed_time": "13:48:16", "remaining_time": "18:56:47", "throughput": 554.17, "total_tokens": 27540256} {"current_steps": 16865, "total_steps": 40000, "loss": 0.1849, "lr": 3.1095453399033466e-05, "epoch": 0.7634849136467552, "percentage": 42.16, "elapsed_time": "13:48:19", "remaining_time": "18:56:17", "throughput": 554.29, "total_tokens": 27548352} {"current_steps": 16870, "total_steps": 40000, "loss": 0.0953, "lr": 3.108593173415835e-05, "epoch": 0.7637112655333982, "percentage": 42.18, "elapsed_time": "13:48:23", "remaining_time": "18:55:46", "throughput": 554.43, "total_tokens": 27556672} {"current_steps": 16875, "total_steps": 40000, "loss": 0.115, "lr": 3.107640913075609e-05, "epoch": 0.7639376174200412, "percentage": 42.19, "elapsed_time": "13:48:26", "remaining_time": "18:55:15", "throughput": 554.56, "total_tokens": 27564960} {"current_steps": 16880, "total_steps": 40000, "loss": 0.1388, "lr": 3.106688559029517e-05, "epoch": 0.7641639693066842, "percentage": 42.2, "elapsed_time": "13:48:29", "remaining_time": "18:54:45", "throughput": 554.69, "total_tokens": 27573248} {"current_steps": 16885, "total_steps": 40000, "loss": 0.1383, "lr": 3.105736111424425e-05, "epoch": 0.7643903211933272, "percentage": 42.21, "elapsed_time": "13:48:32", "remaining_time": "18:54:15", "throughput": 554.83, "total_tokens": 27582016} {"current_steps": 16890, "total_steps": 40000, "loss": 0.1175, "lr": 3.1047835704072136e-05, "epoch": 0.7646166730799702, "percentage": 42.23, "elapsed_time": "13:48:35", "remaining_time": "18:53:44", "throughput": 554.95, "total_tokens": 27589888} {"current_steps": 16895, "total_steps": 40000, "loss": 0.0934, "lr": 3.103830936124775e-05, "epoch": 0.764843024966613, "percentage": 42.24, "elapsed_time": "13:48:38", "remaining_time": "18:53:13", "throughput": 555.08, "total_tokens": 27597888} {"current_steps": 16900, "total_steps": 40000, "loss": 0.1544, "lr": 3.102878208724018e-05, "epoch": 0.765069376853256, "percentage": 42.25, "elapsed_time": "13:48:42", "remaining_time": "18:52:43", "throughput": 555.2, "total_tokens": 27605856} {"current_steps": 16905, "total_steps": 40000, "loss": 0.111, "lr": 3.101925388351865e-05, "epoch": 0.765295728739899, "percentage": 42.26, "elapsed_time": "13:48:45", "remaining_time": "18:52:13", "throughput": 555.35, "total_tokens": 27614944} {"current_steps": 16910, "total_steps": 40000, "loss": 0.0954, "lr": 3.1009724751552515e-05, "epoch": 0.765522080626542, "percentage": 42.27, "elapsed_time": "13:48:48", "remaining_time": "18:51:42", "throughput": 555.48, "total_tokens": 27623392} {"current_steps": 16915, "total_steps": 40000, "loss": 0.1388, "lr": 3.100019469281131e-05, "epoch": 0.765748432513185, "percentage": 42.29, "elapsed_time": "13:48:51", "remaining_time": "18:51:12", "throughput": 555.61, "total_tokens": 27631392} {"current_steps": 16920, "total_steps": 40000, "loss": 0.1253, "lr": 3.0990663708764685e-05, "epoch": 0.765974784399828, "percentage": 42.3, "elapsed_time": "13:48:55", "remaining_time": "18:50:41", "throughput": 555.73, "total_tokens": 27639328} {"current_steps": 16925, "total_steps": 40000, "loss": 0.0921, "lr": 3.098113180088243e-05, "epoch": 0.7662011362864709, "percentage": 42.31, "elapsed_time": "13:48:58", "remaining_time": "18:50:11", "throughput": 555.86, "total_tokens": 27647232} {"current_steps": 16930, "total_steps": 40000, "loss": 0.1408, "lr": 3.097159897063448e-05, "epoch": 0.7664274881731139, "percentage": 42.33, "elapsed_time": "13:49:01", "remaining_time": "18:49:40", "throughput": 555.97, "total_tokens": 27654592} {"current_steps": 16935, "total_steps": 40000, "loss": 0.166, "lr": 3.096206521949094e-05, "epoch": 0.7666538400597569, "percentage": 42.34, "elapsed_time": "13:49:04", "remaining_time": "18:49:10", "throughput": 556.09, "total_tokens": 27662080} {"current_steps": 16940, "total_steps": 40000, "loss": 0.1195, "lr": 3.0952530548922006e-05, "epoch": 0.7668801919463999, "percentage": 42.35, "elapsed_time": "13:49:07", "remaining_time": "18:48:39", "throughput": 556.22, "total_tokens": 27670400} {"current_steps": 16945, "total_steps": 40000, "loss": 0.1277, "lr": 3.0942994960398064e-05, "epoch": 0.7671065438330429, "percentage": 42.36, "elapsed_time": "13:49:10", "remaining_time": "18:48:09", "throughput": 556.34, "total_tokens": 27678400} {"current_steps": 16950, "total_steps": 40000, "loss": 0.117, "lr": 3.093345845538961e-05, "epoch": 0.7673328957196858, "percentage": 42.38, "elapsed_time": "13:49:13", "remaining_time": "18:47:39", "throughput": 556.49, "total_tokens": 27687328} {"current_steps": 16955, "total_steps": 40000, "loss": 0.092, "lr": 3.09239210353673e-05, "epoch": 0.7675592476063288, "percentage": 42.39, "elapsed_time": "13:49:16", "remaining_time": "18:47:09", "throughput": 556.6, "total_tokens": 27694784} {"current_steps": 16960, "total_steps": 40000, "loss": 0.0999, "lr": 3.0914382701801926e-05, "epoch": 0.7677855994929718, "percentage": 42.4, "elapsed_time": "13:49:20", "remaining_time": "18:46:38", "throughput": 556.72, "total_tokens": 27702432} {"current_steps": 16965, "total_steps": 40000, "loss": 0.1263, "lr": 3.090484345616441e-05, "epoch": 0.7680119513796148, "percentage": 42.41, "elapsed_time": "13:49:23", "remaining_time": "18:46:08", "throughput": 556.84, "total_tokens": 27710080} {"current_steps": 16970, "total_steps": 40000, "loss": 0.1526, "lr": 3.0895303299925825e-05, "epoch": 0.7682383032662577, "percentage": 42.43, "elapsed_time": "13:49:26", "remaining_time": "18:45:38", "throughput": 556.98, "total_tokens": 27718752} {"current_steps": 16975, "total_steps": 40000, "loss": 0.1266, "lr": 3.0885762234557393e-05, "epoch": 0.7684646551529007, "percentage": 42.44, "elapsed_time": "13:49:29", "remaining_time": "18:45:07", "throughput": 557.1, "total_tokens": 27726400} {"current_steps": 16980, "total_steps": 40000, "loss": 0.1557, "lr": 3.087622026153045e-05, "epoch": 0.7686910070395436, "percentage": 42.45, "elapsed_time": "13:49:32", "remaining_time": "18:44:37", "throughput": 557.23, "total_tokens": 27734848} {"current_steps": 16985, "total_steps": 40000, "loss": 0.1163, "lr": 3.086667738231651e-05, "epoch": 0.7689173589261866, "percentage": 42.46, "elapsed_time": "13:49:35", "remaining_time": "18:44:07", "throughput": 557.35, "total_tokens": 27742784} {"current_steps": 16990, "total_steps": 40000, "loss": 0.1159, "lr": 3.085713359838718e-05, "epoch": 0.7691437108128296, "percentage": 42.48, "elapsed_time": "13:49:39", "remaining_time": "18:43:37", "throughput": 557.48, "total_tokens": 27750848} {"current_steps": 16995, "total_steps": 40000, "loss": 0.1603, "lr": 3.084758891121425e-05, "epoch": 0.7693700626994726, "percentage": 42.49, "elapsed_time": "13:49:42", "remaining_time": "18:43:06", "throughput": 557.61, "total_tokens": 27758912} {"current_steps": 17000, "total_steps": 40000, "loss": 0.0888, "lr": 3.083804332226963e-05, "epoch": 0.7695964145861156, "percentage": 42.5, "elapsed_time": "13:49:45", "remaining_time": "18:42:36", "throughput": 557.73, "total_tokens": 27766816} {"current_steps": 17000, "total_steps": 40000, "eval_loss": 0.12930282950401306, "epoch": 0.7695964145861156, "percentage": 42.5, "elapsed_time": "13:57:28", "remaining_time": "18:53:02", "throughput": 552.6, "total_tokens": 27766816} {"current_steps": 17005, "total_steps": 40000, "loss": 0.1308, "lr": 3.082849683302536e-05, "epoch": 0.7698227664727586, "percentage": 42.51, "elapsed_time": "13:57:32", "remaining_time": "18:52:33", "throughput": 552.71, "total_tokens": 27774720} {"current_steps": 17010, "total_steps": 40000, "loss": 0.1256, "lr": 3.081894944495363e-05, "epoch": 0.7700491183594015, "percentage": 42.52, "elapsed_time": "13:57:35", "remaining_time": "18:52:02", "throughput": 552.84, "total_tokens": 27782976} {"current_steps": 17015, "total_steps": 40000, "loss": 0.1319, "lr": 3.080940115952677e-05, "epoch": 0.7702754702460445, "percentage": 42.54, "elapsed_time": "13:57:38", "remaining_time": "18:51:32", "throughput": 552.97, "total_tokens": 27791200} {"current_steps": 17020, "total_steps": 40000, "loss": 0.1296, "lr": 3.0799851978217245e-05, "epoch": 0.7705018221326875, "percentage": 42.55, "elapsed_time": "13:57:41", "remaining_time": "18:51:02", "throughput": 553.09, "total_tokens": 27799456} {"current_steps": 17025, "total_steps": 40000, "loss": 0.1492, "lr": 3.0790301902497666e-05, "epoch": 0.7707281740193305, "percentage": 42.56, "elapsed_time": "13:57:44", "remaining_time": "18:50:31", "throughput": 553.23, "total_tokens": 27807968} {"current_steps": 17030, "total_steps": 40000, "loss": 0.114, "lr": 3.078075093384076e-05, "epoch": 0.7709545259059735, "percentage": 42.58, "elapsed_time": "13:57:48", "remaining_time": "18:50:01", "throughput": 553.36, "total_tokens": 27816288} {"current_steps": 17035, "total_steps": 40000, "loss": 0.1246, "lr": 3.077119907371942e-05, "epoch": 0.7711808777926163, "percentage": 42.59, "elapsed_time": "13:57:51", "remaining_time": "18:49:31", "throughput": 553.48, "total_tokens": 27823936} {"current_steps": 17040, "total_steps": 40000, "loss": 0.1614, "lr": 3.076164632360666e-05, "epoch": 0.7714072296792593, "percentage": 42.6, "elapsed_time": "13:57:54", "remaining_time": "18:49:00", "throughput": 553.6, "total_tokens": 27831968} {"current_steps": 17045, "total_steps": 40000, "loss": 0.1388, "lr": 3.075209268497563e-05, "epoch": 0.7716335815659023, "percentage": 42.61, "elapsed_time": "13:57:57", "remaining_time": "18:48:30", "throughput": 553.73, "total_tokens": 27840192} {"current_steps": 17050, "total_steps": 40000, "loss": 0.1101, "lr": 3.074253815929961e-05, "epoch": 0.7718599334525453, "percentage": 42.62, "elapsed_time": "13:58:00", "remaining_time": "18:47:59", "throughput": 553.85, "total_tokens": 27847872} {"current_steps": 17055, "total_steps": 40000, "loss": 0.1526, "lr": 3.0732982748052054e-05, "epoch": 0.7720862853391883, "percentage": 42.64, "elapsed_time": "13:58:03", "remaining_time": "18:47:29", "throughput": 553.98, "total_tokens": 27856512} {"current_steps": 17060, "total_steps": 40000, "loss": 0.1271, "lr": 3.072342645270651e-05, "epoch": 0.7723126372258313, "percentage": 42.65, "elapsed_time": "13:58:07", "remaining_time": "18:46:59", "throughput": 554.11, "total_tokens": 27864416} {"current_steps": 17065, "total_steps": 40000, "loss": 0.1348, "lr": 3.071386927473668e-05, "epoch": 0.7725389891124742, "percentage": 42.66, "elapsed_time": "13:58:10", "remaining_time": "18:46:29", "throughput": 554.24, "total_tokens": 27872832} {"current_steps": 17070, "total_steps": 40000, "loss": 0.1014, "lr": 3.0704311215616404e-05, "epoch": 0.7727653409991172, "percentage": 42.68, "elapsed_time": "13:58:13", "remaining_time": "18:45:58", "throughput": 554.36, "total_tokens": 27880576} {"current_steps": 17075, "total_steps": 40000, "loss": 0.1234, "lr": 3.0694752276819656e-05, "epoch": 0.7729916928857602, "percentage": 42.69, "elapsed_time": "13:58:16", "remaining_time": "18:45:28", "throughput": 554.47, "total_tokens": 27888096} {"current_steps": 17080, "total_steps": 40000, "loss": 0.1102, "lr": 3.068519245982054e-05, "epoch": 0.7732180447724032, "percentage": 42.7, "elapsed_time": "13:58:19", "remaining_time": "18:44:58", "throughput": 554.59, "total_tokens": 27895872} {"current_steps": 17085, "total_steps": 40000, "loss": 0.1304, "lr": 3.0675631766093304e-05, "epoch": 0.7734443966590462, "percentage": 42.71, "elapsed_time": "13:58:22", "remaining_time": "18:44:27", "throughput": 554.73, "total_tokens": 27904608} {"current_steps": 17090, "total_steps": 40000, "loss": 0.0981, "lr": 3.066607019711232e-05, "epoch": 0.7736707485456892, "percentage": 42.73, "elapsed_time": "13:58:26", "remaining_time": "18:43:57", "throughput": 554.86, "total_tokens": 27912960} {"current_steps": 17095, "total_steps": 40000, "loss": 0.1194, "lr": 3.065650775435211e-05, "epoch": 0.7738971004323321, "percentage": 42.74, "elapsed_time": "13:58:29", "remaining_time": "18:43:27", "throughput": 554.99, "total_tokens": 27921248} {"current_steps": 17100, "total_steps": 40000, "loss": 0.1057, "lr": 3.0646944439287326e-05, "epoch": 0.7741234523189751, "percentage": 42.75, "elapsed_time": "13:58:32", "remaining_time": "18:42:57", "throughput": 555.11, "total_tokens": 27928960} {"current_steps": 17105, "total_steps": 40000, "loss": 0.1005, "lr": 3.0637380253392736e-05, "epoch": 0.774349804205618, "percentage": 42.76, "elapsed_time": "13:58:35", "remaining_time": "18:42:27", "throughput": 555.23, "total_tokens": 27936864} {"current_steps": 17110, "total_steps": 40000, "loss": 0.105, "lr": 3.062781519814327e-05, "epoch": 0.774576156092261, "percentage": 42.77, "elapsed_time": "13:58:38", "remaining_time": "18:41:57", "throughput": 555.37, "total_tokens": 27945376} {"current_steps": 17115, "total_steps": 40000, "loss": 0.0859, "lr": 3.0618249275013985e-05, "epoch": 0.774802507978904, "percentage": 42.79, "elapsed_time": "13:58:42", "remaining_time": "18:41:27", "throughput": 555.5, "total_tokens": 27954112} {"current_steps": 17120, "total_steps": 40000, "loss": 0.1085, "lr": 3.060868248548005e-05, "epoch": 0.7750288598655469, "percentage": 42.8, "elapsed_time": "13:58:45", "remaining_time": "18:40:57", "throughput": 555.63, "total_tokens": 27962144} {"current_steps": 17125, "total_steps": 40000, "loss": 0.1356, "lr": 3.0599114831016796e-05, "epoch": 0.7752552117521899, "percentage": 42.81, "elapsed_time": "13:58:48", "remaining_time": "18:40:26", "throughput": 555.75, "total_tokens": 27970080} {"current_steps": 17130, "total_steps": 40000, "loss": 0.1909, "lr": 3.0589546313099666e-05, "epoch": 0.7754815636388329, "percentage": 42.83, "elapsed_time": "13:58:51", "remaining_time": "18:39:56", "throughput": 555.89, "total_tokens": 27978624} {"current_steps": 17135, "total_steps": 40000, "loss": 0.1317, "lr": 3.0579976933204255e-05, "epoch": 0.7757079155254759, "percentage": 42.84, "elapsed_time": "13:58:54", "remaining_time": "18:39:26", "throughput": 556.01, "total_tokens": 27986752} {"current_steps": 17140, "total_steps": 40000, "loss": 0.1387, "lr": 3.0570406692806284e-05, "epoch": 0.7759342674121189, "percentage": 42.85, "elapsed_time": "13:58:57", "remaining_time": "18:38:56", "throughput": 556.15, "total_tokens": 27995488} {"current_steps": 17145, "total_steps": 40000, "loss": 0.2336, "lr": 3.05608355933816e-05, "epoch": 0.7761606192987619, "percentage": 42.86, "elapsed_time": "13:59:01", "remaining_time": "18:38:26", "throughput": 556.27, "total_tokens": 28003424} {"current_steps": 17150, "total_steps": 40000, "loss": 0.1252, "lr": 3.055126363640618e-05, "epoch": 0.7763869711854048, "percentage": 42.88, "elapsed_time": "13:59:04", "remaining_time": "18:37:56", "throughput": 556.39, "total_tokens": 28011232} {"current_steps": 17155, "total_steps": 40000, "loss": 0.1258, "lr": 3.0541690823356146e-05, "epoch": 0.7766133230720478, "percentage": 42.89, "elapsed_time": "13:59:07", "remaining_time": "18:37:26", "throughput": 556.52, "total_tokens": 28019328} {"current_steps": 17160, "total_steps": 40000, "loss": 0.138, "lr": 3.053211715570775e-05, "epoch": 0.7768396749586908, "percentage": 42.9, "elapsed_time": "13:59:10", "remaining_time": "18:36:56", "throughput": 556.64, "total_tokens": 28027456} {"current_steps": 17165, "total_steps": 40000, "loss": 0.1345, "lr": 3.052254263493736e-05, "epoch": 0.7770660268453338, "percentage": 42.91, "elapsed_time": "13:59:13", "remaining_time": "18:36:26", "throughput": 556.76, "total_tokens": 28035232} {"current_steps": 17170, "total_steps": 40000, "loss": 0.1553, "lr": 3.0512967262521498e-05, "epoch": 0.7772923787319768, "percentage": 42.93, "elapsed_time": "13:59:17", "remaining_time": "18:35:56", "throughput": 556.89, "total_tokens": 28043296} {"current_steps": 17175, "total_steps": 40000, "loss": 0.1719, "lr": 3.0503391039936803e-05, "epoch": 0.7775187306186198, "percentage": 42.94, "elapsed_time": "13:59:20", "remaining_time": "18:35:27", "throughput": 557.02, "total_tokens": 28051808} {"current_steps": 17180, "total_steps": 40000, "loss": 0.062, "lr": 3.0493813968660056e-05, "epoch": 0.7777450825052626, "percentage": 42.95, "elapsed_time": "13:59:23", "remaining_time": "18:34:57", "throughput": 557.15, "total_tokens": 28060032} {"current_steps": 17185, "total_steps": 40000, "loss": 0.1421, "lr": 3.0484236050168153e-05, "epoch": 0.7779714343919056, "percentage": 42.96, "elapsed_time": "13:59:26", "remaining_time": "18:34:27", "throughput": 557.28, "total_tokens": 28068224} {"current_steps": 17190, "total_steps": 40000, "loss": 0.1175, "lr": 3.0474657285938123e-05, "epoch": 0.7781977862785486, "percentage": 42.98, "elapsed_time": "13:59:29", "remaining_time": "18:33:57", "throughput": 557.41, "total_tokens": 28076832} {"current_steps": 17195, "total_steps": 40000, "loss": 0.1356, "lr": 3.046507767744715e-05, "epoch": 0.7784241381651916, "percentage": 42.99, "elapsed_time": "13:59:33", "remaining_time": "18:33:27", "throughput": 557.53, "total_tokens": 28084448} {"current_steps": 17200, "total_steps": 40000, "loss": 0.1038, "lr": 3.045549722617252e-05, "epoch": 0.7786504900518346, "percentage": 43.0, "elapsed_time": "13:59:36", "remaining_time": "18:32:57", "throughput": 557.66, "total_tokens": 28092576} {"current_steps": 17200, "total_steps": 40000, "eval_loss": 0.12884247303009033, "epoch": 0.7786504900518346, "percentage": 43.0, "elapsed_time": "14:07:18", "remaining_time": "18:43:11", "throughput": 552.58, "total_tokens": 28092576} {"current_steps": 17205, "total_steps": 40000, "loss": 0.0842, "lr": 3.0445915933591658e-05, "epoch": 0.7788768419384775, "percentage": 43.01, "elapsed_time": "14:07:22", "remaining_time": "18:42:41", "throughput": 552.69, "total_tokens": 28100256} {"current_steps": 17210, "total_steps": 40000, "loss": 0.0958, "lr": 3.0436333801182114e-05, "epoch": 0.7791031938251205, "percentage": 43.03, "elapsed_time": "14:07:25", "remaining_time": "18:42:11", "throughput": 552.81, "total_tokens": 28108384} {"current_steps": 17215, "total_steps": 40000, "loss": 0.1264, "lr": 3.0426750830421596e-05, "epoch": 0.7793295457117635, "percentage": 43.04, "elapsed_time": "14:07:29", "remaining_time": "18:41:41", "throughput": 552.94, "total_tokens": 28116352} {"current_steps": 17220, "total_steps": 40000, "loss": 0.1373, "lr": 3.0417167022787897e-05, "epoch": 0.7795558975984065, "percentage": 43.05, "elapsed_time": "14:07:32", "remaining_time": "18:41:11", "throughput": 553.07, "total_tokens": 28125120} {"current_steps": 17225, "total_steps": 40000, "loss": 0.1087, "lr": 3.0407582379758966e-05, "epoch": 0.7797822494850495, "percentage": 43.06, "elapsed_time": "14:07:35", "remaining_time": "18:40:41", "throughput": 553.2, "total_tokens": 28133280} {"current_steps": 17230, "total_steps": 40000, "loss": 0.1253, "lr": 3.039799690281287e-05, "epoch": 0.7800086013716925, "percentage": 43.08, "elapsed_time": "14:07:38", "remaining_time": "18:40:11", "throughput": 553.33, "total_tokens": 28141632} {"current_steps": 17235, "total_steps": 40000, "loss": 0.1344, "lr": 3.0388410593427823e-05, "epoch": 0.7802349532583354, "percentage": 43.09, "elapsed_time": "14:07:41", "remaining_time": "18:39:41", "throughput": 553.46, "total_tokens": 28150016} {"current_steps": 17240, "total_steps": 40000, "loss": 0.108, "lr": 3.0378823453082146e-05, "epoch": 0.7804613051449784, "percentage": 43.1, "elapsed_time": "14:07:45", "remaining_time": "18:39:11", "throughput": 553.6, "total_tokens": 28158784} {"current_steps": 17245, "total_steps": 40000, "loss": 0.1688, "lr": 3.03692354832543e-05, "epoch": 0.7806876570316214, "percentage": 43.11, "elapsed_time": "14:07:48", "remaining_time": "18:38:41", "throughput": 553.72, "total_tokens": 28166656} {"current_steps": 17250, "total_steps": 40000, "loss": 0.1282, "lr": 3.0359646685422865e-05, "epoch": 0.7809140089182643, "percentage": 43.12, "elapsed_time": "14:07:51", "remaining_time": "18:38:11", "throughput": 553.83, "total_tokens": 28174016} {"current_steps": 17255, "total_steps": 40000, "loss": 0.1484, "lr": 3.035005706106656e-05, "epoch": 0.7811403608049073, "percentage": 43.14, "elapsed_time": "14:07:54", "remaining_time": "18:37:41", "throughput": 553.95, "total_tokens": 28182080} {"current_steps": 17260, "total_steps": 40000, "loss": 0.1254, "lr": 3.034046661166422e-05, "epoch": 0.7813667126915503, "percentage": 43.15, "elapsed_time": "14:07:57", "remaining_time": "18:37:11", "throughput": 554.08, "total_tokens": 28190272} {"current_steps": 17265, "total_steps": 40000, "loss": 0.1085, "lr": 3.033087533869482e-05, "epoch": 0.7815930645781932, "percentage": 43.16, "elapsed_time": "14:08:00", "remaining_time": "18:36:41", "throughput": 554.2, "total_tokens": 28198176} {"current_steps": 17270, "total_steps": 40000, "loss": 0.1064, "lr": 3.0321283243637444e-05, "epoch": 0.7818194164648362, "percentage": 43.18, "elapsed_time": "14:08:03", "remaining_time": "18:36:11", "throughput": 554.32, "total_tokens": 28205920} {"current_steps": 17275, "total_steps": 40000, "loss": 0.1406, "lr": 3.0311690327971326e-05, "epoch": 0.7820457683514792, "percentage": 43.19, "elapsed_time": "14:08:07", "remaining_time": "18:35:41", "throughput": 554.44, "total_tokens": 28213568} {"current_steps": 17280, "total_steps": 40000, "loss": 0.143, "lr": 3.030209659317581e-05, "epoch": 0.7822721202381222, "percentage": 43.2, "elapsed_time": "14:08:10", "remaining_time": "18:35:11", "throughput": 554.56, "total_tokens": 28221664} {"current_steps": 17285, "total_steps": 40000, "loss": 0.1386, "lr": 3.0292502040730362e-05, "epoch": 0.7824984721247652, "percentage": 43.21, "elapsed_time": "14:08:13", "remaining_time": "18:34:41", "throughput": 554.7, "total_tokens": 28230624} {"current_steps": 17290, "total_steps": 40000, "loss": 0.0846, "lr": 3.0282906672114597e-05, "epoch": 0.7827248240114081, "percentage": 43.23, "elapsed_time": "14:08:16", "remaining_time": "18:34:11", "throughput": 554.82, "total_tokens": 28238432} {"current_steps": 17295, "total_steps": 40000, "loss": 0.0683, "lr": 3.027331048880823e-05, "epoch": 0.7829511758980511, "percentage": 43.24, "elapsed_time": "14:08:19", "remaining_time": "18:33:41", "throughput": 554.95, "total_tokens": 28246656} {"current_steps": 17300, "total_steps": 40000, "loss": 0.0862, "lr": 3.0263713492291123e-05, "epoch": 0.7831775277846941, "percentage": 43.25, "elapsed_time": "14:08:22", "remaining_time": "18:33:11", "throughput": 555.06, "total_tokens": 28254368} {"current_steps": 17305, "total_steps": 40000, "loss": 0.1342, "lr": 3.0254115684043242e-05, "epoch": 0.7834038796713371, "percentage": 43.26, "elapsed_time": "14:08:26", "remaining_time": "18:32:41", "throughput": 555.19, "total_tokens": 28262304} {"current_steps": 17310, "total_steps": 40000, "loss": 0.1354, "lr": 3.024451706554469e-05, "epoch": 0.7836302315579801, "percentage": 43.28, "elapsed_time": "14:08:29", "remaining_time": "18:32:12", "throughput": 555.32, "total_tokens": 28271136} {"current_steps": 17315, "total_steps": 40000, "loss": 0.081, "lr": 3.0234917638275705e-05, "epoch": 0.7838565834446231, "percentage": 43.29, "elapsed_time": "14:08:32", "remaining_time": "18:31:42", "throughput": 555.43, "total_tokens": 28278592} {"current_steps": 17320, "total_steps": 40000, "loss": 0.1157, "lr": 3.0225317403716635e-05, "epoch": 0.7840829353312659, "percentage": 43.3, "elapsed_time": "14:08:35", "remaining_time": "18:31:12", "throughput": 555.56, "total_tokens": 28286784} {"current_steps": 17325, "total_steps": 40000, "loss": 0.0801, "lr": 3.0215716363347956e-05, "epoch": 0.7843092872179089, "percentage": 43.31, "elapsed_time": "14:08:39", "remaining_time": "18:30:43", "throughput": 555.7, "total_tokens": 28295904} {"current_steps": 17330, "total_steps": 40000, "loss": 0.1529, "lr": 3.0206114518650275e-05, "epoch": 0.7845356391045519, "percentage": 43.33, "elapsed_time": "14:08:42", "remaining_time": "18:30:13", "throughput": 555.85, "total_tokens": 28305312} {"current_steps": 17335, "total_steps": 40000, "loss": 0.1323, "lr": 3.0196511871104304e-05, "epoch": 0.7847619909911949, "percentage": 43.34, "elapsed_time": "14:08:45", "remaining_time": "18:29:43", "throughput": 555.97, "total_tokens": 28313344} {"current_steps": 17340, "total_steps": 40000, "loss": 0.1602, "lr": 3.01869084221909e-05, "epoch": 0.7849883428778379, "percentage": 43.35, "elapsed_time": "14:08:48", "remaining_time": "18:29:13", "throughput": 556.09, "total_tokens": 28321024} {"current_steps": 17345, "total_steps": 40000, "loss": 0.1769, "lr": 3.0177304173391037e-05, "epoch": 0.7852146947644809, "percentage": 43.36, "elapsed_time": "14:08:51", "remaining_time": "18:28:44", "throughput": 556.22, "total_tokens": 28329248} {"current_steps": 17350, "total_steps": 40000, "loss": 0.11, "lr": 3.01676991261858e-05, "epoch": 0.7854410466511238, "percentage": 43.38, "elapsed_time": "14:08:55", "remaining_time": "18:28:14", "throughput": 556.34, "total_tokens": 28337216} {"current_steps": 17355, "total_steps": 40000, "loss": 0.1566, "lr": 3.015809328205642e-05, "epoch": 0.7856673985377668, "percentage": 43.39, "elapsed_time": "14:08:58", "remaining_time": "18:27:44", "throughput": 556.46, "total_tokens": 28345248} {"current_steps": 17360, "total_steps": 40000, "loss": 0.1294, "lr": 3.0148486642484248e-05, "epoch": 0.7858937504244098, "percentage": 43.4, "elapsed_time": "14:09:01", "remaining_time": "18:27:15", "throughput": 556.59, "total_tokens": 28353312} {"current_steps": 17365, "total_steps": 40000, "loss": 0.1181, "lr": 3.0138879208950722e-05, "epoch": 0.7861201023110528, "percentage": 43.41, "elapsed_time": "14:09:04", "remaining_time": "18:26:45", "throughput": 556.72, "total_tokens": 28361792} {"current_steps": 17370, "total_steps": 40000, "loss": 0.206, "lr": 3.012927098293744e-05, "epoch": 0.7863464541976958, "percentage": 43.43, "elapsed_time": "14:09:07", "remaining_time": "18:26:15", "throughput": 556.85, "total_tokens": 28370048} {"current_steps": 17375, "total_steps": 40000, "loss": 0.0959, "lr": 3.0119661965926123e-05, "epoch": 0.7865728060843387, "percentage": 43.44, "elapsed_time": "14:09:10", "remaining_time": "18:25:46", "throughput": 556.97, "total_tokens": 28377952} {"current_steps": 17380, "total_steps": 40000, "loss": 0.1039, "lr": 3.0110052159398587e-05, "epoch": 0.7867991579709817, "percentage": 43.45, "elapsed_time": "14:09:14", "remaining_time": "18:25:16", "throughput": 557.1, "total_tokens": 28386592} {"current_steps": 17385, "total_steps": 40000, "loss": 0.1202, "lr": 3.0100441564836802e-05, "epoch": 0.7870255098576246, "percentage": 43.46, "elapsed_time": "14:09:17", "remaining_time": "18:24:47", "throughput": 557.23, "total_tokens": 28395040} {"current_steps": 17390, "total_steps": 40000, "loss": 0.1846, "lr": 3.0090830183722817e-05, "epoch": 0.7872518617442676, "percentage": 43.48, "elapsed_time": "14:09:20", "remaining_time": "18:24:17", "throughput": 557.37, "total_tokens": 28403968} {"current_steps": 17395, "total_steps": 40000, "loss": 0.108, "lr": 3.0081218017538852e-05, "epoch": 0.7874782136309106, "percentage": 43.49, "elapsed_time": "14:09:23", "remaining_time": "18:23:48", "throughput": 557.49, "total_tokens": 28411968} {"current_steps": 17400, "total_steps": 40000, "loss": 0.126, "lr": 3.0071605067767212e-05, "epoch": 0.7877045655175536, "percentage": 43.5, "elapsed_time": "14:09:27", "remaining_time": "18:23:18", "throughput": 557.62, "total_tokens": 28420128} {"current_steps": 17400, "total_steps": 40000, "eval_loss": 0.12887655198574066, "epoch": 0.7877045655175536, "percentage": 43.5, "elapsed_time": "14:17:09", "remaining_time": "18:33:19", "throughput": 552.6, "total_tokens": 28420128} {"current_steps": 17405, "total_steps": 40000, "loss": 0.1428, "lr": 3.006199133589034e-05, "epoch": 0.7879309174041965, "percentage": 43.51, "elapsed_time": "14:17:15", "remaining_time": "18:32:52", "throughput": 552.7, "total_tokens": 28428288} {"current_steps": 17410, "total_steps": 40000, "loss": 0.0757, "lr": 3.005237682339079e-05, "epoch": 0.7881572692908395, "percentage": 43.53, "elapsed_time": "14:17:18", "remaining_time": "18:32:23", "throughput": 552.82, "total_tokens": 28436320} {"current_steps": 17415, "total_steps": 40000, "loss": 0.1124, "lr": 3.0042761531751228e-05, "epoch": 0.7883836211774825, "percentage": 43.54, "elapsed_time": "14:17:21", "remaining_time": "18:31:53", "throughput": 552.96, "total_tokens": 28445312} {"current_steps": 17420, "total_steps": 40000, "loss": 0.1524, "lr": 3.0033145462454482e-05, "epoch": 0.7886099730641255, "percentage": 43.55, "elapsed_time": "14:17:25", "remaining_time": "18:31:23", "throughput": 553.08, "total_tokens": 28453504} {"current_steps": 17425, "total_steps": 40000, "loss": 0.1291, "lr": 3.002352861698345e-05, "epoch": 0.7888363249507685, "percentage": 43.56, "elapsed_time": "14:17:28", "remaining_time": "18:30:53", "throughput": 553.21, "total_tokens": 28461632} {"current_steps": 17430, "total_steps": 40000, "loss": 0.0943, "lr": 3.0013910996821178e-05, "epoch": 0.7890626768374115, "percentage": 43.58, "elapsed_time": "14:17:31", "remaining_time": "18:30:24", "throughput": 553.35, "total_tokens": 28470464} {"current_steps": 17435, "total_steps": 40000, "loss": 0.0801, "lr": 3.0004292603450817e-05, "epoch": 0.7892890287240544, "percentage": 43.59, "elapsed_time": "14:17:34", "remaining_time": "18:29:54", "throughput": 553.47, "total_tokens": 28478528} {"current_steps": 17440, "total_steps": 40000, "loss": 0.1679, "lr": 2.9994673438355653e-05, "epoch": 0.7895153806106974, "percentage": 43.6, "elapsed_time": "14:17:37", "remaining_time": "18:29:24", "throughput": 553.6, "total_tokens": 28486880} {"current_steps": 17445, "total_steps": 40000, "loss": 0.1586, "lr": 2.9985053503019078e-05, "epoch": 0.7897417324973404, "percentage": 43.61, "elapsed_time": "14:17:41", "remaining_time": "18:28:55", "throughput": 553.72, "total_tokens": 28495072} {"current_steps": 17450, "total_steps": 40000, "loss": 0.1307, "lr": 2.99754327989246e-05, "epoch": 0.7899680843839834, "percentage": 43.62, "elapsed_time": "14:17:44", "remaining_time": "18:28:25", "throughput": 553.86, "total_tokens": 28504000} {"current_steps": 17455, "total_steps": 40000, "loss": 0.1702, "lr": 2.9965811327555864e-05, "epoch": 0.7901944362706264, "percentage": 43.64, "elapsed_time": "14:17:47", "remaining_time": "18:27:55", "throughput": 553.99, "total_tokens": 28512480} {"current_steps": 17460, "total_steps": 40000, "loss": 0.1149, "lr": 2.995618909039662e-05, "epoch": 0.7904207881572692, "percentage": 43.65, "elapsed_time": "14:17:50", "remaining_time": "18:27:26", "throughput": 554.11, "total_tokens": 28520352} {"current_steps": 17465, "total_steps": 40000, "loss": 0.1092, "lr": 2.9946566088930727e-05, "epoch": 0.7906471400439122, "percentage": 43.66, "elapsed_time": "14:17:53", "remaining_time": "18:26:56", "throughput": 554.23, "total_tokens": 28528384} {"current_steps": 17470, "total_steps": 40000, "loss": 0.1363, "lr": 2.9936942324642192e-05, "epoch": 0.7908734919305552, "percentage": 43.68, "elapsed_time": "14:17:57", "remaining_time": "18:26:26", "throughput": 554.35, "total_tokens": 28536384} {"current_steps": 17475, "total_steps": 40000, "loss": 0.1041, "lr": 2.9927317799015097e-05, "epoch": 0.7910998438171982, "percentage": 43.69, "elapsed_time": "14:18:00", "remaining_time": "18:25:57", "throughput": 554.47, "total_tokens": 28544320} {"current_steps": 17480, "total_steps": 40000, "loss": 0.0828, "lr": 2.9917692513533685e-05, "epoch": 0.7913261957038412, "percentage": 43.7, "elapsed_time": "14:18:03", "remaining_time": "18:25:27", "throughput": 554.59, "total_tokens": 28552288} {"current_steps": 17485, "total_steps": 40000, "loss": 0.1142, "lr": 2.990806646968229e-05, "epoch": 0.7915525475904842, "percentage": 43.71, "elapsed_time": "14:18:06", "remaining_time": "18:24:57", "throughput": 554.72, "total_tokens": 28560768} {"current_steps": 17490, "total_steps": 40000, "loss": 0.1238, "lr": 2.989843966894536e-05, "epoch": 0.7917788994771271, "percentage": 43.73, "elapsed_time": "14:18:09", "remaining_time": "18:24:28", "throughput": 554.84, "total_tokens": 28568736} {"current_steps": 17495, "total_steps": 40000, "loss": 0.1041, "lr": 2.9888812112807472e-05, "epoch": 0.7920052513637701, "percentage": 43.74, "elapsed_time": "14:18:12", "remaining_time": "18:23:58", "throughput": 554.97, "total_tokens": 28577216} {"current_steps": 17500, "total_steps": 40000, "loss": 0.0705, "lr": 2.987918380275333e-05, "epoch": 0.7922316032504131, "percentage": 43.75, "elapsed_time": "14:18:16", "remaining_time": "18:23:29", "throughput": 555.11, "total_tokens": 28586144} {"current_steps": 17505, "total_steps": 40000, "loss": 0.1216, "lr": 2.9869554740267724e-05, "epoch": 0.7924579551370561, "percentage": 43.76, "elapsed_time": "14:18:19", "remaining_time": "18:22:59", "throughput": 555.23, "total_tokens": 28593824} {"current_steps": 17510, "total_steps": 40000, "loss": 0.163, "lr": 2.9859924926835585e-05, "epoch": 0.7926843070236991, "percentage": 43.77, "elapsed_time": "14:18:22", "remaining_time": "18:22:30", "throughput": 555.37, "total_tokens": 28602848} {"current_steps": 17515, "total_steps": 40000, "loss": 0.1171, "lr": 2.9850294363941944e-05, "epoch": 0.7929106589103421, "percentage": 43.79, "elapsed_time": "14:18:26", "remaining_time": "18:22:01", "throughput": 555.5, "total_tokens": 28611872} {"current_steps": 17520, "total_steps": 40000, "loss": 0.1177, "lr": 2.9840663053071967e-05, "epoch": 0.793137010796985, "percentage": 43.8, "elapsed_time": "14:18:29", "remaining_time": "18:21:31", "throughput": 555.63, "total_tokens": 28620160} {"current_steps": 17525, "total_steps": 40000, "loss": 0.1121, "lr": 2.983103099571091e-05, "epoch": 0.793363362683628, "percentage": 43.81, "elapsed_time": "14:18:32", "remaining_time": "18:21:02", "throughput": 555.75, "total_tokens": 28628128} {"current_steps": 17530, "total_steps": 40000, "loss": 0.1403, "lr": 2.9821398193344164e-05, "epoch": 0.7935897145702709, "percentage": 43.82, "elapsed_time": "14:18:35", "remaining_time": "18:20:33", "throughput": 555.89, "total_tokens": 28637344} {"current_steps": 17535, "total_steps": 40000, "loss": 0.1519, "lr": 2.9811764647457226e-05, "epoch": 0.7938160664569139, "percentage": 43.84, "elapsed_time": "14:18:39", "remaining_time": "18:20:03", "throughput": 556.02, "total_tokens": 28645472} {"current_steps": 17540, "total_steps": 40000, "loss": 0.1901, "lr": 2.9802130359535714e-05, "epoch": 0.7940424183435569, "percentage": 43.85, "elapsed_time": "14:18:42", "remaining_time": "18:19:34", "throughput": 556.15, "total_tokens": 28654080} {"current_steps": 17545, "total_steps": 40000, "loss": 0.1385, "lr": 2.979249533106535e-05, "epoch": 0.7942687702301998, "percentage": 43.86, "elapsed_time": "14:18:45", "remaining_time": "18:19:04", "throughput": 556.28, "total_tokens": 28662400} {"current_steps": 17550, "total_steps": 40000, "loss": 0.1139, "lr": 2.9782859563531986e-05, "epoch": 0.7944951221168428, "percentage": 43.88, "elapsed_time": "14:18:48", "remaining_time": "18:18:35", "throughput": 556.4, "total_tokens": 28670752} {"current_steps": 17555, "total_steps": 40000, "loss": 0.1126, "lr": 2.977322305842156e-05, "epoch": 0.7947214740034858, "percentage": 43.89, "elapsed_time": "14:18:51", "remaining_time": "18:18:06", "throughput": 556.54, "total_tokens": 28679488} {"current_steps": 17560, "total_steps": 40000, "loss": 0.1238, "lr": 2.9763585817220162e-05, "epoch": 0.7949478258901288, "percentage": 43.9, "elapsed_time": "14:18:55", "remaining_time": "18:17:36", "throughput": 556.65, "total_tokens": 28687232} {"current_steps": 17565, "total_steps": 40000, "loss": 0.0948, "lr": 2.975394784141397e-05, "epoch": 0.7951741777767718, "percentage": 43.91, "elapsed_time": "14:18:58", "remaining_time": "18:17:07", "throughput": 556.8, "total_tokens": 28696544} {"current_steps": 17570, "total_steps": 40000, "loss": 0.137, "lr": 2.974430913248928e-05, "epoch": 0.7954005296634148, "percentage": 43.92, "elapsed_time": "14:19:01", "remaining_time": "18:16:38", "throughput": 556.92, "total_tokens": 28704672} {"current_steps": 17575, "total_steps": 40000, "loss": 0.0985, "lr": 2.9734669691932497e-05, "epoch": 0.7956268815500577, "percentage": 43.94, "elapsed_time": "14:19:04", "remaining_time": "18:16:09", "throughput": 557.05, "total_tokens": 28712768} {"current_steps": 17580, "total_steps": 40000, "loss": 0.1082, "lr": 2.9725029521230147e-05, "epoch": 0.7958532334367007, "percentage": 43.95, "elapsed_time": "14:19:07", "remaining_time": "18:15:39", "throughput": 557.17, "total_tokens": 28720832} {"current_steps": 17585, "total_steps": 40000, "loss": 0.0905, "lr": 2.9715388621868873e-05, "epoch": 0.7960795853233437, "percentage": 43.96, "elapsed_time": "14:19:11", "remaining_time": "18:15:10", "throughput": 557.29, "total_tokens": 28728992} {"current_steps": 17590, "total_steps": 40000, "loss": 0.1755, "lr": 2.970574699533541e-05, "epoch": 0.7963059372099867, "percentage": 43.97, "elapsed_time": "14:19:14", "remaining_time": "18:14:41", "throughput": 557.42, "total_tokens": 28737216} {"current_steps": 17595, "total_steps": 40000, "loss": 0.1583, "lr": 2.969610464311662e-05, "epoch": 0.7965322890966297, "percentage": 43.99, "elapsed_time": "14:19:17", "remaining_time": "18:14:11", "throughput": 557.53, "total_tokens": 28745024} {"current_steps": 17600, "total_steps": 40000, "loss": 0.1326, "lr": 2.9686461566699487e-05, "epoch": 0.7967586409832726, "percentage": 44.0, "elapsed_time": "14:19:20", "remaining_time": "18:13:42", "throughput": 557.66, "total_tokens": 28753152} {"current_steps": 17600, "total_steps": 40000, "eval_loss": 0.12778936326503754, "epoch": 0.7967586409832726, "percentage": 44.0, "elapsed_time": "14:27:03", "remaining_time": "18:23:31", "throughput": 552.7, "total_tokens": 28753152} {"current_steps": 17605, "total_steps": 40000, "loss": 0.1185, "lr": 2.9676817767571086e-05, "epoch": 0.7969849928699155, "percentage": 44.01, "elapsed_time": "14:27:07", "remaining_time": "18:23:03", "throughput": 552.81, "total_tokens": 28761120} {"current_steps": 17610, "total_steps": 40000, "loss": 0.162, "lr": 2.966717324721861e-05, "epoch": 0.7972113447565585, "percentage": 44.02, "elapsed_time": "14:27:10", "remaining_time": "18:22:33", "throughput": 552.92, "total_tokens": 28768768} {"current_steps": 17615, "total_steps": 40000, "loss": 0.1599, "lr": 2.9657528007129366e-05, "epoch": 0.7974376966432015, "percentage": 44.04, "elapsed_time": "14:27:14", "remaining_time": "18:22:04", "throughput": 553.06, "total_tokens": 28778080} {"current_steps": 17620, "total_steps": 40000, "loss": 0.1427, "lr": 2.9647882048790777e-05, "epoch": 0.7976640485298445, "percentage": 44.05, "elapsed_time": "14:27:17", "remaining_time": "18:21:34", "throughput": 553.18, "total_tokens": 28785888} {"current_steps": 17625, "total_steps": 40000, "loss": 0.0817, "lr": 2.963823537369037e-05, "epoch": 0.7978904004164875, "percentage": 44.06, "elapsed_time": "14:27:20", "remaining_time": "18:21:05", "throughput": 553.3, "total_tokens": 28794176} {"current_steps": 17630, "total_steps": 40000, "loss": 0.1145, "lr": 2.9628587983315775e-05, "epoch": 0.7981167523031304, "percentage": 44.07, "elapsed_time": "14:27:23", "remaining_time": "18:20:35", "throughput": 553.42, "total_tokens": 28801760} {"current_steps": 17635, "total_steps": 40000, "loss": 0.1057, "lr": 2.9618939879154746e-05, "epoch": 0.7983431041897734, "percentage": 44.09, "elapsed_time": "14:27:26", "remaining_time": "18:20:06", "throughput": 553.56, "total_tokens": 28810944} {"current_steps": 17640, "total_steps": 40000, "loss": 0.1989, "lr": 2.9609291062695143e-05, "epoch": 0.7985694560764164, "percentage": 44.1, "elapsed_time": "14:27:30", "remaining_time": "18:19:37", "throughput": 553.68, "total_tokens": 28818976} {"current_steps": 17645, "total_steps": 40000, "loss": 0.1477, "lr": 2.9599641535424938e-05, "epoch": 0.7987958079630594, "percentage": 44.11, "elapsed_time": "14:27:33", "remaining_time": "18:19:07", "throughput": 553.8, "total_tokens": 28826784} {"current_steps": 17650, "total_steps": 40000, "loss": 0.0933, "lr": 2.9589991298832202e-05, "epoch": 0.7990221598497024, "percentage": 44.12, "elapsed_time": "14:27:36", "remaining_time": "18:18:38", "throughput": 553.92, "total_tokens": 28835232} {"current_steps": 17655, "total_steps": 40000, "loss": 0.139, "lr": 2.958034035440513e-05, "epoch": 0.7992485117363454, "percentage": 44.14, "elapsed_time": "14:27:39", "remaining_time": "18:18:08", "throughput": 554.03, "total_tokens": 28842624} {"current_steps": 17660, "total_steps": 40000, "loss": 0.1335, "lr": 2.957068870363201e-05, "epoch": 0.7994748636229883, "percentage": 44.15, "elapsed_time": "14:27:42", "remaining_time": "18:17:39", "throughput": 554.16, "total_tokens": 28850912} {"current_steps": 17665, "total_steps": 40000, "loss": 0.0965, "lr": 2.956103634800126e-05, "epoch": 0.7997012155096312, "percentage": 44.16, "elapsed_time": "14:27:45", "remaining_time": "18:17:10", "throughput": 554.28, "total_tokens": 28858816} {"current_steps": 17670, "total_steps": 40000, "loss": 0.1169, "lr": 2.9551383289001384e-05, "epoch": 0.7999275673962742, "percentage": 44.17, "elapsed_time": "14:27:48", "remaining_time": "18:16:40", "throughput": 554.39, "total_tokens": 28866336} {"current_steps": 17675, "total_steps": 40000, "loss": 0.104, "lr": 2.9541729528121005e-05, "epoch": 0.8001539192829172, "percentage": 44.19, "elapsed_time": "14:27:52", "remaining_time": "18:16:11", "throughput": 554.51, "total_tokens": 28874624} {"current_steps": 17680, "total_steps": 40000, "loss": 0.1268, "lr": 2.9532075066848856e-05, "epoch": 0.8003802711695602, "percentage": 44.2, "elapsed_time": "14:27:55", "remaining_time": "18:15:41", "throughput": 554.63, "total_tokens": 28882560} {"current_steps": 17685, "total_steps": 40000, "loss": 0.1346, "lr": 2.9522419906673786e-05, "epoch": 0.8006066230562032, "percentage": 44.21, "elapsed_time": "14:27:58", "remaining_time": "18:15:12", "throughput": 554.75, "total_tokens": 28890432} {"current_steps": 17690, "total_steps": 40000, "loss": 0.1263, "lr": 2.951276404908474e-05, "epoch": 0.8008329749428461, "percentage": 44.22, "elapsed_time": "14:28:01", "remaining_time": "18:14:43", "throughput": 554.88, "total_tokens": 28898976} {"current_steps": 17695, "total_steps": 40000, "loss": 0.1348, "lr": 2.9503107495570752e-05, "epoch": 0.8010593268294891, "percentage": 44.24, "elapsed_time": "14:28:04", "remaining_time": "18:14:14", "throughput": 554.99, "total_tokens": 28906432} {"current_steps": 17700, "total_steps": 40000, "loss": 0.1449, "lr": 2.9493450247621003e-05, "epoch": 0.8012856787161321, "percentage": 44.25, "elapsed_time": "14:28:07", "remaining_time": "18:13:44", "throughput": 555.12, "total_tokens": 28914752} {"current_steps": 17705, "total_steps": 40000, "loss": 0.1279, "lr": 2.948379230672476e-05, "epoch": 0.8015120306027751, "percentage": 44.26, "elapsed_time": "14:28:11", "remaining_time": "18:13:15", "throughput": 555.24, "total_tokens": 28923008} {"current_steps": 17710, "total_steps": 40000, "loss": 0.1312, "lr": 2.9474133674371396e-05, "epoch": 0.8017383824894181, "percentage": 44.27, "elapsed_time": "14:28:14", "remaining_time": "18:12:46", "throughput": 555.38, "total_tokens": 28931936} {"current_steps": 17715, "total_steps": 40000, "loss": 0.0802, "lr": 2.9464474352050387e-05, "epoch": 0.801964734376061, "percentage": 44.29, "elapsed_time": "14:28:17", "remaining_time": "18:12:17", "throughput": 555.5, "total_tokens": 28940224} {"current_steps": 17720, "total_steps": 40000, "loss": 0.1173, "lr": 2.9454814341251336e-05, "epoch": 0.802191086262704, "percentage": 44.3, "elapsed_time": "14:28:20", "remaining_time": "18:11:48", "throughput": 555.62, "total_tokens": 28948288} {"current_steps": 17725, "total_steps": 40000, "loss": 0.0984, "lr": 2.9445153643463942e-05, "epoch": 0.802417438149347, "percentage": 44.31, "elapsed_time": "14:28:23", "remaining_time": "18:11:18", "throughput": 555.74, "total_tokens": 28956352} {"current_steps": 17730, "total_steps": 40000, "loss": 0.0945, "lr": 2.943549226017798e-05, "epoch": 0.80264379003599, "percentage": 44.32, "elapsed_time": "14:28:27", "remaining_time": "18:10:49", "throughput": 555.86, "total_tokens": 28964416} {"current_steps": 17735, "total_steps": 40000, "loss": 0.1146, "lr": 2.942583019288337e-05, "epoch": 0.802870141922633, "percentage": 44.34, "elapsed_time": "14:28:30", "remaining_time": "18:10:20", "throughput": 555.99, "total_tokens": 28972896} {"current_steps": 17740, "total_steps": 40000, "loss": 0.1402, "lr": 2.9416167443070132e-05, "epoch": 0.803096493809276, "percentage": 44.35, "elapsed_time": "14:28:33", "remaining_time": "18:09:51", "throughput": 556.12, "total_tokens": 28981248} {"current_steps": 17745, "total_steps": 40000, "loss": 0.1588, "lr": 2.9406504012228375e-05, "epoch": 0.8033228456959188, "percentage": 44.36, "elapsed_time": "14:28:36", "remaining_time": "18:09:22", "throughput": 556.25, "total_tokens": 28989856} {"current_steps": 17750, "total_steps": 40000, "loss": 0.1457, "lr": 2.939683990184832e-05, "epoch": 0.8035491975825618, "percentage": 44.38, "elapsed_time": "14:28:39", "remaining_time": "18:08:53", "throughput": 556.37, "total_tokens": 28997760} {"current_steps": 17755, "total_steps": 40000, "loss": 0.1275, "lr": 2.93871751134203e-05, "epoch": 0.8037755494692048, "percentage": 44.39, "elapsed_time": "14:28:43", "remaining_time": "18:08:24", "throughput": 556.49, "total_tokens": 29005984} {"current_steps": 17760, "total_steps": 40000, "loss": 0.122, "lr": 2.9377509648434752e-05, "epoch": 0.8040019013558478, "percentage": 44.4, "elapsed_time": "14:28:46", "remaining_time": "18:07:55", "throughput": 556.62, "total_tokens": 29014528} {"current_steps": 17765, "total_steps": 40000, "loss": 0.1154, "lr": 2.9367843508382203e-05, "epoch": 0.8042282532424908, "percentage": 44.41, "elapsed_time": "14:28:49", "remaining_time": "18:07:26", "throughput": 556.73, "total_tokens": 29022208} {"current_steps": 17770, "total_steps": 40000, "loss": 0.177, "lr": 2.9358176694753293e-05, "epoch": 0.8044546051291338, "percentage": 44.42, "elapsed_time": "14:28:52", "remaining_time": "18:06:57", "throughput": 556.86, "total_tokens": 29030400} {"current_steps": 17775, "total_steps": 40000, "loss": 0.0946, "lr": 2.9348509209038766e-05, "epoch": 0.8046809570157767, "percentage": 44.44, "elapsed_time": "14:28:55", "remaining_time": "18:06:28", "throughput": 556.99, "total_tokens": 29039072} {"current_steps": 17780, "total_steps": 40000, "loss": 0.1443, "lr": 2.933884105272947e-05, "epoch": 0.8049073089024197, "percentage": 44.45, "elapsed_time": "14:28:59", "remaining_time": "18:05:59", "throughput": 557.11, "total_tokens": 29047424} {"current_steps": 17785, "total_steps": 40000, "loss": 0.1207, "lr": 2.9329172227316366e-05, "epoch": 0.8051336607890627, "percentage": 44.46, "elapsed_time": "14:29:02", "remaining_time": "18:05:30", "throughput": 557.23, "total_tokens": 29055296} {"current_steps": 17790, "total_steps": 40000, "loss": 0.1032, "lr": 2.93195027342905e-05, "epoch": 0.8053600126757057, "percentage": 44.47, "elapsed_time": "14:29:05", "remaining_time": "18:05:01", "throughput": 557.35, "total_tokens": 29063360} {"current_steps": 17795, "total_steps": 40000, "loss": 0.1369, "lr": 2.9309832575143024e-05, "epoch": 0.8055863645623487, "percentage": 44.49, "elapsed_time": "14:29:08", "remaining_time": "18:04:32", "throughput": 557.47, "total_tokens": 29071424} {"current_steps": 17800, "total_steps": 40000, "loss": 0.0804, "lr": 2.930016175136521e-05, "epoch": 0.8058127164489916, "percentage": 44.5, "elapsed_time": "14:29:11", "remaining_time": "18:04:03", "throughput": 557.59, "total_tokens": 29079392} {"current_steps": 17800, "total_steps": 40000, "eval_loss": 0.12810851633548737, "epoch": 0.8058127164489916, "percentage": 44.5, "elapsed_time": "14:36:54", "remaining_time": "18:13:40", "throughput": 552.69, "total_tokens": 29079392} {"current_steps": 17805, "total_steps": 40000, "loss": 0.1392, "lr": 2.9290490264448412e-05, "epoch": 0.8060390683356345, "percentage": 44.51, "elapsed_time": "14:36:58", "remaining_time": "18:13:11", "throughput": 552.8, "total_tokens": 29087328} {"current_steps": 17810, "total_steps": 40000, "loss": 0.1301, "lr": 2.9280818115884094e-05, "epoch": 0.8062654202222775, "percentage": 44.52, "elapsed_time": "14:37:01", "remaining_time": "18:12:42", "throughput": 552.91, "total_tokens": 29095168} {"current_steps": 17815, "total_steps": 40000, "loss": 0.1415, "lr": 2.9271145307163828e-05, "epoch": 0.8064917721089205, "percentage": 44.54, "elapsed_time": "14:37:04", "remaining_time": "18:12:13", "throughput": 553.03, "total_tokens": 29102976} {"current_steps": 17820, "total_steps": 40000, "loss": 0.1694, "lr": 2.9261471839779287e-05, "epoch": 0.8067181239955635, "percentage": 44.55, "elapsed_time": "14:37:07", "remaining_time": "18:11:44", "throughput": 553.14, "total_tokens": 29110688} {"current_steps": 17825, "total_steps": 40000, "loss": 0.1317, "lr": 2.925179771522223e-05, "epoch": 0.8069444758822065, "percentage": 44.56, "elapsed_time": "14:37:10", "remaining_time": "18:11:14", "throughput": 553.27, "total_tokens": 29119232} {"current_steps": 17830, "total_steps": 40000, "loss": 0.1345, "lr": 2.9242122934984535e-05, "epoch": 0.8071708277688494, "percentage": 44.57, "elapsed_time": "14:37:14", "remaining_time": "18:10:45", "throughput": 553.4, "total_tokens": 29127488} {"current_steps": 17835, "total_steps": 40000, "loss": 0.084, "lr": 2.9232447500558176e-05, "epoch": 0.8073971796554924, "percentage": 44.59, "elapsed_time": "14:37:17", "remaining_time": "18:10:16", "throughput": 553.52, "total_tokens": 29136000} {"current_steps": 17840, "total_steps": 40000, "loss": 0.1648, "lr": 2.9222771413435225e-05, "epoch": 0.8076235315421354, "percentage": 44.6, "elapsed_time": "14:37:20", "remaining_time": "18:09:47", "throughput": 553.66, "total_tokens": 29144896} {"current_steps": 17845, "total_steps": 40000, "loss": 0.1581, "lr": 2.9213094675107848e-05, "epoch": 0.8078498834287784, "percentage": 44.61, "elapsed_time": "14:37:23", "remaining_time": "18:09:18", "throughput": 553.78, "total_tokens": 29153248} {"current_steps": 17850, "total_steps": 40000, "loss": 0.135, "lr": 2.9203417287068335e-05, "epoch": 0.8080762353154214, "percentage": 44.62, "elapsed_time": "14:37:27", "remaining_time": "18:08:49", "throughput": 553.92, "total_tokens": 29162144} {"current_steps": 17855, "total_steps": 40000, "loss": 0.1423, "lr": 2.9193739250809042e-05, "epoch": 0.8083025872020644, "percentage": 44.64, "elapsed_time": "14:37:30", "remaining_time": "18:08:20", "throughput": 554.03, "total_tokens": 29169984} {"current_steps": 17860, "total_steps": 40000, "loss": 0.1184, "lr": 2.9184060567822463e-05, "epoch": 0.8085289390887073, "percentage": 44.65, "elapsed_time": "14:37:33", "remaining_time": "18:07:51", "throughput": 554.14, "total_tokens": 29177280} {"current_steps": 17865, "total_steps": 40000, "loss": 0.1533, "lr": 2.9174381239601166e-05, "epoch": 0.8087552909753503, "percentage": 44.66, "elapsed_time": "14:37:36", "remaining_time": "18:07:22", "throughput": 554.26, "total_tokens": 29185408} {"current_steps": 17870, "total_steps": 40000, "loss": 0.0705, "lr": 2.916470126763783e-05, "epoch": 0.8089816428619933, "percentage": 44.67, "elapsed_time": "14:37:39", "remaining_time": "18:06:53", "throughput": 554.4, "total_tokens": 29194432} {"current_steps": 17875, "total_steps": 40000, "loss": 0.1312, "lr": 2.9155020653425203e-05, "epoch": 0.8092079947486363, "percentage": 44.69, "elapsed_time": "14:37:43", "remaining_time": "18:06:24", "throughput": 554.52, "total_tokens": 29202944} {"current_steps": 17880, "total_steps": 40000, "loss": 0.1156, "lr": 2.9145339398456184e-05, "epoch": 0.8094343466352792, "percentage": 44.7, "elapsed_time": "14:37:46", "remaining_time": "18:05:55", "throughput": 554.66, "total_tokens": 29211840} {"current_steps": 17885, "total_steps": 40000, "loss": 0.097, "lr": 2.913565750422374e-05, "epoch": 0.8096606985219221, "percentage": 44.71, "elapsed_time": "14:37:49", "remaining_time": "18:05:26", "throughput": 554.78, "total_tokens": 29220128} {"current_steps": 17890, "total_steps": 40000, "loss": 0.1369, "lr": 2.9125974972220938e-05, "epoch": 0.8098870504085651, "percentage": 44.73, "elapsed_time": "14:37:52", "remaining_time": "18:04:57", "throughput": 554.91, "total_tokens": 29228576} {"current_steps": 17895, "total_steps": 40000, "loss": 0.1152, "lr": 2.9116291803940932e-05, "epoch": 0.8101134022952081, "percentage": 44.74, "elapsed_time": "14:37:56", "remaining_time": "18:04:28", "throughput": 555.03, "total_tokens": 29236608} {"current_steps": 17900, "total_steps": 40000, "loss": 0.1411, "lr": 2.910660800087701e-05, "epoch": 0.8103397541818511, "percentage": 44.75, "elapsed_time": "14:37:59", "remaining_time": "18:03:59", "throughput": 555.16, "total_tokens": 29245184} {"current_steps": 17905, "total_steps": 40000, "loss": 0.131, "lr": 2.909692356452254e-05, "epoch": 0.8105661060684941, "percentage": 44.76, "elapsed_time": "14:38:02", "remaining_time": "18:03:30", "throughput": 555.28, "total_tokens": 29253472} {"current_steps": 17910, "total_steps": 40000, "loss": 0.099, "lr": 2.9087238496370962e-05, "epoch": 0.8107924579551371, "percentage": 44.77, "elapsed_time": "14:38:05", "remaining_time": "18:03:01", "throughput": 555.4, "total_tokens": 29261440} {"current_steps": 17915, "total_steps": 40000, "loss": 0.1247, "lr": 2.907755279791583e-05, "epoch": 0.81101880984178, "percentage": 44.79, "elapsed_time": "14:38:08", "remaining_time": "18:02:32", "throughput": 555.52, "total_tokens": 29269472} {"current_steps": 17920, "total_steps": 40000, "loss": 0.1442, "lr": 2.906786647065083e-05, "epoch": 0.811245161728423, "percentage": 44.8, "elapsed_time": "14:38:11", "remaining_time": "18:02:03", "throughput": 555.64, "total_tokens": 29277568} {"current_steps": 17925, "total_steps": 40000, "loss": 0.1232, "lr": 2.9058179516069695e-05, "epoch": 0.811471513615066, "percentage": 44.81, "elapsed_time": "14:38:15", "remaining_time": "18:01:34", "throughput": 555.75, "total_tokens": 29285408} {"current_steps": 17930, "total_steps": 40000, "loss": 0.1652, "lr": 2.9048491935666282e-05, "epoch": 0.811697865501709, "percentage": 44.82, "elapsed_time": "14:38:18", "remaining_time": "18:01:06", "throughput": 555.87, "total_tokens": 29293472} {"current_steps": 17935, "total_steps": 40000, "loss": 0.1246, "lr": 2.9038803730934534e-05, "epoch": 0.811924217388352, "percentage": 44.84, "elapsed_time": "14:38:21", "remaining_time": "18:00:37", "throughput": 555.99, "total_tokens": 29301632} {"current_steps": 17940, "total_steps": 40000, "loss": 0.1239, "lr": 2.9029114903368503e-05, "epoch": 0.812150569274995, "percentage": 44.85, "elapsed_time": "14:38:24", "remaining_time": "18:00:08", "throughput": 556.11, "total_tokens": 29309600} {"current_steps": 17945, "total_steps": 40000, "loss": 0.1342, "lr": 2.9019425454462318e-05, "epoch": 0.8123769211616378, "percentage": 44.86, "elapsed_time": "14:38:27", "remaining_time": "17:59:39", "throughput": 556.22, "total_tokens": 29317152} {"current_steps": 17950, "total_steps": 40000, "loss": 0.1069, "lr": 2.9009735385710212e-05, "epoch": 0.8126032730482808, "percentage": 44.88, "elapsed_time": "14:38:30", "remaining_time": "17:59:10", "throughput": 556.34, "total_tokens": 29325216} {"current_steps": 17955, "total_steps": 40000, "loss": 0.1067, "lr": 2.900004469860652e-05, "epoch": 0.8128296249349238, "percentage": 44.89, "elapsed_time": "14:38:33", "remaining_time": "17:58:41", "throughput": 556.46, "total_tokens": 29333120} {"current_steps": 17960, "total_steps": 40000, "loss": 0.085, "lr": 2.8990353394645668e-05, "epoch": 0.8130559768215668, "percentage": 44.9, "elapsed_time": "14:38:37", "remaining_time": "17:58:12", "throughput": 556.58, "total_tokens": 29341472} {"current_steps": 17965, "total_steps": 40000, "loss": 0.1062, "lr": 2.8980661475322186e-05, "epoch": 0.8132823287082098, "percentage": 44.91, "elapsed_time": "14:38:40", "remaining_time": "17:57:44", "throughput": 556.7, "total_tokens": 29349344} {"current_steps": 17970, "total_steps": 40000, "loss": 0.1153, "lr": 2.897096894213067e-05, "epoch": 0.8135086805948527, "percentage": 44.92, "elapsed_time": "14:38:43", "remaining_time": "17:57:15", "throughput": 556.81, "total_tokens": 29357120} {"current_steps": 17975, "total_steps": 40000, "loss": 0.1278, "lr": 2.8961275796565845e-05, "epoch": 0.8137350324814957, "percentage": 44.94, "elapsed_time": "14:38:46", "remaining_time": "17:56:46", "throughput": 556.94, "total_tokens": 29365600} {"current_steps": 17980, "total_steps": 40000, "loss": 0.1101, "lr": 2.8951582040122517e-05, "epoch": 0.8139613843681387, "percentage": 44.95, "elapsed_time": "14:38:49", "remaining_time": "17:56:17", "throughput": 557.07, "total_tokens": 29373984} {"current_steps": 17985, "total_steps": 40000, "loss": 0.1048, "lr": 2.894188767429557e-05, "epoch": 0.8141877362547817, "percentage": 44.96, "elapsed_time": "14:38:52", "remaining_time": "17:55:49", "throughput": 557.19, "total_tokens": 29382144} {"current_steps": 17990, "total_steps": 40000, "loss": 0.1335, "lr": 2.8932192700580014e-05, "epoch": 0.8144140881414247, "percentage": 44.98, "elapsed_time": "14:38:56", "remaining_time": "17:55:20", "throughput": 557.31, "total_tokens": 29390272} {"current_steps": 17995, "total_steps": 40000, "loss": 0.1521, "lr": 2.8922497120470916e-05, "epoch": 0.8146404400280677, "percentage": 44.99, "elapsed_time": "14:38:59", "remaining_time": "17:54:52", "throughput": 557.45, "total_tokens": 29399616} {"current_steps": 18000, "total_steps": 40000, "loss": 0.1405, "lr": 2.891280093546348e-05, "epoch": 0.8148667919147106, "percentage": 45.0, "elapsed_time": "14:39:02", "remaining_time": "17:54:23", "throughput": 557.57, "total_tokens": 29407776} {"current_steps": 18000, "total_steps": 40000, "eval_loss": 0.12857936322689056, "epoch": 0.8148667919147106, "percentage": 45.0, "elapsed_time": "14:46:45", "remaining_time": "18:03:48", "throughput": 552.72, "total_tokens": 29407776} {"current_steps": 18005, "total_steps": 40000, "loss": 0.1363, "lr": 2.890310414705297e-05, "epoch": 0.8150931438013536, "percentage": 45.01, "elapsed_time": "14:46:49", "remaining_time": "18:03:21", "throughput": 552.84, "total_tokens": 29416352} {"current_steps": 18010, "total_steps": 40000, "loss": 0.1838, "lr": 2.8893406756734742e-05, "epoch": 0.8153194956879966, "percentage": 45.02, "elapsed_time": "14:46:52", "remaining_time": "18:02:52", "throughput": 552.95, "total_tokens": 29424128} {"current_steps": 18015, "total_steps": 40000, "loss": 0.1362, "lr": 2.888370876600427e-05, "epoch": 0.8155458475746395, "percentage": 45.04, "elapsed_time": "14:46:55", "remaining_time": "18:02:23", "throughput": 553.07, "total_tokens": 29431872} {"current_steps": 18020, "total_steps": 40000, "loss": 0.1162, "lr": 2.8874010176357104e-05, "epoch": 0.8157721994612825, "percentage": 45.05, "elapsed_time": "14:46:59", "remaining_time": "18:01:54", "throughput": 553.19, "total_tokens": 29440064} {"current_steps": 18025, "total_steps": 40000, "loss": 0.1105, "lr": 2.886431098928888e-05, "epoch": 0.8159985513479255, "percentage": 45.06, "elapsed_time": "14:47:02", "remaining_time": "18:01:25", "throughput": 553.31, "total_tokens": 29448512} {"current_steps": 18030, "total_steps": 40000, "loss": 0.1417, "lr": 2.885461120629534e-05, "epoch": 0.8162249032345684, "percentage": 45.07, "elapsed_time": "14:47:05", "remaining_time": "18:00:56", "throughput": 553.44, "total_tokens": 29456928} {"current_steps": 18035, "total_steps": 40000, "loss": 0.1292, "lr": 2.8844910828872317e-05, "epoch": 0.8164512551212114, "percentage": 45.09, "elapsed_time": "14:47:08", "remaining_time": "18:00:27", "throughput": 553.57, "total_tokens": 29465728} {"current_steps": 18040, "total_steps": 40000, "loss": 0.1125, "lr": 2.8835209858515715e-05, "epoch": 0.8166776070078544, "percentage": 45.1, "elapsed_time": "14:47:11", "remaining_time": "17:59:58", "throughput": 553.69, "total_tokens": 29473760} {"current_steps": 18045, "total_steps": 40000, "loss": 0.1513, "lr": 2.8825508296721566e-05, "epoch": 0.8169039588944974, "percentage": 45.11, "elapsed_time": "14:47:15", "remaining_time": "17:59:30", "throughput": 553.8, "total_tokens": 29481856} {"current_steps": 18050, "total_steps": 40000, "loss": 0.1361, "lr": 2.881580614498596e-05, "epoch": 0.8171303107811404, "percentage": 45.12, "elapsed_time": "14:47:18", "remaining_time": "17:59:01", "throughput": 553.93, "total_tokens": 29490144} {"current_steps": 18055, "total_steps": 40000, "loss": 0.1657, "lr": 2.8806103404805103e-05, "epoch": 0.8173566626677833, "percentage": 45.14, "elapsed_time": "14:47:21", "remaining_time": "17:58:32", "throughput": 554.05, "total_tokens": 29498208} {"current_steps": 18060, "total_steps": 40000, "loss": 0.1225, "lr": 2.8796400077675257e-05, "epoch": 0.8175830145544263, "percentage": 45.15, "elapsed_time": "14:47:24", "remaining_time": "17:58:03", "throughput": 554.16, "total_tokens": 29506208} {"current_steps": 18065, "total_steps": 40000, "loss": 0.1321, "lr": 2.8786696165092812e-05, "epoch": 0.8178093664410693, "percentage": 45.16, "elapsed_time": "14:47:27", "remaining_time": "17:57:35", "throughput": 554.29, "total_tokens": 29514944} {"current_steps": 18070, "total_steps": 40000, "loss": 0.1247, "lr": 2.8776991668554236e-05, "epoch": 0.8180357183277123, "percentage": 45.17, "elapsed_time": "14:47:31", "remaining_time": "17:57:06", "throughput": 554.41, "total_tokens": 29522816} {"current_steps": 18075, "total_steps": 40000, "loss": 0.1218, "lr": 2.876728658955608e-05, "epoch": 0.8182620702143553, "percentage": 45.19, "elapsed_time": "14:47:34", "remaining_time": "17:56:37", "throughput": 554.52, "total_tokens": 29530496} {"current_steps": 18080, "total_steps": 40000, "loss": 0.1372, "lr": 2.8757580929594986e-05, "epoch": 0.8184884221009983, "percentage": 45.2, "elapsed_time": "14:47:37", "remaining_time": "17:56:08", "throughput": 554.64, "total_tokens": 29538624} {"current_steps": 18085, "total_steps": 40000, "loss": 0.1311, "lr": 2.87478746901677e-05, "epoch": 0.8187147739876411, "percentage": 45.21, "elapsed_time": "14:47:40", "remaining_time": "17:55:40", "throughput": 554.78, "total_tokens": 29548000} {"current_steps": 18090, "total_steps": 40000, "loss": 0.1598, "lr": 2.873816787277103e-05, "epoch": 0.8189411258742841, "percentage": 45.23, "elapsed_time": "14:47:43", "remaining_time": "17:55:11", "throughput": 554.9, "total_tokens": 29555936} {"current_steps": 18095, "total_steps": 40000, "loss": 0.1443, "lr": 2.8728460478901903e-05, "epoch": 0.8191674777609271, "percentage": 45.24, "elapsed_time": "14:47:47", "remaining_time": "17:54:42", "throughput": 555.01, "total_tokens": 29563744} {"current_steps": 18100, "total_steps": 40000, "loss": 0.1246, "lr": 2.8718752510057307e-05, "epoch": 0.8193938296475701, "percentage": 45.25, "elapsed_time": "14:47:50", "remaining_time": "17:54:13", "throughput": 555.12, "total_tokens": 29571296} {"current_steps": 18105, "total_steps": 40000, "loss": 0.1034, "lr": 2.870904396773435e-05, "epoch": 0.8196201815342131, "percentage": 45.26, "elapsed_time": "14:47:53", "remaining_time": "17:53:45", "throughput": 555.25, "total_tokens": 29579968} {"current_steps": 18110, "total_steps": 40000, "loss": 0.156, "lr": 2.86993348534302e-05, "epoch": 0.8198465334208561, "percentage": 45.27, "elapsed_time": "14:47:56", "remaining_time": "17:53:16", "throughput": 555.38, "total_tokens": 29588768} {"current_steps": 18115, "total_steps": 40000, "loss": 0.1513, "lr": 2.868962516864212e-05, "epoch": 0.820072885307499, "percentage": 45.29, "elapsed_time": "14:47:59", "remaining_time": "17:52:48", "throughput": 555.5, "total_tokens": 29596800} {"current_steps": 18120, "total_steps": 40000, "loss": 0.1067, "lr": 2.8679914914867477e-05, "epoch": 0.820299237194142, "percentage": 45.3, "elapsed_time": "14:48:03", "remaining_time": "17:52:19", "throughput": 555.63, "total_tokens": 29605984} {"current_steps": 18125, "total_steps": 40000, "loss": 0.1402, "lr": 2.8670204093603713e-05, "epoch": 0.820525589080785, "percentage": 45.31, "elapsed_time": "14:48:06", "remaining_time": "17:51:51", "throughput": 555.76, "total_tokens": 29614432} {"current_steps": 18130, "total_steps": 40000, "loss": 0.1234, "lr": 2.8660492706348357e-05, "epoch": 0.820751940967428, "percentage": 45.32, "elapsed_time": "14:48:09", "remaining_time": "17:51:22", "throughput": 555.88, "total_tokens": 29622432} {"current_steps": 18135, "total_steps": 40000, "loss": 0.1055, "lr": 2.8650780754599022e-05, "epoch": 0.820978292854071, "percentage": 45.34, "elapsed_time": "14:48:12", "remaining_time": "17:50:54", "throughput": 555.99, "total_tokens": 29630464} {"current_steps": 18140, "total_steps": 40000, "loss": 0.1663, "lr": 2.8641068239853407e-05, "epoch": 0.8212046447407139, "percentage": 45.35, "elapsed_time": "14:48:16", "remaining_time": "17:50:25", "throughput": 556.11, "total_tokens": 29638464} {"current_steps": 18145, "total_steps": 40000, "loss": 0.1203, "lr": 2.863135516360932e-05, "epoch": 0.8214309966273569, "percentage": 45.36, "elapsed_time": "14:48:19", "remaining_time": "17:49:56", "throughput": 556.23, "total_tokens": 29646432} {"current_steps": 18150, "total_steps": 40000, "loss": 0.1146, "lr": 2.8621641527364633e-05, "epoch": 0.8216573485139999, "percentage": 45.38, "elapsed_time": "14:48:22", "remaining_time": "17:49:28", "throughput": 556.34, "total_tokens": 29654368} {"current_steps": 18155, "total_steps": 40000, "loss": 0.0848, "lr": 2.8611927332617313e-05, "epoch": 0.8218837004006428, "percentage": 45.39, "elapsed_time": "14:48:25", "remaining_time": "17:48:59", "throughput": 556.46, "total_tokens": 29662240} {"current_steps": 18160, "total_steps": 40000, "loss": 0.1308, "lr": 2.8602212580865405e-05, "epoch": 0.8221100522872858, "percentage": 45.4, "elapsed_time": "14:48:28", "remaining_time": "17:48:31", "throughput": 556.58, "total_tokens": 29670464} {"current_steps": 18165, "total_steps": 40000, "loss": 0.1241, "lr": 2.859249727360705e-05, "epoch": 0.8223364041739288, "percentage": 45.41, "elapsed_time": "14:48:31", "remaining_time": "17:48:02", "throughput": 556.69, "total_tokens": 29678368} {"current_steps": 18170, "total_steps": 40000, "loss": 0.1775, "lr": 2.8582781412340465e-05, "epoch": 0.8225627560605717, "percentage": 45.42, "elapsed_time": "14:48:34", "remaining_time": "17:47:34", "throughput": 556.8, "total_tokens": 29685920} {"current_steps": 18175, "total_steps": 40000, "loss": 0.154, "lr": 2.857306499856397e-05, "epoch": 0.8227891079472147, "percentage": 45.44, "elapsed_time": "14:48:37", "remaining_time": "17:47:05", "throughput": 556.92, "total_tokens": 29693632} {"current_steps": 18180, "total_steps": 40000, "loss": 0.1282, "lr": 2.856334803377594e-05, "epoch": 0.8230154598338577, "percentage": 45.45, "elapsed_time": "14:48:41", "remaining_time": "17:46:37", "throughput": 557.05, "total_tokens": 29702336} {"current_steps": 18185, "total_steps": 40000, "loss": 0.1546, "lr": 2.8553630519474867e-05, "epoch": 0.8232418117205007, "percentage": 45.46, "elapsed_time": "14:48:44", "remaining_time": "17:46:08", "throughput": 557.16, "total_tokens": 29710304} {"current_steps": 18190, "total_steps": 40000, "loss": 0.0971, "lr": 2.8543912457159317e-05, "epoch": 0.8234681636071437, "percentage": 45.48, "elapsed_time": "14:48:47", "remaining_time": "17:45:40", "throughput": 557.28, "total_tokens": 29718336} {"current_steps": 18195, "total_steps": 40000, "loss": 0.0862, "lr": 2.853419384832792e-05, "epoch": 0.8236945154937867, "percentage": 45.49, "elapsed_time": "14:48:50", "remaining_time": "17:45:11", "throughput": 557.4, "total_tokens": 29726656} {"current_steps": 18200, "total_steps": 40000, "loss": 0.1031, "lr": 2.8524474694479423e-05, "epoch": 0.8239208673804296, "percentage": 45.5, "elapsed_time": "14:48:53", "remaining_time": "17:44:43", "throughput": 557.53, "total_tokens": 29735104} {"current_steps": 18200, "total_steps": 40000, "eval_loss": 0.12738202512264252, "epoch": 0.8239208673804296, "percentage": 45.5, "elapsed_time": "14:56:36", "remaining_time": "17:53:57", "throughput": 552.73, "total_tokens": 29735104} {"current_steps": 18205, "total_steps": 40000, "loss": 0.1563, "lr": 2.851475499711264e-05, "epoch": 0.8241472192670726, "percentage": 45.51, "elapsed_time": "14:56:41", "remaining_time": "17:53:31", "throughput": 552.82, "total_tokens": 29742912} {"current_steps": 18210, "total_steps": 40000, "loss": 0.1913, "lr": 2.8505034757726468e-05, "epoch": 0.8243735711537156, "percentage": 45.52, "elapsed_time": "14:56:44", "remaining_time": "17:53:02", "throughput": 552.94, "total_tokens": 29750880} {"current_steps": 18215, "total_steps": 40000, "loss": 0.1134, "lr": 2.8495313977819886e-05, "epoch": 0.8245999230403586, "percentage": 45.54, "elapsed_time": "14:56:48", "remaining_time": "17:52:34", "throughput": 553.06, "total_tokens": 29759424} {"current_steps": 18220, "total_steps": 40000, "loss": 0.1269, "lr": 2.8485592658891956e-05, "epoch": 0.8248262749270016, "percentage": 45.55, "elapsed_time": "14:56:51", "remaining_time": "17:52:05", "throughput": 553.19, "total_tokens": 29767712} {"current_steps": 18225, "total_steps": 40000, "loss": 0.0985, "lr": 2.8475870802441844e-05, "epoch": 0.8250526268136444, "percentage": 45.56, "elapsed_time": "14:56:54", "remaining_time": "17:51:36", "throughput": 553.29, "total_tokens": 29774912} {"current_steps": 18230, "total_steps": 40000, "loss": 0.1002, "lr": 2.8466148409968774e-05, "epoch": 0.8252789787002874, "percentage": 45.57, "elapsed_time": "14:56:57", "remaining_time": "17:51:08", "throughput": 553.4, "total_tokens": 29782816} {"current_steps": 18235, "total_steps": 40000, "loss": 0.15, "lr": 2.8456425482972067e-05, "epoch": 0.8255053305869304, "percentage": 45.59, "elapsed_time": "14:57:00", "remaining_time": "17:50:39", "throughput": 553.51, "total_tokens": 29790496} {"current_steps": 18240, "total_steps": 40000, "loss": 0.1279, "lr": 2.84467020229511e-05, "epoch": 0.8257316824735734, "percentage": 45.6, "elapsed_time": "14:57:03", "remaining_time": "17:50:10", "throughput": 553.63, "total_tokens": 29798624} {"current_steps": 18245, "total_steps": 40000, "loss": 0.1202, "lr": 2.8436978031405375e-05, "epoch": 0.8259580343602164, "percentage": 45.61, "elapsed_time": "14:57:07", "remaining_time": "17:49:42", "throughput": 553.76, "total_tokens": 29807040} {"current_steps": 18250, "total_steps": 40000, "loss": 0.1169, "lr": 2.842725350983445e-05, "epoch": 0.8261843862468594, "percentage": 45.62, "elapsed_time": "14:57:10", "remaining_time": "17:49:13", "throughput": 553.88, "total_tokens": 29815488} {"current_steps": 18255, "total_steps": 40000, "loss": 0.1921, "lr": 2.8417528459737957e-05, "epoch": 0.8264107381335023, "percentage": 45.64, "elapsed_time": "14:57:13", "remaining_time": "17:48:45", "throughput": 554.0, "total_tokens": 29823744} {"current_steps": 18260, "total_steps": 40000, "loss": 0.1316, "lr": 2.8407802882615624e-05, "epoch": 0.8266370900201453, "percentage": 45.65, "elapsed_time": "14:57:16", "remaining_time": "17:48:16", "throughput": 554.11, "total_tokens": 29831648} {"current_steps": 18265, "total_steps": 40000, "loss": 0.1637, "lr": 2.8398076779967277e-05, "epoch": 0.8268634419067883, "percentage": 45.66, "elapsed_time": "14:57:19", "remaining_time": "17:47:48", "throughput": 554.24, "total_tokens": 29840192} {"current_steps": 18270, "total_steps": 40000, "loss": 0.148, "lr": 2.8388350153292774e-05, "epoch": 0.8270897937934313, "percentage": 45.67, "elapsed_time": "14:57:22", "remaining_time": "17:47:19", "throughput": 554.35, "total_tokens": 29847936} {"current_steps": 18275, "total_steps": 40000, "loss": 0.153, "lr": 2.8378623004092103e-05, "epoch": 0.8273161456800743, "percentage": 45.69, "elapsed_time": "14:57:26", "remaining_time": "17:46:51", "throughput": 554.47, "total_tokens": 29855936} {"current_steps": 18280, "total_steps": 40000, "loss": 0.1594, "lr": 2.8368895333865302e-05, "epoch": 0.8275424975667173, "percentage": 45.7, "elapsed_time": "14:57:29", "remaining_time": "17:46:22", "throughput": 554.58, "total_tokens": 29863904} {"current_steps": 18285, "total_steps": 40000, "loss": 0.1733, "lr": 2.835916714411251e-05, "epoch": 0.8277688494533602, "percentage": 45.71, "elapsed_time": "14:57:32", "remaining_time": "17:45:54", "throughput": 554.7, "total_tokens": 29871904} {"current_steps": 18290, "total_steps": 40000, "loss": 0.1387, "lr": 2.8349438436333926e-05, "epoch": 0.8279952013400032, "percentage": 45.73, "elapsed_time": "14:57:35", "remaining_time": "17:45:25", "throughput": 554.81, "total_tokens": 29879744} {"current_steps": 18295, "total_steps": 40000, "loss": 0.1177, "lr": 2.833970921202984e-05, "epoch": 0.8282215532266461, "percentage": 45.74, "elapsed_time": "14:57:38", "remaining_time": "17:44:57", "throughput": 554.92, "total_tokens": 29887392} {"current_steps": 18300, "total_steps": 40000, "loss": 0.1298, "lr": 2.8329979472700628e-05, "epoch": 0.8284479051132891, "percentage": 45.75, "elapsed_time": "14:57:41", "remaining_time": "17:44:28", "throughput": 555.05, "total_tokens": 29896192} {"current_steps": 18305, "total_steps": 40000, "loss": 0.1231, "lr": 2.832024921984674e-05, "epoch": 0.8286742569999321, "percentage": 45.76, "elapsed_time": "14:57:45", "remaining_time": "17:44:00", "throughput": 555.18, "total_tokens": 29904800} {"current_steps": 18310, "total_steps": 40000, "loss": 0.0793, "lr": 2.8310518454968693e-05, "epoch": 0.828900608886575, "percentage": 45.77, "elapsed_time": "14:57:48", "remaining_time": "17:43:32", "throughput": 555.3, "total_tokens": 29913312} {"current_steps": 18315, "total_steps": 40000, "loss": 0.1228, "lr": 2.8300787179567095e-05, "epoch": 0.829126960773218, "percentage": 45.79, "elapsed_time": "14:57:51", "remaining_time": "17:43:03", "throughput": 555.42, "total_tokens": 29921504} {"current_steps": 18320, "total_steps": 40000, "loss": 0.1077, "lr": 2.8291055395142636e-05, "epoch": 0.829353312659861, "percentage": 45.8, "elapsed_time": "14:57:54", "remaining_time": "17:42:35", "throughput": 555.55, "total_tokens": 29930112} {"current_steps": 18325, "total_steps": 40000, "loss": 0.1449, "lr": 2.8281323103196073e-05, "epoch": 0.829579664546504, "percentage": 45.81, "elapsed_time": "14:57:58", "remaining_time": "17:42:07", "throughput": 555.68, "total_tokens": 29938784} {"current_steps": 18330, "total_steps": 40000, "loss": 0.126, "lr": 2.8271590305228256e-05, "epoch": 0.829806016433147, "percentage": 45.82, "elapsed_time": "14:58:01", "remaining_time": "17:41:39", "throughput": 555.78, "total_tokens": 29946304} {"current_steps": 18335, "total_steps": 40000, "loss": 0.0949, "lr": 2.82618570027401e-05, "epoch": 0.83003236831979, "percentage": 45.84, "elapsed_time": "14:58:04", "remaining_time": "17:41:10", "throughput": 555.9, "total_tokens": 29954432} {"current_steps": 18340, "total_steps": 40000, "loss": 0.1429, "lr": 2.8252123197232604e-05, "epoch": 0.8302587202064329, "percentage": 45.85, "elapsed_time": "14:58:07", "remaining_time": "17:40:42", "throughput": 556.01, "total_tokens": 29962176} {"current_steps": 18345, "total_steps": 40000, "loss": 0.1561, "lr": 2.8242388890206843e-05, "epoch": 0.8304850720930759, "percentage": 45.86, "elapsed_time": "14:58:10", "remaining_time": "17:40:14", "throughput": 556.13, "total_tokens": 29970304} {"current_steps": 18350, "total_steps": 40000, "loss": 0.1355, "lr": 2.8232654083163967e-05, "epoch": 0.8307114239797189, "percentage": 45.88, "elapsed_time": "14:58:13", "remaining_time": "17:39:45", "throughput": 556.26, "total_tokens": 29978912} {"current_steps": 18355, "total_steps": 40000, "loss": 0.1108, "lr": 2.822291877760521e-05, "epoch": 0.8309377758663619, "percentage": 45.89, "elapsed_time": "14:58:17", "remaining_time": "17:39:17", "throughput": 556.38, "total_tokens": 29987008} {"current_steps": 18360, "total_steps": 40000, "loss": 0.1524, "lr": 2.8213182975031864e-05, "epoch": 0.8311641277530049, "percentage": 45.9, "elapsed_time": "14:58:20", "remaining_time": "17:38:49", "throughput": 556.5, "total_tokens": 29995456} {"current_steps": 18365, "total_steps": 40000, "loss": 0.1043, "lr": 2.8203446676945337e-05, "epoch": 0.8313904796396479, "percentage": 45.91, "elapsed_time": "14:58:23", "remaining_time": "17:38:21", "throughput": 556.62, "total_tokens": 30003904} {"current_steps": 18370, "total_steps": 40000, "loss": 0.1623, "lr": 2.8193709884847075e-05, "epoch": 0.8316168315262907, "percentage": 45.92, "elapsed_time": "14:58:26", "remaining_time": "17:37:53", "throughput": 556.75, "total_tokens": 30012352} {"current_steps": 18375, "total_steps": 40000, "loss": 0.1102, "lr": 2.8183972600238605e-05, "epoch": 0.8318431834129337, "percentage": 45.94, "elapsed_time": "14:58:29", "remaining_time": "17:37:24", "throughput": 556.85, "total_tokens": 30019840} {"current_steps": 18380, "total_steps": 40000, "loss": 0.1574, "lr": 2.817423482462156e-05, "epoch": 0.8320695352995767, "percentage": 45.95, "elapsed_time": "14:58:32", "remaining_time": "17:36:56", "throughput": 556.96, "total_tokens": 30027616} {"current_steps": 18385, "total_steps": 40000, "loss": 0.0934, "lr": 2.8164496559497605e-05, "epoch": 0.8322958871862197, "percentage": 45.96, "elapsed_time": "14:58:36", "remaining_time": "17:36:28", "throughput": 557.07, "total_tokens": 30035072} {"current_steps": 18390, "total_steps": 40000, "loss": 0.1258, "lr": 2.815475780636852e-05, "epoch": 0.8325222390728627, "percentage": 45.98, "elapsed_time": "14:58:39", "remaining_time": "17:36:00", "throughput": 557.19, "total_tokens": 30043520} {"current_steps": 18395, "total_steps": 40000, "loss": 0.1283, "lr": 2.814501856673613e-05, "epoch": 0.8327485909595056, "percentage": 45.99, "elapsed_time": "14:58:42", "remaining_time": "17:35:32", "throughput": 557.31, "total_tokens": 30051488} {"current_steps": 18400, "total_steps": 40000, "loss": 0.0959, "lr": 2.8135278842102353e-05, "epoch": 0.8329749428461486, "percentage": 46.0, "elapsed_time": "14:58:45", "remaining_time": "17:35:03", "throughput": 557.43, "total_tokens": 30059584} {"current_steps": 18400, "total_steps": 40000, "eval_loss": 0.1273820698261261, "epoch": 0.8329749428461486, "percentage": 46.0, "elapsed_time": "15:06:28", "remaining_time": "17:44:06", "throughput": 552.69, "total_tokens": 30059584} {"current_steps": 18405, "total_steps": 40000, "loss": 0.1286, "lr": 2.8125538633969183e-05, "epoch": 0.8332012947327916, "percentage": 46.01, "elapsed_time": "15:06:32", "remaining_time": "17:43:39", "throughput": 552.8, "total_tokens": 30068000} {"current_steps": 18410, "total_steps": 40000, "loss": 0.1122, "lr": 2.8115797943838677e-05, "epoch": 0.8334276466194346, "percentage": 46.02, "elapsed_time": "15:06:35", "remaining_time": "17:43:11", "throughput": 552.91, "total_tokens": 30075680} {"current_steps": 18415, "total_steps": 40000, "loss": 0.0884, "lr": 2.810605677321298e-05, "epoch": 0.8336539985060776, "percentage": 46.04, "elapsed_time": "15:06:38", "remaining_time": "17:42:42", "throughput": 553.02, "total_tokens": 30083456} {"current_steps": 18420, "total_steps": 40000, "loss": 0.0586, "lr": 2.809631512359428e-05, "epoch": 0.8338803503927206, "percentage": 46.05, "elapsed_time": "15:06:41", "remaining_time": "17:42:14", "throughput": 553.15, "total_tokens": 30092192} {"current_steps": 18425, "total_steps": 40000, "loss": 0.1304, "lr": 2.8086572996484884e-05, "epoch": 0.8341067022793635, "percentage": 46.06, "elapsed_time": "15:06:44", "remaining_time": "17:41:46", "throughput": 553.27, "total_tokens": 30100320} {"current_steps": 18430, "total_steps": 40000, "loss": 0.1298, "lr": 2.8076830393387143e-05, "epoch": 0.8343330541660064, "percentage": 46.08, "elapsed_time": "15:06:48", "remaining_time": "17:41:17", "throughput": 553.39, "total_tokens": 30108640} {"current_steps": 18435, "total_steps": 40000, "loss": 0.0923, "lr": 2.8067087315803497e-05, "epoch": 0.8345594060526494, "percentage": 46.09, "elapsed_time": "15:06:51", "remaining_time": "17:40:49", "throughput": 553.51, "total_tokens": 30117184} {"current_steps": 18440, "total_steps": 40000, "loss": 0.1285, "lr": 2.8057343765236433e-05, "epoch": 0.8347857579392924, "percentage": 46.1, "elapsed_time": "15:06:54", "remaining_time": "17:40:21", "throughput": 553.62, "total_tokens": 30125216} {"current_steps": 18445, "total_steps": 40000, "loss": 0.1323, "lr": 2.804759974318854e-05, "epoch": 0.8350121098259354, "percentage": 46.11, "elapsed_time": "15:06:57", "remaining_time": "17:39:53", "throughput": 553.74, "total_tokens": 30133088} {"current_steps": 18450, "total_steps": 40000, "loss": 0.1305, "lr": 2.8037855251162482e-05, "epoch": 0.8352384617125784, "percentage": 46.12, "elapsed_time": "15:07:00", "remaining_time": "17:39:24", "throughput": 553.86, "total_tokens": 30141504} {"current_steps": 18455, "total_steps": 40000, "loss": 0.1208, "lr": 2.802811029066096e-05, "epoch": 0.8354648135992213, "percentage": 46.14, "elapsed_time": "15:07:04", "remaining_time": "17:38:56", "throughput": 553.98, "total_tokens": 30149888} {"current_steps": 18460, "total_steps": 40000, "loss": 0.146, "lr": 2.8018364863186764e-05, "epoch": 0.8356911654858643, "percentage": 46.15, "elapsed_time": "15:07:07", "remaining_time": "17:38:28", "throughput": 554.09, "total_tokens": 30157760} {"current_steps": 18465, "total_steps": 40000, "loss": 0.0881, "lr": 2.800861897024279e-05, "epoch": 0.8359175173725073, "percentage": 46.16, "elapsed_time": "15:07:10", "remaining_time": "17:38:00", "throughput": 554.21, "total_tokens": 30166112} {"current_steps": 18470, "total_steps": 40000, "loss": 0.1209, "lr": 2.799887261333196e-05, "epoch": 0.8361438692591503, "percentage": 46.17, "elapsed_time": "15:07:13", "remaining_time": "17:37:31", "throughput": 554.33, "total_tokens": 30174240} {"current_steps": 18475, "total_steps": 40000, "loss": 0.1142, "lr": 2.798912579395728e-05, "epoch": 0.8363702211457933, "percentage": 46.19, "elapsed_time": "15:07:16", "remaining_time": "17:37:03", "throughput": 554.44, "total_tokens": 30181888} {"current_steps": 18480, "total_steps": 40000, "loss": 0.1436, "lr": 2.797937851362185e-05, "epoch": 0.8365965730324362, "percentage": 46.2, "elapsed_time": "15:07:19", "remaining_time": "17:36:35", "throughput": 554.55, "total_tokens": 30189760} {"current_steps": 18485, "total_steps": 40000, "loss": 0.1462, "lr": 2.7969630773828802e-05, "epoch": 0.8368229249190792, "percentage": 46.21, "elapsed_time": "15:07:23", "remaining_time": "17:36:07", "throughput": 554.67, "total_tokens": 30198208} {"current_steps": 18490, "total_steps": 40000, "loss": 0.1324, "lr": 2.7959882576081382e-05, "epoch": 0.8370492768057222, "percentage": 46.23, "elapsed_time": "15:07:26", "remaining_time": "17:35:39", "throughput": 554.8, "total_tokens": 30206784} {"current_steps": 18495, "total_steps": 40000, "loss": 0.1014, "lr": 2.795013392188286e-05, "epoch": 0.8372756286923652, "percentage": 46.24, "elapsed_time": "15:07:29", "remaining_time": "17:35:11", "throughput": 554.91, "total_tokens": 30214656} {"current_steps": 18500, "total_steps": 40000, "loss": 0.1203, "lr": 2.7940384812736614e-05, "epoch": 0.8375019805790082, "percentage": 46.25, "elapsed_time": "15:07:32", "remaining_time": "17:34:43", "throughput": 555.03, "total_tokens": 30223072} {"current_steps": 18505, "total_steps": 40000, "loss": 0.1478, "lr": 2.7930635250146087e-05, "epoch": 0.8377283324656511, "percentage": 46.26, "elapsed_time": "15:07:36", "remaining_time": "17:34:15", "throughput": 555.16, "total_tokens": 30231936} {"current_steps": 18510, "total_steps": 40000, "loss": 0.0937, "lr": 2.792088523561477e-05, "epoch": 0.837954684352294, "percentage": 46.27, "elapsed_time": "15:07:39", "remaining_time": "17:33:46", "throughput": 555.28, "total_tokens": 30239936} {"current_steps": 18515, "total_steps": 40000, "loss": 0.1241, "lr": 2.7911134770646246e-05, "epoch": 0.838181036238937, "percentage": 46.29, "elapsed_time": "15:07:42", "remaining_time": "17:33:18", "throughput": 555.39, "total_tokens": 30247744} {"current_steps": 18520, "total_steps": 40000, "loss": 0.1378, "lr": 2.7901383856744157e-05, "epoch": 0.83840738812558, "percentage": 46.3, "elapsed_time": "15:07:45", "remaining_time": "17:32:50", "throughput": 555.5, "total_tokens": 30255488} {"current_steps": 18525, "total_steps": 40000, "loss": 0.1268, "lr": 2.7891632495412217e-05, "epoch": 0.838633740012223, "percentage": 46.31, "elapsed_time": "15:07:48", "remaining_time": "17:32:22", "throughput": 555.62, "total_tokens": 30263904} {"current_steps": 18530, "total_steps": 40000, "loss": 0.0902, "lr": 2.7881880688154205e-05, "epoch": 0.838860091898866, "percentage": 46.33, "elapsed_time": "15:07:51", "remaining_time": "17:31:54", "throughput": 555.73, "total_tokens": 30271424} {"current_steps": 18535, "total_steps": 40000, "loss": 0.1221, "lr": 2.7872128436473977e-05, "epoch": 0.839086443785509, "percentage": 46.34, "elapsed_time": "15:07:54", "remaining_time": "17:31:26", "throughput": 555.84, "total_tokens": 30279136} {"current_steps": 18540, "total_steps": 40000, "loss": 0.0729, "lr": 2.7862375741875448e-05, "epoch": 0.8393127956721519, "percentage": 46.35, "elapsed_time": "15:07:58", "remaining_time": "17:30:58", "throughput": 555.94, "total_tokens": 30286528} {"current_steps": 18545, "total_steps": 40000, "loss": 0.1226, "lr": 2.785262260586261e-05, "epoch": 0.8395391475587949, "percentage": 46.36, "elapsed_time": "15:08:01", "remaining_time": "17:30:30", "throughput": 556.06, "total_tokens": 30294688} {"current_steps": 18550, "total_steps": 40000, "loss": 0.1105, "lr": 2.7842869029939517e-05, "epoch": 0.8397654994454379, "percentage": 46.38, "elapsed_time": "15:08:04", "remaining_time": "17:30:02", "throughput": 556.17, "total_tokens": 30302752} {"current_steps": 18555, "total_steps": 40000, "loss": 0.0752, "lr": 2.7833115015610296e-05, "epoch": 0.8399918513320809, "percentage": 46.39, "elapsed_time": "15:08:07", "remaining_time": "17:29:34", "throughput": 556.28, "total_tokens": 30310528} {"current_steps": 18560, "total_steps": 40000, "loss": 0.1216, "lr": 2.7823360564379136e-05, "epoch": 0.8402182032187239, "percentage": 46.4, "elapsed_time": "15:08:10", "remaining_time": "17:29:06", "throughput": 556.39, "total_tokens": 30318144} {"current_steps": 18565, "total_steps": 40000, "loss": 0.1736, "lr": 2.7813605677750297e-05, "epoch": 0.8404445551053668, "percentage": 46.41, "elapsed_time": "15:08:13", "remaining_time": "17:28:37", "throughput": 556.5, "total_tokens": 30326016} {"current_steps": 18570, "total_steps": 40000, "loss": 0.0589, "lr": 2.7803850357228102e-05, "epoch": 0.8406709069920097, "percentage": 46.42, "elapsed_time": "15:08:16", "remaining_time": "17:28:10", "throughput": 556.62, "total_tokens": 30333920} {"current_steps": 18575, "total_steps": 40000, "loss": 0.1169, "lr": 2.779409460431695e-05, "epoch": 0.8408972588786527, "percentage": 46.44, "elapsed_time": "15:08:20", "remaining_time": "17:27:42", "throughput": 556.73, "total_tokens": 30342016} {"current_steps": 18580, "total_steps": 40000, "loss": 0.1074, "lr": 2.778433842052129e-05, "epoch": 0.8411236107652957, "percentage": 46.45, "elapsed_time": "15:08:23", "remaining_time": "17:27:14", "throughput": 556.85, "total_tokens": 30350368} {"current_steps": 18585, "total_steps": 40000, "loss": 0.1006, "lr": 2.7774581807345664e-05, "epoch": 0.8413499626519387, "percentage": 46.46, "elapsed_time": "15:08:26", "remaining_time": "17:26:46", "throughput": 556.98, "total_tokens": 30359040} {"current_steps": 18590, "total_steps": 40000, "loss": 0.0946, "lr": 2.776482476629465e-05, "epoch": 0.8415763145385817, "percentage": 46.48, "elapsed_time": "15:08:29", "remaining_time": "17:26:18", "throughput": 557.09, "total_tokens": 30366816} {"current_steps": 18595, "total_steps": 40000, "loss": 0.1685, "lr": 2.7755067298872924e-05, "epoch": 0.8418026664252246, "percentage": 46.49, "elapsed_time": "15:08:32", "remaining_time": "17:25:50", "throughput": 557.2, "total_tokens": 30374656} {"current_steps": 18600, "total_steps": 40000, "loss": 0.1382, "lr": 2.774530940658518e-05, "epoch": 0.8420290183118676, "percentage": 46.5, "elapsed_time": "15:08:35", "remaining_time": "17:25:22", "throughput": 557.32, "total_tokens": 30382752} {"current_steps": 18600, "total_steps": 40000, "eval_loss": 0.12762638926506042, "epoch": 0.8420290183118676, "percentage": 46.5, "elapsed_time": "15:16:18", "remaining_time": "17:34:14", "throughput": 552.63, "total_tokens": 30382752} {"current_steps": 18605, "total_steps": 40000, "loss": 0.106, "lr": 2.7735551090936236e-05, "epoch": 0.8422553701985106, "percentage": 46.51, "elapsed_time": "15:16:22", "remaining_time": "17:33:47", "throughput": 552.74, "total_tokens": 30390720} {"current_steps": 18610, "total_steps": 40000, "loss": 0.1056, "lr": 2.7725792353430934e-05, "epoch": 0.8424817220851536, "percentage": 46.52, "elapsed_time": "15:16:25", "remaining_time": "17:33:19", "throughput": 552.85, "total_tokens": 30398912} {"current_steps": 18615, "total_steps": 40000, "loss": 0.1577, "lr": 2.77160331955742e-05, "epoch": 0.8427080739717966, "percentage": 46.54, "elapsed_time": "15:16:28", "remaining_time": "17:32:51", "throughput": 552.98, "total_tokens": 30407456} {"current_steps": 18620, "total_steps": 40000, "loss": 0.1206, "lr": 2.7706273618871008e-05, "epoch": 0.8429344258584396, "percentage": 46.55, "elapsed_time": "15:16:31", "remaining_time": "17:32:23", "throughput": 553.09, "total_tokens": 30415360} {"current_steps": 18625, "total_steps": 40000, "loss": 0.1181, "lr": 2.769651362482642e-05, "epoch": 0.8431607777450825, "percentage": 46.56, "elapsed_time": "15:16:35", "remaining_time": "17:31:55", "throughput": 553.19, "total_tokens": 30422944} {"current_steps": 18630, "total_steps": 40000, "loss": 0.0937, "lr": 2.768675321494555e-05, "epoch": 0.8433871296317255, "percentage": 46.58, "elapsed_time": "15:16:38", "remaining_time": "17:31:27", "throughput": 553.31, "total_tokens": 30431168} {"current_steps": 18635, "total_steps": 40000, "loss": 0.1624, "lr": 2.7676992390733565e-05, "epoch": 0.8436134815183685, "percentage": 46.59, "elapsed_time": "15:16:41", "remaining_time": "17:30:59", "throughput": 553.44, "total_tokens": 30439840} {"current_steps": 18640, "total_steps": 40000, "loss": 0.1399, "lr": 2.766723115369571e-05, "epoch": 0.8438398334050115, "percentage": 46.6, "elapsed_time": "15:16:44", "remaining_time": "17:30:31", "throughput": 553.55, "total_tokens": 30447712} {"current_steps": 18645, "total_steps": 40000, "loss": 0.1028, "lr": 2.765746950533729e-05, "epoch": 0.8440661852916544, "percentage": 46.61, "elapsed_time": "15:16:47", "remaining_time": "17:30:03", "throughput": 553.67, "total_tokens": 30456096} {"current_steps": 18650, "total_steps": 40000, "loss": 0.1569, "lr": 2.7647707447163684e-05, "epoch": 0.8442925371782973, "percentage": 46.62, "elapsed_time": "15:16:51", "remaining_time": "17:29:35", "throughput": 553.79, "total_tokens": 30464384} {"current_steps": 18655, "total_steps": 40000, "loss": 0.1025, "lr": 2.7637944980680315e-05, "epoch": 0.8445188890649403, "percentage": 46.64, "elapsed_time": "15:16:54", "remaining_time": "17:29:07", "throughput": 553.9, "total_tokens": 30472288} {"current_steps": 18660, "total_steps": 40000, "loss": 0.1075, "lr": 2.762818210739268e-05, "epoch": 0.8447452409515833, "percentage": 46.65, "elapsed_time": "15:16:57", "remaining_time": "17:28:39", "throughput": 554.01, "total_tokens": 30480320} {"current_steps": 18665, "total_steps": 40000, "loss": 0.1423, "lr": 2.7618418828806332e-05, "epoch": 0.8449715928382263, "percentage": 46.66, "elapsed_time": "15:17:00", "remaining_time": "17:28:11", "throughput": 554.13, "total_tokens": 30488448} {"current_steps": 18670, "total_steps": 40000, "loss": 0.0926, "lr": 2.76086551464269e-05, "epoch": 0.8451979447248693, "percentage": 46.67, "elapsed_time": "15:17:03", "remaining_time": "17:27:43", "throughput": 554.25, "total_tokens": 30496800} {"current_steps": 18675, "total_steps": 40000, "loss": 0.1337, "lr": 2.759889106176006e-05, "epoch": 0.8454242966115123, "percentage": 46.69, "elapsed_time": "15:17:06", "remaining_time": "17:27:15", "throughput": 554.36, "total_tokens": 30504576} {"current_steps": 18680, "total_steps": 40000, "loss": 0.1378, "lr": 2.758912657631156e-05, "epoch": 0.8456506484981552, "percentage": 46.7, "elapsed_time": "15:17:10", "remaining_time": "17:26:47", "throughput": 554.48, "total_tokens": 30512832} {"current_steps": 18685, "total_steps": 40000, "loss": 0.0725, "lr": 2.7579361691587198e-05, "epoch": 0.8458770003847982, "percentage": 46.71, "elapsed_time": "15:17:13", "remaining_time": "17:26:19", "throughput": 554.6, "total_tokens": 30521440} {"current_steps": 18690, "total_steps": 40000, "loss": 0.1625, "lr": 2.756959640909285e-05, "epoch": 0.8461033522714412, "percentage": 46.73, "elapsed_time": "15:17:16", "remaining_time": "17:25:51", "throughput": 554.72, "total_tokens": 30530048} {"current_steps": 18695, "total_steps": 40000, "loss": 0.1377, "lr": 2.7559830730334452e-05, "epoch": 0.8463297041580842, "percentage": 46.74, "elapsed_time": "15:17:19", "remaining_time": "17:25:24", "throughput": 554.85, "total_tokens": 30538912} {"current_steps": 18700, "total_steps": 40000, "loss": 0.14, "lr": 2.7550064656817988e-05, "epoch": 0.8465560560447272, "percentage": 46.75, "elapsed_time": "15:17:23", "remaining_time": "17:24:56", "throughput": 554.96, "total_tokens": 30546656} {"current_steps": 18705, "total_steps": 40000, "loss": 0.1281, "lr": 2.7540298190049503e-05, "epoch": 0.8467824079313702, "percentage": 46.76, "elapsed_time": "15:17:26", "remaining_time": "17:24:28", "throughput": 555.07, "total_tokens": 30554624} {"current_steps": 18710, "total_steps": 40000, "loss": 0.142, "lr": 2.7530531331535107e-05, "epoch": 0.847008759818013, "percentage": 46.77, "elapsed_time": "15:17:29", "remaining_time": "17:24:00", "throughput": 555.19, "total_tokens": 30562848} {"current_steps": 18715, "total_steps": 40000, "loss": 0.1034, "lr": 2.752076408278099e-05, "epoch": 0.847235111704656, "percentage": 46.79, "elapsed_time": "15:17:32", "remaining_time": "17:23:32", "throughput": 555.3, "total_tokens": 30570592} {"current_steps": 18720, "total_steps": 40000, "loss": 0.1294, "lr": 2.751099644529337e-05, "epoch": 0.847461463591299, "percentage": 46.8, "elapsed_time": "15:17:35", "remaining_time": "17:23:04", "throughput": 555.42, "total_tokens": 30578688} {"current_steps": 18725, "total_steps": 40000, "loss": 0.1343, "lr": 2.7501228420578533e-05, "epoch": 0.847687815477942, "percentage": 46.81, "elapsed_time": "15:17:38", "remaining_time": "17:22:36", "throughput": 555.53, "total_tokens": 30587072} {"current_steps": 18730, "total_steps": 40000, "loss": 0.1296, "lr": 2.7491460010142857e-05, "epoch": 0.847914167364585, "percentage": 46.83, "elapsed_time": "15:17:41", "remaining_time": "17:22:08", "throughput": 555.65, "total_tokens": 30595200} {"current_steps": 18735, "total_steps": 40000, "loss": 0.0927, "lr": 2.7481691215492727e-05, "epoch": 0.8481405192512279, "percentage": 46.84, "elapsed_time": "15:17:45", "remaining_time": "17:21:41", "throughput": 555.76, "total_tokens": 30602880} {"current_steps": 18740, "total_steps": 40000, "loss": 0.0964, "lr": 2.747192203813463e-05, "epoch": 0.8483668711378709, "percentage": 46.85, "elapsed_time": "15:17:48", "remaining_time": "17:21:13", "throughput": 555.87, "total_tokens": 30610848} {"current_steps": 18745, "total_steps": 40000, "loss": 0.1458, "lr": 2.7462152479575087e-05, "epoch": 0.8485932230245139, "percentage": 46.86, "elapsed_time": "15:17:51", "remaining_time": "17:20:45", "throughput": 555.98, "total_tokens": 30618784} {"current_steps": 18750, "total_steps": 40000, "loss": 0.1108, "lr": 2.7452382541320697e-05, "epoch": 0.8488195749111569, "percentage": 46.88, "elapsed_time": "15:17:54", "remaining_time": "17:20:17", "throughput": 556.11, "total_tokens": 30627392} {"current_steps": 18755, "total_steps": 40000, "loss": 0.1546, "lr": 2.7442612224878096e-05, "epoch": 0.8490459267977999, "percentage": 46.89, "elapsed_time": "15:17:57", "remaining_time": "17:19:50", "throughput": 556.22, "total_tokens": 30635552} {"current_steps": 18760, "total_steps": 40000, "loss": 0.0749, "lr": 2.7432841531753994e-05, "epoch": 0.8492722786844429, "percentage": 46.9, "elapsed_time": "15:18:00", "remaining_time": "17:19:22", "throughput": 556.34, "total_tokens": 30643744} {"current_steps": 18765, "total_steps": 40000, "loss": 0.1711, "lr": 2.7423070463455147e-05, "epoch": 0.8494986305710858, "percentage": 46.91, "elapsed_time": "15:18:04", "remaining_time": "17:18:54", "throughput": 556.45, "total_tokens": 30651552} {"current_steps": 18770, "total_steps": 40000, "loss": 0.1192, "lr": 2.7413299021488397e-05, "epoch": 0.8497249824577288, "percentage": 46.92, "elapsed_time": "15:18:07", "remaining_time": "17:18:26", "throughput": 556.56, "total_tokens": 30659424} {"current_steps": 18775, "total_steps": 40000, "loss": 0.1142, "lr": 2.7403527207360615e-05, "epoch": 0.8499513343443718, "percentage": 46.94, "elapsed_time": "15:18:10", "remaining_time": "17:17:59", "throughput": 556.68, "total_tokens": 30667616} {"current_steps": 18780, "total_steps": 40000, "loss": 0.1115, "lr": 2.7393755022578722e-05, "epoch": 0.8501776862310148, "percentage": 46.95, "elapsed_time": "15:18:13", "remaining_time": "17:17:31", "throughput": 556.8, "total_tokens": 30676064} {"current_steps": 18785, "total_steps": 40000, "loss": 0.0735, "lr": 2.7383982468649714e-05, "epoch": 0.8504040381176577, "percentage": 46.96, "elapsed_time": "15:18:16", "remaining_time": "17:17:04", "throughput": 556.92, "total_tokens": 30684320} {"current_steps": 18790, "total_steps": 40000, "loss": 0.2226, "lr": 2.7374209547080665e-05, "epoch": 0.8506303900043007, "percentage": 46.98, "elapsed_time": "15:18:20", "remaining_time": "17:16:36", "throughput": 557.03, "total_tokens": 30692544} {"current_steps": 18795, "total_steps": 40000, "loss": 0.1535, "lr": 2.7364436259378663e-05, "epoch": 0.8508567418909436, "percentage": 46.99, "elapsed_time": "15:18:23", "remaining_time": "17:16:08", "throughput": 557.15, "total_tokens": 30701056} {"current_steps": 18800, "total_steps": 40000, "loss": 0.112, "lr": 2.735466260705088e-05, "epoch": 0.8510830937775866, "percentage": 47.0, "elapsed_time": "15:18:26", "remaining_time": "17:15:41", "throughput": 557.27, "total_tokens": 30709120} {"current_steps": 18800, "total_steps": 40000, "eval_loss": 0.12773488461971283, "epoch": 0.8510830937775866, "percentage": 47.0, "elapsed_time": "15:26:08", "remaining_time": "17:24:22", "throughput": 552.63, "total_tokens": 30709120} {"current_steps": 18805, "total_steps": 40000, "loss": 0.0872, "lr": 2.7344888591604524e-05, "epoch": 0.8513094456642296, "percentage": 47.01, "elapsed_time": "15:26:13", "remaining_time": "17:23:56", "throughput": 552.74, "total_tokens": 30717440} {"current_steps": 18810, "total_steps": 40000, "loss": 0.1797, "lr": 2.7335114214546893e-05, "epoch": 0.8515357975508726, "percentage": 47.02, "elapsed_time": "15:26:16", "remaining_time": "17:23:28", "throughput": 552.85, "total_tokens": 30725504} {"current_steps": 18815, "total_steps": 40000, "loss": 0.2227, "lr": 2.7325339477385293e-05, "epoch": 0.8517621494375156, "percentage": 47.04, "elapsed_time": "15:26:19", "remaining_time": "17:23:00", "throughput": 552.97, "total_tokens": 30733600} {"current_steps": 18820, "total_steps": 40000, "loss": 0.1213, "lr": 2.7315564381627128e-05, "epoch": 0.8519885013241585, "percentage": 47.05, "elapsed_time": "15:26:22", "remaining_time": "17:22:32", "throughput": 553.08, "total_tokens": 30741728} {"current_steps": 18825, "total_steps": 40000, "loss": 0.0833, "lr": 2.7305788928779835e-05, "epoch": 0.8522148532108015, "percentage": 47.06, "elapsed_time": "15:26:25", "remaining_time": "17:22:05", "throughput": 553.19, "total_tokens": 30749792} {"current_steps": 18830, "total_steps": 40000, "loss": 0.1072, "lr": 2.729601312035091e-05, "epoch": 0.8524412050974445, "percentage": 47.08, "elapsed_time": "15:26:29", "remaining_time": "17:21:37", "throughput": 553.31, "total_tokens": 30757728} {"current_steps": 18835, "total_steps": 40000, "loss": 0.1609, "lr": 2.7286236957847915e-05, "epoch": 0.8526675569840875, "percentage": 47.09, "elapsed_time": "15:26:32", "remaining_time": "17:21:09", "throughput": 553.44, "total_tokens": 30767040} {"current_steps": 18840, "total_steps": 40000, "loss": 0.1401, "lr": 2.7276460442778446e-05, "epoch": 0.8528939088707305, "percentage": 47.1, "elapsed_time": "15:26:35", "remaining_time": "17:20:41", "throughput": 553.55, "total_tokens": 30775136} {"current_steps": 18845, "total_steps": 40000, "loss": 0.1107, "lr": 2.726668357665017e-05, "epoch": 0.8531202607573735, "percentage": 47.11, "elapsed_time": "15:26:38", "remaining_time": "17:20:13", "throughput": 553.66, "total_tokens": 30782976} {"current_steps": 18850, "total_steps": 40000, "loss": 0.1515, "lr": 2.7256906360970808e-05, "epoch": 0.8533466126440163, "percentage": 47.12, "elapsed_time": "15:26:41", "remaining_time": "17:19:46", "throughput": 553.78, "total_tokens": 30791008} {"current_steps": 18855, "total_steps": 40000, "loss": 0.1076, "lr": 2.7247128797248117e-05, "epoch": 0.8535729645306593, "percentage": 47.14, "elapsed_time": "15:26:45", "remaining_time": "17:19:18", "throughput": 553.89, "total_tokens": 30798880} {"current_steps": 18860, "total_steps": 40000, "loss": 0.1094, "lr": 2.7237350886989925e-05, "epoch": 0.8537993164173023, "percentage": 47.15, "elapsed_time": "15:26:48", "remaining_time": "17:18:50", "throughput": 554.0, "total_tokens": 30806816} {"current_steps": 18865, "total_steps": 40000, "loss": 0.1798, "lr": 2.7227572631704107e-05, "epoch": 0.8540256683039453, "percentage": 47.16, "elapsed_time": "15:26:51", "remaining_time": "17:18:23", "throughput": 554.11, "total_tokens": 30814976} {"current_steps": 18870, "total_steps": 40000, "loss": 0.1467, "lr": 2.7217794032898596e-05, "epoch": 0.8542520201905883, "percentage": 47.17, "elapsed_time": "15:26:54", "remaining_time": "17:17:55", "throughput": 554.22, "total_tokens": 30822752} {"current_steps": 18875, "total_steps": 40000, "loss": 0.0924, "lr": 2.7208015092081384e-05, "epoch": 0.8544783720772313, "percentage": 47.19, "elapsed_time": "15:26:57", "remaining_time": "17:17:27", "throughput": 554.34, "total_tokens": 30831072} {"current_steps": 18880, "total_steps": 40000, "loss": 0.1379, "lr": 2.719823581076049e-05, "epoch": 0.8547047239638742, "percentage": 47.2, "elapsed_time": "15:27:00", "remaining_time": "17:16:59", "throughput": 554.45, "total_tokens": 30838720} {"current_steps": 18885, "total_steps": 40000, "loss": 0.1656, "lr": 2.718845619044401e-05, "epoch": 0.8549310758505172, "percentage": 47.21, "elapsed_time": "15:27:03", "remaining_time": "17:16:32", "throughput": 554.55, "total_tokens": 30846432} {"current_steps": 18890, "total_steps": 40000, "loss": 0.1321, "lr": 2.7178676232640088e-05, "epoch": 0.8551574277371602, "percentage": 47.23, "elapsed_time": "15:27:06", "remaining_time": "17:16:04", "throughput": 554.66, "total_tokens": 30854176} {"current_steps": 18895, "total_steps": 40000, "loss": 0.1842, "lr": 2.716889593885691e-05, "epoch": 0.8553837796238032, "percentage": 47.24, "elapsed_time": "15:27:10", "remaining_time": "17:15:36", "throughput": 554.78, "total_tokens": 30862656} {"current_steps": 18900, "total_steps": 40000, "loss": 0.1215, "lr": 2.7159115310602716e-05, "epoch": 0.8556101315104462, "percentage": 47.25, "elapsed_time": "15:27:13", "remaining_time": "17:15:09", "throughput": 554.9, "total_tokens": 30871104} {"current_steps": 18905, "total_steps": 40000, "loss": 0.1438, "lr": 2.7149334349385814e-05, "epoch": 0.8558364833970891, "percentage": 47.26, "elapsed_time": "15:27:16", "remaining_time": "17:14:41", "throughput": 555.01, "total_tokens": 30878848} {"current_steps": 18910, "total_steps": 40000, "loss": 0.1212, "lr": 2.713955305671454e-05, "epoch": 0.8560628352837321, "percentage": 47.27, "elapsed_time": "15:27:19", "remaining_time": "17:14:14", "throughput": 555.13, "total_tokens": 30887360} {"current_steps": 18915, "total_steps": 40000, "loss": 0.1089, "lr": 2.71297714340973e-05, "epoch": 0.856289187170375, "percentage": 47.29, "elapsed_time": "15:27:22", "remaining_time": "17:13:46", "throughput": 555.24, "total_tokens": 30895072} {"current_steps": 18920, "total_steps": 40000, "loss": 0.1627, "lr": 2.7119989483042545e-05, "epoch": 0.856515539057018, "percentage": 47.3, "elapsed_time": "15:27:26", "remaining_time": "17:13:18", "throughput": 555.36, "total_tokens": 30903424} {"current_steps": 18925, "total_steps": 40000, "loss": 0.1473, "lr": 2.7110207205058768e-05, "epoch": 0.856741890943661, "percentage": 47.31, "elapsed_time": "15:27:29", "remaining_time": "17:12:51", "throughput": 555.48, "total_tokens": 30911936} {"current_steps": 18930, "total_steps": 40000, "loss": 0.1352, "lr": 2.7100424601654517e-05, "epoch": 0.856968242830304, "percentage": 47.33, "elapsed_time": "15:27:32", "remaining_time": "17:12:23", "throughput": 555.58, "total_tokens": 30919328} {"current_steps": 18935, "total_steps": 40000, "loss": 0.1423, "lr": 2.7090641674338403e-05, "epoch": 0.8571945947169469, "percentage": 47.34, "elapsed_time": "15:27:35", "remaining_time": "17:11:56", "throughput": 555.7, "total_tokens": 30927616} {"current_steps": 18940, "total_steps": 40000, "loss": 0.1205, "lr": 2.7080858424619072e-05, "epoch": 0.8574209466035899, "percentage": 47.35, "elapsed_time": "15:27:38", "remaining_time": "17:11:28", "throughput": 555.82, "total_tokens": 30936032} {"current_steps": 18945, "total_steps": 40000, "loss": 0.1801, "lr": 2.707107485400521e-05, "epoch": 0.8576472984902329, "percentage": 47.36, "elapsed_time": "15:27:41", "remaining_time": "17:11:01", "throughput": 555.92, "total_tokens": 30943712} {"current_steps": 18950, "total_steps": 40000, "loss": 0.1457, "lr": 2.7061290964005586e-05, "epoch": 0.8578736503768759, "percentage": 47.38, "elapsed_time": "15:27:45", "remaining_time": "17:10:33", "throughput": 556.05, "total_tokens": 30952416} {"current_steps": 18955, "total_steps": 40000, "loss": 0.1487, "lr": 2.7051506756129e-05, "epoch": 0.8581000022635189, "percentage": 47.39, "elapsed_time": "15:27:48", "remaining_time": "17:10:06", "throughput": 556.15, "total_tokens": 30960160} {"current_steps": 18960, "total_steps": 40000, "loss": 0.1221, "lr": 2.704172223188428e-05, "epoch": 0.8583263541501619, "percentage": 47.4, "elapsed_time": "15:27:51", "remaining_time": "17:09:39", "throughput": 556.28, "total_tokens": 30968928} {"current_steps": 18965, "total_steps": 40000, "loss": 0.1069, "lr": 2.7031937392780334e-05, "epoch": 0.8585527060368048, "percentage": 47.41, "elapsed_time": "15:27:54", "remaining_time": "17:09:11", "throughput": 556.39, "total_tokens": 30976992} {"current_steps": 18970, "total_steps": 40000, "loss": 0.116, "lr": 2.702215224032611e-05, "epoch": 0.8587790579234478, "percentage": 47.42, "elapsed_time": "15:27:57", "remaining_time": "17:08:44", "throughput": 556.5, "total_tokens": 30984992} {"current_steps": 18975, "total_steps": 40000, "loss": 0.1531, "lr": 2.70123667760306e-05, "epoch": 0.8590054098100908, "percentage": 47.44, "elapsed_time": "15:28:01", "remaining_time": "17:08:16", "throughput": 556.62, "total_tokens": 30993024} {"current_steps": 18980, "total_steps": 40000, "loss": 0.1257, "lr": 2.7002581001402845e-05, "epoch": 0.8592317616967338, "percentage": 47.45, "elapsed_time": "15:28:04", "remaining_time": "17:07:49", "throughput": 556.72, "total_tokens": 31000608} {"current_steps": 18985, "total_steps": 40000, "loss": 0.1466, "lr": 2.6992794917951923e-05, "epoch": 0.8594581135833768, "percentage": 47.46, "elapsed_time": "15:28:07", "remaining_time": "17:07:21", "throughput": 556.83, "total_tokens": 31008576} {"current_steps": 18990, "total_steps": 40000, "loss": 0.1671, "lr": 2.6983008527187e-05, "epoch": 0.8596844654700196, "percentage": 47.48, "elapsed_time": "15:28:10", "remaining_time": "17:06:54", "throughput": 556.96, "total_tokens": 31017440} {"current_steps": 18995, "total_steps": 40000, "loss": 0.0999, "lr": 2.697322183061723e-05, "epoch": 0.8599108173566626, "percentage": 47.49, "elapsed_time": "15:28:13", "remaining_time": "17:06:27", "throughput": 557.07, "total_tokens": 31025440} {"current_steps": 19000, "total_steps": 40000, "loss": 0.1187, "lr": 2.696343482975186e-05, "epoch": 0.8601371692433056, "percentage": 47.5, "elapsed_time": "15:28:17", "remaining_time": "17:05:59", "throughput": 557.19, "total_tokens": 31033824} {"current_steps": 19000, "total_steps": 40000, "eval_loss": 0.12730568647384644, "epoch": 0.8601371692433056, "percentage": 47.5, "elapsed_time": "15:35:59", "remaining_time": "17:14:31", "throughput": 552.6, "total_tokens": 31033824} {"current_steps": 19005, "total_steps": 40000, "loss": 0.1655, "lr": 2.695364752610016e-05, "epoch": 0.8603635211299486, "percentage": 47.51, "elapsed_time": "15:36:05", "remaining_time": "17:14:06", "throughput": 552.7, "total_tokens": 31042304} {"current_steps": 19010, "total_steps": 40000, "loss": 0.1315, "lr": 2.6943859921171467e-05, "epoch": 0.8605898730165916, "percentage": 47.52, "elapsed_time": "15:36:08", "remaining_time": "17:13:38", "throughput": 552.81, "total_tokens": 31050400} {"current_steps": 19015, "total_steps": 40000, "loss": 0.1045, "lr": 2.6934072016475143e-05, "epoch": 0.8608162249032346, "percentage": 47.54, "elapsed_time": "15:36:11", "remaining_time": "17:13:10", "throughput": 552.91, "total_tokens": 31057856} {"current_steps": 19020, "total_steps": 40000, "loss": 0.1245, "lr": 2.6924283813520606e-05, "epoch": 0.8610425767898775, "percentage": 47.55, "elapsed_time": "15:36:14", "remaining_time": "17:12:43", "throughput": 553.03, "total_tokens": 31066432} {"current_steps": 19025, "total_steps": 40000, "loss": 0.1683, "lr": 2.691449531381733e-05, "epoch": 0.8612689286765205, "percentage": 47.56, "elapsed_time": "15:36:17", "remaining_time": "17:12:15", "throughput": 553.15, "total_tokens": 31074528} {"current_steps": 19030, "total_steps": 40000, "loss": 0.1537, "lr": 2.6904706518874816e-05, "epoch": 0.8614952805631635, "percentage": 47.58, "elapsed_time": "15:36:21", "remaining_time": "17:11:48", "throughput": 553.26, "total_tokens": 31082816} {"current_steps": 19035, "total_steps": 40000, "loss": 0.151, "lr": 2.6894917430202615e-05, "epoch": 0.8617216324498065, "percentage": 47.59, "elapsed_time": "15:36:24", "remaining_time": "17:11:20", "throughput": 553.38, "total_tokens": 31091392} {"current_steps": 19040, "total_steps": 40000, "loss": 0.0887, "lr": 2.6885128049310343e-05, "epoch": 0.8619479843364495, "percentage": 47.6, "elapsed_time": "15:36:27", "remaining_time": "17:10:53", "throughput": 553.5, "total_tokens": 31099968} {"current_steps": 19045, "total_steps": 40000, "loss": 0.1527, "lr": 2.687533837770762e-05, "epoch": 0.8621743362230925, "percentage": 47.61, "elapsed_time": "15:36:30", "remaining_time": "17:10:26", "throughput": 553.62, "total_tokens": 31108544} {"current_steps": 19050, "total_steps": 40000, "loss": 0.1051, "lr": 2.6865548416904162e-05, "epoch": 0.8624006881097354, "percentage": 47.62, "elapsed_time": "15:36:34", "remaining_time": "17:09:58", "throughput": 553.74, "total_tokens": 31117152} {"current_steps": 19055, "total_steps": 40000, "loss": 0.0946, "lr": 2.68557581684097e-05, "epoch": 0.8626270399963784, "percentage": 47.64, "elapsed_time": "15:36:37", "remaining_time": "17:09:31", "throughput": 553.85, "total_tokens": 31124960} {"current_steps": 19060, "total_steps": 40000, "loss": 0.1027, "lr": 2.6845967633733998e-05, "epoch": 0.8628533918830213, "percentage": 47.65, "elapsed_time": "15:36:40", "remaining_time": "17:09:03", "throughput": 553.97, "total_tokens": 31133248} {"current_steps": 19065, "total_steps": 40000, "loss": 0.0917, "lr": 2.683617681438689e-05, "epoch": 0.8630797437696643, "percentage": 47.66, "elapsed_time": "15:36:43", "remaining_time": "17:08:36", "throughput": 554.08, "total_tokens": 31141248} {"current_steps": 19070, "total_steps": 40000, "loss": 0.0962, "lr": 2.682638571187825e-05, "epoch": 0.8633060956563073, "percentage": 47.67, "elapsed_time": "15:36:46", "remaining_time": "17:08:09", "throughput": 554.19, "total_tokens": 31149152} {"current_steps": 19075, "total_steps": 40000, "loss": 0.2057, "lr": 2.6816594327717976e-05, "epoch": 0.8635324475429502, "percentage": 47.69, "elapsed_time": "15:36:50", "remaining_time": "17:07:41", "throughput": 554.3, "total_tokens": 31157088} {"current_steps": 19080, "total_steps": 40000, "loss": 0.1252, "lr": 2.680680266341603e-05, "epoch": 0.8637587994295932, "percentage": 47.7, "elapsed_time": "15:36:53", "remaining_time": "17:07:14", "throughput": 554.41, "total_tokens": 31165056} {"current_steps": 19085, "total_steps": 40000, "loss": 0.1348, "lr": 2.67970107204824e-05, "epoch": 0.8639851513162362, "percentage": 47.71, "elapsed_time": "15:36:56", "remaining_time": "17:06:46", "throughput": 554.52, "total_tokens": 31172992} {"current_steps": 19090, "total_steps": 40000, "loss": 0.1049, "lr": 2.6787218500427142e-05, "epoch": 0.8642115032028792, "percentage": 47.73, "elapsed_time": "15:36:59", "remaining_time": "17:06:19", "throughput": 554.64, "total_tokens": 31182048} {"current_steps": 19095, "total_steps": 40000, "loss": 0.151, "lr": 2.6777426004760332e-05, "epoch": 0.8644378550895222, "percentage": 47.74, "elapsed_time": "15:37:02", "remaining_time": "17:05:52", "throughput": 554.75, "total_tokens": 31189472} {"current_steps": 19100, "total_steps": 40000, "loss": 0.1307, "lr": 2.6767633234992094e-05, "epoch": 0.8646642069761652, "percentage": 47.75, "elapsed_time": "15:37:06", "remaining_time": "17:05:24", "throughput": 554.85, "total_tokens": 31196800} {"current_steps": 19105, "total_steps": 40000, "loss": 0.1264, "lr": 2.6757840192632598e-05, "epoch": 0.8648905588628081, "percentage": 47.76, "elapsed_time": "15:37:09", "remaining_time": "17:04:57", "throughput": 554.95, "total_tokens": 31204384} {"current_steps": 19110, "total_steps": 40000, "loss": 0.1426, "lr": 2.6748046879192052e-05, "epoch": 0.8651169107494511, "percentage": 47.77, "elapsed_time": "15:37:12", "remaining_time": "17:04:30", "throughput": 555.06, "total_tokens": 31212352} {"current_steps": 19115, "total_steps": 40000, "loss": 0.1164, "lr": 2.673825329618071e-05, "epoch": 0.8653432626360941, "percentage": 47.79, "elapsed_time": "15:37:15", "remaining_time": "17:04:02", "throughput": 555.18, "total_tokens": 31220608} {"current_steps": 19120, "total_steps": 40000, "loss": 0.1265, "lr": 2.6728459445108866e-05, "epoch": 0.8655696145227371, "percentage": 47.8, "elapsed_time": "15:37:18", "remaining_time": "17:03:35", "throughput": 555.3, "total_tokens": 31229088} {"current_steps": 19125, "total_steps": 40000, "loss": 0.0911, "lr": 2.6718665327486854e-05, "epoch": 0.8657959664093801, "percentage": 47.81, "elapsed_time": "15:37:21", "remaining_time": "17:03:08", "throughput": 555.41, "total_tokens": 31237184} {"current_steps": 19130, "total_steps": 40000, "loss": 0.1332, "lr": 2.6708870944825048e-05, "epoch": 0.866022318296023, "percentage": 47.83, "elapsed_time": "15:37:25", "remaining_time": "17:02:40", "throughput": 555.52, "total_tokens": 31245504} {"current_steps": 19135, "total_steps": 40000, "loss": 0.1633, "lr": 2.6699076298633874e-05, "epoch": 0.8662486701826659, "percentage": 47.84, "elapsed_time": "15:37:28", "remaining_time": "17:02:13", "throughput": 555.64, "total_tokens": 31253856} {"current_steps": 19140, "total_steps": 40000, "loss": 0.1512, "lr": 2.6689281390423788e-05, "epoch": 0.8664750220693089, "percentage": 47.85, "elapsed_time": "15:37:31", "remaining_time": "17:01:46", "throughput": 555.76, "total_tokens": 31262400} {"current_steps": 19145, "total_steps": 40000, "loss": 0.1505, "lr": 2.667948622170527e-05, "epoch": 0.8667013739559519, "percentage": 47.86, "elapsed_time": "15:37:34", "remaining_time": "17:01:19", "throughput": 555.88, "total_tokens": 31270624} {"current_steps": 19150, "total_steps": 40000, "loss": 0.1368, "lr": 2.6669690793988873e-05, "epoch": 0.8669277258425949, "percentage": 47.88, "elapsed_time": "15:37:37", "remaining_time": "17:00:52", "throughput": 555.99, "total_tokens": 31278848} {"current_steps": 19155, "total_steps": 40000, "loss": 0.1023, "lr": 2.665989510878518e-05, "epoch": 0.8671540777292379, "percentage": 47.89, "elapsed_time": "15:37:41", "remaining_time": "17:00:24", "throughput": 556.1, "total_tokens": 31287008} {"current_steps": 19160, "total_steps": 40000, "loss": 0.1469, "lr": 2.6650099167604793e-05, "epoch": 0.8673804296158808, "percentage": 47.9, "elapsed_time": "15:37:44", "remaining_time": "16:59:57", "throughput": 556.22, "total_tokens": 31295104} {"current_steps": 19165, "total_steps": 40000, "loss": 0.148, "lr": 2.6640302971958376e-05, "epoch": 0.8676067815025238, "percentage": 47.91, "elapsed_time": "15:37:47", "remaining_time": "16:59:30", "throughput": 556.33, "total_tokens": 31303200} {"current_steps": 19170, "total_steps": 40000, "loss": 0.1673, "lr": 2.6630506523356635e-05, "epoch": 0.8678331333891668, "percentage": 47.93, "elapsed_time": "15:37:50", "remaining_time": "16:59:03", "throughput": 556.43, "total_tokens": 31310656} {"current_steps": 19175, "total_steps": 40000, "loss": 0.1224, "lr": 2.6620709823310297e-05, "epoch": 0.8680594852758098, "percentage": 47.94, "elapsed_time": "15:37:53", "remaining_time": "16:58:35", "throughput": 556.54, "total_tokens": 31318496} {"current_steps": 19180, "total_steps": 40000, "loss": 0.1183, "lr": 2.661091287333014e-05, "epoch": 0.8682858371624528, "percentage": 47.95, "elapsed_time": "15:37:56", "remaining_time": "16:58:08", "throughput": 556.66, "total_tokens": 31327200} {"current_steps": 19185, "total_steps": 40000, "loss": 0.102, "lr": 2.660111567492696e-05, "epoch": 0.8685121890490958, "percentage": 47.96, "elapsed_time": "15:38:00", "remaining_time": "16:57:41", "throughput": 556.77, "total_tokens": 31335264} {"current_steps": 19190, "total_steps": 40000, "loss": 0.0798, "lr": 2.6591318229611635e-05, "epoch": 0.8687385409357387, "percentage": 47.98, "elapsed_time": "15:38:03", "remaining_time": "16:57:14", "throughput": 556.89, "total_tokens": 31343424} {"current_steps": 19195, "total_steps": 40000, "loss": 0.1227, "lr": 2.6581520538895037e-05, "epoch": 0.8689648928223817, "percentage": 47.99, "elapsed_time": "15:38:06", "remaining_time": "16:56:47", "throughput": 557.01, "total_tokens": 31352320} {"current_steps": 19200, "total_steps": 40000, "loss": 0.1207, "lr": 2.6571722604288102e-05, "epoch": 0.8691912447090246, "percentage": 48.0, "elapsed_time": "15:38:09", "remaining_time": "16:56:20", "throughput": 557.12, "total_tokens": 31360256} {"current_steps": 19200, "total_steps": 40000, "eval_loss": 0.12684115767478943, "epoch": 0.8691912447090246, "percentage": 48.0, "elapsed_time": "15:45:52", "remaining_time": "17:04:41", "throughput": 552.58, "total_tokens": 31360256} {"current_steps": 19205, "total_steps": 40000, "loss": 0.0923, "lr": 2.656192442730179e-05, "epoch": 0.8694175965956676, "percentage": 48.01, "elapsed_time": "15:45:56", "remaining_time": "17:04:15", "throughput": 552.69, "total_tokens": 31368832} {"current_steps": 19210, "total_steps": 40000, "loss": 0.1655, "lr": 2.6552126009447098e-05, "epoch": 0.8696439484823106, "percentage": 48.02, "elapsed_time": "15:45:59", "remaining_time": "17:03:47", "throughput": 552.8, "total_tokens": 31376928} {"current_steps": 19215, "total_steps": 40000, "loss": 0.108, "lr": 2.654232735223507e-05, "epoch": 0.8698703003689536, "percentage": 48.04, "elapsed_time": "15:46:02", "remaining_time": "17:03:20", "throughput": 552.92, "total_tokens": 31384992} {"current_steps": 19220, "total_steps": 40000, "loss": 0.0894, "lr": 2.6532528457176787e-05, "epoch": 0.8700966522555965, "percentage": 48.05, "elapsed_time": "15:46:05", "remaining_time": "17:02:53", "throughput": 553.03, "total_tokens": 31393056} {"current_steps": 19225, "total_steps": 40000, "loss": 0.1439, "lr": 2.6522729325783348e-05, "epoch": 0.8703230041422395, "percentage": 48.06, "elapsed_time": "15:46:09", "remaining_time": "17:02:26", "throughput": 553.15, "total_tokens": 31401632} {"current_steps": 19230, "total_steps": 40000, "loss": 0.1295, "lr": 2.6512929959565914e-05, "epoch": 0.8705493560288825, "percentage": 48.08, "elapsed_time": "15:46:12", "remaining_time": "17:01:59", "throughput": 553.27, "total_tokens": 31410336} {"current_steps": 19235, "total_steps": 40000, "loss": 0.1964, "lr": 2.6503130360035673e-05, "epoch": 0.8707757079155255, "percentage": 48.09, "elapsed_time": "15:46:15", "remaining_time": "17:01:31", "throughput": 553.37, "total_tokens": 31418048} {"current_steps": 19240, "total_steps": 40000, "loss": 0.1288, "lr": 2.6493330528703835e-05, "epoch": 0.8710020598021685, "percentage": 48.1, "elapsed_time": "15:46:18", "remaining_time": "17:01:04", "throughput": 553.5, "total_tokens": 31426944} {"current_steps": 19245, "total_steps": 40000, "loss": 0.1587, "lr": 2.648353046708167e-05, "epoch": 0.8712284116888114, "percentage": 48.11, "elapsed_time": "15:46:22", "remaining_time": "17:00:37", "throughput": 553.6, "total_tokens": 31434688} {"current_steps": 19250, "total_steps": 40000, "loss": 0.127, "lr": 2.647373017668046e-05, "epoch": 0.8714547635754544, "percentage": 48.12, "elapsed_time": "15:46:25", "remaining_time": "17:00:10", "throughput": 553.72, "total_tokens": 31442848} {"current_steps": 19255, "total_steps": 40000, "loss": 0.1123, "lr": 2.6463929659011537e-05, "epoch": 0.8716811154620974, "percentage": 48.14, "elapsed_time": "15:46:28", "remaining_time": "16:59:42", "throughput": 553.82, "total_tokens": 31450368} {"current_steps": 19260, "total_steps": 40000, "loss": 0.1584, "lr": 2.6454128915586262e-05, "epoch": 0.8719074673487404, "percentage": 48.15, "elapsed_time": "15:46:31", "remaining_time": "16:59:15", "throughput": 553.93, "total_tokens": 31458496} {"current_steps": 19265, "total_steps": 40000, "loss": 0.0757, "lr": 2.6444327947916036e-05, "epoch": 0.8721338192353834, "percentage": 48.16, "elapsed_time": "15:46:34", "remaining_time": "16:58:48", "throughput": 554.03, "total_tokens": 31466080} {"current_steps": 19270, "total_steps": 40000, "loss": 0.126, "lr": 2.6434526757512292e-05, "epoch": 0.8723601711220264, "percentage": 48.18, "elapsed_time": "15:46:37", "remaining_time": "16:58:21", "throughput": 554.14, "total_tokens": 31474080} {"current_steps": 19275, "total_steps": 40000, "loss": 0.1048, "lr": 2.6424725345886486e-05, "epoch": 0.8725865230086692, "percentage": 48.19, "elapsed_time": "15:46:40", "remaining_time": "16:57:53", "throughput": 554.25, "total_tokens": 31482080} {"current_steps": 19280, "total_steps": 40000, "loss": 0.094, "lr": 2.641492371455014e-05, "epoch": 0.8728128748953122, "percentage": 48.2, "elapsed_time": "15:46:43", "remaining_time": "16:57:26", "throughput": 554.36, "total_tokens": 31490112} {"current_steps": 19285, "total_steps": 40000, "loss": 0.1431, "lr": 2.640512186501477e-05, "epoch": 0.8730392267819552, "percentage": 48.21, "elapsed_time": "15:46:47", "remaining_time": "16:56:59", "throughput": 554.47, "total_tokens": 31497888} {"current_steps": 19290, "total_steps": 40000, "loss": 0.1197, "lr": 2.639531979879195e-05, "epoch": 0.8732655786685982, "percentage": 48.23, "elapsed_time": "15:46:50", "remaining_time": "16:56:32", "throughput": 554.59, "total_tokens": 31506400} {"current_steps": 19295, "total_steps": 40000, "loss": 0.1177, "lr": 2.638551751739328e-05, "epoch": 0.8734919305552412, "percentage": 48.24, "elapsed_time": "15:46:53", "remaining_time": "16:56:05", "throughput": 554.71, "total_tokens": 31515040} {"current_steps": 19300, "total_steps": 40000, "loss": 0.1794, "lr": 2.6375715022330404e-05, "epoch": 0.8737182824418841, "percentage": 48.25, "elapsed_time": "15:46:56", "remaining_time": "16:55:38", "throughput": 554.81, "total_tokens": 31522688} {"current_steps": 19305, "total_steps": 40000, "loss": 0.1322, "lr": 2.6365912315114976e-05, "epoch": 0.8739446343285271, "percentage": 48.26, "elapsed_time": "15:47:00", "remaining_time": "16:55:11", "throughput": 554.94, "total_tokens": 31531552} {"current_steps": 19310, "total_steps": 40000, "loss": 0.1136, "lr": 2.6356109397258704e-05, "epoch": 0.8741709862151701, "percentage": 48.27, "elapsed_time": "15:47:03", "remaining_time": "16:54:44", "throughput": 555.05, "total_tokens": 31539968} {"current_steps": 19315, "total_steps": 40000, "loss": 0.1393, "lr": 2.6346306270273325e-05, "epoch": 0.8743973381018131, "percentage": 48.29, "elapsed_time": "15:47:06", "remaining_time": "16:54:16", "throughput": 555.16, "total_tokens": 31547488} {"current_steps": 19320, "total_steps": 40000, "loss": 0.1395, "lr": 2.6336502935670608e-05, "epoch": 0.8746236899884561, "percentage": 48.3, "elapsed_time": "15:47:09", "remaining_time": "16:53:49", "throughput": 555.27, "total_tokens": 31555840} {"current_steps": 19325, "total_steps": 40000, "loss": 0.1419, "lr": 2.6326699394962333e-05, "epoch": 0.8748500418750991, "percentage": 48.31, "elapsed_time": "15:47:12", "remaining_time": "16:53:22", "throughput": 555.39, "total_tokens": 31564160} {"current_steps": 19330, "total_steps": 40000, "loss": 0.0987, "lr": 2.6316895649660334e-05, "epoch": 0.875076393761742, "percentage": 48.33, "elapsed_time": "15:47:15", "remaining_time": "16:52:55", "throughput": 555.5, "total_tokens": 31572416} {"current_steps": 19335, "total_steps": 40000, "loss": 0.1442, "lr": 2.6307091701276486e-05, "epoch": 0.875302745648385, "percentage": 48.34, "elapsed_time": "15:47:18", "remaining_time": "16:52:28", "throughput": 555.61, "total_tokens": 31580192} {"current_steps": 19340, "total_steps": 40000, "loss": 0.1176, "lr": 2.629728755132267e-05, "epoch": 0.875529097535028, "percentage": 48.35, "elapsed_time": "15:47:22", "remaining_time": "16:52:01", "throughput": 555.72, "total_tokens": 31588128} {"current_steps": 19345, "total_steps": 40000, "loss": 0.0921, "lr": 2.628748320131081e-05, "epoch": 0.8757554494216709, "percentage": 48.36, "elapsed_time": "15:47:25", "remaining_time": "16:51:34", "throughput": 555.83, "total_tokens": 31596288} {"current_steps": 19350, "total_steps": 40000, "loss": 0.1156, "lr": 2.6277678652752856e-05, "epoch": 0.8759818013083139, "percentage": 48.38, "elapsed_time": "15:47:28", "remaining_time": "16:51:07", "throughput": 555.94, "total_tokens": 31604160} {"current_steps": 19355, "total_steps": 40000, "loss": 0.1427, "lr": 2.6267873907160807e-05, "epoch": 0.8762081531949569, "percentage": 48.39, "elapsed_time": "15:47:31", "remaining_time": "16:50:40", "throughput": 556.05, "total_tokens": 31612352} {"current_steps": 19360, "total_steps": 40000, "loss": 0.0875, "lr": 2.6258068966046668e-05, "epoch": 0.8764345050815998, "percentage": 48.4, "elapsed_time": "15:47:34", "remaining_time": "16:50:13", "throughput": 556.17, "total_tokens": 31620800} {"current_steps": 19365, "total_steps": 40000, "loss": 0.1209, "lr": 2.6248263830922475e-05, "epoch": 0.8766608569682428, "percentage": 48.41, "elapsed_time": "15:47:37", "remaining_time": "16:49:46", "throughput": 556.27, "total_tokens": 31628192} {"current_steps": 19370, "total_steps": 40000, "loss": 0.1045, "lr": 2.6238458503300318e-05, "epoch": 0.8768872088548858, "percentage": 48.43, "elapsed_time": "15:47:40", "remaining_time": "16:49:19", "throughput": 556.38, "total_tokens": 31636128} {"current_steps": 19375, "total_steps": 40000, "loss": 0.1172, "lr": 2.6228652984692292e-05, "epoch": 0.8771135607415288, "percentage": 48.44, "elapsed_time": "15:47:43", "remaining_time": "16:48:52", "throughput": 556.49, "total_tokens": 31644160} {"current_steps": 19380, "total_steps": 40000, "loss": 0.1261, "lr": 2.621884727661054e-05, "epoch": 0.8773399126281718, "percentage": 48.45, "elapsed_time": "15:47:47", "remaining_time": "16:48:25", "throughput": 556.6, "total_tokens": 31652160} {"current_steps": 19385, "total_steps": 40000, "loss": 0.1147, "lr": 2.6209041380567222e-05, "epoch": 0.8775662645148147, "percentage": 48.46, "elapsed_time": "15:47:50", "remaining_time": "16:47:58", "throughput": 556.71, "total_tokens": 31660448} {"current_steps": 19390, "total_steps": 40000, "loss": 0.1604, "lr": 2.6199235298074527e-05, "epoch": 0.8777926164014577, "percentage": 48.48, "elapsed_time": "15:47:53", "remaining_time": "16:47:31", "throughput": 556.82, "total_tokens": 31668256} {"current_steps": 19395, "total_steps": 40000, "loss": 0.1061, "lr": 2.618942903064468e-05, "epoch": 0.8780189682881007, "percentage": 48.49, "elapsed_time": "15:47:56", "remaining_time": "16:47:05", "throughput": 556.93, "total_tokens": 31676480} {"current_steps": 19400, "total_steps": 40000, "loss": 0.1399, "lr": 2.6179622579789932e-05, "epoch": 0.8782453201747437, "percentage": 48.5, "elapsed_time": "15:47:59", "remaining_time": "16:46:38", "throughput": 557.05, "total_tokens": 31685120} {"current_steps": 19400, "total_steps": 40000, "eval_loss": 0.12701544165611267, "epoch": 0.8782453201747437, "percentage": 48.5, "elapsed_time": "15:55:42", "remaining_time": "16:54:49", "throughput": 552.56, "total_tokens": 31685120} {"current_steps": 19405, "total_steps": 40000, "loss": 0.0948, "lr": 2.6169815947022553e-05, "epoch": 0.8784716720613867, "percentage": 48.51, "elapsed_time": "15:55:46", "remaining_time": "16:54:23", "throughput": 552.66, "total_tokens": 31693344} {"current_steps": 19410, "total_steps": 40000, "loss": 0.1731, "lr": 2.6160009133854853e-05, "epoch": 0.8786980239480296, "percentage": 48.52, "elapsed_time": "15:55:49", "remaining_time": "16:53:56", "throughput": 552.78, "total_tokens": 31701568} {"current_steps": 19415, "total_steps": 40000, "loss": 0.1141, "lr": 2.6150202141799168e-05, "epoch": 0.8789243758346725, "percentage": 48.54, "elapsed_time": "15:55:52", "remaining_time": "16:53:29", "throughput": 552.89, "total_tokens": 31709568} {"current_steps": 19420, "total_steps": 40000, "loss": 0.0935, "lr": 2.614039497236786e-05, "epoch": 0.8791507277213155, "percentage": 48.55, "elapsed_time": "15:55:55", "remaining_time": "16:53:01", "throughput": 553.0, "total_tokens": 31717696} {"current_steps": 19425, "total_steps": 40000, "loss": 0.123, "lr": 2.6130587627073315e-05, "epoch": 0.8793770796079585, "percentage": 48.56, "elapsed_time": "15:55:59", "remaining_time": "16:52:34", "throughput": 553.11, "total_tokens": 31725696} {"current_steps": 19430, "total_steps": 40000, "loss": 0.1256, "lr": 2.6120780107427956e-05, "epoch": 0.8796034314946015, "percentage": 48.58, "elapsed_time": "15:56:02", "remaining_time": "16:52:07", "throughput": 553.22, "total_tokens": 31734112} {"current_steps": 19435, "total_steps": 40000, "loss": 0.1262, "lr": 2.6110972414944214e-05, "epoch": 0.8798297833812445, "percentage": 48.59, "elapsed_time": "15:56:05", "remaining_time": "16:51:40", "throughput": 553.33, "total_tokens": 31742368} {"current_steps": 19440, "total_steps": 40000, "loss": 0.1663, "lr": 2.6101164551134565e-05, "epoch": 0.8800561352678875, "percentage": 48.6, "elapsed_time": "15:56:08", "remaining_time": "16:51:13", "throughput": 553.44, "total_tokens": 31750112} {"current_steps": 19445, "total_steps": 40000, "loss": 0.158, "lr": 2.6091356517511505e-05, "epoch": 0.8802824871545304, "percentage": 48.61, "elapsed_time": "15:56:11", "remaining_time": "16:50:46", "throughput": 553.55, "total_tokens": 31757888} {"current_steps": 19450, "total_steps": 40000, "loss": 0.1487, "lr": 2.608154831558755e-05, "epoch": 0.8805088390411734, "percentage": 48.62, "elapsed_time": "15:56:14", "remaining_time": "16:50:19", "throughput": 553.66, "total_tokens": 31766080} {"current_steps": 19455, "total_steps": 40000, "loss": 0.1654, "lr": 2.607173994687526e-05, "epoch": 0.8807351909278164, "percentage": 48.64, "elapsed_time": "15:56:18", "remaining_time": "16:49:52", "throughput": 553.77, "total_tokens": 31774368} {"current_steps": 19460, "total_steps": 40000, "loss": 0.167, "lr": 2.6061931412887196e-05, "epoch": 0.8809615428144594, "percentage": 48.65, "elapsed_time": "15:56:21", "remaining_time": "16:49:25", "throughput": 553.87, "total_tokens": 31782048} {"current_steps": 19465, "total_steps": 40000, "loss": 0.0894, "lr": 2.6052122715135973e-05, "epoch": 0.8811878947011024, "percentage": 48.66, "elapsed_time": "15:56:24", "remaining_time": "16:48:58", "throughput": 553.98, "total_tokens": 31789888} {"current_steps": 19470, "total_steps": 40000, "loss": 0.1176, "lr": 2.60423138551342e-05, "epoch": 0.8814142465877453, "percentage": 48.68, "elapsed_time": "15:56:27", "remaining_time": "16:48:31", "throughput": 554.09, "total_tokens": 31797664} {"current_steps": 19475, "total_steps": 40000, "loss": 0.0857, "lr": 2.6032504834394527e-05, "epoch": 0.8816405984743882, "percentage": 48.69, "elapsed_time": "15:56:30", "remaining_time": "16:48:04", "throughput": 554.2, "total_tokens": 31806016} {"current_steps": 19480, "total_steps": 40000, "loss": 0.1705, "lr": 2.602269565442964e-05, "epoch": 0.8818669503610312, "percentage": 48.7, "elapsed_time": "15:56:33", "remaining_time": "16:47:37", "throughput": 554.31, "total_tokens": 31813792} {"current_steps": 19485, "total_steps": 40000, "loss": 0.1414, "lr": 2.6012886316752227e-05, "epoch": 0.8820933022476742, "percentage": 48.71, "elapsed_time": "15:56:36", "remaining_time": "16:47:11", "throughput": 554.42, "total_tokens": 31821888} {"current_steps": 19490, "total_steps": 40000, "loss": 0.1212, "lr": 2.6003076822875018e-05, "epoch": 0.8823196541343172, "percentage": 48.73, "elapsed_time": "15:56:40", "remaining_time": "16:46:44", "throughput": 554.52, "total_tokens": 31829664} {"current_steps": 19495, "total_steps": 40000, "loss": 0.1193, "lr": 2.5993267174310755e-05, "epoch": 0.8825460060209602, "percentage": 48.74, "elapsed_time": "15:56:43", "remaining_time": "16:46:17", "throughput": 554.63, "total_tokens": 31837248} {"current_steps": 19500, "total_steps": 40000, "loss": 0.1368, "lr": 2.5983457372572218e-05, "epoch": 0.8827723579076031, "percentage": 48.75, "elapsed_time": "15:56:46", "remaining_time": "16:45:50", "throughput": 554.74, "total_tokens": 31845504} {"current_steps": 19505, "total_steps": 40000, "loss": 0.1251, "lr": 2.597364741917219e-05, "epoch": 0.8829987097942461, "percentage": 48.76, "elapsed_time": "15:56:49", "remaining_time": "16:45:23", "throughput": 554.85, "total_tokens": 31853632} {"current_steps": 19510, "total_steps": 40000, "loss": 0.1334, "lr": 2.5963837315623492e-05, "epoch": 0.8832250616808891, "percentage": 48.77, "elapsed_time": "15:56:52", "remaining_time": "16:44:56", "throughput": 554.97, "total_tokens": 31862176} {"current_steps": 19515, "total_steps": 40000, "loss": 0.129, "lr": 2.595402706343897e-05, "epoch": 0.8834514135675321, "percentage": 48.79, "elapsed_time": "15:56:55", "remaining_time": "16:44:29", "throughput": 555.08, "total_tokens": 31870240} {"current_steps": 19520, "total_steps": 40000, "loss": 0.1172, "lr": 2.594421666413148e-05, "epoch": 0.8836777654541751, "percentage": 48.8, "elapsed_time": "15:56:59", "remaining_time": "16:44:03", "throughput": 555.19, "total_tokens": 31878592} {"current_steps": 19525, "total_steps": 40000, "loss": 0.1204, "lr": 2.5934406119213928e-05, "epoch": 0.8839041173408181, "percentage": 48.81, "elapsed_time": "15:57:02", "remaining_time": "16:43:36", "throughput": 555.3, "total_tokens": 31886592} {"current_steps": 19530, "total_steps": 40000, "loss": 0.1514, "lr": 2.5924595430199193e-05, "epoch": 0.884130469227461, "percentage": 48.83, "elapsed_time": "15:57:05", "remaining_time": "16:43:09", "throughput": 555.41, "total_tokens": 31894464} {"current_steps": 19535, "total_steps": 40000, "loss": 0.1618, "lr": 2.5914784598600238e-05, "epoch": 0.884356821114104, "percentage": 48.84, "elapsed_time": "15:57:08", "remaining_time": "16:42:42", "throughput": 555.51, "total_tokens": 31902432} {"current_steps": 19540, "total_steps": 40000, "loss": 0.1066, "lr": 2.5904973625930002e-05, "epoch": 0.884583173000747, "percentage": 48.85, "elapsed_time": "15:57:11", "remaining_time": "16:42:15", "throughput": 555.63, "total_tokens": 31910592} {"current_steps": 19545, "total_steps": 40000, "loss": 0.1182, "lr": 2.5895162513701456e-05, "epoch": 0.88480952488739, "percentage": 48.86, "elapsed_time": "15:57:14", "remaining_time": "16:41:49", "throughput": 555.74, "total_tokens": 31919200} {"current_steps": 19550, "total_steps": 40000, "loss": 0.1316, "lr": 2.5885351263427593e-05, "epoch": 0.885035876774033, "percentage": 48.88, "elapsed_time": "15:57:18", "remaining_time": "16:41:22", "throughput": 555.86, "total_tokens": 31927424} {"current_steps": 19555, "total_steps": 40000, "loss": 0.1521, "lr": 2.5875539876621448e-05, "epoch": 0.8852622286606758, "percentage": 48.89, "elapsed_time": "15:57:21", "remaining_time": "16:40:55", "throughput": 555.96, "total_tokens": 31935168} {"current_steps": 19560, "total_steps": 40000, "loss": 0.1283, "lr": 2.586572835479605e-05, "epoch": 0.8854885805473188, "percentage": 48.9, "elapsed_time": "15:57:24", "remaining_time": "16:40:28", "throughput": 556.07, "total_tokens": 31942944} {"current_steps": 19565, "total_steps": 40000, "loss": 0.1187, "lr": 2.585591669946446e-05, "epoch": 0.8857149324339618, "percentage": 48.91, "elapsed_time": "15:57:27", "remaining_time": "16:40:02", "throughput": 556.18, "total_tokens": 31951264} {"current_steps": 19570, "total_steps": 40000, "loss": 0.1234, "lr": 2.5846104912139756e-05, "epoch": 0.8859412843206048, "percentage": 48.93, "elapsed_time": "15:57:30", "remaining_time": "16:39:35", "throughput": 556.3, "total_tokens": 31959648} {"current_steps": 19575, "total_steps": 40000, "loss": 0.1174, "lr": 2.583629299433505e-05, "epoch": 0.8861676362072478, "percentage": 48.94, "elapsed_time": "15:57:33", "remaining_time": "16:39:08", "throughput": 556.41, "total_tokens": 31967968} {"current_steps": 19580, "total_steps": 40000, "loss": 0.1632, "lr": 2.582648094756345e-05, "epoch": 0.8863939880938908, "percentage": 48.95, "elapsed_time": "15:57:37", "remaining_time": "16:38:41", "throughput": 556.52, "total_tokens": 31975712} {"current_steps": 19585, "total_steps": 40000, "loss": 0.1282, "lr": 2.5816668773338098e-05, "epoch": 0.8866203399805337, "percentage": 48.96, "elapsed_time": "15:57:40", "remaining_time": "16:38:15", "throughput": 556.63, "total_tokens": 31983776} {"current_steps": 19590, "total_steps": 40000, "loss": 0.086, "lr": 2.580685647317216e-05, "epoch": 0.8868466918671767, "percentage": 48.98, "elapsed_time": "15:57:43", "remaining_time": "16:37:48", "throughput": 556.74, "total_tokens": 31992320} {"current_steps": 19595, "total_steps": 40000, "loss": 0.1062, "lr": 2.5797044048578818e-05, "epoch": 0.8870730437538197, "percentage": 48.99, "elapsed_time": "15:57:46", "remaining_time": "16:37:22", "throughput": 556.85, "total_tokens": 32000192} {"current_steps": 19600, "total_steps": 40000, "loss": 0.1407, "lr": 2.5787231501071262e-05, "epoch": 0.8872993956404627, "percentage": 49.0, "elapsed_time": "15:57:49", "remaining_time": "16:36:55", "throughput": 556.96, "total_tokens": 32008192} {"current_steps": 19600, "total_steps": 40000, "eval_loss": 0.1263018250465393, "epoch": 0.8872993956404627, "percentage": 49.0, "elapsed_time": "16:05:32", "remaining_time": "16:44:56", "throughput": 552.51, "total_tokens": 32008192} {"current_steps": 19605, "total_steps": 40000, "loss": 0.1307, "lr": 2.577741883216272e-05, "epoch": 0.8875257475271057, "percentage": 49.01, "elapsed_time": "16:05:36", "remaining_time": "16:44:31", "throughput": 552.61, "total_tokens": 32016352} {"current_steps": 19610, "total_steps": 40000, "loss": 0.1635, "lr": 2.576760604336642e-05, "epoch": 0.8877520994137487, "percentage": 49.02, "elapsed_time": "16:05:39", "remaining_time": "16:44:04", "throughput": 552.72, "total_tokens": 32024288} {"current_steps": 19615, "total_steps": 40000, "loss": 0.1107, "lr": 2.575779313619563e-05, "epoch": 0.8879784513003915, "percentage": 49.04, "elapsed_time": "16:05:42", "remaining_time": "16:43:37", "throughput": 552.82, "total_tokens": 32032032} {"current_steps": 19620, "total_steps": 40000, "loss": 0.0992, "lr": 2.5747980112163605e-05, "epoch": 0.8882048031870345, "percentage": 49.05, "elapsed_time": "16:05:45", "remaining_time": "16:43:10", "throughput": 552.93, "total_tokens": 32040192} {"current_steps": 19625, "total_steps": 40000, "loss": 0.1071, "lr": 2.5738166972783656e-05, "epoch": 0.8884311550736775, "percentage": 49.06, "elapsed_time": "16:05:48", "remaining_time": "16:42:43", "throughput": 553.04, "total_tokens": 32047936} {"current_steps": 19630, "total_steps": 40000, "loss": 0.1493, "lr": 2.5728353719569075e-05, "epoch": 0.8886575069603205, "percentage": 49.08, "elapsed_time": "16:05:52", "remaining_time": "16:42:16", "throughput": 553.15, "total_tokens": 32055968} {"current_steps": 19635, "total_steps": 40000, "loss": 0.0659, "lr": 2.57185403540332e-05, "epoch": 0.8888838588469635, "percentage": 49.09, "elapsed_time": "16:05:55", "remaining_time": "16:41:49", "throughput": 553.26, "total_tokens": 32064448} {"current_steps": 19640, "total_steps": 40000, "loss": 0.1834, "lr": 2.5708726877689375e-05, "epoch": 0.8891102107336064, "percentage": 49.1, "elapsed_time": "16:05:58", "remaining_time": "16:41:23", "throughput": 553.38, "total_tokens": 32073120} {"current_steps": 19645, "total_steps": 40000, "loss": 0.1181, "lr": 2.5698913292050964e-05, "epoch": 0.8893365626202494, "percentage": 49.11, "elapsed_time": "16:06:01", "remaining_time": "16:40:56", "throughput": 553.49, "total_tokens": 32081408} {"current_steps": 19650, "total_steps": 40000, "loss": 0.1259, "lr": 2.568909959863133e-05, "epoch": 0.8895629145068924, "percentage": 49.12, "elapsed_time": "16:06:04", "remaining_time": "16:40:29", "throughput": 553.6, "total_tokens": 32089312} {"current_steps": 19655, "total_steps": 40000, "loss": 0.1016, "lr": 2.5679285798943887e-05, "epoch": 0.8897892663935354, "percentage": 49.14, "elapsed_time": "16:06:07", "remaining_time": "16:40:02", "throughput": 553.71, "total_tokens": 32097280} {"current_steps": 19660, "total_steps": 40000, "loss": 0.1185, "lr": 2.5669471894502035e-05, "epoch": 0.8900156182801784, "percentage": 49.15, "elapsed_time": "16:06:11", "remaining_time": "16:39:36", "throughput": 553.81, "total_tokens": 32104928} {"current_steps": 19665, "total_steps": 40000, "loss": 0.0843, "lr": 2.56596578868192e-05, "epoch": 0.8902419701668214, "percentage": 49.16, "elapsed_time": "16:06:14", "remaining_time": "16:39:09", "throughput": 553.93, "total_tokens": 32113504} {"current_steps": 19670, "total_steps": 40000, "loss": 0.0952, "lr": 2.564984377740883e-05, "epoch": 0.8904683220534643, "percentage": 49.18, "elapsed_time": "16:06:17", "remaining_time": "16:38:42", "throughput": 554.05, "total_tokens": 32122208} {"current_steps": 19675, "total_steps": 40000, "loss": 0.1012, "lr": 2.564002956778438e-05, "epoch": 0.8906946739401073, "percentage": 49.19, "elapsed_time": "16:06:20", "remaining_time": "16:38:16", "throughput": 554.15, "total_tokens": 32130208} {"current_steps": 19680, "total_steps": 40000, "loss": 0.1536, "lr": 2.563021525945934e-05, "epoch": 0.8909210258267503, "percentage": 49.2, "elapsed_time": "16:06:23", "remaining_time": "16:37:49", "throughput": 554.26, "total_tokens": 32138080} {"current_steps": 19685, "total_steps": 40000, "loss": 0.1928, "lr": 2.562040085394718e-05, "epoch": 0.8911473777133933, "percentage": 49.21, "elapsed_time": "16:06:26", "remaining_time": "16:37:22", "throughput": 554.37, "total_tokens": 32146176} {"current_steps": 19690, "total_steps": 40000, "loss": 0.1736, "lr": 2.56105863527614e-05, "epoch": 0.8913737296000362, "percentage": 49.23, "elapsed_time": "16:06:30", "remaining_time": "16:36:56", "throughput": 554.48, "total_tokens": 32154304} {"current_steps": 19695, "total_steps": 40000, "loss": 0.1256, "lr": 2.5600771757415548e-05, "epoch": 0.8916000814866792, "percentage": 49.24, "elapsed_time": "16:06:33", "remaining_time": "16:36:29", "throughput": 554.6, "total_tokens": 32163040} {"current_steps": 19700, "total_steps": 40000, "loss": 0.1423, "lr": 2.5590957069423134e-05, "epoch": 0.8918264333733221, "percentage": 49.25, "elapsed_time": "16:06:36", "remaining_time": "16:36:02", "throughput": 554.7, "total_tokens": 32170688} {"current_steps": 19705, "total_steps": 40000, "loss": 0.1275, "lr": 2.5581142290297716e-05, "epoch": 0.8920527852599651, "percentage": 49.26, "elapsed_time": "16:06:39", "remaining_time": "16:35:36", "throughput": 554.81, "total_tokens": 32178816} {"current_steps": 19710, "total_steps": 40000, "loss": 0.1513, "lr": 2.557132742155285e-05, "epoch": 0.8922791371466081, "percentage": 49.28, "elapsed_time": "16:06:42", "remaining_time": "16:35:09", "throughput": 554.92, "total_tokens": 32187232} {"current_steps": 19715, "total_steps": 40000, "loss": 0.1525, "lr": 2.556151246470212e-05, "epoch": 0.8925054890332511, "percentage": 49.29, "elapsed_time": "16:06:46", "remaining_time": "16:34:43", "throughput": 555.02, "total_tokens": 32194688} {"current_steps": 19720, "total_steps": 40000, "loss": 0.1735, "lr": 2.5551697421259114e-05, "epoch": 0.8927318409198941, "percentage": 49.3, "elapsed_time": "16:06:49", "remaining_time": "16:34:16", "throughput": 555.13, "total_tokens": 32202688} {"current_steps": 19725, "total_steps": 40000, "loss": 0.1146, "lr": 2.554188229273743e-05, "epoch": 0.892958192806537, "percentage": 49.31, "elapsed_time": "16:06:52", "remaining_time": "16:33:50", "throughput": 555.25, "total_tokens": 32211328} {"current_steps": 19730, "total_steps": 40000, "loss": 0.1269, "lr": 2.5532067080650678e-05, "epoch": 0.89318454469318, "percentage": 49.33, "elapsed_time": "16:06:55", "remaining_time": "16:33:23", "throughput": 555.36, "total_tokens": 32219680} {"current_steps": 19735, "total_steps": 40000, "loss": 0.1043, "lr": 2.55222517865125e-05, "epoch": 0.893410896579823, "percentage": 49.34, "elapsed_time": "16:06:58", "remaining_time": "16:32:57", "throughput": 555.47, "total_tokens": 32227840} {"current_steps": 19740, "total_steps": 40000, "loss": 0.1416, "lr": 2.5512436411836538e-05, "epoch": 0.893637248466466, "percentage": 49.35, "elapsed_time": "16:07:02", "remaining_time": "16:32:30", "throughput": 555.58, "total_tokens": 32236096} {"current_steps": 19745, "total_steps": 40000, "loss": 0.1347, "lr": 2.5502620958136443e-05, "epoch": 0.893863600353109, "percentage": 49.36, "elapsed_time": "16:07:05", "remaining_time": "16:32:04", "throughput": 555.7, "total_tokens": 32244736} {"current_steps": 19750, "total_steps": 40000, "loss": 0.1428, "lr": 2.5492805426925874e-05, "epoch": 0.894089952239752, "percentage": 49.38, "elapsed_time": "16:07:08", "remaining_time": "16:31:37", "throughput": 555.81, "total_tokens": 32252576} {"current_steps": 19755, "total_steps": 40000, "loss": 0.0857, "lr": 2.5482989819718523e-05, "epoch": 0.8943163041263948, "percentage": 49.39, "elapsed_time": "16:07:11", "remaining_time": "16:31:10", "throughput": 555.91, "total_tokens": 32260224} {"current_steps": 19760, "total_steps": 40000, "loss": 0.1024, "lr": 2.5473174138028065e-05, "epoch": 0.8945426560130378, "percentage": 49.4, "elapsed_time": "16:07:14", "remaining_time": "16:30:44", "throughput": 556.02, "total_tokens": 32268384} {"current_steps": 19765, "total_steps": 40000, "loss": 0.0828, "lr": 2.5463358383368212e-05, "epoch": 0.8947690078996808, "percentage": 49.41, "elapsed_time": "16:07:17", "remaining_time": "16:30:18", "throughput": 556.12, "total_tokens": 32276288} {"current_steps": 19770, "total_steps": 40000, "loss": 0.1059, "lr": 2.545354255725267e-05, "epoch": 0.8949953597863238, "percentage": 49.43, "elapsed_time": "16:07:21", "remaining_time": "16:29:51", "throughput": 556.24, "total_tokens": 32284768} {"current_steps": 19775, "total_steps": 40000, "loss": 0.1511, "lr": 2.5443726661195165e-05, "epoch": 0.8952217116729668, "percentage": 49.44, "elapsed_time": "16:07:24", "remaining_time": "16:29:25", "throughput": 556.36, "total_tokens": 32293536} {"current_steps": 19780, "total_steps": 40000, "loss": 0.1158, "lr": 2.543391069670944e-05, "epoch": 0.8954480635596098, "percentage": 