{"current_steps": 5, "total_steps": 40000, "loss": 3.6102, "lr": 4.999999876629946e-05, "epoch": 0.004093327875562832, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "9:17:30", "throughput": 390.26, "total_tokens": 1632} {"current_steps": 10, "total_steps": 40000, "loss": 3.4558, "lr": 4.999999375439123e-05, "epoch": 0.008186655751125664, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "6:50:21", "throughput": 524.93, "total_tokens": 3232} {"current_steps": 15, "total_steps": 40000, "loss": 4.2372, "lr": 4.9999984887169785e-05, "epoch": 0.012279983626688497, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "5:50:22", "throughput": 612.69, "total_tokens": 4832} {"current_steps": 20, "total_steps": 40000, "loss": 3.4723, "lr": 4.9999972164636506e-05, "epoch": 0.01637331150225133, "percentage": 0.05, "elapsed_time": "0:00:09", "remaining_time": "5:20:08", "throughput": 672.71, "total_tokens": 6464} {"current_steps": 25, "total_steps": 40000, "loss": 4.1742, "lr": 4.999995558679334e-05, "epoch": 0.020466639377814164, "percentage": 0.06, "elapsed_time": "0:00:11", "remaining_time": "5:01:45", "throughput": 712.18, "total_tokens": 8064} {"current_steps": 30, "total_steps": 40000, "loss": 3.7794, "lr": 4.999993515364287e-05, "epoch": 0.024559967253376995, "percentage": 0.07, "elapsed_time": "0:00:13", "remaining_time": "4:49:35", "throughput": 744.71, "total_tokens": 9712} {"current_steps": 35, "total_steps": 40000, "loss": 3.847, "lr": 4.999991086518822e-05, "epoch": 0.02865329512893983, "percentage": 0.09, "elapsed_time": "0:00:14", "remaining_time": "4:41:13", "throughput": 766.61, "total_tokens": 11328} {"current_steps": 40, "total_steps": 40000, "loss": 3.8781, "lr": 4.999988272143315e-05, "epoch": 0.03274662300450266, "percentage": 0.1, "elapsed_time": "0:00:16", "remaining_time": "4:34:46", "throughput": 786.27, "total_tokens": 12976} {"current_steps": 45, "total_steps": 40000, "loss": 4.6652, "lr": 4.999985072238199e-05, "epoch": 0.036839950880065496, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:29:39", "throughput": 804.26, "total_tokens": 14656} {"current_steps": 50, "total_steps": 40000, "loss": 3.4343, "lr": 4.999981486803969e-05, "epoch": 0.04093327875562833, "percentage": 0.12, "elapsed_time": "0:00:19", "remaining_time": "4:25:38", "throughput": 815.7, "total_tokens": 16272} {"current_steps": 55, "total_steps": 40000, "loss": 2.4121, "lr": 4.999977515841176e-05, "epoch": 0.04502660663119116, "percentage": 0.14, "elapsed_time": "0:00:21", "remaining_time": "4:22:10", "throughput": 825.88, "total_tokens": 17888} {"current_steps": 60, "total_steps": 40000, "loss": 2.0249, "lr": 4.9999731593504344e-05, "epoch": 0.04911993450675399, "percentage": 0.15, "elapsed_time": "0:00:23", "remaining_time": "4:19:16", "throughput": 833.88, "total_tokens": 19488} {"current_steps": 65, "total_steps": 40000, "loss": 1.43, "lr": 4.999968417332415e-05, "epoch": 0.05321326238231682, "percentage": 0.16, "elapsed_time": "0:00:25", "remaining_time": "4:16:52", "throughput": 841.88, "total_tokens": 21120} {"current_steps": 70, "total_steps": 40000, "loss": 1.2797, "lr": 4.999963289787848e-05, "epoch": 0.05730659025787966, "percentage": 0.18, "elapsed_time": "0:00:26", "remaining_time": "4:14:48", "throughput": 848.32, "total_tokens": 22736} {"current_steps": 75, "total_steps": 40000, "loss": 1.4759, "lr": 4.999957776717526e-05, "epoch": 0.06139991813344249, "percentage": 0.19, "elapsed_time": "0:00:28", "remaining_time": "4:12:59", "throughput": 854.55, "total_tokens": 24368} {"current_steps": 80, "total_steps": 40000, "loss": 0.8055, "lr": 4.9999518781222984e-05, "epoch": 0.06549324600900532, "percentage": 0.2, "elapsed_time": "0:00:30", "remaining_time": "4:11:32", "throughput": 860.69, "total_tokens": 26032} {"current_steps": 85, "total_steps": 40000, "loss": 0.4095, "lr": 4.9999455940030746e-05, "epoch": 0.06958657388456815, "percentage": 0.21, "elapsed_time": "0:00:31", "remaining_time": "4:10:07", "throughput": 865.59, "total_tokens": 27664} {"current_steps": 90, "total_steps": 40000, "loss": 1.4147, "lr": 4.999938924360824e-05, "epoch": 0.07367990176013099, "percentage": 0.22, "elapsed_time": "0:00:33", "remaining_time": "4:08:50", "throughput": 870.08, "total_tokens": 29296} {"current_steps": 95, "total_steps": 40000, "loss": 0.6752, "lr": 4.999931869196575e-05, "epoch": 0.07777322963569382, "percentage": 0.24, "elapsed_time": "0:00:35", "remaining_time": "4:07:43", "throughput": 873.6, "total_tokens": 30912} {"current_steps": 100, "total_steps": 40000, "loss": 0.7675, "lr": 4.999924428511416e-05, "epoch": 0.08186655751125665, "percentage": 0.25, "elapsed_time": "0:00:37", "remaining_time": "4:06:45", "throughput": 875.77, "total_tokens": 32496} {"current_steps": 105, "total_steps": 40000, "loss": 1.1666, "lr": 4.999916602306494e-05, "epoch": 0.08595988538681948, "percentage": 0.26, "elapsed_time": "0:00:38", "remaining_time": "4:05:49", "throughput": 879.98, "total_tokens": 34160} {"current_steps": 110, "total_steps": 40000, "loss": 0.6598, "lr": 4.999908390583016e-05, "epoch": 0.09005321326238232, "percentage": 0.27, "elapsed_time": "0:00:40", "remaining_time": "4:04:59", "throughput": 882.62, "total_tokens": 35776} {"current_steps": 115, "total_steps": 40000, "loss": 0.7652, "lr": 4.999899793342247e-05, "epoch": 0.09414654113794516, "percentage": 0.29, "elapsed_time": "0:00:42", "remaining_time": "4:04:13", "throughput": 884.28, "total_tokens": 37360} {"current_steps": 120, "total_steps": 40000, "loss": 0.567, "lr": 4.999890810585516e-05, "epoch": 0.09823986901350798, "percentage": 0.3, "elapsed_time": "0:00:43", "remaining_time": "4:03:30", "throughput": 885.47, "total_tokens": 38928} {"current_steps": 125, "total_steps": 40000, "loss": 0.688, "lr": 4.999881442314206e-05, "epoch": 0.10233319688907082, "percentage": 0.31, "elapsed_time": "0:00:45", "remaining_time": "4:02:56", "throughput": 886.97, "total_tokens": 40528} {"current_steps": 130, "total_steps": 40000, "loss": 0.6645, "lr": 4.9998716885297617e-05, "epoch": 0.10642652476463364, "percentage": 0.33, "elapsed_time": "0:00:47", "remaining_time": "4:02:20", "throughput": 890.28, "total_tokens": 42208} {"current_steps": 135, "total_steps": 40000, "loss": 0.5095, "lr": 4.999861549233688e-05, "epoch": 0.11051985264019648, "percentage": 0.34, "elapsed_time": "0:00:49", "remaining_time": "4:01:47", "throughput": 891.08, "total_tokens": 43776} {"current_steps": 140, "total_steps": 40000, "loss": 0.8145, "lr": 4.999851024427548e-05, "epoch": 0.11461318051575932, "percentage": 0.35, "elapsed_time": "0:00:50", "remaining_time": "4:01:15", "throughput": 893.1, "total_tokens": 45408} {"current_steps": 145, "total_steps": 40000, "loss": 0.5856, "lr": 4.999840114112965e-05, "epoch": 0.11870650839132214, "percentage": 0.36, "elapsed_time": "0:00:52", "remaining_time": "4:00:46", "throughput": 895.6, "total_tokens": 47072} {"current_steps": 150, "total_steps": 40000, "loss": 0.3627, "lr": 4.999828818291621e-05, "epoch": 0.12279983626688498, "percentage": 0.38, "elapsed_time": "0:00:54", "remaining_time": "4:00:18", "throughput": 900.94, "total_tokens": 48896} {"current_steps": 155, "total_steps": 40000, "loss": 0.7284, "lr": 4.999817136965259e-05, "epoch": 0.1268931641424478, "percentage": 0.39, "elapsed_time": "0:00:55", "remaining_time": "3:59:52", "throughput": 902.21, "total_tokens": 50512} {"current_steps": 160, "total_steps": 40000, "loss": 0.4016, "lr": 4.9998050701356794e-05, "epoch": 0.13098649201801063, "percentage": 0.4, "elapsed_time": "0:00:57", "remaining_time": "3:59:26", "throughput": 904.02, "total_tokens": 52160} {"current_steps": 165, "total_steps": 40000, "loss": 0.6152, "lr": 4.999792617804744e-05, "epoch": 0.13507981989357348, "percentage": 0.41, "elapsed_time": "0:00:59", "remaining_time": "3:59:03", "throughput": 905.39, "total_tokens": 53792} {"current_steps": 170, "total_steps": 40000, "loss": 0.4422, "lr": 4.9997797799743724e-05, "epoch": 0.1391731477691363, "percentage": 0.43, "elapsed_time": "0:01:01", "remaining_time": "3:58:44", "throughput": 906.51, "total_tokens": 55424} {"current_steps": 175, "total_steps": 40000, "loss": 0.4604, "lr": 4.999766556646545e-05, "epoch": 0.14326647564469913, "percentage": 0.44, "elapsed_time": "0:01:02", "remaining_time": "3:58:23", "throughput": 907.75, "total_tokens": 57056} {"current_steps": 180, "total_steps": 40000, "loss": 0.7316, "lr": 4.9997529478232996e-05, "epoch": 0.14735980352026198, "percentage": 0.45, "elapsed_time": "0:01:04", "remaining_time": "3:58:02", "throughput": 908.28, "total_tokens": 58640} {"current_steps": 185, "total_steps": 40000, "loss": 0.7441, "lr": 4.9997389535067365e-05, "epoch": 0.1514531313958248, "percentage": 0.46, "elapsed_time": "0:01:06", "remaining_time": "3:57:43", "throughput": 909.43, "total_tokens": 60272} {"current_steps": 190, "total_steps": 40000, "loss": 0.649, "lr": 4.999724573699012e-05, "epoch": 0.15554645927138763, "percentage": 0.47, "elapsed_time": "0:01:07", "remaining_time": "3:57:24", "throughput": 909.83, "total_tokens": 61856} {"current_steps": 195, "total_steps": 40000, "loss": 0.5222, "lr": 4.9997098084023457e-05, "epoch": 0.15963978714695046, "percentage": 0.49, "elapsed_time": "0:01:09", "remaining_time": "3:57:06", "throughput": 910.24, "total_tokens": 63440} {"current_steps": 200, "total_steps": 40000, "loss": 0.5034, "lr": 4.999694657619013e-05, "epoch": 0.1637331150225133, "percentage": 0.5, "elapsed_time": "0:01:11", "remaining_time": "3:56:50", "throughput": 910.56, "total_tokens": 65024} {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.563525378704071, "epoch": 0.1637331150225133, "percentage": 0.5, "elapsed_time": "0:01:23", "remaining_time": "4:38:01", "throughput": 775.68, "total_tokens": 65024} {"current_steps": 205, "total_steps": 40000, "loss": 0.574, "lr": 4.999679121351352e-05, "epoch": 0.16782644289807613, "percentage": 0.51, "elapsed_time": "0:01:26", "remaining_time": "4:41:25", "throughput": 765.92, "total_tokens": 66624} {"current_steps": 210, "total_steps": 40000, "loss": 0.5569, "lr": 4.9996631996017565e-05, "epoch": 0.17191977077363896, "percentage": 0.53, "elapsed_time": "0:01:28", "remaining_time": "4:40:10", "throughput": 769.32, "total_tokens": 68256} {"current_steps": 215, "total_steps": 40000, "loss": 0.4248, "lr": 4.9996468923726835e-05, "epoch": 0.1760130986492018, "percentage": 0.54, "elapsed_time": "0:01:30", "remaining_time": "4:39:01", "throughput": 772.31, "total_tokens": 69872} {"current_steps": 220, "total_steps": 40000, "loss": 0.4251, "lr": 4.999630199666647e-05, "epoch": 0.18010642652476463, "percentage": 0.55, "elapsed_time": "0:01:32", "remaining_time": "4:37:49", "throughput": 775.64, "total_tokens": 71504} {"current_steps": 225, "total_steps": 40000, "loss": 0.751, "lr": 4.999613121486222e-05, "epoch": 0.18419975440032746, "percentage": 0.56, "elapsed_time": "0:01:33", "remaining_time": "4:36:40", "throughput": 778.5, "total_tokens": 73104} {"current_steps": 230, "total_steps": 40000, "loss": 0.3124, "lr": 4.999595657834041e-05, "epoch": 0.1882930822758903, "percentage": 0.57, "elapsed_time": "0:01:35", "remaining_time": "4:35:33", "throughput": 781.76, "total_tokens": 74752} {"current_steps": 235, "total_steps": 40000, "loss": 0.6975, "lr": 4.999577808712798e-05, "epoch": 0.19238641015145314, "percentage": 0.59, "elapsed_time": "0:01:37", "remaining_time": "4:34:30", "throughput": 785.05, "total_tokens": 76416} {"current_steps": 240, "total_steps": 40000, "loss": 0.5924, "lr": 4.999559574125244e-05, "epoch": 0.19647973802701596, "percentage": 0.6, "elapsed_time": "0:01:39", "remaining_time": "4:33:30", "throughput": 788.41, "total_tokens": 78096} {"current_steps": 245, "total_steps": 40000, "loss": 0.3889, "lr": 4.9995409540741934e-05, "epoch": 0.20057306590257878, "percentage": 0.61, "elapsed_time": "0:01:40", "remaining_time": "4:32:31", "throughput": 791.01, "total_tokens": 79712} {"current_steps": 250, "total_steps": 40000, "loss": 0.395, "lr": 4.999521948562516e-05, "epoch": 0.20466639377814164, "percentage": 0.62, "elapsed_time": "0:01:42", "remaining_time": "4:31:35", "throughput": 793.99, "total_tokens": 81376} {"current_steps": 255, "total_steps": 40000, "loss": 0.6215, "lr": 4.999502557593143e-05, "epoch": 0.20875972165370446, "percentage": 0.64, "elapsed_time": "0:01:44", "remaining_time": "4:30:42", "throughput": 797.02, "total_tokens": 83056} {"current_steps": 260, "total_steps": 40000, "loss": 0.4952, "lr": 4.999482781169066e-05, "epoch": 0.21285304952926729, "percentage": 0.65, "elapsed_time": "0:01:45", "remaining_time": "4:29:51", "throughput": 799.58, "total_tokens": 84704} {"current_steps": 265, "total_steps": 40000, "loss": 0.6687, "lr": 4.9994626192933324e-05, "epoch": 0.21694637740483014, "percentage": 0.66, "elapsed_time": "0:01:47", "remaining_time": "4:29:01", "throughput": 801.84, "total_tokens": 86320} {"current_steps": 270, "total_steps": 40000, "loss": 0.4238, "lr": 4.999442071969054e-05, "epoch": 0.22103970528039296, "percentage": 0.68, "elapsed_time": "0:01:49", "remaining_time": "4:28:13", "throughput": 803.74, "total_tokens": 87904} {"current_steps": 275, "total_steps": 40000, "loss": 0.4576, "lr": 4.999421139199397e-05, "epoch": 0.2251330331559558, "percentage": 0.69, "elapsed_time": "0:01:51", "remaining_time": "4:27:26", "throughput": 806.31, "total_tokens": 89568} {"current_steps": 280, "total_steps": 40000, "loss": 0.5432, "lr": 4.999399820987592e-05, "epoch": 0.22922636103151864, "percentage": 0.7, "elapsed_time": "0:01:52", "remaining_time": "4:26:41", "throughput": 808.08, "total_tokens": 91152} {"current_steps": 285, "total_steps": 40000, "loss": 0.5303, "lr": 4.999378117336924e-05, "epoch": 0.23331968890708146, "percentage": 0.71, "elapsed_time": "0:01:54", "remaining_time": "4:25:58", "throughput": 809.91, "total_tokens": 92752} {"current_steps": 290, "total_steps": 40000, "loss": 0.4043, "lr": 4.9993560282507415e-05, "epoch": 0.2374130167826443, "percentage": 0.73, "elapsed_time": "0:01:56", "remaining_time": "4:25:16", "throughput": 812.14, "total_tokens": 94400} {"current_steps": 295, "total_steps": 40000, "loss": 0.2186, "lr": 4.9993335537324495e-05, "epoch": 0.2415063446582071, "percentage": 0.74, "elapsed_time": "0:01:57", "remaining_time": "4:24:35", "throughput": 814.04, "total_tokens": 96016} {"current_steps": 300, "total_steps": 40000, "loss": 0.6351, "lr": 4.999310693785516e-05, "epoch": 0.24559967253376996, "percentage": 0.75, "elapsed_time": "0:01:59", "remaining_time": "4:23:57", "throughput": 816.34, "total_tokens": 97696} {"current_steps": 305, "total_steps": 40000, "loss": 0.4, "lr": 4.9992874484134653e-05, "epoch": 0.2496930004093328, "percentage": 0.76, "elapsed_time": "0:02:01", "remaining_time": "4:23:19", "throughput": 817.7, "total_tokens": 99264} {"current_steps": 310, "total_steps": 40000, "loss": 0.3273, "lr": 4.999263817619882e-05, "epoch": 0.2537863282848956, "percentage": 0.78, "elapsed_time": "0:02:03", "remaining_time": "4:22:42", "throughput": 819.3, "total_tokens": 100864} {"current_steps": 315, "total_steps": 40000, "loss": 0.4362, "lr": 4.9992398014084105e-05, "epoch": 0.25787965616045844, "percentage": 0.79, "elapsed_time": "0:02:04", "remaining_time": "4:22:06", "throughput": 820.72, "total_tokens": 102448} {"current_steps": 320, "total_steps": 40000, "loss": 0.3726, "lr": 4.999215399782754e-05, "epoch": 0.26197298403602126, "percentage": 0.8, "elapsed_time": "0:02:06", "remaining_time": "4:21:31", "throughput": 822.11, "total_tokens": 104032} {"current_steps": 325, "total_steps": 40000, "loss": 0.4194, "lr": 4.999190612746675e-05, "epoch": 0.26606631191158414, "percentage": 0.81, "elapsed_time": "0:02:08", "remaining_time": "4:20:57", "throughput": 824.21, "total_tokens": 105712} {"current_steps": 330, "total_steps": 40000, "loss": 0.5308, "lr": 4.999165440303998e-05, "epoch": 0.27015963978714697, "percentage": 0.83, "elapsed_time": "0:02:09", "remaining_time": "4:20:24", "throughput": 826.26, "total_tokens": 107392} {"current_steps": 335, "total_steps": 40000, "loss": 0.6905, "lr": 4.999139882458603e-05, "epoch": 0.2742529676627098, "percentage": 0.84, "elapsed_time": "0:02:11", "remaining_time": "4:19:52", "throughput": 827.88, "total_tokens": 109024} {"current_steps": 340, "total_steps": 40000, "loss": 0.3193, "lr": 4.9991139392144314e-05, "epoch": 0.2783462955382726, "percentage": 0.85, "elapsed_time": "0:02:13", "remaining_time": "4:19:21", "throughput": 829.36, "total_tokens": 110640} {"current_steps": 345, "total_steps": 40000, "loss": 0.6189, "lr": 4.999087610575485e-05, "epoch": 0.28243962341383544, "percentage": 0.86, "elapsed_time": "0:02:15", "remaining_time": "4:18:52", "throughput": 830.56, "total_tokens": 112240} {"current_steps": 350, "total_steps": 40000, "loss": 0.2833, "lr": 4.999060896545824e-05, "epoch": 0.28653295128939826, "percentage": 0.88, "elapsed_time": "0:02:16", "remaining_time": "4:18:23", "throughput": 831.61, "total_tokens": 113808} {"current_steps": 355, "total_steps": 40000, "loss": 0.8729, "lr": 4.999033797129568e-05, "epoch": 0.2906262791649611, "percentage": 0.89, "elapsed_time": "0:02:18", "remaining_time": "4:17:54", "throughput": 832.5, "total_tokens": 115360} {"current_steps": 360, "total_steps": 40000, "loss": 0.3589, "lr": 4.999006312330894e-05, "epoch": 0.29471960704052397, "percentage": 0.9, "elapsed_time": "0:02:20", "remaining_time": "4:17:27", "throughput": 834.61, "total_tokens": 117088} {"current_steps": 365, "total_steps": 40000, "loss": 0.3767, "lr": 4.998978442154043e-05, "epoch": 0.2988129349160868, "percentage": 0.91, "elapsed_time": "0:02:22", "remaining_time": "4:17:00", "throughput": 835.92, "total_tokens": 118704} {"current_steps": 370, "total_steps": 40000, "loss": 0.3743, "lr": 4.9989501866033125e-05, "epoch": 0.3029062627916496, "percentage": 0.92, "elapsed_time": "0:02:23", "remaining_time": "4:16:33", "throughput": 837.08, "total_tokens": 120304} {"current_steps": 375, "total_steps": 40000, "loss": 0.3562, "lr": 4.998921545683059e-05, "epoch": 0.30699959066721244, "percentage": 0.94, "elapsed_time": "0:02:25", "remaining_time": "4:16:07", "throughput": 838.22, "total_tokens": 121904} {"current_steps": 380, "total_steps": 40000, "loss": 0.6493, "lr": 4.9988925193976996e-05, "epoch": 0.31109291854277527, "percentage": 0.95, "elapsed_time": "0:02:27", "remaining_time": "4:15:41", "throughput": 839.55, "total_tokens": 123536} {"current_steps": 385, "total_steps": 40000, "loss": 0.3242, "lr": 4.998863107751711e-05, "epoch": 0.3151862464183381, "percentage": 0.96, "elapsed_time": "0:02:28", "remaining_time": "4:15:16", "throughput": 840.54, "total_tokens": 125120} {"current_steps": 390, "total_steps": 40000, "loss": 0.4788, "lr": 4.998833310749629e-05, "epoch": 0.3192795742939009, "percentage": 0.97, "elapsed_time": "0:02:30", "remaining_time": "4:14:53", "throughput": 841.74, "total_tokens": 126752} {"current_steps": 395, "total_steps": 40000, "loss": 0.5122, "lr": 4.998803128396047e-05, "epoch": 0.3233729021694638, "percentage": 0.99, "elapsed_time": "0:02:32", "remaining_time": "4:14:30", "throughput": 842.99, "total_tokens": 128384} {"current_steps": 400, "total_steps": 40000, "loss": 0.3163, "lr": 4.9987725606956215e-05, "epoch": 0.3274662300450266, "percentage": 1.0, "elapsed_time": "0:02:34", "remaining_time": "4:14:07", "throughput": 843.99, "total_tokens": 129984} {"current_steps": 400, "total_steps": 40000, "eval_loss": 0.38372623920440674, "epoch": 0.3274662300450266, "percentage": 1.0, "elapsed_time": "0:02:46", "remaining_time": "4:34:37", "throughput": 780.97, "total_tokens": 129984} {"current_steps": 405, "total_steps": 40000, "loss": 0.3625, "lr": 4.998741607653066e-05, "epoch": 0.33155955792058944, "percentage": 1.01, "elapsed_time": "0:02:49", "remaining_time": "4:36:13", "throughput": 776.57, "total_tokens": 131648} {"current_steps": 410, "total_steps": 40000, "loss": 0.3394, "lr": 4.9987102692731523e-05, "epoch": 0.33565288579615227, "percentage": 1.03, "elapsed_time": "0:02:51", "remaining_time": "4:35:35", "throughput": 778.22, "total_tokens": 133264} {"current_steps": 415, "total_steps": 40000, "loss": 1.0008, "lr": 4.9986785455607157e-05, "epoch": 0.3397462136717151, "percentage": 1.04, "elapsed_time": "0:02:52", "remaining_time": "4:34:58", "throughput": 779.69, "total_tokens": 134864} {"current_steps": 420, "total_steps": 40000, "loss": 0.4189, "lr": 4.9986464365206456e-05, "epoch": 0.3438395415472779, "percentage": 1.05, "elapsed_time": "0:02:54", "remaining_time": "4:34:22", "throughput": 781.27, "total_tokens": 136480} {"current_steps": 425, "total_steps": 40000, "loss": 0.3872, "lr": 4.9986139421578956e-05, "epoch": 0.3479328694228408, "percentage": 1.06, "elapsed_time": "0:02:56", "remaining_time": "4:33:46", "throughput": 782.73, "total_tokens": 138080} {"current_steps": 430, "total_steps": 40000, "loss": 0.3237, "lr": 4.998581062477477e-05, "epoch": 0.3520261972984036, "percentage": 1.07, "elapsed_time": "0:02:58", "remaining_time": "4:33:11", "throughput": 784.16, "total_tokens": 139680} {"current_steps": 435, "total_steps": 40000, "loss": 0.3466, "lr": 4.998547797484458e-05, "epoch": 0.35611952517396644, "percentage": 1.09, "elapsed_time": "0:02:59", "remaining_time": "4:32:38", "throughput": 785.44, "total_tokens": 141264} {"current_steps": 440, "total_steps": 40000, "loss": 0.3107, "lr": 4.9985141471839706e-05, "epoch": 0.36021285304952927, "percentage": 1.1, "elapsed_time": "0:03:01", "remaining_time": "4:32:04", "throughput": 786.73, "total_tokens": 142848} {"current_steps": 445, "total_steps": 40000, "loss": 0.4151, "lr": 4.998480111581203e-05, "epoch": 0.3643061809250921, "percentage": 1.11, "elapsed_time": "0:03:03", "remaining_time": "4:31:31", "throughput": 788.37, "total_tokens": 144496} {"current_steps": 450, "total_steps": 40000, "loss": 0.3215, "lr": 4.998445690681405e-05, "epoch": 0.3683995088006549, "percentage": 1.12, "elapsed_time": "0:03:05", "remaining_time": "4:30:59", "throughput": 789.88, "total_tokens": 146128} {"current_steps": 455, "total_steps": 40000, "loss": 0.2314, "lr": 4.9984108844898834e-05, "epoch": 0.37249283667621774, "percentage": 1.14, "elapsed_time": "0:03:06", "remaining_time": "4:30:27", "throughput": 791.53, "total_tokens": 147792} {"current_steps": 460, "total_steps": 40000, "loss": 0.3164, "lr": 4.9983756930120076e-05, "epoch": 0.3765861645517806, "percentage": 1.15, "elapsed_time": "0:03:08", "remaining_time": "4:29:57", "throughput": 792.9, "total_tokens": 149408} {"current_steps": 465, "total_steps": 40000, "loss": 0.3356, "lr": 4.9983401162532025e-05, "epoch": 0.38067949242734345, "percentage": 1.16, "elapsed_time": "0:03:10", "remaining_time": "4:29:26", "throughput": 794.33, "total_tokens": 151040} {"current_steps": 470, "total_steps": 40000, "loss": 0.3536, "lr": 4.998304154218955e-05, "epoch": 0.38477282030290627, "percentage": 1.18, "elapsed_time": "0:03:11", "remaining_time": "4:28:57", "throughput": 795.73, "total_tokens": 152672} {"current_steps": 475, "total_steps": 40000, "loss": 0.3244, "lr": 4.998267806914812e-05, "epoch": 0.3888661481784691, "percentage": 1.19, "elapsed_time": "0:03:13", "remaining_time": "4:28:28", "throughput": 797.0, "total_tokens": 154288} {"current_steps": 480, "total_steps": 40000, "loss": 0.2605, "lr": 4.998231074346378e-05, "epoch": 0.3929594760540319, "percentage": 1.2, "elapsed_time": "0:03:15", "remaining_time": "4:28:00", "throughput": 798.71, "total_tokens": 156000} {"current_steps": 485, "total_steps": 40000, "loss": 0.2374, "lr": 4.998193956519317e-05, "epoch": 0.39705280392959474, "percentage": 1.21, "elapsed_time": "0:03:17", "remaining_time": "4:27:33", "throughput": 799.77, "total_tokens": 157584} {"current_steps": 490, "total_steps": 40000, "loss": 0.4397, "lr": 4.9981564534393545e-05, "epoch": 0.40114613180515757, "percentage": 1.23, "elapsed_time": "0:03:18", "remaining_time": "4:27:06", "throughput": 801.2, "total_tokens": 159248} {"current_steps": 495, "total_steps": 40000, "loss": 0.2421, "lr": 4.998118565112272e-05, "epoch": 0.40523945968072045, "percentage": 1.24, "elapsed_time": "0:03:20", "remaining_time": "4:26:41", "throughput": 802.34, "total_tokens": 160864} {"current_steps": 500, "total_steps": 40000, "loss": 0.224, "lr": 4.998080291543914e-05, "epoch": 0.4093327875562833, "percentage": 1.25, "elapsed_time": "0:03:22", "remaining_time": "4:26:14", "throughput": 803.43, "total_tokens": 162464} {"current_steps": 505, "total_steps": 40000, "loss": 0.2903, "lr": 4.9980416327401826e-05, "epoch": 0.4134261154318461, "percentage": 1.26, "elapsed_time": "0:03:23", "remaining_time": "4:25:48", "throughput": 804.59, "total_tokens": 164080} {"current_steps": 510, "total_steps": 40000, "loss": 0.3548, "lr": 4.998002588707038e-05, "epoch": 0.4175194433074089, "percentage": 1.27, "elapsed_time": "0:03:25", "remaining_time": "4:25:23", "throughput": 805.73, "total_tokens": 165696} {"current_steps": 515, "total_steps": 40000, "loss": 0.3312, "lr": 4.997963159450503e-05, "epoch": 0.42161277118297175, "percentage": 1.29, "elapsed_time": "0:03:27", "remaining_time": "4:24:58", "throughput": 807.16, "total_tokens": 167376} {"current_steps": 520, "total_steps": 40000, "loss": 0.4, "lr": 4.9979233449766575e-05, "epoch": 0.42570609905853457, "percentage": 1.3, "elapsed_time": "0:03:29", "remaining_time": "4:24:33", "throughput": 808.43, "total_tokens": 169024} {"current_steps": 525, "total_steps": 40000, "loss": 0.2647, "lr": 4.997883145291641e-05, "epoch": 0.4297994269340974, "percentage": 1.31, "elapsed_time": "0:03:30", "remaining_time": "4:24:10", "throughput": 809.53, "total_tokens": 170656} {"current_steps": 530, "total_steps": 40000, "loss": 0.2915, "lr": 4.9978425604016536e-05, "epoch": 0.4338927548096603, "percentage": 1.32, "elapsed_time": "0:03:32", "remaining_time": "4:23:47", "throughput": 810.59, "total_tokens": 172272} {"current_steps": 535, "total_steps": 40000, "loss": 0.3218, "lr": 4.9978015903129536e-05, "epoch": 0.4379860826852231, "percentage": 1.34, "elapsed_time": "0:03:34", "remaining_time": "4:23:23", "throughput": 811.58, "total_tokens": 173872} {"current_steps": 540, "total_steps": 40000, "loss": 0.3858, "lr": 4.997760235031859e-05, "epoch": 0.4420794105607859, "percentage": 1.35, "elapsed_time": "0:03:35", "remaining_time": "4:23:01", "throughput": 812.52, "total_tokens": 175472} {"current_steps": 545, "total_steps": 40000, "loss": 0.2699, "lr": 4.9977184945647473e-05, "epoch": 0.44617273843634875, "percentage": 1.36, "elapsed_time": "0:03:37", "remaining_time": "4:22:38", "throughput": 813.39, "total_tokens": 177056} {"current_steps": 550, "total_steps": 40000, "loss": 0.3265, "lr": 4.997676368918055e-05, "epoch": 0.4502660663119116, "percentage": 1.38, "elapsed_time": "0:03:39", "remaining_time": "4:22:16", "throughput": 814.47, "total_tokens": 178688} {"current_steps": 555, "total_steps": 40000, "loss": 0.2541, "lr": 4.9976338580982794e-05, "epoch": 0.4543593941874744, "percentage": 1.39, "elapsed_time": "0:03:41", "remaining_time": "4:21:54", "throughput": 815.36, "total_tokens": 180288} {"current_steps": 560, "total_steps": 40000, "loss": 0.2496, "lr": 4.9975909621119755e-05, "epoch": 0.4584527220630373, "percentage": 1.4, "elapsed_time": "0:03:42", "remaining_time": "4:21:33", "throughput": 816.42, "total_tokens": 181920} {"current_steps": 565, "total_steps": 40000, "loss": 0.313, "lr": 4.997547680965758e-05, "epoch": 0.4625460499386001, "percentage": 1.41, "elapsed_time": "0:03:44", "remaining_time": "4:21:12", "throughput": 817.35, "total_tokens": 183536} {"current_steps": 570, "total_steps": 40000, "loss": 0.3397, "lr": 4.997504014666302e-05, "epoch": 0.4666393778141629, "percentage": 1.43, "elapsed_time": "0:03:46", "remaining_time": "4:20:52", "throughput": 818.27, "total_tokens": 185152} {"current_steps": 575, "total_steps": 40000, "loss": 0.3157, "lr": 4.997459963220342e-05, "epoch": 0.47073270568972575, "percentage": 1.44, "elapsed_time": "0:03:47", "remaining_time": "4:20:32", "throughput": 819.55, "total_tokens": 186848} {"current_steps": 580, "total_steps": 40000, "loss": 0.3157, "lr": 4.997415526634671e-05, "epoch": 0.4748260335652886, "percentage": 1.45, "elapsed_time": "0:03:49", "remaining_time": "4:20:11", "throughput": 820.47, "total_tokens": 188464} {"current_steps": 585, "total_steps": 40000, "loss": 0.2606, "lr": 4.99737070491614e-05, "epoch": 0.4789193614408514, "percentage": 1.46, "elapsed_time": "0:03:51", "remaining_time": "4:19:52", "throughput": 821.37, "total_tokens": 190080} {"current_steps": 590, "total_steps": 40000, "loss": 0.4128, "lr": 4.997325498071663e-05, "epoch": 0.4830126893164142, "percentage": 1.47, "elapsed_time": "0:03:53", "remaining_time": "4:19:32", "throughput": 822.11, "total_tokens": 191664} {"current_steps": 595, "total_steps": 40000, "loss": 0.3021, "lr": 4.997279906108211e-05, "epoch": 0.4871060171919771, "percentage": 1.49, "elapsed_time": "0:03:54", "remaining_time": "4:19:13", "throughput": 823.33, "total_tokens": 193360} {"current_steps": 600, "total_steps": 40000, "loss": 0.2862, "lr": 4.9972339290328155e-05, "epoch": 0.4911993450675399, "percentage": 1.5, "elapsed_time": "0:03:56", "remaining_time": "4:18:54", "throughput": 824.4, "total_tokens": 195024} {"current_steps": 600, "total_steps": 40000, "eval_loss": 0.3087887167930603, "epoch": 0.4911993450675399, "percentage": 1.5, "elapsed_time": "0:04:09", "remaining_time": "4:32:33", "throughput": 783.1, "total_tokens": 195024} {"current_steps": 605, "total_steps": 40000, "loss": 0.2527, "lr": 4.9971875668525646e-05, "epoch": 0.49529267294310275, "percentage": 1.51, "elapsed_time": "0:04:12", "remaining_time": "4:33:37", "throughput": 779.93, "total_tokens": 196640} {"current_steps": 610, "total_steps": 40000, "loss": 0.6537, "lr": 4.997140819574609e-05, "epoch": 0.4993860008186656, "percentage": 1.52, "elapsed_time": "0:04:13", "remaining_time": "4:33:11", "throughput": 781.27, "total_tokens": 198320} {"current_steps": 615, "total_steps": 40000, "loss": 0.24, "lr": 4.997093687206159e-05, "epoch": 0.5034793286942284, "percentage": 1.54, "elapsed_time": "0:04:15", "remaining_time": "4:32:47", "throughput": 782.3, "total_tokens": 199936} {"current_steps": 620, "total_steps": 40000, "loss": 0.2263, "lr": 4.997046169754482e-05, "epoch": 0.5075726565697912, "percentage": 1.55, "elapsed_time": "0:04:17", "remaining_time": "4:32:22", "throughput": 783.51, "total_tokens": 201600} {"current_steps": 625, "total_steps": 40000, "loss": 0.2659, "lr": 4.996998267226905e-05, "epoch": 0.511665984445354, "percentage": 1.56, "elapsed_time": "0:04:19", "remaining_time": "4:31:58", "throughput": 784.54, "total_tokens": 203216} {"current_steps": 630, "total_steps": 40000, "loss": 0.2843, "lr": 4.996949979630817e-05, "epoch": 0.5157593123209169, "percentage": 1.57, "elapsed_time": "0:04:20", "remaining_time": "4:31:34", "throughput": 785.44, "total_tokens": 204800} {"current_steps": 635, "total_steps": 40000, "loss": 0.2413, "lr": 4.996901306973663e-05, "epoch": 0.5198526401964797, "percentage": 1.59, "elapsed_time": "0:04:22", "remaining_time": "4:31:10", "throughput": 786.7, "total_tokens": 206480} {"current_steps": 640, "total_steps": 40000, "loss": 0.4085, "lr": 4.996852249262949e-05, "epoch": 0.5239459680720425, "percentage": 1.6, "elapsed_time": "0:04:24", "remaining_time": "4:30:47", "throughput": 787.76, "total_tokens": 208112} {"current_steps": 645, "total_steps": 40000, "loss": 0.2575, "lr": 4.996802806506241e-05, "epoch": 0.5280392959476055, "percentage": 1.61, "elapsed_time": "0:04:25", "remaining_time": "4:30:24", "throughput": 788.68, "total_tokens": 209712} {"current_steps": 650, "total_steps": 40000, "loss": 0.4797, "lr": 4.996752978711164e-05, "epoch": 0.5321326238231683, "percentage": 1.62, "elapsed_time": "0:04:27", "remaining_time": "4:30:01", "throughput": 789.71, "total_tokens": 211344} {"current_steps": 655, "total_steps": 40000, "loss": 0.7303, "lr": 4.996702765885401e-05, "epoch": 0.5362259516987311, "percentage": 1.64, "elapsed_time": "0:04:29", "remaining_time": "4:29:38", "throughput": 790.56, "total_tokens": 212928} {"current_steps": 660, "total_steps": 40000, "loss": 0.2869, "lr": 4.9966521680366964e-05, "epoch": 0.5403192795742939, "percentage": 1.65, "elapsed_time": "0:04:31", "remaining_time": "4:29:17", "throughput": 791.47, "total_tokens": 214544} {"current_steps": 665, "total_steps": 40000, "loss": 0.3516, "lr": 4.9966011851728524e-05, "epoch": 0.5444126074498568, "percentage": 1.66, "elapsed_time": "0:04:32", "remaining_time": "4:28:55", "throughput": 792.51, "total_tokens": 216192} {"current_steps": 670, "total_steps": 40000, "loss": 0.3743, "lr": 4.996549817301731e-05, "epoch": 0.5485059353254196, "percentage": 1.68, "elapsed_time": "0:04:34", "remaining_time": "4:28:34", "throughput": 793.5, "total_tokens": 217824} {"current_steps": 675, "total_steps": 40000, "loss": 0.2479, "lr": 4.9964980644312544e-05, "epoch": 0.5525992632009824, "percentage": 1.69, "elapsed_time": "0:04:36", "remaining_time": "4:28:12", "throughput": 794.64, "total_tokens": 219504} {"current_steps": 680, "total_steps": 40000, "loss": 0.4834, "lr": 4.996445926569403e-05, "epoch": 0.5566925910765452, "percentage": 1.7, "elapsed_time": "0:04:37", "remaining_time": "4:27:51", "throughput": 795.66, "total_tokens": 221152} {"current_steps": 685, "total_steps": 40000, "loss": 0.235, "lr": 4.996393403724218e-05, "epoch": 0.560785918952108, "percentage": 1.71, "elapsed_time": "0:04:39", "remaining_time": "4:27:31", "throughput": 796.79, "total_tokens": 222832} {"current_steps": 690, "total_steps": 40000, "loss": 0.3443, "lr": 4.9963404959037985e-05, "epoch": 0.5648792468276709, "percentage": 1.73, "elapsed_time": "0:04:41", "remaining_time": "4:27:10", "throughput": 797.72, "total_tokens": 224464} {"current_steps": 695, "total_steps": 40000, "loss": 0.3126, "lr": 4.996287203116303e-05, "epoch": 0.5689725747032337, "percentage": 1.74, "elapsed_time": "0:04:43", "remaining_time": "4:26:50", "throughput": 798.53, "total_tokens": 226064} {"current_steps": 700, "total_steps": 40000, "loss": 0.3059, "lr": 4.996233525369951e-05, "epoch": 0.5730659025787965, "percentage": 1.75, "elapsed_time": "0:04:44", "remaining_time": "4:26:30", "throughput": 799.53, "total_tokens": 227728} {"current_steps": 705, "total_steps": 40000, "loss": 0.3004, "lr": 4.99617946267302e-05, "epoch": 0.5771592304543594, "percentage": 1.76, "elapsed_time": "0:04:46", "remaining_time": "4:26:11", "throughput": 800.82, "total_tokens": 229472} {"current_steps": 710, "total_steps": 40000, "loss": 0.2755, "lr": 4.996125015033846e-05, "epoch": 0.5812525583299222, "percentage": 1.77, "elapsed_time": "0:04:48", "remaining_time": "4:25:51", "throughput": 801.66, "total_tokens": 231088} {"current_steps": 715, "total_steps": 40000, "loss": 0.2738, "lr": 4.996070182460827e-05, "epoch": 0.5853458862054851, "percentage": 1.79, "elapsed_time": "0:04:49", "remaining_time": "4:25:32", "throughput": 802.7, "total_tokens": 232768} {"current_steps": 720, "total_steps": 40000, "loss": 0.2964, "lr": 4.996014964962418e-05, "epoch": 0.5894392140810479, "percentage": 1.8, "elapsed_time": "0:04:51", "remaining_time": "4:25:13", "throughput": 803.78, "total_tokens": 234464} {"current_steps": 725, "total_steps": 40000, "loss": 0.3404, "lr": 4.9959593625471344e-05, "epoch": 0.5935325419566108, "percentage": 1.81, "elapsed_time": "0:04:53", "remaining_time": "4:24:55", "throughput": 804.81, "total_tokens": 236144} {"current_steps": 730, "total_steps": 40000, "loss": 0.4304, "lr": 4.995903375223552e-05, "epoch": 0.5976258698321736, "percentage": 1.82, "elapsed_time": "0:04:55", "remaining_time": "4:24:37", "throughput": 805.52, "total_tokens": 237744} {"current_steps": 735, "total_steps": 40000, "loss": 0.4147, "lr": 4.995847003000302e-05, "epoch": 0.6017191977077364, "percentage": 1.84, "elapsed_time": "0:04:56", "remaining_time": "4:24:18", "throughput": 806.2, "total_tokens": 239328} {"current_steps": 740, "total_steps": 40000, "loss": 0.388, "lr": 4.9957902458860804e-05, "epoch": 0.6058125255832992, "percentage": 1.85, "elapsed_time": "0:04:58", "remaining_time": "4:24:00", "throughput": 807.03, "total_tokens": 240960} {"current_steps": 745, "total_steps": 40000, "loss": 0.2681, "lr": 4.995733103889639e-05, "epoch": 0.6099058534588621, "percentage": 1.86, "elapsed_time": "0:05:00", "remaining_time": "4:23:43", "throughput": 808.18, "total_tokens": 242704} {"current_steps": 750, "total_steps": 40000, "loss": 0.2595, "lr": 4.99567557701979e-05, "epoch": 0.6139991813344249, "percentage": 1.88, "elapsed_time": "0:05:02", "remaining_time": "4:23:25", "throughput": 808.84, "total_tokens": 244288} {"current_steps": 755, "total_steps": 40000, "loss": 0.5578, "lr": 4.995617665285403e-05, "epoch": 0.6180925092099877, "percentage": 1.89, "elapsed_time": "0:05:03", "remaining_time": "4:23:08", "throughput": 809.75, "total_tokens": 245952} {"current_steps": 760, "total_steps": 40000, "loss": 0.2558, "lr": 4.99555936869541e-05, "epoch": 0.6221858370855505, "percentage": 1.9, "elapsed_time": "0:05:05", "remaining_time": "4:22:51", "throughput": 810.43, "total_tokens": 247552} {"current_steps": 765, "total_steps": 40000, "loss": 0.2823, "lr": 4.995500687258803e-05, "epoch": 0.6262791649611134, "percentage": 1.91, "elapsed_time": "0:05:07", "remaining_time": "4:22:34", "throughput": 811.27, "total_tokens": 249200} {"current_steps": 770, "total_steps": 40000, "loss": 0.4154, "lr": 4.995441620984628e-05, "epoch": 0.6303724928366762, "percentage": 1.93, "elapsed_time": "0:05:08", "remaining_time": "4:22:17", "throughput": 812.2, "total_tokens": 250880} {"current_steps": 775, "total_steps": 40000, "loss": 0.7548, "lr": 4.995382169881996e-05, "epoch": 0.634465820712239, "percentage": 1.94, "elapsed_time": "0:05:10", "remaining_time": "4:22:00", "throughput": 812.81, "total_tokens": 252464} {"current_steps": 780, "total_steps": 40000, "loss": 0.2438, "lr": 4.9953223339600755e-05, "epoch": 0.6385591485878018, "percentage": 1.95, "elapsed_time": "0:05:12", "remaining_time": "4:21:43", "throughput": 813.48, "total_tokens": 254064} {"current_steps": 785, "total_steps": 40000, "loss": 0.2475, "lr": 4.995262113228091e-05, "epoch": 0.6426524764633648, "percentage": 1.96, "elapsed_time": "0:05:14", "remaining_time": "4:21:27", "throughput": 814.14, "total_tokens": 255664} {"current_steps": 790, "total_steps": 40000, "loss": 0.2237, "lr": 4.995201507695332e-05, "epoch": 