49.45, "elapsed_time": "16:07:27", "remaining_time": "16:28:58", "throughput": 556.47, "total_tokens": 32302016} {"current_steps": 19785, "total_steps": 40000, "loss": 0.1581, "lr": 2.5424094665309228e-05, "epoch": 0.8956744154462527, "percentage": 49.46, "elapsed_time": "16:07:30", "remaining_time": "16:28:32", "throughput": 556.59, "total_tokens": 32310304} {"current_steps": 19790, "total_steps": 40000, "loss": 0.0802, "lr": 2.5414278568508292e-05, "epoch": 0.8959007673328957, "percentage": 49.48, "elapsed_time": "16:07:34", "remaining_time": "16:28:06", "throughput": 556.7, "total_tokens": 32318720} {"current_steps": 19795, "total_steps": 40000, "loss": 0.1278, "lr": 2.540446240782039e-05, "epoch": 0.8961271192195387, "percentage": 49.49, "elapsed_time": "16:07:37", "remaining_time": "16:27:39", "throughput": 556.81, "total_tokens": 32326656} {"current_steps": 19800, "total_steps": 40000, "loss": 0.1568, "lr": 2.5394646184759307e-05, "epoch": 0.8963534711061817, "percentage": 49.5, "elapsed_time": "16:07:40", "remaining_time": "16:27:13", "throughput": 556.92, "total_tokens": 32334784} {"current_steps": 19800, "total_steps": 40000, "eval_loss": 0.1268293857574463, "epoch": 0.8963534711061817, "percentage": 49.5, "elapsed_time": "16:15:23", "remaining_time": "16:35:05", "throughput": 552.51, "total_tokens": 32334784} {"current_steps": 19805, "total_steps": 40000, "loss": 0.1391, "lr": 2.538482990083882e-05, "epoch": 0.8965798229928247, "percentage": 49.51, "elapsed_time": "16:15:27", "remaining_time": "16:34:39", "throughput": 552.63, "total_tokens": 32343744} {"current_steps": 19810, "total_steps": 40000, "loss": 0.1474, "lr": 2.5375013557572725e-05, "epoch": 0.8968061748794676, "percentage": 49.53, "elapsed_time": "16:15:30", "remaining_time": "16:34:13", "throughput": 552.75, "total_tokens": 32352448} {"current_steps": 19815, "total_steps": 40000, "loss": 0.1147, "lr": 2.536519715647483e-05, "epoch": 0.8970325267661106, "percentage": 49.54, "elapsed_time": "16:15:33", "remaining_time": "16:33:46", "throughput": 552.85, "total_tokens": 32360000} {"current_steps": 19820, "total_steps": 40000, "loss": 0.1394, "lr": 2.535538069905894e-05, "epoch": 0.8972588786527536, "percentage": 49.55, "elapsed_time": "16:15:37", "remaining_time": "16:33:20", "throughput": 552.97, "total_tokens": 32369056} {"current_steps": 19825, "total_steps": 40000, "loss": 0.1441, "lr": 2.534556418683888e-05, "epoch": 0.8974852305393966, "percentage": 49.56, "elapsed_time": "16:15:40", "remaining_time": "16:32:53", "throughput": 553.09, "total_tokens": 32377920} {"current_steps": 19830, "total_steps": 40000, "loss": 0.1258, "lr": 2.5335747621328486e-05, "epoch": 0.8977115824260395, "percentage": 49.58, "elapsed_time": "16:15:43", "remaining_time": "16:32:27", "throughput": 553.19, "total_tokens": 32385952} {"current_steps": 19835, "total_steps": 40000, "loss": 0.14, "lr": 2.5325931004041586e-05, "epoch": 0.8979379343126825, "percentage": 49.59, "elapsed_time": "16:15:46", "remaining_time": "16:32:00", "throughput": 553.31, "total_tokens": 32394304} {"current_steps": 19840, "total_steps": 40000, "loss": 0.1544, "lr": 2.5316114336492032e-05, "epoch": 0.8981642861993254, "percentage": 49.6, "elapsed_time": "16:15:50", "remaining_time": "16:31:34", "throughput": 553.42, "total_tokens": 32402848} {"current_steps": 19845, "total_steps": 40000, "loss": 0.1695, "lr": 2.530629762019367e-05, "epoch": 0.8983906380859684, "percentage": 49.61, "elapsed_time": "16:15:53", "remaining_time": "16:31:07", "throughput": 553.53, "total_tokens": 32411104} {"current_steps": 19850, "total_steps": 40000, "loss": 0.1339, "lr": 2.5296480856660364e-05, "epoch": 0.8986169899726114, "percentage": 49.62, "elapsed_time": "16:15:56", "remaining_time": "16:30:41", "throughput": 553.64, "total_tokens": 32418912} {"current_steps": 19855, "total_steps": 40000, "loss": 0.1008, "lr": 2.528666404740599e-05, "epoch": 0.8988433418592544, "percentage": 49.64, "elapsed_time": "16:15:59", "remaining_time": "16:30:14", "throughput": 553.75, "total_tokens": 32427552} {"current_steps": 19860, "total_steps": 40000, "loss": 0.1647, "lr": 2.527684719394442e-05, "epoch": 0.8990696937458974, "percentage": 49.65, "elapsed_time": "16:16:02", "remaining_time": "16:29:48", "throughput": 553.86, "total_tokens": 32435328} {"current_steps": 19865, "total_steps": 40000, "loss": 0.1216, "lr": 2.526703029778953e-05, "epoch": 0.8992960456325404, "percentage": 49.66, "elapsed_time": "16:16:05", "remaining_time": "16:29:22", "throughput": 553.97, "total_tokens": 32443616} {"current_steps": 19870, "total_steps": 40000, "loss": 0.1371, "lr": 2.5257213360455208e-05, "epoch": 0.8995223975191833, "percentage": 49.68, "elapsed_time": "16:16:09", "remaining_time": "16:28:55", "throughput": 554.08, "total_tokens": 32452128} {"current_steps": 19875, "total_steps": 40000, "loss": 0.0959, "lr": 2.5247396383455353e-05, "epoch": 0.8997487494058263, "percentage": 49.69, "elapsed_time": "16:16:12", "remaining_time": "16:28:29", "throughput": 554.19, "total_tokens": 32460256} {"current_steps": 19880, "total_steps": 40000, "loss": 0.1028, "lr": 2.523757936830387e-05, "epoch": 0.8999751012924693, "percentage": 49.7, "elapsed_time": "16:16:15", "remaining_time": "16:28:02", "throughput": 554.3, "total_tokens": 32468352} {"current_steps": 19885, "total_steps": 40000, "loss": 0.1409, "lr": 2.5227762316514662e-05, "epoch": 0.9002014531791123, "percentage": 49.71, "elapsed_time": "16:16:18", "remaining_time": "16:27:36", "throughput": 554.42, "total_tokens": 32477056} {"current_steps": 19890, "total_steps": 40000, "loss": 0.1547, "lr": 2.5217945229601648e-05, "epoch": 0.9004278050657553, "percentage": 49.73, "elapsed_time": "16:16:21", "remaining_time": "16:27:09", "throughput": 554.52, "total_tokens": 32484736} {"current_steps": 19895, "total_steps": 40000, "loss": 0.1264, "lr": 2.5208128109078738e-05, "epoch": 0.9006541569523981, "percentage": 49.74, "elapsed_time": "16:16:25", "remaining_time": "16:26:43", "throughput": 554.62, "total_tokens": 32492768} {"current_steps": 19900, "total_steps": 40000, "loss": 0.1042, "lr": 2.5198310956459853e-05, "epoch": 0.9008805088390411, "percentage": 49.75, "elapsed_time": "16:16:28", "remaining_time": "16:26:17", "throughput": 554.73, "total_tokens": 32500704} {"current_steps": 19905, "total_steps": 40000, "loss": 0.0863, "lr": 2.518849377325893e-05, "epoch": 0.9011068607256841, "percentage": 49.76, "elapsed_time": "16:16:31", "remaining_time": "16:25:50", "throughput": 554.83, "total_tokens": 32508320} {"current_steps": 19910, "total_steps": 40000, "loss": 0.1278, "lr": 2.51786765609899e-05, "epoch": 0.9013332126123271, "percentage": 49.78, "elapsed_time": "16:16:34", "remaining_time": "16:25:24", "throughput": 554.94, "total_tokens": 32516512} {"current_steps": 19915, "total_steps": 40000, "loss": 0.0715, "lr": 2.5168859321166694e-05, "epoch": 0.9015595644989701, "percentage": 49.79, "elapsed_time": "16:16:37", "remaining_time": "16:24:57", "throughput": 555.04, "total_tokens": 32523936} {"current_steps": 19920, "total_steps": 40000, "loss": 0.1558, "lr": 2.515904205530326e-05, "epoch": 0.9017859163856131, "percentage": 49.8, "elapsed_time": "16:16:40", "remaining_time": "16:24:31", "throughput": 555.14, "total_tokens": 32531872} {"current_steps": 19925, "total_steps": 40000, "loss": 0.1477, "lr": 2.514922476491355e-05, "epoch": 0.902012268272256, "percentage": 49.81, "elapsed_time": "16:16:44", "remaining_time": "16:24:05", "throughput": 555.26, "total_tokens": 32540608} {"current_steps": 19930, "total_steps": 40000, "loss": 0.126, "lr": 2.51394074515115e-05, "epoch": 0.902238620158899, "percentage": 49.83, "elapsed_time": "16:16:47", "remaining_time": "16:23:38", "throughput": 555.36, "total_tokens": 32548160} {"current_steps": 19935, "total_steps": 40000, "loss": 0.1575, "lr": 2.5129590116611067e-05, "epoch": 0.902464972045542, "percentage": 49.84, "elapsed_time": "16:16:50", "remaining_time": "16:23:12", "throughput": 555.47, "total_tokens": 32556256} {"current_steps": 19940, "total_steps": 40000, "loss": 0.0931, "lr": 2.5119772761726212e-05, "epoch": 0.902691323932185, "percentage": 49.85, "elapsed_time": "16:16:53", "remaining_time": "16:22:46", "throughput": 555.58, "total_tokens": 32564608} {"current_steps": 19945, "total_steps": 40000, "loss": 0.1237, "lr": 2.5109955388370893e-05, "epoch": 0.902917675818828, "percentage": 49.86, "elapsed_time": "16:16:56", "remaining_time": "16:22:19", "throughput": 555.69, "total_tokens": 32572832} {"current_steps": 19950, "total_steps": 40000, "loss": 0.1013, "lr": 2.510013799805907e-05, "epoch": 0.903144027705471, "percentage": 49.88, "elapsed_time": "16:16:59", "remaining_time": "16:21:53", "throughput": 555.81, "total_tokens": 32581312} {"current_steps": 19955, "total_steps": 40000, "loss": 0.134, "lr": 2.5090320592304706e-05, "epoch": 0.9033703795921139, "percentage": 49.89, "elapsed_time": "16:17:03", "remaining_time": "16:21:27", "throughput": 555.92, "total_tokens": 32589824} {"current_steps": 19960, "total_steps": 40000, "loss": 0.14, "lr": 2.5080503172621777e-05, "epoch": 0.9035967314787569, "percentage": 49.9, "elapsed_time": "16:17:06", "remaining_time": "16:21:01", "throughput": 556.03, "total_tokens": 32597984} {"current_steps": 19965, "total_steps": 40000, "loss": 0.1534, "lr": 2.5070685740524246e-05, "epoch": 0.9038230833653998, "percentage": 49.91, "elapsed_time": "16:17:09", "remaining_time": "16:20:35", "throughput": 556.13, "total_tokens": 32605920} {"current_steps": 19970, "total_steps": 40000, "loss": 0.1448, "lr": 2.5060868297526084e-05, "epoch": 0.9040494352520428, "percentage": 49.93, "elapsed_time": "16:17:12", "remaining_time": "16:20:08", "throughput": 556.24, "total_tokens": 32613568} {"current_steps": 19975, "total_steps": 40000, "loss": 0.1089, "lr": 2.5051050845141267e-05, "epoch": 0.9042757871386858, "percentage": 49.94, "elapsed_time": "16:17:15", "remaining_time": "16:19:42", "throughput": 556.33, "total_tokens": 32621056} {"current_steps": 19980, "total_steps": 40000, "loss": 0.0904, "lr": 2.5041233384883765e-05, "epoch": 0.9045021390253287, "percentage": 49.95, "elapsed_time": "16:17:18", "remaining_time": "16:19:16", "throughput": 556.44, "total_tokens": 32629152} {"current_steps": 19985, "total_steps": 40000, "loss": 0.1516, "lr": 2.5031415918267564e-05, "epoch": 0.9047284909119717, "percentage": 49.96, "elapsed_time": "16:17:22", "remaining_time": "16:18:50", "throughput": 556.55, "total_tokens": 32637056} {"current_steps": 19990, "total_steps": 40000, "loss": 0.1631, "lr": 2.5021598446806626e-05, "epoch": 0.9049548427986147, "percentage": 49.98, "elapsed_time": "16:17:25", "remaining_time": "16:18:23", "throughput": 556.64, "total_tokens": 32644480} {"current_steps": 19995, "total_steps": 40000, "loss": 0.1052, "lr": 2.5011780972014937e-05, "epoch": 0.9051811946852577, "percentage": 49.99, "elapsed_time": "16:17:28", "remaining_time": "16:17:57", "throughput": 556.76, "total_tokens": 32653120} {"current_steps": 20000, "total_steps": 40000, "loss": 0.1549, "lr": 2.5001963495406478e-05, "epoch": 0.9054075465719007, "percentage": 50.0, "elapsed_time": "16:17:31", "remaining_time": "16:17:31", "throughput": 556.86, "total_tokens": 32660640} {"current_steps": 20000, "total_steps": 40000, "eval_loss": 0.12644487619400024, "epoch": 0.9054075465719007, "percentage": 50.0, "elapsed_time": "16:25:14", "remaining_time": "16:25:14", "throughput": 552.5, "total_tokens": 32660640} {"current_steps": 20005, "total_steps": 40000, "loss": 0.1098, "lr": 2.499214601849522e-05, "epoch": 0.9056338984585437, "percentage": 50.01, "elapsed_time": "16:25:18", "remaining_time": "16:24:48", "throughput": 552.6, "total_tokens": 32668896} {"current_steps": 20010, "total_steps": 40000, "loss": 0.1201, "lr": 2.4982328542795148e-05, "epoch": 0.9058602503451866, "percentage": 50.02, "elapsed_time": "16:25:21", "remaining_time": "16:24:22", "throughput": 552.7, "total_tokens": 32676704} {"current_steps": 20015, "total_steps": 40000, "loss": 0.1334, "lr": 2.497251106982024e-05, "epoch": 0.9060866022318296, "percentage": 50.04, "elapsed_time": "16:25:24", "remaining_time": "16:23:56", "throughput": 552.82, "total_tokens": 32685280} {"current_steps": 20020, "total_steps": 40000, "loss": 0.1158, "lr": 2.4962693601084458e-05, "epoch": 0.9063129541184726, "percentage": 50.05, "elapsed_time": "16:25:27", "remaining_time": "16:23:29", "throughput": 552.92, "total_tokens": 32693184} {"current_steps": 20025, "total_steps": 40000, "loss": 0.0906, "lr": 2.4952876138101794e-05, "epoch": 0.9065393060051156, "percentage": 50.06, "elapsed_time": "16:25:31", "remaining_time": "16:23:03", "throughput": 553.03, "total_tokens": 32701536} {"current_steps": 20030, "total_steps": 40000, "loss": 0.0716, "lr": 2.4943058682386233e-05, "epoch": 0.9067656578917586, "percentage": 50.08, "elapsed_time": "16:25:34", "remaining_time": "16:22:37", "throughput": 553.15, "total_tokens": 32709856} {"current_steps": 20035, "total_steps": 40000, "loss": 0.0903, "lr": 2.493324123545173e-05, "epoch": 0.9069920097784016, "percentage": 50.09, "elapsed_time": "16:25:37", "remaining_time": "16:22:10", "throughput": 553.26, "total_tokens": 32718144} {"current_steps": 20040, "total_steps": 40000, "loss": 0.1248, "lr": 2.4923423798812272e-05, "epoch": 0.9072183616650444, "percentage": 50.1, "elapsed_time": "16:25:40", "remaining_time": "16:21:44", "throughput": 553.36, "total_tokens": 32726144} {"current_steps": 20045, "total_steps": 40000, "loss": 0.1396, "lr": 2.4913606373981825e-05, "epoch": 0.9074447135516874, "percentage": 50.11, "elapsed_time": "16:25:43", "remaining_time": "16:21:18", "throughput": 553.46, "total_tokens": 32733888} {"current_steps": 20050, "total_steps": 40000, "loss": 0.1106, "lr": 2.4903788962474357e-05, "epoch": 0.9076710654383304, "percentage": 50.12, "elapsed_time": "16:25:46", "remaining_time": "16:20:51", "throughput": 553.57, "total_tokens": 32741984} {"current_steps": 20055, "total_steps": 40000, "loss": 0.1321, "lr": 2.489397156580385e-05, "epoch": 0.9078974173249734, "percentage": 50.14, "elapsed_time": "16:25:50", "remaining_time": "16:20:25", "throughput": 553.68, "total_tokens": 32750304} {"current_steps": 20060, "total_steps": 40000, "loss": 0.1187, "lr": 2.4884154185484246e-05, "epoch": 0.9081237692116164, "percentage": 50.15, "elapsed_time": "16:25:53", "remaining_time": "16:19:59", "throughput": 553.79, "total_tokens": 32758272} {"current_steps": 20065, "total_steps": 40000, "loss": 0.1456, "lr": 2.4874336823029526e-05, "epoch": 0.9083501210982593, "percentage": 50.16, "elapsed_time": "16:25:56", "remaining_time": "16:19:33", "throughput": 553.89, "total_tokens": 32766464} {"current_steps": 20070, "total_steps": 40000, "loss": 0.1179, "lr": 2.4864519479953656e-05, "epoch": 0.9085764729849023, "percentage": 50.18, "elapsed_time": "16:25:59", "remaining_time": "16:19:06", "throughput": 554.0, "total_tokens": 32774624} {"current_steps": 20075, "total_steps": 40000, "loss": 0.0816, "lr": 2.485470215777058e-05, "epoch": 0.9088028248715453, "percentage": 50.19, "elapsed_time": "16:26:02", "remaining_time": "16:18:40", "throughput": 554.12, "total_tokens": 32783232} {"current_steps": 20080, "total_steps": 40000, "loss": 0.178, "lr": 2.4844884857994258e-05, "epoch": 0.9090291767581883, "percentage": 50.2, "elapsed_time": "16:26:06", "remaining_time": "16:18:14", "throughput": 554.24, "total_tokens": 32792064} {"current_steps": 20085, "total_steps": 40000, "loss": 0.0813, "lr": 2.4835067582138638e-05, "epoch": 0.9092555286448313, "percentage": 50.21, "elapsed_time": "16:26:09", "remaining_time": "16:17:48", "throughput": 554.35, "total_tokens": 32800640} {"current_steps": 20090, "total_steps": 40000, "loss": 0.1503, "lr": 2.4825250331717666e-05, "epoch": 0.9094818805314743, "percentage": 50.22, "elapsed_time": "16:26:12", "remaining_time": "16:17:22", "throughput": 554.46, "total_tokens": 32808800} {"current_steps": 20095, "total_steps": 40000, "loss": 0.1522, "lr": 2.4815433108245298e-05, "epoch": 0.9097082324181172, "percentage": 50.24, "elapsed_time": "16:26:15", "remaining_time": "16:16:56", "throughput": 554.57, "total_tokens": 32816864} {"current_steps": 20100, "total_steps": 40000, "loss": 0.1124, "lr": 2.4805615913235456e-05, "epoch": 0.9099345843047602, "percentage": 50.25, "elapsed_time": "16:26:18", "remaining_time": "16:16:30", "throughput": 554.67, "total_tokens": 32824544} {"current_steps": 20105, "total_steps": 40000, "loss": 0.163, "lr": 2.479579874820208e-05, "epoch": 0.9101609361914031, "percentage": 50.26, "elapsed_time": "16:26:22", "remaining_time": "16:16:03", "throughput": 554.78, "total_tokens": 32832896} {"current_steps": 20110, "total_steps": 40000, "loss": 0.1249, "lr": 2.4785981614659115e-05, "epoch": 0.9103872880780461, "percentage": 50.28, "elapsed_time": "16:26:25", "remaining_time": "16:15:37", "throughput": 554.89, "total_tokens": 32841056} {"current_steps": 20115, "total_steps": 40000, "loss": 0.1262, "lr": 2.477616451412047e-05, "epoch": 0.9106136399646891, "percentage": 50.29, "elapsed_time": "16:26:28", "remaining_time": "16:15:11", "throughput": 555.0, "total_tokens": 32849888} {"current_steps": 20120, "total_steps": 40000, "loss": 0.1176, "lr": 2.476634744810007e-05, "epoch": 0.9108399918513321, "percentage": 50.3, "elapsed_time": "16:26:31", "remaining_time": "16:14:45", "throughput": 555.11, "total_tokens": 32857760} {"current_steps": 20125, "total_steps": 40000, "loss": 0.1103, "lr": 2.475653041811183e-05, "epoch": 0.911066343737975, "percentage": 50.31, "elapsed_time": "16:26:34", "remaining_time": "16:14:19", "throughput": 555.22, "total_tokens": 32866112} {"current_steps": 20130, "total_steps": 40000, "loss": 0.1232, "lr": 2.4746713425669652e-05, "epoch": 0.911292695624618, "percentage": 50.32, "elapsed_time": "16:26:38", "remaining_time": "16:13:53", "throughput": 555.32, "total_tokens": 32874144} {"current_steps": 20135, "total_steps": 40000, "loss": 0.13, "lr": 2.4736896472287458e-05, "epoch": 0.911519047511261, "percentage": 50.34, "elapsed_time": "16:26:41", "remaining_time": "16:13:27", "throughput": 555.43, "total_tokens": 32882336} {"current_steps": 20140, "total_steps": 40000, "loss": 0.1245, "lr": 2.4727079559479124e-05, "epoch": 0.911745399397904, "percentage": 50.35, "elapsed_time": "16:26:44", "remaining_time": "16:13:01", "throughput": 555.53, "total_tokens": 32889696} {"current_steps": 20145, "total_steps": 40000, "loss": 0.1982, "lr": 2.4717262688758557e-05, "epoch": 0.911971751284547, "percentage": 50.36, "elapsed_time": "16:26:47", "remaining_time": "16:12:35", "throughput": 555.64, "total_tokens": 32897920} {"current_steps": 20150, "total_steps": 40000, "loss": 0.1054, "lr": 2.4707445861639637e-05, "epoch": 0.9121981031711899, "percentage": 50.38, "elapsed_time": "16:26:50", "remaining_time": "16:12:09", "throughput": 555.75, "total_tokens": 32906048} {"current_steps": 20155, "total_steps": 40000, "loss": 0.1918, "lr": 2.4697629079636244e-05, "epoch": 0.9124244550578329, "percentage": 50.39, "elapsed_time": "16:26:53", "remaining_time": "16:11:43", "throughput": 555.85, "total_tokens": 32914080} {"current_steps": 20160, "total_steps": 40000, "loss": 0.1246, "lr": 2.4687812344262244e-05, "epoch": 0.9126508069444759, "percentage": 50.4, "elapsed_time": "16:26:56", "remaining_time": "16:11:17", "throughput": 555.96, "total_tokens": 32922304} {"current_steps": 20165, "total_steps": 40000, "loss": 0.1482, "lr": 2.46779956570315e-05, "epoch": 0.9128771588311189, "percentage": 50.41, "elapsed_time": "16:27:00", "remaining_time": "16:10:51", "throughput": 556.07, "total_tokens": 32930592} {"current_steps": 20170, "total_steps": 40000, "loss": 0.1537, "lr": 2.466817901945787e-05, "epoch": 0.9131035107177619, "percentage": 50.42, "elapsed_time": "16:27:03", "remaining_time": "16:10:25", "throughput": 556.19, "total_tokens": 32939232} {"current_steps": 20175, "total_steps": 40000, "loss": 0.127, "lr": 2.4658362433055217e-05, "epoch": 0.9133298626044049, "percentage": 50.44, "elapsed_time": "16:27:06", "remaining_time": "16:09:59", "throughput": 556.3, "total_tokens": 32947616} {"current_steps": 20180, "total_steps": 40000, "loss": 0.1241, "lr": 2.4648545899337356e-05, "epoch": 0.9135562144910477, "percentage": 50.45, "elapsed_time": "16:27:09", "remaining_time": "16:09:33", "throughput": 556.4, "total_tokens": 32955584} {"current_steps": 20185, "total_steps": 40000, "loss": 0.1358, "lr": 2.4638729419818143e-05, "epoch": 0.9137825663776907, "percentage": 50.46, "elapsed_time": "16:27:12", "remaining_time": "16:09:07", "throughput": 556.5, "total_tokens": 32963424} {"current_steps": 20190, "total_steps": 40000, "loss": 0.1486, "lr": 2.46289129960114e-05, "epoch": 0.9140089182643337, "percentage": 50.48, "elapsed_time": "16:27:16", "remaining_time": "16:08:41", "throughput": 556.6, "total_tokens": 32971008} {"current_steps": 20195, "total_steps": 40000, "loss": 0.095, "lr": 2.4619096629430924e-05, "epoch": 0.9142352701509767, "percentage": 50.49, "elapsed_time": "16:27:19", "remaining_time": "16:08:15", "throughput": 556.71, "total_tokens": 32978944} {"current_steps": 20200, "total_steps": 40000, "loss": 0.1416, "lr": 2.4609280321590543e-05, "epoch": 0.9144616220376197, "percentage": 50.5, "elapsed_time": "16:27:22", "remaining_time": "16:07:49", "throughput": 556.82, "total_tokens": 32987392} {"current_steps": 20200, "total_steps": 40000, "eval_loss": 0.12575241923332214, "epoch": 0.9144616220376197, "percentage": 50.5, "elapsed_time": "16:35:05", "remaining_time": "16:15:22", "throughput": 552.51, "total_tokens": 32987392} {"current_steps": 20205, "total_steps": 40000, "loss": 0.1354, "lr": 2.4599464074004037e-05, "epoch": 0.9146879739242627, "percentage": 50.51, "elapsed_time": "16:35:09", "remaining_time": "16:14:57", "throughput": 552.61, "total_tokens": 32995808} {"current_steps": 20210, "total_steps": 40000, "loss": 0.098, "lr": 2.4589647888185204e-05, "epoch": 0.9149143258109056, "percentage": 50.52, "elapsed_time": "16:35:12", "remaining_time": "16:14:31", "throughput": 552.72, "total_tokens": 33004032} {"current_steps": 20215, "total_steps": 40000, "loss": 0.0764, "lr": 2.4579831765647836e-05, "epoch": 0.9151406776975486, "percentage": 50.54, "elapsed_time": "16:35:15", "remaining_time": "16:14:05", "throughput": 552.82, "total_tokens": 33011776} {"current_steps": 20220, "total_steps": 40000, "loss": 0.0682, "lr": 2.4570015707905676e-05, "epoch": 0.9153670295841916, "percentage": 50.55, "elapsed_time": "16:35:18", "remaining_time": "16:13:38", "throughput": 552.91, "total_tokens": 33019200} {"current_steps": 20225, "total_steps": 40000, "loss": 0.1504, "lr": 2.4560199716472508e-05, "epoch": 0.9155933814708346, "percentage": 50.56, "elapsed_time": "16:35:21", "remaining_time": "16:13:12", "throughput": 553.02, "total_tokens": 33026976} {"current_steps": 20230, "total_steps": 40000, "loss": 0.107, "lr": 2.455038379286207e-05, "epoch": 0.9158197333574776, "percentage": 50.58, "elapsed_time": "16:35:24", "remaining_time": "16:12:46", "throughput": 553.12, "total_tokens": 33034752} {"current_steps": 20235, "total_steps": 40000, "loss": 0.1454, "lr": 2.4540567938588095e-05, "epoch": 0.9160460852441205, "percentage": 50.59, "elapsed_time": "16:35:27", "remaining_time": "16:12:20", "throughput": 553.23, "total_tokens": 33043008} {"current_steps": 20240, "total_steps": 40000, "loss": 0.1165, "lr": 2.4530752155164328e-05, "epoch": 0.9162724371307635, "percentage": 50.6, "elapsed_time": "16:35:31", "remaining_time": "16:11:54", "throughput": 553.34, "total_tokens": 33051488} {"current_steps": 20245, "total_steps": 40000, "loss": 0.1252, "lr": 2.4520936444104463e-05, "epoch": 0.9164987890174064, "percentage": 50.61, "elapsed_time": "16:35:34", "remaining_time": "16:11:28", "throughput": 553.44, "total_tokens": 33059456} {"current_steps": 20250, "total_steps": 40000, "loss": 0.1335, "lr": 2.4511120806922218e-05, "epoch": 0.9167251409040494, "percentage": 50.62, "elapsed_time": "16:35:37", "remaining_time": "16:11:02", "throughput": 553.55, "total_tokens": 33067552} {"current_steps": 20255, "total_steps": 40000, "loss": 0.1125, "lr": 2.45013052451313e-05, "epoch": 0.9169514927906924, "percentage": 50.64, "elapsed_time": "16:35:40", "remaining_time": "16:10:36", "throughput": 553.66, "total_tokens": 33076224} {"current_steps": 20260, "total_steps": 40000, "loss": 0.1213, "lr": 2.4491489760245376e-05, "epoch": 0.9171778446773354, "percentage": 50.65, "elapsed_time": "16:35:43", "remaining_time": "16:10:10", "throughput": 553.77, "total_tokens": 33084544} {"current_steps": 20265, "total_steps": 40000, "loss": 0.0921, "lr": 2.4481674353778115e-05, "epoch": 0.9174041965639783, "percentage": 50.66, "elapsed_time": "16:35:46", "remaining_time": "16:09:44", "throughput": 553.87, "total_tokens": 33091808} {"current_steps": 20270, "total_steps": 40000, "loss": 0.1012, "lr": 2.447185902724319e-05, "epoch": 0.9176305484506213, "percentage": 50.68, "elapsed_time": "16:35:50", "remaining_time": "16:09:18", "throughput": 553.97, "total_tokens": 33099808} {"current_steps": 20275, "total_steps": 40000, "loss": 0.1257, "lr": 2.4462043782154233e-05, "epoch": 0.9178569003372643, "percentage": 50.69, "elapsed_time": "16:35:53", "remaining_time": "16:08:52", "throughput": 554.08, "total_tokens": 33107968} {"current_steps": 20280, "total_steps": 40000, "loss": 0.1153, "lr": 2.4452228620024895e-05, "epoch": 0.9180832522239073, "percentage": 50.7, "elapsed_time": "16:35:56", "remaining_time": "16:08:26", "throughput": 554.19, "total_tokens": 33116416} {"current_steps": 20285, "total_steps": 40000, "loss": 0.0986, "lr": 2.4442413542368776e-05, "epoch": 0.9183096041105503, "percentage": 50.71, "elapsed_time": "16:35:59", "remaining_time": "16:08:00", "throughput": 554.31, "total_tokens": 33125216} {"current_steps": 20290, "total_steps": 40000, "loss": 0.1128, "lr": 2.4432598550699502e-05, "epoch": 0.9185359559971933, "percentage": 50.72, "elapsed_time": "16:36:02", "remaining_time": "16:07:34", "throughput": 554.41, "total_tokens": 33133056} {"current_steps": 20295, "total_steps": 40000, "loss": 0.129, "lr": 2.4422783646530663e-05, "epoch": 0.9187623078838362, "percentage": 50.74, "elapsed_time": "16:36:06", "remaining_time": "16:07:08", "throughput": 554.52, "total_tokens": 33141664} {"current_steps": 20300, "total_steps": 40000, "loss": 0.1361, "lr": 2.441296883137584e-05, "epoch": 0.9189886597704792, "percentage": 50.75, "elapsed_time": "16:36:09", "remaining_time": "16:06:42", "throughput": 554.64, "total_tokens": 33150752} {"current_steps": 20305, "total_steps": 40000, "loss": 0.0786, "lr": 2.4403154106748592e-05, "epoch": 0.9192150116571222, "percentage": 50.76, "elapsed_time": "16:36:12", "remaining_time": "16:06:16", "throughput": 554.74, "total_tokens": 33158464} {"current_steps": 20310, "total_steps": 40000, "loss": 0.2237, "lr": 2.4393339474162494e-05, "epoch": 0.9194413635437652, "percentage": 50.78, "elapsed_time": "16:36:15", "remaining_time": "16:05:50", "throughput": 554.85, "total_tokens": 33166496} {"current_steps": 20315, "total_steps": 40000, "loss": 0.1359, "lr": 2.4383524935131062e-05, "epoch": 0.9196677154304082, "percentage": 50.79, "elapsed_time": "16:36:18", "remaining_time": "16:05:25", "throughput": 554.96, "total_tokens": 33174720} {"current_steps": 20320, "total_steps": 40000, "loss": 0.1923, "lr": 2.437371049116784e-05, "epoch": 0.919894067317051, "percentage": 50.8, "elapsed_time": "16:36:22", "remaining_time": "16:04:59", "throughput": 555.07, "total_tokens": 33182944} {"current_steps": 20325, "total_steps": 40000, "loss": 0.1174, "lr": 2.436389614378632e-05, "epoch": 0.920120419203694, "percentage": 50.81, "elapsed_time": "16:36:25", "remaining_time": "16:04:33", "throughput": 555.17, "total_tokens": 33190976} {"current_steps": 20330, "total_steps": 40000, "loss": 0.139, "lr": 2.435408189450002e-05, "epoch": 0.920346771090337, "percentage": 50.82, "elapsed_time": "16:36:28", "remaining_time": "16:04:07", "throughput": 555.28, "total_tokens": 33199552} {"current_steps": 20335, "total_steps": 40000, "loss": 0.0963, "lr": 2.4344267744822406e-05, "epoch": 0.92057312297698, "percentage": 50.84, "elapsed_time": "16:36:31", "remaining_time": "16:03:41", "throughput": 555.4, "total_tokens": 33208160} {"current_steps": 20340, "total_steps": 40000, "loss": 0.108, "lr": 2.4334453696266944e-05, "epoch": 0.920799474863623, "percentage": 50.85, "elapsed_time": "16:36:34", "remaining_time": "16:03:15", "throughput": 555.5, "total_tokens": 33216224} {"current_steps": 20345, "total_steps": 40000, "loss": 0.092, "lr": 2.432463975034708e-05, "epoch": 0.921025826750266, "percentage": 50.86, "elapsed_time": "16:36:37", "remaining_time": "16:02:49", "throughput": 555.61, "total_tokens": 33224384} {"current_steps": 20350, "total_steps": 40000, "loss": 0.1766, "lr": 2.4314825908576265e-05, "epoch": 0.9212521786369089, "percentage": 50.88, "elapsed_time": "16:36:41", "remaining_time": "16:02:24", "throughput": 555.71, "total_tokens": 33232224} {"current_steps": 20355, "total_steps": 40000, "loss": 0.1703, "lr": 2.4305012172467897e-05, "epoch": 0.9214785305235519, "percentage": 50.89, "elapsed_time": "16:36:44", "remaining_time": "16:01:58", "throughput": 555.82, "total_tokens": 33240928} {"current_steps": 20360, "total_steps": 40000, "loss": 0.1118, "lr": 2.4295198543535393e-05, "epoch": 0.9217048824101949, "percentage": 50.9, "elapsed_time": "16:36:47", "remaining_time": "16:01:32", "throughput": 555.92, "total_tokens": 33248480} {"current_steps": 20365, "total_steps": 40000, "loss": 0.0523, "lr": 2.4285385023292124e-05, "epoch": 0.9219312342968379, "percentage": 50.91, "elapsed_time": "16:36:50", "remaining_time": "16:01:06", "throughput": 556.03, "total_tokens": 33256736} {"current_steps": 20370, "total_steps": 40000, "loss": 0.1168, "lr": 2.427557161325147e-05, "epoch": 0.9221575861834809, "percentage": 50.92, "elapsed_time": "16:36:54", "remaining_time": "16:00:41", "throughput": 556.14, "total_tokens": 33264960} {"current_steps": 20375, "total_steps": 40000, "loss": 0.1318, "lr": 2.4265758314926778e-05, "epoch": 0.9223839380701239, "percentage": 50.94, "elapsed_time": "16:36:57", "remaining_time": "16:00:15", "throughput": 556.25, "total_tokens": 33273312} {"current_steps": 20380, "total_steps": 40000, "loss": 0.1363, "lr": 2.4255945129831373e-05, "epoch": 0.9226102899567667, "percentage": 50.95, "elapsed_time": "16:37:00", "remaining_time": "15:59:49", "throughput": 556.35, "total_tokens": 33281344} {"current_steps": 20385, "total_steps": 40000, "loss": 0.105, "lr": 2.4246132059478578e-05, "epoch": 0.9228366418434097, "percentage": 50.96, "elapsed_time": "16:37:03", "remaining_time": "15:59:23", "throughput": 556.46, "total_tokens": 33289504} {"current_steps": 20390, "total_steps": 40000, "loss": 0.1612, "lr": 2.4236319105381706e-05, "epoch": 0.9230629937300527, "percentage": 50.98, "elapsed_time": "16:37:06", "remaining_time": "15:58:58", "throughput": 556.57, "total_tokens": 33297664} {"current_steps": 20395, "total_steps": 40000, "loss": 0.1542, "lr": 2.422650626905401e-05, "epoch": 0.9232893456166957, "percentage": 50.99, "elapsed_time": "16:37:10", "remaining_time": "15:58:32", "throughput": 556.69, "total_tokens": 33306528} {"current_steps": 20400, "total_steps": 40000, "loss": 0.0978, "lr": 2.4216693552008785e-05, "epoch": 0.9235156975033387, "percentage": 51.0, "elapsed_time": "16:37:13", "remaining_time": "15:58:06", "throughput": 556.79, "total_tokens": 33314592} {"current_steps": 20400, "total_steps": 40000, "eval_loss": 0.1258331835269928, "epoch": 0.9235156975033387, "percentage": 51.0, "elapsed_time": "16:44:55", "remaining_time": "16:05:31", "throughput": 552.52, "total_tokens": 33314592} {"current_steps": 20405, "total_steps": 40000, "loss": 0.144, "lr": 2.4206880955759247e-05, "epoch": 0.9237420493899816, "percentage": 51.01, "elapsed_time": "16:44:59", "remaining_time": "16:05:06", "throughput": 552.62, "total_tokens": 33323104} {"current_steps": 20410, "total_steps": 40000, "loss": 0.1242, "lr": 2.419706848181863e-05, "epoch": 0.9239684012766246, "percentage": 51.02, "elapsed_time": "16:45:03", "remaining_time": "16:04:40", "throughput": 552.73, "total_tokens": 33331456} {"current_steps": 20415, "total_steps": 40000, "loss": 0.1055, "lr": 2.4187256131700153e-05, "epoch": 0.9241947531632676, "percentage": 51.04, "elapsed_time": "16:45:06", "remaining_time": "16:04:14", "throughput": 552.84, "total_tokens": 33339744} {"current_steps": 20420, "total_steps": 40000, "loss": 0.1449, "lr": 2.4177443906916985e-05, "epoch": 0.9244211050499106, "percentage": 51.05, "elapsed_time": "16:45:09", "remaining_time": "16:03:48", "throughput": 552.94, "total_tokens": 33347296} {"current_steps": 20425, "total_steps": 40000, "loss": 0.1132, "lr": 2.4167631808982303e-05, "epoch": 0.9246474569365536, "percentage": 51.06, "elapsed_time": "16:45:12", "remaining_time": "16:03:22", "throughput": 553.04, "total_tokens": 33355008} {"current_steps": 20430, "total_steps": 40000, "loss": 0.1234, "lr": 2.4157819839409264e-05, "epoch": 0.9248738088231966, "percentage": 51.08, "elapsed_time": "16:45:15", "remaining_time": "16:02:56", "throughput": 553.13, "total_tokens": 33362400} {"current_steps": 20435, "total_steps": 40000, "loss": 0.1155, "lr": 2.414800799971098e-05, "epoch": 0.9251001607098395, "percentage": 51.09, "elapsed_time": "16:45:18", "remaining_time": "16:02:30", "throughput": 553.24, "total_tokens": 33370560} {"current_steps": 20440, "total_steps": 40000, "loss": 0.0732, "lr": 2.4138196291400582e-05, "epoch": 0.9253265125964825, "percentage": 51.1, "elapsed_time": "16:45:21", "remaining_time": "16:02:04", "throughput": 553.34, "total_tokens": 33378496} {"current_steps": 20445, "total_steps": 40000, "loss": 0.1498, "lr": 2.412838471599114e-05, "epoch": 0.9255528644831255, "percentage": 51.11, "elapsed_time": "16:45:25", "remaining_time": "16:01:39", "throughput": 553.45, "total_tokens": 33387072} {"current_steps": 20450, "total_steps": 40000, "loss": 0.1097, "lr": 2.411857327499572e-05, "epoch": 0.9257792163697685, "percentage": 51.12, "elapsed_time": "16:45:28", "remaining_time": "16:01:13", "throughput": 553.55, "total_tokens": 33394912} {"current_steps": 20455, "total_steps": 40000, "loss": 0.1029, "lr": 2.410876196992739e-05, "epoch": 0.9260055682564114, "percentage": 51.14, "elapsed_time": "16:45:31", "remaining_time": "16:00:47", "throughput": 553.66, "total_tokens": 33403040} {"current_steps": 20460, "total_steps": 40000, "loss": 0.118, "lr": 2.4098950802299156e-05, "epoch": 0.9262319201430544, "percentage": 51.15, "elapsed_time": "16:45:34", "remaining_time": "16:00:21", "throughput": 553.77, "total_tokens": 33411168} {"current_steps": 20465, "total_steps": 40000, "loss": 0.1294, "lr": 2.4089139773624027e-05, "epoch": 0.9264582720296973, "percentage": 51.16, "elapsed_time": "16:45:37", "remaining_time": "15:59:55", "throughput": 553.86, "total_tokens": 33418848} {"current_steps": 20470, "total_steps": 40000, "loss": 0.0775, "lr": 2.4079328885415007e-05, "epoch": 0.9266846239163403, "percentage": 51.18, "elapsed_time": "16:45:40", "remaining_time": "15:59:29", "throughput": 553.97, "total_tokens": 33426848} {"current_steps": 20475, "total_steps": 40000, "loss": 0.0807, "lr": 2.4069518139185036e-05, "epoch": 0.9269109758029833, "percentage": 51.19, "elapsed_time": "16:45:44", "remaining_time": "15:59:04", "throughput": 554.09, "total_tokens": 33435744} {"current_steps": 20480, "total_steps": 40000, "loss": 0.0982, "lr": 2.405970753644706e-05, "epoch": 0.9271373276896263, "percentage": 51.2, "elapsed_time": "16:45:47", "remaining_time": "15:58:38", "throughput": 554.18, "total_tokens": 33443136} {"current_steps": 20485, "total_steps": 40000, "loss": 0.1826, "lr": 2.4049897078714e-05, "epoch": 0.9273636795762693, "percentage": 51.21, "elapsed_time": "16:45:50", "remaining_time": "15:58:12", "throughput": 554.28, "total_tokens": 33450880} {"current_steps": 20490, "total_steps": 40000, "loss": 0.1222, "lr": 2.404008676749874e-05, "epoch": 0.9275900314629122, "percentage": 51.23, "elapsed_time": "16:45:53", "remaining_time": "15:57:46", "throughput": 554.38, "total_tokens": 33458720} {"current_steps": 20495, "total_steps": 40000, "loss": 0.1211, "lr": 2.403027660431418e-05, "epoch": 0.9278163833495552, "percentage": 51.24, "elapsed_time": "16:45:56", "remaining_time": "15:57:21", "throughput": 554.48, "total_tokens": 33466752} {"current_steps": 20500, "total_steps": 40000, "loss": 0.1189, "lr": 2.402046659067314e-05, "epoch": 0.9280427352361982, "percentage": 51.25, "elapsed_time": "16:45:59", "remaining_time": "15:56:55", "throughput": 554.59, "total_tokens": 33474688} {"current_steps": 20505, "total_steps": 40000, "loss": 0.1127, "lr": 2.401065672808847e-05, "epoch": 0.9282690871228412, "percentage": 51.26, "elapsed_time": "16:46:02", "remaining_time": "15:56:29", "throughput": 554.7, "total_tokens": 33483296} {"current_steps": 20510, "total_steps": 40000, "loss": 0.1488, "lr": 2.400084701807296e-05, "epoch": 0.9284954390094842, "percentage": 51.28, "elapsed_time": "16:46:06", "remaining_time": "15:56:03", "throughput": 554.8, "total_tokens": 33491008} {"current_steps": 20515, "total_steps": 40000, "loss": 0.1919, "lr": 2.39910374621394e-05, "epoch": 0.9287217908961272, "percentage": 51.29, "elapsed_time": "16:46:09", "remaining_time": "15:55:38", "throughput": 554.91, "total_tokens": 33499392} {"current_steps": 20520, "total_steps": 40000, "loss": 0.1019, "lr": 2.3981228061800544e-05, "epoch": 0.92894814278277, "percentage": 51.3, "elapsed_time": "16:46:12", "remaining_time": "15:55:12", "throughput": 555.02, "total_tokens": 33507872} {"current_steps": 20525, "total_steps": 40000, "loss": 0.1495, "lr": 2.3971418818569115e-05, "epoch": 0.929174494669413, "percentage": 51.31, "elapsed_time": "16:46:15", "remaining_time": "15:54:47", "throughput": 555.13, "total_tokens": 33516224} {"current_steps": 20530, "total_steps": 40000, "loss": 0.1502, "lr": 2.3961609733957832e-05, "epoch": 0.929400846556056, "percentage": 51.32, "elapsed_time": "16:46:18", "remaining_time": "15:54:21", "throughput": 555.24, "total_tokens": 33524448} {"current_steps": 20535, "total_steps": 40000, "loss": 0.0856, "lr": 2.395180080947939e-05, "epoch": 0.929627198442699, "percentage": 51.34, "elapsed_time": "16:46:22", "remaining_time": "15:53:55", "throughput": 555.35, "total_tokens": 33533024} {"current_steps": 20540, "total_steps": 40000, "loss": 0.1619, "lr": 2.394199204664642e-05, "epoch": 0.929853550329342, "percentage": 51.35, "elapsed_time": "16:46:25", "remaining_time": "15:53:30", "throughput": 555.46, "total_tokens": 33541312} {"current_steps": 20545, "total_steps": 40000, "loss": 0.1404, "lr": 2.3932183446971583e-05, "epoch": 0.930079902215985, "percentage": 51.36, "elapsed_time": "16:46:28", "remaining_time": "15:53:04", "throughput": 555.57, "total_tokens": 33550112} {"current_steps": 20550, "total_steps": 40000, "loss": 0.1952, "lr": 2.3922375011967473e-05, "epoch": 0.9303062541026279, "percentage": 51.38, "elapsed_time": "16:46:31", "remaining_time": "15:52:39", "throughput": 555.67, "total_tokens": 33557792} {"current_steps": 20555, "total_steps": 40000, "loss": 0.1153, "lr": 2.3912566743146676e-05, "epoch": 0.9305326059892709, "percentage": 51.39, "elapsed_time": "16:46:34", "remaining_time": "15:52:13", "throughput": 555.78, "total_tokens": 33566112} {"current_steps": 20560, "total_steps": 40000, "loss": 0.0967, "lr": 2.390275864202176e-05, "epoch": 0.9307589578759139, "percentage": 51.4, "elapsed_time": "16:46:38", "remaining_time": "15:51:47", "throughput": 555.89, "total_tokens": 33574656} {"current_steps": 20565, "total_steps": 40000, "loss": 0.1816, "lr": 2.3892950710105243e-05, "epoch": 0.9309853097625569, "percentage": 51.41, "elapsed_time": "16:46:41", "remaining_time": "15:51:22", "throughput": 555.99, "total_tokens": 33582688} {"current_steps": 20570, "total_steps": 40000, "loss": 0.1668, "lr": 2.3883142948909635e-05, "epoch": 0.9312116616491999, "percentage": 51.42, "elapsed_time": "16:46:44", "remaining_time": "15:50:56", "throughput": 556.1, "total_tokens": 33590912} {"current_steps": 20575, "total_steps": 40000, "loss": 0.1152, "lr": 2.3873335359947433e-05, "epoch": 0.9314380135358428, "percentage": 51.44, "elapsed_time": "16:46:47", "remaining_time": "15:50:31", "throughput": 556.21, "total_tokens": 33599424} {"current_steps": 20580, "total_steps": 40000, "loss": 0.0917, "lr": 2.3863527944731066e-05, "epoch": 0.9316643654224858, "percentage": 51.45, "elapsed_time": "16:46:50", "remaining_time": "15:50:05", "throughput": 556.31, "total_tokens": 33607328} {"current_steps": 20585, "total_steps": 40000, "loss": 0.1491, "lr": 2.385372070477298e-05, "epoch": 0.9318907173091288, "percentage": 51.46, "elapsed_time": "16:46:53", "remaining_time": "15:49:40", "throughput": 556.41, "total_tokens": 33615072} {"current_steps": 20590, "total_steps": 40000, "loss": 0.154, "lr": 2.384391364158556e-05, "epoch": 0.9321170691957718, "percentage": 51.48, "elapsed_time": "16:46:57", "remaining_time": "15:49:14", "throughput": 556.53, "total_tokens": 33624128} {"current_steps": 20595, "total_steps": 40000, "loss": 0.1111, "lr": 2.3834106756681185e-05, "epoch": 0.9323434210824147, "percentage": 51.49, "elapsed_time": "16:47:00", "remaining_time": "15:48:49", "throughput": 556.63, "total_tokens": 33632128} {"current_steps": 20600, "total_steps": 40000, "loss": 0.1358, "lr": 2.3824300051572206e-05, "epoch": 0.9325697729690577, "percentage": 51.5, "elapsed_time": "16:47:03", "remaining_time": "15:48:23", "throughput": 556.74, "total_tokens": 33640256} {"current_steps": 20600, "total_steps": 40000, "eval_loss": 0.1255234181880951, "epoch": 0.9325697729690577, "percentage": 51.5, "elapsed_time": "16:54:46", "remaining_time": "15:55:39", "throughput": 552.51, "total_tokens": 33640256} {"current_steps": 20605, "total_steps": 40000, "loss": 0.0962, "lr": 2.3814493527770923e-05, "epoch": 0.9327961248557006, "percentage": 51.51, "elapsed_time": "16:54:50", "remaining_time": "15:55:14", "throughput": 552.61, "total_tokens": 33648448} {"current_steps": 20610, "total_steps": 40000, "loss": 0.0967, "lr": 2.3804687186789637e-05, "epoch": 0.9330224767423436, "percentage": 51.52, "elapsed_time": "16:54:53", "remaining_time": "15:54:48", "throughput": 552.71, "total_tokens": 33656512} {"current_steps": 20615, "total_steps": 40000, "loss": 0.1045, "lr": 2.379488103014062e-05, "epoch": 0.9332488286289866, "percentage": 51.54, "elapsed_time": "16:54:56", "remaining_time": "15:54:23", "throughput": 552.81, "total_tokens": 33664224} {"current_steps": 20620, "total_steps": 40000, "loss": 0.1076, "lr": 2.3785075059336086e-05, "epoch": 0.9334751805156296, "percentage": 51.55, "elapsed_time": "16:54:59", "remaining_time": "15:53:57", "throughput": 552.91, "total_tokens": 33672256} {"current_steps": 20625, "total_steps": 40000, "loss": 0.1079, "lr": 2.3775269275888248e-05, "epoch": 0.9337015324022726, "percentage": 51.56, "elapsed_time": "16:55:02", "remaining_time": "15:53:31", "throughput": 553.02, "total_tokens": 33680416} {"current_steps": 20630, "total_steps": 40000, "loss": 0.0824, "lr": 2.3765463681309274e-05, "epoch": 0.9339278842889156, "percentage": 51.58, "elapsed_time": "16:55:05", "remaining_time": "15:53:06", "throughput": 553.12, "total_tokens": 33688576} {"current_steps": 20635, "total_steps": 40000, "loss": 0.114, "lr": 2.3755658277111313e-05, "epoch": 0.9341542361755585, "percentage": 51.59, "elapsed_time": "16:55:09", "remaining_time": "15:52:40", "throughput": 553.23, "total_tokens": 33696480} {"current_steps": 20640, "total_steps": 40000, "loss": 0.1188, "lr": 2.374585306480649e-05, "epoch": 0.9343805880622015, "percentage": 51.6, "elapsed_time": "16:55:12", "remaining_time": "15:52:14", "throughput": 553.33, "total_tokens": 33704608} {"current_steps": 20645, "total_steps": 40000, "loss": 0.1243, "lr": 2.3736048045906877e-05, "epoch": 0.9346069399488445, "percentage": 51.61, "elapsed_time": "16:55:15", "remaining_time": "15:51:49", "throughput": 553.44, "total_tokens": 33712960} {"current_steps": 20650, "total_steps": 40000, "loss": 0.1188, "lr": 2.372624322192454e-05, "epoch": 0.9348332918354875, "percentage": 51.62, "elapsed_time": "16:55:18", "remaining_time": "15:51:23", "throughput": 553.53, "total_tokens": 33720480} {"current_steps": 20655, "total_steps": 40000, "loss": 0.1094, "lr": 2.3716438594371516e-05, "epoch": 0.9350596437221305, "percentage": 51.64, "elapsed_time": "16:55:21", "remaining_time": "15:50:57", "throughput": 553.64, "total_tokens": 33728768} {"current_steps": 20660, "total_steps": 40000, "loss": 0.1612, "lr": 2.3706634164759784e-05, "epoch": 0.9352859956087733, "percentage": 51.65, "elapsed_time": "16:55:24", "remaining_time": "15:50:32", "throughput": 553.74, "total_tokens": 33736576} {"current_steps": 20665, "total_steps": 40000, "loss": 0.1068, "lr": 2.3696829934601323e-05, "epoch": 0.9355123474954163, "percentage": 51.66, "elapsed_time": "16:55:28", "remaining_time": "15:50:06", "throughput": 553.84, "total_tokens": 33744608} {"current_steps": 20670, "total_steps": 40000, "loss": 0.1781, "lr": 2.3687025905408053e-05, "epoch": 0.9357386993820593, "percentage": 51.68, "elapsed_time": "16:55:31", "remaining_time": "15:49:41", "throughput": 553.95, "total_tokens": 33753088} {"current_steps": 20675, "total_steps": 40000, "loss": 0.0803, "lr": 2.3677222078691886e-05, "epoch": 0.9359650512687023, "percentage": 51.69, "elapsed_time": "16:55:34", "remaining_time": "15:49:15", "throughput": 554.06, "total_tokens": 33761440} {"current_steps": 20680, "total_steps": 40000, "loss": 0.114, "lr": 2.366741845596471e-05, "epoch": 0.9361914031553453, "percentage": 51.7, "elapsed_time": "16:55:37", "remaining_time": "15:48:50", "throughput": 554.17, "total_tokens": 33769952} {"current_steps": 20685, "total_steps": 40000, "loss": 0.0984, "lr": 2.3657615038738343e-05, "epoch": 0.9364177550419883, "percentage": 51.71, "elapsed_time": "16:55:40", "remaining_time": "15:48:24", "throughput": 554.27, "total_tokens": 33777792} {"current_steps": 20690, "total_steps": 40000, "loss": 0.0993, "lr": 2.3647811828524614e-05, "epoch": 0.9366441069286312, "percentage": 51.73, "elapsed_time": "16:55:44", "remaining_time": "15:47:59", "throughput": 554.38, "total_tokens": 33785888} {"current_steps": 20695, "total_steps": 40000, "loss": 0.1201, "lr": 2.363800882683529e-05, "epoch": 0.9368704588152742, "percentage": 51.74, "elapsed_time": "16:55:47", "remaining_time": "15:47:33", "throughput": 554.48, "total_tokens": 33793952} {"current_steps": 20700, "total_steps": 40000, "loss": 0.1134, "lr": 2.3628206035182125e-05, "epoch": 0.9370968107019172, "percentage": 51.75, "elapsed_time": "16:55:50", "remaining_time": "15:47:08", "throughput": 554.58, "total_tokens": 33802144} {"current_steps": 20705, "total_steps": 40000, "loss": 0.0893, "lr": 2.361840345507683e-05, "epoch": 0.9373231625885602, "percentage": 51.76, "elapsed_time": "16:55:53", "remaining_time": "15:46:42", "throughput": 554.7, "total_tokens": 33811040} {"current_steps": 20710, "total_steps": 40000, "loss": 0.1008, "lr": 2.3608601088031073e-05, "epoch": 0.9375495144752032, "percentage": 51.78, "elapsed_time": "16:55:56", "remaining_time": "15:46:17", "throughput": 554.8, "total_tokens": 33818528} {"current_steps": 20715, "total_steps": 40000, "loss": 0.1344, "lr": 2.3598798935556516e-05, "epoch": 0.9377758663618462, "percentage": 51.79, "elapsed_time": "16:55:59", "remaining_time": "15:45:51", "throughput": 554.89, "total_tokens": 33826048} {"current_steps": 20720, "total_steps": 40000, "loss": 0.0922, "lr": 2.3588996999164784e-05, "epoch": 0.9380022182484891, "percentage": 51.8, "elapsed_time": "16:56:03", "remaining_time": "15:45:26", "throughput": 554.99, "total_tokens": 33834176} {"current_steps": 20725, "total_steps": 40000, "loss": 0.1439, "lr": 2.3579195280367434e-05, "epoch": 0.9382285701351321, "percentage": 51.81, "elapsed_time": "16:56:06", "remaining_time": "15:45:00", "throughput": 555.09, "total_tokens": 33841760} {"current_steps": 20730, "total_steps": 40000, "loss": 0.122, "lr": 2.356939378067603e-05, "epoch": 0.938454922021775, "percentage": 51.82, "elapsed_time": "16:56:09", "remaining_time": "15:44:35", "throughput": 555.19, "total_tokens": 33849728} {"current_steps": 20735, "total_steps": 40000, "loss": 0.156, "lr": 2.3559592501602092e-05, "epoch": 0.938681273908418, "percentage": 51.84, "elapsed_time": "16:56:12", "remaining_time": "15:44:09", "throughput": 555.3, "total_tokens": 33858144} {"current_steps": 20740, "total_steps": 40000, "loss": 0.1191, "lr": 2.3549791444657076e-05, "epoch": 0.938907625795061, "percentage": 51.85, "elapsed_time": "16:56:15", "remaining_time": "15:43:44", "throughput": 555.42, "total_tokens": 33866944} {"current_steps": 20745, "total_steps": 40000, "loss": 0.0769, "lr": 2.353999061135246e-05, "epoch": 0.9391339776817039, "percentage": 51.86, "elapsed_time": "16:56:18", "remaining_time": "15:43:19", "throughput": 555.52, "total_tokens": 33874976} {"current_steps": 20750, "total_steps": 40000, "loss": 0.0882, "lr": 2.3530190003199626e-05, "epoch": 0.9393603295683469, "percentage": 51.88, "elapsed_time": "16:56:22", "remaining_time": "15:42:53", "throughput": 555.62, "total_tokens": 33883072} {"current_steps": 20755, "total_steps": 40000, "loss": 0.1203, "lr": 2.3520389621709965e-05, "epoch": 0.9395866814549899, "percentage": 51.89, "elapsed_time": "16:56:25", "remaining_time": "15:42:28", "throughput": 555.72, "total_tokens": 33890848} {"current_steps": 20760, "total_steps": 40000, "loss": 0.1261, "lr": 2.351058946839483e-05, "epoch": 0.9398130333416329, "percentage": 51.9, "elapsed_time": "16:56:28", "remaining_time": "15:42:02", "throughput": 555.82, "total_tokens": 33898656} {"current_steps": 20765, "total_steps": 40000, "loss": 0.0809, "lr": 2.350078954476551e-05, "epoch": 0.9400393852282759, "percentage": 51.91, "elapsed_time": "16:56:31", "remaining_time": "15:41:37", "throughput": 555.93, "total_tokens": 33906880} {"current_steps": 20770, "total_steps": 40000, "loss": 0.0804, "lr": 2.3490989852333272e-05, "epoch": 0.9402657371149189, "percentage": 51.92, "elapsed_time": "16:56:34", "remaining_time": "15:41:12", "throughput": 556.03, "total_tokens": 33915200} {"current_steps": 20775, "total_steps": 40000, "loss": 0.1206, "lr": 2.3481190392609377e-05, "epoch": 0.9404920890015618, "percentage": 51.94, "elapsed_time": "16:56:37", "remaining_time": "15:40:46", "throughput": 556.14, "total_tokens": 33923136} {"current_steps": 20780, "total_steps": 40000, "loss": 0.085, "lr": 2.3471391167105e-05, "epoch": 0.9407184408882048, "percentage": 51.95, "elapsed_time": "16:56:41", "remaining_time": "15:40:21", "throughput": 556.24, "total_tokens": 33931104} {"current_steps": 20785, "total_steps": 40000, "loss": 0.1174, "lr": 2.3461592177331325e-05, "epoch": 0.9409447927748478, "percentage": 51.96, "elapsed_time": "16:56:44", "remaining_time": "15:39:56", "throughput": 556.34, "total_tokens": 33939232} {"current_steps": 20790, "total_steps": 40000, "loss": 0.0861, "lr": 2.345179342479946e-05, "epoch": 0.9411711446614908, "percentage": 51.98, "elapsed_time": "16:56:47", "remaining_time": "15:39:30", "throughput": 556.44, "total_tokens": 33947104} {"current_steps": 20795, "total_steps": 40000, "loss": 0.1293, "lr": 2.3441994911020503e-05, "epoch": 0.9413974965481338, "percentage": 51.99, "elapsed_time": "16:56:50", "remaining_time": "15:39:05", "throughput": 556.55, "total_tokens": 33955136} {"current_steps": 20800, "total_steps": 40000, "loss": 0.1149, "lr": 2.3432196637505522e-05, "epoch": 0.9416238484347768, "percentage": 52.0, "elapsed_time": "16:56:53", "remaining_time": "15:38:40", "throughput": 556.65, "total_tokens": 33963328} {"current_steps": 20800, "total_steps": 40000, "eval_loss": 0.12638185918331146, "epoch": 0.9416238484347768, "percentage": 52.0, "elapsed_time": "17:04:36", "remaining_time": "15:45:47", "throughput": 552.46, "total_tokens": 33963328} {"current_steps": 20805, "total_steps": 40000, "loss": 0.0876, "lr": 2.3422398605765515e-05, "epoch": 0.9418502003214196, "percentage": 52.01, "elapsed_time": "17:04:41", "remaining_time": "15:45:24", "throughput": 552.55, "total_tokens": 33971520} {"current_steps": 20810, "total_steps": 40000, "loss": 0.1301, "lr": 2.3412600817311462e-05, "epoch": 0.9420765522080626, "percentage": 52.02, "elapsed_time": "17:04:44", "remaining_time": "15:44:58", "throughput": 552.64, "total_tokens": 33978912} {"current_steps": 20815, "total_steps": 40000, "loss": 0.1332, "lr": 2.3402803273654326e-05, "epoch": 0.9423029040947056, "percentage": 52.04, "elapsed_time": "17:04:48", "remaining_time": "15:44:32", "throughput": 552.74, "total_tokens": 33987136} {"current_steps": 20820, "total_steps": 40000, "loss": 0.1076, "lr": 2.3393005976304983e-05, "epoch": 0.9425292559813486, "percentage": 52.05, "elapsed_time": "17:04:51", "remaining_time": "15:44:07", "throughput": 552.84, "total_tokens": 33994944} {"current_steps": 20825, "total_steps": 40000, "loss": 0.1225, "lr": 2.338320892677432e-05, "epoch": 0.9427556078679916, "percentage": 52.06, "elapsed_time": "17:04:54", "remaining_time": "15:43:42", "throughput": 552.94, "total_tokens": 34002528} {"current_steps": 20830, "total_steps": 40000, "loss": 0.143, "lr": 2.3373412126573155e-05, "epoch": 0.9429819597546345, "percentage": 52.08, "elapsed_time": "17:04:57", "remaining_time": "15:43:16", "throughput": 553.04, "total_tokens": 34010848} {"current_steps": 20835, "total_steps": 40000, "loss": 0.1247, "lr": 2.3363615577212285e-05, "epoch": 0.9432083116412775, "percentage": 52.09, "elapsed_time": "17:05:00", "remaining_time": "15:42:51", "throughput": 553.15, "total_tokens": 34018880} {"current_steps": 20840, "total_steps": 40000, "loss": 0.129, "lr": 2.3353819280202455e-05, "epoch": 0.9434346635279205, "percentage": 52.1, "elapsed_time": "17:05:03", "remaining_time": "15:42:25", "throughput": 553.26, "total_tokens": 34027360} {"current_steps": 20845, "total_steps": 40000, "loss": 0.0769, "lr": 2.334402323705438e-05, "epoch": 0.9436610154145635, "percentage": 52.11, "elapsed_time": "17:05:07", "remaining_time": "15:42:00", "throughput": 553.36, "total_tokens": 34035648} {"current_steps": 20850, "total_steps": 40000, "loss": 0.1344, "lr": 2.3334227449278725e-05, "epoch": 0.9438873673012065, "percentage": 52.12, "elapsed_time": "17:05:10", "remaining_time": "15:41:35", "throughput": 553.49, "total_tokens": 34045344} {"current_steps": 20855, "total_steps": 40000, "loss": 0.1447, "lr": 2.3324431918386143e-05, "epoch": 0.9441137191878495, "percentage": 52.14, "elapsed_time": "17:05:13", "remaining_time": "15:41:09", "throughput": 553.59, "total_tokens": 34053376} {"current_steps": 20860, "total_steps": 40000, "loss": 0.1526, "lr": 2.3314636645887207e-05, "epoch": 0.9443400710744924, "percentage": 52.15, "elapsed_time": "17:05:16", "remaining_time": "15:40:44", "throughput": 553.69, "total_tokens": 34060960} {"current_steps": 20865, "total_steps": 40000, "loss": 0.1272, "lr": 2.3304841633292487e-05, "epoch": 0.9445664229611354, "percentage": 52.16, "elapsed_time": "17:05:19", "remaining_time": "15:40:19", "throughput": 553.79, "total_tokens": 34069056} {"current_steps": 20870, "total_steps": 40000, "loss": 0.1404, "lr": 2.329504688211248e-05, "epoch": 0.9447927748477783, "percentage": 52.18, "elapsed_time": "17:05:23", "remaining_time": "15:39:53", "throughput": 553.88, "total_tokens": 34076544} {"current_steps": 20875, "total_steps": 40000, "loss": 0.1727, "lr": 2.3285252393857677e-05, "epoch": 0.9450191267344213, "percentage": 52.19, "elapsed_time": "17:05:26", "remaining_time": "15:39:28", "throughput": 553.99, "total_tokens": 34084992} {"current_steps": 20880, "total_steps": 40000, "loss": 0.0911, "lr": 2.327545817003851e-05, "epoch": 0.9452454786210643, "percentage": 52.2, "elapsed_time": "17:05:29", "remaining_time": "15:39:03", "throughput": 554.1, "total_tokens": 34093568} {"current_steps": 20885, "total_steps": 40000, "loss": 0.1798, "lr": 2.326566421216535e-05, "epoch": 0.9454718305077073, "percentage": 52.21, "elapsed_time": "17:05:32", "remaining_time": "15:38:37", "throughput": 554.21, "total_tokens": 34102208} {"current_steps": 20890, "total_steps": 40000, "loss": 0.1336, "lr": 2.3255870521748565e-05, "epoch": 0.9456981823943502, "percentage": 52.23, "elapsed_time": "17:05:36", "remaining_time": "15:38:12", "throughput": 554.32, "total_tokens": 34110528} {"current_steps": 20895, "total_steps": 40000, "loss": 0.1162, "lr": 2.3246077100298474e-05, "epoch": 0.9459245342809932, "percentage": 52.24, "elapsed_time": "17:05:39", "remaining_time": "15:37:47", "throughput": 554.42, "total_tokens": 34118752} {"current_steps": 20900, "total_steps": 40000, "loss": 0.1897, "lr": 2.3236283949325328e-05, "epoch": 0.9461508861676362, "percentage": 52.25, "elapsed_time": "17:05:42", "remaining_time": "15:37:22", "throughput": 554.53, "total_tokens": 34127040} {"current_steps": 20905, "total_steps": 40000, "loss": 0.1057, "lr": 2.3226491070339368e-05, "epoch": 0.9463772380542792, "percentage": 52.26, "elapsed_time": "17:05:45", "remaining_time": "15:36:56", "throughput": 554.63, "total_tokens": 34134752} {"current_steps": 20910, "total_steps": 40000, "loss": 0.1035, "lr": 2.3216698464850762e-05, "epoch": 0.9466035899409222, "percentage": 52.28, "elapsed_time": "17:05:48", "remaining_time": "15:36:31", "throughput": 554.73, "total_tokens": 34142816} {"current_steps": 20915, "total_steps": 40000, "loss": 0.1591, "lr": 2.320690613436967e-05, "epoch": 0.9468299418275651, "percentage": 52.29, "elapsed_time": "17:05:51", "remaining_time": "15:36:06", "throughput": 554.83, "total_tokens": 34150656} {"current_steps": 20920, "total_steps": 40000, "loss": 0.1089, "lr": 2.3197114080406192e-05, "epoch": 0.9470562937142081, "percentage": 52.3, "elapsed_time": "17:05:54", "remaining_time": "15:35:40", "throughput": 554.93, "total_tokens": 34158464} {"current_steps": 20925, "total_steps": 40000, "loss": 0.1541, "lr": 2.3187322304470365e-05, "epoch": 0.9472826456008511, "percentage": 52.31, "elapsed_time": "17:05:58", "remaining_time": "15:35:15", "throughput": 555.03, "total_tokens": 34166912} {"current_steps": 20930, "total_steps": 40000, "loss": 0.0779, "lr": 2.3177530808072222e-05, "epoch": 0.9475089974874941, "percentage": 52.33, "elapsed_time": "17:06:01", "remaining_time": "15:34:50", "throughput": 555.14, "total_tokens": 34175168} {"current_steps": 20935, "total_steps": 40000, "loss": 0.1335, "lr": 2.316773959272174e-05, "epoch": 0.9477353493741371, "percentage": 52.34, "elapsed_time": "17:06:04", "remaining_time": "15:34:25", "throughput": 555.25, "total_tokens": 34183616} {"current_steps": 20940, "total_steps": 40000, "loss": 0.1551, "lr": 2.3157948659928823e-05, "epoch": 0.94796170126078, "percentage": 52.35, "elapsed_time": "17:06:07", "remaining_time": "15:34:00", "throughput": 555.35, "total_tokens": 34191392} {"current_steps": 20945, "total_steps": 40000, "loss": 0.1359, "lr": 2.3148158011203388e-05, "epoch": 0.9481880531474229, "percentage": 52.36, "elapsed_time": "17:06:10", "remaining_time": "15:33:34", "throughput": 555.45, "total_tokens": 34199712} {"current_steps": 20950, "total_steps": 40000, "loss": 0.1362, "lr": 2.3138367648055253e-05, "epoch": 0.9484144050340659, "percentage": 52.38, "elapsed_time": "17:06:14", "remaining_time": "15:33:09", "throughput": 555.56, "total_tokens": 34208032} {"current_steps": 20955, "total_steps": 40000, "loss": 0.1172, "lr": 2.312857757199422e-05, "epoch": 0.9486407569207089, "percentage": 52.39, "elapsed_time": "17:06:17", "remaining_time": "15:32:44", "throughput": 555.66, "total_tokens": 34216192} {"current_steps": 20960, "total_steps": 40000, "loss": 0.1486, "lr": 2.3118787784530048e-05, "epoch": 0.9488671088073519, "percentage": 52.4, "elapsed_time": "17:06:20", "remaining_time": "15:32:19", "throughput": 555.79, "total_tokens": 34225664} {"current_steps": 20965, "total_steps": 40000, "loss": 0.1056, "lr": 2.310899828717243e-05, "epoch": 0.9490934606939949, "percentage": 52.41, "elapsed_time": "17:06:23", "remaining_time": "15:31:54", "throughput": 555.89, "total_tokens": 34234048} {"current_steps": 20970, "total_steps": 40000, "loss": 0.1143, "lr": 2.309920908143104e-05, "epoch": 0.9493198125806379, "percentage": 52.42, "elapsed_time": "17:06:27", "remaining_time": "15:31:29", "throughput": 555.99, "total_tokens": 34241792} {"current_steps": 20975, "total_steps": 40000, "loss": 0.1192, "lr": 2.308942016881551e-05, "epoch": 0.9495461644672808, "percentage": 52.44, "elapsed_time": "17:06:30", "remaining_time": "15:31:04", "throughput": 556.09, "total_tokens": 34249952} {"current_steps": 20980, "total_steps": 40000, "loss": 0.1097, "lr": 2.307963155083539e-05, "epoch": 0.9497725163539238, "percentage": 52.45, "elapsed_time": "17:06:33", "remaining_time": "15:30:39", "throughput": 556.19, "total_tokens": 34257824} {"current_steps": 20985, "total_steps": 40000, "loss": 0.1018, "lr": 2.306984322900022e-05, "epoch": 0.9499988682405668, "percentage": 52.46, "elapsed_time": "17:06:36", "remaining_time": "15:30:14", "throughput": 556.3, "total_tokens": 34266368} {"current_steps": 20990, "total_steps": 40000, "loss": 0.152, "lr": 2.3060055204819482e-05, "epoch": 0.9502252201272098, "percentage": 52.48, "elapsed_time": "17:06:40", "remaining_time": "15:29:49", "throughput": 556.41, "total_tokens": 34274752} {"current_steps": 20995, "total_steps": 40000, "loss": 0.1039, "lr": 2.3050267479802604e-05, "epoch": 0.9504515720138528, "percentage": 52.49, "elapsed_time": "17:06:43", "remaining_time": "15:29:24", "throughput": 556.51, "total_tokens": 34282944} {"current_steps": 21000, "total_steps": 40000, "loss": 0.0931, "lr": 2.304048005545899e-05, "epoch": 0.9506779239004957, "percentage": 52.5, "elapsed_time": "17:06:46", "remaining_time": "15:28:59", "throughput": 556.62, "total_tokens": 34291328} {"current_steps": 21000, "total_steps": 40000, "eval_loss": 0.1254332959651947, "epoch": 0.9506779239004957, "percentage": 52.5, "elapsed_time": "17:14:29", "remaining_time": "15:35:57", "throughput": 552.47, "total_tokens": 34291328} {"current_steps": 21005, "total_steps": 40000, "loss": 0.102, "lr": 2.3030692933297972e-05, "epoch": 0.9509042757871387, "percentage": 52.51, "elapsed_time": "17:14:33", "remaining_time": "15:35:33", "throughput": 552.57, "total_tokens": 34299680} {"current_steps": 21010, "total_steps": 40000, "loss": 0.1607, "lr": 2.3020906114828843e-05, "epoch": 0.9511306276737816, "percentage": 52.52, "elapsed_time": "17:14:36", "remaining_time": "15:35:08", "throughput": 552.69, "total_tokens": 34308992} {"current_steps": 21015, "total_steps": 40000, "loss": 0.0606, "lr": 2.301111960156088e-05, "epoch": 0.9513569795604246, "percentage": 52.54, "elapsed_time": "17:14:39", "remaining_time": "15:34:43", "throughput": 552.79, "total_tokens": 34317120} {"current_steps": 21020, "total_steps": 40000, "loss": 0.0986, "lr": 2.300133339500326e-05, "epoch": 0.9515833314470676, "percentage": 52.55, "elapsed_time": "17:14:43", "remaining_time": "15:34:17", "throughput": 552.9, "total_tokens": 34325664} {"current_steps": 21025, "total_steps": 40000, "loss": 0.0906, "lr": 2.2991547496665148e-05, "epoch": 0.9518096833337106, "percentage": 52.56, "elapsed_time": "17:14:46", "remaining_time": "15:33:52", "throughput": 553.0, "total_tokens": 34333952} {"current_steps": 21030, "total_steps": 40000, "loss": 0.1306, "lr": 2.298176190805565e-05, "epoch": 0.9520360352203535, "percentage": 52.58, "elapsed_time": "17:14:49", "remaining_time": "15:33:27", "throughput": 553.11, "total_tokens": 34342464} {"current_steps": 21035, "total_steps": 40000, "loss": 0.1401, "lr": 2.2971976630683826e-05, "epoch": 0.9522623871069965, "percentage": 52.59, "elapsed_time": "17:14:52", "remaining_time": "15:33:02", "throughput": 553.21, "total_tokens": 34350528} {"current_steps": 21040, "total_steps": 40000, "loss": 0.1381, "lr": 2.29621916660587e-05, "epoch": 0.9524887389936395, "percentage": 52.6, "elapsed_time": "17:14:56", "remaining_time": "15:32:37", "throughput": 553.32, "total_tokens": 34358976} {"current_steps": 21045, "total_steps": 40000, "loss": 0.1017, "lr": 2.295240701568922e-05, "epoch": 0.9527150908802825, "percentage": 52.61, "elapsed_time": "17:14:59", "remaining_time": "15:32:12", "throughput": 553.42, "total_tokens": 34366976} {"current_steps": 21050, "total_steps": 40000, "loss": 0.131, "lr": 2.2942622681084312e-05, "epoch": 0.9529414427669255, "percentage": 52.62, "elapsed_time": "17:15:02", "remaining_time": "15:31:46", "throughput": 553.52, "total_tokens": 34374592} {"current_steps": 21055, "total_steps": 40000, "loss": 0.1049, "lr": 2.293283866375284e-05, "epoch": 0.9531677946535685, "percentage": 52.64, "elapsed_time": "17:15:05", "remaining_time": "15:31:21", "throughput": 553.62, "total_tokens": 34382624} {"current_steps": 21060, "total_steps": 40000, "loss": 0.1754, "lr": 2.2923054965203627e-05, "epoch": 0.9533941465402114, "percentage": 52.65, "elapsed_time": "17:15:08", "remaining_time": "15:30:56", "throughput": 553.73, "total_tokens": 34391136} {"current_steps": 21065, "total_steps": 40000, "loss": 0.1123, "lr": 2.2913271586945443e-05, "epoch": 0.9536204984268544, "percentage": 52.66, "elapsed_time": "17:15:11", "remaining_time": "15:30:31", "throughput": 553.84, "total_tokens": 34399744} {"current_steps": 21070, "total_steps": 40000, "loss": 0.1745, "lr": 2.290348853048699e-05, "epoch": 0.9538468503134974, "percentage": 52.68, "elapsed_time": "17:15:15", "remaining_time": "15:30:06", "throughput": 553.94, "total_tokens": 34408032} {"current_steps": 21075, "total_steps": 40000, "loss": 0.0652, "lr": 2.2893705797336956e-05, "epoch": 0.9540732022001404, "percentage": 52.69, "elapsed_time": "17:15:18", "remaining_time": "15:29:41", "throughput": 554.04, "total_tokens": 34415936} {"current_steps": 21080, "total_steps": 40000, "loss": 0.1619, "lr": 2.288392338900397e-05, "epoch": 0.9542995540867834, "percentage": 52.7, "elapsed_time": "17:15:21", "remaining_time": "15:29:16", "throughput": 554.16, "total_tokens": 34425056} {"current_steps": 21085, "total_steps": 40000, "loss": 0.1559, "lr": 2.2874141306996576e-05, "epoch": 0.9545259059734262, "percentage": 52.71, "elapsed_time": "17:15:24", "remaining_time": "15:28:51", "throughput": 554.26, "total_tokens": 34433376} {"current_steps": 21090, "total_steps": 40000, "loss": 0.1338, "lr": 2.2864359552823312e-05, "epoch": 0.9547522578600692, "percentage": 52.73, "elapsed_time": "17:15:27", "remaining_time": "15:28:26", "throughput": 554.36, "total_tokens": 34441344} {"current_steps": 21095, "total_steps": 40000, "loss": 0.1348, "lr": 2.2854578127992648e-05, "epoch": 0.9549786097467122, "percentage": 52.74, "elapsed_time": "17:15:31", "remaining_time": "15:28:00", "throughput": 554.46, "total_tokens": 34449216} {"current_steps": 21100, "total_steps": 40000, "loss": 0.0996, "lr": 2.2844797034012988e-05, "epoch": 0.9552049616333552, "percentage": 52.75, "elapsed_time": "17:15:34", "remaining_time": "15:27:35", "throughput": 554.56, "total_tokens": 34457056} {"current_steps": 21105, "total_steps": 40000, "loss": 0.1235, "lr": 2.2835016272392722e-05, "epoch": 0.9554313135199982, "percentage": 52.76, "elapsed_time": "17:15:37", "remaining_time": "15:27:10", "throughput": 554.66, "total_tokens": 34465280} {"current_steps": 21110, "total_steps": 40000, "loss": 0.1331, "lr": 2.2825235844640142e-05, "epoch": 0.9556576654066412, "percentage": 52.78, "elapsed_time": "17:15:40", "remaining_time": "15:26:45", "throughput": 554.77, "total_tokens": 34473920} {"current_steps": 21115, "total_steps": 40000, "loss": 0.1104, "lr": 2.2815455752263522e-05, "epoch": 0.9558840172932841, "percentage": 52.79, "elapsed_time": "17:15:43", "remaining_time": "15:26:20", "throughput": 554.87, "total_tokens": 34482048} {"current_steps": 21120, "total_steps": 40000, "loss": 0.1096, "lr": 2.2805675996771092e-05, "epoch": 0.9561103691799271, "percentage": 52.8, "elapsed_time": "17:15:46", "remaining_time": "15:25:55", "throughput": 554.97, "total_tokens": 34489952} {"current_steps": 21125, "total_steps": 40000, "loss": 0.1343, "lr": 2.2795896579670987e-05, "epoch": 0.9563367210665701, "percentage": 52.81, "elapsed_time": "17:15:50", "remaining_time": "15:25:30", "throughput": 555.07, "total_tokens": 34497856} {"current_steps": 21130, "total_steps": 40000, "loss": 0.1281, "lr": 2.2786117502471337e-05, "epoch": 0.9565630729532131, "percentage": 52.83, "elapsed_time": "17:15:53", "remaining_time": "15:25:05", "throughput": 555.17, "total_tokens": 34505504} {"current_steps": 21135, "total_steps": 40000, "loss": 0.1205, "lr": 2.2776338766680185e-05, "epoch": 0.9567894248398561, "percentage": 52.84, "elapsed_time": "17:15:56", "remaining_time": "15:24:40", "throughput": 555.27, "total_tokens": 34513472} {"current_steps": 21140, "total_steps": 40000, "loss": 0.14, "lr": 2.2766560373805533e-05, "epoch": 0.9570157767264991, "percentage": 52.85, "elapsed_time": "17:15:59", "remaining_time": "15:24:15", "throughput": 555.36, "total_tokens": 34521184} {"current_steps": 21145, "total_steps": 40000, "loss": 0.0693, "lr": 2.2756782325355353e-05, "epoch": 0.957242128613142, "percentage": 52.86, "elapsed_time": "17:16:02", "remaining_time": "15:23:50", "throughput": 555.48, "total_tokens": 34530336} {"current_steps": 21150, "total_steps": 40000, "loss": 0.1656, "lr": 2.2747004622837514e-05, "epoch": 0.957468480499785, "percentage": 52.88, "elapsed_time": "17:16:05", "remaining_time": "15:23:25", "throughput": 555.58, "total_tokens": 34538432} {"current_steps": 21155, "total_steps": 40000, "loss": 0.0819, "lr": 2.2737227267759878e-05, "epoch": 0.9576948323864279, "percentage": 52.89, "elapsed_time": "17:16:09", "remaining_time": "15:23:00", "throughput": 555.69, "total_tokens": 34546848} {"current_steps": 21160, "total_steps": 40000, "loss": 0.1515, "lr": 2.272745026163024e-05, "epoch": 0.9579211842730709, "percentage": 52.9, "elapsed_time": "17:16:12", "remaining_time": "15:22:35", "throughput": 555.8, "total_tokens": 34555424} {"current_steps": 21165, "total_steps": 40000, "loss": 0.0729, "lr": 2.271767360595633e-05, "epoch": 0.9581475361597139, "percentage": 52.91, "elapsed_time": "17:16:15", "remaining_time": "15:22:10", "throughput": 555.9, "total_tokens": 34563552} {"current_steps": 21170, "total_steps": 40000, "loss": 0.1197, "lr": 2.270789730224583e-05, "epoch": 0.9583738880463568, "percentage": 52.92, "elapsed_time": "17:16:18", "remaining_time": "15:21:45", "throughput": 556.0, "total_tokens": 34571328} {"current_steps": 21175, "total_steps": 40000, "loss": 0.1104, "lr": 2.2698121352006367e-05, "epoch": 0.9586002399329998, "percentage": 52.94, "elapsed_time": "17:16:22", "remaining_time": "15:21:21", "throughput": 556.12, "total_tokens": 34580512} {"current_steps": 21180, "total_steps": 40000, "loss": 0.083, "lr": 2.2688345756745517e-05, "epoch": 0.9588265918196428, "percentage": 52.95, "elapsed_time": "17:16:25", "remaining_time": "15:20:56", "throughput": 556.22, "total_tokens": 34588448} {"current_steps": 21185, "total_steps": 40000, "loss": 0.1035, "lr": 2.267857051797081e-05, "epoch": 0.9590529437062858, "percentage": 52.96, "elapsed_time": "17:16:28", "remaining_time": "15:20:31", "throughput": 556.32, "total_tokens": 34596576} {"current_steps": 21190, "total_steps": 40000, "loss": 0.1288, "lr": 2.2668795637189695e-05, "epoch": 0.9592792955929288, "percentage": 52.98, "elapsed_time": "17:16:31", "remaining_time": "15:20:06", "throughput": 556.42, "total_tokens": 34604864} {"current_steps": 21195, "total_steps": 40000, "loss": 0.1229, "lr": 2.2659021115909586e-05, "epoch": 0.9595056474795718, "percentage": 52.99, "elapsed_time": "17:16:34", "remaining_time": "15:19:41", "throughput": 556.53, "total_tokens": 34612928} {"current_steps": 21200, "total_steps": 40000, "loss": 0.1168, "lr": 2.2649246955637847e-05, "epoch": 0.9597319993662147, "percentage": 53.0, "elapsed_time": "17:16:37", "remaining_time": "15:19:16", "throughput": 556.63, "total_tokens": 34621536} {"current_steps": 21200, "total_steps": 40000, "eval_loss": 0.12552952766418457, "epoch": 0.9597319993662147, "percentage": 53.0, "elapsed_time": "17:24:20", "remaining_time": "15:26:07", "throughput": 552.52, "total_tokens": 34621536} {"current_steps": 21205, "total_steps": 40000, "loss": 0.1817, "lr": 2.2639473157881766e-05, "epoch": 0.9599583512528577, "percentage": 53.01, "elapsed_time": "17:24:24", "remaining_time": "15:25:42", "throughput": 552.62, "total_tokens": 34629760} {"current_steps": 21210, "total_steps": 40000, "loss": 0.1235, "lr": 2.2629699724148594e-05, "epoch": 0.9601847031395007, "percentage": 53.02, "elapsed_time": "17:24:27", "remaining_time": "15:25:17", "throughput": 552.73, "total_tokens": 34638720} {"current_steps": 21215, "total_steps": 40000, "loss": 0.1215, "lr": 2.26199266559455e-05, "epoch": 0.9604110550261437, "percentage": 53.04, "elapsed_time": "17:24:31", "remaining_time": "15:24:52", "throughput": 552.82, "total_tokens": 34646016} {"current_steps": 21220, "total_steps": 40000, "loss": 0.1099, "lr": 2.2610153954779625e-05, "epoch": 0.9606374069127867, "percentage": 53.05, "elapsed_time": "17:24:34", "remaining_time": "15:24:27", "throughput": 552.93, "total_tokens": 34654272} {"current_steps": 21225, "total_steps": 40000, "loss": 0.1203, "lr": 2.2600381622158056e-05, "epoch": 0.9608637587994296, "percentage": 53.06, "elapsed_time": "17:24:37", "remaining_time": "15:24:02", "throughput": 553.05, "total_tokens": 34663776} {"current_steps": 21230, "total_steps": 40000, "loss": 0.1172, "lr": 2.2590609659587783e-05, "epoch": 0.9610901106860725, "percentage": 53.08, "elapsed_time": "17:24:40", "remaining_time": "15:23:37", "throughput": 553.15, "total_tokens": 34671840} {"current_steps": 21235, "total_steps": 40000, "loss": 0.0906, "lr": 2.2580838068575787e-05, "epoch": 0.9613164625727155, "percentage": 53.09, "elapsed_time": "17:24:43", "remaining_time": "15:23:12", "throughput": 553.26, "total_tokens": 34680544} {"current_steps": 21240, "total_steps": 40000, "loss": 0.1211, "lr": 2.257106685062896e-05, "epoch": 0.9615428144593585, "percentage": 53.1, "elapsed_time": "17:24:47", "remaining_time": "15:22:47", "throughput": 553.36, "total_tokens": 34688672} {"current_steps": 21245, "total_steps": 40000, "loss": 0.143, "lr": 2.256129600725415e-05, "epoch": 0.9617691663460015, "percentage": 53.11, "elapsed_time": "17:24:50", "remaining_time": "15:22:22", "throughput": 553.47, "total_tokens": 34697120} {"current_steps": 21250, "total_steps": 40000, "loss": 0.0803, "lr": 2.2551525539958145e-05, "epoch": 0.9619955182326445, "percentage": 53.12, "elapsed_time": "17:24:53", "remaining_time": "15:21:57", "throughput": 553.57, "total_tokens": 34705440} {"current_steps": 21255, "total_steps": 40000, "loss": 0.1551, "lr": 2.2541755450247663e-05, "epoch": 0.9622218701192874, "percentage": 53.14, "elapsed_time": "17:24:56", "remaining_time": "15:21:32", "throughput": 553.68, "total_tokens": 34713792} {"current_steps": 21260, "total_steps": 40000, "loss": 0.1203, "lr": 2.2531985739629382e-05, "epoch": 0.9624482220059304, "percentage": 53.15, "elapsed_time": "17:24:59", "remaining_time": "15:21:08", "throughput": 553.78, "total_tokens": 34721984} {"current_steps": 21265, "total_steps": 40000, "loss": 0.1407, "lr": 2.2522216409609924e-05, "epoch": 0.9626745738925734, "percentage": 53.16, "elapsed_time": "17:25:03", "remaining_time": "15:20:43", "throughput": 553.88, "total_tokens": 34730304} {"current_steps": 21270, "total_steps": 40000, "loss": 0.1122, "lr": 2.2512447461695826e-05, "epoch": 0.9629009257792164, "percentage": 53.17, "elapsed_time": "17:25:06", "remaining_time": "15:20:18", "throughput": 554.01, "total_tokens": 34740512} {"current_steps": 21275, "total_steps": 40000, "loss": 0.1612, "lr": 2.2502678897393593e-05, "epoch": 0.9631272776658594, "percentage": 53.19, "elapsed_time": "17:25:10", "remaining_time": "15:19:53", "throughput": 554.12, "total_tokens": 34748832} {"current_steps": 21280, "total_steps": 40000, "loss": 0.1433, "lr": 2.2492910718209665e-05, "epoch": 0.9633536295525024, "percentage": 53.2, "elapsed_time": "17:25:13", "remaining_time": "15:19:28", "throughput": 554.23, "total_tokens": 34757376} {"current_steps": 21285, "total_steps": 40000, "loss": 0.1101, "lr": 2.2483142925650398e-05, "epoch": 0.9635799814391453, "percentage": 53.21, "elapsed_time": "17:25:16", "remaining_time": "15:19:03", "throughput": 554.33, "total_tokens": 34765440} {"current_steps": 21290, "total_steps": 40000, "loss": 0.1788, "lr": 2.247337552122213e-05, "epoch": 0.9638063333257882, "percentage": 53.23, "elapsed_time": "17:25:19", "remaining_time": "15:18:39", "throughput": 554.43, "total_tokens": 34773728} {"current_steps": 21295, "total_steps": 40000, "loss": 0.1488, "lr": 2.24636085064311e-05, "epoch": 0.9640326852124312, "percentage": 53.24, "elapsed_time": "17:25:22", "remaining_time": "15:18:14", "throughput": 554.54, "total_tokens": 34782496} {"current_steps": 21300, "total_steps": 40000, "loss": 0.1473, "lr": 2.245384188278351e-05, "epoch": 0.9642590370990742, "percentage": 53.25, "elapsed_time": "17:25:26", "remaining_time": "15:17:49", "throughput": 554.64, "total_tokens": 34790560} {"current_steps": 21305, "total_steps": 40000, "loss": 0.1554, "lr": 2.2444075651785513e-05, "epoch": 0.9644853889857172, "percentage": 53.26, "elapsed_time": "17:25:29", "remaining_time": "15:17:24", "throughput": 554.74, "total_tokens": 34798784} {"current_steps": 21310, "total_steps": 40000, "loss": 0.1394, "lr": 2.243430981494316e-05, "epoch": 0.9647117408723602, "percentage": 53.27, "elapsed_time": "17:25:32", "remaining_time": "15:16:59", "throughput": 554.84, "total_tokens": 34806784} {"current_steps": 21315, "total_steps": 40000, "loss": 0.1424, "lr": 2.2424544373762475e-05, "epoch": 0.9649380927590031, "percentage": 53.29, "elapsed_time": "17:25:35", "remaining_time": "15:16:34", "throughput": 554.94, "total_tokens": 34814336} {"current_steps": 21320, "total_steps": 40000, "loss": 0.1876, "lr": 2.2414779329749418e-05, "epoch": 0.9651644446456461, "percentage": 53.3, "elapsed_time": "17:25:38", "remaining_time": "15:16:09", "throughput": 555.04, "total_tokens": 34822304} {"current_steps": 21325, "total_steps": 40000, "loss": 0.1477, "lr": 2.2405014684409873e-05, "epoch": 0.9653907965322891, "percentage": 53.31, "elapsed_time": "17:25:41", "remaining_time": "15:15:45", "throughput": 555.13, "total_tokens": 34830112} {"current_steps": 21330, "total_steps": 40000, "loss": 0.1017, "lr": 2.239525043924968e-05, "epoch": 0.9656171484189321, "percentage": 53.33, "elapsed_time": "17:25:45", "remaining_time": "15:15:20", "throughput": 555.23, "total_tokens": 34837888} {"current_steps": 21335, "total_steps": 40000, "loss": 0.1827, "lr": 2.2385486595774592e-05, "epoch": 0.9658435003055751, "percentage": 53.34, "elapsed_time": "17:25:48", "remaining_time": "15:14:55", "throughput": 555.33, "total_tokens": 34846272} {"current_steps": 21340, "total_steps": 40000, "loss": 0.097, "lr": 2.237572315549033e-05, "epoch": 0.966069852192218, "percentage": 53.35, "elapsed_time": "17:25:51", "remaining_time": "15:14:30", "throughput": 555.43, "total_tokens": 34853760} {"current_steps": 21345, "total_steps": 40000, "loss": 0.1765, "lr": 2.2365960119902545e-05, "epoch": 0.966296204078861, "percentage": 53.36, "elapsed_time": "17:25:54", "remaining_time": "15:14:05", "throughput": 555.52, "total_tokens": 34861472} {"current_steps": 21350, "total_steps": 40000, "loss": 0.1132, "lr": 2.2356197490516806e-05, "epoch": 0.966522555965504, "percentage": 53.37, "elapsed_time": "17:25:57", "remaining_time": "15:13:41", "throughput": 555.63, "total_tokens": 34870112} {"current_steps": 21355, "total_steps": 40000, "loss": 0.1423, "lr": 2.234643526883863e-05, "epoch": 0.966748907852147, "percentage": 53.39, "elapsed_time": "17:26:00", "remaining_time": "15:13:16", "throughput": 555.74, "total_tokens": 34878720} {"current_steps": 21360, "total_steps": 40000, "loss": 0.1212, "lr": 2.2336673456373497e-05, "epoch": 0.96697525973879, "percentage": 53.4, "elapsed_time": "17:26:04", "remaining_time": "15:12:51", "throughput": 555.84, "total_tokens": 34886720} {"current_steps": 21365, "total_steps": 40000, "loss": 0.1014, "lr": 2.2326912054626772e-05, "epoch": 0.9672016116254329, "percentage": 53.41, "elapsed_time": "17:26:07", "remaining_time": "15:12:27", "throughput": 555.95, "total_tokens": 34895712} {"current_steps": 21370, "total_steps": 40000, "loss": 0.0763, "lr": 2.2317151065103813e-05, "epoch": 0.9674279635120758, "percentage": 53.42, "elapsed_time": "17:26:10", "remaining_time": "15:12:02", "throughput": 556.05, "total_tokens": 34903808} {"current_steps": 21375, "total_steps": 40000, "loss": 0.1383, "lr": 2.2307390489309865e-05, "epoch": 0.9676543153987188, "percentage": 53.44, "elapsed_time": "17:26:13", "remaining_time": "15:11:37", "throughput": 556.15, "total_tokens": 34911680} {"current_steps": 21380, "total_steps": 40000, "loss": 0.0955, "lr": 2.2297630328750146e-05, "epoch": 0.9678806672853618, "percentage": 53.45, "elapsed_time": "17:26:16", "remaining_time": "15:11:12", "throughput": 556.25, "total_tokens": 34919520} {"current_steps": 21385, "total_steps": 40000, "loss": 0.1067, "lr": 2.228787058492979e-05, "epoch": 0.9681070191720048, "percentage": 53.46, "elapsed_time": "17:26:20", "remaining_time": "15:10:48", "throughput": 556.35, "total_tokens": 34927520} {"current_steps": 21390, "total_steps": 40000, "loss": 0.1181, "lr": 2.2278111259353875e-05, "epoch": 0.9683333710586478, "percentage": 53.47, "elapsed_time": "17:26:23", "remaining_time": "15:10:23", "throughput": 556.46, "total_tokens": 34936288} {"current_steps": 21395, "total_steps": 40000, "loss": 0.1791, "lr": 2.2268352353527395e-05, "epoch": 0.9685597229452908, "percentage": 53.49, "elapsed_time": "17:26:26", "remaining_time": "15:09:58", "throughput": 556.56, "total_tokens": 34944224} {"current_steps": 21400, "total_steps": 40000, "loss": 0.1218, "lr": 2.225859386895533e-05, "epoch": 0.9687860748319337, "percentage": 53.5, "elapsed_time": "17:26:29", "remaining_time": "15:09:34", "throughput": 556.66, "total_tokens": 34952416} {"current_steps": 21400, "total_steps": 40000, "eval_loss": 0.1252574473619461, "epoch": 0.9687860748319337, "percentage": 53.5, "elapsed_time": "17:34:12", "remaining_time": "15:16:16", "throughput": 552.59, "total_tokens": 34952416} {"current_steps": 21405, "total_steps": 40000, "loss": 0.1724, "lr": 2.2248835807142525e-05, "epoch": 0.9690124267185767, "percentage": 53.51, "elapsed_time": "17:34:16", "remaining_time": "15:15:52", "throughput": 552.68, "total_tokens": 34960800} {"current_steps": 21410, "total_steps": 40000, "loss": 0.1498, "lr": 2.2239078169593826e-05, "epoch": 0.9692387786052197, "percentage": 53.52, "elapsed_time": "17:34:19", "remaining_time": "15:15:27", "throughput": 552.78, "total_tokens": 34968704} {"current_steps": 21415, "total_steps": 40000, "loss": 0.1142, "lr": 2.222932095781396e-05, "epoch": 0.9694651304918627, "percentage": 53.54, "elapsed_time": "17:34:22", "remaining_time": "15:15:02", "throughput": 552.88, "total_tokens": 34976768} {"current_steps": 21420, "total_steps": 40000, "loss": 0.1269, "lr": 2.221956417330762e-05, "epoch": 0.9696914823785057, "percentage": 53.55, "elapsed_time": "17:34:26", "remaining_time": "15:14:37", "throughput": 552.99, "total_tokens": 34985408} {"current_steps": 21425, "total_steps": 40000, "loss": 0.1309, "lr": 2.2209807817579438e-05, "epoch": 0.9699178342651485, "percentage": 53.56, "elapsed_time": "17:34:29", "remaining_time": "15:14:13", "throughput": 553.09, "total_tokens": 34993536} {"current_steps": 21430, "total_steps": 40000, "loss": 0.0923, "lr": 2.220005189213394e-05, "epoch": 0.9701441861517915, "percentage": 53.57, "elapsed_time": "17:34:32", "remaining_time": "15:13:48", "throughput": 553.19, "total_tokens": 35001536} {"current_steps": 21435, "total_steps": 40000, "loss": 0.1324, "lr": 2.2190296398475624e-05, "epoch": 0.9703705380384345, "percentage": 53.59, "elapsed_time": "17:34:35", "remaining_time": "15:13:23", "throughput": 553.29, "total_tokens": 35009856} {"current_steps": 21440, "total_steps": 40000, "loss": 0.1108, "lr": 2.2180541338108926e-05, "epoch": 0.9705968899250775, "percentage": 53.6, "elapsed_time": "17:34:38", "remaining_time": "15:12:58", "throughput": 553.39, "total_tokens": 35017888} {"current_steps": 21445, "total_steps": 40000, "loss": 0.1245, "lr": 2.2170786712538176e-05, "epoch": 0.9708232418117205, "percentage": 53.61, "elapsed_time": "17:34:41", "remaining_time": "15:12:33", "throughput": 553.49, "total_tokens": 35025760} {"current_steps": 21450, "total_steps": 40000, "loss": 0.0972, "lr": 2.216103252326768e-05, "epoch": 0.9710495936983635, "percentage": 53.62, "elapsed_time": "17:34:45", "remaining_time": "15:12:09", "throughput": 553.6, "total_tokens": 35034432} {"current_steps": 21455, "total_steps": 40000, "loss": 0.0831, "lr": 2.2151278771801635e-05, "epoch": 0.9712759455850064, "percentage": 53.64, "elapsed_time": "17:34:48", "remaining_time": "15:11:44", "throughput": 553.71, "total_tokens": 35043712} {"current_steps": 21460, "total_steps": 40000, "loss": 0.1379, "lr": 2.21415254596442e-05, "epoch": 0.9715022974716494, "percentage": 53.65, "elapsed_time": "17:34:51", "remaining_time": "15:11:19", "throughput": 553.81, "total_tokens": 35051648} {"current_steps": 21465, "total_steps": 40000, "loss": 0.0872, "lr": 2.213177258829947e-05, "epoch": 0.9717286493582924, "percentage": 53.66, "elapsed_time": "17:34:54", "remaining_time": "15:10:55", "throughput": 553.91, "total_tokens": 35059744} {"current_steps": 21470, "total_steps": 40000, "loss": 0.1411, "lr": 2.2122020159271445e-05, "epoch": 0.9719550012449354, "percentage": 53.67, "elapsed_time": "17:34:58", "remaining_time": "15:10:30", "throughput": 554.01, "total_tokens": 35067712} {"current_steps": 21475, "total_steps": 40000, "loss": 0.1126, "lr": 2.2112268174064075e-05, "epoch": 0.9721813531315784, "percentage": 53.69, "elapsed_time": "17:35:01", "remaining_time": "15:10:05", "throughput": 554.13, "total_tokens": 35077376} {"current_steps": 21480, "total_steps": 40000, "loss": 0.1093, "lr": 2.2102516634181253e-05, "epoch": 0.9724077050182214, "percentage": 53.7, "elapsed_time": "17:35:04", "remaining_time": "15:09:41", "throughput": 554.23, "total_tokens": 35085632} {"current_steps": 21485, "total_steps": 40000, "loss": 0.0955, "lr": 2.209276554112677e-05, "epoch": 0.9726340569048643, "percentage": 53.71, "elapsed_time": "17:35:07", "remaining_time": "15:09:16", "throughput": 554.34, "total_tokens": 35093984} {"current_steps": 21490, "total_steps": 40000, "loss": 0.1094, "lr": 2.2083014896404384e-05, "epoch": 0.9728604087915073, "percentage": 53.73, "elapsed_time": "17:35:11", "remaining_time": "15:08:51", "throughput": 554.44, "total_tokens": 35102272} {"current_steps": 21495, "total_steps": 40000, "loss": 0.121, "lr": 2.207326470151775e-05, "epoch": 0.9730867606781503, "percentage": 53.74, "elapsed_time": "17:35:14", "remaining_time": "15:08:27", "throughput": 554.53, "total_tokens": 35109824} {"current_steps": 21500, "total_steps": 40000, "loss": 0.1503, "lr": 2.2063514957970477e-05, "epoch": 0.9733131125647932, "percentage": 53.75, "elapsed_time": "17:35:17", "remaining_time": "15:08:02", "throughput": 554.64, "total_tokens": 35118592} {"current_steps": 21505, "total_steps": 40000, "loss": 0.1377, "lr": 2.205376566726611e-05, "epoch": 0.9735394644514362, "percentage": 53.76, "elapsed_time": "17:35:20", "remaining_time": "15:07:37", "throughput": 554.74, "total_tokens": 35126720} {"current_steps": 21510, "total_steps": 40000, "loss": 0.1135, "lr": 2.204401683090809e-05, "epoch": 0.9737658163380791, "percentage": 53.77, "elapsed_time": "17:35:24", "remaining_time": "15:07:13", "throughput": 554.85, "total_tokens": 35135488} {"current_steps": 21515, "total_steps": 40000, "loss": 0.1112, "lr": 2.203426845039982e-05, "epoch": 0.9739921682247221, "percentage": 53.79, "elapsed_time": "17:35:27", "remaining_time": "15:06:48", "throughput": 554.95, "total_tokens": 35143712} {"current_steps": 21520, "total_steps": 40000, "loss": 0.1101, "lr": 2.202452052724464e-05, "epoch": 0.9742185201113651, "percentage": 53.8, "elapsed_time": "17:35:30", "remaining_time": "15:06:24", "throughput": 555.06, "total_tokens": 35152288} {"current_steps": 21525, "total_steps": 40000, "loss": 0.1065, "lr": 2.2014773062945777e-05, "epoch": 0.9744448719980081, "percentage": 53.81, "elapsed_time": "17:35:33", "remaining_time": "15:05:59", "throughput": 555.16, "total_tokens": 35160160} {"current_steps": 21530, "total_steps": 40000, "loss": 0.1067, "lr": 2.2005026059006427e-05, "epoch": 0.9746712238846511, "percentage": 53.83, "elapsed_time": "17:35:36", "remaining_time": "15:05:34", "throughput": 555.26, "total_tokens": 35168480} {"current_steps": 21535, "total_steps": 40000, "loss": 0.0922, "lr": 2.1995279516929695e-05, "epoch": 0.9748975757712941, "percentage": 53.84, "elapsed_time": "17:35:40", "remaining_time": "15:05:10", "throughput": 555.36, "total_tokens": 35176384} {"current_steps": 21540, "total_steps": 40000, "loss": 0.1469, "lr": 2.1985533438218613e-05, "epoch": 0.975123927657937, "percentage": 53.85, "elapsed_time": "17:35:43", "remaining_time": "15:04:45", "throughput": 555.45, "total_tokens": 35184064} {"current_steps": 21545, "total_steps": 40000, "loss": 0.1218, "lr": 2.197578782437617e-05, "epoch": 0.97535027954458, "percentage": 53.86, "elapsed_time": "17:35:46", "remaining_time": "15:04:21", "throughput": 555.55, "total_tokens": 35191936} {"current_steps": 21550, "total_steps": 40000, "loss": 0.1118, "lr": 2.196604267690524e-05, "epoch": 0.975576631431223, "percentage": 53.87, "elapsed_time": "17:35:49", "remaining_time": "15:03:56", "throughput": 555.65, "total_tokens": 35200256} {"current_steps": 21555, "total_steps": 40000, "loss": 0.2107, "lr": 2.195629799730865e-05, "epoch": 0.975802983317866, "percentage": 53.89, "elapsed_time": "17:35:52", "remaining_time": "15:03:31", "throughput": 555.75, "total_tokens": 35208256} {"current_steps": 21560, "total_steps": 40000, "loss": 0.1333, "lr": 2.1946553787089173e-05, "epoch": 0.976029335204509, "percentage": 53.9, "elapsed_time": "17:35:55", "remaining_time": "15:03:07", "throughput": 555.87, "total_tokens": 35217696} {"current_steps": 21565, "total_steps": 40000, "loss": 0.0885, "lr": 2.193681004774947e-05, "epoch": 0.976255687091152, "percentage": 53.91, "elapsed_time": "17:35:59", "remaining_time": "15:02:43", "throughput": 555.97, "total_tokens": 35225824} {"current_steps": 21570, "total_steps": 40000, "loss": 0.0773, "lr": 2.1927066780792154e-05, "epoch": 0.9764820389777948, "percentage": 53.92, "elapsed_time": "17:36:02", "remaining_time": "15:02:18", "throughput": 556.07, "total_tokens": 35233824} {"current_steps": 21575, "total_steps": 40000, "loss": 0.0836, "lr": 2.191732398771975e-05, "epoch": 0.9767083908644378, "percentage": 53.94, "elapsed_time": "17:36:05", "remaining_time": "15:01:53", "throughput": 556.16, "total_tokens": 35241440} {"current_steps": 21580, "total_steps": 40000, "loss": 0.1002, "lr": 2.1907581670034725e-05, "epoch": 0.9769347427510808, "percentage": 53.95, "elapsed_time": "17:36:08", "remaining_time": "15:01:29", "throughput": 556.26, "total_tokens": 35249536} {"current_steps": 21585, "total_steps": 40000, "loss": 0.1032, "lr": 2.189783982923948e-05, "epoch": 0.9771610946377238, "percentage": 53.96, "elapsed_time": "17:36:11", "remaining_time": "15:01:04", "throughput": 556.35, "total_tokens": 35257024} {"current_steps": 21590, "total_steps": 40000, "loss": 0.0965, "lr": 2.1888098466836303e-05, "epoch": 0.9773874465243668, "percentage": 53.97, "elapsed_time": "17:36:14", "remaining_time": "15:00:40", "throughput": 556.45, "total_tokens": 35264576} {"current_steps": 21595, "total_steps": 40000, "loss": 0.1579, "lr": 2.1878357584327457e-05, "epoch": 0.9776137984110097, "percentage": 53.99, "elapsed_time": "17:36:17", "remaining_time": "15:00:15", "throughput": 556.55, "total_tokens": 35272832} {"current_steps": 21600, "total_steps": 40000, "loss": 0.1276, "lr": 2.1868617183215103e-05, "epoch": 0.9778401502976527, "percentage": 54.0, "elapsed_time": "17:36:21", "remaining_time": "14:59:51", "throughput": 556.65, "total_tokens": 35281184} {"current_steps": 21600, "total_steps": 40000, "eval_loss": 0.12514916062355042, "epoch": 0.9778401502976527, "percentage": 54.0, "elapsed_time": "17:44:03", "remaining_time": "15:06:25", "throughput": 552.62, "total_tokens": 35281184} {"current_steps": 21605, "total_steps": 40000, "loss": 0.1115, "lr": 2.1858877265001327e-05, "epoch": 0.9780665021842957, "percentage": 54.01, "elapsed_time": "17:44:08", "remaining_time": "15:06:02", "throughput": 552.7, "total_tokens": 35289280} {"current_steps": 21610, "total_steps": 40000, "loss": 0.1471, "lr": 2.184913783118816e-05, "epoch": 0.9782928540709387, "percentage": 54.02, "elapsed_time": "17:44:12", "remaining_time": "15:05:37", "throughput": 552.81, "total_tokens": 35298016} {"current_steps": 21615, "total_steps": 40000, "loss": 0.1161, "lr": 2.1839398883277522e-05, "epoch": 0.9785192059575817, "percentage": 54.04, "elapsed_time": "17:44:15", "remaining_time": "15:05:13", "throughput": 552.92, "total_tokens": 35306592} {"current_steps": 21620, "total_steps": 40000, "loss": 0.1095, "lr": 2.182966042277129e-05, "epoch": 0.9787455578442247, "percentage": 54.05, "elapsed_time": "17:44:18", "remaining_time": "15:04:48", "throughput": 553.01, "total_tokens": 35314752} {"current_steps": 21625, "total_steps": 40000, "loss": 0.1124, "lr": 2.181992245117128e-05, "epoch": 0.9789719097308676, "percentage": 54.06, "elapsed_time": "17:44:21", "remaining_time": "15:04:24", "throughput": 553.11, "total_tokens": 35322368} {"current_steps": 21630, "total_steps": 40000, "loss": 0.1871, "lr": 2.181018496997918e-05, "epoch": 0.9791982616175106, "percentage": 54.07, "elapsed_time": "17:44:25", "remaining_time": "15:03:59", "throughput": 553.21, "total_tokens": 35330464} {"current_steps": 21635, "total_steps": 40000, "loss": 0.1506, "lr": 2.1800447980696648e-05, "epoch": 0.9794246135041536, "percentage": 54.09, "elapsed_time": "17:44:28", "remaining_time": "15:03:34", "throughput": 553.31, "total_tokens": 35338816} {"current_steps": 21640, "total_steps": 40000, "loss": 0.1137, "lr": 2.1790711484825248e-05, "epoch": 0.9796509653907965, "percentage": 54.1, "elapsed_time": "17:44:31", "remaining_time": "15:03:10", "throughput": 553.41, "total_tokens": 35346944} {"current_steps": 21645, "total_steps": 40000, "loss": 0.1167, "lr": 2.178097548386646e-05, "epoch": 0.9798773172774395, "percentage": 54.11, "elapsed_time": "17:44:34", "remaining_time": "15:02:45", "throughput": 553.5, "total_tokens": 35354752} {"current_steps": 21650, "total_steps": 40000, "loss": 0.1446, "lr": 2.1771239979321712e-05, "epoch": 0.9801036691640825, "percentage": 54.12, "elapsed_time": "17:44:37", "remaining_time": "15:02:21", "throughput": 553.6, "total_tokens": 35362784} {"current_steps": 21655, "total_steps": 40000, "loss": 0.1105, "lr": 2.1761504972692327e-05, "epoch": 0.9803300210507254, "percentage": 54.14, "elapsed_time": "17:44:40", "remaining_time": "15:01:56", "throughput": 553.7, "total_tokens": 35370912} {"current_steps": 21660, "total_steps": 40000, "loss": 0.1573, "lr": 2.1751770465479572e-05, "epoch": 0.9805563729373684, "percentage": 54.15, "elapsed_time": "17:44:43", "remaining_time": "15:01:31", "throughput": 553.8, "total_tokens": 35378944} {"current_steps": 21665, "total_steps": 40000, "loss": 0.1208, "lr": 2.174203645918464e-05, "epoch": 0.9807827248240114, "percentage": 54.16, "elapsed_time": "17:44:47", "remaining_time": "15:01:07", "throughput": 553.9, "total_tokens": 35386752} {"current_steps": 21670, "total_steps": 40000, "loss": 0.1439, "lr": 2.1732302955308624e-05, "epoch": 0.9810090767106544, "percentage": 54.17, "elapsed_time": "17:44:50", "remaining_time": "15:00:42", "throughput": 554.0, "total_tokens": 35395072} {"current_steps": 21675, "total_steps": 40000, "loss": 0.1169, "lr": 2.172256995535255e-05, "epoch": 0.9812354285972974, "percentage": 54.19, "elapsed_time": "17:44:53", "remaining_time": "15:00:18", "throughput": 554.09, "total_tokens": 35402720} {"current_steps": 21680, "total_steps": 40000, "loss": 0.1055, "lr": 2.171283746081739e-05, "epoch": 0.9814617804839403, "percentage": 54.2, "elapsed_time": "17:44:56", "remaining_time": "14:59:53", "throughput": 554.2, "total_tokens": 35411168} {"current_steps": 21685, "total_steps": 40000, "loss": 0.1201, "lr": 2.1703105473203988e-05, "epoch": 0.9816881323705833, "percentage": 54.21, "elapsed_time": "17:44:59", "remaining_time": "14:59:29", "throughput": 554.3, "total_tokens": 35419392} {"current_steps": 21690, "total_steps": 40000, "loss": 0.147, "lr": 2.1693373994013168e-05, "epoch": 0.9819144842572263, "percentage": 54.23, "elapsed_time": "17:45:02", "remaining_time": "14:59:04", "throughput": 554.39, "total_tokens": 35427360} {"current_steps": 21695, "total_steps": 40000, "loss": 0.1286, "lr": 2.168364302474562e-05, "epoch": 0.9821408361438693, "percentage": 54.24, "elapsed_time": "17:45:05", "remaining_time": "14:58:40", "throughput": 554.49, "total_tokens": 35434912} {"current_steps": 21700, "total_steps": 40000, "loss": 0.1322, "lr": 2.167391256690199e-05, "epoch": 0.9823671880305123, "percentage": 54.25, "elapsed_time": "17:45:09", "remaining_time": "14:58:15", "throughput": 554.59, "total_tokens": 35443296} {"current_steps": 21705, "total_steps": 40000, "loss": 0.1225, "lr": 2.1664182621982855e-05, "epoch": 0.9825935399171553, "percentage": 54.26, "elapsed_time": "17:45:12", "remaining_time": "14:57:51", "throughput": 554.69, "total_tokens": 35451200} {"current_steps": 21710, "total_steps": 40000, "loss": 0.1303, "lr": 2.1654453191488673e-05, "epoch": 0.9828198918037981, "percentage": 54.27, "elapsed_time": "17:45:15", "remaining_time": "14:57:26", "throughput": 554.8, "total_tokens": 35460384} {"current_steps": 21715, "total_steps": 40000, "loss": 0.1476, "lr": 2.1644724276919846e-05, "epoch": 0.9830462436904411, "percentage": 54.29, "elapsed_time": "17:45:18", "remaining_time": "14:57:02", "throughput": 554.9, "total_tokens": 35468352} {"current_steps": 21720, "total_steps": 40000, "loss": 0.1579, "lr": 2.1634995879776715e-05, "epoch": 0.9832725955770841, "percentage": 54.3, "elapsed_time": "17:45:21", "remaining_time": "14:56:38", "throughput": 555.0, "total_tokens": 35476480} {"current_steps": 21725, "total_steps": 40000, "loss": 0.132, "lr": 2.162526800155949e-05, "epoch": 0.9834989474637271, "percentage": 54.31, "elapsed_time": "17:45:25", "remaining_time": "14:56:13", "throughput": 555.1, "total_tokens": 35484512} {"current_steps": 21730, "total_steps": 40000, "loss": 0.097, "lr": 2.1615540643768363e-05, "epoch": 0.9837252993503701, "percentage": 54.33, "elapsed_time": "17:45:28", "remaining_time": "14:55:49", "throughput": 555.21, "total_tokens": 35493536} {"current_steps": 21735, "total_steps": 40000, "loss": 0.1204, "lr": 2.160581380790339e-05, "epoch": 0.9839516512370131, "percentage": 54.34, "elapsed_time": "17:45:31", "remaining_time": "14:55:24", "throughput": 555.3, "total_tokens": 35501056} {"current_steps": 21740, "total_steps": 40000, "loss": 0.1109, "lr": 2.1596087495464586e-05, "epoch": 0.984178003123656, "percentage": 54.35, "elapsed_time": "17:45:34", "remaining_time": "14:55:00", "throughput": 555.4, "total_tokens": 35509312} {"current_steps": 21745, "total_steps": 40000, "loss": 0.1292, "lr": 2.1586361707951866e-05, "epoch": 0.984404355010299, "percentage": 54.36, "elapsed_time": "17:45:37", "remaining_time": "14:54:36", "throughput": 555.5, "total_tokens": 35517824} {"current_steps": 21750, "total_steps": 40000, "loss": 0.1565, "lr": 2.157663644686507e-05, "epoch": 0.984630706896942, "percentage": 54.37, "elapsed_time": "17:45:41", "remaining_time": "14:54:11", "throughput": 555.61, "total_tokens": 35526592} {"current_steps": 21755, "total_steps": 40000, "loss": 0.1296, "lr": 2.156691171370396e-05, "epoch": 0.984857058783585, "percentage": 54.39, "elapsed_time": "17:45:44", "remaining_time": "14:53:47", "throughput": 555.72, "total_tokens": 35535424} {"current_steps": 21760, "total_steps": 40000, "loss": 0.1059, "lr": 2.1557187509968195e-05, "epoch": 0.985083410670228, "percentage": 54.4, "elapsed_time": "17:45:47", "remaining_time": "14:53:23", "throughput": 555.82, "total_tokens": 35543712} {"current_steps": 21765, "total_steps": 40000, "loss": 0.1216, "lr": 2.1547463837157382e-05, "epoch": 0.9853097625568709, "percentage": 54.41, "elapsed_time": "17:45:50", "remaining_time": "14:52:58", "throughput": 555.92, "total_tokens": 35551744} {"current_steps": 21770, "total_steps": 40000, "loss": 0.1727, "lr": 2.1537740696771045e-05, "epoch": 0.9855361144435139, "percentage": 54.43, "elapsed_time": "17:45:54", "remaining_time": "14:52:34", "throughput": 556.02, "total_tokens": 35559808} {"current_steps": 21775, "total_steps": 40000, "loss": 0.1355, "lr": 2.1528018090308587e-05, "epoch": 0.9857624663301569, "percentage": 54.44, "elapsed_time": "17:45:57", "remaining_time": "14:52:10", "throughput": 556.12, "total_tokens": 35567968} {"current_steps": 21780, "total_steps": 40000, "loss": 0.1235, "lr": 2.151829601926938e-05, "epoch": 0.9859888182167998, "percentage": 54.45, "elapsed_time": "17:46:00", "remaining_time": "14:51:46", "throughput": 556.22, "total_tokens": 35576352} {"current_steps": 21785, "total_steps": 40000, "loss": 0.0937, "lr": 2.1508574485152684e-05, "epoch": 0.9862151701034428, "percentage": 54.46, "elapsed_time": "17:46:03", "remaining_time": "14:51:21", "throughput": 556.32, "total_tokens": 35584576} {"current_steps": 21790, "total_steps": 40000, "loss": 0.1034, "lr": 2.1498853489457667e-05, "epoch": 0.9864415219900858, "percentage": 54.47, "elapsed_time": "17:46:06", "remaining_time": "14:50:57", "throughput": 556.43, "total_tokens": 35592800} {"current_steps": 21795, "total_steps": 40000, "loss": 0.108, "lr": 2.1489133033683455e-05, "epoch": 0.9866678738767287, "percentage": 54.49, "elapsed_time": "17:46:10", "remaining_time": "14:50:33", "throughput": 556.54, "total_tokens": 35601728} {"current_steps": 21800, "total_steps": 40000, "loss": 0.1316, "lr": 2.1479413119329038e-05, "epoch": 0.9868942257633717, "percentage": 54.5, "elapsed_time": "17:46:13", "remaining_time": "14:50:08", "throughput": 556.63, "total_tokens": 35609536} {"current_steps": 21800, "total_steps": 40000, "eval_loss": 0.12506915628910065, "epoch": 0.9868942257633717, "percentage": 54.5, "elapsed_time": "17:53:55", "remaining_time": "14:56:35", "throughput": 552.63, "total_tokens": 35609536} {"current_steps": 21805, "total_steps": 40000, "loss": 0.1156, "lr": 2.1469693747893355e-05, "epoch": 0.9871205776500147, "percentage": 54.51, "elapsed_time": "17:54:00", "remaining_time": "14:56:11", "throughput": 552.72, "total_tokens": 35617632} {"current_steps": 21810, "total_steps": 40000, "loss": 0.1069, "lr": 2.1459974920875274e-05, "epoch": 0.9873469295366577, "percentage": 54.52, "elapsed_time": "17:54:03", "remaining_time": "14:55:47", "throughput": 552.82, "total_tokens": 35625568} {"current_steps": 21815, "total_steps": 40000, "loss": 0.1517, "lr": 2.145025663977354e-05, "epoch": 0.9875732814233007, "percentage": 54.54, "elapsed_time": "17:54:06", "remaining_time": "14:55:22", "throughput": 552.92, "total_tokens": 35633824} {"current_steps": 21820, "total_steps": 40000, "loss": 0.1139, "lr": 2.1440538906086844e-05, "epoch": 0.9877996333099437, "percentage": 54.55, "elapsed_time": "17:54:09", "remaining_time": "14:54:58", "throughput": 553.02, "total_tokens": 35642080} {"current_steps": 21825, "total_steps": 40000, "loss": 0.1266, "lr": 2.1430821721313782e-05, "epoch": 0.9880259851965866, "percentage": 54.56, "elapsed_time": "17:54:13", "remaining_time": "14:54:34", "throughput": 553.13, "total_tokens": 35651104} {"current_steps": 21830, "total_steps": 40000, "loss": 0.1106, "lr": 2.142110508695286e-05, "epoch": 0.9882523370832296, "percentage": 54.57, "elapsed_time": "17:54:16", "remaining_time": "14:54:09", "throughput": 553.23, "total_tokens": 35659328} {"current_steps": 21835, "total_steps": 40000, "loss": 0.1182, "lr": 2.1411389004502515e-05, "epoch": 0.9884786889698726, "percentage": 54.59, "elapsed_time": "17:54:19", "remaining_time": "14:53:45", "throughput": 553.33, "total_tokens": 35667392} {"current_steps": 21840, "total_steps": 40000, "loss": 0.1131, "lr": 2.140167347546107e-05, "epoch": 0.9887050408565156, "percentage": 54.6, "elapsed_time": "17:54:22", "remaining_time": "14:53:20", "throughput": 553.43, "total_tokens": 35675360} {"current_steps": 21845, "total_steps": 40000, "loss": 0.1276, "lr": 2.1391958501326793e-05, "epoch": 0.9889313927431586, "percentage": 54.61, "elapsed_time": "17:54:25", "remaining_time": "14:52:56", "throughput": 553.53, "total_tokens": 35683712} {"current_steps": 21850, "total_steps": 40000, "loss": 0.1083, "lr": 2.1382244083597873e-05, "epoch": 0.9891577446298014, "percentage": 54.62, "elapsed_time": "17:54:29", "remaining_time": "14:52:32", "throughput": 553.64, "total_tokens": 35692512} {"current_steps": 21855, "total_steps": 40000, "loss": 0.1155, "lr": 2.137253022377237e-05, "epoch": 0.9893840965164444, "percentage": 54.64, "elapsed_time": "17:54:32", "remaining_time": "14:52:07", "throughput": 553.73, "total_tokens": 35700256} {"current_steps": 21860, "total_steps": 40000, "loss": 0.1032, "lr": 2.136281692334829e-05, "epoch": 0.9896104484030874, "percentage": 54.65, "elapsed_time": "17:54:35", "remaining_time": "14:51:43", "throughput": 553.82, "total_tokens": 35707936} {"current_steps": 21865, "total_steps": 40000, "loss": 0.0963, "lr": 2.135310418382356e-05, "epoch": 0.9898368002897304, "percentage": 54.66, "elapsed_time": "17:54:38", "remaining_time": "14:51:18", "throughput": 553.91, "total_tokens": 35715520} {"current_steps": 21870, "total_steps": 40000, "loss": 0.111, "lr": 2.134339200669598e-05, "epoch": 0.9900631521763734, "percentage": 54.67, "elapsed_time": "17:54:41", "remaining_time": "14:50:54", "throughput": 554.01, "total_tokens": 35723712} {"current_steps": 21875, "total_steps": 40000, "loss": 0.089, "lr": 2.133368039346331e-05, "epoch": 0.9902895040630164, "percentage": 54.69, "elapsed_time": "17:54:44", "remaining_time": "14:50:30", "throughput": 554.1, "total_tokens": 35731264} {"current_steps": 21880, "total_steps": 40000, "loss": 0.1364, "lr": 2.1323969345623195e-05, "epoch": 0.9905158559496593, "percentage": 54.7, "elapsed_time": "17:54:47", "remaining_time": "14:50:05", "throughput": 554.2, "total_tokens": 35739232} {"current_steps": 21885, "total_steps": 40000, "loss": 0.1063, "lr": 2.1314258864673207e-05, "epoch": 0.9907422078363023, "percentage": 54.71, "elapsed_time": "17:54:51", "remaining_time": "14:49:41", "throughput": 554.3, "total_tokens": 35747232} {"current_steps": 21890, "total_steps": 40000, "loss": 0.1315, "lr": 2.130454895211082e-05, "epoch": 0.9909685597229453, "percentage": 54.73, "elapsed_time": "17:54:54", "remaining_time": "14:49:17", "throughput": 554.4, "total_tokens": 35755456} {"current_steps": 21895, "total_steps": 40000, "loss": 0.1298, "lr": 2.129483960943342e-05, "epoch": 0.9911949116095883, "percentage": 54.74, "elapsed_time": "17:54:57", "remaining_time": "14:48:52", "throughput": 554.49, "total_tokens": 35763200} {"current_steps": 21900, "total_steps": 40000, "loss": 0.1, "lr": 2.128513083813831e-05, "epoch": 0.9914212634962313, "percentage": 54.75, "elapsed_time": "17:55:00", "remaining_time": "14:48:28", "throughput": 554.59, "total_tokens": 35771040} {"current_steps": 21905, "total_steps": 40000, "loss": 0.0976, "lr": 2.1275422639722724e-05, "epoch": 0.9916476153828743, "percentage": 54.76, "elapsed_time": "17:55:03", "remaining_time": "14:48:04", "throughput": 554.68, "total_tokens": 35778944} {"current_steps": 21910, "total_steps": 40000, "loss": 0.0986, "lr": 2.126571501568376e-05, "epoch": 0.9918739672695172, "percentage": 54.77, "elapsed_time": "17:55:06", "remaining_time": "14:47:40", "throughput": 554.78, "total_tokens": 35787264} {"current_steps": 21915, "total_steps": 40000, "loss": 0.1266, "lr": 2.1256007967518478e-05, "epoch": 0.9921003191561601, "percentage": 54.79, "elapsed_time": "17:55:09", "remaining_time": "14:47:15", "throughput": 554.88, "total_tokens": 35794976} {"current_steps": 21920, "total_steps": 40000, "loss": 0.0911, "lr": 2.124630149672381e-05, "epoch": 0.9923266710428031, "percentage": 54.8, "elapsed_time": "17:55:13", "remaining_time": "14:46:51", "throughput": 554.97, "total_tokens": 35803040} {"current_steps": 21925, "total_steps": 40000, "loss": 0.1482, "lr": 2.1236595604796624e-05, "epoch": 0.9925530229294461, "percentage": 54.81, "elapsed_time": "17:55:16", "remaining_time": "14:46:27", "throughput": 555.07, "total_tokens": 35811200} {"current_steps": 21930, "total_steps": 40000, "loss": 0.0897, "lr": 2.1226890293233693e-05, "epoch": 0.9927793748160891, "percentage": 54.83, "elapsed_time": "17:55:19", "remaining_time": "14:46:02", "throughput": 555.17, "total_tokens": 35819072} {"current_steps": 21935, "total_steps": 40000, "loss": 0.1143, "lr": 2.1217185563531694e-05, "epoch": 0.993005726702732, "percentage": 54.84, "elapsed_time": "17:55:22", "remaining_time": "14:45:38", "throughput": 555.27, "total_tokens": 35827456} {"current_steps": 21940, "total_steps": 40000, "loss": 0.1325, "lr": 2.120748141718721e-05, "epoch": 0.993232078589375, "percentage": 54.85, "elapsed_time": "17:55:25", "remaining_time": "14:45:14", "throughput": 555.37, "total_tokens": 35835328} {"current_steps": 21945, "total_steps": 40000, "loss": 0.1367, "lr": 2.1197777855696765e-05, "epoch": 0.993458430476018, "percentage": 54.86, "elapsed_time": "17:55:28", "remaining_time": "14:44:50", "throughput": 555.47, "total_tokens": 35843712} {"current_steps": 21950, "total_steps": 40000, "loss": 0.1035, "lr": 2.1188074880556746e-05, "epoch": 0.993684782362661, "percentage": 54.87, "elapsed_time": "17:55:31", "remaining_time": "14:44:26", "throughput": 555.56, "total_tokens": 35851328} {"current_steps": 21955, "total_steps": 40000, "loss": 0.1062, "lr": 2.1178372493263495e-05, "epoch": 0.993911134249304, "percentage": 54.89, "elapsed_time": "17:55:35", "remaining_time": "14:44:01", "throughput": 555.65, "total_tokens": 35859168} {"current_steps": 21960, "total_steps": 40000, "loss": 0.1745, "lr": 2.116867069531322e-05, "epoch": 0.994137486135947, "percentage": 54.9, "elapsed_time": "17:55:38", "remaining_time": "14:43:37", "throughput": 555.75, "total_tokens": 35867104} {"current_steps": 21965, "total_steps": 40000, "loss": 0.1259, "lr": 2.1158969488202073e-05, "epoch": 0.9943638380225899, "percentage": 54.91, "elapsed_time": "17:55:41", "remaining_time": "14:43:13", "throughput": 555.85, "total_tokens": 35875008} {"current_steps": 21970, "total_steps": 40000, "loss": 0.1266, "lr": 2.114926887342611e-05, "epoch": 0.9945901899092329, "percentage": 54.93, "elapsed_time": "17:55:44", "remaining_time": "14:42:49", "throughput": 555.94, "total_tokens": 35882592} {"current_steps": 21975, "total_steps": 40000, "loss": 0.1568, "lr": 2.113956885248127e-05, "epoch": 0.9948165417958759, "percentage": 54.94, "elapsed_time": "17:55:47", "remaining_time": "14:42:25", "throughput": 556.04, "total_tokens": 35890720} {"current_steps": 21980, "total_steps": 40000, "loss": 0.1699, "lr": 2.112986942686342e-05, "epoch": 0.9950428936825189, "percentage": 54.95, "elapsed_time": "17:55:50", "remaining_time": "14:42:00", "throughput": 556.13, "total_tokens": 35898400} {"current_steps": 21985, "total_steps": 40000, "loss": 0.0964, "lr": 2.112017059806835e-05, "epoch": 0.9952692455691619, "percentage": 54.96, "elapsed_time": "17:55:53", "remaining_time": "14:41:36", "throughput": 556.23, "total_tokens": 35906848} {"current_steps": 21990, "total_steps": 40000, "loss": 0.1248, "lr": 2.1110472367591724e-05, "epoch": 0.9954955974558048, "percentage": 54.97, "elapsed_time": "17:55:57", "remaining_time": "14:41:12", "throughput": 556.34, "total_tokens": 35915872} {"current_steps": 21995, "total_steps": 40000, "loss": 0.1053, "lr": 2.1100774736929145e-05, "epoch": 0.9957219493424477, "percentage": 54.99, "elapsed_time": "17:56:00", "remaining_time": "14:40:48", "throughput": 556.44, "total_tokens": 35924128} {"current_steps": 22000, "total_steps": 40000, "loss": 0.1234, "lr": 2.10910777075761e-05, "epoch": 0.9959483012290907, "percentage": 55.0, "elapsed_time": "17:56:03", "remaining_time": "14:40:24", "throughput": 556.54, "total_tokens": 35932000} {"current_steps": 22000, "total_steps": 40000, "eval_loss": 0.12561099231243134, "epoch": 0.9959483012290907, "percentage": 55.0, "elapsed_time": "18:03:46", "remaining_time": "14:46:43", "throughput": 552.58, "total_tokens": 35932000} {"current_steps": 22005, "total_steps": 40000, "loss": 0.0778, "lr": 2.108138128102799e-05, "epoch": 0.9961746531157337, "percentage": 55.01, "elapsed_time": "18:03:50", "remaining_time": "14:46:19", "throughput": 552.66, "total_tokens": 35939552} {"current_steps": 22010, "total_steps": 40000, "loss": 0.0881, "lr": 2.107168545878014e-05, "epoch": 0.9964010050023767, "percentage": 55.02, "elapsed_time": "18:03:53", "remaining_time": "14:45:55", "throughput": 552.77, "total_tokens": 35948608} {"current_steps": 22015, "total_steps": 40000, "loss": 0.1478, "lr": 2.106199024232775e-05, "epoch": 0.9966273568890197, "percentage": 55.04, "elapsed_time": "18:03:56", "remaining_time": "14:45:31", "throughput": 552.86, "total_tokens": 35956352} {"current_steps": 22020, "total_steps": 40000, "loss": 0.1089, "lr": 2.105229563316595e-05, "epoch": 0.9968537087756626, "percentage": 55.05, "elapsed_time": "18:03:59", "remaining_time": "14:45:06", "throughput": 552.96, "total_tokens": 35964512} {"current_steps": 22025, "total_steps": 40000, "loss": 0.1536, "lr": 2.1042601632789784e-05, "epoch": 0.9970800606623056, "percentage": 55.06, "elapsed_time": "18:04:02", "remaining_time": "14:44:42", "throughput": 553.06, "total_tokens": 35972320} {"current_steps": 22030, "total_steps": 40000, "loss": 0.0897, "lr": 2.103290824269417e-05, "epoch": 0.9973064125489486, "percentage": 55.07, "elapsed_time": "18:04:05", "remaining_time": "14:44:18", "throughput": 553.16, "total_tokens": 35980512} {"current_steps": 22035, "total_steps": 40000, "loss": 0.1082, "lr": 2.1023215464373965e-05, "epoch": 0.9975327644355916, "percentage": 55.09, "elapsed_time": "18:04:09", "remaining_time": "14:43:54", "throughput": 553.26, "total_tokens": 35989216} {"current_steps": 22040, "total_steps": 40000, "loss": 0.1371, "lr": 2.1013523299323908e-05, "epoch": 0.9977591163222346, "percentage": 55.1, "elapsed_time": "18:04:12", "remaining_time": "14:43:29", "throughput": 553.36, "total_tokens": 35997408} {"current_steps": 22045, "total_steps": 40000, "loss": 0.1302, "lr": 2.1003831749038654e-05, "epoch": 0.9979854682088776, "percentage": 55.11, "elapsed_time": "18:04:15", "remaining_time": "14:43:05", "throughput": 553.47, "total_tokens": 36006080} {"current_steps": 22050, "total_steps": 40000, "loss": 0.1404, "lr": 2.099414081501277e-05, "epoch": 0.9982118200955205, "percentage": 55.12, "elapsed_time": "18:04:18", "remaining_time": "14:42:41", "throughput": 553.56, "total_tokens": 36013728} {"current_steps": 22055, "total_steps": 40000, "loss": 0.1615, "lr": 2.09844504987407e-05, "epoch": 0.9984381719821634, "percentage": 55.14, "elapsed_time": "18:04:21", "remaining_time": "14:42:17", "throughput": 553.65, "total_tokens": 36021504} {"current_steps": 22060, "total_steps": 40000, "loss": 0.1284, "lr": 2.097476080171683e-05, "epoch": 0.9986645238688064, "percentage": 55.15, "elapsed_time": "18:04:25", "remaining_time": "14:41:53", "throughput": 553.76, "total_tokens": 36030144} {"current_steps": 22065, "total_steps": 40000, "loss": 0.1542, "lr": 2.0965071725435436e-05, "epoch": 0.9988908757554494, "percentage": 55.16, "elapsed_time": "18:04:28", "remaining_time": "14:41:29", "throughput": 553.86, "total_tokens": 36038656} {"current_steps": 22070, "total_steps": 40000, "loss": 0.1578, "lr": 2.0955383271390684e-05, "epoch": 0.9991172276420924, "percentage": 55.17, "elapsed_time": "18:04:31", "remaining_time": "14:41:05", "throughput": 553.96, "total_tokens": 36047072} {"current_steps": 22075, "total_steps": 40000, "loss": 0.1359, "lr": 2.094569544107666e-05, "epoch": 0.9993435795287354, "percentage": 55.19, "elapsed_time": "18:04:34", "remaining_time": "14:40:41", "throughput": 554.06, "total_tokens": 36055584} {"current_steps": 22080, "total_steps": 40000, "loss": 0.0905, "lr": 2.093600823598735e-05, "epoch": 0.9995699314153783, "percentage": 55.2, "elapsed_time": "18:04:37", "remaining_time": "14:40:16", "throughput": 554.16, "total_tokens": 36063872} {"current_steps": 22085, "total_steps": 40000, "loss": 0.0854, "lr": 2.092632165761663e-05, "epoch": 0.9997962833020213, "percentage": 55.21, "elapsed_time": "18:04:41", "remaining_time": "14:39:53", "throughput": 554.28, "total_tokens": 36073312} {"current_steps": 22090, "total_steps": 40000, "loss": 0.1801, "lr": 2.091663570745832e-05, "epoch": 1.0, "percentage": 55.23, "elapsed_time": "18:04:44", "remaining_time": "14:39:28", "throughput": 554.37, "total_tokens": 36080688} {"current_steps": 22095, "total_steps": 40000, "loss": 0.0986, "lr": 2.0906950387006086e-05, "epoch": 1.000226351886643, "percentage": 55.24, "elapsed_time": "18:04:47", "remaining_time": "14:39:04", "throughput": 554.46, "total_tokens": 36088496} {"current_steps": 22100, "total_steps": 40000, "loss": 0.1501, "lr": 2.0897265697753543e-05, "epoch": 1.000452703773286, "percentage": 55.25, "elapsed_time": "18:04:51", "remaining_time": "14:38:40", "throughput": 554.56, "total_tokens": 36097168} {"current_steps": 22105, "total_steps": 40000, "loss": 0.1302, "lr": 2.088758164119419e-05, "epoch": 1.000679055659929, "percentage": 55.26, "elapsed_time": "18:04:54", "remaining_time": "14:38:16", "throughput": 554.66, "total_tokens": 36105328} {"current_steps": 22110, "total_steps": 40000, "loss": 0.1157, "lr": 2.0877898218821428e-05, "epoch": 1.000905407546572, "percentage": 55.27, "elapsed_time": "18:04:57", "remaining_time": "14:37:52", "throughput": 554.76, "total_tokens": 36113424} {"current_steps": 22115, "total_steps": 40000, "loss": 0.1282, "lr": 2.0868215432128565e-05, "epoch": 1.001131759433215, "percentage": 55.29, "elapsed_time": "18:05:00", "remaining_time": "14:37:28", "throughput": 554.85, "total_tokens": 36121104} {"current_steps": 22120, "total_steps": 40000, "loss": 0.1615, "lr": 2.0858533282608796e-05, "epoch": 1.0013581113198577, "percentage": 55.3, "elapsed_time": "18:05:03", "remaining_time": "14:37:04", "throughput": 554.95, "total_tokens": 36129488} {"current_steps": 22125, "total_steps": 40000, "loss": 0.2055, "lr": 2.084885177175524e-05, "epoch": 1.0015844632065007, "percentage": 55.31, "elapsed_time": "18:05:06", "remaining_time": "14:36:40", "throughput": 555.05, "total_tokens": 36137552} {"current_steps": 22130, "total_steps": 40000, "loss": 0.0909, "lr": 2.0839170901060917e-05, "epoch": 1.0018108150931437, "percentage": 55.33, "elapsed_time": "18:05:09", "remaining_time": "14:36:16", "throughput": 555.15, "total_tokens": 36145616} {"current_steps": 22135, "total_steps": 40000, "loss": 0.1169, "lr": 2.082949067201872e-05, "epoch": 1.0020371669797867, "percentage": 55.34, "elapsed_time": "18:05:13", "remaining_time": "14:35:52", "throughput": 555.24, "total_tokens": 36153360} {"current_steps": 22140, "total_steps": 40000, "loss": 0.0883, "lr": 2.0819811086121475e-05, "epoch": 1.0022635188664297, "percentage": 55.35, "elapsed_time": "18:05:16", "remaining_time": "14:35:28", "throughput": 555.34, "total_tokens": 36161360} {"current_steps": 22145, "total_steps": 40000, "loss": 0.0884, "lr": 2.08101321448619e-05, "epoch": 1.0024898707530727, "percentage": 55.36, "elapsed_time": "18:05:19", "remaining_time": "14:35:04", "throughput": 555.44, "total_tokens": 36170096} {"current_steps": 22150, "total_steps": 40000, "loss": 0.1317, "lr": 2.080045384973259e-05, "epoch": 1.0027162226397157, "percentage": 55.38, "elapsed_time": "18:05:22", "remaining_time": "14:34:40", "throughput": 555.53, "total_tokens": 36177712} {"current_steps": 22155, "total_steps": 40000, "loss": 0.1289, "lr": 2.0790776202226082e-05, "epoch": 1.0029425745263587, "percentage": 55.39, "elapsed_time": "18:05:25", "remaining_time": "14:34:16", "throughput": 555.63, "total_tokens": 36185456} {"current_steps": 22160, "total_steps": 40000, "loss": 0.1214, "lr": 2.078109920383477e-05, "epoch": 1.0031689264130017, "percentage": 55.4, "elapsed_time": "18:05:28", "remaining_time": "14:33:52", "throughput": 555.72, "total_tokens": 36193328} {"current_steps": 22165, "total_steps": 40000, "loss": 0.077, "lr": 2.0771422856050978e-05, "epoch": 1.0033952782996447, "percentage": 55.41, "elapsed_time": "18:05:31", "remaining_time": "14:33:28", "throughput": 555.82, "total_tokens": 36201488} {"current_steps": 22170, "total_steps": 40000, "loss": 0.087, "lr": 2.076174716036693e-05, "epoch": 1.0036216301862877, "percentage": 55.43, "elapsed_time": "18:05:35", "remaining_time": "14:33:04", "throughput": 555.92, "total_tokens": 36210128} {"current_steps": 22175, "total_steps": 40000, "loss": 0.1205, "lr": 2.075207211827472e-05, "epoch": 1.0038479820729305, "percentage": 55.44, "elapsed_time": "18:05:38", "remaining_time": "14:32:40", "throughput": 556.03, "total_tokens": 36218672} {"current_steps": 22180, "total_steps": 40000, "loss": 0.1782, "lr": 2.074239773126638e-05, "epoch": 1.0040743339595735, "percentage": 55.45, "elapsed_time": "18:05:41", "remaining_time": "14:32:16", "throughput": 556.14, "total_tokens": 36227600} {"current_steps": 22185, "total_steps": 40000, "loss": 0.1371, "lr": 2.073272400083382e-05, "epoch": 1.0043006858462165, "percentage": 55.46, "elapsed_time": "18:05:44", "remaining_time": "14:31:52", "throughput": 556.23, "total_tokens": 36235792} {"current_steps": 22190, "total_steps": 40000, "loss": 0.0836, "lr": 2.072305092846883e-05, "epoch": 1.0045270377328595, "percentage": 55.47, "elapsed_time": "18:05:47", "remaining_time": "14:31:28", "throughput": 556.33, "total_tokens": 36243600} {"current_steps": 22195, "total_steps": 40000, "loss": 0.1845, "lr": 2.0713378515663152e-05, "epoch": 1.0047533896195024, "percentage": 55.49, "elapsed_time": "18:05:51", "remaining_time": "14:31:04", "throughput": 556.43, "total_tokens": 36252080} {"current_steps": 22200, "total_steps": 40000, "loss": 0.1009, "lr": 2.070370676390836e-05, "epoch": 1.0049797415061454, "percentage": 55.5, "elapsed_time": "18:05:54", "remaining_time": "14:30:41", "throughput": 556.54, "total_tokens": 36261328} {"current_steps": 22200, "total_steps": 40000, "eval_loss": 0.12487843632698059, "epoch": 1.0049797415061454, "percentage": 55.5, "elapsed_time": "18:13:37", "remaining_time": "14:36:51", "throughput": 552.62, "total_tokens": 36261328} {"current_steps": 22205, "total_steps": 40000, "loss": 0.1226, "lr": 2.0694035674695974e-05, "epoch": 1.0052060933927884, "percentage": 55.51, "elapsed_time": "18:13:41", "remaining_time": "14:36:28", "throughput": 552.71, "total_tokens": 36269712} {"current_steps": 22210, "total_steps": 40000, "loss": 0.1162, "lr": 2.0684365249517416e-05, "epoch": 1.0054324452794314, "percentage": 55.53, "elapsed_time": "18:13:44", "remaining_time": "14:36:04", "throughput": 552.81, "total_tokens": 36277584} {"current_steps": 22215, "total_steps": 40000, "loss": 0.0954, "lr": 2.067469548986396e-05, "epoch": 1.0056587971660744, "percentage": 55.54, "elapsed_time": "18:13:47", "remaining_time": "14:35:40", "throughput": 552.91, "total_tokens": 36285872} {"current_steps": 22220, "total_steps": 40000, "loss": 0.1099, "lr": 2.066502639722681e-05, "epoch": 1.0058851490527174, "percentage": 55.55, "elapsed_time": "18:13:50", "remaining_time": "14:35:16", "throughput": 553.0, "total_tokens": 36293680} {"current_steps": 22225, "total_steps": 40000, "loss": 0.1184, "lr": 2.065535797309708e-05, "epoch": 1.0061115009393604, "percentage": 55.56, "elapsed_time": "18:13:53", "remaining_time": "14:34:52", "throughput": 553.09, "total_tokens": 36301488} {"current_steps": 22230, "total_steps": 40000, "loss": 0.1191, "lr": 2.0645690218965736e-05, "epoch": 1.0063378528260034, "percentage": 55.57, "elapsed_time": "18:13:56", "remaining_time": "14:34:28", "throughput": 553.19, "total_tokens": 36309712} {"current_steps": 22235, "total_steps": 40000, "loss": 0.1347, "lr": 2.063602313632369e-05, "epoch": 1.0065642047126462, "percentage": 55.59, "elapsed_time": "18:14:00", "remaining_time": "14:34:04", "throughput": 553.28, "total_tokens": 36317264} {"current_steps": 22240, "total_steps": 40000, "loss": 0.1008, "lr": 2.0626356726661704e-05, "epoch": 1.0067905565992892, "percentage": 55.6, "elapsed_time": "18:14:03", "remaining_time": "14:33:40", "throughput": 553.38, "total_tokens": 36325488} {"current_steps": 22245, "total_steps": 40000, "loss": 0.1157, "lr": 2.0616690991470477e-05, "epoch": 1.0070169084859322, "percentage": 55.61, "elapsed_time": "18:14:06", "remaining_time": "14:33:16", "throughput": 553.47, "total_tokens": 36333552} {"current_steps": 22250, "total_steps": 40000, "loss": 0.1282, "lr": 2.0607025932240595e-05, "epoch": 1.0072432603725752, "percentage": 55.62, "elapsed_time": "18:14:09", "remaining_time": "14:32:52", "throughput": 553.57, "total_tokens": 36341552} {"current_steps": 22255, "total_steps": 40000, "loss": 0.1166, "lr": 2.059736155046251e-05, "epoch": 1.0074696122592182, "percentage": 55.64, "elapsed_time": "18:14:12", "remaining_time": "14:32:28", "throughput": 553.67, "total_tokens": 36349904} {"current_steps": 22260, "total_steps": 40000, "loss": 0.1087, "lr": 2.0587697847626603e-05, "epoch": 1.0076959641458612, "percentage": 55.65, "elapsed_time": "18:14:16", "remaining_time": "14:32:04", "throughput": 553.76, "total_tokens": 36357552} {"current_steps": 22265, "total_steps": 40000, "loss": 0.1238, "lr": 2.057803482522314e-05, "epoch": 1.0079223160325042, "percentage": 55.66, "elapsed_time": "18:14:19", "remaining_time": "14:31:40", "throughput": 553.86, "total_tokens": 36365872} {"current_steps": 22270, "total_steps": 40000, "loss": 0.0927, "lr": 2.056837248474227e-05, "epoch": 1.0081486679191471, "percentage": 55.67, "elapsed_time": "18:14:22", "remaining_time": "14:31:16", "throughput": 553.96, "total_tokens": 36374096} {"current_steps": 22275, "total_steps": 40000, "loss": 0.1188, "lr": 2.0558710827674064e-05, "epoch": 1.0083750198057901, "percentage": 55.69, "elapsed_time": "18:14:25", "remaining_time": "14:30:52", "throughput": 554.05, "total_tokens": 36382192} {"current_steps": 22280, "total_steps": 40000, "loss": 0.1953, "lr": 2.054904985550845e-05, "epoch": 1.0086013716924331, "percentage": 55.7, "elapsed_time": "18:14:28", "remaining_time": "14:30:28", "throughput": 554.15, "total_tokens": 36390576} {"current_steps": 22285, "total_steps": 40000, "loss": 0.1275, "lr": 2.0539389569735287e-05, "epoch": 1.0088277235790761, "percentage": 55.71, "elapsed_time": "18:14:32", "remaining_time": "14:30:04", "throughput": 554.26, "total_tokens": 36399120} {"current_steps": 22290, "total_steps": 40000, "loss": 0.0696, "lr": 2.052972997184431e-05, "epoch": 1.009054075465719, "percentage": 55.73, "elapsed_time": "18:14:35", "remaining_time": "14:29:40", "throughput": 554.34, "total_tokens": 36406704} {"current_steps": 22295, "total_steps": 40000, "loss": 0.1114, "lr": 2.0520071063325146e-05, "epoch": 1.009280427352362, "percentage": 55.74, "elapsed_time": "18:14:38", "remaining_time": "14:29:16", "throughput": 554.45, "total_tokens": 36415760} {"current_steps": 22300, "total_steps": 40000, "loss": 0.145, "lr": 2.051041284566732e-05, "epoch": 1.009506779239005, "percentage": 55.75, "elapsed_time": "18:14:41", "remaining_time": "14:28:53", "throughput": 554.55, "total_tokens": 36423696} {"current_steps": 22305, "total_steps": 40000, "loss": 0.0813, "lr": 2.050075532036026e-05, "epoch": 1.0097331311256479, "percentage": 55.76, "elapsed_time": "18:14:44", "remaining_time": "14:28:29", "throughput": 554.65, "total_tokens": 36431888} {"current_steps": 22310, "total_steps": 40000, "loss": 0.1317, "lr": 2.0491098488893264e-05, "epoch": 1.0099594830122909, "percentage": 55.77, "elapsed_time": "18:14:48", "remaining_time": "14:28:05", "throughput": 554.74, "total_tokens": 36439888} {"current_steps": 22315, "total_steps": 40000, "loss": 0.1217, "lr": 2.0481442352755546e-05, "epoch": 1.0101858348989339, "percentage": 55.79, "elapsed_time": "18:14:51", "remaining_time": "14:27:41", "throughput": 554.84, "total_tokens": 36448400} {"current_steps": 22320, "total_steps": 40000, "loss": 0.1166, "lr": 2.0471786913436198e-05, "epoch": 1.0104121867855769, "percentage": 55.8, "elapsed_time": "18:14:54", "remaining_time": "14:27:17", "throughput": 554.95, "total_tokens": 36456944} {"current_steps": 22325, "total_steps": 40000, "loss": 0.1192, "lr": 2.0462132172424218e-05, "epoch": 1.0106385386722199, "percentage": 55.81, "elapsed_time": "18:14:57", "remaining_time": "14:26:53", "throughput": 555.04, "total_tokens": 36465200} {"current_steps": 22330, "total_steps": 40000, "loss": 0.1477, "lr": 2.0452478131208484e-05, "epoch": 1.0108648905588629, "percentage": 55.83, "elapsed_time": "18:15:01", "remaining_time": "14:26:30", "throughput": 555.15, "total_tokens": 36473808} {"current_steps": 22335, "total_steps": 40000, "loss": 0.1412, "lr": 2.0442824791277765e-05, "epoch": 1.0110912424455059, "percentage": 55.84, "elapsed_time": "18:15:04", "remaining_time": "14:26:06", "throughput": 555.23, "total_tokens": 36481232} {"current_steps": 22340, "total_steps": 40000, "loss": 0.0916, "lr": 2.0433172154120727e-05, "epoch": 1.0113175943321489, "percentage": 55.85, "elapsed_time": "18:15:07", "remaining_time": "14:25:42", "throughput": 555.34, "total_tokens": 36489968} {"current_steps": 22345, "total_steps": 40000, "loss": 0.0961, "lr": 2.0423520221225947e-05, "epoch": 1.0115439462187918, "percentage": 55.86, "elapsed_time": "18:15:10", "remaining_time": "14:25:18", "throughput": 555.44, "total_tokens": 36498160} {"current_steps": 22350, "total_steps": 40000, "loss": 0.1326, "lr": 2.0413868994081848e-05, "epoch": 1.0117702981054346, "percentage": 55.88, "elapsed_time": "18:15:13", "remaining_time": "14:24:54", "throughput": 555.54, "total_tokens": 36506640} {"current_steps": 22355, "total_steps": 40000, "loss": 0.0857, "lr": 2.0404218474176795e-05, "epoch": 1.0119966499920776, "percentage": 55.89, "elapsed_time": "18:15:17", "remaining_time": "14:24:31", "throughput": 555.64, "total_tokens": 36514992} {"current_steps": 22360, "total_steps": 40000, "loss": 0.075, "lr": 2.0394568662999002e-05, "epoch": 1.0122230018787206, "percentage": 55.9, "elapsed_time": "18:15:20", "remaining_time": "14:24:07", "throughput": 555.74, "total_tokens": 36523184} {"current_steps": 22365, "total_steps": 40000, "loss": 0.1461, "lr": 2.0384919562036593e-05, "epoch": 1.0124493537653636, "percentage": 55.91, "elapsed_time": "18:15:23", "remaining_time": "14:23:43", "throughput": 555.84, "total_tokens": 36531440} {"current_steps": 22370, "total_steps": 40000, "loss": 0.1604, "lr": 2.0375271172777593e-05, "epoch": 1.0126757056520066, "percentage": 55.93, "elapsed_time": "18:15:26", "remaining_time": "14:23:19", "throughput": 555.93, "total_tokens": 36539440} {"current_steps": 22375, "total_steps": 40000, "loss": 0.0709, "lr": 2.0365623496709885e-05, "epoch": 1.0129020575386496, "percentage": 55.94, "elapsed_time": "18:15:29", "remaining_time": "14:22:55", "throughput": 556.03, "total_tokens": 36547696} {"current_steps": 22380, "total_steps": 40000, "loss": 0.1113, "lr": 2.0355976535321283e-05, "epoch": 1.0131284094252926, "percentage": 55.95, "elapsed_time": "18:15:32", "remaining_time": "14:22:32", "throughput": 556.13, "total_tokens": 36555856} {"current_steps": 22385, "total_steps": 40000, "loss": 0.13, "lr": 2.034633029009945e-05, "epoch": 1.0133547613119356, "percentage": 55.96, "elapsed_time": "18:15:36", "remaining_time": "14:22:08", "throughput": 556.22, "total_tokens": 36563824} {"current_steps": 22390, "total_steps": 40000, "loss": 0.1047, "lr": 2.0336684762531972e-05, "epoch": 1.0135811131985786, "percentage": 55.97, "elapsed_time": "18:15:39", "remaining_time": "14:21:44", "throughput": 556.32, "total_tokens": 36571888} {"current_steps": 22395, "total_steps": 40000, "loss": 0.0785, "lr": 2.032703995410631e-05, "epoch": 1.0138074650852216, "percentage": 55.99, "elapsed_time": "18:15:42", "remaining_time": "14:21:20", "throughput": 556.4, "total_tokens": 36579344} {"current_steps": 22400, "total_steps": 40000, "loss": 0.1121, "lr": 2.031739586630981e-05, "epoch": 1.0140338169718646, "percentage": 56.0, "elapsed_time": "18:15:45", "remaining_time": "14:20:57", "throughput": 556.49, "total_tokens": 36586768} {"current_steps": 22400, "total_steps": 40000, "eval_loss": 0.12521368265151978, "epoch": 1.0140338169718646, "percentage": 56.0, "elapsed_time": "18:23:28", "remaining_time": "14:27:00", "throughput": 552.6, "total_tokens": 36586768} {"current_steps": 22405, "total_steps": 40000, "loss": 0.1363, "lr": 2.0307752500629707e-05, "epoch": 1.0142601688585073, "percentage": 56.01, "elapsed_time": "18:23:31", "remaining_time": "14:26:37", "throughput": 552.69, "total_tokens": 36594608} {"current_steps": 22410, "total_steps": 40000, "loss": 0.1437, "lr": 2.0298109858553144e-05, "epoch": 1.0144865207451503, "percentage": 56.03, "elapsed_time": "18:23:35", "remaining_time": "14:26:13", "throughput": 552.79, "total_tokens": 36602768} {"current_steps": 22415, "total_steps": 40000, "loss": 0.102, "lr": 2.028846794156712e-05, "epoch": 1.0147128726317933, "percentage": 56.04, "elapsed_time": "18:23:38", "remaining_time": "14:25:49", "throughput": 552.87, "total_tokens": 36610096} {"current_steps": 22420, "total_steps": 40000, "loss": 0.1149, "lr": 2.027882675115856e-05, "epoch": 1.0149392245184363, "percentage": 56.05, "elapsed_time": "18:23:41", "remaining_time": "14:25:25", "throughput": 552.96, "total_tokens": 36618064} {"current_steps": 22425, "total_steps": 40000, "loss": 0.1551, "lr": 2.026918628881423e-05, "epoch": 1.0151655764050793, "percentage": 56.06, "elapsed_time": "18:23:44", "remaining_time": "14:25:01", "throughput": 553.06, "total_tokens": 36626352} {"current_steps": 22430, "total_steps": 40000, "loss": 0.1036, "lr": 2.0259546556020833e-05, "epoch": 1.0153919282917223, "percentage": 56.07, "elapsed_time": "18:23:47", "remaining_time": "14:24:37", "throughput": 553.15, "total_tokens": 36634128} {"current_steps": 22435, "total_steps": 40000, "loss": 0.1344, "lr": 2.024990755426493e-05, "epoch": 1.0156182801783653, "percentage": 56.09, "elapsed_time": "18:23:50", "remaining_time": "14:24:13", "throughput": 553.25, "total_tokens": 36641968} {"current_steps": 22440, "total_steps": 40000, "loss": 0.0829, "lr": 2.0240269285032975e-05, "epoch": 1.0158446320650083, "percentage": 56.1, "elapsed_time": "18:23:53", "remaining_time": "14:23:50", "throughput": 553.35, "total_tokens": 36650416} {"current_steps": 22445, "total_steps": 40000, "loss": 0.1379, "lr": 2.0230631749811306e-05, "epoch": 1.0160709839516513, "percentage": 56.11, "elapsed_time": "18:23:57", "remaining_time": "14:23:26", "throughput": 553.44, "total_tokens": 36658160} {"current_steps": 22450, "total_steps": 40000, "loss": 0.1409, "lr": 2.0220994950086162e-05, "epoch": 1.0162973358382943, "percentage": 56.12, "elapsed_time": "18:24:00", "remaining_time": "14:23:02", "throughput": 553.53, "total_tokens": 36666064} {"current_steps": 22455, "total_steps": 40000, "loss": 0.1412, "lr": 2.021135888734365e-05, "epoch": 1.0165236877249373, "percentage": 56.14, "elapsed_time": "18:24:03", "remaining_time": "14:22:38", "throughput": 553.62, "total_tokens": 36674000} {"current_steps": 22460, "total_steps": 40000, "loss": 0.1147, "lr": 2.0201723563069783e-05, "epoch": 1.01675003961158, "percentage": 56.15, "elapsed_time": "18:24:06", "remaining_time": "14:22:15", "throughput": 553.73, "total_tokens": 36682928} {"current_steps": 22465, "total_steps": 40000, "loss": 0.0826, "lr": 2.0192088978750433e-05, "epoch": 1.016976391498223, "percentage": 56.16, "elapsed_time": "18:24:09", "remaining_time": "14:21:51", "throughput": 553.83, "total_tokens": 36691056} {"current_steps": 22470, "total_steps": 40000, "loss": 0.0782, "lr": 2.0182455135871385e-05, "epoch": 1.017202743384866, "percentage": 56.17, "elapsed_time": "18:24:13", "remaining_time": "14:21:27", "throughput": 553.92, "total_tokens": 36698864} {"current_steps": 22475, "total_steps": 40000, "loss": 0.0823, "lr": 2.0172822035918305e-05, "epoch": 1.017429095271509, "percentage": 56.19, "elapsed_time": "18:24:16", "remaining_time": "14:21:03", "throughput": 554.02, "total_tokens": 36707152} {"current_steps": 22480, "total_steps": 40000, "loss": 0.0847, "lr": 2.016318968037671e-05, "epoch": 1.017655447158152, "percentage": 56.2, "elapsed_time": "18:24:19", "remaining_time": "14:20:39", "throughput": 554.11, "total_tokens": 36714928} {"current_steps": 22485, "total_steps": 40000, "loss": 0.1352, "lr": 2.015355807073206e-05, "epoch": 1.017881799044795, "percentage": 56.21, "elapsed_time": "18:24:22", "remaining_time": "14:20:16", "throughput": 554.2, "total_tokens": 36722608} {"current_steps": 22490, "total_steps": 40000, "loss": 0.1177, "lr": 2.0143927208469664e-05, "epoch": 1.018108150931438, "percentage": 56.23, "elapsed_time": "18:24:25", "remaining_time": "14:19:52", "throughput": 554.29, "total_tokens": 36730448} {"current_steps": 22495, "total_steps": 40000, "loss": 0.1316, "lr": 2.0134297095074708e-05, "epoch": 1.018334502818081, "percentage": 56.24, "elapsed_time": "18:24:28", "remaining_time": "14:19:28", "throughput": 554.38, "total_tokens": 36738416} {"current_steps": 22500, "total_steps": 40000, "loss": 0.0983, "lr": 2.0124667732032297e-05, "epoch": 1.018560854704724, "percentage": 56.25, "elapsed_time": "18:24:32", "remaining_time": "14:19:04", "throughput": 554.49, "total_tokens": 36746992} {"current_steps": 22505, "total_steps": 40000, "loss": 0.1445, "lr": 2.011503912082738e-05, "epoch": 1.018787206591367, "percentage": 56.26, "elapsed_time": "18:24:35", "remaining_time": "14:18:41", "throughput": 554.58, "total_tokens": 36755152} {"current_steps": 22510, "total_steps": 40000, "loss": 0.164, "lr": 2.0105411262944823e-05, "epoch": 1.01901355847801, "percentage": 56.27, "elapsed_time": "18:24:38", "remaining_time": "14:18:17", "throughput": 554.67, "total_tokens": 36762896} {"current_steps": 22515, "total_steps": 40000, "loss": 0.103, "lr": 2.0095784159869366e-05, "epoch": 1.0192399103646528, "percentage": 56.29, "elapsed_time": "18:24:41", "remaining_time": "14:17:53", "throughput": 554.77, "total_tokens": 36771248} {"current_steps": 22520, "total_steps": 40000, "loss": 0.1309, "lr": 2.0086157813085608e-05, "epoch": 1.0194662622512958, "percentage": 56.3, "elapsed_time": "18:24:44", "remaining_time": "14:17:30", "throughput": 554.87, "total_tokens": 36779440} {"current_steps": 22525, "total_steps": 40000, "loss": 0.1202, "lr": 2.0076532224078068e-05, "epoch": 1.0196926141379388, "percentage": 56.31, "elapsed_time": "18:24:47", "remaining_time": "14:17:06", "throughput": 554.96, "total_tokens": 36787440} {"current_steps": 22530, "total_steps": 40000, "loss": 0.1322, "lr": 2.0066907394331142e-05, "epoch": 1.0199189660245818, "percentage": 56.33, "elapsed_time": "18:24:51", "remaining_time": "14:16:42", "throughput": 555.06, "total_tokens": 36795632} {"current_steps": 22535, "total_steps": 40000, "loss": 0.1182, "lr": 2.0057283325329077e-05, "epoch": 1.0201453179112248, "percentage": 56.34, "elapsed_time": "18:24:54", "remaining_time": "14:16:19", "throughput": 555.17, "total_tokens": 36804528} {"current_steps": 22540, "total_steps": 40000, "loss": 0.0907, "lr": 2.0047660018556047e-05, "epoch": 1.0203716697978678, "percentage": 56.35, "elapsed_time": "18:24:57", "remaining_time": "14:15:55", "throughput": 555.26, "total_tokens": 36812272} {"current_steps": 22545, "total_steps": 40000, "loss": 0.0946, "lr": 2.0038037475496075e-05, "epoch": 1.0205980216845107, "percentage": 56.36, "elapsed_time": "18:25:00", "remaining_time": "14:15:31", "throughput": 555.35, "total_tokens": 36820336} {"current_steps": 22550, "total_steps": 40000, "loss": 0.1532, "lr": 2.0028415697633073e-05, "epoch": 1.0208243735711537, "percentage": 56.38, "elapsed_time": "18:25:04", "remaining_time": "14:15:08", "throughput": 555.45, "total_tokens": 36828880} {"current_steps": 22555, "total_steps": 40000, "loss": 0.1932, "lr": 2.0018794686450858e-05, "epoch": 1.0210507254577967, "percentage": 56.39, "elapsed_time": "18:25:07", "remaining_time": "14:14:44", "throughput": 555.55, "total_tokens": 36836656} {"current_steps": 22560, "total_steps": 40000, "loss": 0.1403, "lr": 2.0009174443433088e-05, "epoch": 1.0212770773444397, "percentage": 56.4, "elapsed_time": "18:25:10", "remaining_time": "14:14:21", "throughput": 555.64, "total_tokens": 36844528} {"current_steps": 22565, "total_steps": 40000, "loss": 0.1231, "lr": 1.999955497006334e-05, "epoch": 1.0215034292310827, "percentage": 56.41, "elapsed_time": "18:25:13", "remaining_time": "14:13:57", "throughput": 555.75, "total_tokens": 36854192} {"current_steps": 22570, "total_steps": 40000, "loss": 0.1133, "lr": 1.9989936267825067e-05, "epoch": 1.0217297811177257, "percentage": 56.43, "elapsed_time": "18:25:17", "remaining_time": "14:13:34", "throughput": 555.85, "total_tokens": 36862384} {"current_steps": 22575, "total_steps": 40000, "loss": 0.0929, "lr": 1.9980318338201572e-05, "epoch": 1.0219561330043685, "percentage": 56.44, "elapsed_time": "18:25:20", "remaining_time": "14:13:10", "throughput": 555.95, "total_tokens": 36870928} {"current_steps": 22580, "total_steps": 40000, "loss": 0.0958, "lr": 1.997070118267607e-05, "epoch": 1.0221824848910115, "percentage": 56.45, "elapsed_time": "18:25:23", "remaining_time": "14:12:47", "throughput": 556.04, "total_tokens": 36878640} {"current_steps": 22585, "total_steps": 40000, "loss": 0.1228, "lr": 1.9961084802731654e-05, "epoch": 1.0224088367776545, "percentage": 56.46, "elapsed_time": "18:25:26", "remaining_time": "14:12:23", "throughput": 556.14, "total_tokens": 36886512} {"current_steps": 22590, "total_steps": 40000, "loss": 0.1265, "lr": 1.9951469199851273e-05, "epoch": 1.0226351886642975, "percentage": 56.47, "elapsed_time": "18:25:29", "remaining_time": "14:11:59", "throughput": 556.23, "total_tokens": 36894544} {"current_steps": 22595, "total_steps": 40000, "loss": 0.0961, "lr": 1.99418543755178e-05, "epoch": 1.0228615405509405, "percentage": 56.49, "elapsed_time": "18:25:33", "remaining_time": "14:11:36", "throughput": 556.35, "total_tokens": 36904080} {"current_steps": 22600, "total_steps": 40000, "loss": 0.1369, "lr": 1.9932240331213936e-05, "epoch": 1.0230878924375835, "percentage": 56.5, "elapsed_time": "18:25:36", "remaining_time": "14:11:13", "throughput": 556.44, "total_tokens": 36912400} {"current_steps": 22600, "total_steps": 40000, "eval_loss": 0.12455565482378006, "epoch": 1.0230878924375835, "percentage": 56.5, "elapsed_time": "18:33:18", "remaining_time": "14:17:09", "throughput": 552.59, "total_tokens": 36912400} {"current_steps": 22605, "total_steps": 40000, "loss": 0.1325, "lr": 1.9922627068422297e-05, "epoch": 1.0233142443242265, "percentage": 56.51, "elapsed_time": "18:33:22", "remaining_time": "14:16:46", "throughput": 552.67, "total_tokens": 36920176} {"current_steps": 22610, "total_steps": 40000, "loss": 0.165, "lr": 1.991301458862538e-05, "epoch": 1.0235405962108695, "percentage": 56.53, "elapsed_time": "18:33:25", "remaining_time": "14:16:22", "throughput": 552.77, "total_tokens": 36927984} {"current_steps": 22615, "total_steps": 40000, "loss": 0.1099, "lr": 1.9903402893305536e-05, "epoch": 1.0237669480975125, "percentage": 56.54, "elapsed_time": "18:33:29", "remaining_time": "14:15:58", "throughput": 552.86, "total_tokens": 36936080} {"current_steps": 22620, "total_steps": 40000, "loss": 0.1605, "lr": 1.9893791983945016e-05, "epoch": 1.0239932999841554, "percentage": 56.55, "elapsed_time": "18:33:32", "remaining_time": "14:15:35", "throughput": 552.97, "total_tokens": 36945328} {"current_steps": 22625, "total_steps": 40000, "loss": 0.1305, "lr": 1.988418186202594e-05, "epoch": 1.0242196518707984, "percentage": 56.56, "elapsed_time": "18:33:35", "remaining_time": "14:15:11", "throughput": 553.06, "total_tokens": 36952720} {"current_steps": 22630, "total_steps": 40000, "loss": 0.1248, "lr": 1.98745725290303e-05, "epoch": 1.0244460037574412, "percentage": 56.57, "elapsed_time": "18:33:38", "remaining_time": "14:14:47", "throughput": 553.16, "total_tokens": 36961232} {"current_steps": 22635, "total_steps": 40000, "loss": 0.1092, "lr": 1.986496398644e-05, "epoch": 1.0246723556440842, "percentage": 56.59, "elapsed_time": "18:33:41", "remaining_time": "14:14:23", "throughput": 553.24, "total_tokens": 36968656} {"current_steps": 22640, "total_steps": 40000, "loss": 0.1109, "lr": 1.9855356235736777e-05, "epoch": 1.0248987075307272, "percentage": 56.6, "elapsed_time": "18:33:45", "remaining_time": "14:14:00", "throughput": 553.35, "total_tokens": 36977424} {"current_steps": 22645, "total_steps": 40000, "loss": 0.1235, "lr": 1.9845749278402277e-05, "epoch": 1.0251250594173702, "percentage": 56.61, "elapsed_time": "18:33:48", "remaining_time": "14:13:36", "throughput": 553.44, "total_tokens": 36985360} {"current_steps": 22650, "total_steps": 40000, "loss": 0.213, "lr": 1.9836143115918006e-05, "epoch": 1.0253514113040132, "percentage": 56.62, "elapsed_time": "18:33:51", "remaining_time": "14:13:13", "throughput": 553.53, "total_tokens": 36993008} {"current_steps": 22655, "total_steps": 40000, "loss": 0.1291, "lr": 1.9826537749765367e-05, "epoch": 1.0255777631906562, "percentage": 56.64, "elapsed_time": "18:33:54", "remaining_time": "14:12:49", "throughput": 553.62, "total_tokens": 37000816} {"current_steps": 22660, "total_steps": 40000, "loss": 0.0999, "lr": 1.9816933181425625e-05, "epoch": 1.0258041150772992, "percentage": 56.65, "elapsed_time": "18:33:57", "remaining_time": "14:12:25", "throughput": 553.71, "total_tokens": 37008944} {"current_steps": 22665, "total_steps": 40000, "loss": 0.0891, "lr": 1.9807329412379903e-05, "epoch": 1.0260304669639422, "percentage": 56.66, "elapsed_time": "18:34:00", "remaining_time": "14:12:02", "throughput": 553.81, "total_tokens": 37017296} {"current_steps": 22670, "total_steps": 40000, "loss": 0.1601, "lr": 1.9797726444109247e-05, "epoch": 1.0262568188505852, "percentage": 56.67, "elapsed_time": "18:34:03", "remaining_time": "14:11:38", "throughput": 553.91, "total_tokens": 37025296} {"current_steps": 22675, "total_steps": 40000, "loss": 0.1494, "lr": 1.9788124278094557e-05, "epoch": 1.0264831707372282, "percentage": 56.69, "elapsed_time": "18:34:07", "remaining_time": "14:11:15", "throughput": 554.0, "total_tokens": 37033424} {"current_steps": 22680, "total_steps": 40000, "loss": 0.1297, "lr": 1.9778522915816594e-05, "epoch": 1.0267095226238712, "percentage": 56.7, "elapsed_time": "18:34:10", "remaining_time": "14:10:51", "throughput": 554.09, "total_tokens": 37040944} {"current_steps": 22685, "total_steps": 40000, "loss": 0.0784, "lr": 1.9768922358756014e-05, "epoch": 1.0269358745105142, "percentage": 56.71, "elapsed_time": "18:34:13", "remaining_time": "14:10:27", "throughput": 554.18, "total_tokens": 37048912} {"current_steps": 22690, "total_steps": 40000, "loss": 0.1239, "lr": 1.9759322608393353e-05, "epoch": 1.027162226397157, "percentage": 56.73, "elapsed_time": "18:34:16", "remaining_time": "14:10:04", "throughput": 554.27, "total_tokens": 37056816} {"current_steps": 22695, "total_steps": 40000, "loss": 0.0999, "lr": 1.9749723666208992e-05, "epoch": 