0.6467458043389276, "percentage": 1.98, "elapsed_time": "0:05:15", "remaining_time": "4:21:12", "throughput": 814.9, "total_tokens": 257312} {"current_steps": 795, "total_steps": 40000, "loss": 0.2422, "lr": 4.995140517371144e-05, "epoch": 0.6508391322144904, "percentage": 1.99, "elapsed_time": "0:05:17", "remaining_time": "4:20:56", "throughput": 815.78, "total_tokens": 258992} {"current_steps": 800, "total_steps": 40000, "loss": 0.3287, "lr": 4.995079142264932e-05, "epoch": 0.6549324600900532, "percentage": 2.0, "elapsed_time": "0:05:19", "remaining_time": "4:20:40", "throughput": 816.51, "total_tokens": 260624} {"current_steps": 800, "total_steps": 40000, "eval_loss": 0.27478593587875366, "epoch": 0.6549324600900532, "percentage": 2.0, "elapsed_time": "0:05:31", "remaining_time": "4:30:50", "throughput": 785.87, "total_tokens": 260624} {"current_steps": 805, "total_steps": 40000, "loss": 0.3026, "lr": 4.995017382386162e-05, "epoch": 0.6590257879656161, "percentage": 2.01, "elapsed_time": "0:05:34", "remaining_time": "4:31:46", "throughput": 783.25, "total_tokens": 262320} {"current_steps": 810, "total_steps": 40000, "loss": 0.289, "lr": 4.994955237744356e-05, "epoch": 0.6631191158411789, "percentage": 2.02, "elapsed_time": "0:05:36", "remaining_time": "4:31:26", "throughput": 784.01, "total_tokens": 263920} {"current_steps": 815, "total_steps": 40000, "loss": 0.3046, "lr": 4.994892708349101e-05, "epoch": 0.6672124437167417, "percentage": 2.04, "elapsed_time": "0:05:38", "remaining_time": "4:31:07", "throughput": 784.82, "total_tokens": 265536} {"current_steps": 820, "total_steps": 40000, "loss": 0.269, "lr": 4.994829794210035e-05, "epoch": 0.6713057715923045, "percentage": 2.05, "elapsed_time": "0:05:40", "remaining_time": "4:30:48", "throughput": 785.75, "total_tokens": 267200} {"current_steps": 825, "total_steps": 40000, "loss": 0.1973, "lr": 4.994766495336864e-05, "epoch": 0.6753990994678674, "percentage": 2.06, "elapsed_time": "0:05:41", "remaining_time": "4:30:29", "throughput": 786.58, "total_tokens": 268832} {"current_steps": 830, "total_steps": 40000, "loss": 0.291, "lr": 4.994702811739348e-05, "epoch": 0.6794924273434302, "percentage": 2.08, "elapsed_time": "0:05:43", "remaining_time": "4:30:10", "throughput": 787.39, "total_tokens": 270464} {"current_steps": 835, "total_steps": 40000, "loss": 0.2379, "lr": 4.994638743427308e-05, "epoch": 0.683585755218993, "percentage": 2.09, "elapsed_time": "0:05:45", "remaining_time": "4:29:52", "throughput": 788.21, "total_tokens": 272112} {"current_steps": 840, "total_steps": 40000, "loss": 0.1649, "lr": 4.994574290410624e-05, "epoch": 0.6876790830945558, "percentage": 2.1, "elapsed_time": "0:05:46", "remaining_time": "4:29:34", "throughput": 789.2, "total_tokens": 273808} {"current_steps": 845, "total_steps": 40000, "loss": 0.2943, "lr": 4.9945094526992364e-05, "epoch": 0.6917724109701187, "percentage": 2.11, "elapsed_time": "0:05:48", "remaining_time": "4:29:16", "throughput": 789.81, "total_tokens": 275376} {"current_steps": 850, "total_steps": 40000, "loss": 0.2227, "lr": 4.994444230303142e-05, "epoch": 0.6958657388456816, "percentage": 2.12, "elapsed_time": "0:05:50", "remaining_time": "4:28:57", "throughput": 790.96, "total_tokens": 277136} {"current_steps": 855, "total_steps": 40000, "loss": 0.4697, "lr": 4.994378623232402e-05, "epoch": 0.6999590667212444, "percentage": 2.14, "elapsed_time": "0:05:52", "remaining_time": "4:28:39", "throughput": 791.8, "total_tokens": 278784} {"current_steps": 860, "total_steps": 40000, "loss": 0.1946, "lr": 4.99431263149713e-05, "epoch": 0.7040523945968072, "percentage": 2.15, "elapsed_time": "0:05:53", "remaining_time": "4:28:22", "throughput": 792.49, "total_tokens": 280384} {"current_steps": 865, "total_steps": 40000, "loss": 0.2868, "lr": 4.9942462551075056e-05, "epoch": 0.7081457224723701, "percentage": 2.16, "elapsed_time": "0:05:55", "remaining_time": "4:28:04", "throughput": 793.29, "total_tokens": 282032} {"current_steps": 870, "total_steps": 40000, "loss": 0.2335, "lr": 4.994179494073764e-05, "epoch": 0.7122390503479329, "percentage": 2.17, "elapsed_time": "0:05:57", "remaining_time": "4:27:47", "throughput": 794.1, "total_tokens": 283680} {"current_steps": 875, "total_steps": 40000, "loss": 0.2664, "lr": 4.9941123484062e-05, "epoch": 0.7163323782234957, "percentage": 2.19, "elapsed_time": "0:05:58", "remaining_time": "4:27:30", "throughput": 794.94, "total_tokens": 285344} {"current_steps": 880, "total_steps": 40000, "loss": 0.3295, "lr": 4.99404481811517e-05, "epoch": 0.7204257060990585, "percentage": 2.2, "elapsed_time": "0:06:00", "remaining_time": "4:27:13", "throughput": 795.79, "total_tokens": 287024} {"current_steps": 885, "total_steps": 40000, "loss": 0.1972, "lr": 4.9939769032110864e-05, "epoch": 0.7245190339746214, "percentage": 2.21, "elapsed_time": "0:06:02", "remaining_time": "4:26:57", "throughput": 796.51, "total_tokens": 288656} {"current_steps": 890, "total_steps": 40000, "loss": 0.2853, "lr": 4.993908603704423e-05, "epoch": 0.7286123618501842, "percentage": 2.23, "elapsed_time": "0:06:04", "remaining_time": "4:26:40", "throughput": 797.01, "total_tokens": 290208} {"current_steps": 895, "total_steps": 40000, "loss": 0.2194, "lr": 4.9938399196057126e-05, "epoch": 0.732705689725747, "percentage": 2.24, "elapsed_time": "0:06:05", "remaining_time": "4:26:24", "throughput": 797.69, "total_tokens": 291824} {"current_steps": 900, "total_steps": 40000, "loss": 0.2263, "lr": 4.993770850925547e-05, "epoch": 0.7367990176013098, "percentage": 2.25, "elapsed_time": "0:06:07", "remaining_time": "4:26:08", "throughput": 798.36, "total_tokens": 293440} {"current_steps": 905, "total_steps": 40000, "loss": 0.2216, "lr": 4.993701397674577e-05, "epoch": 0.7408923454768727, "percentage": 2.26, "elapsed_time": "0:06:09", "remaining_time": "4:25:51", "throughput": 799.08, "total_tokens": 295072} {"current_steps": 910, "total_steps": 40000, "loss": 0.2774, "lr": 4.993631559863515e-05, "epoch": 0.7449856733524355, "percentage": 2.27, "elapsed_time": "0:06:10", "remaining_time": "4:25:35", "throughput": 799.75, "total_tokens": 296688} {"current_steps": 915, "total_steps": 40000, "loss": 0.2366, "lr": 4.9935613375031283e-05, "epoch": 0.7490790012279983, "percentage": 2.29, "elapsed_time": "0:06:12", "remaining_time": "4:25:19", "throughput": 800.53, "total_tokens": 298352} {"current_steps": 920, "total_steps": 40000, "loss": 0.2836, "lr": 4.993490730604248e-05, "epoch": 0.7531723291035612, "percentage": 2.3, "elapsed_time": "0:06:14", "remaining_time": "4:25:04", "throughput": 801.39, "total_tokens": 300048} {"current_steps": 925, "total_steps": 40000, "loss": 0.176, "lr": 4.993419739177761e-05, "epoch": 0.7572656569791241, "percentage": 2.31, "elapsed_time": "0:06:16", "remaining_time": "4:24:49", "throughput": 802.09, "total_tokens": 301696} {"current_steps": 930, "total_steps": 40000, "loss": 0.283, "lr": 4.9933483632346164e-05, "epoch": 0.7613589848546869, "percentage": 2.33, "elapsed_time": "0:06:17", "remaining_time": "4:24:33", "throughput": 802.59, "total_tokens": 303264} {"current_steps": 935, "total_steps": 40000, "loss": 0.2066, "lr": 4.993276602785821e-05, "epoch": 0.7654523127302497, "percentage": 2.34, "elapsed_time": "0:06:19", "remaining_time": "4:24:18", "throughput": 803.1, "total_tokens": 304832} {"current_steps": 940, "total_steps": 40000, "loss": 0.2582, "lr": 4.993204457842441e-05, "epoch": 0.7695456406058125, "percentage": 2.35, "elapsed_time": "0:06:21", "remaining_time": "4:24:03", "throughput": 803.94, "total_tokens": 306528} {"current_steps": 945, "total_steps": 40000, "loss": 0.2823, "lr": 4.993131928415602e-05, "epoch": 0.7736389684813754, "percentage": 2.36, "elapsed_time": "0:06:22", "remaining_time": "4:23:48", "throughput": 804.48, "total_tokens": 308112} {"current_steps": 950, "total_steps": 40000, "loss": 0.2006, "lr": 4.993059014516489e-05, "epoch": 0.7777322963569382, "percentage": 2.38, "elapsed_time": "0:06:24", "remaining_time": "4:23:33", "throughput": 805.13, "total_tokens": 309744} {"current_steps": 955, "total_steps": 40000, "loss": 0.3147, "lr": 4.9929857161563464e-05, "epoch": 0.781825624232501, "percentage": 2.39, "elapsed_time": "0:06:26", "remaining_time": "4:23:19", "throughput": 805.86, "total_tokens": 311408} {"current_steps": 960, "total_steps": 40000, "loss": 0.2236, "lr": 4.992912033346477e-05, "epoch": 0.7859189521080638, "percentage": 2.4, "elapsed_time": "0:06:28", "remaining_time": "4:23:04", "throughput": 806.47, "total_tokens": 313024} {"current_steps": 965, "total_steps": 40000, "loss": 0.2782, "lr": 4.992837966098245e-05, "epoch": 0.7900122799836267, "percentage": 2.41, "elapsed_time": "0:06:29", "remaining_time": "4:22:50", "throughput": 807.09, "total_tokens": 314656} {"current_steps": 970, "total_steps": 40000, "loss": 0.2999, "lr": 4.992763514423071e-05, "epoch": 0.7941056078591895, "percentage": 2.43, "elapsed_time": "0:06:31", "remaining_time": "4:22:36", "throughput": 807.76, "total_tokens": 316304} {"current_steps": 975, "total_steps": 40000, "loss": 0.2373, "lr": 4.992688678332437e-05, "epoch": 0.7981989357347523, "percentage": 2.44, "elapsed_time": "0:06:33", "remaining_time": "4:22:21", "throughput": 808.23, "total_tokens": 317872} {"current_steps": 980, "total_steps": 40000, "loss": 0.1988, "lr": 4.992613457837884e-05, "epoch": 0.8022922636103151, "percentage": 2.45, "elapsed_time": "0:06:35", "remaining_time": "4:22:07", "throughput": 808.94, "total_tokens": 319536} {"current_steps": 985, "total_steps": 40000, "loss": 0.2113, "lr": 4.992537852951011e-05, "epoch": 0.8063855914858781, "percentage": 2.46, "elapsed_time": "0:06:36", "remaining_time": "4:21:53", "throughput": 809.48, "total_tokens": 321136} {"current_steps": 990, "total_steps": 40000, "loss": 0.1642, "lr": 4.9924618636834785e-05, "epoch": 0.8104789193614409, "percentage": 2.48, "elapsed_time": "0:06:38", "remaining_time": "4:21:39", "throughput": 810.02, "total_tokens": 322736} {"current_steps": 995, "total_steps": 40000, "loss": 0.5577, "lr": 4.9923854900470046e-05, "epoch": 0.8145722472370037, "percentage": 2.49, "elapsed_time": "0:06:40", "remaining_time": "4:21:25", "throughput": 810.47, "total_tokens": 324304} {"current_steps": 1000, "total_steps": 40000, "loss": 0.2047, "lr": 4.992308732053367e-05, "epoch": 0.8186655751125665, "percentage": 2.5, "elapsed_time": "0:06:41", "remaining_time": "4:21:12", "throughput": 811.2, "total_tokens": 325984} {"current_steps": 1000, "total_steps": 40000, "eval_loss": 0.2613275945186615, "epoch": 0.8186655751125665, "percentage": 2.5, "elapsed_time": "0:06:54", "remaining_time": "4:29:18", "throughput": 786.82, "total_tokens": 325984} {"current_steps": 1005, "total_steps": 40000, "loss": 0.2411, "lr": 4.992231589714402e-05, "epoch": 0.8227589029881294, "percentage": 2.51, "elapsed_time": "0:06:57", "remaining_time": "4:29:56", "throughput": 784.84, "total_tokens": 327616} {"current_steps": 1010, "total_steps": 40000, "loss": 0.2084, "lr": 4.992154063042007e-05, "epoch": 0.8268522308636922, "percentage": 2.53, "elapsed_time": "0:06:59", "remaining_time": "4:29:40", "throughput": 785.59, "total_tokens": 329280} {"current_steps": 1015, "total_steps": 40000, "loss": 0.23, "lr": 4.992076152048136e-05, "epoch": 0.830945558739255, "percentage": 2.54, "elapsed_time": "0:07:00", "remaining_time": "4:29:25", "throughput": 786.13, "total_tokens": 330864} {"current_steps": 1020, "total_steps": 40000, "loss": 0.2334, "lr": 4.991997856744807e-05, "epoch": 0.8350388866148178, "percentage": 2.55, "elapsed_time": "0:07:02", "remaining_time": "4:29:09", "throughput": 786.8, "total_tokens": 332496} {"current_steps": 1025, "total_steps": 40000, "loss": 0.3101, "lr": 4.9919191771440905e-05, "epoch": 0.8391322144903807, "percentage": 2.56, "elapsed_time": "0:07:04", "remaining_time": "4:28:54", "throughput": 787.46, "total_tokens": 334128} {"current_steps": 1030, "total_steps": 40000, "loss": 0.2407, "lr": 4.991840113258122e-05, "epoch": 0.8432255423659435, "percentage": 2.57, "elapsed_time": "0:07:06", "remaining_time": "4:28:39", "throughput": 788.13, "total_tokens": 335776} {"current_steps": 1035, "total_steps": 40000, "loss": 0.2527, "lr": 4.9917606650990933e-05, "epoch": 0.8473188702415063, "percentage": 2.59, "elapsed_time": "0:07:07", "remaining_time": "4:28:23", "throughput": 788.63, "total_tokens": 337344} {"current_steps": 1040, "total_steps": 40000, "loss": 0.3076, "lr": 4.9916808326792566e-05, "epoch": 0.8514121981170691, "percentage": 2.6, "elapsed_time": "0:07:09", "remaining_time": "4:28:08", "throughput": 789.2, "total_tokens": 338944} {"current_steps": 1045, "total_steps": 40000, "loss": 0.1662, "lr": 4.9916006160109235e-05, "epoch": 0.855505525992632, "percentage": 2.61, "elapsed_time": "0:07:11", "remaining_time": "4:27:53", "throughput": 789.73, "total_tokens": 340528} {"current_steps": 1050, "total_steps": 40000, "loss": 0.2512, "lr": 4.991520015106464e-05, "epoch": 0.8595988538681948, "percentage": 2.62, "elapsed_time": "0:07:12", "remaining_time": "4:27:38", "throughput": 790.41, "total_tokens": 342176} {"current_steps": 1055, "total_steps": 40000, "loss": 0.2523, "lr": 4.991439029978308e-05, "epoch": 0.8636921817437577, "percentage": 2.64, "elapsed_time": "0:07:14", "remaining_time": "4:27:24", "throughput": 791.01, "total_tokens": 343808} {"current_steps": 1060, "total_steps": 40000, "loss": 0.2458, "lr": 4.9913576606389434e-05, "epoch": 0.8677855096193205, "percentage": 2.65, "elapsed_time": "0:07:16", "remaining_time": "4:27:10", "throughput": 791.78, "total_tokens": 345504} {"current_steps": 1065, "total_steps": 40000, "loss": 0.2696, "lr": 4.991275907100919e-05, "epoch": 0.8718788374948834, "percentage": 2.66, "elapsed_time": "0:07:18", "remaining_time": "4:26:55", "throughput": 792.4, "total_tokens": 347136} {"current_steps": 1070, "total_steps": 40000, "loss": 0.2273, "lr": 4.9911937693768434e-05, "epoch": 0.8759721653704462, "percentage": 2.67, "elapsed_time": "0:07:19", "remaining_time": "4:26:41", "throughput": 793.22, "total_tokens": 348864} {"current_steps": 1075, "total_steps": 40000, "loss": 0.2679, "lr": 4.991111247479382e-05, "epoch": 0.880065493246009, "percentage": 2.69, "elapsed_time": "0:07:21", "remaining_time": "4:26:27", "throughput": 793.75, "total_tokens": 350464} {"current_steps": 1080, "total_steps": 40000, "loss": 0.2386, "lr": 4.9910283414212605e-05, "epoch": 0.8841588211215718, "percentage": 2.7, "elapsed_time": "0:07:23", "remaining_time": "4:26:13", "throughput": 794.39, "total_tokens": 352112} {"current_steps": 1085, "total_steps": 40000, "loss": 0.2269, "lr": 4.990945051215265e-05, "epoch": 0.8882521489971347, "percentage": 2.71, "elapsed_time": "0:07:24", "remaining_time": "4:25:59", "throughput": 794.88, "total_tokens": 353696} {"current_steps": 1090, "total_steps": 40000, "loss": 0.2358, "lr": 4.99086137687424e-05, "epoch": 0.8923454768726975, "percentage": 2.73, "elapsed_time": "0:07:26", "remaining_time": "4:25:45", "throughput": 795.61, "total_tokens": 355392} {"current_steps": 1095, "total_steps": 40000, "loss": 0.211, "lr": 4.9907773184110874e-05, "epoch": 0.8964388047482603, "percentage": 2.74, "elapsed_time": "0:07:28", "remaining_time": "4:25:31", "throughput": 796.21, "total_tokens": 357024} {"current_steps": 1100, "total_steps": 40000, "loss": 0.2122, "lr": 4.9906928758387715e-05, "epoch": 0.9005321326238231, "percentage": 2.75, "elapsed_time": "0:07:30", "remaining_time": "4:25:18", "throughput": 796.77, "total_tokens": 358656} {"current_steps": 1105, "total_steps": 40000, "loss": 0.2386, "lr": 4.9906080491703146e-05, "epoch": 0.904625460499386, "percentage": 2.76, "elapsed_time": "0:07:31", "remaining_time": "4:25:04", "throughput": 797.21, "total_tokens": 360224} {"current_steps": 1110, "total_steps": 40000, "loss": 0.2892, "lr": 4.990522838418797e-05, "epoch": 0.9087187883749488, "percentage": 2.77, "elapsed_time": "0:07:33", "remaining_time": "4:24:51", "throughput": 797.82, "total_tokens": 361872} {"current_steps": 1115, "total_steps": 40000, "loss": 0.2389, "lr": 4.9904372435973604e-05, "epoch": 0.9128121162505116, "percentage": 2.79, "elapsed_time": "0:07:35", "remaining_time": "4:24:37", "throughput": 798.26, "total_tokens": 363440} {"current_steps": 1120, "total_steps": 40000, "loss": 0.3059, "lr": 4.990351264719203e-05, "epoch": 0.9169054441260746, "percentage": 2.8, "elapsed_time": "0:07:37", "remaining_time": "4:24:24", "throughput": 798.94, "total_tokens": 365120} {"current_steps": 1125, "total_steps": 40000, "loss": 0.266, "lr": 4.990264901797586e-05, "epoch": 0.9209987720016374, "percentage": 2.81, "elapsed_time": "0:07:38", "remaining_time": "4:24:11", "throughput": 799.58, "total_tokens": 366784} {"current_steps": 1130, "total_steps": 40000, "loss": 0.3034, "lr": 4.990178154845826e-05, "epoch": 0.9250920998772002, "percentage": 2.83, "elapsed_time": "0:07:40", "remaining_time": "4:23:58", "throughput": 800.21, "total_tokens": 368448} {"current_steps": 1135, "total_steps": 40000, "loss": 0.2911, "lr": 4.9900910238773014e-05, "epoch": 0.929185427752763, "percentage": 2.84, "elapsed_time": "0:07:42", "remaining_time": "4:23:45", "throughput": 800.77, "total_tokens": 370080} {"current_steps": 1140, "total_steps": 40000, "loss": 0.2088, "lr": 4.990003508905448e-05, "epoch": 0.9332787556283259, "percentage": 2.85, "elapsed_time": "0:07:43", "remaining_time": "4:23:32", "throughput": 801.26, "total_tokens": 371680} {"current_steps": 1145, "total_steps": 40000, "loss": 0.2388, "lr": 4.989915609943763e-05, "epoch": 0.9373720835038887, "percentage": 2.86, "elapsed_time": "0:07:45", "remaining_time": "4:23:19", "throughput": 801.62, "total_tokens": 373232} {"current_steps": 1150, "total_steps": 40000, "loss": 0.2397, "lr": 4.9898273270058e-05, "epoch": 0.9414654113794515, "percentage": 2.88, "elapsed_time": "0:07:47", "remaining_time": "4:23:07", "throughput": 802.27, "total_tokens": 374912} {"current_steps": 1155, "total_steps": 40000, "loss": 0.2371, "lr": 4.989738660105174e-05, "epoch": 0.9455587392550143, "percentage": 2.89, "elapsed_time": "0:07:49", "remaining_time": "4:22:54", "throughput": 802.81, "total_tokens": 376544} {"current_steps": 1160, "total_steps": 40000, "loss": 0.2534, "lr": 4.989649609255559e-05, "epoch": 0.9496520671305771, "percentage": 2.9, "elapsed_time": "0:07:50", "remaining_time": "4:22:41", "throughput": 803.32, "total_tokens": 378160} {"current_steps": 1165, "total_steps": 40000, "loss": 0.1912, "lr": 4.989560174470687e-05, "epoch": 0.95374539500614, "percentage": 2.91, "elapsed_time": "0:07:52", "remaining_time": "4:22:29", "throughput": 803.99, "total_tokens": 379856} {"current_steps": 1170, "total_steps": 40000, "loss": 0.3291, "lr": 4.989470355764351e-05, "epoch": 0.9578387228817028, "percentage": 2.93, "elapsed_time": "0:07:54", "remaining_time": "4:22:16", "throughput": 804.46, "total_tokens": 381456} {"current_steps": 1175, "total_steps": 40000, "loss": 0.276, "lr": 4.9893801531504e-05, "epoch": 0.9619320507572656, "percentage": 2.94, "elapsed_time": "0:07:55", "remaining_time": "4:22:04", "throughput": 805.02, "total_tokens": 383104} {"current_steps": 1180, "total_steps": 40000, "loss": 0.2055, "lr": 4.9892895666427475e-05, "epoch": 0.9660253786328284, "percentage": 2.95, "elapsed_time": "0:07:57", "remaining_time": "4:21:52", "throughput": 805.48, "total_tokens": 384704} {"current_steps": 1185, "total_steps": 40000, "loss": 0.2356, "lr": 4.9891985962553606e-05, "epoch": 0.9701187065083913, "percentage": 2.96, "elapsed_time": "0:07:59", "remaining_time": "4:21:40", "throughput": 806.01, "total_tokens": 386336} {"current_steps": 1190, "total_steps": 40000, "loss": 0.2352, "lr": 4.989107242002269e-05, "epoch": 0.9742120343839542, "percentage": 2.97, "elapsed_time": "0:08:01", "remaining_time": "4:21:28", "throughput": 806.57, "total_tokens": 388000} {"current_steps": 1195, "total_steps": 40000, "loss": 0.2541, "lr": 4.989015503897561e-05, "epoch": 0.978305362259517, "percentage": 2.99, "elapsed_time": "0:08:02", "remaining_time": "4:21:16", "throughput": 807.15, "total_tokens": 389664} {"current_steps": 1200, "total_steps": 40000, "loss": 0.3136, "lr": 4.988923381955383e-05, "epoch": 0.9823986901350799, "percentage": 3.0, "elapsed_time": "0:08:04", "remaining_time": "4:21:04", "throughput": 807.63, "total_tokens": 391280} {"current_steps": 1200, "total_steps": 40000, "eval_loss": 0.24365155398845673, "epoch": 0.9823986901350799, "percentage": 3.0, "elapsed_time": "0:08:16", "remaining_time": "4:27:48", "throughput": 787.32, "total_tokens": 391280} {"current_steps": 1205, "total_steps": 40000, "loss": 0.2839, "lr": 4.988830876189942e-05, "epoch": 0.9864920180106427, "percentage": 3.01, "elapsed_time": "0:08:20", "remaining_time": "4:28:19", "throughput": 785.74, "total_tokens": 392928} {"current_steps": 1210, "total_steps": 40000, "loss": 0.2399, "lr": 4.988737986615503e-05, "epoch": 0.9905853458862055, "percentage": 3.02, "elapsed_time": "0:08:21", "remaining_time": "4:28:06", "throughput": 786.36, "total_tokens": 394592} {"current_steps": 1215, "total_steps": 40000, "loss": 0.2603, "lr": 4.988644713246391e-05, "epoch": 0.9946786737617683, "percentage": 3.04, "elapsed_time": "0:08:23", "remaining_time": "4:27:53", "throughput": 786.98, "total_tokens": 396256} {"current_steps": 1220, "total_steps": 40000, "loss": 0.2345, "lr": 4.988551056096991e-05, "epoch": 0.9987720016373312, "percentage": 3.05, "elapsed_time": "0:08:25", "remaining_time": "4:27:39", "throughput": 787.56, "total_tokens": 397888} {"current_steps": 1225, "total_steps": 40000, "loss": 0.189, "lr": 4.988457015181743e-05, "epoch": 1.0024559967253377, "percentage": 3.06, "elapsed_time": "0:08:27", "remaining_time": "4:27:30", "throughput": 787.44, "total_tokens": 399288} {"current_steps": 1230, "total_steps": 40000, "loss": 0.2181, "lr": 4.988362590515153e-05, "epoch": 1.0065493246009005, "percentage": 3.08, "elapsed_time": "0:08:28", "remaining_time": "4:27:17", "throughput": 787.93, "total_tokens": 400888} {"current_steps": 1235, "total_steps": 40000, "loss": 0.2388, "lr": 4.9882677821117805e-05, "epoch": 1.0106426524764633, "percentage": 3.09, "elapsed_time": "0:08:30", "remaining_time": "4:27:04", "throughput": 788.39, "total_tokens": 402488} {"current_steps": 1240, "total_steps": 40000, "loss": 0.2987, "lr": 4.988172589986246e-05, "epoch": 1.0147359803520262, "percentage": 3.1, "elapsed_time": "0:08:32", "remaining_time": "4:26:51", "throughput": 788.84, "total_tokens": 404072} {"current_steps": 1245, "total_steps": 40000, "loss": 0.2384, "lr": 4.9880770141532304e-05, "epoch": 1.018829308227589, "percentage": 3.11, "elapsed_time": "0:08:33", "remaining_time": "4:26:38", "throughput": 789.38, "total_tokens": 405704} {"current_steps": 1250, "total_steps": 40000, "loss": 0.2924, "lr": 4.987981054627472e-05, "epoch": 1.0229226361031518, "percentage": 3.12, "elapsed_time": "0:08:35", "remaining_time": "4:26:25", "throughput": 789.82, "total_tokens": 407288} {"current_steps": 1255, "total_steps": 40000, "loss": 0.2182, "lr": 4.987884711423769e-05, "epoch": 1.0270159639787146, "percentage": 3.14, "elapsed_time": "0:08:37", "remaining_time": "4:26:12", "throughput": 790.33, "total_tokens": 408904} {"current_steps": 1260, "total_steps": 40000, "loss": 0.2588, "lr": 4.9877879845569784e-05, "epoch": 1.0311092918542775, "percentage": 3.15, "elapsed_time": "0:08:39", "remaining_time": "4:26:00", "throughput": 790.83, "total_tokens": 410520} {"current_steps": 1265, "total_steps": 40000, "loss": 0.2502, "lr": 4.9876908740420175e-05, "epoch": 1.0352026197298403, "percentage": 3.16, "elapsed_time": "0:08:40", "remaining_time": "4:25:47", "throughput": 791.51, "total_tokens": 412232} {"current_steps": 1270, "total_steps": 40000, "loss": 0.264, "lr": 4.987593379893861e-05, "epoch": 1.0392959476054031, "percentage": 3.17, "elapsed_time": "0:08:42", "remaining_time": "4:25:35", "throughput": 791.94, "total_tokens": 413816} {"current_steps": 1275, "total_steps": 40000, "loss": 0.248, "lr": 4.987495502127545e-05, "epoch": 1.043389275480966, "percentage": 3.19, "elapsed_time": "0:08:44", "remaining_time": "4:25:22", "throughput": 792.43, "total_tokens": 415432} {"current_steps": 1280, "total_steps": 40000, "loss": 0.2692, "lr": 4.987397240758162e-05, "epoch": 1.0474826033565288, "percentage": 3.2, "elapsed_time": "0:08:45", "remaining_time": "4:25:11", "throughput": 792.86, "total_tokens": 417032} {"current_steps": 1285, "total_steps": 40000, "loss": 0.2268, "lr": 4.9872985958008664e-05, "epoch": 1.0515759312320916, "percentage": 3.21, "elapsed_time": "0:08:47", "remaining_time": "4:24:58", "throughput": 793.28, "total_tokens": 418616} {"current_steps": 1290, "total_steps": 40000, "loss": 0.213, "lr": 4.987199567270871e-05, "epoch": 1.0556692591076544, "percentage": 3.23, "elapsed_time": "0:08:49", "remaining_time": "4:24:46", "throughput": 793.85, "total_tokens": 420280} {"current_steps": 1295, "total_steps": 40000, "loss": 0.2472, "lr": 4.9871001551834444e-05, "epoch": 1.0597625869832175, "percentage": 3.24, "elapsed_time": "0:08:51", "remaining_time": "4:24:34", "throughput": 794.37, "total_tokens": 421928} {"current_steps": 1300, "total_steps": 40000, "loss": 0.669, "lr": 4.98700035955392e-05, "epoch": 1.0638559148587803, "percentage": 3.25, "elapsed_time": "0:08:52", "remaining_time": "4:24:22", "throughput": 794.93, "total_tokens": 423592} {"current_steps": 1305, "total_steps": 40000, "loss": 0.2128, "lr": 4.986900180397686e-05, "epoch": 1.067949242734343, "percentage": 3.26, "elapsed_time": "0:08:54", "remaining_time": "4:24:11", "throughput": 795.55, "total_tokens": 425288} {"current_steps": 1310, "total_steps": 40000, "loss": 0.2692, "lr": 4.9867996177301926e-05, "epoch": 1.072042570609906, "percentage": 3.28, "elapsed_time": "0:08:56", "remaining_time": "4:23:59", "throughput": 796.08, "total_tokens": 426936} {"current_steps": 1315, "total_steps": 40000, "loss": 0.2194, "lr": 4.9866986715669464e-05, "epoch": 1.0761358984854688, "percentage": 3.29, "elapsed_time": "0:08:58", "remaining_time": "4:23:47", "throughput": 796.57, "total_tokens": 428568} {"current_steps": 1320, "total_steps": 40000, "loss": 0.202, "lr": 4.9865973419235155e-05, "epoch": 1.0802292263610316, "percentage": 3.3, "elapsed_time": "0:08:59", "remaining_time": "4:23:36", "throughput": 797.02, "total_tokens": 430184} {"current_steps": 1325, "total_steps": 40000, "loss": 0.2835, "lr": 4.986495628815526e-05, "epoch": 1.0843225542365944, "percentage": 3.31, "elapsed_time": "0:09:01", "remaining_time": "4:23:24", "throughput": 797.41, "total_tokens": 431768} {"current_steps": 1330, "total_steps": 40000, "loss": 0.2744, "lr": 4.986393532258663e-05, "epoch": 1.0884158821121572, "percentage": 3.33, "elapsed_time": "0:09:03", "remaining_time": "4:23:12", "throughput": 797.81, "total_tokens": 433352} {"current_steps": 1335, "total_steps": 40000, "loss": 0.2319, "lr": 4.986291052268671e-05, "epoch": 1.09250920998772, "percentage": 3.34, "elapsed_time": "0:09:04", "remaining_time": "4:23:01", "throughput": 798.3, "total_tokens": 434984} {"current_steps": 1340, "total_steps": 40000, "loss": 0.2351, "lr": 4.986188188861355e-05, "epoch": 1.0966025378632829, "percentage": 3.35, "elapsed_time": "0:09:06", "remaining_time": "4:22:50", "throughput": 798.63, "total_tokens": 436536} {"current_steps": 1345, "total_steps": 40000, "loss": 0.2088, "lr": 4.9860849420525766e-05, "epoch": 1.1006958657388457, "percentage": 3.36, "elapsed_time": "0:09:08", "remaining_time": "4:22:38", "throughput": 799.19, "total_tokens": 438216} {"current_steps": 1350, "total_steps": 40000, "loss": 0.229, "lr": 4.9859813118582575e-05, "epoch": 1.1047891936144085, "percentage": 3.38, "elapsed_time": "0:09:10", "remaining_time": "4:22:27", "throughput": 799.58, "total_tokens": 439800} {"current_steps": 1355, "total_steps": 40000, "loss": 0.2608, "lr": 4.98587729829438e-05, "epoch": 1.1088825214899714, "percentage": 3.39, "elapsed_time": "0:09:11", "remaining_time": "4:22:16", "throughput": 800.05, "total_tokens": 441432} {"current_steps": 1360, "total_steps": 40000, "loss": 0.2465, "lr": 4.985772901376983e-05, "epoch": 1.1129758493655342, "percentage": 3.4, "elapsed_time": "0:09:13", "remaining_time": "4:22:05", "throughput": 800.49, "total_tokens": 443048} {"current_steps": 1365, "total_steps": 40000, "loss": 0.2284, "lr": 4.9856681211221666e-05, "epoch": 1.117069177241097, "percentage": 3.41, "elapsed_time": "0:09:15", "remaining_time": "4:21:54", "throughput": 800.95, "total_tokens": 444696} {"current_steps": 1370, "total_steps": 40000, "loss": 0.2376, "lr": 4.985562957546089e-05, "epoch": 1.1211625051166598, "percentage": 3.43, "elapsed_time": "0:09:16", "remaining_time": "4:21:43", "throughput": 801.41, "total_tokens": 446328} {"current_steps": 1375, "total_steps": 40000, "loss": 0.2085, "lr": 4.9854574106649686e-05, "epoch": 1.1252558329922226, "percentage": 3.44, "elapsed_time": "0:09:18", "remaining_time": "4:21:32", "throughput": 801.93, "total_tokens": 447992} {"current_steps": 1380, "total_steps": 40000, "loss": 0.3071, "lr": 4.985351480495081e-05, "epoch": 1.1293491608677855, "percentage": 3.45, "elapsed_time": "0:09:20", "remaining_time": "4:21:22", "throughput": 802.46, "total_tokens": 449672} {"current_steps": 1385, "total_steps": 40000, "loss": 0.283, "lr": 4.985245167052762e-05, "epoch": 1.1334424887433483, "percentage": 3.46, "elapsed_time": "0:09:22", "remaining_time": "4:21:11", "throughput": 802.89, "total_tokens": 451288} {"current_steps": 1390, "total_steps": 40000, "loss": 0.3173, "lr": 4.9851384703544066e-05, "epoch": 1.1375358166189111, "percentage": 3.48, "elapsed_time": "0:09:23", "remaining_time": "4:21:00", "throughput": 803.43, "total_tokens": 452968} {"current_steps": 1395, "total_steps": 40000, "loss": 0.2153, "lr": 4.985031390416469e-05, "epoch": 1.141629144494474, "percentage": 3.49, "elapsed_time": "0:09:25", "remaining_time": "4:20:49", "throughput": 803.74, "total_tokens": 454520} {"current_steps": 1400, "total_steps": 40000, "loss": 0.2354, "lr": 4.984923927255461e-05, "epoch": 1.1457224723700368, "percentage": 3.5, "elapsed_time": "0:09:27", "remaining_time": "4:20:39", "throughput": 804.36, "total_tokens": 456248} {"current_steps": 1400, "total_steps": 40000, "eval_loss": 0.23794853687286377, "epoch": 1.1457224723700368, "percentage": 3.5, "elapsed_time": "0:09:39", "remaining_time": "4:26:22", "throughput": 787.05, "total_tokens": 456248} {"current_steps": 1405, "total_steps": 40000, "loss": 0.2453, "lr": 4.984816080887958e-05, "epoch": 1.1498158002455996, "percentage": 3.51, "elapsed_time": "0:09:42", "remaining_time": "4:26:50", "throughput": 785.77, "total_tokens": 457976} {"current_steps": 1410, "total_steps": 40000, "loss": 0.2725, "lr": 4.9847078513305875e-05, "epoch": 1.1539091281211624, "percentage": 3.52, "elapsed_time": "0:09:44", "remaining_time": "4:26:39", "throughput": 786.15, "total_tokens": 459576} {"current_steps": 1415, "total_steps": 40000, "loss": 0.1887, "lr": 4.984599238600043e-05, "epoch": 1.1580024559967252, "percentage": 3.54, "elapsed_time": "0:09:46", "remaining_time": "4:26:28", "throughput": 786.62, "total_tokens": 461208} {"current_steps": 1420, "total_steps": 40000, "loss": 0.1833, "lr": 4.9844902427130716e-05, "epoch": 1.1620957838722883, "percentage": 3.55, "elapsed_time": "0:09:48", "remaining_time": "4:26:16", "throughput": 787.09, "total_tokens": 462840} {"current_steps": 1425, "total_steps": 40000, "loss": 0.1831, "lr": 4.984380863686482e-05, "epoch": 1.1661891117478511, "percentage": 3.56, "elapsed_time": "0:09:49", "remaining_time": "4:26:04", "throughput": 787.59, "total_tokens": 464488} {"current_steps": 1430, "total_steps": 40000, "loss": 0.2219, "lr": 4.984271101537143e-05, "epoch": 1.170282439623414, "percentage": 3.57, "elapsed_time": "0:09:51", "remaining_time": "4:25:53", "throughput": 787.99, "total_tokens": 466072} {"current_steps": 1435, "total_steps": 40000, "loss": 0.2407, "lr": 4.9841609562819816e-05, "epoch": 1.1743757674989768, "percentage": 3.59, "elapsed_time": "0:09:53", "remaining_time": "4:25:41", "throughput": 788.48, "total_tokens": 467720} {"current_steps": 1440, "total_steps": 40000, "loss": 0.219, "lr": 4.984050427937983e-05, "epoch": 1.1784690953745396, "percentage": 3.6, "elapsed_time": "0:09:54", "remaining_time": "4:25:30", "throughput": 789.03, "total_tokens": 469400} {"current_steps": 1445, "total_steps": 40000, "loss": 0.3004, "lr": 4.983939516522191e-05, "epoch": 1.1825624232501024, "percentage": 3.61, "elapsed_time": "0:09:56", "remaining_time": "4:25:19", "throughput": 789.49, "total_tokens": 471032} {"current_steps": 1450, "total_steps": 40000, "loss": 0.2415, "lr": 4.983828222051711e-05, "epoch": 1.1866557511256652, "percentage": 3.62, "elapsed_time": "0:09:58", "remaining_time": "4:25:07", "throughput": 789.92, "total_tokens": 472648} {"current_steps": 1455, "total_steps": 40000, "loss": 0.2084, "lr": 4.983716544543705e-05, "epoch": 1.190749079001228, "percentage": 3.64, "elapsed_time": "0:10:00", "remaining_time": "4:24:57", "throughput": 790.3, "total_tokens": 474248} {"current_steps": 1460, "total_steps": 40000, "loss": 0.2127, "lr": 4.983604484015395e-05, "epoch": 1.1948424068767909, "percentage": 3.65, "elapsed_time": "0:10:01", "remaining_time": "4:24:45", "throughput": 790.81, "total_tokens": 475912} {"current_steps": 1465, "total_steps": 40000, "loss": 0.2131, "lr": 4.983492040484064e-05, "epoch": 1.1989357347523537, "percentage": 3.66, "elapsed_time": "0:10:03", "remaining_time": "4:24:34", "throughput": 791.31, "total_tokens": 477576} {"current_steps": 1470, "total_steps": 40000, "loss": 0.2635, "lr": 4.98337921396705e-05, "epoch": 1.2030290626279165, "percentage": 3.67, "elapsed_time": "0:10:05", "remaining_time": "4:24:23", "throughput": 791.76, "total_tokens": 479208} {"current_steps": 1475, "total_steps": 40000, "loss": 0.2696, "lr": 4.983266004481753e-05, "epoch": 1.2071223905034794, "percentage": 3.69, "elapsed_time": "0:10:06", "remaining_time": "4:24:12", "throughput": 792.18, "total_tokens": 480824} {"current_steps": 1480, "total_steps": 40000, "loss": 0.2565, "lr": 4.9831524120456316e-05, "epoch": 1.2112157183790422, "percentage": 3.7, "elapsed_time": "0:10:08", "remaining_time": "4:24:02", "throughput": 792.55, "total_tokens": 482408} {"current_steps": 1485, "total_steps": 40000, "loss": 0.2149, "lr": 4.9830384366762026e-05, "epoch": 1.215309046254605, "percentage": 3.71, "elapsed_time": "0:10:10", "remaining_time": "4:23:51", "throughput": 792.97, "total_tokens": 484024} {"current_steps": 1490, "total_steps": 40000, "loss": 0.2405, "lr": 4.9829240783910436e-05, "epoch": 1.2194023741301678, "percentage": 3.72, "elapsed_time": "0:10:12", "remaining_time": "4:23:40", "throughput": 793.46, "total_tokens": 485688} {"current_steps": 1495, "total_steps": 40000, "loss": 0.2547, "lr": 4.982809337207789e-05, "epoch": 1.2234957020057307, "percentage": 3.74, "elapsed_time": "0:10:13", "remaining_time": "4:23:29", "throughput": 793.82, "total_tokens": 487272} {"current_steps": 1500, "total_steps": 40000, "loss": 0.2773, "lr": 4.9826942131441337e-05, "epoch": 1.2275890298812935, "percentage": 3.75, "elapsed_time": "0:10:15", "remaining_time": "4:23:19", "throughput": 794.19, "total_tokens": 488872} {"current_steps": 1505, "total_steps": 40000, "loss": 0.2082, "lr": 4.9825787062178315e-05, "epoch": 1.2316823577568563, "percentage": 3.76, "elapsed_time": "0:10:17", "remaining_time": "4:23:08", "throughput": 794.62, "total_tokens": 490504} {"current_steps": 1510, "total_steps": 40000, "loss": 0.2463, "lr": 4.9824628164466945e-05, "epoch": 1.2357756856324191, "percentage": 3.77, "elapsed_time": "0:10:18", "remaining_time": "4:22:58", "throughput": 795.0, "total_tokens": 492104} {"current_steps": 1515, "total_steps": 40000, "loss": 0.1873, "lr": 4.982346543848595e-05, "epoch": 1.239869013507982, "percentage": 3.79, "elapsed_time": "0:10:20", "remaining_time": "4:22:47", "throughput": 795.54, "total_tokens": 493800} {"current_steps": 1520, "total_steps": 40000, "loss": 0.271, "lr": 4.9822298884414626e-05, "epoch": 1.2439623413835448, "percentage": 3.8, "elapsed_time": "0:10:22", "remaining_time": "4:22:37", "throughput": 795.94, "total_tokens": 495416} {"current_steps": 1525, "total_steps": 40000, "loss": 0.2971, "lr": 4.982112850243288e-05, "epoch": 1.2480556692591076, "percentage": 3.81, "elapsed_time": "0:10:24", "remaining_time": "4:22:26", "throughput": 796.31, "total_tokens": 497016} {"current_steps": 1530, "total_steps": 40000, "loss": 0.2527, "lr": 4.98199542927212e-05, "epoch": 1.2521489971346704, "percentage": 3.82, "elapsed_time": "0:10:25", "remaining_time": "4:22:16", "throughput": 796.7, "total_tokens": 498632} {"current_steps": 1535, "total_steps": 40000, "loss": 0.2321, "lr": 4.981877625546066e-05, "epoch": 1.2562423250102333, "percentage": 3.84, "elapsed_time": "0:10:27", "remaining_time": "4:22:06", "throughput": 797.12, "total_tokens": 500264} {"current_steps": 1540, "total_steps": 40000, "loss": 0.2074, "lr": 4.981759439083293e-05, "epoch": 1.260335652885796, "percentage": 3.85, "elapsed_time": "0:10:29", "remaining_time": "4:21:56", "throughput": 797.59, "total_tokens": 501928} {"current_steps": 1545, "total_steps": 40000, "loss": 0.2116, "lr": 4.981640869902027e-05, "epoch": 1.264428980761359, "percentage": 3.86, "elapsed_time": "0:10:31", "remaining_time": "4:21:46", "throughput": 797.93, "total_tokens": 503528} {"current_steps": 1550, "total_steps": 40000, "loss": 0.2457, "lr": 4.9815219180205517e-05, "epoch": 1.2685223086369217, "percentage": 3.88, "elapsed_time": "0:10:32", "remaining_time": "4:21:36", "throughput": 798.24, "total_tokens": 505096} {"current_steps": 1555, "total_steps": 40000, "loss": 0.241, "lr": 4.9814025834572126e-05, "epoch": 1.2726156365124845, "percentage": 3.89, "elapsed_time": "0:10:34", "remaining_time": "4:21:26", "throughput": 798.68, "total_tokens": 506744} {"current_steps": 1560, "total_steps": 40000, "loss": 0.1982, "lr": 4.981282866230411e-05, "epoch": 1.2767089643880474, "percentage": 3.9, "elapsed_time": "0:10:36", "remaining_time": "4:21:16", "throughput": 799.14, "total_tokens": 508408} {"current_steps": 1565, "total_steps": 40000, "loss": 0.2124, "lr": 4.981162766358611e-05, "epoch": 1.2808022922636102, "percentage": 3.91, "elapsed_time": "0:10:37", "remaining_time": "4:21:06", "throughput": 799.58, "total_tokens": 510056} {"current_steps": 1570, "total_steps": 40000, "loss": 