1.0273885782838, "percentage": 56.74, "elapsed_time": "18:34:19", "remaining_time": "14:09:40", "throughput": 554.37, "total_tokens": 37064720} {"current_steps": 22700, "total_steps": 40000, "loss": 0.1334, "lr": 1.9740125533683235e-05, "epoch": 1.027614930170443, "percentage": 56.75, "elapsed_time": "18:34:22", "remaining_time": "14:09:17", "throughput": 554.47, "total_tokens": 37073104} {"current_steps": 22705, "total_steps": 40000, "loss": 0.0922, "lr": 1.9730528212296208e-05, "epoch": 1.027841282057086, "percentage": 56.76, "elapsed_time": "18:34:26", "remaining_time": "14:08:53", "throughput": 554.57, "total_tokens": 37081616} {"current_steps": 22710, "total_steps": 40000, "loss": 0.1356, "lr": 1.9720931703527945e-05, "epoch": 1.028067633943729, "percentage": 56.77, "elapsed_time": "18:34:29", "remaining_time": "14:08:30", "throughput": 554.67, "total_tokens": 37090160} {"current_steps": 22715, "total_steps": 40000, "loss": 0.1178, "lr": 1.9711336008858373e-05, "epoch": 1.028293985830372, "percentage": 56.79, "elapsed_time": "18:34:32", "remaining_time": "14:08:06", "throughput": 554.75, "total_tokens": 37097744} {"current_steps": 22720, "total_steps": 40000, "loss": 0.1206, "lr": 1.9701741129767233e-05, "epoch": 1.028520337717015, "percentage": 56.8, "elapsed_time": "18:34:35", "remaining_time": "14:07:43", "throughput": 554.86, "total_tokens": 37106352} {"current_steps": 22725, "total_steps": 40000, "loss": 0.1343, "lr": 1.9692147067734202e-05, "epoch": 1.028746689603658, "percentage": 56.81, "elapsed_time": "18:34:38", "remaining_time": "14:07:19", "throughput": 554.96, "total_tokens": 37114928} {"current_steps": 22730, "total_steps": 40000, "loss": 0.1053, "lr": 1.96825538242388e-05, "epoch": 1.0289730414903009, "percentage": 56.83, "elapsed_time": "18:34:42", "remaining_time": "14:06:56", "throughput": 555.06, "total_tokens": 37123280} {"current_steps": 22735, "total_steps": 40000, "loss": 0.0723, "lr": 1.967296140076041e-05, "epoch": 1.0291993933769439, "percentage": 56.84, "elapsed_time": "18:34:45", "remaining_time": "14:06:32", "throughput": 555.14, "total_tokens": 37130832} {"current_steps": 22740, "total_steps": 40000, "loss": 0.0919, "lr": 1.966336979877833e-05, "epoch": 1.0294257452635869, "percentage": 56.85, "elapsed_time": "18:34:48", "remaining_time": "14:06:09", "throughput": 555.24, "total_tokens": 37138896} {"current_steps": 22745, "total_steps": 40000, "loss": 0.1455, "lr": 1.9653779019771678e-05, "epoch": 1.0296520971502297, "percentage": 56.86, "elapsed_time": "18:34:51", "remaining_time": "14:05:45", "throughput": 555.33, "total_tokens": 37147120} {"current_steps": 22750, "total_steps": 40000, "loss": 0.1173, "lr": 1.9644189065219488e-05, "epoch": 1.0298784490368726, "percentage": 56.88, "elapsed_time": "18:34:54", "remaining_time": "14:05:22", "throughput": 555.42, "total_tokens": 37154416} {"current_steps": 22755, "total_steps": 40000, "loss": 0.1315, "lr": 1.9634599936600655e-05, "epoch": 1.0301048009235156, "percentage": 56.89, "elapsed_time": "18:34:57", "remaining_time": "14:04:58", "throughput": 555.51, "total_tokens": 37162160} {"current_steps": 22760, "total_steps": 40000, "loss": 0.1112, "lr": 1.9625011635393935e-05, "epoch": 1.0303311528101586, "percentage": 56.9, "elapsed_time": "18:35:00", "remaining_time": "14:04:35", "throughput": 555.6, "total_tokens": 37170064} {"current_steps": 22765, "total_steps": 40000, "loss": 0.1497, "lr": 1.9615424163077963e-05, "epoch": 1.0305575046968016, "percentage": 56.91, "elapsed_time": "18:35:03", "remaining_time": "14:04:11", "throughput": 555.69, "total_tokens": 37177776} {"current_steps": 22770, "total_steps": 40000, "loss": 0.1696, "lr": 1.9605837521131263e-05, "epoch": 1.0307838565834446, "percentage": 56.93, "elapsed_time": "18:35:07", "remaining_time": "14:03:48", "throughput": 555.79, "total_tokens": 37186032} {"current_steps": 22775, "total_steps": 40000, "loss": 0.161, "lr": 1.9596251711032192e-05, "epoch": 1.0310102084700876, "percentage": 56.94, "elapsed_time": "18:35:10", "remaining_time": "14:03:25", "throughput": 555.89, "total_tokens": 37194608} {"current_steps": 22780, "total_steps": 40000, "loss": 0.1368, "lr": 1.958666673425903e-05, "epoch": 1.0312365603567306, "percentage": 56.95, "elapsed_time": "18:35:13", "remaining_time": "14:03:01", "throughput": 555.98, "total_tokens": 37202896} {"current_steps": 22785, "total_steps": 40000, "loss": 0.1188, "lr": 1.957708259228987e-05, "epoch": 1.0314629122433736, "percentage": 56.96, "elapsed_time": "18:35:16", "remaining_time": "14:02:38", "throughput": 556.08, "total_tokens": 37210896} {"current_steps": 22790, "total_steps": 40000, "loss": 0.093, "lr": 1.956749928660273e-05, "epoch": 1.0316892641300166, "percentage": 56.97, "elapsed_time": "18:35:19", "remaining_time": "14:02:14", "throughput": 556.18, "total_tokens": 37219184} {"current_steps": 22795, "total_steps": 40000, "loss": 0.1675, "lr": 1.955791681867547e-05, "epoch": 1.0319156160166596, "percentage": 56.99, "elapsed_time": "18:35:22", "remaining_time": "14:01:51", "throughput": 556.27, "total_tokens": 37227024} {"current_steps": 22800, "total_steps": 40000, "loss": 0.1304, "lr": 1.9548335189985824e-05, "epoch": 1.0321419679033024, "percentage": 57.0, "elapsed_time": "18:35:26", "remaining_time": "14:01:28", "throughput": 556.35, "total_tokens": 37234576} {"current_steps": 22800, "total_steps": 40000, "eval_loss": 0.12443861365318298, "epoch": 1.0321419679033024, "percentage": 57.0, "elapsed_time": "18:43:08", "remaining_time": "14:07:17", "throughput": 552.53, "total_tokens": 37234576} {"current_steps": 22805, "total_steps": 40000, "loss": 0.1693, "lr": 1.9538754402011396e-05, "epoch": 1.0323683197899454, "percentage": 57.01, "elapsed_time": "18:43:12", "remaining_time": "14:06:54", "throughput": 552.63, "total_tokens": 37243152} {"current_steps": 22810, "total_steps": 40000, "loss": 0.1994, "lr": 1.952917445622968e-05, "epoch": 1.0325946716765884, "percentage": 57.03, "elapsed_time": "18:43:15", "remaining_time": "14:06:30", "throughput": 552.72, "total_tokens": 37251056} {"current_steps": 22815, "total_steps": 40000, "loss": 0.1314, "lr": 1.9519595354118005e-05, "epoch": 1.0328210235632314, "percentage": 57.04, "elapsed_time": "18:43:19", "remaining_time": "14:06:07", "throughput": 552.81, "total_tokens": 37259088} {"current_steps": 22820, "total_steps": 40000, "loss": 0.1082, "lr": 1.951001709715361e-05, "epoch": 1.0330473754498743, "percentage": 57.05, "elapsed_time": "18:43:22", "remaining_time": "14:05:43", "throughput": 552.92, "total_tokens": 37267856} {"current_steps": 22825, "total_steps": 40000, "loss": 0.1285, "lr": 1.9500439686813556e-05, "epoch": 1.0332737273365173, "percentage": 57.06, "elapsed_time": "18:43:25", "remaining_time": "14:05:20", "throughput": 553.01, "total_tokens": 37275824} {"current_steps": 22830, "total_steps": 40000, "loss": 0.0984, "lr": 1.949086312457482e-05, "epoch": 1.0335000792231603, "percentage": 57.07, "elapsed_time": "18:43:28", "remaining_time": "14:04:56", "throughput": 553.1, "total_tokens": 37283536} {"current_steps": 22835, "total_steps": 40000, "loss": 0.1014, "lr": 1.9481287411914223e-05, "epoch": 1.0337264311098033, "percentage": 57.09, "elapsed_time": "18:43:31", "remaining_time": "14:04:33", "throughput": 553.2, "total_tokens": 37292080} {"current_steps": 22840, "total_steps": 40000, "loss": 0.1193, "lr": 1.9471712550308457e-05, "epoch": 1.0339527829964463, "percentage": 57.1, "elapsed_time": "18:43:35", "remaining_time": "14:04:09", "throughput": 553.3, "total_tokens": 37300496} {"current_steps": 22845, "total_steps": 40000, "loss": 0.1072, "lr": 1.946213854123409e-05, "epoch": 1.0341791348830893, "percentage": 57.11, "elapsed_time": "18:43:38", "remaining_time": "14:03:46", "throughput": 553.39, "total_tokens": 37308272} {"current_steps": 22850, "total_steps": 40000, "loss": 0.1146, "lr": 1.9452565386167554e-05, "epoch": 1.0344054867697323, "percentage": 57.12, "elapsed_time": "18:43:41", "remaining_time": "14:03:22", "throughput": 553.48, "total_tokens": 37316208} {"current_steps": 22855, "total_steps": 40000, "loss": 0.103, "lr": 1.9442993086585142e-05, "epoch": 1.034631838656375, "percentage": 57.14, "elapsed_time": "18:43:44", "remaining_time": "14:02:59", "throughput": 553.56, "total_tokens": 37323760} {"current_steps": 22860, "total_steps": 40000, "loss": 0.0857, "lr": 1.9433421643963043e-05, "epoch": 1.034858190543018, "percentage": 57.15, "elapsed_time": "18:43:47", "remaining_time": "14:02:35", "throughput": 553.66, "total_tokens": 37332048} {"current_steps": 22865, "total_steps": 40000, "loss": 0.0855, "lr": 1.942385105977727e-05, "epoch": 1.035084542429661, "percentage": 57.16, "elapsed_time": "18:43:50", "remaining_time": "14:02:12", "throughput": 553.75, "total_tokens": 37339568} {"current_steps": 22870, "total_steps": 40000, "loss": 0.0921, "lr": 1.9414281335503743e-05, "epoch": 1.035310894316304, "percentage": 57.17, "elapsed_time": "18:43:53", "remaining_time": "14:01:49", "throughput": 553.83, "total_tokens": 37347184} {"current_steps": 22875, "total_steps": 40000, "loss": 0.1385, "lr": 1.9404712472618232e-05, "epoch": 1.035537246202947, "percentage": 57.19, "elapsed_time": "18:43:56", "remaining_time": "14:01:25", "throughput": 553.92, "total_tokens": 37354832} {"current_steps": 22880, "total_steps": 40000, "loss": 0.1695, "lr": 1.939514447259636e-05, "epoch": 1.03576359808959, "percentage": 57.2, "elapsed_time": "18:44:00", "remaining_time": "14:01:02", "throughput": 554.02, "total_tokens": 37363184} {"current_steps": 22885, "total_steps": 40000, "loss": 0.0759, "lr": 1.938557733691365e-05, "epoch": 1.035989949976233, "percentage": 57.21, "elapsed_time": "18:44:03", "remaining_time": "14:00:38", "throughput": 554.12, "total_tokens": 37371568} {"current_steps": 22890, "total_steps": 40000, "loss": 0.1566, "lr": 1.9376011067045476e-05, "epoch": 1.036216301862876, "percentage": 57.23, "elapsed_time": "18:44:06", "remaining_time": "14:00:15", "throughput": 554.21, "total_tokens": 37379472} {"current_steps": 22895, "total_steps": 40000, "loss": 0.0772, "lr": 1.9366445664467065e-05, "epoch": 1.036442653749519, "percentage": 57.24, "elapsed_time": "18:44:09", "remaining_time": "13:59:52", "throughput": 554.3, "total_tokens": 37387664} {"current_steps": 22900, "total_steps": 40000, "loss": 0.1194, "lr": 1.9356881130653533e-05, "epoch": 1.036669005636162, "percentage": 57.25, "elapsed_time": "18:44:13", "remaining_time": "13:59:28", "throughput": 554.4, "total_tokens": 37396176} {"current_steps": 22905, "total_steps": 40000, "loss": 0.131, "lr": 1.9347317467079846e-05, "epoch": 1.036895357522805, "percentage": 57.26, "elapsed_time": "18:44:16", "remaining_time": "13:59:05", "throughput": 554.49, "total_tokens": 37404048} {"current_steps": 22910, "total_steps": 40000, "loss": 0.0949, "lr": 1.9337754675220836e-05, "epoch": 1.037121709409448, "percentage": 57.27, "elapsed_time": "18:44:19", "remaining_time": "13:58:42", "throughput": 554.59, "total_tokens": 37412240} {"current_steps": 22915, "total_steps": 40000, "loss": 0.0951, "lr": 1.9328192756551218e-05, "epoch": 1.0373480612960908, "percentage": 57.29, "elapsed_time": "18:44:22", "remaining_time": "13:58:18", "throughput": 554.68, "total_tokens": 37420272} {"current_steps": 22920, "total_steps": 40000, "loss": 0.1265, "lr": 1.931863171254555e-05, "epoch": 1.0375744131827338, "percentage": 57.3, "elapsed_time": "18:44:25", "remaining_time": "13:57:55", "throughput": 554.78, "total_tokens": 37428752} {"current_steps": 22925, "total_steps": 40000, "loss": 0.0825, "lr": 1.930907154467826e-05, "epoch": 1.0378007650693768, "percentage": 57.31, "elapsed_time": "18:44:29", "remaining_time": "13:57:32", "throughput": 554.88, "total_tokens": 37437520} {"current_steps": 22930, "total_steps": 40000, "loss": 0.132, "lr": 1.9299512254423673e-05, "epoch": 1.0380271169560198, "percentage": 57.33, "elapsed_time": "18:44:32", "remaining_time": "13:57:09", "throughput": 554.99, "total_tokens": 37446544} {"current_steps": 22935, "total_steps": 40000, "loss": 0.0938, "lr": 1.9289953843255914e-05, "epoch": 1.0382534688426628, "percentage": 57.34, "elapsed_time": "18:44:35", "remaining_time": "13:56:45", "throughput": 555.08, "total_tokens": 37454096} {"current_steps": 22940, "total_steps": 40000, "loss": 0.1101, "lr": 1.9280396312649048e-05, "epoch": 1.0384798207293058, "percentage": 57.35, "elapsed_time": "18:44:38", "remaining_time": "13:56:22", "throughput": 555.17, "total_tokens": 37462000} {"current_steps": 22945, "total_steps": 40000, "loss": 0.1228, "lr": 1.9270839664076936e-05, "epoch": 1.0387061726159488, "percentage": 57.36, "elapsed_time": "18:44:41", "remaining_time": "13:55:59", "throughput": 555.26, "total_tokens": 37470288} {"current_steps": 22950, "total_steps": 40000, "loss": 0.0932, "lr": 1.9261283899013345e-05, "epoch": 1.0389325245025918, "percentage": 57.38, "elapsed_time": "18:44:45", "remaining_time": "13:55:35", "throughput": 555.35, "total_tokens": 37477872} {"current_steps": 22955, "total_steps": 40000, "loss": 0.1314, "lr": 1.92517290189319e-05, "epoch": 1.0391588763892348, "percentage": 57.39, "elapsed_time": "18:44:48", "remaining_time": "13:55:12", "throughput": 555.44, "total_tokens": 37485648} {"current_steps": 22960, "total_steps": 40000, "loss": 0.0854, "lr": 1.924217502530607e-05, "epoch": 1.0393852282758778, "percentage": 57.4, "elapsed_time": "18:44:51", "remaining_time": "13:54:49", "throughput": 555.54, "total_tokens": 37494416} {"current_steps": 22965, "total_steps": 40000, "loss": 0.1352, "lr": 1.9232621919609207e-05, "epoch": 1.0396115801625208, "percentage": 57.41, "elapsed_time": "18:44:54", "remaining_time": "13:54:26", "throughput": 555.63, "total_tokens": 37502224} {"current_steps": 22970, "total_steps": 40000, "loss": 0.1203, "lr": 1.9223069703314534e-05, "epoch": 1.0398379320491635, "percentage": 57.43, "elapsed_time": "18:44:57", "remaining_time": "13:54:03", "throughput": 555.73, "total_tokens": 37510448} {"current_steps": 22975, "total_steps": 40000, "loss": 0.1192, "lr": 1.92135183778951e-05, "epoch": 1.0400642839358065, "percentage": 57.44, "elapsed_time": "18:45:00", "remaining_time": "13:53:39", "throughput": 555.82, "total_tokens": 37518352} {"current_steps": 22980, "total_steps": 40000, "loss": 0.1363, "lr": 1.9203967944823857e-05, "epoch": 1.0402906358224495, "percentage": 57.45, "elapsed_time": "18:45:04", "remaining_time": "13:53:16", "throughput": 555.91, "total_tokens": 37526128} {"current_steps": 22985, "total_steps": 40000, "loss": 0.1151, "lr": 1.9194418405573588e-05, "epoch": 1.0405169877090925, "percentage": 57.46, "elapsed_time": "18:45:07", "remaining_time": "13:52:53", "throughput": 556.0, "total_tokens": 37534160} {"current_steps": 22990, "total_steps": 40000, "loss": 0.1327, "lr": 1.9184869761616954e-05, "epoch": 1.0407433395957355, "percentage": 57.48, "elapsed_time": "18:45:10", "remaining_time": "13:52:30", "throughput": 556.1, "total_tokens": 37542192} {"current_steps": 22995, "total_steps": 40000, "loss": 0.1399, "lr": 1.9175322014426495e-05, "epoch": 1.0409696914823785, "percentage": 57.49, "elapsed_time": "18:45:13", "remaining_time": "13:52:06", "throughput": 556.19, "total_tokens": 37550288} {"current_steps": 23000, "total_steps": 40000, "loss": 0.0972, "lr": 1.9165775165474565e-05, "epoch": 1.0411960433690215, "percentage": 57.5, "elapsed_time": "18:45:16", "remaining_time": "13:51:43", "throughput": 556.28, "total_tokens": 37558256} {"current_steps": 23000, "total_steps": 40000, "eval_loss": 0.12450374662876129, "epoch": 1.0411960433690215, "percentage": 57.5, "elapsed_time": "18:52:59", "remaining_time": "13:57:25", "throughput": 552.5, "total_tokens": 37558256} {"current_steps": 23005, "total_steps": 40000, "loss": 0.1213, "lr": 1.9156229216233434e-05, "epoch": 1.0414223952556645, "percentage": 57.51, "elapsed_time": "18:53:03", "remaining_time": "13:57:02", "throughput": 552.57, "total_tokens": 37565712} {"current_steps": 23010, "total_steps": 40000, "loss": 0.131, "lr": 1.9146684168175184e-05, "epoch": 1.0416487471423075, "percentage": 57.53, "elapsed_time": "18:53:06", "remaining_time": "13:56:39", "throughput": 552.68, "total_tokens": 37574608} {"current_steps": 23015, "total_steps": 40000, "loss": 0.1227, "lr": 1.9137140022771796e-05, "epoch": 1.0418750990289505, "percentage": 57.54, "elapsed_time": "18:53:09", "remaining_time": "13:56:16", "throughput": 552.77, "total_tokens": 37582512} {"current_steps": 23020, "total_steps": 40000, "loss": 0.1073, "lr": 1.9127596781495103e-05, "epoch": 1.0421014509155935, "percentage": 57.55, "elapsed_time": "18:53:13", "remaining_time": "13:55:52", "throughput": 552.86, "total_tokens": 37590448} {"current_steps": 23025, "total_steps": 40000, "loss": 0.1083, "lr": 1.9118054445816767e-05, "epoch": 1.0423278028022365, "percentage": 57.56, "elapsed_time": "18:53:16", "remaining_time": "13:55:29", "throughput": 552.96, "total_tokens": 37599536} {"current_steps": 23030, "total_steps": 40000, "loss": 0.1282, "lr": 1.9108513017208356e-05, "epoch": 1.0425541546888792, "percentage": 57.57, "elapsed_time": "18:53:19", "remaining_time": "13:55:06", "throughput": 553.06, "total_tokens": 37607728} {"current_steps": 23035, "total_steps": 40000, "loss": 0.1344, "lr": 1.9098972497141287e-05, "epoch": 1.0427805065755222, "percentage": 57.59, "elapsed_time": "18:53:22", "remaining_time": "13:54:43", "throughput": 553.15, "total_tokens": 37615440} {"current_steps": 23040, "total_steps": 40000, "loss": 0.1123, "lr": 1.9089432887086806e-05, "epoch": 1.0430068584621652, "percentage": 57.6, "elapsed_time": "18:53:25", "remaining_time": "13:54:19", "throughput": 553.24, "total_tokens": 37623664} {"current_steps": 23045, "total_steps": 40000, "loss": 0.0991, "lr": 1.9079894188516056e-05, "epoch": 1.0432332103488082, "percentage": 57.61, "elapsed_time": "18:53:28", "remaining_time": "13:53:56", "throughput": 553.33, "total_tokens": 37631408} {"current_steps": 23050, "total_steps": 40000, "loss": 0.1478, "lr": 1.907035640290002e-05, "epoch": 1.0434595622354512, "percentage": 57.63, "elapsed_time": "18:53:32", "remaining_time": "13:53:33", "throughput": 553.42, "total_tokens": 37639312} {"current_steps": 23055, "total_steps": 40000, "loss": 0.1015, "lr": 1.9060819531709534e-05, "epoch": 1.0436859141220942, "percentage": 57.64, "elapsed_time": "18:53:35", "remaining_time": "13:53:10", "throughput": 553.52, "total_tokens": 37647888} {"current_steps": 23060, "total_steps": 40000, "loss": 0.1484, "lr": 1.9051283576415325e-05, "epoch": 1.0439122660087372, "percentage": 57.65, "elapsed_time": "18:53:38", "remaining_time": "13:52:46", "throughput": 553.61, "total_tokens": 37655792} {"current_steps": 23065, "total_steps": 40000, "loss": 0.142, "lr": 1.904174853848793e-05, "epoch": 1.0441386178953802, "percentage": 57.66, "elapsed_time": "18:53:41", "remaining_time": "13:52:23", "throughput": 553.71, "total_tokens": 37664048} {"current_steps": 23070, "total_steps": 40000, "loss": 0.1749, "lr": 1.903221441939779e-05, "epoch": 1.0443649697820232, "percentage": 57.67, "elapsed_time": "18:53:44", "remaining_time": "13:52:00", "throughput": 553.79, "total_tokens": 37671728} {"current_steps": 23075, "total_steps": 40000, "loss": 0.1195, "lr": 1.9022681220615194e-05, "epoch": 1.0445913216686662, "percentage": 57.69, "elapsed_time": "18:53:47", "remaining_time": "13:51:36", "throughput": 553.88, "total_tokens": 37679440} {"current_steps": 23080, "total_steps": 40000, "loss": 0.1176, "lr": 1.9013148943610255e-05, "epoch": 1.0448176735553092, "percentage": 57.7, "elapsed_time": "18:53:51", "remaining_time": "13:51:13", "throughput": 553.98, "total_tokens": 37687792} {"current_steps": 23085, "total_steps": 40000, "loss": 0.121, "lr": 1.9003617589852998e-05, "epoch": 1.045044025441952, "percentage": 57.71, "elapsed_time": "18:53:54", "remaining_time": "13:50:50", "throughput": 554.07, "total_tokens": 37695920} {"current_steps": 23090, "total_steps": 40000, "loss": 0.1442, "lr": 1.899408716081326e-05, "epoch": 1.045270377328595, "percentage": 57.73, "elapsed_time": "18:53:57", "remaining_time": "13:50:27", "throughput": 554.17, "total_tokens": 37704272} {"current_steps": 23095, "total_steps": 40000, "loss": 0.182, "lr": 1.898455765796075e-05, "epoch": 1.045496729215238, "percentage": 57.74, "elapsed_time": "18:54:00", "remaining_time": "13:50:04", "throughput": 554.27, "total_tokens": 37712688} {"current_steps": 23100, "total_steps": 40000, "loss": 0.1408, "lr": 1.8975029082765053e-05, "epoch": 1.045723081101881, "percentage": 57.75, "elapsed_time": "18:54:03", "remaining_time": "13:49:41", "throughput": 554.36, "total_tokens": 37720592} {"current_steps": 23105, "total_steps": 40000, "loss": 0.1054, "lr": 1.8965501436695577e-05, "epoch": 1.045949432988524, "percentage": 57.76, "elapsed_time": "18:54:06", "remaining_time": "13:49:17", "throughput": 554.44, "total_tokens": 37727856} {"current_steps": 23110, "total_steps": 40000, "loss": 0.103, "lr": 1.895597472122161e-05, "epoch": 1.046175784875167, "percentage": 57.77, "elapsed_time": "18:54:10", "remaining_time": "13:48:54", "throughput": 554.54, "total_tokens": 37736400} {"current_steps": 23115, "total_steps": 40000, "loss": 0.1071, "lr": 1.894644893781231e-05, "epoch": 1.04640213676181, "percentage": 57.79, "elapsed_time": "18:54:13", "remaining_time": "13:48:31", "throughput": 554.62, "total_tokens": 37743984} {"current_steps": 23120, "total_steps": 40000, "loss": 0.1411, "lr": 1.893692408793665e-05, "epoch": 1.046628488648453, "percentage": 57.8, "elapsed_time": "18:54:16", "remaining_time": "13:48:08", "throughput": 554.71, "total_tokens": 37751856} {"current_steps": 23125, "total_steps": 40000, "loss": 0.1064, "lr": 1.8927400173063493e-05, "epoch": 1.046854840535096, "percentage": 57.81, "elapsed_time": "18:54:19", "remaining_time": "13:47:45", "throughput": 554.81, "total_tokens": 37760112} {"current_steps": 23130, "total_steps": 40000, "loss": 0.07, "lr": 1.891787719466154e-05, "epoch": 1.047081192421739, "percentage": 57.83, "elapsed_time": "18:54:22", "remaining_time": "13:47:22", "throughput": 554.9, "total_tokens": 37767856} {"current_steps": 23135, "total_steps": 40000, "loss": 0.1162, "lr": 1.8908355154199346e-05, "epoch": 1.047307544308382, "percentage": 57.84, "elapsed_time": "18:54:26", "remaining_time": "13:46:58", "throughput": 555.0, "total_tokens": 37776624} {"current_steps": 23140, "total_steps": 40000, "loss": 0.0807, "lr": 1.8898834053145357e-05, "epoch": 1.0475338961950247, "percentage": 57.85, "elapsed_time": "18:54:29", "remaining_time": "13:46:35", "throughput": 555.1, "total_tokens": 37785520} {"current_steps": 23145, "total_steps": 40000, "loss": 0.1329, "lr": 1.8889313892967813e-05, "epoch": 1.0477602480816677, "percentage": 57.86, "elapsed_time": "18:54:32", "remaining_time": "13:46:12", "throughput": 555.2, "total_tokens": 37793712} {"current_steps": 23150, "total_steps": 40000, "loss": 0.1188, "lr": 1.8879794675134863e-05, "epoch": 1.0479865999683107, "percentage": 57.88, "elapsed_time": "18:54:35", "remaining_time": "13:45:49", "throughput": 555.28, "total_tokens": 37801232} {"current_steps": 23155, "total_steps": 40000, "loss": 0.1689, "lr": 1.8870276401114494e-05, "epoch": 1.0482129518549537, "percentage": 57.89, "elapsed_time": "18:54:38", "remaining_time": "13:45:26", "throughput": 555.38, "total_tokens": 37809808} {"current_steps": 23160, "total_steps": 40000, "loss": 0.1273, "lr": 1.886075907237453e-05, "epoch": 1.0484393037415967, "percentage": 57.9, "elapsed_time": "18:54:42", "remaining_time": "13:45:03", "throughput": 555.48, "total_tokens": 37818544} {"current_steps": 23165, "total_steps": 40000, "loss": 0.1638, "lr": 1.8851242690382672e-05, "epoch": 1.0486656556282397, "percentage": 57.91, "elapsed_time": "18:54:45", "remaining_time": "13:44:40", "throughput": 555.59, "total_tokens": 37827312} {"current_steps": 23170, "total_steps": 40000, "loss": 0.1273, "lr": 1.884172725660645e-05, "epoch": 1.0488920075148827, "percentage": 57.93, "elapsed_time": "18:54:48", "remaining_time": "13:44:17", "throughput": 555.68, "total_tokens": 37835728} {"current_steps": 23175, "total_steps": 40000, "loss": 0.1373, "lr": 1.8832212772513277e-05, "epoch": 1.0491183594015256, "percentage": 57.94, "elapsed_time": "18:54:51", "remaining_time": "13:43:54", "throughput": 555.78, "total_tokens": 37843984} {"current_steps": 23180, "total_steps": 40000, "loss": 0.1522, "lr": 1.8822699239570414e-05, "epoch": 1.0493447112881686, "percentage": 57.95, "elapsed_time": "18:54:55", "remaining_time": "13:43:31", "throughput": 555.87, "total_tokens": 37852336} {"current_steps": 23185, "total_steps": 40000, "loss": 0.1652, "lr": 1.8813186659244943e-05, "epoch": 1.0495710631748116, "percentage": 57.96, "elapsed_time": "18:54:58", "remaining_time": "13:43:08", "throughput": 555.97, "total_tokens": 37860656} {"current_steps": 23190, "total_steps": 40000, "loss": 0.2053, "lr": 1.880367503300385e-05, "epoch": 1.0497974150614546, "percentage": 57.98, "elapsed_time": "18:55:01", "remaining_time": "13:42:45", "throughput": 556.07, "total_tokens": 37868816} {"current_steps": 23195, "total_steps": 40000, "loss": 0.0585, "lr": 1.8794164362313927e-05, "epoch": 1.0500237669480974, "percentage": 57.99, "elapsed_time": "18:55:04", "remaining_time": "13:42:22", "throughput": 556.17, "total_tokens": 37877424} {"current_steps": 23200, "total_steps": 40000, "loss": 0.0822, "lr": 1.878465464864185e-05, "epoch": 1.0502501188347404, "percentage": 58.0, "elapsed_time": "18:55:07", "remaining_time": "13:41:59", "throughput": 556.26, "total_tokens": 37885552} {"current_steps": 23200, "total_steps": 40000, "eval_loss": 0.12485463917255402, "epoch": 1.0502501188347404, "percentage": 58.0, "elapsed_time": "19:02:50", "remaining_time": "13:47:34", "throughput": 552.51, "total_tokens": 37885552} {"current_steps": 23205, "total_steps": 40000, "loss": 0.0767, "lr": 1.877514589345414e-05, "epoch": 1.0504764707213834, "percentage": 58.01, "elapsed_time": "19:02:54", "remaining_time": "13:47:11", "throughput": 552.6, "total_tokens": 37893968} {"current_steps": 23210, "total_steps": 40000, "loss": 0.118, "lr": 1.876563809821715e-05, "epoch": 1.0507028226080264, "percentage": 58.03, "elapsed_time": "19:02:57", "remaining_time": "13:46:48", "throughput": 552.68, "total_tokens": 37901744} {"current_steps": 23215, "total_steps": 40000, "loss": 0.1199, "lr": 1.8756131264397106e-05, "epoch": 1.0509291744946694, "percentage": 58.04, "elapsed_time": "19:03:00", "remaining_time": "13:46:25", "throughput": 552.78, "total_tokens": 37910288} {"current_steps": 23220, "total_steps": 40000, "loss": 0.0763, "lr": 1.87466253934601e-05, "epoch": 1.0511555263813124, "percentage": 58.05, "elapsed_time": "19:03:03", "remaining_time": "13:46:02", "throughput": 552.87, "total_tokens": 37918160} {"current_steps": 23225, "total_steps": 40000, "loss": 0.1195, "lr": 1.8737120486872033e-05, "epoch": 1.0513818782679554, "percentage": 58.06, "elapsed_time": "19:03:07", "remaining_time": "13:45:39", "throughput": 552.97, "total_tokens": 37926672} {"current_steps": 23230, "total_steps": 40000, "loss": 0.1121, "lr": 1.8727616546098696e-05, "epoch": 1.0516082301545984, "percentage": 58.07, "elapsed_time": "19:03:10", "remaining_time": "13:45:16", "throughput": 553.07, "total_tokens": 37935536} {"current_steps": 23235, "total_steps": 40000, "loss": 0.134, "lr": 1.8718113572605716e-05, "epoch": 1.0518345820412414, "percentage": 58.09, "elapsed_time": "19:03:13", "remaining_time": "13:44:53", "throughput": 553.16, "total_tokens": 37943088} {"current_steps": 23240, "total_steps": 40000, "loss": 0.1064, "lr": 1.8708611567858554e-05, "epoch": 1.0520609339278844, "percentage": 58.1, "elapsed_time": "19:03:16", "remaining_time": "13:44:29", "throughput": 553.25, "total_tokens": 37951504} {"current_steps": 23245, "total_steps": 40000, "loss": 0.1044, "lr": 1.8699110533322565e-05, "epoch": 1.0522872858145274, "percentage": 58.11, "elapsed_time": "19:03:20", "remaining_time": "13:44:06", "throughput": 553.35, "total_tokens": 37959952} {"current_steps": 23250, "total_steps": 40000, "loss": 0.0983, "lr": 1.8689610470462897e-05, "epoch": 1.0525136377011703, "percentage": 58.13, "elapsed_time": "19:03:23", "remaining_time": "13:43:43", "throughput": 553.45, "total_tokens": 37968176} {"current_steps": 23255, "total_steps": 40000, "loss": 0.0916, "lr": 1.8680111380744604e-05, "epoch": 1.0527399895878131, "percentage": 58.14, "elapsed_time": "19:03:26", "remaining_time": "13:43:20", "throughput": 553.54, "total_tokens": 37976080} {"current_steps": 23260, "total_steps": 40000, "loss": 0.099, "lr": 1.8670613265632564e-05, "epoch": 1.0529663414744561, "percentage": 58.15, "elapsed_time": "19:03:29", "remaining_time": "13:42:57", "throughput": 553.62, "total_tokens": 37983216} {"current_steps": 23265, "total_steps": 40000, "loss": 0.1172, "lr": 1.866111612659149e-05, "epoch": 1.053192693361099, "percentage": 58.16, "elapsed_time": "19:03:32", "remaining_time": "13:42:34", "throughput": 553.71, "total_tokens": 37991792} {"current_steps": 23270, "total_steps": 40000, "loss": 0.1195, "lr": 1.8651619965085967e-05, "epoch": 1.053419045247742, "percentage": 58.17, "elapsed_time": "19:03:36", "remaining_time": "13:42:11", "throughput": 553.82, "total_tokens": 38000624} {"current_steps": 23275, "total_steps": 40000, "loss": 0.1562, "lr": 1.8642124782580433e-05, "epoch": 1.053645397134385, "percentage": 58.19, "elapsed_time": "19:03:39", "remaining_time": "13:41:48", "throughput": 553.91, "total_tokens": 38008880} {"current_steps": 23280, "total_steps": 40000, "loss": 0.1045, "lr": 1.8632630580539144e-05, "epoch": 1.053871749021028, "percentage": 58.2, "elapsed_time": "19:03:42", "remaining_time": "13:41:25", "throughput": 554.0, "total_tokens": 38016816} {"current_steps": 23285, "total_steps": 40000, "loss": 0.1022, "lr": 1.862313736042625e-05, "epoch": 1.054098100907671, "percentage": 58.21, "elapsed_time": "19:03:45", "remaining_time": "13:41:02", "throughput": 554.1, "total_tokens": 38025616} {"current_steps": 23290, "total_steps": 40000, "loss": 0.1154, "lr": 1.8613645123705703e-05, "epoch": 1.054324452794314, "percentage": 58.23, "elapsed_time": "19:03:48", "remaining_time": "13:40:39", "throughput": 554.2, "total_tokens": 38033840} {"current_steps": 23295, "total_steps": 40000, "loss": 0.1059, "lr": 1.8604153871841328e-05, "epoch": 1.054550804680957, "percentage": 58.24, "elapsed_time": "19:03:52", "remaining_time": "13:40:16", "throughput": 554.28, "total_tokens": 38041584} {"current_steps": 23300, "total_steps": 40000, "loss": 0.181, "lr": 1.859466360629682e-05, "epoch": 1.0547771565676, "percentage": 58.25, "elapsed_time": "19:03:55", "remaining_time": "13:39:53", "throughput": 554.38, "total_tokens": 38049840} {"current_steps": 23305, "total_steps": 40000, "loss": 0.1318, "lr": 1.8585174328535666e-05, "epoch": 1.055003508454243, "percentage": 58.26, "elapsed_time": "19:03:58", "remaining_time": "13:39:30", "throughput": 554.47, "total_tokens": 38057648} {"current_steps": 23310, "total_steps": 40000, "loss": 0.1053, "lr": 1.857568604002124e-05, "epoch": 1.0552298603408858, "percentage": 58.27, "elapsed_time": "19:04:01", "remaining_time": "13:39:07", "throughput": 554.55, "total_tokens": 38064912} {"current_steps": 23315, "total_steps": 40000, "loss": 0.0784, "lr": 1.8566198742216774e-05, "epoch": 1.0554562122275288, "percentage": 58.29, "elapsed_time": "19:04:04", "remaining_time": "13:38:44", "throughput": 554.64, "total_tokens": 38073104} {"current_steps": 23320, "total_steps": 40000, "loss": 0.1352, "lr": 1.85567124365853e-05, "epoch": 1.0556825641141718, "percentage": 58.3, "elapsed_time": "19:04:07", "remaining_time": "13:38:21", "throughput": 554.74, "total_tokens": 38081488} {"current_steps": 23325, "total_steps": 40000, "loss": 0.1033, "lr": 1.854722712458975e-05, "epoch": 1.0559089160008148, "percentage": 58.31, "elapsed_time": "19:04:10", "remaining_time": "13:37:58", "throughput": 554.82, "total_tokens": 38089232} {"current_steps": 23330, "total_steps": 40000, "loss": 0.169, "lr": 1.853774280769286e-05, "epoch": 1.0561352678874578, "percentage": 58.33, "elapsed_time": "19:04:14", "remaining_time": "13:37:35", "throughput": 554.91, "total_tokens": 38097168} {"current_steps": 23335, "total_steps": 40000, "loss": 0.1268, "lr": 1.852825948735724e-05, "epoch": 1.0563616197741008, "percentage": 58.34, "elapsed_time": "19:04:17", "remaining_time": "13:37:12", "throughput": 555.0, "total_tokens": 38105040} {"current_steps": 23340, "total_steps": 40000, "loss": 0.1417, "lr": 1.851877716504534e-05, "epoch": 1.0565879716607438, "percentage": 58.35, "elapsed_time": "19:04:20", "remaining_time": "13:36:49", "throughput": 555.09, "total_tokens": 38112912} {"current_steps": 23345, "total_steps": 40000, "loss": 0.1367, "lr": 1.8509295842219448e-05, "epoch": 1.0568143235473868, "percentage": 58.36, "elapsed_time": "19:04:23", "remaining_time": "13:36:26", "throughput": 555.18, "total_tokens": 38120592} {"current_steps": 23350, "total_steps": 40000, "loss": 0.1005, "lr": 1.8499815520341697e-05, "epoch": 1.0570406754340298, "percentage": 58.38, "elapsed_time": "19:04:26", "remaining_time": "13:36:03", "throughput": 555.26, "total_tokens": 38127856} {"current_steps": 23355, "total_steps": 40000, "loss": 0.1203, "lr": 1.8490336200874094e-05, "epoch": 1.0572670273206728, "percentage": 58.39, "elapsed_time": "19:04:29", "remaining_time": "13:35:40", "throughput": 555.36, "total_tokens": 38136144} {"current_steps": 23360, "total_steps": 40000, "loss": 0.1002, "lr": 1.848085788527844e-05, "epoch": 1.0574933792073158, "percentage": 58.4, "elapsed_time": "19:04:33", "remaining_time": "13:35:17", "throughput": 555.46, "total_tokens": 38145008} {"current_steps": 23365, "total_steps": 40000, "loss": 0.1142, "lr": 1.847138057501644e-05, "epoch": 1.0577197310939588, "percentage": 58.41, "elapsed_time": "19:04:36", "remaining_time": "13:34:54", "throughput": 555.56, "total_tokens": 38153488} {"current_steps": 23370, "total_steps": 40000, "loss": 0.1225, "lr": 1.8461904271549582e-05, "epoch": 1.0579460829806016, "percentage": 58.43, "elapsed_time": "19:04:39", "remaining_time": "13:34:32", "throughput": 555.65, "total_tokens": 38162064} {"current_steps": 23375, "total_steps": 40000, "loss": 0.0848, "lr": 1.845242897633926e-05, "epoch": 1.0581724348672445, "percentage": 58.44, "elapsed_time": "19:04:42", "remaining_time": "13:34:09", "throughput": 555.75, "total_tokens": 38170160} {"current_steps": 23380, "total_steps": 40000, "loss": 0.135, "lr": 1.844295469084667e-05, "epoch": 1.0583987867538875, "percentage": 58.45, "elapsed_time": "19:04:45", "remaining_time": "13:33:46", "throughput": 555.84, "total_tokens": 38178256} {"current_steps": 23385, "total_steps": 40000, "loss": 0.1951, "lr": 1.843348141653286e-05, "epoch": 1.0586251386405305, "percentage": 58.46, "elapsed_time": "19:04:49", "remaining_time": "13:33:23", "throughput": 555.93, "total_tokens": 38186160} {"current_steps": 23390, "total_steps": 40000, "loss": 0.1585, "lr": 1.842400915485874e-05, "epoch": 1.0588514905271735, "percentage": 58.48, "elapsed_time": "19:04:52", "remaining_time": "13:33:00", "throughput": 556.03, "total_tokens": 38194864} {"current_steps": 23395, "total_steps": 40000, "loss": 0.1035, "lr": 1.8414537907285053e-05, "epoch": 1.0590778424138165, "percentage": 58.49, "elapsed_time": "19:04:55", "remaining_time": "13:32:37", "throughput": 556.13, "total_tokens": 38203824} {"current_steps": 23400, "total_steps": 40000, "loss": 0.0995, "lr": 1.840506767527237e-05, "epoch": 1.0593041943004595, "percentage": 58.5, "elapsed_time": "19:04:58", "remaining_time": "13:32:15", "throughput": 556.23, "total_tokens": 38212304} {"current_steps": 23400, "total_steps": 40000, "eval_loss": 0.12467966973781586, "epoch": 1.0593041943004595, "percentage": 58.5, "elapsed_time": "19:12:41", "remaining_time": "13:37:43", "throughput": 552.51, "total_tokens": 38212304} {"current_steps": 23405, "total_steps": 40000, "loss": 0.1155, "lr": 1.8395598460281137e-05, "epoch": 1.0595305461871025, "percentage": 58.51, "elapsed_time": "19:12:45", "remaining_time": "13:37:20", "throughput": 552.6, "total_tokens": 38220720} {"current_steps": 23410, "total_steps": 40000, "loss": 0.0891, "lr": 1.838613026377161e-05, "epoch": 1.0597568980737455, "percentage": 58.53, "elapsed_time": "19:12:48", "remaining_time": "13:36:57", "throughput": 552.69, "total_tokens": 38229104} {"current_steps": 23415, "total_steps": 40000, "loss": 0.1119, "lr": 1.8376663087203917e-05, "epoch": 1.0599832499603885, "percentage": 58.54, "elapsed_time": "19:12:51", "remaining_time": "13:36:34", "throughput": 552.78, "total_tokens": 38236560} {"current_steps": 23420, "total_steps": 40000, "loss": 0.1102, "lr": 1.8367196932038014e-05, "epoch": 1.0602096018470315, "percentage": 58.55, "elapsed_time": "19:12:55", "remaining_time": "13:36:11", "throughput": 552.87, "total_tokens": 38244976} {"current_steps": 23425, "total_steps": 40000, "loss": 0.1839, "lr": 1.8357731799733686e-05, "epoch": 1.0604359537336743, "percentage": 58.56, "elapsed_time": "19:12:58", "remaining_time": "13:35:48", "throughput": 552.96, "total_tokens": 38252912} {"current_steps": 23430, "total_steps": 40000, "loss": 0.1382, "lr": 1.8348267691750586e-05, "epoch": 1.0606623056203173, "percentage": 58.58, "elapsed_time": "19:13:01", "remaining_time": "13:35:26", "throughput": 553.06, "total_tokens": 38261488} {"current_steps": 23435, "total_steps": 40000, "loss": 0.0899, "lr": 1.833880460954821e-05, "epoch": 1.0608886575069603, "percentage": 58.59, "elapsed_time": "19:13:04", "remaining_time": "13:35:03", "throughput": 553.14, "total_tokens": 38269040} {"current_steps": 23440, "total_steps": 40000, "loss": 0.1079, "lr": 1.8329342554585866e-05, "epoch": 1.0611150093936033, "percentage": 58.6, "elapsed_time": "19:13:07", "remaining_time": "13:34:39", "throughput": 553.23, "total_tokens": 38276816} {"current_steps": 23445, "total_steps": 40000, "loss": 0.0917, "lr": 1.8319881528322735e-05, "epoch": 1.0613413612802463, "percentage": 58.61, "elapsed_time": "19:13:10", "remaining_time": "13:34:17", "throughput": 553.32, "total_tokens": 38284976} {"current_steps": 23450, "total_steps": 40000, "loss": 0.1311, "lr": 1.8310421532217815e-05, "epoch": 1.0615677131668892, "percentage": 58.63, "elapsed_time": "19:13:13", "remaining_time": "13:33:54", "throughput": 553.41, "total_tokens": 38292880} {"current_steps": 23455, "total_steps": 40000, "loss": 0.137, "lr": 1.8300962567729958e-05, "epoch": 1.0617940650535322, "percentage": 58.64, "elapsed_time": "19:13:17", "remaining_time": "13:33:31", "throughput": 553.51, "total_tokens": 38301040} {"current_steps": 23460, "total_steps": 40000, "loss": 0.0862, "lr": 1.8291504636317866e-05, "epoch": 1.0620204169401752, "percentage": 58.65, "elapsed_time": "19:13:20", "remaining_time": "13:33:08", "throughput": 553.6, "total_tokens": 38309040} {"current_steps": 23465, "total_steps": 40000, "loss": 0.0844, "lr": 1.8282047739440055e-05, "epoch": 1.0622467688268182, "percentage": 58.66, "elapsed_time": "19:13:23", "remaining_time": "13:32:45", "throughput": 553.69, "total_tokens": 38316912} {"current_steps": 23470, "total_steps": 40000, "loss": 0.0754, "lr": 1.8272591878554903e-05, "epoch": 1.0624731207134612, "percentage": 58.67, "elapsed_time": "19:13:26", "remaining_time": "13:32:22", "throughput": 553.78, "total_tokens": 38325104} {"current_steps": 23475, "total_steps": 40000, "loss": 0.1106, "lr": 1.8263137055120638e-05, "epoch": 1.0626994726001042, "percentage": 58.69, "elapsed_time": "19:13:29", "remaining_time": "13:31:59", "throughput": 553.88, "total_tokens": 38334032} {"current_steps": 23480, "total_steps": 40000, "loss": 0.1202, "lr": 1.8253683270595295e-05, "epoch": 1.062925824486747, "percentage": 58.7, "elapsed_time": "19:13:33", "remaining_time": "13:31:36", "throughput": 553.97, "total_tokens": 38342096} {"current_steps": 23485, "total_steps": 40000, "loss": 0.0903, "lr": 1.824423052643677e-05, "epoch": 1.06315217637339, "percentage": 58.71, "elapsed_time": "19:13:36", "remaining_time": "13:31:13", "throughput": 554.06, "total_tokens": 38350352} {"current_steps": 23490, "total_steps": 40000, "loss": 0.1198, "lr": 1.82347788241028e-05, "epoch": 1.063378528260033, "percentage": 58.73, "elapsed_time": "19:13:39", "remaining_time": "13:30:51", "throughput": 554.16, "total_tokens": 38358736} {"current_steps": 23495, "total_steps": 40000, "loss": 0.1553, "lr": 1.8225328165050942e-05, "epoch": 1.063604880146676, "percentage": 58.74, "elapsed_time": "19:13:42", "remaining_time": "13:30:28", "throughput": 554.25, "total_tokens": 38366384} {"current_steps": 23500, "total_steps": 40000, "loss": 0.2089, "lr": 1.821587855073863e-05, "epoch": 1.063831232033319, "percentage": 58.75, "elapsed_time": "19:13:45", "remaining_time": "13:30:05", "throughput": 554.35, "total_tokens": 38375184} {"current_steps": 23505, "total_steps": 40000, "loss": 0.1379, "lr": 1.8206429982623086e-05, "epoch": 1.064057583919962, "percentage": 58.76, "elapsed_time": "19:13:49", "remaining_time": "13:29:42", "throughput": 554.44, "total_tokens": 38383664} {"current_steps": 23510, "total_steps": 40000, "loss": 0.0826, "lr": 1.8196982462161416e-05, "epoch": 1.064283935806605, "percentage": 58.77, "elapsed_time": "19:13:52", "remaining_time": "13:29:19", "throughput": 554.53, "total_tokens": 38391792} {"current_steps": 23515, "total_steps": 40000, "loss": 0.0886, "lr": 1.818753599081055e-05, "epoch": 1.064510287693248, "percentage": 58.79, "elapsed_time": "19:13:55", "remaining_time": "13:28:57", "throughput": 554.62, "total_tokens": 38399632} {"current_steps": 23520, "total_steps": 40000, "loss": 0.1415, "lr": 1.817809057002724e-05, "epoch": 1.064736639579891, "percentage": 58.8, "elapsed_time": "19:13:58", "remaining_time": "13:28:34", "throughput": 554.71, "total_tokens": 38407600} {"current_steps": 23525, "total_steps": 40000, "loss": 0.157, "lr": 1.8168646201268096e-05, "epoch": 1.064962991466534, "percentage": 58.81, "elapsed_time": "19:14:01", "remaining_time": "13:28:11", "throughput": 554.81, "total_tokens": 38415824} {"current_steps": 23530, "total_steps": 40000, "loss": 0.1149, "lr": 1.8159202885989557e-05, "epoch": 1.065189343353177, "percentage": 58.83, "elapsed_time": "19:14:05", "remaining_time": "13:27:48", "throughput": 554.89, "total_tokens": 38423536} {"current_steps": 23535, "total_steps": 40000, "loss": 0.1052, "lr": 1.814976062564789e-05, "epoch": 1.0654156952398197, "percentage": 58.84, "elapsed_time": "19:14:08", "remaining_time": "13:27:25", "throughput": 554.99, "total_tokens": 38431792} {"current_steps": 23540, "total_steps": 40000, "loss": 0.1231, "lr": 1.8140319421699234e-05, "epoch": 1.0656420471264627, "percentage": 58.85, "elapsed_time": "19:14:11", "remaining_time": "13:27:03", "throughput": 555.08, "total_tokens": 38439888} {"current_steps": 23545, "total_steps": 40000, "loss": 0.0845, "lr": 1.8130879275599515e-05, "epoch": 1.0658683990131057, "percentage": 58.86, "elapsed_time": "19:14:14", "remaining_time": "13:26:40", "throughput": 555.17, "total_tokens": 38448176} {"current_steps": 23550, "total_steps": 40000, "loss": 0.071, "lr": 1.8121440188804544e-05, "epoch": 1.0660947508997487, "percentage": 58.88, "elapsed_time": "19:14:17", "remaining_time": "13:26:17", "throughput": 555.26, "total_tokens": 38456112} {"current_steps": 23555, "total_steps": 40000, "loss": 0.0942, "lr": 1.811200216276993e-05, "epoch": 1.0663211027863917, "percentage": 58.89, "elapsed_time": "19:14:21", "remaining_time": "13:25:54", "throughput": 555.35, "total_tokens": 38464240} {"current_steps": 23560, "total_steps": 40000, "loss": 0.1608, "lr": 1.810256519895115e-05, "epoch": 1.0665474546730347, "percentage": 58.9, "elapsed_time": "19:14:24", "remaining_time": "13:25:32", "throughput": 555.46, "total_tokens": 38473296} {"current_steps": 23565, "total_steps": 40000, "loss": 0.1013, "lr": 1.8093129298803494e-05, "epoch": 1.0667738065596777, "percentage": 58.91, "elapsed_time": "19:14:27", "remaining_time": "13:25:09", "throughput": 555.55, "total_tokens": 38481296} {"current_steps": 23570, "total_steps": 40000, "loss": 0.1112, "lr": 1.808369446378209e-05, "epoch": 1.0670001584463207, "percentage": 58.93, "elapsed_time": "19:14:30", "remaining_time": "13:24:46", "throughput": 555.63, "total_tokens": 38488912} {"current_steps": 23575, "total_steps": 40000, "loss": 0.2167, "lr": 1.8074260695341914e-05, "epoch": 1.0672265103329637, "percentage": 58.94, "elapsed_time": "19:14:33", "remaining_time": "13:24:23", "throughput": 555.72, "total_tokens": 38496656} {"current_steps": 23580, "total_steps": 40000, "loss": 0.1154, "lr": 1.8064827994937782e-05, "epoch": 1.0674528622196067, "percentage": 58.95, "elapsed_time": "19:14:37", "remaining_time": "13:24:01", "throughput": 555.82, "total_tokens": 38505264} {"current_steps": 23585, "total_steps": 40000, "loss": 0.1098, "lr": 1.8055396364024317e-05, "epoch": 1.0676792141062497, "percentage": 58.96, "elapsed_time": "19:14:40", "remaining_time": "13:23:38", "throughput": 555.9, "total_tokens": 38513136} {"current_steps": 23590, "total_steps": 40000, "loss": 0.1037, "lr": 1.804596580405601e-05, "epoch": 1.0679055659928927, "percentage": 58.98, "elapsed_time": "19:14:43", "remaining_time": "13:23:15", "throughput": 556.0, "total_tokens": 38521808} {"current_steps": 23595, "total_steps": 40000, "loss": 0.1176, "lr": 1.8036536316487174e-05, "epoch": 1.0681319178795354, "percentage": 58.99, "elapsed_time": "19:14:46", "remaining_time": "13:22:53", "throughput": 556.09, "total_tokens": 38529392} {"current_steps": 23600, "total_steps": 40000, "loss": 0.1047, "lr": 1.802710790277193e-05, "epoch": 1.0683582697661784, "percentage": 59.0, "elapsed_time": "19:14:49", "remaining_time": "13:22:30", "throughput": 556.18, "total_tokens": 38537360} {"current_steps": 23600, "total_steps": 40000, "eval_loss": 0.12511692941188812, "epoch": 1.0683582697661784, "percentage": 59.0, "elapsed_time": "19:22:32", "remaining_time": "13:27:51", "throughput": 552.49, "total_tokens": 38537360} {"current_steps": 23605, "total_steps": 40000, "loss": 0.148, "lr": 1.801768056436429e-05, "epoch": 1.0685846216528214, "percentage": 59.01, "elapsed_time": "19:22:36", "remaining_time": "13:27:30", "throughput": 552.58, "total_tokens": 38546256} {"current_steps": 23610, "total_steps": 40000, "loss": 0.1046, "lr": 1.8008254302718035e-05, "epoch": 1.0688109735394644, "percentage": 59.03, "elapsed_time": "19:22:40", "remaining_time": "13:27:07", "throughput": 552.67, "total_tokens": 38554288} {"current_steps": 23615, "total_steps": 40000, "loss": 0.1501, "lr": 1.7998829119286837e-05, "epoch": 1.0690373254261074, "percentage": 59.04, "elapsed_time": "19:22:43", "remaining_time": "13:26:44", "throughput": 552.76, "total_tokens": 38562288} {"current_steps": 23620, "total_steps": 40000, "loss": 0.1533, "lr": 1.798940501552418e-05, "epoch": 1.0692636773127504, "percentage": 59.05, "elapsed_time": "19:22:46", "remaining_time": "13:26:21", "throughput": 552.86, "total_tokens": 38571504} {"current_steps": 23625, "total_steps": 40000, "loss": 0.1258, "lr": 1.797998199288336e-05, "epoch": 1.0694900291993934, "percentage": 59.06, "elapsed_time": "19:22:49", "remaining_time": "13:25:58", "throughput": 552.95, "total_tokens": 38579504} {"current_steps": 23630, "total_steps": 40000, "loss": 0.0729, "lr": 1.7970560052817543e-05, "epoch": 1.0697163810860364, "percentage": 59.08, "elapsed_time": "19:22:52", "remaining_time": "13:25:36", "throughput": 553.04, "total_tokens": 38587344} {"current_steps": 23635, "total_steps": 40000, "loss": 0.1096, "lr": 1.7961139196779702e-05, "epoch": 1.0699427329726794, "percentage": 59.09, "elapsed_time": "19:22:56", "remaining_time": "13:25:13", "throughput": 553.13, "total_tokens": 38595344} {"current_steps": 23640, "total_steps": 40000, "loss": 0.1135, "lr": 1.7951719426222647e-05, "epoch": 1.0701690848593224, "percentage": 59.1, "elapsed_time": "19:22:59", "remaining_time": "13:24:50", "throughput": 553.22, "total_tokens": 38603376} {"current_steps": 23645, "total_steps": 40000, "loss": 0.1701, "lr": 1.794230074259904e-05, "epoch": 1.0703954367459654, "percentage": 59.11, "elapsed_time": "19:23:02", "remaining_time": "13:24:27", "throughput": 553.32, "total_tokens": 38611824} {"current_steps": 23650, "total_steps": 40000, "loss": 0.0956, "lr": 1.7932883147361336e-05, "epoch": 1.0706217886326082, "percentage": 59.13, "elapsed_time": "19:23:05", "remaining_time": "13:24:05", "throughput": 553.41, "total_tokens": 38620112} {"current_steps": 23655, "total_steps": 40000, "loss": 0.0682, "lr": 1.7923466641961865e-05, "epoch": 1.0708481405192511, "percentage": 59.14, "elapsed_time": "19:23:08", "remaining_time": "13:23:42", "throughput": 553.5, "total_tokens": 38628144} {"current_steps": 23660, "total_steps": 40000, "loss": 0.1675, "lr": 1.791405122785278e-05, "epoch": 1.0710744924058941, "percentage": 59.15, "elapsed_time": "19:23:11", "remaining_time": "13:23:19", "throughput": 553.59, "total_tokens": 38636304} {"current_steps": 23665, "total_steps": 40000, "loss": 0.1454, "lr": 1.7904636906486037e-05, "epoch": 1.0713008442925371, "percentage": 59.16, "elapsed_time": "19:23:15", "remaining_time": "13:22:56", "throughput": 553.68, "total_tokens": 38644176} {"current_steps": 23670, "total_steps": 40000, "loss": 0.1421, "lr": 1.7895223679313448e-05, "epoch": 1.0715271961791801, "percentage": 59.17, "elapsed_time": "19:23:18", "remaining_time": "13:22:33", "throughput": 553.77, "total_tokens": 38652176} {"current_steps": 23675, "total_steps": 40000, "loss": 0.0847, "lr": 1.7885811547786653e-05, "epoch": 1.0717535480658231, "percentage": 59.19, "elapsed_time": "19:23:21", "remaining_time": "13:22:11", "throughput": 553.85, "total_tokens": 38659504} {"current_steps": 23680, "total_steps": 40000, "loss": 0.1501, "lr": 1.7876400513357115e-05, "epoch": 1.0719798999524661, "percentage": 59.2, "elapsed_time": "19:23:24", "remaining_time": "13:21:48", "throughput": 553.93, "total_tokens": 38667024} {"current_steps": 23685, "total_steps": 40000, "loss": 0.1593, "lr": 1.7866990577476146e-05, "epoch": 1.0722062518391091, "percentage": 59.21, "elapsed_time": "19:23:27", "remaining_time": "13:21:25", "throughput": 554.02, "total_tokens": 38674928} {"current_steps": 23690, "total_steps": 40000, "loss": 0.1651, "lr": 1.7857581741594863e-05, "epoch": 1.072432603725752, "percentage": 59.23, "elapsed_time": "19:23:30", "remaining_time": "13:21:02", "throughput": 554.12, "total_tokens": 38683152} {"current_steps": 23695, "total_steps": 40000, "loss": 0.1056, "lr": 1.7848174007164237e-05, "epoch": 1.072658955612395, "percentage": 59.24, "elapsed_time": "19:23:33", "remaining_time": "13:20:40", "throughput": 554.2, "total_tokens": 38691056} {"current_steps": 23700, "total_steps": 40000, "loss": 0.0849, "lr": 1.7838767375635052e-05, "epoch": 1.072885307499038, "percentage": 59.25, "elapsed_time": "19:23:36", "remaining_time": "13:20:17", "throughput": 554.29, "total_tokens": 38698928} {"current_steps": 23705, "total_steps": 40000, "loss": 0.1699, "lr": 1.782936184845793e-05, "epoch": 1.073111659385681, "percentage": 59.26, "elapsed_time": "19:23:40", "remaining_time": "13:19:54", "throughput": 554.38, "total_tokens": 38706992} {"current_steps": 23710, "total_steps": 40000, "loss": 0.1058, "lr": 1.7819957427083334e-05, "epoch": 1.0733380112723239, "percentage": 59.27, "elapsed_time": "19:23:43", "remaining_time": "13:19:32", "throughput": 554.47, "total_tokens": 38714736} {"current_steps": 23715, "total_steps": 40000, "loss": 0.0914, "lr": 1.7810554112961516e-05, "epoch": 1.0735643631589669, "percentage": 59.29, "elapsed_time": "19:23:46", "remaining_time": "13:19:09", "throughput": 554.56, "total_tokens": 38723056} {"current_steps": 23720, "total_steps": 40000, "loss": 0.0958, "lr": 1.7801151907542607e-05, "epoch": 1.0737907150456099, "percentage": 59.3, "elapsed_time": "19:23:49", "remaining_time": "13:18:46", "throughput": 554.65, "total_tokens": 38731280} {"current_steps": 23725, "total_steps": 40000, "loss": 0.1217, "lr": 1.7791750812276547e-05, "epoch": 1.0740170669322529, "percentage": 59.31, "elapsed_time": "19:23:52", "remaining_time": "13:18:24", "throughput": 554.74, "total_tokens": 38739312} {"current_steps": 23730, "total_steps": 40000, "loss": 0.0825, "lr": 1.778235082861309e-05, "epoch": 1.0742434188188958, "percentage": 59.33, "elapsed_time": "19:23:55", "remaining_time": "13:18:01", "throughput": 554.83, "total_tokens": 38746800} {"current_steps": 23735, "total_steps": 40000, "loss": 0.1262, "lr": 1.777295195800184e-05, "epoch": 1.0744697707055388, "percentage": 59.34, "elapsed_time": "19:23:58", "remaining_time": "13:17:38", "throughput": 554.91, "total_tokens": 38754480} {"current_steps": 23740, "total_steps": 40000, "loss": 0.1287, "lr": 1.7763554201892215e-05, "epoch": 1.0746961225921818, "percentage": 59.35, "elapsed_time": "19:24:02", "remaining_time": "13:17:16", "throughput": 555.01, "total_tokens": 38762736} {"current_steps": 23745, "total_steps": 40000, "loss": 0.1852, "lr": 1.7754157561733476e-05, "epoch": 1.0749224744788248, "percentage": 59.36, "elapsed_time": "19:24:05", "remaining_time": "13:16:53", "throughput": 555.1, "total_tokens": 38770992} {"current_steps": 23750, "total_steps": 40000, "loss": 0.0759, "lr": 1.7744762038974702e-05, "epoch": 1.0751488263654678, "percentage": 59.38, "elapsed_time": "19:24:08", "remaining_time": "13:16:31", "throughput": 555.19, "total_tokens": 38779312} {"current_steps": 23755, "total_steps": 40000, "loss": 0.0973, "lr": 1.7735367635064788e-05, "epoch": 1.0753751782521108, "percentage": 59.39, "elapsed_time": "19:24:11", "remaining_time": "13:16:08", "throughput": 555.28, "total_tokens": 38786864} {"current_steps": 23760, "total_steps": 40000, "loss": 0.1, "lr": 1.7725974351452474e-05, "epoch": 1.0756015301387536, "percentage": 59.4, "elapsed_time": "19:24:14", "remaining_time": "13:15:45", "throughput": 555.36, "total_tokens": 38794640} {"current_steps": 23765, "total_steps": 40000, "loss": 0.1689, "lr": 1.771658218958634e-05, "epoch": 1.0758278820253966, "percentage": 59.41, "elapsed_time": "19:24:17", "remaining_time": "13:15:23", "throughput": 555.45, "total_tokens": 38802384} {"current_steps": 23770, "total_steps": 40000, "loss": 0.1125, "lr": 1.770719115091475e-05, "epoch": 1.0760542339120396, "percentage": 59.42, "elapsed_time": "19:24:20", "remaining_time": "13:15:00", "throughput": 555.54, "total_tokens": 38810608} {"current_steps": 23775, "total_steps": 40000, "loss": 0.1405, "lr": 1.7697801236885935e-05, "epoch": 1.0762805857986826, "percentage": 59.44, "elapsed_time": "19:24:24", "remaining_time": "13:14:38", "throughput": 555.65, "total_tokens": 38819856} {"current_steps": 23780, "total_steps": 40000, "loss": 0.133, "lr": 1.7688412448947944e-05, "epoch": 1.0765069376853256, "percentage": 59.45, "elapsed_time": "19:24:27", "remaining_time": "13:14:15", "throughput": 555.74, "total_tokens": 38827952} {"current_steps": 23785, "total_steps": 40000, "loss": 0.1565, "lr": 1.767902478854862e-05, "epoch": 1.0767332895719686, "percentage": 59.46, "elapsed_time": "19:24:30", "remaining_time": "13:13:53", "throughput": 555.82, "total_tokens": 38835792} {"current_steps": 23790, "total_steps": 40000, "loss": 0.0889, "lr": 1.766963825713569e-05, "epoch": 1.0769596414586116, "percentage": 59.48, "elapsed_time": "19:24:33", "remaining_time": "13:13:30", "throughput": 555.91, "total_tokens": 38843856} {"current_steps": 23795, "total_steps": 40000, "loss": 0.1467, "lr": 1.766025285615665e-05, "epoch": 1.0771859933452546, "percentage": 59.49, "elapsed_time": "19:24:36", "remaining_time": "13:13:07", "throughput": 556.0, "total_tokens": 38851600} {"current_steps": 23800, "total_steps": 40000, "loss": 0.1431, "lr": 1.7650868587058854e-05, "epoch": 1.0774123452318976, "percentage": 59.5, "elapsed_time": "19:24:40", "remaining_time": "13:12:45", "throughput": 556.09, "total_tokens": 38859952} {"current_steps": 23800, "total_steps": 40000, "eval_loss": 0.1240093782544136, "epoch": 1.0774123452318976, "percentage": 59.5, "elapsed_time": "19:32:22", "remaining_time": "13:18:00", "throughput": 552.44, "total_tokens": 38859952} {"current_steps": 23805, "total_steps": 40000, "loss": 0.1133, "lr": 1.7641485451289484e-05, "epoch": 1.0776386971185405, "percentage": 59.51, "elapsed_time": "19:32:26", "remaining_time": "13:17:38", "throughput": 552.52, "total_tokens": 38868272} {"current_steps": 23810, "total_steps": 40000, "loss": 0.1698, "lr": 1.7632103450295534e-05, "epoch": 1.0778650490051835, "percentage": 59.52, "elapsed_time": "19:32:29", "remaining_time": "13:17:15", "throughput": 552.61, "total_tokens": 38876368} {"current_steps": 23815, "total_steps": 40000, "loss": 0.173, "lr": 1.762272258552381e-05, "epoch": 1.0780914008918265, "percentage": 59.54, "elapsed_time": "19:32:33", "remaining_time": "13:16:52", "throughput": 552.71, "total_tokens": 38884880} {"current_steps": 23820, "total_steps": 40000, "loss": 0.139, "lr": 1.7613342858420988e-05, "epoch": 1.0783177527784693, "percentage": 59.55, "elapsed_time": "19:32:36", "remaining_time": "13:16:30", "throughput": 552.8, "total_tokens": 38893232} {"current_steps": 23825, "total_steps": 40000, "loss": 0.1654, "lr": 1.760396427043351e-05, "epoch": 1.0785441046651123, "percentage": 59.56, "elapsed_time": "19:32:39", "remaining_time": "13:16:07", "throughput": 552.9, "total_tokens": 38901840} {"current_steps": 23830, "total_steps": 40000, "loss": 0.1705, "lr": 1.7594586823007696e-05, "epoch": 1.0787704565517553, "percentage": 59.58, "elapsed_time": "19:32:42", "remaining_time": "13:15:45", "throughput": 552.99, "total_tokens": 38910064} {"current_steps": 23835, "total_steps": 40000, "loss": 0.1151, "lr": 1.7585210517589646e-05, "epoch": 1.0789968084383983, "percentage": 59.59, "elapsed_time": "19:32:46", "remaining_time": "13:15:22", "throughput": 553.1, "total_tokens": 38919184} {"current_steps": 23840, "total_steps": 40000, "loss": 0.1265, "lr": 1.7575835355625314e-05, "epoch": 1.0792231603250413, "percentage": 59.6, "elapsed_time": "19:32:49", "remaining_time": "13:15:00", "throughput": 553.18, "total_tokens": 38927120} {"current_steps": 23845, "total_steps": 40000, "loss": 0.1633, "lr": 1.756646133856048e-05, "epoch": 1.0794495122116843, "percentage": 59.61, "elapsed_time": "19:32:52", "remaining_time": "13:14:37", "throughput": 553.27, "total_tokens": 38935248} {"current_steps": 23850, "total_steps": 40000, "loss": 0.1764, "lr": 1.7557088467840714e-05, "epoch": 1.0796758640983273, "percentage": 59.62, "elapsed_time": "19:32:55", "remaining_time": "13:14:14", "throughput": 553.36, "total_tokens": 38943248} {"current_steps": 23855, "total_steps": 40000, "loss": 0.0672, "lr": 1.7547716744911438e-05, "epoch": 1.0799022159849703, "percentage": 59.64, "elapsed_time": "19:32:58", "remaining_time": "13:13:52", "throughput": 553.45, "total_tokens": 38950992} {"current_steps": 23860, "total_steps": 40000, "loss": 0.1814, "lr": 1.7538346171217902e-05, "epoch": 1.0801285678716133, "percentage": 59.65, "elapsed_time": "19:33:02", "remaining_time": "13:13:29", "throughput": 553.54, "total_tokens": 38959408} {"current_steps": 23865, "total_steps": 40000, "loss": 0.1116, "lr": 1.7528976748205146e-05, "epoch": 1.0803549197582563, "percentage": 59.66, "elapsed_time": "19:33:05", "remaining_time": "13:13:06", "throughput": 553.62, "total_tokens": 38966704} {"current_steps": 23870, "total_steps": 40000, "loss": 0.0908, "lr": 1.751960847731807e-05, "epoch": 1.0805812716448993, "percentage": 59.67, "elapsed_time": "19:33:08", "remaining_time": "13:12:44", "throughput": 553.72, "total_tokens": 38975056} {"current_steps": 23875, "total_steps": 40000, "loss": 0.1419, "lr": 1.7510241360001362e-05, "epoch": 1.080807623531542, "percentage": 59.69, "elapsed_time": "19:33:11", "remaining_time": "13:12:21", "throughput": 553.8, "total_tokens": 38982704} {"current_steps": 23880, "total_steps": 40000, "loss": 0.149, "lr": 1.7500875397699562e-05, "epoch": 1.081033975418185, "percentage": 59.7, "elapsed_time": "19:33:14", "remaining_time": "13:11:59", "throughput": 553.88, "total_tokens": 38990224} {"current_steps": 23885, "total_steps": 40000, "loss": 0.1151, "lr": 1.7491510591857015e-05, "epoch": 1.081260327304828, "percentage": 59.71, "elapsed_time": "19:33:17", "remaining_time": "13:11:36", "throughput": 553.98, "total_tokens": 38998608} {"current_steps": 23890, "total_steps": 40000, "loss": 0.1357, "lr": 1.7482146943917896e-05, "epoch": 1.081486679191471, "percentage": 59.72, "elapsed_time": "19:33:20", "remaining_time": "13:11:14", "throughput": 554.06, "total_tokens": 39006256} {"current_steps": 23895, "total_steps": 40000, "loss": 0.1397, "lr": 1.7472784455326185e-05, "epoch": 1.081713031078114, "percentage": 59.74, "elapsed_time": "19:33:23", "remaining_time": "13:10:51", "throughput": 554.15, "total_tokens": 39014288} {"current_steps": 23900, "total_steps": 40000, "loss": 0.1645, "lr": 1.746342312752572e-05, "epoch": 1.081939382964757, "percentage": 59.75, "elapsed_time": "19:33:27", "remaining_time": "13:10:29", "throughput": 554.24, "total_tokens": 39022480} {"current_steps": 23905, "total_steps": 40000, "loss": 0.0967, "lr": 1.74540629619601e-05, "epoch": 1.0821657348514, "percentage": 59.76, "elapsed_time": "19:33:30", "remaining_time": "13:10:06", "throughput": 554.33, "total_tokens": 39030640} {"current_steps": 23910, "total_steps": 40000, "loss": 0.1348, "lr": 1.7444703960072815e-05, "epoch": 1.082392086738043, "percentage": 59.77, "elapsed_time": "19:33:33", "remaining_time": "13:09:44", "throughput": 554.42, "total_tokens": 39038672} {"current_steps": 23915, "total_steps": 40000, "loss": 0.127, "lr": 1.7435346123307118e-05, "epoch": 1.082618438624686, "percentage": 59.79, "elapsed_time": "19:33:36", "remaining_time": "13:09:21", "throughput": 554.5, "total_tokens": 39046224} {"current_steps": 23920, "total_steps": 40000, "loss": 0.0873, "lr": 1.742598945310611e-05, "epoch": 1.082844790511329, "percentage": 59.8, "elapsed_time": "19:33:39", "remaining_time": "13:08:58", "throughput": 554.59, "total_tokens": 39054320} {"current_steps": 23925, "total_steps": 40000, "loss": 0.121, "lr": 1.741663395091272e-05, "epoch": 1.083071142397972, "percentage": 59.81, "elapsed_time": "19:33:42", "remaining_time": "13:08:36", "throughput": 554.69, "total_tokens": 39062960} {"current_steps": 23930, "total_steps": 40000, "loss": 0.1245, "lr": 1.7407279618169657e-05, "epoch": 1.083297494284615, "percentage": 59.82, "elapsed_time": "19:33:46", "remaining_time": "13:08:14", "throughput": 554.78, "total_tokens": 39070960} {"current_steps": 23935, "total_steps": 40000, "loss": 0.1161, "lr": 1.73979264563195e-05, "epoch": 1.0835238461712577, "percentage": 59.84, "elapsed_time": "19:33:49", "remaining_time": "13:07:51", "throughput": 554.88, "total_tokens": 39080080} {"current_steps": 23940, "total_steps": 40000, "loss": 0.1326, "lr": 1.7388574466804625e-05, "epoch": 1.0837501980579007, "percentage": 59.85, "elapsed_time": "19:33:52", "remaining_time": "13:07:29", "throughput": 554.98, "total_tokens": 39088464} {"current_steps": 23945, "total_steps": 40000, "loss": 0.1317, "lr": 1.7379223651067207e-05, "epoch": 1.0839765499445437, "percentage": 59.86, "elapsed_time": "19:33:55", "remaining_time": "13:07:06", "throughput": 555.06, "total_tokens": 39096336} {"current_steps": 23950, "total_steps": 40000, "loss": 0.144, "lr": 1.736987401054928e-05, "epoch": 1.0842029018311867, "percentage": 59.88, "elapsed_time": "19:33:58", "remaining_time": "13:06:44", "throughput": 555.16, "total_tokens": 39104592} {"current_steps": 23955, "total_steps": 40000, "loss": 0.0831, "lr": 1.736052554669266e-05, "epoch": 1.0844292537178297, "percentage": 59.89, "elapsed_time": "19:34:02", "remaining_time": "13:06:21", "throughput": 555.24, "total_tokens": 39112624} {"current_steps": 23960, "total_steps": 40000, "loss": 0.1075, "lr": 1.7351178260939007e-05, "epoch": 1.0846556056044727, "percentage": 59.9, "elapsed_time": "19:34:05", "remaining_time": "13:05:59", "throughput": 555.33, "total_tokens": 39120624} {"current_steps": 23965, "total_steps": 40000, "loss": 0.1033, "lr": 1.7341832154729794e-05, "epoch": 1.0848819574911157, "percentage": 59.91, "elapsed_time": "19:34:08", "remaining_time": "13:05:37", "throughput": 555.42, "total_tokens": 39128560} {"current_steps": 23970, "total_steps": 40000, "loss": 0.1363, "lr": 1.7332487229506286e-05, "epoch": 1.0851083093777587, "percentage": 59.92, "elapsed_time": "19:34:11", "remaining_time": "13:05:14", "throughput": 555.51, "total_tokens": 39136400} {"current_steps": 23975, "total_steps": 40000, "loss": 0.086, "lr": 1.732314348670961e-05, "epoch": 1.0853346612644017, "percentage": 59.94, "elapsed_time": "19:34:15", "remaining_time": "13:04:52", "throughput": 555.61, "total_tokens": 39145808} {"current_steps": 23980, "total_steps": 40000, "loss": 0.0908, "lr": 1.7313800927780686e-05, "epoch": 1.0855610131510447, "percentage": 59.95, "elapsed_time": "19:34:18", "remaining_time": "13:04:30", "throughput": 555.7, "total_tokens": 39153616} {"current_steps": 23985, "total_steps": 40000, "loss": 0.0979, "lr": 1.7304459554160245e-05, "epoch": 1.0857873650376877, "percentage": 59.96, "elapsed_time": "19:34:21", "remaining_time": "13:04:07", "throughput": 555.8, "total_tokens": 39162416} {"current_steps": 23990, "total_steps": 40000, "loss": 0.09, "lr": 1.7295119367288853e-05, "epoch": 1.0860137169243305, "percentage": 59.98, "elapsed_time": "19:34:24", "remaining_time": "13:03:45", "throughput": 555.89, "total_tokens": 39170416} {"current_steps": 23995, "total_steps": 40000, "loss": 0.0757, "lr": 1.728578036860688e-05, "epoch": 1.0862400688109735, "percentage": 59.99, "elapsed_time": "19:34:27", "remaining_time": "13:03:23", "throughput": 555.99, "total_tokens": 39179184} {"current_steps": 24000, "total_steps": 40000, "loss": 0.1015, "lr": 1.7276442559554513e-05, "epoch": 1.0864664206976165, "percentage": 60.0, "elapsed_time": "19:34:31", "remaining_time": "13:03:00", "throughput": 556.07, "total_tokens": 39187024} {"current_steps": 24000, "total_steps": 40000, "eval_loss": 0.12408759444952011, "epoch": 1.0864664206976165, "percentage": 60.0, "elapsed_time": "19:42:13", "remaining_time": "13:08:09", "throughput": 552.45, "total_tokens": 39187024} {"current_steps": 24005, "total_steps": 40000, "loss": 0.0735, "lr": 1.726710594157177e-05, "epoch": 1.0866927725842594, "percentage": 60.01, "elapsed_time": "19:42:17", "remaining_time": "13:07:47", "throughput": 552.53, "total_tokens": 39195120} {"current_steps": 24010, "total_steps": 40000, "loss": 0.1414, "lr": 1.725777051609846e-05, "epoch": 1.0869191244709024, "percentage": 60.02, "elapsed_time": "19:42:20", "remaining_time": "13:07:24", "throughput": 552.61, "total_tokens": 39202544} {"current_steps": 24015, "total_steps": 40000, "loss": 0.1249, "lr": 1.7248436284574228e-05, "epoch": 1.0871454763575454, "percentage": 60.04, "elapsed_time": "19:42:23", "remaining_time": "13:07:01", "throughput": 552.7, "total_tokens": 39210576} {"current_steps": 24020, "total_steps": 40000, "loss": 0.1129, "lr": 1.723910324843855e-05, "epoch": 1.0873718282441884, "percentage": 60.05, "elapsed_time": "19:42:26", "remaining_time": "13:06:39", "throughput": 552.79, "total_tokens": 39218416} {"current_steps": 24025, "total_steps": 40000, "loss": 0.1462, "lr": 1.722977140913067e-05, "epoch": 1.0875981801308314, "percentage": 60.06, "elapsed_time": "19:42:30", "remaining_time": "13:06:17", "throughput": 552.88, "total_tokens": 39227056} {"current_steps": 24030, "total_steps": 40000, "loss": 0.1698, "lr": 1.7220440768089688e-05, "epoch": 1.0878245320174744, "percentage": 60.08, "elapsed_time": "19:42:33", "remaining_time": "13:05:54", "throughput": 552.97, "total_tokens": 39235120} {"current_steps": 24035, "total_steps": 40000, "loss": 0.1182, "lr": 1.7211111326754505e-05, "epoch": 1.0880508839041174, "percentage": 60.09, "elapsed_time": "19:42:36", "remaining_time": "13:05:32", "throughput": 553.07, "total_tokens": 39243760} {"current_steps": 24040, "total_steps": 40000, "loss": 0.1421, "lr": 1.720178308656383e-05, "epoch": 1.0882772357907604, "percentage": 60.1, "elapsed_time": "19:42:39", "remaining_time": "13:05:09", "throughput": 553.15, "total_tokens": 39251568} {"current_steps": 24045, "total_steps": 40000, "loss": 0.1391, "lr": 1.719245604895621e-05, "epoch": 1.0885035876774034, "percentage": 60.11, "elapsed_time": "19:42:42", "remaining_time": "13:04:47", "throughput": 553.24, "total_tokens": 39259440} {"current_steps": 24050, "total_steps": 40000, "loss": 0.1313, "lr": 1.7183130215369972e-05, "epoch": 1.0887299395640462, "percentage": 60.12, "elapsed_time": "19:42:45", "remaining_time": "13:04:24", "throughput": 553.33, "total_tokens": 39267472} {"current_steps": 24055, "total_steps": 40000, "loss": 0.1454, "lr": 1.7173805587243292e-05, "epoch": 1.0889562914506892, "percentage": 60.14, "elapsed_time": "19:42:49", "remaining_time": "13:04:02", "throughput": 553.41, "total_tokens": 39274864} {"current_steps": 24060, "total_steps": 40000, "loss": 0.1537, "lr": 1.7164482166014147e-05, "epoch": 1.0891826433373322, "percentage": 60.15, "elapsed_time": "19:42:52", "remaining_time": "13:03:39", "throughput": 553.5, "total_tokens": 39283568} {"current_steps": 24065, "total_steps": 40000, "loss": 0.1144, "lr": 1.7155159953120313e-05, "epoch": 1.0894089952239752, "percentage": 60.16, "elapsed_time": "19:42:55", "remaining_time": "13:03:17", "throughput": 553.6, "total_tokens": 39291760} {"current_steps": 24070, "total_steps": 40000, "loss": 0.0592, "lr": 1.714583894999941e-05, "epoch": 1.0896353471106182, "percentage": 60.17, "elapsed_time": "19:42:58", "remaining_time": "13:02:55", "throughput": 553.69, "total_tokens": 39299952} {"current_steps": 24075, "total_steps": 40000, "loss": 0.1222, "lr": 1.7136519158088826e-05, "epoch": 1.0898616989972612, "percentage": 60.19, "elapsed_time": "19:43:01", "remaining_time": "13:02:32", "throughput": 553.78, "total_tokens": 39308176} {"current_steps": 24080, "total_steps": 40000, "loss": 0.1118, "lr": 1.712720057882581e-05, "epoch": 1.0900880508839041, "percentage": 60.2, "elapsed_time": "19:43:05", "remaining_time": "13:02:10", "throughput": 553.88, "total_tokens": 39317296} {"current_steps": 24085, "total_steps": 40000, "loss": 0.1397, "lr": 1.7117883213647413e-05, "epoch": 1.0903144027705471, "percentage": 60.21, "elapsed_time": "19:43:08", "remaining_time": "13:01:48", "throughput": 553.98, "total_tokens": 39326128} {"current_steps": 24090, "total_steps": 40000, "loss": 0.1113, "lr": 1.710856706399046e-05, "epoch": 1.0905407546571901, "percentage": 60.22, "elapsed_time": "19:43:11", "remaining_time": "13:01:25", "throughput": 554.06, "total_tokens": 39334000} {"current_steps": 24095, "total_steps": 40000, "loss": 0.0874, "lr": 1.7099252131291648e-05, "epoch": 1.0907671065438331, "percentage": 60.24, "elapsed_time": "19:43:14", "remaining_time": "13:01:03", "throughput": 554.15, "total_tokens": 39341936} {"current_steps": 24100, "total_steps": 40000, "loss": 0.0871, "lr": 1.708993841698744e-05, "epoch": 1.090993458430476, "percentage": 60.25, "elapsed_time": "19:43:18", "remaining_time": "13:00:41", "throughput": 554.24, "total_tokens": 39349712} {"current_steps": 24105, "total_steps": 40000, "loss": 0.1056, "lr": 1.7080625922514132e-05, "epoch": 1.091219810317119, "percentage": 60.26, "elapsed_time": "19:43:21", "remaining_time": "13:00:18", "throughput": 554.32, "total_tokens": 39357520} {"current_steps": 24110, "total_steps": 40000, "loss": 0.1723, "lr": 1.7071314649307836e-05, "epoch": 1.091446162203762, "percentage": 60.27, "elapsed_time": "19:43:24", "remaining_time": "12:59:56", "throughput": 554.41, "total_tokens": 39365392} {"current_steps": 24115, "total_steps": 40000, "loss": 0.1321, "lr": 1.7062004598804448e-05, "epoch": 1.0916725140904049, "percentage": 60.29, "elapsed_time": "19:43:27", "remaining_time": "12:59:33", "throughput": 554.5, "total_tokens": 39373584} {"current_steps": 24120, "total_steps": 40000, "loss": 0.1355, "lr": 1.7052695772439702e-05, "epoch": 1.0918988659770479, "percentage": 60.3, "elapsed_time": "19:43:30", "remaining_time": "12:59:11", "throughput": 554.59, "total_tokens": 39381520} {"current_steps": 24125, "total_steps": 40000, "loss": 0.1694, "lr": 1.7043388171649154e-05, "epoch": 1.0921252178636909, "percentage": 60.31, "elapsed_time": "19:43:33", "remaining_time": "12:58:49", "throughput": 554.68, "total_tokens": 39390128} {"current_steps": 24130, "total_steps": 40000, "loss": 0.1402, "lr": 1.7034081797868127e-05, "epoch": 1.0923515697503339, "percentage": 60.32, "elapsed_time": "19:43:37", "remaining_time": "12:58:27", "throughput": 554.78, "total_tokens": 39398832} {"current_steps": 24135, "total_steps": 40000, "loss": 0.0875, "lr": 1.70247766525318e-05, "epoch": 1.0925779216369769, "percentage": 60.34, "elapsed_time": "19:43:40", "remaining_time": "12:58:04", "throughput": 554.87, "total_tokens": 39407280} {"current_steps": 24140, "total_steps": 40000, "loss": 0.0942, "lr": 1.701547273707514e-05, "epoch": 1.0928042735236199, "percentage": 60.35, "elapsed_time": "19:43:43", "remaining_time": "12:57:42", "throughput": 554.96, "total_tokens": 39415504} {"current_steps": 24145, "total_steps": 40000, "loss": 0.0989, "lr": 1.7006170052932916e-05, "epoch": 1.0930306254102629, "percentage": 60.36, "elapsed_time": "19:43:46", "remaining_time": "12:57:20", "throughput": 555.06, "total_tokens": 39424080} {"current_steps": 24150, "total_steps": 40000, "loss": 0.0636, "lr": 1.6996868601539735e-05, "epoch": 1.0932569772969059, "percentage": 60.38, "elapsed_time": "19:43:50", "remaining_time": "12:56:58", "throughput": 555.15, "total_tokens": 39432272} {"current_steps": 24155, "total_steps": 40000, "loss": 0.1246, "lr": 1.6987568384329977e-05, "epoch": 1.0934833291835488, "percentage": 60.39, "elapsed_time": "19:43:53", "remaining_time": "12:56:35", "throughput": 555.24, "total_tokens": 39440272} {"current_steps": 24160, "total_steps": 40000, "loss": 0.112, "lr": 1.6978269402737866e-05, "epoch": 1.0937096810701916, "percentage": 60.4, "elapsed_time": "19:43:56", "remaining_time": "12:56:13", "throughput": 555.32, "total_tokens": 39448048} {"current_steps": 24165, "total_steps": 40000, "loss": 0.0943, "lr": 1.696897165819743e-05, "epoch": 1.0939360329568346, "percentage": 60.41, "elapsed_time": "19:43:59", "remaining_time": "12:55:51", "throughput": 555.42, "total_tokens": 39456688} {"current_steps": 24170, "total_steps": 40000, "loss": 0.1446, "lr": 1.6959675152142487e-05, "epoch": 1.0941623848434776, "percentage": 60.42, "elapsed_time": "19:44:02", "remaining_time": "12:55:28", "throughput": 555.51, "total_tokens": 39464656} {"current_steps": 24175, "total_steps": 40000, "loss": 0.1245, "lr": 1.6950379886006667e-05, "epoch": 1.0943887367301206, "percentage": 60.44, "elapsed_time": "19:44:06", "remaining_time": "12:55:06", "throughput": 555.6, "total_tokens": 39473200} {"current_steps": 24180, "total_steps": 40000, "loss": 0.11, "lr": 1.6941085861223438e-05, "epoch": 1.0946150886167636, "percentage": 60.45, "elapsed_time": "19:44:09", "remaining_time": "12:54:44", "throughput": 555.7, "total_tokens": 39481872} {"current_steps": 24185, "total_steps": 40000, "loss": 0.157, "lr": 1.6931793079226034e-05, "epoch": 1.0948414405034066, "percentage": 60.46, "elapsed_time": "19:44:12", "remaining_time": "12:54:22", "throughput": 555.78, "total_tokens": 39489648} {"current_steps": 24190, "total_steps": 40000, "loss": 0.1005, "lr": 1.692250154144754e-05, "epoch": 1.0950677923900496, "percentage": 60.48, "elapsed_time": "19:44:15", "remaining_time": "12:54:00", "throughput": 555.88, "total_tokens": 39498448} {"current_steps": 24195, "total_steps": 40000, "loss": 0.1181, "lr": 1.6913211249320807e-05, "epoch": 1.0952941442766926, "percentage": 60.49, "elapsed_time": "19:44:18", "remaining_time": "12:53:38", "throughput": 555.97, "total_tokens": 39506352} {"current_steps": 24200, "total_steps": 40000, "loss": 0.1643, "lr": 1.6903922204278522e-05, "epoch": 1.0955204961633356, "percentage": 60.5, "elapsed_time": "19:44:22", "remaining_time": "12:53:16", "throughput": 556.06, "total_tokens": 39514800} {"current_steps": 24200, "total_steps": 40000, "eval_loss": 0.12444112449884415, "epoch": 1.0955204961633356, "percentage": 60.5, "elapsed_time": "19:52:04", "remaining_time": "12:58:18", "throughput": 552.46, "total_tokens": 39514800} {"current_steps": 24205, "total_steps": 40000, "loss": 0.1077, "lr": 1.6894634407753186e-05, "epoch": 1.0957468480499786, "percentage": 60.51, "elapsed_time": "19:52:08", "remaining_time": "12:57:56", "throughput": 552.55, "total_tokens": 39523216} {"current_steps": 24210, "total_steps": 40000, "loss": 0.1374, "lr": 1.6885347861177077e-05, "epoch": 1.0959731999366216, "percentage": 60.52, "elapsed_time": "19:52:12", "remaining_time": "12:57:34", "throughput": 552.65, "total_tokens": 39532144} {"current_steps": 24215, "total_steps": 40000, "loss": 0.1157, "lr": 1.6876062565982298e-05, "epoch": 1.0961995518232643, "percentage": 60.54, "elapsed_time": "19:52:15", "remaining_time": "12:57:11", "throughput": 552.74, "total_tokens": 39540592} {"current_steps": 24220, "total_steps": 40000, "loss": 0.108, "lr": 1.6866778523600774e-05, "epoch": 1.0964259037099073, "percentage": 60.55, "elapsed_time": "19:52:18", "remaining_time": "12:56:49", "throughput": 552.83, "total_tokens": 39549104} {"current_steps": 24225, "total_steps": 40000, "loss": 0.1574, "lr": 1.6857495735464195e-05, "epoch": 1.0966522555965503, "percentage": 60.56, "elapsed_time": "19:52:21", "remaining_time": "12:56:27", "throughput": 552.93, "total_tokens": 39557648} {"current_steps": 24230, "total_steps": 40000, "loss": 0.0744, "lr": 1.6848214203004115e-05, "epoch": 1.0968786074831933, "percentage": 60.58, "elapsed_time": "19:52:25", "remaining_time": "12:56:04", "throughput": 553.02, "total_tokens": 39565968} {"current_steps": 24235, "total_steps": 40000, "loss": 0.0702, "lr": 1.6838933927651835e-05, "epoch": 1.0971049593698363, "percentage": 60.59, "elapsed_time": "19:52:28", "remaining_time": "12:55:42", "throughput": 553.12, "total_tokens": 39574672} {"current_steps": 24240, "total_steps": 40000, "loss": 0.169, "lr": 1.6829654910838506e-05, "epoch": 1.0973313112564793, "percentage": 60.6, "elapsed_time": "19:52:31", "remaining_time": "12:55:20", "throughput": 553.2, "total_tokens": 39582352} {"current_steps": 24245, "total_steps": 40000, "loss": 0.122, "lr": 1.6820377153995065e-05, "epoch": 1.0975576631431223, "percentage": 60.61, "elapsed_time": "19:52:34", "remaining_time": "12:54:58", "throughput": 553.3, "total_tokens": 39591152} {"current_steps": 24250, "total_steps": 40000, "loss": 0.0919, "lr": 1.681110065855226e-05, "epoch": 1.0977840150297653, "percentage": 60.62, "elapsed_time": "19:52:38", "remaining_time": "12:54:35", "throughput": 553.38, "total_tokens": 39598736} {"current_steps": 24255, "total_steps": 40000, "loss": 0.1028, "lr": 1.6801825425940642e-05, "epoch": 1.0980103669164083, "percentage": 60.64, "elapsed_time": "19:52:41", "remaining_time": "12:54:13", "throughput": 553.47, "total_tokens": 39606832} {"current_steps": 24260, "total_steps": 40000, "loss": 0.117, "lr": 1.679255145759056e-05, "epoch": 1.0982367188030513, "percentage": 60.65, "elapsed_time": "19:52:44", "remaining_time": "12:53:51", "throughput": 553.56, "total_tokens": 39615408} {"current_steps": 24265, "total_steps": 40000, "loss": 0.1661, "lr": 1.6783278754932187e-05, "epoch": 1.0984630706896943, "percentage": 60.66, "elapsed_time": "19:52:47", "remaining_time": "12:53:29", "throughput": 553.65, "total_tokens": 39623280} {"current_steps": 24270, "total_steps": 40000, "loss": 0.1212, "lr": 1.6774007319395496e-05, "epoch": 1.0986894225763373, "percentage": 60.68, "elapsed_time": "19:52:50", "remaining_time": "12:53:06", "throughput": 553.74, "total_tokens": 39631888} {"current_steps": 24275, "total_steps": 40000, "loss": 0.1155, "lr": 1.6764737152410243e-05, "epoch": 1.09891577446298, "percentage": 60.69, "elapsed_time": "19:52:53", "remaining_time": "12:52:44", "throughput": 553.82, "total_tokens": 39639280} {"current_steps": 24280, "total_steps": 40000, "loss": 0.1142, "lr": 1.6755468255406016e-05, "epoch": 1.099142126349623, "percentage": 60.7, "elapsed_time": "19:52:56", "remaining_time": "12:52:22", "throughput": 553.91, "total_tokens": 39647024} {"current_steps": 24285, "total_steps": 40000, "loss": 0.1037, "lr": 1.674620062981219e-05, "epoch": 1.099368478236266, "percentage": 60.71, "elapsed_time": "19:53:00", "remaining_time": "12:52:00", "throughput": 553.99, "total_tokens": 39654768} {"current_steps": 24290, "total_steps": 40000, "loss": 0.0983, "lr": 1.6736934277057947e-05, "epoch": 1.099594830122909, "percentage": 60.72, "elapsed_time": "19:53:03", "remaining_time": "12:51:37", "throughput": 554.08, "total_tokens": 39663184} {"current_steps": 24295, "total_steps": 40000, "loss": 0.1109, "lr": 1.6727669198572286e-05, "epoch": 1.099821182009552, "percentage": 60.74, "elapsed_time": "19:53:06", "remaining_time": "12:51:15", "throughput": 554.18, "total_tokens": 39672144} {"current_steps": 24300, "total_steps": 40000, "loss": 0.0736, "lr": 1.6718405395783984e-05, "epoch": 1.100047533896195, "percentage": 60.75, "elapsed_time": "19:53:09", "remaining_time": "12:50:53", "throughput": 554.27, "total_tokens": 39679888} {"current_steps": 24305, "total_steps": 40000, "loss": 0.1084, "lr": 1.6709142870121643e-05, "epoch": 1.100273885782838, "percentage": 60.76, "elapsed_time": "19:53:12", "remaining_time": "12:50:31", "throughput": 554.36, "total_tokens": 39688144} {"current_steps": 24310, "total_steps": 40000, "loss": 0.106, "lr": 1.669988162301367e-05, "epoch": 1.100500237669481, "percentage": 60.77, "elapsed_time": "19:53:16", "remaining_time": "12:50:09", "throughput": 554.45, "total_tokens": 39696176} {"current_steps": 24315, "total_steps": 40000, "loss": 0.1087, "lr": 1.6690621655888243e-05, "epoch": 1.100726589556124, "percentage": 60.79, "elapsed_time": "19:53:19", "remaining_time": "12:49:46", "throughput": 554.53, "total_tokens": 39704240} {"current_steps": 24320, "total_steps": 40000, "loss": 0.1306, "lr": 1.6681362970173386e-05, "epoch": 1.100952941442767, "percentage": 60.8, "elapsed_time": "19:53:22", "remaining_time": "12:49:24", "throughput": 554.62, "total_tokens": 39712400} {"current_steps": 24325, "total_steps": 40000, "loss": 0.1448, "lr": 1.6672105567296904e-05, "epoch": 1.10117929332941, "percentage": 60.81, "elapsed_time": "19:53:25", "remaining_time": "12:49:02", "throughput": 554.71, "total_tokens": 39720784} {"current_steps": 24330, "total_steps": 40000, "loss": 0.1006, "lr": 1.666284944868639e-05, "epoch": 1.1014056452160528, "percentage": 60.82, "elapsed_time": "19:53:28", "remaining_time": "12:48:40", "throughput": 554.8, "total_tokens": 39728912} {"current_steps": 24335, "total_steps": 40000, "loss": 0.1526, "lr": 1.665359461576927e-05, "epoch": 1.1016319971026958, "percentage": 60.84, "elapsed_time": "19:53:32", "remaining_time": "12:48:18", "throughput": 554.9, "total_tokens": 39737776} {"current_steps": 24340, "total_steps": 40000, "loss": 0.1515, "lr": 1.6644341069972736e-05, "epoch": 1.1018583489893388, "percentage": 60.85, "elapsed_time": "19:53:35", "remaining_time": "12:47:56", "throughput": 555.01, "total_tokens": 39747408} {"current_steps": 24345, "total_steps": 40000, "loss": 0.1191, "lr": 1.6635088812723813e-05, "epoch": 1.1020847008759818, "percentage": 60.86, "elapsed_time": "19:53:39", "remaining_time": "12:47:34", "throughput": 555.11, "total_tokens": 39756336} {"current_steps": 24350, "total_steps": 40000, "loss": 0.1045, "lr": 1.6625837845449328e-05, "epoch": 1.1023110527626248, "percentage": 60.88, "elapsed_time": "19:53:42", "remaining_time": "12:47:12", "throughput": 555.2, "total_tokens": 39764432} {"current_steps": 24355, "total_steps": 40000, "loss": 0.1419, "lr": 1.6616588169575874e-05, "epoch": 1.1025374046492677, "percentage": 60.89, "elapsed_time": "19:53:45", "remaining_time": "12:46:50", "throughput": 555.29, "total_tokens": 39772624} {"current_steps": 24360, "total_steps": 40000, "loss": 0.1128, "lr": 1.6607339786529878e-05, "epoch": 1.1027637565359107, "percentage": 60.9, "elapsed_time": "19:53:48", "remaining_time": "12:46:28", "throughput": 555.38, "total_tokens": 39780944} {"current_steps": 24365, "total_steps": 40000, "loss": 0.0865, "lr": 1.659809269773756e-05, "epoch": 1.1029901084225537, "percentage": 60.91, "elapsed_time": "19:53:51", "remaining_time": "12:46:06", "throughput": 555.47, "total_tokens": 39789136} {"current_steps": 24370, "total_steps": 40000, "loss": 0.1489, "lr": 1.658884690462493e-05, "epoch": 1.1032164603091967, "percentage": 60.92, "elapsed_time": "19:53:54", "remaining_time": "12:45:43", "throughput": 555.55, "total_tokens": 39797072} {"current_steps": 24375, "total_steps": 40000, "loss": 0.0883, "lr": 1.6579602408617813e-05, "epoch": 1.1034428121958397, "percentage": 60.94, "elapsed_time": "19:53:58", "remaining_time": "12:45:21", "throughput": 555.63, "total_tokens": 39804464} {"current_steps": 24380, "total_steps": 40000, "loss": 0.1373, "lr": 1.657035921114181e-05, "epoch": 1.1036691640824827, "percentage": 60.95, "elapsed_time": "19:54:01", "remaining_time": "12:44:59", "throughput": 555.71, "total_tokens": 39811984} {"current_steps": 24385, "total_steps": 40000, "loss": 0.1172, "lr": 1.656111731362236e-05, "epoch": 1.1038955159691257, "percentage": 60.96, "elapsed_time": "19:54:04", "remaining_time": "12:44:37", "throughput": 555.8, "total_tokens": 39819984} {"current_steps": 24390, "total_steps": 40000, "loss": 0.1509, "lr": 1.6551876717484666e-05, "epoch": 1.1041218678557685, "percentage": 60.98, "elapsed_time": "19:54:07", "remaining_time": "12:44:15", "throughput": 555.89, "total_tokens": 39828464} {"current_steps": 24395, "total_steps": 40000, "loss": 0.1153, "lr": 1.6542637424153752e-05, "epoch": 1.1043482197424115, "percentage": 60.99, "elapsed_time": "19:54:10", "remaining_time": "12:43:53", "throughput": 555.98, "total_tokens": 39836272} {"current_steps": 24400, "total_steps": 40000, "loss": 0.1877, "lr": 1.6533399435054418e-05, "epoch": 1.1045745716290545, "percentage": 61.0, "elapsed_time": "19:54:13", "remaining_time": "12:43:31", "throughput": 556.07, "total_tokens": 39844432} {"current_steps": 24400, "total_steps": 40000, "eval_loss": 0.12385585159063339, "epoch": 1.1045745716290545, "percentage": 61.0, "elapsed_time": "20:01:56", "remaining_time": "12:48:27", "throughput": 552.5, "total_tokens": 39844432} {"current_steps": 24405, "total_steps": 40000, "loss": 0.1353, "lr": 1.6524162751611304e-05, "epoch": 1.1048009235156975, "percentage": 61.01, "elapsed_time": "20:02:00", "remaining_time": "12:48:05", "throughput": 552.58, "total_tokens": 39852240} {"current_steps": 24410, "total_steps": 40000, "loss": 0.1515, "lr": 1.6514927375248796e-05, "epoch": 1.1050272754023405, "percentage": 61.02, "elapsed_time": "20:02:03", "remaining_time": "12:47:43", "throughput": 552.66, "total_tokens": 39859536} {"current_steps": 24415, "total_steps": 40000, "loss": 0.0917, "lr": 1.6505693307391127e-05, "epoch": 1.1052536272889835, "percentage": 61.04, "elapsed_time": "20:02:06", "remaining_time": "12:47:21", "throughput": 552.75, "total_tokens": 39868048} {"current_steps": 24420, "total_steps": 40000, "loss": 0.0925, "lr": 1.6496460549462288e-05, "epoch": 1.1054799791756265, "percentage": 61.05, "elapsed_time": "20:02:09", "remaining_time": "12:46:58", "throughput": 552.83, "total_tokens": 39875568} {"current_steps": 24425, "total_steps": 40000, "loss": 0.1591, "lr": 1.6487229102886097e-05, "epoch": 1.1057063310622695, "percentage": 61.06, "elapsed_time": "20:02:13", "remaining_time": "12:46:36", "throughput": 552.92, "total_tokens": 39883504} {"current_steps": 24430, "total_steps": 40000, "loss": 0.0904, "lr": 1.6477998969086155e-05, "epoch": 1.1059326829489124, "percentage": 61.08, "elapsed_time": "20:02:16", "remaining_time": "12:46:14", "throughput": 553.01, "total_tokens": 39891888} {"current_steps": 24435, "total_steps": 40000, "loss": 0.0979, "lr": 1.646877014948587e-05, "epoch": 1.1061590348355554, "percentage": 61.09, "elapsed_time": "20:02:19", "remaining_time": "12:45:52", "throughput": 553.09, "total_tokens": 39899504} {"current_steps": 24440, "total_steps": 40000, "loss": 0.0795, "lr": 1.6459542645508433e-05, "epoch": 1.1063853867221982, "percentage": 61.1, "elapsed_time": "20:02:22", "remaining_time": "12:45:30", "throughput": 553.18, "total_tokens": 39908080} {"current_steps": 24445, "total_steps": 40000, "loss": 0.1116, "lr": 1.6450316458576852e-05, "epoch": 1.1066117386088412, "percentage": 61.11, "elapsed_time": "20:02:25", "remaining_time": "12:45:08", "throughput": 553.27, "total_tokens": 39916048} {"current_steps": 24450, "total_steps": 40000, "loss": 0.1125, "lr": 1.6441091590113912e-05, "epoch": 1.1068380904954842, "percentage": 61.12, "elapsed_time": "20:02:28", "remaining_time": "12:44:46", "throughput": 553.36, "total_tokens": 39923920} {"current_steps": 24455, "total_steps": 40000, "loss": 0.0744, "lr": 1.6431868041542213e-05, "epoch": 1.1070644423821272, "percentage": 61.14, "elapsed_time": "20:02:31", "remaining_time": "12:44:23", "throughput": 553.45, "total_tokens": 39932336} {"current_steps": 24460, "total_steps": 40000, "loss": 0.1733, "lr": 1.6422645814284123e-05, "epoch": 1.1072907942687702, "percentage": 61.15, "elapsed_time": "20:02:35", "remaining_time": "12:44:01", "throughput": 553.53, "total_tokens": 39940400} {"current_steps": 24465, "total_steps": 40000, "loss": 0.1423, "lr": 1.6413424909761846e-05, "epoch": 1.1075171461554132, "percentage": 61.16, "elapsed_time": "20:02:38", "remaining_time": "12:43:39", "throughput": 553.62, "total_tokens": 39948592} {"current_steps": 24470, "total_steps": 40000, "loss": 0.1062, "lr": 1.640420532939736e-05, "epoch": 1.1077434980420562, "percentage": 61.18, "elapsed_time": "20:02:41", "remaining_time": "12:43:17", "throughput": 553.71, "total_tokens": 39956400} {"current_steps": 24475, "total_steps": 40000, "loss": 0.0795, "lr": 1.639498707461242e-05, "epoch": 1.1079698499286992, "percentage": 61.19, "elapsed_time": "20:02:44", "remaining_time": "12:42:55", "throughput": 553.8, "total_tokens": 39964624} {"current_steps": 24480, "total_steps": 40000, "loss": 0.1158, "lr": 1.6385770146828614e-05, "epoch": 1.1081962018153422, "percentage": 61.2, "elapsed_time": "20:02:47", "remaining_time": "12:42:33", "throughput": 553.89, "total_tokens": 39972688} {"current_steps": 24485, "total_steps": 40000, "loss": 0.1515, "lr": 1.637655454746731e-05, "epoch": 1.1084225537019852, "percentage": 61.21, "elapsed_time": "20:02:50", "remaining_time": "12:42:11", "throughput": 553.97, "total_tokens": 39980624} {"current_steps": 24490, "total_steps": 40000, "loss": 0.1304, "lr": 1.6367340277949658e-05, "epoch": 1.1086489055886282, "percentage": 61.22, "elapsed_time": "20:02:54", "remaining_time": "12:41:49", "throughput": 554.06, "total_tokens": 39988784} {"current_steps": 24495, "total_steps": 40000, "loss": 0.1156, "lr": 1.635812733969663e-05, "epoch": 1.1088752574752712, "percentage": 61.24, "elapsed_time": "20:02:57", "remaining_time": "12:41:27", "throughput": 554.15, "total_tokens": 39997136} {"current_steps": 24500, "total_steps": 40000, "loss": 0.0588, "lr": 1.634891573412896e-05, "epoch": 1.109101609361914, "percentage": 61.25, "elapsed_time": "20:03:00", "remaining_time": "12:41:05", "throughput": 554.24, "total_tokens": 40005104} {"current_steps": 24505, "total_steps": 40000, "loss": 0.1421, "lr": 1.6339705462667196e-05, "epoch": 1.109327961248557, "percentage": 61.26, "elapsed_time": "20:03:03", "remaining_time": "12:40:43", "throughput": 554.32, "total_tokens": 40013136} {"current_steps": 24510, "total_steps": 40000, "loss": 0.0756, "lr": 1.633049652673169e-05, "epoch": 1.1095543131352, "percentage": 61.27, "elapsed_time": "20:03:06", "remaining_time": "12:40:21", "throughput": 554.42, "total_tokens": 40021648} {"current_steps": 24515, "total_steps": 40000, "loss": 0.0767, "lr": 1.632128892774256e-05, "epoch": 1.109780665021843, "percentage": 61.29, "elapsed_time": "20:03:10", "remaining_time": "12:39:59", "throughput": 554.51, "total_tokens": 40029872} {"current_steps": 24520, "total_steps": 40000, "loss": 0.1012, "lr": 1.6312082667119737e-05, "epoch": 1.110007016908486, "percentage": 61.3, "elapsed_time": "20:03:13", "remaining_time": "12:39:37", "throughput": 554.6, "total_tokens": 40038448} {"current_steps": 24525, "total_steps": 40000, "loss": 0.1235, "lr": 1.630287774628296e-05, "epoch": 1.110233368795129, "percentage": 61.31, "elapsed_time": "20:03:16", "remaining_time": "12:39:15", "throughput": 554.7, "total_tokens": 40047728} {"current_steps": 24530, "total_steps": 40000, "loss": 0.1502, "lr": 1.6293674166651718e-05, "epoch": 1.110459720681772, "percentage": 61.32, "elapsed_time": "20:03:19", "remaining_time": "12:38:53", "throughput": 554.8, "total_tokens": 40056176} {"current_steps": 24535, "total_steps": 40000, "loss": 0.0978, "lr": 1.6284471929645338e-05, "epoch": 1.110686072568415, "percentage": 61.34, "elapsed_time": "20:03:23", "remaining_time": "12:38:31", "throughput": 554.89, "total_tokens": 40064688} {"current_steps": 24540, "total_steps": 40000, "loss": 0.1496, "lr": 1.627527103668291e-05, "epoch": 1.110912424455058, "percentage": 61.35, "elapsed_time": "20:03:26", "remaining_time": "12:38:09", "throughput": 554.97, "total_tokens": 40072560} {"current_steps": 24545, "total_steps": 40000, "loss": 0.1473, "lr": 1.6266071489183327e-05, "epoch": 1.1111387763417009, "percentage": 61.36, "elapsed_time": "20:03:29", "remaining_time": "12:37:47", "throughput": 555.06, "total_tokens": 40080624} {"current_steps": 24550, "total_steps": 40000, "loss": 0.1183, "lr": 1.6256873288565283e-05, "epoch": 1.1113651282283439, "percentage": 61.38, "elapsed_time": "20:03:32", "remaining_time": "12:37:25", "throughput": 555.16, "total_tokens": 40089328} {"current_steps": 24555, "total_steps": 40000, "loss": 0.1124, "lr": 1.6247676436247245e-05, "epoch": 1.1115914801149867, "percentage": 61.39, "elapsed_time": "20:03:36", "remaining_time": "12:37:03", "throughput": 555.26, "total_tokens": 40098640} {"current_steps": 24560, "total_steps": 40000, "loss": 0.0979, "lr": 1.6238480933647486e-05, "epoch": 1.1118178320016296, "percentage": 61.4, "elapsed_time": "20:03:39", "remaining_time": "12:36:41", "throughput": 555.35, "total_tokens": 40106992} {"current_steps": 24565, "total_steps": 40000, "loss": 0.1151, "lr": 1.6229286782184083e-05, "epoch": 1.1120441838882726, "percentage": 61.41, "elapsed_time": "20:03:42", "remaining_time": "12:36:19", "throughput": 555.45, "total_tokens": 40115632} {"current_steps": 24570, "total_steps": 40000, "loss": 0.147, "lr": 1.622009398327487e-05, "epoch": 1.1122705357749156, "percentage": 61.42, "elapsed_time": "20:03:45", "remaining_time": "12:35:57", "throughput": 555.53, "total_tokens": 40123696} {"current_steps": 24575, "total_steps": 40000, "loss": 0.1133, "lr": 1.6210902538337502e-05, "epoch": 1.1124968876615586, "percentage": 61.44, "elapsed_time": "20:03:48", "remaining_time": "12:35:35", "throughput": 555.62, "total_tokens": 40131856} {"current_steps": 24580, "total_steps": 40000, "loss": 0.1161, "lr": 1.6201712448789413e-05, "epoch": 1.1127232395482016, "percentage": 61.45, "elapsed_time": "20:03:51", "remaining_time": "12:35:13", "throughput": 555.71, "total_tokens": 40139920} {"current_steps": 24585, "total_steps": 40000, "loss": 0.1121, "lr": 1.6192523716047827e-05, "epoch": 1.1129495914348446, "percentage": 61.46, "elapsed_time": "20:03:55", "remaining_time": "12:34:52", "throughput": 555.8, "total_tokens": 40148304} {"current_steps": 24590, "total_steps": 40000, "loss": 0.1569, "lr": 1.6183336341529776e-05, "epoch": 1.1131759433214876, "percentage": 61.48, "elapsed_time": "20:03:58", "remaining_time": "12:34:30", "throughput": 555.89, "total_tokens": 40156912} {"current_steps": 24595, "total_steps": 40000, "loss": 0.1202, "lr": 1.6174150326652047e-05, "epoch": 1.1134022952081306, "percentage": 61.49, "elapsed_time": "20:04:01", "remaining_time": "12:34:08", "throughput": 555.98, "total_tokens": 40164880} {"current_steps": 24600, "total_steps": 40000, "loss": 0.0957, "lr": 1.6164965672831256e-05, "epoch": 1.1136286470947736, "percentage": 61.5, "elapsed_time": "20:04:04", "remaining_time": "12:33:46", "throughput": 556.07, "total_tokens": 40173104} {"current_steps": 24600, "total_steps": 40000, "eval_loss": 0.1238485723733902, "epoch": 1.1136286470947736, "percentage": 61.5, "elapsed_time": "20:11:47", "remaining_time": "12:38:35", "throughput": 552.53, "total_tokens": 40173104} {"current_steps": 24605, "total_steps": 40000, "loss": 0.1184, "lr": 1.6155782381483784e-05, "epoch": 1.1138549989814166, "percentage": 61.51, "elapsed_time": "20:11:51", "remaining_time": "12:38:14", "throughput": 552.61, "total_tokens": 40180784} {"current_steps": 24610, "total_steps": 40000, "loss": 0.1466, "lr": 1.6146600454025813e-05, "epoch": 1.1140813508680596, "percentage": 61.52, "elapsed_time": "20:11:54", "remaining_time": "12:37:52", "throughput": 552.69, "total_tokens": 40188912} {"current_steps": 24615, "total_steps": 40000, "loss": 0.1058, "lr": 1.6137419891873317e-05, "epoch": 1.1143077027547024, "percentage": 61.54, "elapsed_time": "20:11:57", "remaining_time": "12:37:30", "throughput": 552.78, "total_tokens": 40196720} {"current_steps": 24620, "total_steps": 40000, "loss": 0.0957, "lr": 1.6128240696442038e-05, "epoch": 1.1145340546413454, "percentage": 61.55, "elapsed_time": "20:12:00", "remaining_time": "12:37:08", "throughput": 552.87, "total_tokens": 40204944} {"current_steps": 24625, "total_steps": 40000, "loss": 0.1276, "lr": 1.611906286914753e-05, "epoch": 1.1147604065279884, "percentage": 61.56, "elapsed_time": "20:12:03", "remaining_time": "12:36:46", "throughput": 552.95, "total_tokens": 40212944} {"current_steps": 24630, "total_steps": 40000, "loss": 0.1102, "lr": 1.6109886411405144e-05, "epoch": 1.1149867584146314, "percentage": 61.58, "elapsed_time": "20:12:07", "remaining_time": "12:36:24", "throughput": 553.05, "total_tokens": 40221744} {"current_steps": 24635, "total_steps": 40000, "loss": 0.0699, "lr": 1.6100711324629985e-05, "epoch": 1.1152131103012743, "percentage": 61.59, "elapsed_time": "20:12:10", "remaining_time": "12:36:02", "throughput": 553.13, "total_tokens": 40229424} {"current_steps": 24640, "total_steps": 40000, "loss": 0.0901, "lr": 1.609153761023698e-05, "epoch": 1.1154394621879173, "percentage": 61.6, "elapsed_time": "20:12:13", "remaining_time": "12:35:40", "throughput": 553.22, "total_tokens": 40237680} {"current_steps": 24645, "total_steps": 40000, "loss": 0.1266, "lr": 1.608236526964083e-05, "epoch": 1.1156658140745603, "percentage": 61.61, "elapsed_time": "20:12:16", "remaining_time": "12:35:18", "throughput": 553.3, "total_tokens": 40245392} {"current_steps": 24650, "total_steps": 40000, "loss": 0.1792, "lr": 1.607319430425601e-05, "epoch": 1.1158921659612033, "percentage": 61.62, "elapsed_time": "20:12:19", "remaining_time": "12:34:56", "throughput": 553.39, "total_tokens": 40253552} {"current_steps": 24655, "total_steps": 40000, "loss": 0.1257, "lr": 1.606402471549682e-05, "epoch": 1.1161185178478463, "percentage": 61.64, "elapsed_time": "20:12:22", "remaining_time": "12:34:34", "throughput": 553.48, "total_tokens": 40261488} {"current_steps": 24660, "total_steps": 40000, "loss": 0.1077, "lr": 1.6054856504777312e-05, "epoch": 1.1163448697344893, "percentage": 61.65, "elapsed_time": "20:12:26", "remaining_time": "12:34:12", "throughput": 553.56, "total_tokens": 40269488} {"current_steps": 24665, "total_steps": 40000, "loss": 0.1449, "lr": 1.6045689673511334e-05, "epoch": 1.1165712216211323, "percentage": 61.66, "elapsed_time": "20:12:29", "remaining_time": "12:33:50", "throughput": 553.65, "total_tokens": 40277872} {"current_steps": 24670, "total_steps": 40000, "loss": 0.0818, "lr": 1.6036524223112548e-05, "epoch": 1.116797573507775, "percentage": 61.68, "elapsed_time": "20:12:32", "remaining_time": "12:33:28", "throughput": 553.74, "total_tokens": 40286032} {"current_steps": 24675, "total_steps": 40000, "loss": 0.081, "lr": 1.602736015499436e-05, "epoch": 1.117023925394418, "percentage": 61.69, "elapsed_time": "20:12:35", "remaining_time": "12:33:06", "throughput": 553.83, "total_tokens": 40293936} {"current_steps": 24680, "total_steps": 40000, "loss": 0.1014, "lr": 1.601819747057e-05, "epoch": 1.117250277281061, "percentage": 61.7, "elapsed_time": "20:12:38", "remaining_time": "12:32:44", "throughput": 553.92, "total_tokens": 40302224} {"current_steps": 24685, "total_steps": 40000, "loss": 0.1038, "lr": 1.6009036171252465e-05, "epoch": 1.117476629167704, "percentage": 61.71, "elapsed_time": "20:12:42", "remaining_time": "12:32:22", "throughput": 554.0, "total_tokens": 40310288} {"current_steps": 24690, "total_steps": 40000, "loss": 0.1406, "lr": 1.599987625845453e-05, "epoch": 1.117702981054347, "percentage": 61.72, "elapsed_time": "20:12:45", "remaining_time": "12:32:00", "throughput": 554.1, "total_tokens": 40319056} {"current_steps": 24695, "total_steps": 40000, "loss": 0.0663, "lr": 1.599071773358879e-05, "epoch": 1.11792933294099, "percentage": 61.74, "elapsed_time": "20:12:48", "remaining_time": "12:31:39", "throughput": 554.19, "total_tokens": 40327440} {"current_steps": 24700, "total_steps": 40000, "loss": 0.1122, "lr": 1.598156059806758e-05, "epoch": 1.118155684827633, "percentage": 61.75, "elapsed_time": "20:12:51", "remaining_time": "12:31:17", "throughput": 554.28, "total_tokens": 40336336} {"current_steps": 24705, "total_steps": 40000, "loss": 0.133, "lr": 1.5972404853303062e-05, "epoch": 1.118382036714276, "percentage": 61.76, "elapsed_time": "20:12:55", "remaining_time": "12:30:55", "throughput": 554.37, "total_tokens": 40344528} {"current_steps": 24710, "total_steps": 40000, "loss": 0.13, "lr": 1.5963250500707172e-05, "epoch": 1.118608388600919, "percentage": 61.78, "elapsed_time": "20:12:58", "remaining_time": "12:30:33", "throughput": 554.47, "total_tokens": 40353104} {"current_steps": 24715, "total_steps": 40000, "loss": 0.1356, "lr": 1.5954097541691612e-05, "epoch": 1.118834740487562, "percentage": 61.79, "elapsed_time": "20:13:01", "remaining_time": "12:30:11", "throughput": 554.56, "total_tokens": 40361840} {"current_steps": 24720, "total_steps": 40000, "loss": 0.1173, "lr": 1.5944945977667884e-05, "epoch": 1.119061092374205, "percentage": 61.8, "elapsed_time": "20:13:04", "remaining_time": "12:29:49", "throughput": 554.65, "total_tokens": 40370192} {"current_steps": 24725, "total_steps": 40000, "loss": 0.1225, "lr": 1.593579581004729e-05, "epoch": 1.119287444260848, "percentage": 61.81, "elapsed_time": "20:13:08", "remaining_time": "12:29:28", "throughput": 554.74, "total_tokens": 40378608} {"current_steps": 24730, "total_steps": 40000, "loss": 0.1268, "lr": 1.592664704024088e-05, "epoch": 1.1195137961474908, "percentage": 61.82, "elapsed_time": "20:13:11", "remaining_time": "12:29:06", "throughput": 554.84, "total_tokens": 40387472} {"current_steps": 24735, "total_steps": 40000, "loss": 0.1193, "lr": 1.591749966965953e-05, "epoch": 1.1197401480341338, "percentage": 61.84, "elapsed_time": "20:13:14", "remaining_time": "12:28:44", "throughput": 554.92, "total_tokens": 40395152} {"current_steps": 24740, "total_steps": 40000, "loss": 0.0876, "lr": 1.5908353699713856e-05, "epoch": 1.1199664999207768, "percentage": 61.85, "elapsed_time": "20:13:17", "remaining_time": "12:28:22", "throughput": 555.01, "total_tokens": 40403056} {"current_steps": 24745, "total_steps": 40000, "loss": 0.1406, "lr": 1.5899209131814298e-05, "epoch": 1.1201928518074198, "percentage": 61.86, "elapsed_time": "20:13:20", "remaining_time": "12:28:00", "throughput": 555.1, "total_tokens": 40411856} {"current_steps": 24750, "total_steps": 40000, "loss": 0.1364, "lr": 1.5890065967371067e-05, "epoch": 1.1204192036940628, "percentage": 61.88, "elapsed_time": "20:13:24", "remaining_time": "12:27:39", "throughput": 555.18, "total_tokens": 40419568} {"current_steps": 24755, "total_steps": 40000, "loss": 0.2428, "lr": 1.5880924207794144e-05, "epoch": 1.1206455555807058, "percentage": 61.89, "elapsed_time": "20:13:27", "remaining_time": "12:27:17", "throughput": 555.28, "total_tokens": 40428080} {"current_steps": 24760, "total_steps": 40000, "loss": 0.0833, "lr": 1.5871783854493298e-05, "epoch": 1.1208719074673488, "percentage": 61.9, "elapsed_time": "20:13:30", "remaining_time": "12:26:55", "throughput": 555.36, "total_tokens": 40436368} {"current_steps": 24765, "total_steps": 40000, "loss": 0.1281, "lr": 1.5862644908878106e-05, "epoch": 1.1210982593539918, "percentage": 61.91, "elapsed_time": "20:13:33", "remaining_time": "12:26:33", "throughput": 555.45, "total_tokens": 40444496} {"current_steps": 24770, "total_steps": 40000, "loss": 0.1479, "lr": 1.5853507372357885e-05, "epoch": 1.1213246112406348, "percentage": 61.92, "elapsed_time": "20:13:36", "remaining_time": "12:26:11", "throughput": 555.54, "total_tokens": 40452528} {"current_steps": 24775, "total_steps": 40000, "loss": 0.0814, "lr": 1.5844371246341776e-05, "epoch": 1.1215509631272778, "percentage": 61.94, "elapsed_time": "20:13:39", "remaining_time": "12:25:50", "throughput": 555.62, "total_tokens": 40460080} {"current_steps": 24780, "total_steps": 40000, "loss": 0.162, "lr": 1.5835236532238674e-05, "epoch": 1.1217773150139205, "percentage": 61.95, "elapsed_time": "20:13:43", "remaining_time": "12:25:28", "throughput": 555.7, "total_tokens": 40467920} {"current_steps": 24785, "total_steps": 40000, "loss": 0.1337, "lr": 1.582610323145727e-05, "epoch": 1.1220036669005635, "percentage": 61.96, "elapsed_time": "20:13:46", "remaining_time": "12:25:06", "throughput": 555.79, "total_tokens": 40476464} {"current_steps": 24790, "total_steps": 40000, "loss": 0.096, "lr": 1.5816971345406035e-05, "epoch": 1.1222300187872065, "percentage": 61.98, "elapsed_time": "20:13:49", "remaining_time": "12:24:44", "throughput": 555.88, "total_tokens": 40484464} {"current_steps": 24795, "total_steps": 40000, "loss": 0.1267, "lr": 1.5807840875493225e-05, "epoch": 1.1224563706738495, "percentage": 61.99, "elapsed_time": "20:13:52", "remaining_time": "12:24:23", "throughput": 555.97, "total_tokens": 40493008} {"current_steps": 24800, "total_steps": 40000, "loss": 0.0896, "lr": 1.5798711823126854e-05, "epoch": 1.1226827225604925, "percentage": 62.0, "elapsed_time": "20:13:55", "remaining_time": "12:24:01", "throughput": 556.07, "total_tokens": 40501584} {"current_steps": 24800, "total_steps": 40000, "eval_loss": 0.12399327754974365, "epoch": 1.1226827225604925, "percentage": 62.0, "elapsed_time": "20:21:38", "remaining_time": "12:28:44", "throughput": 552.56, "total_tokens": 40501584} {"current_steps": 24805, "total_steps": 40000, "loss": 0.1203, "lr": 1.578958418971477e-05, "epoch": 1.1229090744471355, "percentage": 62.01, "elapsed_time": "20:21:42", "remaining_time": "12:28:23", "throughput": 552.64, "total_tokens": 40510032} {"current_steps": 24810, "total_steps": 40000, "loss": 0.0986, "lr": 1.578045797666453e-05, "epoch": 1.1231354263337785, "percentage": 62.02, "elapsed_time": "20:21:45", "remaining_time": "12:28:01", "throughput": 552.73, "total_tokens": 40518320} {"current_steps": 24815, "total_steps": 40000, "loss": 0.1048, "lr": 1.5771333185383548e-05, "epoch": 1.1233617782204215, "percentage": 62.04, "elapsed_time": "20:21:49", "remaining_time": "12:27:39", "throughput": 552.81, "total_tokens": 40525776} {"current_steps": 24820, "total_steps": 40000, "loss": 0.0867, "lr": 1.576220981727895e-05, "epoch": 1.1235881301070645, "percentage": 62.05, "elapsed_time": "20:21:52", "remaining_time": "12:27:17", "throughput": 552.89, "total_tokens": 40533712} {"current_steps": 24825, "total_steps": 40000, "loss": 0.0961, "lr": 1.575308787375769e-05, "epoch": 1.1238144819937075, "percentage": 62.06, "elapsed_time": "20:21:55", "remaining_time": "12:26:56", "throughput": 552.98, "total_tokens": 40542192} {"current_steps": 24830, "total_steps": 40000, "loss": 0.0812, "lr": 1.5743967356226492e-05, "epoch": 1.1240408338803505, "percentage": 62.08, "elapsed_time": "20:21:58", "remaining_time": "12:26:34", "throughput": 553.07, "total_tokens": 40550032} {"current_steps": 24835, "total_steps": 40000, "loss": 0.0902, "lr": 1.5734848266091835e-05, "epoch": 1.1242671857669935, "percentage": 62.09, "elapsed_time": "20:22:01", "remaining_time": "12:26:12", "throughput": 553.16, "total_tokens": 40558416} {"current_steps": 24840, "total_steps": 40000, "loss": 0.1263, "lr": 1.572573060476001e-05, "epoch": 1.1244935376536362, "percentage": 62.1, "elapsed_time": "20:22:04", "remaining_time": "12:25:50", "throughput": 553.24, "total_tokens": 40566160} {"current_steps": 24845, "total_steps": 40000, "loss": 0.1036, "lr": 1.5716614373637085e-05, "epoch": 1.1247198895402792, "percentage": 62.11, "elapsed_time": "20:22:08", "remaining_time": "12:25:28", "throughput": 553.33, "total_tokens": 40575056} {"current_steps": 24850, "total_steps": 40000, "loss": 0.1313, "lr": 1.570749957412887e-05, "epoch": 1.1249462414269222, "percentage": 62.12, "elapsed_time": "20:22:11", "remaining_time": "12:25:07", "throughput": 553.43, "total_tokens": 40584240} {"current_steps": 24855, "total_steps": 40000, "loss": 0.1042, "lr": 1.5698386207641013e-05, "epoch": 1.1251725933135652, "percentage": 62.14, "elapsed_time": "20:22:14", "remaining_time": "12:24:45", "throughput": 553.52, "total_tokens": 40592464} {"current_steps": 24860, "total_steps": 40000, "loss": 0.1515, "lr": 1.5689274275578884e-05, "epoch": 1.1253989452002082, "percentage": 62.15, "elapsed_time": "20:22:18", "remaining_time": "12:24:23", "throughput": 553.61, "total_tokens": 40600400} {"current_steps": 24865, "total_steps": 40000, "loss": 0.1498, "lr": 1.5680163779347667e-05, "epoch": 1.1256252970868512, "percentage": 62.16, "elapsed_time": "20:22:21", "remaining_time": "12:24:01", "throughput": 553.69, "total_tokens": 40608496} {"current_steps": 24870, "total_steps": 40000, "loss": 0.1377, "lr": 1.5671054720352327e-05, "epoch": 1.1258516489734942, "percentage": 62.18, "elapsed_time": "20:22:24", "remaining_time": "12:23:40", "throughput": 553.78, "total_tokens": 40616304} {"current_steps": 24875, "total_steps": 40000, "loss": 0.0912, "lr": 1.566194709999757e-05, "epoch": 1.1260780008601372, "percentage": 62.19, "elapsed_time": "20:22:27", "remaining_time": "12:23:18", "throughput": 553.86, "total_tokens": 40624464} {"current_steps": 24880, "total_steps": 40000, "loss": 0.1037, "lr": 1.5652840919687933e-05, "epoch": 1.1263043527467802, "percentage": 62.2, "elapsed_time": "20:22:30", "remaining_time": "12:22:56", "throughput": 553.94, "total_tokens": 40632144} {"current_steps": 24885, "total_steps": 40000, "loss": 0.0827, "lr": 1.5643736180827676e-05, "epoch": 1.1265307046334232, "percentage": 62.21, "elapsed_time": "20:22:33", "remaining_time": "12:22:34", "throughput": 554.03, "total_tokens": 40640080} {"current_steps": 24890, "total_steps": 40000, "loss": 0.1038, "lr": 1.5634632884820878e-05, "epoch": 1.1267570565200662, "percentage": 62.22, "elapsed_time": "20:22:36", "remaining_time": "12:22:12", "throughput": 554.12, "total_tokens": 40648464} {"current_steps": 24895, "total_steps": 40000, "loss": 0.1363, "lr": 1.5625531033071395e-05, "epoch": 1.126983408406709, "percentage": 62.24, "elapsed_time": "20:22:40", "remaining_time": "12:21:51", "throughput": 554.21, "total_tokens": 40656912} {"current_steps": 24900, "total_steps": 40000, "loss": 0.1464, "lr": 1.5616430626982828e-05, "epoch": 1.127209760293352, "percentage": 62.25, "elapsed_time": "20:22:43", "remaining_time": "12:21:29", "throughput": 554.3, "total_tokens": 40665296} {"current_steps": 24905, "total_steps": 40000, "loss": 0.1436, "lr": 1.5607331667958575e-05, "epoch": 1.127436112179995, "percentage": 62.26, "elapsed_time": "20:22:46", "remaining_time": "12:21:07", "throughput": 554.39, "total_tokens": 40673328} {"current_steps": 24910, "total_steps": 40000, "loss": 0.0842, "lr": 1.5598234157401824e-05, "epoch": 1.127662464066638, "percentage": 62.28, "elapsed_time": "20:22:49", "remaining_time": "12:20:46", "throughput": 554.48, "total_tokens": 40682064} {"current_steps": 24915, "total_steps": 40000, "loss": 0.1163, "lr": 1.5589138096715503e-05, "epoch": 1.127888815953281, "percentage": 62.29, "elapsed_time": "20:22:53", "remaining_time": "12:20:24", "throughput": 554.57, "total_tokens": 40690288} {"current_steps": 24920, "total_steps": 40000, "loss": 0.1125, "lr": 1.5580043487302365e-05, "epoch": 1.128115167839924, "percentage": 62.3, "elapsed_time": "20:22:56", "remaining_time": "12:20:02", "throughput": 554.66, "total_tokens": 40698640} {"current_steps": 24925, "total_steps": 40000, "loss": 0.0958, "lr": 1.5570950330564888e-05, "epoch": 1.128341519726567, "percentage": 62.31, "elapsed_time": "20:22:59", "remaining_time": "12:19:40", "throughput": 554.74, "total_tokens": 40706288} {"current_steps": 24930, "total_steps": 40000, "loss": 0.1088, "lr": 1.5561858627905367e-05, "epoch": 1.12856787161321, "percentage": 62.32, "elapsed_time": "20:23:02", "remaining_time": "12:19:19", "throughput": 554.82, "total_tokens": 40714384} {"current_steps": 24935, "total_steps": 40000, "loss": 0.0966, "lr": 1.5552768380725857e-05, "epoch": 1.128794223499853, "percentage": 62.34, "elapsed_time": "20:23:05", "remaining_time": "12:18:57", "throughput": 554.9, "total_tokens": 40721968} {"current_steps": 24940, "total_steps": 40000, "loss": 0.1527, "lr": 1.5543679590428183e-05, "epoch": 1.129020575386496, "percentage": 62.35, "elapsed_time": "20:23:08", "remaining_time": "12:18:35", "throughput": 554.99, "total_tokens": 40729648} {"current_steps": 24945, "total_steps": 40000, "loss": 0.0763, "lr": 1.5534592258413943e-05, "epoch": 1.129246927273139, "percentage": 62.36, "elapsed_time": "20:23:11", "remaining_time": "12:18:14", "throughput": 555.07, "total_tokens": 40737616} {"current_steps": 24950, "total_steps": 40000, "loss": 0.1358, "lr": 1.5525506386084538e-05, "epoch": 1.129473279159782, "percentage": 62.38, "elapsed_time": "20:23:14", "remaining_time": "12:17:52", "throughput": 555.15, "total_tokens": 40745104} {"current_steps": 24955, "total_steps": 40000, "loss": 0.0855, "lr": 1.55164219748411e-05, "epoch": 1.1296996310464247, "percentage": 62.39, "elapsed_time": "20:23:18", "remaining_time": "12:17:30", "throughput": 555.24, "total_tokens": 40753584} {"current_steps": 24960, "total_steps": 40000, "loss": 0.1289, "lr": 1.550733902608459e-05, "epoch": 1.1299259829330677, "percentage": 62.4, "elapsed_time": "20:23:21", "remaining_time": "12:17:09", "throughput": 555.33, "total_tokens": 40761680} {"current_steps": 24965, "total_steps": 40000, "loss": 0.0995, "lr": 1.549825754121568e-05, "epoch": 1.1301523348197107, "percentage": 62.41, "elapsed_time": "20:23:24", "remaining_time": "12:16:47", "throughput": 555.41, "total_tokens": 40769840} {"current_steps": 24970, "total_steps": 40000, "loss": 0.1044, "lr": 1.5489177521634864e-05, "epoch": 1.1303786867063537, "percentage": 62.42, "elapsed_time": "20:23:27", "remaining_time": "12:16:25", "throughput": 555.5, "total_tokens": 40777840} {"current_steps": 24975, "total_steps": 40000, "loss": 0.1163, "lr": 1.5480098968742402e-05, "epoch": 1.1306050385929967, "percentage": 62.44, "elapsed_time": "20:23:30", "remaining_time": "12:16:04", "throughput": 555.58, "total_tokens": 40785392} {"current_steps": 24980, "total_steps": 40000, "loss": 0.1121, "lr": 1.5471021883938304e-05, "epoch": 1.1308313904796397, "percentage": 62.45, "elapsed_time": "20:23:33", "remaining_time": "12:15:42", "throughput": 555.66, "total_tokens": 40793360} {"current_steps": 24985, "total_steps": 40000, "loss": 0.0902, "lr": 1.546194626862238e-05, "epoch": 1.1310577423662826, "percentage": 62.46, "elapsed_time": "20:23:37", "remaining_time": "12:15:20", "throughput": 555.75, "total_tokens": 40801488} {"current_steps": 24990, "total_steps": 40000, "loss": 0.1213, "lr": 1.5452872124194216e-05, "epoch": 1.1312840942529256, "percentage": 62.48, "elapsed_time": "20:23:40", "remaining_time": "12:14:59", "throughput": 555.84, "total_tokens": 40810032} {"current_steps": 24995, "total_steps": 40000, "loss": 0.114, "lr": 1.5443799452053136e-05, "epoch": 1.1315104461395686, "percentage": 62.49, "elapsed_time": "20:23:43", "remaining_time": "12:14:37", "throughput": 555.92, "total_tokens": 40817872} {"current_steps": 25000, "total_steps": 40000, "loss": 0.1227, "lr": 1.543472825359828e-05, "epoch": 1.1317367980262116, "percentage": 62.5, "elapsed_time": "20:23:46", "remaining_time": "12:14:16", "throughput": 556.01, "total_tokens": 40826064} {"current_steps": 25000, "total_steps": 40000, "eval_loss": 0.12423257529735565, "epoch": 1.1317367980262116, "percentage": 62.5, "elapsed_time": "20:31:29", "remaining_time": "12:18:53", "throughput": 552.53, "total_tokens": 40826064} {"current_steps": 25005, "total_steps": 40000, "loss": 0.1299, "lr": 1.5425658530228522e-05, "epoch": 1.1319631499128544, "percentage": 62.51, "elapsed_time": "20:31:33", "remaining_time": "12:18:32", "throughput": 552.62, "total_tokens": 40834608} {"current_steps": 25010, "total_steps": 40000, "loss": 0.1125, "lr": 1.5416590283342546e-05, "epoch": 1.1321895017994974, "percentage": 62.52, "elapsed_time": "20:31:36", "remaining_time": "12:18:10", "throughput": 552.7, "total_tokens": 40842832} {"current_steps": 25015, "total_steps": 40000, "loss": 0.1615, "lr": 1.5407523514338783e-05, "epoch": 1.1324158536861404, "percentage": 62.54, "elapsed_time": "20:31:39", "remaining_time": "12:17:48", "throughput": 552.79, "total_tokens": 40850960} {"current_steps": 25020, "total_steps": 40000, "loss": 0.1646, "lr": 1.539845822461543e-05, "epoch": 1.1326422055727834, "percentage": 62.55, "elapsed_time": "20:31:42", "remaining_time": "12:17:27", "throughput": 552.87, "total_tokens": 40858672} {"current_steps": 25025, "total_steps": 40000, "loss": 0.1318, "lr": 1.538939441557048e-05, "epoch": 1.1328685574594264, "percentage": 62.56, "elapsed_time": "20:31:45", "remaining_time": "12:17:05", "throughput": 552.96, "total_tokens": 40867088} {"current_steps": 25030, "total_steps": 40000, "loss": 0.1074, "lr": 1.5380332088601696e-05, "epoch": 1.1330949093460694, "percentage": 62.58, "elapsed_time": "20:31:49", "remaining_time": "12:16:43", "throughput": 553.05, "total_tokens": 40875312} {"current_steps": 25035, "total_steps": 40000, "loss": 0.1888, "lr": 1.537127124510658e-05, "epoch": 1.1333212612327124, "percentage": 62.59, "elapsed_time": "20:31:52", "remaining_time": "12:16:22", "throughput": 553.14, "total_tokens": 40883728} {"current_steps": 25040, "total_steps": 40000, "loss": 0.0984, "lr": 1.5362211886482457e-05, "epoch": 1.1335476131193554, "percentage": 62.6, "elapsed_time": "20:31:55", "remaining_time": "12:16:00", "throughput": 553.23, "total_tokens": 40892368} {"current_steps": 25045, "total_steps": 40000, "loss": 0.1582, "lr": 1.5353154014126363e-05, "epoch": 1.1337739650059984, "percentage": 62.61, "elapsed_time": "20:31:58", "remaining_time": "12:15:38", "throughput": 553.31, "total_tokens": 40900112} {"current_steps": 25050, "total_steps": 40000, "loss": 0.1231, "lr": 1.534409762943515e-05, "epoch": 1.1340003168926414, "percentage": 62.62, "elapsed_time": "20:32:02", "remaining_time": "12:15:17", "throughput": 553.4, "total_tokens": 40908400} {"current_steps": 25055, "total_steps": 40000, "loss": 0.1485, "lr": 1.5335042733805438e-05, "epoch": 1.1342266687792844, "percentage": 62.64, "elapsed_time": "20:32:05", "remaining_time": "12:14:55", "throughput": 553.49, "total_tokens": 40916720} {"current_steps": 25060, "total_steps": 40000, "loss": 0.0706, "lr": 1.532598932863358e-05, "epoch": 1.1344530206659273, "percentage": 62.65, "elapsed_time": "20:32:08", "remaining_time": "12:14:33", "throughput": 553.58, "total_tokens": 40925072} {"current_steps": 25065, "total_steps": 40000, "loss": 0.1537, "lr": 1.531693741531574e-05, "epoch": 1.1346793725525703, "percentage": 62.66, "elapsed_time": "20:32:11", "remaining_time": "12:14:12", "throughput": 553.66, "total_tokens": 40933072} {"current_steps": 25070, "total_steps": 40000, "loss": 0.1204, "lr": 1.5307886995247844e-05, "epoch": 1.1349057244392131, "percentage": 62.68, "elapsed_time": "20:32:14", "remaining_time": "12:13:50", "throughput": 553.75, "total_tokens": 40941680} {"current_steps": 25075, "total_steps": 40000, "loss": 0.109, "lr": 1.529883806982557e-05, "epoch": 1.135132076325856, "percentage": 62.69, "elapsed_time": "20:32:18", "remaining_time": "12:13:29", "throughput": 553.84, "total_tokens": 40950224} {"current_steps": 25080, "total_steps": 40000, "loss": 0.1173, "lr": 1.5289790640444376e-05, "epoch": 1.135358428212499, "percentage": 62.7, "elapsed_time": "20:32:21", "remaining_time": "12:13:07", "throughput": 553.94, "total_tokens": 40959440} {"current_steps": 25085, "total_steps": 40000, "loss": 0.1113, "lr": 1.5280744708499494e-05, "epoch": 1.135584780099142, "percentage": 62.71, "elapsed_time": "20:32:24", "remaining_time": "12:12:45", "throughput": 554.03, "total_tokens": 40967888} {"current_steps": 25090, "total_steps": 40000, "loss": 0.0932, "lr": 1.527170027538591e-05, "epoch": 1.135811131985785, "percentage": 62.72, "elapsed_time": "20:32:28", "remaining_time": "12:12:24", "throughput": 554.12, "total_tokens": 40976432} {"current_steps": 25095, "total_steps": 40000, "loss": 0.1111, "lr": 1.5262657342498407e-05, "epoch": 1.136037483872428, "percentage": 62.74, "elapsed_time": "20:32:31", "remaining_time": "12:12:02", "throughput": 554.21, "total_tokens": 40984144} {"current_steps": 25100, "total_steps": 40000, "loss": 0.0944, "lr": 1.52536159112315e-05, "epoch": 1.136263835759071, "percentage": 62.75, "elapsed_time": "20:32:34", "remaining_time": "12:11:41", "throughput": 554.29, "total_tokens": 40991856} {"current_steps": 25105, "total_steps": 40000, "loss": 0.1381, "lr": 1.5244575982979497e-05, "epoch": 1.136490187645714, "percentage": 62.76, "elapsed_time": "20:32:37", "remaining_time": "12:11:19", "throughput": 554.38, "total_tokens": 41000272} {"current_steps": 25110, "total_steps": 40000, "loss": 0.1183, "lr": 1.5235537559136487e-05, "epoch": 1.136716539532357, "percentage": 62.78, "elapsed_time": "20:32:40", "remaining_time": "12:10:58", "throughput": 554.48, "total_tokens": 41009584} {"current_steps": 25115, "total_steps": 40000, "loss": 0.1424, "lr": 1.5226500641096286e-05, "epoch": 1.136942891419, "percentage": 62.79, "elapsed_time": "20:32:44", "remaining_time": "12:10:36", "throughput": 554.56, "total_tokens": 41017776} {"current_steps": 25120, "total_steps": 40000, "loss": 0.0889, "lr": 1.5217465230252509e-05, "epoch": 1.1371692433056428, "percentage": 62.8, "elapsed_time": "20:32:47", "remaining_time": "12:10:14", "throughput": 554.65, "total_tokens": 41025872} {"current_steps": 25125, "total_steps": 40000, "loss": 0.0712, "lr": 1.5208431327998523e-05, "epoch": 1.1373955951922858, "percentage": 62.81, "elapsed_time": "20:32:50", "remaining_time": "12:09:53", "throughput": 554.75, "total_tokens": 41034864} {"current_steps": 25130, "total_steps": 40000, "loss": 0.1213, "lr": 1.5199398935727477e-05, "epoch": 1.1376219470789288, "percentage": 62.82, "elapsed_time": "20:32:53", "remaining_time": "12:09:31", "throughput": 554.83, "total_tokens": 41043024} {"current_steps": 25135, "total_steps": 40000, "loss": 0.1044, "lr": 1.5190368054832282e-05, "epoch": 1.1378482989655718, "percentage": 62.84, "elapsed_time": "20:32:56", "remaining_time": "12:09:10", "throughput": 554.92, "total_tokens": 41051248} {"current_steps": 25140, "total_steps": 40000, "loss": 0.1125, "lr": 1.5181338686705601e-05, "epoch": 1.1380746508522148, "percentage": 62.85, "elapsed_time": "20:33:00", "remaining_time": "12:08:48", "throughput": 555.0, "total_tokens": 41059248} {"current_steps": 25145, "total_steps": 40000, "loss": 0.1273, "lr": 1.5172310832739889e-05, "epoch": 1.1383010027388578, "percentage": 62.86, "elapsed_time": "20:33:03", "remaining_time": "12:08:27", "throughput": 555.09, "total_tokens": 41067312} {"current_steps": 25150, "total_steps": 40000, "loss": 0.0928, "lr": 1.5163284494327346e-05, "epoch": 1.1385273546255008, "percentage": 62.88, "elapsed_time": "20:33:06", "remaining_time": "12:08:05", "throughput": 555.18, "total_tokens": 41075632} {"current_steps": 25155, "total_steps": 40000, "loss": 0.1434, "lr": 1.5154259672859952e-05, "epoch": 1.1387537065121438, "percentage": 62.89, "elapsed_time": "20:33:09", "remaining_time": "12:07:44", "throughput": 555.26, "total_tokens": 41083504} {"current_steps": 25160, "total_steps": 40000, "loss": 0.1073, "lr": 1.5145236369729452e-05, "epoch": 1.1389800583987868, "percentage": 62.9, "elapsed_time": "20:33:12", "remaining_time": "12:07:22", "throughput": 555.35, "total_tokens": 41091920} {"current_steps": 25165, "total_steps": 40000, "loss": 0.1201, "lr": 1.5136214586327335e-05, "epoch": 1.1392064102854298, "percentage": 62.91, "elapsed_time": "20:33:15", "remaining_time": "12:07:01", "throughput": 555.43, "total_tokens": 41099952} {"current_steps": 25170, "total_steps": 40000, "loss": 0.1071, "lr": 1.5127194324044885e-05, "epoch": 1.1394327621720728, "percentage": 62.92, "elapsed_time": "20:33:19", "remaining_time": "12:06:39", "throughput": 555.52, "total_tokens": 41107856} {"current_steps": 25175, "total_steps": 40000, "loss": 0.0932, "lr": 1.5118175584273148e-05, "epoch": 1.1396591140587158, "percentage": 62.94, "elapsed_time": "20:33:22", "remaining_time": "12:06:18", "throughput": 555.6, "total_tokens": 41115952} {"current_steps": 25180, "total_steps": 40000, "loss": 0.1279, "lr": 1.5109158368402909e-05, "epoch": 1.1398854659453588, "percentage": 62.95, "elapsed_time": "20:33:25", "remaining_time": "12:05:56", "throughput": 555.69, "total_tokens": 41123824} {"current_steps": 25185, "total_steps": 40000, "loss": 0.0756, "lr": 1.5100142677824753e-05, "epoch": 1.1401118178320016, "percentage": 62.96, "elapsed_time": "20:33:28", "remaining_time": "12:05:35", "throughput": 555.77, "total_tokens": 41131984} {"current_steps": 25190, "total_steps": 40000, "loss": 0.1347, "lr": 1.509112851392901e-05, "epoch": 1.1403381697186445, "percentage": 62.98, "elapsed_time": "20:33:31", "remaining_time": "12:05:13", "throughput": 555.87, "total_tokens": 41140848} {"current_steps": 25195, "total_steps": 40000, "loss": 0.1065, "lr": 1.5082115878105763e-05, "epoch": 1.1405645216052875, "percentage": 62.99, "elapsed_time": "20:33:35", "remaining_time": "12:04:52", "throughput": 555.96, "total_tokens": 41149136} {"current_steps": 25200, "total_steps": 40000, "loss": 0.1777, "lr": 1.5073104771744892e-05, "epoch": 1.1407908734919305, "percentage": 63.0, "elapsed_time": "20:33:38", "remaining_time": "12:04:31", "throughput": 556.05, "total_tokens": 41157808} {"current_steps": 25200, "total_steps": 40000, "eval_loss": 0.12372566014528275, "epoch": 1.1407908734919305, "percentage": 63.0, "elapsed_time": "20:41:20", "remaining_time": "12:09:02", "throughput": 552.6, "total_tokens": 41157808} {"current_steps": 25205, "total_steps": 40000, "loss": 0.1087, "lr": 1.5064095196236006e-05, "epoch": 1.1410172253785735, "percentage": 63.01, "elapsed_time": "20:41:25", "remaining_time": "12:08:41", "throughput": 552.68, "total_tokens": 41166576} {"current_steps": 25210, "total_steps": 40000, "loss": 0.1447, "lr": 1.50550871529685e-05, "epoch": 1.1412435772652165, "percentage": 63.02, "elapsed_time": "20:41:28", "remaining_time": "12:08:20", "throughput": 552.75, "total_tokens": 41173648} {"current_steps": 25215, "total_steps": 40000, "loss": 0.1435, "lr": 1.5046080643331546e-05, "epoch": 1.1414699291518595, "percentage": 63.04, "elapsed_time": "20:41:31", "remaining_time": "12:07:58", "throughput": 552.84, "total_tokens": 41181360} {"current_steps": 25220, "total_steps": 40000, "loss": 0.1089, "lr": 1.5037075668714028e-05, "epoch": 1.1416962810385025, "percentage": 63.05, "elapsed_time": "20:41:34", "remaining_time": "12:07:36", "throughput": 552.92, "total_tokens": 41189488} {"current_steps": 25225, "total_steps": 40000, "loss": 0.1315, "lr": 1.5028072230504656e-05, "epoch": 1.1419226329251455, "percentage": 63.06, "elapsed_time": "20:41:37", "remaining_time": "12:07:15", "throughput": 553.0, "total_tokens": 41197008} {"current_steps": 25230, "total_steps": 40000, "loss": 0.1021, "lr": 1.5019070330091861e-05, "epoch": 1.1421489848117883, "percentage": 63.08, "elapsed_time": "20:41:40", "remaining_time": "12:06:53", "throughput": 553.09, "total_tokens": 41205360} {"current_steps": 25235, "total_steps": 40000, "loss": 0.1487, "lr": 1.5010069968863843e-05, "epoch": 1.1423753366984313, "percentage": 63.09, "elapsed_time": "20:41:43", "remaining_time": "12:06:32", "throughput": 553.17, "total_tokens": 41213424} {"current_steps": 25240, "total_steps": 40000, "loss": 0.0947, "lr": 1.5001071148208584e-05, "epoch": 1.1426016885850743, "percentage": 63.1, "elapsed_time": "20:41:47", "remaining_time": "12:06:10", "throughput": 553.26, "total_tokens": 41221616} {"current_steps": 25245, "total_steps": 40000, "loss": 0.1007, "lr": 1.49920738695138e-05, "epoch": 1.1428280404717173, "percentage": 63.11, "elapsed_time": "20:41:50", "remaining_time": "12:05:49", "throughput": 553.34, "total_tokens": 41229680} {"current_steps": 25250, "total_steps": 40000, "loss": 0.1008, "lr": 1.4983078134166995e-05, "epoch": 1.1430543923583603, "percentage": 63.12, "elapsed_time": "20:41:53", "remaining_time": "12:05:27", "throughput": 553.43, "total_tokens": 41238160} {"current_steps": 25255, "total_steps": 40000, "loss": 0.1356, "lr": 1.4974083943555428e-05, "epoch": 1.1432807442450033, "percentage": 63.14, "elapsed_time": "20:41:56", "remaining_time": "12:05:06", "throughput": 553.51, "total_tokens": 41245648} {"current_steps": 25260, "total_steps": 40000, "loss": 0.1611, "lr": 1.496509129906611e-05, "epoch": 1.1435070961316463, "percentage": 63.15, "elapsed_time": "20:41:59", "remaining_time": "12:04:44", "throughput": 553.59, "total_tokens": 41253296} {"current_steps": 25265, "total_steps": 40000, "loss": 0.0947, "lr": 1.4956100202085809e-05, "epoch": 1.1437334480182892, "percentage": 63.16, "elapsed_time": "20:42:02", "remaining_time": "12:04:23", "throughput": 553.68, "total_tokens": 41261552} {"current_steps": 25270, "total_steps": 40000, "loss": 0.146, "lr": 1.4947110654001093e-05, "epoch": 1.1439597999049322, "percentage": 63.18, "elapsed_time": "20:42:05", "remaining_time": "12:04:01", "throughput": 553.76, "total_tokens": 41269680} {"current_steps": 25275, "total_steps": 40000, "loss": 0.1151, "lr": 1.4938122656198234e-05, "epoch": 1.1441861517915752, "percentage": 63.19, "elapsed_time": "20:42:09", "remaining_time": "12:03:40", "throughput": 553.85, "total_tokens": 41277808} {"current_steps": 25280, "total_steps": 40000, "loss": 0.0744, "lr": 1.4929136210063316e-05, "epoch": 1.1444125036782182, "percentage": 63.2, "elapsed_time": "20:42:12", "remaining_time": "12:03:18", "throughput": 553.93, "total_tokens": 41286032} {"current_steps": 25285, "total_steps": 40000, "loss": 0.12, "lr": 1.4920151316982146e-05, "epoch": 1.1446388555648612, "percentage": 63.21, "elapsed_time": "20:42:15", "remaining_time": "12:02:57", "throughput": 554.02, "total_tokens": 41294128} {"current_steps": 25290, "total_steps": 40000, "loss": 0.0915, "lr": 1.4911167978340312e-05, "epoch": 1.1448652074515042, "percentage": 63.22, "elapsed_time": "20:42:18", "remaining_time": "12:02:35", "throughput": 554.11, "total_tokens": 41302928} {"current_steps": 25295, "total_steps": 40000, "loss": 0.112, "lr": 1.4902186195523166e-05, "epoch": 1.145091559338147, "percentage": 63.24, "elapsed_time": "20:42:22", "remaining_time": "12:02:14", "throughput": 554.21, "total_tokens": 41311632} {"current_steps": 25300, "total_steps": 40000, "loss": 0.1221, "lr": 1.4893205969915805e-05, "epoch": 1.14531791122479, "percentage": 63.25, "elapsed_time": "20:42:25", "remaining_time": "12:01:53", "throughput": 554.31, "total_tokens": 41321136} {"current_steps": 25305, "total_steps": 40000, "loss": 0.1074, "lr": 1.4884227302903086e-05, "epoch": 1.145544263111433, "percentage": 63.26, "elapsed_time": "20:42:28", "remaining_time": "12:01:31", "throughput": 554.39, "total_tokens": 41329424} {"current_steps": 25310, "total_steps": 40000, "loss": 0.1203, "lr": 1.4875250195869653e-05, "epoch": 1.145770614998076, "percentage": 63.28, "elapsed_time": "20:42:32", "remaining_time": "12:01:10", "throughput": 554.49, "total_tokens": 41338416} {"current_steps": 25315, "total_steps": 40000, "loss": 0.1259, "lr": 1.4866274650199862e-05, "epoch": 1.145996966884719, "percentage": 63.29, "elapsed_time": "20:42:35", "remaining_time": "12:00:48", "throughput": 554.57, "total_tokens": 41345840} {"current_steps": 25320, "total_steps": 40000, "loss": 0.0921, "lr": 1.485730066727788e-05, "epoch": 1.146223318771362, "percentage": 63.3, "elapsed_time": "20:42:38", "remaining_time": "12:00:27", "throughput": 554.65, "total_tokens": 41353936} {"current_steps": 25325, "total_steps": 40000, "loss": 0.0907, "lr": 1.4848328248487586e-05, "epoch": 1.146449670658005, "percentage": 63.31, "elapsed_time": "20:42:41", "remaining_time": "12:00:05", "throughput": 554.73, "total_tokens": 41361712} {"current_steps": 25330, "total_steps": 40000, "loss": 0.1534, "lr": 1.4839357395212656e-05, "epoch": 1.146676022544648, "percentage": 63.32, "elapsed_time": "20:42:44", "remaining_time": "11:59:44", "throughput": 554.83, "total_tokens": 41370576} {"current_steps": 25335, "total_steps": 40000, "loss": 0.1073, "lr": 1.4830388108836502e-05, "epoch": 1.146902374431291, "percentage": 63.34, "elapsed_time": "20:42:47", "remaining_time": "11:59:23", "throughput": 554.91, "total_tokens": 41378608} {"current_steps": 25340, "total_steps": 40000, "loss": 0.1074, "lr": 1.4821420390742299e-05, "epoch": 1.147128726317934, "percentage": 63.35, "elapsed_time": "20:42:50", "remaining_time": "11:59:01", "throughput": 554.99, "total_tokens": 41386416} {"current_steps": 25345, "total_steps": 40000, "loss": 0.1014, "lr": 1.4812454242312979e-05, "epoch": 1.1473550782045767, "percentage": 63.36, "elapsed_time": "20:42:54", "remaining_time": "11:58:40", "throughput": 555.08, "total_tokens": 41394576} {"current_steps": 25350, "total_steps": 40000, "loss": 0.1122, "lr": 1.4803489664931253e-05, "epoch": 1.1475814300912197, "percentage": 63.38, "elapsed_time": "20:42:57", "remaining_time": "11:58:18", "throughput": 555.16, "total_tokens": 41402416} {"current_steps": 25355, "total_steps": 40000, "loss": 0.0981, "lr": 1.4794526659979544e-05, "epoch": 1.1478077819778627, "percentage": 63.39, "elapsed_time": "20:43:00", "remaining_time": "11:57:57", "throughput": 555.25, "total_tokens": 41410448} {"current_steps": 25360, "total_steps": 40000, "loss": 0.0879, "lr": 1.4785565228840086e-05, "epoch": 1.1480341338645057, "percentage": 63.4, "elapsed_time": "20:43:03", "remaining_time": "11:57:36", "throughput": 555.34, "total_tokens": 41419312} {"current_steps": 25365, "total_steps": 40000, "loss": 0.1231, "lr": 1.4776605372894819e-05, "epoch": 1.1482604857511487, "percentage": 63.41, "elapsed_time": "20:43:06", "remaining_time": "11:57:14", "throughput": 555.42, "total_tokens": 41427184} {"current_steps": 25370, "total_steps": 40000, "loss": 0.0906, "lr": 1.4767647093525488e-05, "epoch": 1.1484868376377917, "percentage": 63.42, "elapsed_time": "20:43:10", "remaining_time": "11:56:53", "throughput": 555.5, "total_tokens": 41435120} {"current_steps": 25375, "total_steps": 40000, "loss": 0.1286, "lr": 1.4758690392113566e-05, "epoch": 1.1487131895244347, "percentage": 63.44, "elapsed_time": "20:43:13", "remaining_time": "11:56:32", "throughput": 555.58, "total_tokens": 41442736} {"current_steps": 25380, "total_steps": 40000, "loss": 0.1079, "lr": 1.4749735270040276e-05, "epoch": 1.1489395414110777, "percentage": 63.45, "elapsed_time": "20:43:16", "remaining_time": "11:56:10", "throughput": 555.67, "total_tokens": 41451248} {"current_steps": 25385, "total_steps": 40000, "loss": 0.1044, "lr": 1.4740781728686623e-05, "epoch": 1.1491658932977207, "percentage": 63.46, "elapsed_time": "20:43:19", "remaining_time": "11:55:49", "throughput": 555.76, "total_tokens": 41459760} {"current_steps": 25390, "total_steps": 40000, "loss": 0.082, "lr": 1.4731829769433358e-05, "epoch": 1.1493922451843637, "percentage": 63.48, "elapsed_time": "20:43:22", "remaining_time": "11:55:28", "throughput": 555.85, "total_tokens": 41468048} {"current_steps": 25395, "total_steps": 40000, "loss": 0.0903, "lr": 1.4722879393660976e-05, "epoch": 1.1496185970710067, "percentage": 63.49, "elapsed_time": "20:43:26", "remaining_time": "11:55:06", "throughput": 555.94, "total_tokens": 41476240} {"current_steps": 25400, "total_steps": 40000, "loss": 0.1331, "lr": 1.4713930602749748e-05, "epoch": 1.1498449489576497, "percentage": 63.5, "elapsed_time": "20:43:29", "remaining_time": "11:54:45", "throughput": 556.02, "total_tokens": 41484464} {"current_steps": 25400, "total_steps": 40000, "eval_loss": 0.1236872524023056, "epoch": 1.1498449489576497, "percentage": 63.5, "elapsed_time": "20:51:11", "remaining_time": "11:59:11", "throughput": 552.6, "total_tokens": 41484464} {"current_steps": 25405, "total_steps": 40000, "loss": 0.1325, "lr": 1.470498339807968e-05, "epoch": 1.1500713008442927, "percentage": 63.51, "elapsed_time": "20:51:15", "remaining_time": "11:58:50", "throughput": 552.68, "total_tokens": 41492656} {"current_steps": 25410, "total_steps": 40000, "loss": 0.1259, "lr": 1.4696037781030542e-05, "epoch": 1.1502976527309354, "percentage": 63.52, "elapsed_time": "20:51:19", "remaining_time": "11:58:29", "throughput": 552.76, "total_tokens": 41500880} {"current_steps": 25415, "total_steps": 40000, "loss": 0.1382, "lr": 1.4687093752981876e-05, "epoch": 1.1505240046175784, "percentage": 63.54, "elapsed_time": "20:51:22", "remaining_time": "11:58:07", "throughput": 552.85, "total_tokens": 41509104} {"current_steps": 25420, "total_steps": 40000, "loss": 0.1227, "lr": 1.4678151315312943e-05, "epoch": 1.1507503565042214, "percentage": 63.55, "elapsed_time": "20:51:25", "remaining_time": "11:57:46", "throughput": 552.93, "total_tokens": 41517168} {"current_steps": 25425, "total_steps": 40000, "loss": 0.1264, "lr": 1.4669210469402789e-05, "epoch": 1.1509767083908644, "percentage": 63.56, "elapsed_time": "20:51:28", "remaining_time": "11:57:24", "throughput": 553.02, "total_tokens": 41525392} {"current_steps": 25430, "total_steps": 40000, "loss": 0.106, "lr": 1.4660271216630218e-05, "epoch": 1.1512030602775074, "percentage": 63.58, "elapsed_time": "20:51:31", "remaining_time": "11:57:03", "throughput": 553.1, "total_tokens": 41533456} {"current_steps": 25435, "total_steps": 40000, "loss": 0.0897, "lr": 1.4651333558373748e-05, "epoch": 1.1514294121641504, "percentage": 63.59, "elapsed_time": "20:51:34", "remaining_time": "11:56:42", "throughput": 553.18, "total_tokens": 41541392} {"current_steps": 25440, "total_steps": 40000, "loss": 0.1225, "lr": 1.4642397496011707e-05, "epoch": 1.1516557640507934, "percentage": 63.6, "elapsed_time": "20:51:38", "remaining_time": "11:56:20", "throughput": 553.27, "total_tokens": 41549616} {"current_steps": 25445, "total_steps": 40000, "loss": 0.1216, "lr": 1.4633463030922129e-05, "epoch": 1.1518821159374364, "percentage": 63.61, "elapsed_time": "20:51:41", "remaining_time": "11:55:59", "throughput": 553.35, "total_tokens": 41557456} {"current_steps": 25450, "total_steps": 40000, "loss": 0.1214, "lr": 1.462453016448282e-05, "epoch": 1.1521084678240794, "percentage": 63.62, "elapsed_time": "20:51:44", "remaining_time": "11:55:38", "throughput": 553.43, "total_tokens": 41565328} {"current_steps": 25455, "total_steps": 40000, "loss": 0.1107, "lr": 1.4615598898071354e-05, "epoch": 1.1523348197107224, "percentage": 63.64, "elapsed_time": "20:51:47", "remaining_time": "11:55:16", "throughput": 553.53, "total_tokens": 41574448} {"current_steps": 25460, "total_steps": 40000, "loss": 0.1318, "lr": 1.4606669233065026e-05, "epoch": 1.1525611715973652, "percentage": 63.65, "elapsed_time": "20:51:51", "remaining_time": "11:54:55", "throughput": 553.61, "total_tokens": 41582000} {"current_steps": 25465, "total_steps": 40000, "loss": 0.1378, "lr": 1.4597741170840914e-05, "epoch": 1.1527875234840081, "percentage": 63.66, "elapsed_time": "20:51:54", "remaining_time": "11:54:33", "throughput": 553.69, "total_tokens": 41590224} {"current_steps": 25470, "total_steps": 40000, "loss": 0.1063, "lr": 1.4588814712775853e-05, "epoch": 1.1530138753706511, "percentage": 63.68, "elapsed_time": "20:51:57", "remaining_time": "11:54:12", "throughput": 553.78, "total_tokens": 41598224} {"current_steps": 25475, "total_steps": 40000, "loss": 0.1118, "lr": 1.4579889860246382e-05, "epoch": 1.1532402272572941, "percentage": 63.69, "elapsed_time": "20:52:00", "remaining_time": "11:53:51", "throughput": 553.86, "total_tokens": 41606576} {"current_steps": 25480, "total_steps": 40000, "loss": 0.1049, "lr": 1.457096661462885e-05, "epoch": 1.1534665791439371, "percentage": 63.7, "elapsed_time": "20:52:03", "remaining_time": "11:53:29", "throughput": 553.94, "total_tokens": 41614160} {"current_steps": 25485, "total_steps": 40000, "loss": 0.1602, "lr": 1.4562044977299322e-05, "epoch": 1.1536929310305801, "percentage": 63.71, "elapsed_time": "20:52:06", "remaining_time": "11:53:08", "throughput": 554.02, "total_tokens": 41621648} {"current_steps": 25490, "total_steps": 40000, "loss": 0.1261, "lr": 1.4553124949633623e-05, "epoch": 1.1539192829172231, "percentage": 63.73, "elapsed_time": "20:52:09", "remaining_time": "11:52:47", "throughput": 554.11, "total_tokens": 41629936} {"current_steps": 25495, "total_steps": 40000, "loss": 0.1687, "lr": 1.4544206533007354e-05, "epoch": 1.1541456348038661, "percentage": 63.74, "elapsed_time": "20:52:13", "remaining_time": "11:52:25", "throughput": 554.19, "total_tokens": 41638224} {"current_steps": 25500, "total_steps": 40000, "loss": 0.1324, "lr": 1.4535289728795821e-05, "epoch": 1.154371986690509, "percentage": 63.75, "elapsed_time": "20:52:16", "remaining_time": "11:52:04", "throughput": 554.28, "total_tokens": 41646832} {"current_steps": 25505, "total_steps": 40000, "loss": 0.084, "lr": 1.4526374538374132e-05, "epoch": 1.154598338577152, "percentage": 63.76, "elapsed_time": "20:52:19", "remaining_time": "11:51:43", "throughput": 554.38, "total_tokens": 41655632} {"current_steps": 25510, "total_steps": 40000, "loss": 0.1289, "lr": 1.4517460963117097e-05, "epoch": 1.154824690463795, "percentage": 63.78, "elapsed_time": "20:52:22", "remaining_time": "11:51:22", "throughput": 554.46, "total_tokens": 41663856} {"current_steps": 25515, "total_steps": 40000, "loss": 0.0807, "lr": 1.4508549004399314e-05, "epoch": 1.155051042350438, "percentage": 63.79, "elapsed_time": "20:52:26", "remaining_time": "11:51:00", "throughput": 554.55, "total_tokens": 41672080} {"current_steps": 25520, "total_steps": 40000, "loss": 0.1093, "lr": 1.449963866359513e-05, "epoch": 1.155277394237081, "percentage": 63.8, "elapsed_time": "20:52:29", "remaining_time": "11:50:39", "throughput": 554.64, "total_tokens": 41680560} {"current_steps": 25525, "total_steps": 40000, "loss": 0.1536, "lr": 1.4490729942078607e-05, "epoch": 1.1555037461237239, "percentage": 63.81, "elapsed_time": "20:52:32", "remaining_time": "11:50:18", "throughput": 554.72, "total_tokens": 41689008} {"current_steps": 25530, "total_steps": 40000, "loss": 0.0962, "lr": 1.4481822841223608e-05, "epoch": 1.1557300980103669, "percentage": 63.82, "elapsed_time": "20:52:35", "remaining_time": "11:49:57", "throughput": 554.82, "total_tokens": 41697584} {"current_steps": 25535, "total_steps": 40000, "loss": 0.1537, "lr": 1.4472917362403704e-05, "epoch": 1.1559564498970099, "percentage": 63.84, "elapsed_time": "20:52:39", "remaining_time": "11:49:35", "throughput": 554.9, "total_tokens": 41705840} {"current_steps": 25540, "total_steps": 40000, "loss": 0.1537, "lr": 1.4464013506992224e-05, "epoch": 1.1561828017836528, "percentage": 63.85, "elapsed_time": "20:52:42", "remaining_time": "11:49:14", "throughput": 554.99, "total_tokens": 41713968} {"current_steps": 25545, "total_steps": 40000, "loss": 0.1355, "lr": 1.4455111276362277e-05, "epoch": 1.1564091536702958, "percentage": 63.86, "elapsed_time": "20:52:45", "remaining_time": "11:48:53", "throughput": 555.07, "total_tokens": 41722064} {"current_steps": 25550, "total_steps": 40000, "loss": 0.1682, "lr": 1.4446210671886676e-05, "epoch": 1.1566355055569388, "percentage": 63.88, "elapsed_time": "20:52:48", "remaining_time": "11:48:32", "throughput": 555.16, "total_tokens": 41730384} {"current_steps": 25555, "total_steps": 40000, "loss": 0.1709, "lr": 1.4437311694938015e-05, "epoch": 1.1568618574435818, "percentage": 63.89, "elapsed_time": "20:52:51", "remaining_time": "11:48:10", "throughput": 555.24, "total_tokens": 41738256} {"current_steps": 25560, "total_steps": 40000, "loss": 0.1335, "lr": 1.442841434688864e-05, "epoch": 1.1570882093302248, "percentage": 63.9, "elapsed_time": "20:52:54", "remaining_time": "11:47:49", "throughput": 555.32, "total_tokens": 41746384} {"current_steps": 25565, "total_steps": 40000, "loss": 0.1458, "lr": 1.4419518629110615e-05, "epoch": 1.1573145612168678, "percentage": 63.91, "elapsed_time": "20:52:57", "remaining_time": "11:47:28", "throughput": 555.41, "total_tokens": 41754384} {"current_steps": 25570, "total_steps": 40000, "loss": 0.05, "lr": 1.4410624542975778e-05, "epoch": 1.1575409131035106, "percentage": 63.92, "elapsed_time": "20:53:01", "remaining_time": "11:47:07", "throughput": 555.5, "total_tokens": 41762800} {"current_steps": 25575, "total_steps": 40000, "loss": 0.1408, "lr": 1.4401732089855724e-05, "epoch": 1.1577672649901536, "percentage": 63.94, "elapsed_time": "20:53:04", "remaining_time": "11:46:46", "throughput": 555.58, "total_tokens": 41770864} {"current_steps": 25580, "total_steps": 40000, "loss": 0.131, "lr": 1.4392841271121754e-05, "epoch": 1.1579936168767966, "percentage": 63.95, "elapsed_time": "20:53:07", "remaining_time": "11:46:24", "throughput": 555.67, "total_tokens": 41779792} {"current_steps": 25585, "total_steps": 40000, "loss": 0.1475, "lr": 1.438395208814497e-05, "epoch": 1.1582199687634396, "percentage": 63.96, "elapsed_time": "20:53:10", "remaining_time": "11:46:03", "throughput": 555.76, "total_tokens": 41787856} {"current_steps": 25590, "total_steps": 40000, "loss": 0.1032, "lr": 1.4375064542296174e-05, "epoch": 1.1584463206500826, "percentage": 63.98, "elapsed_time": "20:53:14", "remaining_time": "11:45:42", "throughput": 555.84, "total_tokens": 41796208} {"current_steps": 25595, "total_steps": 40000, "loss": 0.1125, "lr": 1.4366178634945946e-05, "epoch": 1.1586726725367256, "percentage": 63.99, "elapsed_time": "20:53:17", "remaining_time": "11:45:21", "throughput": 555.92, "total_tokens": 41803952} {"current_steps": 25600, "total_steps": 40000, "loss": 0.1713, "lr": 1.4357294367464616e-05, "epoch": 1.1588990244233686, "percentage": 64.0, "elapsed_time": "20:53:20", "remaining_time": "11:45:00", "throughput": 556.02, "total_tokens": 41813008} {"current_steps": 25600, "total_steps": 40000, "eval_loss": 0.12351647019386292, "epoch": 1.1588990244233686, "percentage": 64.0, "elapsed_time": "21:01:03", "remaining_time": "11:49:20", "throughput": 552.62, "total_tokens": 41813008} {"current_steps": 25605, "total_steps": 40000, "loss": 0.1147, "lr": 1.434841174122224e-05, "epoch": 1.1591253763100116, "percentage": 64.01, "elapsed_time": "21:01:07", "remaining_time": "11:48:59", "throughput": 552.69, "total_tokens": 41820688} {"current_steps": 25610, "total_steps": 40000, "loss": 0.1185, "lr": 1.4339530757588615e-05, "epoch": 1.1593517281966546, "percentage": 