0.2681, "lr": 4.9810422838603316e-05, "epoch": 1.284895620139173, "percentage": 3.92, "elapsed_time": "0:10:39", "remaining_time": "4:20:56", "throughput": 799.91, "total_tokens": 511640} {"current_steps": 1575, "total_steps": 40000, "loss": 0.2121, "lr": 4.9809214187541533e-05, "epoch": 1.2889889480147358, "percentage": 3.94, "elapsed_time": "0:10:41", "remaining_time": "4:20:46", "throughput": 800.35, "total_tokens": 513288} {"current_steps": 1580, "total_steps": 40000, "loss": 0.215, "lr": 4.980800171058715e-05, "epoch": 1.293082275890299, "percentage": 3.95, "elapsed_time": "0:10:43", "remaining_time": "4:20:36", "throughput": 800.8, "total_tokens": 514952} {"current_steps": 1585, "total_steps": 40000, "loss": 0.2041, "lr": 4.980678540792715e-05, "epoch": 1.2971756037658617, "percentage": 3.96, "elapsed_time": "0:10:44", "remaining_time": "4:20:26", "throughput": 801.19, "total_tokens": 516584} {"current_steps": 1590, "total_steps": 40000, "loss": 0.434, "lr": 4.980556527974909e-05, "epoch": 1.3012689316414245, "percentage": 3.98, "elapsed_time": "0:10:46", "remaining_time": "4:20:17", "throughput": 801.57, "total_tokens": 518200} {"current_steps": 1595, "total_steps": 40000, "loss": 0.2427, "lr": 4.980434132624114e-05, "epoch": 1.3053622595169874, "percentage": 3.99, "elapsed_time": "0:10:48", "remaining_time": "4:20:07", "throughput": 801.91, "total_tokens": 519800} {"current_steps": 1600, "total_steps": 40000, "loss": 0.2185, "lr": 4.980311354759205e-05, "epoch": 1.3094555873925502, "percentage": 4.0, "elapsed_time": "0:10:49", "remaining_time": "4:19:57", "throughput": 802.36, "total_tokens": 521464} {"current_steps": 1600, "total_steps": 40000, "eval_loss": 0.23361539840698242, "epoch": 1.3094555873925502, "percentage": 4.0, "elapsed_time": "0:11:02", "remaining_time": "4:24:56", "throughput": 787.28, "total_tokens": 521464} {"current_steps": 1605, "total_steps": 40000, "loss": 0.2182, "lr": 4.980188194399116e-05, "epoch": 1.313548915268113, "percentage": 4.01, "elapsed_time": "0:11:05", "remaining_time": "4:25:18", "throughput": 786.06, "total_tokens": 523080} {"current_steps": 1610, "total_steps": 40000, "loss": 0.3065, "lr": 4.9800646515628384e-05, "epoch": 1.3176422431436758, "percentage": 4.03, "elapsed_time": "0:11:07", "remaining_time": "4:25:08", "throughput": 786.45, "total_tokens": 524696} {"current_steps": 1615, "total_steps": 40000, "loss": 0.2433, "lr": 4.979940726269426e-05, "epoch": 1.3217355710192387, "percentage": 4.04, "elapsed_time": "0:11:08", "remaining_time": "4:24:57", "throughput": 786.95, "total_tokens": 526376} {"current_steps": 1620, "total_steps": 40000, "loss": 0.2401, "lr": 4.979816418537988e-05, "epoch": 1.3258288988948015, "percentage": 4.05, "elapsed_time": "0:11:10", "remaining_time": "4:24:47", "throughput": 787.53, "total_tokens": 528120} {"current_steps": 1625, "total_steps": 40000, "loss": 0.2326, "lr": 4.979691728387696e-05, "epoch": 1.3299222267703643, "percentage": 4.06, "elapsed_time": "0:11:12", "remaining_time": "4:24:43", "throughput": 787.57, "total_tokens": 529704} {"current_steps": 1630, "total_steps": 40000, "loss": 0.3402, "lr": 4.979566655837776e-05, "epoch": 1.3340155546459271, "percentage": 4.08, "elapsed_time": "0:11:14", "remaining_time": "4:24:32", "throughput": 787.98, "total_tokens": 531336} {"current_steps": 1635, "total_steps": 40000, "loss": 0.191, "lr": 4.9794412009075184e-05, "epoch": 1.33810888252149, "percentage": 4.09, "elapsed_time": "0:11:16", "remaining_time": "4:24:22", "throughput": 788.28, "total_tokens": 532904} {"current_steps": 1640, "total_steps": 40000, "loss": 0.2618, "lr": 4.979315363616269e-05, "epoch": 1.3422022103970528, "percentage": 4.1, "elapsed_time": "0:11:17", "remaining_time": "4:24:12", "throughput": 788.64, "total_tokens": 534504} {"current_steps": 1645, "total_steps": 40000, "loss": 0.2023, "lr": 4.979189143983434e-05, "epoch": 1.3462955382726156, "percentage": 4.11, "elapsed_time": "0:11:19", "remaining_time": "4:24:02", "throughput": 789.2, "total_tokens": 536248} {"current_steps": 1650, "total_steps": 40000, "loss": 0.1818, "lr": 4.979062542028478e-05, "epoch": 1.3503888661481784, "percentage": 4.12, "elapsed_time": "0:11:21", "remaining_time": "4:23:52", "throughput": 789.63, "total_tokens": 537896} {"current_steps": 1655, "total_steps": 40000, "loss": 0.2334, "lr": 4.978935557770923e-05, "epoch": 1.3544821940237413, "percentage": 4.14, "elapsed_time": "0:11:22", "remaining_time": "4:23:42", "throughput": 790.06, "total_tokens": 539544} {"current_steps": 1660, "total_steps": 40000, "loss": 0.2936, "lr": 4.978808191230353e-05, "epoch": 1.358575521899304, "percentage": 4.15, "elapsed_time": "0:11:24", "remaining_time": "4:23:32", "throughput": 790.39, "total_tokens": 541128} {"current_steps": 1665, "total_steps": 40000, "loss": 0.2215, "lr": 4.9786804424264085e-05, "epoch": 1.362668849774867, "percentage": 4.16, "elapsed_time": "0:11:26", "remaining_time": "4:23:22", "throughput": 790.73, "total_tokens": 542712} {"current_steps": 1670, "total_steps": 40000, "loss": 0.2003, "lr": 4.978552311378792e-05, "epoch": 1.3667621776504297, "percentage": 4.17, "elapsed_time": "0:11:28", "remaining_time": "4:23:12", "throughput": 791.03, "total_tokens": 544280} {"current_steps": 1675, "total_steps": 40000, "loss": 0.2218, "lr": 4.978423798107261e-05, "epoch": 1.3708555055259926, "percentage": 4.19, "elapsed_time": "0:11:29", "remaining_time": "4:23:02", "throughput": 791.41, "total_tokens": 545912} {"current_steps": 1680, "total_steps": 40000, "loss": 0.2264, "lr": 4.978294902631635e-05, "epoch": 1.3749488334015554, "percentage": 4.2, "elapsed_time": "0:11:31", "remaining_time": "4:22:53", "throughput": 791.8, "total_tokens": 547544} {"current_steps": 1685, "total_steps": 40000, "loss": 0.2719, "lr": 4.9781656249717914e-05, "epoch": 1.3790421612771184, "percentage": 4.21, "elapsed_time": "0:11:33", "remaining_time": "4:22:43", "throughput": 792.19, "total_tokens": 549176} {"current_steps": 1690, "total_steps": 40000, "loss": 0.2375, "lr": 4.9780359651476645e-05, "epoch": 1.3831354891526813, "percentage": 4.23, "elapsed_time": "0:11:34", "remaining_time": "4:22:33", "throughput": 792.58, "total_tokens": 550808} {"current_steps": 1695, "total_steps": 40000, "loss": 0.1981, "lr": 4.977905923179251e-05, "epoch": 1.387228817028244, "percentage": 4.24, "elapsed_time": "0:11:36", "remaining_time": "4:22:23", "throughput": 792.91, "total_tokens": 552392} {"current_steps": 1700, "total_steps": 40000, "loss": 0.1817, "lr": 4.977775499086606e-05, "epoch": 1.391322144903807, "percentage": 4.25, "elapsed_time": "0:11:38", "remaining_time": "4:22:14", "throughput": 793.32, "total_tokens": 554040} {"current_steps": 1705, "total_steps": 40000, "loss": 0.3138, "lr": 4.97764469288984e-05, "epoch": 1.3954154727793697, "percentage": 4.26, "elapsed_time": "0:11:40", "remaining_time": "4:22:04", "throughput": 793.68, "total_tokens": 555656} {"current_steps": 1710, "total_steps": 40000, "loss": 0.2611, "lr": 4.977513504609127e-05, "epoch": 1.3995088006549325, "percentage": 4.28, "elapsed_time": "0:11:41", "remaining_time": "4:21:55", "throughput": 794.06, "total_tokens": 557288} {"current_steps": 1715, "total_steps": 40000, "loss": 0.2574, "lr": 4.9773819342646965e-05, "epoch": 1.4036021285304954, "percentage": 4.29, "elapsed_time": "0:11:43", "remaining_time": "4:21:45", "throughput": 794.42, "total_tokens": 558904} {"current_steps": 1720, "total_steps": 40000, "loss": 0.2252, "lr": 4.97724998187684e-05, "epoch": 1.4076954564060582, "percentage": 4.3, "elapsed_time": "0:11:45", "remaining_time": "4:21:36", "throughput": 794.8, "total_tokens": 560552} {"current_steps": 1725, "total_steps": 40000, "loss": 0.2517, "lr": 4.9771176474659045e-05, "epoch": 1.411788784281621, "percentage": 4.31, "elapsed_time": "0:11:46", "remaining_time": "4:21:26", "throughput": 795.11, "total_tokens": 562136} {"current_steps": 1730, "total_steps": 40000, "loss": 0.2188, "lr": 4.976984931052299e-05, "epoch": 1.4158821121571838, "percentage": 4.32, "elapsed_time": "0:11:48", "remaining_time": "4:21:17", "throughput": 795.49, "total_tokens": 563768} {"current_steps": 1735, "total_steps": 40000, "loss": 0.2595, "lr": 4.976851832656489e-05, "epoch": 1.4199754400327467, "percentage": 4.34, "elapsed_time": "0:11:50", "remaining_time": "4:21:08", "throughput": 795.84, "total_tokens": 565384} {"current_steps": 1740, "total_steps": 40000, "loss": 0.1905, "lr": 4.9767183522990004e-05, "epoch": 1.4240687679083095, "percentage": 4.35, "elapsed_time": "0:11:52", "remaining_time": "4:20:58", "throughput": 796.21, "total_tokens": 567016} {"current_steps": 1745, "total_steps": 40000, "loss": 0.2099, "lr": 4.9765844900004176e-05, "epoch": 1.4281620957838723, "percentage": 4.36, "elapsed_time": "0:11:53", "remaining_time": "4:20:49", "throughput": 796.6, "total_tokens": 568664} {"current_steps": 1750, "total_steps": 40000, "loss": 0.2309, "lr": 4.9764502457813834e-05, "epoch": 1.4322554236594351, "percentage": 4.38, "elapsed_time": "0:11:55", "remaining_time": "4:20:40", "throughput": 796.88, "total_tokens": 570232} {"current_steps": 1755, "total_steps": 40000, "loss": 0.1933, "lr": 4.9763156196626005e-05, "epoch": 1.436348751534998, "percentage": 4.39, "elapsed_time": "0:11:57", "remaining_time": "4:20:31", "throughput": 797.31, "total_tokens": 571912} {"current_steps": 1760, "total_steps": 40000, "loss": 0.2083, "lr": 4.97618061166483e-05, "epoch": 1.4404420794105608, "percentage": 4.4, "elapsed_time": "0:11:59", "remaining_time": "4:20:22", "throughput": 797.68, "total_tokens": 573544} {"current_steps": 1765, "total_steps": 40000, "loss": 0.272, "lr": 4.9760452218088915e-05, "epoch": 1.4445354072861236, "percentage": 4.41, "elapsed_time": "0:12:00", "remaining_time": "4:20:13", "throughput": 797.99, "total_tokens": 575144} {"current_steps": 1770, "total_steps": 40000, "loss": 0.1823, "lr": 4.975909450115663e-05, "epoch": 1.4486287351616864, "percentage": 4.42, "elapsed_time": "0:12:02", "remaining_time": "4:20:04", "throughput": 798.33, "total_tokens": 576760} {"current_steps": 1775, "total_steps": 40000, "loss": 0.2392, "lr": 4.975773296606084e-05, "epoch": 1.4527220630372493, "percentage": 4.44, "elapsed_time": "0:12:04", "remaining_time": "4:19:55", "throughput": 798.69, "total_tokens": 578392} {"current_steps": 1780, "total_steps": 40000, "loss": 0.2226, "lr": 4.97563676130115e-05, "epoch": 1.456815390912812, "percentage": 4.45, "elapsed_time": "0:12:05", "remaining_time": "4:19:46", "throughput": 799.12, "total_tokens": 580072} {"current_steps": 1785, "total_steps": 40000, "loss": 0.2341, "lr": 4.9754998442219166e-05, "epoch": 1.460908718788375, "percentage": 4.46, "elapsed_time": "0:12:07", "remaining_time": "4:19:37", "throughput": 799.48, "total_tokens": 581704} {"current_steps": 1790, "total_steps": 40000, "loss": 0.2496, "lr": 4.9753625453894984e-05, "epoch": 1.4650020466639377, "percentage": 4.47, "elapsed_time": "0:12:09", "remaining_time": "4:19:28", "throughput": 800.0, "total_tokens": 583448} {"current_steps": 1795, "total_steps": 40000, "loss": 0.2505, "lr": 4.975224864825068e-05, "epoch": 1.4690953745395006, "percentage": 4.49, "elapsed_time": "0:12:11", "remaining_time": "4:19:19", "throughput": 800.29, "total_tokens": 585032} {"current_steps": 1800, "total_steps": 40000, "loss": 0.1896, "lr": 4.9750868025498576e-05, "epoch": 1.4731887024150634, "percentage": 4.5, "elapsed_time": "0:12:12", "remaining_time": "4:19:10", "throughput": 800.6, "total_tokens": 586632} {"current_steps": 1800, "total_steps": 40000, "eval_loss": 0.23062245547771454, "epoch": 1.4731887024150634, "percentage": 4.5, "elapsed_time": "0:12:25", "remaining_time": "4:23:34", "throughput": 787.22, "total_tokens": 586632} {"current_steps": 1805, "total_steps": 40000, "loss": 0.1915, "lr": 4.974948358585158e-05, "epoch": 1.4772820302906262, "percentage": 4.51, "elapsed_time": "0:12:28", "remaining_time": "4:23:54", "throughput": 786.16, "total_tokens": 588280} {"current_steps": 1810, "total_steps": 40000, "loss": 0.1841, "lr": 4.9748095329523205e-05, "epoch": 1.481375358166189, "percentage": 4.52, "elapsed_time": "0:12:30", "remaining_time": "4:23:45", "throughput": 786.64, "total_tokens": 590008} {"current_steps": 1815, "total_steps": 40000, "loss": 0.2046, "lr": 4.974670325672752e-05, "epoch": 1.4854686860417519, "percentage": 4.54, "elapsed_time": "0:12:31", "remaining_time": "4:23:35", "throughput": 786.96, "total_tokens": 591592} {"current_steps": 1820, "total_steps": 40000, "loss": 0.2353, "lr": 4.974530736767921e-05, "epoch": 1.4895620139173147, "percentage": 4.55, "elapsed_time": "0:12:33", "remaining_time": "4:23:26", "throughput": 787.35, "total_tokens": 593240} {"current_steps": 1825, "total_steps": 40000, "loss": 0.2215, "lr": 4.9743907662593524e-05, "epoch": 1.4936553417928775, "percentage": 4.56, "elapsed_time": "0:12:35", "remaining_time": "4:23:16", "throughput": 787.6, "total_tokens": 594776} {"current_steps": 1830, "total_steps": 40000, "loss": 0.2175, "lr": 4.974250414168633e-05, "epoch": 1.4977486696684403, "percentage": 4.58, "elapsed_time": "0:12:36", "remaining_time": "4:23:07", "throughput": 787.88, "total_tokens": 596344} {"current_steps": 1835, "total_steps": 40000, "loss": 0.1929, "lr": 4.974109680517407e-05, "epoch": 1.5018419975440032, "percentage": 4.59, "elapsed_time": "0:12:38", "remaining_time": "4:22:57", "throughput": 788.21, "total_tokens": 597944} {"current_steps": 1840, "total_steps": 40000, "loss": 0.2487, "lr": 4.973968565327376e-05, "epoch": 1.505935325419566, "percentage": 4.6, "elapsed_time": "0:12:40", "remaining_time": "4:22:48", "throughput": 788.56, "total_tokens": 599560} {"current_steps": 1845, "total_steps": 40000, "loss": 0.2245, "lr": 4.973827068620303e-05, "epoch": 1.5100286532951288, "percentage": 4.61, "elapsed_time": "0:12:42", "remaining_time": "4:22:39", "throughput": 788.97, "total_tokens": 601224} {"current_steps": 1850, "total_steps": 40000, "loss": 0.2157, "lr": 4.973685190418008e-05, "epoch": 1.5141219811706916, "percentage": 4.62, "elapsed_time": "0:12:43", "remaining_time": "4:22:29", "throughput": 789.27, "total_tokens": 602808} {"current_steps": 1855, "total_steps": 40000, "loss": 0.2788, "lr": 4.97354293074237e-05, "epoch": 1.5182153090462545, "percentage": 4.64, "elapsed_time": "0:12:45", "remaining_time": "4:22:20", "throughput": 789.68, "total_tokens": 604488} {"current_steps": 1860, "total_steps": 40000, "loss": 0.3829, "lr": 4.9734002896153276e-05, "epoch": 1.5223086369218173, "percentage": 4.65, "elapsed_time": "0:12:47", "remaining_time": "4:22:11", "throughput": 790.06, "total_tokens": 606136} {"current_steps": 1865, "total_steps": 40000, "loss": 0.1997, "lr": 4.973257267058877e-05, "epoch": 1.52640196479738, "percentage": 4.66, "elapsed_time": "0:12:48", "remaining_time": "4:22:02", "throughput": 790.47, "total_tokens": 607800} {"current_steps": 1870, "total_steps": 40000, "loss": 0.217, "lr": 4.973113863095076e-05, "epoch": 1.5304952926729432, "percentage": 4.67, "elapsed_time": "0:12:50", "remaining_time": "4:21:53", "throughput": 790.74, "total_tokens": 609368} {"current_steps": 1875, "total_steps": 40000, "loss": 0.2404, "lr": 4.9729700777460384e-05, "epoch": 1.534588620548506, "percentage": 4.69, "elapsed_time": "0:12:52", "remaining_time": "4:21:44", "throughput": 791.14, "total_tokens": 611032} {"current_steps": 1880, "total_steps": 40000, "loss": 0.2319, "lr": 4.972825911033937e-05, "epoch": 1.5386819484240688, "percentage": 4.7, "elapsed_time": "0:12:54", "remaining_time": "4:21:35", "throughput": 791.5, "total_tokens": 612680} {"current_steps": 1885, "total_steps": 40000, "loss": 0.1987, "lr": 4.9726813629810056e-05, "epoch": 1.5427752762996316, "percentage": 4.71, "elapsed_time": "0:12:55", "remaining_time": "4:21:26", "throughput": 791.87, "total_tokens": 614328} {"current_steps": 1890, "total_steps": 40000, "loss": 0.2299, "lr": 4.9725364336095326e-05, "epoch": 1.5468686041751945, "percentage": 4.72, "elapsed_time": "0:12:57", "remaining_time": "4:21:17", "throughput": 792.16, "total_tokens": 615912} {"current_steps": 1895, "total_steps": 40000, "loss": 0.2105, "lr": 4.972391122941871e-05, "epoch": 1.5509619320507573, "percentage": 4.74, "elapsed_time": "0:12:59", "remaining_time": "4:21:08", "throughput": 792.49, "total_tokens": 617528} {"current_steps": 1900, "total_steps": 40000, "loss": 0.1837, "lr": 4.972245431000428e-05, "epoch": 1.55505525992632, "percentage": 4.75, "elapsed_time": "0:13:00", "remaining_time": "4:21:00", "throughput": 792.78, "total_tokens": 619128} {"current_steps": 1905, "total_steps": 40000, "loss": 0.2118, "lr": 4.972099357807671e-05, "epoch": 1.559148587801883, "percentage": 4.76, "elapsed_time": "0:13:02", "remaining_time": "4:20:51", "throughput": 793.11, "total_tokens": 620744} {"current_steps": 1910, "total_steps": 40000, "loss": 0.2037, "lr": 4.971952903386127e-05, "epoch": 1.5632419156774457, "percentage": 4.78, "elapsed_time": "0:13:04", "remaining_time": "4:20:42", "throughput": 793.39, "total_tokens": 622328} {"current_steps": 1915, "total_steps": 40000, "loss": 0.2544, "lr": 4.971806067758381e-05, "epoch": 1.5673352435530086, "percentage": 4.79, "elapsed_time": "0:13:06", "remaining_time": "4:20:33", "throughput": 793.66, "total_tokens": 623896} {"current_steps": 1920, "total_steps": 40000, "loss": 0.1908, "lr": 4.971658850947076e-05, "epoch": 1.5714285714285714, "percentage": 4.8, "elapsed_time": "0:13:07", "remaining_time": "4:20:25", "throughput": 793.96, "total_tokens": 625496} {"current_steps": 1925, "total_steps": 40000, "loss": 0.2801, "lr": 4.9715112529749165e-05, "epoch": 1.5755218993041342, "percentage": 4.81, "elapsed_time": "0:13:09", "remaining_time": "4:20:16", "throughput": 794.24, "total_tokens": 627080} {"current_steps": 1930, "total_steps": 40000, "loss": 0.2337, "lr": 4.9713632738646624e-05, "epoch": 1.579615227179697, "percentage": 4.83, "elapsed_time": "0:13:11", "remaining_time": "4:20:07", "throughput": 794.61, "total_tokens": 628728} {"current_steps": 1935, "total_steps": 40000, "loss": 0.2304, "lr": 4.971214913639134e-05, "epoch": 1.58370855505526, "percentage": 4.84, "elapsed_time": "0:13:12", "remaining_time": "4:19:58", "throughput": 794.91, "total_tokens": 630328} {"current_steps": 1940, "total_steps": 40000, "loss": 0.2298, "lr": 4.9710661723212104e-05, "epoch": 1.587801882930823, "percentage": 4.85, "elapsed_time": "0:13:14", "remaining_time": "4:19:50", "throughput": 795.21, "total_tokens": 631944} {"current_steps": 1945, "total_steps": 40000, "loss": 0.1923, "lr": 4.9709170499338295e-05, "epoch": 1.5918952108063857, "percentage": 4.86, "elapsed_time": "0:13:16", "remaining_time": "4:19:42", "throughput": 795.57, "total_tokens": 633592} {"current_steps": 1950, "total_steps": 40000, "loss": 0.2054, "lr": 4.9707675464999895e-05, "epoch": 1.5959885386819486, "percentage": 4.88, "elapsed_time": "0:13:18", "remaining_time": "4:19:33", "throughput": 795.84, "total_tokens": 635176} {"current_steps": 1955, "total_steps": 40000, "loss": 0.2302, "lr": 4.970617662042743e-05, "epoch": 1.6000818665575114, "percentage": 4.89, "elapsed_time": "0:13:19", "remaining_time": "4:19:25", "throughput": 796.15, "total_tokens": 636792} {"current_steps": 1960, "total_steps": 40000, "loss": 0.2233, "lr": 4.970467396585206e-05, "epoch": 1.6041751944330742, "percentage": 4.9, "elapsed_time": "0:13:21", "remaining_time": "4:19:16", "throughput": 796.52, "total_tokens": 638456} {"current_steps": 1965, "total_steps": 40000, "loss": 0.2949, "lr": 4.97031675015055e-05, "epoch": 1.608268522308637, "percentage": 4.91, "elapsed_time": "0:13:23", "remaining_time": "4:19:08", "throughput": 796.86, "total_tokens": 640088} {"current_steps": 1970, "total_steps": 40000, "loss": 0.1879, "lr": 4.9701657227620075e-05, "epoch": 1.6123618501841999, "percentage": 4.92, "elapsed_time": "0:13:24", "remaining_time": "4:18:59", "throughput": 797.13, "total_tokens": 641672} {"current_steps": 1975, "total_steps": 40000, "loss": 0.2258, "lr": 4.9700143144428685e-05, "epoch": 1.6164551780597627, "percentage": 4.94, "elapsed_time": "0:13:26", "remaining_time": "4:18:51", "throughput": 797.41, "total_tokens": 643272} {"current_steps": 1980, "total_steps": 40000, "loss": 0.2186, "lr": 4.969862525216482e-05, "epoch": 1.6205485059353255, "percentage": 4.95, "elapsed_time": "0:13:28", "remaining_time": "4:18:43", "throughput": 797.76, "total_tokens": 644920} {"current_steps": 1985, "total_steps": 40000, "loss": 0.2555, "lr": 4.9697103551062556e-05, "epoch": 1.6246418338108883, "percentage": 4.96, "elapsed_time": "0:13:30", "remaining_time": "4:18:35", "throughput": 798.08, "total_tokens": 646552} {"current_steps": 1990, "total_steps": 40000, "loss": 0.2394, "lr": 4.9695578041356565e-05, "epoch": 1.6287351616864512, "percentage": 4.98, "elapsed_time": "0:13:31", "remaining_time": "4:18:26", "throughput": 798.48, "total_tokens": 648248} {"current_steps": 1995, "total_steps": 40000, "loss": 0.2021, "lr": 4.969404872328209e-05, "epoch": 1.632828489562014, "percentage": 4.99, "elapsed_time": "0:13:33", "remaining_time": "4:18:18", "throughput": 798.74, "total_tokens": 649832} {"current_steps": 2000, "total_steps": 40000, "loss": 0.2201, "lr": 4.969251559707498e-05, "epoch": 1.6369218174375768, "percentage": 5.0, "elapsed_time": "0:13:35", "remaining_time": "4:18:10", "throughput": 798.97, "total_tokens": 651384} {"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.22812990844249725, "epoch": 1.6369218174375768, "percentage": 5.0, "elapsed_time": "0:13:47", "remaining_time": "4:22:06", "throughput": 786.96, "total_tokens": 651384} {"current_steps": 2005, "total_steps": 40000, "loss": 0.2342, "lr": 4.9690978662971674e-05, "epoch": 1.6410151453131396, "percentage": 5.01, "elapsed_time": "0:13:50", "remaining_time": "4:22:26", "throughput": 785.88, "total_tokens": 653016} {"current_steps": 2010, "total_steps": 40000, "loss": 0.1897, "lr": 4.968943792120916e-05, "epoch": 1.6451084731887025, "percentage": 5.03, "elapsed_time": "0:13:52", "remaining_time": "4:22:17", "throughput": 786.26, "total_tokens": 654680} {"current_steps": 2015, "total_steps": 40000, "loss": 0.21, "lr": 4.9687893372025046e-05, "epoch": 1.6492018010642653, "percentage": 5.04, "elapsed_time": "0:13:54", "remaining_time": "4:22:08", "throughput": 786.54, "total_tokens": 656264} {"current_steps": 2020, "total_steps": 40000, "loss": 0.2579, "lr": 4.9686345015657535e-05, "epoch": 1.653295128939828, "percentage": 5.05, "elapsed_time": "0:13:56", "remaining_time": "4:22:00", "throughput": 786.83, "total_tokens": 657864} {"current_steps": 2025, "total_steps": 40000, "loss": 0.2464, "lr": 4.968479285234538e-05, "epoch": 1.657388456815391, "percentage": 5.06, "elapsed_time": "0:13:57", "remaining_time": "4:21:51", "throughput": 787.21, "total_tokens": 659528} {"current_steps": 2030, "total_steps": 40000, "loss": 0.2011, "lr": 4.9683236882327974e-05, "epoch": 1.6614817846909538, "percentage": 5.08, "elapsed_time": "0:13:59", "remaining_time": "4:21:42", "throughput": 787.54, "total_tokens": 661160} {"current_steps": 2035, "total_steps": 40000, "loss": 0.2354, "lr": 4.968167710584526e-05, "epoch": 1.6655751125665166, "percentage": 5.09, "elapsed_time": "0:14:01", "remaining_time": "4:21:34", "throughput": 787.8, "total_tokens": 662744} {"current_steps": 2040, "total_steps": 40000, "loss": 0.2405, "lr": 4.968011352313775e-05, "epoch": 1.6696684404420794, "percentage": 5.1, "elapsed_time": "0:14:02", "remaining_time": "4:21:25", "throughput": 788.13, "total_tokens": 664376} {"current_steps": 2045, "total_steps": 40000, "loss": 0.2731, "lr": 4.967854613444659e-05, "epoch": 1.6737617683176422, "percentage": 5.11, "elapsed_time": "0:14:04", "remaining_time": "4:21:17", "throughput": 788.52, "total_tokens": 666056} {"current_steps": 2050, "total_steps": 40000, "loss": 0.3573, "lr": 4.967697494001349e-05, "epoch": 1.677855096193205, "percentage": 5.12, "elapsed_time": "0:14:06", "remaining_time": "4:21:08", "throughput": 788.77, "total_tokens": 667624} {"current_steps": 2055, "total_steps": 40000, "loss": 0.2453, "lr": 4.9675399940080736e-05, "epoch": 1.6819484240687679, "percentage": 5.14, "elapsed_time": "0:14:08", "remaining_time": "4:21:00", "throughput": 789.07, "total_tokens": 669224} {"current_steps": 2060, "total_steps": 40000, "loss": 0.2125, "lr": 4.9673821134891226e-05, "epoch": 1.6860417519443307, "percentage": 5.15, "elapsed_time": "0:14:09", "remaining_time": "4:20:51", "throughput": 789.41, "total_tokens": 670872} {"current_steps": 2065, "total_steps": 40000, "loss": 0.2543, "lr": 4.967223852468842e-05, "epoch": 1.6901350798198935, "percentage": 5.16, "elapsed_time": "0:14:11", "remaining_time": "4:20:43", "throughput": 789.83, "total_tokens": 672584} {"current_steps": 2070, "total_steps": 40000, "loss": 0.2028, "lr": 4.967065210971639e-05, "epoch": 1.6942284076954564, "percentage": 5.17, "elapsed_time": "0:14:13", "remaining_time": "4:20:35", "throughput": 790.15, "total_tokens": 674216} {"current_steps": 2075, "total_steps": 40000, "loss": 0.228, "lr": 4.966906189021977e-05, "epoch": 1.6983217355710192, "percentage": 5.19, "elapsed_time": "0:14:15", "remaining_time": "4:20:27", "throughput": 790.44, "total_tokens": 675832} {"current_steps": 2080, "total_steps": 40000, "loss": 0.2299, "lr": 4.966746786644379e-05, "epoch": 1.702415063446582, "percentage": 5.2, "elapsed_time": "0:14:16", "remaining_time": "4:20:18", "throughput": 790.81, "total_tokens": 677512} {"current_steps": 2085, "total_steps": 40000, "loss": 0.1958, "lr": 4.966587003863429e-05, "epoch": 1.7065083913221448, "percentage": 5.21, "elapsed_time": "0:14:18", "remaining_time": "4:20:10", "throughput": 791.06, "total_tokens": 679080} {"current_steps": 2090, "total_steps": 40000, "loss": 0.204, "lr": 4.966426840703765e-05, "epoch": 1.7106017191977076, "percentage": 5.22, "elapsed_time": "0:14:20", "remaining_time": "4:20:02", "throughput": 791.43, "total_tokens": 680760} {"current_steps": 2095, "total_steps": 40000, "loss": 0.216, "lr": 4.9662662971900875e-05, "epoch": 1.7146950470732705, "percentage": 5.24, "elapsed_time": "0:14:21", "remaining_time": "4:19:54", "throughput": 791.75, "total_tokens": 682392} {"current_steps": 2100, "total_steps": 40000, "loss": 0.2558, "lr": 4.9661053733471534e-05, "epoch": 1.7187883749488333, "percentage": 5.25, "elapsed_time": "0:14:23", "remaining_time": "4:19:46", "throughput": 792.09, "total_tokens": 684056} {"current_steps": 2105, "total_steps": 40000, "loss": 0.1779, "lr": 4.965944069199781e-05, "epoch": 1.7228817028243961, "percentage": 5.26, "elapsed_time": "0:14:25", "remaining_time": "4:19:37", "throughput": 792.46, "total_tokens": 685736} {"current_steps": 2110, "total_steps": 40000, "loss": 0.1988, "lr": 4.965782384772842e-05, "epoch": 1.726975030699959, "percentage": 5.27, "elapsed_time": "0:14:27", "remaining_time": "4:19:29", "throughput": 792.74, "total_tokens": 687336} {"current_steps": 2115, "total_steps": 40000, "loss": 0.217, "lr": 4.9656203200912734e-05, "epoch": 1.7310683585755218, "percentage": 5.29, "elapsed_time": "0:14:28", "remaining_time": "4:19:21", "throughput": 793.11, "total_tokens": 689016} {"current_steps": 2120, "total_steps": 40000, "loss": 0.2446, "lr": 4.965457875180067e-05, "epoch": 1.7351616864510846, "percentage": 5.3, "elapsed_time": "0:14:30", "remaining_time": "4:19:13", "throughput": 793.37, "total_tokens": 690616} {"current_steps": 2125, "total_steps": 40000, "loss": 0.19, "lr": 4.9652950500642724e-05, "epoch": 1.7392550143266474, "percentage": 5.31, "elapsed_time": "0:14:32", "remaining_time": "4:19:05", "throughput": 793.73, "total_tokens": 692296} {"current_steps": 2130, "total_steps": 40000, "loss": 0.1906, "lr": 4.965131844769001e-05, "epoch": 1.7433483422022102, "percentage": 5.33, "elapsed_time": "0:14:33", "remaining_time": "4:18:57", "throughput": 793.98, "total_tokens": 693880} {"current_steps": 2135, "total_steps": 40000, "loss": 0.2196, "lr": 4.96496825931942e-05, "epoch": 1.747441670077773, "percentage": 5.34, "elapsed_time": "0:14:35", "remaining_time": "4:18:49", "throughput": 794.31, "total_tokens": 695528} {"current_steps": 2140, "total_steps": 40000, "loss": 0.2489, "lr": 4.9648042937407566e-05, "epoch": 1.7515349979533361, "percentage": 5.35, "elapsed_time": "0:14:37", "remaining_time": "4:18:41", "throughput": 794.65, "total_tokens": 697192} {"current_steps": 2145, "total_steps": 40000, "loss": 0.2235, "lr": 4.964639948058297e-05, "epoch": 1.755628325828899, "percentage": 5.36, "elapsed_time": "0:14:39", "remaining_time": "4:18:33", "throughput": 794.88, "total_tokens": 698760} {"current_steps": 2150, "total_steps": 40000, "loss": 0.2152, "lr": 4.9644752222973846e-05, "epoch": 1.7597216537044618, "percentage": 5.38, "elapsed_time": "0:14:40", "remaining_time": "4:18:25", "throughput": 795.15, "total_tokens": 700360} {"current_steps": 2155, "total_steps": 40000, "loss": 0.2754, "lr": 4.964310116483422e-05, "epoch": 1.7638149815800246, "percentage": 5.39, "elapsed_time": "0:14:42", "remaining_time": "4:18:18", "throughput": 795.44, "total_tokens": 701976} {"current_steps": 2160, "total_steps": 40000, "loss": 0.2065, "lr": 4.964144630641872e-05, "epoch": 1.7679083094555874, "percentage": 5.4, "elapsed_time": "0:14:44", "remaining_time": "4:18:10", "throughput": 795.68, "total_tokens": 703560} {"current_steps": 2165, "total_steps": 40000, "loss": 0.2034, "lr": 4.9639787647982525e-05, "epoch": 1.7720016373311502, "percentage": 5.41, "elapsed_time": "0:14:45", "remaining_time": "4:18:02", "throughput": 795.99, "total_tokens": 705208} {"current_steps": 2170, "total_steps": 40000, "loss": 0.1987, "lr": 4.963812518978143e-05, "epoch": 1.776094965206713, "percentage": 5.42, "elapsed_time": "0:14:47", "remaining_time": "4:17:54", "throughput": 796.24, "total_tokens": 706792} {"current_steps": 2175, "total_steps": 40000, "loss": 0.2357, "lr": 4.963645893207182e-05, "epoch": 1.7801882930822759, "percentage": 5.44, "elapsed_time": "0:14:49", "remaining_time": "4:17:47", "throughput": 796.46, "total_tokens": 708360} {"current_steps": 2180, "total_steps": 40000, "loss": 0.2024, "lr": 4.963478887511063e-05, "epoch": 1.7842816209578387, "percentage": 5.45, "elapsed_time": "0:14:51", "remaining_time": "4:17:39", "throughput": 796.78, "total_tokens": 710008} {"current_steps": 2185, "total_steps": 40000, "loss": 0.2343, "lr": 4.963311501915542e-05, "epoch": 1.7883749488334015, "percentage": 5.46, "elapsed_time": "0:14:52", "remaining_time": "4:17:31", "throughput": 797.04, "total_tokens": 711608} {"current_steps": 2190, "total_steps": 40000, "loss": 0.2109, "lr": 4.963143736446432e-05, "epoch": 1.7924682767089644, "percentage": 5.47, "elapsed_time": "0:14:54", "remaining_time": "4:17:23", "throughput": 797.36, "total_tokens": 713256} {"current_steps": 2195, "total_steps": 40000, "loss": 0.2078, "lr": 4.962975591129603e-05, "epoch": 1.7965616045845272, "percentage": 5.49, "elapsed_time": "0:14:56", "remaining_time": "4:17:16", "throughput": 797.72, "total_tokens": 714952} {"current_steps": 2200, "total_steps": 40000, "loss": 0.223, "lr": 4.962807065990986e-05, "epoch": 1.80065493246009, "percentage": 5.5, "elapsed_time": "0:14:57", "remaining_time": "4:17:08", "throughput": 797.98, "total_tokens": 716552} {"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.22881293296813965, "epoch": 1.80065493246009, "percentage": 5.5, "elapsed_time": "0:15:10", "remaining_time": "4:20:42", "throughput": 787.06, "total_tokens": 716552} {"current_steps": 2205, "total_steps": 40000, "loss": 0.2199, "lr": 4.9626381610565714e-05, "epoch": 1.8047482603356528, "percentage": 5.51, "elapsed_time": "0:15:13", "remaining_time": "4:20:58", "throughput": 786.19, "total_tokens": 718184} {"current_steps": 2210, "total_steps": 40000, "loss": 0.2435, "lr": 4.9624688763524043e-05, "epoch": 1.8088415882112159, "percentage": 5.53, "elapsed_time": "0:15:15", "remaining_time": "4:20:50", "throughput": 786.44, "total_tokens": 719784} {"current_steps": 2215, "total_steps": 40000, "loss": 0.2429, "lr": 4.962299211904591e-05, "epoch": 1.8129349160867787, "percentage": 5.54, "elapsed_time": "0:15:16", "remaining_time": "4:20:42", "throughput": 786.75, "total_tokens": 721416} {"current_steps": 2220, "total_steps": 40000, "loss": 0.1747, "lr": 4.962129167739296e-05, "epoch": 1.8170282439623415, "percentage": 5.55, "elapsed_time": "0:15:18", "remaining_time": "4:20:33", "throughput": 787.09, "total_tokens": 723080} {"current_steps": 2225, "total_steps": 40000, "loss": 0.2088, "lr": 4.961958743882742e-05, "epoch": 1.8211215718379044, "percentage": 5.56, "elapsed_time": "0:15:20", "remaining_time": "4:20:25", "throughput": 787.4, "total_tokens": 724712} {"current_steps": 2230, "total_steps": 40000, "loss": 0.1923, "lr": 4.961787940361211e-05, "epoch": 1.8252148997134672, "percentage": 5.58, "elapsed_time": "0:15:22", "remaining_time": "4:20:17", "throughput": 787.72, "total_tokens": 726360} {"current_steps": 2235, "total_steps": 40000, "loss": 0.1916, "lr": 4.961616757201043e-05, "epoch": 1.82930822758903, "percentage": 5.59, "elapsed_time": "0:15:23", "remaining_time": "4:20:09", "throughput": 788.05, "total_tokens": 728024} {"current_steps": 2240, "total_steps": 40000, "loss": 0.227, "lr": 4.961445194428637e-05, "epoch": 1.8334015554645928, "percentage": 5.6, "elapsed_time": "0:15:25", "remaining_time": "4:20:01", "throughput": 788.37, "total_tokens": 729672} {"current_steps": 2245, "total_steps": 40000, "loss": 0.239, "lr": 4.9612732520704486e-05, "epoch": 1.8374948833401556, "percentage": 5.61, "elapsed_time": "0:15:27", "remaining_time": "4:19:54", "throughput": 788.71, "total_tokens": 731336} {"current_steps": 2250, "total_steps": 40000, "loss": 0.2786, "lr": 4.961100930152994e-05, "epoch": 1.8415882112157185, "percentage": 5.62, "elapsed_time": "0:15:28", "remaining_time": "4:19:46", "throughput": 788.99, "total_tokens": 732952} {"current_steps": 2255, "total_steps": 40000, "loss": 0.2151, "lr": 4.960928228702849e-05, "epoch": 1.8456815390912813, "percentage": 5.64, "elapsed_time": "0:15:30", "remaining_time": "4:19:38", "throughput": 789.25, "total_tokens": 734552} {"current_steps": 2260, "total_steps": 40000, "loss": 0.2534, "lr": 4.960755147746645e-05, "epoch": 1.8497748669668441, "percentage": 5.65, "elapsed_time": "0:15:32", "remaining_time": "4:19:30", "throughput": 789.55, "total_tokens": 736200} {"current_steps": 2265, "total_steps": 40000, "loss": 0.2182, "lr": 4.9605816873110736e-05, "epoch": 1.853868194842407, "percentage": 5.66, "elapsed_time": "0:15:34", "remaining_time": "4:19:22", "throughput": 789.82, "total_tokens": 737800} {"current_steps": 2270, "total_steps": 40000, "loss": 0.2463, "lr": 4.960407847422883e-05, "epoch": 1.8579615227179698, "percentage": 5.67, "elapsed_time": "0:15:35", "remaining_time": "4:19:15", "throughput": 790.08, "total_tokens": 739400} {"current_steps": 2275, "total_steps": 40000, "loss": 0.203, "lr": 4.960233628108885e-05, "epoch": 1.8620548505935326, "percentage": 5.69, "elapsed_time": "0:15:37", "remaining_time": "4:19:07", "throughput": 790.37, "total_tokens": 741032} {"current_steps": 2280, "total_steps": 40000, "loss": 0.2415, "lr": 4.960059029395942e-05, "epoch": 1.8661481784690954, "percentage": 5.7, "elapsed_time": "0:15:39", "remaining_time": "4:18:59", "throughput": 790.66, "total_tokens": 742664} {"current_steps": 2285, "total_steps": 40000, "loss": 0.2707, "lr": 4.959884051310983e-05, "epoch": 1.8702415063446582, "percentage": 5.71, "elapsed_time": "0:15:41", "remaining_time": "4:18:51", "throughput": 790.92, "total_tokens": 744264} {"current_steps": 2290, "total_steps": 40000, "loss": 0.2231, "lr": 4.959708693880991e-05, "epoch": 1.874334834220221, "percentage": 5.73, "elapsed_time": "0:15:42", "remaining_time": "4:18:44", "throughput": 791.15, "total_tokens": 745832} {"current_steps": 2295, "total_steps": 40000, "loss": 0.236, "lr": 4.9595329571330074e-05, "epoch": 1.878428162095784, "percentage": 5.74, "elapsed_time": "0:15:44", "remaining_time": "4:18:36", "throughput": 791.49, "total_tokens": 747512} {"current_steps": 2300, "total_steps": 40000, "loss": 0.2299, "lr": 4.9593568410941326e-05, "epoch": 1.8825214899713467, "percentage": 5.75, "elapsed_time": "0:15:46", "remaining_time": "4:18:28", "throughput": 791.71, "total_tokens": 749096} {"current_steps": 2305, "total_steps": 40000, "loss": 0.2453, "lr": 4.959180345791528e-05, "epoch": 1.8866148178469095, "percentage": 5.76, "elapsed_time": "0:15:47", "remaining_time": "4:18:21", "throughput": 792.08, "total_tokens": 750808} {"current_steps": 2310, "total_steps": 40000, "loss": 0.1949, "lr": 4.9590034712524086e-05, "epoch": 1.8907081457224724, "percentage": 5.78, "elapsed_time": "0:15:49", "remaining_time": "4:18:13", "throughput": 792.45, "total_tokens": 752520} {"current_steps": 2315, "total_steps": 40000, "loss": 0.2235, "lr": 4.958826217504053e-05, "epoch": 1.8948014735980352, "percentage": 5.79, "elapsed_time": "0:15:51", "remaining_time": "4:18:06", "throughput": 792.74, "total_tokens": 754152} {"current_steps": 2320, "total_steps": 40000, "loss": 0.2531, "lr": 4.958648584573795e-05, "epoch": 1.898894801473598, "percentage": 5.8, "elapsed_time": "0:15:53", "remaining_time": "4:17:58", "throughput": 792.97, "total_tokens": 755736} {"current_steps": 2325, "total_steps": 40000, "loss": 0.2081, "lr": 4.958470572489028e-05, "epoch": 1.9029881293491608, "percentage": 5.81, "elapsed_time": "0:15:54", "remaining_time": "4:17:51", "throughput": 793.19, "total_tokens": 757304} {"current_steps": 2330, "total_steps": 40000, "loss": 0.2337, "lr": 4.958292181277203e-05, "epoch": 1.9070814572247237, "percentage": 5.83, "elapsed_time": "0:15:56", "remaining_time": "4:17:43", "throughput": 793.51, "total_tokens": 758968} {"current_steps": 2335, "total_steps": 40000, "loss": 0.2493, "lr": 4.958113410965832e-05, "epoch": 1.9111747851002865, "percentage": 5.84, "elapsed_time": "0:15:58", "remaining_time": "4:17:36", "throughput": 793.8, "total_tokens": 760616} {"current_steps": 2340, "total_steps": 40000, "loss": 0.1963, "lr": 4.957934261582481e-05, "epoch": 1.9152681129758493, "percentage": 5.85, "elapsed_time": "0:15:59", "remaining_time": "4:17:29", "throughput": 794.11, "total_tokens": 762280} {"current_steps": 2345, "total_steps": 40000, "loss": 0.201, "lr": 4.95775473315478e-05, "epoch": 1.9193614408514121, "percentage": 5.86, "elapsed_time": "0:16:01", "remaining_time": "4:17:21", "throughput": 794.38, "total_tokens": 