64.03, "elapsed_time": "21:01:10", "remaining_time": "11:48:38", "throughput": 552.77, "total_tokens": 41828848} {"current_steps": 25615, "total_steps": 40000, "loss": 0.1016, "lr": 1.433065141793333e-05, "epoch": 1.1595780800832975, "percentage": 64.04, "elapsed_time": "21:01:13", "remaining_time": "11:48:17", "throughput": 552.86, "total_tokens": 41836688} {"current_steps": 25620, "total_steps": 40000, "loss": 0.1552, "lr": 1.4321773723625665e-05, "epoch": 1.1598044319699405, "percentage": 64.05, "elapsed_time": "21:01:17", "remaining_time": "11:47:56", "throughput": 552.95, "total_tokens": 41845872} {"current_steps": 25625, "total_steps": 40000, "loss": 0.1222, "lr": 1.4312897676034693e-05, "epoch": 1.1600307838565835, "percentage": 64.06, "elapsed_time": "21:01:20", "remaining_time": "11:47:34", "throughput": 553.03, "total_tokens": 41853648} {"current_steps": 25630, "total_steps": 40000, "loss": 0.1259, "lr": 1.4304023276529188e-05, "epoch": 1.1602571357432265, "percentage": 64.08, "elapsed_time": "21:01:23", "remaining_time": "11:47:13", "throughput": 553.11, "total_tokens": 41861136} {"current_steps": 25635, "total_steps": 40000, "loss": 0.1097, "lr": 1.4295150526477712e-05, "epoch": 1.1604834876298693, "percentage": 64.09, "elapsed_time": "21:01:26", "remaining_time": "11:46:52", "throughput": 553.2, "total_tokens": 41869776} {"current_steps": 25640, "total_steps": 40000, "loss": 0.1229, "lr": 1.4286279427248562e-05, "epoch": 1.1607098395165123, "percentage": 64.1, "elapsed_time": "21:01:29", "remaining_time": "11:46:30", "throughput": 553.27, "total_tokens": 41877040} {"current_steps": 25645, "total_steps": 40000, "loss": 0.1575, "lr": 1.4277409980209747e-05, "epoch": 1.1609361914031553, "percentage": 64.11, "elapsed_time": "21:01:32", "remaining_time": "11:46:09", "throughput": 553.35, "total_tokens": 41884592} {"current_steps": 25650, "total_steps": 40000, "loss": 0.1307, "lr": 1.4268542186729061e-05, "epoch": 1.1611625432897983, "percentage": 64.12, "elapsed_time": "21:01:36", "remaining_time": "11:45:48", "throughput": 553.43, "total_tokens": 41892688} {"current_steps": 25655, "total_steps": 40000, "loss": 0.0734, "lr": 1.4259676048174043e-05, "epoch": 1.1613888951764413, "percentage": 64.14, "elapsed_time": "21:01:39", "remaining_time": "11:45:27", "throughput": 553.51, "total_tokens": 41900528} {"current_steps": 25660, "total_steps": 40000, "loss": 0.1533, "lr": 1.4250811565911937e-05, "epoch": 1.1616152470630843, "percentage": 64.15, "elapsed_time": "21:01:42", "remaining_time": "11:45:05", "throughput": 553.59, "total_tokens": 41908208} {"current_steps": 25665, "total_steps": 40000, "loss": 0.1091, "lr": 1.4241948741309782e-05, "epoch": 1.1618415989497273, "percentage": 64.16, "elapsed_time": "21:01:45", "remaining_time": "11:44:44", "throughput": 553.67, "total_tokens": 41916016} {"current_steps": 25670, "total_steps": 40000, "loss": 0.1267, "lr": 1.4233087575734317e-05, "epoch": 1.1620679508363703, "percentage": 64.18, "elapsed_time": "21:01:48", "remaining_time": "11:44:23", "throughput": 553.76, "total_tokens": 41924272} {"current_steps": 25675, "total_steps": 40000, "loss": 0.0902, "lr": 1.422422807055206e-05, "epoch": 1.1622943027230133, "percentage": 64.19, "elapsed_time": "21:01:51", "remaining_time": "11:44:02", "throughput": 553.84, "total_tokens": 41932592} {"current_steps": 25680, "total_steps": 40000, "loss": 0.0636, "lr": 1.4215370227129243e-05, "epoch": 1.1625206546096563, "percentage": 64.2, "elapsed_time": "21:01:54", "remaining_time": "11:43:41", "throughput": 553.93, "total_tokens": 41940688} {"current_steps": 25685, "total_steps": 40000, "loss": 0.1067, "lr": 1.4206514046831876e-05, "epoch": 1.162747006496299, "percentage": 64.21, "elapsed_time": "21:01:58", "remaining_time": "11:43:19", "throughput": 554.01, "total_tokens": 41948240} {"current_steps": 25690, "total_steps": 40000, "loss": 0.1646, "lr": 1.419765953102567e-05, "epoch": 1.162973358382942, "percentage": 64.22, "elapsed_time": "21:02:01", "remaining_time": "11:42:58", "throughput": 554.09, "total_tokens": 41956528} {"current_steps": 25695, "total_steps": 40000, "loss": 0.0983, "lr": 1.4188806681076125e-05, "epoch": 1.163199710269585, "percentage": 64.24, "elapsed_time": "21:02:04", "remaining_time": "11:42:37", "throughput": 554.18, "total_tokens": 41964944} {"current_steps": 25700, "total_steps": 40000, "loss": 0.1088, "lr": 1.4179955498348443e-05, "epoch": 1.163426062156228, "percentage": 64.25, "elapsed_time": "21:02:07", "remaining_time": "11:42:16", "throughput": 554.26, "total_tokens": 41972976} {"current_steps": 25705, "total_steps": 40000, "loss": 0.1046, "lr": 1.4171105984207605e-05, "epoch": 1.163652414042871, "percentage": 64.26, "elapsed_time": "21:02:10", "remaining_time": "11:41:55", "throughput": 554.34, "total_tokens": 41980912} {"current_steps": 25710, "total_steps": 40000, "loss": 0.1184, "lr": 1.4162258140018304e-05, "epoch": 1.163878765929514, "percentage": 64.28, "elapsed_time": "21:02:14", "remaining_time": "11:41:34", "throughput": 554.43, "total_tokens": 41989104} {"current_steps": 25715, "total_steps": 40000, "loss": 0.1328, "lr": 1.4153411967144986e-05, "epoch": 1.164105117816157, "percentage": 64.29, "elapsed_time": "21:02:17", "remaining_time": "11:41:12", "throughput": 554.51, "total_tokens": 41997296} {"current_steps": 25720, "total_steps": 40000, "loss": 0.1045, "lr": 1.4144567466951864e-05, "epoch": 1.1643314697028, "percentage": 64.3, "elapsed_time": "21:02:20", "remaining_time": "11:40:51", "throughput": 554.6, "total_tokens": 42005392} {"current_steps": 25725, "total_steps": 40000, "loss": 0.1313, "lr": 1.4135724640802844e-05, "epoch": 1.164557821589443, "percentage": 64.31, "elapsed_time": "21:02:23", "remaining_time": "11:40:30", "throughput": 554.69, "total_tokens": 42013904} {"current_steps": 25730, "total_steps": 40000, "loss": 0.1376, "lr": 1.4126883490061615e-05, "epoch": 1.164784173476086, "percentage": 64.33, "elapsed_time": "21:02:26", "remaining_time": "11:40:09", "throughput": 554.78, "total_tokens": 42022896} {"current_steps": 25735, "total_steps": 40000, "loss": 0.0949, "lr": 1.4118044016091603e-05, "epoch": 1.165010525362729, "percentage": 64.34, "elapsed_time": "21:02:30", "remaining_time": "11:39:48", "throughput": 554.87, "total_tokens": 42031568} {"current_steps": 25740, "total_steps": 40000, "loss": 0.1489, "lr": 1.410920622025594e-05, "epoch": 1.165236877249372, "percentage": 64.35, "elapsed_time": "21:02:33", "remaining_time": "11:39:27", "throughput": 554.95, "total_tokens": 42039536} {"current_steps": 25745, "total_steps": 40000, "loss": 0.1507, "lr": 1.4100370103917554e-05, "epoch": 1.165463229136015, "percentage": 64.36, "elapsed_time": "21:02:36", "remaining_time": "11:39:06", "throughput": 555.04, "total_tokens": 42047728} {"current_steps": 25750, "total_steps": 40000, "loss": 0.1168, "lr": 1.409153566843907e-05, "epoch": 1.1656895810226577, "percentage": 64.38, "elapsed_time": "21:02:39", "remaining_time": "11:38:45", "throughput": 555.12, "total_tokens": 42056048} {"current_steps": 25755, "total_steps": 40000, "loss": 0.1383, "lr": 1.408270291518286e-05, "epoch": 1.1659159329093007, "percentage": 64.39, "elapsed_time": "21:02:42", "remaining_time": "11:38:24", "throughput": 555.2, "total_tokens": 42063696} {"current_steps": 25760, "total_steps": 40000, "loss": 0.1127, "lr": 1.407387184551107e-05, "epoch": 1.1661422847959437, "percentage": 64.4, "elapsed_time": "21:02:46", "remaining_time": "11:38:03", "throughput": 555.29, "total_tokens": 42071760} {"current_steps": 25765, "total_steps": 40000, "loss": 0.1632, "lr": 1.4065042460785532e-05, "epoch": 1.1663686366825867, "percentage": 64.41, "elapsed_time": "21:02:49", "remaining_time": "11:37:42", "throughput": 555.37, "total_tokens": 42079760} {"current_steps": 25770, "total_steps": 40000, "loss": 0.115, "lr": 1.405621476236787e-05, "epoch": 1.1665949885692297, "percentage": 64.42, "elapsed_time": "21:02:52", "remaining_time": "11:37:20", "throughput": 555.46, "total_tokens": 42088304} {"current_steps": 25775, "total_steps": 40000, "loss": 0.1306, "lr": 1.4047388751619423e-05, "epoch": 1.1668213404558727, "percentage": 64.44, "elapsed_time": "21:02:55", "remaining_time": "11:36:59", "throughput": 555.54, "total_tokens": 42096752} {"current_steps": 25780, "total_steps": 40000, "loss": 0.0932, "lr": 1.4038564429901264e-05, "epoch": 1.1670476923425157, "percentage": 64.45, "elapsed_time": "21:02:58", "remaining_time": "11:36:38", "throughput": 555.63, "total_tokens": 42105264} {"current_steps": 25785, "total_steps": 40000, "loss": 0.1232, "lr": 1.4029741798574227e-05, "epoch": 1.1672740442291587, "percentage": 64.46, "elapsed_time": "21:03:02", "remaining_time": "11:36:17", "throughput": 555.71, "total_tokens": 42113136} {"current_steps": 25790, "total_steps": 40000, "loss": 0.1372, "lr": 1.402092085899886e-05, "epoch": 1.1675003961158017, "percentage": 64.48, "elapsed_time": "21:03:05", "remaining_time": "11:35:56", "throughput": 555.8, "total_tokens": 42121264} {"current_steps": 25795, "total_steps": 40000, "loss": 0.1244, "lr": 1.4012101612535464e-05, "epoch": 1.1677267480024447, "percentage": 64.49, "elapsed_time": "21:03:08", "remaining_time": "11:35:35", "throughput": 555.88, "total_tokens": 42129488} {"current_steps": 25800, "total_steps": 40000, "loss": 0.088, "lr": 1.4003284060544092e-05, "epoch": 1.1679530998890875, "percentage": 64.5, "elapsed_time": "21:03:11", "remaining_time": "11:35:14", "throughput": 555.97, "total_tokens": 42137552} {"current_steps": 25800, "total_steps": 40000, "eval_loss": 0.12347038090229034, "epoch": 1.1679530998890875, "percentage": 64.5, "elapsed_time": "21:10:54", "remaining_time": "11:39:29", "throughput": 552.59, "total_tokens": 42137552} {"current_steps": 25805, "total_steps": 40000, "loss": 0.1069, "lr": 1.3994468204384504e-05, "epoch": 1.1681794517757305, "percentage": 64.51, "elapsed_time": "21:10:58", "remaining_time": "11:39:08", "throughput": 552.68, "total_tokens": 42146512} {"current_steps": 25810, "total_steps": 40000, "loss": 0.1593, "lr": 1.398565404541622e-05, "epoch": 1.1684058036623735, "percentage": 64.53, "elapsed_time": "21:11:01", "remaining_time": "11:38:47", "throughput": 552.76, "total_tokens": 42154608} {"current_steps": 25815, "total_steps": 40000, "loss": 0.1559, "lr": 1.3976841584998513e-05, "epoch": 1.1686321555490164, "percentage": 64.54, "elapsed_time": "21:11:04", "remaining_time": "11:38:26", "throughput": 552.84, "total_tokens": 42162320} {"current_steps": 25820, "total_steps": 40000, "loss": 0.1055, "lr": 1.3968030824490352e-05, "epoch": 1.1688585074356594, "percentage": 64.55, "elapsed_time": "21:11:07", "remaining_time": "11:38:05", "throughput": 552.92, "total_tokens": 42170416} {"current_steps": 25825, "total_steps": 40000, "loss": 0.1443, "lr": 1.3959221765250469e-05, "epoch": 1.1690848593223024, "percentage": 64.56, "elapsed_time": "21:11:11", "remaining_time": "11:37:44", "throughput": 553.01, "total_tokens": 42178992} {"current_steps": 25830, "total_steps": 40000, "loss": 0.1471, "lr": 1.3950414408637343e-05, "epoch": 1.1693112112089454, "percentage": 64.58, "elapsed_time": "21:11:14", "remaining_time": "11:37:23", "throughput": 553.1, "total_tokens": 42187472} {"current_steps": 25835, "total_steps": 40000, "loss": 0.1111, "lr": 1.3941608756009166e-05, "epoch": 1.1695375630955884, "percentage": 64.59, "elapsed_time": "21:11:17", "remaining_time": "11:37:02", "throughput": 553.18, "total_tokens": 42195632} {"current_steps": 25840, "total_steps": 40000, "loss": 0.1552, "lr": 1.3932804808723898e-05, "epoch": 1.1697639149822314, "percentage": 64.6, "elapsed_time": "21:11:20", "remaining_time": "11:36:40", "throughput": 553.27, "total_tokens": 42204144} {"current_steps": 25845, "total_steps": 40000, "loss": 0.1542, "lr": 1.3924002568139194e-05, "epoch": 1.1699902668688744, "percentage": 64.61, "elapsed_time": "21:11:24", "remaining_time": "11:36:19", "throughput": 553.35, "total_tokens": 42212112} {"current_steps": 25850, "total_steps": 40000, "loss": 0.1404, "lr": 1.3915202035612485e-05, "epoch": 1.1702166187555174, "percentage": 64.62, "elapsed_time": "21:11:27", "remaining_time": "11:35:58", "throughput": 553.44, "total_tokens": 42220048} {"current_steps": 25855, "total_steps": 40000, "loss": 0.1109, "lr": 1.3906403212500935e-05, "epoch": 1.1704429706421604, "percentage": 64.64, "elapsed_time": "21:11:30", "remaining_time": "11:35:37", "throughput": 553.52, "total_tokens": 42228048} {"current_steps": 25860, "total_steps": 40000, "loss": 0.1295, "lr": 1.3897606100161409e-05, "epoch": 1.1706693225288034, "percentage": 64.65, "elapsed_time": "21:11:33", "remaining_time": "11:35:16", "throughput": 553.6, "total_tokens": 42236144} {"current_steps": 25865, "total_steps": 40000, "loss": 0.0837, "lr": 1.388881069995055e-05, "epoch": 1.1708956744154462, "percentage": 64.66, "elapsed_time": "21:11:36", "remaining_time": "11:34:55", "throughput": 553.68, "total_tokens": 42243824} {"current_steps": 25870, "total_steps": 40000, "loss": 0.0977, "lr": 1.3880017013224708e-05, "epoch": 1.1711220263020892, "percentage": 64.68, "elapsed_time": "21:11:39", "remaining_time": "11:34:34", "throughput": 553.76, "total_tokens": 42251696} {"current_steps": 25875, "total_steps": 40000, "loss": 0.0993, "lr": 1.3871225041339984e-05, "epoch": 1.1713483781887322, "percentage": 64.69, "elapsed_time": "21:11:42", "remaining_time": "11:34:13", "throughput": 553.84, "total_tokens": 42259760} {"current_steps": 25880, "total_steps": 40000, "loss": 0.1074, "lr": 1.386243478565222e-05, "epoch": 1.1715747300753752, "percentage": 64.7, "elapsed_time": "21:11:46", "remaining_time": "11:33:52", "throughput": 553.93, "total_tokens": 42268144} {"current_steps": 25885, "total_steps": 40000, "loss": 0.1288, "lr": 1.3853646247516966e-05, "epoch": 1.1718010819620182, "percentage": 64.71, "elapsed_time": "21:11:49", "remaining_time": "11:33:31", "throughput": 554.01, "total_tokens": 42275792} {"current_steps": 25890, "total_steps": 40000, "loss": 0.1386, "lr": 1.3844859428289545e-05, "epoch": 1.1720274338486611, "percentage": 64.72, "elapsed_time": "21:11:52", "remaining_time": "11:33:10", "throughput": 554.09, "total_tokens": 42284240} {"current_steps": 25895, "total_steps": 40000, "loss": 0.1462, "lr": 1.3836074329324984e-05, "epoch": 1.1722537857353041, "percentage": 64.74, "elapsed_time": "21:11:55", "remaining_time": "11:32:49", "throughput": 554.18, "total_tokens": 42292336} {"current_steps": 25900, "total_steps": 40000, "loss": 0.1123, "lr": 1.3827290951978044e-05, "epoch": 1.1724801376219471, "percentage": 64.75, "elapsed_time": "21:11:58", "remaining_time": "11:32:28", "throughput": 554.26, "total_tokens": 42300464} {"current_steps": 25905, "total_steps": 40000, "loss": 0.1307, "lr": 1.381850929760326e-05, "epoch": 1.1727064895085901, "percentage": 64.76, "elapsed_time": "21:12:01", "remaining_time": "11:32:07", "throughput": 554.35, "total_tokens": 42309072} {"current_steps": 25910, "total_steps": 40000, "loss": 0.1057, "lr": 1.3809729367554842e-05, "epoch": 1.172932841395233, "percentage": 64.78, "elapsed_time": "21:12:05", "remaining_time": "11:31:46", "throughput": 554.44, "total_tokens": 42317488} {"current_steps": 25915, "total_steps": 40000, "loss": 0.1255, "lr": 1.3800951163186784e-05, "epoch": 1.173159193281876, "percentage": 64.79, "elapsed_time": "21:12:08", "remaining_time": "11:31:25", "throughput": 554.52, "total_tokens": 42325520} {"current_steps": 25920, "total_steps": 40000, "loss": 0.1183, "lr": 1.3792174685852801e-05, "epoch": 1.173385545168519, "percentage": 64.8, "elapsed_time": "21:12:11", "remaining_time": "11:31:04", "throughput": 554.6, "total_tokens": 42333680} {"current_steps": 25925, "total_steps": 40000, "loss": 0.1485, "lr": 1.378339993690632e-05, "epoch": 1.173611897055162, "percentage": 64.81, "elapsed_time": "21:12:14", "remaining_time": "11:30:43", "throughput": 554.68, "total_tokens": 42341296} {"current_steps": 25930, "total_steps": 40000, "loss": 0.082, "lr": 1.3774626917700523e-05, "epoch": 1.1738382489418049, "percentage": 64.83, "elapsed_time": "21:12:17", "remaining_time": "11:30:22", "throughput": 554.76, "total_tokens": 42349040} {"current_steps": 25935, "total_steps": 40000, "loss": 0.1479, "lr": 1.3765855629588334e-05, "epoch": 1.1740646008284479, "percentage": 64.84, "elapsed_time": "21:12:21", "remaining_time": "11:30:01", "throughput": 554.85, "total_tokens": 42357456} {"current_steps": 25940, "total_steps": 40000, "loss": 0.1118, "lr": 1.3757086073922374e-05, "epoch": 1.1742909527150909, "percentage": 64.85, "elapsed_time": "21:12:24", "remaining_time": "11:29:40", "throughput": 554.93, "total_tokens": 42365744} {"current_steps": 25945, "total_steps": 40000, "loss": 0.1079, "lr": 1.3748318252055038e-05, "epoch": 1.1745173046017339, "percentage": 64.86, "elapsed_time": "21:12:27", "remaining_time": "11:29:19", "throughput": 555.02, "total_tokens": 42374000} {"current_steps": 25950, "total_steps": 40000, "loss": 0.0891, "lr": 1.3739552165338416e-05, "epoch": 1.1747436564883769, "percentage": 64.88, "elapsed_time": "21:12:30", "remaining_time": "11:28:58", "throughput": 555.1, "total_tokens": 42382256} {"current_steps": 25955, "total_steps": 40000, "loss": 0.1178, "lr": 1.3730787815124354e-05, "epoch": 1.1749700083750199, "percentage": 64.89, "elapsed_time": "21:12:33", "remaining_time": "11:28:37", "throughput": 555.18, "total_tokens": 42389936} {"current_steps": 25960, "total_steps": 40000, "loss": 0.0923, "lr": 1.3722025202764443e-05, "epoch": 1.1751963602616629, "percentage": 64.9, "elapsed_time": "21:12:36", "remaining_time": "11:28:16", "throughput": 555.26, "total_tokens": 42398256} {"current_steps": 25965, "total_steps": 40000, "loss": 0.119, "lr": 1.371326432960997e-05, "epoch": 1.1754227121483058, "percentage": 64.91, "elapsed_time": "21:12:40", "remaining_time": "11:27:55", "throughput": 555.35, "total_tokens": 42406192} {"current_steps": 25970, "total_steps": 40000, "loss": 0.1014, "lr": 1.3704505197011969e-05, "epoch": 1.1756490640349488, "percentage": 64.92, "elapsed_time": "21:12:43", "remaining_time": "11:27:34", "throughput": 555.43, "total_tokens": 42414256} {"current_steps": 25975, "total_steps": 40000, "loss": 0.1541, "lr": 1.3695747806321224e-05, "epoch": 1.1758754159215916, "percentage": 64.94, "elapsed_time": "21:12:46", "remaining_time": "11:27:13", "throughput": 555.52, "total_tokens": 42423152} {"current_steps": 25980, "total_steps": 40000, "loss": 0.1368, "lr": 1.3686992158888212e-05, "epoch": 1.1761017678082346, "percentage": 64.95, "elapsed_time": "21:12:49", "remaining_time": "11:26:52", "throughput": 555.6, "total_tokens": 42431216} {"current_steps": 25985, "total_steps": 40000, "loss": 0.0934, "lr": 1.367823825606319e-05, "epoch": 1.1763281196948776, "percentage": 64.96, "elapsed_time": "21:12:52", "remaining_time": "11:26:31", "throughput": 555.69, "total_tokens": 42439408} {"current_steps": 25990, "total_steps": 40000, "loss": 0.12, "lr": 1.36694860991961e-05, "epoch": 1.1765544715815206, "percentage": 64.98, "elapsed_time": "21:12:56", "remaining_time": "11:26:10", "throughput": 555.77, "total_tokens": 42447600} {"current_steps": 25995, "total_steps": 40000, "loss": 0.1178, "lr": 1.3660735689636636e-05, "epoch": 1.1767808234681636, "percentage": 64.99, "elapsed_time": "21:12:59", "remaining_time": "11:25:49", "throughput": 555.86, "total_tokens": 42455888} {"current_steps": 26000, "total_steps": 40000, "loss": 0.1092, "lr": 1.365198702873424e-05, "epoch": 1.1770071753548066, "percentage": 65.0, "elapsed_time": "21:13:02", "remaining_time": "11:25:28", "throughput": 555.94, "total_tokens": 42463856} {"current_steps": 26000, "total_steps": 40000, "eval_loss": 0.12338057160377502, "epoch": 1.1770071753548066, "percentage": 65.0, "elapsed_time": "21:20:45", "remaining_time": "11:29:38", "throughput": 552.59, "total_tokens": 42463856} {"current_steps": 26005, "total_steps": 40000, "loss": 0.1194, "lr": 1.364324011783804e-05, "epoch": 1.1772335272414496, "percentage": 65.01, "elapsed_time": "21:20:48", "remaining_time": "11:29:17", "throughput": 552.67, "total_tokens": 42471792} {"current_steps": 26010, "total_steps": 40000, "loss": 0.1213, "lr": 1.3634494958296934e-05, "epoch": 1.1774598791280926, "percentage": 65.03, "elapsed_time": "21:20:52", "remaining_time": "11:28:56", "throughput": 552.75, "total_tokens": 42479632} {"current_steps": 26015, "total_steps": 40000, "loss": 0.0784, "lr": 1.3625751551459542e-05, "epoch": 1.1776862310147356, "percentage": 65.04, "elapsed_time": "21:20:55", "remaining_time": "11:28:35", "throughput": 552.82, "total_tokens": 42487408} {"current_steps": 26020, "total_steps": 40000, "loss": 0.0788, "lr": 1.3617009898674188e-05, "epoch": 1.1779125829013786, "percentage": 65.05, "elapsed_time": "21:20:58", "remaining_time": "11:28:14", "throughput": 552.92, "total_tokens": 42496432} {"current_steps": 26025, "total_steps": 40000, "loss": 0.1168, "lr": 1.3608270001288967e-05, "epoch": 1.1781389347880213, "percentage": 65.06, "elapsed_time": "21:21:01", "remaining_time": "11:27:53", "throughput": 552.99, "total_tokens": 42503856} {"current_steps": 26030, "total_steps": 40000, "loss": 0.0855, "lr": 1.359953186065166e-05, "epoch": 1.1783652866746643, "percentage": 65.08, "elapsed_time": "21:21:04", "remaining_time": "11:27:32", "throughput": 553.07, "total_tokens": 42511440} {"current_steps": 26035, "total_steps": 40000, "loss": 0.1199, "lr": 1.3590795478109814e-05, "epoch": 1.1785916385613073, "percentage": 65.09, "elapsed_time": "21:21:07", "remaining_time": "11:27:11", "throughput": 553.15, "total_tokens": 42519312} {"current_steps": 26040, "total_steps": 40000, "loss": 0.0832, "lr": 1.3582060855010675e-05, "epoch": 1.1788179904479503, "percentage": 65.1, "elapsed_time": "21:21:11", "remaining_time": "11:26:50", "throughput": 553.23, "total_tokens": 42527472} {"current_steps": 26045, "total_steps": 40000, "loss": 0.1357, "lr": 1.3573327992701245e-05, "epoch": 1.1790443423345933, "percentage": 65.11, "elapsed_time": "21:21:14", "remaining_time": "11:26:29", "throughput": 553.31, "total_tokens": 42535504} {"current_steps": 26050, "total_steps": 40000, "loss": 0.1274, "lr": 1.356459689252823e-05, "epoch": 1.1792706942212363, "percentage": 65.12, "elapsed_time": "21:21:17", "remaining_time": "11:26:08", "throughput": 553.4, "total_tokens": 42544304} {"current_steps": 26055, "total_steps": 40000, "loss": 0.12, "lr": 1.3555867555838087e-05, "epoch": 1.1794970461078793, "percentage": 65.14, "elapsed_time": "21:21:20", "remaining_time": "11:25:47", "throughput": 553.48, "total_tokens": 42551984} {"current_steps": 26060, "total_steps": 40000, "loss": 0.1365, "lr": 1.3547139983976975e-05, "epoch": 1.1797233979945223, "percentage": 65.15, "elapsed_time": "21:21:23", "remaining_time": "11:25:26", "throughput": 553.57, "total_tokens": 42560432} {"current_steps": 26065, "total_steps": 40000, "loss": 0.1087, "lr": 1.3538414178290815e-05, "epoch": 1.1799497498811653, "percentage": 65.16, "elapsed_time": "21:21:27", "remaining_time": "11:25:05", "throughput": 553.66, "total_tokens": 42569232} {"current_steps": 26070, "total_steps": 40000, "loss": 0.1427, "lr": 1.3529690140125209e-05, "epoch": 1.1801761017678083, "percentage": 65.18, "elapsed_time": "21:21:30", "remaining_time": "11:24:44", "throughput": 553.74, "total_tokens": 42576912} {"current_steps": 26075, "total_steps": 40000, "loss": 0.1168, "lr": 1.352096787082553e-05, "epoch": 1.1804024536544513, "percentage": 65.19, "elapsed_time": "21:21:33", "remaining_time": "11:24:23", "throughput": 553.81, "total_tokens": 42584624} {"current_steps": 26080, "total_steps": 40000, "loss": 0.1368, "lr": 1.3512247371736871e-05, "epoch": 1.1806288055410943, "percentage": 65.2, "elapsed_time": "21:21:36", "remaining_time": "11:24:03", "throughput": 553.91, "total_tokens": 42593616} {"current_steps": 26085, "total_steps": 40000, "loss": 0.1326, "lr": 1.3503528644204022e-05, "epoch": 1.1808551574277373, "percentage": 65.21, "elapsed_time": "21:21:40", "remaining_time": "11:23:42", "throughput": 554.0, "total_tokens": 42602768} {"current_steps": 26090, "total_steps": 40000, "loss": 0.0985, "lr": 1.349481168957153e-05, "epoch": 1.18108150931438, "percentage": 65.22, "elapsed_time": "21:21:43", "remaining_time": "11:23:21", "throughput": 554.08, "total_tokens": 42610960} {"current_steps": 26095, "total_steps": 40000, "loss": 0.1257, "lr": 1.3486096509183665e-05, "epoch": 1.181307861201023, "percentage": 65.24, "elapsed_time": "21:21:46", "remaining_time": "11:23:00", "throughput": 554.17, "total_tokens": 42619120} {"current_steps": 26100, "total_steps": 40000, "loss": 0.17, "lr": 1.3477383104384406e-05, "epoch": 1.181534213087666, "percentage": 65.25, "elapsed_time": "21:21:50", "remaining_time": "11:22:39", "throughput": 554.24, "total_tokens": 42626960} {"current_steps": 26105, "total_steps": 40000, "loss": 0.1247, "lr": 1.3468671476517481e-05, "epoch": 1.181760564974309, "percentage": 65.26, "elapsed_time": "21:21:53", "remaining_time": "11:22:18", "throughput": 554.33, "total_tokens": 42635152} {"current_steps": 26110, "total_steps": 40000, "loss": 0.1226, "lr": 1.3459961626926326e-05, "epoch": 1.181986916860952, "percentage": 65.28, "elapsed_time": "21:21:56", "remaining_time": "11:21:57", "throughput": 554.42, "total_tokens": 42643632} {"current_steps": 26115, "total_steps": 40000, "loss": 0.1102, "lr": 1.3451253556954101e-05, "epoch": 1.182213268747595, "percentage": 65.29, "elapsed_time": "21:21:59", "remaining_time": "11:21:37", "throughput": 554.49, "total_tokens": 42651344} {"current_steps": 26120, "total_steps": 40000, "loss": 0.092, "lr": 1.3442547267943717e-05, "epoch": 1.182439620634238, "percentage": 65.3, "elapsed_time": "21:22:02", "remaining_time": "11:21:16", "throughput": 554.57, "total_tokens": 42659088} {"current_steps": 26125, "total_steps": 40000, "loss": 0.0911, "lr": 1.3433842761237774e-05, "epoch": 1.182665972520881, "percentage": 65.31, "elapsed_time": "21:22:05", "remaining_time": "11:20:55", "throughput": 554.66, "total_tokens": 42667632} {"current_steps": 26130, "total_steps": 40000, "loss": 0.1178, "lr": 1.3425140038178639e-05, "epoch": 1.182892324407524, "percentage": 65.33, "elapsed_time": "21:22:09", "remaining_time": "11:20:34", "throughput": 554.75, "total_tokens": 42676432} {"current_steps": 26135, "total_steps": 40000, "loss": 0.0867, "lr": 1.3416439100108358e-05, "epoch": 1.183118676294167, "percentage": 65.34, "elapsed_time": "21:22:12", "remaining_time": "11:20:13", "throughput": 554.84, "total_tokens": 42684752} {"current_steps": 26140, "total_steps": 40000, "loss": 0.145, "lr": 1.3407739948368734e-05, "epoch": 1.1833450281808098, "percentage": 65.35, "elapsed_time": "21:22:15", "remaining_time": "11:19:52", "throughput": 554.92, "total_tokens": 42693168} {"current_steps": 26145, "total_steps": 40000, "loss": 0.115, "lr": 1.3399042584301298e-05, "epoch": 1.1835713800674528, "percentage": 65.36, "elapsed_time": "21:22:18", "remaining_time": "11:19:32", "throughput": 555.01, "total_tokens": 42701456} {"current_steps": 26150, "total_steps": 40000, "loss": 0.0937, "lr": 1.3390347009247272e-05, "epoch": 1.1837977319540958, "percentage": 65.38, "elapsed_time": "21:22:21", "remaining_time": "11:19:11", "throughput": 555.09, "total_tokens": 42709744} {"current_steps": 26155, "total_steps": 40000, "loss": 0.1566, "lr": 1.3381653224547635e-05, "epoch": 1.1840240838407388, "percentage": 65.39, "elapsed_time": "21:22:25", "remaining_time": "11:18:50", "throughput": 555.18, "total_tokens": 42718096} {"current_steps": 26160, "total_steps": 40000, "loss": 0.1336, "lr": 1.3372961231543086e-05, "epoch": 1.1842504357273818, "percentage": 65.4, "elapsed_time": "21:22:28", "remaining_time": "11:18:29", "throughput": 555.26, "total_tokens": 42726000} {"current_steps": 26165, "total_steps": 40000, "loss": 0.1001, "lr": 1.3364271031574016e-05, "epoch": 1.1844767876140248, "percentage": 65.41, "elapsed_time": "21:22:31", "remaining_time": "11:18:08", "throughput": 555.35, "total_tokens": 42734928} {"current_steps": 26170, "total_steps": 40000, "loss": 0.1069, "lr": 1.335558262598059e-05, "epoch": 1.1847031395006677, "percentage": 65.42, "elapsed_time": "21:22:34", "remaining_time": "11:17:48", "throughput": 555.43, "total_tokens": 42743280} {"current_steps": 26175, "total_steps": 40000, "loss": 0.1309, "lr": 1.3346896016102645e-05, "epoch": 1.1849294913873107, "percentage": 65.44, "elapsed_time": "21:22:38", "remaining_time": "11:17:27", "throughput": 555.52, "total_tokens": 42751664} {"current_steps": 26180, "total_steps": 40000, "loss": 0.1188, "lr": 1.3338211203279788e-05, "epoch": 1.1851558432739537, "percentage": 65.45, "elapsed_time": "21:22:41", "remaining_time": "11:17:06", "throughput": 555.62, "total_tokens": 42761104} {"current_steps": 26185, "total_steps": 40000, "loss": 0.1892, "lr": 1.3329528188851303e-05, "epoch": 1.1853821951605967, "percentage": 65.46, "elapsed_time": "21:22:44", "remaining_time": "11:16:45", "throughput": 555.69, "total_tokens": 42768720} {"current_steps": 26190, "total_steps": 40000, "loss": 0.1578, "lr": 1.3320846974156242e-05, "epoch": 1.1856085470472397, "percentage": 65.48, "elapsed_time": "21:22:47", "remaining_time": "11:16:25", "throughput": 555.78, "total_tokens": 42776976} {"current_steps": 26195, "total_steps": 40000, "loss": 0.111, "lr": 1.3312167560533337e-05, "epoch": 1.1858348989338827, "percentage": 65.49, "elapsed_time": "21:22:51", "remaining_time": "11:16:04", "throughput": 555.86, "total_tokens": 42784816} {"current_steps": 26200, "total_steps": 40000, "loss": 0.0912, "lr": 1.3303489949321082e-05, "epoch": 1.1860612508205255, "percentage": 65.5, "elapsed_time": "21:22:54", "remaining_time": "11:15:43", "throughput": 555.94, "total_tokens": 42792816} {"current_steps": 26200, "total_steps": 40000, "eval_loss": 0.12338324636220932, "epoch": 1.1860612508205255, "percentage": 65.5, "elapsed_time": "21:30:36", "remaining_time": "11:19:47", "throughput": 552.62, "total_tokens": 42792816} {"current_steps": 26205, "total_steps": 40000, "loss": 0.0889, "lr": 1.3294814141857653e-05, "epoch": 1.1862876027071685, "percentage": 65.51, "elapsed_time": "21:30:42", "remaining_time": "11:19:27", "throughput": 552.68, "total_tokens": 42800560} {"current_steps": 26210, "total_steps": 40000, "loss": 0.1369, "lr": 1.3286140139480992e-05, "epoch": 1.1865139545938115, "percentage": 65.53, "elapsed_time": "21:30:45", "remaining_time": "11:19:06", "throughput": 552.76, "total_tokens": 42808496} {"current_steps": 26215, "total_steps": 40000, "loss": 0.0967, "lr": 1.3277467943528719e-05, "epoch": 1.1867403064804545, "percentage": 65.54, "elapsed_time": "21:30:48", "remaining_time": "11:18:45", "throughput": 552.84, "total_tokens": 42816400} {"current_steps": 26220, "total_steps": 40000, "loss": 0.1197, "lr": 1.3268797555338203e-05, "epoch": 1.1869666583670975, "percentage": 65.55, "elapsed_time": "21:30:51", "remaining_time": "11:18:24", "throughput": 552.92, "total_tokens": 42824688} {"current_steps": 26225, "total_steps": 40000, "loss": 0.0909, "lr": 1.3260128976246533e-05, "epoch": 1.1871930102537405, "percentage": 65.56, "elapsed_time": "21:30:54", "remaining_time": "11:18:03", "throughput": 553.01, "total_tokens": 42832816} {"current_steps": 26230, "total_steps": 40000, "loss": 0.1563, "lr": 1.32514622075905e-05, "epoch": 1.1874193621403835, "percentage": 65.58, "elapsed_time": "21:30:57", "remaining_time": "11:17:43", "throughput": 553.09, "total_tokens": 42840880} {"current_steps": 26235, "total_steps": 40000, "loss": 0.1631, "lr": 1.3242797250706638e-05, "epoch": 1.1876457140270265, "percentage": 65.59, "elapsed_time": "21:31:00", "remaining_time": "11:17:22", "throughput": 553.16, "total_tokens": 42848464} {"current_steps": 26240, "total_steps": 40000, "loss": 0.1392, "lr": 1.3234134106931195e-05, "epoch": 1.1878720659136695, "percentage": 65.6, "elapsed_time": "21:31:03", "remaining_time": "11:17:01", "throughput": 553.24, "total_tokens": 42856400} {"current_steps": 26245, "total_steps": 40000, "loss": 0.1057, "lr": 1.322547277760013e-05, "epoch": 1.1880984178003124, "percentage": 65.61, "elapsed_time": "21:31:07", "remaining_time": "11:16:40", "throughput": 553.33, "total_tokens": 42865136} {"current_steps": 26250, "total_steps": 40000, "loss": 0.111, "lr": 1.3216813264049132e-05, "epoch": 1.1883247696869552, "percentage": 65.62, "elapsed_time": "21:31:10", "remaining_time": "11:16:19", "throughput": 553.42, "total_tokens": 42873424} {"current_steps": 26255, "total_steps": 40000, "loss": 0.1649, "lr": 1.32081555676136e-05, "epoch": 1.1885511215735982, "percentage": 65.64, "elapsed_time": "21:31:13", "remaining_time": "11:15:58", "throughput": 553.5, "total_tokens": 42881648} {"current_steps": 26260, "total_steps": 40000, "loss": 0.1386, "lr": 1.3199499689628674e-05, "epoch": 1.1887774734602412, "percentage": 65.65, "elapsed_time": "21:31:16", "remaining_time": "11:15:38", "throughput": 553.58, "total_tokens": 42889520} {"current_steps": 26265, "total_steps": 40000, "loss": 0.0792, "lr": 1.3190845631429192e-05, "epoch": 1.1890038253468842, "percentage": 65.66, "elapsed_time": "21:31:20", "remaining_time": "11:15:17", "throughput": 553.67, "total_tokens": 42898064} {"current_steps": 26270, "total_steps": 40000, "loss": 0.1783, "lr": 1.3182193394349704e-05, "epoch": 1.1892301772335272, "percentage": 65.67, "elapsed_time": "21:31:23", "remaining_time": "11:14:56", "throughput": 553.75, "total_tokens": 42906320} {"current_steps": 26275, "total_steps": 40000, "loss": 0.1319, "lr": 1.3173542979724507e-05, "epoch": 1.1894565291201702, "percentage": 65.69, "elapsed_time": "21:31:26", "remaining_time": "11:14:35", "throughput": 553.84, "total_tokens": 42914768} {"current_steps": 26280, "total_steps": 40000, "loss": 0.0628, "lr": 1.3164894388887617e-05, "epoch": 1.1896828810068132, "percentage": 65.7, "elapsed_time": "21:31:29", "remaining_time": "11:14:15", "throughput": 553.91, "total_tokens": 42922480} {"current_steps": 26285, "total_steps": 40000, "loss": 0.1203, "lr": 1.3156247623172727e-05, "epoch": 1.1899092328934562, "percentage": 65.71, "elapsed_time": "21:31:32", "remaining_time": "11:13:54", "throughput": 553.99, "total_tokens": 42930480} {"current_steps": 26290, "total_steps": 40000, "loss": 0.1088, "lr": 1.3147602683913302e-05, "epoch": 1.1901355847800992, "percentage": 65.72, "elapsed_time": "21:31:35", "remaining_time": "11:13:33", "throughput": 554.08, "total_tokens": 42938832} {"current_steps": 26295, "total_steps": 40000, "loss": 0.0836, "lr": 1.3138959572442481e-05, "epoch": 1.1903619366667422, "percentage": 65.74, "elapsed_time": "21:31:39", "remaining_time": "11:13:12", "throughput": 554.16, "total_tokens": 42946928} {"current_steps": 26300, "total_steps": 40000, "loss": 0.1186, "lr": 1.3130318290093146e-05, "epoch": 1.1905882885533852, "percentage": 65.75, "elapsed_time": "21:31:42", "remaining_time": "11:12:51", "throughput": 554.24, "total_tokens": 42954704} {"current_steps": 26305, "total_steps": 40000, "loss": 0.1294, "lr": 1.3121678838197909e-05, "epoch": 1.1908146404400282, "percentage": 65.76, "elapsed_time": "21:31:45", "remaining_time": "11:12:31", "throughput": 554.32, "total_tokens": 42962544} {"current_steps": 26310, "total_steps": 40000, "loss": 0.1251, "lr": 1.3113041218089056e-05, "epoch": 1.1910409923266712, "percentage": 65.77, "elapsed_time": "21:31:48", "remaining_time": "11:12:10", "throughput": 554.4, "total_tokens": 42970384} {"current_steps": 26315, "total_steps": 40000, "loss": 0.1132, "lr": 1.3104405431098626e-05, "epoch": 1.191267344213314, "percentage": 65.79, "elapsed_time": "21:31:51", "remaining_time": "11:11:49", "throughput": 554.48, "total_tokens": 42978544} {"current_steps": 26320, "total_steps": 40000, "loss": 0.0941, "lr": 1.3095771478558377e-05, "epoch": 1.191493696099957, "percentage": 65.8, "elapsed_time": "21:31:54", "remaining_time": "11:11:28", "throughput": 554.56, "total_tokens": 42986640} {"current_steps": 26325, "total_steps": 40000, "loss": 0.1337, "lr": 1.3087139361799766e-05, "epoch": 1.1917200479866, "percentage": 65.81, "elapsed_time": "21:31:58", "remaining_time": "11:11:08", "throughput": 554.65, "total_tokens": 42995184} {"current_steps": 26330, "total_steps": 40000, "loss": 0.1266, "lr": 1.3078509082153964e-05, "epoch": 1.191946399873243, "percentage": 65.83, "elapsed_time": "21:32:01", "remaining_time": "11:10:47", "throughput": 554.73, "total_tokens": 43003536} {"current_steps": 26335, "total_steps": 40000, "loss": 0.1146, "lr": 1.3069880640951885e-05, "epoch": 1.192172751759886, "percentage": 65.84, "elapsed_time": "21:32:04", "remaining_time": "11:10:26", "throughput": 554.82, "total_tokens": 43012080} {"current_steps": 26340, "total_steps": 40000, "loss": 0.0688, "lr": 1.3061254039524123e-05, "epoch": 1.192399103646529, "percentage": 65.85, "elapsed_time": "21:32:07", "remaining_time": "11:10:06", "throughput": 554.9, "total_tokens": 43020336} {"current_steps": 26345, "total_steps": 40000, "loss": 0.1131, "lr": 1.3052629279201028e-05, "epoch": 1.192625455533172, "percentage": 65.86, "elapsed_time": "21:32:11", "remaining_time": "11:09:45", "throughput": 554.99, "total_tokens": 43028784} {"current_steps": 26350, "total_steps": 40000, "loss": 0.1169, "lr": 1.3044006361312633e-05, "epoch": 1.192851807419815, "percentage": 65.88, "elapsed_time": "21:32:14", "remaining_time": "11:09:24", "throughput": 555.07, "total_tokens": 43036656} {"current_steps": 26355, "total_steps": 40000, "loss": 0.1255, "lr": 1.30353852871887e-05, "epoch": 1.1930781593064579, "percentage": 65.89, "elapsed_time": "21:32:17", "remaining_time": "11:09:04", "throughput": 555.14, "total_tokens": 43044432} {"current_steps": 26360, "total_steps": 40000, "loss": 0.1431, "lr": 1.302676605815873e-05, "epoch": 1.1933045111931009, "percentage": 65.9, "elapsed_time": "21:32:20", "remaining_time": "11:08:43", "throughput": 555.23, "total_tokens": 43053104} {"current_steps": 26365, "total_steps": 40000, "loss": 0.1124, "lr": 1.3018148675551884e-05, "epoch": 1.1935308630797437, "percentage": 65.91, "elapsed_time": "21:32:23", "remaining_time": "11:08:22", "throughput": 555.32, "total_tokens": 43061744} {"current_steps": 26370, "total_steps": 40000, "loss": 0.0875, "lr": 1.3009533140697094e-05, "epoch": 1.1937572149663866, "percentage": 65.92, "elapsed_time": "21:32:26", "remaining_time": "11:08:02", "throughput": 555.4, "total_tokens": 43069968} {"current_steps": 26375, "total_steps": 40000, "loss": 0.107, "lr": 1.3000919454922966e-05, "epoch": 1.1939835668530296, "percentage": 65.94, "elapsed_time": "21:32:30", "remaining_time": "11:07:41", "throughput": 555.49, "total_tokens": 43078256} {"current_steps": 26380, "total_steps": 40000, "loss": 0.1593, "lr": 1.299230761955785e-05, "epoch": 1.1942099187396726, "percentage": 65.95, "elapsed_time": "21:32:33", "remaining_time": "11:07:20", "throughput": 555.57, "total_tokens": 43086352} {"current_steps": 26385, "total_steps": 40000, "loss": 0.0677, "lr": 1.2983697635929807e-05, "epoch": 1.1944362706263156, "percentage": 65.96, "elapsed_time": "21:32:36", "remaining_time": "11:07:00", "throughput": 555.65, "total_tokens": 43094192} {"current_steps": 26390, "total_steps": 40000, "loss": 0.087, "lr": 1.2975089505366584e-05, "epoch": 1.1946626225129586, "percentage": 65.97, "elapsed_time": "21:32:39", "remaining_time": "11:06:39", "throughput": 555.73, "total_tokens": 43102544} {"current_steps": 26395, "total_steps": 40000, "loss": 0.1357, "lr": 1.2966483229195683e-05, "epoch": 1.1948889743996016, "percentage": 65.99, "elapsed_time": "21:32:42", "remaining_time": "11:06:18", "throughput": 555.82, "total_tokens": 43110704} {"current_steps": 26400, "total_steps": 40000, "loss": 0.1612, "lr": 1.2957878808744283e-05, "epoch": 1.1951153262862446, "percentage": 66.0, "elapsed_time": "21:32:46", "remaining_time": "11:05:58", "throughput": 555.9, "total_tokens": 43119408} {"current_steps": 26400, "total_steps": 40000, "eval_loss": 0.12344332039356232, "epoch": 1.1951153262862446, "percentage": 66.0, "elapsed_time": "21:40:28", "remaining_time": "11:09:56", "throughput": 552.61, "total_tokens": 43119408} {"current_steps": 26405, "total_steps": 40000, "loss": 0.1259, "lr": 1.294927624533931e-05, "epoch": 1.1953416781728876, "percentage": 66.01, "elapsed_time": "21:40:32", "remaining_time": "11:09:36", "throughput": 552.69, "total_tokens": 43127536} {"current_steps": 26410, "total_steps": 40000, "loss": 0.0801, "lr": 1.2940675540307378e-05, "epoch": 1.1955680300595306, "percentage": 66.03, "elapsed_time": "21:40:36", "remaining_time": "11:09:15", "throughput": 552.78, "total_tokens": 43136656} {"current_steps": 26415, "total_steps": 40000, "loss": 0.1727, "lr": 1.2932076694974814e-05, "epoch": 1.1957943819461736, "percentage": 66.04, "elapsed_time": "21:40:39", "remaining_time": "11:08:54", "throughput": 552.86, "total_tokens": 43145200} {"current_steps": 26420, "total_steps": 40000, "loss": 0.1992, "lr": 1.2923479710667682e-05, "epoch": 1.1960207338328166, "percentage": 66.05, "elapsed_time": "21:40:42", "remaining_time": "11:08:34", "throughput": 552.94, "total_tokens": 43153264} {"current_steps": 26425, "total_steps": 40000, "loss": 0.1378, "lr": 1.2914884588711751e-05, "epoch": 1.1962470857194596, "percentage": 66.06, "elapsed_time": "21:40:45", "remaining_time": "11:08:13", "throughput": 553.03, "total_tokens": 43161648} {"current_steps": 26430, "total_steps": 40000, "loss": 0.1238, "lr": 1.2906291330432475e-05, "epoch": 1.1964734376061024, "percentage": 66.07, "elapsed_time": "21:40:48", "remaining_time": "11:07:52", "throughput": 553.11, "total_tokens": 43169584} {"current_steps": 26435, "total_steps": 40000, "loss": 0.086, "lr": 1.2897699937155055e-05, "epoch": 1.1966997894927454, "percentage": 66.09, "elapsed_time": "21:40:52", "remaining_time": "11:07:32", "throughput": 553.2, "total_tokens": 43178224} {"current_steps": 26440, "total_steps": 40000, "loss": 0.1456, "lr": 1.2889110410204403e-05, "epoch": 1.1969261413793884, "percentage": 66.1, "elapsed_time": "21:40:55", "remaining_time": "11:07:11", "throughput": 553.28, "total_tokens": 43186128} {"current_steps": 26445, "total_steps": 40000, "loss": 0.1209, "lr": 1.2880522750905111e-05, "epoch": 1.1971524932660313, "percentage": 66.11, "elapsed_time": "21:40:58", "remaining_time": "11:06:50", "throughput": 553.36, "total_tokens": 43194256} {"current_steps": 26450, "total_steps": 40000, "loss": 0.1322, "lr": 1.2871936960581523e-05, "epoch": 1.1973788451526743, "percentage": 66.12, "elapsed_time": "21:41:01", "remaining_time": "11:06:30", "throughput": 553.44, "total_tokens": 43202896} {"current_steps": 26455, "total_steps": 40000, "loss": 0.1254, "lr": 1.2863353040557658e-05, "epoch": 1.1976051970393173, "percentage": 66.14, "elapsed_time": "21:41:04", "remaining_time": "11:06:09", "throughput": 553.53, "total_tokens": 43211152} {"current_steps": 26460, "total_steps": 40000, "loss": 0.1384, "lr": 1.2854770992157273e-05, "epoch": 1.1978315489259603, "percentage": 66.15, "elapsed_time": "21:41:08", "remaining_time": "11:05:48", "throughput": 553.6, "total_tokens": 43218864} {"current_steps": 26465, "total_steps": 40000, "loss": 0.0901, "lr": 1.2846190816703835e-05, "epoch": 1.1980579008126033, "percentage": 66.16, "elapsed_time": "21:41:11", "remaining_time": "11:05:27", "throughput": 553.68, "total_tokens": 43226576} {"current_steps": 26470, "total_steps": 40000, "loss": 0.1318, "lr": 1.2837612515520498e-05, "epoch": 1.1982842526992463, "percentage": 66.17, "elapsed_time": "21:41:14", "remaining_time": "11:05:07", "throughput": 553.76, "total_tokens": 43234768} {"current_steps": 26475, "total_steps": 40000, "loss": 0.1289, "lr": 1.2829036089930163e-05, "epoch": 1.1985106045858893, "percentage": 66.19, "elapsed_time": "21:41:17", "remaining_time": "11:04:46", "throughput": 553.84, "total_tokens": 43242544} {"current_steps": 26480, "total_steps": 40000, "loss": 0.1359, "lr": 1.2820461541255412e-05, "epoch": 1.198736956472532, "percentage": 66.2, "elapsed_time": "21:41:20", "remaining_time": "11:04:25", "throughput": 553.92, "total_tokens": 43250576} {"current_steps": 26485, "total_steps": 40000, "loss": 0.1403, "lr": 1.2811888870818543e-05, "epoch": 1.198963308359175, "percentage": 66.21, "elapsed_time": "21:41:23", "remaining_time": "11:04:05", "throughput": 554.0, "total_tokens": 43258608} {"current_steps": 26490, "total_steps": 40000, "loss": 0.1838, "lr": 1.2803318079941581e-05, "epoch": 1.199189660245818, "percentage": 66.22, "elapsed_time": "21:41:26", "remaining_time": "11:03:44", "throughput": 554.08, "total_tokens": 43266704} {"current_steps": 26495, "total_steps": 40000, "loss": 0.1181, "lr": 1.2794749169946235e-05, "epoch": 1.199416012132461, "percentage": 66.24, "elapsed_time": "21:41:30", "remaining_time": "11:03:23", "throughput": 554.16, "total_tokens": 43274320} {"current_steps": 26500, "total_steps": 40000, "loss": 0.0973, "lr": 1.2786182142153952e-05, "epoch": 1.199642364019104, "percentage": 66.25, "elapsed_time": "21:41:33", "remaining_time": "11:03:03", "throughput": 554.24, "total_tokens": 43282064} {"current_steps": 26505, "total_steps": 40000, "loss": 0.1097, "lr": 1.2777616997885878e-05, "epoch": 1.199868715905747, "percentage": 66.26, "elapsed_time": "21:41:36", "remaining_time": "11:02:42", "throughput": 554.32, "total_tokens": 43290000} {"current_steps": 26510, "total_steps": 40000, "loss": 0.0987, "lr": 1.2769053738462847e-05, "epoch": 1.20009506779239, "percentage": 66.27, "elapsed_time": "21:41:39", "remaining_time": "11:02:22", "throughput": 554.4, "total_tokens": 43297968} {"current_steps": 26515, "total_steps": 40000, "loss": 0.1474, "lr": 1.2760492365205434e-05, "epoch": 1.200321419679033, "percentage": 66.29, "elapsed_time": "21:41:42", "remaining_time": "11:02:01", "throughput": 554.48, "total_tokens": 43306160} {"current_steps": 26520, "total_steps": 40000, "loss": 0.199, "lr": 1.2751932879433919e-05, "epoch": 1.200547771565676, "percentage": 66.3, "elapsed_time": "21:41:45", "remaining_time": "11:01:40", "throughput": 554.55, "total_tokens": 43313904} {"current_steps": 26525, "total_steps": 40000, "loss": 0.1282, "lr": 1.2743375282468267e-05, "epoch": 1.200774123452319, "percentage": 66.31, "elapsed_time": "21:41:48", "remaining_time": "11:01:20", "throughput": 554.63, "total_tokens": 43321744} {"current_steps": 26530, "total_steps": 40000, "loss": 0.1323, "lr": 1.2734819575628182e-05, "epoch": 1.201000475338962, "percentage": 66.33, "elapsed_time": "21:41:51", "remaining_time": "11:00:59", "throughput": 554.71, "total_tokens": 43329360} {"current_steps": 26535, "total_steps": 40000, "loss": 0.1339, "lr": 1.2726265760233039e-05, "epoch": 1.201226827225605, "percentage": 66.34, "elapsed_time": "21:41:55", "remaining_time": "11:00:38", "throughput": 554.79, "total_tokens": 43337904} {"current_steps": 26540, "total_steps": 40000, "loss": 0.1497, "lr": 1.271771383760197e-05, "epoch": 1.2014531791122478, "percentage": 66.35, "elapsed_time": "21:41:58", "remaining_time": "11:00:18", "throughput": 554.88, "total_tokens": 43346064} {"current_steps": 26545, "total_steps": 40000, "loss": 0.0766, "lr": 1.2709163809053764e-05, "epoch": 1.2016795309988908, "percentage": 66.36, "elapsed_time": "21:42:01", "remaining_time": "10:59:57", "throughput": 554.96, "total_tokens": 43354384} {"current_steps": 26550, "total_steps": 40000, "loss": 0.1506, "lr": 1.2700615675906963e-05, "epoch": 1.2019058828855338, "percentage": 66.38, "elapsed_time": "21:42:04", "remaining_time": "10:59:37", "throughput": 555.04, "total_tokens": 43362704} {"current_steps": 26555, "total_steps": 40000, "loss": 0.121, "lr": 1.269206943947978e-05, "epoch": 1.2021322347721768, "percentage": 66.39, "elapsed_time": "21:42:07", "remaining_time": "10:59:16", "throughput": 555.12, "total_tokens": 43370768} {"current_steps": 26560, "total_steps": 40000, "loss": 0.13, "lr": 1.2683525101090177e-05, "epoch": 1.2023585866588198, "percentage": 66.4, "elapsed_time": "21:42:11", "remaining_time": "10:58:56", "throughput": 555.21, "total_tokens": 43379280} {"current_steps": 26565, "total_steps": 40000, "loss": 0.0905, "lr": 1.2674982662055765e-05, "epoch": 1.2025849385454628, "percentage": 66.41, "elapsed_time": "21:42:14", "remaining_time": "10:58:35", "throughput": 555.29, "total_tokens": 43386896} {"current_steps": 26570, "total_steps": 40000, "loss": 0.1077, "lr": 1.2666442123693922e-05, "epoch": 1.2028112904321058, "percentage": 66.42, "elapsed_time": "21:42:17", "remaining_time": "10:58:15", "throughput": 555.38, "total_tokens": 43395760} {"current_steps": 26575, "total_steps": 40000, "loss": 0.0824, "lr": 1.265790348732169e-05, "epoch": 1.2030376423187488, "percentage": 66.44, "elapsed_time": "21:42:20", "remaining_time": "10:57:54", "throughput": 555.46, "total_tokens": 43403792} {"current_steps": 26580, "total_steps": 40000, "loss": 0.1385, "lr": 1.264936675425584e-05, "epoch": 1.2032639942053918, "percentage": 66.45, "elapsed_time": "21:42:23", "remaining_time": "10:57:34", "throughput": 555.53, "total_tokens": 43411696} {"current_steps": 26585, "total_steps": 40000, "loss": 0.1143, "lr": 1.2640831925812852e-05, "epoch": 1.2034903460920348, "percentage": 66.46, "elapsed_time": "21:42:27", "remaining_time": "10:57:13", "throughput": 555.61, "total_tokens": 43419600} {"current_steps": 26590, "total_steps": 40000, "loss": 0.1396, "lr": 1.263229900330889e-05, "epoch": 1.2037166979786775, "percentage": 66.47, "elapsed_time": "21:42:30", "remaining_time": "10:56:53", "throughput": 555.69, "total_tokens": 43427472} {"current_steps": 26595, "total_steps": 40000, "loss": 0.1007, "lr": 1.2623767988059843e-05, "epoch": 1.2039430498653205, "percentage": 66.49, "elapsed_time": "21:42:33", "remaining_time": "10:56:32", "throughput": 555.77, "total_tokens": 43435248} {"current_steps": 26600, "total_steps": 40000, "loss": 0.1061, "lr": 1.2615238881381309e-05, "epoch": 1.2041694017519635, "percentage": 66.5, "elapsed_time": "21:42:36", "remaining_time": "10:56:12", "throughput": 555.85, "total_tokens": 43443728} {"current_steps": 26600, "total_steps": 40000, "eval_loss": 0.1235150545835495, "epoch": 1.2041694017519635, "percentage": 66.5, "elapsed_time": "21:50:19", "remaining_time": "11:00:05", "throughput": 552.59, "total_tokens": 43443728} {"current_steps": 26605, "total_steps": 40000, "loss": 0.1264, "lr": 1.2606711684588568e-05, "epoch": 1.2043957536386065, "percentage": 66.51, "elapsed_time": "21:50:23", "remaining_time": "10:59:45", "throughput": 552.66, "total_tokens": 43451728} {"current_steps": 26610, "total_steps": 40000, "loss": 0.1166, "lr": 1.2598186398996636e-05, "epoch": 1.2046221055252495, "percentage": 66.53, "elapsed_time": "21:50:26", "remaining_time": "10:59:24", "throughput": 552.75, "total_tokens": 43461008} {"current_steps": 26615, "total_steps": 40000, "loss": 0.1009, "lr": 1.2589663025920207e-05, "epoch": 1.2048484574118925, "percentage": 66.54, "elapsed_time": "21:50:29", "remaining_time": "10:59:03", "throughput": 552.83, "total_tokens": 43468656} {"current_steps": 26620, "total_steps": 40000, "loss": 0.1531, "lr": 1.2581141566673705e-05, "epoch": 1.2050748092985355, "percentage": 66.55, "elapsed_time": "21:50:33", "remaining_time": "10:58:43", "throughput": 552.91, "total_tokens": 43477104} {"current_steps": 26625, "total_steps": 40000, "loss": 0.1332, "lr": 1.257262202257124e-05, "epoch": 1.2053011611851785, "percentage": 66.56, "elapsed_time": "21:50:36", "remaining_time": "10:58:22", "throughput": 552.99, "total_tokens": 43484976} {"current_steps": 26630, "total_steps": 40000, "loss": 0.1233, "lr": 1.2564104394926618e-05, "epoch": 1.2055275130718215, "percentage": 66.57, "elapsed_time": "21:50:39", "remaining_time": "10:58:02", "throughput": 553.07, "total_tokens": 43493104} {"current_steps": 26635, "total_steps": 40000, "loss": 0.1103, "lr": 1.2555588685053383e-05, "epoch": 1.2057538649584645, "percentage": 66.59, "elapsed_time": "21:50:42", "remaining_time": "10:57:41", "throughput": 553.15, "total_tokens": 43501360} {"current_steps": 26640, "total_steps": 40000, "loss": 0.1052, "lr": 1.2547074894264762e-05, "epoch": 1.2059802168451075, "percentage": 66.6, "elapsed_time": "21:50:45", "remaining_time": "10:57:20", "throughput": 553.23, "total_tokens": 43508976} {"current_steps": 26645, "total_steps": 40000, "loss": 0.0644, "lr": 1.2538563023873679e-05, "epoch": 1.2062065687317505, "percentage": 66.61, "elapsed_time": "21:50:48", "remaining_time": "10:57:00", "throughput": 553.32, "total_tokens": 43517552} {"current_steps": 26650, "total_steps": 40000, "loss": 0.0719, "lr": 1.2530053075192789e-05, "epoch": 1.2064329206183935, "percentage": 66.62, "elapsed_time": "21:50:52", "remaining_time": "10:56:39", "throughput": 553.4, "total_tokens": 43525872} {"current_steps": 26655, "total_steps": 40000, "loss": 0.1063, "lr": 1.252154504953441e-05, "epoch": 1.2066592725050362, "percentage": 66.64, "elapsed_time": "21:50:55", "remaining_time": "10:56:19", "throughput": 553.48, "total_tokens": 43533648} {"current_steps": 26660, "total_steps": 40000, "loss": 0.1559, "lr": 1.25130389482106e-05, "epoch": 1.2068856243916792, "percentage": 66.65, "elapsed_time": "21:50:58", "remaining_time": "10:55:58", "throughput": 553.55, "total_tokens": 43541616} {"current_steps": 26665, "total_steps": 40000, "loss": 0.1187, "lr": 1.2504534772533116e-05, "epoch": 1.2071119762783222, "percentage": 66.66, "elapsed_time": "21:51:01", "remaining_time": "10:55:38", "throughput": 553.64, "total_tokens": 43549808} {"current_steps": 26670, "total_steps": 40000, "loss": 0.1149, "lr": 1.2496032523813387e-05, "epoch": 1.2073383281649652, "percentage": 66.67, "elapsed_time": "21:51:04", "remaining_time": "10:55:17", "throughput": 553.71, "total_tokens": 43557520} {"current_steps": 26675, "total_steps": 40000, "loss": 0.1139, "lr": 1.2487532203362576e-05, "epoch": 1.2075646800516082, "percentage": 66.69, "elapsed_time": "21:51:07", "remaining_time": "10:54:56", "throughput": 553.79, "total_tokens": 43565296} {"current_steps": 26680, "total_steps": 40000, "loss": 0.1039, "lr": 1.247903381249155e-05, "epoch": 1.2077910319382512, "percentage": 66.7, "elapsed_time": "21:51:10", "remaining_time": "10:54:36", "throughput": 553.87, "total_tokens": 43573712} {"current_steps": 26685, "total_steps": 40000, "loss": 0.0707, "lr": 1.2470537352510853e-05, "epoch": 1.2080173838248942, "percentage": 66.71, "elapsed_time": "21:51:14", "remaining_time": "10:54:15", "throughput": 553.96, "total_tokens": 43582480} {"current_steps": 26690, "total_steps": 40000, "loss": 0.1321, "lr": 1.2462042824730758e-05, "epoch": 1.2082437357115372, "percentage": 66.72, "elapsed_time": "21:51:17", "remaining_time": "10:53:55", "throughput": 554.04, "total_tokens": 43590544} {"current_steps": 26695, "total_steps": 40000, "loss": 0.159, "lr": 1.245355023046122e-05, "epoch": 1.2084700875981802, "percentage": 66.74, "elapsed_time": "21:51:20", "remaining_time": "10:53:35", "throughput": 554.13, "total_tokens": 43599376} {"current_steps": 26700, "total_steps": 40000, "loss": 0.1261, "lr": 1.2445059571011896e-05, "epoch": 1.2086964394848232, "percentage": 66.75, "elapsed_time": "21:51:23", "remaining_time": "10:53:14", "throughput": 554.21, "total_tokens": 43607536} {"current_steps": 26705, "total_steps": 40000, "loss": 0.1464, "lr": 1.2436570847692173e-05, "epoch": 1.208922791371466, "percentage": 66.76, "elapsed_time": "21:51:26", "remaining_time": "10:52:53", "throughput": 554.29, "total_tokens": 43615120} {"current_steps": 26710, "total_steps": 40000, "loss": 0.1971, "lr": 1.2428084061811096e-05, "epoch": 1.209149143258109, "percentage": 66.77, "elapsed_time": "21:51:29", "remaining_time": "10:52:33", "throughput": 554.37, "total_tokens": 43623248} {"current_steps": 26715, "total_steps": 40000, "loss": 0.1085, "lr": 1.2419599214677447e-05, "epoch": 1.209375495144752, "percentage": 66.79, "elapsed_time": "21:51:33", "remaining_time": "10:52:13", "throughput": 554.45, "total_tokens": 43631472} {"current_steps": 26720, "total_steps": 40000, "loss": 0.1604, "lr": 1.2411116307599702e-05, "epoch": 1.209601847031395, "percentage": 66.8, "elapsed_time": "21:51:36", "remaining_time": "10:51:52", "throughput": 554.53, "total_tokens": 43639440} {"current_steps": 26725, "total_steps": 40000, "loss": 0.1145, "lr": 1.2402635341886016e-05, "epoch": 1.209828198918038, "percentage": 66.81, "elapsed_time": "21:51:39", "remaining_time": "10:51:32", "throughput": 554.61, "total_tokens": 43647472} {"current_steps": 26730, "total_steps": 40000, "loss": 0.1608, "lr": 1.2394156318844278e-05, "epoch": 1.210054550804681, "percentage": 66.83, "elapsed_time": "21:51:42", "remaining_time": "10:51:11", "throughput": 554.69, "total_tokens": 43655888} {"current_steps": 26735, "total_steps": 40000, "loss": 0.1343, "lr": 1.2385679239782039e-05, "epoch": 1.210280902691324, "percentage": 66.84, "elapsed_time": "21:51:45", "remaining_time": "10:50:51", "throughput": 554.77, "total_tokens": 43663440} {"current_steps": 26740, "total_steps": 40000, "loss": 0.1356, "lr": 1.2377204106006585e-05, "epoch": 1.210507254577967, "percentage": 66.85, "elapsed_time": "21:51:49", "remaining_time": "10:50:30", "throughput": 554.84, "total_tokens": 43671280} {"current_steps": 26745, "total_steps": 40000, "loss": 0.1272, "lr": 1.2368730918824891e-05, "epoch": 1.21073360646461, "percentage": 66.86, "elapsed_time": "21:51:52", "remaining_time": "10:50:10", "throughput": 554.93, "total_tokens": 43679568} {"current_steps": 26750, "total_steps": 40000, "loss": 0.0876, "lr": 1.236025967954362e-05, "epoch": 1.210959958351253, "percentage": 66.88, "elapsed_time": "21:51:55", "remaining_time": "10:49:49", "throughput": 555.01, "total_tokens": 43687504} {"current_steps": 26755, "total_steps": 40000, "loss": 0.1838, "lr": 1.2351790389469153e-05, "epoch": 1.211186310237896, "percentage": 66.89, "elapsed_time": "21:51:58", "remaining_time": "10:49:29", "throughput": 555.09, "total_tokens": 43695568} {"current_steps": 26760, "total_steps": 40000, "loss": 0.0769, "lr": 1.234332304990755e-05, "epoch": 1.211412662124539, "percentage": 66.9, "elapsed_time": "21:52:01", "remaining_time": "10:49:09", "throughput": 555.17, "total_tokens": 43703696} {"current_steps": 26765, "total_steps": 40000, "loss": 0.1625, "lr": 1.2334857662164593e-05, "epoch": 1.211639014011182, "percentage": 66.91, "elapsed_time": "21:52:04", "remaining_time": "10:48:48", "throughput": 555.24, "total_tokens": 43711600} {"current_steps": 26770, "total_steps": 40000, "loss": 0.1084, "lr": 1.2326394227545743e-05, "epoch": 1.2118653658978247, "percentage": 66.92, "elapsed_time": "21:52:08", "remaining_time": "10:48:28", "throughput": 555.32, "total_tokens": 43719664} {"current_steps": 26775, "total_steps": 40000, "loss": 0.0991, "lr": 1.2317932747356162e-05, "epoch": 1.2120917177844677, "percentage": 66.94, "elapsed_time": "21:52:11", "remaining_time": "10:48:07", "throughput": 555.4, "total_tokens": 43727440} {"current_steps": 26780, "total_steps": 40000, "loss": 0.1042, "lr": 1.2309473222900726e-05, "epoch": 1.2123180696711107, "percentage": 66.95, "elapsed_time": "21:52:14", "remaining_time": "10:47:47", "throughput": 555.48, "total_tokens": 43735472} {"current_steps": 26785, "total_steps": 40000, "loss": 0.1435, "lr": 1.2301015655484006e-05, "epoch": 1.2125444215577537, "percentage": 66.96, "elapsed_time": "21:52:17", "remaining_time": "10:47:26", "throughput": 555.56, "total_tokens": 43743056} {"current_steps": 26790, "total_steps": 40000, "loss": 0.1405, "lr": 1.2292560046410245e-05, "epoch": 1.2127707734443967, "percentage": 66.97, "elapsed_time": "21:52:20", "remaining_time": "10:47:06", "throughput": 555.64, "total_tokens": 43751472} {"current_steps": 26795, "total_steps": 40000, "loss": 0.1199, "lr": 1.228410639698343e-05, "epoch": 1.2129971253310396, "percentage": 66.99, "elapsed_time": "21:52:23", "remaining_time": "10:46:46", "throughput": 555.72, "total_tokens": 43759792} {"current_steps": 26800, "total_steps": 40000, "loss": 0.1426, "lr": 1.2275654708507195e-05, "epoch": 1.2132234772176826, "percentage": 67.0, "elapsed_time": "21:52:27", "remaining_time": "10:46:25", "throughput": 555.81, "total_tokens": 43768400} {"current_steps": 26800, "total_steps": 40000, "eval_loss": 0.12309839576482773, "epoch": 1.2132234772176826, "percentage": 67.0, "elapsed_time": "22:00:09", "remaining_time": "10:50:13", "throughput": 552.56, "total_tokens": 43768400} {"current_steps": 26805, "total_steps": 40000, "loss": 0.1158, "lr": 1.2267204982284908e-05, "epoch": 1.2134498291043256, "percentage": 67.01, "elapsed_time": "22:00:14", "remaining_time": "10:49:53", "throughput": 552.65, "total_tokens": 43777744} {"current_steps": 26810, "total_steps": 40000, "loss": 0.1271, "lr": 1.2258757219619635e-05, "epoch": 1.2136761809909686, "percentage": 67.03, "elapsed_time": "22:00:17", "remaining_time": "10:49:33", "throughput": 552.74, "total_tokens": 43786320} {"current_steps": 26815, "total_steps": 40000, "loss": 0.127, "lr": 1.2250311421814104e-05, "epoch": 1.2139025328776116, "percentage": 67.04, "elapsed_time": "22:00:20", "remaining_time": "10:49:12", "throughput": 552.82, "total_tokens": 43794384} {"current_steps": 26820, "total_steps": 40000, "loss": 0.1404, "lr": 1.2241867590170772e-05, "epoch": 1.2141288847642544, "percentage": 67.05, "elapsed_time": "22:00:23", "remaining_time": "10:48:52", "throughput": 552.9, "total_tokens": 43802736} {"current_steps": 26825, "total_steps": 40000, "loss": 0.1386, "lr": 1.2233425725991799e-05, "epoch": 1.2143552366508974, "percentage": 67.06, "elapsed_time": "22:00:26", "remaining_time": "10:48:31", "throughput": 552.97, "total_tokens": 43810224} {"current_steps": 26830, "total_steps": 40000, "loss": 0.098, "lr": 1.2224985830579003e-05, "epoch": 1.2145815885375404, "percentage": 67.07, "elapsed_time": "22:00:30", "remaining_time": "10:48:11", "throughput": 553.07, "total_tokens": 43820016} {"current_steps": 26835, "total_steps": 40000, "loss": 0.0946, "lr": 1.2216547905233944e-05, "epoch": 1.2148079404241834, "percentage": 67.09, "elapsed_time": "22:00:33", "remaining_time": "10:47:51", "throughput": 553.15, "total_tokens": 43827696} {"current_steps": 26840, "total_steps": 40000, "loss": 0.1245, "lr": 1.2208111951257842e-05, "epoch": 1.2150342923108264, "percentage": 67.1, "elapsed_time": "22:00:36", "remaining_time": "10:47:30", "throughput": 553.24, "total_tokens": 43836784} {"current_steps": 26845, "total_steps": 40000, "loss": 0.1021, "lr": 1.2199677969951622e-05, "epoch": 1.2152606441974694, "percentage": 67.11, "elapsed_time": "22:00:39", "remaining_time": "10:47:10", "throughput": 553.32, "total_tokens": 43844880} {"current_steps": 26850, "total_steps": 40000, "loss": 0.1075, "lr": 1.2191245962615927e-05, "epoch": 1.2154869960841124, "percentage": 67.12, "elapsed_time": "22:00:43", "remaining_time": "10:46:49", "throughput": 553.4, "total_tokens": 43853072} {"current_steps": 26855, "total_steps": 40000, "loss": 0.1763, "lr": 1.218281593055106e-05, "epoch": 1.2157133479707554, "percentage": 67.14, "elapsed_time": "22:00:46", "remaining_time": "10:46:29", "throughput": 553.48, "total_tokens": 43861648} {"current_steps": 26860, "total_steps": 40000, "loss": 0.1223, "lr": 1.217438787505705e-05, "epoch": 1.2159396998573984, "percentage": 67.15, "elapsed_time": "22:00:49", "remaining_time": "10:46:09", "throughput": 553.56, "total_tokens": 43869712} {"current_steps": 26865, "total_steps": 40000, "loss": 0.1256, "lr": 1.2165961797433615e-05, "epoch": 1.2161660517440414, "percentage": 67.16, "elapsed_time": "22:00:52", "remaining_time": "10:45:48", "throughput": 553.65, "total_tokens": 43877968} {"current_steps": 26870, "total_steps": 40000, "loss": 0.1271, "lr": 1.215753769898014e-05, "epoch": 1.2163924036306843, "percentage": 67.17, "elapsed_time": "22:00:55", "remaining_time": "10:45:28", "throughput": 553.72, "total_tokens": 43885456} {"current_steps": 26875, "total_steps": 40000, "loss": 0.1071, "lr": 1.2149115580995755e-05, "epoch": 1.2166187555173273, "percentage": 67.19, "elapsed_time": "22:00:59", "remaining_time": "10:45:07", "throughput": 553.8, "total_tokens": 43893712} {"current_steps": 26880, "total_steps": 40000, "loss": 0.1133, "lr": 1.2140695444779227e-05, "epoch": 1.2168451074039701, "percentage": 67.2, "elapsed_time": "22:01:02", "remaining_time": "10:44:47", "throughput": 553.88, "total_tokens": 43901776} {"current_steps": 26885, "total_steps": 40000, "loss": 0.1763, "lr": 1.2132277291629066e-05, "epoch": 1.2170714592906131, "percentage": 67.21, "elapsed_time": "22:01:05", "remaining_time": "10:44:27", "throughput": 553.96, "total_tokens": 43909936} {"current_steps": 26890, "total_steps": 40000, "loss": 0.1121, "lr": 1.2123861122843458e-05, "epoch": 1.217297811177256, "percentage": 67.22, "elapsed_time": "22:01:08", "remaining_time": "10:44:06", "throughput": 554.04, "total_tokens": 43918288} {"current_steps": 26895, "total_steps": 40000, "loss": 0.1019, "lr": 1.2115446939720271e-05, "epoch": 1.217524163063899, "percentage": 67.24, "elapsed_time": "22:01:11", "remaining_time": "10:43:46", "throughput": 554.12, "total_tokens": 43926160} {"current_steps": 26900, "total_steps": 40000, "loss": 0.1112, "lr": 1.210703474355708e-05, "epoch": 1.217750514950542, "percentage": 67.25, "elapsed_time": "22:01:15", "remaining_time": "10:43:26", "throughput": 554.21, "total_tokens": 43934768} {"current_steps": 26905, "total_steps": 40000, "loss": 0.1524, "lr": 1.2098624535651164e-05, "epoch": 1.217976866837185, "percentage": 67.26, "elapsed_time": "22:01:18", "remaining_time": "10:43:05", "throughput": 554.28, "total_tokens": 43942576} {"current_steps": 26910, "total_steps": 40000, "loss": 0.0904, "lr": 1.2090216317299477e-05, "epoch": 1.218203218723828, "percentage": 67.27, "elapsed_time": "22:01:21", "remaining_time": "10:42:45", "throughput": 554.36, "total_tokens": 43950320} {"current_steps": 26915, "total_steps": 40000, "loss": 0.1274, "lr": 1.2081810089798668e-05, "epoch": 1.218429570610471, "percentage": 67.29, "elapsed_time": "22:01:24", "remaining_time": "10:42:24", "throughput": 554.43, "total_tokens": 43957776} {"current_steps": 26920, "total_steps": 40000, "loss": 0.1488, "lr": 1.2073405854445072e-05, "epoch": 1.218655922497114, "percentage": 67.3, "elapsed_time": "22:01:27", "remaining_time": "10:42:04", "throughput": 554.51, "total_tokens": 43965520} {"current_steps": 26925, "total_steps": 40000, "loss": 0.1108, "lr": 1.206500361253474e-05, "epoch": 1.218882274383757, "percentage": 67.31, "elapsed_time": "22:01:30", "remaining_time": "10:41:44", "throughput": 554.59, "total_tokens": 43973488} {"current_steps": 26930, "total_steps": 40000, "loss": 0.1455, "lr": 1.2056603365363409e-05, "epoch": 1.2191086262703998, "percentage": 67.33, "elapsed_time": "22:01:33", "remaining_time": "10:41:23", "throughput": 554.68, "total_tokens": 43982384} {"current_steps": 26935, "total_steps": 40000, "loss": 0.1191, "lr": 1.2048205114226487e-05, "epoch": 1.2193349781570428, "percentage": 67.34, "elapsed_time": "22:01:37", "remaining_time": "10:41:03", "throughput": 554.76, "total_tokens": 43991184} {"current_steps": 26940, "total_steps": 40000, "loss": 0.1168, "lr": 1.2039808860419102e-05, "epoch": 1.2195613300436858, "percentage": 67.35, "elapsed_time": "22:01:40", "remaining_time": "10:40:43", "throughput": 554.84, "total_tokens": 43998960} {"current_steps": 26945, "total_steps": 40000, "loss": 0.1009, "lr": 1.2031414605236066e-05, "epoch": 1.2197876819303288, "percentage": 67.36, "elapsed_time": "22:01:43", "remaining_time": "10:40:22", "throughput": 554.92, "total_tokens": 44007344} {"current_steps": 26950, "total_steps": 40000, "loss": 0.135, "lr": 1.2023022349971862e-05, "epoch": 1.2200140338169718, "percentage": 67.38, "elapsed_time": "22:01:46", "remaining_time": "10:40:02", "throughput": 555.01, "total_tokens": 44015920} {"current_steps": 26955, "total_steps": 40000, "loss": 0.1154, "lr": 1.20146320959207e-05, "epoch": 1.2202403857036148, "percentage": 67.39, "elapsed_time": "22:01:50", "remaining_time": "10:39:42", "throughput": 555.1, "total_tokens": 44024720} {"current_steps": 26960, "total_steps": 40000, "loss": 0.097, "lr": 1.2006243844376445e-05, "epoch": 1.2204667375902578, "percentage": 67.4, "elapsed_time": "22:01:53", "remaining_time": "10:39:22", "throughput": 555.17, "total_tokens": 44032720} {"current_steps": 26965, "total_steps": 40000, "loss": 0.1119, "lr": 1.1997857596632678e-05, "epoch": 1.2206930894769008, "percentage": 67.41, "elapsed_time": "22:01:56", "remaining_time": "10:39:01", "throughput": 555.25, "total_tokens": 44040752} {"current_steps": 26970, "total_steps": 40000, "loss": 0.1195, "lr": 1.1989473353982672e-05, "epoch": 1.2209194413635438, "percentage": 67.42, "elapsed_time": "22:01:59", "remaining_time": "10:38:41", "throughput": 555.34, "total_tokens": 44049392} {"current_steps": 26975, "total_steps": 40000, "loss": 0.1158, "lr": 1.198109111771937e-05, "epoch": 1.2211457932501868, "percentage": 67.44, "elapsed_time": "22:02:02", "remaining_time": "10:38:21", "throughput": 555.42, "total_tokens": 44057168} {"current_steps": 26980, "total_steps": 40000, "loss": 0.1203, "lr": 1.197271088913543e-05, "epoch": 1.2213721451368298, "percentage": 67.45, "elapsed_time": "22:02:05", "remaining_time": "10:38:01", "throughput": 555.49, "total_tokens": 44064784} {"current_steps": 26985, "total_steps": 40000, "loss": 0.1157, "lr": 1.1964332669523182e-05, "epoch": 1.2215984970234728, "percentage": 67.46, "elapsed_time": "22:02:08", "remaining_time": "10:37:40", "throughput": 555.56, "total_tokens": 44072208} {"current_steps": 26990, "total_steps": 40000, "loss": 0.0688, "lr": 1.1955956460174645e-05, "epoch": 1.2218248489101158, "percentage": 67.47, "elapsed_time": "22:02:12", "remaining_time": "10:37:20", "throughput": 555.64, "total_tokens": 44080080} {"current_steps": 26995, "total_steps": 40000, "loss": 0.1299, "lr": 1.1947582262381552e-05, "epoch": 1.2220512007967586, "percentage": 67.49, "elapsed_time": "22:02:15", "remaining_time": "10:37:00", "throughput": 555.73, "total_tokens": 44088784} {"current_steps": 27000, "total_steps": 40000, "loss": 0.096, "lr": 1.1939210077435293e-05, "epoch": 1.2222775526834015, "percentage": 67.5, "elapsed_time": "22:02:18", "remaining_time": "10:36:40", "throughput": 555.81, "total_tokens": 44097456} {"current_steps": 27000, "total_steps": 40000, "eval_loss": 0.12323996424674988, "epoch": 1.2222775526834015, "percentage": 67.5, "elapsed_time": "22:10:01", "remaining_time": "10:40:22", "throughput": 552.59, "total_tokens": 44097456} {"current_steps": 27005, "total_steps": 40000, "loss": 0.069, "lr": 1.193083990662697e-05, "epoch": 1.2225039045700445, "percentage": 67.51, "elapsed_time": "22:10:05", "remaining_time": "10:40:03", "throughput": 552.67, "total_tokens": 44106000} {"current_steps": 27010, "total_steps": 40000, "loss": 0.0998, "lr": 1.192247175124738e-05, "epoch": 1.2227302564566875, "percentage": 67.53, "elapsed_time": "22:10:08", "remaining_time": "10:39:42", "throughput": 552.74, "total_tokens": 44113552} {"current_steps": 27015, "total_steps": 40000, "loss": 0.1137, "lr": 1.191410561258698e-05, "epoch": 1.2229566083433305, "percentage": 67.54, "elapsed_time": "22:10:11", "remaining_time": "10:39:22", "throughput": 552.82, "total_tokens": 44121296} {"current_steps": 27020, "total_steps": 40000, "loss": 0.1399, "lr": 1.1905741491935944e-05, "epoch": 1.2231829602299735, "percentage": 67.55, "elapsed_time": "22:10:15", "remaining_time": "10:39:02", "throughput": 552.9, "total_tokens": 44129520} {"current_steps": 27025, "total_steps": 40000, "loss": 0.1187, "lr": 1.1897379390584129e-05, "epoch": 1.2234093121166165, "percentage": 67.56, "elapsed_time": "22:10:18", "remaining_time": "10:38:41", "throughput": 552.97, "total_tokens": 44137424} {"current_steps": 27030, "total_steps": 40000, "loss": 0.193, "lr": 1.1889019309821062e-05, "epoch": 1.2236356640032595, "percentage": 67.58, "elapsed_time": "22:10:21", "remaining_time": "10:38:21", "throughput": 553.06, "total_tokens": 44146224} {"current_steps": 27035, "total_steps": 40000, "loss": 0.0937, "lr": 1.188066125093599e-05, "epoch": 1.2238620158899025, "percentage": 67.59, "elapsed_time": "22:10:24", "remaining_time": "10:38:01", "throughput": 553.15, "total_tokens": 44155280} {"current_steps": 27040, "total_steps": 40000, "loss": 0.1006, "lr": 1.1872305215217811e-05, "epoch": 1.2240883677765455, "percentage": 67.6, "elapsed_time": "22:10:28", "remaining_time": "10:37:40", "throughput": 553.23, "total_tokens": 44163120} {"current_steps": 27045, "total_steps": 40000, "loss": 0.1542, "lr": 1.186395120395514e-05, "epoch": 1.2243147196631883, "percentage": 67.61, "elapsed_time": "22:10:31", "remaining_time": "10:37:20", "throughput": 553.31, "total_tokens": 44171024} {"current_steps": 27050, "total_steps": 40000, "loss": 0.1161, "lr": 1.1855599218436283e-05, "epoch": 1.2245410715498313, "percentage": 67.62, "elapsed_time": "22:10:34", "remaining_time": "10:37:00", "throughput": 553.4, "total_tokens": 44180112} {"current_steps": 27055, "total_steps": 40000, "loss": 0.1052, "lr": 1.1847249259949209e-05, "epoch": 1.2247674234364743, "percentage": 67.64, "elapsed_time": "22:10:37", "remaining_time": "10:36:39", "throughput": 553.48, "total_tokens": 44188208} {"current_steps": 27060, "total_steps": 40000, "loss": 0.0993, "lr": 1.1838901329781574e-05, "epoch": 1.2249937753231173, "percentage": 67.65, "elapsed_time": "22:10:40", "remaining_time": "10:36:19", "throughput": 553.56, "total_tokens": 44196432} {"current_steps": 27065, "total_steps": 40000, "loss": 0.1139, "lr": 1.1830555429220758e-05, "epoch": 1.2252201272097603, "percentage": 67.66, "elapsed_time": "22:10:43", "remaining_time": "10:35:59", "throughput": 553.63, "total_tokens": 44204208} {"current_steps": 27070, "total_steps": 40000, "loss": 0.1252, "lr": 1.1822211559553784e-05, "epoch": 1.2254464790964033, "percentage": 67.67, "elapsed_time": "22:10:47", "remaining_time": "10:35:39", "throughput": 553.71, "total_tokens": 44212272} {"current_steps": 27075, "total_steps": 40000, "loss": 0.1146, "lr": 1.18138697220674e-05, "epoch": 1.2256728309830462, "percentage": 67.69, "elapsed_time": "22:10:50", "remaining_time": "10:35:18", "throughput": 553.79, "total_tokens": 44220560} {"current_steps": 27080, "total_steps": 40000, "loss": 0.1562, "lr": 1.1805529918048e-05, "epoch": 1.2258991828696892, "percentage": 67.7, "elapsed_time": "22:10:53", "remaining_time": "10:34:58", "throughput": 553.87, "total_tokens": 44228880} {"current_steps": 27085, "total_steps": 40000, "loss": 0.1143, "lr": 1.1797192148781702e-05, "epoch": 1.2261255347563322, "percentage": 67.71, "elapsed_time": "22:10:56", "remaining_time": "10:34:38", "throughput": 553.95, "total_tokens": 44236880} {"current_steps": 27090, "total_steps": 40000, "loss": 0.1678, "lr": 1.1788856415554297e-05, "epoch": 1.2263518866429752, "percentage": 67.73, "elapsed_time": "22:11:00", "remaining_time": "10:34:18", "throughput": 554.04, "total_tokens": 44245680} {"current_steps": 27095, "total_steps": 40000, "loss": 0.1601, "lr": 1.1780522719651249e-05, "epoch": 1.2265782385296182, "percentage": 67.74, "elapsed_time": "22:11:03", "remaining_time": "10:33:57", "throughput": 554.12, "total_tokens": 44254000} {"current_steps": 27100, "total_steps": 40000, "loss": 0.0896, "lr": 1.1772191062357721e-05, "epoch": 1.2268045904162612, "percentage": 67.75, "elapsed_time": "22:11:06", "remaining_time": "10:33:37", "throughput": 554.21, "total_tokens": 44262512} {"current_steps": 27105, "total_steps": 40000, "loss": 0.1271, "lr": 1.1763861444958573e-05, "epoch": 1.2270309423029042, "percentage": 67.76, "elapsed_time": "22:11:09", "remaining_time": "10:33:17", "throughput": 554.29, "total_tokens": 44270768} {"current_steps": 27110, "total_steps": 40000, "loss": 0.1235, "lr": 1.1755533868738317e-05, "epoch": 1.227257294189547, "percentage": 67.77, "elapsed_time": "22:11:12", "remaining_time": "10:32:57", "throughput": 554.36, "total_tokens": 44278320} {"current_steps": 27115, "total_steps": 40000, "loss": 0.1875, "lr": 1.1747208334981185e-05, "epoch": 1.22748364607619, "percentage": 67.79, "elapsed_time": "22:11:16", "remaining_time": "10:32:36", "throughput": 554.44, "total_tokens": 44286864} {"current_steps": 27120, "total_steps": 40000, "loss": 0.1066, "lr": 1.1738884844971067e-05, "epoch": 1.227709997962833, "percentage": 67.8, "elapsed_time": "22:11:19", "remaining_time": "10:32:16", "throughput": 554.53, "total_tokens": 44295376} {"current_steps": 27125, "total_steps": 40000, "loss": 0.116, "lr": 1.1730563399991563e-05, "epoch": 1.227936349849476, "percentage": 67.81, "elapsed_time": "22:11:22", "remaining_time": "10:31:56", "throughput": 554.61, "total_tokens": 44303408} {"current_steps": 27130, "total_steps": 40000, "loss": 0.0963, "lr": 1.1722244001325938e-05, "epoch": 1.228162701736119, "percentage": 67.83, "elapsed_time": "22:11:25", "remaining_time": "10:31:36", "throughput": 554.68, "total_tokens": 44311088} {"current_steps": 27135, "total_steps": 40000, "loss": 0.1139, "lr": 1.1713926650257137e-05, "epoch": 1.228389053622762, "percentage": 67.84, "elapsed_time": "22:11:28", "remaining_time": "10:31:16", "throughput": 554.76, "total_tokens": 44318864} {"current_steps": 27140, "total_steps": 40000, "loss": 0.0991, "lr": 1.170561134806781e-05, "epoch": 1.228615405509405, "percentage": 67.85, "elapsed_time": "22:11:31", "remaining_time": "10:30:55", "throughput": 554.85, "total_tokens": 44327664} {"current_steps": 27145, "total_steps": 40000, "loss": 0.1418, "lr": 1.1697298096040287e-05, "epoch": 1.228841757396048, "percentage": 67.86, "elapsed_time": "22:11:35", "remaining_time": "10:30:35", "throughput": 554.93, "total_tokens": 44336240} {"current_steps": 27150, "total_steps": 40000, "loss": 0.133, "lr": 1.1688986895456567e-05, "epoch": 1.229068109282691, "percentage": 67.88, "elapsed_time": "22:11:38", "remaining_time": "10:30:15", "throughput": 555.01, "total_tokens": 44344368} {"current_steps": 27155, "total_steps": 40000, "loss": 0.1097, "lr": 1.1680677747598349e-05, "epoch": 1.229294461169334, "percentage": 67.89, "elapsed_time": "22:11:41", "remaining_time": "10:29:55", "throughput": 555.09, "total_tokens": 44352592} {"current_steps": 27160, "total_steps": 40000, "loss": 0.1258, "lr": 1.1672370653746995e-05, "epoch": 1.2295208130559767, "percentage": 67.9, "elapsed_time": "22:11:44", "remaining_time": "10:29:35", "throughput": 555.17, "total_tokens": 44360848} {"current_steps": 27165, "total_steps": 40000, "loss": 0.1163, "lr": 1.166406561518357e-05, "epoch": 1.2297471649426197, "percentage": 67.91, "elapsed_time": "22:11:47", "remaining_time": "10:29:15", "throughput": 555.25, "total_tokens": 44368688} {"current_steps": 27170, "total_steps": 40000, "loss": 0.1342, "lr": 1.1655762633188826e-05, "epoch": 1.2299735168292627, "percentage": 67.92, "elapsed_time": "22:11:51", "remaining_time": "10:28:54", "throughput": 555.33, "total_tokens": 44377072} {"current_steps": 27175, "total_steps": 40000, "loss": 0.1282, "lr": 1.1647461709043172e-05, "epoch": 1.2301998687159057, "percentage": 67.94, "elapsed_time": "22:11:54", "remaining_time": "10:28:34", "throughput": 555.41, "total_tokens": 44384976} {"current_steps": 27180, "total_steps": 40000, "loss": 0.1132, "lr": 1.1639162844026722e-05, "epoch": 1.2304262206025487, "percentage": 67.95, "elapsed_time": "22:11:57", "remaining_time": "10:28:14", "throughput": 555.49, "total_tokens": 44392880} {"current_steps": 27185, "total_steps": 40000, "loss": 0.1067, "lr": 1.163086603941927e-05, "epoch": 1.2306525724891917, "percentage": 67.96, "elapsed_time": "22:12:00", "remaining_time": "10:27:54", "throughput": 555.56, "total_tokens": 44400944} {"current_steps": 27190, "total_steps": 40000, "loss": 0.1387, "lr": 1.1622571296500273e-05, "epoch": 1.2308789243758347, "percentage": 67.97, "elapsed_time": "22:12:03", "remaining_time": "10:27:34", "throughput": 555.64, "total_tokens": 44408656} {"current_steps": 27195, "total_steps": 40000, "loss": 0.1266, "lr": 1.1614278616548904e-05, "epoch": 1.2311052762624777, "percentage": 67.99, "elapsed_time": "22:12:06", "remaining_time": "10:27:14", "throughput": 555.71, "total_tokens": 44416400} {"current_steps": 27200, "total_steps": 40000, "loss": 0.0845, "lr": 1.1605988000843986e-05, "epoch": 1.2313316281491207, "percentage": 68.0, "elapsed_time": "22:12:09", "remaining_time": "10:26:54", "throughput": 555.79, "total_tokens": 44424592} {"current_steps": 27200, "total_steps": 40000, "eval_loss": 0.12359113991260529, "epoch": 1.2313316281491207, "percentage": 68.0, "elapsed_time": "22:19:52", "remaining_time": "10:30:31", "throughput": 552.6, "total_tokens": 44424592} {"current_steps": 27205, "total_steps": 40000, "loss": 0.1434, "lr": 1.1597699450664028e-05, "epoch": 1.2315579800357637, "percentage": 68.01, "elapsed_time": "22:19:56", "remaining_time": "10:30:11", "throughput": 552.67, "total_tokens": 44432752} {"current_steps": 27210, "total_steps": 40000, "loss": 0.1559, "lr": 1.1589412967287252e-05, "epoch": 1.2317843319224067, "percentage": 68.03, "elapsed_time": "22:19:59", "remaining_time": "10:29:51", "throughput": 552.75, "total_tokens": 44440880} {"current_steps": 27215, "total_steps": 40000, "loss": 0.1234, "lr": 1.1581128551991514e-05, "epoch": 1.2320106838090497, "percentage": 68.04, "elapsed_time": "22:20:02", "remaining_time": "10:29:31", "throughput": 552.83, "total_tokens": 44449168} {"current_steps": 27220, "total_steps": 40000, "loss": 0.0869, "lr": 1.1572846206054383e-05, "epoch": 1.2322370356956924, "percentage": 68.05, "elapsed_time": "22:20:06", "remaining_time": "10:29:11", "throughput": 552.9, "total_tokens": 44456624} {"current_steps": 27225, "total_steps": 40000, "loss": 0.0865, "lr": 1.1564565930753113e-05, "epoch": 1.2324633875823354, "percentage": 68.06, "elapsed_time": "22:20:09", "remaining_time": "10:28:51", "throughput": 552.98, "total_tokens": 44464336} {"current_steps": 27230, "total_steps": 40000, "loss": 0.1196, "lr": 1.1556287727364606e-05, "epoch": 1.2326897394689784, "percentage": 68.08, "elapsed_time": "22:20:12", "remaining_time": "10:28:30", "throughput": 553.05, "total_tokens": 44472368} {"current_steps": 27235, "total_steps": 40000, "loss": 0.1536, "lr": 1.1548011597165489e-05, "epoch": 1.2329160913556214, "percentage": 68.09, "elapsed_time": "22:20:15", "remaining_time": "10:28:10", "throughput": 553.13, "total_tokens": 44480272} {"current_steps": 27240, "total_steps": 40000, "loss": 0.1671, "lr": 1.1539737541432019e-05, "epoch": 1.2331424432422644, "percentage": 68.1, "elapsed_time": "22:20:18", "remaining_time": "10:27:50", "throughput": 553.21, "total_tokens": 44488336} {"current_steps": 27245, "total_steps": 40000, "loss": 0.1005, "lr": 1.1531465561440174e-05, "epoch": 1.2333687951289074, "percentage": 68.11, "elapsed_time": "22:20:21", "remaining_time": "10:27:30", "throughput": 553.29, "total_tokens": 44496240} {"current_steps": 27250, "total_steps": 40000, "loss": 0.1466, "lr": 1.1523195658465605e-05, "epoch": 1.2335951470155504, "percentage": 68.12, "elapsed_time": "22:20:24", "remaining_time": "10:27:09", "throughput": 553.37, "total_tokens": 44504432} {"current_steps": 27255, "total_steps": 40000, "loss": 0.1036, "lr": 1.1514927833783618e-05, "epoch": 1.2338214989021934, "percentage": 68.14, "elapsed_time": "22:20:28", "remaining_time": "10:26:49", "throughput": 553.45, "total_tokens": 44512528} {"current_steps": 27260, "total_steps": 40000, "loss": 0.1358, "lr": 1.150666208866922e-05, "epoch": 1.2340478507888364, "percentage": 68.15, "elapsed_time": "22:20:31", "remaining_time": "10:26:29", "throughput": 553.52, "total_tokens": 44520016} {"current_steps": 27265, "total_steps": 40000, "loss": 0.1181, "lr": 1.1498398424397106e-05, "epoch": 1.2342742026754794, "percentage": 68.16, "elapsed_time": "22:20:34", "remaining_time": "10:26:09", "throughput": 553.6, "total_tokens": 44528240} {"current_steps": 27270, "total_steps": 40000, "loss": 0.1148, "lr": 1.1490136842241628e-05, "epoch": 1.2345005545621222, "percentage": 68.17, "elapsed_time": "22:20:37", "remaining_time": "10:25:49", "throughput": 553.67, "total_tokens": 44536112} {"current_steps": 27275, "total_steps": 40000, "loss": 0.1321, "lr": 1.1481877343476813e-05, "epoch": 1.2347269064487651, "percentage": 68.19, "elapsed_time": "22:20:40", "remaining_time": "10:25:29", "throughput": 553.76, "total_tokens": 44544624} {"current_steps": 27280, "total_steps": 40000, "loss": 0.1327, "lr": 1.14736199293764e-05, "epoch": 1.2349532583354081, "percentage": 68.2, "elapsed_time": "22:20:43", "remaining_time": "10:25:09", "throughput": 553.84, "total_tokens": 44552912} {"current_steps": 27285, "total_steps": 40000, "loss": 0.1583, "lr": 1.1465364601213771e-05, "epoch": 1.2351796102220511, "percentage": 68.21, "elapsed_time": "22:20:47", "remaining_time": "10:24:48", "throughput": 553.92, "total_tokens": 44561584} {"current_steps": 27290, "total_steps": 40000, "loss": 0.1427, "lr": 1.1457111360262012e-05, "epoch": 1.2354059621086941, "percentage": 68.23, "elapsed_time": "22:20:50", "remaining_time": "10:24:28", "throughput": 554.0, "total_tokens": 44569424} {"current_steps": 27295, "total_steps": 40000, "loss": 0.1261, "lr": 1.1448860207793869e-05, "epoch": 1.2356323139953371, "percentage": 68.24, "elapsed_time": "22:20:53", "remaining_time": "10:24:08", "throughput": 554.08, "total_tokens": 44577520} {"current_steps": 27300, "total_steps": 40000, "loss": 0.1477, "lr": 1.144061114508177e-05, "epoch": 1.2358586658819801, "percentage": 68.25, "elapsed_time": "22:20:56", "remaining_time": "10:23:48", "throughput": 554.16, "total_tokens": 44585840} {"current_steps": 27305, "total_steps": 40000, "loss": 0.1441, "lr": 1.1432364173397842e-05, "epoch": 1.2360850177686231, "percentage": 68.26, "elapsed_time": "22:20:59", "remaining_time": "10:23:28", "throughput": 554.24, "total_tokens": 44593776} {"current_steps": 27310, "total_steps": 40000, "loss": 0.1339, "lr": 1.1424119294013852e-05, "epoch": 1.2363113696552661, "percentage": 68.27, "elapsed_time": "22:21:03", "remaining_time": "10:23:08", "throughput": 554.32, "total_tokens": 44602064} {"current_steps": 27315, "total_steps": 40000, "loss": 0.1394, "lr": 1.1415876508201279e-05, "epoch": 1.236537721541909, "percentage": 68.29, "elapsed_time": "22:21:06", "remaining_time": "10:22:48", "throughput": 554.39, "total_tokens": 44609712} {"current_steps": 27320, "total_steps": 40000, "loss": 0.1043, "lr": 1.140763581723125e-05, "epoch": 1.236764073428552, "percentage": 68.3, "elapsed_time": "22:21:09", "remaining_time": "10:22:28", "throughput": 554.47, "total_tokens": 44617936} {"current_steps": 27325, "total_steps": 40000, "loss": 0.1275, "lr": 1.1399397222374588e-05, "epoch": 1.236990425315195, "percentage": 68.31, "elapsed_time": "22:21:12", "remaining_time": "10:22:08", "throughput": 554.54, "total_tokens": 44625584} {"current_steps": 27330, "total_steps": 40000, "loss": 0.103, "lr": 1.1391160724901804e-05, "epoch": 1.237216777201838, "percentage": 68.33, "elapsed_time": "22:21:15", "remaining_time": "10:21:47", "throughput": 554.63, "total_tokens": 44633936} {"current_steps": 27335, "total_steps": 40000, "loss": 0.1175, "lr": 1.138292632608304e-05, "epoch": 1.2374431290884809, "percentage": 68.34, "elapsed_time": "22:21:18", "remaining_time": "10:21:27", "throughput": 554.7, "total_tokens": 44641360} {"current_steps": 27340, "total_steps": 40000, "loss": 0.0794, "lr": 1.1374694027188174e-05, "epoch": 1.2376694809751239, "percentage": 68.35, "elapsed_time": "22:21:21", "remaining_time": "10:21:07", "throughput": 554.78, "total_tokens": 44649584} {"current_steps": 27345, "total_steps": 40000, "loss": 0.1196, "lr": 1.1366463829486711e-05, "epoch": 1.2378958328617669, "percentage": 68.36, "elapsed_time": "22:21:25", "remaining_time": "10:20:47", "throughput": 554.85, "total_tokens": 44657232} {"current_steps": 27350, "total_steps": 40000, "loss": 0.1311, "lr": 1.1358235734247849e-05, "epoch": 1.2381221847484098, "percentage": 68.38, "elapsed_time": "22:21:28", "remaining_time": "10:20:27", "throughput": 554.92, "total_tokens": 44664688} {"current_steps": 27355, "total_steps": 40000, "loss": 0.1231, "lr": 1.1350009742740478e-05, "epoch": 1.2383485366350528, "percentage": 68.39, "elapsed_time": "22:21:31", "remaining_time": "10:20:07", "throughput": 555.01, "total_tokens": 44673680} {"current_steps": 27360, "total_steps": 40000, "loss": 0.1165, "lr": 1.134178585623313e-05, "epoch": 1.2385748885216958, "percentage": 68.4, "elapsed_time": "22:21:34", "remaining_time": "10:19:47", "throughput": 555.09, "total_tokens": 44681488} {"current_steps": 27365, "total_steps": 40000, "loss": 0.1327, "lr": 1.1333564075994047e-05, "epoch": 1.2388012404083388, "percentage": 68.41, "elapsed_time": "22:21:38", "remaining_time": "10:19:27", "throughput": 555.17, "total_tokens": 44689744} {"current_steps": 27370, "total_steps": 40000, "loss": 0.146, "lr": 1.1325344403291133e-05, "epoch": 1.2390275922949818, "percentage": 68.42, "elapsed_time": "22:21:41", "remaining_time": "10:19:07", "throughput": 555.24, "total_tokens": 44697328} {"current_steps": 27375, "total_steps": 40000, "loss": 0.1238, "lr": 1.1317126839391951e-05, "epoch": 1.2392539441816248, "percentage": 68.44, "elapsed_time": "22:21:44", "remaining_time": "10:18:47", "throughput": 555.32, "total_tokens": 44705936} {"current_steps": 27380, "total_steps": 40000, "loss": 0.1273, "lr": 1.1308911385563766e-05, "epoch": 1.2394802960682678, "percentage": 68.45, "elapsed_time": "22:21:47", "remaining_time": "10:18:27", "throughput": 555.4, "total_tokens": 44713872} {"current_steps": 27385, "total_steps": 40000, "loss": 0.1221, "lr": 1.1300698043073494e-05, "epoch": 1.2397066479549106, "percentage": 68.46, "elapsed_time": "22:21:50", "remaining_time": "10:18:07", "throughput": 555.48, "total_tokens": 44721936} {"current_steps": 27390, "total_steps": 40000, "loss": 0.1061, "lr": 1.1292486813187736e-05, "epoch": 1.2399329998415536, "percentage": 68.47, "elapsed_time": "22:21:53", "remaining_time": "10:17:47", "throughput": 555.56, "total_tokens": 44729872} {"current_steps": 27395, "total_steps": 40000, "loss": 0.1096, "lr": 1.1284277697172782e-05, "epoch": 1.2401593517281966, "percentage": 68.49, "elapsed_time": "22:21:56", "remaining_time": "10:17:27", "throughput": 555.63, "total_tokens": 44737968} {"current_steps": 27400, "total_steps": 40000, "loss": 0.1236, "lr": 1.127607069629456e-05, "epoch": 1.2403857036148396, "percentage": 68.5, "elapsed_time": "22:22:00", "remaining_time": "10:17:07", "throughput": 555.71, "total_tokens": 44745968} {"current_steps": 27400, "total_steps": 40000, "eval_loss": 0.12303135544061661, "epoch": 1.2403857036148396, "percentage": 68.5, "elapsed_time": "22:29:42", "remaining_time": "10:20:40", "throughput": 552.54, "total_tokens": 44745968} {"current_steps": 27405, "total_steps": 40000, "loss": 0.1273, "lr": 1.1267865811818701e-05, "epoch": 1.2406120555014826, "percentage": 68.51, "elapsed_time": "22:29:46", "remaining_time": "10:20:20", "throughput": 552.61, "total_tokens": 44754384} {"current_steps": 27410, "total_steps": 40000, "loss": 0.1824, "lr": 1.1259663045010513e-05, "epoch": 1.2408384073881256, "percentage": 68.53, "elapsed_time": "22:29:50", "remaining_time": "10:20:00", "throughput": 552.7, "total_tokens": 44762960} {"current_steps": 27415, "total_steps": 40000, "loss": 0.1032, "lr": 1.1251462397134957e-05, "epoch": 1.2410647592747686, "percentage": 68.54, "elapsed_time": "22:29:53", "remaining_time": "10:19:40", "throughput": 552.78, "total_tokens": 44771408} {"current_steps": 27420, "total_steps": 40000, "loss": 0.1503, "lr": 1.1243263869456664e-05, "epoch": 1.2412911111614116, "percentage": 68.55, "elapsed_time": "22:29:56", "remaining_time": "10:19:20", "throughput": 552.86, "total_tokens": 44780144} {"current_steps": 27425, "total_steps": 40000, "loss": 0.1303, "lr": 1.1235067463239967e-05, "epoch": 1.2415174630480545, "percentage": 68.56, "elapsed_time": "22:29:59", "remaining_time": "10:19:00", "throughput": 552.94, "total_tokens": 44788176} {"current_steps": 27430, "total_steps": 40000, "loss": 0.1043, "lr": 1.122687317974884e-05, "epoch": 1.2417438149346975, "percentage": 68.58, "elapsed_time": "22:30:03", "remaining_time": "10:18:40", "throughput": 553.02, "total_tokens": 44796336} {"current_steps": 27435, "total_steps": 40000, "loss": 0.0977, "lr": 1.1218681020246963e-05, "epoch": 1.2419701668213405, "percentage": 68.59, "elapsed_time": "22:30:06", "remaining_time": "10:18:20", "throughput": 553.1, "total_tokens": 44804496} {"current_steps": 27440, "total_steps": 40000, "loss": 0.148, "lr": 1.1210490985997652e-05, "epoch": 1.2421965187079835, "percentage": 68.6, "elapsed_time": "22:30:09", "remaining_time": "10:18:00", "throughput": 553.17, "total_tokens": 44812304} {"current_steps": 27445, "total_steps": 40000, "loss": 0.1271, "lr": 1.1202303078263917e-05, "epoch": 1.2424228705946265, "percentage": 68.61, "elapsed_time": "22:30:12", "remaining_time": "10:17:39", "throughput": 553.25, "total_tokens": 44820432} {"current_steps": 27450, "total_steps": 40000, "loss": 0.1351, "lr": 1.1194117298308451e-05, "epoch": 1.2426492224812693, "percentage": 68.62, "elapsed_time": "22:30:15", "remaining_time": "10:17:19", "throughput": 553.33, "total_tokens": 44828368} {"current_steps": 27455, "total_steps": 40000, "loss": 0.1102, "lr": 1.1185933647393585e-05, "epoch": 1.2428755743679123, "percentage": 68.64, "elapsed_time": "22:30:18", "remaining_time": "10:16:59", "throughput": 553.41, "total_tokens": 44836368} {"current_steps": 27460, "total_steps": 40000, "loss": 0.141, "lr": 1.1177752126781354e-05, "epoch": 1.2431019262545553, "percentage": 68.65, "elapsed_time": "22:30:21", "remaining_time": "10:16:39", "throughput": 553.48, "total_tokens": 44844304} {"current_steps": 27465, "total_steps": 40000, "loss": 0.1535, "lr": 1.1169572737733441e-05, "epoch": 1.2433282781411983, "percentage": 68.66, "elapsed_time": "22:30:25", "remaining_time": "10:16:19", "throughput": 553.57, "total_tokens": 44852720} {"current_steps": 27470, "total_steps": 40000, "loss": 0.1848, "lr": 1.1161395481511216e-05, "epoch": 1.2435546300278413, "percentage": 68.67, "elapsed_time": "22:30:28", "remaining_time": "10:15:59", "throughput": 553.65, "total_tokens": 44861008} {"current_steps": 27475, "total_steps": 40000, "loss": 0.0881, "lr": 1.1153220359375722e-05, "epoch": 1.2437809819144843, "percentage": 68.69, "elapsed_time": "22:30:31", "remaining_time": "10:15:39", "throughput": 553.73, "total_tokens": 44869232} {"current_steps": 27480, "total_steps": 40000, "loss": 0.0924, "lr": 1.114504737258765e-05, "epoch": 1.2440073338011273, "percentage": 68.7, "elapsed_time": "22:30:34", "remaining_time": "10:15:19", "throughput": 553.81, "total_tokens": 44877936} {"current_steps": 27485, "total_steps": 40000, "loss": 0.138, "lr": 1.1136876522407393e-05, "epoch": 1.2442336856877703, "percentage": 68.71, "elapsed_time": "22:30:37", "remaining_time": "10:14:59", "throughput": 553.89, "total_tokens": 44886000} {"current_steps": 27490, "total_steps": 40000, "loss": 0.1216, "lr": 1.1128707810094985e-05, "epoch": 1.2444600375744133, "percentage": 68.73, "elapsed_time": "22:30:41", "remaining_time": "10:14:39", "throughput": 553.96, "total_tokens": 44893840} {"current_steps": 27495, "total_steps": 40000, "loss": 0.0824, "lr": 1.1120541236910157e-05, "epoch": 1.2446863894610563, "percentage": 68.74, "elapsed_time": "22:30:44", "remaining_time": "10:14:19", "throughput": 554.04, "total_tokens": 44901776} {"current_steps": 27500, "total_steps": 40000, "loss": 0.1834, "lr": 1.111237680411229e-05, "epoch": 1.244912741347699, "percentage": 68.75, "elapsed_time": "22:30:47", "remaining_time": "10:13:59", "throughput": 554.12, "total_tokens": 44910224} {"current_steps": 27505, "total_steps": 40000, "loss": 0.0969, "lr": 1.1104214512960433e-05, "epoch": 1.245139093234342, "percentage": 68.76, "elapsed_time": "22:30:50", "remaining_time": "10:13:39", "throughput": 554.2, "total_tokens": 44917968} {"current_steps": 27510, "total_steps": 40000, "loss": 0.1178, "lr": 1.1096054364713327e-05, "epoch": 1.245365445120985, "percentage": 68.77, "elapsed_time": "22:30:53", "remaining_time": "10:13:19", "throughput": 554.27, "total_tokens": 44925584} {"current_steps": 27515, "total_steps": 40000, "loss": 0.1411, "lr": 1.1087896360629371e-05, "epoch": 1.245591797007628, "percentage": 68.79, "elapsed_time": "22:30:56", "remaining_time": "10:12:59", "throughput": 554.35, "total_tokens": 44933744} {"current_steps": 27520, "total_steps": 40000, "loss": 0.1224, "lr": 1.107974050196662e-05, "epoch": 1.245818148894271, "percentage": 68.8, "elapsed_time": "22:30:59", "remaining_time": "10:12:39", "throughput": 554.43, "total_tokens": 44941648} {"current_steps": 27525, "total_steps": 40000, "loss": 0.1696, "lr": 1.1071586789982816e-05, "epoch": 1.246044500780914, "percentage": 68.81, "elapsed_time": "22:31:03", "remaining_time": "10:12:19", "throughput": 554.5, "total_tokens": 44949296} {"current_steps": 27530, "total_steps": 40000, "loss": 0.1627, "lr": 1.1063435225935373e-05, "epoch": 1.246270852667557, "percentage": 68.83, "elapsed_time": "22:31:06", "remaining_time": "10:11:59", "throughput": 554.58, "total_tokens": 44957456} {"current_steps": 27535, "total_steps": 40000, "loss": 0.0964, "lr": 1.1055285811081348e-05, "epoch": 1.2464972045542, "percentage": 68.84, "elapsed_time": "22:31:09", "remaining_time": "10:11:39", "throughput": 554.66, "total_tokens": 44965744} {"current_steps": 27540, "total_steps": 40000, "loss": 0.0725, "lr": 1.1047138546677499e-05, "epoch": 1.246723556440843, "percentage": 68.85, "elapsed_time": "22:31:12", "remaining_time": "10:11:19", "throughput": 554.73, "total_tokens": 44973744} {"current_steps": 27545, "total_steps": 40000, "loss": 0.0773, "lr": 1.1038993433980219e-05, "epoch": 1.246949908327486, "percentage": 68.86, "elapsed_time": "22:31:15", "remaining_time": "10:10:59", "throughput": 554.82, "total_tokens": 44982128} {"current_steps": 27550, "total_steps": 40000, "loss": 0.1211, "lr": 1.1030850474245597e-05, "epoch": 1.247176260214129, "percentage": 68.88, "elapsed_time": "22:31:18", "remaining_time": "10:10:40", "throughput": 554.89, "total_tokens": 44990096} {"current_steps": 27555, "total_steps": 40000, "loss": 0.1191, "lr": 1.102270966872939e-05, "epoch": 1.247402612100772, "percentage": 68.89, "elapsed_time": "22:31:22", "remaining_time": "10:10:20", "throughput": 554.97, "total_tokens": 44998160} {"current_steps": 27560, "total_steps": 40000, "loss": 0.129, "lr": 1.1014571018687e-05, "epoch": 1.2476289639874147, "percentage": 68.9, "elapsed_time": "22:31:25", "remaining_time": "10:10:00", "throughput": 555.05, "total_tokens": 45006064} {"current_steps": 27565, "total_steps": 40000, "loss": 0.1508, "lr": 1.1006434525373502e-05, "epoch": 1.2478553158740577, "percentage": 68.91, "elapsed_time": "22:31:28", "remaining_time": "10:09:40", "throughput": 555.12, "total_tokens": 45014128} {"current_steps": 27570, "total_steps": 40000, "loss": 0.1141, "lr": 1.0998300190043664e-05, "epoch": 1.2480816677607007, "percentage": 68.92, "elapsed_time": "22:31:31", "remaining_time": "10:09:20", "throughput": 555.2, "total_tokens": 45022448} {"current_steps": 27575, "total_steps": 40000, "loss": 0.0734, "lr": 1.0990168013951882e-05, "epoch": 1.2483080196473437, "percentage": 68.94, "elapsed_time": "22:31:34", "remaining_time": "10:09:00", "throughput": 555.29, "total_tokens": 45030832} {"current_steps": 27580, "total_steps": 40000, "loss": 0.1179, "lr": 1.0982037998352263e-05, "epoch": 1.2485343715339867, "percentage": 68.95, "elapsed_time": "22:31:38", "remaining_time": "10:08:40", "throughput": 555.37, "total_tokens": 45039120} {"current_steps": 27585, "total_steps": 40000, "loss": 0.0897, "lr": 1.0973910144498534e-05, "epoch": 1.2487607234206297, "percentage": 68.96, "elapsed_time": "22:31:41", "remaining_time": "10:08:20", "throughput": 555.44, "total_tokens": 45046640} {"current_steps": 27590, "total_steps": 40000, "loss": 0.1193, "lr": 1.0965784453644123e-05, "epoch": 1.2489870753072727, "percentage": 68.97, "elapsed_time": "22:31:44", "remaining_time": "10:08:00", "throughput": 555.52, "total_tokens": 45054800} {"current_steps": 27595, "total_steps": 40000, "loss": 0.1365, "lr": 1.0957660927042127e-05, "epoch": 1.2492134271939157, "percentage": 68.99, "elapsed_time": "22:31:47", "remaining_time": "10:07:40", "throughput": 555.6, "total_tokens": 45063312} {"current_steps": 27600, "total_steps": 40000, "loss": 0.1298, "lr": 1.094953956594527e-05, "epoch": 1.2494397790805587, "percentage": 69.0, "elapsed_time": "22:31:50", "remaining_time": "10:07:21", "throughput": 555.67, "total_tokens": 45070992} {"current_steps": 27600, "total_steps": 40000, "eval_loss": 0.12293536216020584, "epoch": 1.2494397790805587, "percentage": 69.0, "elapsed_time": "22:39:33", "remaining_time": "10:10:48", "throughput": 552.52, "total_tokens": 45070992} {"current_steps": 27605, "total_steps": 40000, "loss": 0.0781, "lr": 1.0941420371605981e-05, "epoch": 1.2496661309672017, "percentage": 69.01, "elapsed_time": "22:39:37", "remaining_time": "10:10:29", "throughput": 552.59, "total_tokens": 45079024} {"current_steps": 27610, "total_steps": 40000, "loss": 0.1111, "lr": 1.0933303345276354e-05, "epoch": 1.2498924828538445, "percentage": 69.03, "elapsed_time": "22:39:40", "remaining_time": "10:10:09", "throughput": 552.67, "total_tokens": 45086544} {"current_steps": 27615, "total_steps": 40000, "loss": 0.1247, "lr": 1.0925188488208112e-05, "epoch": 1.2501188347404875, "percentage": 69.04, "elapsed_time": "22:39:43", "remaining_time": "10:09:49", "throughput": 552.74, "total_tokens": 45094160} {"current_steps": 27620, "total_steps": 40000, "loss": 0.0829, "lr": 1.0917075801652694e-05, "epoch": 1.2503451866271305, "percentage": 69.05, "elapsed_time": "22:39:46", "remaining_time": "10:09:29", "throughput": 552.82, "total_tokens": 45102704} {"current_steps": 27625, "total_steps": 40000, "loss": 0.1028, "lr": 1.0908965286861151e-05, "epoch": 1.2505715385137735, "percentage": 69.06, "elapsed_time": "22:39:49", "remaining_time": "10:09:09", "throughput": 552.9, "total_tokens": 45110576} {"current_steps": 27630, "total_steps": 40000, "loss": 0.0959, "lr": 1.090085694508425e-05, "epoch": 1.2507978904004164, "percentage": 69.08, "elapsed_time": "22:39:52", "remaining_time": "10:08:49", "throughput": 552.97, "total_tokens": 45118224} {"current_steps": 27635, "total_steps": 40000, "loss": 0.1906, "lr": 1.089275077757238e-05, "epoch": 1.2510242422870594, "percentage": 69.09, "elapsed_time": "22:39:55", "remaining_time": "10:08:29", "throughput": 553.05, "total_tokens": 45126512} {"current_steps": 27640, "total_steps": 40000, "loss": 0.1031, "lr": 1.0884646785575633e-05, "epoch": 1.2512505941737024, "percentage": 69.1, "elapsed_time": "22:39:59", "remaining_time": "10:08:09", "throughput": 553.13, "total_tokens": 45134608} {"current_steps": 27645, "total_steps": 40000, "loss": 0.1085, "lr": 1.0876544970343728e-05, "epoch": 1.2514769460603454, "percentage": 69.11, "elapsed_time": "22:40:02", "remaining_time": "10:07:49", "throughput": 553.21, "total_tokens": 45143088} {"current_steps": 27650, "total_steps": 40000, "loss": 0.1536, "lr": 1.0868445333126082e-05, "epoch": 1.2517032979469884, "percentage": 69.12, "elapsed_time": "22:40:05", "remaining_time": "10:07:29", "throughput": 553.29, "total_tokens": 45151408} {"current_steps": 27655, "total_steps": 40000, "loss": 0.0734, "lr": 1.0860347875171745e-05, "epoch": 1.2519296498336314, "percentage": 69.14, "elapsed_time": "22:40:08", "remaining_time": "10:07:09", "throughput": 553.37, "total_tokens": 45159856} {"current_steps": 27660, "total_steps": 40000, "loss": 0.0883, "lr": 1.0852252597729465e-05, "epoch": 1.2521560017202744, "percentage": 69.15, "elapsed_time": "22:40:12", "remaining_time": "10:06:49", "throughput": 553.45, "total_tokens": 45168304} {"current_steps": 27665, "total_steps": 40000, "loss": 0.1203, "lr": 1.0844159502047615e-05, "epoch": 1.2523823536069174, "percentage": 69.16, "elapsed_time": "22:40:15", "remaining_time": "10:06:29", "throughput": 553.53, "total_tokens": 45176304} {"current_steps": 27670, "total_steps": 40000, "loss": 0.1255, "lr": 1.0836068589374265e-05, "epoch": 1.2526087054935604, "percentage": 69.17, "elapsed_time": "22:40:18", "remaining_time": "10:06:09", "throughput": 553.6, "total_tokens": 45184144} {"current_steps": 27675, "total_steps": 40000, "loss": 0.1122, "lr": 1.0827979860957144e-05, "epoch": 1.2528350573802034, "percentage": 69.19, "elapsed_time": "22:40:21", "remaining_time": "10:05:50", "throughput": 553.69, "total_tokens": 45192784} {"current_steps": 27680, "total_steps": 40000, "loss": 0.0757, "lr": 1.0819893318043615e-05, "epoch": 1.2530614092668462, "percentage": 69.2, "elapsed_time": "22:40:24", "remaining_time": "10:05:30", "throughput": 553.77, "total_tokens": 45201328} {"current_steps": 27685, "total_steps": 40000, "loss": 0.1241, "lr": 1.0811808961880734e-05, "epoch": 1.2532877611534892, "percentage": 69.21, "elapsed_time": "22:40:28", "remaining_time": "10:05:10", "throughput": 553.85, "total_tokens": 45209392} {"current_steps": 27690, "total_steps": 40000, "loss": 0.0955, "lr": 1.080372679371522e-05, "epoch": 1.2535141130401322, "percentage": 69.23, "elapsed_time": "22:40:31", "remaining_time": "10:04:50", "throughput": 553.93, "total_tokens": 45218192} {"current_steps": 27695, "total_steps": 40000, "loss": 0.122, "lr": 1.0795646814793428e-05, "epoch": 1.2537404649267752, "percentage": 69.24, "elapsed_time": "22:40:34", "remaining_time": "10:04:30", "throughput": 554.01, "total_tokens": 45226192} {"current_steps": 27700, "total_steps": 40000, "loss": 0.0687, "lr": 1.078756902636141e-05, "epoch": 1.2539668168134182, "percentage": 69.25, "elapsed_time": "22:40:37", "remaining_time": "10:04:10", "throughput": 554.09, "total_tokens": 45234288} {"current_steps": 27705, "total_steps": 40000, "loss": 0.0947, "lr": 1.077949342966485e-05, "epoch": 1.2541931687000611, "percentage": 69.26, "elapsed_time": "22:40:40", "remaining_time": "10:03:50", "throughput": 554.16, "total_tokens": 45242384} {"current_steps": 27710, "total_steps": 40000, "loss": 0.0822, "lr": 1.0771420025949103e-05, "epoch": 1.2544195205867041, "percentage": 69.27, "elapsed_time": "22:40:44", "remaining_time": "10:03:30", "throughput": 554.25, "total_tokens": 45250960} {"current_steps": 27715, "total_steps": 40000, "loss": 0.1147, "lr": 1.0763348816459204e-05, "epoch": 1.2546458724733471, "percentage": 69.29, "elapsed_time": "22:40:47", "remaining_time": "10:03:11", "throughput": 554.33, "total_tokens": 45259344} {"current_steps": 27720, "total_steps": 40000, "loss": 0.0863, "lr": 1.0755279802439816e-05, "epoch": 1.25487222435999, "percentage": 69.3, "elapsed_time": "22:40:50", "remaining_time": "10:02:51", "throughput": 554.4, "total_tokens": 45267248} {"current_steps": 27725, "total_steps": 40000, "loss": 0.1212, "lr": 1.0747212985135293e-05, "epoch": 1.255098576246633, "percentage": 69.31, "elapsed_time": "22:40:53", "remaining_time": "10:02:31", "throughput": 554.48, "total_tokens": 45275344} {"current_steps": 27730, "total_steps": 40000, "loss": 0.1233, "lr": 1.073914836578965e-05, "epoch": 1.255324928133276, "percentage": 69.33, "elapsed_time": "22:40:56", "remaining_time": "10:02:11", "throughput": 554.55, "total_tokens": 45283056} {"current_steps": 27735, "total_steps": 40000, "loss": 0.0742, "lr": 1.0731085945646529e-05, "epoch": 1.255551280019919, "percentage": 69.34, "elapsed_time": "22:41:00", "remaining_time": "10:01:51", "throughput": 554.63, "total_tokens": 45291312} {"current_steps": 27740, "total_steps": 40000, "loss": 0.151, "lr": 1.0723025725949285e-05, "epoch": 1.2557776319065619, "percentage": 69.35, "elapsed_time": "22:41:03", "remaining_time": "10:01:31", "throughput": 554.72, "total_tokens": 45299888} {"current_steps": 27745, "total_steps": 40000, "loss": 0.1295, "lr": 1.0714967707940875e-05, "epoch": 1.2560039837932049, "percentage": 69.36, "elapsed_time": "22:41:06", "remaining_time": "10:01:12", "throughput": 554.8, "total_tokens": 45308272} {"current_steps": 27750, "total_steps": 40000, "loss": 0.1273, "lr": 1.0706911892863963e-05, "epoch": 1.2562303356798479, "percentage": 69.38, "elapsed_time": "22:41:09", "remaining_time": "10:00:52", "throughput": 554.88, "total_tokens": 45316656} {"current_steps": 27755, "total_steps": 40000, "loss": 0.103, "lr": 1.0698858281960866e-05, "epoch": 1.2564566875664909, "percentage": 69.39, "elapsed_time": "22:41:12", "remaining_time": "10:00:32", "throughput": 554.95, "total_tokens": 45324784} {"current_steps": 27760, "total_steps": 40000, "loss": 0.1109, "lr": 1.069080687647353e-05, "epoch": 1.2566830394531339, "percentage": 69.4, "elapsed_time": "22:41:16", "remaining_time": "10:00:12", "throughput": 555.03, "total_tokens": 45332592} {"current_steps": 27765, "total_steps": 40000, "loss": 0.1298, "lr": 1.0682757677643596e-05, "epoch": 1.2569093913397769, "percentage": 69.41, "elapsed_time": "22:41:19", "remaining_time": "9:59:53", "throughput": 555.11, "total_tokens": 45340752} {"current_steps": 27770, "total_steps": 40000, "loss": 0.0714, "lr": 1.0674710686712359e-05, "epoch": 1.2571357432264199, "percentage": 69.42, "elapsed_time": "22:41:22", "remaining_time": "9:59:33", "throughput": 555.19, "total_tokens": 45348880} {"current_steps": 27775, "total_steps": 40000, "loss": 0.0895, "lr": 1.0666665904920756e-05, "epoch": 1.2573620951130628, "percentage": 69.44, "elapsed_time": "22:41:25", "remaining_time": "9:59:13", "throughput": 555.27, "total_tokens": 45357392} {"current_steps": 27780, "total_steps": 40000, "loss": 0.1319, "lr": 1.0658623333509385e-05, "epoch": 1.2575884469997058, "percentage": 69.45, "elapsed_time": "22:41:28", "remaining_time": "9:58:53", "throughput": 555.34, "total_tokens": 45364944} {"current_steps": 27785, "total_steps": 40000, "loss": 0.1202, "lr": 1.0650582973718532e-05, "epoch": 1.2578147988863488, "percentage": 69.46, "elapsed_time": "22:41:32", "remaining_time": "9:58:33", "throughput": 555.42, "total_tokens": 45373744} {"current_steps": 27790, "total_steps": 40000, "loss": 0.1031, "lr": 1.0642544826788098e-05, "epoch": 1.2580411507729916, "percentage": 69.47, "elapsed_time": "22:41:35", "remaining_time": "9:58:14", "throughput": 555.5, "total_tokens": 45381968} {"current_steps": 27795, "total_steps": 40000, "loss": 0.1211, "lr": 1.063450889395769e-05, "epoch": 1.2582675026596346, "percentage": 69.49, "elapsed_time": "22:41:38", "remaining_time": "9:57:54", "throughput": 555.59, "total_tokens": 45390512} {"current_steps": 27800, "total_steps": 40000, "loss": 0.0784, "lr": 1.062647517646653e-05, "epoch": 1.2584938545462776, "percentage": 69.5, "elapsed_time": "22:41:41", "remaining_time": "9:57:34", "throughput": 555.67, "total_tokens": 45399120} {"current_steps": 27800, "total_steps": 40000, "eval_loss": 0.12371119856834412, "epoch": 1.2584938545462776, "percentage": 69.5, "elapsed_time": "22:49:24", "remaining_time": "10:00:57", "throughput": 552.54, "total_tokens": 45399120} {"current_steps": 27805, "total_steps": 40000, "loss": 0.1507, "lr": 1.0618443675553527e-05, "epoch": 1.2587202064329206, "percentage": 69.51, "elapsed_time": "22:49:28", "remaining_time": "10:00:38", "throughput": 552.61, "total_tokens": 45407440} {"current_steps": 27810, "total_steps": 40000, "loss": 0.1643, "lr": 1.0610414392457247e-05, "epoch": 1.2589465583195636, "percentage": 69.53, "elapsed_time": "22:49:31", "remaining_time": "10:00:18", "throughput": 552.69, "total_tokens": 45415376} {"current_steps": 27815, "total_steps": 40000, "loss": 0.1388, "lr": 1.0602387328415888e-05, "epoch": 1.2591729102062066, "percentage": 69.54, "elapsed_time": "22:49:34", "remaining_time": "9:59:58", "throughput": 552.76, "total_tokens": 45423056} {"current_steps": 27820, "total_steps": 40000, "loss": 0.0977, "lr": 1.0594362484667347e-05, "epoch": 1.2593992620928496, "percentage": 69.55, "elapsed_time": "22:49:37", "remaining_time": "9:59:38", "throughput": 552.83, "total_tokens": 45430768} {"current_steps": 27825, "total_steps": 40000, "loss": 0.1087, "lr": 1.0586339862449132e-05, "epoch": 1.2596256139794926, "percentage": 69.56, "elapsed_time": "22:49:41", "remaining_time": "9:59:18", "throughput": 552.91, "total_tokens": 45438864} {"current_steps": 27830, "total_steps": 40000, "loss": 0.14, "lr": 1.0578319462998445e-05, "epoch": 1.2598519658661356, "percentage": 69.58, "elapsed_time": "22:49:44", "remaining_time": "9:58:59", "throughput": 552.99, "total_tokens": 45447344} {"current_steps": 27835, "total_steps": 40000, "loss": 0.1418, "lr": 1.057030128755214e-05, "epoch": 1.2600783177527783, "percentage": 69.59, "elapsed_time": "22:49:47", "remaining_time": "9:58:39", "throughput": 553.07, "total_tokens": 45455184} {"current_steps": 27840, "total_steps": 40000, "loss": 0.0965, "lr": 1.0562285337346703e-05, "epoch": 1.2603046696394213, "percentage": 69.6, "elapsed_time": "22:49:50", "remaining_time": "9:58:19", "throughput": 553.15, "total_tokens": 45463696} {"current_steps": 27845, "total_steps": 40000, "loss": 0.1478, "lr": 1.0554271613618308e-05, "epoch": 1.2605310215260643, "percentage": 69.61, "elapsed_time": "22:49:53", "remaining_time": "9:57:59", "throughput": 553.23, "total_tokens": 45471792} {"current_steps": 27850, "total_steps": 40000, "loss": 0.1327, "lr": 1.054626011760276e-05, "epoch": 1.2607573734127073, "percentage": 69.62, "elapsed_time": "22:49:57", "remaining_time": "9:57:39", "throughput": 553.31, "total_tokens": 45480528} {"current_steps": 27855, "total_steps": 40000, "loss": 0.1128, "lr": 1.0538250850535549e-05, "epoch": 1.2609837252993503, "percentage": 69.64, "elapsed_time": "22:50:00", "remaining_time": "9:57:20", "throughput": 553.39, "total_tokens": 45488624} {"current_steps": 27860, "total_steps": 40000, "loss": 0.1412, "lr": 1.0530243813651794e-05, "epoch": 1.2612100771859933, "percentage": 69.65, "elapsed_time": "22:50:03", "remaining_time": "9:57:00", "throughput": 553.46, "total_tokens": 45496496} {"current_steps": 27865, "total_steps": 40000, "loss": 0.1203, "lr": 1.0522239008186271e-05, "epoch": 1.2614364290726363, "percentage": 69.66, "elapsed_time": "22:50:06", "remaining_time": "9:56:40", "throughput": 553.54, "total_tokens": 45504656} {"current_steps": 27870, "total_steps": 40000, "loss": 0.0926, "lr": 1.0514236435373434e-05, "epoch": 1.2616627809592793, "percentage": 69.67, "elapsed_time": "22:50:09", "remaining_time": "9:56:20", "throughput": 553.62, "total_tokens": 45512656} {"current_steps": 27875, "total_steps": 40000, "loss": 0.1371, "lr": 1.0506236096447386e-05, "epoch": 1.2618891328459223, "percentage": 69.69, "elapsed_time": "22:50:13", "remaining_time": "9:56:00", "throughput": 553.7, "total_tokens": 45521328} {"current_steps": 27880, "total_steps": 40000, "loss": 0.1478, "lr": 1.049823799264186e-05, "epoch": 1.2621154847325653, "percentage": 69.7, "elapsed_time": "22:50:16", "remaining_time": "9:55:41", "throughput": 553.77, "total_tokens": 45529168} {"current_steps": 27885, "total_steps": 40000, "loss": 0.1487, "lr": 1.049024212519028e-05, "epoch": 1.2623418366192083, "percentage": 69.71, "elapsed_time": "22:50:19", "remaining_time": "9:55:21", "throughput": 553.86, "total_tokens": 45537776} {"current_steps": 27890, "total_steps": 40000, "loss": 0.1005, "lr": 1.0482248495325713e-05, "epoch": 1.2625681885058513, "percentage": 69.73, "elapsed_time": "22:50:22", "remaining_time": "9:55:01", "throughput": 553.93, "total_tokens": 45545840} {"current_steps": 27895, "total_steps": 40000, "loss": 0.1242, "lr": 1.047425710428086e-05, "epoch": 1.2627945403924943, "percentage": 69.74, "elapsed_time": "22:50:25", "remaining_time": "9:54:41", "throughput": 554.01, "total_tokens": 45553744} {"current_steps": 27900, "total_steps": 40000, "loss": 0.1117, "lr": 1.0466267953288114e-05, "epoch": 1.2630208922791373, "percentage": 69.75, "elapsed_time": "22:50:28", "remaining_time": "9:54:21", "throughput": 554.08, "total_tokens": 45561392} {"current_steps": 27905, "total_steps": 40000, "loss": 0.1594, "lr": 1.0458281043579482e-05, "epoch": 1.26324724416578, "percentage": 69.76, "elapsed_time": "22:50:32", "remaining_time": "9:54:02", "throughput": 554.15, "total_tokens": 45569264} {"current_steps": 27910, "total_steps": 40000, "loss": 0.1277, "lr": 1.0450296376386657e-05, "epoch": 1.263473596052423, "percentage": 69.77, "elapsed_time": "22:50:35", "remaining_time": "9:53:42", "throughput": 554.23, "total_tokens": 45577232} {"current_steps": 27915, "total_steps": 40000, "loss": 0.1074, "lr": 1.044231395294098e-05, "epoch": 1.263699947939066, "percentage": 69.79, "elapsed_time": "22:50:38", "remaining_time": "9:53:22", "throughput": 554.31, "total_tokens": 45585360} {"current_steps": 27920, "total_steps": 40000, "loss": 0.0852, "lr": 1.0434333774473435e-05, "epoch": 1.263926299825709, "percentage": 69.8, "elapsed_time": "22:50:41", "remaining_time": "9:53:03", "throughput": 554.39, "total_tokens": 45593584} {"current_steps": 27925, "total_steps": 40000, "loss": 0.0878, "lr": 1.0426355842214657e-05, "epoch": 1.264152651712352, "percentage": 69.81, "elapsed_time": "22:50:44", "remaining_time": "9:52:43", "throughput": 554.47, "total_tokens": 45602384} {"current_steps": 27930, "total_steps": 40000, "loss": 0.1291, "lr": 1.0418380157394963e-05, "epoch": 1.264379003598995, "percentage": 69.83, "elapsed_time": "22:50:47", "remaining_time": "9:52:23", "throughput": 554.54, "total_tokens": 45609648} {"current_steps": 27935, "total_steps": 40000, "loss": 0.1298, "lr": 1.0410406721244281e-05, "epoch": 1.264605355485638, "percentage": 69.84, "elapsed_time": "22:50:51", "remaining_time": "9:52:03", "throughput": 554.62, "total_tokens": 45617808} {"current_steps": 27940, "total_steps": 40000, "loss": 0.1077, "lr": 1.0402435534992238e-05, "epoch": 1.264831707372281, "percentage": 69.85, "elapsed_time": "22:50:54", "remaining_time": "9:51:44", "throughput": 554.7, "total_tokens": 45626128} {"current_steps": 27945, "total_steps": 40000, "loss": 0.0963, "lr": 1.0394466599868071e-05, "epoch": 1.265058059258924, "percentage": 69.86, "elapsed_time": "22:50:57", "remaining_time": "9:51:24", "throughput": 554.77, "total_tokens": 45634160} {"current_steps": 27950, "total_steps": 40000, "loss": 0.1098, "lr": 1.0386499917100697e-05, "epoch": 1.2652844111455668, "percentage": 69.88, "elapsed_time": "22:51:00", "remaining_time": "9:51:04", "throughput": 554.84, "total_tokens": 45641776} {"current_steps": 27955, "total_steps": 40000, "loss": 0.1224, "lr": 1.0378535487918692e-05, "epoch": 1.2655107630322098, "percentage": 69.89, "elapsed_time": "22:51:03", "remaining_time": "9:50:45", "throughput": 554.92, "total_tokens": 45649712} {"current_steps": 27960, "total_steps": 40000, "loss": 0.1406, "lr": 1.037057331355025e-05, "epoch": 1.2657371149188528, "percentage": 69.9, "elapsed_time": "22:51:06", "remaining_time": "9:50:25", "throughput": 554.99, "total_tokens": 45657488} {"current_steps": 27965, "total_steps": 40000, "loss": 0.1073, "lr": 1.0362613395223247e-05, "epoch": 1.2659634668054958, "percentage": 69.91, "elapsed_time": "22:51:10", "remaining_time": "9:50:05", "throughput": 555.08, "total_tokens": 45666096} {"current_steps": 27970, "total_steps": 40000, "loss": 0.1227, "lr": 1.0354655734165212e-05, "epoch": 1.2661898186921388, "percentage": 69.92, "elapsed_time": "22:51:13", "remaining_time": "9:49:46", "throughput": 555.16, "total_tokens": 45674576} {"current_steps": 27975, "total_steps": 40000, "loss": 0.0982, "lr": 1.03467003316033e-05, "epoch": 1.2664161705787818, "percentage": 69.94, "elapsed_time": "22:51:16", "remaining_time": "9:49:26", "throughput": 555.24, "total_tokens": 45682864} {"current_steps": 27980, "total_steps": 40000, "loss": 0.1378, "lr": 1.033874718876435e-05, "epoch": 1.2666425224654247, "percentage": 69.95, "elapsed_time": "22:51:19", "remaining_time": "9:49:06", "throughput": 555.31, "total_tokens": 45690672} {"current_steps": 27985, "total_steps": 40000, "loss": 0.1409, "lr": 1.0330796306874818e-05, "epoch": 1.2668688743520677, "percentage": 69.96, "elapsed_time": "22:51:22", "remaining_time": "9:48:47", "throughput": 555.38, "total_tokens": 45698544} {"current_steps": 27990, "total_steps": 40000, "loss": 0.0993, "lr": 1.032284768716085e-05, "epoch": 1.2670952262387107, "percentage": 69.97, "elapsed_time": "22:51:26", "remaining_time": "9:48:27", "throughput": 555.47, "total_tokens": 45707376} {"current_steps": 27995, "total_steps": 40000, "loss": 0.1391, "lr": 1.0314901330848206e-05, "epoch": 1.2673215781253537, "percentage": 69.99, "elapsed_time": "22:51:29", "remaining_time": "9:48:07", "throughput": 555.55, "total_tokens": 45715792} {"current_steps": 28000, "total_steps": 40000, "loss": 0.1172, "lr": 1.030695723916233e-05, "epoch": 1.2675479300119967, "percentage": 70.0, "elapsed_time": "22:51:32", "remaining_time": "9:47:48", "throughput": 555.63, "total_tokens": 45724560} {"current_steps": 28000, "total_steps": 40000, "eval_loss": 0.12302731722593307, "epoch": 1.2675479300119967, "percentage": 70.0, "elapsed_time": "22:59:15", "remaining_time": "9:51:06", "throughput": 552.52, "total_tokens": 45724560} {"current_steps": 28005, "total_steps": 40000, "loss": 0.1398, "lr": 1.0299015413328289e-05, "epoch": 1.2677742818986397, "percentage": 70.01, "elapsed_time": "22:59:19", "remaining_time": "9:50:47", "throughput": 552.6, "total_tokens": 45732976} {"current_steps": 28010, "total_steps": 40000, "loss": 0.08, "lr": 1.0291075854570809e-05, "epoch": 1.2680006337852827, "percentage": 70.03, "elapsed_time": "22:59:22", "remaining_time": "9:50:27", "throughput": 552.68, "total_tokens": 45741104} {"current_steps": 28015, "total_steps": 40000, "loss": 0.1179, "lr": 1.0283138564114275e-05, "epoch": 1.2682269856719257, "percentage": 70.04, "elapsed_time": "22:59:26", "remaining_time": "9:50:07", "throughput": 552.75, "total_tokens": 45749040} {"current_steps": 28020, "total_steps": 40000, "loss": 0.0774, "lr": 1.027520354318273e-05, "epoch": 1.2684533375585685, "percentage": 70.05, "elapsed_time": "22:59:29", "remaining_time": "9:49:48", "throughput": 552.83, "total_tokens": 45757200} {"current_steps": 28025, "total_steps": 40000, "loss": 0.092, "lr": 1.0267270792999828e-05, "epoch": 1.2686796894452115, "percentage": 70.06, "elapsed_time": "22:59:32", "remaining_time": "9:49:28", "throughput": 552.91, "total_tokens": 45765520} {"current_steps": 28030, "total_steps": 40000, "loss": 0.1067, "lr": 1.0259340314788919e-05, "epoch": 1.2689060413318545, "percentage": 70.08, "elapsed_time": "22:59:35", "remaining_time": "9:49:08", "throughput": 552.99, "total_tokens": 45773712} {"current_steps": 28035, "total_steps": 40000, "loss": 0.163, "lr": 1.0251412109772979e-05, "epoch": 1.2691323932184975, "percentage": 70.09, "elapsed_time": "22:59:38", "remaining_time": "9:48:48", "throughput": 553.06, "total_tokens": 45781360} {"current_steps": 28040, "total_steps": 40000, "loss": 0.0558, "lr": 1.0243486179174627e-05, "epoch": 1.2693587451051405, "percentage": 70.1, "elapsed_time": "22:59:41", "remaining_time": "9:48:29", "throughput": 553.14, "total_tokens": 45789968} {"current_steps": 28045, "total_steps": 40000, "loss": 0.1159, "lr": 1.0235562524216158e-05, "epoch": 1.2695850969917835, "percentage": 70.11, "elapsed_time": "22:59:45", "remaining_time": "9:48:09", "throughput": 553.21, "total_tokens": 45797744} {"current_steps": 28050, "total_steps": 40000, "loss": 0.106, "lr": 1.022764114611948e-05, "epoch": 1.2698114488784265, "percentage": 70.12, "elapsed_time": "22:59:48", "remaining_time": "9:47:49", "throughput": 553.29, "total_tokens": 45805872} {"current_steps": 28055, "total_steps": 40000, "loss": 0.1397, "lr": 1.0219722046106178e-05, "epoch": 1.2700378007650694, "percentage": 70.14, "elapsed_time": "22:59:51", "remaining_time": "9:47:30", "throughput": 553.37, "total_tokens": 45814512} {"current_steps": 28060, "total_steps": 40000, "loss": 0.1451, "lr": 1.0211805225397486e-05, "epoch": 1.2702641526517122, "percentage": 70.15, "elapsed_time": "22:59:54", "remaining_time": "9:47:10", "throughput": 553.45, "total_tokens": 45822736} {"current_steps": 28065, "total_steps": 40000, "loss": 0.0976, "lr": 1.020389068521426e-05, "epoch": 1.2704905045383552, "percentage": 70.16, "elapsed_time": "22:59:57", "remaining_time": "9:46:50", "throughput": 553.52, "total_tokens": 45829904} {"current_steps": 28070, "total_steps": 40000, "loss": 0.1583, "lr": 1.0195978426777039e-05, "epoch": 1.2707168564249982, "percentage": 70.17, "elapsed_time": "23:00:00", "remaining_time": "9:46:31", "throughput": 553.59, "total_tokens": 45837424} {"current_steps": 28075, "total_steps": 40000, "loss": 0.1678, "lr": 1.0188068451305982e-05, "epoch": 1.2709432083116412, "percentage": 70.19, "elapsed_time": "23:00:03", "remaining_time": "9:46:11", "throughput": 553.66, "total_tokens": 45845200} {"current_steps": 28080, "total_steps": 40000, "loss": 0.0861, "lr": 1.0180160760020902e-05, "epoch": 1.2711695601982842, "percentage": 70.2, "elapsed_time": "23:00:07", "remaining_time": "9:45:51", "throughput": 553.75, "total_tokens": 45854544} {"current_steps": 28085, "total_steps": 40000, "loss": 0.2041, "lr": 1.0172255354141278e-05, "epoch": 1.2713959120849272, "percentage": 70.21, "elapsed_time": "23:00:10", "remaining_time": "9:45:32", "throughput": 553.82, "total_tokens": 45861904} {"current_steps": 28090, "total_steps": 40000, "loss": 0.1208, "lr": 1.0164352234886205e-05, "epoch": 1.2716222639715702, "percentage": 70.23, "elapsed_time": "23:00:13", "remaining_time": "9:45:12", "throughput": 553.89, "total_tokens": 45869872} {"current_steps": 28095, "total_steps": 40000, "loss": 0.0876, "lr": 1.0156451403474454e-05, "epoch": 1.2718486158582132, "percentage": 70.24, "elapsed_time": "23:00:16", "remaining_time": "9:44:52", "throughput": 553.97, "total_tokens": 45877552} {"current_steps": 28100, "total_steps": 40000, "loss": 0.1195, "lr": 1.0148552861124443e-05, "epoch": 1.2720749677448562, "percentage": 70.25, "elapsed_time": "23:00:19", "remaining_time": "9:44:33", "throughput": 554.04, "total_tokens": 45885872} {"current_steps": 28105, "total_steps": 40000, "loss": 0.1299, "lr": 1.0140656609054205e-05, "epoch": 1.2723013196314992, "percentage": 70.26, "elapsed_time": "23:00:22", "remaining_time": "9:44:13", "throughput": 554.12, "total_tokens": 45894160} {"current_steps": 28110, "total_steps": 40000, "loss": 0.0952, "lr": 1.0132762648481455e-05, "epoch": 1.2725276715181422, "percentage": 70.28, "elapsed_time": "23:00:26", "remaining_time": "9:43:53", "throughput": 554.2, "total_tokens": 45902512} {"current_steps": 28115, "total_steps": 40000, "loss": 0.1334, "lr": 1.0124870980623543e-05, "epoch": 1.2727540234047852, "percentage": 70.29, "elapsed_time": "23:00:29", "remaining_time": "9:43:34", "throughput": 554.28, "total_tokens": 45910544} {"current_steps": 28120, "total_steps": 40000, "loss": 0.138, "lr": 1.0116981606697453e-05, "epoch": 1.2729803752914282, "percentage": 70.3, "elapsed_time": "23:00:32", "remaining_time": "9:43:14", "throughput": 554.36, "total_tokens": 45918992} {"current_steps": 28125, "total_steps": 40000, "loss": 0.1302, "lr": 1.0109094527919838e-05, "epoch": 1.2732067271780712, "percentage": 70.31, "elapsed_time": "23:00:35", "remaining_time": "9:42:55", "throughput": 554.43, "total_tokens": 45927024} {"current_steps": 28130, "total_steps": 40000, "loss": 0.0737, "lr": 1.010120974550697e-05, "epoch": 1.273433079064714, "percentage": 70.33, "elapsed_time": "23:00:39", "remaining_time": "9:42:35", "throughput": 554.52, "total_tokens": 45935792} {"current_steps": 28135, "total_steps": 40000, "loss": 0.099, "lr": 1.0093327260674795e-05, "epoch": 1.273659430951357, "percentage": 70.34, "elapsed_time": "23:00:42", "remaining_time": "9:42:16", "throughput": 554.6, "total_tokens": 45944720} {"current_steps": 28140, "total_steps": 40000, "loss": 0.1043, "lr": 1.0085447074638878e-05, "epoch": 1.273885782838, "percentage": 70.35, "elapsed_time": "23:00:45", "remaining_time": "9:41:56", "throughput": 554.68, "total_tokens": 45952816} {"current_steps": 28145, "total_steps": 40000, "loss": 0.0872, "lr": 1.0077569188614461e-05, "epoch": 1.274112134724643, "percentage": 70.36, "elapsed_time": "23:00:48", "remaining_time": "9:41:36", "throughput": 554.76, "total_tokens": 45961040} {"current_steps": 28150, "total_steps": 40000, "loss": 0.1062, "lr": 1.0069693603816393e-05, "epoch": 1.274338486611286, "percentage": 70.38, "elapsed_time": "23:00:52", "remaining_time": "9:41:17", "throughput": 554.84, "total_tokens": 45969616} {"current_steps": 28155, "total_steps": 40000, "loss": 0.1304, "lr": 1.0061820321459204e-05, "epoch": 1.274564838497929, "percentage": 70.39, "elapsed_time": "23:00:55", "remaining_time": "9:40:57", "throughput": 554.92, "total_tokens": 45977680} {"current_steps": 28160, "total_steps": 40000, "loss": 0.0848, "lr": 1.0053949342757038e-05, "epoch": 1.274791190384572, "percentage": 70.4, "elapsed_time": "23:00:58", "remaining_time": "9:40:38", "throughput": 554.99, "total_tokens": 45985936} {"current_steps": 28165, "total_steps": 40000, "loss": 0.0882, "lr": 1.0046080668923717e-05, "epoch": 1.2750175422712149, "percentage": 70.41, "elapsed_time": "23:01:01", "remaining_time": "9:40:18", "throughput": 555.07, "total_tokens": 45994288} {"current_steps": 28170, "total_steps": 40000, "loss": 0.1541, "lr": 1.003821430117267e-05, "epoch": 1.2752438941578579, "percentage": 70.43, "elapsed_time": "23:01:04", "remaining_time": "9:39:59", "throughput": 555.15, "total_tokens": 46002192} {"current_steps": 28175, "total_steps": 40000, "loss": 0.1136, "lr": 1.0030350240716999e-05, "epoch": 1.2754702460445007, "percentage": 70.44, "elapsed_time": "23:01:07", "remaining_time": "9:39:39", "throughput": 555.22, "total_tokens": 46009936} {"current_steps": 28180, "total_steps": 40000, "loss": 0.1239, "lr": 1.0022488488769449e-05, "epoch": 1.2756965979311436, "percentage": 70.45, "elapsed_time": "23:01:10", "remaining_time": "9:39:19", "throughput": 555.3, "total_tokens": 46017904} {"current_steps": 28185, "total_steps": 40000, "loss": 0.1382, "lr": 1.0014629046542387e-05, "epoch": 1.2759229498177866, "percentage": 70.46, "elapsed_time": "23:01:14", "remaining_time": "9:39:00", "throughput": 555.38, "total_tokens": 46026640} {"current_steps": 28190, "total_steps": 40000, "loss": 0.1614, "lr": 1.0006771915247842e-05, "epoch": 1.2761493017044296, "percentage": 70.47, "elapsed_time": "23:01:17", "remaining_time": "9:38:40", "throughput": 555.45, "total_tokens": 46034320} {"current_steps": 28195, "total_steps": 40000, "loss": 0.0854, "lr": 9.998917096097495e-06, "epoch": 1.2763756535910726, "percentage": 70.49, "elapsed_time": "23:01:20", "remaining_time": "9:38:21", "throughput": 555.52, "total_tokens": 46041808} {"current_steps": 28200, "total_steps": 40000, "loss": 0.0987, "lr": 9.991064590302638e-06, "epoch": 1.2766020054777156, "percentage": 70.5, "elapsed_time": "23:01:23", "remaining_time": "9:38:01", "throughput": 555.59, "total_tokens": 46049424} {"current_steps": 28200, "total_steps": 40000, "eval_loss": 0.12296801060438156, "epoch": 1.2766020054777156, "percentage": 70.5, "elapsed_time": "23:09:06", "remaining_time": "9:41:15", "throughput": 552.51, "total_tokens": 46049424} {"current_steps": 28205, "total_steps": 40000, "loss": 0.1257, "lr": 9.983214399074241e-06, "epoch": 1.2768283573643586, "percentage": 70.51, "elapsed_time": "23:09:10", "remaining_time": "9:40:56", "throughput": 552.58, "total_tokens": 46057680} {"current_steps": 28210, "total_steps": 40000, "loss": 0.1449, "lr": 9.975366523622893e-06, "epoch": 1.2770547092510016, "percentage": 70.53, "elapsed_time": "23:09:13", "remaining_time": "9:40:36", "throughput": 552.66, "total_tokens": 46066480} {"current_steps": 28215, "total_steps": 40000, "loss": 0.1157, "lr": 9.967520965158841e-06, "epoch": 1.2772810611376446, "percentage": 70.54, "elapsed_time": "23:09:16", "remaining_time": "9:40:17", "throughput": 552.74, "total_tokens": 46074896} {"current_steps": 28220, "total_steps": 40000, "loss": 0.0905, "lr": 9.95967772489197e-06, "epoch": 1.2775074130242876, "percentage": 70.55, "elapsed_time": "23:09:20", "remaining_time": "9:39:57", "throughput": 552.82, "total_tokens": 46082992} {"current_steps": 28225, "total_steps": 40000, "loss": 0.1011, "lr": 9.951836804031794e-06, "epoch": 1.2777337649109306, "percentage": 70.56, "elapsed_time": "23:09:23", "remaining_time": "9:39:37", "throughput": 552.9, "total_tokens": 46091440} {"current_steps": 28230, "total_steps": 40000, "loss": 0.1805, "lr": 9.943998203787489e-06, "epoch": 1.2779601167975736, "percentage": 70.58, "elapsed_time": "23:09:26", "remaining_time": "9:39:18", "throughput": 552.98, "total_tokens": 46099760} {"current_steps": 28235, "total_steps": 40000, "loss": 0.131, "lr": 9.936161925367874e-06, "epoch": 1.2781864686842166, "percentage": 70.59, "elapsed_time": "23:09:29", "remaining_time": "9:38:58", "throughput": 553.06, "total_tokens": 46108048} {"current_steps": 28240, "total_steps": 40000, "loss": 0.1063, "lr": 9.928327969981386e-06, "epoch": 1.2784128205708596, "percentage": 70.6, "elapsed_time": "23:09:32", "remaining_time": "9:38:38", "throughput": 553.13, "total_tokens": 46115728} {"current_steps": 28245, "total_steps": 40000, "loss": 0.0783, "lr": 9.920496338836135e-06, "epoch": 1.2786391724575024, "percentage": 70.61, "elapsed_time": "23:09:36", "remaining_time": "9:38:19", "throughput": 553.21, "total_tokens": 46124432} {"current_steps": 28250, "total_steps": 40000, "loss": 0.1349, "lr": 9.912667033139844e-06, "epoch": 1.2788655243441454, "percentage": 70.62, "elapsed_time": "23:09:39", "remaining_time": "9:37:59", "throughput": 553.29, "total_tokens": 46132880} {"current_steps": 28255, "total_steps": 40000, "loss": 0.1283, "lr": 9.904840054099893e-06, "epoch": 1.2790918762307883, "percentage": 70.64, "elapsed_time": "23:09:42", "remaining_time": "9:37:40", "throughput": 553.37, "total_tokens": 46141040} {"current_steps": 28260, "total_steps": 40000, "loss": 0.1364, "lr": 9.897015402923312e-06, "epoch": 1.2793182281174313, "percentage": 70.65, "elapsed_time": "23:09:45", "remaining_time": "9:37:20", "throughput": 553.44, "total_tokens": 46149264} {"current_steps": 28265, "total_steps": 40000, "loss": 0.0886, "lr": 9.889193080816744e-06, "epoch": 1.2795445800040743, "percentage": 70.66, "elapsed_time": "23:09:48", "remaining_time": "9:37:01", "throughput": 553.52, "total_tokens": 46157136} {"current_steps": 28270, "total_steps": 40000, "loss": 0.0999, "lr": 9.881373088986498e-06, "epoch": 1.2797709318907173, "percentage": 70.67, "elapsed_time": "23:09:51", "remaining_time": "9:36:41", "throughput": 553.59, "total_tokens": 46164624} {"current_steps": 28275, "total_steps": 40000, "loss": 0.1078, "lr": 9.873555428638523e-06, "epoch": 1.2799972837773603, "percentage": 70.69, "elapsed_time": "23:09:54", "remaining_time": "9:36:21", "throughput": 553.66, "total_tokens": 46172144} {"current_steps": 28280, "total_steps": 40000, "loss": 0.1493, "lr": 9.865740100978383e-06, "epoch": 1.2802236356640033, "percentage": 70.7, "elapsed_time": "23:09:58", "remaining_time": "9:36:02", "throughput": 553.74, "total_tokens": 46181264} {"current_steps": 28285, "total_steps": 40000, "loss": 0.1149, "lr": 9.857927107211315e-06, "epoch": 1.280449987550646, "percentage": 70.71, "elapsed_time": "23:10:01", "remaining_time": "9:35:42", "throughput": 553.82, "total_tokens": 46189424} {"current_steps": 28290, "total_steps": 40000, "loss": 0.1323, "lr": 9.850116448542177e-06, "epoch": 1.280676339437289, "percentage": 70.73, "elapsed_time": "23:10:04", "remaining_time": "9:35:23", "throughput": 553.9, "total_tokens": 46197776} {"current_steps": 28295, "total_steps": 40000, "loss": 0.1083, "lr": 9.842308126175457e-06, "epoch": 1.280902691323932, "percentage": 70.74, "elapsed_time": "23:10:07", "remaining_time": "9:35:03", "throughput": 553.98, "total_tokens": 46205968} {"current_steps": 28300, "total_steps": 40000, "loss": 0.0989, "lr": 9.834502141315315e-06, "epoch": 1.281129043210575, "percentage": 70.75, "elapsed_time": "23:10:11", "remaining_time": "9:34:44", "throughput": 554.05, "total_tokens": 46213808} {"current_steps": 28305, "total_steps": 40000, "loss": 0.1533, "lr": 9.82669849516552e-06, "epoch": 1.281355395097218, "percentage": 70.76, "elapsed_time": "23:10:14", "remaining_time": "9:34:24", "throughput": 554.12, "total_tokens": 46221616} {"current_steps": 28310, "total_steps": 40000, "loss": 0.1159, "lr": 9.818897188929493e-06, "epoch": 1.281581746983861, "percentage": 70.78, "elapsed_time": "23:10:17", "remaining_time": "9:34:05", "throughput": 554.2, "total_tokens": 46230064} {"current_steps": 28315, "total_steps": 40000, "loss": 0.1909, "lr": 9.811098223810309e-06, "epoch": 1.281808098870504, "percentage": 70.79, "elapsed_time": "23:10:20", "remaining_time": "9:33:45", "throughput": 554.28, "total_tokens": 46238000} {"current_steps": 28320, "total_steps": 40000, "loss": 0.1121, "lr": 9.803301601010641e-06, "epoch": 1.282034450757147, "percentage": 70.8, "elapsed_time": "23:10:23", "remaining_time": "9:33:26", "throughput": 554.35, "total_tokens": 46246288} {"current_steps": 28325, "total_steps": 40000, "loss": 0.1267, "lr": 9.795507321732853e-06, "epoch": 1.28226080264379, "percentage": 70.81, "elapsed_time": "23:10:26", "remaining_time": "9:33:06", "throughput": 554.43, "total_tokens": 46254800} {"current_steps": 28330, "total_steps": 40000, "loss": 0.1523, "lr": 9.787715387178898e-06, "epoch": 1.282487154530433, "percentage": 70.83, "elapsed_time": "23:10:30", "remaining_time": "9:32:47", "throughput": 554.51, "total_tokens": 46263088} {"current_steps": 28335, "total_steps": 40000, "loss": 0.1154, "lr": 9.779925798550399e-06, "epoch": 1.282713506417076, "percentage": 70.84, "elapsed_time": "23:10:33", "remaining_time": "9:32:27", "throughput": 554.59, "total_tokens": 46271152} {"current_steps": 28340, "total_steps": 40000, "loss": 0.126, "lr": 9.772138557048619e-06, "epoch": 1.282939858303719, "percentage": 70.85, "elapsed_time": "23:10:36", "remaining_time": "9:32:08", "throughput": 554.67, "total_tokens": 46279600} {"current_steps": 28345, "total_steps": 40000, "loss": 0.138, "lr": 9.764353663874426e-06, "epoch": 1.283166210190362, "percentage": 70.86, "elapsed_time": "23:10:39", "remaining_time": "9:31:49", "throughput": 554.74, "total_tokens": 46287472} {"current_steps": 28350, "total_steps": 40000, "loss": 0.096, "lr": 9.756571120228375e-06, "epoch": 1.283392562077005, "percentage": 70.88, "elapsed_time": "23:10:42", "remaining_time": "9:31:29", "throughput": 554.82, "total_tokens": 46295760} {"current_steps": 28355, "total_steps": 40000, "loss": 0.1129, "lr": 9.748790927310605e-06, "epoch": 1.283618913963648, "percentage": 70.89, "elapsed_time": "23:10:46", "remaining_time": "9:31:10", "throughput": 554.9, "total_tokens": 46304368} {"current_steps": 28360, "total_steps": 40000, "loss": 0.1162, "lr": 9.741013086320946e-06, "epoch": 1.2838452658502908, "percentage": 70.9, "elapsed_time": "23:10:49", "remaining_time": "9:30:50", "throughput": 554.98, "total_tokens": 46312560} {"current_steps": 28365, "total_steps": 40000, "loss": 0.0778, "lr": 9.733237598458821e-06, "epoch": 1.2840716177369338, "percentage": 70.91, "elapsed_time": "23:10:52", "remaining_time": "9:30:31", "throughput": 555.05, "total_tokens": 46320400} {"current_steps": 28370, "total_steps": 40000, "loss": 0.1313, "lr": 9.725464464923308e-06, "epoch": 1.2842979696235768, "percentage": 70.93, "elapsed_time": "23:10:55", "remaining_time": "9:30:11", "throughput": 555.13, "total_tokens": 46328656} {"current_steps": 28375, "total_steps": 40000, "loss": 0.1515, "lr": 9.717693686913123e-06, "epoch": 1.2845243215102198, "percentage": 70.94, "elapsed_time": "23:10:58", "remaining_time": "9:29:52", "throughput": 555.21, "total_tokens": 46337104} {"current_steps": 28380, "total_steps": 40000, "loss": 0.1706, "lr": 9.709925265626632e-06, "epoch": 1.2847506733968628, "percentage": 70.95, "elapsed_time": "23:11:01", "remaining_time": "9:29:32", "throughput": 555.29, "total_tokens": 46345584} {"current_steps": 28385, "total_steps": 40000, "loss": 0.0938, "lr": 9.702159202261801e-06, "epoch": 1.2849770252835058, "percentage": 70.96, "elapsed_time": "23:11:05", "remaining_time": "9:29:13", "throughput": 555.36, "total_tokens": 46353584} {"current_steps": 28390, "total_steps": 40000, "loss": 0.1072, "lr": 9.694395498016268e-06, "epoch": 1.2852033771701488, "percentage": 70.97, "elapsed_time": "23:11:08", "remaining_time": "9:28:54", "throughput": 555.44, "total_tokens": 46361360} {"current_steps": 28395, "total_steps": 40000, "loss": 0.1453, "lr": 9.686634154087298e-06, "epoch": 1.2854297290567918, "percentage": 70.99, "elapsed_time": "23:11:11", "remaining_time": "9:28:34", "throughput": 555.53, "total_tokens": 46371024} {"current_steps": 28400, "total_steps": 40000, "loss": 0.1963, "lr": 9.678875171671776e-06, "epoch": 1.2856560809434345, "percentage": 71.0, "elapsed_time": "23:11:14", "remaining_time": "9:28:15", "throughput": 555.6, "total_tokens": 46378736} {"current_steps": 28400, "total_steps": 40000, "eval_loss": 0.12264515459537506, "epoch": 1.2856560809434345, "percentage": 71.0, "elapsed_time": "23:18:57", "remaining_time": "9:31:24", "throughput": 552.54, "total_tokens": 46378736} {"current_steps": 28405, "total_steps": 40000, "loss": 0.1369, "lr": 9.671118551966246e-06, "epoch": 1.2858824328300775, "percentage": 71.01, "elapsed_time": "23:19:01", "remaining_time": "9:31:05", "throughput": 552.61, "total_tokens": 46386960} {"current_steps": 28410, "total_steps": 40000, "loss": 0.0732, "lr": 9.66336429616686e-06, "epoch": 1.2861087847167205, "percentage": 71.03, "elapsed_time": "23:19:04", "remaining_time": "9:30:45", "throughput": 552.69, "total_tokens": 46395472} {"current_steps": 28415, "total_steps": 40000, "loss": 0.1049, "lr": 9.655612405469436e-06, "epoch": 1.2863351366033635, "percentage": 71.04, "elapsed_time": "23:19:08", "remaining_time": "9:30:26", "throughput": 552.77, "total_tokens": 46404016} {"current_steps": 28420, "total_steps": 40000, "loss": 0.1432, "lr": 9.647862881069413e-06, "epoch": 1.2865614884900065, "percentage": 71.05, "elapsed_time": "23:19:11", "remaining_time": "9:30:06", "throughput": 552.84, "total_tokens": 46411888} {"current_steps": 28425, "total_steps": 40000, "loss": 0.1249, "lr": 9.640115724161855e-06, "epoch": 1.2867878403766495, "percentage": 71.06, "elapsed_time": "23:19:14", "remaining_time": "9:29:47", "throughput": 552.92, "total_tokens": 46419952} {"current_steps": 28430, "total_steps": 40000, "loss": 0.1168, "lr": 9.632370935941483e-06, "epoch": 1.2870141922632925, "percentage": 71.08, "elapsed_time": "23:19:17", "remaining_time": "9:29:27", "throughput": 552.99, "total_tokens": 46427920} {"current_steps": 28435, "total_steps": 40000, "loss": 0.0816, "lr": 9.624628517602634e-06, "epoch": 1.2872405441499355, "percentage": 71.09, "elapsed_time": "23:19:20", "remaining_time": "9:29:08", "throughput": 553.07, "total_tokens": 46436048} {"current_steps": 28440, "total_steps": 40000, "loss": 0.1541, "lr": 9.61688847033928e-06, "epoch": 1.2874668960365785, "percentage": 71.1, "elapsed_time": "23:19:24", "remaining_time": "9:28:48", "throughput": 553.15, "total_tokens": 46444752} {"current_steps": 28445, "total_steps": 40000, "loss": 0.0845, "lr": 9.609150795345051e-06, "epoch": 1.2876932479232215, "percentage": 71.11, "elapsed_time": "23:19:27", "remaining_time": "9:28:29", "throughput": 553.22, "total_tokens": 46452560} {"current_steps": 28450, "total_steps": 40000, "loss": 0.1201, "lr": 9.601415493813171e-06, "epoch": 1.2879195998098645, "percentage": 71.12, "elapsed_time": "23:19:30", "remaining_time": "9:28:09", "throughput": 553.31, "total_tokens": 46461392} {"current_steps": 28455, "total_steps": 40000, "loss": 0.201, "lr": 9.593682566936533e-06, "epoch": 1.2881459516965075, "percentage": 71.14, "elapsed_time": "23:19:33", "remaining_time": "9:27:50", "throughput": 553.38, "total_tokens": 46469424} {"current_steps": 28460, "total_steps": 40000, "loss": 0.098, "lr": 9.58595201590766e-06, "epoch": 1.2883723035831505, "percentage": 71.15, "elapsed_time": "23:19:36", "remaining_time": "9:27:31", "throughput": 553.46, "total_tokens": 46477424} {"current_steps": 28465, "total_steps": 40000, "loss": 0.131, "lr": 9.578223841918681e-06, "epoch": 1.2885986554697935, "percentage": 71.16, "elapsed_time": "23:19:39", "remaining_time": "9:27:11", "throughput": 553.53, "total_tokens": 46485360} {"current_steps": 28470, "total_steps": 40000, "loss": 0.1813, "lr": 9.570498046161389e-06, "epoch": 1.2888250073564362, "percentage": 71.17, "elapsed_time": "23:19:43", "remaining_time": "9:26:52", "throughput": 553.6, "total_tokens": 46493296} {"current_steps": 28475, "total_steps": 40000, "loss": 0.1104, "lr": 9.562774629827206e-06, "epoch": 1.2890513592430792, "percentage": 71.19, "elapsed_time": "23:19:46", "remaining_time": "9:26:32", "throughput": 553.67, "total_tokens": 46501008} {"current_steps": 28480, "total_steps": 40000, "loss": 0.0901, "lr": 9.555053594107163e-06, "epoch": 1.2892777111297222, "percentage": 71.2, "elapsed_time": "23:19:49", "remaining_time": "9:26:13", "throughput": 553.75, "total_tokens": 46509168} {"current_steps": 28485, "total_steps": 40000, "loss": 0.1672, "lr": 9.547334940191957e-06, "epoch": 1.2895040630163652, "percentage": 71.21, "elapsed_time": "23:19:52", "remaining_time": "9:25:53", "throughput": 553.83, "total_tokens": 46517776} {"current_steps": 28490, "total_steps": 40000, "loss": 0.0781, "lr": 9.539618669271886e-06, "epoch": 1.2897304149030082, "percentage": 71.23, "elapsed_time": "23:19:55", "remaining_time": "9:25:34", "throughput": 553.91, "total_tokens": 46525744} {"current_steps": 28495, "total_steps": 40000, "loss": 0.1473, "lr": 9.531904782536904e-06, "epoch": 1.2899567667896512, "percentage": 71.24, "elapsed_time": "23:19:58", "remaining_time": "9:25:14", "throughput": 553.98, "total_tokens": 46533968} {"current_steps": 28500, "total_steps": 40000, "loss": 0.1135, "lr": 9.524193281176597e-06, "epoch": 1.2901831186762942, "percentage": 71.25, "elapsed_time": "23:20:02", "remaining_time": "9:24:55", "throughput": 554.06, "total_tokens": 46542032} {"current_steps": 28505, "total_steps": 40000, "loss": 0.12, "lr": 9.516484166380165e-06, "epoch": 1.2904094705629372, "percentage": 71.26, "elapsed_time": "23:20:05", "remaining_time": "9:24:36", "throughput": 554.14, "total_tokens": 46550352} {"current_steps": 28510, "total_steps": 40000, "loss": 0.1204, "lr": 9.508777439336447e-06, "epoch": 1.2906358224495802, "percentage": 71.28, "elapsed_time": "23:20:08", "remaining_time": "9:24:16", "throughput": 554.21, "total_tokens": 46558480} {"current_steps": 28515, "total_steps": 40000, "loss": 0.0878, "lr": 9.50107310123393e-06, "epoch": 1.290862174336223, "percentage": 71.29, "elapsed_time": "23:20:11", "remaining_time": "9:23:57", "throughput": 554.29, "total_tokens": 46566480} {"current_steps": 28520, "total_steps": 40000, "loss": 0.1395, "lr": 9.493371153260702e-06, "epoch": 1.291088526222866, "percentage": 71.3, "elapsed_time": "23:20:14", "remaining_time": "9:23:38", "throughput": 554.36, "total_tokens": 46574416} {"current_steps": 28525, "total_steps": 40000, "loss": 0.1245, "lr": 9.485671596604523e-06, "epoch": 1.291314878109509, "percentage": 71.31, "elapsed_time": "23:20:17", "remaining_time": "9:23:18", "throughput": 554.43, "total_tokens": 46581968} {"current_steps": 28530, "total_steps": 40000, "loss": 0.1381, "lr": 9.477974432452738e-06, "epoch": 1.291541229996152, "percentage": 71.33, "elapsed_time": "23:20:21", "remaining_time": "9:22:59", "throughput": 554.51, "total_tokens": 46590480} {"current_steps": 