763912} {"current_steps": 2350, "total_steps": 40000, "loss": 0.2848, "lr": 4.9575748257104124e-05, "epoch": 1.923454768726975, "percentage": 5.88, "elapsed_time": "0:16:03", "remaining_time": "4:17:14", "throughput": 794.73, "total_tokens": 765608} {"current_steps": 2355, "total_steps": 40000, "loss": 0.2589, "lr": 4.9573945392771224e-05, "epoch": 1.9275480966025378, "percentage": 5.89, "elapsed_time": "0:16:05", "remaining_time": "4:17:06", "throughput": 794.97, "total_tokens": 767208} {"current_steps": 2360, "total_steps": 40000, "loss": 0.2515, "lr": 4.9572138738827134e-05, "epoch": 1.9316414244781006, "percentage": 5.9, "elapsed_time": "0:16:06", "remaining_time": "4:16:59", "throughput": 795.25, "total_tokens": 768840} {"current_steps": 2365, "total_steps": 40000, "loss": 0.2392, "lr": 4.957032829555046e-05, "epoch": 1.9357347523536634, "percentage": 5.91, "elapsed_time": "0:16:08", "remaining_time": "4:16:52", "throughput": 795.64, "total_tokens": 770584} {"current_steps": 2370, "total_steps": 40000, "loss": 0.2787, "lr": 4.956851406322039e-05, "epoch": 1.9398280802292263, "percentage": 5.92, "elapsed_time": "0:16:10", "remaining_time": "4:16:44", "throughput": 795.86, "total_tokens": 772168} {"current_steps": 2375, "total_steps": 40000, "loss": 0.2196, "lr": 4.9566696042116704e-05, "epoch": 1.943921408104789, "percentage": 5.94, "elapsed_time": "0:16:11", "remaining_time": "4:16:37", "throughput": 796.21, "total_tokens": 773864} {"current_steps": 2380, "total_steps": 40000, "loss": 0.2369, "lr": 4.9564874232519766e-05, "epoch": 1.948014735980352, "percentage": 5.95, "elapsed_time": "0:16:13", "remaining_time": "4:16:30", "throughput": 796.5, "total_tokens": 775512} {"current_steps": 2385, "total_steps": 40000, "loss": 0.2072, "lr": 4.9563048634710516e-05, "epoch": 1.9521080638559147, "percentage": 5.96, "elapsed_time": "0:16:15", "remaining_time": "4:16:23", "throughput": 796.7, "total_tokens": 777080} {"current_steps": 2390, "total_steps": 40000, "loss": 0.2041, "lr": 4.956121924897049e-05, "epoch": 1.9562013917314776, "percentage": 5.97, "elapsed_time": "0:16:17", "remaining_time": "4:16:15", "throughput": 796.95, "total_tokens": 778696} {"current_steps": 2395, "total_steps": 40000, "loss": 0.2059, "lr": 4.955938607558181e-05, "epoch": 1.9602947196070404, "percentage": 5.99, "elapsed_time": "0:16:18", "remaining_time": "4:16:08", "throughput": 797.24, "total_tokens": 780344} {"current_steps": 2400, "total_steps": 40000, "loss": 0.1983, "lr": 4.955754911482715e-05, "epoch": 1.9643880474826032, "percentage": 6.0, "elapsed_time": "0:16:20", "remaining_time": "4:16:01", "throughput": 797.53, "total_tokens": 781992} {"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.2223738133907318, "epoch": 1.9643880474826032, "percentage": 6.0, "elapsed_time": "0:16:32", "remaining_time": "4:19:16", "throughput": 787.53, "total_tokens": 781992} {"current_steps": 2405, "total_steps": 40000, "loss": 0.2009, "lr": 4.9555708366989804e-05, "epoch": 1.968481375358166, "percentage": 6.01, "elapsed_time": "0:16:36", "remaining_time": "4:19:35", "throughput": 786.51, "total_tokens": 783656} {"current_steps": 2410, "total_steps": 40000, "loss": 0.2083, "lr": 4.9553863832353655e-05, "epoch": 1.972574703233729, "percentage": 6.02, "elapsed_time": "0:16:38", "remaining_time": "4:19:27", "throughput": 786.87, "total_tokens": 785368} {"current_steps": 2415, "total_steps": 40000, "loss": 0.2301, "lr": 4.955201551120313e-05, "epoch": 1.976668031109292, "percentage": 6.04, "elapsed_time": "0:16:39", "remaining_time": "4:19:20", "throughput": 787.2, "total_tokens": 787048} {"current_steps": 2420, "total_steps": 40000, "loss": 0.4262, "lr": 4.955016340382328e-05, "epoch": 1.9807613589848547, "percentage": 6.05, "elapsed_time": "0:16:41", "remaining_time": "4:19:12", "throughput": 787.48, "total_tokens": 788680} {"current_steps": 2425, "total_steps": 40000, "loss": 0.2138, "lr": 4.954830751049972e-05, "epoch": 1.9848546868604175, "percentage": 6.06, "elapsed_time": "0:16:43", "remaining_time": "4:19:04", "throughput": 787.78, "total_tokens": 790328} {"current_steps": 2430, "total_steps": 40000, "loss": 0.1861, "lr": 4.954644783151864e-05, "epoch": 1.9889480147359804, "percentage": 6.08, "elapsed_time": "0:16:44", "remaining_time": "4:18:57", "throughput": 788.16, "total_tokens": 792072} {"current_steps": 2435, "total_steps": 40000, "loss": 0.243, "lr": 4.954458436716684e-05, "epoch": 1.9930413426115432, "percentage": 6.09, "elapsed_time": "0:16:46", "remaining_time": "4:18:50", "throughput": 788.45, "total_tokens": 793720} {"current_steps": 2440, "total_steps": 40000, "loss": 0.1895, "lr": 4.954271711773168e-05, "epoch": 1.997134670487106, "percentage": 6.1, "elapsed_time": "0:16:48", "remaining_time": "4:18:42", "throughput": 788.66, "total_tokens": 795288} {"current_steps": 2445, "total_steps": 40000, "loss": 0.2244, "lr": 4.9540846083501115e-05, "epoch": 2.0008186655751126, "percentage": 6.11, "elapsed_time": "0:16:50", "remaining_time": "4:18:37", "throughput": 788.54, "total_tokens": 796656} {"current_steps": 2450, "total_steps": 40000, "loss": 0.2222, "lr": 4.953897126476369e-05, "epoch": 2.0049119934506754, "percentage": 6.12, "elapsed_time": "0:16:52", "remaining_time": "4:18:30", "throughput": 788.88, "total_tokens": 798352} {"current_steps": 2455, "total_steps": 40000, "loss": 0.1917, "lr": 4.9537092661808514e-05, "epoch": 2.009005321326238, "percentage": 6.14, "elapsed_time": "0:16:53", "remaining_time": "4:18:23", "throughput": 789.26, "total_tokens": 800096} {"current_steps": 2460, "total_steps": 40000, "loss": 0.218, "lr": 4.9535210274925306e-05, "epoch": 2.013098649201801, "percentage": 6.15, "elapsed_time": "0:16:55", "remaining_time": "4:18:15", "throughput": 789.52, "total_tokens": 801712} {"current_steps": 2465, "total_steps": 40000, "loss": 0.5014, "lr": 4.953332410440435e-05, "epoch": 2.017191977077364, "percentage": 6.16, "elapsed_time": "0:16:57", "remaining_time": "4:18:08", "throughput": 789.92, "total_tokens": 803472} {"current_steps": 2470, "total_steps": 40000, "loss": 0.2119, "lr": 4.9531434150536496e-05, "epoch": 2.0212853049529267, "percentage": 6.17, "elapsed_time": "0:16:58", "remaining_time": "4:18:01", "throughput": 790.16, "total_tokens": 805072} {"current_steps": 2475, "total_steps": 40000, "loss": 0.1843, "lr": 4.952954041361322e-05, "epoch": 2.0253786328284895, "percentage": 6.19, "elapsed_time": "0:17:00", "remaining_time": "4:17:54", "throughput": 790.43, "total_tokens": 806720} {"current_steps": 2480, "total_steps": 40000, "loss": 0.2208, "lr": 4.952764289392655e-05, "epoch": 2.0294719607040523, "percentage": 6.2, "elapsed_time": "0:17:02", "remaining_time": "4:17:46", "throughput": 790.7, "total_tokens": 808352} {"current_steps": 2485, "total_steps": 40000, "loss": 0.2063, "lr": 4.952574159176912e-05, "epoch": 2.033565288579615, "percentage": 6.21, "elapsed_time": "0:17:04", "remaining_time": "4:17:39", "throughput": 790.92, "total_tokens": 809936} {"current_steps": 2490, "total_steps": 40000, "loss": 0.2384, "lr": 4.952383650743413e-05, "epoch": 2.037658616455178, "percentage": 6.22, "elapsed_time": "0:17:05", "remaining_time": "4:17:32", "throughput": 791.14, "total_tokens": 811520} {"current_steps": 2495, "total_steps": 40000, "loss": 0.1894, "lr": 4.952192764121536e-05, "epoch": 2.041751944330741, "percentage": 6.24, "elapsed_time": "0:17:07", "remaining_time": "4:17:25", "throughput": 791.38, "total_tokens": 813120} {"current_steps": 2500, "total_steps": 40000, "loss": 0.1888, "lr": 4.9520014993407185e-05, "epoch": 2.0458452722063036, "percentage": 6.25, "elapsed_time": "0:17:09", "remaining_time": "4:17:17", "throughput": 791.66, "total_tokens": 814768} {"current_steps": 2505, "total_steps": 40000, "loss": 0.2486, "lr": 4.951809856430456e-05, "epoch": 2.0499386000818665, "percentage": 6.26, "elapsed_time": "0:17:10", "remaining_time": "4:17:10", "throughput": 791.92, "total_tokens": 816400} {"current_steps": 2510, "total_steps": 40000, "loss": 0.2029, "lr": 4.951617835420303e-05, "epoch": 2.0540319279574293, "percentage": 6.28, "elapsed_time": "0:17:12", "remaining_time": "4:17:03", "throughput": 792.18, "total_tokens": 818032} {"current_steps": 2515, "total_steps": 40000, "loss": 0.2245, "lr": 4.951425436339869e-05, "epoch": 2.058125255832992, "percentage": 6.29, "elapsed_time": "0:17:14", "remaining_time": "4:16:56", "throughput": 792.37, "total_tokens": 819584} {"current_steps": 2520, "total_steps": 40000, "loss": 0.2591, "lr": 4.9512326592188274e-05, "epoch": 2.062218583708555, "percentage": 6.3, "elapsed_time": "0:17:16", "remaining_time": "4:16:49", "throughput": 792.61, "total_tokens": 821216} {"current_steps": 2525, "total_steps": 40000, "loss": 0.2506, "lr": 4.9510395040869054e-05, "epoch": 2.0663119115841178, "percentage": 6.31, "elapsed_time": "0:17:17", "remaining_time": "4:16:42", "throughput": 792.94, "total_tokens": 822912} {"current_steps": 2530, "total_steps": 40000, "loss": 0.193, "lr": 4.9508459709738905e-05, "epoch": 2.0704052394596806, "percentage": 6.33, "elapsed_time": "0:17:19", "remaining_time": "4:16:35", "throughput": 793.17, "total_tokens": 824512} {"current_steps": 2535, "total_steps": 40000, "loss": 0.2021, "lr": 4.950652059909627e-05, "epoch": 2.0744985673352434, "percentage": 6.34, "elapsed_time": "0:17:21", "remaining_time": "4:16:28", "throughput": 793.41, "total_tokens": 826128} {"current_steps": 2540, "total_steps": 40000, "loss": 0.246, "lr": 4.95045777092402e-05, "epoch": 2.0785918952108062, "percentage": 6.35, "elapsed_time": "0:17:22", "remaining_time": "4:16:21", "throughput": 793.66, "total_tokens": 827744} {"current_steps": 2545, "total_steps": 40000, "loss": 0.2456, "lr": 4.950263104047031e-05, "epoch": 2.082685223086369, "percentage": 6.36, "elapsed_time": "0:17:24", "remaining_time": "4:16:14", "throughput": 793.85, "total_tokens": 829312} {"current_steps": 2550, "total_steps": 40000, "loss": 0.2336, "lr": 4.9500680593086775e-05, "epoch": 2.086778550961932, "percentage": 6.38, "elapsed_time": "0:17:26", "remaining_time": "4:16:07", "throughput": 794.08, "total_tokens": 830912} {"current_steps": 2555, "total_steps": 40000, "loss": 0.2375, "lr": 4.94987263673904e-05, "epoch": 2.0908718788374947, "percentage": 6.39, "elapsed_time": "0:17:28", "remaining_time": "4:16:00", "throughput": 794.32, "total_tokens": 832528} {"current_steps": 2560, "total_steps": 40000, "loss": 0.1966, "lr": 4.949676836368256e-05, "epoch": 2.0949652067130575, "percentage": 6.4, "elapsed_time": "0:17:29", "remaining_time": "4:15:53", "throughput": 794.59, "total_tokens": 834176} {"current_steps": 2565, "total_steps": 40000, "loss": 0.2591, "lr": 4.949480658226518e-05, "epoch": 2.0990585345886204, "percentage": 6.41, "elapsed_time": "0:17:31", "remaining_time": "4:15:46", "throughput": 794.89, "total_tokens": 835856} {"current_steps": 2570, "total_steps": 40000, "loss": 0.2605, "lr": 4.949284102344082e-05, "epoch": 2.103151862464183, "percentage": 6.42, "elapsed_time": "0:17:33", "remaining_time": "4:15:39", "throughput": 795.13, "total_tokens": 837472} {"current_steps": 2575, "total_steps": 40000, "loss": 0.2032, "lr": 4.9490871687512565e-05, "epoch": 2.107245190339746, "percentage": 6.44, "elapsed_time": "0:17:34", "remaining_time": "4:15:32", "throughput": 795.41, "total_tokens": 839136} {"current_steps": 2580, "total_steps": 40000, "loss": 0.2491, "lr": 4.948889857478413e-05, "epoch": 2.111338518215309, "percentage": 6.45, "elapsed_time": "0:17:36", "remaining_time": "4:15:26", "throughput": 795.63, "total_tokens": 840736} {"current_steps": 2585, "total_steps": 40000, "loss": 0.2253, "lr": 4.948692168555978e-05, "epoch": 2.115431846090872, "percentage": 6.46, "elapsed_time": "0:17:38", "remaining_time": "4:15:19", "throughput": 795.88, "total_tokens": 842368} {"current_steps": 2590, "total_steps": 40000, "loss": 0.2078, "lr": 4.94849410201444e-05, "epoch": 2.119525173966435, "percentage": 6.48, "elapsed_time": "0:17:40", "remaining_time": "4:15:12", "throughput": 796.08, "total_tokens": 843952} {"current_steps": 2595, "total_steps": 40000, "loss": 0.2641, "lr": 4.948295657884341e-05, "epoch": 2.1236185018419977, "percentage": 6.49, "elapsed_time": "0:17:41", "remaining_time": "4:15:05", "throughput": 796.3, "total_tokens": 845552} {"current_steps": 2600, "total_steps": 40000, "loss": 0.2409, "lr": 4.9480968361962835e-05, "epoch": 2.1277118297175606, "percentage": 6.5, "elapsed_time": "0:17:43", "remaining_time": "4:14:59", "throughput": 796.5, "total_tokens": 847136} {"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.22447283565998077, "epoch": 2.1277118297175606, "percentage": 6.5, "elapsed_time": "0:17:56", "remaining_time": "4:17:57", "throughput": 787.3, "total_tokens": 847136} {"current_steps": 2605, "total_steps": 40000, "loss": 0.2632, "lr": 4.9478976369809305e-05, "epoch": 2.1318051575931234, "percentage": 6.51, "elapsed_time": "0:17:59", "remaining_time": "4:18:14", "throughput": 786.33, "total_tokens": 848720} {"current_steps": 2610, "total_steps": 40000, "loss": 0.2263, "lr": 4.947698060268999e-05, "epoch": 2.135898485468686, "percentage": 6.53, "elapsed_time": "0:18:01", "remaining_time": "4:18:07", "throughput": 786.53, "total_tokens": 850304} {"current_steps": 2615, "total_steps": 40000, "loss": 0.21, "lr": 4.9474981060912665e-05, "epoch": 2.139991813344249, "percentage": 6.54, "elapsed_time": "0:18:02", "remaining_time": "4:18:00", "throughput": 786.75, "total_tokens": 851888} {"current_steps": 2620, "total_steps": 40000, "loss": 0.2303, "lr": 4.94729777447857e-05, "epoch": 2.144085141219812, "percentage": 6.55, "elapsed_time": "0:18:04", "remaining_time": "4:17:52", "throughput": 787.06, "total_tokens": 853584} {"current_steps": 2625, "total_steps": 40000, "loss": 0.2056, "lr": 4.947097065461801e-05, "epoch": 2.1481784690953747, "percentage": 6.56, "elapsed_time": "0:18:06", "remaining_time": "4:17:45", "throughput": 787.3, "total_tokens": 855200} {"current_steps": 2630, "total_steps": 40000, "loss": 0.2099, "lr": 4.9468959790719125e-05, "epoch": 2.1522717969709375, "percentage": 6.58, "elapsed_time": "0:18:07", "remaining_time": "4:17:38", "throughput": 787.55, "total_tokens": 856816} {"current_steps": 2635, "total_steps": 40000, "loss": 0.2017, "lr": 4.9466945153399146e-05, "epoch": 2.1563651248465003, "percentage": 6.59, "elapsed_time": "0:18:09", "remaining_time": "4:17:31", "throughput": 787.79, "total_tokens": 858432} {"current_steps": 2640, "total_steps": 40000, "loss": 0.2472, "lr": 4.9464926742968755e-05, "epoch": 2.160458452722063, "percentage": 6.6, "elapsed_time": "0:18:11", "remaining_time": "4:17:24", "throughput": 788.04, "total_tokens": 860064} {"current_steps": 2645, "total_steps": 40000, "loss": 0.1797, "lr": 4.946290455973921e-05, "epoch": 2.164551780597626, "percentage": 6.61, "elapsed_time": "0:18:13", "remaining_time": "4:17:17", "throughput": 788.37, "total_tokens": 861776} {"current_steps": 2650, "total_steps": 40000, "loss": 0.2059, "lr": 4.9460878604022365e-05, "epoch": 2.168645108473189, "percentage": 6.62, "elapsed_time": "0:18:14", "remaining_time": "4:17:11", "throughput": 788.6, "total_tokens": 863392} {"current_steps": 2655, "total_steps": 40000, "loss": 0.2382, "lr": 4.945884887613065e-05, "epoch": 2.1727384363487516, "percentage": 6.64, "elapsed_time": "0:18:16", "remaining_time": "4:17:04", "throughput": 788.83, "total_tokens": 865008} {"current_steps": 2660, "total_steps": 40000, "loss": 0.1939, "lr": 4.9456815376377055e-05, "epoch": 2.1768317642243145, "percentage": 6.65, "elapsed_time": "0:18:18", "remaining_time": "4:16:57", "throughput": 789.06, "total_tokens": 866624} {"current_steps": 2665, "total_steps": 40000, "loss": 0.221, "lr": 4.9454778105075195e-05, "epoch": 2.1809250920998773, "percentage": 6.66, "elapsed_time": "0:18:20", "remaining_time": "4:16:50", "throughput": 789.27, "total_tokens": 868208} {"current_steps": 2670, "total_steps": 40000, "loss": 0.2251, "lr": 4.945273706253924e-05, "epoch": 2.18501841997544, "percentage": 6.68, "elapsed_time": "0:18:21", "remaining_time": "4:16:43", "throughput": 789.55, "total_tokens": 869872} {"current_steps": 2675, "total_steps": 40000, "loss": 0.1988, "lr": 4.9450692249083925e-05, "epoch": 2.189111747851003, "percentage": 6.69, "elapsed_time": "0:18:23", "remaining_time": "4:16:36", "throughput": 789.77, "total_tokens": 871472} {"current_steps": 2680, "total_steps": 40000, "loss": 0.2673, "lr": 4.9448643665024605e-05, "epoch": 2.1932050757265658, "percentage": 6.7, "elapsed_time": "0:18:25", "remaining_time": "4:16:29", "throughput": 790.06, "total_tokens": 873152} {"current_steps": 2685, "total_steps": 40000, "loss": 0.2284, "lr": 4.944659131067719e-05, "epoch": 2.1972984036021286, "percentage": 6.71, "elapsed_time": "0:18:26", "remaining_time": "4:16:23", "throughput": 790.29, "total_tokens": 874768} {"current_steps": 2690, "total_steps": 40000, "loss": 0.2683, "lr": 4.944453518635818e-05, "epoch": 2.2013917314776914, "percentage": 6.73, "elapsed_time": "0:18:28", "remaining_time": "4:16:16", "throughput": 790.51, "total_tokens": 876368} {"current_steps": 2695, "total_steps": 40000, "loss": 0.2599, "lr": 4.944247529238465e-05, "epoch": 2.2054850593532542, "percentage": 6.74, "elapsed_time": "0:18:30", "remaining_time": "4:16:09", "throughput": 790.73, "total_tokens": 877984} {"current_steps": 2700, "total_steps": 40000, "loss": 0.2058, "lr": 4.944041162907427e-05, "epoch": 2.209578387228817, "percentage": 6.75, "elapsed_time": "0:18:32", "remaining_time": "4:16:02", "throughput": 791.01, "total_tokens": 879648} {"current_steps": 2705, "total_steps": 40000, "loss": 0.2195, "lr": 4.943834419674529e-05, "epoch": 2.21367171510438, "percentage": 6.76, "elapsed_time": "0:18:33", "remaining_time": "4:15:56", "throughput": 791.24, "total_tokens": 881264} {"current_steps": 2710, "total_steps": 40000, "loss": 0.2055, "lr": 4.9436272995716506e-05, "epoch": 2.2177650429799427, "percentage": 6.78, "elapsed_time": "0:18:35", "remaining_time": "4:15:49", "throughput": 791.5, "total_tokens": 882912} {"current_steps": 2715, "total_steps": 40000, "loss": 0.2256, "lr": 4.943419802630735e-05, "epoch": 2.2218583708555055, "percentage": 6.79, "elapsed_time": "0:18:37", "remaining_time": "4:15:42", "throughput": 791.71, "total_tokens": 884512} {"current_steps": 2720, "total_steps": 40000, "loss": 0.2504, "lr": 4.94321192888378e-05, "epoch": 2.2259516987310684, "percentage": 6.8, "elapsed_time": "0:18:38", "remaining_time": "4:15:35", "throughput": 791.96, "total_tokens": 886144} {"current_steps": 2725, "total_steps": 40000, "loss": 0.2261, "lr": 4.943003678362842e-05, "epoch": 2.230045026606631, "percentage": 6.81, "elapsed_time": "0:18:40", "remaining_time": "4:15:29", "throughput": 792.17, "total_tokens": 887744} {"current_steps": 2730, "total_steps": 40000, "loss": 0.2619, "lr": 4.942795051100036e-05, "epoch": 2.234138354482194, "percentage": 6.83, "elapsed_time": "0:18:42", "remaining_time": "4:15:22", "throughput": 792.39, "total_tokens": 889344} {"current_steps": 2735, "total_steps": 40000, "loss": 0.207, "lr": 4.942586047127536e-05, "epoch": 2.238231682357757, "percentage": 6.84, "elapsed_time": "0:18:44", "remaining_time": "4:15:15", "throughput": 792.66, "total_tokens": 891008} {"current_steps": 2740, "total_steps": 40000, "loss": 0.2018, "lr": 4.942376666477571e-05, "epoch": 2.2423250102333196, "percentage": 6.85, "elapsed_time": "0:18:45", "remaining_time": "4:15:09", "throughput": 792.92, "total_tokens": 892672} {"current_steps": 2745, "total_steps": 40000, "loss": 0.2015, "lr": 4.9421669091824304e-05, "epoch": 2.2464183381088825, "percentage": 6.86, "elapsed_time": "0:18:47", "remaining_time": "4:15:02", "throughput": 793.16, "total_tokens": 894304} {"current_steps": 2750, "total_steps": 40000, "loss": 0.2471, "lr": 4.9419567752744634e-05, "epoch": 2.2505116659844453, "percentage": 6.88, "elapsed_time": "0:18:49", "remaining_time": "4:14:56", "throughput": 793.42, "total_tokens": 895968} {"current_steps": 2755, "total_steps": 40000, "loss": 0.186, "lr": 4.941746264786074e-05, "epoch": 2.254604993860008, "percentage": 6.89, "elapsed_time": "0:18:50", "remaining_time": "4:14:49", "throughput": 793.63, "total_tokens": 897568} {"current_steps": 2760, "total_steps": 40000, "loss": 0.181, "lr": 4.9415353777497254e-05, "epoch": 2.258698321735571, "percentage": 6.9, "elapsed_time": "0:18:52", "remaining_time": "4:14:42", "throughput": 793.89, "total_tokens": 899216} {"current_steps": 2765, "total_steps": 40000, "loss": 0.2464, "lr": 4.9413241141979394e-05, "epoch": 2.2627916496111338, "percentage": 6.91, "elapsed_time": "0:18:54", "remaining_time": "4:14:36", "throughput": 794.11, "total_tokens": 900832} {"current_steps": 2770, "total_steps": 40000, "loss": 0.1923, "lr": 4.9411124741632956e-05, "epoch": 2.2668849774866966, "percentage": 6.93, "elapsed_time": "0:18:56", "remaining_time": "4:14:29", "throughput": 794.26, "total_tokens": 902368} {"current_steps": 2775, "total_steps": 40000, "loss": 0.179, "lr": 4.940900457678431e-05, "epoch": 2.2709783053622594, "percentage": 6.94, "elapsed_time": "0:18:57", "remaining_time": "4:14:23", "throughput": 794.5, "total_tokens": 904000} {"current_steps": 2780, "total_steps": 40000, "loss": 0.2121, "lr": 4.9406880647760425e-05, "epoch": 2.2750716332378222, "percentage": 6.95, "elapsed_time": "0:18:59", "remaining_time": "4:14:16", "throughput": 794.72, "total_tokens": 905616} {"current_steps": 2785, "total_steps": 40000, "loss": 0.1948, "lr": 4.9404752954888824e-05, "epoch": 2.279164961113385, "percentage": 6.96, "elapsed_time": "0:19:01", "remaining_time": "4:14:10", "throughput": 794.95, "total_tokens": 907248} {"current_steps": 2790, "total_steps": 40000, "loss": 0.2205, "lr": 4.940262149849762e-05, "epoch": 2.283258288988948, "percentage": 6.98, "elapsed_time": "0:19:02", "remaining_time": "4:14:03", "throughput": 795.16, "total_tokens": 908848} {"current_steps": 2795, "total_steps": 40000, "loss": 0.2069, "lr": 4.9400486278915526e-05, "epoch": 2.2873516168645107, "percentage": 6.99, "elapsed_time": "0:19:04", "remaining_time": "4:13:57", "throughput": 795.39, "total_tokens": 910480} {"current_steps": 2800, "total_steps": 40000, "loss": 0.2164, "lr": 4.939834729647181e-05, "epoch": 2.2914449447400735, "percentage": 7.0, "elapsed_time": "0:19:06", "remaining_time": "4:13:50", "throughput": 795.59, "total_tokens": 912064} {"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.21949447691440582, "epoch": 2.2914449447400735, "percentage": 7.0, "elapsed_time": "0:19:18", "remaining_time": "4:16:36", "throughput": 787.02, "total_tokens": 912064} {"current_steps": 2805, "total_steps": 40000, "loss": 0.2237, "lr": 4.9396204551496326e-05, "epoch": 2.2955382726156364, "percentage": 7.01, "elapsed_time": "0:19:22", "remaining_time": "4:16:48", "throughput": 786.3, "total_tokens": 913696} {"current_steps": 2810, "total_steps": 40000, "loss": 0.2222, "lr": 4.939405804431952e-05, "epoch": 2.299631600491199, "percentage": 7.03, "elapsed_time": "0:19:23", "remaining_time": "4:16:41", "throughput": 786.57, "total_tokens": 915360} {"current_steps": 2815, "total_steps": 40000, "loss": 0.2237, "lr": 4.9391907775272414e-05, "epoch": 2.303724928366762, "percentage": 7.04, "elapsed_time": "0:19:25", "remaining_time": "4:16:35", "throughput": 786.8, "total_tokens": 916976} {"current_steps": 2820, "total_steps": 40000, "loss": 0.2121, "lr": 4.9389753744686604e-05, "epoch": 2.307818256242325, "percentage": 7.05, "elapsed_time": "0:19:27", "remaining_time": "4:16:28", "throughput": 787.04, "total_tokens": 918608} {"current_steps": 2825, "total_steps": 40000, "loss": 0.1653, "lr": 4.938759595289426e-05, "epoch": 2.3119115841178877, "percentage": 7.06, "elapsed_time": "0:19:28", "remaining_time": "4:16:21", "throughput": 787.26, "total_tokens": 920224} {"current_steps": 2830, "total_steps": 40000, "loss": 0.1868, "lr": 4.938543440022815e-05, "epoch": 2.3160049119934505, "percentage": 7.07, "elapsed_time": "0:19:30", "remaining_time": "4:16:15", "throughput": 787.46, "total_tokens": 921824} {"current_steps": 2835, "total_steps": 40000, "loss": 0.2707, "lr": 4.938326908702161e-05, "epoch": 2.3200982398690133, "percentage": 7.09, "elapsed_time": "0:19:32", "remaining_time": "4:16:08", "throughput": 787.66, "total_tokens": 923408} {"current_steps": 2840, "total_steps": 40000, "loss": 0.1873, "lr": 4.9381100013608554e-05, "epoch": 2.3241915677445766, "percentage": 7.1, "elapsed_time": "0:19:34", "remaining_time": "4:16:02", "throughput": 787.92, "total_tokens": 925072} {"current_steps": 2845, "total_steps": 40000, "loss": 0.2223, "lr": 4.9378927180323485e-05, "epoch": 2.328284895620139, "percentage": 7.11, "elapsed_time": "0:19:35", "remaining_time": "4:15:55", "throughput": 788.13, "total_tokens": 926672} {"current_steps": 2850, "total_steps": 40000, "loss": 0.264, "lr": 4.937675058750148e-05, "epoch": 2.3323782234957022, "percentage": 7.12, "elapsed_time": "0:19:37", "remaining_time": "4:15:48", "throughput": 788.42, "total_tokens": 928368} {"current_steps": 2855, "total_steps": 40000, "loss": 0.2116, "lr": 4.937457023547819e-05, "epoch": 2.3364715513712646, "percentage": 7.14, "elapsed_time": "0:19:39", "remaining_time": "4:15:42", "throughput": 788.59, "total_tokens": 929920} {"current_steps": 2860, "total_steps": 40000, "loss": 0.2041, "lr": 4.9372386124589876e-05, "epoch": 2.340564879246828, "percentage": 7.15, "elapsed_time": "0:19:40", "remaining_time": "4:15:35", "throughput": 788.78, "total_tokens": 931504} {"current_steps": 2865, "total_steps": 40000, "loss": 0.2244, "lr": 4.937019825517333e-05, "epoch": 2.3446582071223903, "percentage": 7.16, "elapsed_time": "0:19:42", "remaining_time": "4:15:29", "throughput": 788.98, "total_tokens": 933088} {"current_steps": 2870, "total_steps": 40000, "loss": 0.1668, "lr": 4.9368006627565954e-05, "epoch": 2.3487515349979535, "percentage": 7.17, "elapsed_time": "0:19:44", "remaining_time": "4:15:22", "throughput": 789.18, "total_tokens": 934688} {"current_steps": 2875, "total_steps": 40000, "loss": 0.245, "lr": 4.936581124210573e-05, "epoch": 2.3528448628735164, "percentage": 7.19, "elapsed_time": "0:19:46", "remaining_time": "4:15:16", "throughput": 789.43, "total_tokens": 936352} {"current_steps": 2880, "total_steps": 40000, "loss": 0.2063, "lr": 4.9363612099131216e-05, "epoch": 2.356938190749079, "percentage": 7.2, "elapsed_time": "0:19:47", "remaining_time": "4:15:09", "throughput": 789.66, "total_tokens": 937984} {"current_steps": 2885, "total_steps": 40000, "loss": 0.2043, "lr": 4.936140919898155e-05, "epoch": 2.361031518624642, "percentage": 7.21, "elapsed_time": "0:19:49", "remaining_time": "4:15:03", "throughput": 789.89, "total_tokens": 939616} {"current_steps": 2890, "total_steps": 40000, "loss": 0.178, "lr": 4.9359202541996426e-05, "epoch": 2.365124846500205, "percentage": 7.22, "elapsed_time": "0:19:51", "remaining_time": "4:14:56", "throughput": 790.14, "total_tokens": 941264} {"current_steps": 2895, "total_steps": 40000, "loss": 0.2076, "lr": 4.935699212851616e-05, "epoch": 2.3692181743757676, "percentage": 7.24, "elapsed_time": "0:19:52", "remaining_time": "4:14:50", "throughput": 790.46, "total_tokens": 943008} {"current_steps": 2900, "total_steps": 40000, "loss": 0.2053, "lr": 4.935477795888162e-05, "epoch": 2.3733115022513305, "percentage": 7.25, "elapsed_time": "0:19:54", "remaining_time": "4:14:44", "throughput": 790.73, "total_tokens": 944688} {"current_steps": 2905, "total_steps": 40000, "loss": 0.218, "lr": 4.935256003343426e-05, "epoch": 2.3774048301268933, "percentage": 7.26, "elapsed_time": "0:19:56", "remaining_time": "4:14:37", "throughput": 790.94, "total_tokens": 946304} {"current_steps": 2910, "total_steps": 40000, "loss": 0.2375, "lr": 4.93503383525161e-05, "epoch": 2.381498158002456, "percentage": 7.27, "elapsed_time": "0:19:58", "remaining_time": "4:14:31", "throughput": 791.21, "total_tokens": 947984} {"current_steps": 2915, "total_steps": 40000, "loss": 0.1717, "lr": 4.934811291646977e-05, "epoch": 2.385591485878019, "percentage": 7.29, "elapsed_time": "0:19:59", "remaining_time": "4:14:24", "throughput": 791.39, "total_tokens": 949568} {"current_steps": 2920, "total_steps": 40000, "loss": 0.247, "lr": 4.934588372563845e-05, "epoch": 2.3896848137535818, "percentage": 7.3, "elapsed_time": "0:20:01", "remaining_time": "4:14:18", "throughput": 791.61, "total_tokens": 951200} {"current_steps": 2925, "total_steps": 40000, "loss": 0.2102, "lr": 4.93436507803659e-05, "epoch": 2.3937781416291446, "percentage": 7.31, "elapsed_time": "0:20:03", "remaining_time": "4:14:12", "throughput": 791.84, "total_tokens": 952832} {"current_steps": 2930, "total_steps": 40000, "loss": 0.2033, "lr": 4.934141408099649e-05, "epoch": 2.3978714695047074, "percentage": 7.32, "elapsed_time": "0:20:05", "remaining_time": "4:14:05", "throughput": 792.09, "total_tokens": 954496} {"current_steps": 2935, "total_steps": 40000, "loss": 0.2679, "lr": 4.9339173627875135e-05, "epoch": 2.4019647973802702, "percentage": 7.34, "elapsed_time": "0:20:06", "remaining_time": "4:13:59", "throughput": 792.25, "total_tokens": 956048} {"current_steps": 2940, "total_steps": 40000, "loss": 0.2353, "lr": 4.9336929421347335e-05, "epoch": 2.406058125255833, "percentage": 7.35, "elapsed_time": "0:20:08", "remaining_time": "4:13:53", "throughput": 792.5, "total_tokens": 957712} {"current_steps": 2945, "total_steps": 40000, "loss": 0.2364, "lr": 4.933468146175918e-05, "epoch": 2.410151453131396, "percentage": 7.36, "elapsed_time": "0:20:10", "remaining_time": "4:13:46", "throughput": 792.7, "total_tokens": 959312} {"current_steps": 2950, "total_steps": 40000, "loss": 0.2403, "lr": 4.933242974945734e-05, "epoch": 2.4142447810069587, "percentage": 7.38, "elapsed_time": "0:20:11", "remaining_time": "4:13:40", "throughput": 792.95, "total_tokens": 960976} {"current_steps": 2955, "total_steps": 40000, "loss": 0.2348, "lr": 4.933017428478906e-05, "epoch": 2.4183381088825215, "percentage": 7.39, "elapsed_time": "0:20:13", "remaining_time": "4:13:34", "throughput": 793.13, "total_tokens": 962560} {"current_steps": 2960, "total_steps": 40000, "loss": 0.2494, "lr": 4.932791506810214e-05, "epoch": 2.4224314367580844, "percentage": 7.4, "elapsed_time": "0:20:15", "remaining_time": "4:13:28", "throughput": 793.34, "total_tokens": 964192} {"current_steps": 2965, "total_steps": 40000, "loss": 0.1932, "lr": 4.932565209974499e-05, "epoch": 2.426524764633647, "percentage": 7.41, "elapsed_time": "0:20:17", "remaining_time": "4:13:22", "throughput": 793.55, "total_tokens": 965808} {"current_steps": 2970, "total_steps": 40000, "loss": 0.2417, "lr": 4.93233853800666e-05, "epoch": 2.43061809250921, "percentage": 7.42, "elapsed_time": "0:20:18", "remaining_time": "4:13:15", "throughput": 793.82, "total_tokens": 967504} {"current_steps": 2975, "total_steps": 40000, "loss": 0.1914, "lr": 4.932111490941651e-05, "epoch": 2.434711420384773, "percentage": 7.44, "elapsed_time": "0:20:20", "remaining_time": "4:13:09", "throughput": 794.07, "total_tokens": 969168} {"current_steps": 2980, "total_steps": 40000, "loss": 0.2057, "lr": 4.9318840688144876e-05, "epoch": 2.4388047482603357, "percentage": 7.45, "elapsed_time": "0:20:22", "remaining_time": "4:13:03", "throughput": 794.27, "total_tokens": 970768} {"current_steps": 2985, "total_steps": 40000, "loss": 0.2128, "lr": 4.9316562716602387e-05, "epoch": 2.4428980761358985, "percentage": 7.46, "elapsed_time": "0:20:23", "remaining_time": "4:12:57", "throughput": 794.47, "total_tokens": 972384} {"current_steps": 2990, "total_steps": 40000, "loss": 0.1808, "lr": 4.9314280995140346e-05, "epoch": 2.4469914040114613, "percentage": 7.47, "elapsed_time": "0:20:25", "remaining_time": "4:12:50", "throughput": 794.75, "total_tokens": 974080} {"current_steps": 2995, "total_steps": 40000, "loss": 0.1996, "lr": 4.931199552411063e-05, "epoch": 2.451084731887024, "percentage": 7.49, "elapsed_time": "0:20:27", "remaining_time": "4:12:44", "throughput": 794.99, "total_tokens": 975744} {"current_steps": 3000, "total_steps": 40000, "loss": 0.2203, "lr": 4.930970630386568e-05, "epoch": 2.455178059762587, "percentage": 7.5, "elapsed_time": "0:20:29", "remaining_time": "4:12:38", "throughput": 795.16, "total_tokens": 977312} {"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.2207007110118866, "epoch": 2.455178059762587, "percentage": 7.5, "elapsed_time": "0:20:41", "remaining_time": "4:15:12", "throughput": 787.18, "total_tokens": 977312} {"current_steps": 3005, "total_steps": 40000, "loss": 0.2311, "lr": 4.9307413334758524e-05, "epoch": 2.45927138763815, "percentage": 7.51, "elapsed_time": "0:20:44", "remaining_time": "4:15:22", "throughput": 786.59, "total_tokens": 978992} {"current_steps": 3010, "total_steps": 40000, "loss": 0.286, "lr": 4.930511661714276e-05, "epoch": 2.4633647155137126, "percentage": 7.52, "elapsed_time": "0:20:46", "remaining_time": "4:15:16", "throughput": 786.81, "total_tokens": 980624} {"current_steps": 3015, "total_steps": 40000, "loss": 0.2088, "lr": 4.9302816151372576e-05, "epoch": 2.4674580433892754, "percentage": 7.54, "elapsed_time": "0:20:48", "remaining_time": "4:15:09", "throughput": 787.03, "total_tokens": 982256} {"current_steps": 3020, "total_steps": 40000, "loss": 0.262, "lr": 4.930051193780274e-05, "epoch": 2.4715513712648383, "percentage": 7.55, "elapsed_time": "0:20:49", "remaining_time": "4:15:03", "throughput": 787.31, "total_tokens": 983952} {"current_steps": 3025, "total_steps": 40000, "loss": 0.2068, "lr": 4.929820397678858e-05, "epoch": 2.475644699140401, "percentage": 7.56, "elapsed_time": "0:20:51", "remaining_time": "4:14:57", "throughput": 787.56, "total_tokens": 985616} {"current_steps": 3030, "total_steps": 40000, "loss": 0.1657, "lr": 4.9295892268686015e-05, "epoch": 2.479738027015964, "percentage": 7.58, "elapsed_time": "0:20:53", "remaining_time": "4:14:50", "throughput": 787.78, "total_tokens": 987248} {"current_steps": 3035, "total_steps": 40000, "loss": 0.2465, "lr": 4.9293576813851536e-05, "epoch": 2.4838313548915267, "percentage": 7.59, "elapsed_time": "0:20:54", "remaining_time": "4:14:44", "throughput": 787.99, "total_tokens": 988864} {"current_steps": 3040, "total_steps": 40000, "loss": 0.2501, "lr": 4.929125761264223e-05, "epoch": 2.4879246827670896, "percentage": 7.6, "elapsed_time": "0:20:56", "remaining_time": "4:14:38", "throughput": 788.21, "total_tokens": 990496} {"current_steps": 3045, "total_steps": 40000, "loss": 0.2095, "lr": 4.928893466541573e-05, "epoch": 2.4920180106426524, "percentage": 7.61, "elapsed_time": "0:20:58", "remaining_time": "4:14:31", "throughput": 788.45, "total_tokens": 992144} {"current_steps": 3050, "total_steps": 40000, "loss": 0.2012, "lr": 4.928660797253027e-05, "epoch": 2.496111338518215, "percentage": 7.62, "elapsed_time": "0:21:00", "remaining_time": "4:14:25", "throughput": 788.69, "total_tokens": 993808} {"current_steps": 3055, "total_steps": 40000, "loss": 0.2258, "lr": 4.928427753434467e-05, "epoch": 2.500204666393778, "percentage": 7.64, "elapsed_time": "0:21:01", "remaining_time": "4:14:19", "throughput": 788.88, "total_tokens": 995408} {"current_steps": 3060, "total_steps": 40000, "loss": 0.1816, "lr": 4.9281943351218286e-05, "epoch": 2.504297994269341, "percentage": 7.65, "elapsed_time": "0:21:03", "remaining_time": "4:14:13", "throughput": 789.06, "total_tokens": 996992} {"current_steps": 3065, "total_steps": 40000, "loss": 0.1947, "lr": 4.9279605423511095e-05, "epoch": 2.5083913221449037, "percentage": 7.66, "elapsed_time": "0:21:05", "remaining_time": "4:14:06", "throughput": 789.26, "total_tokens": 998608} {"current_steps": 3070, "total_steps": 40000, "loss": 0.2037, "lr": 4.927726375158363e-05, "epoch": 2.5124846500204665, "percentage": 7.67, "elapsed_time": "0:21:06", "remaining_time": "4:14:00", "throughput": 789.46, "total_tokens": 1000208} {"current_steps": 3075, "total_steps": 40000, "loss": 0.1877, "lr": 4.9274918335797004e-05, "epoch": 2.5165779778960293, "percentage": 7.69, "elapsed_time": "0:21:08", "remaining_time": "4:13:54", "throughput": 789.7, "total_tokens": 1001872} {"current_steps": 3080, "total_steps": 40000, "loss": 0.2144, "lr": 4.927256917651292e-05, "epoch": 2.520671305771592, "percentage": 7.7, "elapsed_time": "0:21:10", "remaining_time": "4:13:48", "throughput": 789.93, "total_tokens": 1003520} {"current_steps": 3085, "total_steps": 40000, "loss": 0.2036, "lr": 4.927021627409364e-05, "epoch": 2.524764633647155, "percentage": 7.71, "elapsed_time": "0:21:12", "remaining_time": "4:13:41", "throughput": 790.17, "total_tokens": 1005184} {"current_steps": 3090, "total_steps": 40000, "loss": 0.2494, "lr": 4.9267859628902005e-05, "epoch": 2.528857961522718, "percentage": 7.72, "elapsed_time": "0:21:13", "remaining_time": "4:13:35", "throughput": 790.37, "total_tokens": 1006784} {"current_steps": 3095, "total_steps": 40000, "loss": 0.2043, "lr": 4.9265499241301454e-05, "epoch": 2.532951289398281, "percentage": 7.74, "elapsed_time": "0:21:15", "remaining_time": "4:13:29", "throughput": 790.56, "total_tokens": 1008400} {"current_steps": 3100, "total_steps": 40000, "loss": 0.2494, "lr": 4.926313511165598e-05, "epoch": 2.5370446172738434, "percentage": 7.75, "elapsed_time": "0:21:17", "remaining_time": "4:13:23", "throughput": 790.78, "total_tokens": 1010032} {"current_steps": 3105, "total_steps": 40000, "loss": 0.2089, "lr": 4.926076724033016e-05, "epoch": 2.5411379451494067, "percentage": 7.76, "elapsed_time": "0:21:18", "remaining_time": "4:13:17", "throughput": 790.97, "total_tokens": 1011632} {"current_steps": 3110, "total_steps": 40000, "loss": 0.192, "lr": 4.9258395627689146e-05, "epoch": 2.545231273024969, "percentage": 7.78, "elapsed_time": "0:21:20", "remaining_time": "4:13:11", "throughput": 791.17, "total_tokens": 1013248} {"current_steps": 3115, "total_steps": 40000, "loss": 0.2542, "lr": 4.925602027409868e-05, "epoch": 2.5493246009005324, "percentage": 7.79, "elapsed_time": "0:21:22", "remaining_time": "4:13:05", "throughput": 791.48, "total_tokens": 1015008} {"current_steps": 3120, "total_steps": 40000, "loss": 0.2019, "lr": 4.925364117992507e-05, "epoch": 2.5534179287760947, "percentage": 7.8, "elapsed_time": "0:21:24", "remaining_time": "4:12:59", "throughput": 791.66, "total_tokens": 1016592} {"current_steps": 3125, "total_steps": 40000, "loss": 0.1879, "lr": 4.92512583455352e-05, "epoch": 2.557511256651658, "percentage": 7.81, "elapsed_time": "0:21:25", "remaining_time": "4:12:53", "throughput": 