28535, "total_steps": 40000, "loss": 0.0943, "lr": 9.470279661992356e-06, "epoch": 1.291767581882795, "percentage": 71.34, "elapsed_time": "23:20:24", "remaining_time": "9:22:39", "throughput": 554.59, "total_tokens": 46599344} {"current_steps": 28540, "total_steps": 40000, "loss": 0.0954, "lr": 9.462587286410021e-06, "epoch": 1.291993933769438, "percentage": 71.35, "elapsed_time": "23:20:27", "remaining_time": "9:22:20", "throughput": 554.67, "total_tokens": 46607504} {"current_steps": 28545, "total_steps": 40000, "loss": 0.1534, "lr": 9.454897306891972e-06, "epoch": 1.292220285656081, "percentage": 71.36, "elapsed_time": "23:20:30", "remaining_time": "9:22:01", "throughput": 554.73, "total_tokens": 46614672} {"current_steps": 28550, "total_steps": 40000, "loss": 0.105, "lr": 9.44720972462411e-06, "epoch": 1.292446637542724, "percentage": 71.38, "elapsed_time": "23:20:33", "remaining_time": "9:21:41", "throughput": 554.82, "total_tokens": 46623472} {"current_steps": 28555, "total_steps": 40000, "loss": 0.1495, "lr": 9.439524540791964e-06, "epoch": 1.292672989429367, "percentage": 71.39, "elapsed_time": "23:20:37", "remaining_time": "9:21:22", "throughput": 554.89, "total_tokens": 46631536} {"current_steps": 28560, "total_steps": 40000, "loss": 0.0759, "lr": 9.431841756580673e-06, "epoch": 1.29289934131601, "percentage": 71.4, "elapsed_time": "23:20:40", "remaining_time": "9:21:03", "throughput": 554.97, "total_tokens": 46639728} {"current_steps": 28565, "total_steps": 40000, "loss": 0.1332, "lr": 9.42416137317503e-06, "epoch": 1.293125693202653, "percentage": 71.41, "elapsed_time": "23:20:43", "remaining_time": "9:20:43", "throughput": 555.04, "total_tokens": 46647408} {"current_steps": 28570, "total_steps": 40000, "loss": 0.1642, "lr": 9.416483391759437e-06, "epoch": 1.293352045089296, "percentage": 71.43, "elapsed_time": "23:20:46", "remaining_time": "9:20:24", "throughput": 555.11, "total_tokens": 46655120} {"current_steps": 28575, "total_steps": 40000, "loss": 0.1573, "lr": 9.408807813517945e-06, "epoch": 1.293578396975939, "percentage": 71.44, "elapsed_time": "23:20:49", "remaining_time": "9:20:05", "throughput": 555.19, "total_tokens": 46663216} {"current_steps": 28580, "total_steps": 40000, "loss": 0.117, "lr": 9.401134639634221e-06, "epoch": 1.293804748862582, "percentage": 71.45, "elapsed_time": "23:20:52", "remaining_time": "9:19:45", "throughput": 555.26, "total_tokens": 46671568} {"current_steps": 28585, "total_steps": 40000, "loss": 0.1198, "lr": 9.393463871291555e-06, "epoch": 1.2940311007492247, "percentage": 71.46, "elapsed_time": "23:20:55", "remaining_time": "9:19:26", "throughput": 555.34, "total_tokens": 46679664} {"current_steps": 28590, "total_steps": 40000, "loss": 0.1125, "lr": 9.385795509672881e-06, "epoch": 1.2942574526358677, "percentage": 71.47, "elapsed_time": "23:20:59", "remaining_time": "9:19:07", "throughput": 555.42, "total_tokens": 46687920} {"current_steps": 28595, "total_steps": 40000, "loss": 0.1726, "lr": 9.378129555960771e-06, "epoch": 1.2944838045225107, "percentage": 71.49, "elapsed_time": "23:21:02", "remaining_time": "9:18:47", "throughput": 555.49, "total_tokens": 46695408} {"current_steps": 28600, "total_steps": 40000, "loss": 0.1376, "lr": 9.370466011337392e-06, "epoch": 1.2947101564091537, "percentage": 71.5, "elapsed_time": "23:21:05", "remaining_time": "9:18:28", "throughput": 555.57, "total_tokens": 46704368} {"current_steps": 28600, "total_steps": 40000, "eval_loss": 0.12295767664909363, "epoch": 1.2947101564091537, "percentage": 71.5, "elapsed_time": "23:28:48", "remaining_time": "9:21:33", "throughput": 552.53, "total_tokens": 46704368} {"current_steps": 28605, "total_steps": 40000, "loss": 0.1446, "lr": 9.362804876984573e-06, "epoch": 1.2949365082957967, "percentage": 71.51, "elapsed_time": "23:28:52", "remaining_time": "9:21:14", "throughput": 552.59, "total_tokens": 46712080} {"current_steps": 28610, "total_steps": 40000, "loss": 0.0812, "lr": 9.355146154083747e-06, "epoch": 1.2951628601824396, "percentage": 71.53, "elapsed_time": "23:28:55", "remaining_time": "9:20:54", "throughput": 552.67, "total_tokens": 46720400} {"current_steps": 28615, "total_steps": 40000, "loss": 0.1495, "lr": 9.347489843815987e-06, "epoch": 1.2953892120690826, "percentage": 71.54, "elapsed_time": "23:28:58", "remaining_time": "9:20:35", "throughput": 552.76, "total_tokens": 46729392} {"current_steps": 28620, "total_steps": 40000, "loss": 0.1077, "lr": 9.339835947362002e-06, "epoch": 1.2956155639557256, "percentage": 71.55, "elapsed_time": "23:29:02", "remaining_time": "9:20:15", "throughput": 552.83, "total_tokens": 46737136} {"current_steps": 28625, "total_steps": 40000, "loss": 0.1518, "lr": 9.332184465902105e-06, "epoch": 1.2958419158423684, "percentage": 71.56, "elapsed_time": "23:29:05", "remaining_time": "9:19:56", "throughput": 552.9, "total_tokens": 46745008} {"current_steps": 28630, "total_steps": 40000, "loss": 0.097, "lr": 9.324535400616266e-06, "epoch": 1.2960682677290114, "percentage": 71.58, "elapsed_time": "23:29:08", "remaining_time": "9:19:37", "throughput": 552.98, "total_tokens": 46753168} {"current_steps": 28635, "total_steps": 40000, "loss": 0.1365, "lr": 9.31688875268405e-06, "epoch": 1.2962946196156544, "percentage": 71.59, "elapsed_time": "23:29:11", "remaining_time": "9:19:17", "throughput": 553.05, "total_tokens": 46761072} {"current_steps": 28640, "total_steps": 40000, "loss": 0.152, "lr": 9.309244523284674e-06, "epoch": 1.2965209715022974, "percentage": 71.6, "elapsed_time": "23:29:14", "remaining_time": "9:18:58", "throughput": 553.12, "total_tokens": 46769392} {"current_steps": 28645, "total_steps": 40000, "loss": 0.0983, "lr": 9.301602713596982e-06, "epoch": 1.2967473233889404, "percentage": 71.61, "elapsed_time": "23:29:18", "remaining_time": "9:18:39", "throughput": 553.2, "total_tokens": 46777424} {"current_steps": 28650, "total_steps": 40000, "loss": 0.1176, "lr": 9.293963324799432e-06, "epoch": 1.2969736752755834, "percentage": 71.62, "elapsed_time": "23:29:21", "remaining_time": "9:18:19", "throughput": 553.28, "total_tokens": 46786096} {"current_steps": 28655, "total_steps": 40000, "loss": 0.0843, "lr": 9.286326358070104e-06, "epoch": 1.2972000271622264, "percentage": 71.64, "elapsed_time": "23:29:24", "remaining_time": "9:18:00", "throughput": 553.35, "total_tokens": 46793648} {"current_steps": 28660, "total_steps": 40000, "loss": 0.1114, "lr": 9.278691814586729e-06, "epoch": 1.2974263790488694, "percentage": 71.65, "elapsed_time": "23:29:27", "remaining_time": "9:17:41", "throughput": 553.42, "total_tokens": 46801776} {"current_steps": 28665, "total_steps": 40000, "loss": 0.1286, "lr": 9.271059695526635e-06, "epoch": 1.2976527309355124, "percentage": 71.66, "elapsed_time": "23:29:30", "remaining_time": "9:17:21", "throughput": 553.5, "total_tokens": 46809680} {"current_steps": 28670, "total_steps": 40000, "loss": 0.1022, "lr": 9.263430002066805e-06, "epoch": 1.2978790828221554, "percentage": 71.67, "elapsed_time": "23:29:33", "remaining_time": "9:17:02", "throughput": 553.57, "total_tokens": 46817904} {"current_steps": 28675, "total_steps": 40000, "loss": 0.1434, "lr": 9.25580273538382e-06, "epoch": 1.2981054347087984, "percentage": 71.69, "elapsed_time": "23:29:37", "remaining_time": "9:16:43", "throughput": 553.64, "total_tokens": 46825328} {"current_steps": 28680, "total_steps": 40000, "loss": 0.1532, "lr": 9.248177896653907e-06, "epoch": 1.2983317865954414, "percentage": 71.7, "elapsed_time": "23:29:40", "remaining_time": "9:16:23", "throughput": 553.71, "total_tokens": 46832784} {"current_steps": 28685, "total_steps": 40000, "loss": 0.1295, "lr": 9.240555487052918e-06, "epoch": 1.2985581384820843, "percentage": 71.71, "elapsed_time": "23:29:43", "remaining_time": "9:16:04", "throughput": 553.78, "total_tokens": 46840656} {"current_steps": 28690, "total_steps": 40000, "loss": 0.1397, "lr": 9.232935507756313e-06, "epoch": 1.2987844903687273, "percentage": 71.73, "elapsed_time": "23:29:46", "remaining_time": "9:15:45", "throughput": 553.85, "total_tokens": 46848240} {"current_steps": 28695, "total_steps": 40000, "loss": 0.1575, "lr": 9.225317959939193e-06, "epoch": 1.2990108422553703, "percentage": 71.74, "elapsed_time": "23:29:49", "remaining_time": "9:15:25", "throughput": 553.93, "total_tokens": 46856784} {"current_steps": 28700, "total_steps": 40000, "loss": 0.1506, "lr": 9.217702844776287e-06, "epoch": 1.299237194142013, "percentage": 71.75, "elapsed_time": "23:29:52", "remaining_time": "9:15:06", "throughput": 554.0, "total_tokens": 46864240} {"current_steps": 28705, "total_steps": 40000, "loss": 0.1479, "lr": 9.210090163441929e-06, "epoch": 1.299463546028656, "percentage": 71.76, "elapsed_time": "23:29:55", "remaining_time": "9:14:47", "throughput": 554.08, "total_tokens": 46872784} {"current_steps": 28710, "total_steps": 40000, "loss": 0.1306, "lr": 9.202479917110105e-06, "epoch": 1.299689897915299, "percentage": 71.78, "elapsed_time": "23:29:59", "remaining_time": "9:14:27", "throughput": 554.15, "total_tokens": 46880784} {"current_steps": 28715, "total_steps": 40000, "loss": 0.1334, "lr": 9.194872106954392e-06, "epoch": 1.299916249801942, "percentage": 71.79, "elapsed_time": "23:30:02", "remaining_time": "9:14:08", "throughput": 554.23, "total_tokens": 46889232} {"current_steps": 28720, "total_steps": 40000, "loss": 0.0995, "lr": 9.187266734148029e-06, "epoch": 1.300142601688585, "percentage": 71.8, "elapsed_time": "23:30:05", "remaining_time": "9:13:49", "throughput": 554.3, "total_tokens": 46897200} {"current_steps": 28725, "total_steps": 40000, "loss": 0.1194, "lr": 9.179663799863849e-06, "epoch": 1.300368953575228, "percentage": 71.81, "elapsed_time": "23:30:08", "remaining_time": "9:13:30", "throughput": 554.37, "total_tokens": 46904560} {"current_steps": 28730, "total_steps": 40000, "loss": 0.1135, "lr": 9.172063305274317e-06, "epoch": 1.300595305461871, "percentage": 71.83, "elapsed_time": "23:30:11", "remaining_time": "9:13:10", "throughput": 554.44, "total_tokens": 46912240} {"current_steps": 28735, "total_steps": 40000, "loss": 0.1706, "lr": 9.164465251551527e-06, "epoch": 1.300821657348514, "percentage": 71.84, "elapsed_time": "23:30:14", "remaining_time": "9:12:51", "throughput": 554.52, "total_tokens": 46920240} {"current_steps": 28740, "total_steps": 40000, "loss": 0.1417, "lr": 9.156869639867205e-06, "epoch": 1.3010480092351568, "percentage": 71.85, "elapsed_time": "23:30:18", "remaining_time": "9:12:32", "throughput": 554.59, "total_tokens": 46928656} {"current_steps": 28745, "total_steps": 40000, "loss": 0.1384, "lr": 9.149276471392677e-06, "epoch": 1.3012743611217998, "percentage": 71.86, "elapsed_time": "23:30:21", "remaining_time": "9:12:13", "throughput": 554.67, "total_tokens": 46936944} {"current_steps": 28750, "total_steps": 40000, "loss": 0.0815, "lr": 9.141685747298914e-06, "epoch": 1.3015007130084428, "percentage": 71.88, "elapsed_time": "23:30:24", "remaining_time": "9:11:53", "throughput": 554.75, "total_tokens": 46945008} {"current_steps": 28755, "total_steps": 40000, "loss": 0.106, "lr": 9.13409746875649e-06, "epoch": 1.3017270648950858, "percentage": 71.89, "elapsed_time": "23:30:27", "remaining_time": "9:11:34", "throughput": 554.82, "total_tokens": 46952752} {"current_steps": 28760, "total_steps": 40000, "loss": 0.1068, "lr": 9.12651163693562e-06, "epoch": 1.3019534167817288, "percentage": 71.9, "elapsed_time": "23:30:30", "remaining_time": "9:11:15", "throughput": 554.89, "total_tokens": 46960272} {"current_steps": 28765, "total_steps": 40000, "loss": 0.1415, "lr": 9.11892825300614e-06, "epoch": 1.3021797686683718, "percentage": 71.91, "elapsed_time": "23:30:33", "remaining_time": "9:10:56", "throughput": 554.96, "total_tokens": 46968016} {"current_steps": 28770, "total_steps": 40000, "loss": 0.1078, "lr": 9.111347318137491e-06, "epoch": 1.3024061205550148, "percentage": 71.92, "elapsed_time": "23:30:36", "remaining_time": "9:10:36", "throughput": 555.03, "total_tokens": 46976048} {"current_steps": 28775, "total_steps": 40000, "loss": 0.0821, "lr": 9.103768833498755e-06, "epoch": 1.3026324724416578, "percentage": 71.94, "elapsed_time": "23:30:39", "remaining_time": "9:10:17", "throughput": 555.1, "total_tokens": 46983984} {"current_steps": 28780, "total_steps": 40000, "loss": 0.0829, "lr": 9.096192800258639e-06, "epoch": 1.3028588243283008, "percentage": 71.95, "elapsed_time": "23:30:43", "remaining_time": "9:09:58", "throughput": 555.19, "total_tokens": 46992720} {"current_steps": 28785, "total_steps": 40000, "loss": 0.1162, "lr": 9.088619219585443e-06, "epoch": 1.3030851762149438, "percentage": 71.96, "elapsed_time": "23:30:46", "remaining_time": "9:09:39", "throughput": 555.26, "total_tokens": 47001104} {"current_steps": 28790, "total_steps": 40000, "loss": 0.0887, "lr": 9.081048092647127e-06, "epoch": 1.3033115281015868, "percentage": 71.97, "elapsed_time": "23:30:49", "remaining_time": "9:09:20", "throughput": 555.33, "total_tokens": 47008816} {"current_steps": 28795, "total_steps": 40000, "loss": 0.1182, "lr": 9.073479420611245e-06, "epoch": 1.3035378799882298, "percentage": 71.99, "elapsed_time": "23:30:52", "remaining_time": "9:09:00", "throughput": 555.41, "total_tokens": 47016528} {"current_steps": 28800, "total_steps": 40000, "loss": 0.1788, "lr": 9.065913204644974e-06, "epoch": 1.3037642318748728, "percentage": 72.0, "elapsed_time": "23:30:55", "remaining_time": "9:08:41", "throughput": 555.48, "total_tokens": 47024752} {"current_steps": 28800, "total_steps": 40000, "eval_loss": 0.12305662035942078, "epoch": 1.3037642318748728, "percentage": 72.0, "elapsed_time": "23:38:38", "remaining_time": "9:11:41", "throughput": 552.46, "total_tokens": 47024752} {"current_steps": 28805, "total_steps": 40000, "loss": 0.1337, "lr": 9.058349445915135e-06, "epoch": 1.3039905837615158, "percentage": 72.01, "elapsed_time": "23:38:42", "remaining_time": "9:11:22", "throughput": 552.53, "total_tokens": 47033072} {"current_steps": 28810, "total_steps": 40000, "loss": 0.1739, "lr": 9.050788145588138e-06, "epoch": 1.3042169356481585, "percentage": 72.02, "elapsed_time": "23:38:45", "remaining_time": "9:11:03", "throughput": 552.61, "total_tokens": 47041648} {"current_steps": 28815, "total_steps": 40000, "loss": 0.1008, "lr": 9.043229304830039e-06, "epoch": 1.3044432875348015, "percentage": 72.04, "elapsed_time": "23:38:49", "remaining_time": "9:10:44", "throughput": 552.7, "total_tokens": 47050544} {"current_steps": 28820, "total_steps": 40000, "loss": 0.0907, "lr": 9.035672924806515e-06, "epoch": 1.3046696394214445, "percentage": 72.05, "elapsed_time": "23:38:52", "remaining_time": "9:10:25", "throughput": 552.78, "total_tokens": 47059920} {"current_steps": 28825, "total_steps": 40000, "loss": 0.1219, "lr": 9.028119006682839e-06, "epoch": 1.3048959913080875, "percentage": 72.06, "elapsed_time": "23:38:55", "remaining_time": "9:10:05", "throughput": 552.86, "total_tokens": 47068080} {"current_steps": 28830, "total_steps": 40000, "loss": 0.1012, "lr": 9.020567551623935e-06, "epoch": 1.3051223431947305, "percentage": 72.08, "elapsed_time": "23:38:58", "remaining_time": "9:09:46", "throughput": 552.93, "total_tokens": 47075888} {"current_steps": 28835, "total_steps": 40000, "loss": 0.0912, "lr": 9.013018560794318e-06, "epoch": 1.3053486950813735, "percentage": 72.09, "elapsed_time": "23:39:02", "remaining_time": "9:09:27", "throughput": 553.01, "total_tokens": 47084208} {"current_steps": 28840, "total_steps": 40000, "loss": 0.1322, "lr": 9.005472035358139e-06, "epoch": 1.3055750469680165, "percentage": 72.1, "elapsed_time": "23:39:05", "remaining_time": "9:09:07", "throughput": 553.08, "total_tokens": 47092112} {"current_steps": 28845, "total_steps": 40000, "loss": 0.0723, "lr": 8.997927976479185e-06, "epoch": 1.3058013988546595, "percentage": 72.11, "elapsed_time": "23:39:08", "remaining_time": "9:08:48", "throughput": 553.16, "total_tokens": 47100816} {"current_steps": 28850, "total_steps": 40000, "loss": 0.0839, "lr": 8.99038638532082e-06, "epoch": 1.3060277507413025, "percentage": 72.12, "elapsed_time": "23:39:11", "remaining_time": "9:08:29", "throughput": 553.25, "total_tokens": 47109968} {"current_steps": 28855, "total_steps": 40000, "loss": 0.0887, "lr": 8.982847263046065e-06, "epoch": 1.3062541026279453, "percentage": 72.14, "elapsed_time": "23:39:14", "remaining_time": "9:08:10", "throughput": 553.31, "total_tokens": 47117392} {"current_steps": 28860, "total_steps": 40000, "loss": 0.101, "lr": 8.975310610817555e-06, "epoch": 1.3064804545145883, "percentage": 72.15, "elapsed_time": "23:39:18", "remaining_time": "9:07:51", "throughput": 553.39, "total_tokens": 47125456} {"current_steps": 28865, "total_steps": 40000, "loss": 0.1384, "lr": 8.967776429797528e-06, "epoch": 1.3067068064012313, "percentage": 72.16, "elapsed_time": "23:39:21", "remaining_time": "9:07:31", "throughput": 553.47, "total_tokens": 47134160} {"current_steps": 28870, "total_steps": 40000, "loss": 0.0881, "lr": 8.960244721147842e-06, "epoch": 1.3069331582878743, "percentage": 72.17, "elapsed_time": "23:39:24", "remaining_time": "9:07:12", "throughput": 553.54, "total_tokens": 47142288} {"current_steps": 28875, "total_steps": 40000, "loss": 0.1444, "lr": 8.952715486029995e-06, "epoch": 1.3071595101745173, "percentage": 72.19, "elapsed_time": "23:39:27", "remaining_time": "9:06:53", "throughput": 553.62, "total_tokens": 47150736} {"current_steps": 28880, "total_steps": 40000, "loss": 0.1303, "lr": 8.945188725605075e-06, "epoch": 1.3073858620611603, "percentage": 72.2, "elapsed_time": "23:39:30", "remaining_time": "9:06:34", "throughput": 553.69, "total_tokens": 47158416} {"current_steps": 28885, "total_steps": 40000, "loss": 0.0732, "lr": 8.937664441033817e-06, "epoch": 1.3076122139478032, "percentage": 72.21, "elapsed_time": "23:39:34", "remaining_time": "9:06:15", "throughput": 553.77, "total_tokens": 47167056} {"current_steps": 28890, "total_steps": 40000, "loss": 0.0889, "lr": 8.930142633476549e-06, "epoch": 1.3078385658344462, "percentage": 72.22, "elapsed_time": "23:39:37", "remaining_time": "9:05:55", "throughput": 553.85, "total_tokens": 47175184} {"current_steps": 28895, "total_steps": 40000, "loss": 0.1173, "lr": 8.92262330409323e-06, "epoch": 1.3080649177210892, "percentage": 72.24, "elapsed_time": "23:39:40", "remaining_time": "9:05:36", "throughput": 553.93, "total_tokens": 47184080} {"current_steps": 28900, "total_steps": 40000, "loss": 0.1351, "lr": 8.915106454043448e-06, "epoch": 1.3082912696077322, "percentage": 72.25, "elapsed_time": "23:39:43", "remaining_time": "9:05:17", "throughput": 554.0, "total_tokens": 47191760} {"current_steps": 28905, "total_steps": 40000, "loss": 0.0779, "lr": 8.90759208448638e-06, "epoch": 1.3085176214943752, "percentage": 72.26, "elapsed_time": "23:39:46", "remaining_time": "9:04:58", "throughput": 554.07, "total_tokens": 47199472} {"current_steps": 28910, "total_steps": 40000, "loss": 0.083, "lr": 8.900080196580848e-06, "epoch": 1.3087439733810182, "percentage": 72.28, "elapsed_time": "23:39:50", "remaining_time": "9:04:39", "throughput": 554.16, "total_tokens": 47208752} {"current_steps": 28915, "total_steps": 40000, "loss": 0.0948, "lr": 8.892570791485267e-06, "epoch": 1.3089703252676612, "percentage": 72.29, "elapsed_time": "23:39:53", "remaining_time": "9:04:20", "throughput": 554.23, "total_tokens": 47216784} {"current_steps": 28920, "total_steps": 40000, "loss": 0.1032, "lr": 8.885063870357688e-06, "epoch": 1.3091966771543042, "percentage": 72.3, "elapsed_time": "23:39:56", "remaining_time": "9:04:01", "throughput": 554.3, "total_tokens": 47224912} {"current_steps": 28925, "total_steps": 40000, "loss": 0.1075, "lr": 8.87755943435578e-06, "epoch": 1.309423029040947, "percentage": 72.31, "elapsed_time": "23:39:59", "remaining_time": "9:03:41", "throughput": 554.38, "total_tokens": 47233424} {"current_steps": 28930, "total_steps": 40000, "loss": 0.0907, "lr": 8.87005748463681e-06, "epoch": 1.30964938092759, "percentage": 72.32, "elapsed_time": "23:40:03", "remaining_time": "9:03:22", "throughput": 554.46, "total_tokens": 47241264} {"current_steps": 28935, "total_steps": 40000, "loss": 0.1069, "lr": 8.862558022357681e-06, "epoch": 1.309875732814233, "percentage": 72.34, "elapsed_time": "23:40:06", "remaining_time": "9:03:03", "throughput": 554.54, "total_tokens": 47250160} {"current_steps": 28940, "total_steps": 40000, "loss": 0.1656, "lr": 8.855061048674903e-06, "epoch": 1.310102084700876, "percentage": 72.35, "elapsed_time": "23:40:09", "remaining_time": "9:02:44", "throughput": 554.61, "total_tokens": 47257904} {"current_steps": 28945, "total_steps": 40000, "loss": 0.1404, "lr": 8.847566564744595e-06, "epoch": 1.310328436587519, "percentage": 72.36, "elapsed_time": "23:40:12", "remaining_time": "9:02:25", "throughput": 554.69, "total_tokens": 47266256} {"current_steps": 28950, "total_steps": 40000, "loss": 0.1602, "lr": 8.840074571722512e-06, "epoch": 1.310554788474162, "percentage": 72.38, "elapsed_time": "23:40:15", "remaining_time": "9:02:06", "throughput": 554.76, "total_tokens": 47274128} {"current_steps": 28955, "total_steps": 40000, "loss": 0.1148, "lr": 8.832585070764002e-06, "epoch": 1.310781140360805, "percentage": 72.39, "elapsed_time": "23:40:19", "remaining_time": "9:01:47", "throughput": 554.83, "total_tokens": 47281648} {"current_steps": 28960, "total_steps": 40000, "loss": 0.128, "lr": 8.825098063024045e-06, "epoch": 1.311007492247448, "percentage": 72.4, "elapsed_time": "23:40:22", "remaining_time": "9:01:28", "throughput": 554.91, "total_tokens": 47290288} {"current_steps": 28965, "total_steps": 40000, "loss": 0.1526, "lr": 8.817613549657244e-06, "epoch": 1.3112338441340907, "percentage": 72.41, "elapsed_time": "23:40:25", "remaining_time": "9:01:08", "throughput": 554.98, "total_tokens": 47298800} {"current_steps": 28970, "total_steps": 40000, "loss": 0.1227, "lr": 8.810131531817783e-06, "epoch": 1.3114601960207337, "percentage": 72.42, "elapsed_time": "23:40:28", "remaining_time": "9:00:49", "throughput": 555.06, "total_tokens": 47307088} {"current_steps": 28975, "total_steps": 40000, "loss": 0.1012, "lr": 8.802652010659496e-06, "epoch": 1.3116865479073767, "percentage": 72.44, "elapsed_time": "23:40:31", "remaining_time": "9:00:30", "throughput": 555.14, "total_tokens": 47315472} {"current_steps": 28980, "total_steps": 40000, "loss": 0.1088, "lr": 8.795174987335827e-06, "epoch": 1.3119128997940197, "percentage": 72.45, "elapsed_time": "23:40:34", "remaining_time": "9:00:11", "throughput": 555.21, "total_tokens": 47322960} {"current_steps": 28985, "total_steps": 40000, "loss": 0.0815, "lr": 8.787700462999807e-06, "epoch": 1.3121392516806627, "percentage": 72.46, "elapsed_time": "23:40:38", "remaining_time": "8:59:52", "throughput": 555.28, "total_tokens": 47330832} {"current_steps": 28990, "total_steps": 40000, "loss": 0.1205, "lr": 8.780228438804122e-06, "epoch": 1.3123656035673057, "percentage": 72.47, "elapsed_time": "23:40:41", "remaining_time": "8:59:33", "throughput": 555.35, "total_tokens": 47338736} {"current_steps": 28995, "total_steps": 40000, "loss": 0.0876, "lr": 8.772758915901032e-06, "epoch": 1.3125919554539487, "percentage": 72.49, "elapsed_time": "23:40:44", "remaining_time": "8:59:14", "throughput": 555.42, "total_tokens": 47346704} {"current_steps": 29000, "total_steps": 40000, "loss": 0.0925, "lr": 8.765291895442443e-06, "epoch": 1.3128183073405917, "percentage": 72.5, "elapsed_time": "23:40:47", "remaining_time": "8:58:55", "throughput": 555.5, "total_tokens": 47354768} {"current_steps": 29000, "total_steps": 40000, "eval_loss": 0.1226072609424591, "epoch": 1.3128183073405917, "percentage": 72.5, "elapsed_time": "23:48:30", "remaining_time": "9:01:50", "throughput": 552.5, "total_tokens": 47354768} {"current_steps": 29005, "total_steps": 40000, "loss": 0.1053, "lr": 8.75782737857987e-06, "epoch": 1.3130446592272347, "percentage": 72.51, "elapsed_time": "23:48:34", "remaining_time": "9:01:31", "throughput": 552.56, "total_tokens": 47362704} {"current_steps": 29010, "total_steps": 40000, "loss": 0.0965, "lr": 8.750365366464425e-06, "epoch": 1.3132710111138777, "percentage": 72.52, "elapsed_time": "23:48:37", "remaining_time": "9:01:12", "throughput": 552.63, "total_tokens": 47370256} {"current_steps": 29015, "total_steps": 40000, "loss": 0.1469, "lr": 8.742905860246838e-06, "epoch": 1.3134973630005207, "percentage": 72.54, "elapsed_time": "23:48:40", "remaining_time": "9:00:53", "throughput": 552.72, "total_tokens": 47379376} {"current_steps": 29020, "total_steps": 40000, "loss": 0.1503, "lr": 8.735448861077478e-06, "epoch": 1.3137237148871637, "percentage": 72.55, "elapsed_time": "23:48:44", "remaining_time": "9:00:34", "throughput": 552.8, "total_tokens": 47388336} {"current_steps": 29025, "total_steps": 40000, "loss": 0.1251, "lr": 8.727994370106288e-06, "epoch": 1.3139500667738067, "percentage": 72.56, "elapsed_time": "23:48:47", "remaining_time": "9:00:15", "throughput": 552.88, "total_tokens": 47396624} {"current_steps": 29030, "total_steps": 40000, "loss": 0.1033, "lr": 8.720542388482861e-06, "epoch": 1.3141764186604497, "percentage": 72.58, "elapsed_time": "23:48:50", "remaining_time": "8:59:56", "throughput": 552.95, "total_tokens": 47404560} {"current_steps": 29035, "total_steps": 40000, "loss": 0.1154, "lr": 8.71309291735637e-06, "epoch": 1.3144027705470926, "percentage": 72.59, "elapsed_time": "23:48:53", "remaining_time": "8:59:37", "throughput": 553.02, "total_tokens": 47412144} {"current_steps": 29040, "total_steps": 40000, "loss": 0.1846, "lr": 8.705645957875621e-06, "epoch": 1.3146291224337354, "percentage": 72.6, "elapsed_time": "23:48:56", "remaining_time": "8:59:17", "throughput": 553.09, "total_tokens": 47420272} {"current_steps": 29045, "total_steps": 40000, "loss": 0.1348, "lr": 8.698201511189048e-06, "epoch": 1.3148554743203784, "percentage": 72.61, "elapsed_time": "23:49:00", "remaining_time": "8:58:58", "throughput": 553.18, "total_tokens": 47429968} {"current_steps": 29050, "total_steps": 40000, "loss": 0.1364, "lr": 8.690759578444649e-06, "epoch": 1.3150818262070214, "percentage": 72.62, "elapsed_time": "23:49:03", "remaining_time": "8:58:39", "throughput": 553.26, "total_tokens": 47438224} {"current_steps": 29055, "total_steps": 40000, "loss": 0.1535, "lr": 8.68332016079008e-06, "epoch": 1.3153081780936644, "percentage": 72.64, "elapsed_time": "23:49:06", "remaining_time": "8:58:20", "throughput": 553.33, "total_tokens": 47446160} {"current_steps": 29060, "total_steps": 40000, "loss": 0.1438, "lr": 8.6758832593726e-06, "epoch": 1.3155345299803074, "percentage": 72.65, "elapsed_time": "23:49:09", "remaining_time": "8:58:01", "throughput": 553.4, "total_tokens": 47454256} {"current_steps": 29065, "total_steps": 40000, "loss": 0.1069, "lr": 8.668448875339053e-06, "epoch": 1.3157608818669504, "percentage": 72.66, "elapsed_time": "23:49:12", "remaining_time": "8:57:42", "throughput": 553.47, "total_tokens": 47461616} {"current_steps": 29070, "total_steps": 40000, "loss": 0.1422, "lr": 8.661017009835933e-06, "epoch": 1.3159872337535934, "percentage": 72.67, "elapsed_time": "23:49:15", "remaining_time": "8:57:23", "throughput": 553.55, "total_tokens": 47469776} {"current_steps": 29075, "total_steps": 40000, "loss": 0.1292, "lr": 8.653587664009311e-06, "epoch": 1.3162135856402364, "percentage": 72.69, "elapsed_time": "23:49:19", "remaining_time": "8:57:04", "throughput": 553.62, "total_tokens": 47477584} {"current_steps": 29080, "total_steps": 40000, "loss": 0.1194, "lr": 8.646160839004902e-06, "epoch": 1.3164399375268792, "percentage": 72.7, "elapsed_time": "23:49:22", "remaining_time": "8:56:45", "throughput": 553.69, "total_tokens": 47485712} {"current_steps": 29085, "total_steps": 40000, "loss": 0.1106, "lr": 8.638736535967998e-06, "epoch": 1.3166662894135222, "percentage": 72.71, "elapsed_time": "23:49:25", "remaining_time": "8:56:25", "throughput": 553.77, "total_tokens": 47494352} {"current_steps": 29090, "total_steps": 40000, "loss": 0.1632, "lr": 8.631314756043535e-06, "epoch": 1.3168926413001651, "percentage": 72.72, "elapsed_time": "23:49:28", "remaining_time": "8:56:06", "throughput": 553.84, "total_tokens": 47502288} {"current_steps": 29095, "total_steps": 40000, "loss": 0.1629, "lr": 8.62389550037603e-06, "epoch": 1.3171189931868081, "percentage": 72.74, "elapsed_time": "23:49:31", "remaining_time": "8:55:47", "throughput": 553.93, "total_tokens": 47511664} {"current_steps": 29100, "total_steps": 40000, "loss": 0.1292, "lr": 8.616478770109646e-06, "epoch": 1.3173453450734511, "percentage": 72.75, "elapsed_time": "23:49:35", "remaining_time": "8:55:28", "throughput": 554.0, "total_tokens": 47519504} {"current_steps": 29105, "total_steps": 40000, "loss": 0.1085, "lr": 8.609064566388111e-06, "epoch": 1.3175716969600941, "percentage": 72.76, "elapsed_time": "23:49:38", "remaining_time": "8:55:09", "throughput": 554.07, "total_tokens": 47527376} {"current_steps": 29110, "total_steps": 40000, "loss": 0.1145, "lr": 8.601652890354815e-06, "epoch": 1.3177980488467371, "percentage": 72.78, "elapsed_time": "23:49:41", "remaining_time": "8:54:50", "throughput": 554.15, "total_tokens": 47535728} {"current_steps": 29115, "total_steps": 40000, "loss": 0.1747, "lr": 8.594243743152705e-06, "epoch": 1.3180244007333801, "percentage": 72.79, "elapsed_time": "23:49:44", "remaining_time": "8:54:31", "throughput": 554.23, "total_tokens": 47544368} {"current_steps": 29120, "total_steps": 40000, "loss": 0.1314, "lr": 8.58683712592438e-06, "epoch": 1.3182507526200231, "percentage": 72.8, "elapsed_time": "23:49:47", "remaining_time": "8:54:12", "throughput": 554.3, "total_tokens": 47552112} {"current_steps": 29125, "total_steps": 40000, "loss": 0.1164, "lr": 8.579433039812037e-06, "epoch": 1.318477104506666, "percentage": 72.81, "elapsed_time": "23:49:51", "remaining_time": "8:53:53", "throughput": 554.38, "total_tokens": 47560400} {"current_steps": 29130, "total_steps": 40000, "loss": 0.1659, "lr": 8.572031485957466e-06, "epoch": 1.318703456393309, "percentage": 72.82, "elapsed_time": "23:49:54", "remaining_time": "8:53:34", "throughput": 554.45, "total_tokens": 47569040} {"current_steps": 29135, "total_steps": 40000, "loss": 0.0908, "lr": 8.564632465502084e-06, "epoch": 1.318929808279952, "percentage": 72.84, "elapsed_time": "23:49:57", "remaining_time": "8:53:15", "throughput": 554.53, "total_tokens": 47577424} {"current_steps": 29140, "total_steps": 40000, "loss": 0.119, "lr": 8.557235979586928e-06, "epoch": 1.319156160166595, "percentage": 72.85, "elapsed_time": "23:50:00", "remaining_time": "8:52:56", "throughput": 554.61, "total_tokens": 47585840} {"current_steps": 29145, "total_steps": 40000, "loss": 0.1298, "lr": 8.549842029352606e-06, "epoch": 1.319382512053238, "percentage": 72.86, "elapsed_time": "23:50:03", "remaining_time": "8:52:37", "throughput": 554.68, "total_tokens": 47594032} {"current_steps": 29150, "total_steps": 40000, "loss": 0.1181, "lr": 8.542450615939376e-06, "epoch": 1.3196088639398809, "percentage": 72.88, "elapsed_time": "23:50:07", "remaining_time": "8:52:18", "throughput": 554.76, "total_tokens": 47602224} {"current_steps": 29155, "total_steps": 40000, "loss": 0.2042, "lr": 8.535061740487082e-06, "epoch": 1.3198352158265239, "percentage": 72.89, "elapsed_time": "23:50:10", "remaining_time": "8:51:59", "throughput": 554.83, "total_tokens": 47610256} {"current_steps": 29160, "total_steps": 40000, "loss": 0.1316, "lr": 8.527675404135168e-06, "epoch": 1.3200615677131669, "percentage": 72.9, "elapsed_time": "23:50:13", "remaining_time": "8:51:40", "throughput": 554.9, "total_tokens": 47618224} {"current_steps": 29165, "total_steps": 40000, "loss": 0.1277, "lr": 8.520291608022724e-06, "epoch": 1.3202879195998098, "percentage": 72.91, "elapsed_time": "23:50:16", "remaining_time": "8:51:21", "throughput": 554.98, "total_tokens": 47626416} {"current_steps": 29170, "total_steps": 40000, "loss": 0.1503, "lr": 8.512910353288398e-06, "epoch": 1.3205142714864528, "percentage": 72.92, "elapsed_time": "23:50:19", "remaining_time": "8:51:02", "throughput": 555.06, "total_tokens": 47634832} {"current_steps": 29175, "total_steps": 40000, "loss": 0.109, "lr": 8.505531641070486e-06, "epoch": 1.3207406233730958, "percentage": 72.94, "elapsed_time": "23:50:23", "remaining_time": "8:50:43", "throughput": 555.13, "total_tokens": 47642832} {"current_steps": 29180, "total_steps": 40000, "loss": 0.1024, "lr": 8.498155472506885e-06, "epoch": 1.3209669752597388, "percentage": 72.95, "elapsed_time": "23:50:26", "remaining_time": "8:50:24", "throughput": 555.2, "total_tokens": 47651088} {"current_steps": 29185, "total_steps": 40000, "loss": 0.0996, "lr": 8.49078184873508e-06, "epoch": 1.3211933271463818, "percentage": 72.96, "elapsed_time": "23:50:29", "remaining_time": "8:50:05", "throughput": 555.28, "total_tokens": 47659408} {"current_steps": 29190, "total_steps": 40000, "loss": 0.1104, "lr": 8.483410770892188e-06, "epoch": 1.3214196790330248, "percentage": 72.97, "elapsed_time": "23:50:32", "remaining_time": "8:49:46", "throughput": 555.35, "total_tokens": 47667248} {"current_steps": 29195, "total_steps": 40000, "loss": 0.1356, "lr": 8.476042240114909e-06, "epoch": 1.3216460309196676, "percentage": 72.99, "elapsed_time": "23:50:35", "remaining_time": "8:49:27", "throughput": 555.42, "total_tokens": 47675184} {"current_steps": 29200, "total_steps": 40000, "loss": 0.1576, "lr": 8.468676257539568e-06, "epoch": 1.3218723828063106, "percentage": 73.0, "elapsed_time": "23:50:38", "remaining_time": "8:49:08", "throughput": 555.5, "total_tokens": 47683536} {"current_steps": 29200, "total_steps": 40000, "eval_loss": 0.12244368344545364, "epoch": 1.3218723828063106, "percentage": 73.0, "elapsed_time": "23:58:21", "remaining_time": "8:51:59", "throughput": 552.52, "total_tokens": 47683536} {"current_steps": 29205, "total_steps": 40000, "loss": 0.1168, "lr": 8.4613128243021e-06, "epoch": 1.3220987346929536, "percentage": 73.01, "elapsed_time": "23:58:26", "remaining_time": "8:51:41", "throughput": 552.58, "total_tokens": 47691312} {"current_steps": 29210, "total_steps": 40000, "loss": 0.1342, "lr": 8.453951941538028e-06, "epoch": 1.3223250865795966, "percentage": 73.02, "elapsed_time": "23:58:29", "remaining_time": "8:51:22", "throughput": 552.66, "total_tokens": 47699664} {"current_steps": 29215, "total_steps": 40000, "loss": 0.1297, "lr": 8.446593610382495e-06, "epoch": 1.3225514384662396, "percentage": 73.04, "elapsed_time": "23:58:32", "remaining_time": "8:51:03", "throughput": 552.73, "total_tokens": 47707728} {"current_steps": 29220, "total_steps": 40000, "loss": 0.1418, "lr": 8.439237831970259e-06, "epoch": 1.3227777903528826, "percentage": 73.05, "elapsed_time": "23:58:35", "remaining_time": "8:50:44", "throughput": 552.8, "total_tokens": 47715440} {"current_steps": 29225, "total_steps": 40000, "loss": 0.139, "lr": 8.431884607435667e-06, "epoch": 1.3230041422395256, "percentage": 73.06, "elapsed_time": "23:58:38", "remaining_time": "8:50:25", "throughput": 552.87, "total_tokens": 47723440} {"current_steps": 29230, "total_steps": 40000, "loss": 0.1315, "lr": 8.424533937912665e-06, "epoch": 1.3232304941261686, "percentage": 73.08, "elapsed_time": "23:58:42", "remaining_time": "8:50:05", "throughput": 552.95, "total_tokens": 47731728} {"current_steps": 29235, "total_steps": 40000, "loss": 0.1157, "lr": 8.41718582453484e-06, "epoch": 1.3234568460128115, "percentage": 73.09, "elapsed_time": "23:58:45", "remaining_time": "8:49:46", "throughput": 553.02, "total_tokens": 47740048} {"current_steps": 29240, "total_steps": 40000, "loss": 0.1099, "lr": 8.409840268435346e-06, "epoch": 1.3236831978994545, "percentage": 73.1, "elapsed_time": "23:58:48", "remaining_time": "8:49:27", "throughput": 553.1, "total_tokens": 47748176} {"current_steps": 29245, "total_steps": 40000, "loss": 0.1365, "lr": 8.402497270746976e-06, "epoch": 1.3239095497860975, "percentage": 73.11, "elapsed_time": "23:58:51", "remaining_time": "8:49:08", "throughput": 553.17, "total_tokens": 47756304} {"current_steps": 29250, "total_steps": 40000, "loss": 0.1429, "lr": 8.395156832602095e-06, "epoch": 1.3241359016727405, "percentage": 73.12, "elapsed_time": "23:58:54", "remaining_time": "8:48:49", "throughput": 553.25, "total_tokens": 47764752} {"current_steps": 29255, "total_steps": 40000, "loss": 0.1016, "lr": 8.387818955132707e-06, "epoch": 1.3243622535593835, "percentage": 73.14, "elapsed_time": "23:58:58", "remaining_time": "8:48:30", "throughput": 553.32, "total_tokens": 47772912} {"current_steps": 29260, "total_steps": 40000, "loss": 0.1422, "lr": 8.38048363947039e-06, "epoch": 1.3245886054460265, "percentage": 73.15, "elapsed_time": "23:59:01", "remaining_time": "8:48:11", "throughput": 553.4, "total_tokens": 47780880} {"current_steps": 29265, "total_steps": 40000, "loss": 0.1222, "lr": 8.373150886746351e-06, "epoch": 1.3248149573326693, "percentage": 73.16, "elapsed_time": "23:59:04", "remaining_time": "8:47:52", "throughput": 553.47, "total_tokens": 47789168} {"current_steps": 29270, "total_steps": 40000, "loss": 0.0977, "lr": 8.365820698091397e-06, "epoch": 1.3250413092193123, "percentage": 73.17, "elapsed_time": "23:59:07", "remaining_time": "8:47:33", "throughput": 553.54, "total_tokens": 47797072} {"current_steps": 29275, "total_steps": 40000, "loss": 0.0755, "lr": 8.358493074635922e-06, "epoch": 1.3252676611059553, "percentage": 73.19, "elapsed_time": "23:59:10", "remaining_time": "8:47:14", "throughput": 553.61, "total_tokens": 47804528} {"current_steps": 29280, "total_steps": 40000, "loss": 0.1387, "lr": 8.351168017509948e-06, "epoch": 1.3254940129925983, "percentage": 73.2, "elapsed_time": "23:59:14", "remaining_time": "8:46:56", "throughput": 553.69, "total_tokens": 47813584} {"current_steps": 29285, "total_steps": 40000, "loss": 0.1105, "lr": 8.343845527843094e-06, "epoch": 1.3257203648792413, "percentage": 73.21, "elapsed_time": "23:59:17", "remaining_time": "8:46:37", "throughput": 553.76, "total_tokens": 47821584} {"current_steps": 29290, "total_steps": 40000, "loss": 0.0953, "lr": 8.336525606764566e-06, "epoch": 1.3259467167658843, "percentage": 73.22, "elapsed_time": "23:59:20", "remaining_time": "8:46:18", "throughput": 553.84, "total_tokens": 47830192} {"current_steps": 29295, "total_steps": 40000, "loss": 0.1139, "lr": 8.329208255403204e-06, "epoch": 1.3261730686525273, "percentage": 73.24, "elapsed_time": "23:59:24", "remaining_time": "8:45:59", "throughput": 553.93, "total_tokens": 47839312} {"current_steps": 29300, "total_steps": 40000, "loss": 0.0999, "lr": 8.321893474887426e-06, "epoch": 1.3263994205391703, "percentage": 73.25, "elapsed_time": "23:59:27", "remaining_time": "8:45:40", "throughput": 554.0, "total_tokens": 47847696} {"current_steps": 29305, "total_steps": 40000, "loss": 0.0987, "lr": 8.31458126634526e-06, "epoch": 1.326625772425813, "percentage": 73.26, "elapsed_time": "23:59:30", "remaining_time": "8:45:21", "throughput": 554.08, "total_tokens": 47855696} {"current_steps": 29310, "total_steps": 40000, "loss": 0.086, "lr": 8.30727163090435e-06, "epoch": 1.326852124312456, "percentage": 73.28, "elapsed_time": "23:59:33", "remaining_time": "8:45:02", "throughput": 554.15, "total_tokens": 47863664} {"current_steps": 29315, "total_steps": 40000, "loss": 0.1053, "lr": 8.29996456969192e-06, "epoch": 1.327078476199099, "percentage": 73.29, "elapsed_time": "23:59:36", "remaining_time": "8:44:43", "throughput": 554.22, "total_tokens": 47871568} {"current_steps": 29320, "total_steps": 40000, "loss": 0.1312, "lr": 8.292660083834818e-06, "epoch": 1.327304828085742, "percentage": 73.3, "elapsed_time": "23:59:39", "remaining_time": "8:44:24", "throughput": 554.29, "total_tokens": 47879312} {"current_steps": 29325, "total_steps": 40000, "loss": 0.1443, "lr": 8.2853581744595e-06, "epoch": 1.327531179972385, "percentage": 73.31, "elapsed_time": "23:59:42", "remaining_time": "8:44:05", "throughput": 554.36, "total_tokens": 47887376} {"current_steps": 29330, "total_steps": 40000, "loss": 0.1473, "lr": 8.278058842691991e-06, "epoch": 1.327757531859028, "percentage": 73.32, "elapsed_time": "23:59:46", "remaining_time": "8:43:46", "throughput": 554.43, "total_tokens": 47895344} {"current_steps": 29335, "total_steps": 40000, "loss": 0.1162, "lr": 8.27076208965796e-06, "epoch": 1.327983883745671, "percentage": 73.34, "elapsed_time": "23:59:49", "remaining_time": "8:43:27", "throughput": 554.5, "total_tokens": 47903280} {"current_steps": 29340, "total_steps": 40000, "loss": 0.1117, "lr": 8.263467916482637e-06, "epoch": 1.328210235632314, "percentage": 73.35, "elapsed_time": "23:59:52", "remaining_time": "8:43:08", "throughput": 554.57, "total_tokens": 47911056} {"current_steps": 29345, "total_steps": 40000, "loss": 0.1125, "lr": 8.256176324290885e-06, "epoch": 1.328436587518957, "percentage": 73.36, "elapsed_time": "23:59:55", "remaining_time": "8:42:49", "throughput": 554.65, "total_tokens": 47919472} {"current_steps": 29350, "total_steps": 40000, "loss": 0.1342, "lr": 8.248887314207168e-06, "epoch": 1.3286629394056, "percentage": 73.38, "elapsed_time": "23:59:58", "remaining_time": "8:42:30", "throughput": 554.72, "total_tokens": 47927408} {"current_steps": 29355, "total_steps": 40000, "loss": 0.1257, "lr": 8.24160088735553e-06, "epoch": 1.328889291292243, "percentage": 73.39, "elapsed_time": "1 day, 0:00:02", "remaining_time": "8:42:12", "throughput": 554.81, "total_tokens": 47936624} {"current_steps": 29360, "total_steps": 40000, "loss": 0.102, "lr": 8.234317044859629e-06, "epoch": 1.329115643178886, "percentage": 73.4, "elapsed_time": "1 day, 0:00:05", "remaining_time": "8:41:53", "throughput": 554.88, "total_tokens": 47944496} {"current_steps": 29365, "total_steps": 40000, "loss": 0.1229, "lr": 8.227035787842744e-06, "epoch": 1.329341995065529, "percentage": 73.41, "elapsed_time": "1 day, 0:00:08", "remaining_time": "8:41:34", "throughput": 554.95, "total_tokens": 47952272} {"current_steps": 29370, "total_steps": 40000, "loss": 0.13, "lr": 8.219757117427721e-06, "epoch": 1.329568346952172, "percentage": 73.42, "elapsed_time": "1 day, 0:00:11", "remaining_time": "8:41:15", "throughput": 555.02, "total_tokens": 47960272} {"current_steps": 29375, "total_steps": 40000, "loss": 0.082, "lr": 8.212481034737014e-06, "epoch": 1.329794698838815, "percentage": 73.44, "elapsed_time": "1 day, 0:00:14", "remaining_time": "8:40:56", "throughput": 555.1, "total_tokens": 47968496} {"current_steps": 29380, "total_steps": 40000, "loss": 0.1445, "lr": 8.205207540892707e-06, "epoch": 1.3300210507254577, "percentage": 73.45, "elapsed_time": "1 day, 0:00:17", "remaining_time": "8:40:37", "throughput": 555.17, "total_tokens": 47976752} {"current_steps": 29385, "total_steps": 40000, "loss": 0.1275, "lr": 8.197936637016442e-06, "epoch": 1.3302474026121007, "percentage": 73.46, "elapsed_time": "1 day, 0:00:21", "remaining_time": "8:40:18", "throughput": 555.25, "total_tokens": 47985360} {"current_steps": 29390, "total_steps": 40000, "loss": 0.1149, "lr": 8.190668324229508e-06, "epoch": 1.3304737544987437, "percentage": 73.47, "elapsed_time": "1 day, 0:00:24", "remaining_time": "8:39:59", "throughput": 555.32, "total_tokens": 47993200} {"current_steps": 29395, "total_steps": 40000, "loss": 0.1423, "lr": 8.183402603652749e-06, "epoch": 1.3307001063853867, "percentage": 73.49, "elapsed_time": "1 day, 0:00:27", "remaining_time": "8:39:40", "throughput": 555.39, "total_tokens": 48001392} {"current_steps": 29400, "total_steps": 40000, "loss": 0.1154, "lr": 8.176139476406635e-06, "epoch": 1.3309264582720297, "percentage": 73.5, "elapsed_time": "1 day, 0:00:30", "remaining_time": "8:39:22", "throughput": 555.47, "total_tokens": 48009456} {"current_steps": 29400, "total_steps": 40000, "eval_loss": 0.12252642959356308, "epoch": 1.3309264582720297, "percentage": 73.5, "elapsed_time": "1 day, 0:08:13", "remaining_time": "8:42:08", "throughput": 552.51, "total_tokens": 48009456} {"current_steps": 29405, "total_steps": 40000, "loss": 0.0877, "lr": 8.16887894361125e-06, "epoch": 1.3311528101586727, "percentage": 73.51, "elapsed_time": "1 day, 0:08:17", "remaining_time": "8:41:50", "throughput": 552.57, "total_tokens": 48016912} {"current_steps": 29410, "total_steps": 40000, "loss": 0.102, "lr": 8.161621006386233e-06, "epoch": 1.3313791620453157, "percentage": 73.52, "elapsed_time": "1 day, 0:08:20", "remaining_time": "8:41:31", "throughput": 552.64, "total_tokens": 48024496} {"current_steps": 29415, "total_steps": 40000, "loss": 0.1154, "lr": 8.154365665850869e-06, "epoch": 1.3316055139319587, "percentage": 73.54, "elapsed_time": "1 day, 0:08:23", "remaining_time": "8:41:12", "throughput": 552.72, "total_tokens": 48033168} {"current_steps": 29420, "total_steps": 40000, "loss": 0.0798, "lr": 8.147112923124005e-06, "epoch": 1.3318318658186015, "percentage": 73.55, "elapsed_time": "1 day, 0:08:26", "remaining_time": "8:40:53", "throughput": 552.78, "total_tokens": 48040816} {"current_steps": 29425, "total_steps": 40000, "loss": 0.1039, "lr": 8.13986277932412e-06, "epoch": 1.3320582177052445, "percentage": 73.56, "elapsed_time": "1 day, 0:08:30", "remaining_time": "8:40:34", "throughput": 552.85, "total_tokens": 48048400} {"current_steps": 29430, "total_steps": 40000, "loss": 0.0801, "lr": 8.132615235569277e-06, "epoch": 1.3322845695918875, "percentage": 73.58, "elapsed_time": "1 day, 0:08:33", "remaining_time": "8:40:15", "throughput": 552.93, "total_tokens": 48056656} {"current_steps": 29435, "total_steps": 40000, "loss": 0.137, "lr": 8.125370292977124e-06, "epoch": 1.3325109214785305, "percentage": 73.59, "elapsed_time": "1 day, 0:08:36", "remaining_time": "8:39:56", "throughput": 553.0, "total_tokens": 48064656} {"current_steps": 29440, "total_steps": 40000, "loss": 0.1135, "lr": 8.118127952664944e-06, "epoch": 1.3327372733651734, "percentage": 73.6, "elapsed_time": "1 day, 0:08:39", "remaining_time": "8:39:37", "throughput": 553.07, "total_tokens": 48072720} {"current_steps": 29445, "total_steps": 40000, "loss": 0.1264, "lr": 8.110888215749574e-06, "epoch": 1.3329636252518164, "percentage": 73.61, "elapsed_time": "1 day, 0:08:42", "remaining_time": "8:39:18", "throughput": 553.14, "total_tokens": 48080112} {"current_steps": 29450, "total_steps": 40000, "loss": 0.0727, "lr": 8.10365108334749e-06, "epoch": 1.3331899771384594, "percentage": 73.62, "elapsed_time": "1 day, 0:08:46", "remaining_time": "8:38:59", "throughput": 553.22, "total_tokens": 48089392} {"current_steps": 29455, "total_steps": 40000, "loss": 0.1192, "lr": 8.096416556574743e-06, "epoch": 1.3334163290251024, "percentage": 73.64, "elapsed_time": "1 day, 0:08:49", "remaining_time": "8:38:40", "throughput": 553.29, "total_tokens": 48096880} {"current_steps": 29460, "total_steps": 40000, "loss": 0.1212, "lr": 8.08918463654698e-06, "epoch": 1.3336426809117454, "percentage": 73.65, "elapsed_time": "1 day, 0:08:52", "remaining_time": "8:38:21", "throughput": 553.36, "total_tokens": 48104400} {"current_steps": 29465, "total_steps": 40000, "loss": 0.0884, "lr": 8.081955324379458e-06, "epoch": 1.3338690327983884, "percentage": 73.66, "elapsed_time": "1 day, 0:08:55", "remaining_time": "8:38:03", "throughput": 553.44, "total_tokens": 48113104} {"current_steps": 29470, "total_steps": 40000, "loss": 0.1081, "lr": 8.074728621187039e-06, "epoch": 1.3340953846850314, "percentage": 73.67, "elapsed_time": "1 day, 0:08:58", "remaining_time": "8:37:44", "throughput": 553.51, "total_tokens": 48121200} {"current_steps": 29475, "total_steps": 40000, "loss": 0.0754, "lr": 8.067504528084158e-06, "epoch": 1.3343217365716744, "percentage": 73.69, "elapsed_time": "1 day, 0:09:01", "remaining_time": "8:37:25", "throughput": 553.59, "total_tokens": 48129744} {"current_steps": 29480, "total_steps": 40000, "loss": 0.1508, "lr": 8.060283046184861e-06, "epoch": 1.3345480884583174, "percentage": 73.7, "elapsed_time": "1 day, 0:09:04", "remaining_time": "8:37:06", "throughput": 553.65, "total_tokens": 48137360} {"current_steps": 29485, "total_steps": 40000, "loss": 0.0803, "lr": 8.053064176602806e-06, "epoch": 1.3347744403449604, "percentage": 73.71, "elapsed_time": "1 day, 0:09:07", "remaining_time": "8:36:47", "throughput": 553.72, "total_tokens": 48145072} {"current_steps": 29490, "total_steps": 40000, "loss": 0.1128, "lr": 8.045847920451216e-06, "epoch": 1.3350007922316032, "percentage": 73.72, "elapsed_time": "1 day, 0:09:11", "remaining_time": "8:36:28", "throughput": 553.79, "total_tokens": 48152912} {"current_steps": 29495, "total_steps": 40000, "loss": 0.1412, "lr": 8.038634278842944e-06, "epoch": 1.3352271441182462, "percentage": 73.74, "elapsed_time": "1 day, 0:09:14", "remaining_time": "8:36:09", "throughput": 553.87, "total_tokens": 48161104} {"current_steps": 29500, "total_steps": 40000, "loss": 0.1237, "lr": 8.031423252890408e-06, "epoch": 1.3354534960048892, "percentage": 73.75, "elapsed_time": "1 day, 0:09:17", "remaining_time": "8:35:50", "throughput": 553.95, "total_tokens": 48170000} {"current_steps": 29505, "total_steps": 40000, "loss": 0.1412, "lr": 8.024214843705646e-06, "epoch": 1.3356798478915322, "percentage": 73.76, "elapsed_time": "1 day, 0:09:20", "remaining_time": "8:35:32", "throughput": 554.02, "total_tokens": 48178384} {"current_steps": 29510, "total_steps": 40000, "loss": 0.1516, "lr": 8.017009052400295e-06, "epoch": 1.3359061997781752, "percentage": 73.78, "elapsed_time": "1 day, 0:09:24", "remaining_time": "8:35:13", "throughput": 554.1, "total_tokens": 48186576} {"current_steps": 29515, "total_steps": 40000, "loss": 0.1128, "lr": 8.00980588008557e-06, "epoch": 1.3361325516648181, "percentage": 73.79, "elapsed_time": "1 day, 0:09:27", "remaining_time": "8:34:54", "throughput": 554.17, "total_tokens": 48194608} {"current_steps": 29520, "total_steps": 40000, "loss": 0.1456, "lr": 8.002605327872282e-06, "epoch": 1.3363589035514611, "percentage": 73.8, "elapsed_time": "1 day, 0:09:30", "remaining_time": "8:34:35", "throughput": 554.24, "total_tokens": 48202576} {"current_steps": 29525, "total_steps": 40000, "loss": 0.0942, "lr": 7.995407396870862e-06, "epoch": 1.3365852554381041, "percentage": 73.81, "elapsed_time": "1 day, 0:09:33", "remaining_time": "8:34:16", "throughput": 554.31, "total_tokens": 48210512} {"current_steps": 29530, "total_steps": 40000, "loss": 0.1459, "lr": 7.988212088191307e-06, "epoch": 1.3368116073247471, "percentage": 73.83, "elapsed_time": "1 day, 0:09:36", "remaining_time": "8:33:57", "throughput": 554.39, "total_tokens": 48218992} {"current_steps": 29535, "total_steps": 40000, "loss": 0.0973, "lr": 7.98101940294324e-06, "epoch": 1.33703795921139, "percentage": 73.84, "elapsed_time": "1 day, 0:09:39", "remaining_time": "8:33:39", "throughput": 554.46, "total_tokens": 48226832} {"current_steps": 29540, "total_steps": 40000, "loss": 0.099, "lr": 7.973829342235847e-06, "epoch": 1.337264311098033, "percentage": 73.85, "elapsed_time": "1 day, 0:09:43", "remaining_time": "8:33:20", "throughput": 554.54, "total_tokens": 48235632} {"current_steps": 29545, "total_steps": 40000, "loss": 0.1185, "lr": 7.966641907177936e-06, "epoch": 1.337490662984676, "percentage": 73.86, "elapsed_time": "1 day, 0:09:46", "remaining_time": "8:33:01", "throughput": 554.62, "total_tokens": 48243952} {"current_steps": 29550, "total_steps": 40000, "loss": 0.2195, "lr": 7.959457098877901e-06, "epoch": 1.3377170148713189, "percentage": 73.88, "elapsed_time": "1 day, 0:09:49", "remaining_time": "8:32:42", "throughput": 554.69, "total_tokens": 48252208} {"current_steps": 29555, "total_steps": 40000, "loss": 0.128, "lr": 7.952274918443719e-06, "epoch": 1.3379433667579619, "percentage": 73.89, "elapsed_time": "1 day, 0:09:52", "remaining_time": "8:32:24", "throughput": 554.76, "total_tokens": 48260560} {"current_steps": 29560, "total_steps": 40000, "loss": 0.0851, "lr": 7.945095366982983e-06, "epoch": 1.3381697186446049, "percentage": 73.9, "elapsed_time": "1 day, 0:09:56", "remaining_time": "8:32:05", "throughput": 554.84, "total_tokens": 48269008} {"current_steps": 29565, "total_steps": 40000, "loss": 0.1026, "lr": 7.937918445602871e-06, "epoch": 1.3383960705312479, "percentage": 73.91, "elapsed_time": "1 day, 0:09:59", "remaining_time": "8:31:46", "throughput": 554.92, "total_tokens": 48277456} {"current_steps": 29570, "total_steps": 40000, "loss": 0.1036, "lr": 7.930744155410145e-06, "epoch": 1.3386224224178909, "percentage": 73.92, "elapsed_time": "1 day, 0:10:02", "remaining_time": "8:31:27", "throughput": 554.99, "total_tokens": 48285136} {"current_steps": 29575, "total_steps": 40000, "loss": 0.1462, "lr": 7.923572497511181e-06, "epoch": 1.3388487743045339, "percentage": 73.94, "elapsed_time": "1 day, 0:10:05", "remaining_time": "8:31:08", "throughput": 555.06, "total_tokens": 48293360} {"current_steps": 29580, "total_steps": 40000, "loss": 0.1333, "lr": 7.916403473011927e-06, "epoch": 1.3390751261911769, "percentage": 73.95, "elapsed_time": "1 day, 0:10:08", "remaining_time": "8:30:50", "throughput": 555.14, "total_tokens": 48302096} {"current_steps": 29585, "total_steps": 40000, "loss": 0.084, "lr": 7.909237083017953e-06, "epoch": 1.3393014780778199, "percentage": 73.96, "elapsed_time": "1 day, 0:10:11", "remaining_time": "8:30:31", "throughput": 555.21, "total_tokens": 48310096} {"current_steps": 29590, "total_steps": 40000, "loss": 0.1201, "lr": 7.902073328634389e-06, "epoch": 1.3395278299644628, "percentage": 73.98, "elapsed_time": "1 day, 0:10:15", "remaining_time": "8:30:12", "throughput": 555.3, "total_tokens": 48319440} {"current_steps": 29595, "total_steps": 40000, "loss": 0.1755, "lr": 7.894912210965987e-06, "epoch": 1.3397541818511058, "percentage": 73.99, "elapsed_time": "1 day, 0:10:18", "remaining_time": "8:29:53", "throughput": 555.37, "total_tokens": 48327376} {"current_steps": 29600, "total_steps": 40000, "loss": 0.1532, "lr": 7.887753731117075e-06, "epoch": 1.3399805337377488, "percentage": 74.0, "elapsed_time": "1 day, 0:10:21", "remaining_time": "8:29:35", "throughput": 555.44, "total_tokens": 48335280} {"current_steps": 29600, "total_steps": 40000, "eval_loss": 0.12253124266862869, "epoch": 1.3399805337377488, "percentage": 74.0, "elapsed_time": "1 day, 0:18:04", "remaining_time": "8:32:17", "throughput": 552.5, "total_tokens": 48335280} {"current_steps": 29605, "total_steps": 40000, "loss": 0.1219, "lr": 7.880597890191587e-06, "epoch": 1.3402068856243916, "percentage": 74.01, "elapsed_time": "1 day, 0:18:08", "remaining_time": "8:31:59", "throughput": 552.57, "total_tokens": 48343664} {"current_steps": 29610, "total_steps": 40000, "loss": 0.1042, "lr": 7.873444689293036e-06, "epoch": 1.3404332375110346, "percentage": 74.02, "elapsed_time": "1 day, 0:18:11", "remaining_time": "8:31:40", "throughput": 552.64, "total_tokens": 48351600} {"current_steps": 29615, "total_steps": 40000, "loss": 0.1297, "lr": 7.866294129524548e-06, "epoch": 1.3406595893976776, "percentage": 74.04, "elapsed_time": "1 day, 0:18:14", "remaining_time": "8:31:21", "throughput": 552.72, "total_tokens": 48359728} {"current_steps": 29620, "total_steps": 40000, "loss": 0.183, "lr": 7.859146211988811e-06, "epoch": 1.3408859412843206, "percentage": 74.05, "elapsed_time": "1 day, 0:18:18", "remaining_time": "8:31:02", "throughput": 552.8, "total_tokens": 48368848} {"current_steps": 29625, "total_steps": 40000, "loss": 0.0974, "lr": 7.852000937788134e-06, "epoch": 1.3411122931709636, "percentage": 74.06, "elapsed_time": "1 day, 0:18:21", "remaining_time": "8:30:43", "throughput": 552.87, "total_tokens": 48376784} {"current_steps": 29630, "total_steps": 40000, "loss": 0.1295, "lr": 7.844858308024416e-06, "epoch": 1.3413386450576066, "percentage": 74.08, "elapsed_time": "1 day, 0:18:24", "remaining_time": "8:30:25", "throughput": 552.94, "total_tokens": 48384944} {"current_steps": 29635, "total_steps": 40000, "loss": 0.0894, "lr": 7.837718323799122e-06, "epoch": 1.3415649969442496, "percentage": 74.09, "elapsed_time": "1 day, 0:18:27", "remaining_time": "8:30:06", "throughput": 553.01, "total_tokens": 48392656} {"current_steps": 29640, "total_steps": 40000, "loss": 0.1818, "lr": 7.83058098621334e-06, "epoch": 1.3417913488308926, "percentage": 74.1, "elapsed_time": "1 day, 0:18:30", "remaining_time": "8:29:47", "throughput": 553.09, "total_tokens": 48401008} {"current_steps": 29645, "total_steps": 40000, "loss": 0.0887, "lr": 7.823446296367739e-06, "epoch": 1.3420177007175353, "percentage": 74.11, "elapsed_time": "1 day, 0:18:33", "remaining_time": "8:29:28", "throughput": 553.16, "total_tokens": 48408912} {"current_steps": 29650, "total_steps": 40000, "loss": 0.1126, "lr": 7.81631425536257e-06, "epoch": 1.3422440526041783, "percentage": 74.12, "elapsed_time": "1 day, 0:18:37", "remaining_time": "8:29:09", "throughput": 553.23, "total_tokens": 48417456} {"current_steps": 29655, "total_steps": 40000, "loss": 0.117, "lr": 7.809184864297689e-06, "epoch": 1.3424704044908213, "percentage": 74.14, "elapsed_time": "1 day, 0:18:40", "remaining_time": "8:28:51", "throughput": 553.31, "total_tokens": 48425936} {"current_steps": 29660, "total_steps": 40000, "loss": 0.1239, "lr": 7.802058124272532e-06, "epoch": 1.3426967563774643, "percentage": 74.15, "elapsed_time": "1 day, 0:18:43", "remaining_time": "8:28:32", "throughput": 553.38, "total_tokens": 48433840} {"current_steps": 29665, "total_steps": 40000, "loss": 0.0442, "lr": 7.79493403638614e-06, "epoch": 1.3429231082641073, "percentage": 74.16, "elapsed_time": "1 day, 0:18:46", "remaining_time": "8:28:13", "throughput": 553.45, "total_tokens": 48441872} {"current_steps": 29670, "total_steps": 40000, "loss": 0.0934, "lr": 7.787812601737132e-06, "epoch": 1.3431494601507503, "percentage": 74.17, "elapsed_time": "1 day, 0:18:49", "remaining_time": "8:27:54", "throughput": 553.53, "total_tokens": 48450256} {"current_steps": 29675, "total_steps": 40000, "loss": 0.0745, "lr": 7.780693821423715e-06, "epoch": 1.3433758120373933, "percentage": 74.19, "elapsed_time": "1 day, 0:18:53", "remaining_time": "8:27:35", "throughput": 553.6, "total_tokens": 48458640} {"current_steps": 29680, "total_steps": 40000, "loss": 0.128, "lr": 7.773577696543705e-06, "epoch": 1.3436021639240363, "percentage": 74.2, "elapsed_time": "1 day, 0:18:56", "remaining_time": "8:27:17", "throughput": 553.67, "total_tokens": 48466544} {"current_steps": 29685, "total_steps": 40000, "loss": 0.1264, "lr": 7.7664642281945e-06, "epoch": 1.3438285158106793, "percentage": 74.21, "elapsed_time": "1 day, 0:18:59", "remaining_time": "8:26:58", "throughput": 553.74, "total_tokens": 48474448} {"current_steps": 29690, "total_steps": 40000, "loss": 0.068, "lr": 7.759353417473072e-06, "epoch": 1.3440548676973223, "percentage": 74.22, "elapsed_time": "1 day, 0:19:02", "remaining_time": "8:26:39", "throughput": 553.82, "total_tokens": 48482544} {"current_steps": 29695, "total_steps": 40000, "loss": 0.127, "lr": 7.752245265476016e-06, "epoch": 1.3442812195839653, "percentage": 74.24, "elapsed_time": "1 day, 0:19:05", "remaining_time": "8:26:20", "throughput": 553.89, "total_tokens": 48490896} {"current_steps": 29700, "total_steps": 40000, "loss": 0.094, "lr": 7.745139773299481e-06, "epoch": 1.3445075714706083, "percentage": 74.25, "elapsed_time": "1 day, 0:19:08", "remaining_time": "8:26:02", "throughput": 553.97, "total_tokens": 48499216} {"current_steps": 29705, "total_steps": 40000, "loss": 0.1472, "lr": 7.738036942039232e-06, "epoch": 1.3447339233572513, "percentage": 74.26, "elapsed_time": "1 day, 0:19:11", "remaining_time": "8:25:43", "throughput": 554.04, "total_tokens": 48507152} {"current_steps": 29710, "total_steps": 40000, "loss": 0.0914, "lr": 7.73093677279062e-06, "epoch": 1.3449602752438943, "percentage": 74.28, "elapsed_time": "1 day, 0:19:15", "remaining_time": "8:25:24", "throughput": 554.11, "total_tokens": 48515376} {"current_steps": 29715, "total_steps": 40000, "loss": 0.1906, "lr": 7.72383926664857e-06, "epoch": 1.3451866271305373, "percentage": 74.29, "elapsed_time": "1 day, 0:19:18", "remaining_time": "8:25:05", "throughput": 554.18, "total_tokens": 48523408} {"current_steps": 29720, "total_steps": 40000, "loss": 0.1012, "lr": 7.716744424707606e-06, "epoch": 1.34541297901718, "percentage": 74.3, "elapsed_time": "1 day, 0:19:21", "remaining_time": "8:24:47", "throughput": 554.25, "total_tokens": 48530832} {"current_steps": 29725, "total_steps": 40000, "loss": 0.1291, "lr": 7.709652248061858e-06, "epoch": 1.345639330903823, "percentage": 74.31, "elapsed_time": "1 day, 0:19:24", "remaining_time": "8:24:28", "throughput": 554.33, "total_tokens": 48539248} {"current_steps": 29730, "total_steps": 40000, "loss": 0.0944, "lr": 7.702562737805017e-06, "epoch": 1.345865682790466, "percentage": 74.33, "elapsed_time": "1 day, 0:19:27", "remaining_time": "8:24:09", "throughput": 554.4, "total_tokens": 48547376} {"current_steps": 29735, "total_steps": 40000, "loss": 0.1297, "lr": 7.695475895030365e-06, "epoch": 1.346092034677109, "percentage": 74.34, "elapsed_time": "1 day, 0:19:30", "remaining_time": "8:23:50", "throughput": 554.47, "total_tokens": 48555184} {"current_steps": 29740, "total_steps": 40000, "loss": 0.1372, "lr": 7.6883917208308e-06, "epoch": 1.346318386563752, "percentage": 74.35, "elapsed_time": "1 day, 0:19:34", "remaining_time": "8:23:32", "throughput": 554.54, "total_tokens": 48563472} {"current_steps": 29745, "total_steps": 40000, "loss": 0.1177, "lr": 7.681310216298778e-06, "epoch": 1.346544738450395, "percentage": 74.36, "elapsed_time": "1 day, 0:19:37", "remaining_time": "8:23:13", "throughput": 554.61, "total_tokens": 48571216} {"current_steps": 29750, "total_steps": 40000, "loss": 0.1216, "lr": 7.674231382526367e-06, "epoch": 1.346771090337038, "percentage": 74.38, "elapsed_time": "1 day, 0:19:40", "remaining_time": "8:22:54", "throughput": 554.68, "total_tokens": 48579120} {"current_steps": 29755, "total_steps": 40000, "loss": 0.103, "lr": 7.667155220605198e-06, "epoch": 1.346997442223681, "percentage": 74.39, "elapsed_time": "1 day, 0:19:43", "remaining_time": "8:22:36", "throughput": 554.75, "total_tokens": 48587344} {"current_steps": 29760, "total_steps": 40000, "loss": 0.1088, "lr": 7.660081731626515e-06, "epoch": 1.3472237941103238, "percentage": 74.4, "elapsed_time": "1 day, 0:19:46", "remaining_time": "8:22:17", "throughput": 554.83, "total_tokens": 48596112} {"current_steps": 29765, "total_steps": 40000, "loss": 0.115, "lr": 7.653010916681141e-06, "epoch": 1.3474501459969668, "percentage": 74.41, "elapsed_time": "1 day, 0:19:49", "remaining_time": "8:21:58", "throughput": 554.9, "total_tokens": 48603760} {"current_steps": 29770, "total_steps": 40000, "loss": 0.1207, "lr": 7.645942776859472e-06, "epoch": 1.3476764978836098, "percentage": 74.42, "elapsed_time": "1 day, 0:19:52", "remaining_time": "8:21:39", "throughput": 554.98, "total_tokens": 48611920} {"current_steps": 29775, "total_steps": 40000, "loss": 0.1291, "lr": 7.63887731325152e-06, "epoch": 1.3479028497702528, "percentage": 74.44, "elapsed_time": "1 day, 0:19:56", "remaining_time": "8:21:21", "throughput": 555.05, "total_tokens": 48620176} {"current_steps": 29780, "total_steps": 40000, "loss": 0.0895, "lr": 7.63181452694685e-06, "epoch": 1.3481292016568958, "percentage": 74.45, "elapsed_time": "1 day, 0:19:59", "remaining_time": "8:21:02", "throughput": 555.12, "total_tokens": 48628016} {"current_steps": 29785, "total_steps": 40000, "loss": 0.1109, "lr": 7.624754419034644e-06, "epoch": 1.3483555535435388, "percentage": 74.46, "elapsed_time": "1 day, 0:20:02", "remaining_time": "8:20:43", "throughput": 555.19, "total_tokens": 48636016} {"current_steps": 29790, "total_steps": 40000, "loss": 0.0808, "lr": 7.6176969906036645e-06, "epoch": 1.3485819054301817, "percentage": 74.48, "elapsed_time": "1 day, 0:20:05", "remaining_time": "8:20:25", "throughput": 555.27, "total_tokens": 48644496} {"current_steps": 29795, "total_steps": 40000, "loss": 0.1342, "lr": 7.610642242742242e-06, "epoch": 1.3488082573168247, "percentage": 74.49, "elapsed_time": "1 day, 0:20:08", "remaining_time": "8:20:06", "throughput": 555.35, "total_tokens": 48653264} {"current_steps": 29800, "total_steps": 40000, "loss": 0.1133, "lr": 7.603590176538322e-06, "epoch": 1.3490346092034677, "percentage": 74.5, "elapsed_time": "1 day, 0:20:12", "remaining_time": "8:19:48", "throughput": 555.42, "total_tokens": 48661616} {"current_steps": 29800, "total_steps": 40000, "eval_loss": 0.12269871681928635, "epoch": 1.3490346092034677, "percentage": 74.5, "elapsed_time": "1 day, 0:27:54", "remaining_time": "8:22:26", "throughput": 552.5, "total_tokens": 48661616} {"current_steps": 29805, "total_steps": 40000, "loss": 0.1197, "lr": 7.596540793079404e-06, "epoch": 1.3492609610901107, "percentage": 74.51, "elapsed_time": "1 day, 0:27:59", "remaining_time": "8:22:08", "throughput": 552.57, "total_tokens": 48669904} {"current_steps": 29810, "total_steps": 40000, "loss": 0.1484, "lr": 7.5894940934526125e-06, "epoch": 1.3494873129767537, "percentage": 74.52, "elapsed_time": "1 day, 0:28:02", "remaining_time": "8:21:49", "throughput": 552.64, "total_tokens": 48677616} {"current_steps": 29815, "total_steps": 40000, "loss": 0.1151, "lr": 7.582450078744621e-06, "epoch": 1.3497136648633967, "percentage": 74.54, "elapsed_time": "1 day, 0:28:05", "remaining_time": "8:21:30", "throughput": 552.71, "total_tokens": 48686064} {"current_steps": 29820, "total_steps": 40000, "loss": 0.141, "lr": 7.575408750041707e-06, "epoch": 1.3499400167500397, "percentage": 74.55, "elapsed_time": "1 day, 0:28:08", "remaining_time": "8:21:11", "throughput": 552.79, "total_tokens": 48694800} {"current_steps": 29825, "total_steps": 40000, "loss": 0.0769, "lr": 7.568370108429732e-06, "epoch": 1.3501663686366827, "percentage": 74.56, "elapsed_time": "1 day, 0:28:11", "remaining_time": "8:20:53", "throughput": 552.86, "total_tokens": 48702704} {"current_steps": 29830, "total_steps": 40000, "loss": 0.1873, "lr": 7.561334154994154e-06, "epoch": 1.3503927205233255, "percentage": 74.58, "elapsed_time": "1 day, 0:28:15", "remaining_time": "8:20:34", "throughput": 552.94, "total_tokens": 48711440} {"current_steps": 29835, "total_steps": 40000, "loss": 0.0942, "lr": 7.55430089081999e-06, "epoch": 1.3506190724099685, "percentage": 74.59, "elapsed_time": "1 day, 0:28:18", "remaining_time": "8:20:15", "throughput": 553.01, "total_tokens": 48719632} {"current_steps": 29840, "total_steps": 40000, "loss": 0.135, "lr": 7.547270316991864e-06, "epoch": 1.3508454242966115, "percentage": 74.6, "elapsed_time": "1 day, 0:28:21", "remaining_time": "8:19:57", "throughput": 553.09, "total_tokens": 48727792} {"current_steps": 29845, "total_steps": 40000, "loss": 0.1032, "lr": 7.5402424345939884e-06, "epoch": 1.3510717761832545, "percentage": 74.61, "elapsed_time": "1 day, 0:28:24", "remaining_time": "8:19:38", "throughput": 553.16, "total_tokens": 48735856} {"current_steps": 29850, "total_steps": 40000, "loss": 0.1308, "lr": 7.533217244710133e-06, "epoch": 1.3512981280698975, "percentage": 74.62, "elapsed_time": "1 day, 0:28:27", "remaining_time": "8:19:19", "throughput": 553.23, "total_tokens": 48743952} {"current_steps": 29855, "total_steps": 40000, "loss": 0.1828, "lr": 7.52619474842369e-06, "epoch": 1.3515244799565405, "percentage": 74.64, "elapsed_time": "1 day, 0:28:31", "remaining_time": "8:19:00", "throughput": 553.31, "total_tokens": 48753008} {"current_steps": 29860, "total_steps": 40000, "loss": 0.1039, "lr": 7.519174946817597e-06, "epoch": 1.3517508318431835, "percentage": 74.65, "elapsed_time": "1 day, 0:28:34", "remaining_time": "8:18:42", "throughput": 553.39, "total_tokens": 48761680} {"current_steps": 29865, "total_steps": 40000, "loss": 0.0882, "lr": 7.512157840974407e-06, "epoch": 1.3519771837298264, "percentage": 74.66, "elapsed_time": "1 day, 0:28:37", "remaining_time": "8:18:23", "throughput": 553.46, "total_tokens": 48769936} {"current_steps": 29870, "total_steps": 40000, "loss": 0.1295, "lr": 7.5051434319762496e-06, "epoch": 1.3522035356164694, "percentage": 74.67, "elapsed_time": "1 day, 0:28:40", "remaining_time": "8:18:04", "throughput": 553.54, "total_tokens": 48778096} {"current_steps": 29875, "total_steps": 40000, "loss": 0.124, "lr": 7.498131720904822e-06, "epoch": 1.3524298875031122, "percentage": 74.69, "elapsed_time": "1 day, 0:28:44", "remaining_time": "8:17:46", "throughput": 553.61, "total_tokens": 48786608} {"current_steps": 29880, "total_steps": 40000, "loss": 0.1148, "lr": 7.491122708841433e-06, "epoch": 1.3526562393897552, "percentage": 74.7, "elapsed_time": "1 day, 0:28:47", "remaining_time": "8:17:27", "throughput": 553.69, "total_tokens": 48795152} {"current_steps": 29885, "total_steps": 40000, "loss": 0.1125, "lr": 7.4841163968669524e-06, "epoch": 1.3528825912763982, "percentage": 74.71, "elapsed_time": "1 day, 0:28:50", "remaining_time": "8:17:09", "throughput": 553.77, "total_tokens": 48803792} {"current_steps": 29890, "total_steps": 40000, "loss": 0.0836, "lr": 7.4771127860618355e-06, "epoch": 1.3531089431630412, "percentage": 74.72, "elapsed_time": "1 day, 0:28:53", "remaining_time": "8:16:50", "throughput": 553.84, "total_tokens": 48811696} {"current_steps": 29895, "total_steps": 40000, "loss": 0.0974, "lr": 7.470111877506139e-06, "epoch": 1.3533352950496842, "percentage": 74.74, "elapsed_time": "1 day, 0:28:56", "remaining_time": "8:16:31", "throughput": 553.91, "total_tokens": 48819568} {"current_steps": 29900, "total_steps": 40000, "loss": 0.1006, "lr": 7.463113672279479e-06, "epoch": 1.3535616469363272, "percentage": 74.75, "elapsed_time": "1 day, 0:29:00", "remaining_time": "8:16:13", "throughput": 553.98, "total_tokens": 48828016} {"current_steps": 29905, "total_steps": 40000, "loss": 0.1303, "lr": 7.456118171461071e-06, "epoch": 1.3537879988229702, "percentage": 74.76, "elapsed_time": "1 day, 0:29:03", "remaining_time": "8:15:54", "throughput": 554.05, "total_tokens": 48835792} {"current_steps": 29910, "total_steps": 40000, "loss": 0.1344, "lr": 7.449125376129721e-06, "epoch": 1.3540143507096132, "percentage": 74.78, "elapsed_time": "1 day, 0:29:06", "remaining_time": "8:15:35", "throughput": 554.12, "total_tokens": 48843280} {"current_steps": 29915, "total_steps": 40000, "loss": 0.0995, "lr": 7.442135287363788e-06, "epoch": 1.3542407025962562, "percentage": 74.79, "elapsed_time": "1 day, 0:29:09", "remaining_time": "8:15:17", "throughput": 554.2, "total_tokens": 48852112} {"current_steps": 29920, "total_steps": 40000, "loss": 0.1018, "lr": 7.435147906241247e-06, "epoch": 1.3544670544828992, "percentage": 74.8, "elapsed_time": "1 day, 0:29:13", "remaining_time": "8:14:58", "throughput": 554.27, "total_tokens": 48860208} {"current_steps": 29925, "total_steps": 40000, "loss": 0.1321, "lr": 7.428163233839624e-06, "epoch": 1.3546934063695422, "percentage": 74.81, "elapsed_time": "1 day, 0:29:16", "remaining_time": "8:14:40", "throughput": 554.35, "total_tokens": 48869232} {"current_steps": 29930, "total_steps": 40000, "loss": 0.1251, "lr": 7.4211812712360525e-06, "epoch": 1.3549197582561852, "percentage": 74.83, "elapsed_time": "1 day, 0:29:19", "remaining_time": "8:14:21", "throughput": 554.42, "total_tokens": 48877200} {"current_steps": 29935, "total_steps": 40000, "loss": 0.0815, "lr": 7.4142020195072464e-06, "epoch": 1.3551461101428282, "percentage": 74.84, "elapsed_time": "1 day, 0:29:22", "remaining_time": "8:14:02", "throughput": 554.49, "total_tokens": 48885328} {"current_steps": 29940, "total_steps": 40000, "loss": 0.096, "lr": 7.407225479729479e-06, "epoch": 1.3553724620294711, "percentage": 74.85, "elapsed_time": "1 day, 0:29:26", "remaining_time": "8:13:44", "throughput": 554.57, "total_tokens": 48894640} {"current_steps": 29945, "total_steps": 40000, "loss": 0.0807, "lr": 7.400251652978632e-06, "epoch": 1.355598813916114, "percentage": 74.86, "elapsed_time": "1 day, 0:29:29", "remaining_time": "8:13:25", "throughput": 554.64, "total_tokens": 48902256} {"current_steps": 29950, "total_steps": 40000, "loss": 0.1665, "lr": 7.393280540330147e-06, "epoch": 1.355825165802757, "percentage": 74.88, "elapsed_time": "1 day, 0:29:32", "remaining_time": "8:13:07", "throughput": 554.72, "total_tokens": 48910800} {"current_steps": 29955, "total_steps": 40000, "loss": 0.114, "lr": 7.386312142859069e-06, "epoch": 1.3560515176894, "percentage": 74.89, "elapsed_time": "1 day, 0:29:35", "remaining_time": "8:12:48", "throughput": 554.79, "total_tokens": 48918704} {"current_steps": 29960, "total_steps": 40000, "loss": 0.131, "lr": 7.379346461640008e-06, "epoch": 1.356277869576043, "percentage": 74.9, "elapsed_time": "1 day, 0:29:38", "remaining_time": "8:12:29", "throughput": 554.85, "total_tokens": 48926352} {"current_steps": 29965, "total_steps": 40000, "loss": 0.1197, "lr": 7.372383497747149e-06, "epoch": 1.356504221462686, "percentage": 74.91, "elapsed_time": "1 day, 0:29:41", "remaining_time": "8:12:11", "throughput": 554.92, "total_tokens": 48933904} {"current_steps": 29970, "total_steps": 40000, "loss": 0.0756, "lr": 7.3654232522542775e-06, "epoch": 1.356730573349329, "percentage": 74.92, "elapsed_time": "1 day, 0:29:45", "remaining_time": "8:11:52", "throughput": 555.0, "total_tokens": 48942640} {"current_steps": 29975, "total_steps": 40000, "loss": 0.1117, "lr": 7.358465726234756e-06, "epoch": 1.356956925235972, "percentage": 74.94, "elapsed_time": "1 day, 0:29:48", "remaining_time": "8:11:34", "throughput": 555.07, "total_tokens": 48950672} {"current_steps": 29980, "total_steps": 40000, "loss": 0.1143, "lr": 7.351510920761512e-06, "epoch": 1.3571832771226149, "percentage": 74.95, "elapsed_time": "1 day, 0:29:51", "remaining_time": "8:11:15", "throughput": 555.14, "total_tokens": 48958896} {"current_steps": 29985, "total_steps": 40000, "loss": 0.1175, "lr": 7.344558836907067e-06, "epoch": 1.3574096290092577, "percentage": 74.96, "elapsed_time": "1 day, 0:29:54", "remaining_time": "8:10:57", "throughput": 555.21, "total_tokens": 48966896} {"current_steps": 29990, "total_steps": 40000, "loss": 0.1079, "lr": 7.3376094757435285e-06, "epoch": 1.3576359808959007, "percentage": 74.98, "elapsed_time": "1 day, 0:29:57", "remaining_time": "8:10:38", "throughput": 555.29, "total_tokens": 48974896} {"current_steps": 29995, "total_steps": 40000, "loss": 0.1287, "lr": 7.330662838342561e-06, "epoch": 1.3578623327825436, "percentage": 74.99, "elapsed_time": "1 day, 0:30:00", "remaining_time": "8:10:19", "throughput": 555.36, "total_tokens": 48982896} {"current_steps": 30000, "total_steps": 40000, "loss": 0.1822, "lr": 7.323718925775438e-06, "epoch": 1.3580886846691866, "percentage": 75.0, "elapsed_time": "1 day, 0:30:04", "remaining_time": "8:10:01", "throughput": 555.43, "total_tokens": 48990960} {"current_steps": 30000, "total_steps": 40000, "eval_loss": 0.12245585769414902, "epoch": 1.3580886846691866, "percentage": 75.0, "elapsed_time": "1 day, 0:37:46", "remaining_time": "8:12:35", "throughput": 552.53, "total_tokens": 48990960} {"current_steps": 30005, "total_steps": 40000, "loss": 0.1312, "lr": 7.316777739112985e-06, "epoch": 1.3583150365558296, "percentage": 75.01, "elapsed_time": "1 day, 0:37:50", "remaining_time": "8:12:17", "throughput": 552.59, "total_tokens": 48998800} {"current_steps": 30010, "total_steps": 40000, "loss": 0.1173, "lr": 7.309839279425626e-06, "epoch": 1.3585413884424726, "percentage": 75.02, "elapsed_time": "1 day, 0:37:53", "remaining_time": "8:11:58", "throughput": 552.67, "total_tokens": 49006992} {"current_steps": 30015, "total_steps": 40000, "loss": 0.1009, "lr": 7.302903547783366e-06, "epoch": 1.3587677403291156, "percentage": 75.04, "elapsed_time": "1 day, 0:37:56", "remaining_time": "8:11:39", "throughput": 552.74, "total_tokens": 49015216} {"current_steps": 30020, "total_steps": 40000, "loss": 0.1067, "lr": 7.2959705452557644e-06, "epoch": 1.3589940922157586, "percentage": 75.05, "elapsed_time": "1 day, 0:38:00", "remaining_time": "8:11:21", "throughput": 552.81, "total_tokens": 49023568} {"current_steps": 30025, "total_steps": 40000, "loss": 0.1001, "lr": 7.289040272911996e-06, "epoch": 1.3592204441024016, "percentage": 75.06, "elapsed_time": "1 day, 0:38:03", "remaining_time": "8:11:02", "throughput": 552.88, "total_tokens": 49031280} {"current_steps": 30030, "total_steps": 40000, "loss": 0.1077, "lr": 7.282112731820789e-06, "epoch": 1.3594467959890446, "percentage": 75.08, "elapsed_time": "1 day, 0:38:06", "remaining_time": "8:10:44", "throughput": 552.95, "total_tokens": 49039184} {"current_steps": 30035, "total_steps": 40000, "loss": 0.0802, "lr": 7.275187923050447e-06, "epoch": 1.3596731478756876, "percentage": 75.09, "elapsed_time": "1 day, 0:38:09", "remaining_time": "8:10:25", "throughput": 553.02, "total_tokens": 49047344} {"current_steps": 30040, "total_steps": 40000, "loss": 0.1528, "lr": 7.268265847668879e-06, "epoch": 1.3598994997623306, "percentage": 75.1, "elapsed_time": "1 day, 0:38:12", "remaining_time": "8:10:06", "throughput": 553.09, "total_tokens": 49055568} {"current_steps": 30045, "total_steps": 40000, "loss": 0.1463, "lr": 7.261346506743538e-06, "epoch": 1.3601258516489736, "percentage": 75.11, "elapsed_time": "1 day, 0:38:16", "remaining_time": "8:09:48", "throughput": 553.17, "total_tokens": 49063856} {"current_steps": 30050, "total_steps": 40000, "loss": 0.1305, "lr": 7.254429901341486e-06, "epoch": 1.3603522035356166, "percentage": 75.12, "elapsed_time": "1 day, 0:38:19", "remaining_time": "8:09:29", "throughput": 553.23, "total_tokens": 49071472} {"current_steps": 30055, "total_steps": 40000, "loss": 0.116, "lr": 7.247516032529356e-06, "epoch": 1.3605785554222594, "percentage": 75.14, "elapsed_time": "1 day, 0:38:22", "remaining_time": "8:09:11", "throughput": 553.31, "total_tokens": 49080176} {"current_steps": 30060, "total_steps": 40000, "loss": 0.0953, "lr": 7.240604901373338e-06, "epoch": 1.3608049073089024, "percentage": 75.15, "elapsed_time": "1 day, 0:38:25", "remaining_time": "8:08:52", "throughput": 553.39, "total_tokens": 49088688} {"current_steps": 30065, "total_steps": 40000, "loss": 0.0929, "lr": 7.233696508939223e-06, "epoch": 1.3610312591955454, "percentage": 75.16, "elapsed_time": "1 day, 0:38:28", "remaining_time": "8:08:33", "throughput": 553.46, "total_tokens": 49096752} {"current_steps": 30070, "total_steps": 40000, "loss": 0.098, "lr": 7.226790856292376e-06, "epoch": 1.3612576110821883, "percentage": 75.17, "elapsed_time": "1 day, 0:38:31", "remaining_time": "8:08:15", "throughput": 553.52, "total_tokens": 49104272} {"current_steps": 30075, "total_steps": 40000, "loss": 0.136, "lr": 7.219887944497727e-06, "epoch": 1.3614839629688313, "percentage": 75.19, "elapsed_time": "1 day, 0:38:35", "remaining_time": "8:07:56", "throughput": 553.59, "total_tokens": 49111952} {"current_steps": 30080, "total_steps": 40000, "loss": 0.1574, "lr": 7.2129877746198e-06, "epoch": 1.3617103148554743, "percentage": 75.2, "elapsed_time": "1 day, 0:38:38", "remaining_time": "8:07:38", "throughput": 553.66, "total_tokens": 49120112} {"current_steps": 30085, "total_steps": 40000, "loss": 0.0941, "lr": 7.20609034772268e-06, "epoch": 1.3619366667421173, "percentage": 75.21, "elapsed_time": "1 day, 0:38:41", "remaining_time": "8:07:19", "throughput": 553.74, "total_tokens": 49128400} {"current_steps": 30090, "total_steps": 40000, "loss": 0.1183, "lr": 7.19919566487004e-06, "epoch": 1.3621630186287603, "percentage": 75.22, "elapsed_time": "1 day, 0:38:44", "remaining_time": "8:07:01", "throughput": 553.81, "total_tokens": 49136976} {"current_steps": 30095, "total_steps": 40000, "loss": 0.0909, "lr": 7.192303727125132e-06, "epoch": 1.3623893705154033, "percentage": 75.24, "elapsed_time": "1 day, 0:38:47", "remaining_time": "8:06:42", "throughput": 553.89, "total_tokens": 49145072} {"current_steps": 30100, "total_steps": 40000, "loss": 0.1233, "lr": 7.185414535550777e-06, "epoch": 1.362615722402046, "percentage": 75.25, "elapsed_time": "1 day, 0:38:51", "remaining_time": "8:06:23", "throughput": 553.96, "total_tokens": 49153840} {"current_steps": 30105, "total_steps": 40000, "loss": 0.1227, "lr": 7.178528091209363e-06, "epoch": 1.362842074288689, "percentage": 75.26, "elapsed_time": "1 day, 0:38:54", "remaining_time": "8:06:05", "throughput": 554.03, "total_tokens": 49161456} {"current_steps": 30110, "total_steps": 40000, "loss": 0.1128, "lr": 7.171644395162888e-06, "epoch": 1.363068426175332, "percentage": 75.28, "elapsed_time": "1 day, 0:38:57", "remaining_time": "8:05:46", "throughput": 554.1, "total_tokens": 49169200} {"current_steps": 30115, "total_steps": 40000, "loss": 0.1329, "lr": 7.164763448472881e-06, "epoch": 1.363294778061975, "percentage": 75.29, "elapsed_time": "1 day, 0:39:00", "remaining_time": "8:05:28", "throughput": 554.17, "total_tokens": 49177168} {"current_steps": 30120, "total_steps": 40000, "loss": 0.0961, "lr": 7.157885252200491e-06, "epoch": 1.363521129948618, "percentage": 75.3, "elapsed_time": "1 day, 0:39:03", "remaining_time": "8:05:09", "throughput": 554.24, "total_tokens": 49185104} {"current_steps": 30125, "total_steps": 40000, "loss": 0.1169, "lr": 7.151009807406403e-06, "epoch": 1.363747481835261, "percentage": 75.31, "elapsed_time": "1 day, 0:39:06", "remaining_time": "8:04:51", "throughput": 554.31, "total_tokens": 49193456} {"current_steps": 30130, "total_steps": 40000, "loss": 0.1003, "lr": 7.144137115150909e-06, "epoch": 1.363973833721904, "percentage": 75.33, "elapsed_time": "1 day, 0:39:09", "remaining_time": "8:04:32", "throughput": 554.38, "total_tokens": 49201136} {"current_steps": 30135, "total_steps": 40000, "loss": 0.1508, "lr": 7.1372671764938725e-06, "epoch": 1.364200185608547, "percentage": 75.34, "elapsed_time": "1 day, 0:39:13", "remaining_time": "8:04:14", "throughput": 554.45, "total_tokens": 49209520} {"current_steps": 30140, "total_steps": 40000, "loss": 0.1202, "lr": 7.130399992494705e-06, "epoch": 1.36442653749519, "percentage": 75.35, "elapsed_time": "1 day, 0:39:16", "remaining_time": "8:03:55", "throughput": 554.52, "total_tokens": 49217232} {"current_steps": 30145, "total_steps": 40000, "loss": 0.0642, "lr": 7.123535564212419e-06, "epoch": 1.364652889381833, "percentage": 75.36, "elapsed_time": "1 day, 0:39:19", "remaining_time": "8:03:37", "throughput": 554.59, "total_tokens": 49225488} {"current_steps": 30150, "total_steps": 40000, "loss": 0.1042, "lr": 7.116673892705611e-06, "epoch": 1.364879241268476, "percentage": 75.38, "elapsed_time": "1 day, 0:39:22", "remaining_time": "8:03:18", "throughput": 554.67, "total_tokens": 49233584} {"current_steps": 30155, "total_steps": 40000, "loss": 0.1125, "lr": 7.109814979032415e-06, "epoch": 1.365105593155119, "percentage": 75.39, "elapsed_time": "1 day, 0:39:25", "remaining_time": "8:03:00", "throughput": 554.74, "total_tokens": 49241808} {"current_steps": 30160, "total_steps": 40000, "loss": 0.126, "lr": 7.102958824250577e-06, "epoch": 1.365331945041762, "percentage": 75.4, "elapsed_time": "1 day, 0:39:28", "remaining_time": "8:02:41", "throughput": 554.81, "total_tokens": 49249648} {"current_steps": 30165, "total_steps": 40000, "loss": 0.1471, "lr": 7.096105429417393e-06, "epoch": 1.365558296928405, "percentage": 75.41, "elapsed_time": "1 day, 0:39:32", "remaining_time": "8:02:23", "throughput": 554.88, "total_tokens": 49257712} {"current_steps": 30170, "total_steps": 40000, "loss": 0.1389, "lr": 7.0892547955897506e-06, "epoch": 1.3657846488150478, "percentage": 75.42, "elapsed_time": "1 day, 0:39:35", "remaining_time": "8:02:04", "throughput": 554.95, "total_tokens": 49266000} {"current_steps": 30175, "total_steps": 40000, "loss": 0.1067, "lr": 7.0824069238241e-06, "epoch": 1.3660110007016908, "percentage": 75.44, "elapsed_time": "1 day, 0:39:38", "remaining_time": "8:01:46", "throughput": 555.02, "total_tokens": 49274192} {"current_steps": 30180, "total_steps": 40000, "loss": 0.1103, "lr": 7.075561815176462e-06, "epoch": 1.3662373525883338, "percentage": 75.45, "elapsed_time": "1 day, 0:39:41", "remaining_time": "8:01:27", "throughput": 555.1, "total_tokens": 49282256} {"current_steps": 30185, "total_steps": 40000, "loss": 0.1524, "lr": 7.068719470702445e-06, "epoch": 1.3664637044749768, "percentage": 75.46, "elapsed_time": "1 day, 0:39:44", "remaining_time": "8:01:09", "throughput": 555.16, "total_tokens": 49290160} {"current_steps": 30190, "total_steps": 40000, "loss": 0.0933, "lr": 7.061879891457229e-06, "epoch": 1.3666900563616198, "percentage": 75.48, "elapsed_time": "1 day, 0:39:48", "remaining_time": "8:00:51", "throughput": 555.25, "total_tokens": 49299824} {"current_steps": 30195, "total_steps": 40000, "loss": 0.1113, "lr": 7.0550430784955515e-06, "epoch": 1.3669164082482628, "percentage": 75.49, "elapsed_time": "1 day, 0:39:51", "remaining_time": "8:00:32", "throughput": 555.32, "total_tokens": 49308112} {"current_steps": 30200, "total_steps": 40000, "loss": 0.1113, "lr": 7.048209032871752e-06, "epoch": 1.3671427601349058, "percentage": 75.5, "elapsed_time": "1 day, 0:39:54", "remaining_time": "8:00:14", "throughput": 555.4, "total_tokens": 49316656} {"current_steps": 30200, "total_steps": 40000, "eval_loss": 0.12222326546907425, "epoch": 1.3671427601349058, "percentage": 75.5, "elapsed_time": "1 day, 0:47:37", "remaining_time": "8:02:44", "throughput": 552.52, "total_tokens": 49316656} {"current_steps": 30205, "total_steps": 40000, "loss": 0.0976, "lr": 7.0413777556397055e-06, "epoch": 1.3673691120215488, "percentage": 75.51, "elapsed_time": "1 day, 0:47:41", "remaining_time": "8:02:26", "throughput": 552.59, "total_tokens": 49325392} {"current_steps": 30210, "total_steps": 40000, "loss": 0.0954, "lr": 7.0345492478528925e-06, "epoch": 1.3675954639081918, "percentage": 75.52, "elapsed_time": "1 day, 0:47:44", "remaining_time": "8:02:07", "throughput": 552.66, "total_tokens": 49332976} {"current_steps": 30215, "total_steps": 40000, "loss": 0.1562, "lr": 7.02772351056436e-06, "epoch": 1.3678218157948345, "percentage": 75.54, "elapsed_time": "1 day, 0:47:47", "remaining_time": "8:01:49", "throughput": 552.73, "total_tokens": 49340752} {"current_steps": 30220, "total_steps": 40000, "loss": 0.1305, "lr": 7.020900544826709e-06, "epoch": 1.3680481676814775, "percentage": 75.55, "elapsed_time": "1 day, 0:47:51", "remaining_time": "8:01:30", "throughput": 552.8, "total_tokens": 49348848} {"current_steps": 30225, "total_steps": 40000, "loss": 0.111, "lr": 7.014080351692134e-06, "epoch": 1.3682745195681205, "percentage": 75.56, "elapsed_time": "1 day, 0:47:54", "remaining_time": "8:01:11", "throughput": 552.87, "total_tokens": 49356624} {"current_steps": 30230, "total_steps": 40000, "loss": 0.1485, "lr": 7.0072629322124024e-06, "epoch": 1.3685008714547635, "percentage": 75.58, "elapsed_time": "1 day, 0:47:57", "remaining_time": "8:00:53", "throughput": 552.94, "total_tokens": 49364752} {"current_steps": 30235, "total_steps": 40000, "loss": 0.09, "lr": 7.000448287438827e-06, "epoch": 1.3687272233414065, "percentage": 75.59, "elapsed_time": "1 day, 0:48:00", "remaining_time": "8:00:34", "throughput": 553.01, "total_tokens": 49373264} {"current_steps": 30240, "total_steps": 40000, "loss": 0.1134, "lr": 6.993636418422331e-06, "epoch": 1.3689535752280495, "percentage": 75.6, "elapsed_time": "1 day, 0:48:03", "remaining_time": "8:00:16", "throughput": 553.08, "total_tokens": 49381456} {"current_steps": 30245, "total_steps": 40000, "loss": 0.1112, "lr": 6.986827326213383e-06, "epoch": 1.3691799271146925, "percentage": 75.61, "elapsed_time": "1 day, 0:48:07", "remaining_time": "7:59:57", "throughput": 553.16, "total_tokens": 49390064} {"current_steps": 30250, "total_steps": 40000, "loss": 0.1606, "lr": 6.9800210118620205e-06, "epoch": 1.3694062790013355, "percentage": 75.62, "elapsed_time": "1 day, 0:48:10", "remaining_time": "7:59:39", "throughput": 553.23, "total_tokens": 49398160} {"current_steps": 30255, "total_steps": 40000, "loss": 0.1366, "lr": 6.973217476417876e-06, "epoch": 1.3696326308879785, "percentage": 75.64, "elapsed_time": "1 day, 0:48:13", "remaining_time": "7:59:20", "throughput": 553.3, "total_tokens": 49405744} {"current_steps": 30260, "total_steps": 40000, "loss": 0.1514, "lr": 6.96641672093013e-06, "epoch": 1.3698589827746215, "percentage": 75.65, "elapsed_time": "1 day, 0:48:16", "remaining_time": "7:59:02", "throughput": 553.37, "total_tokens": 49414256} {"current_steps": 30265, "total_steps": 40000, "loss": 0.1136, "lr": 6.95961874644755e-06, "epoch": 1.3700853346612645, "percentage": 75.66, "elapsed_time": "1 day, 0:48:19", "remaining_time": "7:58:44", "throughput": 553.45, "total_tokens": 49422608} {"current_steps": 30270, "total_steps": 40000, "loss": 0.1112, "lr": 6.952823554018476e-06, "epoch": 1.3703116865479075, "percentage": 75.67, "elapsed_time": "1 day, 0:48:23", "remaining_time": "7:58:25", "throughput": 553.53, "total_tokens": 49431632} {"current_steps": 30275, "total_steps": 40000, "loss": 0.1016, "lr": 6.946031144690798e-06, "epoch": 1.3705380384345505, "percentage": 75.69, "elapsed_time": "1 day, 0:48:26", "remaining_time": "7:58:07", "throughput": 553.6, "total_tokens": 49439568} {"current_steps": 30280, "total_steps": 40000, "loss": 0.1208, "lr": 6.939241519512005e-06, "epoch": 1.3707643903211935, "percentage": 75.7, "elapsed_time": "1 day, 0:48:29", "remaining_time": "7:57:48", "throughput": 553.67, "total_tokens": 49447600} {"current_steps": 30285, "total_steps": 40000, "loss": 0.1284, "lr": 6.932454679529129e-06, "epoch": 1.3709907422078362, "percentage": 75.71, "elapsed_time": "1 day, 0:48:32", "remaining_time": "7:57:30", "throughput": 553.73, "total_tokens": 49455280} {"current_steps": 30290, "total_steps": 40000, "loss": 0.1192, "lr": 6.925670625788791e-06, "epoch": 1.3712170940944792, "percentage": 75.72, "elapsed_time": "1 day, 0:48:35", "remaining_time": "7:57:11", "throughput": 553.8, "total_tokens": 49463344} {"current_steps": 30295, "total_steps": 40000, "loss": 0.1104, "lr": 6.918889359337186e-06, "epoch": 1.3714434459811222, "percentage": 75.74, "elapsed_time": "1 day, 0:48:38", "remaining_time": "7:56:53", "throughput": 553.87, "total_tokens": 49471184} {"current_steps": 30300, "total_steps": 40000, "loss": 0.1083, "lr": 6.912110881220058e-06, "epoch": 1.3716697978677652, "percentage": 75.75, "elapsed_time": "1 day, 0:48:41", "remaining_time": "7:56:34", "throughput": 553.94, "total_tokens": 49479376} {"current_steps": 30305, "total_steps": 40000, "loss": 0.1282, "lr": 6.905335192482735e-06, "epoch": 1.3718961497544082, "percentage": 75.76, "elapsed_time": "1 day, 0:48:45", "remaining_time": "7:56:16", "throughput": 554.02, "total_tokens": 49487728} {"current_steps": 30310, "total_steps": 40000, "loss": 0.1019, "lr": 6.8985622941701275e-06, "epoch": 1.3721225016410512, "percentage": 75.78, "elapsed_time": "1 day, 0:48:48", "remaining_time": "7:55:57", "throughput": 554.08, "total_tokens": 49495376} {"current_steps": 30315, "total_steps": 40000, "loss": 0.1627, "lr": 6.89179218732669e-06, "epoch": 1.3723488535276942, "percentage": 75.79, "elapsed_time": "1 day, 0:48:51", "remaining_time": "7:55:39", "throughput": 554.16, "total_tokens": 49503472} {"current_steps": 30320, "total_steps": 40000, "loss": 0.1546, "lr": 6.8850248729964595e-06, "epoch": 1.3725752054143372, "percentage": 75.8, "elapsed_time": "1 day, 0:48:54", "remaining_time": "7:55:21", "throughput": 554.23, "total_tokens": 49511728} {"current_steps": 30325, "total_steps": 40000, "loss": 0.1774, "lr": 6.8782603522230314e-06, "epoch": 1.37280155730098, "percentage": 75.81, "elapsed_time": "1 day, 0:48:57", "remaining_time": "7:55:02", "throughput": 554.3, "total_tokens": 49520112} {"current_steps": 30330, "total_steps": 40000, "loss": 0.1241, "lr": 6.871498626049591e-06, "epoch": 1.373027909187623, "percentage": 75.83, "elapsed_time": "1 day, 0:49:00", "remaining_time": "7:54:44", "throughput": 554.37, "total_tokens": 49527920} {"current_steps": 30335, "total_steps": 40000, "loss": 0.0918, "lr": 6.8647396955188875e-06, "epoch": 1.373254261074266, "percentage": 75.84, "elapsed_time": "1 day, 0:49:04", "remaining_time": "7:54:25", "throughput": 554.44, "total_tokens": 49536112} {"current_steps": 30340, "total_steps": 40000, "loss": 0.1422, "lr": 6.857983561673218e-06, "epoch": 1.373480612960909, "percentage": 75.85, "elapsed_time": "1 day, 0:49:07", "remaining_time": "7:54:07", "throughput": 554.51, "total_tokens": 49543728} {"current_steps": 30345, "total_steps": 40000, "loss": 0.1144, "lr": 6.851230225554467e-06, "epoch": 1.373706964847552, "percentage": 75.86, "elapsed_time": "1 day, 0:49:10", "remaining_time": "7:53:48", "throughput": 554.58, "total_tokens": 49551632} {"current_steps": 30350, "total_steps": 40000, "loss": 0.1339, "lr": 6.8444796882040946e-06, "epoch": 1.373933316734195, "percentage": 75.88, "elapsed_time": "1 day, 0:49:13", "remaining_time": "7:53:30", "throughput": 554.65, "total_tokens": 49560240} {"current_steps": 30355, "total_steps": 40000, "loss": 0.1193, "lr": 6.837731950663106e-06, "epoch": 1.374159668620838, "percentage": 75.89, "elapsed_time": "1 day, 0:49:16", "remaining_time": "7:53:12", "throughput": 554.72, "total_tokens": 49568272} {"current_steps": 30360, "total_steps": 40000, "loss": 0.1474, "lr": 6.830987013972098e-06, "epoch": 1.374386020507481, "percentage": 75.9, "elapsed_time": "1 day, 0:49:19", "remaining_time": "7:52:53", "throughput": 554.8, "total_tokens": 49576912} {"current_steps": 30365, "total_steps": 40000, "loss": 0.126, "lr": 6.82424487917121e-06, "epoch": 1.374612372394124, "percentage": 75.91, "elapsed_time": "1 day, 0:49:23", "remaining_time": "7:52:35", "throughput": 554.87, "total_tokens": 49585136} {"current_steps": 30370, "total_steps": 40000, "loss": 0.128, "lr": 6.8175055473001735e-06, "epoch": 1.374838724280767, "percentage": 75.92, "elapsed_time": "1 day, 0:49:26", "remaining_time": "7:52:17", "throughput": 554.95, "total_tokens": 49594192} {"current_steps": 30375, "total_steps": 40000, "loss": 0.1075, "lr": 6.8107690193982855e-06, "epoch": 1.37506507616741, "percentage": 75.94, "elapsed_time": "1 day, 0:49:29", "remaining_time": "7:51:58", "throughput": 555.02, "total_tokens": 49602160} {"current_steps": 30380, "total_steps": 40000, "loss": 0.1493, "lr": 6.804035296504385e-06, "epoch": 1.375291428054053, "percentage": 75.95, "elapsed_time": "1 day, 0:49:32", "remaining_time": "7:51:40", "throughput": 555.09, "total_tokens": 49610352} {"current_steps": 30385, "total_steps": 40000, "loss": 0.176, "lr": 6.797304379656916e-06, "epoch": 1.375517779940696, "percentage": 75.96, "elapsed_time": "1 day, 0:49:36", "remaining_time": "7:51:22", "throughput": 555.17, "total_tokens": 49618928} {"current_steps": 30390, "total_steps": 40000, "loss": 0.119, "lr": 6.790576269893861e-06, "epoch": 1.375744131827339, "percentage": 75.98, "elapsed_time": "1 day, 0:49:39", "remaining_time": "7:51:03", "throughput": 555.24, "total_tokens": 49626928} {"current_steps": 30395, "total_steps": 40000, "loss": 0.1113, "lr": 6.783850968252772e-06, "epoch": 1.3759704837139817, "percentage": 75.99, "elapsed_time": "1 day, 0:49:42", "remaining_time": "7:50:45", "throughput": 555.31, "total_tokens": 49634896} {"current_steps": 30400, "total_steps": 40000, "loss": 0.1181, "lr": 6.777128475770789e-06, "epoch": 1.3761968356006247, "percentage": 76.0, "elapsed_time": "1 day, 0:49:45", "remaining_time": "7:50:27", "throughput": 555.38, "total_tokens": 49642704} {"current_steps": 30400, "total_steps": 40000, "eval_loss": 0.1226152554154396, "epoch": 1.3761968356006247, "percentage": 76.0, "elapsed_time": "1 day, 0:57:28", "remaining_time": "7:52:53", "throughput": 552.52, "total_tokens": 49642704} {"current_steps": 30405, "total_steps": 40000, "loss": 0.1086, "lr": 6.77040879348459e-06, "epoch": 1.3764231874872677, "percentage": 76.01, "elapsed_time": "1 day, 0:57:32", "remaining_time": "7:52:34", "throughput": 552.58, "total_tokens": 49650896} {"current_steps": 30410, "total_steps": 40000, "loss": 0.0998, "lr": 6.763691922430443e-06, "epoch": 1.3766495393739107, "percentage": 76.02, "elapsed_time": "1 day, 0:57:35", "remaining_time": "7:52:16", "throughput": 552.66, "total_tokens": 49659248} {"current_steps": 30415, "total_steps": 40000, "loss": 0.113, "lr": 6.756977863644178e-06, "epoch": 1.3768758912605537, "percentage": 76.04, "elapsed_time": "1 day, 0:57:38", "remaining_time": "7:51:58", "throughput": 552.73, "total_tokens": 49667376} {"current_steps": 30420, "total_steps": 40000, "loss": 0.1182, "lr": 6.7502666181611804e-06, "epoch": 1.3771022431471966, "percentage": 76.05, "elapsed_time": "1 day, 0:57:41", "remaining_time": "7:51:39", "throughput": 552.8, "total_tokens": 49675632} {"current_steps": 30425, "total_steps": 40000, "loss": 0.171, "lr": 6.743558187016405e-06, "epoch": 1.3773285950338396, "percentage": 76.06, "elapsed_time": "1 day, 0:57:45", "remaining_time": "7:51:21", "throughput": 552.87, "total_tokens": 49683760} {"current_steps": 30430, "total_steps": 40000, "loss": 0.1422, "lr": 6.7368525712443925e-06, "epoch": 1.3775549469204826, "percentage": 76.08, "elapsed_time": "1 day, 0:57:48", "remaining_time": "7:51:02", "throughput": 552.95, "total_tokens": 49693072} {"current_steps": 30435, "total_steps": 40000, "loss": 0.1104, "lr": 6.7301497718792155e-06, "epoch": 1.3777812988071256, "percentage": 76.09, "elapsed_time": "1 day, 0:57:51", "remaining_time": "7:50:44", "throughput": 553.03, "total_tokens": 49702032} {"current_steps": 30440, "total_steps": 40000, "loss": 0.0727, "lr": 6.723449789954544e-06, "epoch": 1.3780076506937684, "percentage": 76.1, "elapsed_time": "1 day, 0:57:54", "remaining_time": "7:50:26", "throughput": 553.1, "total_tokens": 49709424} {"current_steps": 30445, "total_steps": 40000, "loss": 0.0827, "lr": 6.716752626503586e-06, "epoch": 1.3782340025804114, "percentage": 76.11, "elapsed_time": "1 day, 0:57:58", "remaining_time": "7:50:07", "throughput": 553.16, "total_tokens": 49717168} {"current_steps": 30450, "total_steps": 40000, "loss": 0.1291, "lr": 6.710058282559131e-06, "epoch": 1.3784603544670544, "percentage": 76.12, "elapsed_time": "1 day, 0:58:01", "remaining_time": "7:49:49", "throughput": 553.23, "total_tokens": 49725040} {"current_steps": 30455, "total_steps": 40000, "loss": 0.1225, "lr": 6.703366759153545e-06, "epoch": 1.3786867063536974, "percentage": 76.14, "elapsed_time": "1 day, 0:58:04", "remaining_time": "7:49:30", "throughput": 553.3, "total_tokens": 49733008} {"current_steps": 30460, "total_steps": 40000, "loss": 0.0966, "lr": 6.6966780573187335e-06, "epoch": 1.3789130582403404, "percentage": 76.15, "elapsed_time": "1 day, 0:58:07", "remaining_time": "7:49:12", "throughput": 553.37, "total_tokens": 49741392} {"current_steps": 30465, "total_steps": 40000, "loss": 0.0866, "lr": 6.689992178086174e-06, "epoch": 1.3791394101269834, "percentage": 76.16, "elapsed_time": "1 day, 0:58:10", "remaining_time": "7:48:54", "throughput": 553.44, "total_tokens": 49749552} {"current_steps": 30470, "total_steps": 40000, "loss": 0.1856, "lr": 6.683309122486925e-06, "epoch": 1.3793657620136264, "percentage": 76.17, "elapsed_time": "1 day, 0:58:14", "remaining_time": "7:48:35", "throughput": 553.52, "total_tokens": 49758288} {"current_steps": 30475, "total_steps": 40000, "loss": 0.1099, "lr": 6.676628891551584e-06, "epoch": 1.3795921139002694, "percentage": 76.19, "elapsed_time": "1 day, 0:58:17", "remaining_time": "7:48:17", "throughput": 553.6, "total_tokens": 49767600} {"current_steps": 30480, "total_steps": 40000, "loss": 0.1479, "lr": 6.6699514863103385e-06, "epoch": 1.3798184657869124, "percentage": 76.2, "elapsed_time": "1 day, 0:58:20", "remaining_time": "7:47:59", "throughput": 553.68, "total_tokens": 49775824} {"current_steps": 30485, "total_steps": 40000, "loss": 0.0781, "lr": 6.663276907792921e-06, "epoch": 1.3800448176735554, "percentage": 76.21, "elapsed_time": "1 day, 0:58:24", "remaining_time": "7:47:40", "throughput": 553.75, "total_tokens": 49784528} {"current_steps": 30490, "total_steps": 40000, "loss": 0.1483, "lr": 6.656605157028634e-06, "epoch": 1.3802711695601984, "percentage": 76.22, "elapsed_time": "1 day, 0:58:27", "remaining_time": "7:47:22", "throughput": 553.82, "total_tokens": 49792336} {"current_steps": 30495, "total_steps": 40000, "loss": 0.1277, "lr": 6.649936235046358e-06, "epoch": 1.3804975214468413, "percentage": 76.24, "elapsed_time": "1 day, 0:58:30", "remaining_time": "7:47:04", "throughput": 553.89, "total_tokens": 49800144} {"current_steps": 30500, "total_steps": 40000, "loss": 0.1093, "lr": 6.643270142874508e-06, "epoch": 1.3807238733334843, "percentage": 76.25, "elapsed_time": "1 day, 0:58:33", "remaining_time": "7:46:45", "throughput": 553.95, "total_tokens": 49807920} {"current_steps": 30505, "total_steps": 40000, "loss": 0.0971, "lr": 6.636606881541094e-06, "epoch": 1.3809502252201273, "percentage": 76.26, "elapsed_time": "1 day, 0:58:36", "remaining_time": "7:46:27", "throughput": 554.02, "total_tokens": 49815632} {"current_steps": 30510, "total_steps": 40000, "loss": 0.1216, "lr": 6.629946452073662e-06, "epoch": 1.38117657710677, "percentage": 76.28, "elapsed_time": "1 day, 0:58:39", "remaining_time": "7:46:09", "throughput": 554.09, "total_tokens": 49824016} {"current_steps": 30515, "total_steps": 40000, "loss": 0.1432, "lr": 6.6232888554993375e-06, "epoch": 1.381402928993413, "percentage": 76.29, "elapsed_time": "1 day, 0:58:42", "remaining_time": "7:45:50", "throughput": 554.17, "total_tokens": 49832208} {"current_steps": 30520, "total_steps": 40000, "loss": 0.0976, "lr": 6.616634092844817e-06, "epoch": 1.381629280880056, "percentage": 76.3, "elapsed_time": "1 day, 0:58:46", "remaining_time": "7:45:32", "throughput": 554.24, "total_tokens": 49840208} {"current_steps": 30525, "total_steps": 40000, "loss": 0.1075, "lr": 6.609982165136331e-06, "epoch": 1.381855632766699, "percentage": 76.31, "elapsed_time": "1 day, 0:58:49", "remaining_time": "7:45:14", "throughput": 554.3, "total_tokens": 49848080} {"current_steps": 30530, "total_steps": 40000, "loss": 0.1001, "lr": 6.603333073399706e-06, "epoch": 1.382081984653342, "percentage": 76.33, "elapsed_time": "1 day, 0:58:52", "remaining_time": "7:44:55", "throughput": 554.37, "total_tokens": 49855760} {"current_steps": 30535, "total_steps": 40000, "loss": 0.1258, "lr": 6.596686818660308e-06, "epoch": 1.382308336539985, "percentage": 76.34, "elapsed_time": "1 day, 0:58:55", "remaining_time": "7:44:37", "throughput": 554.44, "total_tokens": 49863888} {"current_steps": 30540, "total_steps": 40000, "loss": 0.1146, "lr": 6.590043401943066e-06, "epoch": 1.382534688426628, "percentage": 76.35, "elapsed_time": "1 day, 0:58:58", "remaining_time": "7:44:19", "throughput": 554.51, "total_tokens": 49871984} {"current_steps": 30545, "total_steps": 40000, "loss": 0.1292, "lr": 6.583402824272494e-06, "epoch": 1.382761040313271, "percentage": 76.36, "elapsed_time": "1 day, 0:59:01", "remaining_time": "7:44:00", "throughput": 554.59, "total_tokens": 49880656} {"current_steps": 30550, "total_steps": 40000, "loss": 0.0731, "lr": 6.576765086672634e-06, "epoch": 1.382987392199914, "percentage": 76.38, "elapsed_time": "1 day, 0:59:05", "remaining_time": "7:43:42", "throughput": 554.66, "total_tokens": 49889136} {"current_steps": 30555, "total_steps": 40000, "loss": 0.13, "lr": 6.57013019016712e-06, "epoch": 1.3832137440865568, "percentage": 76.39, "elapsed_time": "1 day, 0:59:08", "remaining_time": "7:43:24", "throughput": 554.73, "total_tokens": 49897072} {"current_steps": 30560, "total_steps": 40000, "loss": 0.0969, "lr": 6.563498135779142e-06, "epoch": 1.3834400959731998, "percentage": 76.4, "elapsed_time": "1 day, 0:59:11", "remaining_time": "7:43:06", "throughput": 554.8, "total_tokens": 49905200} {"current_steps": 30565, "total_steps": 40000, "loss": 0.1158, "lr": 6.556868924531431e-06, "epoch": 1.3836664478598428, "percentage": 76.41, "elapsed_time": "1 day, 0:59:14", "remaining_time": "7:42:47", "throughput": 554.88, "total_tokens": 49913776} {"current_steps": 30570, "total_steps": 40000, "loss": 0.0772, "lr": 6.550242557446304e-06, "epoch": 1.3838927997464858, "percentage": 76.42, "elapsed_time": "1 day, 0:59:18", "remaining_time": "7:42:29", "throughput": 554.96, "total_tokens": 49922864} {"current_steps": 30575, "total_steps": 40000, "loss": 0.1701, "lr": 6.543619035545634e-06, "epoch": 1.3841191516331288, "percentage": 76.44, "elapsed_time": "1 day, 0:59:21", "remaining_time": "7:42:11", "throughput": 555.02, "total_tokens": 49930672} {"current_steps": 30580, "total_steps": 40000, "loss": 0.1114, "lr": 6.53699835985084e-06, "epoch": 1.3843455035197718, "percentage": 76.45, "elapsed_time": "1 day, 0:59:24", "remaining_time": "7:41:53", "throughput": 555.09, "total_tokens": 49938512} {"current_steps": 30585, "total_steps": 40000, "loss": 0.2095, "lr": 6.530380531382927e-06, "epoch": 1.3845718554064148, "percentage": 76.46, "elapsed_time": "1 day, 0:59:27", "remaining_time": "7:41:34", "throughput": 555.17, "total_tokens": 49947856} {"current_steps": 30590, "total_steps": 40000, "loss": 0.1128, "lr": 6.523765551162433e-06, "epoch": 1.3847982072930578, "percentage": 76.48, "elapsed_time": "1 day, 0:59:31", "remaining_time": "7:41:16", "throughput": 555.24, "total_tokens": 49955536} {"current_steps": 30595, "total_steps": 40000, "loss": 0.1244, "lr": 6.517153420209476e-06, "epoch": 1.3850245591797008, "percentage": 76.49, "elapsed_time": "1 day, 0:59:34", "remaining_time": "7:40:58", "throughput": 555.31, "total_tokens": 49964080} {"current_steps": 30600, "total_steps": 40000, "loss": 0.1216, "lr": 6.510544139543739e-06, "epoch": 1.3852509110663438, "percentage": 76.5, "elapsed_time": "1 day, 0:59:37", "remaining_time": "7:40:40", "throughput": 555.4, "total_tokens": 49973200} {"current_steps": 30600, "total_steps": 40000, "eval_loss": 0.12269414216279984, "epoch": 1.3852509110663438, "percentage": 76.5, "elapsed_time": "1 day, 1:07:20", "remaining_time": "7:43:02", "throughput": 552.55, "total_tokens": 49973200} {"current_steps": 30605, "total_steps": 40000, "loss": 0.1439, "lr": 6.503937710184452e-06, "epoch": 1.3854772629529868, "percentage": 76.51, "elapsed_time": "1 day, 1:07:24", "remaining_time": "7:42:44", "throughput": 552.62, "total_tokens": 49981296} {"current_steps": 30610, "total_steps": 40000, "loss": 0.1399, "lr": 6.4973341331503954e-06, "epoch": 1.3857036148396298, "percentage": 76.53, "elapsed_time": "1 day, 1:07:27", "remaining_time": "7:42:25", "throughput": 552.69, "total_tokens": 49989488} {"current_steps": 30615, "total_steps": 40000, "loss": 0.1218, "lr": 6.490733409459942e-06, "epoch": 1.3859299667262728, "percentage": 76.54, "elapsed_time": "1 day, 1:07:30", "remaining_time": "7:42:07", "throughput": 552.76, "total_tokens": 49997680} {"current_steps": 30620, "total_steps": 40000, "loss": 0.1218, "lr": 6.484135540130995e-06, "epoch": 1.3861563186129158, "percentage": 76.55, "elapsed_time": "1 day, 1:07:34", "remaining_time": "7:41:49", "throughput": 552.83, "total_tokens": 50005552} {"current_steps": 30625, "total_steps": 40000, "loss": 0.1233, "lr": 6.4775405261810364e-06, "epoch": 1.3863826704995585, "percentage": 76.56, "elapsed_time": "1 day, 1:07:37", "remaining_time": "7:41:30", "throughput": 552.9, "total_tokens": 50013712} {"current_steps": 30630, "total_steps": 40000, "loss": 0.1333, "lr": 6.470948368627092e-06, "epoch": 1.3866090223862015, "percentage": 76.58, "elapsed_time": "1 day, 1:07:40", "remaining_time": "7:41:12", "throughput": 552.97, "total_tokens": 50022320} {"current_steps": 30635, "total_steps": 40000, "loss": 0.1235, "lr": 6.464359068485756e-06, "epoch": 1.3868353742728445, "percentage": 76.59, "elapsed_time": "1 day, 1:07:43", "remaining_time": "7:40:54", "throughput": 553.05, "total_tokens": 50030640} {"current_steps": 30640, "total_steps": 40000, "loss": 0.092, "lr": 6.457772626773195e-06, "epoch": 1.3870617261594875, "percentage": 76.6, "elapsed_time": "1 day, 1:07:46", "remaining_time": "7:40:36", "throughput": 553.12, "total_tokens": 50039216} {"current_steps": 30645, "total_steps": 40000, "loss": 0.132, "lr": 6.451189044505104e-06, "epoch": 1.3872880780461305, "percentage": 76.61, "elapsed_time": "1 day, 1:07:50", "remaining_time": "7:40:17", "throughput": 553.19, "total_tokens": 50047408} {"current_steps": 30650, "total_steps": 40000, "loss": 0.1105, "lr": 6.44460832269676e-06, "epoch": 1.3875144299327735, "percentage": 76.62, "elapsed_time": "1 day, 1:07:53", "remaining_time": "7:39:59", "throughput": 553.27, "total_tokens": 50055984} {"current_steps": 30655, "total_steps": 40000, "loss": 0.1217, "lr": 6.438030462363001e-06, "epoch": 1.3877407818194165, "percentage": 76.64, "elapsed_time": "1 day, 1:07:56", "remaining_time": "7:39:41", "throughput": 553.34, "total_tokens": 50063920} {"current_steps": 30660, "total_steps": 40000, "loss": 0.0799, "lr": 6.431455464518205e-06, "epoch": 1.3879671337060595, "percentage": 76.65, "elapsed_time": "1 day, 1:07:59", "remaining_time": "7:39:22", "throughput": 553.41, "total_tokens": 50072208} {"current_steps": 30665, "total_steps": 40000, "loss": 0.1149, "lr": 6.424883330176326e-06, "epoch": 1.3881934855927023, "percentage": 76.66, "elapsed_time": "1 day, 1:08:02", "remaining_time": "7:39:04", "throughput": 553.48, "total_tokens": 50080304} {"current_steps": 30670, "total_steps": 40000, "loss": 0.0939, "lr": 6.418314060350864e-06, "epoch": 1.3884198374793453, "percentage": 76.68, "elapsed_time": "1 day, 1:08:06", "remaining_time": "7:38:46", "throughput": 553.55, "total_tokens": 50088336} {"current_steps": 30675, "total_steps": 40000, "loss": 0.1047, "lr": 6.4117476560548895e-06, "epoch": 1.3886461893659883, "percentage": 76.69, "elapsed_time": "1 day, 1:08:09", "remaining_time": "7:38:28", "throughput": 553.62, "total_tokens": 50096336} {"current_steps": 30680, "total_steps": 40000, "loss": 0.1407, "lr": 6.405184118301016e-06, "epoch": 1.3888725412526313, "percentage": 76.7, "elapsed_time": "1 day, 1:08:12", "remaining_time": "7:38:09", "throughput": 553.68, "total_tokens": 50104112} {"current_steps": 30685, "total_steps": 40000, "loss": 0.0963, "lr": 6.398623448101434e-06, "epoch": 1.3890988931392743, "percentage": 76.71, "elapsed_time": "1 day, 1:08:15", "remaining_time": "7:37:51", "throughput": 553.75, "total_tokens": 50111664} {"current_steps": 30690, "total_steps": 40000, "loss": 0.1043, "lr": 6.392065646467871e-06, "epoch": 1.3893252450259173, "percentage": 76.72, "elapsed_time": "1 day, 1:08:18", "remaining_time": "7:37:33", "throughput": 553.82, "total_tokens": 50119952} {"current_steps": 30695, "total_steps": 40000, "loss": 0.1332, "lr": 6.385510714411632e-06, "epoch": 1.3895515969125602, "percentage": 76.74, "elapsed_time": "1 day, 1:08:21", "remaining_time": "7:37:15", "throughput": 553.89, "total_tokens": 50127920} {"current_steps": 30700, "total_steps": 40000, "loss": 0.1653, "lr": 6.378958652943559e-06, "epoch": 1.3897779487992032, "percentage": 76.75, "elapsed_time": "1 day, 1:08:25", "remaining_time": "7:36:56", "throughput": 553.96, "total_tokens": 50136208} {"current_steps": 30705, "total_steps": 40000, "loss": 0.0801, "lr": 6.3724094630740776e-06, "epoch": 1.3900043006858462, "percentage": 76.76, "elapsed_time": "1 day, 1:08:28", "remaining_time": "7:36:38", "throughput": 554.03, "total_tokens": 50143824} {"current_steps": 30710, "total_steps": 40000, "loss": 0.1184, "lr": 6.365863145813136e-06, "epoch": 1.3902306525724892, "percentage": 76.78, "elapsed_time": "1 day, 1:08:31", "remaining_time": "7:36:20", "throughput": 554.1, "total_tokens": 50152112} {"current_steps": 30715, "total_steps": 40000, "loss": 0.0963, "lr": 6.359319702170269e-06, "epoch": 1.3904570044591322, "percentage": 76.79, "elapsed_time": "1 day, 1:08:34", "remaining_time": "7:36:02", "throughput": 554.17, "total_tokens": 50160496} {"current_steps": 30720, "total_steps": 40000, "loss": 0.0936, "lr": 6.352779133154566e-06, "epoch": 1.3906833563457752, "percentage": 76.8, "elapsed_time": "1 day, 1:08:37", "remaining_time": "7:35:43", "throughput": 554.24, "total_tokens": 50168752} {"current_steps": 30725, "total_steps": 40000, "loss": 0.1676, "lr": 6.346241439774648e-06, "epoch": 1.3909097082324182, "percentage": 76.81, "elapsed_time": "1 day, 1:08:41", "remaining_time": "7:35:25", "throughput": 554.31, "total_tokens": 50177008} {"current_steps": 30730, "total_steps": 40000, "loss": 0.122, "lr": 6.339706623038716e-06, "epoch": 1.3911360601190612, "percentage": 76.83, "elapsed_time": "1 day, 1:08:44", "remaining_time": "7:35:07", "throughput": 554.38, "total_tokens": 50184304} {"current_steps": 30735, "total_steps": 40000, "loss": 0.0776, "lr": 6.333174683954532e-06, "epoch": 1.391362412005704, "percentage": 76.84, "elapsed_time": "1 day, 1:08:47", "remaining_time": "7:34:49", "throughput": 554.44, "total_tokens": 50191760} {"current_steps": 30740, "total_steps": 40000, "loss": 0.0932, "lr": 6.326645623529387e-06, "epoch": 1.391588763892347, "percentage": 76.85, "elapsed_time": "1 day, 1:08:50", "remaining_time": "7:34:30", "throughput": 554.5, "total_tokens": 50199376} {"current_steps": 30745, "total_steps": 40000, "loss": 0.1786, "lr": 6.320119442770156e-06, "epoch": 1.39181511577899, "percentage": 76.86, "elapsed_time": "1 day, 1:08:53", "remaining_time": "7:34:12", "throughput": 554.57, "total_tokens": 50207312} {"current_steps": 30750, "total_steps": 40000, "loss": 0.1154, "lr": 6.313596142683254e-06, "epoch": 1.392041467665633, "percentage": 76.88, "elapsed_time": "1 day, 1:08:56", "remaining_time": "7:33:54", "throughput": 554.65, "total_tokens": 50215856} {"current_steps": 30755, "total_steps": 40000, "loss": 0.1341, "lr": 6.307075724274647e-06, "epoch": 1.392267819552276, "percentage": 76.89, "elapsed_time": "1 day, 1:08:59", "remaining_time": "7:33:36", "throughput": 554.72, "total_tokens": 50223984} {"current_steps": 30760, "total_steps": 40000, "loss": 0.1419, "lr": 6.300558188549882e-06, "epoch": 1.392494171438919, "percentage": 76.9, "elapsed_time": "1 day, 1:09:02", "remaining_time": "7:33:18", "throughput": 554.79, "total_tokens": 50231952} {"current_steps": 30765, "total_steps": 40000, "loss": 0.1399, "lr": 6.29404353651403e-06, "epoch": 1.392720523325562, "percentage": 76.91, "elapsed_time": "1 day, 1:09:06", "remaining_time": "7:32:59", "throughput": 554.85, "total_tokens": 50239760} {"current_steps": 30770, "total_steps": 40000, "loss": 0.1015, "lr": 6.287531769171737e-06, "epoch": 1.392946875212205, "percentage": 76.92, "elapsed_time": "1 day, 1:09:09", "remaining_time": "7:32:41", "throughput": 554.92, "total_tokens": 50247440} {"current_steps": 30775, "total_steps": 40000, "loss": 0.1845, "lr": 6.2810228875272045e-06, "epoch": 1.393173227098848, "percentage": 76.94, "elapsed_time": "1 day, 1:09:12", "remaining_time": "7:32:23", "throughput": 554.99, "total_tokens": 50255888} {"current_steps": 30780, "total_steps": 40000, "loss": 0.0667, "lr": 6.274516892584179e-06, "epoch": 1.3933995789854907, "percentage": 76.95, "elapsed_time": "1 day, 1:09:15", "remaining_time": "7:32:05", "throughput": 555.07, "total_tokens": 50264752} {"current_steps": 30785, "total_steps": 40000, "loss": 0.115, "lr": 6.268013785345969e-06, "epoch": 1.3936259308721337, "percentage": 76.96, "elapsed_time": "1 day, 1:09:18", "remaining_time": "7:31:47", "throughput": 555.14, "total_tokens": 50272432} {"current_steps": 30790, "total_steps": 40000, "loss": 0.1229, "lr": 6.26151356681543e-06, "epoch": 1.3938522827587767, "percentage": 76.98, "elapsed_time": "1 day, 1:09:21", "remaining_time": "7:31:29", "throughput": 555.2, "total_tokens": 50280048} {"current_steps": 30795, "total_steps": 40000, "loss": 0.1132, "lr": 6.255016237994981e-06, "epoch": 1.3940786346454197, "percentage": 76.99, "elapsed_time": "1 day, 1:09:25", "remaining_time": "7:31:11", "throughput": 555.27, "total_tokens": 50288240} {"current_steps": 30800, "total_steps": 40000, "loss": 0.1208, "lr": 6.248521799886603e-06, "epoch": 1.3943049865320627, "percentage": 77.0, "elapsed_time": "1 day, 1:09:28", "remaining_time": "7:30:52", "throughput": 555.34, "total_tokens": 50295952} {"current_steps": 30800, "total_steps": 40000, "eval_loss": 0.12249212712049484, "epoch": 1.3943049865320627, "percentage": 77.0, "elapsed_time": "1 day, 1:17:10", "remaining_time": "7:33:11", "throughput": 552.52, "total_tokens": 50295952} {"current_steps": 30805, "total_steps": 40000, "loss": 0.1295, "lr": 6.242030253491798e-06, "epoch": 1.3945313384187057, "percentage": 77.01, "elapsed_time": "1 day, 1:17:14", "remaining_time": "7:32:53", "throughput": 552.58, "total_tokens": 50304112} {"current_steps": 30810, "total_steps": 40000, "loss": 0.0748, "lr": 6.235541599811656e-06, "epoch": 1.3947576903053487, "percentage": 77.03, "elapsed_time": "1 day, 1:17:18", "remaining_time": "7:32:34", "throughput": 552.66, "total_tokens": 50313040} {"current_steps": 30815, "total_steps": 40000, "loss": 0.1005, "lr": 6.229055839846814e-06, "epoch": 1.3949840421919917, "percentage": 77.04, "elapsed_time": "1 day, 1:17:21", "remaining_time": "7:32:16", "throughput": 552.73, "total_tokens": 50321584} {"current_steps": 30820, "total_steps": 40000, "loss": 0.0687, "lr": 6.222572974597455e-06, "epoch": 1.3952103940786347, "percentage": 77.05, "elapsed_time": "1 day, 1:17:24", "remaining_time": "7:31:58", "throughput": 552.8, "total_tokens": 50329680} {"current_steps": 30825, "total_steps": 40000, "loss": 0.1208, "lr": 6.216093005063306e-06, "epoch": 1.3954367459652777, "percentage": 77.06, "elapsed_time": "1 day, 1:17:27", "remaining_time": "7:31:40", "throughput": 552.87, "total_tokens": 50337968} {"current_steps": 30830, "total_steps": 40000, "loss": 0.0991, "lr": 6.209615932243678e-06, "epoch": 1.3956630978519207, "percentage": 77.08, "elapsed_time": "1 day, 1:17:30", "remaining_time": "7:31:21", "throughput": 552.95, "total_tokens": 50346256} {"current_steps": 30835, "total_steps": 40000, "loss": 0.1129, "lr": 6.203141757137399e-06, "epoch": 1.3958894497385637, "percentage": 77.09, "elapsed_time": "1 day, 1:17:34", "remaining_time": "7:31:03", "throughput": 553.01, "total_tokens": 50354192} {"current_steps": 30840, "total_steps": 40000, "loss": 0.1127, "lr": 6.196670480742886e-06, "epoch": 1.3961158016252067, "percentage": 77.1, "elapsed_time": "1 day, 1:17:37", "remaining_time": "7:30:45", "throughput": 553.08, "total_tokens": 50361840} {"current_steps": 30845, "total_steps": 40000, "loss": 0.0818, "lr": 6.190202104058074e-06, "epoch": 1.3963421535118496, "percentage": 77.11, "elapsed_time": "1 day, 1:17:40", "remaining_time": "7:30:27", "throughput": 553.15, "total_tokens": 50369968} {"current_steps": 30850, "total_steps": 40000, "loss": 0.1195, "lr": 6.183736628080475e-06, "epoch": 1.3965685053984924, "percentage": 77.12, "elapsed_time": "1 day, 1:17:43", "remaining_time": "7:30:09", "throughput": 553.22, "total_tokens": 50378288} {"current_steps": 30855, "total_steps": 40000, "loss": 0.1192, "lr": 6.177274053807155e-06, "epoch": 1.3967948572851354, "percentage": 77.14, "elapsed_time": "1 day, 1:17:46", "remaining_time": "7:29:50", "throughput": 553.29, "total_tokens": 50386096} {"current_steps": 30860, "total_steps": 40000, "loss": 0.1413, "lr": 6.170814382234713e-06, "epoch": 1.3970212091717784, "percentage": 77.15, "elapsed_time": "1 day, 1:17:49", "remaining_time": "7:29:32", "throughput": 553.36, "total_tokens": 50394128} {"current_steps": 30865, "total_steps": 40000, "loss": 0.1042, "lr": 6.16435761435932e-06, "epoch": 1.3972475610584214, "percentage": 77.16, "elapsed_time": "1 day, 1:17:53", "remaining_time": "7:29:14", "throughput": 553.43, "total_tokens": 50402640} {"current_steps": 30870, "total_steps": 40000, "loss": 0.0961, "lr": 6.157903751176681e-06, "epoch": 1.3974739129450644, "percentage": 77.18, "elapsed_time": "1 day, 1:17:56", "remaining_time": "7:28:56", "throughput": 553.5, "total_tokens": 50411088} {"current_steps": 30875, "total_steps": 40000, "loss": 0.0606, "lr": 6.151452793682066e-06, "epoch": 1.3977002648317074, "percentage": 77.19, "elapsed_time": "1 day, 1:17:59", "remaining_time": "7:28:38", "throughput": 553.57, "total_tokens": 50418960} {"current_steps": 30880, "total_steps": 40000, "loss": 0.1107, "lr": 6.145004742870305e-06, "epoch": 1.3979266167183504, "percentage": 77.2, "elapsed_time": "1 day, 1:18:02", "remaining_time": "7:28:20", "throughput": 553.64, "total_tokens": 50426896} {"current_steps": 30885, "total_steps": 40000, "loss": 0.0905, "lr": 6.138559599735752e-06, "epoch": 1.3981529686049934, "percentage": 77.21, "elapsed_time": "1 day, 1:18:05", "remaining_time": "7:28:01", "throughput": 553.71, "total_tokens": 50435056} {"current_steps": 30890, "total_steps": 40000, "loss": 0.0577, "lr": 6.132117365272344e-06, "epoch": 1.3983793204916364, "percentage": 77.22, "elapsed_time": "1 day, 1:18:09", "remaining_time": "7:27:43", "throughput": 553.78, "total_tokens": 50443184} {"current_steps": 30895, "total_steps": 40000, "loss": 0.1176, "lr": 6.125678040473545e-06, "epoch": 1.3986056723782792, "percentage": 77.24, "elapsed_time": "1 day, 1:18:12", "remaining_time": "7:27:25", "throughput": 553.86, "total_tokens": 50452208} {"current_steps": 30900, "total_steps": 40000, "loss": 0.0801, "lr": 6.1192416263323755e-06, "epoch": 1.3988320242649221, "percentage": 77.25, "elapsed_time": "1 day, 1:18:15", "remaining_time": "7:27:07", "throughput": 553.92, "total_tokens": 50459856} {"current_steps": 30905, "total_steps": 40000, "loss": 0.1372, "lr": 6.112808123841424e-06, "epoch": 1.3990583761515651, "percentage": 77.26, "elapsed_time": "1 day, 1:18:18", "remaining_time": "7:26:49", "throughput": 554.0, "total_tokens": 50468272} {"current_steps": 30910, "total_steps": 40000, "loss": 0.1309, "lr": 6.106377533992805e-06, "epoch": 1.3992847280382081, "percentage": 77.28, "elapsed_time": "1 day, 1:18:21", "remaining_time": "7:26:31", "throughput": 554.06, "total_tokens": 50476272} {"current_steps": 30915, "total_steps": 40000, "loss": 0.1177, "lr": 6.099949857778204e-06, "epoch": 1.3995110799248511, "percentage": 77.29, "elapsed_time": "1 day, 1:18:25", "remaining_time": "7:26:13", "throughput": 554.13, "total_tokens": 50484336} {"current_steps": 30920, "total_steps": 40000, "loss": 0.1199, "lr": 6.093525096188852e-06, "epoch": 1.3997374318114941, "percentage": 77.3, "elapsed_time": "1 day, 1:18:28", "remaining_time": "7:25:54", "throughput": 554.21, "total_tokens": 50492880} {"current_steps": 30925, "total_steps": 40000, "loss": 0.0944, "lr": 6.087103250215518e-06, "epoch": 1.3999637836981371, "percentage": 77.31, "elapsed_time": "1 day, 1:18:31", "remaining_time": "7:25:36", "throughput": 554.28, "total_tokens": 50501200} {"current_steps": 30930, "total_steps": 40000, "loss": 0.0856, "lr": 6.080684320848537e-06, "epoch": 1.4001901355847801, "percentage": 77.33, "elapsed_time": "1 day, 1:18:34", "remaining_time": "7:25:18", "throughput": 554.35, "total_tokens": 50510000} {"current_steps": 30935, "total_steps": 40000, "loss": 0.1036, "lr": 6.074268309077794e-06, "epoch": 1.400416487471423, "percentage": 77.34, "elapsed_time": "1 day, 1:18:38", "remaining_time": "7:25:00", "throughput": 554.43, "total_tokens": 50518288} {"current_steps": 30940, "total_steps": 40000, "loss": 0.1151, "lr": 6.067855215892709e-06, "epoch": 1.400642839358066, "percentage": 77.35, "elapsed_time": "1 day, 1:18:41", "remaining_time": "7:24:42", "throughput": 554.5, "total_tokens": 50526704} {"current_steps": 30945, "total_steps": 40000, "loss": 0.1205, "lr": 6.061445042282271e-06, "epoch": 1.400869191244709, "percentage": 77.36, "elapsed_time": "1 day, 1:18:44", "remaining_time": "7:24:24", "throughput": 554.57, "total_tokens": 50535088} {"current_steps": 30950, "total_steps": 40000, "loss": 0.1206, "lr": 6.055037789234999e-06, "epoch": 1.401095543131352, "percentage": 77.38, "elapsed_time": "1 day, 1:18:47", "remaining_time": "7:24:06", "throughput": 554.64, "total_tokens": 50543248} {"current_steps": 30955, "total_steps": 40000, "loss": 0.1199, "lr": 6.048633457738975e-06, "epoch": 1.401321895017995, "percentage": 77.39, "elapsed_time": "1 day, 1:18:50", "remaining_time": "7:23:48", "throughput": 554.72, "total_tokens": 50551760} {"current_steps": 30960, "total_steps": 40000, "loss": 0.13, "lr": 6.042232048781837e-06, "epoch": 1.401548246904638, "percentage": 77.4, "elapsed_time": "1 day, 1:18:54", "remaining_time": "7:23:30", "throughput": 554.78, "total_tokens": 50559696} {"current_steps": 30965, "total_steps": 40000, "loss": 0.0682, "lr": 6.035833563350757e-06, "epoch": 1.4017745987912809, "percentage": 77.41, "elapsed_time": "1 day, 1:18:57", "remaining_time": "7:23:12", "throughput": 554.85, "total_tokens": 50567856} {"current_steps": 30970, "total_steps": 40000, "loss": 0.1517, "lr": 6.0294380024324525e-06, "epoch": 1.4020009506779239, "percentage": 77.42, "elapsed_time": "1 day, 1:19:00", "remaining_time": "7:22:54", "throughput": 554.92, "total_tokens": 50575696} {"current_steps": 30975, "total_steps": 40000, "loss": 0.1173, "lr": 6.023045367013213e-06, "epoch": 1.4022273025645668, "percentage": 77.44, "elapsed_time": "1 day, 1:19:03", "remaining_time": "7:22:35", "throughput": 554.99, "total_tokens": 50583920} {"current_steps": 30980, "total_steps": 40000, "loss": 0.1557, "lr": 6.016655658078851e-06, "epoch": 1.4024536544512098, "percentage": 77.45, "elapsed_time": "1 day, 1:19:06", "remaining_time": "7:22:17", "throughput": 555.06, "total_tokens": 50591984} {"current_steps": 30985, "total_steps": 40000, "loss": 0.1056, "lr": 6.010268876614753e-06, "epoch": 1.4026800063378528, "percentage": 77.46, "elapsed_time": "1 day, 1:19:09", "remaining_time": "7:21:59", "throughput": 555.13, "total_tokens": 50600240} {"current_steps": 30990, "total_steps": 40000, "loss": 0.1339, "lr": 6.0038850236058266e-06, "epoch": 1.4029063582244958, "percentage": 77.48, "elapsed_time": "1 day, 1:19:13", "remaining_time": "7:21:41", "throughput": 555.22, "total_tokens": 50610416} {"current_steps": 30995, "total_steps": 40000, "loss": 0.0824, "lr": 5.997504100036549e-06, "epoch": 1.4031327101111388, "percentage": 77.49, "elapsed_time": "1 day, 1:19:16", "remaining_time": "7:21:23", "throughput": 555.29, "total_tokens": 50618896} {"current_steps": 31000, "total_steps": 40000, "loss": 0.131, "lr": 5.991126106890949e-06, "epoch": 1.4033590619977818, "percentage": 77.5, "elapsed_time": "1 day, 1:19:19", "remaining_time": "7:21:05", "throughput": 555.36, "total_tokens": 50626416} {"current_steps": 31000, "total_steps": 40000, "eval_loss": 0.12233555316925049, "epoch": 1.4033590619977818, "percentage": 77.5, "elapsed_time": "1 day, 1:27:02", "remaining_time": "7:23:20", "throughput": 552.55, "total_tokens": 50626416} {"current_steps": 31005, "total_steps": 40000, "loss": 0.1498, "lr": 5.984751045152576e-06, "epoch": 1.4035854138844246, "percentage": 77.51, "elapsed_time": "1 day, 1:27:06", "remaining_time": "7:23:02", "throughput": 552.62, "total_tokens": 50634384} {"current_steps": 31010, "total_steps": 40000, "loss": 0.1491, "lr": 5.978378915804553e-06, "epoch": 1.4038117657710676, "percentage": 77.53, "elapsed_time": "1 day, 1:27:09", "remaining_time": "7:22:44", "throughput": 552.69, "total_tokens": 50642512} {"current_steps": 31015, "total_steps": 40000, "loss": 0.1213, "lr": 5.972009719829547e-06, "epoch": 1.4040381176577106, "percentage": 77.54, "elapsed_time": "1 day, 1:27:12", "remaining_time": "7:22:25", "throughput": 552.76, "total_tokens": 50651088} {"current_steps": 31020, "total_steps": 40000, "loss": 0.1171, "lr": 5.965643458209755e-06, "epoch": 1.4042644695443536, "percentage": 77.55, "elapsed_time": "1 day, 1:27:16", "remaining_time": "7:22:07", "throughput": 552.83, "total_tokens": 50659088} {"current_steps": 31025, "total_steps": 40000, "loss": 0.1091, "lr": 5.95928013192695e-06, "epoch": 1.4044908214309966, "percentage": 77.56, "elapsed_time": "1 day, 1:27:19", "remaining_time": "7:21:49", "throughput": 552.9, "total_tokens": 50667408} {"current_steps": 31030, "total_steps": 40000, "loss": 0.1095, "lr": 5.952919741962423e-06, "epoch": 1.4047171733176396, "percentage": 77.58, "elapsed_time": "1 day, 1:27:22", "remaining_time": "7:21:31", "throughput": 552.97, "total_tokens": 50675568} {"current_steps": 31035, "total_steps": 40000, "loss": 0.0985, "lr": 5.946562289297042e-06, "epoch": 1.4049435252042826, "percentage": 77.59, "elapsed_time": "1 day, 1:27:25", "remaining_time": "7:21:13", "throughput": 553.05, "total_tokens": 50684336} {"current_steps": 31040, "total_steps": 40000, "loss": 0.1174, "lr": 5.9402077749111855e-06, "epoch": 1.4051698770909256, "percentage": 77.6, "elapsed_time": "1 day, 1:27:29", "remaining_time": "7:20:55", "throughput": 553.12, "total_tokens": 50692624} {"current_steps": 31045, "total_steps": 40000, "loss": 0.0999, "lr": 5.933856199784821e-06, "epoch": 1.4053962289775686, "percentage": 77.61, "elapsed_time": "1 day, 1:27:32", "remaining_time": "7:20:37", "throughput": 553.19, "total_tokens": 50700752} {"current_steps": 31050, "total_steps": 40000, "loss": 0.103, "lr": 5.927507564897419e-06, "epoch": 1.4056225808642115, "percentage": 77.62, "elapsed_time": "1 day, 1:27:35", "remaining_time": "7:20:19", "throughput": 553.26, "total_tokens": 50709712} {"current_steps": 31055, "total_steps": 40000, "loss": 0.091, "lr": 5.9211618712280395e-06, "epoch": 1.4058489327508545, "percentage": 77.64, "elapsed_time": "1 day, 1:27:38", "remaining_time": "7:20:01", "throughput": 553.33, "total_tokens": 50717392} {"current_steps": 31060, "total_steps": 40000, "loss": 0.1273, "lr": 5.914819119755255e-06, "epoch": 1.4060752846374975, "percentage": 77.65, "elapsed_time": "1 day, 1:27:41", "remaining_time": "7:19:43", "throughput": 553.4, "total_tokens": 50725424} {"current_steps": 31065, "total_steps": 40000, "loss": 0.1399, "lr": 5.908479311457205e-06, "epoch": 1.4063016365241405, "percentage": 77.66, "elapsed_time": "1 day, 1:27:45", "remaining_time": "7:19:24", "throughput": 553.47, "total_tokens": 50733776} {"current_steps": 31070, "total_steps": 40000, "loss": 0.1315, "lr": 5.902142447311559e-06, "epoch": 1.4065279884107835, "percentage": 77.68, "elapsed_time": "1 day, 1:27:48", "remaining_time": "7:19:06", "throughput": 553.54, "total_tokens": 50742256} {"current_steps": 31075, "total_steps": 40000, "loss": 0.0817, "lr": 5.895808528295546e-06, "epoch": 1.4067543402974263, "percentage": 77.69, "elapsed_time": "1 day, 1:27:51", "remaining_time": "7:18:48", "throughput": 553.61, "total_tokens": 50750416} {"current_steps": 31080, "total_steps": 40000, "loss": 0.1481, "lr": 5.889477555385941e-06, "epoch": 1.4069806921840693, "percentage": 77.7, "elapsed_time": "1 day, 1:27:54", "remaining_time": "7:18:30", "throughput": 553.68, "total_tokens": 50758896} {"current_steps": 31085, "total_steps": 40000, "loss": 0.1028, "lr": 5.883149529559051e-06, "epoch": 1.4072070440707123, "percentage": 77.71, "elapsed_time": "1 day, 1:27:57", "remaining_time": "7:18:12", "throughput": 553.76, "total_tokens": 50767184} {"current_steps": 31090, "total_steps": 40000, "loss": 0.1855, "lr": 5.876824451790738e-06, "epoch": 1.4074333959573553, "percentage": 77.72, "elapsed_time": "1 day, 1:28:01", "remaining_time": "7:17:54", "throughput": 553.82, "total_tokens": 50775088} {"current_steps": 31095, "total_steps": 40000, "loss": 0.1414, "lr": 5.87050232305642e-06, "epoch": 1.4076597478439983, "percentage": 77.74, "elapsed_time": "1 day, 1:28:04", "remaining_time": "7:17:36", "throughput": 553.9, "total_tokens": 50783632} {"current_steps": 31100, "total_steps": 40000, "loss": 0.1021, "lr": 5.864183144331034e-06, "epoch": 1.4078860997306413, "percentage": 77.75, "elapsed_time": "1 day, 1:28:07", "remaining_time": "7:17:18", "throughput": 553.96, "total_tokens": 50791536} {"current_steps": 31105, "total_steps": 40000, "loss": 0.1104, "lr": 5.857866916589089e-06, "epoch": 1.4081124516172843, "percentage": 77.76, "elapsed_time": "1 day, 1:28:10", "remaining_time": "7:17:00", "throughput": 554.04, "total_tokens": 50799984} {"current_steps": 31110, "total_steps": 40000, "loss": 0.1349, "lr": 5.8515536408046216e-06, "epoch": 1.4083388035039273, "percentage": 77.78, "elapsed_time": "1 day, 1:28:13", "remaining_time": "7:16:42", "throughput": 554.1, "total_tokens": 50807824} {"current_steps": 31115, "total_steps": 40000, "loss": 0.1343, "lr": 5.845243317951208e-06, "epoch": 1.4085651553905703, "percentage": 77.79, "elapsed_time": "1 day, 1:28:17", "remaining_time": "7:16:24", "throughput": 554.17, "total_tokens": 50815920} {"current_steps": 31120, "total_steps": 40000, "loss": 0.106, "lr": 5.838935949001997e-06, "epoch": 1.408791507277213, "percentage": 77.8, "elapsed_time": "1 day, 1:28:20", "remaining_time": "7:16:06", "throughput": 554.25, "total_tokens": 50824656} {"current_steps": 31125, "total_steps": 40000, "loss": 0.1766, "lr": 5.8326315349296476e-06, "epoch": 1.409017859163856, "percentage": 77.81, "elapsed_time": "1 day, 1:28:23", "remaining_time": "7:15:48", "throughput": 554.32, "total_tokens": 50833232} {"current_steps": 31130, "total_steps": 40000, "loss": 0.1162, "lr": 5.826330076706396e-06, "epoch": 1.409244211050499, "percentage": 77.83, "elapsed_time": "1 day, 1:28:26", "remaining_time": "7:15:30", "throughput": 554.39, "total_tokens": 50841744} {"current_steps": 31135, "total_steps": 40000, "loss": 0.1403, "lr": 5.820031575303988e-06, "epoch": 1.409470562937142, "percentage": 77.84, "elapsed_time": "1 day, 1:28:30", "remaining_time": "7:15:12", "throughput": 554.46, "total_tokens": 50849808} {"current_steps": 31140, "total_steps": 40000, "loss": 0.1481, "lr": 5.813736031693745e-06, "epoch": 1.409696914823785, "percentage": 77.85, "elapsed_time": "1 day, 1:28:33", "remaining_time": "7:14:54", "throughput": 554.53, "total_tokens": 50857776} {"current_steps": 31145, "total_steps": 40000, "loss": 0.1044, "lr": 5.807443446846522e-06, "epoch": 1.409923266710428, "percentage": 77.86, "elapsed_time": "1 day, 1:28:36", "remaining_time": "7:14:36", "throughput": 554.6, "total_tokens": 50866192} {"current_steps": 31150, "total_steps": 40000, "loss": 0.118, "lr": 5.801153821732699e-06, "epoch": 1.410149618597071, "percentage": 77.88, "elapsed_time": "1 day, 1:28:39", "remaining_time": "7:14:18", "throughput": 554.67, "total_tokens": 50874544} {"current_steps": 31155, "total_steps": 40000, "loss": 0.1361, "lr": 5.794867157322229e-06, "epoch": 1.410375970483714, "percentage": 77.89, "elapsed_time": "1 day, 1:28:42", "remaining_time": "7:14:00", "throughput": 554.74, "total_tokens": 50881968} {"current_steps": 31160, "total_steps": 40000, "loss": 0.1116, "lr": 5.788583454584593e-06, "epoch": 1.410602322370357, "percentage": 77.9, "elapsed_time": "1 day, 1:28:46", "remaining_time": "7:13:42", "throughput": 554.81, "total_tokens": 50890448} {"current_steps": 31165, "total_steps": 40000, "loss": 0.1076, "lr": 5.7823027144888075e-06, "epoch": 1.410828674257, "percentage": 77.91, "elapsed_time": "1 day, 1:28:49", "remaining_time": "7:13:24", "throughput": 554.88, "total_tokens": 50899056} {"current_steps": 31170, "total_steps": 40000, "loss": 0.0905, "lr": 5.776024938003455e-06, "epoch": 1.411055026143643, "percentage": 77.92, "elapsed_time": "1 day, 1:28:52", "remaining_time": "7:13:06", "throughput": 554.96, "total_tokens": 50907664} {"current_steps": 31175, "total_steps": 40000, "loss": 0.1613, "lr": 5.7697501260966345e-06, "epoch": 1.411281378030286, "percentage": 77.94, "elapsed_time": "1 day, 1:28:55", "remaining_time": "7:12:48", "throughput": 555.03, "total_tokens": 50916208} {"current_steps": 31180, "total_steps": 40000, "loss": 0.0894, "lr": 5.7634782797360145e-06, "epoch": 1.411507729916929, "percentage": 77.95, "elapsed_time": "1 day, 1:28:58", "remaining_time": "7:12:30", "throughput": 555.1, "total_tokens": 50924144} {"current_steps": 31185, "total_steps": 40000, "loss": 0.0904, "lr": 5.757209399888777e-06, "epoch": 1.411734081803572, "percentage": 77.96, "elapsed_time": "1 day, 1:29:02", "remaining_time": "7:12:12", "throughput": 555.16, "total_tokens": 50931408} {"current_steps": 31190, "total_steps": 40000, "loss": 0.1331, "lr": 5.750943487521679e-06, "epoch": 1.4119604336902147, "percentage": 77.98, "elapsed_time": "1 day, 1:29:05", "remaining_time": "7:11:54", "throughput": 555.22, "total_tokens": 50939120} {"current_steps": 31195, "total_steps": 40000, "loss": 0.1128, "lr": 5.744680543600986e-06, "epoch": 1.4121867855768577, "percentage": 77.99, "elapsed_time": "1 day, 1:29:08", "remaining_time": "7:11:36", "throughput": 555.29, "total_tokens": 50946928} {"current_steps": 31200, "total_steps": 40000, "loss": 0.1164, "lr": 5.738420569092537e-06, "epoch": 1.4124131374635007, "percentage": 78.0, "elapsed_time": "1 day, 1:29:11", "remaining_time": "7:11:18", "throughput": 555.37, "total_tokens": 50955696} {"current_steps": 31200, "total_steps": 40000, "eval_loss": 0.12220349907875061, "epoch": 1.4124131374635007, "percentage": 78.0, "elapsed_time": "1 day, 1:36:54", "remaining_time": "7:13:29", "throughput": 552.58, "total_tokens": 50955696} {"current_steps": 31205, "total_steps": 40000, "loss": 0.0779, "lr": 5.732163564961684e-06, "epoch": 1.4126394893501437, "percentage": 78.01, "elapsed_time": "1 day, 1:36:58", "remaining_time": "7:13:11", "throughput": 552.64, "total_tokens": 50964336} {"current_steps": 31210, "total_steps": 40000, "loss": 0.1292, "lr": 5.725909532173354e-06, "epoch": 1.4128658412367867, "percentage": 78.03, "elapsed_time": "1 day, 1:37:02", "remaining_time": "7:12:53", "throughput": 552.71, "total_tokens": 50972176} {"current_steps": 31215, "total_steps": 40000, "loss": 0.1111, "lr": 5.719658471691977e-06, "epoch": 1.4130921931234297, "percentage": 78.04, "elapsed_time": "1 day, 1:37:05", "remaining_time": "7:12:35", "throughput": 552.77, "total_tokens": 50979728} {"current_steps": 31220, "total_steps": 40000, "loss": 0.1574, "lr": 5.71341038448156e-06, "epoch": 1.4133185450100727, "percentage": 78.05, "elapsed_time": "1 day, 1:37:08", "remaining_time": "7:12:17", "throughput": 552.84, "total_tokens": 50987856} {"current_steps": 31225, "total_steps": 40000, "loss": 0.1132, "lr": 5.707165271505635e-06, "epoch": 1.4135448968967157, "percentage": 78.06, "elapsed_time": "1 day, 1:37:11", "remaining_time": "7:11:59", "throughput": 552.92, "total_tokens": 50996400} {"current_steps": 31230, "total_steps": 40000, "loss": 0.1202, "lr": 5.700923133727271e-06, "epoch": 1.4137712487833587, "percentage": 78.08, "elapsed_time": "1 day, 1:37:14", "remaining_time": "7:11:41", "throughput": 552.98, "total_tokens": 51004272} {"current_steps": 31235, "total_steps": 40000, "loss": 0.131, "lr": 5.694683972109083e-06, "epoch": 1.4139976006700015, "percentage": 78.09, "elapsed_time": "1 day, 1:37:17", "remaining_time": "7:11:23", "throughput": 553.05, "total_tokens": 51012240} {"current_steps": 31240, "total_steps": 40000, "loss": 0.0986, "lr": 5.688447787613241e-06, "epoch": 1.4142239525566445, "percentage": 78.1, "elapsed_time": "1 day, 1:37:21", "remaining_time": "7:11:05", "throughput": 553.12, "total_tokens": 51020688} {"current_steps": 31245, "total_steps": 40000, "loss": 0.1401, "lr": 5.6822145812014285e-06, "epoch": 1.4144503044432875, "percentage": 78.11, "elapsed_time": "1 day, 1:37:24", "remaining_time": "7:10:47", "throughput": 553.19, "total_tokens": 51028720} {"current_steps": 31250, "total_steps": 40000, "loss": 0.1597, "lr": 5.675984353834896e-06, "epoch": 1.4146766563299304, "percentage": 78.12, "elapsed_time": "1 day, 1:37:27", "remaining_time": "7:10:29", "throughput": 553.26, "total_tokens": 51036656} {"current_steps": 31255, "total_steps": 40000, "loss": 0.1106, "lr": 5.66975710647441e-06, "epoch": 1.4149030082165734, "percentage": 78.14, "elapsed_time": "1 day, 1:37:30", "remaining_time": "7:10:11", "throughput": 553.33, "total_tokens": 51044624} {"current_steps": 31260, "total_steps": 40000, "loss": 0.1048, "lr": 5.663532840080304e-06, "epoch": 1.4151293601032164, "percentage": 78.15, "elapsed_time": "1 day, 1:37:33", "remaining_time": "7:09:53", "throughput": 553.4, "total_tokens": 51053360} {"current_steps": 31265, "total_steps": 40000, "loss": 0.1367, "lr": 5.6573115556124325e-06, "epoch": 1.4153557119898594, "percentage": 78.16, "elapsed_time": "1 day, 1:37:36", "remaining_time": "7:09:35", "throughput": 553.47, "total_tokens": 51061360} {"current_steps": 31270, "total_steps": 40000, "loss": 0.1357, "lr": 5.651093254030185e-06, "epoch": 1.4155820638765024, "percentage": 78.17, "elapsed_time": "1 day, 1:37:40", "remaining_time": "7:09:17", "throughput": 553.54, "total_tokens": 51069296} {"current_steps": 31275, "total_steps": 40000, "loss": 0.1897, "lr": 5.644877936292514e-06, "epoch": 1.4158084157631454, "percentage": 78.19, "elapsed_time": "1 day, 1:37:43", "remaining_time": "7:08:59", "throughput": 553.61, "total_tokens": 51077616} {"current_steps": 31280, "total_steps": 40000, "loss": 0.1056, "lr": 5.638665603357901e-06, "epoch": 1.4160347676497884, "percentage": 78.2, "elapsed_time": "1 day, 1:37:46", "remaining_time": "7:08:41", "throughput": 553.68, "total_tokens": 51085648} {"current_steps": 31285, "total_steps": 40000, "loss": 0.1091, "lr": 5.632456256184357e-06, "epoch": 1.4162611195364314, "percentage": 78.21, "elapsed_time": "1 day, 1:37:49", "remaining_time": "7:08:23", "throughput": 553.75, "total_tokens": 51093840} {"current_steps": 31290, "total_steps": 40000, "loss": 0.2, "lr": 5.626249895729452e-06, "epoch": 1.4164874714230744, "percentage": 78.22, "elapsed_time": "1 day, 1:37:52", "remaining_time": "7:08:05", "throughput": 553.81, "total_tokens": 51101840} {"current_steps": 31295, "total_steps": 40000, "loss": 0.0737, "lr": 5.620046522950273e-06, "epoch": 1.4167138233097174, "percentage": 78.24, "elapsed_time": "1 day, 1:37:56", "remaining_time": "7:07:47", "throughput": 553.89, "total_tokens": 51110448} {"current_steps": 31300, "total_steps": 40000, "loss": 0.1334, "lr": 5.613846138803464e-06, "epoch": 1.4169401751963604, "percentage": 78.25, "elapsed_time": "1 day, 1:37:59", "remaining_time": "7:07:29", "throughput": 553.96, "total_tokens": 51118576} {"current_steps": 31305, "total_steps": 40000, "loss": 0.1332, "lr": 5.607648744245206e-06, "epoch": 1.4171665270830032, "percentage": 78.26, "elapsed_time": "1 day, 1:38:02", "remaining_time": "7:07:11", "throughput": 554.02, "total_tokens": 51126736} {"current_steps": 31310, "total_steps": 40000, "loss": 0.1417, "lr": 5.601454340231207e-06, "epoch": 1.4173928789696462, "percentage": 78.27, "elapsed_time": "1 day, 1:38:05", "remaining_time": "7:06:53", "throughput": 554.1, "total_tokens": 51135248} {"current_steps": 31315, "total_steps": 40000, "loss": 0.1353, "lr": 5.595262927716724e-06, "epoch": 1.4176192308562892, "percentage": 78.29, "elapsed_time": "1 day, 1:38:08", "remaining_time": "7:06:35", "throughput": 554.17, "total_tokens": 51143312} {"current_steps": 31320, "total_steps": 40000, "loss": 0.1391, "lr": 5.589074507656561e-06, "epoch": 1.4178455827429322, "percentage": 78.3, "elapsed_time": "1 day, 1:38:11", "remaining_time": "7:06:17", "throughput": 554.23, "total_tokens": 51151248} {"current_steps": 31325, "total_steps": 40000, "loss": 0.1149, "lr": 5.582889081005044e-06, "epoch": 1.4180719346295751, "percentage": 78.31, "elapsed_time": "1 day, 1:38:15", "remaining_time": "7:05:59", "throughput": 554.31, "total_tokens": 51160400} {"current_steps": 31330, "total_steps": 40000, "loss": 0.1129, "lr": 5.5767066487160316e-06, "epoch": 1.4182982865162181, "percentage": 78.33, "elapsed_time": "1 day, 1:38:18", "remaining_time": "7:05:41", "throughput": 554.39, "total_tokens": 51169328} {"current_steps": 31335, "total_steps": 40000, "loss": 0.1167, "lr": 5.570527211742949e-06, "epoch": 1.4185246384028611, "percentage": 78.34, "elapsed_time": "1 day, 1:38:21", "remaining_time": "7:05:24", "throughput": 554.45, "total_tokens": 51177072} {"current_steps": 31340, "total_steps": 40000, "loss": 0.1116, "lr": 5.564350771038731e-06, "epoch": 1.4187509902895041, "percentage": 78.35, "elapsed_time": "1 day, 1:38:25", "remaining_time": "7:05:06", "throughput": 554.53, "total_tokens": 51185808} {"current_steps": 31345, "total_steps": 40000, "loss": 0.1248, "lr": 5.558177327555875e-06, "epoch": 1.418977342176147, "percentage": 78.36, "elapsed_time": "1 day, 1:38:28", "remaining_time": "7:04:48", "throughput": 554.59, "total_tokens": 51193616} {"current_steps": 31350, "total_steps": 40000, "loss": 0.0762, "lr": 5.552006882246388e-06, "epoch": 1.41920369406279, "percentage": 78.38, "elapsed_time": "1 day, 1:38:31", "remaining_time": "7:04:30", "throughput": 554.66, "total_tokens": 51201488} {"current_steps": 31355, "total_steps": 40000, "loss": 0.1155, "lr": 5.545839436061839e-06, "epoch": 1.419430045949433, "percentage": 78.39, "elapsed_time": "1 day, 1:38:34", "remaining_time": "7:04:12", "throughput": 554.73, "total_tokens": 51209168} {"current_steps": 31360, "total_steps": 40000, "loss": 0.1078, "lr": 5.539674989953331e-06, "epoch": 1.419656397836076, "percentage": 78.4, "elapsed_time": "1 day, 1:38:37", "remaining_time": "7:03:54", "throughput": 554.79, "total_tokens": 51217168} {"current_steps": 31365, "total_steps": 40000, "loss": 0.1125, "lr": 5.533513544871488e-06, "epoch": 1.4198827497227189, "percentage": 78.41, "elapsed_time": "1 day, 1:38:40", "remaining_time": "7:03:36", "throughput": 554.87, "total_tokens": 51226192} {"current_steps": 31370, "total_steps": 40000, "loss": 0.1019, "lr": 5.527355101766493e-06, "epoch": 1.4201091016093619, "percentage": 78.42, "elapsed_time": "1 day, 1:38:44", "remaining_time": "7:03:18", "throughput": 554.94, "total_tokens": 51234416} {"current_steps": 31375, "total_steps": 40000, "loss": 0.0786, "lr": 5.521199661588044e-06, "epoch": 1.4203354534960049, "percentage": 78.44, "elapsed_time": "1 day, 1:38:47", "remaining_time": "7:03:00", "throughput": 555.01, "total_tokens": 51242416} {"current_steps": 31380, "total_steps": 40000, "loss": 0.128, "lr": 5.5150472252853944e-06, "epoch": 1.4205618053826479, "percentage": 78.45, "elapsed_time": "1 day, 1:38:50", "remaining_time": "7:02:42", "throughput": 555.08, "total_tokens": 51250608} {"current_steps": 31385, "total_steps": 40000, "loss": 0.1322, "lr": 5.50889779380733e-06, "epoch": 1.4207881572692909, "percentage": 78.46, "elapsed_time": "1 day, 1:38:53", "remaining_time": "7:02:25", "throughput": 555.15, "total_tokens": 51258832} {"current_steps": 31390, "total_steps": 40000, "loss": 0.1075, "lr": 5.5027513681021605e-06, "epoch": 1.4210145091559339, "percentage": 78.47, "elapsed_time": "1 day, 1:38:56", "remaining_time": "7:02:07", "throughput": 555.22, "total_tokens": 51266992} {"current_steps": 31395, "total_steps": 40000, "loss": 0.1006, "lr": 5.4966079491177545e-06, "epoch": 1.4212408610425769, "percentage": 78.49, "elapsed_time": "1 day, 1:38:59", "remaining_time": "7:01:49", "throughput": 555.29, "total_tokens": 51275184} {"current_steps": 31400, "total_steps": 40000, "loss": 0.0775, "lr": 5.490467537801491e-06, "epoch": 1.4214672129292198, "percentage": 78.5, "elapsed_time": "1 day, 1:39:03", "remaining_time": "7:01:31", "throughput": 555.36, "total_tokens": 51283248} {"current_steps": 31400, "total_steps": 40000, "eval_loss": 0.12242110818624496, "epoch": 1.4214672129292198, "percentage": 78.5, "elapsed_time": "1 day, 1:46:45", "remaining_time": "7:03:38", "throughput": 552.59, "total_tokens": 51283248} {"current_steps": 31405, "total_steps": 40000, "loss": 0.1367, "lr": 5.484330135100313e-06, "epoch": 1.4216935648158628, "percentage": 78.51, "elapsed_time": "1 day, 1:46:49", "remaining_time": "7:03:20", "throughput": 552.65, "total_tokens": 51291504} {"current_steps": 31410, "total_steps": 40000, "loss": 0.1439, "lr": 5.4781957419606785e-06, "epoch": 1.4219199167025058, "percentage": 78.53, "elapsed_time": "1 day, 1:46:53", "remaining_time": "7:03:02", "throughput": 552.72, "total_tokens": 51299824} {"current_steps": 31415, "total_steps": 40000, "loss": 0.1029, "lr": 5.472064359328577e-06, "epoch": 1.4221462685891486, "percentage": 78.54, "elapsed_time": "1 day, 1:46:56", "remaining_time": "7:02:44", "throughput": 552.78, "total_tokens": 