791.84, "total_tokens": 1018192} {"current_steps": 3130, "total_steps": 40000, "loss": 0.2881, "lr": 4.9248871771296536e-05, "epoch": 2.5616045845272204, "percentage": 7.83, "elapsed_time": "0:21:27", "remaining_time": "4:12:46", "throughput": 792.02, "total_tokens": 1019776} {"current_steps": 3135, "total_steps": 40000, "loss": 0.2166, "lr": 4.924648145757711e-05, "epoch": 2.5656979124027837, "percentage": 7.84, "elapsed_time": "0:21:29", "remaining_time": "4:12:40", "throughput": 792.23, "total_tokens": 1021408} {"current_steps": 3140, "total_steps": 40000, "loss": 0.2361, "lr": 4.924408740474554e-05, "epoch": 2.569791240278346, "percentage": 7.85, "elapsed_time": "0:21:31", "remaining_time": "4:12:34", "throughput": 792.42, "total_tokens": 1023024} {"current_steps": 3145, "total_steps": 40000, "loss": 0.1976, "lr": 4.924168961317103e-05, "epoch": 2.5738845681539093, "percentage": 7.86, "elapsed_time": "0:21:32", "remaining_time": "4:12:28", "throughput": 792.62, "total_tokens": 1024640} {"current_steps": 3150, "total_steps": 40000, "loss": 0.1922, "lr": 4.9239288083223334e-05, "epoch": 2.5779778960294717, "percentage": 7.88, "elapsed_time": "0:21:34", "remaining_time": "4:12:22", "throughput": 792.87, "total_tokens": 1026320} {"current_steps": 3155, "total_steps": 40000, "loss": 0.2524, "lr": 4.9236882815272803e-05, "epoch": 2.582071223905035, "percentage": 7.89, "elapsed_time": "0:21:36", "remaining_time": "4:12:16", "throughput": 793.05, "total_tokens": 1027920} {"current_steps": 3160, "total_steps": 40000, "loss": 0.2252, "lr": 4.9234473809690365e-05, "epoch": 2.586164551780598, "percentage": 7.9, "elapsed_time": "0:21:37", "remaining_time": "4:12:10", "throughput": 793.29, "total_tokens": 1029584} {"current_steps": 3165, "total_steps": 40000, "loss": 0.2052, "lr": 4.923206106684752e-05, "epoch": 2.5902578796561606, "percentage": 7.91, "elapsed_time": "0:21:39", "remaining_time": "4:12:04", "throughput": 793.51, "total_tokens": 1031232} {"current_steps": 3170, "total_steps": 40000, "loss": 0.3543, "lr": 4.922964458711634e-05, "epoch": 2.5943512075317234, "percentage": 7.92, "elapsed_time": "0:21:41", "remaining_time": "4:11:58", "throughput": 793.69, "total_tokens": 1032832} {"current_steps": 3175, "total_steps": 40000, "loss": 0.1803, "lr": 4.9227224370869474e-05, "epoch": 2.5984445354072863, "percentage": 7.94, "elapsed_time": "0:21:43", "remaining_time": "4:11:52", "throughput": 793.96, "total_tokens": 1034544} {"current_steps": 3180, "total_steps": 40000, "loss": 0.222, "lr": 4.9224800418480155e-05, "epoch": 2.602537863282849, "percentage": 7.95, "elapsed_time": "0:21:44", "remaining_time": "4:11:47", "throughput": 794.2, "total_tokens": 1036224} {"current_steps": 3185, "total_steps": 40000, "loss": 0.1893, "lr": 4.9222372730322176e-05, "epoch": 2.606631191158412, "percentage": 7.96, "elapsed_time": "0:21:46", "remaining_time": "4:11:41", "throughput": 794.37, "total_tokens": 1037808} {"current_steps": 3190, "total_steps": 40000, "loss": 0.1876, "lr": 4.921994130676993e-05, "epoch": 2.6107245190339747, "percentage": 7.98, "elapsed_time": "0:21:48", "remaining_time": "4:11:35", "throughput": 794.55, "total_tokens": 1039408} {"current_steps": 3195, "total_steps": 40000, "loss": 0.196, "lr": 4.9217506148198366e-05, "epoch": 2.6148178469095376, "percentage": 7.99, "elapsed_time": "0:21:49", "remaining_time": "4:11:29", "throughput": 794.73, "total_tokens": 1041008} {"current_steps": 3200, "total_steps": 40000, "loss": 0.202, "lr": 4.921506725498302e-05, "epoch": 2.6189111747851004, "percentage": 8.0, "elapsed_time": "0:21:51", "remaining_time": "4:11:23", "throughput": 794.91, "total_tokens": 1042608} {"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.22307471930980682, "epoch": 2.6189111747851004, "percentage": 8.0, "elapsed_time": "0:22:04", "remaining_time": "4:13:47", "throughput": 787.42, "total_tokens": 1042608} {"current_steps": 3205, "total_steps": 40000, "loss": 0.1849, "lr": 4.9212624627499994e-05, "epoch": 2.623004502660663, "percentage": 8.01, "elapsed_time": "0:22:07", "remaining_time": "4:13:56", "throughput": 786.8, "total_tokens": 1044240} {"current_steps": 3210, "total_steps": 40000, "loss": 0.2013, "lr": 4.921017826612597e-05, "epoch": 2.627097830536226, "percentage": 8.03, "elapsed_time": "0:22:08", "remaining_time": "4:13:50", "throughput": 787.04, "total_tokens": 1045904} {"current_steps": 3215, "total_steps": 40000, "loss": 0.2219, "lr": 4.9207728171238223e-05, "epoch": 2.631191158411789, "percentage": 8.04, "elapsed_time": "0:22:10", "remaining_time": "4:13:44", "throughput": 787.25, "total_tokens": 1047536} {"current_steps": 3220, "total_steps": 40000, "loss": 0.3002, "lr": 4.920527434321458e-05, "epoch": 2.6352844862873517, "percentage": 8.05, "elapsed_time": "0:22:12", "remaining_time": "4:13:38", "throughput": 787.49, "total_tokens": 1049216} {"current_steps": 3225, "total_steps": 40000, "loss": 0.2015, "lr": 4.920281678243345e-05, "epoch": 2.6393778141629145, "percentage": 8.06, "elapsed_time": "0:22:14", "remaining_time": "4:13:32", "throughput": 787.69, "total_tokens": 1050832} {"current_steps": 3230, "total_steps": 40000, "loss": 0.2234, "lr": 4.920035548927381e-05, "epoch": 2.6434711420384773, "percentage": 8.08, "elapsed_time": "0:22:15", "remaining_time": "4:13:26", "throughput": 787.88, "total_tokens": 1052448} {"current_steps": 3235, "total_steps": 40000, "loss": 0.2362, "lr": 4.919789046411525e-05, "epoch": 2.64756446991404, "percentage": 8.09, "elapsed_time": "0:22:17", "remaining_time": "4:13:20", "throughput": 788.09, "total_tokens": 1054080} {"current_steps": 3240, "total_steps": 40000, "loss": 0.1819, "lr": 4.919542170733787e-05, "epoch": 2.651657797789603, "percentage": 8.1, "elapsed_time": "0:22:19", "remaining_time": "4:13:14", "throughput": 788.26, "total_tokens": 1055664} {"current_steps": 3245, "total_steps": 40000, "loss": 0.1804, "lr": 4.919294921932242e-05, "epoch": 2.655751125665166, "percentage": 8.11, "elapsed_time": "0:22:20", "remaining_time": "4:13:08", "throughput": 788.41, "total_tokens": 1057216} {"current_steps": 3250, "total_steps": 40000, "loss": 0.1989, "lr": 4.919047300045016e-05, "epoch": 2.6598444535407286, "percentage": 8.12, "elapsed_time": "0:22:22", "remaining_time": "4:13:02", "throughput": 788.59, "total_tokens": 1058800} {"current_steps": 3255, "total_steps": 40000, "loss": 0.2063, "lr": 4.918799305110299e-05, "epoch": 2.6639377814162915, "percentage": 8.14, "elapsed_time": "0:22:24", "remaining_time": "4:12:56", "throughput": 788.78, "total_tokens": 1060416} {"current_steps": 3260, "total_steps": 40000, "loss": 0.1825, "lr": 4.918550937166331e-05, "epoch": 2.6680311092918543, "percentage": 8.15, "elapsed_time": "0:22:26", "remaining_time": "4:12:50", "throughput": 788.91, "total_tokens": 1061952} {"current_steps": 3265, "total_steps": 40000, "loss": 0.176, "lr": 4.918302196251415e-05, "epoch": 2.672124437167417, "percentage": 8.16, "elapsed_time": "0:22:27", "remaining_time": "4:12:44", "throughput": 789.08, "total_tokens": 1063552} {"current_steps": 3270, "total_steps": 40000, "loss": 0.202, "lr": 4.91805308240391e-05, "epoch": 2.67621776504298, "percentage": 8.18, "elapsed_time": "0:22:29", "remaining_time": "4:12:38", "throughput": 789.3, "total_tokens": 1065200} {"current_steps": 3275, "total_steps": 40000, "loss": 0.2332, "lr": 4.9178035956622326e-05, "epoch": 2.6803110929185427, "percentage": 8.19, "elapsed_time": "0:22:31", "remaining_time": "4:12:32", "throughput": 789.5, "total_tokens": 1066832} {"current_steps": 3280, "total_steps": 40000, "loss": 0.2367, "lr": 4.917553736064857e-05, "epoch": 2.6844044207941056, "percentage": 8.2, "elapsed_time": "0:22:32", "remaining_time": "4:12:26", "throughput": 789.7, "total_tokens": 1068464} {"current_steps": 3285, "total_steps": 40000, "loss": 0.203, "lr": 4.917303503650314e-05, "epoch": 2.6884977486696684, "percentage": 8.21, "elapsed_time": "0:22:34", "remaining_time": "4:12:21", "throughput": 789.88, "total_tokens": 1070064} {"current_steps": 3290, "total_steps": 40000, "loss": 0.1504, "lr": 4.917052898457194e-05, "epoch": 2.692591076545231, "percentage": 8.22, "elapsed_time": "0:22:36", "remaining_time": "4:12:15", "throughput": 790.09, "total_tokens": 1071712} {"current_steps": 3295, "total_steps": 40000, "loss": 0.2106, "lr": 4.916801920524141e-05, "epoch": 2.696684404420794, "percentage": 8.24, "elapsed_time": "0:22:38", "remaining_time": "4:12:09", "throughput": 790.31, "total_tokens": 1073360} {"current_steps": 3300, "total_steps": 40000, "loss": 0.2049, "lr": 4.916550569889862e-05, "epoch": 2.700777732296357, "percentage": 8.25, "elapsed_time": "0:22:39", "remaining_time": "4:12:03", "throughput": 790.5, "total_tokens": 1074976} {"current_steps": 3305, "total_steps": 40000, "loss": 0.1934, "lr": 4.916298846593116e-05, "epoch": 2.7048710601719197, "percentage": 8.26, "elapsed_time": "0:22:41", "remaining_time": "4:11:57", "throughput": 790.74, "total_tokens": 1076656} {"current_steps": 3310, "total_steps": 40000, "loss": 0.2388, "lr": 4.916046750672722e-05, "epoch": 2.7089643880474825, "percentage": 8.28, "elapsed_time": "0:22:43", "remaining_time": "4:11:51", "throughput": 790.91, "total_tokens": 1078256} {"current_steps": 3315, "total_steps": 40000, "loss": 0.224, "lr": 4.915794282167559e-05, "epoch": 2.7130577159230453, "percentage": 8.29, "elapsed_time": "0:22:45", "remaining_time": "4:11:45", "throughput": 791.12, "total_tokens": 1079904} {"current_steps": 3320, "total_steps": 40000, "loss": 0.2042, "lr": 4.915541441116558e-05, "epoch": 2.717151043798608, "percentage": 8.3, "elapsed_time": "0:22:46", "remaining_time": "4:11:40", "throughput": 791.3, "total_tokens": 1081504} {"current_steps": 3325, "total_steps": 40000, "loss": 0.2415, "lr": 4.915288227558711e-05, "epoch": 2.721244371674171, "percentage": 8.31, "elapsed_time": "0:22:48", "remaining_time": "4:11:34", "throughput": 791.47, "total_tokens": 1083088} {"current_steps": 3330, "total_steps": 40000, "loss": 0.1908, "lr": 4.915034641533066e-05, "epoch": 2.725337699549734, "percentage": 8.33, "elapsed_time": "0:22:50", "remaining_time": "4:11:28", "throughput": 791.64, "total_tokens": 1084688} {"current_steps": 3335, "total_steps": 40000, "loss": 0.2084, "lr": 4.914780683078731e-05, "epoch": 2.7294310274252966, "percentage": 8.34, "elapsed_time": "0:22:51", "remaining_time": "4:11:22", "throughput": 791.89, "total_tokens": 1086384} {"current_steps": 3340, "total_steps": 40000, "loss": 0.1884, "lr": 4.9145263522348695e-05, "epoch": 2.7335243553008595, "percentage": 8.35, "elapsed_time": "0:22:53", "remaining_time": "4:11:16", "throughput": 792.1, "total_tokens": 1088032} {"current_steps": 3345, "total_steps": 40000, "loss": 0.2409, "lr": 4.9142716490407e-05, "epoch": 2.7376176831764223, "percentage": 8.36, "elapsed_time": "0:22:55", "remaining_time": "4:11:11", "throughput": 792.28, "total_tokens": 1089648} {"current_steps": 3350, "total_steps": 40000, "loss": 0.222, "lr": 4.914016573535504e-05, "epoch": 2.741711011051985, "percentage": 8.38, "elapsed_time": "0:22:57", "remaining_time": "4:11:05", "throughput": 792.46, "total_tokens": 1091248} {"current_steps": 3355, "total_steps": 40000, "loss": 0.2225, "lr": 4.9137611257586154e-05, "epoch": 2.745804338927548, "percentage": 8.39, "elapsed_time": "0:22:58", "remaining_time": "4:10:59", "throughput": 792.67, "total_tokens": 1092896} {"current_steps": 3360, "total_steps": 40000, "loss": 0.1836, "lr": 4.9135053057494274e-05, "epoch": 2.7498976668031108, "percentage": 8.4, "elapsed_time": "0:23:00", "remaining_time": "4:10:53", "throughput": 792.85, "total_tokens": 1094512} {"current_steps": 3365, "total_steps": 40000, "loss": 0.209, "lr": 4.913249113547392e-05, "epoch": 2.7539909946786736, "percentage": 8.41, "elapsed_time": "0:23:02", "remaining_time": "4:10:48", "throughput": 793.02, "total_tokens": 1096112} {"current_steps": 3370, "total_steps": 40000, "loss": 0.22, "lr": 4.912992549192016e-05, "epoch": 2.758084322554237, "percentage": 8.43, "elapsed_time": "0:23:04", "remaining_time": "4:10:45", "throughput": 793.08, "total_tokens": 1097776} {"current_steps": 3375, "total_steps": 40000, "loss": 0.2177, "lr": 4.9127356127228665e-05, "epoch": 2.7621776504297992, "percentage": 8.44, "elapsed_time": "0:23:05", "remaining_time": "4:10:39", "throughput": 793.28, "total_tokens": 1099408} {"current_steps": 3380, "total_steps": 40000, "loss": 0.2357, "lr": 4.912478304179564e-05, "epoch": 2.7662709783053625, "percentage": 8.45, "elapsed_time": "0:23:07", "remaining_time": "4:10:33", "throughput": 793.48, "total_tokens": 1101040} {"current_steps": 3385, "total_steps": 40000, "loss": 0.2296, "lr": 4.9122206236017896e-05, "epoch": 2.770364306180925, "percentage": 8.46, "elapsed_time": "0:23:09", "remaining_time": "4:10:28", "throughput": 793.68, "total_tokens": 1102688} {"current_steps": 3390, "total_steps": 40000, "loss": 0.2419, "lr": 4.911962571029282e-05, "epoch": 2.774457634056488, "percentage": 8.48, "elapsed_time": "0:23:11", "remaining_time": "4:10:22", "throughput": 793.87, "total_tokens": 1104304} {"current_steps": 3395, "total_steps": 40000, "loss": 0.1991, "lr": 4.9117041465018353e-05, "epoch": 2.7785509619320505, "percentage": 8.49, "elapsed_time": "0:23:12", "remaining_time": "4:10:16", "throughput": 794.01, "total_tokens": 1105856} {"current_steps": 3400, "total_steps": 40000, "loss": 0.2518, "lr": 4.911445350059302e-05, "epoch": 2.782644289807614, "percentage": 8.5, "elapsed_time": "0:23:14", "remaining_time": "4:10:11", "throughput": 794.2, "total_tokens": 1107488} {"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.217619851231575, "epoch": 2.782644289807614, "percentage": 8.5, "elapsed_time": "0:23:26", "remaining_time": "4:12:25", "throughput": 787.16, "total_tokens": 1107488} {"current_steps": 3405, "total_steps": 40000, "loss": 0.1999, "lr": 4.9111861817415905e-05, "epoch": 2.786737617683176, "percentage": 8.51, "elapsed_time": "0:23:30", "remaining_time": "4:12:34", "throughput": 786.57, "total_tokens": 1109136} {"current_steps": 3410, "total_steps": 40000, "loss": 0.2149, "lr": 4.91092664158867e-05, "epoch": 2.7908309455587395, "percentage": 8.53, "elapsed_time": "0:23:31", "remaining_time": "4:12:28", "throughput": 786.74, "total_tokens": 1110720} {"current_steps": 3415, "total_steps": 40000, "loss": 0.2274, "lr": 4.910666729640563e-05, "epoch": 2.794924273434302, "percentage": 8.54, "elapsed_time": "0:23:33", "remaining_time": "4:12:23", "throughput": 786.96, "total_tokens": 1112384} {"current_steps": 3420, "total_steps": 40000, "loss": 0.237, "lr": 4.910406445937353e-05, "epoch": 2.799017601309865, "percentage": 8.55, "elapsed_time": "0:23:35", "remaining_time": "4:12:17", "throughput": 787.15, "total_tokens": 1114000} {"current_steps": 3425, "total_steps": 40000, "loss": 0.3326, "lr": 4.9101457905191774e-05, "epoch": 2.8031109291854275, "percentage": 8.56, "elapsed_time": "0:23:36", "remaining_time": "4:12:11", "throughput": 787.33, "total_tokens": 1115600} {"current_steps": 3430, "total_steps": 40000, "loss": 0.3511, "lr": 4.909884763426233e-05, "epoch": 2.8072042570609907, "percentage": 8.58, "elapsed_time": "0:23:38", "remaining_time": "4:12:05", "throughput": 787.51, "total_tokens": 1117200} {"current_steps": 3435, "total_steps": 40000, "loss": 0.1886, "lr": 4.9096233646987736e-05, "epoch": 2.8112975849365536, "percentage": 8.59, "elapsed_time": "0:23:40", "remaining_time": "4:11:59", "throughput": 787.71, "total_tokens": 1118832} {"current_steps": 3440, "total_steps": 40000, "loss": 0.2248, "lr": 4.9093615943771104e-05, "epoch": 2.8153909128121164, "percentage": 8.6, "elapsed_time": "0:23:42", "remaining_time": "4:11:53", "throughput": 787.88, "total_tokens": 1120432} {"current_steps": 3445, "total_steps": 40000, "loss": 0.2265, "lr": 4.909099452501611e-05, "epoch": 2.819484240687679, "percentage": 8.61, "elapsed_time": "0:23:43", "remaining_time": "4:11:47", "throughput": 788.06, "total_tokens": 1122032} {"current_steps": 3450, "total_steps": 40000, "loss": 0.2452, "lr": 4.908836939112702e-05, "epoch": 2.823577568563242, "percentage": 8.62, "elapsed_time": "0:23:45", "remaining_time": "4:11:42", "throughput": 788.27, "total_tokens": 1123696} {"current_steps": 3455, "total_steps": 40000, "loss": 0.1537, "lr": 4.908574054250865e-05, "epoch": 2.827670896438805, "percentage": 8.64, "elapsed_time": "0:23:47", "remaining_time": "4:11:36", "throughput": 788.5, "total_tokens": 1125376} {"current_steps": 3460, "total_steps": 40000, "loss": 0.227, "lr": 4.9083107979566414e-05, "epoch": 2.8317642243143677, "percentage": 8.65, "elapsed_time": "0:23:48", "remaining_time": "4:11:30", "throughput": 788.72, "total_tokens": 1127040} {"current_steps": 3465, "total_steps": 40000, "loss": 0.227, "lr": 4.908047170270628e-05, "epoch": 2.8358575521899305, "percentage": 8.66, "elapsed_time": "0:23:50", "remaining_time": "4:11:24", "throughput": 788.9, "total_tokens": 1128656} {"current_steps": 3470, "total_steps": 40000, "loss": 0.1637, "lr": 4.9077831712334784e-05, "epoch": 2.8399508800654933, "percentage": 8.67, "elapsed_time": "0:23:52", "remaining_time": "4:11:19", "throughput": 789.13, "total_tokens": 1130336} {"current_steps": 3475, "total_steps": 40000, "loss": 0.2044, "lr": 4.907518800885907e-05, "epoch": 2.844044207941056, "percentage": 8.69, "elapsed_time": "0:23:54", "remaining_time": "4:11:13", "throughput": 789.31, "total_tokens": 1131952} {"current_steps": 3480, "total_steps": 40000, "loss": 0.2022, "lr": 4.907254059268681e-05, "epoch": 2.848137535816619, "percentage": 8.7, "elapsed_time": "0:23:55", "remaining_time": "4:11:07", "throughput": 789.56, "total_tokens": 1133664} {"current_steps": 3485, "total_steps": 40000, "loss": 0.2582, "lr": 4.906988946422628e-05, "epoch": 2.852230863692182, "percentage": 8.71, "elapsed_time": "0:23:57", "remaining_time": "4:11:02", "throughput": 789.74, "total_tokens": 1135280} {"current_steps": 3490, "total_steps": 40000, "loss": 0.1927, "lr": 4.9067234623886315e-05, "epoch": 2.8563241915677446, "percentage": 8.72, "elapsed_time": "0:23:59", "remaining_time": "4:10:56", "throughput": 789.93, "total_tokens": 1136912} {"current_steps": 3495, "total_steps": 40000, "loss": 0.1925, "lr": 4.9064576072076316e-05, "epoch": 2.8604175194433075, "percentage": 8.74, "elapsed_time": "0:24:00", "remaining_time": "4:10:50", "throughput": 790.07, "total_tokens": 1138480} {"current_steps": 3500, "total_steps": 40000, "loss": 0.2597, "lr": 4.906191380920628e-05, "epoch": 2.8645108473188703, "percentage": 8.75, "elapsed_time": "0:24:02", "remaining_time": "4:10:45", "throughput": 790.25, "total_tokens": 1140096} {"current_steps": 3505, "total_steps": 40000, "loss": 0.2246, "lr": 4.905924783568675e-05, "epoch": 2.868604175194433, "percentage": 8.76, "elapsed_time": "0:24:04", "remaining_time": "4:10:39", "throughput": 790.43, "total_tokens": 1141712} {"current_steps": 3510, "total_steps": 40000, "loss": 0.2186, "lr": 4.905657815192886e-05, "epoch": 2.872697503069996, "percentage": 8.77, "elapsed_time": "0:24:06", "remaining_time": "4:10:33", "throughput": 790.63, "total_tokens": 1143344} {"current_steps": 3515, "total_steps": 40000, "loss": 0.1967, "lr": 4.90539047583443e-05, "epoch": 2.8767908309455588, "percentage": 8.79, "elapsed_time": "0:24:07", "remaining_time": "4:10:28", "throughput": 790.82, "total_tokens": 1144992} {"current_steps": 3520, "total_steps": 40000, "loss": 0.2113, "lr": 4.905122765534534e-05, "epoch": 2.8808841588211216, "percentage": 8.8, "elapsed_time": "0:24:09", "remaining_time": "4:10:22", "throughput": 790.98, "total_tokens": 1146576} {"current_steps": 3525, "total_steps": 40000, "loss": 0.2226, "lr": 4.9048546843344846e-05, "epoch": 2.8849774866966844, "percentage": 8.81, "elapsed_time": "0:24:11", "remaining_time": "4:10:17", "throughput": 791.2, "total_tokens": 1148256} {"current_steps": 3530, "total_steps": 40000, "loss": 0.2384, "lr": 4.9045862322756206e-05, "epoch": 2.8890708145722472, "percentage": 8.82, "elapsed_time": "0:24:12", "remaining_time": "4:10:11", "throughput": 791.4, "total_tokens": 1149904} {"current_steps": 3535, "total_steps": 40000, "loss": 0.2101, "lr": 4.904317409399342e-05, "epoch": 2.89316414244781, "percentage": 8.84, "elapsed_time": "0:24:14", "remaining_time": "4:10:06", "throughput": 791.59, "total_tokens": 1151536} {"current_steps": 3540, "total_steps": 40000, "loss": 0.2378, "lr": 4.904048215747104e-05, "epoch": 2.897257470323373, "percentage": 8.85, "elapsed_time": "0:24:16", "remaining_time": "4:10:00", "throughput": 791.8, "total_tokens": 1153200} {"current_steps": 3545, "total_steps": 40000, "loss": 0.2204, "lr": 4.90377865136042e-05, "epoch": 2.9013507981989357, "percentage": 8.86, "elapsed_time": "0:24:18", "remaining_time": "4:09:54", "throughput": 791.95, "total_tokens": 1154784} {"current_steps": 3550, "total_steps": 40000, "loss": 0.1842, "lr": 4.90350871628086e-05, "epoch": 2.9054441260744985, "percentage": 8.88, "elapsed_time": "0:24:19", "remaining_time": "4:09:49", "throughput": 792.16, "total_tokens": 1156448} {"current_steps": 3555, "total_steps": 40000, "loss": 0.1601, "lr": 4.903238410550052e-05, "epoch": 2.9095374539500614, "percentage": 8.89, "elapsed_time": "0:24:21", "remaining_time": "4:09:43", "throughput": 792.32, "total_tokens": 1158048} {"current_steps": 3560, "total_steps": 40000, "loss": 0.2531, "lr": 4.90296773420968e-05, "epoch": 2.913630781825624, "percentage": 8.9, "elapsed_time": "0:24:23", "remaining_time": "4:09:38", "throughput": 792.55, "total_tokens": 1159744} {"current_steps": 3565, "total_steps": 40000, "loss": 0.227, "lr": 4.902696687301486e-05, "epoch": 2.917724109701187, "percentage": 8.91, "elapsed_time": "0:24:25", "remaining_time": "4:09:32", "throughput": 792.75, "total_tokens": 1161392} {"current_steps": 3570, "total_steps": 40000, "loss": 0.203, "lr": 4.902425269867268e-05, "epoch": 2.92181743757675, "percentage": 8.92, "elapsed_time": "0:24:26", "remaining_time": "4:09:27", "throughput": 793.01, "total_tokens": 1163136} {"current_steps": 3575, "total_steps": 40000, "loss": 0.2353, "lr": 4.902153481948883e-05, "epoch": 2.9259107654523127, "percentage": 8.94, "elapsed_time": "0:24:28", "remaining_time": "4:09:21", "throughput": 793.21, "total_tokens": 1164784} {"current_steps": 3580, "total_steps": 40000, "loss": 0.2068, "lr": 4.901881323588244e-05, "epoch": 2.9300040933278755, "percentage": 8.95, "elapsed_time": "0:24:30", "remaining_time": "4:09:16", "throughput": 793.37, "total_tokens": 1166384} {"current_steps": 3585, "total_steps": 40000, "loss": 0.2436, "lr": 4.90160879482732e-05, "epoch": 2.9340974212034383, "percentage": 8.96, "elapsed_time": "0:24:31", "remaining_time": "4:09:10", "throughput": 793.53, "total_tokens": 1167984} {"current_steps": 3590, "total_steps": 40000, "loss": 0.2142, "lr": 4.9013358957081405e-05, "epoch": 2.938190749079001, "percentage": 8.97, "elapsed_time": "0:24:33", "remaining_time": "4:09:05", "throughput": 793.73, "total_tokens": 1169632} {"current_steps": 3595, "total_steps": 40000, "loss": 0.2239, "lr": 4.901062626272789e-05, "epoch": 2.942284076954564, "percentage": 8.99, "elapsed_time": "0:24:35", "remaining_time": "4:08:59", "throughput": 793.89, "total_tokens": 1171232} {"current_steps": 3600, "total_steps": 40000, "loss": 0.2164, "lr": 4.900788986563406e-05, "epoch": 2.946377404830127, "percentage": 9.0, "elapsed_time": "0:24:37", "remaining_time": "4:08:54", "throughput": 794.08, "total_tokens": 1172864} {"current_steps": 3600, "total_steps": 40000, "eval_loss": 0.21802200376987457, "epoch": 2.946377404830127, "percentage": 9.0, "elapsed_time": "0:24:49", "remaining_time": "4:11:00", "throughput": 787.43, "total_tokens": 1172864} {"current_steps": 3605, "total_steps": 40000, "loss": 0.2281, "lr": 4.9005149766221915e-05, "epoch": 2.9504707327056896, "percentage": 9.01, "elapsed_time": "0:24:52", "remaining_time": "4:11:08", "throughput": 786.87, "total_tokens": 1174464} {"current_steps": 3610, "total_steps": 40000, "loss": 0.2137, "lr": 4.9002405964914e-05, "epoch": 2.9545640605812524, "percentage": 9.03, "elapsed_time": "0:24:54", "remaining_time": "4:11:03", "throughput": 787.04, "total_tokens": 1176080} {"current_steps": 3615, "total_steps": 40000, "loss": 0.1613, "lr": 4.899965846213346e-05, "epoch": 2.9586573884568153, "percentage": 9.04, "elapsed_time": "0:24:56", "remaining_time": "4:10:57", "throughput": 787.18, "total_tokens": 1177648} {"current_steps": 3620, "total_steps": 40000, "loss": 0.1996, "lr": 4.899690725830399e-05, "epoch": 2.962750716332378, "percentage": 9.05, "elapsed_time": "0:24:57", "remaining_time": "4:10:51", "throughput": 787.35, "total_tokens": 1179248} {"current_steps": 3625, "total_steps": 40000, "loss": 0.1873, "lr": 4.899415235384985e-05, "epoch": 2.966844044207941, "percentage": 9.06, "elapsed_time": "0:24:59", "remaining_time": "4:10:46", "throughput": 787.56, "total_tokens": 1180912} {"current_steps": 3630, "total_steps": 40000, "loss": 0.2164, "lr": 4.899139374919589e-05, "epoch": 2.9709373720835037, "percentage": 9.07, "elapsed_time": "0:25:01", "remaining_time": "4:10:40", "throughput": 787.78, "total_tokens": 1182608} {"current_steps": 3635, "total_steps": 40000, "loss": 0.2738, "lr": 4.898863144476752e-05, "epoch": 2.975030699959067, "percentage": 9.09, "elapsed_time": "0:25:02", "remaining_time": "4:10:35", "throughput": 787.96, "total_tokens": 1184240} {"current_steps": 3640, "total_steps": 40000, "loss": 0.2139, "lr": 4.898586544099072e-05, "epoch": 2.9791240278346294, "percentage": 9.1, "elapsed_time": "0:25:04", "remaining_time": "4:10:29", "throughput": 788.19, "total_tokens": 1185936} {"current_steps": 3645, "total_steps": 40000, "loss": 0.181, "lr": 4.898309573829204e-05, "epoch": 2.9832173557101926, "percentage": 9.11, "elapsed_time": "0:25:06", "remaining_time": "4:10:24", "throughput": 788.39, "total_tokens": 1187600} {"current_steps": 3650, "total_steps": 40000, "loss": 0.2032, "lr": 4.898032233709862e-05, "epoch": 2.987310683585755, "percentage": 9.12, "elapsed_time": "0:25:08", "remaining_time": "4:10:18", "throughput": 788.57, "total_tokens": 1189216} {"current_steps": 3655, "total_steps": 40000, "loss": 0.1843, "lr": 4.8977545237838123e-05, "epoch": 2.9914040114613183, "percentage": 9.14, "elapsed_time": "0:25:09", "remaining_time": "4:10:13", "throughput": 788.88, "total_tokens": 1191040} {"current_steps": 3660, "total_steps": 40000, "loss": 0.2269, "lr": 4.8974764440938836e-05, "epoch": 2.9954973393368807, "percentage": 9.15, "elapsed_time": "0:25:11", "remaining_time": "4:10:07", "throughput": 789.09, "total_tokens": 1192720} {"current_steps": 3665, "total_steps": 40000, "loss": 0.2533, "lr": 4.897197994682959e-05, "epoch": 2.999590667212444, "percentage": 9.16, "elapsed_time": "0:25:13", "remaining_time": "4:10:02", "throughput": 789.29, "total_tokens": 1194368} {"current_steps": 3670, "total_steps": 40000, "loss": 0.2541, "lr": 4.8969191755939786e-05, "epoch": 3.0032746623004503, "percentage": 9.18, "elapsed_time": "0:25:15", "remaining_time": "4:09:58", "throughput": 789.21, "total_tokens": 1195752} {"current_steps": 3675, "total_steps": 40000, "loss": 0.2493, "lr": 4.8966399868699396e-05, "epoch": 3.007367990176013, "percentage": 9.19, "elapsed_time": "0:25:16", "remaining_time": "4:09:53", "throughput": 789.37, "total_tokens": 1197352} {"current_steps": 3680, "total_steps": 40000, "loss": 0.2461, "lr": 4.8963604285538965e-05, "epoch": 3.011461318051576, "percentage": 9.2, "elapsed_time": "0:25:18", "remaining_time": "4:09:47", "throughput": 789.53, "total_tokens": 1198952} {"current_steps": 3685, "total_steps": 40000, "loss": 0.2449, "lr": 4.8960805006889604e-05, "epoch": 3.0155546459271387, "percentage": 9.21, "elapsed_time": "0:25:20", "remaining_time": "4:09:42", "throughput": 789.69, "total_tokens": 1200552} {"current_steps": 3690, "total_steps": 40000, "loss": 0.1587, "lr": 4.8958002033183004e-05, "epoch": 3.0196479738027016, "percentage": 9.22, "elapsed_time": "0:25:22", "remaining_time": "4:09:36", "throughput": 789.88, "total_tokens": 1202200} {"current_steps": 3695, "total_steps": 40000, "loss": 0.1958, "lr": 4.8955195364851414e-05, "epoch": 3.0237413016782644, "percentage": 9.24, "elapsed_time": "0:25:23", "remaining_time": "4:09:31", "throughput": 790.06, "total_tokens": 1203832} {"current_steps": 3700, "total_steps": 40000, "loss": 0.1546, "lr": 4.895238500232766e-05, "epoch": 3.027834629553827, "percentage": 9.25, "elapsed_time": "0:25:25", "remaining_time": "4:09:25", "throughput": 790.26, "total_tokens": 1205496} {"current_steps": 3705, "total_steps": 40000, "loss": 0.2276, "lr": 4.8949570946045143e-05, "epoch": 3.03192795742939, "percentage": 9.26, "elapsed_time": "0:25:27", "remaining_time": "4:09:20", "throughput": 790.45, "total_tokens": 1207144} {"current_steps": 3710, "total_steps": 40000, "loss": 0.2133, "lr": 4.89467531964378e-05, "epoch": 3.036021285304953, "percentage": 9.28, "elapsed_time": "0:25:28", "remaining_time": "4:09:15", "throughput": 790.65, "total_tokens": 1208808} {"current_steps": 3715, "total_steps": 40000, "loss": 0.2242, "lr": 4.894393175394019e-05, "epoch": 3.0401146131805157, "percentage": 9.29, "elapsed_time": "0:25:30", "remaining_time": "4:09:09", "throughput": 790.8, "total_tokens": 1210408} {"current_steps": 3720, "total_steps": 40000, "loss": 0.2205, "lr": 4.8941106618987406e-05, "epoch": 3.0442079410560785, "percentage": 9.3, "elapsed_time": "0:25:32", "remaining_time": "4:09:04", "throughput": 790.97, "total_tokens": 1212024} {"current_steps": 3725, "total_steps": 40000, "loss": 0.2463, "lr": 4.893827779201512e-05, "epoch": 3.0483012689316413, "percentage": 9.31, "elapsed_time": "0:25:34", "remaining_time": "4:08:58", "throughput": 791.12, "total_tokens": 1213608} {"current_steps": 3730, "total_steps": 40000, "loss": 0.2034, "lr": 4.893544527345957e-05, "epoch": 3.052394596807204, "percentage": 9.32, "elapsed_time": "0:25:35", "remaining_time": "4:08:53", "throughput": 791.3, "total_tokens": 1215256} {"current_steps": 3735, "total_steps": 40000, "loss": 0.2151, "lr": 4.8932609063757563e-05, "epoch": 3.056487924682767, "percentage": 9.34, "elapsed_time": "0:25:37", "remaining_time": "4:08:48", "throughput": 791.5, "total_tokens": 1216920} {"current_steps": 3740, "total_steps": 40000, "loss": 0.2044, "lr": 4.8929769163346484e-05, "epoch": 3.06058125255833, "percentage": 9.35, "elapsed_time": "0:25:39", "remaining_time": "4:08:42", "throughput": 791.65, "total_tokens": 1218520} {"current_steps": 3745, "total_steps": 40000, "loss": 0.2525, "lr": 4.892692557266429e-05, "epoch": 3.0646745804338926, "percentage": 9.36, "elapsed_time": "0:25:40", "remaining_time": "4:08:37", "throughput": 791.85, "total_tokens": 1220184} {"current_steps": 3750, "total_steps": 40000, "loss": 0.2245, "lr": 4.8924078292149464e-05, "epoch": 3.0687679083094554, "percentage": 9.38, "elapsed_time": "0:25:42", "remaining_time": "4:08:32", "throughput": 792.07, "total_tokens": 1221880} {"current_steps": 3755, "total_steps": 40000, "loss": 0.2099, "lr": 4.892122732224114e-05, "epoch": 3.0728612361850183, "percentage": 9.39, "elapsed_time": "0:25:44", "remaining_time": "4:08:26", "throughput": 792.29, "total_tokens": 1223592} {"current_steps": 3760, "total_steps": 40000, "loss": 0.2008, "lr": 4.8918372663378944e-05, "epoch": 3.076954564060581, "percentage": 9.4, "elapsed_time": "0:25:46", "remaining_time": "4:08:21", "throughput": 792.48, "total_tokens": 1225256} {"current_steps": 3765, "total_steps": 40000, "loss": 0.2036, "lr": 4.89155143160031e-05, "epoch": 3.081047891936144, "percentage": 9.41, "elapsed_time": "0:25:47", "remaining_time": "4:08:16", "throughput": 792.63, "total_tokens": 1226840} {"current_steps": 3770, "total_steps": 40000, "loss": 0.1938, "lr": 4.891265228055441e-05, "epoch": 3.0851412198117067, "percentage": 9.43, "elapsed_time": "0:25:49", "remaining_time": "4:08:11", "throughput": 792.8, "total_tokens": 1228472} {"current_steps": 3775, "total_steps": 40000, "loss": 0.189, "lr": 4.890978655747424e-05, "epoch": 3.0892345476872696, "percentage": 9.44, "elapsed_time": "0:25:51", "remaining_time": "4:08:05", "throughput": 792.97, "total_tokens": 1230104} {"current_steps": 3780, "total_steps": 40000, "loss": 0.1806, "lr": 4.89069171472045e-05, "epoch": 3.0933278755628324, "percentage": 9.45, "elapsed_time": "0:25:52", "remaining_time": "4:08:00", "throughput": 793.19, "total_tokens": 1231800} {"current_steps": 3785, "total_steps": 40000, "loss": 0.2266, "lr": 4.890404405018772e-05, "epoch": 3.097421203438395, "percentage": 9.46, "elapsed_time": "0:25:54", "remaining_time": "4:07:55", "throughput": 793.34, "total_tokens": 1233400} {"current_steps": 3790, "total_steps": 40000, "loss": 0.2453, "lr": 4.8901167266866934e-05, "epoch": 3.101514531313958, "percentage": 9.47, "elapsed_time": "0:25:56", "remaining_time": "4:07:50", "throughput": 793.54, "total_tokens": 1235064} {"current_steps": 3795, "total_steps": 40000, "loss": 0.2162, "lr": 4.88982867976858e-05, "epoch": 3.105607859189521, "percentage": 9.49, "elapsed_time": "0:25:58", "remaining_time": "4:07:44", "throughput": 793.76, "total_tokens": 1236776} {"current_steps": 3800, "total_steps": 40000, "loss": 0.2582, "lr": 4.889540264308852e-05, "epoch": 3.1097011870650837, "percentage": 9.5, "elapsed_time": "0:25:59", "remaining_time": "4:07:39", "throughput": 793.92, "total_tokens": 1238392} {"current_steps": 3800, "total_steps": 40000, "eval_loss": 0.22622285783290863, "epoch": 3.1097011870650837, "percentage": 9.5, "elapsed_time": "0:26:12", "remaining_time": "4:09:38", "throughput": 787.64, "total_tokens": 1238392} {"current_steps": 3805, "total_steps": 40000, "loss": 0.2593, "lr": 4.889251480351986e-05, "epoch": 3.113794514940647, "percentage": 9.51, "elapsed_time": "0:26:15", "remaining_time": "4:09:46", "throughput": 787.12, "total_tokens": 1240056} {"current_steps": 3810, "total_steps": 40000, "loss": 0.2329, "lr": 4.888962327942517e-05, "epoch": 3.11788784281621, "percentage": 9.53, "elapsed_time": "0:26:17", "remaining_time": "4:09:40", "throughput": 787.3, "total_tokens": 1241704} {"current_steps": 3815, "total_steps": 40000, "loss": 0.1818, "lr": 4.8886728071250356e-05, "epoch": 3.1219811706917726, "percentage": 9.54, "elapsed_time": "0:26:18", "remaining_time": "4:09:35", "throughput": 787.52, "total_tokens": 1243400} {"current_steps": 3820, "total_steps": 40000, "loss": 0.2584, "lr": 4.8883829179441884e-05, "epoch": 3.1260744985673354, "percentage": 9.55, "elapsed_time": "0:26:20", "remaining_time": "4:09:30", "throughput": 787.68, "total_tokens": 1245000} {"current_steps": 3825, "total_steps": 40000, "loss": 0.2011, "lr": 4.888092660444682e-05, "epoch": 3.1301678264428983, "percentage": 9.56, "elapsed_time": "0:26:22", "remaining_time": "4:09:24", "throughput": 787.86, "total_tokens": 1246648} {"current_steps": 3830, "total_steps": 40000, "loss": 0.1917, "lr": 4.887802034671276e-05, "epoch": 3.134261154318461, "percentage": 9.57, "elapsed_time": "0:26:24", "remaining_time": "4:09:19", "throughput": 788.08, "total_tokens": 1248344} {"current_steps": 3835, "total_steps": 40000, "loss": 0.2226, "lr": 4.88751104066879e-05, "epoch": 3.138354482194024, "percentage": 9.59, "elapsed_time": "0:26:25", "remaining_time": "4:09:13", "throughput": 788.25, "total_tokens": 1249960} {"current_steps": 3840, "total_steps": 40000, "loss": 0.2186, "lr": 4.887219678482098e-05, "epoch": 3.1424478100695867, "percentage": 9.6, "elapsed_time": "0:26:27", "remaining_time": "4:09:08", "throughput": 788.44, "total_tokens": 1251624} {"current_steps": 3845, "total_steps": 40000, "loss": 0.1928, "lr": 4.8869279481561316e-05, "epoch": 3.1465411379451496, "percentage": 9.61, "elapsed_time": "0:26:29", "remaining_time": "4:09:03", "throughput": 788.63, "total_tokens": 1253272} {"current_steps": 3850, "total_steps": 40000, "loss": 0.1957, "lr": 4.88663584973588e-05, "epoch": 3.1506344658207124, "percentage": 9.62, "elapsed_time": "0:26:30", "remaining_time": "4:08:58", "throughput": 788.83, "total_tokens": 1254952} {"current_steps": 3855, "total_steps": 40000, "loss": 0.2394, "lr": 4.8863433832663874e-05, "epoch": 3.154727793696275, "percentage": 9.64, "elapsed_time": "0:26:32", "remaining_time": "4:08:52", "throughput": 788.96, "total_tokens": 1256520} {"current_steps": 3860, "total_steps": 40000, "loss": 0.2095, "lr": 4.886050548792757e-05, "epoch": 3.158821121571838, "percentage": 9.65, "elapsed_time": "0:26:34", "remaining_time": "4:08:47", "throughput": 789.13, "total_tokens": 1258136} {"current_steps": 3865, "total_steps": 40000, "loss": 0.2289, "lr": 4.8857573463601465e-05, "epoch": 3.162914449447401, "percentage": 9.66, "elapsed_time": "0:26:36", "remaining_time": "4:08:41", "throughput": 789.28, "total_tokens": 1259736} {"current_steps": 3870, "total_steps": 40000, "loss": 0.1918, "lr": 4.885463776013772e-05, "epoch": 3.1670077773229637, "percentage": 9.68, "elapsed_time": "0:26:37", "remaining_time": "4:08:36", "throughput": 789.45, "total_tokens": 1261352} {"current_steps": 3875, "total_steps": 40000, "loss": 0.2049, "lr": 4.8851698377989056e-05, "epoch": 3.1711011051985265, "percentage": 9.69, "elapsed_time": "0:26:39", "remaining_time": "4:08:31", "throughput": 789.62, "total_tokens": 1262984} {"current_steps": 3880, "total_steps": 40000, "loss": 0.2017, "lr": 4.884875531760876e-05, "epoch": 3.1751944330740893, "percentage": 9.7, "elapsed_time": "0:26:41", "remaining_time": "4:08:26", "throughput": 789.78, "total_tokens": 1264600} {"current_steps": 3885, "total_steps": 40000, "loss": 0.1812, "lr": 4.88458085794507e-05, "epoch": 3.179287760949652, "percentage": 9.71, "elapsed_time": "0:26:42", "remaining_time": "4:08:20", "throughput": 789.96, "total_tokens": 1266232} {"current_steps": 3890, "total_steps": 40000, "loss": 0.2026, "lr": 4.884285816396929e-05, "epoch": 3.183381088825215, "percentage": 9.72, "elapsed_time": "0:26:44", "remaining_time": "4:08:15", "throughput": 790.14, "total_tokens": 1267896} {"current_steps": 3895, "total_steps": 40000, "loss": 0.2059, "lr": 4.8839904071619526e-05, "epoch": 3.187474416700778, "percentage": 9.74, "elapsed_time": "0:26:46", "remaining_time": "4:08:10", "throughput": 790.28, "total_tokens": 1269480} {"current_steps": 3900, "total_steps": 40000, "loss": 0.1682, "lr": 4.8836946302856955e-05, "epoch": 3.1915677445763406, "percentage": 9.75, "elapsed_time": "0:26:48", "remaining_time": "4:08:05", "throughput": 790.49, "total_tokens": 1271176} {"current_steps": 3905, "total_steps": 40000, "loss": 0.203, "lr": 4.8833984858137715e-05, "epoch": 3.1956610724519035, "percentage": 9.76, "elapsed_time": "0:26:49", "remaining_time": "4:07:59", "throughput": 790.6, "total_tokens": 1272712} {"current_steps": 3910, "total_steps": 40000, "loss": 0.1915, "lr": 4.8831019737918494e-05, "epoch": 3.1997544003274663, "percentage": 9.78, "elapsed_time": "0:26:51", "remaining_time": "4:07:54", "throughput": 790.77, "total_tokens": 1274344} {"current_steps": 3915, "total_steps": 40000, "loss": 0.2648, "lr": 4.882805094265655e-05, "epoch": 3.203847728203029, "percentage": 9.79, "elapsed_time": "0:26:53", "remaining_time": "4:07:49", "throughput": 790.94, "total_tokens": 1275976} {"current_steps": 3920, "total_steps": 40000, "loss": 0.1769, "lr": 4.8825078472809706e-05, "epoch": 3.207941056078592, "percentage": 9.8, "elapsed_time": "0:26:54", "remaining_time": "4:07:44", "throughput": 791.04, "total_tokens": 1277496} {"current_steps": 3925, "total_steps": 40000, "loss": 0.201, "lr": 4.882210232883635e-05, "epoch": 3.2120343839541547, "percentage": 9.81, "elapsed_time": "0:26:56", "remaining_time": "4:07:38", "throughput": 791.25, "total_tokens": 1279192} {"current_steps": 3930, "total_steps": 40000, "loss": 0.2335, "lr": 4.881912251119546e-05, "epoch": 3.2161277118297176, "percentage": 9.83, "elapsed_time": "0:26:58", "remaining_time": "4:07:33", "throughput": 791.4, "total_tokens": 1280792} {"current_steps": 3935, "total_steps": 40000, "loss": 0.1957, "lr": 4.881613902034654e-05, "epoch": 3.2202210397052804, "percentage": 9.84, "elapsed_time": "0:27:00", "remaining_time": "4:07:28", "throughput": 791.53, "total_tokens": 1282376} {"current_steps": 3940, "total_steps": 40000, "loss": 0.2567, "lr": 4.88131518567497e-05, "epoch": 3.224314367580843, "percentage": 9.85, "elapsed_time": "0:27:01", "remaining_time": "4:07:23", "throughput": 791.66, "total_tokens": 1283944} {"current_steps": 3945, "total_steps": 40000, "loss": 0.2137, "lr": 4.881016102086558e-05, "epoch": 3.228407695456406, "percentage": 9.86, "elapsed_time": "0:27:03", "remaining_time": "4:07:18", "throughput": 791.83, "total_tokens": 1285576} {"current_steps": 3950, "total_steps": 40000, "loss": 0.217, "lr": 4.8807166513155425e-05, "epoch": 3.232501023331969, "percentage": 9.88, "elapsed_time": "0:27:05", "remaining_time": "4:07:13", "throughput": 792.06, "total_tokens": 1287304} {"current_steps": 3955, "total_steps": 40000, "loss": 0.1934, "lr": 4.8804168334081004e-05, "epoch": 3.2365943512075317, "percentage": 9.89, "elapsed_time": "0:27:06", "remaining_time": "4:07:07", "throughput": 792.22, "total_tokens": 1288936} {"current_steps": 3960, "total_steps": 40000, "loss": 0.167, "lr": 4.880116648410468e-05, "epoch": 3.2406876790830945, "percentage": 9.9, "elapsed_time": "0:27:08", "remaining_time": "4:07:02", "throughput": 792.4, "total_tokens": 1290584} {"current_steps": 3965, "total_steps": 40000, "loss": 0.1937, "lr": 4.879816096368939e-05, "epoch": 3.2447810069586573, "percentage": 9.91, "elapsed_time": "0:27:10", "remaining_time": "4:06:57", "throughput": 792.53, "total_tokens": 1292152} {"current_steps": 3970, "total_steps": 40000, "loss": 0.2042, "lr": 4.879515177329861e-05, "epoch": 3.24887433483422, "percentage": 9.93, "elapsed_time": "0:27:12", "remaining_time": "4:06:52", "throughput": 792.67, "total_tokens": 1293752} {"current_steps": 3975, "total_steps": 40000, "loss": 0.15, "lr": 4.8792138913396394e-05, "epoch": 3.252967662709783, "percentage": 9.94, "elapsed_time": "0:27:13", "remaining_time": "4:06:47", "throughput": 792.84, "total_tokens": 1295384} {"current_steps": 3980, "total_steps": 40000, "loss": 0.2199, "lr": 4.8789122384447374e-05, "epoch": 3.257060990585346, "percentage": 9.95, "elapsed_time": "0:27:15", "remaining_time": "4:06:42", "throughput": 793.03, "total_tokens": 1297064} {"current_steps": 3985, "total_steps": 40000, "loss": 0.2211, "lr": 4.878610218691673e-05, "epoch": 3.2611543184609086, "percentage": 9.96, "elapsed_time": "0:27:17", "remaining_time": "4:06:37", "throughput": 793.15, "total_tokens": 1298632} {"current_steps": 3990, "total_steps": 40000, "loss": 0.1903, "lr": 4.87830783212702e-05, "epoch": 3.2652476463364715, "percentage": 9.98, "elapsed_time": "0:27:19", "remaining_time": "4:06:32", "throughput": 793.36, "total_tokens": 1300344} {"current_steps": 3995, "total_steps": 40000, "loss": 0.2324, "lr": 4.878005078797413e-05, "epoch": 3.2693409742120343, "percentage": 9.99, "elapsed_time": "0:27:20", "remaining_time": "4:06:27", "throughput": 793.52, "total_tokens": 1301960} {"current_steps": 4000, "total_steps": 40000, "loss": 0.19, "lr": 4.877701958749539e-05, "epoch": 3.273434302087597, "percentage": 10.0, "elapsed_time": "0:27:22", "remaining_time": "4:06:22", "throughput": 793.71, "total_tokens": 1303640} {"current_steps": 4000, "total_steps": 40000, "eval_loss": 0.21676234900951385, "epoch": 3.273434302087597, "percentage": 10.0, "elapsed_time": "0:27:34", "remaining_time": "4:08:14", "throughput": 787.74, "total_tokens": 1303640} {"current_steps": 4005, "total_steps": 40000, "loss": 0.2149, "lr": 4.877398472030142e-05, "epoch": 3.27752762996316, "percentage": 10.01, "elapsed_time": "0:27:38", "remaining_time": "4:08:25", "throughput": 787.05, "total_tokens": 1305304} {"current_steps": 4010, "total_steps": 40000, "loss": 0.1868, "lr": 4.877094618686024e-05, "epoch": 3.2816209578387228, "percentage": 10.03, "elapsed_time": "0:27:40", "remaining_time": "4:08:20", "throughput": 787.22, "total_tokens": 1306936} {"current_steps": 4015, "total_steps": 40000, "loss": 0.2414, "lr": 4.876790398764045e-05, "epoch": 3.2857142857142856, "percentage": 10.04, "elapsed_time": "0:27:41", "remaining_time": "4:08:15", "throughput": 787.36, "total_tokens": 1308520} {"current_steps": 4020, "total_steps": 40000, "loss": 0.2308, "lr": 4.8764858123111167e-05, "epoch": 3.2898076135898484, "percentage": 10.05, "elapsed_time": "0:27:43", "remaining_time": "4:08:09", "throughput": 787.53, "total_tokens": 1310152} {"current_steps": 4025, "total_steps": 40000, "loss": 0.2605, "lr": 4.876180859374212e-05, "epoch": 3.2939009414654112, "percentage": 10.06, "elapsed_time": "0:27:45", "remaining_time": "4:08:04", "throughput": 787.67, "total_tokens": 1311752} {"current_steps": 4030, "total_steps": 40000, "loss": 0.1779, "lr": 4.875875540000357e-05, "epoch": 3.297994269340974, "percentage": 10.08, "elapsed_time": "0:27:47", "remaining_time": "4:07:59", "throughput": 787.81, "total_tokens": 1313336} {"current_steps": 4035, "total_steps": 40000, "loss": 0.257, "lr": 4.8755698542366376e-05, "epoch": 3.302087597216537, "percentage": 10.09, "elapsed_time": "0:27:48", "remaining_time": "4:07:54", "throughput": 787.97, "total_tokens": 1314952} {"current_steps": 4040, "total_steps": 40000, "loss": 0.2002, "lr": 4.875263802130193e-05, "epoch": 3.3061809250920997, "percentage": 10.1, "elapsed_time": "0:27:50", "remaining_time": "4:07:49", "throughput": 788.14, "total_tokens": 1316600} {"current_steps": 4045, "total_steps": 40000, "loss": 0.2796, "lr": 4.8749573837282207e-05, "epoch": 3.3102742529676625, "percentage": 10.11, "elapsed_time": "0:27:52", "remaining_time": "4:07:43", "throughput": 788.27, "total_tokens": 1318168} {"current_steps": 4050, "total_steps": 40000, "loss": 0.2492, "lr": 4.874650599077974e-05, "epoch": 3.3143675808432254, "percentage": 10.12, "elapsed_time": "0:27:53", "remaining_time": "4:07:38", "throughput": 788.38, "total_tokens": 1319704} {"current_steps": 4055, "total_steps": 40000, "loss": 0.2061, "lr": 4.874343448226764e-05, "epoch": 3.318460908718788, "percentage": 10.14, "elapsed_time": "0:27:55", "remaining_time": "4:07:33", "throughput": 788.56, "total_tokens": 1321352} {"current_steps": 4060, "total_steps": 40000, "loss": 0.1923, "lr": 4.874035931221955e-05, "epoch": 3.3225542365943515, "percentage": 10.15, "elapsed_time": "0:27:57", "remaining_time": "4:07:28", "throughput": 788.71, "total_tokens": 1322968} {"current_steps": 4065, "total_steps": 40000, "loss": 0.211, "lr": 4.8737280481109724e-05, "epoch": 3.326647564469914, "percentage": 10.16, "elapsed_time": "0:27:59", "remaining_time": "4:07:23", "throughput": 788.87, "total_tokens": 1324584} {"current_steps": 4070, "total_steps": 40000, "loss": 0.1841, "lr": 4.873419798941294e-05, "epoch": 3.330740892345477, "percentage": 10.17, "elapsed_time": "0:28:00", "remaining_time": "4:07:18", "throughput": 789.03, "total_tokens": 1326216} {"current_steps": 4075, "total_steps": 40000, "loss": 0.1958, "lr": 4.873111183760458e-05, "epoch": 3.3348342202210395, "percentage": 10.19, "elapsed_time": "0:28:02", "remaining_time": "4:07:13", "throughput": 789.17, "total_tokens": 1327800} {"current_steps": 4080, "total_steps": 40000, "loss": 0.1853, "lr": 4.8728022026160537e-05, "epoch": 3.3389275480966027, "percentage": 10.2, "elapsed_time": "0:28:04", "remaining_time": "4:07:08", "throughput": 789.35, "total_tokens": 1329464} {"current_steps": 4085, "total_steps": 40000, "loss": 0.1924, "lr": 4.872492855555732e-05, "epoch": 3.343020875972165, "percentage": 10.21, "elapsed_time": "0:28:05", "remaining_time": "4:07:02", "throughput": 789.48, "total_tokens": 1331048} {"current_steps": 4090, "total_steps": 40000, "loss": 0.2472, "lr": 4.8721831426271956e-05, "epoch": 3.3471142038477284, "percentage": 10.22, "elapsed_time": "0:28:07", "remaining_time": "4:06:57", "throughput": 789.65, "total_tokens": 1332680} {"current_steps": 4095, "total_steps": 40000, "loss": 0.2226, "lr": 4.87187306387821e-05, "epoch": 3.351207531723291, "percentage": 10.24, "elapsed_time": "0:28:09", "remaining_time": "4:06:52", "throughput": 789.83, "total_tokens": 1334344} {"current_steps": 4100, "total_steps": 40000, "loss": 0.2323, "lr": 4.87156261935659e-05, "epoch": 3.355300859598854, "percentage": 10.25, "elapsed_time": "0:28:11", "remaining_time": "4:06:47", "throughput": 789.99, "total_tokens": 1335992} {"current_steps": 4105, "total_steps": 40000, "loss": 0.1823, "lr": 4.871251809110211e-05, "epoch": 3.359394187474417, "percentage": 10.26, "elapsed_time": "0:28:12", "remaining_time": "4:06:42", "throughput": 790.14, "total_tokens": 1337592} {"current_steps": 4110, "total_steps": 40000, "loss": 0.2229, "lr": 4.8709406331870044e-05, "epoch": 3.3634875153499797, "percentage": 10.27, "elapsed_time": "0:28:14", "remaining_time": "4:06:37", "throughput": 790.27, "total_tokens": 1339176} {"current_steps": 4115, "total_steps": 40000, "loss": 0.2355, "lr": 4.8706290916349574e-05, "epoch": 3.3675808432255425, "percentage": 10.29, "elapsed_time": "0:28:16", "remaining_time": "4:06:32", "throughput": 790.4, "total_tokens": 1340776} {"current_steps": 4120, "total_steps": 40000, "loss": 0.2404, "lr": 4.8703171845021134e-05, "epoch": 3.3716741711011053, "percentage": 10.3, "elapsed_time": "0:28:18", "remaining_time": "4:06:27", "throughput": 790.54, "total_tokens": 1342376} {"current_steps": 4125, "total_steps": 40000, "loss": 0.2274, "lr": 4.870004911836572e-05, "epoch": 3.375767498976668, "percentage": 10.31, "elapsed_time": "0:28:19", "remaining_time": "4:06:22", "throughput": 790.7, "total_tokens": 1343992} {"current_steps": 4130, "total_steps": 40000, "loss": 0.2042, "lr": 4.869692273686489e-05, "epoch": 3.379860826852231, "percentage": 10.32, "elapsed_time": "0:28:21", "remaining_time": "4:06:17", "throughput": 790.87, "total_tokens": 1345640} {"current_steps": 4135, "total_steps": 40000, "loss": 0.249, "lr": 4.869379270100079e-05, "epoch": 3.383954154727794, "percentage": 10.34, "elapsed_time": "0:28:23", "remaining_time": "4:06:12", "throughput": 791.04, "total_tokens": 1347288} {"current_steps": 4140, "total_steps": 40000, "loss": 0.1963, "lr": 4.86906590112561e-05, "epoch": 3.3880474826033566, "percentage": 10.35, "elapsed_time": "0:28:24", "remaining_time": "4:06:07", "throughput": 791.18, "total_tokens": 1348888} {"current_steps": 4145, "total_steps": 40000, "loss": 0.235, "lr": 4.8687521668114064e-05, "epoch": 3.3921408104789195, "percentage": 10.36, "elapsed_time": "0:28:26", "remaining_time": "4:06:02", "throughput": 791.33, "total_tokens": 1350504} {"current_steps": 4150, "total_steps": 40000, "loss": 0.187, "lr": 4.868438067205853e-05, "epoch": 3.3962341383544823, "percentage": 10.38, "elapsed_time": "0:28:28", "remaining_time": "4:05:57", "throughput": 791.49, "total_tokens": 1352136} {"current_steps": 4155, "total_steps": 40000, "loss": 0.2204, "lr": 4.8681236023573844e-05, "epoch": 3.400327466230045, "percentage": 10.39, "elapsed_time": "0:28:30", "remaining_time": "4:05:52", "throughput": 791.69, "total_tokens": 1353848} {"current_steps": 4160, "total_steps": 40000, "loss": 0.1975, "lr": 4.867808772314497e-05, "epoch": 3.404420794105608, "percentage": 10.4, "elapsed_time": "0:28:31", "remaining_time": "4:05:47", "throughput": 791.85, "total_tokens": 1355496} {"current_steps": 4165, "total_steps": 40000, "loss": 0.2145, "lr": 4.867493577125741e-05, "epoch": 3.4085141219811708, "percentage": 10.41, "elapsed_time": "0:28:33", "remaining_time": "4:05:42", "throughput": 791.99, "total_tokens": 1357096} {"current_steps": 4170, "total_steps": 40000, "loss": 0.1507, "lr": 4.867178016839725e-05, "epoch": 3.4126074498567336, "percentage": 10.42, "elapsed_time": "0:28:35", "remaining_time": "4:05:37", "throughput": 792.18, "total_tokens": 1358776} {"current_steps": 4175, "total_steps": 40000, "loss": 0.2127, "lr": 4.8668620915051094e-05, "epoch": 3.4167007777322964, "percentage": 10.44, "elapsed_time": "0:28:36", "remaining_time": "4:05:32", "throughput": 792.31, "total_tokens": 1360360} {"current_steps": 4180, "total_steps": 40000, "loss": 0.2033, "lr": 4.866545801170616e-05, "epoch": 3.4207941056078592, "percentage": 10.45, "elapsed_time": "0:28:38", "remaining_time": "4:05:27", "throughput": 792.45, "total_tokens": 1361960} {"current_steps": 4185, "total_steps": 40000, "loss": 0.2009, "lr": 4.86622914588502e-05, "epoch": 3.424887433483422, "percentage": 10.46, "elapsed_time": "0:28:40", "remaining_time": "4:05:22", "throughput": 792.61, "total_tokens": 1363592} {"current_steps": 4190, "total_steps": 40000, "loss": 0.2101, "lr": 4.865912125697154e-05, "epoch": 3.428980761358985, "percentage": 10.47, "elapsed_time": "0:28:42", "remaining_time": "4:05:17", "throughput": 792.77, "total_tokens": 1365224} {"current_steps": 4195, "total_steps": 40000, "loss": 0.206, "lr": 4.865594740655907e-05, "epoch": 3.4330740892345477, "percentage": 10.49, "elapsed_time": "0:28:43", "remaining_time": "4:05:13", "throughput": 792.91, "total_tokens": 1366824} {"current_steps": 4200, "total_steps": 40000, "loss": 0.2214, "lr": 4.865276990810222e-05, "epoch": 3.4371674171101105, "percentage": 10.5, "elapsed_time": "0:28:45", "remaining_time": "4:05:08", "throughput": 793.09, "total_tokens": 1368504} {"current_steps": 4200, "total_steps": 40000, "eval_loss": 0.21309331059455872, "epoch": 3.4371674171101105, "percentage": 10.5, "elapsed_time": "0:28:57", "remaining_time": "4:06:54", "throughput": 787.41, "total_tokens": 1368504} {"current_steps": 4205, "total_steps": 40000, "loss": 0.2441, "lr": 4.8649588762091016e-05, "epoch": 3.4412607449856734, "percentage": 10.51, "elapsed_time": "0:29:01", "remaining_time": "4:07:01", "throughput": 786.9, "total_tokens": 1370088} {"current_steps": 4210, "total_steps": 40000, "loss": 0.2573, "lr": 4.8646403969016016e-05, "epoch": 3.445354072861236, "percentage": 10.53, "elapsed_time": "0:29:02", "remaining_time": "4:06:56", "throughput": 787.04, "total_tokens": 1371672} {"current_steps": 4215, "total_steps": 40000, "loss": 0.2257, "lr": 4.864321552936838e-05, "epoch": 3.449447400736799, "percentage": 10.54, "elapsed_time": "0:29:04", "remaining_time": "4:06:51", "throughput": 787.17, "total_tokens": 1373256} {"current_steps": 4220, "total_steps": 40000, "loss": 0.2229, "lr": 4.864002344363978e-05, "epoch": 3.453540728612362, "percentage": 10.55, "elapsed_time": "0:29:06", "remaining_time": "4:06:45", "throughput": 787.33, "total_tokens": 1374888} {"current_steps": 4225, "total_steps": 40000, "loss": 0.1741, "lr": 4.863682771232248e-05, "epoch": 3.4576340564879247, "percentage": 10.56, "elapsed_time": "0:29:07", "remaining_time": "4:06:40", "throughput": 787.48, "total_tokens": 1376504} {"current_steps": 4230, "total_steps": 40000, "loss": 0.1874, "lr": 4.8633628335909324e-05, "epoch": 3.4617273843634875, "percentage": 10.57, "elapsed_time": "0:29:09", "remaining_time": "4:06:35", "throughput": 787.64, "total_tokens": 1378136} {"current_steps": 4235, "total_steps": 40000, "loss": 0.2337, "lr": 4.8630425314893676e-05, "epoch": 3.4658207122390503, "percentage": 10.59, "elapsed_time": "0:29:11", "remaining_time": "4:06:30", "throughput": 787.8, "total_tokens": 1379768} {"current_steps": 4240, "total_steps": 40000, "loss": 0.264, "lr": 4.862721864976948e-05, "epoch": 3.469914040114613, "percentage": 10.6, "elapsed_time": "0:29:13", "remaining_time": "4:06:25", "throughput": 787.95, "total_tokens": 1381368} {"current_steps": 4245, "total_steps": 40000, "loss": 0.202, "lr": 4.862400834103125e-05, "epoch": 3.474007367990176, "percentage": 10.61, "elapsed_time": "0:29:14", "remaining_time": "4:06:20", "throughput": 788.08, "total_tokens": 1382968} {"current_steps": 4250, "total_steps": 40000, "loss": 0.1866, "lr": 4.862079438917406e-05, "epoch": 3.478100695865739, "percentage": 10.62, "elapsed_time": "0:29:16", "remaining_time": "4:06:15", "throughput": 788.26, "total_tokens": 1384648} {"current_steps": 4255, "total_steps": 40000, "loss": 0.1945, "lr": 4.8617576794693536e-05, "epoch": 3.4821940237413016, "percentage": 10.64, "elapsed_time": "0:29:18", "remaining_time": "4:06:10", "throughput": 788.42, "total_tokens": 1386280} {"current_steps": 4260, "total_steps": 40000, "loss": 0.2487, "lr": 4.8614355558085875e-05, "epoch": 3.4862873516168644, "percentage": 10.65, "elapsed_time": "0:29:20", "remaining_time": "4:06:05", "throughput": 788.59, "total_tokens": 1387928} {"current_steps": 4265, "total_steps": 40000, "loss": 0.2183, "lr": 4.861113067984783e-05, "epoch": 3.4903806794924273, "percentage": 10.66, "elapsed_time": "0:29:21", "remaining_time": "4:06:01", "throughput": 788.73, "total_tokens": 1389544} {"current_steps": 4270, "total_steps": 40000, "loss": 0.1855, "lr": 4.860790216047671e-05, "epoch": 3.49447400736799, "percentage": 10.67, "elapsed_time": "0:29:23", "remaining_time": "4:05:56", "throughput": 788.93, "total_tokens": 1391240} {"current_steps": 4275, "total_steps": 40000, "loss": 0.1786, "lr": 4.860467000047041e-05, "epoch": 3.498567335243553, "percentage": 10.69, "elapsed_time": "0:29:25", "remaining_time": "4:05:51", "throughput": 789.09, "total_tokens": 1392872} {"current_steps": 4280, "total_steps": 40000, "loss": 0.1813, "lr": 4.860143420032737e-05, "epoch": 3.5026606631191157, "percentage": 10.7, "elapsed_time": "0:29:26", "remaining_time": "4:05:46", "throughput": 789.24, "total_tokens": 1394504} {"current_steps": 4285, "total_steps": 40000, "loss": 0.1532, "lr": 4.859819476054657e-05, "epoch": 3.5067539909946785, "percentage": 10.71, "elapsed_time": "0:29:28", "remaining_time": "4:05:41", "throughput": 789.41, "total_tokens": 1396168} {"current_steps": 4290, "total_steps": 40000, "loss": 0.2087, "lr": 4.859495168162758e-05, "epoch": 3.5108473188702414, "percentage": 10.72, "elapsed_time": "0:29:30", "remaining_time": "4:05:36", "throughput": 789.54, "total_tokens": 1397752} {"current_steps": 4295, "total_steps": 40000, "loss": 0.1802, "lr": 4.859170496407054e-05, "epoch": 3.514940646745804, "percentage": 10.74, "elapsed_time": "0:29:32", "remaining_time": "4:05:31", "throughput": 789.67, "total_tokens": 1399336} {"current_steps": 4300, "total_steps": 40000, "loss": 0.1956, "lr": 4.8588454608376114e-05, "epoch": 3.519033974621367, "percentage": 10.75, "elapsed_time": "0:29:33", "remaining_time": "4:05:26", "throughput": 789.8, "total_tokens": 1400936} {"current_steps": 4305, "total_steps": 40000, "loss": 0.2308, "lr": 4.8585200615045555e-05, "epoch": 3.52312730249693, "percentage": 10.76, "elapsed_time": "0:29:35", "remaining_time": "4:05:21", "throughput": 789.97, "total_tokens": 1402584} {"current_steps": 4310, "total_steps": 40000, "loss": 0.1958, "lr": 4.8581942984580674e-05, "epoch": 3.5272206303724927, "percentage": 10.78, "elapsed_time": "0:29:37", "remaining_time": "4:05:16", "throughput": 790.09, "total_tokens": 1404152} {"current_steps": 4315, "total_steps": 40000, "loss": 0.2233, "lr": 4.857868171748384e-05, "epoch": 3.531313958248056, "percentage": 10.79, "elapsed_time": "0:29:38", "remaining_time": "4:05:11", "throughput": 790.23, "total_tokens": 1405768} {"current_steps": 4320, "total_steps": 40000, "loss": 0.2419, "lr": 4.8575416814257976e-05, "epoch": 3.5354072861236183, "percentage": 10.8, "elapsed_time": "0:29:40", "remaining_time": "4:05:06", "throughput": 790.37, "total_tokens": 1407368} {"current_steps": 4325, "total_steps": 40000, "loss": 0.3169, "lr": 4.857214827540657e-05, "epoch": 3.5395006139991816, "percentage": 10.81, "elapsed_time": "0:29:42", "remaining_time": "4:05:01", "throughput": 790.55, "total_tokens": 1409048} {"current_steps": 4330, "total_steps": 40000, "loss": 0.2314, "lr": 4.856887610143367e-05, "epoch": 3.543593941874744, "percentage": 10.82, "elapsed_time": "0:29:44", "remaining_time": "4:04:57", "throughput": 790.71, "total_tokens": 1410696} {"current_steps": 4335, "total_steps": 40000, "loss": 0.2893, "lr": 4.8565600292843896e-05, "epoch": 3.5476872697503072, "percentage": 10.84, "elapsed_time": "0:29:45", "remaining_time": "4:04:52", "throughput": 790.85, "total_tokens": 1412312} {"current_steps": 4340, "total_steps": 40000, "loss": 0.2182, "lr": 4.856232085014241e-05, "epoch": 3.5517805976258696, "percentage": 10.85, "elapsed_time": "0:29:47", "remaining_time": "4:04:47", "throughput": 791.01, "total_tokens": 1413960} {"current_steps": 4345, "total_steps": 40000, "loss": 0.1947, "lr": 4.855903777383495e-05, "epoch": 3.555873925501433, "percentage": 10.86, "elapsed_time": "0:29:49", "remaining_time": "4:04:42", "throughput": 791.18, "total_tokens": 1415624} {"current_steps": 4350, "total_steps": 40000, "loss": 0.1908, "lr": 4.85557510644278e-05, "epoch": 3.5599672533769953, "percentage": 10.88, "elapsed_time": "0:29:50", "remaining_time": "4:04:37", "throughput": 791.37, "total_tokens": 1417320} {"current_steps": 4355, "total_steps": 40000, "loss": 0.24, "lr": 4.855246072242782e-05, "epoch": 3.5640605812525585, "percentage": 10.89, "elapsed_time": "0:29:52", "remaining_time": "4:04:32", "throughput": 791.48, "total_tokens": 1418888} {"current_steps": 4360, "total_steps": 40000, "loss": 0.2026, "lr": 4.8549166748342414e-05, "epoch": 3.568153909128121, "percentage": 10.9, "elapsed_time": "0:29:54", "remaining_time": "4:04:28", "throughput": 791.63, "total_tokens": 1420520} {"current_steps": 4365, "total_steps": 40000, "loss": 0.2005, "lr": 4.8545869142679556e-05, "epoch": 3.572247237003684, "percentage": 10.91, "elapsed_time": "0:29:56", "remaining_time": "4:04:23", "throughput": 791.77, "total_tokens": 1422120} {"current_steps": 4370, "total_steps": 40000, "loss": 0.2653, "lr": 4.8542567905947776e-05, "epoch": 3.5763405648792466, "percentage": 10.93, "elapsed_time": "0:29:57", "remaining_time": "4:04:18", "throughput": 791.93, "total_tokens": 1423768} {"current_steps": 4375, "total_steps": 40000, "loss": 0.1994, "lr": 4.853926303865618e-05, "epoch": 3.58043389275481, "percentage": 10.94, "elapsed_time": "0:29:59", "remaining_time": "4:04:13", "throughput": 792.09, "total_tokens": 1425416} {"current_steps": 4380, "total_steps": 40000, "loss": 0.1701, "lr": 4.853595454131441e-05, "epoch": 3.5845272206303727, "percentage": 10.95, "elapsed_time": "0:30:01", "remaining_time": "4:04:08", "throughput": 792.25, "total_tokens": 1427064} {"current_steps": 4385, "total_steps": 40000, "loss": 0.1893, "lr": 4.8532642414432674e-05, "epoch": 3.5886205485059355, "percentage": 10.96, "elapsed_time": "0:30:03", "remaining_time": "4:04:04", "throughput": 792.39, "total_tokens": 1428680} {"current_steps": 4390, "total_steps": 40000, "loss": 0.2216, "lr": 4.8529326658521754e-05, "epoch": 3.5927138763814983, "percentage": 10.97, "elapsed_time": "0:30:04", "remaining_time": "4:03:59", "throughput": 792.51, "total_tokens": 1430264} {"current_steps": 4395, "total_steps": 40000, "loss": 0.2529, "lr": 4.8526007274092965e-05, "epoch": 3.596807204257061, "percentage": 10.99, "elapsed_time": "0:30:06", "remaining_time": "4:03:54", "throughput": 792.65, "total_tokens": 1431864} {"current_steps": 4400, "total_steps": 40000, "loss": 0.2204, "lr": 4.852268426165822e-05, "epoch": 3.600900532132624, "percentage": 11.0, "elapsed_time": "0:30:08", "remaining_time": "4:03:49", "throughput": 792.79, "total_tokens": 1433480} {"current_steps": 4400, "total_steps": 40000, "eval_loss": 0.21189142763614655, "epoch": 3.600900532132624, "percentage": 11.0, "elapsed_time": "0:30:20", "remaining_time": "4:05:30", "throughput": 787.36, "total_tokens": 1433480} {"current_steps": 4405, "total_steps": 40000, "loss": 0.2102, "lr": 4.851935762172995e-05, "epoch": 3.604993860008187, "percentage": 11.01, "elapsed_time": "0:30:23", "remaining_time": "4:05:36", "throughput": 786.92, "total_tokens": 1435128} {"current_steps": 4410, "total_steps": 40000, "loss": 0.1953, "lr": 4.8516027354821175e-05, "epoch": 3.6090871878837496, "percentage": 11.03, "elapsed_time": "0:30:25", "remaining_time": "4:05:31", "throughput": 787.1, "total_tokens": 1436808} {"current_steps": 4415, "total_steps": 40000, "loss": 0.1622, "lr": 4.851269346144546e-05, "epoch": 3.6131805157593124, "percentage": 11.04, "elapsed_time": "0:30:27", "remaining_time": "4:05:26", "throughput": 787.28, "total_tokens": 1438472} {"current_steps": 4420, "total_steps": 40000, "loss": 0.2157, "lr": 4.850935594211693e-05, "epoch": 3.6172738436348753, "percentage": 11.05, "elapsed_time": "0:30:28", "remaining_time": "4:05:21", "throughput": 787.43, "total_tokens": 1440104} {"current_steps": 4425, "total_steps": 40000, "loss": 0.2621, "lr": 4.850601479735029e-05, "epoch": 3.621367171510438, "percentage": 11.06, "elapsed_time": "0:30:30", "remaining_time": "4:05:17", "throughput": 787.56, "total_tokens": 1441704} {"current_steps": 4430, "total_steps": 40000, "loss": 0.3186, "lr": 4.850267002766076e-05, "epoch": 3.625460499386001, "percentage": 11.07, "elapsed_time": "0:30:32", "remaining_time": "4:05:12", "throughput": 787.67, "total_tokens": 1443256} {"current_steps": 4435, "total_steps": 40000, "loss": 0.194, "lr": 4.849932163356417e-05, "epoch": 3.6295538272615637, "percentage": 11.09, "elapsed_time": "0:30:34", "remaining_time": "4:05:07", "throughput": 787.81, "total_tokens": 1444856} {"current_steps": 4440, "total_steps": 40000, "loss": 0.2374, "lr": 4.8495969615576864e-05, "epoch": 3.6336471551371265, "percentage": 11.1, "elapsed_time": "0:30:35", "remaining_time": "4:05:02", "throughput": 787.94, "total_tokens": 1446456} {"current_steps": 4445, "total_steps": 40000, "loss": 0.1852, "lr": 4.849261397421577e-05, "epoch": 3.6377404830126894, "percentage": 11.11, "elapsed_time": "0:30:37", "remaining_time": "4:04:57", "throughput": 788.07, "total_tokens": 1448040} {"current_steps": 4450, "total_steps": 40000, "loss": 0.1632, "lr": 4.848925470999839e-05, "epoch": 3.641833810888252, "percentage": 11.12, "elapsed_time": "0:30:39", "remaining_time": "4:04:52", "throughput": 788.21, "total_tokens": 1449656} {"current_steps": 4455, "total_steps": 40000, "loss": 0.2053, "lr": 4.848589182344273e-05, "epoch": 3.645927138763815, "percentage": 11.14, "elapsed_time": "0:30:40", "remaining_time": "4:04:47", "throughput": 788.36, "total_tokens": 1451288} {"current_steps": 4460, "total_steps": 40000, "loss": 0.1837, "lr": 4.848252531506742e-05, "epoch": 3.650020466639378, "percentage": 11.15, "elapsed_time": "0:30:42", "remaining_time": "4:04:43", "throughput": 788.51, "total_tokens": 1452920} {"current_steps": 4465, "total_steps": 40000, "loss": 0.1878, "lr": 4.847915518539161e-05, "epoch": 3.6541137945149407, "percentage": 11.16, "elapsed_time": "0:30:44", "remaining_time": "4:04:38", "throughput": 788.64, "total_tokens": 1454504} {"current_steps": 4470, "total_steps": 40000, "loss": 0.2194, "lr": 4.847578143493501e-05, "epoch": 3.6582071223905035, "percentage": 11.18, "elapsed_time": "0:30:46", "remaining_time": "4:04:33", "throughput": 788.82, "total_tokens": 1456200} {"current_steps": 4475, "total_steps": 40000, "loss": 0.2025, "lr": 4.847240406421789e-05, "epoch": 3.6623004502660663, "percentage": 11.19, "elapsed_time": "0:30:47", "remaining_time": "4:04:28", "throughput": 788.96, "total_tokens": 1457816} {"current_steps": 4480, "total_steps": 40000, "loss": 0.2003, "lr": 4.84690230737611e-05, "epoch": 3.666393778141629, "percentage": 11.2, "elapsed_time": "0:30:49", "remaining_time": "4:04:23", "throughput": 789.09, "total_tokens": 1459416} {"current_steps": 4485, "total_steps": 40000, "loss": 0.2293, "lr": 4.846563846408602e-05, "epoch": 3.670487106017192, "percentage": 11.21, "elapsed_time": "0:30:51", "remaining_time": "4:04:18", "throughput": 789.24, "total_tokens": 1461048} {"current_steps": 4490, "total_steps": 40000, "loss": 0.2214, "lr": 4.84622502357146e-05, "epoch": 3.674580433892755, "percentage": 11.22, "elapsed_time": "0:30:52", "remaining_time": "4:04:14", "throughput": 789.38, "total_tokens": 1462648} {"current_steps": 4495, "total_steps": 40000, "loss": 0.1567, "lr": 4.8458858389169345e-05, "epoch": 3.6786737617683176, "percentage": 11.24, "elapsed_time": "0:30:54", "remaining_time": "4:04:09", "throughput": 789.49, "total_tokens": 1464216} {"current_steps": 4500, "total_steps": 40000, "loss": 0.1797, "lr": 4.8455462924973334e-05, "epoch": 3.6827670896438804, "percentage": 11.25, "elapsed_time": "0:30:56", "remaining_time": "4:04:04", "throughput": 789.67, "total_tokens": 1465896} {"current_steps": 4505, "total_steps": 40000, "loss": 0.1815, "lr": 4.845206384365018e-05, "epoch": 3.6868604175194433, "percentage": 11.26, "elapsed_time": "0:30:58", "remaining_time": "4:03:59", "throughput": 789.8, "total_tokens": 1467496} {"current_steps": 4510, "total_steps": 40000, "loss": 0.2401, "lr": 4.844866114572405e-05, "epoch": 3.690953745395006, "percentage": 11.28, "elapsed_time": "0:30:59", "remaining_time": "4:03:54", "throughput": 789.94, "total_tokens": 1469128} {"current_steps": 4515, "total_steps": 40000, "loss": 0.2121, "lr": 4.8445254831719706e-05, "epoch": 3.695047073270569, "percentage": 11.29, "elapsed_time": "0:31:01", "remaining_time": "4:03:50", "throughput": 790.09, "total_tokens": 1470760} {"current_steps": 4520, "total_steps": 40000, "loss": 0.1661, "lr": 4.8441844902162434e-05, "epoch": 3.6991404011461317, "percentage": 11.3, "elapsed_time": "0:31:03", "remaining_time": "4:03:45", "throughput": 790.27, "total_tokens": 1472456} {"current_steps": 4525, "total_steps": 40000, "loss": 0.2156, "lr": 4.843843135757809e-05, "epoch": 3.7032337290216946, "percentage": 11.31, "elapsed_time": "0:31:04", "remaining_time": "4:03:40", "throughput": 790.44, "total_tokens": 1474120} {"current_steps": 4530, "total_steps": 40000, "loss": 0.2176, "lr": 4.843501419849308e-05, "epoch": 3.7073270568972574, "percentage": 11.33, "elapsed_time": "0:31:06", "remaining_time": "4:03:35", "throughput": 790.62, "total_tokens": 1475816} {"current_steps": 4535, "total_steps": 40000, "loss": 0.2837, "lr": 4.8431593425434386e-05, "epoch": 3.71142038477282, "percentage": 11.34, "elapsed_time": "0:31:08", "remaining_time": "4:03:31", "throughput": 790.8, "total_tokens": 1477512} {"current_steps": 4540, "total_steps": 40000, "loss": 0.1903, "lr": 4.8428169038929526e-05, "epoch": 3.715513712648383, "percentage": 11.35, "elapsed_time": "0:31:10", "remaining_time": "4:03:26", "throughput": 790.98, "total_tokens": 1479208} {"current_steps": 4545, "total_steps": 40000, "loss": 0.17, "lr": 4.8424741039506575e-05, "epoch": 3.719607040523946, "percentage": 11.36, "elapsed_time": "0:31:11", "remaining_time": "4:03:21", "throughput": 791.16, "total_tokens": 1480904} {"current_steps": 4550, "total_steps": 40000, "loss": 0.1955, "lr": 4.842130942769419e-05, "epoch": 3.7237003683995087, "percentage": 11.38, "elapsed_time": "0:31:13", "remaining_time": "4:03:17", "throughput": 791.32, "total_tokens": 1482552} {"current_steps": 4555, "total_steps": 40000, "loss": 0.211, "lr": 4.841787420402156e-05, "epoch": 3.7277936962750715, "percentage": 11.39, "elapsed_time": "0:31:15", "remaining_time": "4:03:12", "throughput": 791.47, "total_tokens": 1484216} {"current_steps": 4560, "total_steps": 40000, "loss": 0.1512, "lr": 4.841443536901844e-05, "epoch": 3.7318870241506343, "percentage": 11.4, "elapsed_time": "0:31:16", "remaining_time": "4:03:07", "throughput": 791.65, "total_tokens": 1485896} {"current_steps": 4565, "total_steps": 40000, "loss": 0.1608, "lr": 4.841099292321514e-05, "epoch": 3.735980352026197, "percentage": 11.41, "elapsed_time": "0:31:18", "remaining_time": "4:03:03", "throughput": 791.81, "total_tokens": 1487560} {"current_steps": 4570, "total_steps": 40000, "loss": 0.2601, "lr": 4.8407546867142525e-05, "epoch": 3.74007367990176, "percentage": 11.43, "elapsed_time": "0:31:20", "remaining_time": "4:02:58", "throughput": 791.99, "total_tokens": 1489256} {"current_steps": 4575, "total_steps": 40000, "loss": 0.2242, "lr": 4.840409720133203e-05, "epoch": 3.744167007777323, "percentage": 11.44, "elapsed_time": "0:31:22", "remaining_time": "4:02:53", "throughput": 792.12, "total_tokens": 1490872} {"current_steps": 4580, "total_steps": 40000, "loss": 0.2414, "lr": 4.8400643926315634e-05, "epoch": 3.7482603356528856, "percentage": 11.45, "elapsed_time": "0:31:23", "remaining_time": "4:02:48", "throughput": 792.25, "total_tokens": 1492472} {"current_steps": 4585, "total_steps": 40000, "loss": 0.1908, "lr": 4.839718704262587e-05, "epoch": 3.7523536635284485, "percentage": 11.46, "elapsed_time": "0:31:25", "remaining_time": "4:02:44", "throughput": 792.42, "total_tokens": 1494152} {"current_steps": 4590, "total_steps": 40000, "loss": 0.192, "lr": 4.839372655079585e-05, "epoch": 3.7564469914040117, "percentage": 11.47, "elapsed_time": "0:31:27", "remaining_time": "4:02:39", "throughput": 792.57, "total_tokens": 1495784} {"current_steps": 4595, "total_steps": 40000, "loss": 0.2463, "lr": 4.83902624513592e-05, "epoch": 3.760540319279574, "percentage": 11.49, "elapsed_time": "0:31:28", "remaining_time": "4:02:34", "throughput": 792.71, "total_tokens": 1497416} {"current_steps": 4600, "total_steps": 40000, "loss": 0.2295, "lr": 4.838679474485014e-05, "epoch": 3.7646336471551374, "percentage": 11.5, "elapsed_time": "0:31:30", "remaining_time": "4:02:30", "throughput": 792.84, "total_tokens": 1499016} {"current_steps": 4600, "total_steps": 40000, "eval_loss": 0.21339285373687744, "epoch": 3.7646336471551374, "percentage": 11.5, "elapsed_time": "0:31:43", "remaining_time": "4:04:05", "throughput": 787.66, "total_tokens": 1499016} {"current_steps": 4605, "total_steps": 40000, "loss": 0.2327, "lr": 4.838332343180343e-05, "epoch": 3.7687269750306998, "percentage": 11.51, "elapsed_time": "0:31:46", "remaining_time": "4:04:11", "throughput": 787.22, "total_tokens": 1500616} {"current_steps": 4610, "total_steps": 40000, "loss": 0.2676, "lr": 4.83798485127544e-05, "epoch": 3.772820302906263, "percentage": 11.53, "elapsed_time": "0:31:47", "remaining_time": "4:04:06", "throughput": 787.32, "total_tokens": 1502168} {"current_steps": 4615, "total_steps": 40000, "loss": 0.2202, "lr": 4.837636998823892e-05, "epoch": 3.7769136307818254, "percentage": 11.54, "elapsed_time": "0:31:49", "remaining_time": "4:04:02", "throughput": 787.49, "total_tokens": 1503832} {"current_steps": 4620, "total_steps": 40000, "loss": 0.2237, "lr": 4.8372887858793414e-05, "epoch": 3.7810069586573887, "percentage": 11.55, "elapsed_time": "0:31:51", "remaining_time": "4:03:57", "throughput": 787.62, "total_tokens": 1505448} {"current_steps": 4625, "total_steps": 40000, "loss": 0.2068, "lr": 4.836940212495489e-05, "epoch": 3.785100286532951, "percentage": 11.56, "elapsed_time": "0:31:53", "remaining_time": "4:03:52", "throughput": 787.74, "total_tokens": 1507032} {"current_steps": 4630, "total_steps": 40000, "loss": 0.2306, "lr": 4.836591278726087e-05, "epoch": 3.7891936144085143, "percentage": 11.58, "elapsed_time": "0:31:54", "remaining_time": "4:03:47", "throughput": 787.89, "total_tokens": 1508664} {"current_steps": 4635, "total_steps": 40000, "loss": 0.2242, "lr": 4.836241984624947e-05, "epoch": 3.7932869422840767, "percentage": 11.59, "elapsed_time": "0:31:56", "remaining_time": "4:03:43", "throughput": 788.06, "total_tokens": 1510344} {"current_steps": 4640, "total_steps": 40000, "loss": 0.2047, "lr": 4.8358923302459336e-05, "epoch": 3.79738027015964, "percentage": 11.6, "elapsed_time": "0:31:58", "remaining_time": "4:03:38", "throughput": 788.21, "total_tokens": 1511976} {"current_steps": 4645, "total_steps": 40000, "loss": 0.1694, "lr": 4.835542315642968e-05, "epoch": 3.8014735980352024, "percentage": 11.61, "elapsed_time": "0:31:59", "remaining_time": "4:03:33", "throughput": 788.31, "total_tokens": 1513544} {"current_steps": 4650, "total_steps": 40000, "loss": 0.2042, "lr": 4.8351919408700274e-05, "epoch": 3.8055669259107656, "percentage": 11.62, "elapsed_time": "0:32:01", "remaining_time": "4:03:29", "throughput": 788.48, "total_tokens": 1515208} {"current_steps": 4655, "total_steps": 40000, "loss": 0.1767, "lr": 4.834841205981144e-05, "epoch": 3.8096602537863284, "percentage": 11.64, "elapsed_time": "0:32:03", "remaining_time": "4:03:24", "throughput": 788.64, "total_tokens": 1516888} {"current_steps": 4660, "total_steps": 40000, "loss": 0.1983, "lr": 4.8344901110304054e-05, "epoch": 3.8137535816618913, "percentage": 11.65, "elapsed_time": "0:32:05", "remaining_time": "4:03:19", "throughput": 788.77, "total_tokens": 1518504} {"current_steps": 4665, "total_steps": 40000, "loss": 0.2321, "lr": 4.8341386560719534e-05, "epoch": 3.817846909537454, "percentage": 11.66, "elapsed_time": "0:32:06", "remaining_time": "4:03:14", "throughput": 788.91, "total_tokens": 1520120} {"current_steps": 4670, "total_steps": 40000, "loss": 0.2347, "lr": 4.833786841159989e-05, "epoch": 3.821940237413017, "percentage": 11.68, "elapsed_time": "0:32:08", "remaining_time": "4:03:10", "throughput": 789.04, "total_tokens": 1521736} {"current_steps": 4675, "total_steps": 40000, "loss": 0.2136, "lr": 4.833434666348765e-05, "epoch": 3.8260335652885797, "percentage": 