51307408} {"current_steps": 31420, "total_steps": 40000, "loss": 0.1453, "lr": 5.4659359881495565e-06, "epoch": 1.4223726204757916, "percentage": 78.55, "elapsed_time": "1 day, 1:46:59", "remaining_time": "7:02:26", "throughput": 552.85, "total_tokens": 51315344} {"current_steps": 31425, "total_steps": 40000, "loss": 0.0917, "lr": 5.4598106293686916e-06, "epoch": 1.4225989723624346, "percentage": 78.56, "elapsed_time": "1 day, 1:47:02", "remaining_time": "7:02:08", "throughput": 552.92, "total_tokens": 51323824} {"current_steps": 31430, "total_steps": 40000, "loss": 0.1608, "lr": 5.45368828393058e-06, "epoch": 1.4228253242490776, "percentage": 78.57, "elapsed_time": "1 day, 1:47:05", "remaining_time": "7:01:50", "throughput": 552.99, "total_tokens": 51332144} {"current_steps": 31435, "total_steps": 40000, "loss": 0.1426, "lr": 5.44756895277937e-06, "epoch": 1.4230516761357206, "percentage": 78.59, "elapsed_time": "1 day, 1:47:08", "remaining_time": "7:01:32", "throughput": 553.06, "total_tokens": 51340080} {"current_steps": 31440, "total_steps": 40000, "loss": 0.0988, "lr": 5.441452636858746e-06, "epoch": 1.4232780280223636, "percentage": 78.6, "elapsed_time": "1 day, 1:47:12", "remaining_time": "7:01:14", "throughput": 553.13, "total_tokens": 51348336} {"current_steps": 31445, "total_steps": 40000, "loss": 0.1395, "lr": 5.435339337111905e-06, "epoch": 1.4235043799090066, "percentage": 78.61, "elapsed_time": "1 day, 1:47:15", "remaining_time": "7:00:56", "throughput": 553.2, "total_tokens": 51356048} {"current_steps": 31450, "total_steps": 40000, "loss": 0.1079, "lr": 5.42922905448161e-06, "epoch": 1.4237307317956496, "percentage": 78.62, "elapsed_time": "1 day, 1:47:18", "remaining_time": "7:00:39", "throughput": 553.27, "total_tokens": 51364400} {"current_steps": 31455, "total_steps": 40000, "loss": 0.1372, "lr": 5.423121789910129e-06, "epoch": 1.4239570836822926, "percentage": 78.64, "elapsed_time": "1 day, 1:47:21", "remaining_time": "7:00:21", "throughput": 553.33, "total_tokens": 51372336} {"current_steps": 31460, "total_steps": 40000, "loss": 0.1605, "lr": 5.417017544339287e-06, "epoch": 1.4241834355689353, "percentage": 78.65, "elapsed_time": "1 day, 1:47:24", "remaining_time": "7:00:03", "throughput": 553.41, "total_tokens": 51381264} {"current_steps": 31465, "total_steps": 40000, "loss": 0.0985, "lr": 5.410916318710443e-06, "epoch": 1.4244097874555783, "percentage": 78.66, "elapsed_time": "1 day, 1:47:28", "remaining_time": "6:59:45", "throughput": 553.48, "total_tokens": 51389104} {"current_steps": 31470, "total_steps": 40000, "loss": 0.1193, "lr": 5.404818113964466e-06, "epoch": 1.4246361393422213, "percentage": 78.67, "elapsed_time": "1 day, 1:47:31", "remaining_time": "6:59:27", "throughput": 553.55, "total_tokens": 51397584} {"current_steps": 31475, "total_steps": 40000, "loss": 0.091, "lr": 5.398722931041792e-06, "epoch": 1.4248624912288643, "percentage": 78.69, "elapsed_time": "1 day, 1:47:34", "remaining_time": "6:59:09", "throughput": 553.62, "total_tokens": 51406192} {"current_steps": 31480, "total_steps": 40000, "loss": 0.1113, "lr": 5.392630770882367e-06, "epoch": 1.4250888431155073, "percentage": 78.7, "elapsed_time": "1 day, 1:47:37", "remaining_time": "6:58:51", "throughput": 553.68, "total_tokens": 51413744} {"current_steps": 31485, "total_steps": 40000, "loss": 0.1314, "lr": 5.3865416344256705e-06, "epoch": 1.4253151950021503, "percentage": 78.71, "elapsed_time": "1 day, 1:47:40", "remaining_time": "6:58:33", "throughput": 553.75, "total_tokens": 51422032} {"current_steps": 31490, "total_steps": 40000, "loss": 0.1824, "lr": 5.380455522610742e-06, "epoch": 1.4255415468887933, "percentage": 78.72, "elapsed_time": "1 day, 1:47:43", "remaining_time": "6:58:15", "throughput": 553.82, "total_tokens": 51429872} {"current_steps": 31495, "total_steps": 40000, "loss": 0.1214, "lr": 5.374372436376116e-06, "epoch": 1.4257678987754363, "percentage": 78.74, "elapsed_time": "1 day, 1:47:47", "remaining_time": "6:57:58", "throughput": 553.89, "total_tokens": 51438000} {"current_steps": 31500, "total_steps": 40000, "loss": 0.0925, "lr": 5.368292376659895e-06, "epoch": 1.4259942506620793, "percentage": 78.75, "elapsed_time": "1 day, 1:47:50", "remaining_time": "6:57:40", "throughput": 553.96, "total_tokens": 51446096} {"current_steps": 31505, "total_steps": 40000, "loss": 0.0893, "lr": 5.362215344399701e-06, "epoch": 1.4262206025487223, "percentage": 78.76, "elapsed_time": "1 day, 1:47:53", "remaining_time": "6:57:22", "throughput": 554.03, "total_tokens": 51454512} {"current_steps": 31510, "total_steps": 40000, "loss": 0.0958, "lr": 5.356141340532678e-06, "epoch": 1.4264469544353653, "percentage": 78.77, "elapsed_time": "1 day, 1:47:56", "remaining_time": "6:57:04", "throughput": 554.1, "total_tokens": 51462800} {"current_steps": 31515, "total_steps": 40000, "loss": 0.1035, "lr": 5.350070365995522e-06, "epoch": 1.4266733063220083, "percentage": 78.79, "elapsed_time": "1 day, 1:48:00", "remaining_time": "6:56:46", "throughput": 554.17, "total_tokens": 51471344} {"current_steps": 31520, "total_steps": 40000, "loss": 0.1124, "lr": 5.344002421724459e-06, "epoch": 1.4268996582086513, "percentage": 78.8, "elapsed_time": "1 day, 1:48:03", "remaining_time": "6:56:28", "throughput": 554.24, "total_tokens": 51479664} {"current_steps": 31525, "total_steps": 40000, "loss": 0.117, "lr": 5.337937508655228e-06, "epoch": 1.4271260100952943, "percentage": 78.81, "elapsed_time": "1 day, 1:48:06", "remaining_time": "6:56:11", "throughput": 554.31, "total_tokens": 51487664} {"current_steps": 31530, "total_steps": 40000, "loss": 0.1404, "lr": 5.331875627723126e-06, "epoch": 1.427352361981937, "percentage": 78.83, "elapsed_time": "1 day, 1:48:09", "remaining_time": "6:55:53", "throughput": 554.38, "total_tokens": 51495664} {"current_steps": 31535, "total_steps": 40000, "loss": 0.1128, "lr": 5.325816779862963e-06, "epoch": 1.42757871386858, "percentage": 78.84, "elapsed_time": "1 day, 1:48:12", "remaining_time": "6:55:35", "throughput": 554.44, "total_tokens": 51503792} {"current_steps": 31540, "total_steps": 40000, "loss": 0.1478, "lr": 5.319760966009102e-06, "epoch": 1.427805065755223, "percentage": 78.85, "elapsed_time": "1 day, 1:48:15", "remaining_time": "6:55:17", "throughput": 554.51, "total_tokens": 51511696} {"current_steps": 31545, "total_steps": 40000, "loss": 0.078, "lr": 5.3137081870954096e-06, "epoch": 1.428031417641866, "percentage": 78.86, "elapsed_time": "1 day, 1:48:19", "remaining_time": "6:54:59", "throughput": 554.57, "total_tokens": 51519280} {"current_steps": 31550, "total_steps": 40000, "loss": 0.0729, "lr": 5.307658444055313e-06, "epoch": 1.428257769528509, "percentage": 78.88, "elapsed_time": "1 day, 1:48:22", "remaining_time": "6:54:41", "throughput": 554.64, "total_tokens": 51527120} {"current_steps": 31555, "total_steps": 40000, "loss": 0.1384, "lr": 5.301611737821749e-06, "epoch": 1.428484121415152, "percentage": 78.89, "elapsed_time": "1 day, 1:48:25", "remaining_time": "6:54:24", "throughput": 554.7, "total_tokens": 51534832} {"current_steps": 31560, "total_steps": 40000, "loss": 0.1212, "lr": 5.295568069327206e-06, "epoch": 1.428710473301795, "percentage": 78.9, "elapsed_time": "1 day, 1:48:28", "remaining_time": "6:54:06", "throughput": 554.77, "total_tokens": 51542928} {"current_steps": 31565, "total_steps": 40000, "loss": 0.1054, "lr": 5.289527439503683e-06, "epoch": 1.428936825188438, "percentage": 78.91, "elapsed_time": "1 day, 1:48:31", "remaining_time": "6:53:48", "throughput": 554.84, "total_tokens": 51550832} {"current_steps": 31570, "total_steps": 40000, "loss": 0.1228, "lr": 5.28348984928273e-06, "epoch": 1.429163177075081, "percentage": 78.92, "elapsed_time": "1 day, 1:48:34", "remaining_time": "6:53:30", "throughput": 554.9, "total_tokens": 51558928} {"current_steps": 31575, "total_steps": 40000, "loss": 0.1102, "lr": 5.27745529959541e-06, "epoch": 1.4293895289617238, "percentage": 78.94, "elapsed_time": "1 day, 1:48:38", "remaining_time": "6:53:12", "throughput": 554.97, "total_tokens": 51566544} {"current_steps": 31580, "total_steps": 40000, "loss": 0.0571, "lr": 5.271423791372335e-06, "epoch": 1.4296158808483668, "percentage": 78.95, "elapsed_time": "1 day, 1:48:41", "remaining_time": "6:52:55", "throughput": 555.03, "total_tokens": 51574096} {"current_steps": 31585, "total_steps": 40000, "loss": 0.1291, "lr": 5.26539532554364e-06, "epoch": 1.4298422327350098, "percentage": 78.96, "elapsed_time": "1 day, 1:48:44", "remaining_time": "6:52:37", "throughput": 555.1, "total_tokens": 51581936} {"current_steps": 31590, "total_steps": 40000, "loss": 0.1136, "lr": 5.25936990303898e-06, "epoch": 1.4300685846216528, "percentage": 78.97, "elapsed_time": "1 day, 1:48:47", "remaining_time": "6:52:19", "throughput": 555.16, "total_tokens": 51589776} {"current_steps": 31595, "total_steps": 40000, "loss": 0.1214, "lr": 5.253347524787555e-06, "epoch": 1.4302949365082958, "percentage": 78.99, "elapsed_time": "1 day, 1:48:50", "remaining_time": "6:52:01", "throughput": 555.23, "total_tokens": 51597776} {"current_steps": 31600, "total_steps": 40000, "loss": 0.0786, "lr": 5.2473281917181035e-06, "epoch": 1.4305212883949388, "percentage": 79.0, "elapsed_time": "1 day, 1:48:53", "remaining_time": "6:51:43", "throughput": 555.29, "total_tokens": 51605616} {"current_steps": 31600, "total_steps": 40000, "eval_loss": 0.12231971323490143, "epoch": 1.4305212883949388, "percentage": 79.0, "elapsed_time": "1 day, 1:56:36", "remaining_time": "6:53:46", "throughput": 552.54, "total_tokens": 51605616} {"current_steps": 31605, "total_steps": 40000, "loss": 0.1043, "lr": 5.241311904758864e-06, "epoch": 1.4307476402815817, "percentage": 79.01, "elapsed_time": "1 day, 1:56:40", "remaining_time": "6:53:29", "throughput": 552.61, "total_tokens": 51614000} {"current_steps": 31610, "total_steps": 40000, "loss": 0.1951, "lr": 5.23529866483764e-06, "epoch": 1.4309739921682247, "percentage": 79.03, "elapsed_time": "1 day, 1:56:43", "remaining_time": "6:53:11", "throughput": 552.67, "total_tokens": 51621584} {"current_steps": 31615, "total_steps": 40000, "loss": 0.1764, "lr": 5.229288472881732e-06, "epoch": 1.4312003440548677, "percentage": 79.04, "elapsed_time": "1 day, 1:56:46", "remaining_time": "6:52:53", "throughput": 552.75, "total_tokens": 51630416} {"current_steps": 31620, "total_steps": 40000, "loss": 0.1194, "lr": 5.2232813298180025e-06, "epoch": 1.4314266959415107, "percentage": 79.05, "elapsed_time": "1 day, 1:56:50", "remaining_time": "6:52:35", "throughput": 552.82, "total_tokens": 51638736} {"current_steps": 31625, "total_steps": 40000, "loss": 0.1235, "lr": 5.217277236572824e-06, "epoch": 1.4316530478281537, "percentage": 79.06, "elapsed_time": "1 day, 1:56:53", "remaining_time": "6:52:17", "throughput": 552.89, "total_tokens": 51646928} {"current_steps": 31630, "total_steps": 40000, "loss": 0.1566, "lr": 5.211276194072093e-06, "epoch": 1.4318793997147967, "percentage": 79.07, "elapsed_time": "1 day, 1:56:56", "remaining_time": "6:52:00", "throughput": 552.95, "total_tokens": 51654864} {"current_steps": 31635, "total_steps": 40000, "loss": 0.149, "lr": 5.205278203241254e-06, "epoch": 1.4321057516014397, "percentage": 79.09, "elapsed_time": "1 day, 1:56:59", "remaining_time": "6:51:42", "throughput": 553.03, "total_tokens": 51663408} {"current_steps": 31640, "total_steps": 40000, "loss": 0.1299, "lr": 5.199283265005278e-06, "epoch": 1.4323321034880827, "percentage": 79.1, "elapsed_time": "1 day, 1:57:02", "remaining_time": "6:51:24", "throughput": 553.09, "total_tokens": 51671280} {"current_steps": 31645, "total_steps": 40000, "loss": 0.1019, "lr": 5.193291380288648e-06, "epoch": 1.4325584553747255, "percentage": 79.11, "elapsed_time": "1 day, 1:57:06", "remaining_time": "6:51:06", "throughput": 553.17, "total_tokens": 51680144} {"current_steps": 31650, "total_steps": 40000, "loss": 0.0873, "lr": 5.1873025500153995e-06, "epoch": 1.4327848072613685, "percentage": 79.12, "elapsed_time": "1 day, 1:57:09", "remaining_time": "6:50:48", "throughput": 553.23, "total_tokens": 51688176} {"current_steps": 31655, "total_steps": 40000, "loss": 0.1093, "lr": 5.181316775109071e-06, "epoch": 1.4330111591480115, "percentage": 79.14, "elapsed_time": "1 day, 1:57:12", "remaining_time": "6:50:31", "throughput": 553.3, "total_tokens": 51696400} {"current_steps": 31660, "total_steps": 40000, "loss": 0.1428, "lr": 5.1753340564927564e-06, "epoch": 1.4332375110346545, "percentage": 79.15, "elapsed_time": "1 day, 1:57:15", "remaining_time": "6:50:13", "throughput": 553.36, "total_tokens": 51703952} {"current_steps": 31665, "total_steps": 40000, "loss": 0.1563, "lr": 5.169354395089068e-06, "epoch": 1.4334638629212975, "percentage": 79.16, "elapsed_time": "1 day, 1:57:18", "remaining_time": "6:49:55", "throughput": 553.43, "total_tokens": 51712368} {"current_steps": 31670, "total_steps": 40000, "loss": 0.121, "lr": 5.1633777918201346e-06, "epoch": 1.4336902148079405, "percentage": 79.17, "elapsed_time": "1 day, 1:57:22", "remaining_time": "6:49:37", "throughput": 553.51, "total_tokens": 51720848} {"current_steps": 31675, "total_steps": 40000, "loss": 0.0896, "lr": 5.157404247607625e-06, "epoch": 1.4339165666945834, "percentage": 79.19, "elapsed_time": "1 day, 1:57:25", "remaining_time": "6:49:19", "throughput": 553.57, "total_tokens": 51728656} {"current_steps": 31680, "total_steps": 40000, "loss": 0.1294, "lr": 5.1514337633727454e-06, "epoch": 1.4341429185812264, "percentage": 79.2, "elapsed_time": "1 day, 1:57:28", "remaining_time": "6:49:02", "throughput": 553.64, "total_tokens": 51737264} {"current_steps": 31685, "total_steps": 40000, "loss": 0.1038, "lr": 5.145466340036206e-06, "epoch": 1.4343692704678692, "percentage": 79.21, "elapsed_time": "1 day, 1:57:31", "remaining_time": "6:48:44", "throughput": 553.71, "total_tokens": 51744880} {"current_steps": 31690, "total_steps": 40000, "loss": 0.1103, "lr": 5.139501978518274e-06, "epoch": 1.4345956223545122, "percentage": 79.22, "elapsed_time": "1 day, 1:57:34", "remaining_time": "6:48:26", "throughput": 553.77, "total_tokens": 51752784} {"current_steps": 31695, "total_steps": 40000, "loss": 0.1023, "lr": 5.133540679738716e-06, "epoch": 1.4348219742411552, "percentage": 79.24, "elapsed_time": "1 day, 1:57:38", "remaining_time": "6:48:08", "throughput": 553.84, "total_tokens": 51761296} {"current_steps": 31700, "total_steps": 40000, "loss": 0.1814, "lr": 5.127582444616838e-06, "epoch": 1.4350483261277982, "percentage": 79.25, "elapsed_time": "1 day, 1:57:41", "remaining_time": "6:47:50", "throughput": 553.91, "total_tokens": 51768848} {"current_steps": 31705, "total_steps": 40000, "loss": 0.1763, "lr": 5.121627274071486e-06, "epoch": 1.4352746780144412, "percentage": 79.26, "elapsed_time": "1 day, 1:57:44", "remaining_time": "6:47:33", "throughput": 553.98, "total_tokens": 51777072} {"current_steps": 31710, "total_steps": 40000, "loss": 0.0936, "lr": 5.115675169021009e-06, "epoch": 1.4355010299010842, "percentage": 79.27, "elapsed_time": "1 day, 1:57:47", "remaining_time": "6:47:15", "throughput": 554.05, "total_tokens": 51785296} {"current_steps": 31715, "total_steps": 40000, "loss": 0.1131, "lr": 5.1097261303832994e-06, "epoch": 1.4357273817877272, "percentage": 79.29, "elapsed_time": "1 day, 1:57:50", "remaining_time": "6:46:57", "throughput": 554.11, "total_tokens": 51793296} {"current_steps": 31720, "total_steps": 40000, "loss": 0.1369, "lr": 5.103780159075788e-06, "epoch": 1.4359537336743702, "percentage": 79.3, "elapsed_time": "1 day, 1:57:54", "remaining_time": "6:46:39", "throughput": 554.18, "total_tokens": 51801648} {"current_steps": 31725, "total_steps": 40000, "loss": 0.1281, "lr": 5.0978372560154e-06, "epoch": 1.4361800855610132, "percentage": 79.31, "elapsed_time": "1 day, 1:57:57", "remaining_time": "6:46:22", "throughput": 554.25, "total_tokens": 51809232} {"current_steps": 31730, "total_steps": 40000, "loss": 0.1121, "lr": 5.091897422118619e-06, "epoch": 1.4364064374476562, "percentage": 79.33, "elapsed_time": "1 day, 1:58:00", "remaining_time": "6:46:04", "throughput": 554.32, "total_tokens": 51817872} {"current_steps": 31735, "total_steps": 40000, "loss": 0.1559, "lr": 5.0859606583014305e-06, "epoch": 1.4366327893342992, "percentage": 79.34, "elapsed_time": "1 day, 1:58:03", "remaining_time": "6:45:46", "throughput": 554.39, "total_tokens": 51826032} {"current_steps": 31740, "total_steps": 40000, "loss": 0.1131, "lr": 5.080026965479365e-06, "epoch": 1.4368591412209422, "percentage": 79.35, "elapsed_time": "1 day, 1:58:06", "remaining_time": "6:45:28", "throughput": 554.45, "total_tokens": 51834032} {"current_steps": 31745, "total_steps": 40000, "loss": 0.1141, "lr": 5.074096344567475e-06, "epoch": 1.4370854931075852, "percentage": 79.36, "elapsed_time": "1 day, 1:58:09", "remaining_time": "6:45:11", "throughput": 554.52, "total_tokens": 51841872} {"current_steps": 31750, "total_steps": 40000, "loss": 0.1584, "lr": 5.0681687964803294e-06, "epoch": 1.4373118449942281, "percentage": 79.38, "elapsed_time": "1 day, 1:58:13", "remaining_time": "6:44:53", "throughput": 554.59, "total_tokens": 51850384} {"current_steps": 31755, "total_steps": 40000, "loss": 0.1786, "lr": 5.06224432213204e-06, "epoch": 1.437538196880871, "percentage": 79.39, "elapsed_time": "1 day, 1:58:16", "remaining_time": "6:44:35", "throughput": 554.66, "total_tokens": 51858928} {"current_steps": 31760, "total_steps": 40000, "loss": 0.0741, "lr": 5.056322922436224e-06, "epoch": 1.437764548767514, "percentage": 79.4, "elapsed_time": "1 day, 1:58:19", "remaining_time": "6:44:18", "throughput": 554.72, "total_tokens": 51866480} {"current_steps": 31765, "total_steps": 40000, "loss": 0.1139, "lr": 5.0504045983060465e-06, "epoch": 1.437990900654157, "percentage": 79.41, "elapsed_time": "1 day, 1:58:22", "remaining_time": "6:44:00", "throughput": 554.79, "total_tokens": 51874160} {"current_steps": 31770, "total_steps": 40000, "loss": 0.102, "lr": 5.044489350654183e-06, "epoch": 1.4382172525408, "percentage": 79.42, "elapsed_time": "1 day, 1:58:25", "remaining_time": "6:43:42", "throughput": 554.85, "total_tokens": 51881840} {"current_steps": 31775, "total_steps": 40000, "loss": 0.0986, "lr": 5.038577180392831e-06, "epoch": 1.438443604427443, "percentage": 79.44, "elapsed_time": "1 day, 1:58:28", "remaining_time": "6:43:24", "throughput": 554.91, "total_tokens": 51889200} {"current_steps": 31780, "total_steps": 40000, "loss": 0.0799, "lr": 5.032668088433729e-06, "epoch": 1.438669956314086, "percentage": 79.45, "elapsed_time": "1 day, 1:58:31", "remaining_time": "6:43:07", "throughput": 554.98, "total_tokens": 51896816} {"current_steps": 31785, "total_steps": 40000, "loss": 0.1259, "lr": 5.02676207568814e-06, "epoch": 1.438896308200729, "percentage": 79.46, "elapsed_time": "1 day, 1:58:35", "remaining_time": "6:42:49", "throughput": 555.04, "total_tokens": 51904720} {"current_steps": 31790, "total_steps": 40000, "loss": 0.1291, "lr": 5.02085914306683e-06, "epoch": 1.4391226600873719, "percentage": 79.47, "elapsed_time": "1 day, 1:58:38", "remaining_time": "6:42:31", "throughput": 555.11, "total_tokens": 51912624} {"current_steps": 31795, "total_steps": 40000, "loss": 0.1385, "lr": 5.014959291480123e-06, "epoch": 1.4393490119740149, "percentage": 79.49, "elapsed_time": "1 day, 1:58:41", "remaining_time": "6:42:14", "throughput": 555.17, "total_tokens": 51920560} {"current_steps": 31800, "total_steps": 40000, "loss": 0.0685, "lr": 5.009062521837835e-06, "epoch": 1.4395753638606577, "percentage": 79.5, "elapsed_time": "1 day, 1:58:44", "remaining_time": "6:41:56", "throughput": 555.24, "total_tokens": 51928880} {"current_steps": 31800, "total_steps": 40000, "eval_loss": 0.12271899729967117, "epoch": 1.4395753638606577, "percentage": 79.5, "elapsed_time": "1 day, 2:06:27", "remaining_time": "6:43:55", "throughput": 552.51, "total_tokens": 51928880} {"current_steps": 31805, "total_steps": 40000, "loss": 0.1282, "lr": 5.003168835049324e-06, "epoch": 1.4398017157473006, "percentage": 79.51, "elapsed_time": "1 day, 2:06:31", "remaining_time": "6:43:38", "throughput": 552.58, "total_tokens": 51937552} {"current_steps": 31810, "total_steps": 40000, "loss": 0.0648, "lr": 4.997278232023483e-06, "epoch": 1.4400280676339436, "percentage": 79.53, "elapsed_time": "1 day, 2:06:34", "remaining_time": "6:43:20", "throughput": 552.64, "total_tokens": 51945520} {"current_steps": 31815, "total_steps": 40000, "loss": 0.1186, "lr": 4.9913907136687036e-06, "epoch": 1.4402544195205866, "percentage": 79.54, "elapsed_time": "1 day, 2:06:37", "remaining_time": "6:43:02", "throughput": 552.71, "total_tokens": 51953712} {"current_steps": 31820, "total_steps": 40000, "loss": 0.083, "lr": 4.985506280892918e-06, "epoch": 1.4404807714072296, "percentage": 79.55, "elapsed_time": "1 day, 2:06:41", "remaining_time": "6:42:44", "throughput": 552.78, "total_tokens": 51962320} {"current_steps": 31825, "total_steps": 40000, "loss": 0.1731, "lr": 4.979624934603589e-06, "epoch": 1.4407071232938726, "percentage": 79.56, "elapsed_time": "1 day, 2:06:44", "remaining_time": "6:42:27", "throughput": 552.85, "total_tokens": 51970576} {"current_steps": 31830, "total_steps": 40000, "loss": 0.0957, "lr": 4.97374667570768e-06, "epoch": 1.4409334751805156, "percentage": 79.57, "elapsed_time": "1 day, 2:06:47", "remaining_time": "6:42:09", "throughput": 552.93, "total_tokens": 51979248} {"current_steps": 31835, "total_steps": 40000, "loss": 0.1243, "lr": 4.967871505111704e-06, "epoch": 1.4411598270671586, "percentage": 79.59, "elapsed_time": "1 day, 2:06:50", "remaining_time": "6:41:51", "throughput": 552.99, "total_tokens": 51987280} {"current_steps": 31840, "total_steps": 40000, "loss": 0.102, "lr": 4.961999423721686e-06, "epoch": 1.4413861789538016, "percentage": 79.6, "elapsed_time": "1 day, 2:06:53", "remaining_time": "6:41:34", "throughput": 553.06, "total_tokens": 51995344} {"current_steps": 31845, "total_steps": 40000, "loss": 0.1159, "lr": 4.956130432443159e-06, "epoch": 1.4416125308404446, "percentage": 79.61, "elapsed_time": "1 day, 2:06:57", "remaining_time": "6:41:16", "throughput": 553.12, "total_tokens": 52003280} {"current_steps": 31850, "total_steps": 40000, "loss": 0.1005, "lr": 4.950264532181215e-06, "epoch": 1.4418388827270876, "percentage": 79.62, "elapsed_time": "1 day, 2:07:00", "remaining_time": "6:40:58", "throughput": 553.19, "total_tokens": 52011248} {"current_steps": 31855, "total_steps": 40000, "loss": 0.0815, "lr": 4.944401723840433e-06, "epoch": 1.4420652346137306, "percentage": 79.64, "elapsed_time": "1 day, 2:07:03", "remaining_time": "6:40:40", "throughput": 553.25, "total_tokens": 52018896} {"current_steps": 31860, "total_steps": 40000, "loss": 0.1227, "lr": 4.938542008324942e-06, "epoch": 1.4422915865003736, "percentage": 79.65, "elapsed_time": "1 day, 2:07:06", "remaining_time": "6:40:23", "throughput": 553.32, "total_tokens": 52026800} {"current_steps": 31865, "total_steps": 40000, "loss": 0.1175, "lr": 4.9326853865383855e-06, "epoch": 1.4425179383870166, "percentage": 79.66, "elapsed_time": "1 day, 2:07:10", "remaining_time": "6:40:05", "throughput": 553.39, "total_tokens": 52035120} {"current_steps": 31870, "total_steps": 40000, "loss": 0.0941, "lr": 4.926831859383918e-06, "epoch": 1.4427442902736594, "percentage": 79.67, "elapsed_time": "1 day, 2:07:13", "remaining_time": "6:39:47", "throughput": 553.46, "total_tokens": 52043376} {"current_steps": 31875, "total_steps": 40000, "loss": 0.1633, "lr": 4.92098142776424e-06, "epoch": 1.4429706421603024, "percentage": 79.69, "elapsed_time": "1 day, 2:07:16", "remaining_time": "6:39:30", "throughput": 553.52, "total_tokens": 52051248} {"current_steps": 31880, "total_steps": 40000, "loss": 0.1309, "lr": 4.91513409258155e-06, "epoch": 1.4431969940469453, "percentage": 79.7, "elapsed_time": "1 day, 2:07:19", "remaining_time": "6:39:12", "throughput": 553.59, "total_tokens": 52059408} {"current_steps": 31885, "total_steps": 40000, "loss": 0.1499, "lr": 4.909289854737581e-06, "epoch": 1.4434233459335883, "percentage": 79.71, "elapsed_time": "1 day, 2:07:22", "remaining_time": "6:38:54", "throughput": 553.65, "total_tokens": 52067088} {"current_steps": 31890, "total_steps": 40000, "loss": 0.0857, "lr": 4.903448715133602e-06, "epoch": 1.4436496978202313, "percentage": 79.72, "elapsed_time": "1 day, 2:07:25", "remaining_time": "6:38:36", "throughput": 553.72, "total_tokens": 52075152} {"current_steps": 31895, "total_steps": 40000, "loss": 0.1637, "lr": 4.897610674670372e-06, "epoch": 1.4438760497068743, "percentage": 79.74, "elapsed_time": "1 day, 2:07:29", "remaining_time": "6:38:19", "throughput": 553.79, "total_tokens": 52083632} {"current_steps": 31900, "total_steps": 40000, "loss": 0.1538, "lr": 4.8917757342482e-06, "epoch": 1.4441024015935173, "percentage": 79.75, "elapsed_time": "1 day, 2:07:32", "remaining_time": "6:38:01", "throughput": 553.86, "total_tokens": 52091888} {"current_steps": 31905, "total_steps": 40000, "loss": 0.0811, "lr": 4.885943894766909e-06, "epoch": 1.4443287534801603, "percentage": 79.76, "elapsed_time": "1 day, 2:07:35", "remaining_time": "6:37:43", "throughput": 553.93, "total_tokens": 52100336} {"current_steps": 31910, "total_steps": 40000, "loss": 0.1696, "lr": 4.880115157125842e-06, "epoch": 1.444555105366803, "percentage": 79.77, "elapsed_time": "1 day, 2:07:38", "remaining_time": "6:37:26", "throughput": 554.0, "total_tokens": 52108592} {"current_steps": 31915, "total_steps": 40000, "loss": 0.1084, "lr": 4.874289522223857e-06, "epoch": 1.444781457253446, "percentage": 79.79, "elapsed_time": "1 day, 2:07:42", "remaining_time": "6:37:08", "throughput": 554.07, "total_tokens": 52116528} {"current_steps": 31920, "total_steps": 40000, "loss": 0.2085, "lr": 4.868466990959339e-06, "epoch": 1.445007809140089, "percentage": 79.8, "elapsed_time": "1 day, 2:07:45", "remaining_time": "6:36:50", "throughput": 554.13, "total_tokens": 52124208} {"current_steps": 31925, "total_steps": 40000, "loss": 0.1297, "lr": 4.8626475642301964e-06, "epoch": 1.445234161026732, "percentage": 79.81, "elapsed_time": "1 day, 2:07:48", "remaining_time": "6:36:33", "throughput": 554.2, "total_tokens": 52132752} {"current_steps": 31930, "total_steps": 40000, "loss": 0.1361, "lr": 4.856831242933871e-06, "epoch": 1.445460512913375, "percentage": 79.83, "elapsed_time": "1 day, 2:07:51", "remaining_time": "6:36:15", "throughput": 554.26, "total_tokens": 52140368} {"current_steps": 31935, "total_steps": 40000, "loss": 0.1558, "lr": 4.851018027967294e-06, "epoch": 1.445686864800018, "percentage": 79.84, "elapsed_time": "1 day, 2:07:54", "remaining_time": "6:35:58", "throughput": 554.33, "total_tokens": 52148624} {"current_steps": 31940, "total_steps": 40000, "loss": 0.1557, "lr": 4.845207920226946e-06, "epoch": 1.445913216686661, "percentage": 79.85, "elapsed_time": "1 day, 2:07:57", "remaining_time": "6:35:40", "throughput": 554.4, "total_tokens": 52156816} {"current_steps": 31945, "total_steps": 40000, "loss": 0.1093, "lr": 4.839400920608825e-06, "epoch": 1.446139568573304, "percentage": 79.86, "elapsed_time": "1 day, 2:08:01", "remaining_time": "6:35:22", "throughput": 554.47, "total_tokens": 52165392} {"current_steps": 31950, "total_steps": 40000, "loss": 0.1771, "lr": 4.83359703000843e-06, "epoch": 1.446365920459947, "percentage": 79.88, "elapsed_time": "1 day, 2:08:04", "remaining_time": "6:35:05", "throughput": 554.54, "total_tokens": 52173744} {"current_steps": 31955, "total_steps": 40000, "loss": 0.1126, "lr": 4.827796249320804e-06, "epoch": 1.44659227234659, "percentage": 79.89, "elapsed_time": "1 day, 2:08:07", "remaining_time": "6:34:47", "throughput": 554.61, "total_tokens": 52181520} {"current_steps": 31960, "total_steps": 40000, "loss": 0.0937, "lr": 4.82199857944049e-06, "epoch": 1.446818624233233, "percentage": 79.9, "elapsed_time": "1 day, 2:08:10", "remaining_time": "6:34:29", "throughput": 554.67, "total_tokens": 52189104} {"current_steps": 31965, "total_steps": 40000, "loss": 0.1115, "lr": 4.8162040212615695e-06, "epoch": 1.447044976119876, "percentage": 79.91, "elapsed_time": "1 day, 2:08:14", "remaining_time": "6:34:12", "throughput": 554.74, "total_tokens": 52197296} {"current_steps": 31970, "total_steps": 40000, "loss": 0.1119, "lr": 4.810412575677639e-06, "epoch": 1.447271328006519, "percentage": 79.92, "elapsed_time": "1 day, 2:08:17", "remaining_time": "6:33:54", "throughput": 554.8, "total_tokens": 52205520} {"current_steps": 31975, "total_steps": 40000, "loss": 0.104, "lr": 4.804624243581801e-06, "epoch": 1.447497679893162, "percentage": 79.94, "elapsed_time": "1 day, 2:08:20", "remaining_time": "6:33:37", "throughput": 554.87, "total_tokens": 52213296} {"current_steps": 31980, "total_steps": 40000, "loss": 0.1636, "lr": 4.798839025866703e-06, "epoch": 1.447724031779805, "percentage": 79.95, "elapsed_time": "1 day, 2:08:23", "remaining_time": "6:33:19", "throughput": 554.94, "total_tokens": 52221392} {"current_steps": 31985, "total_steps": 40000, "loss": 0.1502, "lr": 4.793056923424491e-06, "epoch": 1.4479503836664478, "percentage": 79.96, "elapsed_time": "1 day, 2:08:26", "remaining_time": "6:33:01", "throughput": 555.0, "total_tokens": 52229328} {"current_steps": 31990, "total_steps": 40000, "loss": 0.0899, "lr": 4.78727793714683e-06, "epoch": 1.4481767355530908, "percentage": 79.97, "elapsed_time": "1 day, 2:08:29", "remaining_time": "6:32:44", "throughput": 555.07, "total_tokens": 52237744} {"current_steps": 31995, "total_steps": 40000, "loss": 0.1274, "lr": 4.7815020679249285e-06, "epoch": 1.4484030874397338, "percentage": 79.99, "elapsed_time": "1 day, 2:08:33", "remaining_time": "6:32:26", "throughput": 555.14, "total_tokens": 52246160} {"current_steps": 32000, "total_steps": 40000, "loss": 0.0833, "lr": 4.775729316649483e-06, "epoch": 1.4486294393263768, "percentage": 80.0, "elapsed_time": "1 day, 2:08:36", "remaining_time": "6:32:09", "throughput": 555.21, "total_tokens": 52254448} {"current_steps": 32000, "total_steps": 40000, "eval_loss": 0.12227338552474976, "epoch": 1.4486294393263768, "percentage": 80.0, "elapsed_time": "1 day, 2:16:19", "remaining_time": "6:34:04", "throughput": 552.49, "total_tokens": 52254448} {"current_steps": 32005, "total_steps": 40000, "loss": 0.0877, "lr": 4.769959684210728e-06, "epoch": 1.4488557912130198, "percentage": 80.01, "elapsed_time": "1 day, 2:16:23", "remaining_time": "6:33:47", "throughput": 552.56, "total_tokens": 52262640} {"current_steps": 32010, "total_steps": 40000, "loss": 0.1217, "lr": 4.764193171498426e-06, "epoch": 1.4490821430996628, "percentage": 80.03, "elapsed_time": "1 day, 2:16:26", "remaining_time": "6:33:29", "throughput": 552.63, "total_tokens": 52271536} {"current_steps": 32015, "total_steps": 40000, "loss": 0.1111, "lr": 4.75842977940183e-06, "epoch": 1.4493084949863058, "percentage": 80.04, "elapsed_time": "1 day, 2:16:29", "remaining_time": "6:33:12", "throughput": 552.7, "total_tokens": 52279952} {"current_steps": 32020, "total_steps": 40000, "loss": 0.0948, "lr": 4.752669508809729e-06, "epoch": 1.4495348468729488, "percentage": 80.05, "elapsed_time": "1 day, 2:16:33", "remaining_time": "6:32:54", "throughput": 552.78, "total_tokens": 52289008} {"current_steps": 32025, "total_steps": 40000, "loss": 0.1446, "lr": 4.746912360610445e-06, "epoch": 1.4497611987595915, "percentage": 80.06, "elapsed_time": "1 day, 2:16:36", "remaining_time": "6:32:36", "throughput": 552.85, "total_tokens": 52297200} {"current_steps": 32030, "total_steps": 40000, "loss": 0.1228, "lr": 4.741158335691781e-06, "epoch": 1.4499875506462345, "percentage": 80.08, "elapsed_time": "1 day, 2:16:39", "remaining_time": "6:32:19", "throughput": 552.92, "total_tokens": 52305712} {"current_steps": 32035, "total_steps": 40000, "loss": 0.13, "lr": 4.7354074349410994e-06, "epoch": 1.4502139025328775, "percentage": 80.09, "elapsed_time": "1 day, 2:16:42", "remaining_time": "6:32:01", "throughput": 552.98, "total_tokens": 52313840} {"current_steps": 32040, "total_steps": 40000, "loss": 0.1237, "lr": 4.729659659245245e-06, "epoch": 1.4504402544195205, "percentage": 80.1, "elapsed_time": "1 day, 2:16:45", "remaining_time": "6:31:43", "throughput": 553.06, "total_tokens": 52322320} {"current_steps": 32045, "total_steps": 40000, "loss": 0.1339, "lr": 4.723915009490601e-06, "epoch": 1.4506666063061635, "percentage": 80.11, "elapsed_time": "1 day, 2:16:49", "remaining_time": "6:31:26", "throughput": 553.12, "total_tokens": 52330096} {"current_steps": 32050, "total_steps": 40000, "loss": 0.1339, "lr": 4.718173486563077e-06, "epoch": 1.4508929581928065, "percentage": 80.12, "elapsed_time": "1 day, 2:16:52", "remaining_time": "6:31:08", "throughput": 553.19, "total_tokens": 52338704} {"current_steps": 32055, "total_steps": 40000, "loss": 0.107, "lr": 4.71243509134808e-06, "epoch": 1.4511193100794495, "percentage": 80.14, "elapsed_time": "1 day, 2:16:55", "remaining_time": "6:30:50", "throughput": 553.26, "total_tokens": 52346928} {"current_steps": 32060, "total_steps": 40000, "loss": 0.1455, "lr": 4.706699824730532e-06, "epoch": 1.4513456619660925, "percentage": 80.15, "elapsed_time": "1 day, 2:16:58", "remaining_time": "6:30:33", "throughput": 553.33, "total_tokens": 52354960} {"current_steps": 32065, "total_steps": 40000, "loss": 0.0936, "lr": 4.700967687594901e-06, "epoch": 1.4515720138527355, "percentage": 80.16, "elapsed_time": "1 day, 2:17:01", "remaining_time": "6:30:15", "throughput": 553.39, "total_tokens": 52362896} {"current_steps": 32070, "total_steps": 40000, "loss": 0.1306, "lr": 4.69523868082514e-06, "epoch": 1.4517983657393785, "percentage": 80.17, "elapsed_time": "1 day, 2:17:05", "remaining_time": "6:29:58", "throughput": 553.46, "total_tokens": 52371216} {"current_steps": 32075, "total_steps": 40000, "loss": 0.1009, "lr": 4.689512805304747e-06, "epoch": 1.4520247176260215, "percentage": 80.19, "elapsed_time": "1 day, 2:17:08", "remaining_time": "6:29:40", "throughput": 553.53, "total_tokens": 52379248} {"current_steps": 32080, "total_steps": 40000, "loss": 0.0977, "lr": 4.683790061916707e-06, "epoch": 1.4522510695126645, "percentage": 80.2, "elapsed_time": "1 day, 2:17:11", "remaining_time": "6:29:22", "throughput": 553.6, "total_tokens": 52387888} {"current_steps": 32085, "total_steps": 40000, "loss": 0.1433, "lr": 4.678070451543551e-06, "epoch": 1.4524774213993075, "percentage": 80.21, "elapsed_time": "1 day, 2:17:14", "remaining_time": "6:29:05", "throughput": 553.67, "total_tokens": 52396432} {"current_steps": 32090, "total_steps": 40000, "loss": 0.1186, "lr": 4.6723539750673204e-06, "epoch": 1.4527037732859505, "percentage": 80.23, "elapsed_time": "1 day, 2:17:18", "remaining_time": "6:28:47", "throughput": 553.74, "total_tokens": 52404848} {"current_steps": 32095, "total_steps": 40000, "loss": 0.1033, "lr": 4.666640633369551e-06, "epoch": 1.4529301251725932, "percentage": 80.24, "elapsed_time": "1 day, 2:17:21", "remaining_time": "6:28:30", "throughput": 553.81, "total_tokens": 52412880} {"current_steps": 32100, "total_steps": 40000, "loss": 0.0752, "lr": 4.660930427331323e-06, "epoch": 1.4531564770592362, "percentage": 80.25, "elapsed_time": "1 day, 2:17:24", "remaining_time": "6:28:12", "throughput": 553.87, "total_tokens": 52420560} {"current_steps": 32105, "total_steps": 40000, "loss": 0.1737, "lr": 4.6552233578332244e-06, "epoch": 1.4533828289458792, "percentage": 80.26, "elapsed_time": "1 day, 2:17:27", "remaining_time": "6:27:54", "throughput": 553.94, "total_tokens": 52428784} {"current_steps": 32110, "total_steps": 40000, "loss": 0.0834, "lr": 4.649519425755347e-06, "epoch": 1.4536091808325222, "percentage": 80.27, "elapsed_time": "1 day, 2:17:30", "remaining_time": "6:27:37", "throughput": 554.0, "total_tokens": 52437040} {"current_steps": 32115, "total_steps": 40000, "loss": 0.1229, "lr": 4.64381863197732e-06, "epoch": 1.4538355327191652, "percentage": 80.29, "elapsed_time": "1 day, 2:17:34", "remaining_time": "6:27:19", "throughput": 554.07, "total_tokens": 52444880} {"current_steps": 32120, "total_steps": 40000, "loss": 0.1463, "lr": 4.638120977378269e-06, "epoch": 1.4540618846058082, "percentage": 80.3, "elapsed_time": "1 day, 2:17:37", "remaining_time": "6:27:02", "throughput": 554.13, "total_tokens": 52452624} {"current_steps": 32125, "total_steps": 40000, "loss": 0.1148, "lr": 4.632426462836848e-06, "epoch": 1.4542882364924512, "percentage": 80.31, "elapsed_time": "1 day, 2:17:40", "remaining_time": "6:26:44", "throughput": 554.2, "total_tokens": 52461136} {"current_steps": 32130, "total_steps": 40000, "loss": 0.1207, "lr": 4.626735089231224e-06, "epoch": 1.4545145883790942, "percentage": 80.33, "elapsed_time": "1 day, 2:17:43", "remaining_time": "6:26:27", "throughput": 554.27, "total_tokens": 52469104} {"current_steps": 32135, "total_steps": 40000, "loss": 0.0977, "lr": 4.621046857439068e-06, "epoch": 1.4547409402657372, "percentage": 80.34, "elapsed_time": "1 day, 2:17:46", "remaining_time": "6:26:09", "throughput": 554.33, "total_tokens": 52476848} {"current_steps": 32140, "total_steps": 40000, "loss": 0.1119, "lr": 4.615361768337587e-06, "epoch": 1.45496729215238, "percentage": 80.35, "elapsed_time": "1 day, 2:17:49", "remaining_time": "6:25:52", "throughput": 554.4, "total_tokens": 52485072} {"current_steps": 32145, "total_steps": 40000, "loss": 0.1119, "lr": 4.6096798228034946e-06, "epoch": 1.455193644039023, "percentage": 80.36, "elapsed_time": "1 day, 2:17:53", "remaining_time": "6:25:34", "throughput": 554.48, "total_tokens": 52494032} {"current_steps": 32150, "total_steps": 40000, "loss": 0.0907, "lr": 4.604001021713008e-06, "epoch": 1.455419995925666, "percentage": 80.38, "elapsed_time": "1 day, 2:17:56", "remaining_time": "6:25:16", "throughput": 554.54, "total_tokens": 52501712} {"current_steps": 32155, "total_steps": 40000, "loss": 0.1558, "lr": 4.598325365941883e-06, "epoch": 1.455646347812309, "percentage": 80.39, "elapsed_time": "1 day, 2:17:59", "remaining_time": "6:24:59", "throughput": 554.61, "total_tokens": 52509968} {"current_steps": 32160, "total_steps": 40000, "loss": 0.13, "lr": 4.5926528563653645e-06, "epoch": 1.455872699698952, "percentage": 80.4, "elapsed_time": "1 day, 2:18:02", "remaining_time": "6:24:41", "throughput": 554.67, "total_tokens": 52518128} {"current_steps": 32165, "total_steps": 40000, "loss": 0.1196, "lr": 4.5869834938582295e-06, "epoch": 1.456099051585595, "percentage": 80.41, "elapsed_time": "1 day, 2:18:05", "remaining_time": "6:24:24", "throughput": 554.74, "total_tokens": 52526224} {"current_steps": 32170, "total_steps": 40000, "loss": 0.0968, "lr": 4.581317279294772e-06, "epoch": 1.456325403472238, "percentage": 80.42, "elapsed_time": "1 day, 2:18:09", "remaining_time": "6:24:06", "throughput": 554.81, "total_tokens": 52534160} {"current_steps": 32175, "total_steps": 40000, "loss": 0.0984, "lr": 4.57565421354878e-06, "epoch": 1.456551755358881, "percentage": 80.44, "elapsed_time": "1 day, 2:18:12", "remaining_time": "6:23:49", "throughput": 554.88, "total_tokens": 52543088} {"current_steps": 32180, "total_steps": 40000, "loss": 0.1286, "lr": 4.569994297493579e-06, "epoch": 1.456778107245524, "percentage": 80.45, "elapsed_time": "1 day, 2:18:15", "remaining_time": "6:23:31", "throughput": 554.95, "total_tokens": 52551184} {"current_steps": 32185, "total_steps": 40000, "loss": 0.121, "lr": 4.564337532002002e-06, "epoch": 1.457004459132167, "percentage": 80.46, "elapsed_time": "1 day, 2:18:18", "remaining_time": "6:23:14", "throughput": 555.02, "total_tokens": 52560240} {"current_steps": 32190, "total_steps": 40000, "loss": 0.1049, "lr": 4.55868391794638e-06, "epoch": 1.45723081101881, "percentage": 80.47, "elapsed_time": "1 day, 2:18:22", "remaining_time": "6:22:56", "throughput": 555.09, "total_tokens": 52568016} {"current_steps": 32195, "total_steps": 40000, "loss": 0.1235, "lr": 4.553033456198588e-06, "epoch": 1.457457162905453, "percentage": 80.49, "elapsed_time": "1 day, 2:18:25", "remaining_time": "6:22:39", "throughput": 555.16, "total_tokens": 52576656} {"current_steps": 32200, "total_steps": 40000, "loss": 0.1098, "lr": 4.54738614762999e-06, "epoch": 1.457683514792096, "percentage": 80.5, "elapsed_time": "1 day, 2:18:28", "remaining_time": "6:22:21", "throughput": 555.23, "total_tokens": 52584816} {"current_steps": 32200, "total_steps": 40000, "eval_loss": 0.12241945415735245, "epoch": 1.457683514792096, "percentage": 80.5, "elapsed_time": "1 day, 2:26:11", "remaining_time": "6:24:13", "throughput": 552.53, "total_tokens": 52584816} {"current_steps": 32205, "total_steps": 40000, "loss": 0.1146, "lr": 4.541741993111465e-06, "epoch": 1.457909866678739, "percentage": 80.51, "elapsed_time": "1 day, 2:26:15", "remaining_time": "6:23:56", "throughput": 552.59, "total_tokens": 52593232} {"current_steps": 32210, "total_steps": 40000, "loss": 0.0998, "lr": 4.536100993513423e-06, "epoch": 1.4581362185653817, "percentage": 80.53, "elapsed_time": "1 day, 2:26:18", "remaining_time": "6:23:38", "throughput": 552.66, "total_tokens": 52601200} {"current_steps": 32215, "total_steps": 40000, "loss": 0.1233, "lr": 4.530463149705768e-06, "epoch": 1.4583625704520247, "percentage": 80.54, "elapsed_time": "1 day, 2:26:21", "remaining_time": "6:23:21", "throughput": 552.73, "total_tokens": 52609648} {"current_steps": 32220, "total_steps": 40000, "loss": 0.0931, "lr": 4.524828462557934e-06, "epoch": 1.4585889223386677, "percentage": 80.55, "elapsed_time": "1 day, 2:26:25", "remaining_time": "6:23:03", "throughput": 552.8, "total_tokens": 52618224} {"current_steps": 32225, "total_steps": 40000, "loss": 0.1497, "lr": 4.5191969329388625e-06, "epoch": 1.4588152742253107, "percentage": 80.56, "elapsed_time": "1 day, 2:26:28", "remaining_time": "6:22:46", "throughput": 552.87, "total_tokens": 52627120} {"current_steps": 32230, "total_steps": 40000, "loss": 0.0618, "lr": 4.5135685617169965e-06, "epoch": 1.4590416261119536, "percentage": 80.58, "elapsed_time": "1 day, 2:26:31", "remaining_time": "6:22:28", "throughput": 552.94, "total_tokens": 52635024} {"current_steps": 32235, "total_steps": 40000, "loss": 0.1528, "lr": 4.507943349760313e-06, "epoch": 1.4592679779985966, "percentage": 80.59, "elapsed_time": "1 day, 2:26:34", "remaining_time": "6:22:11", "throughput": 553.01, "total_tokens": 52643632} {"current_steps": 32240, "total_steps": 40000, "loss": 0.1005, "lr": 4.502321297936277e-06, "epoch": 1.4594943298852396, "percentage": 80.6, "elapsed_time": "1 day, 2:26:38", "remaining_time": "6:21:53", "throughput": 553.08, "total_tokens": 52652144} {"current_steps": 32245, "total_steps": 40000, "loss": 0.0925, "lr": 4.496702407111888e-06, "epoch": 1.4597206817718826, "percentage": 80.61, "elapsed_time": "1 day, 2:26:41", "remaining_time": "6:21:36", "throughput": 553.14, "total_tokens": 52659664} {"current_steps": 32250, "total_steps": 40000, "loss": 0.1019, "lr": 4.491086678153653e-06, "epoch": 1.4599470336585254, "percentage": 80.62, "elapsed_time": "1 day, 2:26:44", "remaining_time": "6:21:18", "throughput": 553.21, "total_tokens": 52667760} {"current_steps": 32255, "total_steps": 40000, "loss": 0.12, "lr": 4.485474111927579e-06, "epoch": 1.4601733855451684, "percentage": 80.64, "elapsed_time": "1 day, 2:26:47", "remaining_time": "6:21:01", "throughput": 553.27, "total_tokens": 52675344} {"current_steps": 32260, "total_steps": 40000, "loss": 0.0995, "lr": 4.479864709299197e-06, "epoch": 1.4603997374318114, "percentage": 80.65, "elapsed_time": "1 day, 2:26:50", "remaining_time": "6:20:43", "throughput": 553.34, "total_tokens": 52683632} {"current_steps": 32265, "total_steps": 40000, "loss": 0.1474, "lr": 4.474258471133555e-06, "epoch": 1.4606260893184544, "percentage": 80.66, "elapsed_time": "1 day, 2:26:53", "remaining_time": "6:20:25", "throughput": 553.4, "total_tokens": 52691536} {"current_steps": 32270, "total_steps": 40000, "loss": 0.1136, "lr": 4.4686553982952014e-06, "epoch": 1.4608524412050974, "percentage": 80.67, "elapsed_time": "1 day, 2:26:57", "remaining_time": "6:20:08", "throughput": 553.47, "total_tokens": 52699408} {"current_steps": 32275, "total_steps": 40000, "loss": 0.1263, "lr": 4.463055491648191e-06, "epoch": 1.4610787930917404, "percentage": 80.69, "elapsed_time": "1 day, 2:27:00", "remaining_time": "6:19:50", "throughput": 553.53, "total_tokens": 52707056} {"current_steps": 32280, "total_steps": 40000, "loss": 0.1471, "lr": 4.457458752056112e-06, "epoch": 1.4613051449783834, "percentage": 80.7, "elapsed_time": "1 day, 2:27:03", "remaining_time": "6:19:33", "throughput": 553.59, "total_tokens": 52715088} {"current_steps": 32285, "total_steps": 40000, "loss": 0.1643, "lr": 4.451865180382042e-06, "epoch": 1.4615314968650264, "percentage": 80.71, "elapsed_time": "1 day, 2:27:06", "remaining_time": "6:19:15", "throughput": 553.66, "total_tokens": 52722832} {"current_steps": 32290, "total_steps": 40000, "loss": 0.1476, "lr": 4.4462747774885936e-06, "epoch": 1.4617578487516694, "percentage": 80.73, "elapsed_time": "1 day, 2:27:09", "remaining_time": "6:18:58", "throughput": 553.73, "total_tokens": 52731120} {"current_steps": 32295, "total_steps": 40000, "loss": 0.1386, "lr": 4.440687544237859e-06, "epoch": 1.4619842006383124, "percentage": 80.74, "elapsed_time": "1 day, 2:27:12", "remaining_time": "6:18:40", "throughput": 553.79, "total_tokens": 52739248} {"current_steps": 32300, "total_steps": 40000, "loss": 0.102, "lr": 4.435103481491471e-06, "epoch": 1.4622105525249554, "percentage": 80.75, "elapsed_time": "1 day, 2:27:16", "remaining_time": "6:18:23", "throughput": 553.86, "total_tokens": 52747920} {"current_steps": 32305, "total_steps": 40000, "loss": 0.1464, "lr": 4.429522590110569e-06, "epoch": 1.4624369044115983, "percentage": 80.76, "elapsed_time": "1 day, 2:27:19", "remaining_time": "6:18:05", "throughput": 553.93, "total_tokens": 52756176} {"current_steps": 32310, "total_steps": 40000, "loss": 0.1222, "lr": 4.423944870955779e-06, "epoch": 1.4626632562982413, "percentage": 80.77, "elapsed_time": "1 day, 2:27:22", "remaining_time": "6:17:48", "throughput": 554.0, "total_tokens": 52764432} {"current_steps": 32315, "total_steps": 40000, "loss": 0.1668, "lr": 4.418370324887272e-06, "epoch": 1.4628896081848843, "percentage": 80.79, "elapsed_time": "1 day, 2:27:25", "remaining_time": "6:17:30", "throughput": 554.06, "total_tokens": 52772400} {"current_steps": 32320, "total_steps": 40000, "loss": 0.1016, "lr": 4.412798952764699e-06, "epoch": 1.4631159600715273, "percentage": 80.8, "elapsed_time": "1 day, 2:27:29", "remaining_time": "6:17:13", "throughput": 554.14, "total_tokens": 52781264} {"current_steps": 32325, "total_steps": 40000, "loss": 0.1053, "lr": 4.407230755447245e-06, "epoch": 1.46334231195817, "percentage": 80.81, "elapsed_time": "1 day, 2:27:32", "remaining_time": "6:16:56", "throughput": 554.21, "total_tokens": 52790096} {"current_steps": 32330, "total_steps": 40000, "loss": 0.0618, "lr": 4.401665733793598e-06, "epoch": 1.463568663844813, "percentage": 80.83, "elapsed_time": "1 day, 2:27:35", "remaining_time": "6:16:38", "throughput": 554.27, "total_tokens": 52797808} {"current_steps": 32335, "total_steps": 40000, "loss": 0.0918, "lr": 4.3961038886619425e-06, "epoch": 1.463795015731456, "percentage": 80.84, "elapsed_time": "1 day, 2:27:38", "remaining_time": "6:16:21", "throughput": 554.34, "total_tokens": 52805872} {"current_steps": 32340, "total_steps": 40000, "loss": 0.114, "lr": 4.39054522091e-06, "epoch": 1.464021367618099, "percentage": 80.85, "elapsed_time": "1 day, 2:27:41", "remaining_time": "6:16:03", "throughput": 554.41, "total_tokens": 52813712} {"current_steps": 32345, "total_steps": 40000, "loss": 0.0575, "lr": 4.384989731394979e-06, "epoch": 1.464247719504742, "percentage": 80.86, "elapsed_time": "1 day, 2:27:45", "remaining_time": "6:15:46", "throughput": 554.47, "total_tokens": 52821936} {"current_steps": 32350, "total_steps": 40000, "loss": 0.1584, "lr": 4.379437420973598e-06, "epoch": 1.464474071391385, "percentage": 80.88, "elapsed_time": "1 day, 2:27:48", "remaining_time": "6:15:28", "throughput": 554.53, "total_tokens": 52829392} {"current_steps": 32355, "total_steps": 40000, "loss": 0.1143, "lr": 4.373888290502107e-06, "epoch": 1.464700423278028, "percentage": 80.89, "elapsed_time": "1 day, 2:27:51", "remaining_time": "6:15:11", "throughput": 554.59, "total_tokens": 52837008} {"current_steps": 32360, "total_steps": 40000, "loss": 0.1244, "lr": 4.36834234083624e-06, "epoch": 1.464926775164671, "percentage": 80.9, "elapsed_time": "1 day, 2:27:54", "remaining_time": "6:14:53", "throughput": 554.66, "total_tokens": 52844848} {"current_steps": 32365, "total_steps": 40000, "loss": 0.1542, "lr": 4.362799572831258e-06, "epoch": 1.4651531270513138, "percentage": 80.91, "elapsed_time": "1 day, 2:27:57", "remaining_time": "6:14:36", "throughput": 554.72, "total_tokens": 52852720} {"current_steps": 32370, "total_steps": 40000, "loss": 0.0995, "lr": 4.35725998734193e-06, "epoch": 1.4653794789379568, "percentage": 80.92, "elapsed_time": "1 day, 2:28:00", "remaining_time": "6:14:18", "throughput": 554.79, "total_tokens": 52860912} {"current_steps": 32375, "total_steps": 40000, "loss": 0.0931, "lr": 4.3517235852225195e-06, "epoch": 1.4656058308245998, "percentage": 80.94, "elapsed_time": "1 day, 2:28:03", "remaining_time": "6:14:01", "throughput": 554.85, "total_tokens": 52868688} {"current_steps": 32380, "total_steps": 40000, "loss": 0.1359, "lr": 4.346190367326822e-06, "epoch": 1.4658321827112428, "percentage": 80.95, "elapsed_time": "1 day, 2:28:07", "remaining_time": "6:13:44", "throughput": 554.92, "total_tokens": 52877168} {"current_steps": 32385, "total_steps": 40000, "loss": 0.1198, "lr": 4.340660334508115e-06, "epoch": 1.4660585345978858, "percentage": 80.96, "elapsed_time": "1 day, 2:28:10", "remaining_time": "6:13:26", "throughput": 554.99, "total_tokens": 52885200} {"current_steps": 32390, "total_steps": 40000, "loss": 0.0988, "lr": 4.335133487619206e-06, "epoch": 1.4662848864845288, "percentage": 80.97, "elapsed_time": "1 day, 2:28:13", "remaining_time": "6:13:09", "throughput": 555.05, "total_tokens": 52892560} {"current_steps": 32395, "total_steps": 40000, "loss": 0.1653, "lr": 4.329609827512409e-06, "epoch": 1.4665112383711718, "percentage": 80.99, "elapsed_time": "1 day, 2:28:16", "remaining_time": "6:12:51", "throughput": 555.12, "total_tokens": 52900656} {"current_steps": 32400, "total_steps": 40000, "loss": 0.067, "lr": 4.324089355039531e-06, "epoch": 1.4667375902578148, "percentage": 81.0, "elapsed_time": "1 day, 2:28:19", "remaining_time": "6:12:34", "throughput": 555.19, "total_tokens": 52909264} {"current_steps": 32400, "total_steps": 40000, "eval_loss": 0.12217503786087036, "epoch": 1.4667375902578148, "percentage": 81.0, "elapsed_time": "1 day, 2:36:02", "remaining_time": "6:14:22", "throughput": 552.5, "total_tokens": 52909264} {"current_steps": 32405, "total_steps": 40000, "loss": 0.1047, "lr": 4.3185720710519075e-06, "epoch": 1.4669639421444578, "percentage": 81.01, "elapsed_time": "1 day, 2:36:06", "remaining_time": "6:14:05", "throughput": 552.56, "total_tokens": 52917168} {"current_steps": 32410, "total_steps": 40000, "loss": 0.1388, "lr": 4.3130579764003724e-06, "epoch": 1.4671902940311008, "percentage": 81.03, "elapsed_time": "1 day, 2:36:10", "remaining_time": "6:13:48", "throughput": 552.63, "total_tokens": 52925040} {"current_steps": 32415, "total_steps": 40000, "loss": 0.1801, "lr": 4.307547071935267e-06, "epoch": 1.4674166459177438, "percentage": 81.04, "elapsed_time": "1 day, 2:36:13", "remaining_time": "6:13:30", "throughput": 552.7, "total_tokens": 52933776} {"current_steps": 32420, "total_steps": 40000, "loss": 0.1192, "lr": 4.302039358506435e-06, "epoch": 1.4676429978043868, "percentage": 81.05, "elapsed_time": "1 day, 2:36:16", "remaining_time": "6:13:13", "throughput": 552.76, "total_tokens": 52941616} {"current_steps": 32425, "total_steps": 40000, "loss": 0.1116, "lr": 4.296534836963245e-06, "epoch": 1.4678693496910298, "percentage": 81.06, "elapsed_time": "1 day, 2:36:19", "remaining_time": "6:12:55", "throughput": 552.83, "total_tokens": 52950288} {"current_steps": 32430, "total_steps": 40000, "loss": 0.1294, "lr": 4.291033508154555e-06, "epoch": 1.4680957015776728, "percentage": 81.08, "elapsed_time": "1 day, 2:36:22", "remaining_time": "6:12:38", "throughput": 552.9, "total_tokens": 52958064} {"current_steps": 32435, "total_steps": 40000, "loss": 0.103, "lr": 4.285535372928748e-06, "epoch": 1.4683220534643155, "percentage": 81.09, "elapsed_time": "1 day, 2:36:26", "remaining_time": "6:12:20", "throughput": 552.96, "total_tokens": 52965968} {"current_steps": 32440, "total_steps": 40000, "loss": 0.1129, "lr": 4.280040432133695e-06, "epoch": 1.4685484053509585, "percentage": 81.1, "elapsed_time": "1 day, 2:36:29", "remaining_time": "6:12:03", "throughput": 553.03, "total_tokens": 52974384} {"current_steps": 32445, "total_steps": 40000, "loss": 0.0833, "lr": 4.274548686616789e-06, "epoch": 1.4687747572376015, "percentage": 81.11, "elapsed_time": "1 day, 2:36:32", "remaining_time": "6:11:45", "throughput": 553.1, "total_tokens": 52982416} {"current_steps": 32450, "total_steps": 40000, "loss": 0.1693, "lr": 4.2690601372249364e-06, "epoch": 1.4690011091242445, "percentage": 81.12, "elapsed_time": "1 day, 2:36:35", "remaining_time": "6:11:28", "throughput": 553.16, "total_tokens": 52990768} {"current_steps": 32455, "total_steps": 40000, "loss": 0.1059, "lr": 4.263574784804525e-06, "epoch": 1.4692274610108875, "percentage": 81.14, "elapsed_time": "1 day, 2:36:38", "remaining_time": "6:11:10", "throughput": 553.23, "total_tokens": 52998800} {"current_steps": 32460, "total_steps": 40000, "loss": 0.1297, "lr": 4.258092630201479e-06, "epoch": 1.4694538128975305, "percentage": 81.15, "elapsed_time": "1 day, 2:36:42", "remaining_time": "6:10:53", "throughput": 553.3, "total_tokens": 53006960} {"current_steps": 32465, "total_steps": 40000, "loss": 0.1253, "lr": 4.252613674261202e-06, "epoch": 1.4696801647841735, "percentage": 81.16, "elapsed_time": "1 day, 2:36:45", "remaining_time": "6:10:36", "throughput": 553.37, "total_tokens": 53015824} {"current_steps": 32470, "total_steps": 40000, "loss": 0.0845, "lr": 4.2471379178286224e-06, "epoch": 1.4699065166708165, "percentage": 81.17, "elapsed_time": "1 day, 2:36:48", "remaining_time": "6:10:18", "throughput": 553.44, "total_tokens": 53024208} {"current_steps": 32475, "total_steps": 40000, "loss": 0.0839, "lr": 4.241665361748181e-06, "epoch": 1.4701328685574595, "percentage": 81.19, "elapsed_time": "1 day, 2:36:51", "remaining_time": "6:10:01", "throughput": 553.5, "total_tokens": 53032368} {"current_steps": 32480, "total_steps": 40000, "loss": 0.1245, "lr": 4.2361960068637994e-06, "epoch": 1.4703592204441023, "percentage": 81.2, "elapsed_time": "1 day, 2:36:55", "remaining_time": "6:09:43", "throughput": 553.57, "total_tokens": 53040208} {"current_steps": 32485, "total_steps": 40000, "loss": 0.0997, "lr": 4.230729854018933e-06, "epoch": 1.4705855723307453, "percentage": 81.21, "elapsed_time": "1 day, 2:36:58", "remaining_time": "6:09:26", "throughput": 553.64, "total_tokens": 53048912} {"current_steps": 32490, "total_steps": 40000, "loss": 0.1406, "lr": 4.225266904056521e-06, "epoch": 1.4708119242173883, "percentage": 81.23, "elapsed_time": "1 day, 2:37:01", "remaining_time": "6:09:09", "throughput": 553.71, "total_tokens": 53057136} {"current_steps": 32495, "total_steps": 40000, "loss": 0.1144, "lr": 4.21980715781903e-06, "epoch": 1.4710382761040313, "percentage": 81.24, "elapsed_time": "1 day, 2:37:05", "remaining_time": "6:08:51", "throughput": 553.77, "total_tokens": 53064752} {"current_steps": 32500, "total_steps": 40000, "loss": 0.1272, "lr": 4.214350616148416e-06, "epoch": 1.4712646279906743, "percentage": 81.25, "elapsed_time": "1 day, 2:37:08", "remaining_time": "6:08:34", "throughput": 553.84, "total_tokens": 53073680} {"current_steps": 32505, "total_steps": 40000, "loss": 0.1431, "lr": 4.20889727988614e-06, "epoch": 1.4714909798773173, "percentage": 81.26, "elapsed_time": "1 day, 2:37:11", "remaining_time": "6:08:16", "throughput": 553.9, "total_tokens": 53081296} {"current_steps": 32510, "total_steps": 40000, "loss": 0.1104, "lr": 4.20344714987318e-06, "epoch": 1.4717173317639602, "percentage": 81.27, "elapsed_time": "1 day, 2:37:14", "remaining_time": "6:07:59", "throughput": 553.97, "total_tokens": 53089648} {"current_steps": 32515, "total_steps": 40000, "loss": 0.1272, "lr": 4.198000226950022e-06, "epoch": 1.4719436836506032, "percentage": 81.29, "elapsed_time": "1 day, 2:37:17", "remaining_time": "6:07:42", "throughput": 554.04, "total_tokens": 53097552} {"current_steps": 32520, "total_steps": 40000, "loss": 0.123, "lr": 4.192556511956635e-06, "epoch": 1.4721700355372462, "percentage": 81.3, "elapsed_time": "1 day, 2:37:21", "remaining_time": "6:07:24", "throughput": 554.1, "total_tokens": 53105360} {"current_steps": 32525, "total_steps": 40000, "loss": 0.1781, "lr": 4.18711600573252e-06, "epoch": 1.4723963874238892, "percentage": 81.31, "elapsed_time": "1 day, 2:37:24", "remaining_time": "6:07:07", "throughput": 554.17, "total_tokens": 53113616} {"current_steps": 32530, "total_steps": 40000, "loss": 0.0939, "lr": 4.181678709116671e-06, "epoch": 1.4726227393105322, "percentage": 81.33, "elapsed_time": "1 day, 2:37:27", "remaining_time": "6:06:49", "throughput": 554.23, "total_tokens": 53121456} {"current_steps": 32535, "total_steps": 40000, "loss": 0.0749, "lr": 4.1762446229475785e-06, "epoch": 1.4728490911971752, "percentage": 81.34, "elapsed_time": "1 day, 2:37:30", "remaining_time": "6:06:32", "throughput": 554.29, "total_tokens": 53129392} {"current_steps": 32540, "total_steps": 40000, "loss": 0.1037, "lr": 4.17081374806326e-06, "epoch": 1.4730754430838182, "percentage": 81.35, "elapsed_time": "1 day, 2:37:33", "remaining_time": "6:06:15", "throughput": 554.36, "total_tokens": 53137552} {"current_steps": 32545, "total_steps": 40000, "loss": 0.1533, "lr": 4.165386085301212e-06, "epoch": 1.4733017949704612, "percentage": 81.36, "elapsed_time": "1 day, 2:37:36", "remaining_time": "6:05:57", "throughput": 554.43, "total_tokens": 53145968} {"current_steps": 32550, "total_steps": 40000, "loss": 0.1351, "lr": 4.1599616354984525e-06, "epoch": 1.473528146857104, "percentage": 81.38, "elapsed_time": "1 day, 2:37:40", "remaining_time": "6:05:40", "throughput": 554.49, "total_tokens": 53153392} {"current_steps": 32555, "total_steps": 40000, "loss": 0.1514, "lr": 4.154540399491508e-06, "epoch": 1.473754498743747, "percentage": 81.39, "elapsed_time": "1 day, 2:37:43", "remaining_time": "6:05:22", "throughput": 554.56, "total_tokens": 53161968} {"current_steps": 32560, "total_steps": 40000, "loss": 0.1189, "lr": 4.149122378116394e-06, "epoch": 1.47398085063039, "percentage": 81.4, "elapsed_time": "1 day, 2:37:46", "remaining_time": "6:05:05", "throughput": 554.62, "total_tokens": 53169648} {"current_steps": 32565, "total_steps": 40000, "loss": 0.1098, "lr": 4.14370757220863e-06, "epoch": 1.474207202517033, "percentage": 81.41, "elapsed_time": "1 day, 2:37:49", "remaining_time": "6:04:48", "throughput": 554.68, "total_tokens": 53177328} {"current_steps": 32570, "total_steps": 40000, "loss": 0.1138, "lr": 4.138295982603263e-06, "epoch": 1.474433554403676, "percentage": 81.42, "elapsed_time": "1 day, 2:37:52", "remaining_time": "6:04:30", "throughput": 554.76, "total_tokens": 53186096} {"current_steps": 32575, "total_steps": 40000, "loss": 0.0895, "lr": 4.132887610134814e-06, "epoch": 1.474659906290319, "percentage": 81.44, "elapsed_time": "1 day, 2:37:56", "remaining_time": "6:04:13", "throughput": 554.82, "total_tokens": 53194352} {"current_steps": 32580, "total_steps": 40000, "loss": 0.1956, "lr": 4.127482455637335e-06, "epoch": 1.474886258176962, "percentage": 81.45, "elapsed_time": "1 day, 2:37:59", "remaining_time": "6:03:56", "throughput": 554.89, "total_tokens": 53202096} {"current_steps": 32585, "total_steps": 40000, "loss": 0.1102, "lr": 4.1220805199443545e-06, "epoch": 1.475112610063605, "percentage": 81.46, "elapsed_time": "1 day, 2:38:02", "remaining_time": "6:03:38", "throughput": 554.97, "total_tokens": 53211728} {"current_steps": 32590, "total_steps": 40000, "loss": 0.1246, "lr": 4.116681803888925e-06, "epoch": 1.4753389619502477, "percentage": 81.47, "elapsed_time": "1 day, 2:38:06", "remaining_time": "6:03:21", "throughput": 555.04, "total_tokens": 53220816} {"current_steps": 32595, "total_steps": 40000, "loss": 0.0785, "lr": 4.111286308303605e-06, "epoch": 1.4755653138368907, "percentage": 81.49, "elapsed_time": "1 day, 2:38:09", "remaining_time": "6:03:04", "throughput": 555.11, "total_tokens": 53228976} {"current_steps": 32600, "total_steps": 40000, "loss": 0.1011, "lr": 4.105894034020433e-06, "epoch": 1.4757916657235337, "percentage": 81.5, "elapsed_time": "1 day, 2:38:12", "remaining_time": "6:02:47", "throughput": 555.18, "total_tokens": 53237136} {"current_steps": 32600, "total_steps": 40000, "eval_loss": 0.12217165529727936, "epoch": 1.4757916657235337, "percentage": 81.5, "elapsed_time": "1 day, 2:45:55", "remaining_time": "6:04:32", "throughput": 552.51, "total_tokens": 53237136} {"current_steps": 32605, "total_steps": 40000, "loss": 0.0742, "lr": 4.100504981870975e-06, "epoch": 1.4760180176101767, "percentage": 81.51, "elapsed_time": "1 day, 2:45:59", "remaining_time": "6:04:14", "throughput": 552.57, "total_tokens": 53245264} {"current_steps": 32610, "total_steps": 40000, "loss": 0.1256, "lr": 4.0951191526862915e-06, "epoch": 1.4762443694968197, "percentage": 81.53, "elapsed_time": "1 day, 2:46:02", "remaining_time": "6:03:57", "throughput": 552.63, "total_tokens": 53252976} {"current_steps": 32615, "total_steps": 40000, "loss": 0.1952, "lr": 4.089736547296938e-06, "epoch": 1.4764707213834627, "percentage": 81.54, "elapsed_time": "1 day, 2:46:05", "remaining_time": "6:03:40", "throughput": 552.7, "total_tokens": 53261264} {"current_steps": 32620, "total_steps": 40000, "loss": 0.1693, "lr": 4.08435716653299e-06, "epoch": 1.4766970732701057, "percentage": 81.55, "elapsed_time": "1 day, 2:46:09", "remaining_time": "6:03:22", "throughput": 552.76, "total_tokens": 53269360} {"current_steps": 32625, "total_steps": 40000, "loss": 0.1368, "lr": 4.0789810112240005e-06, "epoch": 1.4769234251567487, "percentage": 81.56, "elapsed_time": "1 day, 2:46:12", "remaining_time": "6:03:05", "throughput": 552.83, "total_tokens": 53277360} {"current_steps": 32630, "total_steps": 40000, "loss": 0.1355, "lr": 4.073608082199057e-06, "epoch": 1.4771497770433917, "percentage": 81.58, "elapsed_time": "1 day, 2:46:15", "remaining_time": "6:02:47", "throughput": 552.89, "total_tokens": 53285104} {"current_steps": 32635, "total_steps": 40000, "loss": 0.1238, "lr": 4.068238380286718e-06, "epoch": 1.4773761289300347, "percentage": 81.59, "elapsed_time": "1 day, 2:46:18", "remaining_time": "6:02:30", "throughput": 552.96, "total_tokens": 53293744} {"current_steps": 32640, "total_steps": 40000, "loss": 0.1033, "lr": 4.062871906315072e-06, "epoch": 1.4776024808166777, "percentage": 81.6, "elapsed_time": "1 day, 2:46:21", "remaining_time": "6:02:13", "throughput": 553.04, "total_tokens": 53302608} {"current_steps": 32645, "total_steps": 40000, "loss": 0.0791, "lr": 4.057508661111686e-06, "epoch": 1.4778288327033207, "percentage": 81.61, "elapsed_time": "1 day, 2:46:25", "remaining_time": "6:01:55", "throughput": 553.1, "total_tokens": 53311056} {"current_steps": 32650, "total_steps": 40000, "loss": 0.1039, "lr": 4.052148645503648e-06, "epoch": 1.4780551845899637, "percentage": 81.62, "elapsed_time": "1 day, 2:46:28", "remaining_time": "6:01:38", "throughput": 553.17, "total_tokens": 53319504} {"current_steps": 32655, "total_steps": 40000, "loss": 0.074, "lr": 4.046791860317531e-06, "epoch": 1.4782815364766067, "percentage": 81.64, "elapsed_time": "1 day, 2:46:31", "remaining_time": "6:01:21", "throughput": 553.23, "total_tokens": 53326992} {"current_steps": 32660, "total_steps": 40000, "loss": 0.1034, "lr": 4.041438306379431e-06, "epoch": 1.4785078883632496, "percentage": 81.65, "elapsed_time": "1 day, 2:46:34", "remaining_time": "6:01:03", "throughput": 553.29, "total_tokens": 53334704} {"current_steps": 32665, "total_steps": 40000, "loss": 0.1307, "lr": 4.036087984514916e-06, "epoch": 1.4787342402498924, "percentage": 81.66, "elapsed_time": "1 day, 2:46:38", "remaining_time": "6:00:46", "throughput": 553.37, "total_tokens": 53343344} {"current_steps": 32670, "total_steps": 40000, "loss": 0.2052, "lr": 4.030740895549084e-06, "epoch": 1.4789605921365354, "percentage": 81.67, "elapsed_time": "1 day, 2:46:41", "remaining_time": "6:00:29", "throughput": 553.43, "total_tokens": 53351408} {"current_steps": 32675, "total_steps": 40000, "loss": 0.1248, "lr": 4.025397040306531e-06, "epoch": 1.4791869440231784, "percentage": 81.69, "elapsed_time": "1 day, 2:46:44", "remaining_time": "6:00:11", "throughput": 553.49, "total_tokens": 53359120} {"current_steps": 32680, "total_steps": 40000, "loss": 0.0787, "lr": 4.0200564196113285e-06, "epoch": 1.4794132959098214, "percentage": 81.7, "elapsed_time": "1 day, 2:46:47", "remaining_time": "5:59:54", "throughput": 553.56, "total_tokens": 53367152} {"current_steps": 32685, "total_steps": 40000, "loss": 0.0912, "lr": 4.014719034287079e-06, "epoch": 1.4796396477964644, "percentage": 81.71, "elapsed_time": "1 day, 2:46:51", "remaining_time": "5:59:37", "throughput": 553.63, "total_tokens": 53376112} {"current_steps": 32690, "total_steps": 40000, "loss": 0.1007, "lr": 4.0093848851568775e-06, "epoch": 1.4798659996831074, "percentage": 81.73, "elapsed_time": "1 day, 2:46:54", "remaining_time": "5:59:19", "throughput": 553.69, "total_tokens": 53383984} {"current_steps": 32695, "total_steps": 40000, "loss": 0.1573, "lr": 4.004053973043304e-06, "epoch": 1.4800923515697504, "percentage": 81.74, "elapsed_time": "1 day, 2:46:57", "remaining_time": "5:59:02", "throughput": 553.76, "total_tokens": 53392112} {"current_steps": 32700, "total_steps": 40000, "loss": 0.1182, "lr": 3.998726298768465e-06, "epoch": 1.4803187034563934, "percentage": 81.75, "elapsed_time": "1 day, 2:47:00", "remaining_time": "5:58:45", "throughput": 553.83, "total_tokens": 53400816} {"current_steps": 32705, "total_steps": 40000, "loss": 0.084, "lr": 3.99340186315395e-06, "epoch": 1.4805450553430362, "percentage": 81.76, "elapsed_time": "1 day, 2:47:03", "remaining_time": "5:58:27", "throughput": 553.89, "total_tokens": 53408592} {"current_steps": 32710, "total_steps": 40000, "loss": 0.1165, "lr": 3.988080667020849e-06, "epoch": 1.4807714072296791, "percentage": 81.77, "elapsed_time": "1 day, 2:47:07", "remaining_time": "5:58:10", "throughput": 553.96, "total_tokens": 53416848} {"current_steps": 32715, "total_steps": 40000, "loss": 0.1267, "lr": 3.982762711189766e-06, "epoch": 1.4809977591163221, "percentage": 81.79, "elapsed_time": "1 day, 2:47:10", "remaining_time": "5:57:53", "throughput": 554.02, "total_tokens": 53424528} {"current_steps": 32720, "total_steps": 40000, "loss": 0.1003, "lr": 3.977447996480785e-06, "epoch": 1.4812241110029651, "percentage": 81.8, "elapsed_time": "1 day, 2:47:13", "remaining_time": "5:57:35", "throughput": 554.09, "total_tokens": 53432880} {"current_steps": 32725, "total_steps": 40000, "loss": 0.1601, "lr": 3.97213652371351e-06, "epoch": 1.4814504628896081, "percentage": 81.81, "elapsed_time": "1 day, 2:47:16", "remaining_time": "5:57:18", "throughput": 554.16, "total_tokens": 53440880} {"current_steps": 32730, "total_steps": 40000, "loss": 0.099, "lr": 3.966828293707042e-06, "epoch": 1.4816768147762511, "percentage": 81.83, "elapsed_time": "1 day, 2:47:19", "remaining_time": "5:57:01", "throughput": 554.22, "total_tokens": 53448624} {"current_steps": 32735, "total_steps": 40000, "loss": 0.1304, "lr": 3.961523307279963e-06, "epoch": 1.4819031666628941, "percentage": 81.84, "elapsed_time": "1 day, 2:47:23", "remaining_time": "5:56:43", "throughput": 554.29, "total_tokens": 53457360} {"current_steps": 32740, "total_steps": 40000, "loss": 0.1639, "lr": 3.956221565250382e-06, "epoch": 1.4821295185495371, "percentage": 81.85, "elapsed_time": "1 day, 2:47:26", "remaining_time": "5:56:26", "throughput": 554.36, "total_tokens": 53465648} {"current_steps": 32745, "total_steps": 40000, "loss": 0.1137, "lr": 3.950923068435883e-06, "epoch": 1.4823558704361801, "percentage": 81.86, "elapsed_time": "1 day, 2:47:29", "remaining_time": "5:56:09", "throughput": 554.42, "total_tokens": 53473360} {"current_steps": 32750, "total_steps": 40000, "loss": 0.083, "lr": 3.945627817653566e-06, "epoch": 1.482582222322823, "percentage": 81.88, "elapsed_time": "1 day, 2:47:32", "remaining_time": "5:55:52", "throughput": 554.48, "total_tokens": 53481424} {"current_steps": 32755, "total_steps": 40000, "loss": 0.1351, "lr": 3.9403358137200335e-06, "epoch": 1.482808574209466, "percentage": 81.89, "elapsed_time": "1 day, 2:47:35", "remaining_time": "5:55:34", "throughput": 554.55, "total_tokens": 53490096} {"current_steps": 32760, "total_steps": 40000, "loss": 0.1127, "lr": 3.9350470574513605e-06, "epoch": 1.483034926096109, "percentage": 81.9, "elapsed_time": "1 day, 2:47:39", "remaining_time": "5:55:17", "throughput": 554.62, "total_tokens": 53497648} {"current_steps": 32765, "total_steps": 40000, "loss": 0.1159, "lr": 3.9297615496631525e-06, "epoch": 1.483261277982752, "percentage": 81.91, "elapsed_time": "1 day, 2:47:42", "remaining_time": "5:55:00", "throughput": 554.68, "total_tokens": 53505424} {"current_steps": 32770, "total_steps": 40000, "loss": 0.1275, "lr": 3.924479291170505e-06, "epoch": 1.483487629869395, "percentage": 81.92, "elapsed_time": "1 day, 2:47:45", "remaining_time": "5:54:43", "throughput": 554.74, "total_tokens": 53513488} {"current_steps": 32775, "total_steps": 40000, "loss": 0.1464, "lr": 3.919200282788002e-06, "epoch": 1.4837139817560379, "percentage": 81.94, "elapsed_time": "1 day, 2:47:48", "remaining_time": "5:54:25", "throughput": 554.81, "total_tokens": 53521392} {"current_steps": 32780, "total_steps": 40000, "loss": 0.0842, "lr": 3.913924525329726e-06, "epoch": 1.4839403336426809, "percentage": 81.95, "elapsed_time": "1 day, 2:47:51", "remaining_time": "5:54:08", "throughput": 554.87, "total_tokens": 53529104} {"current_steps": 32785, "total_steps": 40000, "loss": 0.1563, "lr": 3.908652019609279e-06, "epoch": 1.4841666855293238, "percentage": 81.96, "elapsed_time": "1 day, 2:47:54", "remaining_time": "5:53:51", "throughput": 554.93, "total_tokens": 53536976} {"current_steps": 32790, "total_steps": 40000, "loss": 0.1242, "lr": 3.9033827664397364e-06, "epoch": 1.4843930374159668, "percentage": 81.97, "elapsed_time": "1 day, 2:47:58", "remaining_time": "5:53:33", "throughput": 554.99, "total_tokens": 53544784} {"current_steps": 32795, "total_steps": 40000, "loss": 0.0938, "lr": 3.898116766633694e-06, "epoch": 1.4846193893026098, "percentage": 81.99, "elapsed_time": "1 day, 2:48:01", "remaining_time": "5:53:16", "throughput": 555.07, "total_tokens": 53553424} {"current_steps": 32800, "total_steps": 40000, "loss": 0.1434, "lr": 3.8928540210032225e-06, "epoch": 1.4848457411892528, "percentage": 82.0, "elapsed_time": "1 day, 2:48:04", "remaining_time": "5:52:59", "throughput": 555.13, "total_tokens": 53561232} {"current_steps": 32800, "total_steps": 40000, "eval_loss": 0.12225272506475449, "epoch": 1.4848457411892528, "percentage": 82.0, "elapsed_time": "1 day, 2:55:47", "remaining_time": "5:54:41", "throughput": 552.48, "total_tokens": 53561232} {"current_steps": 32805, "total_steps": 40000, "loss": 0.1334, "lr": 3.887594530359909e-06, "epoch": 1.4850720930758958, "percentage": 82.01, "elapsed_time": "1 day, 2:55:50", "remaining_time": "5:54:23", "throughput": 552.53, "total_tokens": 53568688} {"current_steps": 32810, "total_steps": 40000, "loss": 0.1624, "lr": 3.88233829551484e-06, "epoch": 1.4852984449625388, "percentage": 82.03, "elapsed_time": "1 day, 2:55:54", "remaining_time": "5:54:06", "throughput": 552.6, "total_tokens": 53576720} {"current_steps": 32815, "total_steps": 40000, "loss": 0.1116, "lr": 3.877085317278581e-06, "epoch": 1.4855247968491818, "percentage": 82.04, "elapsed_time": "1 day, 2:55:57", "remaining_time": "5:53:49", "throughput": 552.67, "total_tokens": 53585072} {"current_steps": 32820, "total_steps": 40000, "loss": 0.1672, "lr": 3.87183559646122e-06, "epoch": 1.4857511487358246, "percentage": 82.05, "elapsed_time": "1 day, 2:56:00", "remaining_time": "5:53:31", "throughput": 552.73, "total_tokens": 53592912} {"current_steps": 32825, "total_steps": 40000, "loss": 0.134, "lr": 3.866589133872317e-06, "epoch": 1.4859775006224676, "percentage": 82.06, "elapsed_time": "1 day, 2:56:03", "remaining_time": "5:53:14", "throughput": 552.79, "total_tokens": 53600304} {"current_steps": 32830, "total_steps": 40000, "loss": 0.1292, "lr": 3.861345930320948e-06, "epoch": 1.4862038525091106, "percentage": 82.08, "elapsed_time": "1 day, 2:56:06", "remaining_time": "5:52:57", "throughput": 552.85, "total_tokens": 53608304} {"current_steps": 32835, "total_steps": 40000, "loss": 0.1601, "lr": 3.856105986615688e-06, "epoch": 1.4864302043957536, "percentage": 82.09, "elapsed_time": "1 day, 2:56:09", "remaining_time": "5:52:40", "throughput": 552.91, "total_tokens": 53615728} {"current_steps": 32840, "total_steps": 40000, "loss": 0.1011, "lr": 3.850869303564589e-06, "epoch": 1.4866565562823966, "percentage": 82.1, "elapsed_time": "1 day, 2:56:13", "remaining_time": "5:52:22", "throughput": 552.98, "total_tokens": 53624304} {"current_steps": 32845, "total_steps": 40000, "loss": 0.1476, "lr": 3.845635881975226e-06, "epoch": 1.4868829081690396, "percentage": 82.11, "elapsed_time": "1 day, 2:56:16", "remaining_time": "5:52:05", "throughput": 553.05, "total_tokens": 53632400} {"current_steps": 32850, "total_steps": 40000, "loss": 0.1495, "lr": 3.840405722654647e-06, "epoch": 1.4871092600556826, "percentage": 82.12, "elapsed_time": "1 day, 2:56:19", "remaining_time": "5:51:48", "throughput": 553.11, "total_tokens": 53640560} {"current_steps": 32855, "total_steps": 40000, "loss": 0.1367, "lr": 3.835178826409419e-06, "epoch": 1.4873356119423256, "percentage": 82.14, "elapsed_time": "1 day, 2:56:22", "remaining_time": "5:51:30", "throughput": 553.18, "total_tokens": 53648880} {"current_steps": 32860, "total_steps": 40000, "loss": 0.0832, "lr": 3.8299551940455895e-06, "epoch": 1.4875619638289685, "percentage": 82.15, "elapsed_time": "1 day, 2:56:25", "remaining_time": "5:51:13", "throughput": 553.25, "total_tokens": 53657104} {"current_steps": 32865, "total_steps": 40000, "loss": 0.1202, "lr": 3.824734826368703e-06, "epoch": 1.4877883157156115, "percentage": 82.16, "elapsed_time": "1 day, 2:56:29", "remaining_time": "5:50:56", "throughput": 553.31, "total_tokens": 53664976} {"current_steps": 32870, "total_steps": 40000, "loss": 0.1573, "lr": 3.819517724183813e-06, "epoch": 1.4880146676022545, "percentage": 82.17, "elapsed_time": "1 day, 2:56:32", "remaining_time": "5:50:39", "throughput": 553.38, "total_tokens": 53673520} {"current_steps": 32875, "total_steps": 40000, "loss": 0.1137, "lr": 3.8143038882954648e-06, "epoch": 1.4882410194888975, "percentage": 82.19, "elapsed_time": "1 day, 2:56:35", "remaining_time": "5:50:21", "throughput": 553.45, "total_tokens": 53681776} {"current_steps": 32880, "total_steps": 40000, "loss": 0.1626, "lr": 3.8090933195076867e-06, "epoch": 1.4884673713755405, "percentage": 82.2, "elapsed_time": "1 day, 2:56:38", "remaining_time": "5:50:04", "throughput": 553.52, "total_tokens": 53690576} {"current_steps": 32885, "total_steps": 40000, "loss": 0.0686, "lr": 3.8038860186240198e-06, "epoch": 1.4886937232621835, "percentage": 82.21, "elapsed_time": "1 day, 2:56:42", "remaining_time": "5:49:47", "throughput": 553.59, "total_tokens": 53698992} {"current_steps": 32890, "total_steps": 40000, "loss": 0.1368, "lr": 3.7986819864475026e-06, "epoch": 1.4889200751488263, "percentage": 82.23, "elapsed_time": "1 day, 2:56:45", "remaining_time": "5:49:30", "throughput": 553.66, "total_tokens": 53707600} {"current_steps": 32895, "total_steps": 40000, "loss": 0.1448, "lr": 3.793481223780651e-06, "epoch": 1.4891464270354693, "percentage": 82.24, "elapsed_time": "1 day, 2:56:48", "remaining_time": "5:49:12", "throughput": 553.73, "total_tokens": 53716240} {"current_steps": 32900, "total_steps": 40000, "loss": 0.1067, "lr": 3.788283731425496e-06, "epoch": 1.4893727789221123, "percentage": 82.25, "elapsed_time": "1 day, 2:56:51", "remaining_time": "5:48:55", "throughput": 553.79, "total_tokens": 53724592} {"current_steps": 32905, "total_steps": 40000, "loss": 0.1115, "lr": 3.7830895101835488e-06, "epoch": 1.4895991308087553, "percentage": 82.26, "elapsed_time": "1 day, 2:56:55", "remaining_time": "5:48:38", "throughput": 553.86, "total_tokens": 53732912} {"current_steps": 32910, "total_steps": 40000, "loss": 0.1972, "lr": 3.7778985608558274e-06, "epoch": 1.4898254826953983, "percentage": 82.27, "elapsed_time": "1 day, 2:56:58", "remaining_time": "5:48:21", "throughput": 553.93, "total_tokens": 53741136} {"current_steps": 32915, "total_steps": 40000, "loss": 0.1658, "lr": 3.7727108842428443e-06, "epoch": 1.4900518345820413, "percentage": 82.29, "elapsed_time": "1 day, 2:57:01", "remaining_time": "5:48:04", "throughput": 553.99, "total_tokens": 53748848} {"current_steps": 32920, "total_steps": 40000, "loss": 0.1242, "lr": 3.7675264811446065e-06, "epoch": 1.4902781864686843, "percentage": 82.3, "elapsed_time": "1 day, 2:57:04", "remaining_time": "5:47:46", "throughput": 554.05, "total_tokens": 53757008} {"current_steps": 32925, "total_steps": 40000, "loss": 0.1109, "lr": 3.7623453523605994e-06, "epoch": 1.4905045383553273, "percentage": 82.31, "elapsed_time": "1 day, 2:57:07", "remaining_time": "5:47:29", "throughput": 554.11, "total_tokens": 53764592} {"current_steps": 32930, "total_steps": 40000, "loss": 0.1319, "lr": 3.757167498689834e-06, "epoch": 1.49073089024197, "percentage": 82.33, "elapsed_time": "1 day, 2:57:11", "remaining_time": "5:47:12", "throughput": 554.18, "total_tokens": 53772592} {"current_steps": 32935, "total_steps": 40000, "loss": 0.1064, "lr": 3.7519929209307914e-06, "epoch": 1.490957242128613, "percentage": 82.34, "elapsed_time": "1 day, 2:57:14", "remaining_time": "5:46:55", "throughput": 554.24, "total_tokens": 53780592} {"current_steps": 32940, "total_steps": 40000, "loss": 0.1461, "lr": 3.746821619881463e-06, "epoch": 1.491183594015256, "percentage": 82.35, "elapsed_time": "1 day, 2:57:17", "remaining_time": "5:46:37", "throughput": 554.3, "total_tokens": 53788176} {"current_steps": 32945, "total_steps": 40000, "loss": 0.091, "lr": 3.74165359633932e-06, "epoch": 1.491409945901899, "percentage": 82.36, "elapsed_time": "1 day, 2:57:20", "remaining_time": "5:46:20", "throughput": 554.37, "total_tokens": 53796400} {"current_steps": 32950, "total_steps": 40000, "loss": 0.1154, "lr": 3.736488851101341e-06, "epoch": 1.491636297788542, "percentage": 82.38, "elapsed_time": "1 day, 2:57:23", "remaining_time": "5:46:03", "throughput": 554.44, "total_tokens": 53804624} {"current_steps": 32955, "total_steps": 40000, "loss": 0.147, "lr": 3.7313273849640035e-06, "epoch": 1.491862649675185, "percentage": 82.39, "elapsed_time": "1 day, 2:57:26", "remaining_time": "5:45:46", "throughput": 554.5, "total_tokens": 53812208} {"current_steps": 32960, "total_steps": 40000, "loss": 0.1023, "lr": 3.7261691987232533e-06, "epoch": 1.492089001561828, "percentage": 82.4, "elapsed_time": "1 day, 2:57:30", "remaining_time": "5:45:29", "throughput": 554.57, "total_tokens": 53820816} {"current_steps": 32965, "total_steps": 40000, "loss": 0.0964, "lr": 3.7210142931745575e-06, "epoch": 1.492315353448471, "percentage": 82.41, "elapsed_time": "1 day, 2:57:33", "remaining_time": "5:45:11", "throughput": 554.64, "total_tokens": 53829232} {"current_steps": 32970, "total_steps": 40000, "loss": 0.1014, "lr": 3.7158626691128712e-06, "epoch": 1.492541705335114, "percentage": 82.42, "elapsed_time": "1 day, 2:57:36", "remaining_time": "5:44:54", "throughput": 554.7, "total_tokens": 53837680} {"current_steps": 32975, "total_steps": 40000, "loss": 0.0918, "lr": 3.710714327332629e-06, "epoch": 1.492768057221757, "percentage": 82.44, "elapsed_time": "1 day, 2:57:39", "remaining_time": "5:44:37", "throughput": 554.77, "total_tokens": 53845776} {"current_steps": 32980, "total_steps": 40000, "loss": 0.1763, "lr": 3.7055692686277815e-06, "epoch": 1.4929944091084, "percentage": 82.45, "elapsed_time": "1 day, 2:57:43", "remaining_time": "5:44:20", "throughput": 554.84, "total_tokens": 53853968} {"current_steps": 32985, "total_steps": 40000, "loss": 0.1875, "lr": 3.70042749379175e-06, "epoch": 1.493220760995043, "percentage": 82.46, "elapsed_time": "1 day, 2:57:46", "remaining_time": "5:44:03", "throughput": 554.9, "total_tokens": 53861520} {"current_steps": 32990, "total_steps": 40000, "loss": 0.0849, "lr": 3.6952890036174693e-06, "epoch": 1.493447112881686, "percentage": 82.47, "elapsed_time": "1 day, 2:57:49", "remaining_time": "5:43:46", "throughput": 554.96, "total_tokens": 53869744} {"current_steps": 32995, "total_steps": 40000, "loss": 0.1195, "lr": 3.690153798897353e-06, "epoch": 1.493673464768329, "percentage": 82.49, "elapsed_time": "1 day, 2:57:52", "remaining_time": "5:43:28", "throughput": 555.03, "total_tokens": 53878192} {"current_steps": 33000, "total_steps": 40000, "loss": 0.1549, "lr": 3.6850218804233225e-06, "epoch": 1.493899816654972, "percentage": 82.5, "elapsed_time": "1 day, 2:57:55", "remaining_time": "5:43:11", "throughput": 555.09, "total_tokens": 53886096} {"current_steps": 33000, "total_steps": 40000, "eval_loss": 0.12226888537406921, "epoch": 1.493899816654972, "percentage": 82.5, "elapsed_time": "1 day, 3:05:38", "remaining_time": "5:44:49", "throughput": 552.46, "total_tokens": 53886096} {"current_steps": 33005, "total_steps": 40000, "loss": 0.1532, "lr": 3.679893248986779e-06, "epoch": 1.4941261685416147, "percentage": 82.51, "elapsed_time": "1 day, 3:05:42", "remaining_time": "5:44:32", "throughput": 552.52, "total_tokens": 53894512} {"current_steps": 33010, "total_steps": 40000, "loss": 0.1478, "lr": 3.6747679053786147e-06, "epoch": 1.4943525204282577, "percentage": 82.53, "elapsed_time": "1 day, 3:05:45", "remaining_time": "5:44:15", "throughput": 552.59, "total_tokens": 53903216} {"current_steps": 33015, "total_steps": 40000, "loss": 0.1116, "lr": 3.669645850389228e-06, "epoch": 1.4945788723149007, "percentage": 82.54, "elapsed_time": "1 day, 3:05:49", "remaining_time": "5:43:58", "throughput": 552.66, "total_tokens": 53911152} {"current_steps": 33020, "total_steps": 40000, "loss": 0.1101, "lr": 3.664527084808514e-06, "epoch": 1.4948052242015437, "percentage": 82.55, "elapsed_time": "1 day, 3:05:52", "remaining_time": "5:43:41", "throughput": 552.72, "total_tokens": 53918544} {"current_steps": 33025, "total_steps": 40000, "loss": 0.1371, "lr": 3.6594116094258337e-06, "epoch": 1.4950315760881867, "percentage": 82.56, "elapsed_time": "1 day, 3:05:55", "remaining_time": "5:43:24", "throughput": 552.78, "total_tokens": 53926416} {"current_steps": 33030, "total_steps": 40000, "loss": 0.1179, "lr": 3.6542994250300665e-06, "epoch": 1.4952579279748297, "percentage": 82.58, "elapsed_time": "1 day, 3:05:58", "remaining_time": "5:43:06", "throughput": 552.84, "total_tokens": 53933968} {"current_steps": 33035, "total_steps": 40000, "loss": 0.1487, "lr": 3.6491905324095825e-06, "epoch": 1.4954842798614727, "percentage": 82.59, "elapsed_time": "1 day, 3:06:01", "remaining_time": "5:42:49", "throughput": 552.9, "total_tokens": 53942160} {"current_steps": 33040, "total_steps": 40000, "loss": 0.1363, "lr": 3.644084932352221e-06, "epoch": 1.4957106317481157, "percentage": 82.6, "elapsed_time": "1 day, 3:06:04", "remaining_time": "5:42:32", "throughput": 552.97, "total_tokens": 53950000} {"current_steps": 33045, "total_steps": 40000, "loss": 0.0742, "lr": 3.6389826256453457e-06, "epoch": 1.4959369836347585, "percentage": 82.61, "elapsed_time": "1 day, 3:06:07", "remaining_time": "5:42:15", "throughput": 553.03, "total_tokens": 53958320} {"current_steps": 33050, "total_steps": 40000, "loss": 0.1238, "lr": 3.633883613075781e-06, "epoch": 1.4961633355214015, "percentage": 82.62, "elapsed_time": "1 day, 3:06:11", "remaining_time": "5:41:57", "throughput": 553.1, "total_tokens": 53966640} {"current_steps": 33055, "total_steps": 40000, "loss": 0.1287, "lr": 3.6287878954298693e-06, "epoch": 1.4963896874080445, "percentage": 82.64, "elapsed_time": "1 day, 3:06:14", "remaining_time": "5:41:40", "throughput": 553.16, "total_tokens": 53974416} {"current_steps": 33060, "total_steps": 40000, "loss": 0.1636, "lr": 3.6236954734934354e-06, "epoch": 1.4966160392946875, "percentage": 82.65, "elapsed_time": "1 day, 3:06:17", "remaining_time": "5:41:23", "throughput": 553.23, "total_tokens": 53982800} {"current_steps": 33065, "total_steps": 40000, "loss": 0.1175, "lr": 3.618606348051784e-06, "epoch": 1.4968423911813304, "percentage": 82.66, "elapsed_time": "1 day, 3:06:20", "remaining_time": "5:41:06", "throughput": 553.3, "total_tokens": 53991088} {"current_steps": 33070, "total_steps": 40000, "loss": 0.0657, "lr": 3.6135205198897376e-06, "epoch": 1.4970687430679734, "percentage": 82.67, "elapsed_time": "1 day, 3:06:23", "remaining_time": "5:40:49", "throughput": 553.37, "total_tokens": 53999568} {"current_steps": 33075, "total_steps": 40000, "loss": 0.1159, "lr": 3.6084379897915854e-06, "epoch": 1.4972950949546164, "percentage": 82.69, "elapsed_time": "1 day, 3:06:27", "remaining_time": "5:40:32", "throughput": 553.43, "total_tokens": 54007568} {"current_steps": 33080, "total_steps": 40000, "loss": 0.0709, "lr": 3.6033587585411115e-06, "epoch": 1.4975214468412594, "percentage": 82.7, "elapsed_time": "1 day, 3:06:30", "remaining_time": "5:40:14", "throughput": 553.5, "total_tokens": 54016016} {"current_steps": 33085, "total_steps": 40000, "loss": 0.1351, "lr": 3.5982828269216117e-06, "epoch": 1.4977477987279024, "percentage": 82.71, "elapsed_time": "1 day, 3:06:33", "remaining_time": "5:39:57", "throughput": 553.56, "total_tokens": 54024208} {"current_steps": 33090, "total_steps": 40000, "loss": 0.1701, "lr": 3.593210195715843e-06, "epoch": 1.4979741506145454, "percentage": 82.73, "elapsed_time": "1 day, 3:06:36", "remaining_time": "5:39:40", "throughput": 553.63, "total_tokens": 54031984} {"current_steps": 33095, "total_steps": 40000, "loss": 0.1099, "lr": 3.5881408657060773e-06, "epoch": 1.4982005025011884, "percentage": 82.74, "elapsed_time": "1 day, 3:06:39", "remaining_time": "5:39:23", "throughput": 553.68, "total_tokens": 54039440} {"current_steps": 33100, "total_steps": 40000, "loss": 0.1488, "lr": 3.583074837674075e-06, "epoch": 1.4984268543878314, "percentage": 82.75, "elapsed_time": "1 day, 3:06:42", "remaining_time": "5:39:06", "throughput": 553.75, "total_tokens": 54047632} {"current_steps": 33105, "total_steps": 40000, "loss": 0.1281, "lr": 3.578012112401069e-06, "epoch": 1.4986532062744744, "percentage": 82.76, "elapsed_time": "1 day, 3:06:46", "remaining_time": "5:38:49", "throughput": 553.82, "total_tokens": 54056048} {"current_steps": 33110, "total_steps": 40000, "loss": 0.1231, "lr": 3.5729526906677996e-06, "epoch": 1.4988795581611174, "percentage": 82.78, "elapsed_time": "1 day, 3:06:49", "remaining_time": "5:38:31", "throughput": 553.89, "total_tokens": 54064816} {"current_steps": 33115, "total_steps": 40000, "loss": 0.0863, "lr": 3.5678965732545007e-06, "epoch": 1.4991059100477602, "percentage": 82.79, "elapsed_time": "1 day, 3:06:52", "remaining_time": "5:38:14", "throughput": 553.95, "total_tokens": 54073008} {"current_steps": 33120, "total_steps": 40000, "loss": 0.1394, "lr": 3.562843760940876e-06, "epoch": 1.4993322619344032, "percentage": 82.8, "elapsed_time": "1 day, 3:06:56", "remaining_time": "5:37:57", "throughput": 554.02, "total_tokens": 54081040} {"current_steps": 33125, "total_steps": 40000, "loss": 0.0977, "lr": 3.5577942545061473e-06, "epoch": 1.4995586138210462, "percentage": 82.81, "elapsed_time": "1 day, 3:06:59", "remaining_time": "5:37:40", "throughput": 554.08, "total_tokens": 54089168} {"current_steps": 33130, "total_steps": 40000, "loss": 0.1193, "lr": 3.5527480547289967e-06, "epoch": 1.4997849657076892, "percentage": 82.83, "elapsed_time": "1 day, 3:07:02", "remaining_time": "5:37:23", "throughput": 554.14, "total_tokens": 54096912} {"current_steps": 33135, "total_steps": 40000, "loss": 0.1117, "lr": 3.547705162387624e-06, "epoch": 1.5000113175943321, "percentage": 82.84, "elapsed_time": "1 day, 3:07:05", "remaining_time": "5:37:06", "throughput": 554.21, "total_tokens": 54105104} {"current_steps": 33140, "total_steps": 40000, "loss": 0.1666, "lr": 3.542665578259699e-06, "epoch": 1.5002376694809751, "percentage": 82.85, "elapsed_time": "1 day, 3:07:08", "remaining_time": "5:36:49", "throughput": 554.27, "total_tokens": 54113136} {"current_steps": 33145, "total_steps": 40000, "loss": 0.1626, "lr": 3.5376293031223945e-06, "epoch": 1.5004640213676181, "percentage": 82.86, "elapsed_time": "1 day, 3:07:12", "remaining_time": "5:36:32", "throughput": 554.34, "total_tokens": 54121424} {"current_steps": 33150, "total_steps": 40000, "loss": 0.1199, "lr": 3.5325963377523614e-06, "epoch": 1.500690373254261, "percentage": 82.88, "elapsed_time": "1 day, 3:07:15", "remaining_time": "5:36:15", "throughput": 554.42, "total_tokens": 54130576} {"current_steps": 33155, "total_steps": 40000, "loss": 0.1598, "lr": 3.5275666829257536e-06, "epoch": 1.500916725140904, "percentage": 82.89, "elapsed_time": "1 day, 3:07:18", "remaining_time": "5:35:57", "throughput": 554.48, "total_tokens": 54138832} {"current_steps": 33160, "total_steps": 40000, "loss": 0.1165, "lr": 3.5225403394181955e-06, "epoch": 1.501143077027547, "percentage": 82.9, "elapsed_time": "1 day, 3:07:21", "remaining_time": "5:35:40", "throughput": 554.54, "total_tokens": 54146576} {"current_steps": 33165, "total_steps": 40000, "loss": 0.1079, "lr": 3.517517308004828e-06, "epoch": 1.50136942891419, "percentage": 82.91, "elapsed_time": "1 day, 3:07:25", "remaining_time": "5:35:23", "throughput": 554.61, "total_tokens": 54154960} {"current_steps": 33170, "total_steps": 40000, "loss": 0.077, "lr": 3.512497589460251e-06, "epoch": 1.501595780800833, "percentage": 82.93, "elapsed_time": "1 day, 3:07:28", "remaining_time": "5:35:06", "throughput": 554.67, "total_tokens": 54163024} {"current_steps": 33175, "total_steps": 40000, "loss": 0.1395, "lr": 3.5074811845585727e-06, "epoch": 1.5018221326874759, "percentage": 82.94, "elapsed_time": "1 day, 3:07:31", "remaining_time": "5:34:49", "throughput": 554.74, "total_tokens": 54171280} {"current_steps": 33180, "total_steps": 40000, "loss": 0.0984, "lr": 3.5024680940733937e-06, "epoch": 1.5020484845741189, "percentage": 82.95, "elapsed_time": "1 day, 3:07:34", "remaining_time": "5:34:32", "throughput": 554.81, "total_tokens": 54180176} {"current_steps": 33185, "total_steps": 40000, "loss": 0.0986, "lr": 3.4974583187777852e-06, "epoch": 1.5022748364607619, "percentage": 82.96, "elapsed_time": "1 day, 3:07:38", "remaining_time": "5:34:15", "throughput": 554.88, "total_tokens": 54188816} {"current_steps": 33190, "total_steps": 40000, "loss": 0.1395, "lr": 3.4924518594443204e-06, "epoch": 1.5025011883474049, "percentage": 82.97, "elapsed_time": "1 day, 3:07:41", "remaining_time": "5:33:58", "throughput": 554.95, "total_tokens": 54197392} {"current_steps": 33195, "total_steps": 40000, "loss": 0.1021, "lr": 3.4874487168450682e-06, "epoch": 1.5027275402340479, "percentage": 82.99, "elapsed_time": "1 day, 3:07:44", "remaining_time": "5:33:41", "throughput": 555.02, "total_tokens": 54205584} {"current_steps": 33200, "total_steps": 40000, "loss": 0.1455, "lr": 3.482448891751558e-06, "epoch": 1.5029538921206909, "percentage": 83.0, "elapsed_time": "1 day, 3:07:47", "remaining_time": "5:33:24", "throughput": 555.08, "total_tokens": 54213552} {"current_steps": 33200, "total_steps": 40000, "eval_loss": 0.12210097163915634, "epoch": 1.5029538921206909, "percentage": 83.0, "elapsed_time": "1 day, 3:15:30", "remaining_time": "5:34:58", "throughput": 552.46, "total_tokens": 54213552} {"current_steps": 33205, "total_steps": 40000, "loss": 0.1423, "lr": 3.477452384934843e-06, "epoch": 1.5031802440073339, "percentage": 83.01, "elapsed_time": "1 day, 3:15:34", "remaining_time": "5:34:42", "throughput": 552.52, "total_tokens": 54221552} {"current_steps": 33210, "total_steps": 40000, "loss": 0.139, "lr": 3.472459197165434e-06, "epoch": 1.5034065958939768, "percentage": 83.03, "elapsed_time": "1 day, 3:15:37", "remaining_time": "5:34:24", "throughput": 552.59, "total_tokens": 54229776} {"current_steps": 33215, "total_steps": 40000, "loss": 0.0778, "lr": 3.4674693292133518e-06, "epoch": 1.5036329477806198, "percentage": 83.04, "elapsed_time": "1 day, 3:15:40", "remaining_time": "5:34:07", "throughput": 552.65, "total_tokens": 54237488} {"current_steps": 33220, "total_steps": 40000, "loss": 0.1877, "lr": 3.4624827818480977e-06, "epoch": 1.5038592996672628, "percentage": 83.05, "elapsed_time": "1 day, 3:15:43", "remaining_time": "5:33:50", "throughput": 552.71, "total_tokens": 54245584} {"current_steps": 33225, "total_steps": 40000, "loss": 0.1044, "lr": 3.4574995558386474e-06, "epoch": 1.5040856515539058, "percentage": 83.06, "elapsed_time": "1 day, 3:15:47", "remaining_time": "5:33:33", "throughput": 552.78, "total_tokens": 54254000} {"current_steps": 33230, "total_steps": 40000, "loss": 0.1184, "lr": 3.452519651953487e-06, "epoch": 1.5043120034405488, "percentage": 83.08, "elapsed_time": "1 day, 3:15:50", "remaining_time": "5:33:16", "throughput": 552.85, "total_tokens": 54262384} {"current_steps": 33235, "total_steps": 40000, "loss": 0.138, "lr": 3.447543070960585e-06, "epoch": 1.5045383553271916, "percentage": 83.09, "elapsed_time": "1 day, 3:15:53", "remaining_time": "5:32:59", "throughput": 552.91, "total_tokens": 54270608} {"current_steps": 33240, "total_steps": 40000, "loss": 0.1063, "lr": 3.4425698136273778e-06, "epoch": 1.5047647072138346, "percentage": 83.1, "elapsed_time": "1 day, 3:15:57", "remaining_time": "5:32:42", "throughput": 552.99, "total_tokens": 54279568} {"current_steps": 33245, "total_steps": 40000, "loss": 0.1327, "lr": 3.437599880720821e-06, "epoch": 1.5049910591004776, "percentage": 83.11, "elapsed_time": "1 day, 3:16:00", "remaining_time": "5:32:25", "throughput": 553.05, "total_tokens": 54287664} {"current_steps": 33250, "total_steps": 40000, "loss": 0.0832, "lr": 3.4326332730073267e-06, "epoch": 1.5052174109871206, "percentage": 83.12, "elapsed_time": "1 day, 3:16:03", "remaining_time": "5:32:07", "throughput": 553.12, "total_tokens": 54296016} {"current_steps": 33255, "total_steps": 40000, "loss": 0.0986, "lr": 3.427669991252813e-06, "epoch": 1.5054437628737636, "percentage": 83.14, "elapsed_time": "1 day, 3:16:06", "remaining_time": "5:31:50", "throughput": 553.18, "total_tokens": 54303824} {"current_steps": 33260, "total_steps": 40000, "loss": 0.1413, "lr": 3.42271003622269e-06, "epoch": 1.5056701147604066, "percentage": 83.15, "elapsed_time": "1 day, 3:16:09", "remaining_time": "5:31:33", "throughput": 553.24, "total_tokens": 54311696} {"current_steps": 33265, "total_steps": 40000, "loss": 0.1141, "lr": 3.4177534086818286e-06, "epoch": 1.5058964666470493, "percentage": 83.16, "elapsed_time": "1 day, 3:16:12", "remaining_time": "5:31:16", "throughput": 553.31, "total_tokens": 54320400} {"current_steps": 33270, "total_steps": 40000, "loss": 0.1726, "lr": 3.412800109394612e-06, "epoch": 1.5061228185336923, "percentage": 83.17, "elapsed_time": "1 day, 3:16:16", "remaining_time": "5:30:59", "throughput": 553.39, "total_tokens": 54329456} {"current_steps": 33275, "total_steps": 40000, "loss": 0.1109, "lr": 3.4078501391249044e-06, "epoch": 1.5063491704203353, "percentage": 83.19, "elapsed_time": "1 day, 3:16:19", "remaining_time": "5:30:42", "throughput": 553.45, "total_tokens": 54337200} {"current_steps": 33280, "total_steps": 40000, "loss": 0.1397, "lr": 3.4029034986360453e-06, "epoch": 1.5065755223069783, "percentage": 83.2, "elapsed_time": "1 day, 3:16:22", "remaining_time": "5:30:25", "throughput": 553.53, "total_tokens": 54346640} {"current_steps": 33285, "total_steps": 40000, "loss": 0.1092, "lr": 3.397960188690877e-06, "epoch": 1.5068018741936213, "percentage": 83.21, "elapsed_time": "1 day, 3:16:25", "remaining_time": "5:30:08", "throughput": 553.59, "total_tokens": 54354704} {"current_steps": 33290, "total_steps": 40000, "loss": 0.089, "lr": 3.393020210051717e-06, "epoch": 1.5070282260802643, "percentage": 83.23, "elapsed_time": "1 day, 3:16:29", "remaining_time": "5:29:51", "throughput": 553.65, "total_tokens": 54362480} {"current_steps": 33295, "total_steps": 40000, "loss": 0.1151, "lr": 3.3880835634803655e-06, "epoch": 1.5072545779669073, "percentage": 83.24, "elapsed_time": "1 day, 3:16:32", "remaining_time": "5:29:34", "throughput": 553.72, "total_tokens": 54370672} {"current_steps": 33300, "total_steps": 40000, "loss": 0.1681, "lr": 3.383150249738126e-06, "epoch": 1.5074809298535503, "percentage": 83.25, "elapsed_time": "1 day, 3:16:35", "remaining_time": "5:29:17", "throughput": 553.79, "total_tokens": 54379408} {"current_steps": 33305, "total_steps": 40000, "loss": 0.1648, "lr": 3.3782202695857663e-06, "epoch": 1.5077072817401933, "percentage": 83.26, "elapsed_time": "1 day, 3:16:38", "remaining_time": "5:29:00", "throughput": 553.85, "total_tokens": 54387152} {"current_steps": 33310, "total_steps": 40000, "loss": 0.1065, "lr": 3.373293623783558e-06, "epoch": 1.5079336336268363, "percentage": 83.28, "elapsed_time": "1 day, 3:16:41", "remaining_time": "5:28:42", "throughput": 553.91, "total_tokens": 54395088} {"current_steps": 33315, "total_steps": 40000, "loss": 0.1302, "lr": 3.368370313091257e-06, "epoch": 1.5081599855134793, "percentage": 83.29, "elapsed_time": "1 day, 3:16:45", "remaining_time": "5:28:25", "throughput": 553.97, "total_tokens": 54402960} {"current_steps": 33320, "total_steps": 40000, "loss": 0.0867, "lr": 3.363450338268087e-06, "epoch": 1.5083863374001223, "percentage": 83.3, "elapsed_time": "1 day, 3:16:48", "remaining_time": "5:28:08", "throughput": 554.05, "total_tokens": 54411888} {"current_steps": 33325, "total_steps": 40000, "loss": 0.1273, "lr": 3.358533700072783e-06, "epoch": 1.5086126892867653, "percentage": 83.31, "elapsed_time": "1 day, 3:16:51", "remaining_time": "5:27:51", "throughput": 554.11, "total_tokens": 54420080} {"current_steps": 33330, "total_steps": 40000, "loss": 0.0917, "lr": 3.3536203992635377e-06, "epoch": 1.5088390411734083, "percentage": 83.33, "elapsed_time": "1 day, 3:16:54", "remaining_time": "5:27:34", "throughput": 554.17, "total_tokens": 54427792} {"current_steps": 33335, "total_steps": 40000, "loss": 0.1344, "lr": 3.348710436598057e-06, "epoch": 1.5090653930600513, "percentage": 83.34, "elapsed_time": "1 day, 3:16:57", "remaining_time": "5:27:17", "throughput": 554.24, "total_tokens": 54435920} {"current_steps": 33340, "total_steps": 40000, "loss": 0.1372, "lr": 3.3438038128335155e-06, "epoch": 1.5092917449466943, "percentage": 83.35, "elapsed_time": "1 day, 3:17:00", "remaining_time": "5:27:00", "throughput": 554.3, "total_tokens": 54444048} {"current_steps": 33345, "total_steps": 40000, "loss": 0.1618, "lr": 3.338900528726571e-06, "epoch": 1.5095180968333373, "percentage": 83.36, "elapsed_time": "1 day, 3:17:04", "remaining_time": "5:26:43", "throughput": 554.37, "total_tokens": 54452560} {"current_steps": 33350, "total_steps": 40000, "loss": 0.1446, "lr": 3.3340005850333812e-06, "epoch": 1.50974444871998, "percentage": 83.38, "elapsed_time": "1 day, 3:17:07", "remaining_time": "5:26:26", "throughput": 554.44, "total_tokens": 54461232} {"current_steps": 33355, "total_steps": 40000, "loss": 0.0931, "lr": 3.329103982509568e-06, "epoch": 1.509970800606623, "percentage": 83.39, "elapsed_time": "1 day, 3:17:10", "remaining_time": "5:26:09", "throughput": 554.5, "total_tokens": 54468944} {"current_steps": 33360, "total_steps": 40000, "loss": 0.1586, "lr": 3.324210721910259e-06, "epoch": 1.510197152493266, "percentage": 83.4, "elapsed_time": "1 day, 3:17:13", "remaining_time": "5:25:52", "throughput": 554.56, "total_tokens": 54477040} {"current_steps": 33365, "total_steps": 40000, "loss": 0.1087, "lr": 3.319320803990053e-06, "epoch": 1.510423504379909, "percentage": 83.41, "elapsed_time": "1 day, 3:17:17", "remaining_time": "5:25:35", "throughput": 554.63, "total_tokens": 54484912} {"current_steps": 33370, "total_steps": 40000, "loss": 0.1722, "lr": 3.3144342295030274e-06, "epoch": 1.510649856266552, "percentage": 83.43, "elapsed_time": "1 day, 3:17:20", "remaining_time": "5:25:18", "throughput": 554.69, "total_tokens": 54492400} {"current_steps": 33375, "total_steps": 40000, "loss": 0.1086, "lr": 3.309550999202765e-06, "epoch": 1.510876208153195, "percentage": 83.44, "elapsed_time": "1 day, 3:17:23", "remaining_time": "5:25:01", "throughput": 554.75, "total_tokens": 54500528} {"current_steps": 33380, "total_steps": 40000, "loss": 0.104, "lr": 3.3046711138423197e-06, "epoch": 1.5111025600398378, "percentage": 83.45, "elapsed_time": "1 day, 3:17:26", "remaining_time": "5:24:44", "throughput": 554.81, "total_tokens": 54508432} {"current_steps": 33385, "total_steps": 40000, "loss": 0.1678, "lr": 3.2997945741742255e-06, "epoch": 1.5113289119264808, "percentage": 83.46, "elapsed_time": "1 day, 3:17:29", "remaining_time": "5:24:27", "throughput": 554.88, "total_tokens": 54516944} {"current_steps": 33390, "total_steps": 40000, "loss": 0.1008, "lr": 3.2949213809505082e-06, "epoch": 1.5115552638131238, "percentage": 83.47, "elapsed_time": "1 day, 3:17:32", "remaining_time": "5:24:10", "throughput": 554.95, "total_tokens": 54525776} {"current_steps": 33395, "total_steps": 40000, "loss": 0.1193, "lr": 3.2900515349226834e-06, "epoch": 1.5117816156997668, "percentage": 83.49, "elapsed_time": "1 day, 3:17:36", "remaining_time": "5:23:53", "throughput": 555.02, "total_tokens": 54533680} {"current_steps": 33400, "total_steps": 40000, "loss": 0.1236, "lr": 3.285185036841731e-06, "epoch": 1.5120079675864098, "percentage": 83.5, "elapsed_time": "1 day, 3:17:39", "remaining_time": "5:23:36", "throughput": 555.08, "total_tokens": 54541744} {"current_steps": 33400, "total_steps": 40000, "eval_loss": 0.12257647514343262, "epoch": 1.5120079675864098, "percentage": 83.5, "elapsed_time": "1 day, 3:25:21", "remaining_time": "5:25:07", "throughput": 552.48, "total_tokens": 54541744} {"current_steps": 33405, "total_steps": 40000, "loss": 0.136, "lr": 3.2803218874581377e-06, "epoch": 1.5122343194730528, "percentage": 83.51, "elapsed_time": "1 day, 3:25:25", "remaining_time": "5:24:50", "throughput": 552.54, "total_tokens": 54549616} {"current_steps": 33410, "total_steps": 40000, "loss": 0.0665, "lr": 3.2754620875218494e-06, "epoch": 1.5124606713596958, "percentage": 83.53, "elapsed_time": "1 day, 3:25:29", "remaining_time": "5:24:33", "throughput": 552.6, "total_tokens": 54557936} {"current_steps": 33415, "total_steps": 40000, "loss": 0.1452, "lr": 3.2706056377823146e-06, "epoch": 1.5126870232463387, "percentage": 83.54, "elapsed_time": "1 day, 3:25:32", "remaining_time": "5:24:16", "throughput": 552.66, "total_tokens": 54565648} {"current_steps": 33420, "total_steps": 40000, "loss": 0.1011, "lr": 3.2657525389884647e-06, "epoch": 1.5129133751329817, "percentage": 83.55, "elapsed_time": "1 day, 3:25:35", "remaining_time": "5:23:59", "throughput": 552.73, "total_tokens": 54573744} {"current_steps": 33425, "total_steps": 40000, "loss": 0.138, "lr": 3.260902791888698e-06, "epoch": 1.5131397270196247, "percentage": 83.56, "elapsed_time": "1 day, 3:25:38", "remaining_time": "5:23:42", "throughput": 552.79, "total_tokens": 54581680} {"current_steps": 33430, "total_steps": 40000, "loss": 0.1106, "lr": 3.2560563972309166e-06, "epoch": 1.5133660789062677, "percentage": 83.58, "elapsed_time": "1 day, 3:25:41", "remaining_time": "5:23:25", "throughput": 552.86, "total_tokens": 54590032} {"current_steps": 33435, "total_steps": 40000, "loss": 0.1113, "lr": 3.251213355762489e-06, "epoch": 1.5135924307929107, "percentage": 83.59, "elapsed_time": "1 day, 3:25:45", "remaining_time": "5:23:08", "throughput": 552.92, "total_tokens": 54597872} {"current_steps": 33440, "total_steps": 40000, "loss": 0.0777, "lr": 3.2463736682302707e-06, "epoch": 1.5138187826795537, "percentage": 83.6, "elapsed_time": "1 day, 3:25:48", "remaining_time": "5:22:51", "throughput": 552.98, "total_tokens": 54605648} {"current_steps": 33445, "total_steps": 40000, "loss": 0.1831, "lr": 3.2415373353806124e-06, "epoch": 1.5140451345661967, "percentage": 83.61, "elapsed_time": "1 day, 3:25:51", "remaining_time": "5:22:34", "throughput": 553.05, "total_tokens": 54614544} {"current_steps": 33450, "total_steps": 40000, "loss": 0.1034, "lr": 3.236704357959322e-06, "epoch": 1.5142714864528397, "percentage": 83.62, "elapsed_time": "1 day, 3:25:54", "remaining_time": "5:22:17", "throughput": 553.12, "total_tokens": 54623568} {"current_steps": 33455, "total_steps": 40000, "loss": 0.1436, "lr": 3.2318747367117154e-06, "epoch": 1.5144978383394827, "percentage": 83.64, "elapsed_time": "1 day, 3:25:58", "remaining_time": "5:22:00", "throughput": 553.19, "total_tokens": 54632016} {"current_steps": 33460, "total_steps": 40000, "loss": 0.0755, "lr": 3.227048472382585e-06, "epoch": 1.5147241902261257, "percentage": 83.65, "elapsed_time": "1 day, 3:26:01", "remaining_time": "5:21:43", "throughput": 553.26, "total_tokens": 54640560} {"current_steps": 33465, "total_steps": 40000, "loss": 0.1197, "lr": 3.2222255657161915e-06, "epoch": 1.5149505421127685, "percentage": 83.66, "elapsed_time": "1 day, 3:26:04", "remaining_time": "5:21:26", "throughput": 553.33, "total_tokens": 54649008} {"current_steps": 33470, "total_steps": 40000, "loss": 0.1051, "lr": 3.2174060174562924e-06, "epoch": 1.5151768939994115, "percentage": 83.67, "elapsed_time": "1 day, 3:26:07", "remaining_time": "5:21:09", "throughput": 553.39, "total_tokens": 54656912} {"current_steps": 33475, "total_steps": 40000, "loss": 0.1237, "lr": 3.2125898283461298e-06, "epoch": 1.5154032458860545, "percentage": 83.69, "elapsed_time": "1 day, 3:26:10", "remaining_time": "5:20:52", "throughput": 553.45, "total_tokens": 54664816} {"current_steps": 33480, "total_steps": 40000, "loss": 0.0964, "lr": 3.207776999128406e-06, "epoch": 1.5156295977726975, "percentage": 83.7, "elapsed_time": "1 day, 3:26:13", "remaining_time": "5:20:35", "throughput": 553.51, "total_tokens": 54672336} {"current_steps": 33485, "total_steps": 40000, "loss": 0.109, "lr": 3.202967530545331e-06, "epoch": 1.5158559496593405, "percentage": 83.71, "elapsed_time": "1 day, 3:26:17", "remaining_time": "5:20:18", "throughput": 553.57, "total_tokens": 54680304} {"current_steps": 33490, "total_steps": 40000, "loss": 0.1139, "lr": 3.1981614233385778e-06, "epoch": 1.5160823015459832, "percentage": 83.73, "elapsed_time": "1 day, 3:26:20", "remaining_time": "5:20:01", "throughput": 553.64, "total_tokens": 54688944} {"current_steps": 33495, "total_steps": 40000, "loss": 0.1401, "lr": 3.1933586782493115e-06, "epoch": 1.5163086534326262, "percentage": 83.74, "elapsed_time": "1 day, 3:26:23", "remaining_time": "5:19:44", "throughput": 553.71, "total_tokens": 54697392} {"current_steps": 33500, "total_steps": 40000, "loss": 0.149, "lr": 3.188559296018184e-06, "epoch": 1.5165350053192692, "percentage": 83.75, "elapsed_time": "1 day, 3:26:26", "remaining_time": "5:19:27", "throughput": 553.77, "total_tokens": 54705360} {"current_steps": 33505, "total_steps": 40000, "loss": 0.1416, "lr": 3.1837632773853098e-06, "epoch": 1.5167613572059122, "percentage": 83.76, "elapsed_time": "1 day, 3:26:30", "remaining_time": "5:19:10", "throughput": 553.84, "total_tokens": 54713936} {"current_steps": 33510, "total_steps": 40000, "loss": 0.0931, "lr": 3.178970623090294e-06, "epoch": 1.5169877090925552, "percentage": 83.78, "elapsed_time": "1 day, 3:26:33", "remaining_time": "5:18:53", "throughput": 553.9, "total_tokens": 54721616} {"current_steps": 33515, "total_steps": 40000, "loss": 0.0819, "lr": 3.174181333872234e-06, "epoch": 1.5172140609791982, "percentage": 83.79, "elapsed_time": "1 day, 3:26:36", "remaining_time": "5:18:36", "throughput": 553.97, "total_tokens": 54729968} {"current_steps": 33520, "total_steps": 40000, "loss": 0.1315, "lr": 3.169395410469686e-06, "epoch": 1.5174404128658412, "percentage": 83.8, "elapsed_time": "1 day, 3:26:39", "remaining_time": "5:18:19", "throughput": 554.03, "total_tokens": 54737808} {"current_steps": 33525, "total_steps": 40000, "loss": 0.1452, "lr": 3.164612853620713e-06, "epoch": 1.5176667647524842, "percentage": 83.81, "elapsed_time": "1 day, 3:26:42", "remaining_time": "5:18:02", "throughput": 554.09, "total_tokens": 54745904} {"current_steps": 33530, "total_steps": 40000, "loss": 0.1316, "lr": 3.1598336640628333e-06, "epoch": 1.5178931166391272, "percentage": 83.83, "elapsed_time": "1 day, 3:26:46", "remaining_time": "5:17:45", "throughput": 554.16, "total_tokens": 54754352} {"current_steps": 33535, "total_steps": 40000, "loss": 0.1239, "lr": 3.155057842533063e-06, "epoch": 1.5181194685257702, "percentage": 83.84, "elapsed_time": "1 day, 3:26:49", "remaining_time": "5:17:28", "throughput": 554.23, "total_tokens": 54762768} {"current_steps": 33540, "total_steps": 40000, "loss": 0.0868, "lr": 3.1502853897678984e-06, "epoch": 1.5183458204124132, "percentage": 83.85, "elapsed_time": "1 day, 3:26:52", "remaining_time": "5:17:11", "throughput": 554.29, "total_tokens": 54770384} {"current_steps": 33545, "total_steps": 40000, "loss": 0.0889, "lr": 3.1455163065033017e-06, "epoch": 1.5185721722990562, "percentage": 83.86, "elapsed_time": "1 day, 3:26:55", "remaining_time": "5:16:54", "throughput": 554.35, "total_tokens": 54778160} {"current_steps": 33550, "total_steps": 40000, "loss": 0.1087, "lr": 3.140750593474734e-06, "epoch": 1.5187985241856992, "percentage": 83.88, "elapsed_time": "1 day, 3:26:58", "remaining_time": "5:16:37", "throughput": 554.41, "total_tokens": 54786512} {"current_steps": 33555, "total_steps": 40000, "loss": 0.1541, "lr": 3.1359882514171294e-06, "epoch": 1.5190248760723422, "percentage": 83.89, "elapsed_time": "1 day, 3:27:02", "remaining_time": "5:16:21", "throughput": 554.48, "total_tokens": 54795184} {"current_steps": 33560, "total_steps": 40000, "loss": 0.1469, "lr": 3.1312292810648903e-06, "epoch": 1.5192512279589852, "percentage": 83.9, "elapsed_time": "1 day, 3:27:05", "remaining_time": "5:16:04", "throughput": 554.54, "total_tokens": 54802576} {"current_steps": 33565, "total_steps": 40000, "loss": 0.0904, "lr": 3.1264736831519204e-06, "epoch": 1.5194775798456281, "percentage": 83.91, "elapsed_time": "1 day, 3:27:08", "remaining_time": "5:15:47", "throughput": 554.6, "total_tokens": 54810000} {"current_steps": 33570, "total_steps": 40000, "loss": 0.1006, "lr": 3.1217214584115863e-06, "epoch": 1.5197039317322711, "percentage": 83.93, "elapsed_time": "1 day, 3:27:11", "remaining_time": "5:15:30", "throughput": 554.66, "total_tokens": 54817904} {"current_steps": 33575, "total_steps": 40000, "loss": 0.1261, "lr": 3.116972607576746e-06, "epoch": 1.519930283618914, "percentage": 83.94, "elapsed_time": "1 day, 3:27:14", "remaining_time": "5:15:13", "throughput": 554.72, "total_tokens": 54825808} {"current_steps": 33580, "total_steps": 40000, "loss": 0.1311, "lr": 3.1122271313797303e-06, "epoch": 1.520156635505557, "percentage": 83.95, "elapsed_time": "1 day, 3:27:17", "remaining_time": "5:14:56", "throughput": 554.79, "total_tokens": 54833840} {"current_steps": 33585, "total_steps": 40000, "loss": 0.1232, "lr": 3.107485030552343e-06, "epoch": 1.5203829873922, "percentage": 83.96, "elapsed_time": "1 day, 3:27:21", "remaining_time": "5:14:39", "throughput": 554.85, "total_tokens": 54841744} {"current_steps": 33590, "total_steps": 40000, "loss": 0.1039, "lr": 3.1027463058258848e-06, "epoch": 1.520609339278843, "percentage": 83.97, "elapsed_time": "1 day, 3:27:24", "remaining_time": "5:14:22", "throughput": 554.91, "total_tokens": 54850192} {"current_steps": 33595, "total_steps": 40000, "loss": 0.0779, "lr": 3.0980109579311273e-06, "epoch": 1.520835691165486, "percentage": 83.99, "elapsed_time": "1 day, 3:27:27", "remaining_time": "5:14:05", "throughput": 554.98, "total_tokens": 54858544} {"current_steps": 33600, "total_steps": 40000, "loss": 0.1055, "lr": 3.093278987598314e-06, "epoch": 1.5210620430521289, "percentage": 84.0, "elapsed_time": "1 day, 3:27:31", "remaining_time": "5:13:48", "throughput": 555.04, "total_tokens": 54866672} {"current_steps": 33600, "total_steps": 40000, "eval_loss": 0.12250056862831116, "epoch": 1.5210620430521289, "percentage": 84.0, "elapsed_time": "1 day, 3:35:13", "remaining_time": "5:15:16", "throughput": 552.46, "total_tokens": 54866672} {"current_steps": 33605, "total_steps": 40000, "loss": 0.1131, "lr": 3.0885503955571826e-06, "epoch": 1.5212883949387717, "percentage": 84.01, "elapsed_time": "1 day, 3:35:18", "remaining_time": "5:15:00", "throughput": 552.52, "total_tokens": 54875120} {"current_steps": 33610, "total_steps": 40000, "loss": 0.1114, "lr": 3.0838251825369313e-06, "epoch": 1.5215147468254147, "percentage": 84.03, "elapsed_time": "1 day, 3:35:21", "remaining_time": "5:14:43", "throughput": 552.59, "total_tokens": 54883536} {"current_steps": 33615, "total_steps": 40000, "loss": 0.1019, "lr": 3.0791033492662517e-06, "epoch": 1.5217410987120576, "percentage": 84.04, "elapsed_time": "1 day, 3:35:24", "remaining_time": "5:14:26", "throughput": 552.65, "total_tokens": 54891280} {"current_steps": 33620, "total_steps": 40000, "loss": 0.1132, "lr": 3.0743848964733203e-06, "epoch": 1.5219674505987006, "percentage": 84.05, "elapsed_time": "1 day, 3:35:27", "remaining_time": "5:14:09", "throughput": 552.71, "total_tokens": 54899856} {"current_steps": 33625, "total_steps": 40000, "loss": 0.1446, "lr": 3.0696698248857625e-06, "epoch": 1.5221938024853436, "percentage": 84.06, "elapsed_time": "1 day, 3:35:30", "remaining_time": "5:13:52", "throughput": 552.78, "total_tokens": 54908016} {"current_steps": 33630, "total_steps": 40000, "loss": 0.1933, "lr": 3.0649581352307192e-06, "epoch": 1.5224201543719866, "percentage": 84.08, "elapsed_time": "1 day, 3:35:34", "remaining_time": "5:13:35", "throughput": 552.84, "total_tokens": 54916208} {"current_steps": 33635, "total_steps": 40000, "loss": 0.1163, "lr": 3.060249828234776e-06, "epoch": 1.5226465062586296, "percentage": 84.09, "elapsed_time": "1 day, 3:35:37", "remaining_time": "5:13:18", "throughput": 552.91, "total_tokens": 54924240} {"current_steps": 33640, "total_steps": 40000, "loss": 0.1077, "lr": 3.055544904624025e-06, "epoch": 1.5228728581452726, "percentage": 84.1, "elapsed_time": "1 day, 3:35:40", "remaining_time": "5:13:01", "throughput": 552.98, "total_tokens": 54932816} {"current_steps": 33645, "total_steps": 40000, "loss": 0.1111, "lr": 3.050843365124026e-06, "epoch": 1.5230992100319156, "percentage": 84.11, "elapsed_time": "1 day, 3:35:43", "remaining_time": "5:12:44", "throughput": 553.04, "total_tokens": 54940656} {"current_steps": 33650, "total_steps": 40000, "loss": 0.1052, "lr": 3.0461452104598083e-06, "epoch": 1.5233255619185586, "percentage": 84.12, "elapsed_time": "1 day, 3:35:46", "remaining_time": "5:12:27", "throughput": 553.1, "total_tokens": 54948336} {"current_steps": 33655, "total_steps": 40000, "loss": 0.1354, "lr": 3.0414504413558836e-06, "epoch": 1.5235519138052016, "percentage": 84.14, "elapsed_time": "1 day, 3:35:49", "remaining_time": "5:12:10", "throughput": 553.16, "total_tokens": 54956048} {"current_steps": 33660, "total_steps": 40000, "loss": 0.0882, "lr": 3.0367590585362564e-06, "epoch": 1.5237782656918446, "percentage": 84.15, "elapsed_time": "1 day, 3:35:53", "remaining_time": "5:11:53", "throughput": 553.22, "total_tokens": 54964080} {"current_steps": 33665, "total_steps": 40000, "loss": 0.0889, "lr": 3.0320710627243813e-06, "epoch": 1.5240046175784876, "percentage": 84.16, "elapsed_time": "1 day, 3:35:56", "remaining_time": "5:11:36", "throughput": 553.28, "total_tokens": 54972016} {"current_steps": 33670, "total_steps": 40000, "loss": 0.1745, "lr": 3.027386454643222e-06, "epoch": 1.5242309694651306, "percentage": 84.17, "elapsed_time": "1 day, 3:35:59", "remaining_time": "5:11:19", "throughput": 553.34, "total_tokens": 54979760} {"current_steps": 33675, "total_steps": 40000, "loss": 0.1249, "lr": 3.0227052350151914e-06, "epoch": 1.5244573213517736, "percentage": 84.19, "elapsed_time": "1 day, 3:36:02", "remaining_time": "5:11:02", "throughput": 553.4, "total_tokens": 54987760} {"current_steps": 33680, "total_steps": 40000, "loss": 0.0824, "lr": 3.0180274045621957e-06, "epoch": 1.5246836732384166, "percentage": 84.2, "elapsed_time": "1 day, 3:36:05", "remaining_time": "5:10:45", "throughput": 553.47, "total_tokens": 54995856} {"current_steps": 33685, "total_steps": 40000, "loss": 0.1195, "lr": 3.013352964005625e-06, "epoch": 1.5249100251250596, "percentage": 84.21, "elapsed_time": "1 day, 3:36:09", "remaining_time": "5:10:28", "throughput": 553.54, "total_tokens": 55004368} {"current_steps": 33690, "total_steps": 40000, "loss": 0.1197, "lr": 3.0086819140663218e-06, "epoch": 1.5251363770117023, "percentage": 84.23, "elapsed_time": "1 day, 3:36:12", "remaining_time": "5:10:12", "throughput": 553.6, "total_tokens": 55012432} {"current_steps": 33695, "total_steps": 40000, "loss": 0.095, "lr": 3.0040142554646265e-06, "epoch": 1.5253627288983453, "percentage": 84.24, "elapsed_time": "1 day, 3:36:15", "remaining_time": "5:09:55", "throughput": 553.66, "total_tokens": 55020592} {"current_steps": 33700, "total_steps": 40000, "loss": 0.103, "lr": 2.999349988920361e-06, "epoch": 1.5255890807849883, "percentage": 84.25, "elapsed_time": "1 day, 3:36:18", "remaining_time": "5:09:38", "throughput": 553.73, "total_tokens": 55029072} {"current_steps": 33705, "total_steps": 40000, "loss": 0.1671, "lr": 2.994689115152796e-06, "epoch": 1.5258154326716313, "percentage": 84.26, "elapsed_time": "1 day, 3:36:22", "remaining_time": "5:09:21", "throughput": 553.8, "total_tokens": 55037872} {"current_steps": 33710, "total_steps": 40000, "loss": 0.092, "lr": 2.9900316348807105e-06, "epoch": 1.5260417845582743, "percentage": 84.28, "elapsed_time": "1 day, 3:36:25", "remaining_time": "5:09:04", "throughput": 553.87, "total_tokens": 55046288} {"current_steps": 33715, "total_steps": 40000, "loss": 0.0944, "lr": 2.985377548822338e-06, "epoch": 1.5262681364449173, "percentage": 84.29, "elapsed_time": "1 day, 3:36:28", "remaining_time": "5:08:47", "throughput": 553.93, "total_tokens": 55054096} {"current_steps": 33720, "total_steps": 40000, "loss": 0.1168, "lr": 2.980726857695404e-06, "epoch": 1.52649448833156, "percentage": 84.3, "elapsed_time": "1 day, 3:36:31", "remaining_time": "5:08:30", "throughput": 553.99, "total_tokens": 55062032} {"current_steps": 33725, "total_steps": 40000, "loss": 0.0993, "lr": 2.9760795622171017e-06, "epoch": 1.526720840218203, "percentage": 84.31, "elapsed_time": "1 day, 3:36:34", "remaining_time": "5:08:13", "throughput": 554.05, "total_tokens": 55069712} {"current_steps": 33730, "total_steps": 40000, "loss": 0.1283, "lr": 2.971435663104094e-06, "epoch": 1.526947192104846, "percentage": 84.33, "elapsed_time": "1 day, 3:36:37", "remaining_time": "5:07:56", "throughput": 554.12, "total_tokens": 55078256} {"current_steps": 33735, "total_steps": 40000, "loss": 0.134, "lr": 2.9667951610725385e-06, "epoch": 1.527173543991489, "percentage": 84.34, "elapsed_time": "1 day, 3:36:41", "remaining_time": "5:07:39", "throughput": 554.18, "total_tokens": 55086416} {"current_steps": 33740, "total_steps": 40000, "loss": 0.1385, "lr": 2.9621580568380575e-06, "epoch": 1.527399895878132, "percentage": 84.35, "elapsed_time": "1 day, 3:36:44", "remaining_time": "5:07:23", "throughput": 554.25, "total_tokens": 55094960} {"current_steps": 33745, "total_steps": 40000, "loss": 0.1492, "lr": 2.9575243511157453e-06, "epoch": 1.527626247764775, "percentage": 84.36, "elapsed_time": "1 day, 3:36:47", "remaining_time": "5:07:06", "throughput": 554.31, "total_tokens": 55102992} {"current_steps": 33750, "total_steps": 40000, "loss": 0.0937, "lr": 2.952894044620186e-06, "epoch": 1.527852599651418, "percentage": 84.38, "elapsed_time": "1 day, 3:36:50", "remaining_time": "5:06:49", "throughput": 554.38, "total_tokens": 55111888} {"current_steps": 33755, "total_steps": 40000, "loss": 0.1581, "lr": 2.948267138065419e-06, "epoch": 1.528078951538061, "percentage": 84.39, "elapsed_time": "1 day, 3:36:54", "remaining_time": "5:06:32", "throughput": 554.45, "total_tokens": 55120112} {"current_steps": 33760, "total_steps": 40000, "loss": 0.0816, "lr": 2.943643632164983e-06, "epoch": 1.528305303424704, "percentage": 84.4, "elapsed_time": "1 day, 3:36:57", "remaining_time": "5:06:15", "throughput": 554.51, "total_tokens": 55128144} {"current_steps": 33765, "total_steps": 40000, "loss": 0.1547, "lr": 2.939023527631879e-06, "epoch": 1.528531655311347, "percentage": 84.41, "elapsed_time": "1 day, 3:37:00", "remaining_time": "5:05:58", "throughput": 554.58, "total_tokens": 55136464} {"current_steps": 33770, "total_steps": 40000, "loss": 0.108, "lr": 2.934406825178576e-06, "epoch": 1.52875800719799, "percentage": 84.42, "elapsed_time": "1 day, 3:37:04", "remaining_time": "5:05:42", "throughput": 554.64, "total_tokens": 55145008} {"current_steps": 33775, "total_steps": 40000, "loss": 0.1096, "lr": 2.9297935255170357e-06, "epoch": 1.528984359084633, "percentage": 84.44, "elapsed_time": "1 day, 3:37:07", "remaining_time": "5:05:25", "throughput": 554.71, "total_tokens": 55153776} {"current_steps": 33780, "total_steps": 40000, "loss": 0.1418, "lr": 2.925183629358691e-06, "epoch": 1.529210710971276, "percentage": 84.45, "elapsed_time": "1 day, 3:37:10", "remaining_time": "5:05:08", "throughput": 554.79, "total_tokens": 55162768} {"current_steps": 33785, "total_steps": 40000, "loss": 0.1444, "lr": 2.9205771374144346e-06, "epoch": 1.529437062857919, "percentage": 84.46, "elapsed_time": "1 day, 3:37:14", "remaining_time": "5:04:51", "throughput": 554.85, "total_tokens": 55171152} {"current_steps": 33790, "total_steps": 40000, "loss": 0.0639, "lr": 2.915974050394657e-06, "epoch": 1.529663414744562, "percentage": 84.47, "elapsed_time": "1 day, 3:37:17", "remaining_time": "5:04:34", "throughput": 554.92, "total_tokens": 55179600} {"current_steps": 33795, "total_steps": 40000, "loss": 0.1865, "lr": 2.9113743690092067e-06, "epoch": 1.529889766631205, "percentage": 84.49, "elapsed_time": "1 day, 3:37:20", "remaining_time": "5:04:18", "throughput": 554.99, "total_tokens": 55188208} {"current_steps": 33800, "total_steps": 40000, "loss": 0.1559, "lr": 2.906778093967402e-06, "epoch": 1.530116118517848, "percentage": 84.5, "elapsed_time": "1 day, 3:37:23", "remaining_time": "5:04:01", "throughput": 555.05, "total_tokens": 55196400} {"current_steps": 33800, "total_steps": 40000, "eval_loss": 0.12244465202093124, "epoch": 1.530116118517848, "percentage": 84.5, "elapsed_time": "1 day, 3:45:06", "remaining_time": "5:05:26", "throughput": 552.48, "total_tokens": 55196400} {"current_steps": 33805, "total_steps": 40000, "loss": 0.1256, "lr": 2.9021852259780656e-06, "epoch": 1.5303424704044908, "percentage": 84.51, "elapsed_time": "1 day, 3:45:10", "remaining_time": "5:05:09", "throughput": 552.55, "total_tokens": 55205200} {"current_steps": 33810, "total_steps": 40000, "loss": 0.1252, "lr": 2.8975957657494583e-06, "epoch": 1.5305688222911338, "percentage": 84.52, "elapsed_time": "1 day, 3:45:13", "remaining_time": "5:04:52", "throughput": 552.61, "total_tokens": 55213168} {"current_steps": 33815, "total_steps": 40000, "loss": 0.1058, "lr": 2.8930097139893417e-06, "epoch": 1.5307951741777768, "percentage": 84.54, "elapsed_time": "1 day, 3:45:17", "remaining_time": "5:04:35", "throughput": 552.67, "total_tokens": 55221616} {"current_steps": 33820, "total_steps": 40000, "loss": 0.1385, "lr": 2.888427071404945e-06, "epoch": 1.5310215260644198, "percentage": 84.55, "elapsed_time": "1 day, 3:45:20", "remaining_time": "5:04:18", "throughput": 552.75, "total_tokens": 55230576} {"current_steps": 33825, "total_steps": 40000, "loss": 0.1262, "lr": 2.8838478387029606e-06, "epoch": 1.5312478779510628, "percentage": 84.56, "elapsed_time": "1 day, 3:45:23", "remaining_time": "5:04:01", "throughput": 552.8, "total_tokens": 55238064} {"current_steps": 33830, "total_steps": 40000, "loss": 0.1233, "lr": 2.8792720165895737e-06, "epoch": 1.5314742298377055, "percentage": 84.58, "elapsed_time": "1 day, 3:45:26", "remaining_time": "5:03:44", "throughput": 552.87, "total_tokens": 55246768} {"current_steps": 33835, "total_steps": 40000, "loss": 0.1552, "lr": 2.874699605770423e-06, "epoch": 1.5317005817243485, "percentage": 84.59, "elapsed_time": "1 day, 3:45:29", "remaining_time": "5:03:28", "throughput": 552.94, "total_tokens": 55254896} {"current_steps": 33840, "total_steps": 40000, "loss": 0.088, "lr": 2.8701306069506383e-06, "epoch": 1.5319269336109915, "percentage": 84.6, "elapsed_time": "1 day, 3:45:33", "remaining_time": "5:03:11", "throughput": 553.0, "total_tokens": 55262992} {"current_steps": 33845, "total_steps": 40000, "loss": 0.1462, "lr": 2.8655650208348178e-06, "epoch": 1.5321532854976345, "percentage": 84.61, "elapsed_time": "1 day, 3:45:36", "remaining_time": "5:02:54", "throughput": 553.06, "total_tokens": 55270928} {"current_steps": 33850, "total_steps": 40000, "loss": 0.0974, "lr": 2.8610028481270257e-06, "epoch": 1.5323796373842775, "percentage": 84.62, "elapsed_time": "1 day, 3:45:39", "remaining_time": "5:02:37", "throughput": 553.13, "total_tokens": 55279120} {"current_steps": 33855, "total_steps": 40000, "loss": 0.1001, "lr": 2.856444089530813e-06, "epoch": 1.5326059892709205, "percentage": 84.64, "elapsed_time": "1 day, 3:45:42", "remaining_time": "5:02:20", "throughput": 553.18, "total_tokens": 55286512} {"current_steps": 33860, "total_steps": 40000, "loss": 0.1014, "lr": 2.8518887457491955e-06, "epoch": 1.5328323411575635, "percentage": 84.65, "elapsed_time": "1 day, 3:45:45", "remaining_time": "5:02:03", "throughput": 553.25, "total_tokens": 55294704} {"current_steps": 33865, "total_steps": 40000, "loss": 0.0485, "lr": 2.8473368174846666e-06, "epoch": 1.5330586930442065, "percentage": 84.66, "elapsed_time": "1 day, 3:45:48", "remaining_time": "5:01:46", "throughput": 553.31, "total_tokens": 55302672} {"current_steps": 33870, "total_steps": 40000, "loss": 0.1396, "lr": 2.842788305439184e-06, "epoch": 1.5332850449308495, "percentage": 84.67, "elapsed_time": "1 day, 3:45:52", "remaining_time": "5:01:29", "throughput": 553.38, "total_tokens": 55311088} {"current_steps": 33875, "total_steps": 40000, "loss": 0.1218, "lr": 2.8382432103141925e-06, "epoch": 1.5335113968174925, "percentage": 84.69, "elapsed_time": "1 day, 3:45:55", "remaining_time": "5:01:13", "throughput": 553.44, "total_tokens": 55319024} {"current_steps": 33880, "total_steps": 40000, "loss": 0.1346, "lr": 2.833701532810598e-06, "epoch": 1.5337377487041355, "percentage": 84.7, "elapsed_time": "1 day, 3:45:58", "remaining_time": "5:00:56", "throughput": 553.51, "total_tokens": 55327760} {"current_steps": 33885, "total_steps": 40000, "loss": 0.0926, "lr": 2.8291632736287877e-06, "epoch": 1.5339641005907785, "percentage": 84.71, "elapsed_time": "1 day, 3:46:01", "remaining_time": "5:00:39", "throughput": 553.57, "total_tokens": 55335600} {"current_steps": 33890, "total_steps": 40000, "loss": 0.1229, "lr": 2.824628433468615e-06, "epoch": 1.5341904524774215, "percentage": 84.72, "elapsed_time": "1 day, 3:46:04", "remaining_time": "5:00:22", "throughput": 553.63, "total_tokens": 55343152} {"current_steps": 33895, "total_steps": 40000, "loss": 0.1209, "lr": 2.8200970130294073e-06, "epoch": 1.5344168043640645, "percentage": 84.74, "elapsed_time": "1 day, 3:46:08", "remaining_time": "5:00:05", "throughput": 553.69, "total_tokens": 55350992} {"current_steps": 33900, "total_steps": 40000, "loss": 0.1386, "lr": 2.8155690130099775e-06, "epoch": 1.5346431562507075, "percentage": 84.75, "elapsed_time": "1 day, 3:46:11", "remaining_time": "4:59:48", "throughput": 553.75, "total_tokens": 55358800} {"current_steps": 33905, "total_steps": 40000, "loss": 0.1155, "lr": 2.8110444341085895e-06, "epoch": 1.5348695081373505, "percentage": 84.76, "elapsed_time": "1 day, 3:46:14", "remaining_time": "4:59:32", "throughput": 553.82, "total_tokens": 55367600} {"current_steps": 33910, "total_steps": 40000, "loss": 0.1369, "lr": 2.806523277022996e-06, "epoch": 1.5350958600239935, "percentage": 84.78, "elapsed_time": "1 day, 3:46:17", "remaining_time": "4:59:15", "throughput": 553.88, "total_tokens": 55376112} {"current_steps": 33915, "total_steps": 40000, "loss": 0.1168, "lr": 2.802005542450409e-06, "epoch": 1.5353222119106362, "percentage": 84.79, "elapsed_time": "1 day, 3:46:21", "remaining_time": "4:58:58", "throughput": 553.94, "total_tokens": 55383984} {"current_steps": 33920, "total_steps": 40000, "loss": 0.0885, "lr": 2.797491231087526e-06, "epoch": 1.5355485637972792, "percentage": 84.8, "elapsed_time": "1 day, 3:46:24", "remaining_time": "4:58:41", "throughput": 554.01, "total_tokens": 55392176} {"current_steps": 33925, "total_steps": 40000, "loss": 0.1197, "lr": 2.7929803436305137e-06, "epoch": 1.5357749156839222, "percentage": 84.81, "elapsed_time": "1 day, 3:46:27", "remaining_time": "4:58:24", "throughput": 554.07, "total_tokens": 55400432} {"current_steps": 33930, "total_steps": 40000, "loss": 0.0965, "lr": 2.788472880774998e-06, "epoch": 1.5360012675705652, "percentage": 84.82, "elapsed_time": "1 day, 3:46:30", "remaining_time": "4:58:08", "throughput": 554.13, "total_tokens": 55407952} {"current_steps": 33935, "total_steps": 40000, "loss": 0.1357, "lr": 2.7839688432160977e-06, "epoch": 1.5362276194572082, "percentage": 84.84, "elapsed_time": "1 day, 3:46:33", "remaining_time": "4:57:51", "throughput": 554.2, "total_tokens": 55416368} {"current_steps": 33940, "total_steps": 40000, "loss": 0.0824, "lr": 2.779468231648383e-06, "epoch": 1.5364539713438512, "percentage": 84.85, "elapsed_time": "1 day, 3:46:36", "remaining_time": "4:57:34", "throughput": 554.26, "total_tokens": 55424752} {"current_steps": 33945, "total_steps": 40000, "loss": 0.0907, "lr": 2.774971046765906e-06, "epoch": 1.536680323230494, "percentage": 84.86, "elapsed_time": "1 day, 3:46:40", "remaining_time": "4:57:17", "throughput": 554.33, "total_tokens": 55432688} {"current_steps": 33950, "total_steps": 40000, "loss": 0.117, "lr": 2.770477289262194e-06, "epoch": 1.536906675117137, "percentage": 84.88, "elapsed_time": "1 day, 3:46:43", "remaining_time": "4:57:00", "throughput": 554.39, "total_tokens": 55440944} {"current_steps": 33955, "total_steps": 40000, "loss": 0.1996, "lr": 2.765986959830233e-06, "epoch": 1.53713302700378, "percentage": 84.89, "elapsed_time": "1 day, 3:46:46", "remaining_time": "4:56:44", "throughput": 554.45, "total_tokens": 55448656} {"current_steps": 33960, "total_steps": 40000, "loss": 0.1333, "lr": 2.761500059162492e-06, "epoch": 1.537359378890423, "percentage": 84.9, "elapsed_time": "1 day, 3:46:49", "remaining_time": "4:56:27", "throughput": 554.52, "total_tokens": 55456976} {"current_steps": 33965, "total_steps": 40000, "loss": 0.1086, "lr": 2.757016587950914e-06, "epoch": 1.537585730777066, "percentage": 84.91, "elapsed_time": "1 day, 3:46:52", "remaining_time": "4:56:10", "throughput": 554.58, "total_tokens": 55465168} {"current_steps": 33970, "total_steps": 40000, "loss": 0.1407, "lr": 2.752536546886897e-06, "epoch": 1.537812082663709, "percentage": 84.92, "elapsed_time": "1 day, 3:46:55", "remaining_time": "4:55:53", "throughput": 554.64, "total_tokens": 55473328} {"current_steps": 33975, "total_steps": 40000, "loss": 0.078, "lr": 2.7480599366613234e-06, "epoch": 1.538038434550352, "percentage": 84.94, "elapsed_time": "1 day, 3:46:59", "remaining_time": "4:55:37", "throughput": 554.71, "total_tokens": 55481584} {"current_steps": 33980, "total_steps": 40000, "loss": 0.1621, "lr": 2.7435867579645473e-06, "epoch": 1.538264786436995, "percentage": 84.95, "elapsed_time": "1 day, 3:47:02", "remaining_time": "4:55:20", "throughput": 554.77, "total_tokens": 55489520} {"current_steps": 33985, "total_steps": 40000, "loss": 0.1003, "lr": 2.739117011486378e-06, "epoch": 1.538491138323638, "percentage": 84.96, "elapsed_time": "1 day, 3:47:05", "remaining_time": "4:55:03", "throughput": 554.83, "total_tokens": 55497552} {"current_steps": 33990, "total_steps": 40000, "loss": 0.1232, "lr": 2.7346506979161216e-06, "epoch": 1.538717490210281, "percentage": 84.97, "elapsed_time": "1 day, 3:47:08", "remaining_time": "4:54:46", "throughput": 554.9, "total_tokens": 55506032} {"current_steps": 33995, "total_steps": 40000, "loss": 0.1039, "lr": 2.7301878179425227e-06, "epoch": 1.538943842096924, "percentage": 84.99, "elapsed_time": "1 day, 3:47:11", "remaining_time": "4:54:29", "throughput": 554.96, "total_tokens": 55513776} {"current_steps": 34000, "total_steps": 40000, "loss": 0.1011, "lr": 2.7257283722538244e-06, "epoch": 1.539170193983567, "percentage": 85.0, "elapsed_time": "1 day, 3:47:15", "remaining_time": "4:54:13", "throughput": 555.03, "total_tokens": 55522928} {"current_steps": 34000, "total_steps": 40000, "eval_loss": 0.12197238951921463, "epoch": 1.539170193983567, "percentage": 85.0, "elapsed_time": "1 day, 3:54:57", "remaining_time": "4:55:34", "throughput": 552.48, "total_tokens": 55522928} {"current_steps": 34005, "total_steps": 40000, "loss": 0.0861, "lr": 2.7212723615377326e-06, "epoch": 1.53939654587021, "percentage": 85.01, "elapsed_time": "1 day, 3:55:01", "remaining_time": "4:55:18", "throughput": 552.53, "total_tokens": 55530672} {"current_steps": 34010, "total_steps": 40000, "loss": 0.1211, "lr": 2.7168197864814145e-06, "epoch": 1.539622897756853, "percentage": 85.02, "elapsed_time": "1 day, 3:55:04", "remaining_time": "4:55:01", "throughput": 552.59, "total_tokens": 55538480} {"current_steps": 34015, "total_steps": 40000, "loss": 0.1237, "lr": 2.712370647771509e-06, "epoch": 1.539849249643496, "percentage": 85.04, "elapsed_time": "1 day, 3:55:08", "remaining_time": "4:54:44", "throughput": 552.66, "total_tokens": 55546544} {"current_steps": 34020, "total_steps": 40000, "loss": 0.1123, "lr": 2.707924946094137e-06, "epoch": 1.540075601530139, "percentage": 85.05, "elapsed_time": "1 day, 3:55:11", "remaining_time": "4:54:27", "throughput": 552.72, "total_tokens": 55555184} {"current_steps": 34025, "total_steps": 40000, "loss": 0.1345, "lr": 2.7034826821348723e-06, "epoch": 1.5403019534167819, "percentage": 85.06, "elapsed_time": "1 day, 3:55:14", "remaining_time": "4:54:11", "throughput": 552.79, "total_tokens": 55563440} {"current_steps": 34030, "total_steps": 40000, "loss": 0.1334, "lr": 2.6990438565787786e-06, "epoch": 1.5405283053034247, "percentage": 85.08, "elapsed_time": "1 day, 3:55:18", "remaining_time": "4:53:54", "throughput": 552.85, "total_tokens": 55571824} {"current_steps": 34035, "total_steps": 40000, "loss": 0.0939, "lr": 2.6946084701103714e-06, "epoch": 1.5407546571900677, "percentage": 85.09, "elapsed_time": "1 day, 3:55:21", "remaining_time": "4:53:37", "throughput": 552.91, "total_tokens": 55579568} {"current_steps": 34040, "total_steps": 40000, "loss": 0.1439, "lr": 2.6901765234136428e-06, "epoch": 1.5409810090767107, "percentage": 85.1, "elapsed_time": "1 day, 3:55:24", "remaining_time": "4:53:20", "throughput": 552.98, "total_tokens": 55588432} {"current_steps": 34045, "total_steps": 40000, "loss": 0.1558, "lr": 2.685748017172063e-06, "epoch": 1.5412073609633536, "percentage": 85.11, "elapsed_time": "1 day, 3:55:27", "remaining_time": "4:53:03", "throughput": 553.05, "total_tokens": 55596912} {"current_steps": 34050, "total_steps": 40000, "loss": 0.1428, "lr": 2.681322952068549e-06, "epoch": 1.5414337128499966, "percentage": 85.12, "elapsed_time": "1 day, 3:55:31", "remaining_time": "4:52:47", "throughput": 553.12, "total_tokens": 55605616} {"current_steps": 34055, "total_steps": 40000, "loss": 0.12, "lr": 2.6769013287855137e-06, "epoch": 1.5416600647366396, "percentage": 85.14, "elapsed_time": "1 day, 3:55:34", "remaining_time": "4:52:30", "throughput": 553.18, "total_tokens": 55614000} {"current_steps": 34060, "total_steps": 40000, "loss": 0.1502, "lr": 2.6724831480048286e-06, "epoch": 1.5418864166232824, "percentage": 85.15, "elapsed_time": "1 day, 3:55:37", "remaining_time": "4:52:13", "throughput": 553.25, "total_tokens": 55621840} {"current_steps": 34065, "total_steps": 40000, "loss": 0.0785, "lr": 2.66806841040782e-06, "epoch": 1.5421127685099254, "percentage": 85.16, "elapsed_time": "1 day, 3:55:40", "remaining_time": "4:51:56", "throughput": 553.3, "total_tokens": 55629392} {"current_steps": 34070, "total_steps": 40000, "loss": 0.0994, "lr": 2.6636571166753083e-06, "epoch": 1.5423391203965684, "percentage": 85.17, "elapsed_time": "1 day, 3:55:43", "remaining_time": "4:51:39", "throughput": 553.37, "total_tokens": 55637648} {"current_steps": 34075, "total_steps": 40000, "loss": 0.14, "lr": 2.6592492674875598e-06, "epoch": 1.5425654722832114, "percentage": 85.19, "elapsed_time": "1 day, 3:55:46", "remaining_time": "4:51:23", "throughput": 553.43, "total_tokens": 55645808} {"current_steps": 34080, "total_steps": 40000, "loss": 0.067, "lr": 2.6548448635243305e-06, "epoch": 1.5427918241698544, "percentage": 85.2, "elapsed_time": "1 day, 3:55:50", "remaining_time": "4:51:06", "throughput": 553.5, "total_tokens": 55654352} {"current_steps": 34085, "total_steps": 40000, "loss": 0.0912, "lr": 2.650443905464828e-06, "epoch": 1.5430181760564974, "percentage": 85.21, "elapsed_time": "1 day, 3:55:53", "remaining_time": "4:50:49", "throughput": 553.56, "total_tokens": 55662448} {"current_steps": 34090, "total_steps": 40000, "loss": 0.1028, "lr": 2.646046393987739e-06, "epoch": 1.5432445279431404, "percentage": 85.22, "elapsed_time": "1 day, 3:55:56", "remaining_time": "4:50:32", "throughput": 553.63, "total_tokens": 55671120} {"current_steps": 34095, "total_steps": 40000, "loss": 0.1356, "lr": 2.64165232977121e-06, "epoch": 1.5434708798297834, "percentage": 85.24, "elapsed_time": "1 day, 3:55:59", "remaining_time": "4:50:16", "throughput": 553.7, "total_tokens": 55679952} {"current_steps": 34100, "total_steps": 40000, "loss": 0.1078, "lr": 2.6372617134928695e-06, "epoch": 1.5436972317164264, "percentage": 85.25, "elapsed_time": "1 day, 3:56:02", "remaining_time": "4:49:59", "throughput": 553.76, "total_tokens": 55687600} {"current_steps": 34105, "total_steps": 40000, "loss": 0.0852, "lr": 2.6328745458297943e-06, "epoch": 1.5439235836030694, "percentage": 85.26, "elapsed_time": "1 day, 3:56:05", "remaining_time": "4:49:42", "throughput": 553.82, "total_tokens": 55695248} {"current_steps": 34110, "total_steps": 40000, "loss": 0.1644, "lr": 2.6284908274585546e-06, "epoch": 1.5441499354897124, "percentage": 85.28, "elapsed_time": "1 day, 3:56:09", "remaining_time": "4:49:25", "throughput": 553.88, "total_tokens": 55703504} {"current_steps": 34115, "total_steps": 40000, "loss": 0.0911, "lr": 2.6241105590551595e-06, "epoch": 1.5443762873763554, "percentage": 85.29, "elapsed_time": "1 day, 3:56:12", "remaining_time": "4:49:09", "throughput": 553.95, "total_tokens": 55711856} {"current_steps": 34120, "total_steps": 40000, "loss": 0.1096, "lr": 2.6197337412951105e-06, "epoch": 1.5446026392629983, "percentage": 85.3, "elapsed_time": "1 day, 3:56:15", "remaining_time": "4:48:52", "throughput": 554.01, "total_tokens": 55719536} {"current_steps": 34125, "total_steps": 40000, "loss": 0.1273, "lr": 2.6153603748533705e-06, "epoch": 1.5448289911496413, "percentage": 85.31, "elapsed_time": "1 day, 3:56:18", "remaining_time": "4:48:35", "throughput": 554.07, "total_tokens": 55727696} {"current_steps": 34130, "total_steps": 40000, "loss": 0.0936, "lr": 2.6109904604043585e-06, "epoch": 1.5450553430362843, "percentage": 85.32, "elapsed_time": "1 day, 3:56:21", "remaining_time": "4:48:19", "throughput": 554.13, "total_tokens": 55735376} {"current_steps": 34135, "total_steps": 40000, "loss": 0.1329, "lr": 2.6066239986219765e-06, "epoch": 1.5452816949229273, "percentage": 85.34, "elapsed_time": "1 day, 3:56:24", "remaining_time": "4:48:02", "throughput": 554.19, "total_tokens": 55742992} {"current_steps": 34140, "total_steps": 40000, "loss": 0.1411, "lr": 2.602260990179592e-06, "epoch": 1.5455080468095703, "percentage": 85.35, "elapsed_time": "1 day, 3:56:28", "remaining_time": "4:47:45", "throughput": 554.25, "total_tokens": 55751312} {"current_steps": 34145, "total_steps": 40000, "loss": 0.1234, "lr": 2.5979014357500248e-06, "epoch": 1.545734398696213, "percentage": 85.36, "elapsed_time": "1 day, 3:56:31", "remaining_time": "4:47:28", "throughput": 554.32, "total_tokens": 55759696} {"current_steps": 34150, "total_steps": 40000, "loss": 0.1306, "lr": 2.5935453360055844e-06, "epoch": 1.545960750582856, "percentage": 85.38, "elapsed_time": "1 day, 3:56:34", "remaining_time": "4:47:12", "throughput": 554.38, "total_tokens": 55767632} {"current_steps": 34155, "total_steps": 40000, "loss": 0.1067, "lr": 2.5891926916180283e-06, "epoch": 1.546187102469499, "percentage": 85.39, "elapsed_time": "1 day, 3:56:37", "remaining_time": "4:46:55", "throughput": 554.44, "total_tokens": 55775920} {"current_steps": 34160, "total_steps": 40000, "loss": 0.1329, "lr": 2.5848435032585883e-06, "epoch": 1.546413454356142, "percentage": 85.4, "elapsed_time": "1 day, 3:56:41", "remaining_time": "4:46:38", "throughput": 554.51, "total_tokens": 55784208} {"current_steps": 34165, "total_steps": 40000, "loss": 0.1553, "lr": 2.58049777159797e-06, "epoch": 1.546639806242785, "percentage": 85.41, "elapsed_time": "1 day, 3:56:44", "remaining_time": "4:46:22", "throughput": 554.57, "total_tokens": 55792208} {"current_steps": 34170, "total_steps": 40000, "loss": 0.1781, "lr": 2.576155497306332e-06, "epoch": 1.5468661581294278, "percentage": 85.42, "elapsed_time": "1 day, 3:56:47", "remaining_time": "4:46:05", "throughput": 554.64, "total_tokens": 55801488} {"current_steps": 34175, "total_steps": 40000, "loss": 0.1526, "lr": 2.57181668105331e-06, "epoch": 1.5470925100160708, "percentage": 85.44, "elapsed_time": "1 day, 3:56:50", "remaining_time": "4:45:48", "throughput": 554.71, "total_tokens": 55809840} {"current_steps": 34180, "total_steps": 40000, "loss": 0.0901, "lr": 2.567481323508014e-06, "epoch": 1.5473188619027138, "percentage": 85.45, "elapsed_time": "1 day, 3:56:54", "remaining_time": "4:45:32", "throughput": 554.78, "total_tokens": 55818384} {"current_steps": 34185, "total_steps": 40000, "loss": 0.1524, "lr": 2.5631494253389954e-06, "epoch": 1.5475452137893568, "percentage": 85.46, "elapsed_time": "1 day, 3:56:57", "remaining_time": "4:45:15", "throughput": 554.85, "total_tokens": 55827312} {"current_steps": 34190, "total_steps": 40000, "loss": 0.1368, "lr": 2.5588209872142997e-06, "epoch": 1.5477715656759998, "percentage": 85.47, "elapsed_time": "1 day, 3:57:00", "remaining_time": "4:44:58", "throughput": 554.91, "total_tokens": 55835056} {"current_steps": 34195, "total_steps": 40000, "loss": 0.1528, "lr": 2.5544960098014186e-06, "epoch": 1.5479979175626428, "percentage": 85.49, "elapsed_time": "1 day, 3:57:04", "remaining_time": "4:44:42", "throughput": 554.97, "total_tokens": 55843824} {"current_steps": 34200, "total_steps": 40000, "loss": 0.1099, "lr": 2.550174493767318e-06, "epoch": 1.5482242694492858, "percentage": 85.5, "elapsed_time": "1 day, 3:57:07", "remaining_time": "4:44:25", "throughput": 555.04, "total_tokens": 55851984} {"current_steps": 34200, "total_steps": 40000, "eval_loss": 0.12196372449398041, "epoch": 1.5482242694492858, "percentage": 85.5, "elapsed_time": "1 day, 4:04:50", "remaining_time": "4:45:43", "throughput": 552.5, "total_tokens": 55851984} {"current_steps": 34205, "total_steps": 40000, "loss": 0.1023, "lr": 2.545856439778438e-06, "epoch": 1.5484506213359288, "percentage": 85.51, "elapsed_time": "1 day, 4:04:54", "remaining_time": "4:45:27", "throughput": 552.56, "total_tokens": 55860496} {"current_steps": 34210, "total_steps": 40000, "loss": 0.1396, "lr": 2.541541848500667e-06, "epoch": 1.5486769732225718, "percentage": 85.52, "elapsed_time": "1 day, 4:04:57", "remaining_time": "4:45:10", "throughput": 552.63, "total_tokens": 55869168} {"current_steps": 34215, "total_steps": 40000, "loss": 0.0906, "lr": 2.5372307205993733e-06, "epoch": 1.5489033251092148, "percentage": 85.54, "elapsed_time": "1 day, 4:05:00", "remaining_time": "4:44:53", "throughput": 552.69, "total_tokens": 55876880} {"current_steps": 34220, "total_steps": 40000, "loss": 0.1067, "lr": 2.5329230567393917e-06, "epoch": 1.5491296769958578, "percentage": 85.55, "elapsed_time": "1 day, 4:05:03", "remaining_time": "4:44:37", "throughput": 552.75, "total_tokens": 55884944} {"current_steps": 34225, "total_steps": 40000, "loss": 0.0917, "lr": 2.5286188575850164e-06, "epoch": 1.5493560288825008, "percentage": 85.56, "elapsed_time": "1 day, 4:05:06", "remaining_time": "4:44:20", "throughput": 552.81, "total_tokens": 55893360} {"current_steps": 34230, "total_steps": 40000, "loss": 0.1243, "lr": 2.5243181237999984e-06, "epoch": 1.5495823807691438, "percentage": 85.58, "elapsed_time": "1 day, 4:05:10", "remaining_time": "4:44:03", "throughput": 552.88, "total_tokens": 55901904} {"current_steps": 34235, "total_steps": 40000, "loss": 0.1624, "lr": 2.520020856047578e-06, "epoch": 1.5498087326557868, "percentage": 85.59, "elapsed_time": "1 day, 4:05:13", "remaining_time": "4:43:46", "throughput": 552.95, "total_tokens": 55910448} {"current_steps": 34240, "total_steps": 40000, "loss": 0.1377, "lr": 2.515727054990438e-06, "epoch": 1.5500350845424298, "percentage": 85.6, "elapsed_time": "1 day, 4:05:16", "remaining_time": "4:43:30", "throughput": 553.01, "total_tokens": 55918288} {"current_steps": 34245, "total_steps": 40000, "loss": 0.1069, "lr": 2.511436721290747e-06, "epoch": 1.5502614364290728, "percentage": 85.61, "elapsed_time": "1 day, 4:05:19", "remaining_time": "4:43:13", "throughput": 553.07, "total_tokens": 55926160} {"current_steps": 34250, "total_steps": 40000, "loss": 0.1044, "lr": 2.5071498556101164e-06, "epoch": 1.5504877883157158, "percentage": 85.62, "elapsed_time": "1 day, 4:05:22", "remaining_time": "4:42:56", "throughput": 553.14, "total_tokens": 55934672} {"current_steps": 34255, "total_steps": 40000, "loss": 0.0854, "lr": 2.5028664586096485e-06, "epoch": 1.5507141402023585, "percentage": 85.64, "elapsed_time": "1 day, 4:05:26", "remaining_time": "4:42:40", "throughput": 553.19, "total_tokens": 55942416} {"current_steps": 34260, "total_steps": 40000, "loss": 0.1164, "lr": 2.498586530949881e-06, "epoch": 1.5509404920890015, "percentage": 85.65, "elapsed_time": "1 day, 4:05:29", "remaining_time": "4:42:23", "throughput": 553.26, "total_tokens": 55951056} {"current_steps": 34265, "total_steps": 40000, "loss": 0.0849, "lr": 2.4943100732908427e-06, "epoch": 1.5511668439756445, "percentage": 85.66, "elapsed_time": "1 day, 4:05:32", "remaining_time": "4:42:06", "throughput": 553.33, "total_tokens": 55959152} {"current_steps": 34270, "total_steps": 40000, "loss": 0.1301, "lr": 2.4900370862920188e-06, "epoch": 1.5513931958622875, "percentage": 85.67, "elapsed_time": "1 day, 4:05:35", "remaining_time": "4:41:50", "throughput": 553.4, "total_tokens": 55968080} {"current_steps": 34275, "total_steps": 40000, "loss": 0.0762, "lr": 2.4857675706123518e-06, "epoch": 1.5516195477489305, "percentage": 85.69, "elapsed_time": "1 day, 4:05:38", "remaining_time": "4:41:33", "throughput": 553.46, "total_tokens": 55976240} {"current_steps": 34280, "total_steps": 40000, "loss": 0.1365, "lr": 2.4815015269102543e-06, "epoch": 1.5518458996355735, "percentage": 85.7, "elapsed_time": "1 day, 4:05:42", "remaining_time": "4:41:16", "throughput": 553.52, "total_tokens": 