11.69, "elapsed_time": "0:32:10", "remaining_time": "4:03:05", "throughput": 789.16, "total_tokens": 1523320} {"current_steps": 4680, "total_steps": 40000, "loss": 0.2062, "lr": 4.833082131692592e-05, "epoch": 3.8301268931641426, "percentage": 11.7, "elapsed_time": "0:32:12", "remaining_time": "4:03:00", "throughput": 789.32, "total_tokens": 1524968} {"current_steps": 4685, "total_steps": 40000, "loss": 0.218, "lr": 4.832729237245835e-05, "epoch": 3.8342202210397054, "percentage": 11.71, "elapsed_time": "0:32:13", "remaining_time": "4:02:56", "throughput": 789.44, "total_tokens": 1526568} {"current_steps": 4690, "total_steps": 40000, "loss": 0.2217, "lr": 4.8323759830629145e-05, "epoch": 3.838313548915268, "percentage": 11.72, "elapsed_time": "0:32:15", "remaining_time": "4:02:51", "throughput": 789.58, "total_tokens": 1528200} {"current_steps": 4695, "total_steps": 40000, "loss": 0.2045, "lr": 4.8320223691983066e-05, "epoch": 3.842406876790831, "percentage": 11.74, "elapsed_time": "0:32:17", "remaining_time": "4:02:46", "throughput": 789.67, "total_tokens": 1529736} {"current_steps": 4700, "total_steps": 40000, "loss": 0.208, "lr": 4.831668395706544e-05, "epoch": 3.846500204666394, "percentage": 11.75, "elapsed_time": "0:32:18", "remaining_time": "4:02:42", "throughput": 789.81, "total_tokens": 1531352} {"current_steps": 4705, "total_steps": 40000, "loss": 0.2477, "lr": 4.8313140626422125e-05, "epoch": 3.8505935325419567, "percentage": 11.76, "elapsed_time": "0:32:20", "remaining_time": "4:02:37", "throughput": 789.95, "total_tokens": 1532984} {"current_steps": 4710, "total_steps": 40000, "loss": 0.1811, "lr": 4.830959370059956e-05, "epoch": 3.8546868604175195, "percentage": 11.77, "elapsed_time": "0:32:22", "remaining_time": "4:02:33", "throughput": 790.08, "total_tokens": 1534584} {"current_steps": 4715, "total_steps": 40000, "loss": 0.2148, "lr": 4.830604318014472e-05, "epoch": 3.8587801882930823, "percentage": 11.79, "elapsed_time": "0:32:24", "remaining_time": "4:02:28", "throughput": 790.21, "total_tokens": 1536216} {"current_steps": 4720, "total_steps": 40000, "loss": 0.1778, "lr": 4.830248906560514e-05, "epoch": 3.862873516168645, "percentage": 11.8, "elapsed_time": "0:32:25", "remaining_time": "4:02:23", "throughput": 790.35, "total_tokens": 1537848} {"current_steps": 4725, "total_steps": 40000, "loss": 0.201, "lr": 4.829893135752891e-05, "epoch": 3.866966844044208, "percentage": 11.81, "elapsed_time": "0:32:27", "remaining_time": "4:02:19", "throughput": 790.49, "total_tokens": 1539480} {"current_steps": 4730, "total_steps": 40000, "loss": 0.2618, "lr": 4.829537005646466e-05, "epoch": 3.871060171919771, "percentage": 11.82, "elapsed_time": "0:32:29", "remaining_time": "4:02:14", "throughput": 790.64, "total_tokens": 1541128} {"current_steps": 4735, "total_steps": 40000, "loss": 0.1959, "lr": 4.8291805162961615e-05, "epoch": 3.8751534997953336, "percentage": 11.84, "elapsed_time": "0:32:30", "remaining_time": "4:02:10", "throughput": 790.76, "total_tokens": 1542728} {"current_steps": 4740, "total_steps": 40000, "loss": 0.2108, "lr": 4.82882366775695e-05, "epoch": 3.8792468276708965, "percentage": 11.85, "elapsed_time": "0:32:32", "remaining_time": "4:02:05", "throughput": 790.89, "total_tokens": 1544344} {"current_steps": 4745, "total_steps": 40000, "loss": 0.2332, "lr": 4.828466460083864e-05, "epoch": 3.8833401555464593, "percentage": 11.86, "elapsed_time": "0:32:34", "remaining_time": "4:02:00", "throughput": 791.03, "total_tokens": 1545976} {"current_steps": 4750, "total_steps": 40000, "loss": 0.2439, "lr": 4.8281088933319877e-05, "epoch": 3.887433483422022, "percentage": 11.88, "elapsed_time": "0:32:36", "remaining_time": "4:01:56", "throughput": 791.17, "total_tokens": 1547608} {"current_steps": 4755, "total_steps": 40000, "loss": 0.1892, "lr": 4.827750967556464e-05, "epoch": 3.891526811297585, "percentage": 11.89, "elapsed_time": "0:32:37", "remaining_time": "4:01:51", "throughput": 791.3, "total_tokens": 1549224} {"current_steps": 4760, "total_steps": 40000, "loss": 0.2128, "lr": 4.827392682812488e-05, "epoch": 3.8956201391731478, "percentage": 11.9, "elapsed_time": "0:32:39", "remaining_time": "4:01:47", "throughput": 791.43, "total_tokens": 1550840} {"current_steps": 4765, "total_steps": 40000, "loss": 0.1804, "lr": 4.827034039155312e-05, "epoch": 3.8997134670487106, "percentage": 11.91, "elapsed_time": "0:32:41", "remaining_time": "4:01:42", "throughput": 791.57, "total_tokens": 1552472} {"current_steps": 4770, "total_steps": 40000, "loss": 0.214, "lr": 4.8266750366402445e-05, "epoch": 3.9038067949242734, "percentage": 11.92, "elapsed_time": "0:32:42", "remaining_time": "4:01:37", "throughput": 791.71, "total_tokens": 1554104} {"current_steps": 4775, "total_steps": 40000, "loss": 0.2194, "lr": 4.8263156753226476e-05, "epoch": 3.9079001227998362, "percentage": 11.94, "elapsed_time": "0:32:44", "remaining_time": "4:01:33", "throughput": 791.84, "total_tokens": 1555720} {"current_steps": 4780, "total_steps": 40000, "loss": 0.1895, "lr": 4.8259559552579394e-05, "epoch": 3.911993450675399, "percentage": 11.95, "elapsed_time": "0:32:46", "remaining_time": "4:01:28", "throughput": 791.98, "total_tokens": 1557352} {"current_steps": 4785, "total_steps": 40000, "loss": 0.2075, "lr": 4.825595876501593e-05, "epoch": 3.916086778550962, "percentage": 11.96, "elapsed_time": "0:32:48", "remaining_time": "4:01:24", "throughput": 792.09, "total_tokens": 1558936} {"current_steps": 4790, "total_steps": 40000, "loss": 0.2632, "lr": 4.825235439109137e-05, "epoch": 3.9201801064265247, "percentage": 11.97, "elapsed_time": "0:32:49", "remaining_time": "4:01:19", "throughput": 792.24, "total_tokens": 1560600} {"current_steps": 4795, "total_steps": 40000, "loss": 0.1997, "lr": 4.824874643136156e-05, "epoch": 3.9242734343020875, "percentage": 11.99, "elapsed_time": "0:32:51", "remaining_time": "4:01:15", "throughput": 792.38, "total_tokens": 1562232} {"current_steps": 4800, "total_steps": 40000, "loss": 0.1886, "lr": 4.824513488638288e-05, "epoch": 3.9283667621776504, "percentage": 12.0, "elapsed_time": "0:32:53", "remaining_time": "4:01:10", "throughput": 792.53, "total_tokens": 1563880} {"current_steps": 4800, "total_steps": 40000, "eval_loss": 0.210882306098938, "epoch": 3.9283667621776504, "percentage": 12.0, "elapsed_time": "0:33:05", "remaining_time": "4:02:41", "throughput": 787.57, "total_tokens": 1563880} {"current_steps": 4805, "total_steps": 40000, "loss": 0.2413, "lr": 4.8241519756712293e-05, "epoch": 3.932460090053213, "percentage": 12.01, "elapsed_time": "0:33:08", "remaining_time": "4:02:47", "throughput": 787.11, "total_tokens": 1565464} {"current_steps": 4810, "total_steps": 40000, "loss": 0.2444, "lr": 4.8237901042907285e-05, "epoch": 3.936553417928776, "percentage": 12.03, "elapsed_time": "0:33:10", "remaining_time": "4:02:43", "throughput": 787.29, "total_tokens": 1567176} {"current_steps": 4815, "total_steps": 40000, "loss": 0.2216, "lr": 4.823427874552591e-05, "epoch": 3.940646745804339, "percentage": 12.04, "elapsed_time": "0:33:12", "remaining_time": "4:02:38", "throughput": 787.42, "total_tokens": 1568776} {"current_steps": 4820, "total_steps": 40000, "loss": 0.2146, "lr": 4.823065286512677e-05, "epoch": 3.9447400736799016, "percentage": 12.05, "elapsed_time": "0:33:14", "remaining_time": "4:02:33", "throughput": 787.51, "total_tokens": 1570328} {"current_steps": 4825, "total_steps": 40000, "loss": 0.1965, "lr": 4.8227023402269025e-05, "epoch": 3.9488334015554645, "percentage": 12.06, "elapsed_time": "0:33:15", "remaining_time": "4:02:29", "throughput": 787.67, "total_tokens": 1572008} {"current_steps": 4830, "total_steps": 40000, "loss": 0.1733, "lr": 4.822339035751239e-05, "epoch": 3.9529267294310273, "percentage": 12.07, "elapsed_time": "0:33:17", "remaining_time": "4:02:24", "throughput": 787.83, "total_tokens": 1573672} {"current_steps": 4835, "total_steps": 40000, "loss": 0.2035, "lr": 4.8219753731417104e-05, "epoch": 3.95702005730659, "percentage": 12.09, "elapsed_time": "0:33:19", "remaining_time": "4:02:20", "throughput": 787.96, "total_tokens": 1575288} {"current_steps": 4840, "total_steps": 40000, "loss": 0.1993, "lr": 4.821611352454401e-05, "epoch": 3.961113385182153, "percentage": 12.1, "elapsed_time": "0:33:20", "remaining_time": "4:02:15", "throughput": 788.1, "total_tokens": 1576920} {"current_steps": 4845, "total_steps": 40000, "loss": 0.2117, "lr": 4.8212469737454444e-05, "epoch": 3.9652067130577158, "percentage": 12.11, "elapsed_time": "0:33:22", "remaining_time": "4:02:10", "throughput": 788.25, "total_tokens": 1578568} {"current_steps": 4850, "total_steps": 40000, "loss": 0.2277, "lr": 4.820882237071035e-05, "epoch": 3.9693000409332786, "percentage": 12.12, "elapsed_time": "0:33:24", "remaining_time": "4:02:06", "throughput": 788.36, "total_tokens": 1580152} {"current_steps": 4855, "total_steps": 40000, "loss": 0.2754, "lr": 4.820517142487417e-05, "epoch": 3.973393368808842, "percentage": 12.14, "elapsed_time": "0:33:26", "remaining_time": "4:02:01", "throughput": 788.55, "total_tokens": 1581880} {"current_steps": 4860, "total_steps": 40000, "loss": 0.1947, "lr": 4.8201516900508956e-05, "epoch": 3.9774866966844042, "percentage": 12.15, "elapsed_time": "0:33:27", "remaining_time": "4:01:57", "throughput": 788.69, "total_tokens": 1583512} {"current_steps": 4865, "total_steps": 40000, "loss": 0.1987, "lr": 4.819785879817827e-05, "epoch": 3.9815800245599675, "percentage": 12.16, "elapsed_time": "0:33:29", "remaining_time": "4:01:52", "throughput": 788.83, "total_tokens": 1585144} {"current_steps": 4870, "total_steps": 40000, "loss": 0.2043, "lr": 4.8194197118446226e-05, "epoch": 3.98567335243553, "percentage": 12.17, "elapsed_time": "0:33:31", "remaining_time": "4:01:48", "throughput": 788.96, "total_tokens": 1586776} {"current_steps": 4875, "total_steps": 40000, "loss": 0.2124, "lr": 4.819053186187752e-05, "epoch": 3.989766680311093, "percentage": 12.19, "elapsed_time": "0:33:32", "remaining_time": "4:01:43", "throughput": 789.1, "total_tokens": 1588424} {"current_steps": 4880, "total_steps": 40000, "loss": 0.2018, "lr": 4.818686302903736e-05, "epoch": 3.9938600081866555, "percentage": 12.2, "elapsed_time": "0:33:34", "remaining_time": "4:01:39", "throughput": 789.23, "total_tokens": 1590040} {"current_steps": 4885, "total_steps": 40000, "loss": 0.2299, "lr": 4.818319062049154e-05, "epoch": 3.997953336062219, "percentage": 12.21, "elapsed_time": "0:33:36", "remaining_time": "4:01:34", "throughput": 789.37, "total_tokens": 1591672} {"current_steps": 4890, "total_steps": 40000, "loss": 0.2506, "lr": 4.817951463680639e-05, "epoch": 4.001637331150225, "percentage": 12.22, "elapsed_time": "0:33:38", "remaining_time": "4:01:31", "throughput": 789.34, "total_tokens": 1593096} {"current_steps": 4895, "total_steps": 40000, "loss": 0.1829, "lr": 4.817583507854879e-05, "epoch": 4.005730659025788, "percentage": 12.24, "elapsed_time": "0:33:39", "remaining_time": "4:01:26", "throughput": 789.47, "total_tokens": 1594712} {"current_steps": 4900, "total_steps": 40000, "loss": 0.2164, "lr": 4.817215194628617e-05, "epoch": 4.009823986901351, "percentage": 12.25, "elapsed_time": "0:33:41", "remaining_time": "4:01:21", "throughput": 789.6, "total_tokens": 1596328} {"current_steps": 4905, "total_steps": 40000, "loss": 0.2017, "lr": 4.816846524058653e-05, "epoch": 4.013917314776914, "percentage": 12.26, "elapsed_time": "0:33:43", "remaining_time": "4:01:17", "throughput": 789.73, "total_tokens": 1597944} {"current_steps": 4910, "total_steps": 40000, "loss": 0.1527, "lr": 4.816477496201839e-05, "epoch": 4.018010642652476, "percentage": 12.28, "elapsed_time": "0:33:45", "remaining_time": "4:01:13", "throughput": 789.84, "total_tokens": 1599544} {"current_steps": 4915, "total_steps": 40000, "loss": 0.2682, "lr": 4.8161081111150845e-05, "epoch": 4.02210397052804, "percentage": 12.29, "elapsed_time": "0:33:46", "remaining_time": "4:01:08", "throughput": 789.96, "total_tokens": 1601144} {"current_steps": 4920, "total_steps": 40000, "loss": 0.2218, "lr": 4.815738368855354e-05, "epoch": 4.026197298403602, "percentage": 12.3, "elapsed_time": "0:33:48", "remaining_time": "4:01:04", "throughput": 790.13, "total_tokens": 1602856} {"current_steps": 4925, "total_steps": 40000, "loss": 0.2304, "lr": 4.815368269479664e-05, "epoch": 4.030290626279165, "percentage": 12.31, "elapsed_time": "0:33:50", "remaining_time": "4:00:59", "throughput": 790.23, "total_tokens": 1604408} {"current_steps": 4930, "total_steps": 40000, "loss": 0.1909, "lr": 4.814997813045092e-05, "epoch": 4.034383954154728, "percentage": 12.32, "elapsed_time": "0:33:52", "remaining_time": "4:00:54", "throughput": 790.4, "total_tokens": 1606104} {"current_steps": 4935, "total_steps": 40000, "loss": 0.1791, "lr": 4.814626999608764e-05, "epoch": 4.038477282030291, "percentage": 12.34, "elapsed_time": "0:33:53", "remaining_time": "4:00:50", "throughput": 790.51, "total_tokens": 1607688} {"current_steps": 4940, "total_steps": 40000, "loss": 0.2177, "lr": 4.814255829227865e-05, "epoch": 4.042570609905853, "percentage": 12.35, "elapsed_time": "0:33:55", "remaining_time": "4:00:45", "throughput": 790.63, "total_tokens": 1609288} {"current_steps": 4945, "total_steps": 40000, "loss": 0.1736, "lr": 4.813884301959635e-05, "epoch": 4.046663937781417, "percentage": 12.36, "elapsed_time": "0:33:57", "remaining_time": "4:00:41", "throughput": 790.74, "total_tokens": 1610872} {"current_steps": 4950, "total_steps": 40000, "loss": 0.202, "lr": 4.813512417861368e-05, "epoch": 4.050757265656979, "percentage": 12.38, "elapsed_time": "0:33:58", "remaining_time": "4:00:36", "throughput": 790.88, "total_tokens": 1612520} {"current_steps": 4955, "total_steps": 40000, "loss": 0.2595, "lr": 4.813140176990411e-05, "epoch": 4.054850593532542, "percentage": 12.39, "elapsed_time": "0:34:00", "remaining_time": "4:00:32", "throughput": 791.02, "total_tokens": 1614168} {"current_steps": 4960, "total_steps": 40000, "loss": 0.2164, "lr": 4.8127675794041714e-05, "epoch": 4.058943921408105, "percentage": 12.4, "elapsed_time": "0:34:02", "remaining_time": "4:00:28", "throughput": 791.14, "total_tokens": 1615768} {"current_steps": 4965, "total_steps": 40000, "loss": 0.1911, "lr": 4.812394625160107e-05, "epoch": 4.063037249283668, "percentage": 12.41, "elapsed_time": "0:34:04", "remaining_time": "4:00:23", "throughput": 791.29, "total_tokens": 1617448} {"current_steps": 4970, "total_steps": 40000, "loss": 0.1874, "lr": 4.812021314315732e-05, "epoch": 4.06713057715923, "percentage": 12.43, "elapsed_time": "0:34:05", "remaining_time": "4:00:19", "throughput": 791.44, "total_tokens": 1619112} {"current_steps": 4975, "total_steps": 40000, "loss": 0.2159, "lr": 4.811647646928616e-05, "epoch": 4.071223905034794, "percentage": 12.44, "elapsed_time": "0:34:07", "remaining_time": "4:00:14", "throughput": 791.54, "total_tokens": 1620680} {"current_steps": 4980, "total_steps": 40000, "loss": 0.1787, "lr": 4.8112736230563814e-05, "epoch": 4.075317232910356, "percentage": 12.45, "elapsed_time": "0:34:09", "remaining_time": "4:00:12", "throughput": 791.58, "total_tokens": 1622328} {"current_steps": 4985, "total_steps": 40000, "loss": 0.3006, "lr": 4.81089924275671e-05, "epoch": 4.079410560785919, "percentage": 12.46, "elapsed_time": "0:34:11", "remaining_time": "4:00:07", "throughput": 791.73, "total_tokens": 1623992} {"current_steps": 4990, "total_steps": 40000, "loss": 0.2599, "lr": 4.810524506087335e-05, "epoch": 4.083503888661482, "percentage": 12.47, "elapsed_time": "0:34:12", "remaining_time": "4:00:03", "throughput": 791.83, "total_tokens": 1625544} {"current_steps": 4995, "total_steps": 40000, "loss": 0.1857, "lr": 4.810149413106044e-05, "epoch": 4.087597216537045, "percentage": 12.49, "elapsed_time": "0:34:14", "remaining_time": "3:59:58", "throughput": 791.96, "total_tokens": 1627192} {"current_steps": 5000, "total_steps": 40000, "loss": 0.1749, "lr": 4.809773963870684e-05, "epoch": 4.091690544412607, "percentage": 12.5, "elapsed_time": "0:34:16", "remaining_time": "3:59:54", "throughput": 792.09, "total_tokens": 1628808} {"current_steps": 5000, "total_steps": 40000, "eval_loss": 0.21081534028053284, "epoch": 4.091690544412607, "percentage": 12.5, "elapsed_time": "0:34:28", "remaining_time": "4:01:21", "throughput": 787.31, "total_tokens": 1628808} {"current_steps": 5005, "total_steps": 40000, "loss": 0.1771, "lr": 4.809398158439151e-05, "epoch": 4.0957838722881705, "percentage": 12.51, "elapsed_time": "0:34:31", "remaining_time": "4:01:27", "throughput": 786.88, "total_tokens": 1630408} {"current_steps": 5010, "total_steps": 40000, "loss": 0.1971, "lr": 4.8090219968694005e-05, "epoch": 4.099877200163733, "percentage": 12.53, "elapsed_time": "0:34:33", "remaining_time": "4:01:22", "throughput": 787.02, "total_tokens": 1632040} {"current_steps": 5015, "total_steps": 40000, "loss": 0.1922, "lr": 4.808645479219442e-05, "epoch": 4.103970528039296, "percentage": 12.54, "elapsed_time": "0:34:35", "remaining_time": "4:01:18", "throughput": 787.16, "total_tokens": 1633688} {"current_steps": 5020, "total_steps": 40000, "loss": 0.2196, "lr": 4.8082686055473375e-05, "epoch": 4.108063855914859, "percentage": 12.55, "elapsed_time": "0:34:37", "remaining_time": "4:01:13", "throughput": 787.28, "total_tokens": 1635288} {"current_steps": 5025, "total_steps": 40000, "loss": 0.2859, "lr": 4.8078913759112066e-05, "epoch": 4.112157183790422, "percentage": 12.56, "elapsed_time": "0:34:38", "remaining_time": "4:01:09", "throughput": 787.43, "total_tokens": 1636936} {"current_steps": 5030, "total_steps": 40000, "loss": 0.2103, "lr": 4.807513790369223e-05, "epoch": 4.116250511665984, "percentage": 12.57, "elapsed_time": "0:34:40", "remaining_time": "4:01:04", "throughput": 787.6, "total_tokens": 1638648} {"current_steps": 5035, "total_steps": 40000, "loss": 0.2128, "lr": 4.8071358489796145e-05, "epoch": 4.1203438395415475, "percentage": 12.59, "elapsed_time": "0:34:42", "remaining_time": "4:01:00", "throughput": 787.74, "total_tokens": 1640280} {"current_steps": 5040, "total_steps": 40000, "loss": 0.2531, "lr": 4.806757551800665e-05, "epoch": 4.12443716741711, "percentage": 12.6, "elapsed_time": "0:34:43", "remaining_time": "4:00:55", "throughput": 787.86, "total_tokens": 1641896} {"current_steps": 5045, "total_steps": 40000, "loss": 0.1895, "lr": 4.806378898890713e-05, "epoch": 4.128530495292673, "percentage": 12.61, "elapsed_time": "0:34:45", "remaining_time": "4:00:51", "throughput": 787.97, "total_tokens": 1643480} {"current_steps": 5050, "total_steps": 40000, "loss": 0.2396, "lr": 4.80599989030815e-05, "epoch": 4.1326238231682355, "percentage": 12.62, "elapsed_time": "0:34:47", "remaining_time": "4:00:46", "throughput": 788.06, "total_tokens": 1645032} {"current_steps": 5055, "total_steps": 40000, "loss": 0.2011, "lr": 4.805620526111426e-05, "epoch": 4.136717151043799, "percentage": 12.64, "elapsed_time": "0:34:49", "remaining_time": "4:00:42", "throughput": 788.2, "total_tokens": 1646680} {"current_steps": 5060, "total_steps": 40000, "loss": 0.2261, "lr": 4.805240806359042e-05, "epoch": 4.140810478919361, "percentage": 12.65, "elapsed_time": "0:34:50", "remaining_time": "4:00:37", "throughput": 788.32, "total_tokens": 1648264} {"current_steps": 5065, "total_steps": 40000, "loss": 0.2046, "lr": 4.804860731109557e-05, "epoch": 4.144903806794924, "percentage": 12.66, "elapsed_time": "0:34:52", "remaining_time": "4:00:33", "throughput": 788.43, "total_tokens": 1649864} {"current_steps": 5070, "total_steps": 40000, "loss": 0.1601, "lr": 4.804480300421581e-05, "epoch": 4.148997134670487, "percentage": 12.68, "elapsed_time": "0:34:54", "remaining_time": "4:00:28", "throughput": 788.54, "total_tokens": 1651448} {"current_steps": 5075, "total_steps": 40000, "loss": 0.2161, "lr": 4.804099514353784e-05, "epoch": 4.15309046254605, "percentage": 12.69, "elapsed_time": "0:34:56", "remaining_time": "4:00:24", "throughput": 788.7, "total_tokens": 1653128} {"current_steps": 5080, "total_steps": 40000, "loss": 0.2035, "lr": 4.8037183729648867e-05, "epoch": 4.1571837904216125, "percentage": 12.7, "elapsed_time": "0:34:57", "remaining_time": "4:00:19", "throughput": 788.83, "total_tokens": 1654744} {"current_steps": 5085, "total_steps": 40000, "loss": 0.2662, "lr": 4.803336876313666e-05, "epoch": 4.161277118297176, "percentage": 12.71, "elapsed_time": "0:34:59", "remaining_time": "4:00:15", "throughput": 788.92, "total_tokens": 1656296} {"current_steps": 5090, "total_steps": 40000, "loss": 0.2209, "lr": 4.802955024458953e-05, "epoch": 4.165370446172738, "percentage": 12.72, "elapsed_time": "0:35:01", "remaining_time": "4:00:10", "throughput": 789.04, "total_tokens": 1657912} {"current_steps": 5095, "total_steps": 40000, "loss": 0.2354, "lr": 4.802572817459634e-05, "epoch": 4.169463774048301, "percentage": 12.74, "elapsed_time": "0:35:02", "remaining_time": "4:00:06", "throughput": 789.17, "total_tokens": 1659544} {"current_steps": 5100, "total_steps": 40000, "loss": 0.2228, "lr": 4.802190255374651e-05, "epoch": 4.173557101923864, "percentage": 12.75, "elapsed_time": "0:35:04", "remaining_time": "4:00:02", "throughput": 789.28, "total_tokens": 1661128} {"current_steps": 5105, "total_steps": 40000, "loss": 0.1874, "lr": 4.801807338263e-05, "epoch": 4.177650429799427, "percentage": 12.76, "elapsed_time": "0:35:06", "remaining_time": "3:59:57", "throughput": 789.42, "total_tokens": 1662776} {"current_steps": 5110, "total_steps": 40000, "loss": 0.1669, "lr": 4.8014240661837306e-05, "epoch": 4.181743757674989, "percentage": 12.78, "elapsed_time": "0:35:08", "remaining_time": "3:59:53", "throughput": 789.55, "total_tokens": 1664408} {"current_steps": 5115, "total_steps": 40000, "loss": 0.2113, "lr": 4.80104043919595e-05, "epoch": 4.185837085550553, "percentage": 12.79, "elapsed_time": "0:35:09", "remaining_time": "3:59:48", "throughput": 789.7, "total_tokens": 1666072} {"current_steps": 5120, "total_steps": 40000, "loss": 0.1873, "lr": 4.800656457358815e-05, "epoch": 4.189930413426115, "percentage": 12.8, "elapsed_time": "0:35:11", "remaining_time": "3:59:44", "throughput": 789.83, "total_tokens": 1667688} {"current_steps": 5125, "total_steps": 40000, "loss": 0.2108, "lr": 4.800272120731544e-05, "epoch": 4.194023741301678, "percentage": 12.81, "elapsed_time": "0:35:13", "remaining_time": "3:59:39", "throughput": 789.96, "total_tokens": 1669336} {"current_steps": 5130, "total_steps": 40000, "loss": 0.2616, "lr": 4.799887429373404e-05, "epoch": 4.198117069177241, "percentage": 12.83, "elapsed_time": "0:35:14", "remaining_time": "3:59:35", "throughput": 790.11, "total_tokens": 1671016} {"current_steps": 5135, "total_steps": 40000, "loss": 0.2072, "lr": 4.79950238334372e-05, "epoch": 4.202210397052804, "percentage": 12.84, "elapsed_time": "0:35:16", "remaining_time": "3:59:31", "throughput": 790.21, "total_tokens": 1672584} {"current_steps": 5140, "total_steps": 40000, "loss": 0.1995, "lr": 4.799116982701872e-05, "epoch": 4.206303724928366, "percentage": 12.85, "elapsed_time": "0:35:18", "remaining_time": "3:59:26", "throughput": 790.34, "total_tokens": 1674216} {"current_steps": 5145, "total_steps": 40000, "loss": 0.1863, "lr": 4.7987312275072926e-05, "epoch": 4.21039705280393, "percentage": 12.86, "elapsed_time": "0:35:20", "remaining_time": "3:59:22", "throughput": 790.45, "total_tokens": 1675800} {"current_steps": 5150, "total_steps": 40000, "loss": 0.2244, "lr": 4.79834511781947e-05, "epoch": 4.214490380679492, "percentage": 12.88, "elapsed_time": "0:35:21", "remaining_time": "3:59:18", "throughput": 790.56, "total_tokens": 1677384} {"current_steps": 5155, "total_steps": 40000, "loss": 0.2202, "lr": 4.797958653697947e-05, "epoch": 4.218583708555055, "percentage": 12.89, "elapsed_time": "0:35:23", "remaining_time": "3:59:13", "throughput": 790.69, "total_tokens": 1679016} {"current_steps": 5160, "total_steps": 40000, "loss": 0.2237, "lr": 4.7975718352023225e-05, "epoch": 4.222677036430618, "percentage": 12.9, "elapsed_time": "0:35:25", "remaining_time": "3:59:09", "throughput": 790.8, "total_tokens": 1680616} {"current_steps": 5165, "total_steps": 40000, "loss": 0.1995, "lr": 4.7971846623922476e-05, "epoch": 4.226770364306181, "percentage": 12.91, "elapsed_time": "0:35:26", "remaining_time": "3:59:04", "throughput": 790.93, "total_tokens": 1682232} {"current_steps": 5170, "total_steps": 40000, "loss": 0.2083, "lr": 4.7967971353274294e-05, "epoch": 4.230863692181744, "percentage": 12.93, "elapsed_time": "0:35:28", "remaining_time": "3:59:00", "throughput": 791.06, "total_tokens": 1683880} {"current_steps": 5175, "total_steps": 40000, "loss": 0.211, "lr": 4.79640925406763e-05, "epoch": 4.234957020057307, "percentage": 12.94, "elapsed_time": "0:35:30", "remaining_time": "3:58:56", "throughput": 791.17, "total_tokens": 1685464} {"current_steps": 5180, "total_steps": 40000, "loss": 0.1905, "lr": 4.796021018672664e-05, "epoch": 4.23905034793287, "percentage": 12.95, "elapsed_time": "0:35:32", "remaining_time": "3:58:51", "throughput": 791.29, "total_tokens": 1687080} {"current_steps": 5185, "total_steps": 40000, "loss": 0.3231, "lr": 4.795632429202405e-05, "epoch": 4.243143675808432, "percentage": 12.96, "elapsed_time": "0:35:33", "remaining_time": "3:58:47", "throughput": 791.43, "total_tokens": 1688728} {"current_steps": 5190, "total_steps": 40000, "loss": 0.2171, "lr": 4.795243485716775e-05, "epoch": 4.2472370036839955, "percentage": 12.97, "elapsed_time": "0:35:35", "remaining_time": "3:58:43", "throughput": 791.55, "total_tokens": 1690344} {"current_steps": 5195, "total_steps": 40000, "loss": 0.2212, "lr": 4.794854188275757e-05, "epoch": 4.251330331559558, "percentage": 12.99, "elapsed_time": "0:35:37", "remaining_time": "3:58:38", "throughput": 791.69, "total_tokens": 1691992} {"current_steps": 5200, "total_steps": 40000, "loss": 0.2002, "lr": 4.794464536939384e-05, "epoch": 4.255423659435121, "percentage": 13.0, "elapsed_time": "0:35:38", "remaining_time": "3:58:34", "throughput": 791.79, "total_tokens": 1693576} {"current_steps": 5200, "total_steps": 40000, "eval_loss": 0.20924778282642365, "epoch": 4.255423659435121, "percentage": 13.0, "elapsed_time": "0:35:51", "remaining_time": "3:59:57", "throughput": 787.22, "total_tokens": 1693576} {"current_steps": 5205, "total_steps": 40000, "loss": 0.2047, "lr": 4.794074531767745e-05, "epoch": 4.2595169873106835, "percentage": 13.01, "elapsed_time": "0:35:54", "remaining_time": "4:00:02", "throughput": 786.81, "total_tokens": 1695176} {"current_steps": 5210, "total_steps": 40000, "loss": 0.1858, "lr": 4.7936841728209834e-05, "epoch": 4.263610315186247, "percentage": 13.03, "elapsed_time": "0:35:56", "remaining_time": "3:59:58", "throughput": 786.94, "total_tokens": 1696808} {"current_steps": 5215, "total_steps": 40000, "loss": 0.1845, "lr": 4.7932934601593e-05, "epoch": 4.267703643061809, "percentage": 13.04, "elapsed_time": "0:35:57", "remaining_time": "3:59:53", "throughput": 787.11, "total_tokens": 1698520} {"current_steps": 5220, "total_steps": 40000, "loss": 0.2772, "lr": 4.792902393842943e-05, "epoch": 4.271796970937372, "percentage": 13.05, "elapsed_time": "0:35:59", "remaining_time": "3:59:49", "throughput": 787.21, "total_tokens": 1700088} {"current_steps": 5225, "total_steps": 40000, "loss": 0.2204, "lr": 4.792510973932225e-05, "epoch": 4.275890298812935, "percentage": 13.06, "elapsed_time": "0:36:01", "remaining_time": "3:59:44", "throughput": 787.35, "total_tokens": 1701736} {"current_steps": 5230, "total_steps": 40000, "loss": 0.1893, "lr": 4.7921192004875036e-05, "epoch": 4.279983626688498, "percentage": 13.08, "elapsed_time": "0:36:03", "remaining_time": "3:59:40", "throughput": 787.46, "total_tokens": 1703320} {"current_steps": 5235, "total_steps": 40000, "loss": 0.2261, "lr": 4.791727073569198e-05, "epoch": 4.2840769545640605, "percentage": 13.09, "elapsed_time": "0:36:04", "remaining_time": "3:59:36", "throughput": 787.61, "total_tokens": 1705000} {"current_steps": 5240, "total_steps": 40000, "loss": 0.1757, "lr": 4.7913345932377775e-05, "epoch": 4.288170282439624, "percentage": 13.1, "elapsed_time": "0:36:06", "remaining_time": "3:59:31", "throughput": 787.71, "total_tokens": 1706568} {"current_steps": 5245, "total_steps": 40000, "loss": 0.165, "lr": 4.790941759553769e-05, "epoch": 4.292263610315186, "percentage": 13.11, "elapsed_time": "0:36:08", "remaining_time": "3:59:27", "throughput": 787.82, "total_tokens": 1708152} {"current_steps": 5250, "total_steps": 40000, "loss": 0.2262, "lr": 4.79054857257775e-05, "epoch": 4.296356938190749, "percentage": 13.12, "elapsed_time": "0:36:09", "remaining_time": "3:59:22", "throughput": 787.94, "total_tokens": 1709768} {"current_steps": 5255, "total_steps": 40000, "loss": 0.1919, "lr": 4.790155032370357e-05, "epoch": 4.300450266066312, "percentage": 13.14, "elapsed_time": "0:36:11", "remaining_time": "3:59:18", "throughput": 788.12, "total_tokens": 1711512} {"current_steps": 5260, "total_steps": 40000, "loss": 0.247, "lr": 4.789761138992278e-05, "epoch": 4.304543593941875, "percentage": 13.15, "elapsed_time": "0:36:13", "remaining_time": "3:59:14", "throughput": 788.23, "total_tokens": 1713112} {"current_steps": 5265, "total_steps": 40000, "loss": 0.2674, "lr": 4.7893668925042565e-05, "epoch": 4.308636921817437, "percentage": 13.16, "elapsed_time": "0:36:15", "remaining_time": "3:59:09", "throughput": 788.34, "total_tokens": 1714712} {"current_steps": 5270, "total_steps": 40000, "loss": 0.2154, "lr": 4.78897229296709e-05, "epoch": 4.312730249693001, "percentage": 13.18, "elapsed_time": "0:36:16", "remaining_time": "3:59:05", "throughput": 788.46, "total_tokens": 1716344} {"current_steps": 5275, "total_steps": 40000, "loss": 0.2261, "lr": 4.7885773404416315e-05, "epoch": 4.316823577568563, "percentage": 13.19, "elapsed_time": "0:36:18", "remaining_time": "3:59:01", "throughput": 788.59, "total_tokens": 1717976} {"current_steps": 5280, "total_steps": 40000, "loss": 0.2005, "lr": 4.788182034988786e-05, "epoch": 4.320916905444126, "percentage": 13.2, "elapsed_time": "0:36:20", "remaining_time": "3:58:56", "throughput": 788.69, "total_tokens": 1719544} {"current_steps": 5285, "total_steps": 40000, "loss": 0.2109, "lr": 4.787786376669516e-05, "epoch": 4.325010233319689, "percentage": 13.21, "elapsed_time": "0:36:21", "remaining_time": "3:58:52", "throughput": 788.83, "total_tokens": 1721208} {"current_steps": 5290, "total_steps": 40000, "loss": 0.1824, "lr": 4.787390365544837e-05, "epoch": 4.329103561195252, "percentage": 13.23, "elapsed_time": "0:36:23", "remaining_time": "3:58:48", "throughput": 788.92, "total_tokens": 1722744} {"current_steps": 5295, "total_steps": 40000, "loss": 0.2221, "lr": 4.786994001675818e-05, "epoch": 4.333196889070814, "percentage": 13.24, "elapsed_time": "0:36:25", "remaining_time": "3:58:43", "throughput": 789.01, "total_tokens": 1724296} {"current_steps": 5300, "total_steps": 40000, "loss": 0.186, "lr": 4.786597285123584e-05, "epoch": 4.337290216946378, "percentage": 13.25, "elapsed_time": "0:36:27", "remaining_time": "3:58:39", "throughput": 789.12, "total_tokens": 1725912} {"current_steps": 5305, "total_steps": 40000, "loss": 0.1955, "lr": 4.7862002159493135e-05, "epoch": 4.34138354482194, "percentage": 13.26, "elapsed_time": "0:36:28", "remaining_time": "3:58:35", "throughput": 789.24, "total_tokens": 1727512} {"current_steps": 5310, "total_steps": 40000, "loss": 0.2371, "lr": 4.785802794214239e-05, "epoch": 4.345476872697503, "percentage": 13.28, "elapsed_time": "0:36:30", "remaining_time": "3:58:30", "throughput": 789.36, "total_tokens": 1729144} {"current_steps": 5315, "total_steps": 40000, "loss": 0.2163, "lr": 4.7854050199796495e-05, "epoch": 4.349570200573066, "percentage": 13.29, "elapsed_time": "0:36:32", "remaining_time": "3:58:26", "throughput": 789.49, "total_tokens": 1730776} {"current_steps": 5320, "total_steps": 40000, "loss": 0.2366, "lr": 4.7850068933068845e-05, "epoch": 4.353663528448629, "percentage": 13.3, "elapsed_time": "0:36:34", "remaining_time": "3:58:22", "throughput": 789.6, "total_tokens": 1732392} {"current_steps": 5325, "total_steps": 40000, "loss": 0.183, "lr": 4.7846084142573425e-05, "epoch": 4.357756856324191, "percentage": 13.31, "elapsed_time": "0:36:35", "remaining_time": "3:58:17", "throughput": 789.72, "total_tokens": 1734008} {"current_steps": 5330, "total_steps": 40000, "loss": 0.1665, "lr": 4.7842095828924725e-05, "epoch": 4.361850184199755, "percentage": 13.33, "elapsed_time": "0:36:37", "remaining_time": "3:58:13", "throughput": 789.84, "total_tokens": 1735624} {"current_steps": 5335, "total_steps": 40000, "loss": 0.1772, "lr": 4.783810399273779e-05, "epoch": 4.365943512075317, "percentage": 13.34, "elapsed_time": "0:36:39", "remaining_time": "3:58:09", "throughput": 789.99, "total_tokens": 1737320} {"current_steps": 5340, "total_steps": 40000, "loss": 0.1488, "lr": 4.7834108634628226e-05, "epoch": 4.37003683995088, "percentage": 13.35, "elapsed_time": "0:36:40", "remaining_time": "3:58:05", "throughput": 790.12, "total_tokens": 1738952} {"current_steps": 5345, "total_steps": 40000, "loss": 0.1958, "lr": 4.783010975521216e-05, "epoch": 4.374130167826443, "percentage": 13.36, "elapsed_time": "0:36:42", "remaining_time": "3:58:00", "throughput": 790.22, "total_tokens": 1740536} {"current_steps": 5350, "total_steps": 40000, "loss": 0.1941, "lr": 4.782610735510626e-05, "epoch": 4.378223495702006, "percentage": 13.38, "elapsed_time": "0:36:44", "remaining_time": "3:57:56", "throughput": 790.36, "total_tokens": 1742200} {"current_steps": 5355, "total_steps": 40000, "loss": 0.1735, "lr": 4.782210143492776e-05, "epoch": 4.382316823577568, "percentage": 13.39, "elapsed_time": "0:36:46", "remaining_time": "3:57:52", "throughput": 790.5, "total_tokens": 1743864} {"current_steps": 5360, "total_steps": 40000, "loss": 0.2395, "lr": 4.781809199529442e-05, "epoch": 4.3864101514531315, "percentage": 13.4, "elapsed_time": "0:36:47", "remaining_time": "3:57:48", "throughput": 790.6, "total_tokens": 1745448} {"current_steps": 5365, "total_steps": 40000, "loss": 0.2075, "lr": 4.781407903682454e-05, "epoch": 4.390503479328694, "percentage": 13.41, "elapsed_time": "0:36:49", "remaining_time": "3:57:43", "throughput": 790.72, "total_tokens": 1747080} {"current_steps": 5370, "total_steps": 40000, "loss": 0.1889, "lr": 4.781006256013698e-05, "epoch": 4.394596807204257, "percentage": 13.43, "elapsed_time": "0:36:51", "remaining_time": "3:57:39", "throughput": 790.83, "total_tokens": 1748680} {"current_steps": 5375, "total_steps": 40000, "loss": 0.1797, "lr": 4.7806042565851115e-05, "epoch": 4.3986901350798195, "percentage": 13.44, "elapsed_time": "0:36:52", "remaining_time": "3:57:35", "throughput": 790.98, "total_tokens": 1750376} {"current_steps": 5380, "total_steps": 40000, "loss": 0.1986, "lr": 4.7802019054586895e-05, "epoch": 4.402783462955383, "percentage": 13.45, "elapsed_time": "0:36:54", "remaining_time": "3:57:31", "throughput": 791.11, "total_tokens": 1752008} {"current_steps": 5385, "total_steps": 40000, "loss": 0.2204, "lr": 4.779799202696479e-05, "epoch": 4.406876790830945, "percentage": 13.46, "elapsed_time": "0:36:56", "remaining_time": "3:57:26", "throughput": 791.24, "total_tokens": 1753656} {"current_steps": 5390, "total_steps": 40000, "loss": 0.1613, "lr": 4.779396148360581e-05, "epoch": 4.4109701187065085, "percentage": 13.48, "elapsed_time": "0:36:58", "remaining_time": "3:57:22", "throughput": 791.36, "total_tokens": 1755288} {"current_steps": 5395, "total_steps": 40000, "loss": 0.203, "lr": 4.7789927425131517e-05, "epoch": 4.415063446582071, "percentage": 13.49, "elapsed_time": "0:36:59", "remaining_time": "3:57:18", "throughput": 791.47, "total_tokens": 1756904} {"current_steps": 5400, "total_steps": 40000, "loss": 0.1981, "lr": 4.778588985216403e-05, "epoch": 4.419156774457634, "percentage": 13.5, "elapsed_time": "0:37:01", "remaining_time": "3:57:14", "throughput": 791.6, "total_tokens": 1758536} {"current_steps": 5400, "total_steps": 40000, "eval_loss": 0.20941542088985443, "epoch": 4.419156774457634, "percentage": 13.5, "elapsed_time": "0:37:13", "remaining_time": "3:58:33", "throughput": 787.18, "total_tokens": 1758536} {"current_steps": 5405, "total_steps": 40000, "loss": 0.2248, "lr": 4.778184876532598e-05, "epoch": 4.4232501023331965, "percentage": 13.51, "elapsed_time": "0:37:17", "remaining_time": "3:58:38", "throughput": 786.82, "total_tokens": 1760232} {"current_steps": 5410, "total_steps": 40000, "loss": 0.1798, "lr": 4.7777804165240556e-05, "epoch": 4.42734343020876, "percentage": 13.53, "elapsed_time": "0:37:18", "remaining_time": "3:58:34", "throughput": 786.95, "total_tokens": 1761864} {"current_steps": 5415, "total_steps": 40000, "loss": 0.1661, "lr": 4.7773756052531485e-05, "epoch": 4.431436758084322, "percentage": 13.54, "elapsed_time": "0:37:20", "remaining_time": "3:58:30", "throughput": 787.07, "total_tokens": 1763480} {"current_steps": 5420, "total_steps": 40000, "loss": 0.2034, "lr": 4.7769704427823035e-05, "epoch": 4.435530085959885, "percentage": 13.55, "elapsed_time": "0:37:22", "remaining_time": "3:58:25", "throughput": 787.18, "total_tokens": 1765096} {"current_steps": 5425, "total_steps": 40000, "loss": 0.2402, "lr": 4.776564929174003e-05, "epoch": 4.439623413835449, "percentage": 13.56, "elapsed_time": "0:37:24", "remaining_time": "3:58:21", "throughput": 787.32, "total_tokens": 1766744} {"current_steps": 5430, "total_steps": 40000, "loss": 0.2114, "lr": 4.7761590644907806e-05, "epoch": 4.443716741711011, "percentage": 13.58, "elapsed_time": "0:37:25", "remaining_time": "3:58:17", "throughput": 787.48, "total_tokens": 1768456} {"current_steps": 5435, "total_steps": 40000, "loss": 0.3139, "lr": 4.7757528487952263e-05, "epoch": 4.447810069586573, "percentage": 13.59, "elapsed_time": "0:37:27", "remaining_time": "3:58:13", "throughput": 787.6, "total_tokens": 1770088} {"current_steps": 5440, "total_steps": 40000, "loss": 0.2354, "lr": 4.7753462821499836e-05, "epoch": 4.451903397462137, "percentage": 13.6, "elapsed_time": "0:37:29", "remaining_time": "3:58:08", "throughput": 787.71, "total_tokens": 1771688} {"current_steps": 5445, "total_steps": 40000, "loss": 0.2055, "lr": 4.774939364617751e-05, "epoch": 4.4559967253377, "percentage": 13.61, "elapsed_time": "0:37:30", "remaining_time": "3:58:04", "throughput": 787.79, "total_tokens": 1773224} {"current_steps": 5450, "total_steps": 40000, "loss": 0.1823, "lr": 4.7745320962612795e-05, "epoch": 