55984208} {"current_steps": 34285, "total_steps": 40000, "loss": 0.1042, "lr": 2.477238955843611e-06, "epoch": 1.5520722515222163, "percentage": 85.71, "elapsed_time": "1 day, 4:05:45", "remaining_time": "4:41:00", "throughput": 553.58, "total_tokens": 55991856} {"current_steps": 34290, "total_steps": 40000, "loss": 0.1677, "lr": 2.4729798580697573e-06, "epoch": 1.5522986034088593, "percentage": 85.72, "elapsed_time": "1 day, 4:05:48", "remaining_time": "4:40:43", "throughput": 553.64, "total_tokens": 55999568} {"current_steps": 34295, "total_steps": 40000, "loss": 0.0947, "lr": 2.4687242342455034e-06, "epoch": 1.5525249552955023, "percentage": 85.74, "elapsed_time": "1 day, 4:05:51", "remaining_time": "4:40:26", "throughput": 553.7, "total_tokens": 56007280} {"current_steps": 34300, "total_steps": 40000, "loss": 0.1364, "lr": 2.4644720850271196e-06, "epoch": 1.5527513071821453, "percentage": 85.75, "elapsed_time": "1 day, 4:05:54", "remaining_time": "4:40:10", "throughput": 553.76, "total_tokens": 56015728} {"current_steps": 34305, "total_steps": 40000, "loss": 0.0931, "lr": 2.4602234110703364e-06, "epoch": 1.5529776590687883, "percentage": 85.76, "elapsed_time": "1 day, 4:05:58", "remaining_time": "4:39:53", "throughput": 553.83, "total_tokens": 56024144} {"current_steps": 34310, "total_steps": 40000, "loss": 0.1331, "lr": 2.4559782130303576e-06, "epoch": 1.5532040109554313, "percentage": 85.78, "elapsed_time": "1 day, 4:06:01", "remaining_time": "4:39:36", "throughput": 553.89, "total_tokens": 56031792} {"current_steps": 34315, "total_steps": 40000, "loss": 0.1705, "lr": 2.451736491561843e-06, "epoch": 1.5534303628420743, "percentage": 85.79, "elapsed_time": "1 day, 4:06:04", "remaining_time": "4:39:20", "throughput": 553.95, "total_tokens": 56040400} {"current_steps": 34320, "total_steps": 40000, "loss": 0.1304, "lr": 2.4474982473189163e-06, "epoch": 1.5536567147287172, "percentage": 85.8, "elapsed_time": "1 day, 4:06:07", "remaining_time": "4:39:03", "throughput": 554.02, "total_tokens": 56048688} {"current_steps": 34325, "total_steps": 40000, "loss": 0.0929, "lr": 2.4432634809551796e-06, "epoch": 1.5538830666153602, "percentage": 85.81, "elapsed_time": "1 day, 4:06:11", "remaining_time": "4:38:46", "throughput": 554.08, "total_tokens": 56057072} {"current_steps": 34330, "total_steps": 40000, "loss": 0.0984, "lr": 2.439032193123675e-06, "epoch": 1.5541094185020032, "percentage": 85.82, "elapsed_time": "1 day, 4:06:14", "remaining_time": "4:38:30", "throughput": 554.14, "total_tokens": 56064624} {"current_steps": 34335, "total_steps": 40000, "loss": 0.1634, "lr": 2.4348043844769297e-06, "epoch": 1.5543357703886462, "percentage": 85.84, "elapsed_time": "1 day, 4:06:17", "remaining_time": "4:38:13", "throughput": 554.2, "total_tokens": 56072688} {"current_steps": 34340, "total_steps": 40000, "loss": 0.1313, "lr": 2.4305800556669146e-06, "epoch": 1.5545621222752892, "percentage": 85.85, "elapsed_time": "1 day, 4:06:20", "remaining_time": "4:37:56", "throughput": 554.26, "total_tokens": 56080656} {"current_steps": 34345, "total_steps": 40000, "loss": 0.124, "lr": 2.426359207345083e-06, "epoch": 1.5547884741619322, "percentage": 85.86, "elapsed_time": "1 day, 4:06:23", "remaining_time": "4:37:40", "throughput": 554.32, "total_tokens": 56088592} {"current_steps": 34350, "total_steps": 40000, "loss": 0.1449, "lr": 2.4221418401623396e-06, "epoch": 1.5550148260485752, "percentage": 85.88, "elapsed_time": "1 day, 4:06:26", "remaining_time": "4:37:23", "throughput": 554.38, "total_tokens": 56096528} {"current_steps": 34355, "total_steps": 40000, "loss": 0.0997, "lr": 2.4179279547690557e-06, "epoch": 1.5552411779352182, "percentage": 85.89, "elapsed_time": "1 day, 4:06:30", "remaining_time": "4:37:06", "throughput": 554.45, "total_tokens": 56105200} {"current_steps": 34360, "total_steps": 40000, "loss": 0.1357, "lr": 2.413717551815062e-06, "epoch": 1.5554675298218612, "percentage": 85.9, "elapsed_time": "1 day, 4:06:33", "remaining_time": "4:36:50", "throughput": 554.52, "total_tokens": 56113328} {"current_steps": 34365, "total_steps": 40000, "loss": 0.1113, "lr": 2.409510631949666e-06, "epoch": 1.5556938817085042, "percentage": 85.91, "elapsed_time": "1 day, 4:06:36", "remaining_time": "4:36:33", "throughput": 554.58, "total_tokens": 56121200} {"current_steps": 34370, "total_steps": 40000, "loss": 0.0605, "lr": 2.405307195821618e-06, "epoch": 1.555920233595147, "percentage": 85.92, "elapsed_time": "1 day, 4:06:39", "remaining_time": "4:36:17", "throughput": 554.64, "total_tokens": 56129552} {"current_steps": 34375, "total_steps": 40000, "loss": 0.1435, "lr": 2.4011072440791372e-06, "epoch": 1.55614658548179, "percentage": 85.94, "elapsed_time": "1 day, 4:06:42", "remaining_time": "4:36:00", "throughput": 554.7, "total_tokens": 56137488} {"current_steps": 34380, "total_steps": 40000, "loss": 0.1097, "lr": 2.3969107773699233e-06, "epoch": 1.556372937368433, "percentage": 85.95, "elapsed_time": "1 day, 4:06:46", "remaining_time": "4:35:43", "throughput": 554.77, "total_tokens": 56145776} {"current_steps": 34385, "total_steps": 40000, "loss": 0.1916, "lr": 2.3927177963411096e-06, "epoch": 1.556599289255076, "percentage": 85.96, "elapsed_time": "1 day, 4:06:49", "remaining_time": "4:35:27", "throughput": 554.83, "total_tokens": 56154448} {"current_steps": 34390, "total_steps": 40000, "loss": 0.1759, "lr": 2.3885283016393144e-06, "epoch": 1.556825641141719, "percentage": 85.97, "elapsed_time": "1 day, 4:06:52", "remaining_time": "4:35:10", "throughput": 554.9, "total_tokens": 56162736} {"current_steps": 34395, "total_steps": 40000, "loss": 0.0706, "lr": 2.3843422939106076e-06, "epoch": 1.5570519930283617, "percentage": 85.99, "elapsed_time": "1 day, 4:06:55", "remaining_time": "4:34:54", "throughput": 554.96, "total_tokens": 56171184} {"current_steps": 34400, "total_steps": 40000, "loss": 0.0908, "lr": 2.380159773800525e-06, "epoch": 1.5572783449150047, "percentage": 86.0, "elapsed_time": "1 day, 4:06:59", "remaining_time": "4:34:37", "throughput": 555.03, "total_tokens": 56180080} {"current_steps": 34400, "total_steps": 40000, "eval_loss": 0.12207600474357605, "epoch": 1.5572783449150047, "percentage": 86.0, "elapsed_time": "1 day, 4:14:42", "remaining_time": "4:35:52", "throughput": 552.51, "total_tokens": 56180080} {"current_steps": 34405, "total_steps": 40000, "loss": 0.1688, "lr": 2.3759807419540675e-06, "epoch": 1.5575046968016477, "percentage": 86.01, "elapsed_time": "1 day, 4:14:46", "remaining_time": "4:35:36", "throughput": 552.56, "total_tokens": 56187632} {"current_steps": 34410, "total_steps": 40000, "loss": 0.1491, "lr": 2.3718051990156835e-06, "epoch": 1.5577310486882907, "percentage": 86.02, "elapsed_time": "1 day, 4:14:49", "remaining_time": "4:35:19", "throughput": 552.62, "total_tokens": 56195600} {"current_steps": 34415, "total_steps": 40000, "loss": 0.0914, "lr": 2.367633145629311e-06, "epoch": 1.5579574005749337, "percentage": 86.04, "elapsed_time": "1 day, 4:14:52", "remaining_time": "4:35:03", "throughput": 552.68, "total_tokens": 56203952} {"current_steps": 34420, "total_steps": 40000, "loss": 0.0641, "lr": 2.363464582438316e-06, "epoch": 1.5581837524615767, "percentage": 86.05, "elapsed_time": "1 day, 4:14:55", "remaining_time": "4:34:46", "throughput": 552.75, "total_tokens": 56212528} {"current_steps": 34425, "total_steps": 40000, "loss": 0.0555, "lr": 2.3592995100855526e-06, "epoch": 1.5584101043482197, "percentage": 86.06, "elapsed_time": "1 day, 4:14:58", "remaining_time": "4:34:29", "throughput": 552.81, "total_tokens": 56220432} {"current_steps": 34430, "total_steps": 40000, "loss": 0.1718, "lr": 2.3551379292133273e-06, "epoch": 1.5586364562348627, "percentage": 86.08, "elapsed_time": "1 day, 4:15:02", "remaining_time": "4:34:13", "throughput": 552.88, "total_tokens": 56228784} {"current_steps": 34435, "total_steps": 40000, "loss": 0.079, "lr": 2.3509798404634047e-06, "epoch": 1.5588628081215057, "percentage": 86.09, "elapsed_time": "1 day, 4:15:05", "remaining_time": "4:33:56", "throughput": 552.94, "total_tokens": 56236976} {"current_steps": 34440, "total_steps": 40000, "loss": 0.0843, "lr": 2.346825244477019e-06, "epoch": 1.5590891600081487, "percentage": 86.1, "elapsed_time": "1 day, 4:15:08", "remaining_time": "4:33:39", "throughput": 553.01, "total_tokens": 56246032} {"current_steps": 34445, "total_steps": 40000, "loss": 0.1376, "lr": 2.3426741418948545e-06, "epoch": 1.5593155118947917, "percentage": 86.11, "elapsed_time": "1 day, 4:15:11", "remaining_time": "4:33:23", "throughput": 553.07, "total_tokens": 56254160} {"current_steps": 34450, "total_steps": 40000, "loss": 0.1294, "lr": 2.3385265333570715e-06, "epoch": 1.5595418637814347, "percentage": 86.12, "elapsed_time": "1 day, 4:15:15", "remaining_time": "4:33:06", "throughput": 553.14, "total_tokens": 56262640} {"current_steps": 34455, "total_steps": 40000, "loss": 0.1189, "lr": 2.334382419503278e-06, "epoch": 1.5597682156680777, "percentage": 86.14, "elapsed_time": "1 day, 4:15:18", "remaining_time": "4:32:49", "throughput": 553.21, "total_tokens": 56271152} {"current_steps": 34460, "total_steps": 40000, "loss": 0.0811, "lr": 2.3302418009725465e-06, "epoch": 1.5599945675547207, "percentage": 86.15, "elapsed_time": "1 day, 4:15:21", "remaining_time": "4:32:33", "throughput": 553.27, "total_tokens": 56279568} {"current_steps": 34465, "total_steps": 40000, "loss": 0.0771, "lr": 2.326104678403415e-06, "epoch": 1.5602209194413637, "percentage": 86.16, "elapsed_time": "1 day, 4:15:24", "remaining_time": "4:32:16", "throughput": 553.33, "total_tokens": 56287536} {"current_steps": 34470, "total_steps": 40000, "loss": 0.0898, "lr": 2.321971052433883e-06, "epoch": 1.5604472713280066, "percentage": 86.17, "elapsed_time": "1 day, 4:15:27", "remaining_time": "4:32:00", "throughput": 553.39, "total_tokens": 56295472} {"current_steps": 34475, "total_steps": 40000, "loss": 0.1264, "lr": 2.3178409237014004e-06, "epoch": 1.5606736232146496, "percentage": 86.19, "elapsed_time": "1 day, 4:15:31", "remaining_time": "4:31:43", "throughput": 553.45, "total_tokens": 56303184} {"current_steps": 34480, "total_steps": 40000, "loss": 0.1077, "lr": 2.313714292842889e-06, "epoch": 1.5608999751012924, "percentage": 86.2, "elapsed_time": "1 day, 4:15:34", "remaining_time": "4:31:26", "throughput": 553.51, "total_tokens": 56310768} {"current_steps": 34485, "total_steps": 40000, "loss": 0.0882, "lr": 2.309591160494734e-06, "epoch": 1.5611263269879354, "percentage": 86.21, "elapsed_time": "1 day, 4:15:37", "remaining_time": "4:31:10", "throughput": 553.57, "total_tokens": 56318832} {"current_steps": 34490, "total_steps": 40000, "loss": 0.1206, "lr": 2.305471527292763e-06, "epoch": 1.5613526788745784, "percentage": 86.22, "elapsed_time": "1 day, 4:15:40", "remaining_time": "4:30:53", "throughput": 553.63, "total_tokens": 56327120} {"current_steps": 34495, "total_steps": 40000, "loss": 0.1081, "lr": 2.3013553938722817e-06, "epoch": 1.5615790307612214, "percentage": 86.24, "elapsed_time": "1 day, 4:15:43", "remaining_time": "4:30:37", "throughput": 553.7, "total_tokens": 56335792} {"current_steps": 34500, "total_steps": 40000, "loss": 0.1583, "lr": 2.297242760868043e-06, "epoch": 1.5618053826478644, "percentage": 86.25, "elapsed_time": "1 day, 4:15:47", "remaining_time": "4:30:20", "throughput": 553.77, "total_tokens": 56344720} {"current_steps": 34505, "total_steps": 40000, "loss": 0.1183, "lr": 2.2931336289142735e-06, "epoch": 1.5620317345345074, "percentage": 86.26, "elapsed_time": "1 day, 4:15:50", "remaining_time": "4:30:04", "throughput": 553.84, "total_tokens": 56353072} {"current_steps": 34510, "total_steps": 40000, "loss": 0.0893, "lr": 2.289027998644655e-06, "epoch": 1.5622580864211502, "percentage": 86.28, "elapsed_time": "1 day, 4:15:53", "remaining_time": "4:29:47", "throughput": 553.89, "total_tokens": 56360432} {"current_steps": 34515, "total_steps": 40000, "loss": 0.0903, "lr": 2.2849258706923228e-06, "epoch": 1.5624844383077932, "percentage": 86.29, "elapsed_time": "1 day, 4:15:56", "remaining_time": "4:29:30", "throughput": 553.95, "total_tokens": 56368016} {"current_steps": 34520, "total_steps": 40000, "loss": 0.1121, "lr": 2.2808272456898705e-06, "epoch": 1.5627107901944362, "percentage": 86.3, "elapsed_time": "1 day, 4:16:00", "remaining_time": "4:29:14", "throughput": 554.01, "total_tokens": 56376240} {"current_steps": 34525, "total_steps": 40000, "loss": 0.1396, "lr": 2.2767321242693707e-06, "epoch": 1.5629371420810791, "percentage": 86.31, "elapsed_time": "1 day, 4:16:03", "remaining_time": "4:28:57", "throughput": 554.08, "total_tokens": 56384528} {"current_steps": 34530, "total_steps": 40000, "loss": 0.1561, "lr": 2.272640507062329e-06, "epoch": 1.5631634939677221, "percentage": 86.33, "elapsed_time": "1 day, 4:16:06", "remaining_time": "4:28:41", "throughput": 554.14, "total_tokens": 56392624} {"current_steps": 34535, "total_steps": 40000, "loss": 0.0765, "lr": 2.2685523946997382e-06, "epoch": 1.5633898458543651, "percentage": 86.34, "elapsed_time": "1 day, 4:16:09", "remaining_time": "4:28:24", "throughput": 554.2, "total_tokens": 56400624} {"current_steps": 34540, "total_steps": 40000, "loss": 0.1333, "lr": 2.2644677878120245e-06, "epoch": 1.5636161977410081, "percentage": 86.35, "elapsed_time": "1 day, 4:16:12", "remaining_time": "4:28:08", "throughput": 554.26, "total_tokens": 56409040} {"current_steps": 34545, "total_steps": 40000, "loss": 0.1272, "lr": 2.2603866870290897e-06, "epoch": 1.5638425496276511, "percentage": 86.36, "elapsed_time": "1 day, 4:16:16", "remaining_time": "4:27:51", "throughput": 554.32, "total_tokens": 56416464} {"current_steps": 34550, "total_steps": 40000, "loss": 0.1826, "lr": 2.256309092980294e-06, "epoch": 1.5640689015142941, "percentage": 86.38, "elapsed_time": "1 day, 4:16:19", "remaining_time": "4:27:34", "throughput": 554.38, "total_tokens": 56424464} {"current_steps": 34555, "total_steps": 40000, "loss": 0.0973, "lr": 2.252235006294448e-06, "epoch": 1.5642952534009371, "percentage": 86.39, "elapsed_time": "1 day, 4:16:22", "remaining_time": "4:27:18", "throughput": 554.45, "total_tokens": 56433104} {"current_steps": 34560, "total_steps": 40000, "loss": 0.1134, "lr": 2.2481644275998333e-06, "epoch": 1.56452160528758, "percentage": 86.4, "elapsed_time": "1 day, 4:16:25", "remaining_time": "4:27:01", "throughput": 554.51, "total_tokens": 56441360} {"current_steps": 34565, "total_steps": 40000, "loss": 0.1424, "lr": 2.2440973575241832e-06, "epoch": 1.564747957174223, "percentage": 86.41, "elapsed_time": "1 day, 4:16:29", "remaining_time": "4:26:45", "throughput": 554.58, "total_tokens": 56449680} {"current_steps": 34570, "total_steps": 40000, "loss": 0.2151, "lr": 2.240033796694685e-06, "epoch": 1.564974309060866, "percentage": 86.42, "elapsed_time": "1 day, 4:16:32", "remaining_time": "4:26:28", "throughput": 554.64, "total_tokens": 56458224} {"current_steps": 34575, "total_steps": 40000, "loss": 0.1117, "lr": 2.235973745737999e-06, "epoch": 1.565200660947509, "percentage": 86.44, "elapsed_time": "1 day, 4:16:35", "remaining_time": "4:26:12", "throughput": 554.71, "total_tokens": 56466544} {"current_steps": 34580, "total_steps": 40000, "loss": 0.0715, "lr": 2.2319172052802263e-06, "epoch": 1.565427012834152, "percentage": 86.45, "elapsed_time": "1 day, 4:16:38", "remaining_time": "4:25:55", "throughput": 554.77, "total_tokens": 56474864} {"current_steps": 34585, "total_steps": 40000, "loss": 0.1704, "lr": 2.2278641759469477e-06, "epoch": 1.565653364720795, "percentage": 86.46, "elapsed_time": "1 day, 4:16:41", "remaining_time": "4:25:39", "throughput": 554.83, "total_tokens": 56482864} {"current_steps": 34590, "total_steps": 40000, "loss": 0.1119, "lr": 2.2238146583631825e-06, "epoch": 1.565879716607438, "percentage": 86.48, "elapsed_time": "1 day, 4:16:45", "remaining_time": "4:25:22", "throughput": 554.89, "total_tokens": 56490864} {"current_steps": 34595, "total_steps": 40000, "loss": 0.132, "lr": 2.2197686531534256e-06, "epoch": 1.5661060684940808, "percentage": 86.49, "elapsed_time": "1 day, 4:16:48", "remaining_time": "4:25:06", "throughput": 554.96, "total_tokens": 56499088} {"current_steps": 34600, "total_steps": 40000, "loss": 0.1314, "lr": 2.2157261609416087e-06, "epoch": 1.5663324203807238, "percentage": 86.5, "elapsed_time": "1 day, 4:16:51", "remaining_time": "4:24:49", "throughput": 555.03, "total_tokens": 56508016} {"current_steps": 34600, "total_steps": 40000, "eval_loss": 0.12212986499071121, "epoch": 1.5663324203807238, "percentage": 86.5, "elapsed_time": "1 day, 4:24:34", "remaining_time": "4:26:01", "throughput": 552.51, "total_tokens": 56508016} {"current_steps": 34605, "total_steps": 40000, "loss": 0.1037, "lr": 2.211687182351149e-06, "epoch": 1.5665587722673668, "percentage": 86.51, "elapsed_time": "1 day, 4:24:38", "remaining_time": "4:25:45", "throughput": 552.58, "total_tokens": 56516464} {"current_steps": 34610, "total_steps": 40000, "loss": 0.126, "lr": 2.2076517180048993e-06, "epoch": 1.5667851241540098, "percentage": 86.52, "elapsed_time": "1 day, 4:24:41", "remaining_time": "4:25:28", "throughput": 552.64, "total_tokens": 56525008} {"current_steps": 34615, "total_steps": 40000, "loss": 0.0649, "lr": 2.2036197685251834e-06, "epoch": 1.5670114760406528, "percentage": 86.54, "elapsed_time": "1 day, 4:24:44", "remaining_time": "4:25:12", "throughput": 552.71, "total_tokens": 56533744} {"current_steps": 34620, "total_steps": 40000, "loss": 0.0977, "lr": 2.199591334533771e-06, "epoch": 1.5672378279272958, "percentage": 86.55, "elapsed_time": "1 day, 4:24:48", "remaining_time": "4:24:55", "throughput": 552.77, "total_tokens": 56541648} {"current_steps": 34625, "total_steps": 40000, "loss": 0.1378, "lr": 2.1955664166519036e-06, "epoch": 1.5674641798139386, "percentage": 86.56, "elapsed_time": "1 day, 4:24:51", "remaining_time": "4:24:39", "throughput": 552.83, "total_tokens": 56549712} {"current_steps": 34630, "total_steps": 40000, "loss": 0.1201, "lr": 2.1915450155002793e-06, "epoch": 1.5676905317005816, "percentage": 86.58, "elapsed_time": "1 day, 4:24:54", "remaining_time": "4:24:22", "throughput": 552.9, "total_tokens": 56558608} {"current_steps": 34635, "total_steps": 40000, "loss": 0.1212, "lr": 2.187527131699038e-06, "epoch": 1.5679168835872246, "percentage": 86.59, "elapsed_time": "1 day, 4:24:57", "remaining_time": "4:24:06", "throughput": 552.96, "total_tokens": 56566352} {"current_steps": 34640, "total_steps": 40000, "loss": 0.1736, "lr": 2.18351276586779e-06, "epoch": 1.5681432354738676, "percentage": 86.6, "elapsed_time": "1 day, 4:25:00", "remaining_time": "4:23:49", "throughput": 553.02, "total_tokens": 56574384} {"current_steps": 34645, "total_steps": 40000, "loss": 0.119, "lr": 2.1795019186256092e-06, "epoch": 1.5683695873605106, "percentage": 86.61, "elapsed_time": "1 day, 4:25:04", "remaining_time": "4:23:32", "throughput": 553.08, "total_tokens": 56582832} {"current_steps": 34650, "total_steps": 40000, "loss": 0.1057, "lr": 2.1754945905910094e-06, "epoch": 1.5685959392471536, "percentage": 86.62, "elapsed_time": "1 day, 4:25:07", "remaining_time": "4:23:16", "throughput": 553.14, "total_tokens": 56590544} {"current_steps": 34655, "total_steps": 40000, "loss": 0.094, "lr": 2.171490782381977e-06, "epoch": 1.5688222911337966, "percentage": 86.64, "elapsed_time": "1 day, 4:25:10", "remaining_time": "4:22:59", "throughput": 553.2, "total_tokens": 56598032} {"current_steps": 34660, "total_steps": 40000, "loss": 0.1042, "lr": 2.1674904946159425e-06, "epoch": 1.5690486430204396, "percentage": 86.65, "elapsed_time": "1 day, 4:25:13", "remaining_time": "4:22:43", "throughput": 553.26, "total_tokens": 56605776} {"current_steps": 34665, "total_steps": 40000, "loss": 0.1227, "lr": 2.16349372790981e-06, "epoch": 1.5692749949070826, "percentage": 86.66, "elapsed_time": "1 day, 4:25:16", "remaining_time": "4:22:26", "throughput": 553.32, "total_tokens": 56614096} {"current_steps": 34670, "total_steps": 40000, "loss": 0.157, "lr": 2.159500482879928e-06, "epoch": 1.5695013467937255, "percentage": 86.67, "elapsed_time": "1 day, 4:25:19", "remaining_time": "4:22:10", "throughput": 553.38, "total_tokens": 56622064} {"current_steps": 34675, "total_steps": 40000, "loss": 0.1319, "lr": 2.155510760142096e-06, "epoch": 1.5697276986803685, "percentage": 86.69, "elapsed_time": "1 day, 4:25:22", "remaining_time": "4:21:53", "throughput": 553.44, "total_tokens": 56630064} {"current_steps": 34680, "total_steps": 40000, "loss": 0.1233, "lr": 2.151524560311588e-06, "epoch": 1.5699540505670115, "percentage": 86.7, "elapsed_time": "1 day, 4:25:26", "remaining_time": "4:21:37", "throughput": 553.51, "total_tokens": 56638064} {"current_steps": 34685, "total_steps": 40000, "loss": 0.1554, "lr": 2.147541884003129e-06, "epoch": 1.5701804024536545, "percentage": 86.71, "elapsed_time": "1 day, 4:25:29", "remaining_time": "4:21:20", "throughput": 553.57, "total_tokens": 56646160} {"current_steps": 34690, "total_steps": 40000, "loss": 0.0853, "lr": 2.1435627318308895e-06, "epoch": 1.5704067543402975, "percentage": 86.72, "elapsed_time": "1 day, 4:25:32", "remaining_time": "4:21:04", "throughput": 553.63, "total_tokens": 56654000} {"current_steps": 34695, "total_steps": 40000, "loss": 0.1194, "lr": 2.139587104408511e-06, "epoch": 1.5706331062269405, "percentage": 86.74, "elapsed_time": "1 day, 4:25:35", "remaining_time": "4:20:47", "throughput": 553.69, "total_tokens": 56662320} {"current_steps": 34700, "total_steps": 40000, "loss": 0.1609, "lr": 2.1356150023490783e-06, "epoch": 1.5708594581135835, "percentage": 86.75, "elapsed_time": "1 day, 4:25:38", "remaining_time": "4:20:30", "throughput": 553.75, "total_tokens": 56670160} {"current_steps": 34705, "total_steps": 40000, "loss": 0.1388, "lr": 2.1316464262651464e-06, "epoch": 1.5710858100002265, "percentage": 86.76, "elapsed_time": "1 day, 4:25:41", "remaining_time": "4:20:14", "throughput": 553.81, "total_tokens": 56677808} {"current_steps": 34710, "total_steps": 40000, "loss": 0.1102, "lr": 2.1276813767687224e-06, "epoch": 1.5713121618868693, "percentage": 86.78, "elapsed_time": "1 day, 4:25:45", "remaining_time": "4:19:57", "throughput": 553.87, "total_tokens": 56686256} {"current_steps": 34715, "total_steps": 40000, "loss": 0.1033, "lr": 2.123719854471254e-06, "epoch": 1.5715385137735123, "percentage": 86.79, "elapsed_time": "1 day, 4:25:48", "remaining_time": "4:19:41", "throughput": 553.94, "total_tokens": 56695184} {"current_steps": 34720, "total_steps": 40000, "loss": 0.1254, "lr": 2.119761859983668e-06, "epoch": 1.5717648656601553, "percentage": 86.8, "elapsed_time": "1 day, 4:25:51", "remaining_time": "4:19:25", "throughput": 554.0, "total_tokens": 56703184} {"current_steps": 34725, "total_steps": 40000, "loss": 0.1719, "lr": 2.1158073939163386e-06, "epoch": 1.5719912175467983, "percentage": 86.81, "elapsed_time": "1 day, 4:25:54", "remaining_time": "4:19:08", "throughput": 554.06, "total_tokens": 56711216} {"current_steps": 34730, "total_steps": 40000, "loss": 0.132, "lr": 2.111856456879088e-06, "epoch": 1.5722175694334413, "percentage": 86.83, "elapsed_time": "1 day, 4:25:58", "remaining_time": "4:18:52", "throughput": 554.13, "total_tokens": 56719600} {"current_steps": 34735, "total_steps": 40000, "loss": 0.0914, "lr": 2.1079090494811993e-06, "epoch": 1.572443921320084, "percentage": 86.84, "elapsed_time": "1 day, 4:26:01", "remaining_time": "4:18:35", "throughput": 554.19, "total_tokens": 56728208} {"current_steps": 34740, "total_steps": 40000, "loss": 0.087, "lr": 2.103965172331418e-06, "epoch": 1.572670273206727, "percentage": 86.85, "elapsed_time": "1 day, 4:26:04", "remaining_time": "4:18:19", "throughput": 554.26, "total_tokens": 56736400} {"current_steps": 34745, "total_steps": 40000, "loss": 0.0784, "lr": 2.100024826037933e-06, "epoch": 1.57289662509337, "percentage": 86.86, "elapsed_time": "1 day, 4:26:08", "remaining_time": "4:18:02", "throughput": 554.32, "total_tokens": 56745136} {"current_steps": 34750, "total_steps": 40000, "loss": 0.1566, "lr": 2.0960880112084027e-06, "epoch": 1.573122976980013, "percentage": 86.88, "elapsed_time": "1 day, 4:26:11", "remaining_time": "4:17:46", "throughput": 554.39, "total_tokens": 56753424} {"current_steps": 34755, "total_steps": 40000, "loss": 0.084, "lr": 2.092154728449927e-06, "epoch": 1.573349328866656, "percentage": 86.89, "elapsed_time": "1 day, 4:26:14", "remaining_time": "4:17:29", "throughput": 554.45, "total_tokens": 56761744} {"current_steps": 34760, "total_steps": 40000, "loss": 0.1461, "lr": 2.0882249783690687e-06, "epoch": 1.573575680753299, "percentage": 86.9, "elapsed_time": "1 day, 4:26:17", "remaining_time": "4:17:13", "throughput": 554.51, "total_tokens": 56769840} {"current_steps": 34765, "total_steps": 40000, "loss": 0.088, "lr": 2.084298761571851e-06, "epoch": 1.573802032639942, "percentage": 86.91, "elapsed_time": "1 day, 4:26:20", "remaining_time": "4:16:56", "throughput": 554.57, "total_tokens": 56777520} {"current_steps": 34770, "total_steps": 40000, "loss": 0.1653, "lr": 2.080376078663737e-06, "epoch": 1.574028384526585, "percentage": 86.92, "elapsed_time": "1 day, 4:26:24", "remaining_time": "4:16:40", "throughput": 554.63, "total_tokens": 56785392} {"current_steps": 34775, "total_steps": 40000, "loss": 0.1201, "lr": 2.0764569302496593e-06, "epoch": 1.574254736413228, "percentage": 86.94, "elapsed_time": "1 day, 4:26:27", "remaining_time": "4:16:23", "throughput": 554.69, "total_tokens": 56793488} {"current_steps": 34780, "total_steps": 40000, "loss": 0.1036, "lr": 2.0725413169339957e-06, "epoch": 1.574481088299871, "percentage": 86.95, "elapsed_time": "1 day, 4:26:30", "remaining_time": "4:16:07", "throughput": 554.75, "total_tokens": 56801424} {"current_steps": 34785, "total_steps": 40000, "loss": 0.171, "lr": 2.068629239320588e-06, "epoch": 1.574707440186514, "percentage": 86.96, "elapsed_time": "1 day, 4:26:33", "remaining_time": "4:15:51", "throughput": 554.82, "total_tokens": 56810512} {"current_steps": 34790, "total_steps": 40000, "loss": 0.129, "lr": 2.064720698012726e-06, "epoch": 1.574933792073157, "percentage": 86.98, "elapsed_time": "1 day, 4:26:37", "remaining_time": "4:15:34", "throughput": 554.89, "total_tokens": 56819280} {"current_steps": 34795, "total_steps": 40000, "loss": 0.0971, "lr": 2.0608156936131522e-06, "epoch": 1.5751601439598, "percentage": 86.99, "elapsed_time": "1 day, 4:26:40", "remaining_time": "4:15:18", "throughput": 554.95, "total_tokens": 56826800} {"current_steps": 34800, "total_steps": 40000, "loss": 0.0865, "lr": 2.056914226724074e-06, "epoch": 1.575386495846443, "percentage": 87.0, "elapsed_time": "1 day, 4:26:43", "remaining_time": "4:15:01", "throughput": 555.01, "total_tokens": 56834992} {"current_steps": 34800, "total_steps": 40000, "eval_loss": 0.12220392376184464, "epoch": 1.575386495846443, "percentage": 87.0, "elapsed_time": "1 day, 4:34:26", "remaining_time": "4:16:10", "throughput": 552.51, "total_tokens": 56834992} {"current_steps": 34805, "total_steps": 40000, "loss": 0.1201, "lr": 2.0530162979471385e-06, "epoch": 1.575612847733086, "percentage": 87.01, "elapsed_time": "1 day, 4:34:30", "remaining_time": "4:15:54", "throughput": 552.57, "total_tokens": 56843632} {"current_steps": 34810, "total_steps": 40000, "loss": 0.1347, "lr": 2.0491219078834667e-06, "epoch": 1.575839199619729, "percentage": 87.02, "elapsed_time": "1 day, 4:34:33", "remaining_time": "4:15:37", "throughput": 552.63, "total_tokens": 56851600} {"current_steps": 34815, "total_steps": 40000, "loss": 0.0942, "lr": 2.045231057133612e-06, "epoch": 1.576065551506372, "percentage": 87.04, "elapsed_time": "1 day, 4:34:36", "remaining_time": "4:15:21", "throughput": 552.7, "total_tokens": 56859824} {"current_steps": 34820, "total_steps": 40000, "loss": 0.0971, "lr": 2.0413437462975944e-06, "epoch": 1.5762919033930147, "percentage": 87.05, "elapsed_time": "1 day, 4:34:40", "remaining_time": "4:15:04", "throughput": 552.76, "total_tokens": 56867664} {"current_steps": 34825, "total_steps": 40000, "loss": 0.0973, "lr": 2.0374599759748843e-06, "epoch": 1.5765182552796577, "percentage": 87.06, "elapsed_time": "1 day, 4:34:43", "remaining_time": "4:14:48", "throughput": 552.82, "total_tokens": 56875792} {"current_steps": 34830, "total_steps": 40000, "loss": 0.0978, "lr": 2.033579746764419e-06, "epoch": 1.5767446071663007, "percentage": 87.08, "elapsed_time": "1 day, 4:34:46", "remaining_time": "4:14:32", "throughput": 552.88, "total_tokens": 56884336} {"current_steps": 34835, "total_steps": 40000, "loss": 0.1234, "lr": 2.029703059264565e-06, "epoch": 1.5769709590529437, "percentage": 87.09, "elapsed_time": "1 day, 4:34:49", "remaining_time": "4:14:15", "throughput": 552.94, "total_tokens": 56892400} {"current_steps": 34840, "total_steps": 40000, "loss": 0.1277, "lr": 2.02582991407316e-06, "epoch": 1.5771973109395867, "percentage": 87.1, "elapsed_time": "1 day, 4:34:53", "remaining_time": "4:13:59", "throughput": 553.0, "total_tokens": 56900208} {"current_steps": 34845, "total_steps": 40000, "loss": 0.075, "lr": 2.0219603117874992e-06, "epoch": 1.5774236628262297, "percentage": 87.11, "elapsed_time": "1 day, 4:34:56", "remaining_time": "4:13:42", "throughput": 553.07, "total_tokens": 56908368} {"current_steps": 34850, "total_steps": 40000, "loss": 0.1694, "lr": 2.0180942530043156e-06, "epoch": 1.5776500147128725, "percentage": 87.12, "elapsed_time": "1 day, 4:34:59", "remaining_time": "4:13:26", "throughput": 553.12, "total_tokens": 56916048} {"current_steps": 34855, "total_steps": 40000, "loss": 0.1156, "lr": 2.0142317383198107e-06, "epoch": 1.5778763665995155, "percentage": 87.14, "elapsed_time": "1 day, 4:35:02", "remaining_time": "4:13:09", "throughput": 553.19, "total_tokens": 56924336} {"current_steps": 34860, "total_steps": 40000, "loss": 0.1471, "lr": 2.0103727683296243e-06, "epoch": 1.5781027184861585, "percentage": 87.15, "elapsed_time": "1 day, 4:35:05", "remaining_time": "4:12:53", "throughput": 553.25, "total_tokens": 56932624} {"current_steps": 34865, "total_steps": 40000, "loss": 0.1126, "lr": 2.0065173436288636e-06, "epoch": 1.5783290703728015, "percentage": 87.16, "elapsed_time": "1 day, 4:35:08", "remaining_time": "4:12:36", "throughput": 553.31, "total_tokens": 56940368} {"current_steps": 34870, "total_steps": 40000, "loss": 0.1352, "lr": 2.002665464812087e-06, "epoch": 1.5785554222594445, "percentage": 87.17, "elapsed_time": "1 day, 4:35:11", "remaining_time": "4:12:20", "throughput": 553.37, "total_tokens": 56947952} {"current_steps": 34875, "total_steps": 40000, "loss": 0.1089, "lr": 1.998817132473291e-06, "epoch": 1.5787817741460874, "percentage": 87.19, "elapsed_time": "1 day, 4:35:15", "remaining_time": "4:12:03", "throughput": 553.43, "total_tokens": 56956688} {"current_steps": 34880, "total_steps": 40000, "loss": 0.1584, "lr": 1.9949723472059507e-06, "epoch": 1.5790081260327304, "percentage": 87.2, "elapsed_time": "1 day, 4:35:18", "remaining_time": "4:11:47", "throughput": 553.49, "total_tokens": 56964496} {"current_steps": 34885, "total_steps": 40000, "loss": 0.1391, "lr": 1.9911311096029726e-06, "epoch": 1.5792344779193734, "percentage": 87.21, "elapsed_time": "1 day, 4:35:21", "remaining_time": "4:11:30", "throughput": 553.56, "total_tokens": 56973104} {"current_steps": 34890, "total_steps": 40000, "loss": 0.111, "lr": 1.9872934202567224e-06, "epoch": 1.5794608298060164, "percentage": 87.22, "elapsed_time": "1 day, 4:35:24", "remaining_time": "4:11:14", "throughput": 553.62, "total_tokens": 56981200} {"current_steps": 34895, "total_steps": 40000, "loss": 0.1517, "lr": 1.9834592797590257e-06, "epoch": 1.5796871816926594, "percentage": 87.24, "elapsed_time": "1 day, 4:35:27", "remaining_time": "4:10:57", "throughput": 553.68, "total_tokens": 56989264} {"current_steps": 34900, "total_steps": 40000, "loss": 0.114, "lr": 1.979628688701149e-06, "epoch": 1.5799135335793024, "percentage": 87.25, "elapsed_time": "1 day, 4:35:31", "remaining_time": "4:10:41", "throughput": 553.75, "total_tokens": 56997648} {"current_steps": 34905, "total_steps": 40000, "loss": 0.1391, "lr": 1.9758016476738193e-06, "epoch": 1.5801398854659454, "percentage": 87.26, "elapsed_time": "1 day, 4:35:34", "remaining_time": "4:10:25", "throughput": 553.81, "total_tokens": 57005744} {"current_steps": 34910, "total_steps": 40000, "loss": 0.1062, "lr": 1.971978157267221e-06, "epoch": 1.5803662373525884, "percentage": 87.28, "elapsed_time": "1 day, 4:35:37", "remaining_time": "4:10:08", "throughput": 553.87, "total_tokens": 57013840} {"current_steps": 34915, "total_steps": 40000, "loss": 0.1235, "lr": 1.968158218070973e-06, "epoch": 1.5805925892392314, "percentage": 87.29, "elapsed_time": "1 day, 4:35:40", "remaining_time": "4:09:52", "throughput": 553.93, "total_tokens": 57022384} {"current_steps": 34920, "total_steps": 40000, "loss": 0.1749, "lr": 1.9643418306741682e-06, "epoch": 1.5808189411258744, "percentage": 87.3, "elapsed_time": "1 day, 4:35:43", "remaining_time": "4:09:35", "throughput": 553.99, "total_tokens": 57030288} {"current_steps": 34925, "total_steps": 40000, "loss": 0.1289, "lr": 1.9605289956653337e-06, "epoch": 1.5810452930125174, "percentage": 87.31, "elapsed_time": "1 day, 4:35:47", "remaining_time": "4:09:19", "throughput": 554.06, "total_tokens": 57038832} {"current_steps": 34930, "total_steps": 40000, "loss": 0.1166, "lr": 1.9567197136324626e-06, "epoch": 1.5812716448991604, "percentage": 87.33, "elapsed_time": "1 day, 4:35:50", "remaining_time": "4:09:02", "throughput": 554.13, "total_tokens": 57047824} {"current_steps": 34935, "total_steps": 40000, "loss": 0.1399, "lr": 1.9529139851629935e-06, "epoch": 1.5814979967858032, "percentage": 87.34, "elapsed_time": "1 day, 4:35:53", "remaining_time": "4:08:46", "throughput": 554.19, "total_tokens": 57055792} {"current_steps": 34940, "total_steps": 40000, "loss": 0.1449, "lr": 1.949111810843812e-06, "epoch": 1.5817243486724462, "percentage": 87.35, "elapsed_time": "1 day, 4:35:56", "remaining_time": "4:08:30", "throughput": 554.25, "total_tokens": 57063952} {"current_steps": 34945, "total_steps": 40000, "loss": 0.0976, "lr": 1.9453131912612694e-06, "epoch": 1.5819507005590892, "percentage": 87.36, "elapsed_time": "1 day, 4:36:00", "remaining_time": "4:08:13", "throughput": 554.32, "total_tokens": 57072496} {"current_steps": 34950, "total_steps": 40000, "loss": 0.0897, "lr": 1.941518127001149e-06, "epoch": 1.5821770524457321, "percentage": 87.38, "elapsed_time": "1 day, 4:36:03", "remaining_time": "4:07:57", "throughput": 554.38, "total_tokens": 57081104} {"current_steps": 34955, "total_steps": 40000, "loss": 0.1255, "lr": 1.9377266186487107e-06, "epoch": 1.5824034043323751, "percentage": 87.39, "elapsed_time": "1 day, 4:36:06", "remaining_time": "4:07:40", "throughput": 554.44, "total_tokens": 57088848} {"current_steps": 34960, "total_steps": 40000, "loss": 0.1207, "lr": 1.9339386667886483e-06, "epoch": 1.5826297562190181, "percentage": 87.4, "elapsed_time": "1 day, 4:36:09", "remaining_time": "4:07:24", "throughput": 554.51, "total_tokens": 57097232} {"current_steps": 34965, "total_steps": 40000, "loss": 0.1288, "lr": 1.9301542720051024e-06, "epoch": 1.582856108105661, "percentage": 87.41, "elapsed_time": "1 day, 4:36:12", "remaining_time": "4:07:08", "throughput": 554.56, "total_tokens": 57104816} {"current_steps": 34970, "total_steps": 40000, "loss": 0.1067, "lr": 1.926373434881684e-06, "epoch": 1.583082459992304, "percentage": 87.42, "elapsed_time": "1 day, 4:36:15", "remaining_time": "4:06:51", "throughput": 554.62, "total_tokens": 57112656} {"current_steps": 34975, "total_steps": 40000, "loss": 0.0962, "lr": 1.9225961560014468e-06, "epoch": 1.583308811878947, "percentage": 87.44, "elapsed_time": "1 day, 4:36:19", "remaining_time": "4:06:35", "throughput": 554.69, "total_tokens": 57121264} {"current_steps": 34980, "total_steps": 40000, "loss": 0.1116, "lr": 1.918822435946885e-06, "epoch": 1.58353516376559, "percentage": 87.45, "elapsed_time": "1 day, 4:36:22", "remaining_time": "4:06:19", "throughput": 554.75, "total_tokens": 57128944} {"current_steps": 34985, "total_steps": 40000, "loss": 0.1208, "lr": 1.915052275299961e-06, "epoch": 1.5837615156522329, "percentage": 87.46, "elapsed_time": "1 day, 4:36:25", "remaining_time": "4:06:02", "throughput": 554.81, "total_tokens": 57136848} {"current_steps": 34990, "total_steps": 40000, "loss": 0.0799, "lr": 1.9112856746420854e-06, "epoch": 1.5839878675388759, "percentage": 87.48, "elapsed_time": "1 day, 4:36:28", "remaining_time": "4:05:46", "throughput": 554.87, "total_tokens": 57144976} {"current_steps": 34995, "total_steps": 40000, "loss": 0.1267, "lr": 1.907522634554104e-06, "epoch": 1.5842142194255189, "percentage": 87.49, "elapsed_time": "1 day, 4:36:31", "remaining_time": "4:05:29", "throughput": 554.93, "total_tokens": 57153296} {"current_steps": 35000, "total_steps": 40000, "loss": 0.1051, "lr": 1.9037631556163337e-06, "epoch": 1.5844405713121619, "percentage": 87.5, "elapsed_time": "1 day, 4:36:34", "remaining_time": "4:05:13", "throughput": 554.99, "total_tokens": 57161136} {"current_steps": 35000, "total_steps": 40000, "eval_loss": 0.1218891367316246, "epoch": 1.5844405713121619, "percentage": 87.5, "elapsed_time": "1 day, 4:44:17", "remaining_time": "4:06:19", "throughput": 552.51, "total_tokens": 57161136} {"current_steps": 35005, "total_steps": 40000, "loss": 0.0963, "lr": 1.9000072384085272e-06, "epoch": 1.5846669231988049, "percentage": 87.51, "elapsed_time": "1 day, 4:44:22", "remaining_time": "4:06:03", "throughput": 552.56, "total_tokens": 57169296} {"current_steps": 35010, "total_steps": 40000, "loss": 0.1306, "lr": 1.8962548835098987e-06, "epoch": 1.5848932750854479, "percentage": 87.52, "elapsed_time": "1 day, 4:44:25", "remaining_time": "4:05:47", "throughput": 552.62, "total_tokens": 57177360} {"current_steps": 35015, "total_steps": 40000, "loss": 0.1038, "lr": 1.8925060914991077e-06, "epoch": 1.5851196269720909, "percentage": 87.54, "elapsed_time": "1 day, 4:44:28", "remaining_time": "4:05:30", "throughput": 552.68, "total_tokens": 57185616} {"current_steps": 35020, "total_steps": 40000, "loss": 0.1003, "lr": 1.888760862954264e-06, "epoch": 1.5853459788587339, "percentage": 87.55, "elapsed_time": "1 day, 4:44:32", "remaining_time": "4:05:14", "throughput": 552.75, "total_tokens": 57194672} {"current_steps": 35025, "total_steps": 40000, "loss": 0.1104, "lr": 1.8850191984529309e-06, "epoch": 1.5855723307453768, "percentage": 87.56, "elapsed_time": "1 day, 4:44:35", "remaining_time": "4:04:57", "throughput": 552.81, "total_tokens": 57202800} {"current_steps": 35030, "total_steps": 40000, "loss": 0.1415, "lr": 1.8812810985721186e-06, "epoch": 1.5857986826320198, "percentage": 87.58, "elapsed_time": "1 day, 4:44:38", "remaining_time": "4:04:41", "throughput": 552.88, "total_tokens": 57211472} {"current_steps": 35035, "total_steps": 40000, "loss": 0.1129, "lr": 1.8775465638882856e-06, "epoch": 1.5860250345186628, "percentage": 87.59, "elapsed_time": "1 day, 4:44:42", "remaining_time": "4:04:25", "throughput": 552.94, "total_tokens": 57219600} {"current_steps": 35040, "total_steps": 40000, "loss": 0.0995, "lr": 1.8738155949773517e-06, "epoch": 1.5862513864053058, "percentage": 87.6, "elapsed_time": "1 day, 4:44:45", "remaining_time": "4:04:08", "throughput": 553.0, "total_tokens": 57227760} {"current_steps": 35045, "total_steps": 40000, "loss": 0.1594, "lr": 1.8700881924146707e-06, "epoch": 1.5864777382919488, "percentage": 87.61, "elapsed_time": "1 day, 4:44:48", "remaining_time": "4:03:52", "throughput": 553.07, "total_tokens": 57236240} {"current_steps": 35050, "total_steps": 40000, "loss": 0.1193, "lr": 1.8663643567750577e-06, "epoch": 1.5867040901785916, "percentage": 87.62, "elapsed_time": "1 day, 4:44:52", "remaining_time": "4:03:35", "throughput": 553.13, "total_tokens": 57244592} {"current_steps": 35055, "total_steps": 40000, "loss": 0.1424, "lr": 1.8626440886327813e-06, "epoch": 1.5869304420652346, "percentage": 87.64, "elapsed_time": "1 day, 4:44:55", "remaining_time": "4:03:19", "throughput": 553.19, "total_tokens": 57252656} {"current_steps": 35060, "total_steps": 40000, "loss": 0.1188, "lr": 1.8589273885615432e-06, "epoch": 1.5871567939518776, "percentage": 87.65, "elapsed_time": "1 day, 4:44:58", "remaining_time": "4:03:03", "throughput": 553.25, "total_tokens": 57260656} {"current_steps": 35065, "total_steps": 40000, "loss": 0.0903, "lr": 1.8552142571345133e-06, "epoch": 1.5873831458385206, "percentage": 87.66, "elapsed_time": "1 day, 4:45:01", "remaining_time": "4:02:46", "throughput": 553.31, "total_tokens": 57268624} {"current_steps": 35070, "total_steps": 40000, "loss": 0.1029, "lr": 1.8515046949243025e-06, "epoch": 1.5876094977251636, "percentage": 87.67, "elapsed_time": "1 day, 4:45:04", "remaining_time": "4:02:30", "throughput": 553.37, "total_tokens": 57276784} {"current_steps": 35075, "total_steps": 40000, "loss": 0.1169, "lr": 1.8477987025029674e-06, "epoch": 1.5878358496118063, "percentage": 87.69, "elapsed_time": "1 day, 4:45:08", "remaining_time": "4:02:13", "throughput": 553.44, "total_tokens": 57285680} {"current_steps": 35080, "total_steps": 40000, "loss": 0.1017, "lr": 1.8440962804420232e-06, "epoch": 1.5880622014984493, "percentage": 87.7, "elapsed_time": "1 day, 4:45:11", "remaining_time": "4:01:57", "throughput": 553.5, "total_tokens": 57293840} {"current_steps": 35085, "total_steps": 40000, "loss": 0.087, "lr": 1.8403974293124265e-06, "epoch": 1.5882885533850923, "percentage": 87.71, "elapsed_time": "1 day, 4:45:14", "remaining_time": "4:01:41", "throughput": 553.57, "total_tokens": 57302512} {"current_steps": 35090, "total_steps": 40000, "loss": 0.1097, "lr": 1.8367021496845854e-06, "epoch": 1.5885149052717353, "percentage": 87.72, "elapsed_time": "1 day, 4:45:18", "remaining_time": "4:01:24", "throughput": 553.63, "total_tokens": 57310704} {"current_steps": 35095, "total_steps": 40000, "loss": 0.1346, "lr": 1.8330104421283662e-06, "epoch": 1.5887412571583783, "percentage": 87.74, "elapsed_time": "1 day, 4:45:21", "remaining_time": "4:01:08", "throughput": 553.69, "total_tokens": 57318480} {"current_steps": 35100, "total_steps": 40000, "loss": 0.1133, "lr": 1.8293223072130717e-06, "epoch": 1.5889676090450213, "percentage": 87.75, "elapsed_time": "1 day, 4:45:24", "remaining_time": "4:00:52", "throughput": 553.75, "total_tokens": 57326416} {"current_steps": 35105, "total_steps": 40000, "loss": 0.1066, "lr": 1.8256377455074525e-06, "epoch": 1.5891939609316643, "percentage": 87.76, "elapsed_time": "1 day, 4:45:27", "remaining_time": "4:00:35", "throughput": 553.81, "total_tokens": 57334736} {"current_steps": 35110, "total_steps": 40000, "loss": 0.1208, "lr": 1.8219567575797263e-06, "epoch": 1.5894203128183073, "percentage": 87.78, "elapsed_time": "1 day, 4:45:30", "remaining_time": "4:00:19", "throughput": 553.88, "total_tokens": 57343312} {"current_steps": 35115, "total_steps": 40000, "loss": 0.072, "lr": 1.8182793439975365e-06, "epoch": 1.5896466647049503, "percentage": 87.79, "elapsed_time": "1 day, 4:45:34", "remaining_time": "4:00:03", "throughput": 553.94, "total_tokens": 57351952} {"current_steps": 35120, "total_steps": 40000, "loss": 0.1314, "lr": 1.8146055053279958e-06, "epoch": 1.5898730165915933, "percentage": 87.8, "elapsed_time": "1 day, 4:45:37", "remaining_time": "3:59:46", "throughput": 554.0, "total_tokens": 57359472} {"current_steps": 35125, "total_steps": 40000, "loss": 0.1024, "lr": 1.8109352421376486e-06, "epoch": 1.5900993684782363, "percentage": 87.81, "elapsed_time": "1 day, 4:45:40", "remaining_time": "3:59:30", "throughput": 554.06, "total_tokens": 57367344} {"current_steps": 35130, "total_steps": 40000, "loss": 0.1751, "lr": 1.8072685549924972e-06, "epoch": 1.5903257203648793, "percentage": 87.83, "elapsed_time": "1 day, 4:45:43", "remaining_time": "3:59:14", "throughput": 554.12, "total_tokens": 57375600} {"current_steps": 35135, "total_steps": 40000, "loss": 0.1102, "lr": 1.8036054444579982e-06, "epoch": 1.5905520722515223, "percentage": 87.84, "elapsed_time": "1 day, 4:45:46", "remaining_time": "3:58:57", "throughput": 554.18, "total_tokens": 57383536} {"current_steps": 35140, "total_steps": 40000, "loss": 0.1041, "lr": 1.7999459110990407e-06, "epoch": 1.5907784241381653, "percentage": 87.85, "elapsed_time": "1 day, 4:45:50", "remaining_time": "3:58:41", "throughput": 554.24, "total_tokens": 57391536} {"current_steps": 35145, "total_steps": 40000, "loss": 0.1173, "lr": 1.7962899554799712e-06, "epoch": 1.5910047760248083, "percentage": 87.86, "elapsed_time": "1 day, 4:45:53", "remaining_time": "3:58:25", "throughput": 554.3, "total_tokens": 57399664} {"current_steps": 35150, "total_steps": 40000, "loss": 0.1355, "lr": 1.7926375781645937e-06, "epoch": 1.5912311279114513, "percentage": 87.88, "elapsed_time": "1 day, 4:45:56", "remaining_time": "3:58:08", "throughput": 554.36, "total_tokens": 57407312} {"current_steps": 35155, "total_steps": 40000, "loss": 0.1305, "lr": 1.7889887797161359e-06, "epoch": 1.5914574797980943, "percentage": 87.89, "elapsed_time": "1 day, 4:45:59", "remaining_time": "3:57:52", "throughput": 554.42, "total_tokens": 57416048} {"current_steps": 35160, "total_steps": 40000, "loss": 0.1302, "lr": 1.7853435606973028e-06, "epoch": 1.591683831684737, "percentage": 87.9, "elapsed_time": "1 day, 4:46:03", "remaining_time": "3:57:36", "throughput": 554.48, "total_tokens": 57424080} {"current_steps": 35165, "total_steps": 40000, "loss": 0.1388, "lr": 1.781701921670223e-06, "epoch": 1.59191018357138, "percentage": 87.91, "elapsed_time": "1 day, 4:46:06", "remaining_time": "3:57:19", "throughput": 554.55, "total_tokens": 57432336} {"current_steps": 35170, "total_steps": 40000, "loss": 0.1381, "lr": 1.7780638631964886e-06, "epoch": 1.592136535458023, "percentage": 87.92, "elapsed_time": "1 day, 4:46:09", "remaining_time": "3:57:03", "throughput": 554.61, "total_tokens": 57440592} {"current_steps": 35175, "total_steps": 40000, "loss": 0.1414, "lr": 1.7744293858371314e-06, "epoch": 1.592362887344666, "percentage": 87.94, "elapsed_time": "1 day, 4:46:12", "remaining_time": "3:56:47", "throughput": 554.67, "total_tokens": 57449040} {"current_steps": 35180, "total_steps": 40000, "loss": 0.1357, "lr": 1.770798490152631e-06, "epoch": 1.592589239231309, "percentage": 87.95, "elapsed_time": "1 day, 4:46:16", "remaining_time": "3:56:30", "throughput": 554.73, "total_tokens": 57456944} {"current_steps": 35185, "total_steps": 40000, "loss": 0.1049, "lr": 1.767171176702917e-06, "epoch": 1.592815591117952, "percentage": 87.96, "elapsed_time": "1 day, 4:46:19", "remaining_time": "3:56:14", "throughput": 554.79, "total_tokens": 57465136} {"current_steps": 35190, "total_steps": 40000, "loss": 0.1075, "lr": 1.7635474460473755e-06, "epoch": 1.5930419430045948, "percentage": 87.98, "elapsed_time": "1 day, 4:46:22", "remaining_time": "3:55:58", "throughput": 554.86, "total_tokens": 57473328} {"current_steps": 35195, "total_steps": 40000, "loss": 0.1187, "lr": 1.7599272987448206e-06, "epoch": 1.5932682948912378, "percentage": 87.99, "elapsed_time": "1 day, 4:46:25", "remaining_time": "3:55:42", "throughput": 554.92, "total_tokens": 57481680} {"current_steps": 35200, "total_steps": 40000, "loss": 0.1176, "lr": 1.7563107353535362e-06, "epoch": 1.5934946467778808, "percentage": 88.0, "elapsed_time": "1 day, 4:46:28", "remaining_time": "3:55:25", "throughput": 554.98, "total_tokens": 57489264} {"current_steps": 35200, "total_steps": 40000, "eval_loss": 0.12210967391729355, "epoch": 1.5934946467778808, "percentage": 88.0, "elapsed_time": "1 day, 4:54:11", "remaining_time": "3:56:28", "throughput": 552.51, "total_tokens": 57489264} {"current_steps": 35205, "total_steps": 40000, "loss": 0.1542, "lr": 1.7526977564312263e-06, "epoch": 1.5937209986645238, "percentage": 88.01, "elapsed_time": "1 day, 4:54:15", "remaining_time": "3:56:12", "throughput": 552.56, "total_tokens": 57497168} {"current_steps": 35210, "total_steps": 40000, "loss": 0.128, "lr": 1.7490883625350701e-06, "epoch": 1.5939473505511668, "percentage": 88.02, "elapsed_time": "1 day, 4:54:18", "remaining_time": "3:55:56", "throughput": 552.62, "total_tokens": 57505008} {"current_steps": 35215, "total_steps": 40000, "loss": 0.164, "lr": 1.7454825542216807e-06, "epoch": 1.5941737024378098, "percentage": 88.04, "elapsed_time": "1 day, 4:54:22", "remaining_time": "3:55:39", "throughput": 552.68, "total_tokens": 57513360} {"current_steps": 35220, "total_steps": 40000, "loss": 0.1483, "lr": 1.7418803320471105e-06, "epoch": 1.5944000543244528, "percentage": 88.05, "elapsed_time": "1 day, 4:54:25", "remaining_time": "3:55:23", "throughput": 552.74, "total_tokens": 57521360} {"current_steps": 35225, "total_steps": 40000, "loss": 0.0694, "lr": 1.7382816965668737e-06, "epoch": 1.5946264062110957, "percentage": 88.06, "elapsed_time": "1 day, 4:54:28", "remaining_time": "3:55:07", "throughput": 552.81, "total_tokens": 57529648} {"current_steps": 35230, "total_steps": 40000, "loss": 0.1272, "lr": 1.7346866483359285e-06, "epoch": 1.5948527580977387, "percentage": 88.08, "elapsed_time": "1 day, 4:54:31", "remaining_time": "3:54:50", "throughput": 552.87, "total_tokens": 57538064} {"current_steps": 35235, "total_steps": 40000, "loss": 0.1292, "lr": 1.7310951879086657e-06, "epoch": 1.5950791099843817, "percentage": 88.09, "elapsed_time": "1 day, 4:54:34", "remaining_time": "3:54:34", "throughput": 552.93, "total_tokens": 57545712} {"current_steps": 35240, "total_steps": 40000, "loss": 0.1599, "lr": 1.7275073158389471e-06, "epoch": 1.5953054618710247, "percentage": 88.1, "elapsed_time": "1 day, 4:54:37", "remaining_time": "3:54:18", "throughput": 552.99, "total_tokens": 57553840} {"current_steps": 35245, "total_steps": 40000, "loss": 0.1281, "lr": 1.723923032680061e-06, "epoch": 1.5955318137576677, "percentage": 88.11, "elapsed_time": "1 day, 4:54:41", "remaining_time": "3:54:01", "throughput": 553.05, "total_tokens": 57562544} {"current_steps": 35250, "total_steps": 40000, "loss": 0.1412, "lr": 1.7203423389847428e-06, "epoch": 1.5957581656443107, "percentage": 88.12, "elapsed_time": "1 day, 4:54:44", "remaining_time": "3:53:45", "throughput": 553.12, "total_tokens": 57570928} {"current_steps": 35255, "total_steps": 40000, "loss": 0.1158, "lr": 1.7167652353051928e-06, "epoch": 1.5959845175309537, "percentage": 88.14, "elapsed_time": "1 day, 4:54:47", "remaining_time": "3:53:29", "throughput": 553.18, "total_tokens": 57579120} {"current_steps": 35260, "total_steps": 40000, "loss": 0.1335, "lr": 1.7131917221930333e-06, "epoch": 1.5962108694175967, "percentage": 88.15, "elapsed_time": "1 day, 4:54:50", "remaining_time": "3:53:12", "throughput": 553.23, "total_tokens": 57586512} {"current_steps": 35265, "total_steps": 40000, "loss": 0.1656, "lr": 1.7096218001993513e-06, "epoch": 1.5964372213042397, "percentage": 88.16, "elapsed_time": "1 day, 4:54:53", "remaining_time": "3:52:56", "throughput": 553.3, "total_tokens": 57594800} {"current_steps": 35270, "total_steps": 40000, "loss": 0.0887, "lr": 1.706055469874676e-06, "epoch": 1.5966635731908827, "percentage": 88.17, "elapsed_time": "1 day, 4:54:57", "remaining_time": "3:52:40", "throughput": 553.36, "total_tokens": 57603312} {"current_steps": 35275, "total_steps": 40000, "loss": 0.0964, "lr": 1.702492731768976e-06, "epoch": 1.5968899250775255, "percentage": 88.19, "elapsed_time": "1 day, 4:55:00", "remaining_time": "3:52:24", "throughput": 553.44, "total_tokens": 57613136} {"current_steps": 35280, "total_steps": 40000, "loss": 0.1462, "lr": 1.6989335864316724e-06, "epoch": 1.5971162769641685, "percentage": 88.2, "elapsed_time": "1 day, 4:55:03", "remaining_time": "3:52:07", "throughput": 553.5, "total_tokens": 57621072} {"current_steps": 35285, "total_steps": 40000, "loss": 0.1024, "lr": 1.6953780344116265e-06, "epoch": 1.5973426288508115, "percentage": 88.21, "elapsed_time": "1 day, 4:55:07", "remaining_time": "3:51:51", "throughput": 553.56, "total_tokens": 57629328} {"current_steps": 35290, "total_steps": 40000, "loss": 0.1009, "lr": 1.6918260762571497e-06, "epoch": 1.5975689807374545, "percentage": 88.22, "elapsed_time": "1 day, 4:55:10", "remaining_time": "3:51:35", "throughput": 553.62, "total_tokens": 57637616} {"current_steps": 35295, "total_steps": 40000, "loss": 0.1385, "lr": 1.6882777125160093e-06, "epoch": 1.5977953326240975, "percentage": 88.24, "elapsed_time": "1 day, 4:55:13", "remaining_time": "3:51:18", "throughput": 553.69, "total_tokens": 57646224} {"current_steps": 35300, "total_steps": 40000, "loss": 0.1006, "lr": 1.6847329437353899e-06, "epoch": 1.5980216845107404, "percentage": 88.25, "elapsed_time": "1 day, 4:55:16", "remaining_time": "3:51:02", "throughput": 553.75, "total_tokens": 57654096} {"current_steps": 35305, "total_steps": 40000, "loss": 0.1174, "lr": 1.6811917704619511e-06, "epoch": 1.5982480363973832, "percentage": 88.26, "elapsed_time": "1 day, 4:55:19", "remaining_time": "3:50:46", "throughput": 553.81, "total_tokens": 57662160} {"current_steps": 35310, "total_steps": 40000, "loss": 0.1137, "lr": 1.67765419324179e-06, "epoch": 1.5984743882840262, "percentage": 88.28, "elapsed_time": "1 day, 4:55:22", "remaining_time": "3:50:29", "throughput": 553.87, "total_tokens": 57670096} {"current_steps": 35315, "total_steps": 40000, "loss": 0.1065, "lr": 1.6741202126204364e-06, "epoch": 1.5987007401706692, "percentage": 88.29, "elapsed_time": "1 day, 4:55:26", "remaining_time": "3:50:13", "throughput": 553.92, "total_tokens": 57677872} {"current_steps": 35320, "total_steps": 40000, "loss": 0.1184, "lr": 1.6705898291428767e-06, "epoch": 1.5989270920573122, "percentage": 88.3, "elapsed_time": "1 day, 4:55:29", "remaining_time": "3:49:57", "throughput": 553.98, "total_tokens": 57685616} {"current_steps": 35325, "total_steps": 40000, "loss": 0.1529, "lr": 1.6670630433535395e-06, "epoch": 1.5991534439439552, "percentage": 88.31, "elapsed_time": "1 day, 4:55:32", "remaining_time": "3:49:41", "throughput": 554.05, "total_tokens": 57694320} {"current_steps": 35330, "total_steps": 40000, "loss": 0.0813, "lr": 1.6635398557962979e-06, "epoch": 1.5993797958305982, "percentage": 88.33, "elapsed_time": "1 day, 4:55:35", "remaining_time": "3:49:24", "throughput": 554.11, "total_tokens": 57702288} {"current_steps": 35335, "total_steps": 40000, "loss": 0.1369, "lr": 1.660020267014481e-06, "epoch": 1.5996061477172412, "percentage": 88.34, "elapsed_time": "1 day, 4:55:38", "remaining_time": "3:49:08", "throughput": 554.16, "total_tokens": 57710064} {"current_steps": 35340, "total_steps": 40000, "loss": 0.1729, "lr": 1.6565042775508438e-06, "epoch": 1.5998324996038842, "percentage": 88.35, "elapsed_time": "1 day, 4:55:42", "remaining_time": "3:48:52", "throughput": 554.23, "total_tokens": 57718576} {"current_steps": 35345, "total_steps": 40000, "loss": 0.1184, "lr": 1.6529918879475997e-06, "epoch": 1.6000588514905272, "percentage": 88.36, "elapsed_time": "1 day, 4:55:45", "remaining_time": "3:48:36", "throughput": 554.29, "total_tokens": 57726768} {"current_steps": 35350, "total_steps": 40000, "loss": 0.0876, "lr": 1.6494830987464043e-06, "epoch": 1.6002852033771702, "percentage": 88.38, "elapsed_time": "1 day, 4:55:48", "remaining_time": "3:48:19", "throughput": 554.35, "total_tokens": 57734736} {"current_steps": 35355, "total_steps": 40000, "loss": 0.1056, "lr": 1.6459779104883555e-06, "epoch": 1.6005115552638132, "percentage": 88.39, "elapsed_time": "1 day, 4:55:51", "remaining_time": "3:48:03", "throughput": 554.41, "total_tokens": 57742768} {"current_steps": 35360, "total_steps": 40000, "loss": 0.135, "lr": 1.6424763237140013e-06, "epoch": 1.6007379071504562, "percentage": 88.4, "elapsed_time": "1 day, 4:55:54", "remaining_time": "3:47:47", "throughput": 554.47, "total_tokens": 57750192} {"current_steps": 35365, "total_steps": 40000, "loss": 0.0852, "lr": 1.6389783389633207e-06, "epoch": 1.6009642590370992, "percentage": 88.41, "elapsed_time": "1 day, 4:55:57", "remaining_time": "3:47:31", "throughput": 554.52, "total_tokens": 57758064} {"current_steps": 35370, "total_steps": 40000, "loss": 0.1293, "lr": 1.6354839567757546e-06, "epoch": 1.6011906109237422, "percentage": 88.42, "elapsed_time": "1 day, 4:56:00", "remaining_time": "3:47:14", "throughput": 554.59, "total_tokens": 57766384} {"current_steps": 35375, "total_steps": 40000, "loss": 0.1404, "lr": 1.6319931776901831e-06, "epoch": 1.6014169628103851, "percentage": 88.44, "elapsed_time": "1 day, 4:56:04", "remaining_time": "3:46:58", "throughput": 554.65, "total_tokens": 57774800} {"current_steps": 35380, "total_steps": 40000, "loss": 0.1099, "lr": 1.6285060022449229e-06, "epoch": 1.6016433146970281, "percentage": 88.45, "elapsed_time": "1 day, 4:56:07", "remaining_time": "3:46:42", "throughput": 554.71, "total_tokens": 57783024} {"current_steps": 35385, "total_steps": 40000, "loss": 0.0867, "lr": 1.6250224309777434e-06, "epoch": 1.6018696665836711, "percentage": 88.46, "elapsed_time": "1 day, 4:56:10", "remaining_time": "3:46:26", "throughput": 554.78, "total_tokens": 57791696} {"current_steps": 35390, "total_steps": 40000, "loss": 0.0714, "lr": 1.6215424644258515e-06, "epoch": 1.602096018470314, "percentage": 88.48, "elapsed_time": "1 day, 4:56:13", "remaining_time": "3:46:09", "throughput": 554.84, "total_tokens": 57799344} {"current_steps": 35395, "total_steps": 40000, "loss": 0.1035, "lr": 1.6180661031259036e-06, "epoch": 1.602322370356957, "percentage": 88.49, "elapsed_time": "1 day, 4:56:17", "remaining_time": "3:45:53", "throughput": 554.9, "total_tokens": 57807824} {"current_steps": 35400, "total_steps": 40000, "loss": 0.1073, "lr": 1.614593347613999e-06, "epoch": 1.6025487222436, "percentage": 88.5, "elapsed_time": "1 day, 4:56:20", "remaining_time": "3:45:37", "throughput": 554.96, "total_tokens": 57815440} {"current_steps": 35400, "total_steps": 40000, "eval_loss": 0.12196049839258194, "epoch": 1.6025487222436, "percentage": 88.5, "elapsed_time": "1 day, 5:04:02", "remaining_time": "3:46:37", "throughput": 552.5, "total_tokens": 57815440} {"current_steps": 35405, "total_steps": 40000, "loss": 0.0841, "lr": 1.6111241984256758e-06, "epoch": 1.602775074130243, "percentage": 88.51, "elapsed_time": "1 day, 5:04:07", "remaining_time": "3:46:21", "throughput": 552.57, "total_tokens": 57824784} {"current_steps": 35410, "total_steps": 40000, "loss": 0.123, "lr": 1.6076586560959257e-06, "epoch": 1.6030014260168859, "percentage": 88.52, "elapsed_time": "1 day, 5:04:10", "remaining_time": "3:46:05", "throughput": 552.63, "total_tokens": 57832464} {"current_steps": 35415, "total_steps": 40000, "loss": 0.072, "lr": 1.604196721159182e-06, "epoch": 1.6032277779035287, "percentage": 88.54, "elapsed_time": "1 day, 5:04:13", "remaining_time": "3:45:48", "throughput": 552.69, "total_tokens": 57840752} {"current_steps": 35420, "total_steps": 40000, "loss": 0.1168, "lr": 1.6007383941493092e-06, "epoch": 1.6034541297901717, "percentage": 88.55, "elapsed_time": "1 day, 5:04:16", "remaining_time": "3:45:32", "throughput": 552.75, "total_tokens": 57848784} {"current_steps": 35425, "total_steps": 40000, "loss": 0.1064, "lr": 1.5972836755996285e-06, "epoch": 1.6036804816768147, "percentage": 88.56, "elapsed_time": "1 day, 5:04:19", "remaining_time": "3:45:16", "throughput": 552.81, "total_tokens": 57857328} {"current_steps": 35430, "total_steps": 40000, "loss": 0.0892, "lr": 1.5938325660429076e-06, "epoch": 1.6039068335634576, "percentage": 88.58, "elapsed_time": "1 day, 5:04:23", "remaining_time": "3:45:00", "throughput": 552.88, "total_tokens": 57865936} {"current_steps": 35435, "total_steps": 40000, "loss": 0.0759, "lr": 1.5903850660113378e-06, "epoch": 1.6041331854501006, "percentage": 88.59, "elapsed_time": "1 day, 5:04:26", "remaining_time": "3:44:43", "throughput": 552.94, "total_tokens": 57873712} {"current_steps": 35440, "total_steps": 40000, "loss": 0.1073, "lr": 1.5869411760365826e-06, "epoch": 1.6043595373367436, "percentage": 88.6, "elapsed_time": "1 day, 5:04:29", "remaining_time": "3:44:27", "throughput": 553.0, "total_tokens": 57882000} {"current_steps": 35445, "total_steps": 40000, "loss": 0.0904, "lr": 1.58350089664972e-06, "epoch": 1.6045858892233866, "percentage": 88.61, "elapsed_time": "1 day, 5:04:32", "remaining_time": "3:44:11", "throughput": 553.06, "total_tokens": 57890192} {"current_steps": 35450, "total_steps": 40000, "loss": 0.0985, "lr": 1.5800642283812865e-06, "epoch": 1.6048122411100296, "percentage": 88.62, "elapsed_time": "1 day, 5:04:35", "remaining_time": "3:43:55", "throughput": 553.12, "total_tokens": 57898576} {"current_steps": 35455, "total_steps": 40000, "loss": 0.1452, "lr": 1.5766311717612698e-06, "epoch": 1.6050385929966726, "percentage": 88.64, "elapsed_time": "1 day, 5:04:39", "remaining_time": "3:43:38", "throughput": 553.18, "total_tokens": 57906512} {"current_steps": 35460, "total_steps": 40000, "loss": 0.1148, "lr": 1.5732017273190818e-06, "epoch": 1.6052649448833156, "percentage": 88.65, "elapsed_time": "1 day, 5:04:42", "remaining_time": "3:43:22", "throughput": 553.25, "total_tokens": 57915024} {"current_steps": 35465, "total_steps": 40000, "loss": 0.1183, "lr": 1.5697758955835806e-06, "epoch": 1.6054912967699586, "percentage": 88.66, "elapsed_time": "1 day, 5:04:45", "remaining_time": "3:43:06", "throughput": 553.31, "total_tokens": 57923056} {"current_steps": 35470, "total_steps": 40000, "loss": 0.1048, "lr": 1.566353677083085e-06, "epoch": 1.6057176486566016, "percentage": 88.67, "elapsed_time": "1 day, 5:04:48", "remaining_time": "3:42:50", "throughput": 553.36, "total_tokens": 57930832} {"current_steps": 35475, "total_steps": 40000, "loss": 0.1273, "lr": 1.562935072345334e-06, "epoch": 1.6059440005432446, "percentage": 88.69, "elapsed_time": "1 day, 5:04:51", "remaining_time": "3:42:33", "throughput": 553.42, "total_tokens": 57939088} {"current_steps": 35480, "total_steps": 40000, "loss": 0.087, "lr": 1.5595200818975281e-06, "epoch": 1.6061703524298876, "percentage": 88.7, "elapsed_time": "1 day, 5:04:55", "remaining_time": "3:42:17", "throughput": 553.48, "total_tokens": 57947120} {"current_steps": 35485, "total_steps": 40000, "loss": 0.1195, "lr": 1.5561087062662905e-06, "epoch": 1.6063967043165306, "percentage": 88.71, "elapsed_time": "1 day, 5:04:58", "remaining_time": "3:42:01", "throughput": 553.55, "total_tokens": 57955440} {"current_steps": 35490, "total_steps": 40000, "loss": 0.1143, "lr": 1.5527009459777087e-06, "epoch": 1.6066230562031736, "percentage": 88.72, "elapsed_time": "1 day, 5:05:01", "remaining_time": "3:41:45", "throughput": 553.61, "total_tokens": 57964240} {"current_steps": 35495, "total_steps": 40000, "loss": 0.132, "lr": 1.5492968015572984e-06, "epoch": 1.6068494080898166, "percentage": 88.74, "elapsed_time": "1 day, 5:05:04", "remaining_time": "3:41:29", "throughput": 553.67, "total_tokens": 57972176} {"current_steps": 35500, "total_steps": 40000, "loss": 0.1548, "lr": 1.5458962735300203e-06, "epoch": 1.6070757599764594, "percentage": 88.75, "elapsed_time": "1 day, 5:05:08", "remaining_time": "3:41:12", "throughput": 553.74, "total_tokens": 57980624} {"current_steps": 35505, "total_steps": 40000, "loss": 0.0888, "lr": 1.54249936242028e-06, "epoch": 1.6073021118631023, "percentage": 88.76, "elapsed_time": "1 day, 5:05:11", "remaining_time": "3:40:56", "throughput": 553.79, "total_tokens": 57988304} {"current_steps": 35510, "total_steps": 40000, "loss": 0.122, "lr": 1.5391060687519222e-06, "epoch": 1.6075284637497453, "percentage": 88.78, "elapsed_time": "1 day, 5:05:14", "remaining_time": "3:40:40", "throughput": 553.85, "total_tokens": 57996112} {"current_steps": 35515, "total_steps": 40000, "loss": 0.0562, "lr": 1.5357163930482367e-06, "epoch": 1.6077548156363883, "percentage": 88.79, "elapsed_time": "1 day, 5:05:17", "remaining_time": "3:40:24", "throughput": 553.91, "total_tokens": 58004560} {"current_steps": 35520, "total_steps": 40000, "loss": 0.138, "lr": 1.532330335831955e-06, "epoch": 1.6079811675230313, "percentage": 88.8, "elapsed_time": "1 day, 5:05:21", "remaining_time": "3:40:08", "throughput": 553.98, "total_tokens": 58013360} {"current_steps": 35525, "total_steps": 40000, "loss": 0.1391, "lr": 1.5289478976252491e-06, "epoch": 1.6082075194096743, "percentage": 88.81, "elapsed_time": "1 day, 5:05:24", "remaining_time": "3:39:51", "throughput": 554.04, "total_tokens": 58021616} {"current_steps": 35530, "total_steps": 40000, "loss": 0.108, "lr": 1.5255690789497345e-06, "epoch": 1.608433871296317, "percentage": 88.83, "elapsed_time": "1 day, 5:05:27", "remaining_time": "3:39:35", "throughput": 554.1, "total_tokens": 58029488} {"current_steps": 35535, "total_steps": 40000, "loss": 0.1034, "lr": 1.5221938803264641e-06, "epoch": 1.60866022318296, "percentage": 88.84, "elapsed_time": "1 day, 5:05:30", "remaining_time": "3:39:19", "throughput": 554.16, "total_tokens": 58037232} {"current_steps": 35540, "total_steps": 40000, "loss": 0.115, "lr": 1.518822302275938e-06, "epoch": 1.608886575069603, "percentage": 88.85, "elapsed_time": "1 day, 5:05:33", "remaining_time": "3:39:03", "throughput": 554.22, "total_tokens": 58045392} {"current_steps": 35545, "total_steps": 40000, "loss": 0.1362, "lr": 1.5154543453180958e-06, "epoch": 1.609112926956246, "percentage": 88.86, "elapsed_time": "1 day, 5:05:37", "remaining_time": "3:38:47", "throughput": 554.28, "total_tokens": 58053648} {"current_steps": 35550, "total_steps": 40000, "loss": 0.0825, "lr": 1.5120900099723167e-06, "epoch": 1.609339278842889, "percentage": 88.88, "elapsed_time": "1 day, 5:05:40", "remaining_time": "3:38:30", "throughput": 554.34, "total_tokens": 58061552} {"current_steps": 35555, "total_steps": 40000, "loss": 0.0978, "lr": 1.5087292967574273e-06, "epoch": 1.609565630729532, "percentage": 88.89, "elapsed_time": "1 day, 5:05:43", "remaining_time": "3:38:14", "throughput": 554.4, "total_tokens": 58069680} {"current_steps": 35560, "total_steps": 40000, "loss": 0.1878, "lr": 1.5053722061916908e-06, "epoch": 1.609791982616175, "percentage": 88.9, "elapsed_time": "1 day, 5:05:46", "remaining_time": "3:37:58", "throughput": 554.46, "total_tokens": 58077904} {"current_steps": 35565, "total_steps": 40000, "loss": 0.1122, "lr": 1.5020187387928124e-06, "epoch": 1.610018334502818, "percentage": 88.91, "elapsed_time": "1 day, 5:05:50", "remaining_time": "3:37:42", "throughput": 554.52, "total_tokens": 58086096} {"current_steps": 35570, "total_steps": 40000, "loss": 0.095, "lr": 1.4986688950779343e-06, "epoch": 1.610244686389461, "percentage": 88.92, "elapsed_time": "1 day, 5:05:53", "remaining_time": "3:37:26", "throughput": 554.58, "total_tokens": 58094096} {"current_steps": 35575, "total_steps": 40000, "loss": 0.0758, "lr": 1.495322675563654e-06, "epoch": 1.610471038276104, "percentage": 88.94, "elapsed_time": "1 day, 5:05:56", "remaining_time": "3:37:10", "throughput": 554.64, "total_tokens": 58102320} {"current_steps": 35580, "total_steps": 40000, "loss": 0.1075, "lr": 1.4919800807659922e-06, "epoch": 1.610697390162747, "percentage": 88.95, "elapsed_time": "1 day, 5:05:59", "remaining_time": "3:36:53", "throughput": 554.7, "total_tokens": 58110224} {"current_steps": 35585, "total_steps": 40000, "loss": 0.0876, "lr": 1.4886411112004255e-06, "epoch": 1.61092374204939, "percentage": 88.96, "elapsed_time": "1 day, 5:06:02", "remaining_time": "3:36:37", "throughput": 554.77, "total_tokens": 58119248} {"current_steps": 35590, "total_steps": 40000, "loss": 0.1487, "lr": 1.4853057673818588e-06, "epoch": 1.611150093936033, "percentage": 88.98, "elapsed_time": "1 day, 5:06:06", "remaining_time": "3:36:21", "throughput": 554.83, "total_tokens": 58127504} {"current_steps": 35595, "total_steps": 40000, "loss": 0.1367, "lr": 1.481974049824647e-06, "epoch": 1.611376445822676, "percentage": 88.99, "elapsed_time": "1 day, 5:06:09", "remaining_time": "3:36:05", "throughput": 554.89, "total_tokens": 58135344} {"current_steps": 35600, "total_steps": 40000, "loss": 0.1508, "lr": 1.4786459590425849e-06, "epoch": 1.611602797709319, "percentage": 89.0, "elapsed_time": "1 day, 5:06:12", "remaining_time": "3:35:49", "throughput": 554.94, "total_tokens": 58142864} {"current_steps": 35600, "total_steps": 40000, "eval_loss": 0.12202422320842743, "epoch": 1.611602797709319, "percentage": 89.0, "elapsed_time": "1 day, 5:13:55", "remaining_time": "3:36:46", "throughput": 552.5, "total_tokens": 58142864} {"current_steps": 35605, "total_steps": 40000, "loss": 0.1676, "lr": 1.4753214955489036e-06, "epoch": 1.611829149595962, "percentage": 89.01, "elapsed_time": "1 day, 5:13:59", "remaining_time": "3:36:30", "throughput": 552.56, "total_tokens": 58150608} {"current_steps": 35610, "total_steps": 40000, "loss": 0.1012, "lr": 1.4720006598562737e-06, "epoch": 1.612055501482605, "percentage": 89.03, "elapsed_time": "1 day, 5:14:02", "remaining_time": "3:36:14", "throughput": 552.62, "total_tokens": 58158896} {"current_steps": 35615, "total_steps": 40000, "loss": 0.1363, "lr": 1.4686834524768185e-06, "epoch": 1.6122818533692478, "percentage": 89.04, "elapsed_time": "1 day, 5:14:05", "remaining_time": "3:35:58", "throughput": 552.69, "total_tokens": 58168016} {"current_steps": 35620, "total_steps": 40000, "loss": 0.1198, "lr": 1.4653698739220844e-06, "epoch": 1.6125082052558908, "percentage": 89.05, "elapsed_time": "1 day, 5:14:08", "remaining_time": "3:35:41", "throughput": 552.75, "total_tokens": 58176176} {"current_steps": 35625, "total_steps": 40000, "loss": 0.1293, "lr": 1.4620599247030715e-06, "epoch": 1.6127345571425338, "percentage": 89.06, "elapsed_time": "1 day, 5:14:12", "remaining_time": "3:35:25", "throughput": 552.81, "total_tokens": 58184752} {"current_steps": 35630, "total_steps": 40000, "loss": 0.1172, "lr": 1.4587536053302125e-06, "epoch": 1.6129609090291768, "percentage": 89.08, "elapsed_time": "1 day, 5:14:15", "remaining_time": "3:35:09", "throughput": 552.87, "total_tokens": 58192432} {"current_steps": 35635, "total_steps": 40000, "loss": 0.1021, "lr": 1.4554509163133862e-06, "epoch": 1.6131872609158198, "percentage": 89.09, "elapsed_time": "1 day, 5:14:18", "remaining_time": "3:34:53", "throughput": 552.93, "total_tokens": 58200432} {"current_steps": 35640, "total_steps": 40000, "loss": 0.1626, "lr": 1.4521518581619098e-06, "epoch": 1.6134136128024628, "percentage": 89.1, "elapsed_time": "1 day, 5:14:21", "remaining_time": "3:34:37", "throughput": 552.99, "total_tokens": 58208752} {"current_steps": 35645, "total_steps": 40000, "loss": 0.1019, "lr": 1.4488564313845348e-06, "epoch": 1.6136399646891055, "percentage": 89.11, "elapsed_time": "1 day, 5:14:25", "remaining_time": "3:34:20", "throughput": 553.05, "total_tokens": 58217424} {"current_steps": 35650, "total_steps": 40000, "loss": 0.1583, "lr": 1.4455646364894603e-06, "epoch": 1.6138663165757485, "percentage": 89.12, "elapsed_time": "1 day, 5:14:28", "remaining_time": "3:34:04", "throughput": 553.11, "total_tokens": 58224976} {"current_steps": 35655, "total_steps": 40000, "loss": 0.1298, "lr": 1.4422764739843247e-06, "epoch": 1.6140926684623915, "percentage": 89.14, "elapsed_time": "1 day, 5:14:31", "remaining_time": "3:33:48", "throughput": 553.18, "total_tokens": 58233680} {"current_steps": 35660, "total_steps": 40000, "loss": 0.0953, "lr": 1.4389919443762e-06, "epoch": 1.6143190203490345, "percentage": 89.15, "elapsed_time": "1 day, 5:14:34", "remaining_time": "3:33:32", "throughput": 553.23, "total_tokens": 58241552} {"current_steps": 35665, "total_steps": 40000, "loss": 0.0915, "lr": 1.4357110481716063e-06, "epoch": 1.6145453722356775, "percentage": 89.16, "elapsed_time": "1 day, 5:14:38", "remaining_time": "3:33:16", "throughput": 553.29, "total_tokens": 58249744} {"current_steps": 35670, "total_steps": 40000, "loss": 0.1265, "lr": 1.4324337858764941e-06, "epoch": 1.6147717241223205, "percentage": 89.18, "elapsed_time": "1 day, 5:14:41", "remaining_time": "3:33:00", "throughput": 553.36, "total_tokens": 58258064} {"current_steps": 35675, "total_steps": 40000, "loss": 0.0908, "lr": 1.4291601579962622e-06, "epoch": 1.6149980760089635, "percentage": 89.19, "elapsed_time": "1 day, 5:14:44", "remaining_time": "3:32:43", "throughput": 553.41, "total_tokens": 58265648} {"current_steps": 35680, "total_steps": 40000, "loss": 0.0797, "lr": 1.42589016503574e-06, "epoch": 1.6152244278956065, "percentage": 89.2, "elapsed_time": "1 day, 5:14:47", "remaining_time": "3:32:27", "throughput": 553.47, "total_tokens": 58273776} {"current_steps": 35685, "total_steps": 40000, "loss": 0.1009, "lr": 1.4226238074992099e-06, "epoch": 1.6154507797822495, "percentage": 89.21, "elapsed_time": "1 day, 5:14:50", "remaining_time": "3:32:11", "throughput": 553.53, "total_tokens": 58281264} {"current_steps": 35690, "total_steps": 40000, "loss": 0.1422, "lr": 1.4193610858903778e-06, "epoch": 1.6156771316688925, "percentage": 89.22, "elapsed_time": "1 day, 5:14:54", "remaining_time": "3:31:55", "throughput": 553.59, "total_tokens": 58289808} {"current_steps": 35695, "total_steps": 40000, "loss": 0.126, "lr": 1.416102000712402e-06, "epoch": 1.6159034835555355, "percentage": 89.24, "elapsed_time": "1 day, 5:14:57", "remaining_time": "3:31:39", "throughput": 553.66, "total_tokens": 58298896} {"current_steps": 35700, "total_steps": 40000, "loss": 0.1146, "lr": 1.4128465524678668e-06, "epoch": 1.6161298354421785, "percentage": 89.25, "elapsed_time": "1 day, 5:15:00", "remaining_time": "3:31:23", "throughput": 553.71, "total_tokens": 58306640} {"current_steps": 35705, "total_steps": 40000, "loss": 0.0999, "lr": 1.4095947416588124e-06, "epoch": 1.6163561873288215, "percentage": 89.26, "elapsed_time": "1 day, 5:15:04", "remaining_time": "3:31:07", "throughput": 553.78, "total_tokens": 58315088} {"current_steps": 35710, "total_steps": 40000, "loss": 0.1208, "lr": 1.4063465687866983e-06, "epoch": 1.6165825392154645, "percentage": 89.28, "elapsed_time": "1 day, 5:15:07", "remaining_time": "3:30:51", "throughput": 553.84, "total_tokens": 58323568} {"current_steps": 35715, "total_steps": 40000, "loss": 0.1119, "lr": 1.4031020343524438e-06, "epoch": 1.6168088911021075, "percentage": 89.29, "elapsed_time": "1 day, 5:15:10", "remaining_time": "3:30:34", "throughput": 553.9, "total_tokens": 58331824} {"current_steps": 35720, "total_steps": 40000, "loss": 0.1075, "lr": 1.3998611388563926e-06, "epoch": 1.6170352429887505, "percentage": 89.3, "elapsed_time": "1 day, 5:15:13", "remaining_time": "3:30:18", "throughput": 553.96, "total_tokens": 58339984} {"current_steps": 35725, "total_steps": 40000, "loss": 0.1225, "lr": 1.3966238827983314e-06, "epoch": 1.6172615948753934, "percentage": 89.31, "elapsed_time": "1 day, 5:15:17", "remaining_time": "3:30:02", "throughput": 554.02, "total_tokens": 58347984} {"current_steps": 35730, "total_steps": 40000, "loss": 0.1195, "lr": 1.393390266677483e-06, "epoch": 1.6174879467620362, "percentage": 89.33, "elapsed_time": "1 day, 5:15:20", "remaining_time": "3:29:46", "throughput": 554.08, "total_tokens": 58356240} {"current_steps": 35735, "total_steps": 40000, "loss": 0.118, "lr": 1.3901602909925204e-06, "epoch": 1.6177142986486792, "percentage": 89.34, "elapsed_time": "1 day, 5:15:23", "remaining_time": "3:29:30", "throughput": 554.14, "total_tokens": 58363664} {"current_steps": 35740, "total_steps": 40000, "loss": 0.0947, "lr": 1.3869339562415373e-06, "epoch": 1.6179406505353222, "percentage": 89.35, "elapsed_time": "1 day, 5:15:26", "remaining_time": "3:29:14", "throughput": 554.2, "total_tokens": 58372208} {"current_steps": 35745, "total_steps": 40000, "loss": 0.1019, "lr": 1.38371126292208e-06, "epoch": 1.6181670024219652, "percentage": 89.36, "elapsed_time": "1 day, 5:15:29", "remaining_time": "3:28:58", "throughput": 554.26, "total_tokens": 58379856} {"current_steps": 35750, "total_steps": 40000, "loss": 0.0937, "lr": 1.3804922115311286e-06, "epoch": 1.6183933543086082, "percentage": 89.38, "elapsed_time": "1 day, 5:15:33", "remaining_time": "3:28:42", "throughput": 554.32, "total_tokens": 58388336} {"current_steps": 35755, "total_steps": 40000, "loss": 0.0713, "lr": 1.3772768025650945e-06, "epoch": 1.618619706195251, "percentage": 89.39, "elapsed_time": "1 day, 5:15:36", "remaining_time": "3:28:26", "throughput": 554.39, "total_tokens": 58397168} {"current_steps": 35760, "total_steps": 40000, "loss": 0.1407, "lr": 1.3740650365198448e-06, "epoch": 1.618846058081894, "percentage": 89.4, "elapsed_time": "1 day, 5:15:39", "remaining_time": "3:28:09", "throughput": 554.45, "total_tokens": 58405424} {"current_steps": 35765, "total_steps": 40000, "loss": 0.1161, "lr": 1.3708569138906612e-06, "epoch": 1.619072409968537, "percentage": 89.41, "elapsed_time": "1 day, 5:15:43", "remaining_time": "3:27:53", "throughput": 554.51, "total_tokens": 58413456} {"current_steps": 35770, "total_steps": 40000, "loss": 0.1757, "lr": 1.367652435172287e-06, "epoch": 1.61929876185518, "percentage": 89.42, "elapsed_time": "1 day, 5:15:46", "remaining_time": "3:27:37", "throughput": 554.57, "total_tokens": 58421424} {"current_steps": 35775, "total_steps": 40000, "loss": 0.0908, "lr": 1.364451600858893e-06, "epoch": 1.619525113741823, "percentage": 89.44, "elapsed_time": "1 day, 5:15:49", "remaining_time": "3:27:21", "throughput": 554.63, "total_tokens": 58430224} {"current_steps": 35780, "total_steps": 40000, "loss": 0.0734, "lr": 1.3612544114440823e-06, "epoch": 1.619751465628466, "percentage": 89.45, "elapsed_time": "1 day, 5:15:52", "remaining_time": "3:27:05", "throughput": 554.69, "total_tokens": 58438608} {"current_steps": 35785, "total_steps": 40000, "loss": 0.1073, "lr": 1.3580608674209072e-06, "epoch": 1.619977817515109, "percentage": 89.46, "elapsed_time": "1 day, 5:15:56", "remaining_time": "3:26:49", "throughput": 554.75, "total_tokens": 58446032} {"current_steps": 35790, "total_steps": 40000, "loss": 0.1327, "lr": 1.3548709692818434e-06, "epoch": 1.620204169401752, "percentage": 89.48, "elapsed_time": "1 day, 5:15:59", "remaining_time": "3:26:33", "throughput": 554.81, "total_tokens": 58453840} {"current_steps": 35795, "total_steps": 40000, "loss": 0.1183, "lr": 1.3516847175188223e-06, "epoch": 1.620430521288395, "percentage": 89.49, "elapsed_time": "1 day, 5:16:02", "remaining_time": "3:26:17", "throughput": 554.86, "total_tokens": 58461712} {"current_steps": 35800, "total_steps": 40000, "loss": 0.0994, "lr": 1.348502112623204e-06, "epoch": 1.620656873175038, "percentage": 89.5, "elapsed_time": "1 day, 5:16:05", "remaining_time": "3:26:01", "throughput": 554.92, "total_tokens": 58469616} {"current_steps": 35800, "total_steps": 40000, "eval_loss": 0.12191226333379745, "epoch": 1.620656873175038, "percentage": 89.5, "elapsed_time": "1 day, 5:23:48", "remaining_time": "3:26:55", "throughput": 552.5, "total_tokens": 58469616} {"current_steps": 35805, "total_steps": 40000, "loss": 0.0994, "lr": 1.3453231550857787e-06, "epoch": 1.620883225061681, "percentage": 89.51, "elapsed_time": "1 day, 5:23:53", "remaining_time": "3:26:39", "throughput": 552.54, "total_tokens": 58477648} {"current_steps": 35810, "total_steps": 40000, "loss": 0.0938, "lr": 1.3421478453967878e-06, "epoch": 1.621109576948324, "percentage": 89.53, "elapsed_time": "1 day, 5:23:56", "remaining_time": "3:26:23", "throughput": 552.61, "total_tokens": 58486192} {"current_steps": 35815, "total_steps": 40000, "loss": 0.1137, "lr": 1.3389761840459065e-06, "epoch": 1.621335928834967, "percentage": 89.54, "elapsed_time": "1 day, 5:23:59", "remaining_time": "3:26:07", "throughput": 552.67, "total_tokens": 58494224} {"current_steps": 35820, "total_steps": 40000, "loss": 0.1366, "lr": 1.3358081715222376e-06, "epoch": 1.62156228072161, "percentage": 89.55, "elapsed_time": "1 day, 5:24:03", "remaining_time": "3:25:51", "throughput": 552.73, "total_tokens": 58502864} {"current_steps": 35825, "total_steps": 40000, "loss": 0.1526, "lr": 1.3326438083143295e-06, "epoch": 1.621788632608253, "percentage": 89.56, "elapsed_time": "1 day, 5:24:06", "remaining_time": "3:25:35", "throughput": 552.79, "total_tokens": 58510768} {"current_steps": 35830, "total_steps": 40000, "loss": 0.118, "lr": 1.3294830949101723e-06, "epoch": 1.622014984494896, "percentage": 89.58, "elapsed_time": "1 day, 5:24:09", "remaining_time": "3:25:19", "throughput": 552.85, "total_tokens": 58519056} {"current_steps": 35835, "total_steps": 40000, "loss": 0.116, "lr": 1.3263260317971815e-06, "epoch": 1.622241336381539, "percentage": 89.59, "elapsed_time": "1 day, 5:24:12", "remaining_time": "3:25:02", "throughput": 552.92, "total_tokens": 58527696} {"current_steps": 35840, "total_steps": 40000, "loss": 0.0836, "lr": 1.3231726194622208e-06, "epoch": 1.6224676882681817, "percentage": 89.6, "elapsed_time": "1 day, 5:24:15", "remaining_time": "3:24:46", "throughput": 552.97, "total_tokens": 58535024} {"current_steps": 35845, "total_steps": 40000, "loss": 0.1587, "lr": 1.3200228583915814e-06, "epoch": 1.6226940401548247, "percentage": 89.61, "elapsed_time": "1 day, 5:24:19", "remaining_time": "3:24:30", "throughput": 553.03, "total_tokens": 58543408} {"current_steps": 35850, "total_steps": 40000, "loss": 0.086, "lr": 1.3168767490709971e-06, "epoch": 1.6229203920414677, "percentage": 89.62, "elapsed_time": "1 day, 5:24:22", "remaining_time": "3:24:14", "throughput": 553.09, "total_tokens": 58551056} {"current_steps": 35855, "total_steps": 40000, "loss": 0.179, "lr": 1.3137342919856437e-06, "epoch": 1.6231467439281106, "percentage": 89.64, "elapsed_time": "1 day, 5:24:25", "remaining_time": "3:23:58", "throughput": 553.15, "total_tokens": 58559248} {"current_steps": 35860, "total_steps": 40000, "loss": 0.1451, "lr": 1.310595487620117e-06, "epoch": 1.6233730958147536, "percentage": 89.65, "elapsed_time": "1 day, 5:24:28", "remaining_time": "3:23:42", "throughput": 553.21, "total_tokens": 58567024} {"current_steps": 35865, "total_steps": 40000, "loss": 0.114, "lr": 1.3074603364584715e-06, "epoch": 1.6235994477013966, "percentage": 89.66, "elapsed_time": "1 day, 5:24:31", "remaining_time": "3:23:26", "throughput": 553.27, "total_tokens": 58575088} {"current_steps": 35870, "total_steps": 40000, "loss": 0.1238, "lr": 1.3043288389841758e-06, "epoch": 1.6238257995880394, "percentage": 89.68, "elapsed_time": "1 day, 5:24:34", "remaining_time": "3:23:10", "throughput": 553.33, "total_tokens": 58583472} {"current_steps": 35875, "total_steps": 40000, "loss": 0.1394, "lr": 1.3012009956801546e-06, "epoch": 1.6240521514746824, "percentage": 89.69, "elapsed_time": "1 day, 5:24:37", "remaining_time": "3:22:54", "throughput": 553.38, "total_tokens": 58591120} {"current_steps": 35880, "total_steps": 40000, "loss": 0.0692, "lr": 1.2980768070287586e-06, "epoch": 1.6242785033613254, "percentage": 89.7, "elapsed_time": "1 day, 5:24:41", "remaining_time": "3:22:38", "throughput": 553.44, "total_tokens": 58599280} {"current_steps": 35885, "total_steps": 40000, "loss": 0.1323, "lr": 1.2949562735117716e-06, "epoch": 1.6245048552479684, "percentage": 89.71, "elapsed_time": "1 day, 5:24:44", "remaining_time": "3:22:21", "throughput": 553.5, "total_tokens": 58607312} {"current_steps": 35890, "total_steps": 40000, "loss": 0.1061, "lr": 1.291839395610428e-06, "epoch": 1.6247312071346114, "percentage": 89.72, "elapsed_time": "1 day, 5:24:47", "remaining_time": "3:22:05", "throughput": 553.57, "total_tokens": 58616272} {"current_steps": 35895, "total_steps": 40000, "loss": 0.1286, "lr": 1.2887261738053852e-06, "epoch": 1.6249575590212544, "percentage": 89.74, "elapsed_time": "1 day, 5:24:50", "remaining_time": "3:21:49", "throughput": 553.63, "total_tokens": 58624144} {"current_steps": 35900, "total_steps": 40000, "loss": 0.1445, "lr": 1.2856166085767396e-06, "epoch": 1.6251839109078974, "percentage": 89.75, "elapsed_time": "1 day, 5:24:53", "remaining_time": "3:21:33", "throughput": 553.69, "total_tokens": 58632272} {"current_steps": 35905, "total_steps": 40000, "loss": 0.119, "lr": 1.2825107004040272e-06, "epoch": 1.6254102627945404, "percentage": 89.76, "elapsed_time": "1 day, 5:24:56", "remaining_time": "3:21:17", "throughput": 553.74, "total_tokens": 58639856} {"current_steps": 35910, "total_steps": 40000, "loss": 0.1141, "lr": 1.2794084497662146e-06, "epoch": 1.6256366146811834, "percentage": 89.78, "elapsed_time": "1 day, 5:25:00", "remaining_time": "3:21:01", "throughput": 553.8, "total_tokens": 58648016} {"current_steps": 35915, "total_steps": 40000, "loss": 0.0909, "lr": 1.276309857141711e-06, "epoch": 1.6258629665678264, "percentage": 89.79, "elapsed_time": "1 day, 5:25:03", "remaining_time": "3:20:45", "throughput": 553.87, "total_tokens": 58656144} {"current_steps": 35920, "total_steps": 40000, "loss": 0.1133, "lr": 1.273214923008359e-06, "epoch": 1.6260893184544694, "percentage": 89.8, "elapsed_time": "1 day, 5:25:06", "remaining_time": "3:20:29", "throughput": 553.92, "total_tokens": 58664048} {"current_steps": 35925, "total_steps": 40000, "loss": 0.1703, "lr": 1.2701236478434352e-06, "epoch": 1.6263156703411124, "percentage": 89.81, "elapsed_time": "1 day, 5:25:09", "remaining_time": "3:20:13", "throughput": 553.98, "total_tokens": 58671408} {"current_steps": 35930, "total_steps": 40000, "loss": 0.1169, "lr": 1.2670360321236502e-06, "epoch": 1.6265420222277553, "percentage": 89.83, "elapsed_time": "1 day, 5:25:12", "remaining_time": "3:19:57", "throughput": 554.04, "total_tokens": 58679472} {"current_steps": 35935, "total_steps": 40000, "loss": 0.1055, "lr": 1.2639520763251617e-06, "epoch": 1.6267683741143983, "percentage": 89.84, "elapsed_time": "1 day, 5:25:15", "remaining_time": "3:19:41", "throughput": 554.1, "total_tokens": 58687408} {"current_steps": 35940, "total_steps": 40000, "loss": 0.1067, "lr": 1.2608717809235448e-06, "epoch": 1.6269947260010413, "percentage": 89.85, "elapsed_time": "1 day, 5:25:18", "remaining_time": "3:19:25", "throughput": 554.16, "total_tokens": 58695664} {"current_steps": 35945, "total_steps": 40000, "loss": 0.1298, "lr": 1.2577951463938282e-06, "epoch": 1.6272210778876843, "percentage": 89.86, "elapsed_time": "1 day, 5:25:22", "remaining_time": "3:19:09", "throughput": 554.22, "total_tokens": 58704400} {"current_steps": 35950, "total_steps": 40000, "loss": 0.1321, "lr": 1.2547221732104569e-06, "epoch": 1.6274474297743273, "percentage": 89.88, "elapsed_time": "1 day, 5:25:25", "remaining_time": "3:18:53", "throughput": 554.28, "total_tokens": 58712272} {"current_steps": 35955, "total_steps": 40000, "loss": 0.118, "lr": 1.25165286184733e-06, "epoch": 1.62767378166097, "percentage": 89.89, "elapsed_time": "1 day, 5:25:28", "remaining_time": "3:18:37", "throughput": 554.34, "total_tokens": 58720016} {"current_steps": 35960, "total_steps": 40000, "loss": 0.1107, "lr": 1.248587212777777e-06, "epoch": 1.627900133547613, "percentage": 89.9, "elapsed_time": "1 day, 5:25:31", "remaining_time": "3:18:21", "throughput": 554.4, "total_tokens": 58728176} {"current_steps": 35965, "total_steps": 40000, "loss": 0.0968, "lr": 1.2455252264745532e-06, "epoch": 1.628126485434256, "percentage": 89.91, "elapsed_time": "1 day, 5:25:34", "remaining_time": "3:18:05", "throughput": 554.45, "total_tokens": 58735728} {"current_steps": 35970, "total_steps": 40000, "loss": 0.1429, "lr": 1.2424669034098528e-06, "epoch": 1.628352837320899, "percentage": 89.92, "elapsed_time": "1 day, 5:25:37", "remaining_time": "3:17:49", "throughput": 554.51, "total_tokens": 58743920} {"current_steps": 35975, "total_steps": 40000, "loss": 0.1043, "lr": 1.2394122440553185e-06, "epoch": 1.628579189207542, "percentage": 89.94, "elapsed_time": "1 day, 5:25:41", "remaining_time": "3:17:33", "throughput": 554.57, "total_tokens": 58751888} {"current_steps": 35980, "total_steps": 40000, "loss": 0.0953, "lr": 1.2363612488820037e-06, "epoch": 1.628805541094185, "percentage": 89.95, "elapsed_time": "1 day, 5:25:44", "remaining_time": "3:17:17", "throughput": 554.63, "total_tokens": 58760048} {"current_steps": 35985, "total_steps": 40000, "loss": 0.1145, "lr": 1.2333139183604208e-06, "epoch": 1.6290318929808278, "percentage": 89.96, "elapsed_time": "1 day, 5:25:47", "remaining_time": "3:17:01", "throughput": 554.69, "total_tokens": 58767856} {"current_steps": 35990, "total_steps": 40000, "loss": 0.2014, "lr": 1.2302702529604998e-06, "epoch": 1.6292582448674708, "percentage": 89.98, "elapsed_time": "1 day, 5:25:50", "remaining_time": "3:16:44", "throughput": 554.75, "total_tokens": 58775664} {"current_steps": 35995, "total_steps": 40000, "loss": 0.1195, "lr": 1.227230253151615e-06, "epoch": 1.6294845967541138, "percentage": 89.99, "elapsed_time": "1 day, 5:25:53", "remaining_time": "3:16:29", "throughput": 554.82, "total_tokens": 58784848} {"current_steps": 36000, "total_steps": 40000, "loss": 0.1437, "lr": 1.2241939194025748e-06, "epoch": 1.6297109486407568, "percentage": 90.0, "elapsed_time": "1 day, 5:25:57", "remaining_time": "3:16:13", "throughput": 554.87, "total_tokens": 58792656} {"current_steps": 36000, "total_steps": 40000, "eval_loss": 0.12202613800764084, "epoch": 1.6297109486407568, "percentage": 90.0, "elapsed_time": "1 day, 5:33:39", "remaining_time": "3:17:04", "throughput": 552.46, "total_tokens": 58792656} {"current_steps": 36005, "total_steps": 40000, "loss": 0.1239, "lr": 1.2211612521816156e-06, "epoch": 1.6299373005273998, "percentage": 90.01, "elapsed_time": "1 day, 5:33:43", "remaining_time": "3:16:48", "throughput": 552.51, "total_tokens": 58800272} {"current_steps": 36010, "total_steps": 40000, "loss": 0.1335, "lr": 1.2181322519564137e-06, "epoch": 1.6301636524140428, "percentage": 90.03, "elapsed_time": "1 day, 5:33:46", "remaining_time": "3:16:32", "throughput": 552.57, "total_tokens": 58808144} {"current_steps": 36015, "total_steps": 40000, "loss": 0.0854, "lr": 1.2151069191940839e-06, "epoch": 1.6303900043006858, "percentage": 90.04, "elapsed_time": "1 day, 5:33:50", "remaining_time": "3:16:16", "throughput": 552.63, "total_tokens": 58816720} {"current_steps": 36020, "total_steps": 40000, "loss": 0.1529, "lr": 1.2120852543611644e-06, "epoch": 1.6306163561873288, "percentage": 90.05, "elapsed_time": "1 day, 5:33:53", "remaining_time": "3:16:00", "throughput": 552.69, "total_tokens": 58824432} {"current_steps": 36025, "total_steps": 40000, "loss": 0.1096, "lr": 1.2090672579236379e-06, "epoch": 1.6308427080739718, "percentage": 90.06, "elapsed_time": "1 day, 5:33:56", "remaining_time": "3:15:44", "throughput": 552.75, "total_tokens": 58832912} {"current_steps": 36030, "total_steps": 40000, "loss": 0.1869, "lr": 1.2060529303469126e-06, "epoch": 1.6310690599606148, "percentage": 90.08, "elapsed_time": "1 day, 5:33:59", "remaining_time": "3:15:28", "throughput": 552.81, "total_tokens": 58841168} {"current_steps": 36035, "total_steps": 40000, "loss": 0.1502, "lr": 1.2030422720958445e-06, "epoch": 1.6312954118472578, "percentage": 90.09, "elapsed_time": "1 day, 5:34:02", "remaining_time": "3:15:12", "throughput": 552.87, "total_tokens": 58849168} {"current_steps": 36040, "total_steps": 40000, "loss": 0.1321, "lr": 1.200035283634704e-06, "epoch": 1.6315217637339008, "percentage": 90.1, "elapsed_time": "1 day, 5:34:05", "remaining_time": "3:14:56", "throughput": 552.93, "total_tokens": 58857264} {"current_steps": 36045, "total_steps": 40000, "loss": 0.127, "lr": 1.1970319654272144e-06, "epoch": 1.6317481156205438, "percentage": 90.11, "elapsed_time": "1 day, 5:34:09", "remaining_time": "3:14:40", "throughput": 552.99, "total_tokens": 58865264} {"current_steps": 36050, "total_steps": 40000, "loss": 0.0724, "lr": 1.1940323179365192e-06, "epoch": 1.6319744675071868, "percentage": 90.12, "elapsed_time": "1 day, 5:34:12", "remaining_time": "3:14:23", "throughput": 553.05, "total_tokens": 58873392} {"current_steps": 36055, "total_steps": 40000, "loss": 0.121, "lr": 1.1910363416252095e-06, "epoch": 1.6322008193938298, "percentage": 90.14, "elapsed_time": "1 day, 5:34:15", "remaining_time": "3:14:07", "throughput": 553.12, "total_tokens": 58882416} {"current_steps": 36060, "total_steps": 40000, "loss": 0.1307, "lr": 1.1880440369552964e-06, "epoch": 1.6324271712804728, "percentage": 90.15, "elapsed_time": "1 day, 5:34:18", "remaining_time": "3:13:51", "throughput": 553.18, "total_tokens": 58890768} {"current_steps": 36065, "total_steps": 40000, "loss": 0.0932, "lr": 1.1850554043882328e-06, "epoch": 1.6326535231671158, "percentage": 90.16, "elapsed_time": "1 day, 5:34:22", "remaining_time": "3:13:35", "throughput": 553.24, "total_tokens": 58899056} {"current_steps": 36070, "total_steps": 40000, "loss": 0.1136, "lr": 1.1820704443849028e-06, "epoch": 1.6328798750537585, "percentage": 90.18, "elapsed_time": "1 day, 5:34:25", "remaining_time": "3:13:19", "throughput": 553.31, "total_tokens": 58907856} {"current_steps": 36075, "total_steps": 40000, "loss": 0.1342, "lr": 1.1790891574056219e-06, "epoch": 1.6331062269404015, "percentage": 90.19, "elapsed_time": "1 day, 5:34:28", "remaining_time": "3:13:03", "throughput": 553.36, "total_tokens": 58915728} {"current_steps": 36080, "total_steps": 40000, "loss": 0.1348, "lr": 1.1761115439101523e-06, "epoch": 1.6333325788270445, "percentage": 90.2, "elapsed_time": "1 day, 5:34:31", "remaining_time": "3:12:47", "throughput": 553.43, "total_tokens": 58924816} {"current_steps": 36085, "total_steps": 40000, "loss": 0.1487, "lr": 1.1731376043576659e-06, "epoch": 1.6335589307136875, "percentage": 90.21, "elapsed_time": "1 day, 5:34:35", "remaining_time": "3:12:31", "throughput": 553.49, "total_tokens": 58933136} {"current_steps": 36090, "total_steps": 40000, "loss": 0.1257, "lr": 1.1701673392067875e-06, "epoch": 1.6337852826003305, "percentage": 90.22, "elapsed_time": "1 day, 5:34:38", "remaining_time": "3:12:15", "throughput": 553.55, "total_tokens": 58941200} {"current_steps": 36095, "total_steps": 40000, "loss": 0.1308, "lr": 1.1672007489155757e-06, "epoch": 1.6340116344869733, "percentage": 90.24, "elapsed_time": "1 day, 5:34:41", "remaining_time": "3:11:59", "throughput": 553.61, "total_tokens": 58949744} {"current_steps": 36100, "total_steps": 40000, "loss": 0.0689, "lr": 1.164237833941506e-06, "epoch": 1.6342379863736163, "percentage": 90.25, "elapsed_time": "1 day, 5:34:44", "remaining_time": "3:11:43", "throughput": 553.67, "total_tokens": 58957680} {"current_steps": 36105, "total_steps": 40000, "loss": 0.1103, "lr": 1.1612785947415022e-06, "epoch": 1.6344643382602593, "percentage": 90.26, "elapsed_time": "1 day, 5:34:48", "remaining_time": "3:11:27", "throughput": 553.73, "total_tokens": 58965840} {"current_steps": 36110, "total_steps": 40000, "loss": 0.1022, "lr": 1.1583230317719185e-06, "epoch": 1.6346906901469023, "percentage": 90.28, "elapsed_time": "1 day, 5:34:51", "remaining_time": "3:11:11", "throughput": 553.79, "total_tokens": 58973840} {"current_steps": 36115, "total_steps": 40000, "loss": 0.1264, "lr": 1.1553711454885318e-06, "epoch": 1.6349170420335453, "percentage": 90.29, "elapsed_time": "1 day, 5:34:54", "remaining_time": "3:10:55", "throughput": 553.86, "total_tokens": 58982928} {"current_steps": 36120, "total_steps": 40000, "loss": 0.1501, "lr": 1.152422936346567e-06, "epoch": 1.6351433939201883, "percentage": 90.3, "elapsed_time": "1 day, 5:34:57", "remaining_time": "3:10:39", "throughput": 553.92, "total_tokens": 58990640} {"current_steps": 36125, "total_steps": 40000, "loss": 0.1251, "lr": 1.1494784048006718e-06, "epoch": 1.6353697458068313, "percentage": 90.31, "elapsed_time": "1 day, 5:35:00", "remaining_time": "3:10:23", "throughput": 553.98, "total_tokens": 58998992} {"current_steps": 36130, "total_steps": 40000, "loss": 0.1018, "lr": 1.1465375513049326e-06, "epoch": 1.6355960976934742, "percentage": 90.33, "elapsed_time": "1 day, 5:35:04", "remaining_time": "3:10:07", "throughput": 554.04, "total_tokens": 59007056} {"current_steps": 36135, "total_steps": 40000, "loss": 0.1617, "lr": 1.1436003763128616e-06, "epoch": 1.6358224495801172, "percentage": 90.34, "elapsed_time": "1 day, 5:35:07", "remaining_time": "3:09:51", "throughput": 554.09, "total_tokens": 59014768} {"current_steps": 36140, "total_steps": 40000, "loss": 0.169, "lr": 1.1406668802774106e-06, "epoch": 1.6360488014667602, "percentage": 90.35, "elapsed_time": "1 day, 5:35:10", "remaining_time": "3:09:36", "throughput": 554.16, "total_tokens": 59024176} {"current_steps": 36145, "total_steps": 40000, "loss": 0.1106, "lr": 1.137737063650965e-06, "epoch": 1.6362751533534032, "percentage": 90.36, "elapsed_time": "1 day, 5:35:13", "remaining_time": "3:09:20", "throughput": 554.23, "total_tokens": 59032912} {"current_steps": 36150, "total_steps": 40000, "loss": 0.1268, "lr": 1.1348109268853323e-06, "epoch": 1.6365015052400462, "percentage": 90.38, "elapsed_time": "1 day, 5:35:17", "remaining_time": "3:09:04", "throughput": 554.29, "total_tokens": 59041296} {"current_steps": 36155, "total_steps": 40000, "loss": 0.1233, "lr": 1.1318884704317634e-06, "epoch": 1.6367278571266892, "percentage": 90.39, "elapsed_time": "1 day, 5:35:20", "remaining_time": "3:08:48", "throughput": 554.35, "total_tokens": 59049232} {"current_steps": 36160, "total_steps": 40000, "loss": 0.1158, "lr": 1.1289696947409417e-06, "epoch": 1.6369542090133322, "percentage": 90.4, "elapsed_time": "1 day, 5:35:23", "remaining_time": "3:08:32", "throughput": 554.41, "total_tokens": 59057424} {"current_steps": 36165, "total_steps": 40000, "loss": 0.1233, "lr": 1.126054600262974e-06, "epoch": 1.6371805608999752, "percentage": 90.41, "elapsed_time": "1 day, 5:35:26", "remaining_time": "3:08:16", "throughput": 554.47, "total_tokens": 59065808} {"current_steps": 36170, "total_steps": 40000, "loss": 0.1822, "lr": 1.1231431874474064e-06, "epoch": 1.6374069127866182, "percentage": 90.42, "elapsed_time": "1 day, 5:35:29", "remaining_time": "3:08:00", "throughput": 554.53, "total_tokens": 59074128} {"current_steps": 36175, "total_steps": 40000, "loss": 0.1308, "lr": 1.12023545674321e-06, "epoch": 1.6376332646732612, "percentage": 90.44, "elapsed_time": "1 day, 5:35:33", "remaining_time": "3:07:44", "throughput": 554.6, "total_tokens": 59083216} {"current_steps": 36180, "total_steps": 40000, "loss": 0.1055, "lr": 1.117331408598804e-06, "epoch": 1.637859616559904, "percentage": 90.45, "elapsed_time": "1 day, 5:35:36", "remaining_time": "3:07:28", "throughput": 554.66, "total_tokens": 59091216} {"current_steps": 36185, "total_steps": 40000, "loss": 0.0928, "lr": 1.1144310434620191e-06, "epoch": 1.638085968446547, "percentage": 90.46, "elapsed_time": "1 day, 5:35:39", "remaining_time": "3:07:12", "throughput": 554.71, "total_tokens": 59098864} {"current_steps": 36190, "total_steps": 40000, "loss": 0.1575, "lr": 1.1115343617801365e-06, "epoch": 1.63831232033319, "percentage": 90.48, "elapsed_time": "1 day, 5:35:42", "remaining_time": "3:06:56", "throughput": 554.77, "total_tokens": 59107152} {"current_steps": 36195, "total_steps": 40000, "loss": 0.0805, "lr": 1.1086413639998515e-06, "epoch": 1.638538672219833, "percentage": 90.49, "elapsed_time": "1 day, 5:35:45", "remaining_time": "3:06:40", "throughput": 554.83, "total_tokens": 59115184} {"current_steps": 36200, "total_steps": 40000, "loss": 0.159, "lr": 1.1057520505673103e-06, "epoch": 1.638765024106476, "percentage": 90.5, "elapsed_time": "1 day, 5:35:48", "remaining_time": "3:06:24", "throughput": 554.9, "total_tokens": 59123504} {"current_steps": 36200, "total_steps": 40000, "eval_loss": 0.12204698473215103, "epoch": 1.638765024106476, "percentage": 90.5, "elapsed_time": "1 day, 5:43:31", "remaining_time": "3:07:13", "throughput": 552.5, "total_tokens": 59123504} {"current_steps": 36205, "total_steps": 40000, "loss": 0.0917, "lr": 1.1028664219280727e-06, "epoch": 1.638991375993119, "percentage": 90.51, "elapsed_time": "1 day, 5:43:35", "remaining_time": "3:06:57", "throughput": 552.56, "total_tokens": 59132112} {"current_steps": 36210, "total_steps": 40000, "loss": 0.1137, "lr": 1.0999844785271468e-06, "epoch": 1.6392177278797617, "percentage": 90.53, "elapsed_time": "1 day, 5:43:38", "remaining_time": "3:06:41", "throughput": 552.61, "total_tokens": 59139984} {"current_steps": 36215, "total_steps": 40000, "loss": 0.131, "lr": 1.097106220808955e-06, "epoch": 1.6394440797664047, "percentage": 90.54, "elapsed_time": "1 day, 5:43:41", "remaining_time": "3:06:25", "throughput": 552.67, "total_tokens": 59147504} {"current_steps": 36220, "total_steps": 40000, "loss": 0.1008, "lr": 1.0942316492173698e-06, "epoch": 1.6396704316530477, "percentage": 90.55, "elapsed_time": "1 day, 5:43:45", "remaining_time": "3:06:09", "throughput": 552.73, "total_tokens": 59155696} {"current_steps": 36225, "total_steps": 40000, "loss": 0.1348, "lr": 1.0913607641956841e-06, "epoch": 1.6398967835396907, "percentage": 90.56, "elapsed_time": "1 day, 5:43:48", "remaining_time": "3:05:53", "throughput": 552.78, "total_tokens": 59163376} {"current_steps": 36230, "total_steps": 40000, "loss": 0.1229, "lr": 1.0884935661866213e-06, "epoch": 1.6401231354263337, "percentage": 90.58, "elapsed_time": "1 day, 5:43:51", "remaining_time": "3:05:37", "throughput": 552.84, "total_tokens": 59171056} {"current_steps": 36235, "total_steps": 40000, "loss": 0.102, "lr": 1.0856300556323418e-06, "epoch": 1.6403494873129767, "percentage": 90.59, "elapsed_time": "1 day, 5:43:54", "remaining_time": "3:05:21", "throughput": 552.9, "total_tokens": 59178928} {"current_steps": 36240, "total_steps": 40000, "loss": 0.0772, "lr": 1.0827702329744365e-06, "epoch": 1.6405758391996197, "percentage": 90.6, "elapsed_time": "1 day, 5:43:57", "remaining_time": "3:05:05", "throughput": 552.96, "total_tokens": 59187248} {"current_steps": 36245, "total_steps": 40000, "loss": 0.1385, "lr": 1.0799140986539197e-06, "epoch": 1.6408021910862627, "percentage": 90.61, "elapsed_time": "1 day, 5:44:00", "remaining_time": "3:04:49", "throughput": 553.02, "total_tokens": 59195344} {"current_steps": 36250, "total_steps": 40000, "loss": 0.083, "lr": 1.0770616531112526e-06, "epoch": 1.6410285429729057, "percentage": 90.62, "elapsed_time": "1 day, 5:44:03", "remaining_time": "3:04:33", "throughput": 553.07, "total_tokens": 59203152} {"current_steps": 36255, "total_steps": 40000, "loss": 0.1004, "lr": 1.0742128967863085e-06, "epoch": 1.6412548948595487, "percentage": 90.64, "elapsed_time": "1 day, 5:44:06", "remaining_time": "3:04:17", "throughput": 553.13, "total_tokens": 59210864} {"current_steps": 36260, "total_steps": 40000, "loss": 0.1071, "lr": 1.071367830118411e-06, "epoch": 1.6414812467461917, "percentage": 90.65, "elapsed_time": "1 day, 5:44:10", "remaining_time": "3:04:01", "throughput": 553.19, "total_tokens": 59218800} {"current_steps": 36265, "total_steps": 40000, "loss": 0.0864, "lr": 1.068526453546298e-06, "epoch": 1.6417075986328347, "percentage": 90.66, "elapsed_time": "1 day, 5:44:13", "remaining_time": "3:03:45", "throughput": 553.25, "total_tokens": 59227120} {"current_steps": 36270, "total_steps": 40000, "loss": 0.1163, "lr": 1.0656887675081467e-06, "epoch": 1.6419339505194777, "percentage": 90.67, "elapsed_time": "1 day, 5:44:16", "remaining_time": "3:03:29", "throughput": 553.32, "total_tokens": 59236208} {"current_steps": 36275, "total_steps": 40000, "loss": 0.0984, "lr": 1.0628547724415628e-06, "epoch": 1.6421603024061207, "percentage": 90.69, "elapsed_time": "1 day, 5:44:19", "remaining_time": "3:03:13", "throughput": 553.38, "total_tokens": 59244944} {"current_steps": 36280, "total_steps": 40000, "loss": 0.1715, "lr": 1.0600244687835881e-06, "epoch": 1.6423866542927636, "percentage": 90.7, "elapsed_time": "1 day, 5:44:23", "remaining_time": "3:02:57", "throughput": 553.44, "total_tokens": 59253104} {"current_steps": 36285, "total_steps": 40000, "loss": 0.1432, "lr": 1.0571978569706876e-06, "epoch": 1.6426130061794066, "percentage": 90.71, "elapsed_time": "1 day, 5:44:26", "remaining_time": "3:02:41", "throughput": 553.5, "total_tokens": 59261776} {"current_steps": 36290, "total_steps": 40000, "loss": 0.0828, "lr": 1.0543749374387652e-06, "epoch": 1.6428393580660496, "percentage": 90.72, "elapsed_time": "1 day, 5:44:29", "remaining_time": "3:02:25", "throughput": 553.57, "total_tokens": 59270064} {"current_steps": 36295, "total_steps": 40000, "loss": 0.1009, "lr": 1.051555710623142e-06, "epoch": 1.6430657099526924, "percentage": 90.74, "elapsed_time": "1 day, 5:44:32", "remaining_time": "3:02:10", "throughput": 553.62, "total_tokens": 59277840} {"current_steps": 36300, "total_steps": 40000, "loss": 0.1173, "lr": 1.0487401769585847e-06, "epoch": 1.6432920618393354, "percentage": 90.75, "elapsed_time": "1 day, 5:44:35", "remaining_time": "3:01:54", "throughput": 553.68, "total_tokens": 59285936} {"current_steps": 36305, "total_steps": 40000, "loss": 0.1583, "lr": 1.0459283368792845e-06, "epoch": 1.6435184137259784, "percentage": 90.76, "elapsed_time": "1 day, 5:44:39", "remaining_time": "3:01:38", "throughput": 553.75, "total_tokens": 59294928} {"current_steps": 36310, "total_steps": 40000, "loss": 0.1254, "lr": 1.043120190818858e-06, "epoch": 1.6437447656126214, "percentage": 90.77, "elapsed_time": "1 day, 5:44:42", "remaining_time": "3:01:22", "throughput": 553.81, "total_tokens": 59303600} {"current_steps": 36315, "total_steps": 40000, "loss": 0.1291, "lr": 1.0403157392103596e-06, "epoch": 1.6439711174992644, "percentage": 90.79, "elapsed_time": "1 day, 5:44:45", "remaining_time": "3:01:06", "throughput": 553.87, "total_tokens": 59312016} {"current_steps": 36320, "total_steps": 40000, "loss": 0.1521, "lr": 1.0375149824862735e-06, "epoch": 1.6441974693859074, "percentage": 90.8, "elapsed_time": "1 day, 5:44:49", "remaining_time": "3:00:50", "throughput": 553.93, "total_tokens": 59320304} {"current_steps": 36325, "total_steps": 40000, "loss": 0.1065, "lr": 1.034717921078507e-06, "epoch": 1.6444238212725502, "percentage": 90.81, "elapsed_time": "1 day, 5:44:52", "remaining_time": "3:00:34", "throughput": 553.99, "total_tokens": 59328240} {"current_steps": 36330, "total_steps": 40000, "loss": 0.1373, "lr": 1.0319245554184009e-06, "epoch": 1.6446501731591932, "percentage": 90.83, "elapsed_time": "1 day, 5:44:55", "remaining_time": "3:00:18", "throughput": 554.05, "total_tokens": 59336272} {"current_steps": 36335, "total_steps": 40000, "loss": 0.0774, "lr": 1.0291348859367361e-06, "epoch": 1.6448765250458361, "percentage": 90.84, "elapsed_time": "1 day, 5:44:58", "remaining_time": "3:00:02", "throughput": 554.11, "total_tokens": 59344144} {"current_steps": 36340, "total_steps": 40000, "loss": 0.1372, "lr": 1.0263489130637016e-06, "epoch": 1.6451028769324791, "percentage": 90.85, "elapsed_time": "1 day, 5:45:02", "remaining_time": "2:59:46", "throughput": 554.17, "total_tokens": 59352336} {"current_steps": 36345, "total_steps": 40000, "loss": 0.1577, "lr": 1.0235666372289427e-06, "epoch": 1.6453292288191221, "percentage": 90.86, "elapsed_time": "1 day, 5:45:05", "remaining_time": "2:59:30", "throughput": 554.22, "total_tokens": 59360016} {"current_steps": 36350, "total_steps": 40000, "loss": 0.172, "lr": 1.0207880588615076e-06, "epoch": 1.6455555807057651, "percentage": 90.88, "elapsed_time": "1 day, 5:45:08", "remaining_time": "2:59:15", "throughput": 554.28, "total_tokens": 59368496} {"current_steps": 36355, "total_steps": 40000, "loss": 0.1269, "lr": 1.0180131783898984e-06, "epoch": 1.6457819325924081, "percentage": 90.89, "elapsed_time": "1 day, 5:45:11", "remaining_time": "2:58:59", "throughput": 554.34, "total_tokens": 59376752} {"current_steps": 36360, "total_steps": 40000, "loss": 0.1044, "lr": 1.0152419962420362e-06, "epoch": 1.6460082844790511, "percentage": 90.9, "elapsed_time": "1 day, 5:45:14", "remaining_time": "2:58:43", "throughput": 554.4, "total_tokens": 59384400} {"current_steps": 36365, "total_steps": 40000, "loss": 0.106, "lr": 1.0124745128452685e-06, "epoch": 1.6462346363656941, "percentage": 90.91, "elapsed_time": "1 day, 5:45:18", "remaining_time": "2:58:27", "throughput": 554.46, "total_tokens": 59392688} {"current_steps": 36370, "total_steps": 40000, "loss": 0.1264, "lr": 1.0097107286263758e-06, "epoch": 1.646460988252337, "percentage": 90.92, "elapsed_time": "1 day, 5:45:21", "remaining_time": "2:58:11", "throughput": 554.52, "total_tokens": 59401200} {"current_steps": 36375, "total_steps": 40000, "loss": 0.1166, "lr": 1.00695064401157e-06, "epoch": 1.64668734013898, "percentage": 90.94, "elapsed_time": "1 day, 5:45:24", "remaining_time": "2:57:55", "throughput": 554.58, "total_tokens": 59409264} {"current_steps": 36380, "total_steps": 40000, "loss": 0.08, "lr": 1.0041942594264886e-06, "epoch": 1.646913692025623, "percentage": 90.95, "elapsed_time": "1 day, 5:45:27", "remaining_time": "2:57:39", "throughput": 554.64, "total_tokens": 59417712} {"current_steps": 36385, "total_steps": 40000, "loss": 0.155, "lr": 1.001441575296208e-06, "epoch": 1.647140043912266, "percentage": 90.96, "elapsed_time": "1 day, 5:45:31", "remaining_time": "2:57:23", "throughput": 554.7, "total_tokens": 59425616} {"current_steps": 36390, "total_steps": 40000, "loss": 0.0734, "lr": 9.986925920452139e-07, "epoch": 1.647366395798909, "percentage": 90.97, "elapsed_time": "1 day, 5:45:34", "remaining_time": "2:57:08", "throughput": 554.76, "total_tokens": 59433648} {"current_steps": 36395, "total_steps": 40000, "loss": 0.1372, "lr": 9.959473100974475e-07, "epoch": 1.647592747685552, "percentage": 90.99, "elapsed_time": "1 day, 5:45:37", "remaining_time": "2:56:52", "throughput": 554.82, "total_tokens": 59441808} {"current_steps": 36400, "total_steps": 40000, "loss": 0.1009, "lr": 9.932057298762564e-07, "epoch": 1.647819099572195, "percentage": 91.0, "elapsed_time": "1 day, 5:45:40", "remaining_time": "2:56:36", "throughput": 554.88, "total_tokens": 59449936} {"current_steps": 36400, "total_steps": 40000, "eval_loss": 0.12214837223291397, "epoch": 1.647819099572195, "percentage": 91.0, "elapsed_time": "1 day, 5:53:23", "remaining_time": "2:57:22", "throughput": 552.49, "total_tokens": 59449936} {"current_steps": 36405, "total_steps": 40000, "loss": 0.1427, "lr": 9.90467851804433e-07, "epoch": 1.648045451458838, "percentage": 91.01, "elapsed_time": "1 day, 5:53:27", "remaining_time": "2:57:06", "throughput": 552.55, "total_tokens": 59458000} {"current_steps": 36410, "total_steps": 40000, "loss": 0.0912, "lr": 9.877336763041895e-07, "epoch": 1.6482718033454808, "percentage": 91.03, "elapsed_time": "1 day, 5:53:30", "remaining_time": "2:56:50", "throughput": 552.6, "total_tokens": 59466096} {"current_steps": 36415, "total_steps": 40000, "loss": 0.1137, "lr": 9.850032037971662e-07, "epoch": 1.6484981552321238, "percentage": 91.04, "elapsed_time": "1 day, 5:53:34", "remaining_time": "2:56:34", "throughput": 552.67, "total_tokens": 59475056} {"current_steps": 36420, "total_steps": 40000, "loss": 0.1498, "lr": 9.822764347044406e-07, "epoch": 1.6487245071187668, "percentage": 91.05, "elapsed_time": "1 day, 5:53:37", "remaining_time": "2:56:18", "throughput": 552.73, "total_tokens": 59483024} {"current_steps": 36425, "total_steps": 40000, "loss": 0.126, "lr": 9.795533694465175e-07, "epoch": 1.6489508590054098, "percentage": 91.06, "elapsed_time": "1 day, 5:53:40", "remaining_time": "2:56:02", "throughput": 552.79, "total_tokens": 59491600} {"current_steps": 36430, "total_steps": 40000, "loss": 0.1096, "lr": 9.768340084433197e-07, "epoch": 1.6491772108920528, "percentage": 91.07, "elapsed_time": "1 day, 5:53:43", "remaining_time": "2:55:46", "throughput": 552.85, "total_tokens": 59499376} {"current_steps": 36435, "total_steps": 40000, "loss": 0.1331, "lr": 9.741183521142143e-07, "epoch": 1.6494035627786956, "percentage": 91.09, "elapsed_time": "1 day, 5:53:46", "remaining_time": "2:55:30", "throughput": 552.9, "total_tokens": 59506896} {"current_steps": 36440, "total_steps": 40000, "loss": 0.1284, "lr": 9.714064008779889e-07, "epoch": 1.6496299146653386, "percentage": 91.1, "elapsed_time": "1 day, 5:53:50", "remaining_time": "2:55:14", "throughput": 552.96, "total_tokens": 59515152} {"current_steps": 36445, "total_steps": 40000, "loss": 0.1238, "lr": 9.686981551528584e-07, "epoch": 1.6498562665519816, "percentage": 91.11, "elapsed_time": "1 day, 5:53:53", "remaining_time": "2:54:59", "throughput": 553.02, "total_tokens": 59523600} {"current_steps": 36450, "total_steps": 40000, "loss": 0.0862, "lr": 9.65993615356467e-07, "epoch": 1.6500826184386246, "percentage": 91.12, "elapsed_time": "1 day, 5:53:56", "remaining_time": "2:54:43", "throughput": 553.08, "total_tokens": 59531472} {"current_steps": 36455, "total_steps": 40000, "loss": 0.1214, "lr": 9.632927819058917e-07, "epoch": 1.6503089703252676, "percentage": 91.14, "elapsed_time": "1 day, 5:53:59", "remaining_time": "2:54:27", "throughput": 553.14, "total_tokens": 59539920} {"current_steps": 36460, "total_steps": 40000, "loss": 0.1599, "lr": 9.605956552176305e-07, "epoch": 1.6505353222119106, "percentage": 91.15, "elapsed_time": "1 day, 5:54:03", "remaining_time": "2:54:11", "throughput": 553.21, "total_tokens": 59549744} {"current_steps": 36465, "total_steps": 40000, "loss": 0.0872, "lr": 9.579022357076223e-07, "epoch": 1.6507616740985536, "percentage": 91.16, "elapsed_time": "1 day, 5:54:06", "remaining_time": "2:53:55", "throughput": 553.28, "total_tokens": 59558192} {"current_steps": 36470, "total_steps": 40000, "loss": 0.1082, "lr": 9.552125237912158e-07, "epoch": 1.6509880259851966, "percentage": 91.17, "elapsed_time": "1 day, 5:54:09", "remaining_time": "2:53:39", "throughput": 553.34, "total_tokens": 59566576} {"current_steps": 36475, "total_steps": 40000, "loss": 0.1309, "lr": 9.525265198832096e-07, "epoch": 1.6512143778718396, "percentage": 91.19, "elapsed_time": "1 day, 5:54:13", "remaining_time": "2:53:23", "throughput": 553.39, "total_tokens": 59574224} {"current_steps": 36480, "total_steps": 40000, "loss": 0.0871, "lr": 9.498442243978112e-07, "epoch": 1.6514407297584826, "percentage": 91.2, "elapsed_time": "1 day, 5:54:16", "remaining_time": "2:53:07", "throughput": 553.44, "total_tokens": 59581456} {"current_steps": 36485, "total_steps": 40000, "loss": 0.0854, "lr": 9.471656377486649e-07, "epoch": 1.6516670816451255, "percentage": 91.21, "elapsed_time": "1 day, 5:54:19", "remaining_time": "2:52:52", "throughput": 553.5, "total_tokens": 59589584} {"current_steps": 36490, "total_steps": 40000, "loss": 0.1287, "lr": 9.444907603488456e-07, "epoch": 1.6518934335317685, "percentage": 91.22, "elapsed_time": "1 day, 5:54:22", "remaining_time": "2:52:36", "throughput": 553.56, "total_tokens": 59598000} {"current_steps": 36495, "total_steps": 40000, "loss": 0.1189, "lr": 9.418195926108514e-07, "epoch": 1.6521197854184115, "percentage": 91.24, "elapsed_time": "1 day, 5:54:25", "remaining_time": "2:52:20", "throughput": 553.62, "total_tokens": 59605680} {"current_steps": 36500, "total_steps": 40000, "loss": 0.0823, "lr": 9.391521349466053e-07, "epoch": 1.6523461373050545, "percentage": 91.25, "elapsed_time": "1 day, 5:54:28", "remaining_time": "2:52:04", "throughput": 553.68, "total_tokens": 59614000} {"current_steps": 36505, "total_steps": 40000, "loss": 0.1426, "lr": 9.364883877674758e-07, "epoch": 1.6525724891916975, "percentage": 91.26, "elapsed_time": "1 day, 5:54:32", "remaining_time": "2:51:48", "throughput": 553.74, "total_tokens": 59622416} {"current_steps": 36510, "total_steps": 40000, "loss": 0.1426, "lr": 9.33828351484231e-07, "epoch": 1.6527988410783405, "percentage": 91.27, "elapsed_time": "1 day, 5:54:35", "remaining_time": "2:51:32", "throughput": 553.8, "total_tokens": 59630640} {"current_steps": 36515, "total_steps": 40000, "loss": 0.0928, "lr": 9.311720265070906e-07, "epoch": 1.6530251929649835, "percentage": 91.29, "elapsed_time": "1 day, 5:54:38", "remaining_time": "2:51:16", "throughput": 553.86, "total_tokens": 59639024} {"current_steps": 36520, "total_steps": 40000, "loss": 0.1562, "lr": 9.285194132456931e-07, "epoch": 1.6532515448516263, "percentage": 91.3, "elapsed_time": "1 day, 5:54:41", "remaining_time": "2:51:01", "throughput": 553.92, "total_tokens": 59646960} {"current_steps": 36525, "total_steps": 40000, "loss": 0.1121, "lr": 9.258705121091032e-07, "epoch": 1.6534778967382693, "percentage": 91.31, "elapsed_time": "1 day, 5:54:45", "remaining_time": "2:50:45", "throughput": 553.98, "total_tokens": 59655152} {"current_steps": 36530, "total_steps": 40000, "loss": 0.1155, "lr": 9.232253235058136e-07, "epoch": 1.6537042486249123, "percentage": 91.33, "elapsed_time": "1 day, 5:54:48", "remaining_time": "2:50:29", "throughput": 554.04, "total_tokens": 59663248} {"current_steps": 36535, "total_steps": 40000, "loss": 0.1214, "lr": 9.205838478437478e-07, "epoch": 1.6539306005115553, "percentage": 91.34, "elapsed_time": "1 day, 5:54:51", "remaining_time": "2:50:13", "throughput": 554.09, "total_tokens": 59670864} {"current_steps": 36540, "total_steps": 40000, "loss": 0.1343, "lr": 9.179460855302524e-07, "epoch": 1.6541569523981983, "percentage": 91.35, "elapsed_time": "1 day, 5:54:54", "remaining_time": "2:49:57", "throughput": 554.14, "total_tokens": 59678352} {"current_steps": 36545, "total_steps": 40000, "loss": 0.1128, "lr": 9.153120369721046e-07, "epoch": 1.6543833042848413, "percentage": 91.36, "elapsed_time": "1 day, 5:54:57", "remaining_time": "2:49:41", "throughput": 554.2, "total_tokens": 59686640} {"current_steps": 36550, "total_steps": 40000, "loss": 0.1185, "lr": 9.126817025755103e-07, "epoch": 1.654609656171484, "percentage": 91.38, "elapsed_time": "1 day, 5:55:01", "remaining_time": "2:49:26", "throughput": 554.26, "total_tokens": 59694896} {"current_steps": 36555, "total_steps": 40000, "loss": 0.158, "lr": 9.100550827460947e-07, "epoch": 1.654836008058127, "percentage": 91.39, "elapsed_time": "1 day, 5:55:04", "remaining_time": "2:49:10", "throughput": 554.32, "total_tokens": 59703152} {"current_steps": 36560, "total_steps": 40000, "loss": 0.1148, "lr": 9.0743217788892e-07, "epoch": 1.65506235994477, "percentage": 91.4, "elapsed_time": "1 day, 5:55:07", "remaining_time": "2:48:54", "throughput": 554.39, "total_tokens": 59711472} {"current_steps": 36565, "total_steps": 40000, "loss": 0.0964, "lr": 9.048129884084683e-07, "epoch": 1.655288711831413, "percentage": 91.41, "elapsed_time": "1 day, 5:55:10", "remaining_time": "2:48:38", "throughput": 554.44, "total_tokens": 59719248} {"current_steps": 36570, "total_steps": 40000, "loss": 0.1065, "lr": 9.021975147086553e-07, "epoch": 1.655515063718056, "percentage": 91.42, "elapsed_time": "1 day, 5:55:13", "remaining_time": "2:48:22", "throughput": 554.5, "total_tokens": 59726960} {"current_steps": 36575, "total_steps": 40000, "loss": 0.097, "lr": 8.995857571928141e-07, "epoch": 1.655741415604699, "percentage": 91.44, "elapsed_time": "1 day, 5:55:17", "remaining_time": "2:48:06", "throughput": 554.56, "total_tokens": 59735088} {"current_steps": 36580, "total_steps": 40000, "loss": 0.1035, "lr": 8.969777162637139e-07, "epoch": 1.655967767491342, "percentage": 91.45, "elapsed_time": "1 day, 5:55:20", "remaining_time": "2:47:51", "throughput": 554.61, "total_tokens": 59743248} {"current_steps": 36585, "total_steps": 40000, "loss": 0.1285, "lr": 8.943733923235525e-07, "epoch": 1.656194119377985, "percentage": 91.46, "elapsed_time": "1 day, 5:55:23", "remaining_time": "2:47:35", "throughput": 554.67, "total_tokens": 59751120} {"current_steps": 36590, "total_steps": 40000, "loss": 0.1749, "lr": 8.917727857739394e-07, "epoch": 1.656420471264628, "percentage": 91.47, "elapsed_time": "1 day, 5:55:26", "remaining_time": "2:47:19", "throughput": 554.73, "total_tokens": 59759536} {"current_steps": 36595, "total_steps": 40000, "loss": 0.1143, "lr": 8.891758970159258e-07, "epoch": 1.656646823151271, "percentage": 91.49, "elapsed_time": "1 day, 5:55:29", "remaining_time": "2:47:03", "throughput": 554.79, "total_tokens": 59767696} {"current_steps": 36600, "total_steps": 40000, "loss": 0.0874, "lr": 8.86582726449986e-07, "epoch": 1.656873175037914, "percentage": 91.5, "elapsed_time": "1 day, 5:55:33", "remaining_time": "2:46:48", "throughput": 554.85, "total_tokens": 59776048} {"current_steps": 36600, "total_steps": 40000, "eval_loss": 0.12189286202192307, "epoch": 1.656873175037914, "percentage": 91.5, "elapsed_time": "1 day, 6:03:15", "remaining_time": "2:47:30", "throughput": 552.48, "total_tokens": 59776048} {"current_steps": 36605, "total_steps": 40000, "loss": 0.124, "lr": 8.839932744760165e-07, "epoch": 1.657099526924557, "percentage": 91.51, "elapsed_time": "1 day, 6:03:19", "remaining_time": "2:47:15", "throughput": 552.54, "total_tokens": 59784560} {"current_steps": 36610, "total_steps": 40000, "loss": 0.1084, "lr": 8.814075414933482e-07, "epoch": 1.6573258788112, "percentage": 91.53, "elapsed_time": "1 day, 6:03:23", "remaining_time": "2:46:59", "throughput": 552.6, "total_tokens": 59792880} {"current_steps": 36615, "total_steps": 40000, "loss": 0.1696, "lr": 8.788255279007257e-07, "epoch": 1.657552230697843, "percentage": 91.54, "elapsed_time": "1 day, 6:03:26", "remaining_time": "2:46:43", "throughput": 552.66, "total_tokens": 59801072} {"current_steps": 36620, "total_steps": 40000, "loss": 0.1192, "lr": 8.762472340963362e-07, "epoch": 1.657778582584486, "percentage": 91.55, "elapsed_time": "1 day, 6:03:29", "remaining_time": "2:46:27", "throughput": 552.72, "total_tokens": 59809552} {"current_steps": 36625, "total_steps": 40000, "loss": 0.0931, "lr": 8.736726604777811e-07, "epoch": 1.658004934471129, "percentage": 91.56, "elapsed_time": "1 day, 6:03:32", "remaining_time": "2:46:11", "throughput": 552.77, "total_tokens": 59817136} {"current_steps": 36630, "total_steps": 40000, "loss": 0.09, "lr": 8.711018074420901e-07, "epoch": 1.658231286357772, "percentage": 91.57, "elapsed_time": "1 day, 6:03:36", "remaining_time": "2:45:55", "throughput": 552.83, "total_tokens": 59825328} {"current_steps": 36635, "total_steps": 40000, "loss": 0.1083, "lr": 8.685346753857209e-07, "epoch": 1.6584576382444147, "percentage": 91.59, "elapsed_time": "1 day, 6:03:39", "remaining_time": "2:45:40", "throughput": 552.9, "total_tokens": 59833936} {"current_steps": 36640, "total_steps": 40000, "loss": 0.1053, "lr": 8.659712647045654e-07, "epoch": 1.6586839901310577, "percentage": 91.6, "elapsed_time": "1 day, 6:03:42", "remaining_time": "2:45:24", "throughput": 552.96, "total_tokens": 59842672} {"current_steps": 36645, "total_steps": 40000, "loss": 0.1032, "lr": 8.634115757939209e-07, "epoch": 1.6589103420177007, "percentage": 91.61, "elapsed_time": "1 day, 6:03:45", "remaining_time": "2:45:08", "throughput": 553.01, "total_tokens": 59850288} {"current_steps": 36650, "total_steps": 40000, "loss": 0.1294, "lr": 8.608556090485387e-07, "epoch": 1.6591366939043437, "percentage": 91.62, "elapsed_time": "1 day, 6:03:49", "remaining_time": "2:44:52", "throughput": 553.08, "total_tokens": 59859280} {"current_steps": 36655, "total_steps": 40000, "loss": 0.1182, "lr": 8.583033648625671e-07, "epoch": 1.6593630457909867, "percentage": 91.64, "elapsed_time": "1 day, 6:03:52", "remaining_time": "2:44:36", "throughput": 553.13, "total_tokens": 59866896} {"current_steps": 36660, "total_steps": 40000, "loss": 0.143, "lr": 8.557548436295998e-07, "epoch": 1.6595893976776297, "percentage": 91.65, "elapsed_time": "1 day, 6:03:55", "remaining_time": "2:44:21", "throughput": 553.19, "total_tokens": 59874928} {"current_steps": 36665, "total_steps": 40000, "loss": 0.1356, "lr": 8.532100457426556e-07, "epoch": 1.6598157495642725, "percentage": 91.66, "elapsed_time": "1 day, 6:03:58", "remaining_time": "2:44:05", "throughput": 553.25, "total_tokens": 59882800} {"current_steps": 36670, "total_steps": 40000, "loss": 0.0733, "lr": 8.506689715941679e-07, "epoch": 1.6600421014509155, "percentage": 91.67, "elapsed_time": "1 day, 6:04:01", "remaining_time": "2:43:49", "throughput": 553.31, "total_tokens": 59891088} {"current_steps": 36675, "total_steps": 40000, "loss": 0.1228, "lr": 8.481316215760011e-07, "epoch": 1.6602684533375585, "percentage": 91.69, "elapsed_time": "1 day, 6:04:05", "remaining_time": "2:43:33", "throughput": 553.37, "total_tokens": 59900112} {"current_steps": 36680, "total_steps": 40000, "loss": 0.1548, "lr": 8.455979960794558e-07, "epoch": 1.6604948052242015, "percentage": 91.7, "elapsed_time": "1 day, 6:04:08", "remaining_time": "2:43:17", "throughput": 553.43, "total_tokens": 59908080} {"current_steps": 36685, "total_steps": 40000, "loss": 0.1752, "lr": 8.430680954952364e-07, "epoch": 1.6607211571108444, "percentage": 91.71, "elapsed_time": "1 day, 6:04:11", "remaining_time": "2:43:02", "throughput": 553.49, "total_tokens": 59916720} {"current_steps": 36690, "total_steps": 40000, "loss": 0.1326, "lr": 8.405419202134974e-07, "epoch": 1.6609475089974874, "percentage": 91.72, "elapsed_time": "1 day, 6:04:15", "remaining_time": "2:42:46", "throughput": 553.55, "total_tokens": 59924464} {"current_steps": 36695, "total_steps": 40000, "loss": 0.1698, "lr": 8.380194706237993e-07, "epoch": 1.6611738608841304, "percentage": 91.74, "elapsed_time": "1 day, 6:04:18", "remaining_time": "2:42:30", "throughput": 553.6, "total_tokens": 59932112} {"current_steps": 36700, "total_steps": 40000, "loss": 0.1053, "lr": 8.355007471151366e-07, "epoch": 1.6614002127707734, "percentage": 91.75, "elapsed_time": "1 day, 6:04:21", "remaining_time": "2:42:14", "throughput": 553.66, "total_tokens": 59939888} {"current_steps": 36705, "total_steps": 40000, "loss": 0.1244, "lr": 8.329857500759292e-07, "epoch": 1.6616265646574164, "percentage": 91.76, "elapsed_time": "1 day, 6:04:24", "remaining_time": "2:41:58", "throughput": 553.72, "total_tokens": 59947792} {"current_steps": 36710, "total_steps": 40000, "loss": 0.1363, "lr": 8.304744798940194e-07, "epoch": 1.6618529165440594, "percentage": 91.77, "elapsed_time": "1 day, 6:04:27", "remaining_time": "2:41:43", "throughput": 553.78, "total_tokens": 59956048} {"current_steps": 36715, "total_steps": 40000, "loss": 0.1012, "lr": 8.279669369566756e-07, "epoch": 1.6620792684307024, "percentage": 91.79, "elapsed_time": "1 day, 6:04:31", "remaining_time": "2:41:27", "throughput": 553.85, "total_tokens": 59965872} {"current_steps": 36720, "total_steps": 40000, "loss": 0.1247, "lr": 8.254631216505993e-07, "epoch": 1.6623056203173454, "percentage": 91.8, "elapsed_time": "1 day, 6:04:34", "remaining_time": "2:41:11", "throughput": 553.91, "total_tokens": 59974064} {"current_steps": 36725, "total_steps": 40000, "loss": 0.1566, "lr": 8.229630343619038e-07, "epoch": 1.6625319722039884, "percentage": 91.81, "elapsed_time": "1 day, 6:04:37", "remaining_time": "2:40:55", "throughput": 553.96, "total_tokens": 59981776} {"current_steps": 36730, "total_steps": 40000, "loss": 0.1277, "lr": 8.204666754761392e-07, "epoch": 1.6627583240906314, "percentage": 91.83, "elapsed_time": "1 day, 6:04:41", "remaining_time": "2:40:40", "throughput": 554.03, "total_tokens": 59990672} {"current_steps": 36735, "total_steps": 40000, "loss": 0.091, "lr": 8.179740453782669e-07, "epoch": 1.6629846759772744, "percentage": 91.84, "elapsed_time": "1 day, 6:04:44", "remaining_time": "2:40:24", "throughput": 554.08, "total_tokens": 59998000} {"current_steps": 36740, "total_steps": 40000, "loss": 0.1049, "lr": 8.154851444526907e-07, "epoch": 1.6632110278639174, "percentage": 91.85, "elapsed_time": "1 day, 6:04:47", "remaining_time": "2:40:08", "throughput": 554.14, "total_tokens": 60006160} {"current_steps": 36745, "total_steps": 40000, "loss": 0.0895, "lr": 8.129999730832283e-07, "epoch": 1.6634373797505604, "percentage": 91.86, "elapsed_time": "1 day, 6:04:50", "remaining_time": "2:39:52", "throughput": 554.2, "total_tokens": 60014384} {"current_steps": 36750, "total_steps": 40000, "loss": 0.1012, "lr": 8.105185316531178e-07, "epoch": 1.6636637316372032, "percentage": 91.88, "elapsed_time": "1 day, 6:04:53", "remaining_time": "2:39:37", "throughput": 554.25, "total_tokens": 60022288} {"current_steps": 36755, "total_steps": 40000, "loss": 0.1503, "lr": 8.08040820545039e-07, "epoch": 1.6638900835238462, "percentage": 91.89, "elapsed_time": "1 day, 6:04:57", "remaining_time": "2:39:21", "throughput": 554.31, "total_tokens": 60029968} {"current_steps": 36760, "total_steps": 40000, "loss": 0.136, "lr": 8.055668401410782e-07, "epoch": 1.6641164354104891, "percentage": 91.9, "elapsed_time": "1 day, 6:05:00", "remaining_time": "2:39:05", "throughput": 554.37, "total_tokens": 60038128} {"current_steps": 36765, "total_steps": 40000, "loss": 0.1, "lr": 8.030965908227578e-07, "epoch": 1.6643427872971321, "percentage": 91.91, "elapsed_time": "1 day, 6:05:03", "remaining_time": "2:38:49", "throughput": 554.43, "total_tokens": 60046320} {"current_steps": 36770, "total_steps": 40000, "loss": 0.1158, "lr": 8.006300729710203e-07, "epoch": 1.6645691391837751, "percentage": 91.92, "elapsed_time": "1 day, 6:05:06", "remaining_time": "2:38:34", "throughput": 554.49, "total_tokens": 60055056} {"current_steps": 36775, "total_steps": 40000, "loss": 0.1035, "lr": 7.981672869662337e-07, "epoch": 1.664795491070418, "percentage": 91.94, "elapsed_time": "1 day, 6:05:09", "remaining_time": "2:38:18", "throughput": 554.55, "total_tokens": 60062832} {"current_steps": 36780, "total_steps": 40000, "loss": 0.2284, "lr": 7.957082331881888e-07, "epoch": 1.665021842957061, "percentage": 91.95, "elapsed_time": "1 day, 6:05:13", "remaining_time": "2:38:02", "throughput": 554.6, "total_tokens": 60070960} {"current_steps": 36785, "total_steps": 40000, "loss": 0.0969, "lr": 7.932529120161069e-07, "epoch": 1.665248194843704, "percentage": 91.96, "elapsed_time": "1 day, 6:05:16", "remaining_time": "2:37:46", "throughput": 554.66, "total_tokens": 60078864} {"current_steps": 36790, "total_steps": 40000, "loss": 0.122, "lr": 7.908013238286243e-07, "epoch": 1.665474546730347, "percentage": 91.97, "elapsed_time": "1 day, 6:05:19", "remaining_time": "2:37:31", "throughput": 554.72, "total_tokens": 60087504} {"current_steps": 36795, "total_steps": 40000, "loss": 0.0785, "lr": 7.883534690038136e-07, "epoch": 1.66570089861699, "percentage": 91.99, "elapsed_time": "1 day, 6:05:23", "remaining_time": "2:37:15", "throughput": 554.79, "total_tokens": 60096336} {"current_steps": 36800, "total_steps": 40000, "loss": 0.1021, "lr": 7.859093479191559e-07, "epoch": 1.6659272505036329, "percentage": 92.0, "elapsed_time": "1 day, 6:05:26", "remaining_time": "2:36:59", "throughput": 554.85, "total_tokens": 60104592} {"current_steps": 36800, "total_steps": 40000, "eval_loss": 0.12204759567975998, "epoch": 1.6659272505036329, "percentage": 92.0, "elapsed_time": "1 day, 6:13:08", "remaining_time": "2:37:39", "throughput": 552.49, "total_tokens": 60104592} {"current_steps": 36805, "total_steps": 40000, "loss": 0.0776, "lr": 7.834689609515722e-07, "epoch": 1.6661536023902759, "percentage": 92.01, "elapsed_time": "1 day, 6:13:13", "remaining_time": "2:37:24", "throughput": 552.54, "total_tokens": 60112592} {"current_steps": 36810, "total_steps": 40000, "loss": 0.0763, "lr": 7.810323084774002e-07, "epoch": 1.6663799542769189, "percentage": 92.03, "elapsed_time": "1 day, 6:13:16", "remaining_time": "2:37:08", "throughput": 552.6, "total_tokens": 60121040} {"current_steps": 36815, "total_steps": 40000, "loss": 0.0916, "lr": 7.785993908723976e-07, "epoch": 1.6666063061635619, "percentage": 92.04, "elapsed_time": "1 day, 6:13:19", "remaining_time": "2:36:52", "throughput": 552.67, "total_tokens": 60130064} {"current_steps": 36820, "total_steps": 40000, "loss": 0.1973, "lr": 7.761702085117534e-07, "epoch": 1.6668326580502049, "percentage": 92.05, "elapsed_time": "1 day, 6:13:22", "remaining_time": "2:36:36", "throughput": 552.73, "total_tokens": 60138192} {"current_steps": 36825, "total_steps": 40000, "loss": 0.0834, "lr": 7.737447617700844e-07, "epoch": 1.6670590099368479, "percentage": 92.06, "elapsed_time": "1 day, 6:13:26", "remaining_time": "2:36:21", "throughput": 552.79, "total_tokens": 60146864} {"current_steps": 36830, "total_steps": 40000, "loss": 0.1489, "lr": 7.713230510214136e-07, "epoch": 1.6672853618234909, "percentage": 92.07, "elapsed_time": "1 day, 6:13:29", "remaining_time": "2:36:05", "throughput": 552.85, "total_tokens": 60154992} {"current_steps": 36835, "total_steps": 40000, "loss": 0.1374, "lr": 7.689050766392092e-07, "epoch": 1.6675117137101338, "percentage": 92.09, "elapsed_time": "1 day, 6:13:32", "remaining_time": "2:35:49", "throughput": 552.91, "total_tokens": 60163856} {"current_steps": 36840, "total_steps": 40000, "loss": 0.1178, "lr": 7.664908389963477e-07, "epoch": 1.6677380655967768, "percentage": 92.1, "elapsed_time": "1 day, 6:13:35", "remaining_time": "2:35:33", "throughput": 552.97, "total_tokens": 60171664} {"current_steps": 36845, "total_steps": 40000, "loss": 0.1658, "lr": 7.64080338465134e-07, "epoch": 1.6679644174834198, "percentage": 92.11, "elapsed_time": "1 day, 6:13:39", "remaining_time": "2:35:18", "throughput": 553.03, "total_tokens": 60180432} {"current_steps": 36850, "total_steps": 40000, "loss": 0.1413, "lr": 7.616735754173043e-07, "epoch": 1.6681907693700628, "percentage": 92.12, "elapsed_time": "1 day, 6:13:42", "remaining_time": "2:35:02", "throughput": 553.09, "total_tokens": 60188624} {"current_steps": 36855, "total_steps": 40000, "loss": 0.1248, "lr": 7.592705502240005e-07, "epoch": 1.6684171212567058, "percentage": 92.14, "elapsed_time": "1 day, 6:13:45", "remaining_time": "2:34:46", "throughput": 553.15, "total_tokens": 60197552} {"current_steps": 36860, "total_steps": 40000, "loss": 0.0996, "lr": 7.568712632558095e-07, "epoch": 1.6686434731433486, "percentage": 92.15, "elapsed_time": "1 day, 6:13:49", "remaining_time": "2:34:30", "throughput": 553.21, "total_tokens": 60205872} {"current_steps": 36865, "total_steps": 40000, "loss": 0.09, "lr": 7.544757148827297e-07, "epoch": 1.6688698250299916, "percentage": 92.16, "elapsed_time": "1 day, 6:13:52", "remaining_time": "2:34:15", "throughput": 553.27, "total_tokens": 60214096} {"current_steps": 36870, "total_steps": 40000, "loss": 0.1201, "lr": 7.520839054741797e-07, "epoch": 1.6690961769166346, "percentage": 92.17, "elapsed_time": "1 day, 6:13:55", "remaining_time": "2:33:59", "throughput": 553.33, "total_tokens": 60222256} {"current_steps": 36875, "total_steps": 40000, "loss": 0.0838, "lr": 7.496958353990113e-07, "epoch": 1.6693225288032776, "percentage": 92.19, "elapsed_time": "1 day, 6:13:58", "remaining_time": "2:33:43", "throughput": 553.39, "total_tokens": 60230832} {"current_steps": 36880, "total_steps": 40000, "loss": 0.1569, "lr": 7.473115050254941e-07, "epoch": 1.6695488806899206, "percentage": 92.2, "elapsed_time": "1 day, 6:14:02", "remaining_time": "2:33:27", "throughput": 553.45, "total_tokens": 60239088} {"current_steps": 36885, "total_steps": 40000, "loss": 0.1317, "lr": 7.449309147213173e-07, "epoch": 1.6697752325765636, "percentage": 92.21, "elapsed_time": "1 day, 6:14:05", "remaining_time": "2:33:12", "throughput": 553.51, "total_tokens": 60246672} {"current_steps": 36890, "total_steps": 40000, "loss": 0.0785, "lr": 7.425540648536067e-07, "epoch": 1.6700015844632063, "percentage": 92.22, "elapsed_time": "1 day, 6:14:08", "remaining_time": "2:32:56", "throughput": 553.57, "total_tokens": 60254992} {"current_steps": 36895, "total_steps": 40000, "loss": 0.1406, "lr": 7.40180955788894e-07, "epoch": 1.6702279363498493, "percentage": 92.24, "elapsed_time": "1 day, 6:14:11", "remaining_time": "2:32:40", "throughput": 553.63, "total_tokens": 60263248} {"current_steps": 36900, "total_steps": 40000, "loss": 0.0979, "lr": 7.378115878931474e-07, "epoch": 1.6704542882364923, "percentage": 92.25, "elapsed_time": "1 day, 6:14:14", "remaining_time": "2:32:24", "throughput": 553.68, "total_tokens": 60270704} {"current_steps": 36905, "total_steps": 40000, "loss": 0.1062, "lr": 7.354459615317527e-07, "epoch": 1.6706806401231353, "percentage": 92.26, "elapsed_time": "1 day, 6:14:18", "remaining_time": "2:32:09", "throughput": 553.74, "total_tokens": 60278832} {"current_steps": 36910, "total_steps": 40000, "loss": 0.1494, "lr": 7.33084077069518e-07, "epoch": 1.6709069920097783, "percentage": 92.27, "elapsed_time": "1 day, 6:14:21", "remaining_time": "2:31:53", "throughput": 553.79, "total_tokens": 60286800} {"current_steps": 36915, "total_steps": 40000, "loss": 0.1302, "lr": 7.307259348706768e-07, "epoch": 1.6711333438964213, "percentage": 92.29, "elapsed_time": "1 day, 6:14:24", "remaining_time": "2:31:37", "throughput": 553.86, "total_tokens": 60295312} {"current_steps": 36920, "total_steps": 40000, "loss": 0.1566, "lr": 7.283715352988801e-07, "epoch": 1.6713596957830643, "percentage": 92.3, "elapsed_time": "1 day, 6:14:27", "remaining_time": "2:31:22", "throughput": 553.91, "total_tokens": 60302768} {"current_steps": 36925, "total_steps": 40000, "loss": 0.1037, "lr": 7.260208787172068e-07, "epoch": 1.6715860476697073, "percentage": 92.31, "elapsed_time": "1 day, 6:14:30", "remaining_time": "2:31:06", "throughput": 553.97, "total_tokens": 60311120} {"current_steps": 36930, "total_steps": 40000, "loss": 0.1164, "lr": 7.23673965488167e-07, "epoch": 1.6718123995563503, "percentage": 92.33, "elapsed_time": "1 day, 6:14:34", "remaining_time": "2:30:50", "throughput": 554.02, "total_tokens": 60318832} {"current_steps": 36935, "total_steps": 40000, "loss": 0.113, "lr": 7.213307959736709e-07, "epoch": 1.6720387514429933, "percentage": 92.34, "elapsed_time": "1 day, 6:14:37", "remaining_time": "2:30:35", "throughput": 554.08, "total_tokens": 60326352} {"current_steps": 36940, "total_steps": 40000, "loss": 0.1271, "lr": 7.189913705350715e-07, "epoch": 1.6722651033296363, "percentage": 92.35, "elapsed_time": "1 day, 6:14:40", "remaining_time": "2:30:19", "throughput": 554.14, "total_tokens": 60334576} {"current_steps": 36945, "total_steps": 40000, "loss": 0.171, "lr": 7.166556895331411e-07, "epoch": 1.6724914552162793, "percentage": 92.36, "elapsed_time": "1 day, 6:14:43", "remaining_time": "2:30:03", "throughput": 554.2, "total_tokens": 60343152} {"current_steps": 36950, "total_steps": 40000, "loss": 0.1106, "lr": 7.143237533280639e-07, "epoch": 1.6727178071029223, "percentage": 92.38, "elapsed_time": "1 day, 6:14:46", "remaining_time": "2:29:47", "throughput": 554.26, "total_tokens": 60351408} {"current_steps": 36955, "total_steps": 40000, "loss": 0.1318, "lr": 7.119955622794578e-07, "epoch": 1.6729441589895653, "percentage": 92.39, "elapsed_time": "1 day, 6:14:50", "remaining_time": "2:29:32", "throughput": 554.32, "total_tokens": 60359632} {"current_steps": 36960, "total_steps": 40000, "loss": 0.1357, "lr": 7.096711167463577e-07, "epoch": 1.6731705108762083, "percentage": 92.4, "elapsed_time": "1 day, 6:14:53", "remaining_time": "2:29:16", "throughput": 554.38, "total_tokens": 60367824} {"current_steps": 36965, "total_steps": 40000, "loss": 0.1361, "lr": 7.073504170872213e-07, "epoch": 1.6733968627628513, "percentage": 92.41, "elapsed_time": "1 day, 6:14:56", "remaining_time": "2:29:00", "throughput": 554.43, "total_tokens": 60376048} {"current_steps": 36970, "total_steps": 40000, "loss": 0.1969, "lr": 7.05033463659932e-07, "epoch": 1.6736232146494943, "percentage": 92.42, "elapsed_time": "1 day, 6:14:59", "remaining_time": "2:28:45", "throughput": 554.49, "total_tokens": 60384368} {"current_steps": 36975, "total_steps": 40000, "loss": 0.1596, "lr": 7.027202568217928e-07, "epoch": 1.673849566536137, "percentage": 92.44, "elapsed_time": "1 day, 6:15:03", "remaining_time": "2:28:29", "throughput": 554.55, "total_tokens": 60392432} {"current_steps": 36980, "total_steps": 40000, "loss": 0.1588, "lr": 7.004107969295293e-07, "epoch": 1.67407591842278, "percentage": 92.45, "elapsed_time": "1 day, 6:15:06", "remaining_time": "2:28:13", "throughput": 554.62, "total_tokens": 60401424} {"current_steps": 36985, "total_steps": 40000, "loss": 0.1671, "lr": 6.9810508433929e-07, "epoch": 1.674302270309423, "percentage": 92.46, "elapsed_time": "1 day, 6:15:09", "remaining_time": "2:27:58", "throughput": 554.67, "total_tokens": 60409040} {"current_steps": 36990, "total_steps": 40000, "loss": 0.1172, "lr": 6.958031194066406e-07, "epoch": 1.674528622196066, "percentage": 92.47, "elapsed_time": "1 day, 6:15:12", "remaining_time": "2:27:42", "throughput": 554.73, "total_tokens": 60417040} {"current_steps": 36995, "total_steps": 40000, "loss": 0.1253, "lr": 6.935049024865776e-07, "epoch": 1.674754974082709, "percentage": 92.49, "elapsed_time": "1 day, 6:15:16", "remaining_time": "2:27:26", "throughput": 554.79, "total_tokens": 60426064} {"current_steps": 37000, "total_steps": 40000, "loss": 0.1486, "lr": 6.912104339335118e-07, "epoch": 1.674981325969352, "percentage": 92.5, "elapsed_time": "1 day, 6:15:19", "remaining_time": "2:27:11", "throughput": 554.85, "total_tokens": 60434192} {"current_steps": 37000, "total_steps": 40000, "eval_loss": 0.12208408862352371, "epoch": 1.674981325969352, "percentage": 92.5, "elapsed_time": "1 day, 6:23:01", "remaining_time": "2:27:48", "throughput": 552.51, "total_tokens": 60434192} {"current_steps": 37005, "total_steps": 40000, "loss": 0.1025, "lr": 6.889197141012799e-07, "epoch": 1.6752076778559948, "percentage": 92.51, "elapsed_time": "1 day, 6:23:06", "remaining_time": "2:27:33", "throughput": 552.56, "total_tokens": 60442320} {"current_steps": 37010, "total_steps": 40000, "loss": 0.1079, "lr": 6.866327433431435e-07, "epoch": 1.6754340297426378, "percentage": 92.53, "elapsed_time": "1 day, 6:23:09", "remaining_time": "2:27:17", "throughput": 552.62, "total_tokens": 60450320} {"current_steps": 37015, "total_steps": 40000, "loss": 0.1267, "lr": 6.843495220117735e-07, "epoch": 1.6756603816292808, "percentage": 92.54, "elapsed_time": "1 day, 6:23:12", "remaining_time": "2:27:01", "throughput": 552.67, "total_tokens": 60458416} {"current_steps": 37020, "total_steps": 40000, "loss": 0.1249, "lr": 6.820700504592798e-07, "epoch": 1.6758867335159238, "percentage": 92.55, "elapsed_time": "1 day, 6:23:15", "remaining_time": "2:26:46", "throughput": 552.73, "total_tokens": 60466160} {"current_steps": 37025, "total_steps": 40000, "loss": 0.1463, "lr": 6.797943290371839e-07, "epoch": 1.6761130854025668, "percentage": 92.56, "elapsed_time": "1 day, 6:23:18", "remaining_time": "2:26:30", "throughput": 552.79, "total_tokens": 60474480} {"current_steps": 37030, "total_steps": 40000, "loss": 0.0747, "lr": 6.775223580964274e-07, "epoch": 1.6763394372892098, "percentage": 92.58, "elapsed_time": "1 day, 6:23:21", "remaining_time": "2:26:14", "throughput": 552.84, "total_tokens": 60482128} {"current_steps": 37035, "total_steps": 40000, "loss": 0.094, "lr": 6.7525413798738e-07, "epoch": 1.6765657891758527, "percentage": 92.59, "elapsed_time": "1 day, 6:23:25", "remaining_time": "2:25:58", "throughput": 552.9, "total_tokens": 60490288} {"current_steps": 37040, "total_steps": 40000, "loss": 0.0771, "lr": 6.729896690598259e-07, "epoch": 1.6767921410624957, "percentage": 92.6, "elapsed_time": "1 day, 6:23:28", "remaining_time": "2:25:43", "throughput": 552.96, "total_tokens": 60498544} {"current_steps": 37045, "total_steps": 40000, "loss": 0.1471, "lr": 6.707289516629772e-07, "epoch": 1.6770184929491387, "percentage": 92.61, "elapsed_time": "1 day, 6:23:31", "remaining_time": "2:25:27", "throughput": 553.02, "total_tokens": 60506544} {"current_steps": 37050, "total_steps": 40000, "loss": 0.1192, "lr": 6.684719861454692e-07, "epoch": 1.6772448448357817, "percentage": 92.62, "elapsed_time": "1 day, 6:23:34", "remaining_time": "2:25:11", "throughput": 553.08, "total_tokens": 60514832} {"current_steps": 37055, "total_steps": 40000, "loss": 0.1461, "lr": 6.662187728553481e-07, "epoch": 1.6774711967224247, "percentage": 92.64, "elapsed_time": "1 day, 6:23:38", "remaining_time": "2:24:56", "throughput": 553.14, "total_tokens": 60523120} {"current_steps": 37060, "total_steps": 40000, "loss": 0.0974, "lr": 6.639693121400892e-07, "epoch": 1.6776975486090677, "percentage": 92.65, "elapsed_time": "1 day, 6:23:41", "remaining_time": "2:24:40", "throughput": 553.21, "total_tokens": 60532816} {"current_steps": 37065, "total_steps": 40000, "loss": 0.1337, "lr": 6.617236043465868e-07, "epoch": 1.6779239004957107, "percentage": 92.66, "elapsed_time": "1 day, 6:23:44", "remaining_time": "2:24:24", "throughput": 553.26, "total_tokens": 60540784} {"current_steps": 37070, "total_steps": 40000, "loss": 0.0945, "lr": 6.594816498211587e-07, "epoch": 1.6781502523823537, "percentage": 92.67, "elapsed_time": "1 day, 6:23:48", "remaining_time": "2:24:09", "throughput": 553.33, "total_tokens": 60549520} {"current_steps": 37075, "total_steps": 40000, "loss": 0.1189, "lr": 6.572434489095447e-07, "epoch": 1.6783766042689967, "percentage": 92.69, "elapsed_time": "1 day, 6:23:51", "remaining_time": "2:23:53", "throughput": 553.38, "total_tokens": 60557456} {"current_steps": 37080, "total_steps": 40000, "loss": 0.1317, "lr": 6.550090019568994e-07, "epoch": 1.6786029561556397, "percentage": 92.7, "elapsed_time": "1 day, 6:23:54", "remaining_time": "2:23:37", "throughput": 553.45, "total_tokens": 60566160} {"current_steps": 37085, "total_steps": 40000, "loss": 0.093, "lr": 6.527783093078027e-07, "epoch": 1.6788293080422827, "percentage": 92.71, "elapsed_time": "1 day, 6:23:57", "remaining_time": "2:23:22", "throughput": 553.5, "total_tokens": 60574416} {"current_steps": 37090, "total_steps": 40000, "loss": 0.1633, "lr": 6.5055137130626e-07, "epoch": 1.6790556599289255, "percentage": 92.73, "elapsed_time": "1 day, 6:24:01", "remaining_time": "2:23:06", "throughput": 553.56, "total_tokens": 60582544} {"current_steps": 37095, "total_steps": 40000, "loss": 0.0789, "lr": 6.483281882956854e-07, "epoch": 1.6792820118155685, "percentage": 92.74, "elapsed_time": "1 day, 6:24:04", "remaining_time": "2:22:50", "throughput": 553.62, "total_tokens": 60590608} {"current_steps": 37100, "total_steps": 40000, "loss": 0.0852, "lr": 6.461087606189298e-07, "epoch": 1.6795083637022115, "percentage": 92.75, "elapsed_time": "1 day, 6:24:07", "remaining_time": "2:22:35", "throughput": 553.68, "total_tokens": 60599024} {"current_steps": 37105, "total_steps": 40000, "loss": 0.1181, "lr": 6.438930886182554e-07, "epoch": 1.6797347155888545, "percentage": 92.76, "elapsed_time": "1 day, 6:24:10", "remaining_time": "2:22:19", "throughput": 553.73, "total_tokens": 60606672} {"current_steps": 37110, "total_steps": 40000, "loss": 0.1163, "lr": 6.416811726353417e-07, "epoch": 1.6799610674754974, "percentage": 92.77, "elapsed_time": "1 day, 6:24:14", "remaining_time": "2:22:03", "throughput": 553.8, "total_tokens": 60615664} {"current_steps": 37115, "total_steps": 40000, "loss": 0.1407, "lr": 6.394730130112991e-07, "epoch": 1.6801874193621402, "percentage": 92.79, "elapsed_time": "1 day, 6:24:17", "remaining_time": "2:21:48", "throughput": 553.85, "total_tokens": 60623440} {"current_steps": 37120, "total_steps": 40000, "loss": 0.0918, "lr": 6.372686100866471e-07, "epoch": 1.6804137712487832, "percentage": 92.8, "elapsed_time": "1 day, 6:24:20", "remaining_time": "2:21:32", "throughput": 553.91, "total_tokens": 60631728} {"current_steps": 37125, "total_steps": 40000, "loss": 0.133, "lr": 6.350679642013413e-07, "epoch": 1.6806401231354262, "percentage": 92.81, "elapsed_time": "1 day, 6:24:23", "remaining_time": "2:21:16", "throughput": 553.97, "total_tokens": 60640144} {"current_steps": 37130, "total_steps": 40000, "loss": 0.1044, "lr": 6.328710756947437e-07, "epoch": 1.6808664750220692, "percentage": 92.83, "elapsed_time": "1 day, 6:24:27", "remaining_time": "2:21:01", "throughput": 554.03, "total_tokens": 60648528} {"current_steps": 37135, "total_steps": 40000, "loss": 0.1552, "lr": 6.306779449056416e-07, "epoch": 1.6810928269087122, "percentage": 92.84, "elapsed_time": "1 day, 6:24:30", "remaining_time": "2:20:45", "throughput": 554.09, "total_tokens": 60656752} {"current_steps": 37140, "total_steps": 40000, "loss": 0.0711, "lr": 6.284885721722422e-07, "epoch": 1.6813191787953552, "percentage": 92.85, "elapsed_time": "1 day, 6:24:33", "remaining_time": "2:20:30", "throughput": 554.15, "total_tokens": 60664944} {"current_steps": 37145, "total_steps": 40000, "loss": 0.1149, "lr": 6.26302957832181e-07, "epoch": 1.6815455306819982, "percentage": 92.86, "elapsed_time": "1 day, 6:24:36", "remaining_time": "2:20:14", "throughput": 554.21, "total_tokens": 60672560} {"current_steps": 37150, "total_steps": 40000, "loss": 0.0999, "lr": 6.241211022224997e-07, "epoch": 1.6817718825686412, "percentage": 92.88, "elapsed_time": "1 day, 6:24:39", "remaining_time": "2:19:58", "throughput": 554.26, "total_tokens": 60680720} {"current_steps": 37155, "total_steps": 40000, "loss": 0.0867, "lr": 6.219430056796732e-07, "epoch": 1.6819982344552842, "percentage": 92.89, "elapsed_time": "1 day, 6:24:43", "remaining_time": "2:19:43", "throughput": 554.32, "total_tokens": 60688624} {"current_steps": 37160, "total_steps": 40000, "loss": 0.113, "lr": 6.19768668539586e-07, "epoch": 1.6822245863419272, "percentage": 92.9, "elapsed_time": "1 day, 6:24:46", "remaining_time": "2:19:27", "throughput": 554.38, "total_tokens": 60696816} {"current_steps": 37165, "total_steps": 40000, "loss": 0.0888, "lr": 6.175980911375528e-07, "epoch": 1.6824509382285702, "percentage": 92.91, "elapsed_time": "1 day, 6:24:49", "remaining_time": "2:19:12", "throughput": 554.43, "total_tokens": 60704560} {"current_steps": 37170, "total_steps": 40000, "loss": 0.0884, "lr": 6.154312738083034e-07, "epoch": 1.6826772901152132, "percentage": 92.92, "elapsed_time": "1 day, 6:24:52", "remaining_time": "2:18:56", "throughput": 554.49, "total_tokens": 60713104} {"current_steps": 37175, "total_steps": 40000, "loss": 0.0839, "lr": 6.132682168859843e-07, "epoch": 1.6829036420018562, "percentage": 92.94, "elapsed_time": "1 day, 6:24:56", "remaining_time": "2:18:40", "throughput": 554.55, "total_tokens": 60721232} {"current_steps": 37180, "total_steps": 40000, "loss": 0.1048, "lr": 6.111089207041704e-07, "epoch": 1.6831299938884992, "percentage": 92.95, "elapsed_time": "1 day, 6:24:59", "remaining_time": "2:18:25", "throughput": 554.61, "total_tokens": 60729872} {"current_steps": 37185, "total_steps": 40000, "loss": 0.1159, "lr": 6.089533855958507e-07, "epoch": 1.6833563457751421, "percentage": 92.96, "elapsed_time": "1 day, 6:25:02", "remaining_time": "2:18:09", "throughput": 554.67, "total_tokens": 60737936} {"current_steps": 37190, "total_steps": 40000, "loss": 0.1504, "lr": 6.068016118934372e-07, "epoch": 1.6835826976617851, "percentage": 92.97, "elapsed_time": "1 day, 6:25:05", "remaining_time": "2:17:54", "throughput": 554.73, "total_tokens": 60746576} {"current_steps": 37195, "total_steps": 40000, "loss": 0.0747, "lr": 6.04653599928759e-07, "epoch": 1.6838090495484281, "percentage": 92.99, "elapsed_time": "1 day, 6:25:08", "remaining_time": "2:17:38", "throughput": 554.79, "total_tokens": 60754192} {"current_steps": 37200, "total_steps": 40000, "loss": 0.0819, "lr": 6.025093500330675e-07, "epoch": 1.684035401435071, "percentage": 93.0, "elapsed_time": "1 day, 6:25:12", "remaining_time": "2:17:22", "throughput": 554.84, "total_tokens": 60762128} {"current_steps": 37200, "total_steps": 40000, "eval_loss": 0.12195153534412384, "epoch": 1.684035401435071, "percentage": 93.0, "elapsed_time": "1 day, 6:32:54", "remaining_time": "2:17:57", "throughput": 552.51, "total_tokens": 60762128} {"current_steps": 37205, "total_steps": 40000, "loss": 0.139, "lr": 6.003688625370291e-07, "epoch": 1.684261753321714, "percentage": 93.01, "elapsed_time": "1 day, 6:32:59", "remaining_time": "2:17:42", "throughput": 552.56, "total_tokens": 60770320} {"current_steps": 37210, "total_steps": 40000, "loss": 0.1136, "lr": 5.982321377707406e-07, "epoch": 1.684488105208357, "percentage": 93.03, "elapsed_time": "1 day, 6:33:02", "remaining_time": "2:17:26", "throughput": 552.63, "total_tokens": 60779376} {"current_steps": 37215, "total_steps": 40000, "loss": 0.1157, "lr": 5.96099176063708e-07, "epoch": 1.684714457095, "percentage": 93.04, "elapsed_time": "1 day, 6:33:05", "remaining_time": "2:17:10", "throughput": 552.68, "total_tokens": 60786832} {"current_steps": 37220, "total_steps": 40000, "loss": 0.0883, "lr": 5.93969977744857e-07, "epoch": 1.684940808981643, "percentage": 93.05, "elapsed_time": "1 day, 6:33:08", "remaining_time": "2:16:55", "throughput": 552.73, "total_tokens": 60794640} {"current_steps": 37225, "total_steps": 40000, "loss": 0.0996, "lr": 5.918445431425445e-07, "epoch": 1.6851671608682859, "percentage": 93.06, "elapsed_time": "1 day, 6:33:12", "remaining_time": "2:16:39", "throughput": 552.79, "total_tokens": 60802704} {"current_steps": 37230, "total_steps": 40000, "loss": 0.1158, "lr": 5.897228725845333e-07, "epoch": 1.6853935127549287, "percentage": 93.08, "elapsed_time": "1 day, 6:33:15", "remaining_time": "2:16:23", "throughput": 552.85, "total_tokens": 60811024} {"current_steps": 37235, "total_steps": 40000, "loss": 0.1013, "lr": 5.876049663980171e-07, "epoch": 1.6856198646415717, "percentage": 93.09, "elapsed_time": "1 day, 6:33:18", "remaining_time": "2:16:08", "throughput": 552.91, "total_tokens": 60819312} {"current_steps": 37240, "total_steps": 40000, "loss": 0.1231, "lr": 5.854908249095959e-07, "epoch": 1.6858462165282146, "percentage": 93.1, "elapsed_time": "1 day, 6:33:21", "remaining_time": "2:15:52", "throughput": 552.97, "total_tokens": 60827728} {"current_steps": 37245, "total_steps": 40000, "loss": 0.1338, "lr": 5.833804484453031e-07, "epoch": 1.6860725684148576, "percentage": 93.11, "elapsed_time": "1 day, 6:33:25", "remaining_time": "2:15:37", "throughput": 553.03, "total_tokens": 60836528} {"current_steps": 37250, "total_steps": 40000, "loss": 0.0876, "lr": 5.81273837330587e-07, "epoch": 1.6862989203015006, "percentage": 93.12, "elapsed_time": "1 day, 6:33:28", "remaining_time": "2:15:21", "throughput": 553.09, "total_tokens": 60844368} {"current_steps": 37255, "total_steps": 40000, "loss": 0.2175, "lr": 5.791709918903071e-07, "epoch": 1.6865252721881436, "percentage": 93.14, "elapsed_time": "1 day, 6:33:31", "remaining_time": "2:15:05", "throughput": 553.15, "total_tokens": 60853040} {"current_steps": 37260, "total_steps": 40000, "loss": 0.1039, "lr": 5.770719124487483e-07, "epoch": 1.6867516240747866, "percentage": 93.15, "elapsed_time": "1 day, 6:33:34", "remaining_time": "2:14:50", "throughput": 553.21, "total_tokens": 60861424} {"current_steps": 37265, "total_steps": 40000, "loss": 0.1092, "lr": 5.749765993296241e-07, "epoch": 1.6869779759614296, "percentage": 93.16, "elapsed_time": "1 day, 6:33:38", "remaining_time": "2:14:34", "throughput": 553.28, "total_tokens": 60870832} {"current_steps": 37270, "total_steps": 40000, "loss": 0.1429, "lr": 5.728850528560509e-07, "epoch": 1.6872043278480726, "percentage": 93.17, "elapsed_time": "1 day, 6:33:41", "remaining_time": "2:14:19", "throughput": 553.34, "total_tokens": 60879248} {"current_steps": 37275, "total_steps": 40000, "loss": 0.1523, "lr": 5.707972733505707e-07, "epoch": 1.6874306797347156, "percentage": 93.19, "elapsed_time": "1 day, 6:33:44", "remaining_time": "2:14:03", "throughput": 553.4, "total_tokens": 60887888} {"current_steps": 37280, "total_steps": 40000, "loss": 0.1042, "lr": 5.687132611351509e-07, "epoch": 1.6876570316213586, "percentage": 93.2, "elapsed_time": "1 day, 6:33:48", "remaining_time": "2:13:47", "throughput": 553.46, "total_tokens": 60895824} {"current_steps": 37285, "total_steps": 40000, "loss": 0.0968, "lr": 5.666330165311651e-07, "epoch": 1.6878833835080016, "percentage": 93.21, "elapsed_time": "1 day, 6:33:51", "remaining_time": "2:13:32", "throughput": 553.51, "total_tokens": 60903792} {"current_steps": 37290, "total_steps": 40000, "loss": 0.0822, "lr": 5.645565398594204e-07, "epoch": 1.6881097353946446, "percentage": 93.23, "elapsed_time": "1 day, 6:33:54", "remaining_time": "2:13:16", "throughput": 553.57, "total_tokens": 60912176} {"current_steps": 37295, "total_steps": 40000, "loss": 0.1044, "lr": 5.624838314401304e-07, "epoch": 1.6883360872812876, "percentage": 93.24, "elapsed_time": "1 day, 6:33:57", "remaining_time": "2:13:01", "throughput": 553.63, "total_tokens": 60920752} {"current_steps": 37300, "total_steps": 40000, "loss": 0.1324, "lr": 5.604148915929336e-07, "epoch": 1.6885624391679306, "percentage": 93.25, "elapsed_time": "1 day, 6:34:01", "remaining_time": "2:12:45", "throughput": 553.69, "total_tokens": 60928304} {"current_steps": 37305, "total_steps": 40000, "loss": 0.1696, "lr": 5.583497206368887e-07, "epoch": 1.6887887910545736, "percentage": 93.26, "elapsed_time": "1 day, 6:34:04", "remaining_time": "2:12:29", "throughput": 553.74, "total_tokens": 60936144} {"current_steps": 37310, "total_steps": 40000, "loss": 0.0948, "lr": 5.562883188904688e-07, "epoch": 1.6890151429412166, "percentage": 93.27, "elapsed_time": "1 day, 6:34:07", "remaining_time": "2:12:14", "throughput": 553.8, "total_tokens": 60944784} {"current_steps": 37315, "total_steps": 40000, "loss": 0.0705, "lr": 5.542306866715724e-07, "epoch": 1.6892414948278593, "percentage": 93.29, "elapsed_time": "1 day, 6:34:10", "remaining_time": "2:11:58", "throughput": 553.87, "total_tokens": 60953648} {"current_steps": 37320, "total_steps": 40000, "loss": 0.1039, "lr": 5.52176824297504e-07, "epoch": 1.6894678467145023, "percentage": 93.3, "elapsed_time": "1 day, 6:34:14", "remaining_time": "2:11:43", "throughput": 553.93, "total_tokens": 60962800} {"current_steps": 37325, "total_steps": 40000, "loss": 0.1084, "lr": 5.501267320850018e-07, "epoch": 1.6896941986011453, "percentage": 93.31, "elapsed_time": "1 day, 6:34:17", "remaining_time": "2:11:27", "throughput": 554.0, "total_tokens": 60971792} {"current_steps": 37330, "total_steps": 40000, "loss": 0.1547, "lr": 5.480804103502157e-07, "epoch": 1.6899205504877883, "percentage": 93.33, "elapsed_time": "1 day, 6:34:20", "remaining_time": "2:11:12", "throughput": 554.06, "total_tokens": 60980208} {"current_steps": 37335, "total_steps": 40000, "loss": 0.1662, "lr": 5.460378594087101e-07, "epoch": 1.6901469023744313, "percentage": 93.34, "elapsed_time": "1 day, 6:34:24", "remaining_time": "2:10:56", "throughput": 554.11, "total_tokens": 60987728} {"current_steps": 37340, "total_steps": 40000, "loss": 0.1148, "lr": 5.439990795754773e-07, "epoch": 1.6903732542610743, "percentage": 93.35, "elapsed_time": "1 day, 6:34:27", "remaining_time": "2:10:40", "throughput": 554.17, "total_tokens": 60996304} {"current_steps": 37345, "total_steps": 40000, "loss": 0.1181, "lr": 5.419640711649188e-07, "epoch": 1.690599606147717, "percentage": 93.36, "elapsed_time": "1 day, 6:34:30", "remaining_time": "2:10:25", "throughput": 554.23, "total_tokens": 61004848} {"current_steps": 37350, "total_steps": 40000, "loss": 0.1055, "lr": 5.399328344908583e-07, "epoch": 1.69082595803436, "percentage": 93.38, "elapsed_time": "1 day, 6:34:33", "remaining_time": "2:10:09", "throughput": 554.29, "total_tokens": 61013328} {"current_steps": 37355, "total_steps": 40000, "loss": 0.0901, "lr": 5.379053698665399e-07, "epoch": 1.691052309921003, "percentage": 93.39, "elapsed_time": "1 day, 6:34:37", "remaining_time": "2:09:54", "throughput": 554.35, "total_tokens": 61020976} {"current_steps": 37360, "total_steps": 40000, "loss": 0.1491, "lr": 5.358816776046216e-07, "epoch": 1.691278661807646, "percentage": 93.4, "elapsed_time": "1 day, 6:34:40", "remaining_time": "2:09:38", "throughput": 554.4, "total_tokens": 61028560} {"current_steps": 37365, "total_steps": 40000, "loss": 0.1184, "lr": 5.338617580171817e-07, "epoch": 1.691505013694289, "percentage": 93.41, "elapsed_time": "1 day, 6:34:43", "remaining_time": "2:09:23", "throughput": 554.46, "total_tokens": 61036368} {"current_steps": 37370, "total_steps": 40000, "loss": 0.0777, "lr": 5.318456114157239e-07, "epoch": 1.691731365580932, "percentage": 93.42, "elapsed_time": "1 day, 6:34:46", "remaining_time": "2:09:07", "throughput": 554.52, "total_tokens": 61044752} {"current_steps": 37375, "total_steps": 40000, "loss": 0.0911, "lr": 5.298332381111576e-07, "epoch": 1.691957717467575, "percentage": 93.44, "elapsed_time": "1 day, 6:34:49", "remaining_time": "2:08:52", "throughput": 554.57, "total_tokens": 61052624} {"current_steps": 37380, "total_steps": 40000, "loss": 0.1678, "lr": 5.27824638413818e-07, "epoch": 1.692184069354218, "percentage": 93.45, "elapsed_time": "1 day, 6:34:53", "remaining_time": "2:08:36", "throughput": 554.63, "total_tokens": 61061136} {"current_steps": 37385, "total_steps": 40000, "loss": 0.1346, "lr": 5.258198126334546e-07, "epoch": 1.692410421240861, "percentage": 93.46, "elapsed_time": "1 day, 6:34:56", "remaining_time": "2:08:21", "throughput": 554.69, "total_tokens": 61069360} {"current_steps": 37390, "total_steps": 40000, "loss": 0.1066, "lr": 5.238187610792367e-07, "epoch": 1.692636773127504, "percentage": 93.47, "elapsed_time": "1 day, 6:34:59", "remaining_time": "2:08:05", "throughput": 554.75, "total_tokens": 61077744} {"current_steps": 37395, "total_steps": 40000, "loss": 0.1165, "lr": 5.218214840597563e-07, "epoch": 1.692863125014147, "percentage": 93.49, "elapsed_time": "1 day, 6:35:02", "remaining_time": "2:07:49", "throughput": 554.81, "total_tokens": 61086224} {"current_steps": 37400, "total_steps": 40000, "loss": 0.0808, "lr": 5.198279818830115e-07, "epoch": 1.69308947690079, "percentage": 93.5, "elapsed_time": "1 day, 6:35:06", "remaining_time": "2:07:34", "throughput": 554.87, "total_tokens": 61094320} {"current_steps": 37400, "total_steps": 40000, "eval_loss": 0.12199903279542923, "epoch": 1.69308947690079, "percentage": 93.5, "elapsed_time": "1 day, 6:42:48", "remaining_time": "2:08:06", "throughput": 552.55, "total_tokens": 61094320} {"current_steps": 37405, "total_steps": 40000, "loss": 0.151, "lr": 5.178382548564287e-07, "epoch": 1.693315828787433, "percentage": 93.51, "elapsed_time": "1 day, 6:42:52", "remaining_time": "2:07:51", "throughput": 552.6, "total_tokens": 61102416} {"current_steps": 37410, "total_steps": 40000, "loss": 0.0938, "lr": 5.15852303286854e-07, "epoch": 1.693542180674076, "percentage": 93.53, "elapsed_time": "1 day, 6:42:56", "remaining_time": "2:07:35", "throughput": 552.66, "total_tokens": 61110512} {"current_steps": 37415, "total_steps": 40000, "loss": 0.0949, "lr": 5.138701274805396e-07, "epoch": 1.693768532560719, "percentage": 93.54, "elapsed_time": "1 day, 6:42:59", "remaining_time": "2:07:19", "throughput": 552.71, "total_tokens": 61118544} {"current_steps": 37420, "total_steps": 40000, "loss": 0.0922, "lr": 5.118917277431606e-07, "epoch": 1.693994884447362, "percentage": 93.55, "elapsed_time": "1 day, 6:43:02", "remaining_time": "2:07:04", "throughput": 552.77, "total_tokens": 61126192} {"current_steps": 37425, "total_steps": 40000, "loss": 0.1066, "lr": 5.099171043798145e-07, "epoch": 1.694221236334005, "percentage": 93.56, "elapsed_time": "1 day, 6:43:05", "remaining_time": "2:06:48", "throughput": 552.83, "total_tokens": 61134640} {"current_steps": 37430, "total_steps": 40000, "loss": 0.1068, "lr": 5.079462576950133e-07, "epoch": 1.6944475882206478, "percentage": 93.58, "elapsed_time": "1 day, 6:43:08", "remaining_time": "2:06:33", "throughput": 552.89, "total_tokens": 61143344} {"current_steps": 37435, "total_steps": 40000, "loss": 0.0901, "lr": 5.059791879926862e-07, "epoch": 1.6946739401072908, "percentage": 93.59, "elapsed_time": "1 day, 6:43:12", "remaining_time": "2:06:17", "throughput": 552.95, "total_tokens": 61151760} {"current_steps": 37440, "total_steps": 40000, "loss": 0.1142, "lr": 5.040158955761793e-07, "epoch": 1.6949002919939338, "percentage": 93.6, "elapsed_time": "1 day, 6:43:15", "remaining_time": "2:06:02", "throughput": 553.02, "total_tokens": 61161296} {"current_steps": 37445, "total_steps": 40000, "loss": 0.1338, "lr": 5.020563807482559e-07, "epoch": 1.6951266438805768, "percentage": 93.61, "elapsed_time": "1 day, 6:43:18", "remaining_time": "2:05:46", "throughput": 553.07, "total_tokens": 61169136} {"current_steps": 37450, "total_steps": 40000, "loss": 0.1587, "lr": 5.001006438110995e-07, "epoch": 1.6953529957672198, "percentage": 93.62, "elapsed_time": "1 day, 6:43:22", "remaining_time": "2:05:30", "throughput": 553.14, "total_tokens": 61178192} {"current_steps": 37455, "total_steps": 40000, "loss": 0.1376, "lr": 4.981486850663075e-07, "epoch": 1.6955793476538625, "percentage": 93.64, "elapsed_time": "1 day, 6:43:25", "remaining_time": "2:05:15", "throughput": 553.19, "total_tokens": 61186320} {"current_steps": 37460, "total_steps": 40000, "loss": 0.1768, "lr": 4.962005048149005e-07, "epoch": 1.6958056995405055, "percentage": 93.65, "elapsed_time": "1 day, 6:43:28", "remaining_time": "2:04:59", "throughput": 553.25, "total_tokens": 61193968} {"current_steps": 37465, "total_steps": 40000, "loss": 0.1722, "lr": 4.942561033573073e-07, "epoch": 1.6960320514271485, "percentage": 93.66, "elapsed_time": "1 day, 6:43:31", "remaining_time": "2:04:44", "throughput": 553.3, "total_tokens": 61201840} {"current_steps": 37470, "total_steps": 40000, "loss": 0.0743, "lr": 4.923154809933827e-07, "epoch": 1.6962584033137915, "percentage": 93.67, "elapsed_time": "1 day, 6:43:34", "remaining_time": "2:04:28", "throughput": 553.36, "total_tokens": 61210128} {"current_steps": 37475, "total_steps": 40000, "loss": 0.1242, "lr": 4.903786380223957e-07, "epoch": 1.6964847552004345, "percentage": 93.69, "elapsed_time": "1 day, 6:43:37", "remaining_time": "2:04:13", "throughput": 553.42, "total_tokens": 61217936} {"current_steps": 37480, "total_steps": 40000, "loss": 0.1281, "lr": 4.884455747430266e-07, "epoch": 1.6967111070870775, "percentage": 93.7, "elapsed_time": "1 day, 6:43:41", "remaining_time": "2:03:57", "throughput": 553.47, "total_tokens": 61225872} {"current_steps": 37485, "total_steps": 40000, "loss": 0.1305, "lr": 4.865162914533816e-07, "epoch": 1.6969374589737205, "percentage": 93.71, "elapsed_time": "1 day, 6:43:44", "remaining_time": "2:03:42", "throughput": 553.53, "total_tokens": 61234320} {"current_steps": 37490, "total_steps": 40000, "loss": 0.1273, "lr": 4.845907884509809e-07, "epoch": 1.6971638108603635, "percentage": 93.73, "elapsed_time": "1 day, 6:43:47", "remaining_time": "2:03:26", "throughput": 553.59, "total_tokens": 61241808} {"current_steps": 37495, "total_steps": 40000, "loss": 0.1024, "lr": 4.82669066032762e-07, "epoch": 1.6973901627470065, "percentage": 93.74, "elapsed_time": "1 day, 6:43:50", "remaining_time": "2:03:11", "throughput": 553.64, "total_tokens": 61250000} {"current_steps": 37500, "total_steps": 40000, "loss": 0.1015, "lr": 4.807511244950768e-07, "epoch": 1.6976165146336495, "percentage": 93.75, "elapsed_time": "1 day, 6:43:53", "remaining_time": "2:02:55", "throughput": 553.7, "total_tokens": 61258128} {"current_steps": 37505, "total_steps": 40000, "loss": 0.1396, "lr": 4.788369641336943e-07, "epoch": 1.6978428665202925, "percentage": 93.76, "elapsed_time": "1 day, 6:43:56", "remaining_time": "2:02:40", "throughput": 553.75, "total_tokens": 61265680} {"current_steps": 37510, "total_steps": 40000, "loss": 0.1334, "lr": 4.769265852438032e-07, "epoch": 1.6980692184069355, "percentage": 93.77, "elapsed_time": "1 day, 6:44:00", "remaining_time": "2:02:24", "throughput": 553.82, "total_tokens": 61274224} {"current_steps": 37515, "total_steps": 40000, "loss": 0.1645, "lr": 4.750199881200124e-07, "epoch": 1.6982955702935785, "percentage": 93.79, "elapsed_time": "1 day, 6:44:03", "remaining_time": "2:02:09", "throughput": 553.87, "total_tokens": 61281776} {"current_steps": 37520, "total_steps": 40000, "loss": 0.1192, "lr": 4.7311717305633664e-07, "epoch": 1.6985219221802215, "percentage": 93.8, "elapsed_time": "1 day, 6:44:06", "remaining_time": "2:01:53", "throughput": 553.93, "total_tokens": 61290192} {"current_steps": 37525, "total_steps": 40000, "loss": 0.1195, "lr": 4.7121814034621623e-07, "epoch": 1.6987482740668645, "percentage": 93.81, "elapsed_time": "1 day, 6:44:09", "remaining_time": "2:01:38", "throughput": 554.0, "total_tokens": 61299632} {"current_steps": 37530, "total_steps": 40000, "loss": 0.0666, "lr": 4.693228902825114e-07, "epoch": 1.6989746259535075, "percentage": 93.83, "elapsed_time": "1 day, 6:44:13", "remaining_time": "2:01:22", "throughput": 554.06, "total_tokens": 61308272} {"current_steps": 37535, "total_steps": 40000, "loss": 0.1194, "lr": 4.6743142315748277e-07, "epoch": 1.6992009778401505, "percentage": 93.84, "elapsed_time": "1 day, 6:44:16", "remaining_time": "2:01:07", "throughput": 554.11, "total_tokens": 61315984} {"current_steps": 37540, "total_steps": 40000, "loss": 0.0886, "lr": 4.655437392628276e-07, "epoch": 1.6994273297267932, "percentage": 93.85, "elapsed_time": "1 day, 6:44:19", "remaining_time": "2:00:51", "throughput": 554.17, "total_tokens": 61324496} {"current_steps": 37545, "total_steps": 40000, "loss": 0.0842, "lr": 4.636598388896463e-07, "epoch": 1.6996536816134362, "percentage": 93.86, "elapsed_time": "1 day, 6:44:22", "remaining_time": "2:00:36", "throughput": 554.23, "total_tokens": 61332080} {"current_steps": 37550, "total_steps": 40000, "loss": 0.1007, "lr": 4.6177972232845925e-07, "epoch": 1.6998800335000792, "percentage": 93.88, "elapsed_time": "1 day, 6:44:25", "remaining_time": "2:00:20", "throughput": 554.28, "total_tokens": 61339984} {"current_steps": 37555, "total_steps": 40000, "loss": 0.1406, "lr": 4.5990338986920953e-07, "epoch": 1.7001063853867222, "percentage": 93.89, "elapsed_time": "1 day, 6:44:28", "remaining_time": "2:00:05", "throughput": 554.34, "total_tokens": 61347696} {"current_steps": 37560, "total_steps": 40000, "loss": 0.1034, "lr": 4.5803084180124633e-07, "epoch": 1.7003327372733652, "percentage": 93.9, "elapsed_time": "1 day, 6:44:32", "remaining_time": "1:59:49", "throughput": 554.4, "total_tokens": 61356144} {"current_steps": 37565, "total_steps": 40000, "loss": 0.0905, "lr": 4.561620784133386e-07, "epoch": 1.7005590891600082, "percentage": 93.91, "elapsed_time": "1 day, 6:44:35", "remaining_time": "1:59:34", "throughput": 554.45, "total_tokens": 61364208} {"current_steps": 37570, "total_steps": 40000, "loss": 0.0724, "lr": 4.5429709999367796e-07, "epoch": 1.700785441046651, "percentage": 93.92, "elapsed_time": "1 day, 6:44:38", "remaining_time": "1:59:18", "throughput": 554.51, "total_tokens": 61372816} {"current_steps": 37575, "total_steps": 40000, "loss": 0.0936, "lr": 4.5243590682986223e-07, "epoch": 1.701011792933294, "percentage": 93.94, "elapsed_time": "1 day, 6:44:41", "remaining_time": "1:59:03", "throughput": 554.57, "total_tokens": 61380432} {"current_steps": 37580, "total_steps": 40000, "loss": 0.1023, "lr": 4.5057849920891735e-07, "epoch": 1.701238144819937, "percentage": 93.95, "elapsed_time": "1 day, 6:44:44", "remaining_time": "1:58:47", "throughput": 554.62, "total_tokens": 61388464} {"current_steps": 37585, "total_steps": 40000, "loss": 0.1575, "lr": 4.487248774172698e-07, "epoch": 1.70146449670658, "percentage": 93.96, "elapsed_time": "1 day, 6:44:47", "remaining_time": "1:58:32", "throughput": 554.68, "total_tokens": 61396560} {"current_steps": 37590, "total_steps": 40000, "loss": 0.1337, "lr": 4.4687504174077965e-07, "epoch": 1.701690848593223, "percentage": 93.97, "elapsed_time": "1 day, 6:44:51", "remaining_time": "1:58:16", "throughput": 554.74, "total_tokens": 61404592} {"current_steps": 37595, "total_steps": 40000, "loss": 0.107, "lr": 4.450289924647133e-07, "epoch": 1.701917200479866, "percentage": 93.99, "elapsed_time": "1 day, 6:44:54", "remaining_time": "1:58:01", "throughput": 554.8, "total_tokens": 61412880} {"current_steps": 37600, "total_steps": 40000, "loss": 0.1355, "lr": 4.431867298737513e-07, "epoch": 1.702143552366509, "percentage": 94.0, "elapsed_time": "1 day, 6:44:57", "remaining_time": "1:57:45", "throughput": 554.85, "total_tokens": 61421040} {"current_steps": 37600, "total_steps": 40000, "eval_loss": 0.12230271846055984, "epoch": 1.702143552366509, "percentage": 94.0, "elapsed_time": "1 day, 6:52:40", "remaining_time": "1:58:15", "throughput": 552.54, "total_tokens": 61421040} {"current_steps": 37605, "total_steps": 40000, "loss": 0.1715, "lr": 4.41348254251997e-07, "epoch": 1.702369904253152, "percentage": 94.01, "elapsed_time": "1 day, 6:52:44", "remaining_time": "1:57:59", "throughput": 552.59, "total_tokens": 61428880} {"current_steps": 37610, "total_steps": 40000, "loss": 0.1083, "lr": 4.395135658829652e-07, "epoch": 1.702596256139795, "percentage": 94.03, "elapsed_time": "1 day, 6:52:47", "remaining_time": "1:57:44", "throughput": 552.65, "total_tokens": 61436816} {"current_steps": 37615, "total_steps": 40000, "loss": 0.1315, "lr": 4.376826650495852e-07, "epoch": 1.702822608026438, "percentage": 94.04, "elapsed_time": "1 day, 6:52:51", "remaining_time": "1:57:28", "throughput": 552.71, "total_tokens": 61445776} {"current_steps": 37620, "total_steps": 40000, "loss": 0.108, "lr": 4.358555520342117e-07, "epoch": 1.703048959913081, "percentage": 94.05, "elapsed_time": "1 day, 6:52:54", "remaining_time": "1:57:13", "throughput": 552.77, "total_tokens": 61453936} {"current_steps": 37625, "total_steps": 40000, "loss": 0.1673, "lr": 4.3403222711860257e-07, "epoch": 1.703275311799724, "percentage": 94.06, "elapsed_time": "1 day, 6:52:57", "remaining_time": "1:56:57", "throughput": 552.82, "total_tokens": 61461264} {"current_steps": 37630, "total_steps": 40000, "loss": 0.1732, "lr": 4.3221269058394133e-07, "epoch": 1.703501663686367, "percentage": 94.08, "elapsed_time": "1 day, 6:53:00", "remaining_time": "1:56:42", "throughput": 552.88, "total_tokens": 61469232} {"current_steps": 37635, "total_steps": 40000, "loss": 0.0744, "lr": 4.303969427108173e-07, "epoch": 1.70372801557301, "percentage": 94.09, "elapsed_time": "1 day, 6:53:03", "remaining_time": "1:56:26", "throughput": 552.94, "total_tokens": 61477552} {"current_steps": 37640, "total_steps": 40000, "loss": 0.1269, "lr": 4.2858498377924825e-07, "epoch": 1.703954367459653, "percentage": 94.1, "elapsed_time": "1 day, 6:53:06", "remaining_time": "1:56:11", "throughput": 553.0, "total_tokens": 61485872} {"current_steps": 37645, "total_steps": 40000, "loss": 0.1485, "lr": 4.267768140686579e-07, "epoch": 1.704180719346296, "percentage": 94.11, "elapsed_time": "1 day, 6:53:09", "remaining_time": "1:55:55", "throughput": 553.05, "total_tokens": 61493744} {"current_steps": 37650, "total_steps": 40000, "loss": 0.1283, "lr": 4.2497243385788975e-07, "epoch": 1.7044070712329389, "percentage": 94.12, "elapsed_time": "1 day, 6:53:13", "remaining_time": "1:55:40", "throughput": 553.11, "total_tokens": 61501840} {"current_steps": 37655, "total_steps": 40000, "loss": 0.1439, "lr": 4.231718434251991e-07, "epoch": 1.7046334231195817, "percentage": 94.14, "elapsed_time": "1 day, 6:53:16", "remaining_time": "1:55:24", "throughput": 553.17, "total_tokens": 61510224} {"current_steps": 37660, "total_steps": 40000, "loss": 0.1739, "lr": 4.213750430482666e-07, "epoch": 1.7048597750062247, "percentage": 94.15, "elapsed_time": "1 day, 6:53:19", "remaining_time": "1:55:09", "throughput": 553.23, "total_tokens": 61518640} {"current_steps": 37665, "total_steps": 40000, "loss": 0.1006, "lr": 4.1958203300417054e-07, "epoch": 1.7050861268928676, "percentage": 94.16, "elapsed_time": "1 day, 6:53:22", "remaining_time": "1:54:53", "throughput": 553.29, "total_tokens": 61527600} {"current_steps": 37670, "total_steps": 40000, "loss": 0.1094, "lr": 4.177928135694259e-07, "epoch": 1.7053124787795106, "percentage": 94.17, "elapsed_time": "1 day, 6:53:26", "remaining_time": "1:54:38", "throughput": 553.35, "total_tokens": 61536080} {"current_steps": 37675, "total_steps": 40000, "loss": 0.1859, "lr": 4.1600738501994807e-07, "epoch": 1.7055388306661536, "percentage": 94.19, "elapsed_time": "1 day, 6:53:29", "remaining_time": "1:54:22", "throughput": 553.41, "total_tokens": 61544368} {"current_steps": 37680, "total_steps": 40000, "loss": 0.1216, "lr": 4.1422574763107237e-07, "epoch": 1.7057651825527966, "percentage": 94.2, "elapsed_time": "1 day, 6:53:32", "remaining_time": "1:54:07", "throughput": 553.47, "total_tokens": 61552688} {"current_steps": 37685, "total_steps": 40000, "loss": 0.082, "lr": 4.124479016775512e-07, "epoch": 1.7059915344394394, "percentage": 94.21, "elapsed_time": "1 day, 6:53:35", "remaining_time": "1:53:52", "throughput": 553.53, "total_tokens": 61561008} {"current_steps": 37690, "total_steps": 40000, "loss": 0.1171, "lr": 4.106738474335514e-07, "epoch": 1.7062178863260824, "percentage": 94.23, "elapsed_time": "1 day, 6:53:38", "remaining_time": "1:53:36", "throughput": 553.58, "total_tokens": 61568976} {"current_steps": 37695, "total_steps": 40000, "loss": 0.1272, "lr": 4.089035851726486e-07, "epoch": 1.7064442382127254, "percentage": 94.24, "elapsed_time": "1 day, 6:53:42", "remaining_time": "1:53:21", "throughput": 553.64, "total_tokens": 61576688} {"current_steps": 37700, "total_steps": 40000, "loss": 0.1545, "lr": 4.0713711516784937e-07, "epoch": 1.7066705900993684, "percentage": 94.25, "elapsed_time": "1 day, 6:53:45", "remaining_time": "1:53:05", "throughput": 553.69, "total_tokens": 61584720} {"current_steps": 37705, "total_steps": 40000, "loss": 0.1894, "lr": 4.05374437691558e-07, "epoch": 1.7068969419860114, "percentage": 94.26, "elapsed_time": "1 day, 6:53:48", "remaining_time": "1:52:50", "throughput": 553.75, "total_tokens": 61592656} {"current_steps": 37710, "total_steps": 40000, "loss": 0.1363, "lr": 4.036155530156044e-07, "epoch": 1.7071232938726544, "percentage": 94.27, "elapsed_time": "1 day, 6:53:51", "remaining_time": "1:52:34", "throughput": 553.81, "total_tokens": 61600912} {"current_steps": 37715, "total_steps": 40000, "loss": 0.1262, "lr": 4.018604614112298e-07, "epoch": 1.7073496457592974, "percentage": 94.29, "elapsed_time": "1 day, 6:53:54", "remaining_time": "1:52:19", "throughput": 553.87, "total_tokens": 61609680} {"current_steps": 37720, "total_steps": 40000, "loss": 0.1545, "lr": 4.0010916314908996e-07, "epoch": 1.7075759976459404, "percentage": 94.3, "elapsed_time": "1 day, 6:53:58", "remaining_time": "1:52:03", "throughput": 553.93, "total_tokens": 61618096} {"current_steps": 37725, "total_steps": 40000, "loss": 0.1146, "lr": 3.983616584992578e-07, "epoch": 1.7078023495325834, "percentage": 94.31, "elapsed_time": "1 day, 6:54:01", "remaining_time": "1:51:48", "throughput": 553.98, "total_tokens": 61625904} {"current_steps": 37730, "total_steps": 40000, "loss": 0.1274, "lr": 3.9661794773122595e-07, "epoch": 1.7080287014192264, "percentage": 94.33, "elapsed_time": "1 day, 6:54:04", "remaining_time": "1:51:32", "throughput": 554.04, "total_tokens": 61633776} {"current_steps": 37735, "total_steps": 40000, "loss": 0.1025, "lr": 3.9487803111388777e-07, "epoch": 1.7082550533058694, "percentage": 94.34, "elapsed_time": "1 day, 6:54:07", "remaining_time": "1:51:17", "throughput": 554.09, "total_tokens": 61641584} {"current_steps": 37740, "total_steps": 40000, "loss": 0.1282, "lr": 3.9314190891556747e-07, "epoch": 1.7084814051925123, "percentage": 94.35, "elapsed_time": "1 day, 6:54:10", "remaining_time": "1:51:02", "throughput": 554.15, "total_tokens": 61649232} {"current_steps": 37745, "total_steps": 40000, "loss": 0.0861, "lr": 3.914095814039925e-07, "epoch": 1.7087077570791553, "percentage": 94.36, "elapsed_time": "1 day, 6:54:13", "remaining_time": "1:50:46", "throughput": 554.21, "total_tokens": 61657680} {"current_steps": 37750, "total_steps": 40000, "loss": 0.0961, "lr": 3.896810488463104e-07, "epoch": 1.7089341089657983, "percentage": 94.38, "elapsed_time": "1 day, 6:54:16", "remaining_time": "1:50:31", "throughput": 554.27, "total_tokens": 61666288} {"current_steps": 37755, "total_steps": 40000, "loss": 0.1199, "lr": 3.8795631150908565e-07, "epoch": 1.7091604608524413, "percentage": 94.39, "elapsed_time": "1 day, 6:54:20", "remaining_time": "1:50:15", "throughput": 554.33, "total_tokens": 61674512} {"current_steps": 37760, "total_steps": 40000, "loss": 0.0832, "lr": 3.862353696582888e-07, "epoch": 1.7093868127390843, "percentage": 94.4, "elapsed_time": "1 day, 6:54:23", "remaining_time": "1:50:00", "throughput": 554.39, "total_tokens": 61683120} {"current_steps": 37765, "total_steps": 40000, "loss": 0.1232, "lr": 3.8451822355931313e-07, "epoch": 1.7096131646257273, "percentage": 94.41, "elapsed_time": "1 day, 6:54:26", "remaining_time": "1:49:44", "throughput": 554.45, "total_tokens": 61691376} {"current_steps": 37770, "total_steps": 40000, "loss": 0.12, "lr": 3.82804873476969e-07, "epoch": 1.70983951651237, "percentage": 94.42, "elapsed_time": "1 day, 6:54:29", "remaining_time": "1:49:29", "throughput": 554.5, "total_tokens": 61699216} {"current_steps": 37775, "total_steps": 40000, "loss": 0.1725, "lr": 3.810953196754702e-07, "epoch": 1.710065868399013, "percentage": 94.44, "elapsed_time": "1 day, 6:54:32", "remaining_time": "1:49:14", "throughput": 554.56, "total_tokens": 61707152} {"current_steps": 37780, "total_steps": 40000, "loss": 0.1663, "lr": 3.793895624184529e-07, "epoch": 1.710292220285656, "percentage": 94.45, "elapsed_time": "1 day, 6:54:35", "remaining_time": "1:48:58", "throughput": 554.61, "total_tokens": 61715056} {"current_steps": 37785, "total_steps": 40000, "loss": 0.1403, "lr": 3.776876019689679e-07, "epoch": 1.710518572172299, "percentage": 94.46, "elapsed_time": "1 day, 6:54:39", "remaining_time": "1:48:43", "throughput": 554.67, "total_tokens": 61723216} {"current_steps": 37790, "total_steps": 40000, "loss": 0.104, "lr": 3.7598943858947743e-07, "epoch": 1.710744924058942, "percentage": 94.47, "elapsed_time": "1 day, 6:54:42", "remaining_time": "1:48:27", "throughput": 554.73, "total_tokens": 61731632} {"current_steps": 37795, "total_steps": 40000, "loss": 0.1258, "lr": 3.742950725418637e-07, "epoch": 1.7109712759455848, "percentage": 94.49, "elapsed_time": "1 day, 6:54:45", "remaining_time": "1:48:12", "throughput": 554.79, "total_tokens": 61739472} {"current_steps": 37800, "total_steps": 40000, "loss": 0.1033, "lr": 3.726045040874093e-07, "epoch": 1.7111976278322278, "percentage": 94.5, "elapsed_time": "1 day, 6:54:48", "remaining_time": "1:47:57", "throughput": 554.84, "total_tokens": 61747120} {"current_steps": 37800, "total_steps": 40000, "eval_loss": 0.12196214497089386, "epoch": 1.7111976278322278, "percentage": 94.5, "elapsed_time": "1 day, 7:02:31", "remaining_time": "1:48:24", "throughput": 552.54, "total_tokens": 61747120} {"current_steps": 37805, "total_steps": 40000, "loss": 0.0776, "lr": 3.709177334868308e-07, "epoch": 1.7114239797188708, "percentage": 94.51, "elapsed_time": "1 day, 7:02:35", "remaining_time": "1:48:08", "throughput": 552.59, "total_tokens": 61755152} {"current_steps": 37810, "total_steps": 40000, "loss": 0.1303, "lr": 3.692347610002478e-07, "epoch": 1.7116503316055138, "percentage": 94.53, "elapsed_time": "1 day, 7:02:38", "remaining_time": "1:47:53", "throughput": 552.65, "total_tokens": 61763152} {"current_steps": 37815, "total_steps": 40000, "loss": 0.1143, "lr": 3.675555868871916e-07, "epoch": 1.7118766834921568, "percentage": 94.54, "elapsed_time": "1 day, 7:02:41", "remaining_time": "1:47:37", "throughput": 552.71, "total_tokens": 61771280} {"current_steps": 37820, "total_steps": 40000, "loss": 0.1571, "lr": 3.658802114066162e-07, "epoch": 1.7121030353787998, "percentage": 94.55, "elapsed_time": "1 day, 7:02:44", "remaining_time": "1:47:22", "throughput": 552.76, "total_tokens": 61779152} {"current_steps": 37825, "total_steps": 40000, "loss": 0.122, "lr": 3.6420863481688437e-07, "epoch": 1.7123293872654428, "percentage": 94.56, "elapsed_time": "1 day, 7:02:47", "remaining_time": "1:47:06", "throughput": 552.82, "total_tokens": 61787728} {"current_steps": 37830, "total_steps": 40000, "loss": 0.1032, "lr": 3.625408573757705e-07, "epoch": 1.7125557391520858, "percentage": 94.58, "elapsed_time": "1 day, 7:02:51", "remaining_time": "1:46:51", "throughput": 552.87, "total_tokens": 61795312} {"current_steps": 37835, "total_steps": 40000, "loss": 0.1181, "lr": 3.608768793404743e-07, "epoch": 1.7127820910387288, "percentage": 94.59, "elapsed_time": "1 day, 7:02:54", "remaining_time": "1:46:35", "throughput": 552.93, "total_tokens": 61803696} {"current_steps": 37840, "total_steps": 40000, "loss": 0.1426, "lr": 3.592167009675934e-07, "epoch": 1.7130084429253718, "percentage": 94.6, "elapsed_time": "1 day, 7:02:57", "remaining_time": "1:46:20", "throughput": 553.0, "total_tokens": 61812432} {"current_steps": 37845, "total_steps": 40000, "loss": 0.1382, "lr": 3.575603225131563e-07, "epoch": 1.7132347948120148, "percentage": 94.61, "elapsed_time": "1 day, 7:03:00", "remaining_time": "1:46:05", "throughput": 553.06, "total_tokens": 61821072} {"current_steps": 37850, "total_steps": 40000, "loss": 0.0996, "lr": 3.55907744232592e-07, "epoch": 1.7134611466986578, "percentage": 94.62, "elapsed_time": "1 day, 7:03:03", "remaining_time": "1:45:49", "throughput": 553.11, "total_tokens": 61828848} {"current_steps": 37855, "total_steps": 40000, "loss": 0.1064, "lr": 3.5425896638075217e-07, "epoch": 1.7136874985853008, "percentage": 94.64, "elapsed_time": "1 day, 7:03:07", "remaining_time": "1:45:34", "throughput": 553.17, "total_tokens": 61837744} {"current_steps": 37860, "total_steps": 40000, "loss": 0.1722, "lr": 3.5261398921189736e-07, "epoch": 1.7139138504719438, "percentage": 94.65, "elapsed_time": "1 day, 7:03:10", "remaining_time": "1:45:18", "throughput": 553.23, "total_tokens": 61846000} {"current_steps": 37865, "total_steps": 40000, "loss": 0.1006, "lr": 3.509728129797024e-07, "epoch": 1.7141402023585868, "percentage": 94.66, "elapsed_time": "1 day, 7:03:13", "remaining_time": "1:45:03", "throughput": 553.29, "total_tokens": 61854320} {"current_steps": 37870, "total_steps": 40000, "loss": 0.1747, "lr": 3.4933543793725656e-07, "epoch": 1.7143665542452298, "percentage": 94.67, "elapsed_time": "1 day, 7:03:16", "remaining_time": "1:44:48", "throughput": 553.35, "total_tokens": 61862480} {"current_steps": 37875, "total_steps": 40000, "loss": 0.1744, "lr": 3.4770186433707163e-07, "epoch": 1.7145929061318728, "percentage": 94.69, "elapsed_time": "1 day, 7:03:19", "remaining_time": "1:44:32", "throughput": 553.4, "total_tokens": 61870032} {"current_steps": 37880, "total_steps": 40000, "loss": 0.1358, "lr": 3.4607209243105453e-07, "epoch": 1.7148192580185155, "percentage": 94.7, "elapsed_time": "1 day, 7:03:23", "remaining_time": "1:44:17", "throughput": 553.46, "total_tokens": 61878448} {"current_steps": 37885, "total_steps": 40000, "loss": 0.1528, "lr": 3.444461224705431e-07, "epoch": 1.7150456099051585, "percentage": 94.71, "elapsed_time": "1 day, 7:03:26", "remaining_time": "1:44:01", "throughput": 553.52, "total_tokens": 61886544} {"current_steps": 37890, "total_steps": 40000, "loss": 0.1311, "lr": 3.4282395470628116e-07, "epoch": 1.7152719617918015, "percentage": 94.73, "elapsed_time": "1 day, 7:03:29", "remaining_time": "1:43:46", "throughput": 553.57, "total_tokens": 61894576} {"current_steps": 37895, "total_steps": 40000, "loss": 0.0721, "lr": 3.4120558938842417e-07, "epoch": 1.7154983136784445, "percentage": 94.74, "elapsed_time": "1 day, 7:03:32", "remaining_time": "1:43:30", "throughput": 553.63, "total_tokens": 61902640} {"current_steps": 37900, "total_steps": 40000, "loss": 0.1262, "lr": 3.395910267665503e-07, "epoch": 1.7157246655650875, "percentage": 94.75, "elapsed_time": "1 day, 7:03:35", "remaining_time": "1:43:15", "throughput": 553.68, "total_tokens": 61910576} {"current_steps": 37905, "total_steps": 40000, "loss": 0.0752, "lr": 3.3798026708964094e-07, "epoch": 1.7159510174517305, "percentage": 94.76, "elapsed_time": "1 day, 7:03:38", "remaining_time": "1:43:00", "throughput": 553.74, "total_tokens": 61918288} {"current_steps": 37910, "total_steps": 40000, "loss": 0.1138, "lr": 3.3637331060609456e-07, "epoch": 1.7161773693383733, "percentage": 94.77, "elapsed_time": "1 day, 7:03:42", "remaining_time": "1:42:44", "throughput": 553.79, "total_tokens": 61926480} {"current_steps": 37915, "total_steps": 40000, "loss": 0.0771, "lr": 3.3477015756372966e-07, "epoch": 1.7164037212250163, "percentage": 94.79, "elapsed_time": "1 day, 7:03:45", "remaining_time": "1:42:29", "throughput": 553.85, "total_tokens": 61934512} {"current_steps": 37920, "total_steps": 40000, "loss": 0.0947, "lr": 3.3317080820976785e-07, "epoch": 1.7166300731116593, "percentage": 94.8, "elapsed_time": "1 day, 7:03:48", "remaining_time": "1:42:14", "throughput": 553.91, "total_tokens": 61942672} {"current_steps": 37925, "total_steps": 40000, "loss": 0.1117, "lr": 3.315752627908508e-07, "epoch": 1.7168564249983023, "percentage": 94.81, "elapsed_time": "1 day, 7:03:51", "remaining_time": "1:41:58", "throughput": 553.96, "total_tokens": 61950608} {"current_steps": 37930, "total_steps": 40000, "loss": 0.1117, "lr": 3.299835215530317e-07, "epoch": 1.7170827768849453, "percentage": 94.83, "elapsed_time": "1 day, 7:03:54", "remaining_time": "1:41:43", "throughput": 554.02, "total_tokens": 61958704} {"current_steps": 37935, "total_steps": 40000, "loss": 0.1434, "lr": 3.2839558474177245e-07, "epoch": 1.7173091287715883, "percentage": 94.84, "elapsed_time": "1 day, 7:03:57", "remaining_time": "1:41:27", "throughput": 554.08, "total_tokens": 61967632} {"current_steps": 37940, "total_steps": 40000, "loss": 0.1444, "lr": 3.2681145260196056e-07, "epoch": 1.7175354806582313, "percentage": 94.85, "elapsed_time": "1 day, 7:04:01", "remaining_time": "1:41:12", "throughput": 554.14, "total_tokens": 61975408} {"current_steps": 37945, "total_steps": 40000, "loss": 0.1109, "lr": 3.252311253778839e-07, "epoch": 1.7177618325448742, "percentage": 94.86, "elapsed_time": "1 day, 7:04:04", "remaining_time": "1:40:57", "throughput": 554.2, "total_tokens": 61984496} {"current_steps": 37950, "total_steps": 40000, "loss": 0.1007, "lr": 3.2365460331325034e-07, "epoch": 1.7179881844315172, "percentage": 94.88, "elapsed_time": "1 day, 7:04:07", "remaining_time": "1:40:41", "throughput": 554.26, "total_tokens": 61993104} {"current_steps": 37955, "total_steps": 40000, "loss": 0.1646, "lr": 3.2208188665117934e-07, "epoch": 1.7182145363181602, "percentage": 94.89, "elapsed_time": "1 day, 7:04:10", "remaining_time": "1:40:26", "throughput": 554.32, "total_tokens": 62001104} {"current_steps": 37960, "total_steps": 40000, "loss": 0.1695, "lr": 3.205129756342018e-07, "epoch": 1.7184408882048032, "percentage": 94.9, "elapsed_time": "1 day, 7:04:14", "remaining_time": "1:40:11", "throughput": 554.38, "total_tokens": 62009680} {"current_steps": 37965, "total_steps": 40000, "loss": 0.1486, "lr": 3.189478705042659e-07, "epoch": 1.7186672400914462, "percentage": 94.91, "elapsed_time": "1 day, 7:04:17", "remaining_time": "1:39:55", "throughput": 554.44, "total_tokens": 62018224} {"current_steps": 37970, "total_steps": 40000, "loss": 0.1218, "lr": 3.173865715027341e-07, "epoch": 1.7188935919780892, "percentage": 94.92, "elapsed_time": "1 day, 7:04:20", "remaining_time": "1:39:40", "throughput": 554.49, "total_tokens": 62025808} {"current_steps": 37975, "total_steps": 40000, "loss": 0.0635, "lr": 3.158290788703694e-07, "epoch": 1.7191199438647322, "percentage": 94.94, "elapsed_time": "1 day, 7:04:23", "remaining_time": "1:39:25", "throughput": 554.55, "total_tokens": 62033616} {"current_steps": 37980, "total_steps": 40000, "loss": 0.131, "lr": 3.1427539284736297e-07, "epoch": 1.7193462957513752, "percentage": 94.95, "elapsed_time": "1 day, 7:04:26", "remaining_time": "1:39:09", "throughput": 554.6, "total_tokens": 62041328} {"current_steps": 37985, "total_steps": 40000, "loss": 0.0996, "lr": 3.127255136733093e-07, "epoch": 1.7195726476380182, "percentage": 94.96, "elapsed_time": "1 day, 7:04:29", "remaining_time": "1:38:54", "throughput": 554.66, "total_tokens": 62049680} {"current_steps": 37990, "total_steps": 40000, "loss": 0.1017, "lr": 3.1117944158722544e-07, "epoch": 1.7197989995246612, "percentage": 94.97, "elapsed_time": "1 day, 7:04:32", "remaining_time": "1:38:39", "throughput": 554.71, "total_tokens": 62057520} {"current_steps": 37995, "total_steps": 40000, "loss": 0.1477, "lr": 3.0963717682752635e-07, "epoch": 1.720025351411304, "percentage": 94.99, "elapsed_time": "1 day, 7:04:36", "remaining_time": "1:38:23", "throughput": 554.77, "total_tokens": 62065424} {"current_steps": 38000, "total_steps": 40000, "loss": 0.1151, "lr": 3.080987196320578e-07, "epoch": 1.720251703297947, "percentage": 95.0, "elapsed_time": "1 day, 7:04:39", "remaining_time": "1:38:08", "throughput": 554.82, "total_tokens": 62073424} {"current_steps": 38000, "total_steps": 40000, "eval_loss": 0.12195879966020584, "epoch": 1.720251703297947, "percentage": 95.0, "elapsed_time": "1 day, 7:12:21", "remaining_time": "1:38:32", "throughput": 552.54, "total_tokens": 62073424} {"current_steps": 38005, "total_steps": 40000, "loss": 0.129, "lr": 3.065640702380607e-07, "epoch": 1.72047805518459, "percentage": 95.01, "elapsed_time": "1 day, 7:12:25", "remaining_time": "1:38:17", "throughput": 552.59, "total_tokens": 62081616} {"current_steps": 38010, "total_steps": 40000, "loss": 0.0972, "lr": 3.050332288822011e-07, "epoch": 1.720704407071233, "percentage": 95.03, "elapsed_time": "1 day, 7:12:29", "remaining_time": "1:38:01", "throughput": 552.65, "total_tokens": 62089456} {"current_steps": 38015, "total_steps": 40000, "loss": 0.1185, "lr": 3.035061958005542e-07, "epoch": 1.720930758957876, "percentage": 95.04, "elapsed_time": "1 day, 7:12:32", "remaining_time": "1:37:46", "throughput": 552.71, "total_tokens": 62098704} {"current_steps": 38020, "total_steps": 40000, "loss": 0.1014, "lr": 3.019829712286093e-07, "epoch": 1.7211571108445187, "percentage": 95.05, "elapsed_time": "1 day, 7:12:35", "remaining_time": "1:37:31", "throughput": 552.77, "total_tokens": 62107216} {"current_steps": 38025, "total_steps": 40000, "loss": 0.0708, "lr": 3.004635554012647e-07, "epoch": 1.7213834627311617, "percentage": 95.06, "elapsed_time": "1 day, 7:12:38", "remaining_time": "1:37:15", "throughput": 552.83, "total_tokens": 62115568} {"current_steps": 38030, "total_steps": 40000, "loss": 0.1157, "lr": 2.9894794855283017e-07, "epoch": 1.7216098146178047, "percentage": 95.08, "elapsed_time": "1 day, 7:12:42", "remaining_time": "1:37:00", "throughput": 552.89, "total_tokens": 62123664} {"current_steps": 38035, "total_steps": 40000, "loss": 0.0895, "lr": 2.9743615091703816e-07, "epoch": 1.7218361665044477, "percentage": 95.09, "elapsed_time": "1 day, 7:12:45", "remaining_time": "1:36:45", "throughput": 552.94, "total_tokens": 62131792} {"current_steps": 38040, "total_steps": 40000, "loss": 0.1119, "lr": 2.959281627270216e-07, "epoch": 1.7220625183910907, "percentage": 95.1, "elapsed_time": "1 day, 7:12:48", "remaining_time": "1:36:29", "throughput": 553.0, "total_tokens": 62139664} {"current_steps": 38045, "total_steps": 40000, "loss": 0.0902, "lr": 2.944239842153362e-07, "epoch": 1.7222888702777337, "percentage": 95.11, "elapsed_time": "1 day, 7:12:51", "remaining_time": "1:36:14", "throughput": 553.06, "total_tokens": 62148144} {"current_steps": 38050, "total_steps": 40000, "loss": 0.1014, "lr": 2.929236156139381e-07, "epoch": 1.7225152221643767, "percentage": 95.12, "elapsed_time": "1 day, 7:12:54", "remaining_time": "1:35:59", "throughput": 553.12, "total_tokens": 62156624} {"current_steps": 38055, "total_steps": 40000, "loss": 0.1357, "lr": 2.9142705715420883e-07, "epoch": 1.7227415740510197, "percentage": 95.14, "elapsed_time": "1 day, 7:12:58", "remaining_time": "1:35:43", "throughput": 553.18, "total_tokens": 62164976} {"current_steps": 38060, "total_steps": 40000, "loss": 0.1435, "lr": 2.8993430906693595e-07, "epoch": 1.7229679259376627, "percentage": 95.15, "elapsed_time": "1 day, 7:13:01", "remaining_time": "1:35:28", "throughput": 553.23, "total_tokens": 62173232} {"current_steps": 38065, "total_steps": 40000, "loss": 0.1409, "lr": 2.88445371582316e-07, "epoch": 1.7231942778243057, "percentage": 95.16, "elapsed_time": "1 day, 7:13:04", "remaining_time": "1:35:12", "throughput": 553.29, "total_tokens": 62181232} {"current_steps": 38070, "total_steps": 40000, "loss": 0.0933, "lr": 2.8696024492996796e-07, "epoch": 1.7234206297109487, "percentage": 95.17, "elapsed_time": "1 day, 7:13:07", "remaining_time": "1:34:57", "throughput": 553.35, "total_tokens": 62189296} {"current_steps": 38075, "total_steps": 40000, "loss": 0.1143, "lr": 2.854789293389115e-07, "epoch": 1.7236469815975917, "percentage": 95.19, "elapsed_time": "1 day, 7:13:10", "remaining_time": "1:34:42", "throughput": 553.4, "total_tokens": 62197584} {"current_steps": 38080, "total_steps": 40000, "loss": 0.1439, "lr": 2.8400142503758606e-07, "epoch": 1.7238733334842347, "percentage": 95.2, "elapsed_time": "1 day, 7:13:14", "remaining_time": "1:34:26", "throughput": 553.46, "total_tokens": 62206064} {"current_steps": 38085, "total_steps": 40000, "loss": 0.1063, "lr": 2.8252773225384276e-07, "epoch": 1.7240996853708777, "percentage": 95.21, "elapsed_time": "1 day, 7:13:17", "remaining_time": "1:34:11", "throughput": 553.52, "total_tokens": 62214256} {"current_steps": 38090, "total_steps": 40000, "loss": 0.1122, "lr": 2.8105785121494143e-07, "epoch": 1.7243260372575206, "percentage": 95.23, "elapsed_time": "1 day, 7:13:20", "remaining_time": "1:33:56", "throughput": 553.57, "total_tokens": 62221872} {"current_steps": 38095, "total_steps": 40000, "loss": 0.1258, "lr": 2.795917821475563e-07, "epoch": 1.7245523891441636, "percentage": 95.24, "elapsed_time": "1 day, 7:13:23", "remaining_time": "1:33:40", "throughput": 553.63, "total_tokens": 62229840} {"current_steps": 38100, "total_steps": 40000, "loss": 0.1192, "lr": 2.78129525277776e-07, "epoch": 1.7247787410308066, "percentage": 95.25, "elapsed_time": "1 day, 7:13:26", "remaining_time": "1:33:25", "throughput": 553.69, "total_tokens": 62238800} {"current_steps": 38105, "total_steps": 40000, "loss": 0.0993, "lr": 2.766710808310952e-07, "epoch": 1.7250050929174494, "percentage": 95.26, "elapsed_time": "1 day, 7:13:30", "remaining_time": "1:33:10", "throughput": 553.75, "total_tokens": 62247504} {"current_steps": 38110, "total_steps": 40000, "loss": 0.1085, "lr": 2.7521644903242827e-07, "epoch": 1.7252314448040924, "percentage": 95.28, "elapsed_time": "1 day, 7:13:33", "remaining_time": "1:32:54", "throughput": 553.81, "total_tokens": 62255888} {"current_steps": 38115, "total_steps": 40000, "loss": 0.1321, "lr": 2.7376563010609593e-07, "epoch": 1.7254577966907354, "percentage": 95.29, "elapsed_time": "1 day, 7:13:36", "remaining_time": "1:32:39", "throughput": 553.87, "total_tokens": 62263760} {"current_steps": 38120, "total_steps": 40000, "loss": 0.1086, "lr": 2.72318624275833e-07, "epoch": 1.7256841485773784, "percentage": 95.3, "elapsed_time": "1 day, 7:13:39", "remaining_time": "1:32:24", "throughput": 553.92, "total_tokens": 62271472} {"current_steps": 38125, "total_steps": 40000, "loss": 0.1045, "lr": 2.7087543176478324e-07, "epoch": 1.7259105004640214, "percentage": 95.31, "elapsed_time": "1 day, 7:13:42", "remaining_time": "1:32:08", "throughput": 553.98, "total_tokens": 62279536} {"current_steps": 38130, "total_steps": 40000, "loss": 0.1286, "lr": 2.694360527955103e-07, "epoch": 1.7261368523506644, "percentage": 95.33, "elapsed_time": "1 day, 7:13:45", "remaining_time": "1:31:53", "throughput": 554.03, "total_tokens": 62287632} {"current_steps": 38135, "total_steps": 40000, "loss": 0.0925, "lr": 2.680004875899811e-07, "epoch": 1.7263632042373072, "percentage": 95.34, "elapsed_time": "1 day, 7:13:49", "remaining_time": "1:31:38", "throughput": 554.09, "total_tokens": 62296176} {"current_steps": 38140, "total_steps": 40000, "loss": 0.0911, "lr": 2.665687363695768e-07, "epoch": 1.7265895561239502, "percentage": 95.35, "elapsed_time": "1 day, 7:13:52", "remaining_time": "1:31:23", "throughput": 554.15, "total_tokens": 62304016} {"current_steps": 38145, "total_steps": 40000, "loss": 0.1845, "lr": 2.6514079935509584e-07, "epoch": 1.7268159080105931, "percentage": 95.36, "elapsed_time": "1 day, 7:13:55", "remaining_time": "1:31:07", "throughput": 554.21, "total_tokens": 62312688} {"current_steps": 38150, "total_steps": 40000, "loss": 0.1397, "lr": 2.6371667676673983e-07, "epoch": 1.7270422598972361, "percentage": 95.38, "elapsed_time": "1 day, 7:13:58", "remaining_time": "1:30:52", "throughput": 554.26, "total_tokens": 62320656} {"current_steps": 38155, "total_steps": 40000, "loss": 0.1207, "lr": 2.6229636882412755e-07, "epoch": 1.7272686117838791, "percentage": 95.39, "elapsed_time": "1 day, 7:14:01", "remaining_time": "1:30:37", "throughput": 554.32, "total_tokens": 62328368} {"current_steps": 38160, "total_steps": 40000, "loss": 0.1162, "lr": 2.6087987574628935e-07, "epoch": 1.7274949636705221, "percentage": 95.4, "elapsed_time": "1 day, 7:14:05", "remaining_time": "1:30:21", "throughput": 554.38, "total_tokens": 62336880} {"current_steps": 38165, "total_steps": 40000, "loss": 0.1174, "lr": 2.5946719775166437e-07, "epoch": 1.7277213155571651, "percentage": 95.41, "elapsed_time": "1 day, 7:14:08", "remaining_time": "1:30:06", "throughput": 554.44, "total_tokens": 62345456} {"current_steps": 38170, "total_steps": 40000, "loss": 0.083, "lr": 2.5805833505810616e-07, "epoch": 1.7279476674438081, "percentage": 95.43, "elapsed_time": "1 day, 7:14:11", "remaining_time": "1:29:51", "throughput": 554.49, "total_tokens": 62353648} {"current_steps": 38175, "total_steps": 40000, "loss": 0.1389, "lr": 2.566532878828798e-07, "epoch": 1.7281740193304511, "percentage": 95.44, "elapsed_time": "1 day, 7:14:14", "remaining_time": "1:29:36", "throughput": 554.55, "total_tokens": 62362320} {"current_steps": 38180, "total_steps": 40000, "loss": 0.1368, "lr": 2.552520564426619e-07, "epoch": 1.7284003712170941, "percentage": 95.45, "elapsed_time": "1 day, 7:14:17", "remaining_time": "1:29:20", "throughput": 554.61, "total_tokens": 62370160} {"current_steps": 38185, "total_steps": 40000, "loss": 0.1545, "lr": 2.5385464095353803e-07, "epoch": 1.728626723103737, "percentage": 95.46, "elapsed_time": "1 day, 7:14:21", "remaining_time": "1:29:05", "throughput": 554.66, "total_tokens": 62377968} {"current_steps": 38190, "total_steps": 40000, "loss": 0.097, "lr": 2.5246104163100804e-07, "epoch": 1.72885307499038, "percentage": 95.47, "elapsed_time": "1 day, 7:14:24", "remaining_time": "1:28:50", "throughput": 554.72, "total_tokens": 62386032} {"current_steps": 38195, "total_steps": 40000, "loss": 0.1598, "lr": 2.510712586899833e-07, "epoch": 1.729079426877023, "percentage": 95.49, "elapsed_time": "1 day, 7:14:27", "remaining_time": "1:28:34", "throughput": 554.77, "total_tokens": 62393584} {"current_steps": 38200, "total_steps": 40000, "loss": 0.122, "lr": 2.4968529234478124e-07, "epoch": 1.729305778763666, "percentage": 95.5, "elapsed_time": "1 day, 7:14:30", "remaining_time": "1:28:19", "throughput": 554.83, "total_tokens": 62401776} {"current_steps": 38200, "total_steps": 40000, "eval_loss": 0.1220889464020729, "epoch": 1.729305778763666, "percentage": 95.5, "elapsed_time": "1 day, 7:22:13", "remaining_time": "1:28:41", "throughput": 552.55, "total_tokens": 62401776} {"current_steps": 38205, "total_steps": 40000, "loss": 0.0649, "lr": 2.483031428091448e-07, "epoch": 1.729532130650309, "percentage": 95.51, "elapsed_time": "1 day, 7:22:18", "remaining_time": "1:28:26", "throughput": 552.6, "total_tokens": 62409616} {"current_steps": 38210, "total_steps": 40000, "loss": 0.1076, "lr": 2.469248102962091e-07, "epoch": 1.729758482536952, "percentage": 95.53, "elapsed_time": "1 day, 7:22:21", "remaining_time": "1:28:10", "throughput": 552.65, "total_tokens": 62417168} {"current_steps": 38215, "total_steps": 40000, "loss": 0.1164, "lr": 2.4555029501853455e-07, "epoch": 1.729984834423595, "percentage": 95.54, "elapsed_time": "1 day, 7:22:24", "remaining_time": "1:27:55", "throughput": 552.7, "total_tokens": 62425136} {"current_steps": 38220, "total_steps": 40000, "loss": 0.1357, "lr": 2.441795971880906e-07, "epoch": 1.7302111863102378, "percentage": 95.55, "elapsed_time": "1 day, 7:22:28", "remaining_time": "1:27:40", "throughput": 552.76, "total_tokens": 62433616} {"current_steps": 38225, "total_steps": 40000, "loss": 0.0761, "lr": 2.4281271701625255e-07, "epoch": 1.7304375381968808, "percentage": 95.56, "elapsed_time": "1 day, 7:22:31", "remaining_time": "1:27:24", "throughput": 552.82, "total_tokens": 62442320} {"current_steps": 38230, "total_steps": 40000, "loss": 0.1125, "lr": 2.4144965471381007e-07, "epoch": 1.7306638900835238, "percentage": 95.58, "elapsed_time": "1 day, 7:22:34", "remaining_time": "1:27:09", "throughput": 552.88, "total_tokens": 62450416} {"current_steps": 38235, "total_steps": 40000, "loss": 0.1259, "lr": 2.400904104909674e-07, "epoch": 1.7308902419701668, "percentage": 95.59, "elapsed_time": "1 day, 7:22:37", "remaining_time": "1:26:54", "throughput": 552.94, "total_tokens": 62459344} {"current_steps": 38240, "total_steps": 40000, "loss": 0.151, "lr": 2.3873498455733725e-07, "epoch": 1.7311165938568098, "percentage": 95.6, "elapsed_time": "1 day, 7:22:41", "remaining_time": "1:26:39", "throughput": 553.0, "total_tokens": 62467760} {"current_steps": 38245, "total_steps": 40000, "loss": 0.1095, "lr": 2.3738337712194137e-07, "epoch": 1.7313429457434528, "percentage": 95.61, "elapsed_time": "1 day, 7:22:44", "remaining_time": "1:26:23", "throughput": 553.06, "total_tokens": 62475696} {"current_steps": 38250, "total_steps": 40000, "loss": 0.141, "lr": 2.3603558839321305e-07, "epoch": 1.7315692976300956, "percentage": 95.62, "elapsed_time": "1 day, 7:22:47", "remaining_time": "1:26:08", "throughput": 553.12, "total_tokens": 62484336} {"current_steps": 38255, "total_steps": 40000, "loss": 0.1826, "lr": 2.3469161857900267e-07, "epoch": 1.7317956495167386, "percentage": 95.64, "elapsed_time": "1 day, 7:22:50", "remaining_time": "1:25:53", "throughput": 553.17, "total_tokens": 62491888} {"current_steps": 38260, "total_steps": 40000, "loss": 0.1197, "lr": 2.3335146788656393e-07, "epoch": 1.7320220014033816, "percentage": 95.65, "elapsed_time": "1 day, 7:22:53", "remaining_time": "1:25:37", "throughput": 553.22, "total_tokens": 62499280} {"current_steps": 38265, "total_steps": 40000, "loss": 0.1222, "lr": 2.3201513652256757e-07, "epoch": 1.7322483532900246, "percentage": 95.66, "elapsed_time": "1 day, 7:22:57", "remaining_time": "1:25:22", "throughput": 553.28, "total_tokens": 62507824} {"current_steps": 38270, "total_steps": 40000, "loss": 0.1086, "lr": 2.3068262469308766e-07, "epoch": 1.7324747051766676, "percentage": 95.67, "elapsed_time": "1 day, 7:23:00", "remaining_time": "1:25:07", "throughput": 553.34, "total_tokens": 62516144} {"current_steps": 38275, "total_steps": 40000, "loss": 0.1021, "lr": 2.2935393260362093e-07, "epoch": 1.7327010570633106, "percentage": 95.69, "elapsed_time": "1 day, 7:23:03", "remaining_time": "1:24:52", "throughput": 553.39, "total_tokens": 62524176} {"current_steps": 38280, "total_steps": 40000, "loss": 0.0825, "lr": 2.2802906045906458e-07, "epoch": 1.7329274089499536, "percentage": 95.7, "elapsed_time": "1 day, 7:23:06", "remaining_time": "1:24:36", "throughput": 553.45, "total_tokens": 62532176} {"current_steps": 38285, "total_steps": 40000, "loss": 0.1146, "lr": 2.2670800846373018e-07, "epoch": 1.7331537608365966, "percentage": 95.71, "elapsed_time": "1 day, 7:23:09", "remaining_time": "1:24:21", "throughput": 553.51, "total_tokens": 62540528} {"current_steps": 38290, "total_steps": 40000, "loss": 0.152, "lr": 2.2539077682134367e-07, "epoch": 1.7333801127232396, "percentage": 95.73, "elapsed_time": "1 day, 7:23:13", "remaining_time": "1:24:06", "throughput": 553.56, "total_tokens": 62548848} {"current_steps": 38295, "total_steps": 40000, "loss": 0.133, "lr": 2.2407736573503423e-07, "epoch": 1.7336064646098825, "percentage": 95.74, "elapsed_time": "1 day, 7:23:16", "remaining_time": "1:23:50", "throughput": 553.62, "total_tokens": 62557264} {"current_steps": 38300, "total_steps": 40000, "loss": 0.1573, "lr": 2.2276777540735093e-07, "epoch": 1.7338328164965255, "percentage": 95.75, "elapsed_time": "1 day, 7:23:19", "remaining_time": "1:23:35", "throughput": 553.68, "total_tokens": 62565648} {"current_steps": 38305, "total_steps": 40000, "loss": 0.1031, "lr": 2.2146200604024613e-07, "epoch": 1.7340591683831685, "percentage": 95.76, "elapsed_time": "1 day, 7:23:22", "remaining_time": "1:23:20", "throughput": 553.74, "total_tokens": 62574064} {"current_steps": 38310, "total_steps": 40000, "loss": 0.1145, "lr": 2.2016005783508375e-07, "epoch": 1.7342855202698115, "percentage": 95.78, "elapsed_time": "1 day, 7:23:25", "remaining_time": "1:23:05", "throughput": 553.79, "total_tokens": 62582064} {"current_steps": 38315, "total_steps": 40000, "loss": 0.1205, "lr": 2.1886193099264763e-07, "epoch": 1.7345118721564545, "percentage": 95.79, "elapsed_time": "1 day, 7:23:29", "remaining_time": "1:22:49", "throughput": 553.86, "total_tokens": 62590896} {"current_steps": 38320, "total_steps": 40000, "loss": 0.1271, "lr": 2.175676257131165e-07, "epoch": 1.7347382240430975, "percentage": 95.8, "elapsed_time": "1 day, 7:23:32", "remaining_time": "1:22:34", "throughput": 553.91, "total_tokens": 62598672} {"current_steps": 38325, "total_steps": 40000, "loss": 0.1388, "lr": 2.162771421960974e-07, "epoch": 1.7349645759297405, "percentage": 95.81, "elapsed_time": "1 day, 7:23:35", "remaining_time": "1:22:19", "throughput": 553.97, "total_tokens": 62606800} {"current_steps": 38330, "total_steps": 40000, "loss": 0.1117, "lr": 2.1499048064059224e-07, "epoch": 1.7351909278163835, "percentage": 95.83, "elapsed_time": "1 day, 7:23:38", "remaining_time": "1:22:04", "throughput": 554.03, "total_tokens": 62615280} {"current_steps": 38335, "total_steps": 40000, "loss": 0.1163, "lr": 2.1370764124502285e-07, "epoch": 1.7354172797030263, "percentage": 95.84, "elapsed_time": "1 day, 7:23:41", "remaining_time": "1:21:48", "throughput": 554.08, "total_tokens": 62622864} {"current_steps": 38340, "total_steps": 40000, "loss": 0.079, "lr": 2.1242862420721988e-07, "epoch": 1.7356436315896693, "percentage": 95.85, "elapsed_time": "1 day, 7:23:44", "remaining_time": "1:21:33", "throughput": 554.13, "total_tokens": 62630480} {"current_steps": 38345, "total_steps": 40000, "loss": 0.0687, "lr": 2.1115342972442276e-07, "epoch": 1.7358699834763123, "percentage": 95.86, "elapsed_time": "1 day, 7:23:48", "remaining_time": "1:21:18", "throughput": 554.19, "total_tokens": 62638512} {"current_steps": 38350, "total_steps": 40000, "loss": 0.1074, "lr": 2.0988205799328252e-07, "epoch": 1.7360963353629553, "percentage": 95.88, "elapsed_time": "1 day, 7:23:51", "remaining_time": "1:21:03", "throughput": 554.24, "total_tokens": 62646832} {"current_steps": 38355, "total_steps": 40000, "loss": 0.1841, "lr": 2.0861450920986182e-07, "epoch": 1.7363226872495983, "percentage": 95.89, "elapsed_time": "1 day, 7:23:54", "remaining_time": "1:20:47", "throughput": 554.3, "total_tokens": 62655344} {"current_steps": 38360, "total_steps": 40000, "loss": 0.1439, "lr": 2.07350783569632e-07, "epoch": 1.736549039136241, "percentage": 95.9, "elapsed_time": "1 day, 7:23:57", "remaining_time": "1:20:32", "throughput": 554.36, "total_tokens": 62663056} {"current_steps": 38365, "total_steps": 40000, "loss": 0.139, "lr": 2.060908812674761e-07, "epoch": 1.736775391022884, "percentage": 95.91, "elapsed_time": "1 day, 7:24:00", "remaining_time": "1:20:17", "throughput": 554.41, "total_tokens": 62671088} {"current_steps": 38370, "total_steps": 40000, "loss": 0.1033, "lr": 2.0483480249768317e-07, "epoch": 1.737001742909527, "percentage": 95.93, "elapsed_time": "1 day, 7:24:03", "remaining_time": "1:20:02", "throughput": 554.47, "total_tokens": 62679280} {"current_steps": 38375, "total_steps": 40000, "loss": 0.1314, "lr": 2.035825474539621e-07, "epoch": 1.73722809479617, "percentage": 95.94, "elapsed_time": "1 day, 7:24:07", "remaining_time": "1:19:47", "throughput": 554.52, "total_tokens": 62686928} {"current_steps": 38380, "total_steps": 40000, "loss": 0.1075, "lr": 2.0233411632942235e-07, "epoch": 1.737454446682813, "percentage": 95.95, "elapsed_time": "1 day, 7:24:10", "remaining_time": "1:19:31", "throughput": 554.58, "total_tokens": 62695024} {"current_steps": 38385, "total_steps": 40000, "loss": 0.1401, "lr": 2.0108950931658764e-07, "epoch": 1.737680798569456, "percentage": 95.96, "elapsed_time": "1 day, 7:24:13", "remaining_time": "1:19:16", "throughput": 554.63, "total_tokens": 62703024} {"current_steps": 38390, "total_steps": 40000, "loss": 0.1318, "lr": 1.998487266073934e-07, "epoch": 1.737907150456099, "percentage": 95.97, "elapsed_time": "1 day, 7:24:16", "remaining_time": "1:19:01", "throughput": 554.69, "total_tokens": 62710992} {"current_steps": 38395, "total_steps": 40000, "loss": 0.1624, "lr": 1.986117683931865e-07, "epoch": 1.738133502342742, "percentage": 95.99, "elapsed_time": "1 day, 7:24:19", "remaining_time": "1:18:46", "throughput": 554.74, "total_tokens": 62719056} {"current_steps": 38400, "total_steps": 40000, "loss": 0.0992, "lr": 1.9737863486471442e-07, "epoch": 1.738359854229385, "percentage": 96.0, "elapsed_time": "1 day, 7:24:22", "remaining_time": "1:18:30", "throughput": 554.8, "total_tokens": 62726928} {"current_steps": 38400, "total_steps": 40000, "eval_loss": 0.12194701284170151, "epoch": 1.738359854229385, "percentage": 96.0, "elapsed_time": "1 day, 7:32:05", "remaining_time": "1:18:50", "throughput": 552.54, "total_tokens": 62726928} {"current_steps": 38405, "total_steps": 40000, "loss": 0.1376, "lr": 1.9614932621215e-07, "epoch": 1.738586206116028, "percentage": 96.01, "elapsed_time": "1 day, 7:32:10", "remaining_time": "1:18:35", "throughput": 552.59, "total_tokens": 62735824} {"current_steps": 38410, "total_steps": 40000, "loss": 0.1559, "lr": 1.9492384262506102e-07, "epoch": 1.738812558002671, "percentage": 96.03, "elapsed_time": "1 day, 7:32:14", "remaining_time": "1:18:19", "throughput": 552.64, "total_tokens": 62743600} {"current_steps": 38415, "total_steps": 40000, "loss": 0.1165, "lr": 1.9370218429243524e-07, "epoch": 1.739038909889314, "percentage": 96.04, "elapsed_time": "1 day, 7:32:17", "remaining_time": "1:18:04", "throughput": 552.7, "total_tokens": 62751824} {"current_steps": 38420, "total_steps": 40000, "loss": 0.1521, "lr": 1.9248435140267197e-07, "epoch": 1.739265261775957, "percentage": 96.05, "elapsed_time": "1 day, 7:32:20", "remaining_time": "1:17:49", "throughput": 552.75, "total_tokens": 62759728} {"current_steps": 38425, "total_steps": 40000, "loss": 0.0755, "lr": 1.9127034414356814e-07, "epoch": 1.7394916136626, "percentage": 96.06, "elapsed_time": "1 day, 7:32:23", "remaining_time": "1:17:34", "throughput": 552.81, "total_tokens": 62767472} {"current_steps": 38430, "total_steps": 40000, "loss": 0.0942, "lr": 1.9006016270234627e-07, "epoch": 1.739717965549243, "percentage": 96.08, "elapsed_time": "1 day, 7:32:26", "remaining_time": "1:17:18", "throughput": 552.86, "total_tokens": 62775280} {"current_steps": 38435, "total_steps": 40000, "loss": 0.1245, "lr": 1.888538072656293e-07, "epoch": 1.739944317435886, "percentage": 96.09, "elapsed_time": "1 day, 7:32:29", "remaining_time": "1:17:03", "throughput": 552.92, "total_tokens": 62783824} {"current_steps": 38440, "total_steps": 40000, "loss": 0.0795, "lr": 1.8765127801944893e-07, "epoch": 1.740170669322529, "percentage": 96.1, "elapsed_time": "1 day, 7:32:32", "remaining_time": "1:16:48", "throughput": 552.97, "total_tokens": 62791472} {"current_steps": 38445, "total_steps": 40000, "loss": 0.1165, "lr": 1.8645257514925406e-07, "epoch": 1.7403970212091717, "percentage": 96.11, "elapsed_time": "1 day, 7:32:36", "remaining_time": "1:16:33", "throughput": 553.03, "total_tokens": 62800016} {"current_steps": 38450, "total_steps": 40000, "loss": 0.0973, "lr": 1.8525769883989685e-07, "epoch": 1.7406233730958147, "percentage": 96.12, "elapsed_time": "1 day, 7:32:39", "remaining_time": "1:16:17", "throughput": 553.08, "total_tokens": 62807216} {"current_steps": 38455, "total_steps": 40000, "loss": 0.1267, "lr": 1.8406664927564654e-07, "epoch": 1.7408497249824577, "percentage": 96.14, "elapsed_time": "1 day, 7:32:42", "remaining_time": "1:16:02", "throughput": 553.13, "total_tokens": 62814288} {"current_steps": 38460, "total_steps": 40000, "loss": 0.1604, "lr": 1.8287942664017566e-07, "epoch": 1.7410760768691007, "percentage": 96.15, "elapsed_time": "1 day, 7:32:45", "remaining_time": "1:15:47", "throughput": 553.18, "total_tokens": 62822384} {"current_steps": 38465, "total_steps": 40000, "loss": 0.0925, "lr": 1.8169603111656552e-07, "epoch": 1.7413024287557437, "percentage": 96.16, "elapsed_time": "1 day, 7:32:48", "remaining_time": "1:15:32", "throughput": 553.24, "total_tokens": 62830256} {"current_steps": 38470, "total_steps": 40000, "loss": 0.0943, "lr": 1.805164628873146e-07, "epoch": 1.7415287806423867, "percentage": 96.17, "elapsed_time": "1 day, 7:32:51", "remaining_time": "1:15:16", "throughput": 553.29, "total_tokens": 62838288} {"current_steps": 38475, "total_steps": 40000, "loss": 0.1253, "lr": 1.793407221343274e-07, "epoch": 1.7417551325290295, "percentage": 96.19, "elapsed_time": "1 day, 7:32:54", "remaining_time": "1:15:01", "throughput": 553.35, "total_tokens": 62846256} {"current_steps": 38480, "total_steps": 40000, "loss": 0.104, "lr": 1.781688090389172e-07, "epoch": 1.7419814844156725, "percentage": 96.2, "elapsed_time": "1 day, 7:32:58", "remaining_time": "1:14:46", "throughput": 553.41, "total_tokens": 62854928} {"current_steps": 38485, "total_steps": 40000, "loss": 0.1144, "lr": 1.770007237818061e-07, "epoch": 1.7422078363023155, "percentage": 96.21, "elapsed_time": "1 day, 7:33:01", "remaining_time": "1:14:31", "throughput": 553.46, "total_tokens": 62862992} {"current_steps": 38490, "total_steps": 40000, "loss": 0.0891, "lr": 1.7583646654313059e-07, "epoch": 1.7424341881889585, "percentage": 96.23, "elapsed_time": "1 day, 7:33:04", "remaining_time": "1:14:16", "throughput": 553.52, "total_tokens": 62870736} {"current_steps": 38495, "total_steps": 40000, "loss": 0.1015, "lr": 1.7467603750242757e-07, "epoch": 1.7426605400756014, "percentage": 96.24, "elapsed_time": "1 day, 7:33:07", "remaining_time": "1:14:00", "throughput": 553.57, "total_tokens": 62878256} {"current_steps": 38500, "total_steps": 40000, "loss": 0.1436, "lr": 1.7351943683865944e-07, "epoch": 1.7428868919622444, "percentage": 96.25, "elapsed_time": "1 day, 7:33:10", "remaining_time": "1:13:45", "throughput": 553.63, "total_tokens": 62886672} {"current_steps": 38505, "total_steps": 40000, "loss": 0.0734, "lr": 1.723666647301808e-07, "epoch": 1.7431132438488874, "percentage": 96.26, "elapsed_time": "1 day, 7:33:13", "remaining_time": "1:13:30", "throughput": 553.68, "total_tokens": 62894768} {"current_steps": 38510, "total_steps": 40000, "loss": 0.1419, "lr": 1.712177213547661e-07, "epoch": 1.7433395957355304, "percentage": 96.28, "elapsed_time": "1 day, 7:33:16", "remaining_time": "1:13:15", "throughput": 553.73, "total_tokens": 62902352} {"current_steps": 38515, "total_steps": 40000, "loss": 0.154, "lr": 1.7007260688959581e-07, "epoch": 1.7435659476221734, "percentage": 96.29, "elapsed_time": "1 day, 7:33:20", "remaining_time": "1:13:00", "throughput": 553.79, "total_tokens": 62911088} {"current_steps": 38520, "total_steps": 40000, "loss": 0.1287, "lr": 1.68931321511262e-07, "epoch": 1.7437922995088164, "percentage": 96.3, "elapsed_time": "1 day, 7:33:23", "remaining_time": "1:12:44", "throughput": 553.85, "total_tokens": 62919568} {"current_steps": 38525, "total_steps": 40000, "loss": 0.1153, "lr": 1.6779386539576835e-07, "epoch": 1.7440186513954594, "percentage": 96.31, "elapsed_time": "1 day, 7:33:26", "remaining_time": "1:12:29", "throughput": 553.91, "total_tokens": 62927664} {"current_steps": 38530, "total_steps": 40000, "loss": 0.126, "lr": 1.666602387185162e-07, "epoch": 1.7442450032821024, "percentage": 96.33, "elapsed_time": "1 day, 7:33:29", "remaining_time": "1:12:14", "throughput": 553.96, "total_tokens": 62935600} {"current_steps": 38535, "total_steps": 40000, "loss": 0.0869, "lr": 1.655304416543352e-07, "epoch": 1.7444713551687454, "percentage": 96.34, "elapsed_time": "1 day, 7:33:33", "remaining_time": "1:11:59", "throughput": 554.02, "total_tokens": 62943792} {"current_steps": 38540, "total_steps": 40000, "loss": 0.1135, "lr": 1.6440447437744698e-07, "epoch": 1.7446977070553884, "percentage": 96.35, "elapsed_time": "1 day, 7:33:36", "remaining_time": "1:11:44", "throughput": 554.07, "total_tokens": 62951600} {"current_steps": 38545, "total_steps": 40000, "loss": 0.1245, "lr": 1.6328233706149332e-07, "epoch": 1.7449240589420314, "percentage": 96.36, "elapsed_time": "1 day, 7:33:39", "remaining_time": "1:11:28", "throughput": 554.13, "total_tokens": 62959792} {"current_steps": 38550, "total_steps": 40000, "loss": 0.147, "lr": 1.6216402987951906e-07, "epoch": 1.7451504108286744, "percentage": 96.38, "elapsed_time": "1 day, 7:33:42", "remaining_time": "1:11:13", "throughput": 554.18, "total_tokens": 62967824} {"current_steps": 38555, "total_steps": 40000, "loss": 0.0828, "lr": 1.6104955300398627e-07, "epoch": 1.7453767627153174, "percentage": 96.39, "elapsed_time": "1 day, 7:33:45", "remaining_time": "1:10:58", "throughput": 554.24, "total_tokens": 62975920} {"current_steps": 38560, "total_steps": 40000, "loss": 0.1132, "lr": 1.5993890660675748e-07, "epoch": 1.7456031146019602, "percentage": 96.4, "elapsed_time": "1 day, 7:33:48", "remaining_time": "1:10:43", "throughput": 554.3, "total_tokens": 62983856} {"current_steps": 38565, "total_steps": 40000, "loss": 0.1135, "lr": 1.5883209085910678e-07, "epoch": 1.7458294664886032, "percentage": 96.41, "elapsed_time": "1 day, 7:33:51", "remaining_time": "1:10:28", "throughput": 554.36, "total_tokens": 62992464} {"current_steps": 38570, "total_steps": 40000, "loss": 0.1096, "lr": 1.5772910593172264e-07, "epoch": 1.7460558183752461, "percentage": 96.43, "elapsed_time": "1 day, 7:33:55", "remaining_time": "1:10:13", "throughput": 554.41, "total_tokens": 63000624} {"current_steps": 38575, "total_steps": 40000, "loss": 0.1619, "lr": 1.5662995199469954e-07, "epoch": 1.7462821702618891, "percentage": 96.44, "elapsed_time": "1 day, 7:33:58", "remaining_time": "1:09:57", "throughput": 554.46, "total_tokens": 63008336} {"current_steps": 38580, "total_steps": 40000, "loss": 0.0904, "lr": 1.5553462921753802e-07, "epoch": 1.7465085221485321, "percentage": 96.45, "elapsed_time": "1 day, 7:34:01", "remaining_time": "1:09:42", "throughput": 554.52, "total_tokens": 63016560} {"current_steps": 38585, "total_steps": 40000, "loss": 0.1474, "lr": 1.544431377691502e-07, "epoch": 1.7467348740351751, "percentage": 96.46, "elapsed_time": "1 day, 7:34:04", "remaining_time": "1:09:27", "throughput": 554.58, "total_tokens": 63024912} {"current_steps": 38590, "total_steps": 40000, "loss": 0.1089, "lr": 1.5335547781785975e-07, "epoch": 1.746961225921818, "percentage": 96.47, "elapsed_time": "1 day, 7:34:07", "remaining_time": "1:09:12", "throughput": 554.63, "total_tokens": 63032496} {"current_steps": 38595, "total_steps": 40000, "loss": 0.1316, "lr": 1.5227164953139917e-07, "epoch": 1.747187577808461, "percentage": 96.49, "elapsed_time": "1 day, 7:34:10", "remaining_time": "1:08:57", "throughput": 554.68, "total_tokens": 63040176} {"current_steps": 38600, "total_steps": 40000, "loss": 0.1577, "lr": 1.511916530769042e-07, "epoch": 1.747413929695104, "percentage": 96.5, "elapsed_time": "1 day, 7:34:13", "remaining_time": "1:08:42", "throughput": 554.74, "total_tokens": 63048080} {"current_steps": 38600, "total_steps": 40000, "eval_loss": 0.12212678790092468, "epoch": 1.747413929695104, "percentage": 96.5, "elapsed_time": "1 day, 7:41:56", "remaining_time": "1:08:58", "throughput": 552.49, "total_tokens": 63048080} {"current_steps": 38605, "total_steps": 40000, "loss": 0.1743, "lr": 1.5011548862092773e-07, "epoch": 1.747640281581747, "percentage": 96.51, "elapsed_time": "1 day, 7:42:00", "remaining_time": "1:08:43", "throughput": 552.54, "total_tokens": 63055760} {"current_steps": 38610, "total_steps": 40000, "loss": 0.1163, "lr": 1.490431563294231e-07, "epoch": 1.7478666334683899, "percentage": 96.53, "elapsed_time": "1 day, 7:42:03", "remaining_time": "1:08:28", "throughput": 552.58, "total_tokens": 63062992} {"current_steps": 38615, "total_steps": 40000, "loss": 0.0966, "lr": 1.4797465636776365e-07, "epoch": 1.7480929853550329, "percentage": 96.54, "elapsed_time": "1 day, 7:42:06", "remaining_time": "1:08:13", "throughput": 552.64, "total_tokens": 63071152} {"current_steps": 38620, "total_steps": 40000, "loss": 0.1325, "lr": 1.4690998890072027e-07, "epoch": 1.7483193372416759, "percentage": 96.55, "elapsed_time": "1 day, 7:42:10", "remaining_time": "1:07:58", "throughput": 552.7, "total_tokens": 63079184} {"current_steps": 38625, "total_steps": 40000, "loss": 0.1043, "lr": 1.4584915409248112e-07, "epoch": 1.7485456891283189, "percentage": 96.56, "elapsed_time": "1 day, 7:42:13", "remaining_time": "1:07:42", "throughput": 552.75, "total_tokens": 63087184} {"current_steps": 38630, "total_steps": 40000, "loss": 0.0996, "lr": 1.4479215210663754e-07, "epoch": 1.7487720410149619, "percentage": 96.58, "elapsed_time": "1 day, 7:42:16", "remaining_time": "1:07:27", "throughput": 552.8, "total_tokens": 63094544} {"current_steps": 38635, "total_steps": 40000, "loss": 0.082, "lr": 1.4373898310619528e-07, "epoch": 1.7489983929016049, "percentage": 96.59, "elapsed_time": "1 day, 7:42:19", "remaining_time": "1:07:12", "throughput": 552.86, "total_tokens": 63102544} {"current_steps": 38640, "total_steps": 40000, "loss": 0.1041, "lr": 1.4268964725356604e-07, "epoch": 1.7492247447882479, "percentage": 96.6, "elapsed_time": "1 day, 7:42:22", "remaining_time": "1:06:57", "throughput": 552.92, "total_tokens": 63111568} {"current_steps": 38645, "total_steps": 40000, "loss": 0.1211, "lr": 1.4164414471056764e-07, "epoch": 1.7494510966748908, "percentage": 96.61, "elapsed_time": "1 day, 7:42:25", "remaining_time": "1:06:42", "throughput": 552.97, "total_tokens": 63119824} {"current_steps": 38650, "total_steps": 40000, "loss": 0.1723, "lr": 1.4060247563843497e-07, "epoch": 1.7496774485615338, "percentage": 96.62, "elapsed_time": "1 day, 7:42:29", "remaining_time": "1:06:27", "throughput": 553.03, "total_tokens": 63127856} {"current_steps": 38655, "total_steps": 40000, "loss": 0.0768, "lr": 1.3956464019780068e-07, "epoch": 1.7499038004481768, "percentage": 96.64, "elapsed_time": "1 day, 7:42:32", "remaining_time": "1:06:11", "throughput": 553.09, "total_tokens": 63135984} {"current_steps": 38660, "total_steps": 40000, "loss": 0.1265, "lr": 1.385306385487145e-07, "epoch": 1.7501301523348198, "percentage": 96.65, "elapsed_time": "1 day, 7:42:35", "remaining_time": "1:05:56", "throughput": 553.14, "total_tokens": 63144208} {"current_steps": 38665, "total_steps": 40000, "loss": 0.0924, "lr": 1.3750047085063222e-07, "epoch": 1.7503565042214628, "percentage": 96.66, "elapsed_time": "1 day, 7:42:38", "remaining_time": "1:05:41", "throughput": 553.19, "total_tokens": 63151600} {"current_steps": 38670, "total_steps": 40000, "loss": 0.1127, "lr": 1.3647413726242119e-07, "epoch": 1.7505828561081058, "percentage": 96.67, "elapsed_time": "1 day, 7:42:41", "remaining_time": "1:05:26", "throughput": 553.25, "total_tokens": 63159440} {"current_steps": 38675, "total_steps": 40000, "loss": 0.0927, "lr": 1.3545163794235205e-07, "epoch": 1.7508092079947486, "percentage": 96.69, "elapsed_time": "1 day, 7:42:44", "remaining_time": "1:05:11", "throughput": 553.3, "total_tokens": 63167600} {"current_steps": 38680, "total_steps": 40000, "loss": 0.0852, "lr": 1.3443297304810698e-07, "epoch": 1.7510355598813916, "percentage": 96.7, "elapsed_time": "1 day, 7:42:47", "remaining_time": "1:04:56", "throughput": 553.35, "total_tokens": 63175088} {"current_steps": 38685, "total_steps": 40000, "loss": 0.1255, "lr": 1.3341814273677977e-07, "epoch": 1.7512619117680346, "percentage": 96.71, "elapsed_time": "1 day, 7:42:51", "remaining_time": "1:04:40", "throughput": 553.41, "total_tokens": 63183152} {"current_steps": 38690, "total_steps": 40000, "loss": 0.0994, "lr": 1.324071471648647e-07, "epoch": 1.7514882636546776, "percentage": 96.73, "elapsed_time": "1 day, 7:42:54", "remaining_time": "1:04:25", "throughput": 553.47, "total_tokens": 63192080} {"current_steps": 38695, "total_steps": 40000, "loss": 0.1366, "lr": 1.3139998648827312e-07, "epoch": 1.7517146155413206, "percentage": 96.74, "elapsed_time": "1 day, 7:42:57", "remaining_time": "1:04:10", "throughput": 553.52, "total_tokens": 63199632} {"current_steps": 38700, "total_steps": 40000, "loss": 0.091, "lr": 1.3039666086232526e-07, "epoch": 1.7519409674279633, "percentage": 96.75, "elapsed_time": "1 day, 7:43:00", "remaining_time": "1:03:55", "throughput": 553.57, "total_tokens": 63207472} {"current_steps": 38705, "total_steps": 40000, "loss": 0.1392, "lr": 1.2939717044174183e-07, "epoch": 1.7521673193146063, "percentage": 96.76, "elapsed_time": "1 day, 7:43:03", "remaining_time": "1:03:40", "throughput": 553.63, "total_tokens": 63215504} {"current_steps": 38710, "total_steps": 40000, "loss": 0.0863, "lr": 1.284015153806578e-07, "epoch": 1.7523936712012493, "percentage": 96.78, "elapsed_time": "1 day, 7:43:06", "remaining_time": "1:03:25", "throughput": 553.68, "total_tokens": 63223184} {"current_steps": 38715, "total_steps": 40000, "loss": 0.1246, "lr": 1.274096958326171e-07, "epoch": 1.7526200230878923, "percentage": 96.79, "elapsed_time": "1 day, 7:43:09", "remaining_time": "1:03:10", "throughput": 553.74, "total_tokens": 63231088} {"current_steps": 38720, "total_steps": 40000, "loss": 0.1415, "lr": 1.2642171195056952e-07, "epoch": 1.7528463749745353, "percentage": 96.8, "elapsed_time": "1 day, 7:43:13", "remaining_time": "1:02:54", "throughput": 553.79, "total_tokens": 63239184} {"current_steps": 38725, "total_steps": 40000, "loss": 0.1407, "lr": 1.2543756388687377e-07, "epoch": 1.7530727268611783, "percentage": 96.81, "elapsed_time": "1 day, 7:43:16", "remaining_time": "1:02:39", "throughput": 553.85, "total_tokens": 63247760} {"current_steps": 38730, "total_steps": 40000, "loss": 0.1267, "lr": 1.2445725179330014e-07, "epoch": 1.7532990787478213, "percentage": 96.83, "elapsed_time": "1 day, 7:43:19", "remaining_time": "1:02:24", "throughput": 553.91, "total_tokens": 63255792} {"current_steps": 38735, "total_steps": 40000, "loss": 0.0773, "lr": 1.2348077582102212e-07, "epoch": 1.7535254306344643, "percentage": 96.84, "elapsed_time": "1 day, 7:43:22", "remaining_time": "1:02:09", "throughput": 553.96, "total_tokens": 63263696} {"current_steps": 38740, "total_steps": 40000, "loss": 0.0913, "lr": 1.2250813612062762e-07, "epoch": 1.7537517825211073, "percentage": 96.85, "elapsed_time": "1 day, 7:43:25", "remaining_time": "1:01:54", "throughput": 554.02, "total_tokens": 63271888} {"current_steps": 38745, "total_steps": 40000, "loss": 0.1064, "lr": 1.215393328421105e-07, "epoch": 1.7539781344077503, "percentage": 96.86, "elapsed_time": "1 day, 7:43:29", "remaining_time": "1:01:39", "throughput": 554.07, "total_tokens": 63279984} {"current_steps": 38750, "total_steps": 40000, "loss": 0.1631, "lr": 1.2057436613486796e-07, "epoch": 1.7542044862943933, "percentage": 96.88, "elapsed_time": "1 day, 7:43:32", "remaining_time": "1:01:24", "throughput": 554.12, "total_tokens": 63287792} {"current_steps": 38755, "total_steps": 40000, "loss": 0.0945, "lr": 1.1961323614771424e-07, "epoch": 1.7544308381810363, "percentage": 96.89, "elapsed_time": "1 day, 7:43:35", "remaining_time": "1:01:09", "throughput": 554.18, "total_tokens": 63296336} {"current_steps": 38760, "total_steps": 40000, "loss": 0.1342, "lr": 1.1865594302886418e-07, "epoch": 1.7546571900676793, "percentage": 96.9, "elapsed_time": "1 day, 7:43:38", "remaining_time": "1:00:54", "throughput": 554.24, "total_tokens": 63304144} {"current_steps": 38765, "total_steps": 40000, "loss": 0.0962, "lr": 1.1770248692594687e-07, "epoch": 1.7548835419543223, "percentage": 96.91, "elapsed_time": "1 day, 7:43:41", "remaining_time": "1:00:38", "throughput": 554.29, "total_tokens": 63312272} {"current_steps": 38770, "total_steps": 40000, "loss": 0.0911, "lr": 1.167528679859975e-07, "epoch": 1.7551098938409653, "percentage": 96.92, "elapsed_time": "1 day, 7:43:44", "remaining_time": "1:00:23", "throughput": 554.35, "total_tokens": 63320112} {"current_steps": 38775, "total_steps": 40000, "loss": 0.1226, "lr": 1.1580708635545446e-07, "epoch": 1.7553362457276083, "percentage": 96.94, "elapsed_time": "1 day, 7:43:48", "remaining_time": "1:00:08", "throughput": 554.4, "total_tokens": 63328048} {"current_steps": 38780, "total_steps": 40000, "loss": 0.1187, "lr": 1.1486514218017885e-07, "epoch": 1.7555625976142513, "percentage": 96.95, "elapsed_time": "1 day, 7:43:51", "remaining_time": "0:59:53", "throughput": 554.46, "total_tokens": 63336272} {"current_steps": 38785, "total_steps": 40000, "loss": 0.1647, "lr": 1.1392703560542117e-07, "epoch": 1.755788949500894, "percentage": 96.96, "elapsed_time": "1 day, 7:43:54", "remaining_time": "0:59:38", "throughput": 554.52, "total_tokens": 63344944} {"current_steps": 38790, "total_steps": 40000, "loss": 0.1122, "lr": 1.129927667758518e-07, "epoch": 1.756015301387537, "percentage": 96.97, "elapsed_time": "1 day, 7:43:57", "remaining_time": "0:59:23", "throughput": 554.57, "total_tokens": 63353168} {"current_steps": 38795, "total_steps": 40000, "loss": 0.146, "lr": 1.1206233583554992e-07, "epoch": 1.75624165327418, "percentage": 96.99, "elapsed_time": "1 day, 7:44:00", "remaining_time": "0:59:08", "throughput": 554.63, "total_tokens": 63361904} {"current_steps": 38800, "total_steps": 40000, "loss": 0.1311, "lr": 1.1113574292799523e-07, "epoch": 1.756468005160823, "percentage": 97.0, "elapsed_time": "1 day, 7:44:04", "remaining_time": "0:58:53", "throughput": 554.69, "total_tokens": 63369712} {"current_steps": 38800, "total_steps": 40000, "eval_loss": 0.12205666303634644, "epoch": 1.756468005160823, "percentage": 97.0, "elapsed_time": "1 day, 7:51:46", "remaining_time": "0:59:07", "throughput": 552.45, "total_tokens": 63369712} {"current_steps": 38805, "total_steps": 40000, "loss": 0.1215, "lr": 1.1021298819608449e-07, "epoch": 1.756694357047466, "percentage": 97.01, "elapsed_time": "1 day, 7:51:50", "remaining_time": "0:58:52", "throughput": 552.5, "total_tokens": 63377680} {"current_steps": 38810, "total_steps": 40000, "loss": 0.1405, "lr": 1.0929407178211226e-07, "epoch": 1.756920708934109, "percentage": 97.02, "elapsed_time": "1 day, 7:51:54", "remaining_time": "0:58:37", "throughput": 552.56, "total_tokens": 63385904} {"current_steps": 38815, "total_steps": 40000, "loss": 0.093, "lr": 1.0837899382779293e-07, "epoch": 1.7571470608207518, "percentage": 97.04, "elapsed_time": "1 day, 7:51:57", "remaining_time": "0:58:22", "throughput": 552.62, "total_tokens": 63394736} {"current_steps": 38820, "total_steps": 40000, "loss": 0.1129, "lr": 1.0746775447423862e-07, "epoch": 1.7573734127073948, "percentage": 97.05, "elapsed_time": "1 day, 7:52:00", "remaining_time": "0:58:07", "throughput": 552.67, "total_tokens": 63402864} {"current_steps": 38825, "total_steps": 40000, "loss": 0.0809, "lr": 1.0656035386197583e-07, "epoch": 1.7575997645940378, "percentage": 97.06, "elapsed_time": "1 day, 7:52:03", "remaining_time": "0:57:52", "throughput": 552.73, "total_tokens": 63411408} {"current_steps": 38830, "total_steps": 40000, "loss": 0.0941, "lr": 1.0565679213093982e-07, "epoch": 1.7578261164806808, "percentage": 97.08, "elapsed_time": "1 day, 7:52:07", "remaining_time": "0:57:36", "throughput": 552.79, "total_tokens": 63419600} {"current_steps": 38835, "total_steps": 40000, "loss": 0.1484, "lr": 1.0475706942046638e-07, "epoch": 1.7580524683673238, "percentage": 97.09, "elapsed_time": "1 day, 7:52:10", "remaining_time": "0:57:21", "throughput": 552.84, "total_tokens": 63428048} {"current_steps": 38840, "total_steps": 40000, "loss": 0.1089, "lr": 1.0386118586930282e-07, "epoch": 1.7582788202539668, "percentage": 97.1, "elapsed_time": "1 day, 7:52:13", "remaining_time": "0:57:06", "throughput": 552.9, "total_tokens": 63436144} {"current_steps": 38845, "total_steps": 40000, "loss": 0.1094, "lr": 1.0296914161561367e-07, "epoch": 1.7585051721406098, "percentage": 97.11, "elapsed_time": "1 day, 7:52:16", "remaining_time": "0:56:51", "throughput": 552.96, "total_tokens": 63444368} {"current_steps": 38850, "total_steps": 40000, "loss": 0.0748, "lr": 1.0208093679695552e-07, "epoch": 1.7587315240272527, "percentage": 97.12, "elapsed_time": "1 day, 7:52:19", "remaining_time": "0:56:36", "throughput": 553.01, "total_tokens": 63452560} {"current_steps": 38855, "total_steps": 40000, "loss": 0.1339, "lr": 1.0119657155030493e-07, "epoch": 1.7589578759138957, "percentage": 97.14, "elapsed_time": "1 day, 7:52:23", "remaining_time": "0:56:21", "throughput": 553.07, "total_tokens": 63460816} {"current_steps": 38860, "total_steps": 40000, "loss": 0.1169, "lr": 1.003160460120417e-07, "epoch": 1.7591842278005387, "percentage": 97.15, "elapsed_time": "1 day, 7:52:26", "remaining_time": "0:56:06", "throughput": 553.13, "total_tokens": 63469200} {"current_steps": 38865, "total_steps": 40000, "loss": 0.13, "lr": 9.943936031795165e-08, "epoch": 1.7594105796871817, "percentage": 97.16, "elapsed_time": "1 day, 7:52:29", "remaining_time": "0:55:51", "throughput": 553.18, "total_tokens": 63477616} {"current_steps": 38870, "total_steps": 40000, "loss": 0.0814, "lr": 9.856651460323219e-08, "epoch": 1.7596369315738247, "percentage": 97.17, "elapsed_time": "1 day, 7:52:32", "remaining_time": "0:55:36", "throughput": 553.24, "total_tokens": 63485680} {"current_steps": 38875, "total_steps": 40000, "loss": 0.1305, "lr": 9.769750900248953e-08, "epoch": 1.7598632834604677, "percentage": 97.19, "elapsed_time": "1 day, 7:52:35", "remaining_time": "0:55:20", "throughput": 553.29, "total_tokens": 63493584} {"current_steps": 38880, "total_steps": 40000, "loss": 0.1805, "lr": 9.683234364973038e-08, "epoch": 1.7600896353471107, "percentage": 97.2, "elapsed_time": "1 day, 7:52:38", "remaining_time": "0:55:05", "throughput": 553.35, "total_tokens": 63501680} {"current_steps": 38885, "total_steps": 40000, "loss": 0.128, "lr": 9.597101867837854e-08, "epoch": 1.7603159872337537, "percentage": 97.21, "elapsed_time": "1 day, 7:52:42", "remaining_time": "0:54:50", "throughput": 553.41, "total_tokens": 63510256} {"current_steps": 38890, "total_steps": 40000, "loss": 0.1886, "lr": 9.511353422125835e-08, "epoch": 1.7605423391203967, "percentage": 97.22, "elapsed_time": "1 day, 7:52:45", "remaining_time": "0:54:35", "throughput": 553.46, "total_tokens": 63517712} {"current_steps": 38895, "total_steps": 40000, "loss": 0.1068, "lr": 9.42598904106029e-08, "epoch": 1.7607686910070397, "percentage": 97.24, "elapsed_time": "1 day, 7:52:48", "remaining_time": "0:54:20", "throughput": 553.51, "total_tokens": 63525936} {"current_steps": 38900, "total_steps": 40000, "loss": 0.1041, "lr": 9.341008737806245e-08, "epoch": 1.7609950428936825, "percentage": 97.25, "elapsed_time": "1 day, 7:52:51", "remaining_time": "0:54:05", "throughput": 553.57, "total_tokens": 63534288} {"current_steps": 38905, "total_steps": 40000, "loss": 0.0884, "lr": 9.256412525467661e-08, "epoch": 1.7612213947803255, "percentage": 97.26, "elapsed_time": "1 day, 7:52:54", "remaining_time": "0:53:50", "throughput": 553.63, "total_tokens": 63542448} {"current_steps": 38910, "total_steps": 40000, "loss": 0.1001, "lr": 9.172200417091326e-08, "epoch": 1.7614477466669685, "percentage": 97.28, "elapsed_time": "1 day, 7:52:58", "remaining_time": "0:53:35", "throughput": 553.68, "total_tokens": 63550672} {"current_steps": 38915, "total_steps": 40000, "loss": 0.1317, "lr": 9.088372425663239e-08, "epoch": 1.7616740985536115, "percentage": 97.29, "elapsed_time": "1 day, 7:53:01", "remaining_time": "0:53:20", "throughput": 553.74, "total_tokens": 63558448} {"current_steps": 38920, "total_steps": 40000, "loss": 0.0833, "lr": 9.004928564110837e-08, "epoch": 1.7619004504402545, "percentage": 97.3, "elapsed_time": "1 day, 7:53:04", "remaining_time": "0:53:05", "throughput": 553.79, "total_tokens": 63566608} {"current_steps": 38925, "total_steps": 40000, "loss": 0.112, "lr": 8.92186884530244e-08, "epoch": 1.7621268023268974, "percentage": 97.31, "elapsed_time": "1 day, 7:53:07", "remaining_time": "0:52:50", "throughput": 553.84, "total_tokens": 63574288} {"current_steps": 38930, "total_steps": 40000, "loss": 0.0882, "lr": 8.83919328204641e-08, "epoch": 1.7623531542135402, "percentage": 97.32, "elapsed_time": "1 day, 7:53:10", "remaining_time": "0:52:35", "throughput": 553.9, "total_tokens": 63582768} {"current_steps": 38935, "total_steps": 40000, "loss": 0.1181, "lr": 8.756901887093105e-08, "epoch": 1.7625795061001832, "percentage": 97.34, "elapsed_time": "1 day, 7:53:13", "remaining_time": "0:52:19", "throughput": 553.96, "total_tokens": 63590800} {"current_steps": 38940, "total_steps": 40000, "loss": 0.1057, "lr": 8.674994673132098e-08, "epoch": 1.7628058579868262, "percentage": 97.35, "elapsed_time": "1 day, 7:53:16", "remaining_time": "0:52:04", "throughput": 554.01, "total_tokens": 63598928} {"current_steps": 38945, "total_steps": 40000, "loss": 0.1031, "lr": 8.593471652794949e-08, "epoch": 1.7630322098734692, "percentage": 97.36, "elapsed_time": "1 day, 7:53:20", "remaining_time": "0:51:49", "throughput": 554.07, "total_tokens": 63606736} {"current_steps": 38950, "total_steps": 40000, "loss": 0.092, "lr": 8.512332838653548e-08, "epoch": 1.7632585617601122, "percentage": 97.38, "elapsed_time": "1 day, 7:53:23", "remaining_time": "0:51:34", "throughput": 554.12, "total_tokens": 63614864} {"current_steps": 38955, "total_steps": 40000, "loss": 0.1335, "lr": 8.431578243220106e-08, "epoch": 1.7634849136467552, "percentage": 97.39, "elapsed_time": "1 day, 7:53:26", "remaining_time": "0:51:19", "throughput": 554.18, "total_tokens": 63623984} {"current_steps": 38960, "total_steps": 40000, "loss": 0.1305, "lr": 8.351207878948552e-08, "epoch": 1.7637112655333982, "percentage": 97.4, "elapsed_time": "1 day, 7:53:29", "remaining_time": "0:51:04", "throughput": 554.24, "total_tokens": 63632016} {"current_steps": 38965, "total_steps": 40000, "loss": 0.1368, "lr": 8.271221758232583e-08, "epoch": 1.7639376174200412, "percentage": 97.41, "elapsed_time": "1 day, 7:53:33", "remaining_time": "0:50:49", "throughput": 554.29, "total_tokens": 63640016} {"current_steps": 38970, "total_steps": 40000, "loss": 0.1301, "lr": 8.191619893407332e-08, "epoch": 1.7641639693066842, "percentage": 97.42, "elapsed_time": "1 day, 7:53:36", "remaining_time": "0:50:34", "throughput": 554.35, "total_tokens": 63648112} {"current_steps": 38975, "total_steps": 40000, "loss": 0.0895, "lr": 8.112402296748534e-08, "epoch": 1.7643903211933272, "percentage": 97.44, "elapsed_time": "1 day, 7:53:39", "remaining_time": "0:50:19", "throughput": 554.4, "total_tokens": 63656272} {"current_steps": 38980, "total_steps": 40000, "loss": 0.1271, "lr": 8.033568980471973e-08, "epoch": 1.7646166730799702, "percentage": 97.45, "elapsed_time": "1 day, 7:53:42", "remaining_time": "0:50:04", "throughput": 554.46, "total_tokens": 63663984} {"current_steps": 38985, "total_steps": 40000, "loss": 0.1029, "lr": 7.955119956735146e-08, "epoch": 1.7648430249666132, "percentage": 97.46, "elapsed_time": "1 day, 7:53:45", "remaining_time": "0:49:49", "throughput": 554.51, "total_tokens": 63671984} {"current_steps": 38990, "total_steps": 40000, "loss": 0.1898, "lr": 7.877055237636155e-08, "epoch": 1.7650693768532562, "percentage": 97.47, "elapsed_time": "1 day, 7:53:48", "remaining_time": "0:49:34", "throughput": 554.57, "total_tokens": 63680048} {"current_steps": 38995, "total_steps": 40000, "loss": 0.1109, "lr": 7.79937483521287e-08, "epoch": 1.7652957287398992, "percentage": 97.49, "elapsed_time": "1 day, 7:53:51", "remaining_time": "0:49:19", "throughput": 554.62, "total_tokens": 63687888} {"current_steps": 39000, "total_steps": 40000, "loss": 0.1018, "lr": 7.722078761444873e-08, "epoch": 1.7655220806265421, "percentage": 97.5, "elapsed_time": "1 day, 7:53:55", "remaining_time": "0:49:04", "throughput": 554.67, "total_tokens": 63696112} {"current_steps": 39000, "total_steps": 40000, "eval_loss": 0.12202145159244537, "epoch": 1.7655220806265421, "percentage": 97.5, "elapsed_time": "1 day, 8:01:37", "remaining_time": "0:49:16", "throughput": 552.45, "total_tokens": 63696112} {"current_steps": 39005, "total_steps": 40000, "loss": 0.13, "lr": 7.645167028252631e-08, "epoch": 1.7657484325131851, "percentage": 97.51, "elapsed_time": "1 day, 8:01:41", "remaining_time": "0:49:01", "throughput": 552.5, "total_tokens": 63704016} {"current_steps": 39010, "total_steps": 40000, "loss": 0.1368, "lr": 7.568639647496379e-08, "epoch": 1.7659747843998281, "percentage": 97.52, "elapsed_time": "1 day, 8:01:45", "remaining_time": "0:48:46", "throughput": 552.55, "total_tokens": 63712272} {"current_steps": 39015, "total_steps": 40000, "loss": 0.1261, "lr": 7.492496630977508e-08, "epoch": 1.766201136286471, "percentage": 97.54, "elapsed_time": "1 day, 8:01:48", "remaining_time": "0:48:31", "throughput": 552.61, "total_tokens": 63720112} {"current_steps": 39020, "total_steps": 40000, "loss": 0.1688, "lr": 7.416737990438571e-08, "epoch": 1.766427488173114, "percentage": 97.55, "elapsed_time": "1 day, 8:01:51", "remaining_time": "0:48:16", "throughput": 552.66, "total_tokens": 63728400} {"current_steps": 39025, "total_steps": 40000, "loss": 0.1249, "lr": 7.341363737562445e-08, "epoch": 1.766653840059757, "percentage": 97.56, "elapsed_time": "1 day, 8:01:54", "remaining_time": "0:48:01", "throughput": 552.72, "total_tokens": 63736720} {"current_steps": 39030, "total_steps": 40000, "loss": 0.0798, "lr": 7.266373883972887e-08, "epoch": 1.7668801919464, "percentage": 97.58, "elapsed_time": "1 day, 8:01:57", "remaining_time": "0:47:45", "throughput": 552.78, "total_tokens": 63745008} {"current_steps": 39035, "total_steps": 40000, "loss": 0.0955, "lr": 7.191768441233981e-08, "epoch": 1.7671065438330429, "percentage": 97.59, "elapsed_time": "1 day, 8:02:00", "remaining_time": "0:47:30", "throughput": 552.83, "total_tokens": 63752720} {"current_steps": 39040, "total_steps": 40000, "loss": 0.1207, "lr": 7.11754742085069e-08, "epoch": 1.7673328957196857, "percentage": 97.6, "elapsed_time": "1 day, 8:02:04", "remaining_time": "0:47:15", "throughput": 552.89, "total_tokens": 63761616} {"current_steps": 39045, "total_steps": 40000, "loss": 0.1736, "lr": 7.043710834269413e-08, "epoch": 1.7675592476063287, "percentage": 97.61, "elapsed_time": "1 day, 8:02:07", "remaining_time": "0:47:00", "throughput": 552.94, "total_tokens": 63769552} {"current_steps": 39050, "total_steps": 40000, "loss": 0.1144, "lr": 6.970258692876319e-08, "epoch": 1.7677855994929716, "percentage": 97.62, "elapsed_time": "1 day, 8:02:10", "remaining_time": "0:46:45", "throughput": 552.99, "total_tokens": 63776848} {"current_steps": 39055, "total_steps": 40000, "loss": 0.119, "lr": 6.897191007998738e-08, "epoch": 1.7680119513796146, "percentage": 97.64, "elapsed_time": "1 day, 8:02:13", "remaining_time": "0:46:30", "throughput": 553.05, "total_tokens": 63784848} {"current_steps": 39060, "total_steps": 40000, "loss": 0.1192, "lr": 6.824507790904599e-08, "epoch": 1.7682383032662576, "percentage": 97.65, "elapsed_time": "1 day, 8:02:16", "remaining_time": "0:46:15", "throughput": 553.1, "total_tokens": 63792336} {"current_steps": 39065, "total_steps": 40000, "loss": 0.1645, "lr": 6.752209052802439e-08, "epoch": 1.7684646551529006, "percentage": 97.66, "elapsed_time": "1 day, 8:02:19", "remaining_time": "0:46:00", "throughput": 553.16, "total_tokens": 63800944} {"current_steps": 39070, "total_steps": 40000, "loss": 0.0747, "lr": 6.680294804841946e-08, "epoch": 1.7686910070395436, "percentage": 97.67, "elapsed_time": "1 day, 8:02:23", "remaining_time": "0:45:45", "throughput": 553.21, "total_tokens": 63808464} {"current_steps": 39075, "total_steps": 40000, "loss": 0.1259, "lr": 6.608765058112865e-08, "epoch": 1.7689173589261866, "percentage": 97.69, "elapsed_time": "1 day, 8:02:26", "remaining_time": "0:45:30", "throughput": 553.26, "total_tokens": 63816720} {"current_steps": 39080, "total_steps": 40000, "loss": 0.1381, "lr": 6.537619823646368e-08, "epoch": 1.7691437108128296, "percentage": 97.7, "elapsed_time": "1 day, 8:02:29", "remaining_time": "0:45:15", "throughput": 553.32, "total_tokens": 63824848} {"current_steps": 39085, "total_steps": 40000, "loss": 0.1131, "lr": 6.466859112413404e-08, "epoch": 1.7693700626994726, "percentage": 97.71, "elapsed_time": "1 day, 8:02:32", "remaining_time": "0:45:00", "throughput": 553.38, "total_tokens": 63833264} {"current_steps": 39090, "total_steps": 40000, "loss": 0.1289, "lr": 6.39648293532663e-08, "epoch": 1.7695964145861156, "percentage": 97.72, "elapsed_time": "1 day, 8:02:35", "remaining_time": "0:44:45", "throughput": 553.43, "total_tokens": 63841520} {"current_steps": 39095, "total_steps": 40000, "loss": 0.0952, "lr": 6.32649130323848e-08, "epoch": 1.7698227664727586, "percentage": 97.74, "elapsed_time": "1 day, 8:02:38", "remaining_time": "0:44:30", "throughput": 553.49, "total_tokens": 63849968} {"current_steps": 39100, "total_steps": 40000, "loss": 0.1301, "lr": 6.256884226943094e-08, "epoch": 1.7700491183594016, "percentage": 97.75, "elapsed_time": "1 day, 8:02:42", "remaining_time": "0:44:15", "throughput": 553.55, "total_tokens": 63858224} {"current_steps": 39105, "total_steps": 40000, "loss": 0.1222, "lr": 6.187661717174386e-08, "epoch": 1.7702754702460446, "percentage": 97.76, "elapsed_time": "1 day, 8:02:45", "remaining_time": "0:44:00", "throughput": 553.61, "total_tokens": 63867632} {"current_steps": 39110, "total_steps": 40000, "loss": 0.1114, "lr": 6.118823784607708e-08, "epoch": 1.7705018221326876, "percentage": 97.78, "elapsed_time": "1 day, 8:02:48", "remaining_time": "0:43:45", "throughput": 553.66, "total_tokens": 63875504} {"current_steps": 39115, "total_steps": 40000, "loss": 0.1103, "lr": 6.050370439858178e-08, "epoch": 1.7707281740193306, "percentage": 97.79, "elapsed_time": "1 day, 8:02:52", "remaining_time": "0:43:30", "throughput": 553.72, "total_tokens": 63884368} {"current_steps": 39120, "total_steps": 40000, "loss": 0.1133, "lr": 5.98230169348235e-08, "epoch": 1.7709545259059736, "percentage": 97.8, "elapsed_time": "1 day, 8:02:55", "remaining_time": "0:43:15", "throughput": 553.78, "total_tokens": 63893072} {"current_steps": 39125, "total_steps": 40000, "loss": 0.0758, "lr": 5.914617555977664e-08, "epoch": 1.7711808777926163, "percentage": 97.81, "elapsed_time": "1 day, 8:02:58", "remaining_time": "0:43:00", "throughput": 553.84, "total_tokens": 63900944} {"current_steps": 39130, "total_steps": 40000, "loss": 0.1304, "lr": 5.8473180377816017e-08, "epoch": 1.7714072296792593, "percentage": 97.82, "elapsed_time": "1 day, 8:03:01", "remaining_time": "0:42:45", "throughput": 553.89, "total_tokens": 63909040} {"current_steps": 39135, "total_steps": 40000, "loss": 0.1711, "lr": 5.780403149272251e-08, "epoch": 1.7716335815659023, "percentage": 97.84, "elapsed_time": "1 day, 8:03:04", "remaining_time": "0:42:30", "throughput": 553.95, "total_tokens": 63917808} {"current_steps": 39140, "total_steps": 40000, "loss": 0.0839, "lr": 5.7138729007694126e-08, "epoch": 1.7718599334525453, "percentage": 97.85, "elapsed_time": "1 day, 8:03:08", "remaining_time": "0:42:15", "throughput": 554.01, "total_tokens": 63925616} {"current_steps": 39145, "total_steps": 40000, "loss": 0.076, "lr": 5.64772730253238e-08, "epoch": 1.7720862853391883, "percentage": 97.86, "elapsed_time": "1 day, 8:03:11", "remaining_time": "0:42:00", "throughput": 554.06, "total_tokens": 63934064} {"current_steps": 39150, "total_steps": 40000, "loss": 0.1173, "lr": 5.5819663647618814e-08, "epoch": 1.7723126372258313, "percentage": 97.88, "elapsed_time": "1 day, 8:03:14", "remaining_time": "0:41:45", "throughput": 554.12, "total_tokens": 63942512} {"current_steps": 39155, "total_steps": 40000, "loss": 0.1586, "lr": 5.5165900975989723e-08, "epoch": 1.772538989112474, "percentage": 97.89, "elapsed_time": "1 day, 8:03:17", "remaining_time": "0:41:30", "throughput": 554.17, "total_tokens": 63949776} {"current_steps": 39160, "total_steps": 40000, "loss": 0.1144, "lr": 5.451598511125311e-08, "epoch": 1.772765340999117, "percentage": 97.9, "elapsed_time": "1 day, 8:03:20", "remaining_time": "0:41:15", "throughput": 554.23, "total_tokens": 63958320} {"current_steps": 39165, "total_steps": 40000, "loss": 0.1137, "lr": 5.3869916153637124e-08, "epoch": 1.77299169288576, "percentage": 97.91, "elapsed_time": "1 day, 8:03:23", "remaining_time": "0:41:00", "throughput": 554.28, "total_tokens": 63966320} {"current_steps": 39170, "total_steps": 40000, "loss": 0.1412, "lr": 5.322769420277318e-08, "epoch": 1.773218044772403, "percentage": 97.92, "elapsed_time": "1 day, 8:03:27", "remaining_time": "0:40:45", "throughput": 554.34, "total_tokens": 63974768} {"current_steps": 39175, "total_steps": 40000, "loss": 0.0843, "lr": 5.258931935769873e-08, "epoch": 1.773444396659046, "percentage": 97.94, "elapsed_time": "1 day, 8:03:30", "remaining_time": "0:40:30", "throughput": 554.39, "total_tokens": 63982832} {"current_steps": 39180, "total_steps": 40000, "loss": 0.1618, "lr": 5.19547917168628e-08, "epoch": 1.773670748545689, "percentage": 97.95, "elapsed_time": "1 day, 8:03:33", "remaining_time": "0:40:15", "throughput": 554.45, "total_tokens": 63990480} {"current_steps": 39185, "total_steps": 40000, "loss": 0.1162, "lr": 5.13241113781121e-08, "epoch": 1.773897100432332, "percentage": 97.96, "elapsed_time": "1 day, 8:03:36", "remaining_time": "0:40:00", "throughput": 554.5, "total_tokens": 63998416} {"current_steps": 39190, "total_steps": 40000, "loss": 0.1369, "lr": 5.0697278438707755e-08, "epoch": 1.774123452318975, "percentage": 97.97, "elapsed_time": "1 day, 8:03:39", "remaining_time": "0:39:45", "throughput": 554.55, "total_tokens": 64006416} {"current_steps": 39195, "total_steps": 40000, "loss": 0.0906, "lr": 5.0074292995316854e-08, "epoch": 1.774349804205618, "percentage": 97.99, "elapsed_time": "1 day, 8:03:42", "remaining_time": "0:39:30", "throughput": 554.61, "total_tokens": 64014224} {"current_steps": 39200, "total_steps": 40000, "loss": 0.1229, "lr": 4.945515514400978e-08, "epoch": 1.774576156092261, "percentage": 98.0, "elapsed_time": "1 day, 8:03:46", "remaining_time": "0:39:15", "throughput": 554.66, "total_tokens": 64022416} {"current_steps": 39200, "total_steps": 40000, "eval_loss": 0.12192931771278381, "epoch": 1.774576156092261, "percentage": 98.0, "elapsed_time": "1 day, 8:11:28", "remaining_time": "0:39:25", "throughput": 552.45, "total_tokens": 64022416} {"current_steps": 39205, "total_steps": 40000, "loss": 0.107, "lr": 4.883986498026571e-08, "epoch": 1.774802507978904, "percentage": 98.01, "elapsed_time": "1 day, 8:11:32", "remaining_time": "0:39:10", "throughput": 552.5, "total_tokens": 64031056} {"current_steps": 39210, "total_steps": 40000, "loss": 0.1468, "lr": 4.822842259896987e-08, "epoch": 1.775028859865547, "percentage": 98.02, "elapsed_time": "1 day, 8:11:36", "remaining_time": "0:38:55", "throughput": 552.56, "total_tokens": 64039344} {"current_steps": 39215, "total_steps": 40000, "loss": 0.1513, "lr": 4.762082809441626e-08, "epoch": 1.77525521175219, "percentage": 98.04, "elapsed_time": "1 day, 8:11:39", "remaining_time": "0:38:40", "throughput": 552.61, "total_tokens": 64047472} {"current_steps": 39220, "total_steps": 40000, "loss": 0.1179, "lr": 4.7017081560302156e-08, "epoch": 1.775481563638833, "percentage": 98.05, "elapsed_time": "1 day, 8:11:42", "remaining_time": "0:38:25", "throughput": 552.67, "total_tokens": 64055920} {"current_steps": 39225, "total_steps": 40000, "loss": 0.1142, "lr": 4.6417183089730866e-08, "epoch": 1.775707915525476, "percentage": 98.06, "elapsed_time": "1 day, 8:11:45", "remaining_time": "0:38:10", "throughput": 552.73, "total_tokens": 64064112} {"current_steps": 39230, "total_steps": 40000, "loss": 0.0791, "lr": 4.5821132775217265e-08, "epoch": 1.775934267412119, "percentage": 98.08, "elapsed_time": "1 day, 8:11:48", "remaining_time": "0:37:55", "throughput": 552.78, "total_tokens": 64072304} {"current_steps": 39235, "total_steps": 40000, "loss": 0.0992, "lr": 4.5228930708679504e-08, "epoch": 1.776160619298762, "percentage": 98.09, "elapsed_time": "1 day, 8:11:51", "remaining_time": "0:37:40", "throughput": 552.84, "total_tokens": 64080272} {"current_steps": 39240, "total_steps": 40000, "loss": 0.1456, "lr": 4.464057698144175e-08, "epoch": 1.7763869711854048, "percentage": 98.1, "elapsed_time": "1 day, 8:11:55", "remaining_time": "0:37:25", "throughput": 552.89, "total_tokens": 64088176} {"current_steps": 39245, "total_steps": 40000, "loss": 0.0909, "lr": 4.4056071684236974e-08, "epoch": 1.7766133230720478, "percentage": 98.11, "elapsed_time": "1 day, 8:11:58", "remaining_time": "0:37:10", "throughput": 552.95, "total_tokens": 64096912} {"current_steps": 39250, "total_steps": 40000, "loss": 0.0971, "lr": 4.347541490719864e-08, "epoch": 1.7768396749586908, "percentage": 98.12, "elapsed_time": "1 day, 8:12:01", "remaining_time": "0:36:55", "throughput": 553.01, "total_tokens": 64105872} {"current_steps": 39255, "total_steps": 40000, "loss": 0.1284, "lr": 4.2898606739877336e-08, "epoch": 1.7770660268453338, "percentage": 98.14, "elapsed_time": "1 day, 8:12:04", "remaining_time": "0:36:40", "throughput": 553.07, "total_tokens": 64114064} {"current_steps": 39260, "total_steps": 40000, "loss": 0.0899, "lr": 4.232564727122135e-08, "epoch": 1.7772923787319768, "percentage": 98.15, "elapsed_time": "1 day, 8:12:08", "remaining_time": "0:36:25", "throughput": 553.12, "total_tokens": 64121840} {"current_steps": 39265, "total_steps": 40000, "loss": 0.1126, "lr": 4.1756536589585004e-08, "epoch": 1.7775187306186198, "percentage": 98.16, "elapsed_time": "1 day, 8:12:11", "remaining_time": "0:36:10", "throughput": 553.17, "total_tokens": 64130128} {"current_steps": 39270, "total_steps": 40000, "loss": 0.1299, "lr": 4.119127478273976e-08, "epoch": 1.7777450825052625, "percentage": 98.17, "elapsed_time": "1 day, 8:12:14", "remaining_time": "0:35:55", "throughput": 553.22, "total_tokens": 64137648} {"current_steps": 39275, "total_steps": 40000, "loss": 0.0954, "lr": 4.062986193784923e-08, "epoch": 1.7779714343919055, "percentage": 98.19, "elapsed_time": "1 day, 8:12:17", "remaining_time": "0:35:40", "throughput": 553.27, "total_tokens": 64145200} {"current_steps": 39280, "total_steps": 40000, "loss": 0.1257, "lr": 4.007229814149416e-08, "epoch": 1.7781977862785485, "percentage": 98.2, "elapsed_time": "1 day, 8:12:20", "remaining_time": "0:35:25", "throughput": 553.33, "total_tokens": 64153776} {"current_steps": 39285, "total_steps": 40000, "loss": 0.13, "lr": 3.951858347965576e-08, "epoch": 1.7784241381651915, "percentage": 98.21, "elapsed_time": "1 day, 8:12:23", "remaining_time": "0:35:10", "throughput": 553.39, "total_tokens": 64161840} {"current_steps": 39290, "total_steps": 40000, "loss": 0.1265, "lr": 3.896871803772684e-08, "epoch": 1.7786504900518345, "percentage": 98.22, "elapsed_time": "1 day, 8:12:27", "remaining_time": "0:34:55", "throughput": 553.44, "total_tokens": 64170160} {"current_steps": 39295, "total_steps": 40000, "loss": 0.0926, "lr": 3.842270190050068e-08, "epoch": 1.7788768419384775, "percentage": 98.24, "elapsed_time": "1 day, 8:12:30", "remaining_time": "0:34:40", "throughput": 553.5, "total_tokens": 64178544} {"current_steps": 39300, "total_steps": 40000, "loss": 0.0496, "lr": 3.7880535152179376e-08, "epoch": 1.7791031938251205, "percentage": 98.25, "elapsed_time": "1 day, 8:12:33", "remaining_time": "0:34:25", "throughput": 553.56, "total_tokens": 64187024} {"current_steps": 39305, "total_steps": 40000, "loss": 0.0935, "lr": 3.734221787637382e-08, "epoch": 1.7793295457117635, "percentage": 98.26, "elapsed_time": "1 day, 8:12:36", "remaining_time": "0:34:10", "throughput": 553.61, "total_tokens": 64195088} {"current_steps": 39310, "total_steps": 40000, "loss": 0.1317, "lr": 3.680775015609817e-08, "epoch": 1.7795558975984065, "percentage": 98.28, "elapsed_time": "1 day, 8:12:39", "remaining_time": "0:33:55", "throughput": 553.67, "total_tokens": 64202992} {"current_steps": 39315, "total_steps": 40000, "loss": 0.0931, "lr": 3.627713207377537e-08, "epoch": 1.7797822494850495, "percentage": 98.29, "elapsed_time": "1 day, 8:12:42", "remaining_time": "0:33:40", "throughput": 553.72, "total_tokens": 64210800} {"current_steps": 39320, "total_steps": 40000, "loss": 0.1063, "lr": 3.575036371123164e-08, "epoch": 1.7800086013716925, "percentage": 98.3, "elapsed_time": "1 day, 8:12:46", "remaining_time": "0:33:25", "throughput": 553.78, "total_tokens": 64219344} {"current_steps": 39325, "total_steps": 40000, "loss": 0.1033, "lr": 3.5227445149704776e-08, "epoch": 1.7802349532583355, "percentage": 98.31, "elapsed_time": "1 day, 8:12:49", "remaining_time": "0:33:10", "throughput": 553.83, "total_tokens": 64227632} {"current_steps": 39330, "total_steps": 40000, "loss": 0.0841, "lr": 3.470837646983027e-08, "epoch": 1.7804613051449785, "percentage": 98.32, "elapsed_time": "1 day, 8:12:52", "remaining_time": "0:32:55", "throughput": 553.89, "total_tokens": 64235760} {"current_steps": 39335, "total_steps": 40000, "loss": 0.1099, "lr": 3.419315775165799e-08, "epoch": 1.7806876570316215, "percentage": 98.34, "elapsed_time": "1 day, 8:12:55", "remaining_time": "0:32:40", "throughput": 553.94, "total_tokens": 64243632} {"current_steps": 39340, "total_steps": 40000, "loss": 0.1071, "lr": 3.368178907464103e-08, "epoch": 1.7809140089182645, "percentage": 98.35, "elapsed_time": "1 day, 8:12:58", "remaining_time": "0:32:25", "throughput": 553.99, "total_tokens": 64251632} {"current_steps": 39345, "total_steps": 40000, "loss": 0.1177, "lr": 3.317427051763855e-08, "epoch": 1.7811403608049075, "percentage": 98.36, "elapsed_time": "1 day, 8:13:01", "remaining_time": "0:32:10", "throughput": 554.05, "total_tokens": 64259600} {"current_steps": 39350, "total_steps": 40000, "loss": 0.2056, "lr": 3.267060215891571e-08, "epoch": 1.7813667126915504, "percentage": 98.38, "elapsed_time": "1 day, 8:13:05", "remaining_time": "0:31:55", "throughput": 554.1, "total_tokens": 64267600} {"current_steps": 39355, "total_steps": 40000, "loss": 0.1205, "lr": 3.217078407614649e-08, "epoch": 1.7815930645781932, "percentage": 98.39, "elapsed_time": "1 day, 8:13:08", "remaining_time": "0:31:40", "throughput": 554.16, "total_tokens": 64275600} {"current_steps": 39360, "total_steps": 40000, "loss": 0.1037, "lr": 3.1674816346405345e-08, "epoch": 1.7818194164648362, "percentage": 98.4, "elapsed_time": "1 day, 8:13:11", "remaining_time": "0:31:26", "throughput": 554.21, "total_tokens": 64283824} {"current_steps": 39365, "total_steps": 40000, "loss": 0.0705, "lr": 3.11826990461811e-08, "epoch": 1.7820457683514792, "percentage": 98.41, "elapsed_time": "1 day, 8:13:14", "remaining_time": "0:31:11", "throughput": 554.27, "total_tokens": 64292016} {"current_steps": 39370, "total_steps": 40000, "loss": 0.1373, "lr": 3.069443225136304e-08, "epoch": 1.7822721202381222, "percentage": 98.42, "elapsed_time": "1 day, 8:13:17", "remaining_time": "0:30:56", "throughput": 554.32, "total_tokens": 64300240} {"current_steps": 39375, "total_steps": 40000, "loss": 0.1464, "lr": 3.021001603724372e-08, "epoch": 1.7824984721247652, "percentage": 98.44, "elapsed_time": "1 day, 8:13:20", "remaining_time": "0:30:41", "throughput": 554.37, "total_tokens": 64307920} {"current_steps": 39380, "total_steps": 40000, "loss": 0.085, "lr": 2.9729450478532818e-08, "epoch": 1.782724824011408, "percentage": 98.45, "elapsed_time": "1 day, 8:13:24", "remaining_time": "0:30:26", "throughput": 554.43, "total_tokens": 64316048} {"current_steps": 39385, "total_steps": 40000, "loss": 0.1015, "lr": 2.9252735649337726e-08, "epoch": 1.782951175898051, "percentage": 98.46, "elapsed_time": "1 day, 8:13:27", "remaining_time": "0:30:11", "throughput": 554.49, "total_tokens": 64324464} {"current_steps": 39390, "total_steps": 40000, "loss": 0.0946, "lr": 2.8779871623171863e-08, "epoch": 1.783177527784694, "percentage": 98.47, "elapsed_time": "1 day, 8:13:30", "remaining_time": "0:29:56", "throughput": 554.54, "total_tokens": 64332080} {"current_steps": 39395, "total_steps": 40000, "loss": 0.1193, "lr": 2.8310858472957448e-08, "epoch": 1.783403879671337, "percentage": 98.49, "elapsed_time": "1 day, 8:13:33", "remaining_time": "0:29:41", "throughput": 554.59, "total_tokens": 64340048} {"current_steps": 39400, "total_steps": 40000, "loss": 0.1105, "lr": 2.784569627101996e-08, "epoch": 1.78363023155798, "percentage": 98.5, "elapsed_time": "1 day, 8:13:36", "remaining_time": "0:29:26", "throughput": 554.65, "total_tokens": 64348304} {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.12190044671297073, "epoch": 1.78363023155798, "percentage": 98.5, "elapsed_time": "1 day, 8:21:19", "remaining_time": "0:29:33", "throughput": 552.44, "total_tokens": 64348304} {"current_steps": 39405, "total_steps": 40000, "loss": 0.1356, "lr": 2.738438508909924e-08, "epoch": 1.783856583444623, "percentage": 98.51, "elapsed_time": "1 day, 8:21:23", "remaining_time": "0:29:18", "throughput": 552.49, "total_tokens": 64355920} {"current_steps": 39410, "total_steps": 40000, "loss": 0.1203, "lr": 2.692692499833005e-08, "epoch": 1.784082935331266, "percentage": 98.52, "elapsed_time": "1 day, 8:21:26", "remaining_time": "0:29:03", "throughput": 552.55, "total_tokens": 64364240} {"current_steps": 39415, "total_steps": 40000, "loss": 0.1164, "lr": 2.647331606926151e-08, "epoch": 1.784309287217909, "percentage": 98.54, "elapsed_time": "1 day, 8:21:29", "remaining_time": "0:28:48", "throughput": 552.6, "total_tokens": 64372144} {"current_steps": 39420, "total_steps": 40000, "loss": 0.143, "lr": 2.6023558371843225e-08, "epoch": 1.784535639104552, "percentage": 98.55, "elapsed_time": "1 day, 8:21:32", "remaining_time": "0:28:33", "throughput": 552.65, "total_tokens": 64379984} {"current_steps": 39425, "total_steps": 40000, "loss": 0.1312, "lr": 2.557765197543638e-08, "epoch": 1.784761990991195, "percentage": 98.56, "elapsed_time": "1 day, 8:21:35", "remaining_time": "0:28:19", "throughput": 552.7, "total_tokens": 64387856} {"current_steps": 39430, "total_steps": 40000, "loss": 0.1298, "lr": 2.513559694880263e-08, "epoch": 1.784988342877838, "percentage": 98.58, "elapsed_time": "1 day, 8:21:39", "remaining_time": "0:28:04", "throughput": 552.76, "total_tokens": 64395856} {"current_steps": 39435, "total_steps": 40000, "loss": 0.1134, "lr": 2.469739336011523e-08, "epoch": 1.785214694764481, "percentage": 98.59, "elapsed_time": "1 day, 8:21:42", "remaining_time": "0:27:49", "throughput": 552.81, "total_tokens": 64404208} {"current_steps": 39440, "total_steps": 40000, "loss": 0.1043, "lr": 2.4263041276947894e-08, "epoch": 1.785441046651124, "percentage": 98.6, "elapsed_time": "1 day, 8:21:45", "remaining_time": "0:27:34", "throughput": 552.87, "total_tokens": 64411952} {"current_steps": 39445, "total_steps": 40000, "loss": 0.1025, "lr": 2.3832540766283164e-08, "epoch": 1.785667398537767, "percentage": 98.61, "elapsed_time": "1 day, 8:21:48", "remaining_time": "0:27:19", "throughput": 552.92, "total_tokens": 64419984} {"current_steps": 39450, "total_steps": 40000, "loss": 0.1218, "lr": 2.3405891894512366e-08, "epoch": 1.78589375042441, "percentage": 98.62, "elapsed_time": "1 day, 8:21:51", "remaining_time": "0:27:04", "throughput": 552.97, "total_tokens": 64428144} {"current_steps": 39455, "total_steps": 40000, "loss": 0.1367, "lr": 2.29830947274301e-08, "epoch": 1.786120102311053, "percentage": 98.64, "elapsed_time": "1 day, 8:21:55", "remaining_time": "0:26:49", "throughput": 553.03, "total_tokens": 64436528} {"current_steps": 39460, "total_steps": 40000, "loss": 0.1025, "lr": 2.2564149330231432e-08, "epoch": 1.7863464541976959, "percentage": 98.65, "elapsed_time": "1 day, 8:21:58", "remaining_time": "0:26:34", "throughput": 553.09, "total_tokens": 64444912} {"current_steps": 39465, "total_steps": 40000, "loss": 0.1245, "lr": 2.2149055767528572e-08, "epoch": 1.7865728060843387, "percentage": 98.66, "elapsed_time": "1 day, 8:22:01", "remaining_time": "0:26:19", "throughput": 553.14, "total_tokens": 64453072} {"current_steps": 39470, "total_steps": 40000, "loss": 0.0822, "lr": 2.1737814103334197e-08, "epoch": 1.7867991579709817, "percentage": 98.67, "elapsed_time": "1 day, 8:22:04", "remaining_time": "0:26:04", "throughput": 553.2, "total_tokens": 64461840} {"current_steps": 39475, "total_steps": 40000, "loss": 0.1385, "lr": 2.1330424401064253e-08, "epoch": 1.7870255098576246, "percentage": 98.69, "elapsed_time": "1 day, 8:22:08", "remaining_time": "0:25:49", "throughput": 553.26, "total_tokens": 64469840} {"current_steps": 39480, "total_steps": 40000, "loss": 0.1099, "lr": 2.092688672354348e-08, "epoch": 1.7872518617442676, "percentage": 98.7, "elapsed_time": "1 day, 8:22:11", "remaining_time": "0:25:34", "throughput": 553.31, "total_tokens": 64478288} {"current_steps": 39485, "total_steps": 40000, "loss": 0.1461, "lr": 2.0527201133005435e-08, "epoch": 1.7874782136309106, "percentage": 98.71, "elapsed_time": "1 day, 8:22:14", "remaining_time": "0:25:19", "throughput": 553.37, "total_tokens": 64486576} {"current_steps": 39490, "total_steps": 40000, "loss": 0.0773, "lr": 2.0131367691084148e-08, "epoch": 1.7877045655175536, "percentage": 98.72, "elapsed_time": "1 day, 8:22:17", "remaining_time": "0:25:05", "throughput": 553.43, "total_tokens": 64495472} {"current_steps": 39495, "total_steps": 40000, "loss": 0.1474, "lr": 1.9739386458819675e-08, "epoch": 1.7879309174041964, "percentage": 98.74, "elapsed_time": "1 day, 8:22:20", "remaining_time": "0:24:50", "throughput": 553.48, "total_tokens": 64503600} {"current_steps": 39500, "total_steps": 40000, "loss": 0.1028, "lr": 1.9351257496666442e-08, "epoch": 1.7881572692908394, "percentage": 98.75, "elapsed_time": "1 day, 8:22:24", "remaining_time": "0:24:35", "throughput": 553.54, "total_tokens": 64511440} {"current_steps": 39505, "total_steps": 40000, "loss": 0.1039, "lr": 1.896698086447657e-08, "epoch": 1.7883836211774824, "percentage": 98.76, "elapsed_time": "1 day, 8:22:27", "remaining_time": "0:24:20", "throughput": 553.59, "total_tokens": 64519664} {"current_steps": 39510, "total_steps": 40000, "loss": 0.097, "lr": 1.8586556621505436e-08, "epoch": 1.7886099730641254, "percentage": 98.78, "elapsed_time": "1 day, 8:22:30", "remaining_time": "0:24:05", "throughput": 553.64, "total_tokens": 64527472} {"current_steps": 39515, "total_steps": 40000, "loss": 0.1358, "lr": 1.820998482642833e-08, "epoch": 1.7888363249507684, "percentage": 98.79, "elapsed_time": "1 day, 8:22:33", "remaining_time": "0:23:50", "throughput": 553.71, "total_tokens": 64536464} {"current_steps": 39520, "total_steps": 40000, "loss": 0.0935, "lr": 1.7837265537309912e-08, "epoch": 1.7890626768374114, "percentage": 98.8, "elapsed_time": "1 day, 8:22:37", "remaining_time": "0:23:35", "throughput": 553.76, "total_tokens": 64545136} {"current_steps": 39525, "total_steps": 40000, "loss": 0.121, "lr": 1.7468398811629206e-08, "epoch": 1.7892890287240544, "percentage": 98.81, "elapsed_time": "1 day, 8:22:40", "remaining_time": "0:23:20", "throughput": 553.82, "total_tokens": 64553040} {"current_steps": 39530, "total_steps": 40000, "loss": 0.1159, "lr": 1.710338470627404e-08, "epoch": 1.7895153806106974, "percentage": 98.83, "elapsed_time": "1 day, 8:22:43", "remaining_time": "0:23:05", "throughput": 553.87, "total_tokens": 64561168} {"current_steps": 39535, "total_steps": 40000, "loss": 0.127, "lr": 1.6742223277529945e-08, "epoch": 1.7897417324973404, "percentage": 98.84, "elapsed_time": "1 day, 8:22:46", "remaining_time": "0:22:51", "throughput": 553.92, "total_tokens": 64569104} {"current_steps": 39540, "total_steps": 40000, "loss": 0.1506, "lr": 1.6384914581094036e-08, "epoch": 1.7899680843839834, "percentage": 98.85, "elapsed_time": "1 day, 8:22:49", "remaining_time": "0:22:36", "throughput": 553.98, "total_tokens": 64577040} {"current_steps": 39545, "total_steps": 40000, "loss": 0.132, "lr": 1.6031458672069455e-08, "epoch": 1.7901944362706264, "percentage": 98.86, "elapsed_time": "1 day, 8:22:53", "remaining_time": "0:22:21", "throughput": 554.05, "total_tokens": 64587120} {"current_steps": 39550, "total_steps": 40000, "loss": 0.0876, "lr": 1.5681855604962602e-08, "epoch": 1.7904207881572693, "percentage": 98.88, "elapsed_time": "1 day, 8:22:56", "remaining_time": "0:22:06", "throughput": 554.1, "total_tokens": 64595120} {"current_steps": 39555, "total_steps": 40000, "loss": 0.14, "lr": 1.5336105433683135e-08, "epoch": 1.7906471400439123, "percentage": 98.89, "elapsed_time": "1 day, 8:22:59", "remaining_time": "0:21:51", "throughput": 554.16, "total_tokens": 64603568} {"current_steps": 39560, "total_steps": 40000, "loss": 0.1221, "lr": 1.499420821155506e-08, "epoch": 1.7908734919305553, "percentage": 98.9, "elapsed_time": "1 day, 8:23:02", "remaining_time": "0:21:36", "throughput": 554.21, "total_tokens": 64611184} {"current_steps": 39565, "total_steps": 40000, "loss": 0.1328, "lr": 1.4656163991302874e-08, "epoch": 1.7910998438171983, "percentage": 98.91, "elapsed_time": "1 day, 8:23:06", "remaining_time": "0:21:21", "throughput": 554.26, "total_tokens": 64619344} {"current_steps": 39570, "total_steps": 40000, "loss": 0.1206, "lr": 1.4321972825051544e-08, "epoch": 1.7913261957038413, "percentage": 98.92, "elapsed_time": "1 day, 8:23:09", "remaining_time": "0:21:06", "throughput": 554.32, "total_tokens": 64627600} {"current_steps": 39575, "total_steps": 40000, "loss": 0.1469, "lr": 1.3991634764345951e-08, "epoch": 1.7915525475904843, "percentage": 98.94, "elapsed_time": "1 day, 8:23:12", "remaining_time": "0:20:52", "throughput": 554.37, "total_tokens": 64635760} {"current_steps": 39580, "total_steps": 40000, "loss": 0.0981, "lr": 1.3665149860120352e-08, "epoch": 1.791778899477127, "percentage": 98.95, "elapsed_time": "1 day, 8:23:15", "remaining_time": "0:20:37", "throughput": 554.43, "total_tokens": 64643920} {"current_steps": 39585, "total_steps": 40000, "loss": 0.1375, "lr": 1.3342518162728912e-08, "epoch": 1.79200525136377, "percentage": 98.96, "elapsed_time": "1 day, 8:23:18", "remaining_time": "0:20:22", "throughput": 554.48, "total_tokens": 64651888} {"current_steps": 39590, "total_steps": 40000, "loss": 0.1268, "lr": 1.30237397219235e-08, "epoch": 1.792231603250413, "percentage": 98.98, "elapsed_time": "1 day, 8:23:21", "remaining_time": "0:20:07", "throughput": 554.53, "total_tokens": 64659728} {"current_steps": 39595, "total_steps": 40000, "loss": 0.0803, "lr": 1.2708814586862016e-08, "epoch": 1.792457955137056, "percentage": 98.99, "elapsed_time": "1 day, 8:23:24", "remaining_time": "0:19:52", "throughput": 554.59, "total_tokens": 64667504} {"current_steps": 39600, "total_steps": 40000, "loss": 0.0664, "lr": 1.2397742806111168e-08, "epoch": 1.792684307023699, "percentage": 99.0, "elapsed_time": "1 day, 8:23:28", "remaining_time": "0:19:37", "throughput": 554.64, "total_tokens": 64675472} {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.12190044671297073, "epoch": 1.792684307023699, "percentage": 99.0, "elapsed_time": "1 day, 8:31:10", "remaining_time": "0:19:42", "throughput": 552.45, "total_tokens": 64675472} {"current_steps": 39605, "total_steps": 40000, "loss": 0.133, "lr": 1.209052442764369e-08, "epoch": 1.792910658910342, "percentage": 99.01, "elapsed_time": "1 day, 8:31:14", "remaining_time": "0:19:27", "throughput": 552.5, "total_tokens": 64683440} {"current_steps": 39610, "total_steps": 40000, "loss": 0.1354, "lr": 1.17871594988328e-08, "epoch": 1.7931370107969848, "percentage": 99.02, "elapsed_time": "1 day, 8:31:17", "remaining_time": "0:19:12", "throughput": 552.55, "total_tokens": 64691408} {"current_steps": 39615, "total_steps": 40000, "loss": 0.145, "lr": 1.1487648066466072e-08, "epoch": 1.7933633626836278, "percentage": 99.04, "elapsed_time": "1 day, 8:31:21", "remaining_time": "0:18:57", "throughput": 552.6, "total_tokens": 64699312} {"current_steps": 39620, "total_steps": 40000, "loss": 0.0943, "lr": 1.1191990176728784e-08, "epoch": 1.7935897145702708, "percentage": 99.05, "elapsed_time": "1 day, 8:31:24", "remaining_time": "0:18:42", "throughput": 552.66, "total_tokens": 64708080} {"current_steps": 39625, "total_steps": 40000, "loss": 0.1229, "lr": 1.0900185875215018e-08, "epoch": 1.7938160664569138, "percentage": 99.06, "elapsed_time": "1 day, 8:31:27", "remaining_time": "0:18:28", "throughput": 552.72, "total_tokens": 64716112} {"current_steps": 39630, "total_steps": 40000, "loss": 0.1163, "lr": 1.0612235206924891e-08, "epoch": 1.7940424183435568, "percentage": 99.08, "elapsed_time": "1 day, 8:31:30", "remaining_time": "0:18:13", "throughput": 552.77, "total_tokens": 64724048} {"current_steps": 39635, "total_steps": 40000, "loss": 0.1443, "lr": 1.0328138216264549e-08, "epoch": 1.7942687702301998, "percentage": 99.09, "elapsed_time": "1 day, 8:31:33", "remaining_time": "0:17:58", "throughput": 552.83, "total_tokens": 64732624} {"current_steps": 39640, "total_steps": 40000, "loss": 0.1187, "lr": 1.004789494704339e-08, "epoch": 1.7944951221168428, "percentage": 99.1, "elapsed_time": "1 day, 8:31:36", "remaining_time": "0:17:43", "throughput": 552.88, "total_tokens": 64740144} {"current_steps": 39645, "total_steps": 40000, "loss": 0.1612, "lr": 9.771505442482397e-09, "epoch": 1.7947214740034858, "percentage": 99.11, "elapsed_time": "1 day, 8:31:40", "remaining_time": "0:17:28", "throughput": 552.93, "total_tokens": 64747952} {"current_steps": 39650, "total_steps": 40000, "loss": 0.1003, "lr": 9.498969745200259e-09, "epoch": 1.7949478258901288, "percentage": 99.12, "elapsed_time": "1 day, 8:31:43", "remaining_time": "0:17:13", "throughput": 552.98, "total_tokens": 64756336} {"current_steps": 39655, "total_steps": 40000, "loss": 0.0983, "lr": 9.230287897230017e-09, "epoch": 1.7951741777767718, "percentage": 99.14, "elapsed_time": "1 day, 8:31:46", "remaining_time": "0:16:58", "throughput": 553.03, "total_tokens": 64763824} {"current_steps": 39660, "total_steps": 40000, "loss": 0.1973, "lr": 8.965459940002419e-09, "epoch": 1.7954005296634148, "percentage": 99.15, "elapsed_time": "1 day, 8:31:49", "remaining_time": "0:16:43", "throughput": 553.09, "total_tokens": 64771856} {"current_steps": 39665, "total_steps": 40000, "loss": 0.1569, "lr": 8.704485914357019e-09, "epoch": 1.7956268815500578, "percentage": 99.16, "elapsed_time": "1 day, 8:31:52", "remaining_time": "0:16:29", "throughput": 553.15, "total_tokens": 64780784} {"current_steps": 39670, "total_steps": 40000, "loss": 0.1347, "lr": 8.447365860539402e-09, "epoch": 1.7958532334367008, "percentage": 99.17, "elapsed_time": "1 day, 8:31:55", "remaining_time": "0:16:14", "throughput": 553.2, "total_tokens": 64788912} {"current_steps": 39675, "total_steps": 40000, "loss": 0.1127, "lr": 8.194099818201184e-09, "epoch": 1.7960795853233438, "percentage": 99.19, "elapsed_time": "1 day, 8:31:59", "remaining_time": "0:15:59", "throughput": 553.25, "total_tokens": 64796112} {"current_steps": 39680, "total_steps": 40000, "loss": 0.1121, "lr": 7.944687826400011e-09, "epoch": 1.7963059372099868, "percentage": 99.2, "elapsed_time": "1 day, 8:32:02", "remaining_time": "0:15:44", "throughput": 553.31, "total_tokens": 64804592} {"current_steps": 39685, "total_steps": 40000, "loss": 0.1219, "lr": 7.699129923599557e-09, "epoch": 1.7965322890966298, "percentage": 99.21, "elapsed_time": "1 day, 8:32:05", "remaining_time": "0:15:29", "throughput": 553.37, "total_tokens": 64813904} {"current_steps": 39690, "total_steps": 40000, "loss": 0.1145, "lr": 7.457426147663982e-09, "epoch": 1.7967586409832728, "percentage": 99.22, "elapsed_time": "1 day, 8:32:08", "remaining_time": "0:15:14", "throughput": 553.42, "total_tokens": 64822000} {"current_steps": 39695, "total_steps": 40000, "loss": 0.1197, "lr": 7.219576535871797e-09, "epoch": 1.7969849928699155, "percentage": 99.24, "elapsed_time": "1 day, 8:32:12", "remaining_time": "0:14:59", "throughput": 553.48, "total_tokens": 64830192} {"current_steps": 39700, "total_steps": 40000, "loss": 0.1398, "lr": 6.985581124896445e-09, "epoch": 1.7972113447565585, "percentage": 99.25, "elapsed_time": "1 day, 8:32:15", "remaining_time": "0:14:45", "throughput": 553.53, "total_tokens": 64838256} {"current_steps": 39705, "total_steps": 40000, "loss": 0.1343, "lr": 6.755439950828501e-09, "epoch": 1.7974376966432015, "percentage": 99.26, "elapsed_time": "1 day, 8:32:18", "remaining_time": "0:14:30", "throughput": 553.59, "total_tokens": 64846256} {"current_steps": 39710, "total_steps": 40000, "loss": 0.0959, "lr": 6.5291530491562444e-09, "epoch": 1.7976640485298445, "percentage": 99.28, "elapsed_time": "1 day, 8:32:21", "remaining_time": "0:14:15", "throughput": 553.65, "total_tokens": 64854992} {"current_steps": 39715, "total_steps": 40000, "loss": 0.1142, "lr": 6.3067204547739845e-09, "epoch": 1.7978904004164875, "percentage": 99.29, "elapsed_time": "1 day, 8:32:24", "remaining_time": "0:14:00", "throughput": 553.7, "total_tokens": 64862928} {"current_steps": 39720, "total_steps": 40000, "loss": 0.1464, "lr": 6.088142201987612e-09, "epoch": 1.7981167523031303, "percentage": 99.3, "elapsed_time": "1 day, 8:32:28", "remaining_time": "0:13:45", "throughput": 553.76, "total_tokens": 64871312} {"current_steps": 39725, "total_steps": 40000, "loss": 0.1558, "lr": 5.873418324503499e-09, "epoch": 1.7983431041897733, "percentage": 99.31, "elapsed_time": "1 day, 8:32:31", "remaining_time": "0:13:30", "throughput": 553.81, "total_tokens": 64879536} {"current_steps": 39730, "total_steps": 40000, "loss": 0.1274, "lr": 5.6625488554340465e-09, "epoch": 1.7985694560764163, "percentage": 99.33, "elapsed_time": "1 day, 8:32:34", "remaining_time": "0:13:16", "throughput": 553.87, "total_tokens": 64888112} {"current_steps": 39735, "total_steps": 40000, "loss": 0.0931, "lr": 5.455533827297688e-09, "epoch": 1.7987958079630593, "percentage": 99.34, "elapsed_time": "1 day, 8:32:37", "remaining_time": "0:13:01", "throughput": 553.92, "total_tokens": 64896080} {"current_steps": 39740, "total_steps": 40000, "loss": 0.0983, "lr": 5.252373272018885e-09, "epoch": 1.7990221598497023, "percentage": 99.35, "elapsed_time": "1 day, 8:32:40", "remaining_time": "0:12:46", "throughput": 553.98, "total_tokens": 64904720} {"current_steps": 39745, "total_steps": 40000, "loss": 0.1248, "lr": 5.053067220925356e-09, "epoch": 1.7992485117363453, "percentage": 99.36, "elapsed_time": "1 day, 8:32:44", "remaining_time": "0:12:31", "throughput": 554.04, "total_tokens": 64913072} {"current_steps": 39750, "total_steps": 40000, "loss": 0.1849, "lr": 4.857615704759177e-09, "epoch": 1.7994748636229883, "percentage": 99.38, "elapsed_time": "1 day, 8:32:47", "remaining_time": "0:12:16", "throughput": 554.09, "total_tokens": 64920688} {"current_steps": 39755, "total_steps": 40000, "loss": 0.1105, "lr": 4.666018753654577e-09, "epoch": 1.7997012155096312, "percentage": 99.39, "elapsed_time": "1 day, 8:32:50", "remaining_time": "0:12:02", "throughput": 554.14, "total_tokens": 64928976} {"current_steps": 39760, "total_steps": 40000, "loss": 0.1402, "lr": 4.478276397162917e-09, "epoch": 1.7999275673962742, "percentage": 99.4, "elapsed_time": "1 day, 8:32:53", "remaining_time": "0:11:47", "throughput": 554.19, "total_tokens": 64936560} {"current_steps": 39765, "total_steps": 40000, "loss": 0.1663, "lr": 4.294388664233262e-09, "epoch": 1.8001539192829172, "percentage": 99.41, "elapsed_time": "1 day, 8:32:56", "remaining_time": "0:11:32", "throughput": 554.25, "total_tokens": 64944912} {"current_steps": 39770, "total_steps": 40000, "loss": 0.1442, "lr": 4.114355583223484e-09, "epoch": 1.8003802711695602, "percentage": 99.42, "elapsed_time": "1 day, 8:32:59", "remaining_time": "0:11:17", "throughput": 554.31, "total_tokens": 64953360} {"current_steps": 39775, "total_steps": 40000, "loss": 0.106, "lr": 3.9381771818974845e-09, "epoch": 1.8006066230562032, "percentage": 99.44, "elapsed_time": "1 day, 8:33:02", "remaining_time": "0:11:02", "throughput": 554.36, "total_tokens": 64961264} {"current_steps": 39780, "total_steps": 40000, "loss": 0.1566, "lr": 3.765853487427973e-09, "epoch": 1.8008329749428462, "percentage": 99.45, "elapsed_time": "1 day, 8:33:06", "remaining_time": "0:10:48", "throughput": 554.41, "total_tokens": 64968912} {"current_steps": 39785, "total_steps": 40000, "loss": 0.1187, "lr": 3.5973845263825857e-09, "epoch": 1.8010593268294892, "percentage": 99.46, "elapsed_time": "1 day, 8:33:09", "remaining_time": "0:10:33", "throughput": 554.46, "total_tokens": 64976720} {"current_steps": 39790, "total_steps": 40000, "loss": 0.1048, "lr": 3.4327703247488684e-09, "epoch": 1.8012856787161322, "percentage": 99.48, "elapsed_time": "1 day, 8:33:12", "remaining_time": "0:10:18", "throughput": 554.51, "total_tokens": 64984368} {"current_steps": 39795, "total_steps": 40000, "loss": 0.1549, "lr": 3.2720109079037443e-09, "epoch": 1.8015120306027752, "percentage": 99.49, "elapsed_time": "1 day, 8:33:15", "remaining_time": "0:10:03", "throughput": 554.56, "total_tokens": 64992016} {"current_steps": 39800, "total_steps": 40000, "loss": 0.0694, "lr": 3.1151063006468193e-09, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "1 day, 8:33:18", "remaining_time": "0:09:48", "throughput": 554.61, "total_tokens": 64999728} {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.12190044671297073, "epoch": 1.8017383824894182, "percentage": 99.5, "elapsed_time": "1 day, 8:41:01", "remaining_time": "0:09:51", "throughput": 552.43, "total_tokens": 64999728} {"current_steps": 39805, "total_steps": 40000, "loss": 0.0865, "lr": 2.962056527169854e-09, "epoch": 1.801964734376061, "percentage": 99.51, "elapsed_time": "1 day, 8:41:05", "remaining_time": "0:09:36", "throughput": 552.48, "total_tokens": 65007856} {"current_steps": 39810, "total_steps": 40000, "loss": 0.1475, "lr": 2.8128616110761898e-09, "epoch": 1.802191086262704, "percentage": 99.52, "elapsed_time": "1 day, 8:41:08", "remaining_time": "0:09:21", "throughput": 552.54, "total_tokens": 65016432} {"current_steps": 39815, "total_steps": 40000, "loss": 0.1189, "lr": 2.6675215753724223e-09, "epoch": 1.802417438149347, "percentage": 99.54, "elapsed_time": "1 day, 8:41:11", "remaining_time": "0:09:06", "throughput": 552.59, "total_tokens": 65024112} {"current_steps": 39820, "total_steps": 40000, "loss": 0.1035, "lr": 2.5260364424739557e-09, "epoch": 1.80264379003599, "percentage": 99.55, "elapsed_time": "1 day, 8:41:14", "remaining_time": "0:08:51", "throughput": 552.64, "total_tokens": 65031920} {"current_steps": 39825, "total_steps": 40000, "loss": 0.1312, "lr": 2.3884062341994475e-09, "epoch": 1.802870141922633, "percentage": 99.56, "elapsed_time": "1 day, 8:41:17", "remaining_time": "0:08:37", "throughput": 552.69, "total_tokens": 65039536} {"current_steps": 39830, "total_steps": 40000, "loss": 0.1956, "lr": 2.25463097177081e-09, "epoch": 1.803096493809276, "percentage": 99.58, "elapsed_time": "1 day, 8:41:20", "remaining_time": "0:08:22", "throughput": 552.75, "total_tokens": 65047632} {"current_steps": 39835, "total_steps": 40000, "loss": 0.0732, "lr": 2.1247106758215397e-09, "epoch": 1.8033228456959187, "percentage": 99.59, "elapsed_time": "1 day, 8:41:24", "remaining_time": "0:08:07", "throughput": 552.8, "total_tokens": 65055792} {"current_steps": 39840, "total_steps": 40000, "loss": 0.1482, "lr": 1.998645366382834e-09, "epoch": 1.8035491975825617, "percentage": 99.6, "elapsed_time": "1 day, 8:41:27", "remaining_time": "0:07:52", "throughput": 552.86, "total_tokens": 65064240} {"current_steps": 39845, "total_steps": 40000, "loss": 0.1216, "lr": 1.876435062897475e-09, "epoch": 1.8037755494692047, "percentage": 99.61, "elapsed_time": "1 day, 8:41:30", "remaining_time": "0:07:37", "throughput": 552.91, "total_tokens": 65072528} {"current_steps": 39850, "total_steps": 40000, "loss": 0.1082, "lr": 1.758079784211497e-09, "epoch": 1.8040019013558477, "percentage": 99.62, "elapsed_time": "1 day, 8:41:33", "remaining_time": "0:07:23", "throughput": 552.96, "total_tokens": 65080432} {"current_steps": 39855, "total_steps": 40000, "loss": 0.1576, "lr": 1.6435795485797434e-09, "epoch": 1.8042282532424907, "percentage": 99.64, "elapsed_time": "1 day, 8:41:36", "remaining_time": "0:07:08", "throughput": 553.02, "total_tokens": 65088720} {"current_steps": 39860, "total_steps": 40000, "loss": 0.1393, "lr": 1.5329343736547596e-09, "epoch": 1.8044546051291337, "percentage": 99.65, "elapsed_time": "1 day, 8:41:40", "remaining_time": "0:06:53", "throughput": 553.07, "total_tokens": 65096752} {"current_steps": 39865, "total_steps": 40000, "loss": 0.1204, "lr": 1.4261442765006739e-09, "epoch": 1.8046809570157767, "percentage": 99.66, "elapsed_time": "1 day, 8:41:43", "remaining_time": "0:06:38", "throughput": 553.13, "total_tokens": 65105328} {"current_steps": 39870, "total_steps": 40000, "loss": 0.1707, "lr": 1.3232092735876445e-09, "epoch": 1.8049073089024197, "percentage": 99.67, "elapsed_time": "1 day, 8:41:46", "remaining_time": "0:06:23", "throughput": 553.19, "total_tokens": 65113456} {"current_steps": 39875, "total_steps": 40000, "loss": 0.0651, "lr": 1.2241293807918607e-09, "epoch": 1.8051336607890627, "percentage": 99.69, "elapsed_time": "1 day, 8:41:49", "remaining_time": "0:06:08", "throughput": 553.24, "total_tokens": 65121552} {"current_steps": 39880, "total_steps": 40000, "loss": 0.1315, "lr": 1.128904613387216e-09, "epoch": 1.8053600126757057, "percentage": 99.7, "elapsed_time": "1 day, 8:41:52", "remaining_time": "0:05:54", "throughput": 553.29, "total_tokens": 65129296} {"current_steps": 39885, "total_steps": 40000, "loss": 0.1189, "lr": 1.0375349860591853e-09, "epoch": 1.8055863645623487, "percentage": 99.71, "elapsed_time": "1 day, 8:41:55", "remaining_time": "0:05:39", "throughput": 553.35, "total_tokens": 65137808} {"current_steps": 39890, "total_steps": 40000, "loss": 0.1212, "lr": 9.5002051290205e-10, "epoch": 1.8058127164489917, "percentage": 99.72, "elapsed_time": "1 day, 8:41:59", "remaining_time": "0:05:24", "throughput": 553.4, "total_tokens": 65145744} {"current_steps": 39895, "total_steps": 40000, "loss": 0.1124, "lr": 8.663612074077954e-10, "epoch": 1.8060390683356347, "percentage": 99.74, "elapsed_time": "1 day, 8:42:02", "remaining_time": "0:05:09", "throughput": 553.45, "total_tokens": 65153872} {"current_steps": 39900, "total_steps": 40000, "loss": 0.0888, "lr": 7.865570824799884e-10, "epoch": 1.8062654202222777, "percentage": 99.75, "elapsed_time": "1 day, 8:42:05", "remaining_time": "0:04:55", "throughput": 553.51, "total_tokens": 65162704} {"current_steps": 39905, "total_steps": 40000, "loss": 0.125, "lr": 7.106081504254514e-10, "epoch": 1.8064917721089206, "percentage": 99.76, "elapsed_time": "1 day, 8:42:08", "remaining_time": "0:04:40", "throughput": 553.57, "total_tokens": 65171152} {"current_steps": 39910, "total_steps": 40000, "loss": 0.1021, "lr": 6.385144229570372e-10, "epoch": 1.8067181239955636, "percentage": 99.78, "elapsed_time": "1 day, 8:42:12", "remaining_time": "0:04:25", "throughput": 553.62, "total_tokens": 65179472} {"current_steps": 39915, "total_steps": 40000, "loss": 0.1658, "lr": 5.70275911190854e-10, "epoch": 1.8069444758822066, "percentage": 99.79, "elapsed_time": "1 day, 8:42:15", "remaining_time": "0:04:10", "throughput": 553.67, "total_tokens": 65187056} {"current_steps": 39920, "total_steps": 40000, "loss": 0.1041, "lr": 5.058926256490403e-10, "epoch": 1.8071708277688494, "percentage": 99.8, "elapsed_time": "1 day, 8:42:18", "remaining_time": "0:03:55", "throughput": 553.73, "total_tokens": 65195984} {"current_steps": 39925, "total_steps": 40000, "loss": 0.112, "lr": 4.4536457626254134e-10, "epoch": 1.8073971796554924, "percentage": 99.81, "elapsed_time": "1 day, 8:42:21", "remaining_time": "0:03:41", "throughput": 553.79, "total_tokens": 65204432} {"current_steps": 39930, "total_steps": 40000, "loss": 0.1239, "lr": 3.88691772365557e-10, "epoch": 1.8076235315421354, "percentage": 99.83, "elapsed_time": "1 day, 8:42:25", "remaining_time": "0:03:26", "throughput": 553.85, "total_tokens": 65212528} {"current_steps": 39935, "total_steps": 40000, "loss": 0.0597, "lr": 3.358742226955425e-10, "epoch": 1.8078498834287784, "percentage": 99.84, "elapsed_time": "1 day, 8:42:28", "remaining_time": "0:03:11", "throughput": 553.9, "total_tokens": 65220112} {"current_steps": 39940, "total_steps": 40000, "loss": 0.0988, "lr": 2.8691193539875925e-10, "epoch": 1.8080762353154214, "percentage": 99.85, "elapsed_time": "1 day, 8:42:31", "remaining_time": "0:02:56", "throughput": 553.95, "total_tokens": 65228112} {"current_steps": 39945, "total_steps": 40000, "loss": 0.163, "lr": 2.418049180274995e-10, "epoch": 1.8083025872020644, "percentage": 99.86, "elapsed_time": "1 day, 8:42:34", "remaining_time": "0:02:42", "throughput": 554.0, "total_tokens": 65236176} {"current_steps": 39950, "total_steps": 40000, "loss": 0.1462, "lr": 2.005531775373104e-10, "epoch": 1.8085289390887072, "percentage": 99.88, "elapsed_time": "1 day, 8:42:37", "remaining_time": "0:02:27", "throughput": 554.05, "total_tokens": 65244080} {"current_steps": 39955, "total_steps": 40000, "loss": 0.0597, "lr": 1.6315672028699435e-10, "epoch": 1.8087552909753501, "percentage": 99.89, "elapsed_time": "1 day, 8:42:40", "remaining_time": "0:02:12", "throughput": 554.1, "total_tokens": 65251696} {"current_steps": 39960, "total_steps": 40000, "loss": 0.0987, "lr": 1.2961555204693555e-10, "epoch": 1.8089816428619931, "percentage": 99.9, "elapsed_time": "1 day, 8:42:43", "remaining_time": "0:01:57", "throughput": 554.16, "total_tokens": 65259664} {"current_steps": 39965, "total_steps": 40000, "loss": 0.1236, "lr": 9.992967798799768e-11, "epoch": 1.8092079947486361, "percentage": 99.91, "elapsed_time": "1 day, 8:42:47", "remaining_time": "0:01:43", "throughput": 554.22, "total_tokens": 65268368} {"current_steps": 39970, "total_steps": 40000, "loss": 0.0717, "lr": 7.409910268707521e-11, "epoch": 1.8094343466352791, "percentage": 99.92, "elapsed_time": "1 day, 8:42:50", "remaining_time": "0:01:28", "throughput": 554.27, "total_tokens": 65276176} {"current_steps": 39975, "total_steps": 40000, "loss": 0.1418, "lr": 5.212383012986877e-11, "epoch": 1.8096606985219221, "percentage": 99.94, "elapsed_time": "1 day, 8:42:53", "remaining_time": "0:01:13", "throughput": 554.32, "total_tokens": 65284688} {"current_steps": 39980, "total_steps": 40000, "loss": 0.147, "lr": 3.400386370533415e-11, "epoch": 1.8098870504085651, "percentage": 99.95, "elapsed_time": "1 day, 8:42:56", "remaining_time": "0:00:58", "throughput": 554.38, "total_tokens": 65293424} {"current_steps": 39985, "total_steps": 40000, "loss": 0.1032, "lr": 1.9739206205682258e-11, "epoch": 1.8101134022952081, "percentage": 99.96, "elapsed_time": "1 day, 8:42:59", "remaining_time": "0:00:44", "throughput": 554.44, "total_tokens": 65301296} {"current_steps": 39990, "total_steps": 40000, "loss": 0.1633, "lr": 9.329859829154685e-12, "epoch": 1.8103397541818511, "percentage": 99.98, "elapsed_time": "1 day, 8:43:02", "remaining_time": "0:00:29", "throughput": 554.49, "total_tokens": 65309104} {"current_steps": 39995, "total_steps": 40000, "loss": 0.1227, "lr": 2.7758261855748148e-12, "epoch": 1.810566106068494, "percentage": 99.99, "elapsed_time": "1 day, 8:43:06", "remaining_time": "0:00:14", "throughput": 554.54, "total_tokens": 65317552} {"current_steps": 40000, "total_steps": 40000, "loss": 0.1083, "lr": 7.710628524559838e-14, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "1 day, 8:43:09", "remaining_time": "0:00:00", "throughput": 554.6, "total_tokens": 65325648} {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.12190044671297073, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "1 day, 8:50:52", "remaining_time": "0:00:00", "throughput": 552.43, "total_tokens": 65325648} {"current_steps": 40000, "total_steps": 40000, "epoch": 1.810792457955137, "percentage": 100.0, "elapsed_time": "1 day, 8:50:52", "remaining_time": "0:00:00", "throughput": 552.42, "total_tokens": 65325648}