4.460090053213262, "percentage": 13.63, "elapsed_time": "0:37:32", "remaining_time": "3:58:00", "throughput": 787.9, "total_tokens": 1774824} {"current_steps": 5455, "total_steps": 40000, "loss": 0.1847, "lr": 4.7741244771433756e-05, "epoch": 4.464183381088826, "percentage": 13.64, "elapsed_time": "0:37:34", "remaining_time": "3:57:56", "throughput": 788.03, "total_tokens": 1776472} {"current_steps": 5460, "total_steps": 40000, "loss": 0.2118, "lr": 4.7737165073268985e-05, "epoch": 4.468276708964388, "percentage": 13.65, "elapsed_time": "0:37:36", "remaining_time": "3:57:51", "throughput": 788.14, "total_tokens": 1778072} {"current_steps": 5465, "total_steps": 40000, "loss": 0.2103, "lr": 4.7733081868747626e-05, "epoch": 4.472370036839951, "percentage": 13.66, "elapsed_time": "0:37:37", "remaining_time": "3:57:47", "throughput": 788.27, "total_tokens": 1779720} {"current_steps": 5470, "total_steps": 40000, "loss": 0.2369, "lr": 4.772899515849936e-05, "epoch": 4.476463364715514, "percentage": 13.68, "elapsed_time": "0:37:39", "remaining_time": "3:57:43", "throughput": 788.37, "total_tokens": 1781304} {"current_steps": 5475, "total_steps": 40000, "loss": 0.1957, "lr": 4.7724904943154414e-05, "epoch": 4.480556692591077, "percentage": 13.69, "elapsed_time": "0:37:41", "remaining_time": "3:57:38", "throughput": 788.48, "total_tokens": 1782920} {"current_steps": 5480, "total_steps": 40000, "loss": 0.171, "lr": 4.772081122334354e-05, "epoch": 4.484650020466639, "percentage": 13.7, "elapsed_time": "0:37:42", "remaining_time": "3:57:34", "throughput": 788.6, "total_tokens": 1784536} {"current_steps": 5485, "total_steps": 40000, "loss": 0.2308, "lr": 4.771671399969806e-05, "epoch": 4.488743348342203, "percentage": 13.71, "elapsed_time": "0:37:44", "remaining_time": "3:57:30", "throughput": 788.73, "total_tokens": 1786200} {"current_steps": 5490, "total_steps": 40000, "loss": 0.2145, "lr": 4.7712613272849794e-05, "epoch": 4.492836676217765, "percentage": 13.73, "elapsed_time": "0:37:46", "remaining_time": "3:57:26", "throughput": 788.84, "total_tokens": 1787816} {"current_steps": 5495, "total_steps": 40000, "loss": 0.2122, "lr": 4.770850904343114e-05, "epoch": 4.496930004093328, "percentage": 13.74, "elapsed_time": "0:37:48", "remaining_time": "3:57:22", "throughput": 788.96, "total_tokens": 1789432} {"current_steps": 5500, "total_steps": 40000, "loss": 0.2102, "lr": 4.770440131207502e-05, "epoch": 4.501023331968891, "percentage": 13.75, "elapsed_time": "0:37:49", "remaining_time": "3:57:17", "throughput": 789.06, "total_tokens": 1791016} {"current_steps": 5505, "total_steps": 40000, "loss": 0.231, "lr": 4.7700290079414896e-05, "epoch": 4.505116659844454, "percentage": 13.76, "elapsed_time": "0:37:51", "remaining_time": "3:57:13", "throughput": 789.16, "total_tokens": 1792600} {"current_steps": 5510, "total_steps": 40000, "loss": 0.2016, "lr": 4.769617534608477e-05, "epoch": 4.509209987720016, "percentage": 13.78, "elapsed_time": "0:37:53", "remaining_time": "3:57:09", "throughput": 789.27, "total_tokens": 1794200} {"current_steps": 5515, "total_steps": 40000, "loss": 0.2461, "lr": 4.7692057112719193e-05, "epoch": 4.5133033155955795, "percentage": 13.79, "elapsed_time": "0:37:54", "remaining_time": "3:57:05", "throughput": 789.36, "total_tokens": 1795768} {"current_steps": 5520, "total_steps": 40000, "loss": 0.2212, "lr": 4.7687935379953234e-05, "epoch": 4.517396643471142, "percentage": 13.8, "elapsed_time": "0:37:56", "remaining_time": "3:57:01", "throughput": 789.47, "total_tokens": 1797368} {"current_steps": 5525, "total_steps": 40000, "loss": 0.1924, "lr": 4.7683810148422534e-05, "epoch": 4.521489971346705, "percentage": 13.81, "elapsed_time": "0:37:58", "remaining_time": "3:56:56", "throughput": 789.59, "total_tokens": 1799016} {"current_steps": 5530, "total_steps": 40000, "loss": 0.2114, "lr": 4.767968141876324e-05, "epoch": 4.5255832992222675, "percentage": 13.83, "elapsed_time": "0:38:00", "remaining_time": "3:56:52", "throughput": 789.7, "total_tokens": 1800632} {"current_steps": 5535, "total_steps": 40000, "loss": 0.2136, "lr": 4.767554919161207e-05, "epoch": 4.529676627097831, "percentage": 13.84, "elapsed_time": "0:38:01", "remaining_time": "3:56:48", "throughput": 789.85, "total_tokens": 1802328} {"current_steps": 5540, "total_steps": 40000, "loss": 0.2324, "lr": 4.767141346760624e-05, "epoch": 4.533769954973393, "percentage": 13.85, "elapsed_time": "0:38:03", "remaining_time": "3:56:44", "throughput": 790.0, "total_tokens": 1804024} {"current_steps": 5545, "total_steps": 40000, "loss": 0.1711, "lr": 4.766727424738356e-05, "epoch": 4.5378632828489565, "percentage": 13.86, "elapsed_time": "0:38:05", "remaining_time": "3:56:40", "throughput": 790.11, "total_tokens": 1805640} {"current_steps": 5550, "total_steps": 40000, "loss": 0.1694, "lr": 4.7663131531582325e-05, "epoch": 4.541956610724519, "percentage": 13.88, "elapsed_time": "0:38:07", "remaining_time": "3:56:35", "throughput": 790.21, "total_tokens": 1807224} {"current_steps": 5555, "total_steps": 40000, "loss": 0.1836, "lr": 4.765898532084142e-05, "epoch": 4.546049938600082, "percentage": 13.89, "elapsed_time": "0:38:08", "remaining_time": "3:56:31", "throughput": 790.35, "total_tokens": 1808904} {"current_steps": 5560, "total_steps": 40000, "loss": 0.2148, "lr": 4.765483561580022e-05, "epoch": 4.5501432664756445, "percentage": 13.9, "elapsed_time": "0:38:10", "remaining_time": "3:56:27", "throughput": 790.46, "total_tokens": 1810504} {"current_steps": 5565, "total_steps": 40000, "loss": 0.2002, "lr": 4.7650682417098666e-05, "epoch": 4.554236594351208, "percentage": 13.91, "elapsed_time": "0:38:12", "remaining_time": "3:56:23", "throughput": 790.58, "total_tokens": 1812136} {"current_steps": 5570, "total_steps": 40000, "loss": 0.1695, "lr": 4.7646525725377244e-05, "epoch": 4.55832992222677, "percentage": 13.93, "elapsed_time": "0:38:13", "remaining_time": "3:56:19", "throughput": 790.72, "total_tokens": 1813816} {"current_steps": 5575, "total_steps": 40000, "loss": 0.1828, "lr": 4.764236554127696e-05, "epoch": 4.562423250102333, "percentage": 13.94, "elapsed_time": "0:38:15", "remaining_time": "3:56:15", "throughput": 790.83, "total_tokens": 1815448} {"current_steps": 5580, "total_steps": 40000, "loss": 0.1875, "lr": 4.7638201865439356e-05, "epoch": 4.566516577977896, "percentage": 13.95, "elapsed_time": "0:38:17", "remaining_time": "3:56:11", "throughput": 790.93, "total_tokens": 1817048} {"current_steps": 5585, "total_steps": 40000, "loss": 0.1696, "lr": 4.7634034698506545e-05, "epoch": 4.570609905853459, "percentage": 13.96, "elapsed_time": "0:38:19", "remaining_time": "3:56:06", "throughput": 791.07, "total_tokens": 1818712} {"current_steps": 5590, "total_steps": 40000, "loss": 0.1846, "lr": 4.762986404112115e-05, "epoch": 4.574703233729021, "percentage": 13.98, "elapsed_time": "0:38:20", "remaining_time": "3:56:02", "throughput": 791.16, "total_tokens": 1820280} {"current_steps": 5595, "total_steps": 40000, "loss": 0.1886, "lr": 4.762568989392633e-05, "epoch": 4.578796561604585, "percentage": 13.99, "elapsed_time": "0:38:22", "remaining_time": "3:55:58", "throughput": 791.29, "total_tokens": 1821928} {"current_steps": 5600, "total_steps": 40000, "loss": 0.2221, "lr": 4.76215122575658e-05, "epoch": 4.582889889480147, "percentage": 14.0, "elapsed_time": "0:38:24", "remaining_time": "3:55:54", "throughput": 791.4, "total_tokens": 1823544} {"current_steps": 5600, "total_steps": 40000, "eval_loss": 0.20939308404922485, "epoch": 4.582889889480147, "percentage": 14.0, "elapsed_time": "0:38:36", "remaining_time": "3:57:10", "throughput": 787.15, "total_tokens": 1823544} {"current_steps": 5605, "total_steps": 40000, "loss": 0.2101, "lr": 4.7617331132683795e-05, "epoch": 4.58698321735571, "percentage": 14.01, "elapsed_time": "0:38:39", "remaining_time": "3:57:15", "throughput": 786.79, "total_tokens": 1825176} {"current_steps": 5610, "total_steps": 40000, "loss": 0.1993, "lr": 4.7613146519925105e-05, "epoch": 4.591076545231273, "percentage": 14.03, "elapsed_time": "0:38:41", "remaining_time": "3:57:11", "throughput": 786.91, "total_tokens": 1826824} {"current_steps": 5615, "total_steps": 40000, "loss": 0.3846, "lr": 4.7608958419935045e-05, "epoch": 4.595169873106836, "percentage": 14.04, "elapsed_time": "0:38:43", "remaining_time": "3:57:06", "throughput": 787.04, "total_tokens": 1828472} {"current_steps": 5620, "total_steps": 40000, "loss": 0.2303, "lr": 4.760476683335948e-05, "epoch": 4.599263200982398, "percentage": 14.05, "elapsed_time": "0:38:44", "remaining_time": "3:57:02", "throughput": 787.17, "total_tokens": 1830120} {"current_steps": 5625, "total_steps": 40000, "loss": 0.2367, "lr": 4.760057176084479e-05, "epoch": 4.603356528857962, "percentage": 14.06, "elapsed_time": "0:38:46", "remaining_time": "3:56:58", "throughput": 787.31, "total_tokens": 1831816} {"current_steps": 5630, "total_steps": 40000, "loss": 0.2049, "lr": 4.759637320303793e-05, "epoch": 4.607449856733524, "percentage": 14.07, "elapsed_time": "0:38:48", "remaining_time": "3:56:54", "throughput": 787.44, "total_tokens": 1833464} {"current_steps": 5635, "total_steps": 40000, "loss": 0.2276, "lr": 4.759217116058635e-05, "epoch": 4.611543184609087, "percentage": 14.09, "elapsed_time": "0:38:50", "remaining_time": "3:56:50", "throughput": 787.58, "total_tokens": 1835128} {"current_steps": 5640, "total_steps": 40000, "loss": 0.2044, "lr": 4.758796563413807e-05, "epoch": 4.61563651248465, "percentage": 14.1, "elapsed_time": "0:38:51", "remaining_time": "3:56:45", "throughput": 787.69, "total_tokens": 1836744} {"current_steps": 5645, "total_steps": 40000, "loss": 0.1943, "lr": 4.758375662434163e-05, "epoch": 4.619729840360213, "percentage": 14.11, "elapsed_time": "0:38:53", "remaining_time": "3:56:41", "throughput": 787.82, "total_tokens": 1838408} {"current_steps": 5650, "total_steps": 40000, "loss": 0.2047, "lr": 4.7579544131846114e-05, "epoch": 4.623823168235775, "percentage": 14.12, "elapsed_time": "0:38:55", "remaining_time": "3:56:37", "throughput": 787.98, "total_tokens": 1840120} {"current_steps": 5655, "total_steps": 40000, "loss": 0.1788, "lr": 4.757532815730114e-05, "epoch": 4.627916496111339, "percentage": 14.14, "elapsed_time": "0:38:56", "remaining_time": "3:56:33", "throughput": 788.09, "total_tokens": 1841736} {"current_steps": 5660, "total_steps": 40000, "loss": 0.2035, "lr": 4.7571108701356865e-05, "epoch": 4.632009823986901, "percentage": 14.15, "elapsed_time": "0:38:58", "remaining_time": "3:56:29", "throughput": 788.22, "total_tokens": 1843384} {"current_steps": 5665, "total_steps": 40000, "loss": 0.1966, "lr": 4.756688576466398e-05, "epoch": 4.636103151862464, "percentage": 14.16, "elapsed_time": "0:39:00", "remaining_time": "3:56:24", "throughput": 788.33, "total_tokens": 1845016} {"current_steps": 5670, "total_steps": 40000, "loss": 0.2205, "lr": 4.756265934787372e-05, "epoch": 4.640196479738027, "percentage": 14.17, "elapsed_time": "0:39:02", "remaining_time": "3:56:20", "throughput": 788.45, "total_tokens": 1846648} {"current_steps": 5675, "total_steps": 40000, "loss": 0.2061, "lr": 4.755842945163785e-05, "epoch": 4.64428980761359, "percentage": 14.19, "elapsed_time": "0:39:03", "remaining_time": "3:56:16", "throughput": 788.53, "total_tokens": 1848200} {"current_steps": 5680, "total_steps": 40000, "loss": 0.2401, "lr": 4.755419607660867e-05, "epoch": 4.648383135489153, "percentage": 14.2, "elapsed_time": "0:39:05", "remaining_time": "3:56:12", "throughput": 788.69, "total_tokens": 1849928} {"current_steps": 5685, "total_steps": 40000, "loss": 0.2371, "lr": 4.7549959223439016e-05, "epoch": 4.6524764633647155, "percentage": 14.21, "elapsed_time": "0:39:07", "remaining_time": "3:56:08", "throughput": 788.82, "total_tokens": 1851576} {"current_steps": 5690, "total_steps": 40000, "loss": 0.2222, "lr": 4.754571889278228e-05, "epoch": 4.656569791240278, "percentage": 14.22, "elapsed_time": "0:39:08", "remaining_time": "3:56:04", "throughput": 788.94, "total_tokens": 1853208} {"current_steps": 5695, "total_steps": 40000, "loss": 0.1594, "lr": 4.754147508529235e-05, "epoch": 4.660663119115841, "percentage": 14.24, "elapsed_time": "0:39:10", "remaining_time": "3:55:59", "throughput": 789.08, "total_tokens": 1854904} {"current_steps": 5700, "total_steps": 40000, "loss": 0.2043, "lr": 4.75372278016237e-05, "epoch": 4.6647564469914045, "percentage": 14.25, "elapsed_time": "0:39:12", "remaining_time": "3:55:55", "throughput": 789.21, "total_tokens": 1856552} {"current_steps": 5705, "total_steps": 40000, "loss": 0.1916, "lr": 4.753297704243129e-05, "epoch": 4.668849774866967, "percentage": 14.26, "elapsed_time": "0:39:14", "remaining_time": "3:55:51", "throughput": 789.33, "total_tokens": 1858200} {"current_steps": 5710, "total_steps": 40000, "loss": 0.1966, "lr": 4.752872280837066e-05, "epoch": 4.672943102742529, "percentage": 14.27, "elapsed_time": "0:39:15", "remaining_time": "3:55:47", "throughput": 789.44, "total_tokens": 1859832} {"current_steps": 5715, "total_steps": 40000, "loss": 0.2039, "lr": 4.752446510009786e-05, "epoch": 4.6770364306180925, "percentage": 14.29, "elapsed_time": "0:39:17", "remaining_time": "3:55:43", "throughput": 789.53, "total_tokens": 1861400} {"current_steps": 5720, "total_steps": 40000, "loss": 0.208, "lr": 4.7520203918269476e-05, "epoch": 4.681129758493656, "percentage": 14.3, "elapsed_time": "0:39:19", "remaining_time": "3:55:39", "throughput": 789.65, "total_tokens": 1863032} {"current_steps": 5725, "total_steps": 40000, "loss": 0.2384, "lr": 4.751593926354265e-05, "epoch": 4.685223086369218, "percentage": 14.31, "elapsed_time": "0:39:21", "remaining_time": "3:55:35", "throughput": 789.76, "total_tokens": 1864648} {"current_steps": 5730, "total_steps": 40000, "loss": 0.237, "lr": 4.751167113657503e-05, "epoch": 4.6893164142447805, "percentage": 14.32, "elapsed_time": "0:39:22", "remaining_time": "3:55:31", "throughput": 789.86, "total_tokens": 1866248} {"current_steps": 5735, "total_steps": 40000, "loss": 0.1947, "lr": 4.7507399538024834e-05, "epoch": 4.693409742120344, "percentage": 14.34, "elapsed_time": "0:39:24", "remaining_time": "3:55:27", "throughput": 789.96, "total_tokens": 1867832} {"current_steps": 5740, "total_steps": 40000, "loss": 0.2332, "lr": 4.750312446855077e-05, "epoch": 4.697503069995907, "percentage": 14.35, "elapsed_time": "0:39:26", "remaining_time": "3:55:22", "throughput": 790.08, "total_tokens": 1869480} {"current_steps": 5745, "total_steps": 40000, "loss": 0.2044, "lr": 4.749884592881212e-05, "epoch": 4.701596397871469, "percentage": 14.36, "elapsed_time": "0:39:27", "remaining_time": "3:55:18", "throughput": 790.25, "total_tokens": 1871224} {"current_steps": 5750, "total_steps": 40000, "loss": 0.2189, "lr": 4.74945639194687e-05, "epoch": 4.705689725747033, "percentage": 14.37, "elapsed_time": "0:39:29", "remaining_time": "3:55:14", "throughput": 790.35, "total_tokens": 1872840} {"current_steps": 5755, "total_steps": 40000, "loss": 0.1875, "lr": 4.749027844118083e-05, "epoch": 4.709783053622595, "percentage": 14.39, "elapsed_time": "0:39:31", "remaining_time": "3:55:10", "throughput": 790.45, "total_tokens": 1874440} {"current_steps": 5760, "total_steps": 40000, "loss": 0.248, "lr": 4.7485989494609395e-05, "epoch": 4.713876381498158, "percentage": 14.4, "elapsed_time": "0:39:33", "remaining_time": "3:55:06", "throughput": 790.59, "total_tokens": 1876120} {"current_steps": 5765, "total_steps": 40000, "loss": 0.1877, "lr": 4.748169708041581e-05, "epoch": 4.717969709373721, "percentage": 14.41, "elapsed_time": "0:39:34", "remaining_time": "3:55:02", "throughput": 790.7, "total_tokens": 1877736} {"current_steps": 5770, "total_steps": 40000, "loss": 0.206, "lr": 4.7477401199262004e-05, "epoch": 4.722063037249284, "percentage": 14.42, "elapsed_time": "0:39:36", "remaining_time": "3:54:58", "throughput": 790.83, "total_tokens": 1879400} {"current_steps": 5775, "total_steps": 40000, "loss": 0.2035, "lr": 4.747310185181048e-05, "epoch": 4.726156365124846, "percentage": 14.44, "elapsed_time": "0:39:38", "remaining_time": "3:54:54", "throughput": 790.93, "total_tokens": 1881000} {"current_steps": 5780, "total_steps": 40000, "loss": 0.192, "lr": 4.746879903872422e-05, "epoch": 4.73024969300041, "percentage": 14.45, "elapsed_time": "0:39:39", "remaining_time": "3:54:50", "throughput": 791.03, "total_tokens": 1882584} {"current_steps": 5785, "total_steps": 40000, "loss": 0.2227, "lr": 4.746449276066679e-05, "epoch": 4.734343020875972, "percentage": 14.46, "elapsed_time": "0:39:41", "remaining_time": "3:54:45", "throughput": 791.16, "total_tokens": 1884248} {"current_steps": 5790, "total_steps": 40000, "loss": 0.2281, "lr": 4.746018301830227e-05, "epoch": 4.738436348751535, "percentage": 14.47, "elapsed_time": "0:39:43", "remaining_time": "3:54:41", "throughput": 791.3, "total_tokens": 1885928} {"current_steps": 5795, "total_steps": 40000, "loss": 0.1957, "lr": 4.7455869812295275e-05, "epoch": 4.742529676627098, "percentage": 14.49, "elapsed_time": "0:39:45", "remaining_time": "3:54:37", "throughput": 791.42, "total_tokens": 1887592} {"current_steps": 5800, "total_steps": 40000, "loss": 0.2198, "lr": 4.7451553143310964e-05, "epoch": 4.746623004502661, "percentage": 14.5, "elapsed_time": "0:39:46", "remaining_time": "3:54:33", "throughput": 791.56, "total_tokens": 1889272} {"current_steps": 5800, "total_steps": 40000, "eval_loss": 0.20803390443325043, "epoch": 4.746623004502661, "percentage": 14.5, "elapsed_time": "0:39:59", "remaining_time": "3:55:47", "throughput": 787.46, "total_tokens": 1889272} {"current_steps": 5805, "total_steps": 40000, "loss": 0.2154, "lr": 4.744723301201501e-05, "epoch": 4.750716332378223, "percentage": 14.51, "elapsed_time": "0:40:02", "remaining_time": "3:55:51", "throughput": 787.1, "total_tokens": 1890920} {"current_steps": 5810, "total_steps": 40000, "loss": 0.1733, "lr": 4.744290941907364e-05, "epoch": 4.754809660253787, "percentage": 14.52, "elapsed_time": "0:40:04", "remaining_time": "3:55:47", "throughput": 787.23, "total_tokens": 1892584} {"current_steps": 5815, "total_steps": 40000, "loss": 0.2183, "lr": 4.7438582365153594e-05, "epoch": 4.758902988129349, "percentage": 14.54, "elapsed_time": "0:40:05", "remaining_time": "3:55:43", "throughput": 787.33, "total_tokens": 1894184} {"current_steps": 5820, "total_steps": 40000, "loss": 0.1699, "lr": 4.743425185092217e-05, "epoch": 4.762996316004912, "percentage": 14.55, "elapsed_time": "0:40:07", "remaining_time": "3:55:39", "throughput": 787.43, "total_tokens": 1895784} {"current_steps": 5825, "total_steps": 40000, "loss": 0.2528, "lr": 4.742991787704719e-05, "epoch": 4.767089643880475, "percentage": 14.56, "elapsed_time": "0:40:09", "remaining_time": "3:55:35", "throughput": 787.54, "total_tokens": 1897384} {"current_steps": 5830, "total_steps": 40000, "loss": 0.2017, "lr": 4.7425580444196994e-05, "epoch": 4.771182971756038, "percentage": 14.57, "elapsed_time": "0:40:10", "remaining_time": "3:55:30", "throughput": 787.64, "total_tokens": 1898984} {"current_steps": 5835, "total_steps": 40000, "loss": 0.2676, "lr": 4.742123955304048e-05, "epoch": 4.7752762996316, "percentage": 14.59, "elapsed_time": "0:40:12", "remaining_time": "3:55:26", "throughput": 787.75, "total_tokens": 1900600} {"current_steps": 5840, "total_steps": 40000, "loss": 0.2443, "lr": 4.741689520424706e-05, "epoch": 4.7793696275071635, "percentage": 14.6, "elapsed_time": "0:40:14", "remaining_time": "3:55:22", "throughput": 787.94, "total_tokens": 1902408} {"current_steps": 5845, "total_steps": 40000, "loss": 0.1488, "lr": 4.741254739848669e-05, "epoch": 4.783462955382726, "percentage": 14.61, "elapsed_time": "0:40:16", "remaining_time": "3:55:18", "throughput": 788.06, "total_tokens": 1904072} {"current_steps": 5850, "total_steps": 40000, "loss": 0.1843, "lr": 4.740819613642987e-05, "epoch": 4.787556283258289, "percentage": 14.62, "elapsed_time": "0:40:17", "remaining_time": "3:55:14", "throughput": 788.17, "total_tokens": 1905688} {"current_steps": 5855, "total_steps": 40000, "loss": 0.1601, "lr": 4.74038414187476e-05, "epoch": 4.791649611133852, "percentage": 14.64, "elapsed_time": "0:40:19", "remaining_time": "3:55:10", "throughput": 788.3, "total_tokens": 1907368} {"current_steps": 5860, "total_steps": 40000, "loss": 0.169, "lr": 4.739948324611144e-05, "epoch": 4.795742939009415, "percentage": 14.65, "elapsed_time": "0:40:21", "remaining_time": "3:55:06", "throughput": 788.42, "total_tokens": 1909000} {"current_steps": 5865, "total_steps": 40000, "loss": 0.2021, "lr": 4.7395121619193465e-05, "epoch": 4.799836266884977, "percentage": 14.66, "elapsed_time": "0:40:23", "remaining_time": "3:55:02", "throughput": 788.57, "total_tokens": 1910712} {"current_steps": 5870, "total_steps": 40000, "loss": 0.1739, "lr": 4.7390756538666313e-05, "epoch": 4.8039295947605405, "percentage": 14.67, "elapsed_time": "0:40:24", "remaining_time": "3:54:58", "throughput": 788.68, "total_tokens": 1912344} {"current_steps": 5875, "total_steps": 40000, "loss": 0.1817, "lr": 4.738638800520311e-05, "epoch": 4.808022922636103, "percentage": 14.69, "elapsed_time": "0:40:26", "remaining_time": "3:54:54", "throughput": 788.79, "total_tokens": 1913960} {"current_steps": 5880, "total_steps": 40000, "loss": 0.221, "lr": 4.738201601947757e-05, "epoch": 4.812116250511666, "percentage": 14.7, "elapsed_time": "0:40:28", "remaining_time": "3:54:50", "throughput": 788.89, "total_tokens": 1915560} {"current_steps": 5885, "total_steps": 40000, "loss": 0.1992, "lr": 4.7377640582163876e-05, "epoch": 4.8162095783872285, "percentage": 14.71, "elapsed_time": "0:40:29", "remaining_time": "3:54:45", "throughput": 789.01, "total_tokens": 1917224} {"current_steps": 5890, "total_steps": 40000, "loss": 0.1902, "lr": 4.7373261693936786e-05, "epoch": 4.820302906262792, "percentage": 14.72, "elapsed_time": "0:40:31", "remaining_time": "3:54:41", "throughput": 789.13, "total_tokens": 1918856} {"current_steps": 5895, "total_steps": 40000, "loss": 0.2334, "lr": 4.7368879355471595e-05, "epoch": 4.824396234138354, "percentage": 14.74, "elapsed_time": "0:40:33", "remaining_time": "3:54:37", "throughput": 789.23, "total_tokens": 1920472} {"current_steps": 5900, "total_steps": 40000, "loss": 0.1988, "lr": 4.736449356744409e-05, "epoch": 4.828489562013917, "percentage": 14.75, "elapsed_time": "0:40:35", "remaining_time": "3:54:33", "throughput": 789.35, "total_tokens": 1922120} {"current_steps": 5905, "total_steps": 40000, "loss": 0.2259, "lr": 4.736010433053064e-05, "epoch": 4.83258288988948, "percentage": 14.76, "elapsed_time": "0:40:36", "remaining_time": "3:54:29", "throughput": 789.47, "total_tokens": 1923752} {"current_steps": 5910, "total_steps": 40000, "loss": 0.1818, "lr": 4.73557116454081e-05, "epoch": 4.836676217765043, "percentage": 14.77, "elapsed_time": "0:40:38", "remaining_time": "3:54:25", "throughput": 789.57, "total_tokens": 1925352} {"current_steps": 5915, "total_steps": 40000, "loss": 0.2065, "lr": 4.735131551275389e-05, "epoch": 4.8407695456406055, "percentage": 14.79, "elapsed_time": "0:40:40", "remaining_time": "3:54:21", "throughput": 789.67, "total_tokens": 1926952} {"current_steps": 5920, "total_steps": 40000, "loss": 0.2067, "lr": 4.734691593324594e-05, "epoch": 4.844862873516169, "percentage": 14.8, "elapsed_time": "0:40:41", "remaining_time": "3:54:17", "throughput": 789.78, "total_tokens": 1928584} {"current_steps": 5925, "total_steps": 40000, "loss": 0.2598, "lr": 4.734251290756272e-05, "epoch": 4.848956201391731, "percentage": 14.81, "elapsed_time": "0:40:43", "remaining_time": "3:54:13", "throughput": 789.89, "total_tokens": 1930216} {"current_steps": 5930, "total_steps": 40000, "loss": 0.1893, "lr": 4.7338106436383246e-05, "epoch": 4.853049529267294, "percentage": 14.82, "elapsed_time": "0:40:45", "remaining_time": "3:54:09", "throughput": 790.02, "total_tokens": 1931880} {"current_steps": 5935, "total_steps": 40000, "loss": 0.234, "lr": 4.733369652038703e-05, "epoch": 4.857142857142857, "percentage": 14.84, "elapsed_time": "0:40:47", "remaining_time": "3:54:05", "throughput": 790.12, "total_tokens": 1933496} {"current_steps": 5940, "total_steps": 40000, "loss": 0.2446, "lr": 4.7329283160254156e-05, "epoch": 4.86123618501842, "percentage": 14.85, "elapsed_time": "0:40:48", "remaining_time": "3:54:01", "throughput": 790.21, "total_tokens": 1935080} {"current_steps": 5945, "total_steps": 40000, "loss": 0.1914, "lr": 4.732486635666521e-05, "epoch": 4.865329512893982, "percentage": 14.86, "elapsed_time": "0:40:50", "remaining_time": "3:53:57", "throughput": 790.31, "total_tokens": 1936696} {"current_steps": 5950, "total_steps": 40000, "loss": 0.1733, "lr": 4.732044611030132e-05, "epoch": 4.869422840769546, "percentage": 14.88, "elapsed_time": "0:40:52", "remaining_time": "3:53:53", "throughput": 790.42, "total_tokens": 1938312} {"current_steps": 5955, "total_steps": 40000, "loss": 0.2281, "lr": 4.731602242184414e-05, "epoch": 4.873516168645109, "percentage": 14.89, "elapsed_time": "0:40:53", "remaining_time": "3:53:49", "throughput": 790.53, "total_tokens": 1939944} {"current_steps": 5960, "total_steps": 40000, "loss": 0.2165, "lr": 4.7311595291975864e-05, "epoch": 4.877609496520671, "percentage": 14.9, "elapsed_time": "0:40:55", "remaining_time": "3:53:45", "throughput": 790.62, "total_tokens": 1941512} {"current_steps": 5965, "total_steps": 40000, "loss": 0.2354, "lr": 4.7307164721379216e-05, "epoch": 4.881702824396234, "percentage": 14.91, "elapsed_time": "0:40:57", "remaining_time": "3:53:41", "throughput": 790.72, "total_tokens": 1943128} {"current_steps": 5970, "total_steps": 40000, "loss": 0.2111, "lr": 4.730273071073743e-05, "epoch": 4.885796152271797, "percentage": 14.92, "elapsed_time": "0:40:59", "remaining_time": "3:53:37", "throughput": 790.83, "total_tokens": 1944744} {"current_steps": 5975, "total_steps": 40000, "loss": 0.1815, "lr": 4.729829326073429e-05, "epoch": 4.88988948014736, "percentage": 14.94, "elapsed_time": "0:41:00", "remaining_time": "3:53:33", "throughput": 790.96, "total_tokens": 1946424} {"current_steps": 5980, "total_steps": 40000, "loss": 0.2107, "lr": 4.7293852372054126e-05, "epoch": 4.893982808022923, "percentage": 14.95, "elapsed_time": "0:41:02", "remaining_time": "3:53:29", "throughput": 791.04, "total_tokens": 1947992} {"current_steps": 5985, "total_steps": 40000, "loss": 0.2313, "lr": 4.728940804538176e-05, "epoch": 4.898076135898485, "percentage": 14.96, "elapsed_time": "0:41:04", "remaining_time": "3:53:25", "throughput": 791.17, "total_tokens": 1949656} {"current_steps": 5990, "total_steps": 40000, "loss": 0.2154, "lr": 4.7284960281402556e-05, "epoch": 4.902169463774048, "percentage": 14.97, "elapsed_time": "0:41:05", "remaining_time": "3:53:21", "throughput": 791.26, "total_tokens": 1951240} {"current_steps": 5995, "total_steps": 40000, "loss": 0.2169, "lr": 4.728050908080244e-05, "epoch": 4.9062627916496115, "percentage": 14.99, "elapsed_time": "0:41:07", "remaining_time": "3:53:17", "throughput": 791.37, "total_tokens": 1952872} {"current_steps": 6000, "total_steps": 40000, "loss": 0.2502, "lr": 4.727605444426782e-05, "epoch": 4.910356119525174, "percentage": 15.0, "elapsed_time": "0:41:09", "remaining_time": "3:53:13", "throughput": 791.53, "total_tokens": 1954632} {"current_steps": 6000, "total_steps": 40000, "eval_loss": 0.20706959068775177, "epoch": 4.910356119525174, "percentage": 15.0, "elapsed_time": "0:41:21", "remaining_time": "3:54:24", "throughput": 787.56, "total_tokens": 1954632} {"current_steps": 6005, "total_steps": 40000, "loss": 0.1698, "lr": 4.727159637248567e-05, "epoch": 4.914449447400736, "percentage": 15.01, "elapsed_time": "0:41:25", "remaining_time": "3:54:28", "throughput": 787.24, "total_tokens": 1956312} {"current_steps": 6010, "total_steps": 40000, "loss": 0.2448, "lr": 4.7267134866143474e-05, "epoch": 4.9185427752763, "percentage": 15.02, "elapsed_time": "0:41:26", "remaining_time": "3:54:24", "throughput": 787.37, "total_tokens": 1958008} {"current_steps": 6015, "total_steps": 40000, "loss": 0.1843, "lr": 4.726266992592926e-05, "epoch": 4.922636103151863, "percentage": 15.04, "elapsed_time": "0:41:28", "remaining_time": "3:54:19", "throughput": 787.48, "total_tokens": 1959624} {"current_steps": 6020, "total_steps": 40000, "loss": 0.1664, "lr": 4.725820155253157e-05, "epoch": 4.926729431027425, "percentage": 15.05, "elapsed_time": "0:41:30", "remaining_time": "3:54:15", "throughput": 787.59, "total_tokens": 1961256} {"current_steps": 6025, "total_steps": 40000, "loss": 0.2251, "lr": 4.725372974663948e-05, "epoch": 4.9308227589029885, "percentage": 15.06, "elapsed_time": "0:41:31", "remaining_time": "3:54:11", "throughput": 787.71, "total_tokens": 1962904} {"current_steps": 6030, "total_steps": 40000, "loss": 0.1591, "lr": 4.724925450894262e-05, "epoch": 4.934916086778551, "percentage": 15.07, "elapsed_time": "0:41:33", "remaining_time": "3:54:07", "throughput": 787.8, "total_tokens": 1964488} {"current_steps": 6035, "total_steps": 40000, "loss": 0.189, "lr": 4.72447758401311e-05, "epoch": 4.939009414654114, "percentage": 15.09, "elapsed_time": "0:41:35", "remaining_time": "3:54:03", "throughput": 787.9, "total_tokens": 1966104} {"current_steps": 6040, "total_steps": 40000, "loss": 0.2014, "lr": 4.7240293740895616e-05, "epoch": 4.9431027425296765, "percentage": 15.1, "elapsed_time": "0:41:37", "remaining_time": "3:53:59", "throughput": 788.0, "total_tokens": 1967688} {"current_steps": 6045, "total_steps": 40000, "loss": 0.245, "lr": 4.723580821192733e-05, "epoch": 4.94719607040524, "percentage": 15.11, "elapsed_time": "0:41:38", "remaining_time": "3:53:55", "throughput": 788.1, "total_tokens": 1969304} {"current_steps": 6050, "total_steps": 40000, "loss": 0.2033, "lr": 4.7231319253917996e-05, "epoch": 4.951289398280802, "percentage": 15.12, "elapsed_time": "0:41:40", "remaining_time": "3:53:51", "throughput": 788.21, "total_tokens": 1970936} {"current_steps": 6055, "total_steps": 40000, "loss": 0.2218, "lr": 4.722682686755986e-05, "epoch": 4.955382726156365, "percentage": 15.14, "elapsed_time": "0:41:42", "remaining_time": "3:53:47", "throughput": 788.31, "total_tokens": 1972536} {"current_steps": 6060, "total_steps": 40000, "loss": 0.1935, "lr": 4.722233105354569e-05, "epoch": 4.959476054031928, "percentage": 15.15, "elapsed_time": "0:41:43", "remaining_time": "3:53:43", "throughput": 788.41, "total_tokens": 1974152} {"current_steps": 6065, "total_steps": 40000, "loss": 0.1866, "lr": 4.7217831812568815e-05, "epoch": 4.963569381907491, "percentage": 15.16, "elapsed_time": "0:41:45", "remaining_time": "3:53:39", "throughput": 788.52, "total_tokens": 1975784} {"current_steps": 6070, "total_steps": 40000, "loss": 0.213, "lr": 4.721332914532307e-05, "epoch": 4.9676627097830535, "percentage": 15.17, "elapsed_time": "0:41:47", "remaining_time": "3:53:35", "throughput": 788.59, "total_tokens": 1977320} {"current_steps": 6075, "total_steps": 40000, "loss": 0.2466, "lr": 4.720882305250281e-05, "epoch": 4.971756037658617, "percentage": 15.19, "elapsed_time": "0:41:49", "remaining_time": "3:53:31", "throughput": 788.69, "total_tokens": 1978936} {"current_steps": 6080, "total_steps": 40000, "loss": 0.2605, "lr": 4.720431353480295e-05, "epoch": 4.975849365534179, "percentage": 15.2, "elapsed_time": "0:41:50", "remaining_time": "3:53:27", "throughput": 788.8, "total_tokens": 1980568} {"current_steps": 6085, "total_steps": 40000, "loss": 0.206, "lr": 4.719980059291891e-05, "epoch": 4.979942693409742, "percentage": 15.21, "elapsed_time": "0:41:52", "remaining_time": "3:53:23", "throughput": 788.92, "total_tokens": 1982216} {"current_steps": 6090, "total_steps": 40000, "loss": 0.2009, "lr": 4.7195284227546634e-05, "epoch": 4.984036021285305, "percentage": 15.22, "elapsed_time": "0:41:54", "remaining_time": "3:53:19", "throughput": 789.03, "total_tokens": 1983848} {"current_steps": 6095, "total_steps": 40000, "loss": 0.1607, "lr": 4.7190764439382604e-05, "epoch": 4.988129349160868, "percentage": 15.24, "elapsed_time": "0:41:55", "remaining_time": "3:53:15", "throughput": 789.17, "total_tokens": 1985544} {"current_steps": 6100, "total_steps": 40000, "loss": 0.1646, "lr": 4.7186241229123826e-05, "epoch": 4.99222267703643, "percentage": 15.25, "elapsed_time": "0:41:57", "remaining_time": "3:53:11", "throughput": 789.27, "total_tokens": 1987160} {"current_steps": 6105, "total_steps": 40000, "loss": 0.1793, "lr": 4.718171459746785e-05, "epoch": 4.996316004911994, "percentage": 15.26, "elapsed_time": "0:41:59", "remaining_time": "3:53:07", "throughput": 789.37, "total_tokens": 1988776} {"current_steps": 6110, "total_steps": 40000, "loss": 0.1868, "lr": 4.717718454511273e-05, "epoch": 5.0, "percentage": 15.28, "elapsed_time": "0:42:01", "remaining_time": "3:53:03", "throughput": 789.4, "total_tokens": 1990176} {"current_steps": 6115, "total_steps": 40000, "loss": 0.2084, "lr": 4.7172651072757056e-05, "epoch": 5.004093327875563, "percentage": 15.29, "elapsed_time": "0:42:03", "remaining_time": "3:53:01", "throughput": 789.44, "total_tokens": 1991808} {"current_steps": 6120, "total_steps": 40000, "loss": 0.2814, "lr": 4.7168114181099945e-05, "epoch": 5.008186655751126, "percentage": 15.3, "elapsed_time": "0:42:04", "remaining_time": "3:52:57", "throughput": 789.55, "total_tokens": 1993440} {"current_steps": 6125, "total_steps": 40000, "loss": 0.2185, "lr": 4.716357387084105e-05, "epoch": 5.012279983626689, "percentage": 15.31, "elapsed_time": "0:42:06", "remaining_time": "3:52:53", "throughput": 789.64, "total_tokens": 1995024} {"current_steps": 6130, "total_steps": 40000, "loss": 0.1772, "lr": 4.715903014268054e-05, "epoch": 5.016373311502251, "percentage": 15.32, "elapsed_time": "0:42:08", "remaining_time": "3:52:49", "throughput": 789.75, "total_tokens": 1996656} {"current_steps": 6135, "total_steps": 40000, "loss": 0.2293, "lr": 4.715448299731911e-05, "epoch": 5.020466639377815, "percentage": 15.34, "elapsed_time": "0:42:09", "remaining_time": "3:52:45", "throughput": 789.87, "total_tokens": 1998320} {"current_steps": 6140, "total_steps": 40000, "loss": 0.3162, "lr": 4.7149932435457986e-05, "epoch": 5.024559967253377, "percentage": 15.35, "elapsed_time": "0:42:11", "remaining_time": "3:52:41", "throughput": 789.99, "total_tokens": 1999968} {"current_steps": 6145, "total_steps": 40000, "loss": 0.2027, "lr": 4.714537845779894e-05, "epoch": 5.02865329512894, "percentage": 15.36, "elapsed_time": "0:42:13", "remaining_time": "3:52:37", "throughput": 790.1, "total_tokens": 2001600} {"current_steps": 6150, "total_steps": 40000, "loss": 0.1735, "lr": 4.714082106504423e-05, "epoch": 5.032746623004503, "percentage": 15.38, "elapsed_time": "0:42:15", "remaining_time": "3:52:33", "throughput": 790.19, "total_tokens": 2003216} {"current_steps": 6155, "total_steps": 40000, "loss": 0.251, "lr": 4.713626025789667e-05, "epoch": 5.036839950880066, "percentage": 15.39, "elapsed_time": "0:42:16", "remaining_time": "3:52:29", "throughput": 790.29, "total_tokens": 2004816} {"current_steps": 6160, "total_steps": 40000, "loss": 0.2328, "lr": 4.7131696037059606e-05, "epoch": 5.040933278755628, "percentage": 15.4, "elapsed_time": "0:42:18", "remaining_time": "3:52:25", "throughput": 790.4, "total_tokens": 2006464} {"current_steps": 6165, "total_steps": 40000, "loss": 0.2477, "lr": 4.712712840323689e-05, "epoch": 5.0450266066311915, "percentage": 15.41, "elapsed_time": "0:42:20", "remaining_time": "3:52:21", "throughput": 790.51, "total_tokens": 2008096} {"current_steps": 6170, "total_steps": 40000, "loss": 0.2115, "lr": 4.71225573571329e-05, "epoch": 5.049119934506754, "percentage": 15.43, "elapsed_time": "0:42:21", "remaining_time": "3:52:17", "throughput": 790.6, "total_tokens": 2009680} {"current_steps": 6175, "total_steps": 40000, "loss": 0.1818, "lr": 4.711798289945256e-05, "epoch": 5.053213262382317, "percentage": 15.44, "elapsed_time": "0:42:23", "remaining_time": "3:52:13", "throughput": 790.71, "total_tokens": 2011328} {"current_steps": 6180, "total_steps": 40000, "loss": 0.2282, "lr": 4.71134050309013e-05, "epoch": 5.0573065902578795, "percentage": 15.45, "elapsed_time": "0:42:25", "remaining_time": "3:52:09", "throughput": 790.84, "total_tokens": 2013008} {"current_steps": 6185, "total_steps": 40000, "loss": 0.2075, "lr": 4.710882375218509e-05, "epoch": 5.061399918133443, "percentage": 15.46, "elapsed_time": "0:42:27", "remaining_time": "3:52:05", "throughput": 790.96, "total_tokens": 2014672} {"current_steps": 6190, "total_steps": 40000, "loss": 0.1774, "lr": 4.7104239064010424e-05, "epoch": 5.065493246009005, "percentage": 15.47, "elapsed_time": "0:42:28", "remaining_time": "3:52:01", "throughput": 791.05, "total_tokens": 2016272} {"current_steps": 6195, "total_steps": 40000, "loss": 0.1943, "lr": 4.709965096708432e-05, "epoch": 5.0695865738845685, "percentage": 15.49, "elapsed_time": "0:42:30", "remaining_time": "3:51:58", "throughput": 791.13, "total_tokens": 2017840} {"current_steps": 6200, "total_steps": 40000, "loss": 0.2157, "lr": 4.709505946211431e-05, "epoch": 5.073679901760131, "percentage": 15.5, "elapsed_time": "0:42:32", "remaining_time": "3:51:54", "throughput": 791.22, "total_tokens": 2019440} {"current_steps": 6200, "total_steps": 40000, "eval_loss": 0.20677843689918518, "epoch": 5.073679901760131, "percentage": 15.5, "elapsed_time": "0:42:44", "remaining_time": "3:53:01", "throughput": 787.39, "total_tokens": 2019440} {"current_steps": 6205, "total_steps": 40000, "loss": 0.1952, "lr": 4.709046454980846e-05, "epoch": 5.077773229635694, "percentage": 15.51, "elapsed_time": "0:42:48", "remaining_time": "3:53:06", "throughput": 787.0, "total_tokens": 2021072} {"current_steps": 6210, "total_steps": 40000, "loss": 0.1873, "lr": 4.708586623087538e-05, "epoch": 5.0818665575112565, "percentage": 15.53, "elapsed_time": "0:42:49", "remaining_time": "3:53:02", "throughput": 787.09, "total_tokens": 2022640} {"current_steps": 6215, "total_steps": 40000, "loss": 0.2226, "lr": 4.708126450602418e-05, "epoch": 5.08595988538682, "percentage": 15.54, "elapsed_time": "0:42:51", "remaining_time": "3:52:58", "throughput": 787.2, "total_tokens": 2024272} {"current_steps": 6220, "total_steps": 40000, "loss": 0.1687, "lr": 4.7076659375964495e-05, "epoch": 5.090053213262382, "percentage": 15.55, "elapsed_time": "0:42:53", "remaining_time": "3:52:54", "throughput": 787.34, "total_tokens": 2025984} {"current_steps": 6225, "total_steps": 40000, "loss": 0.1767, "lr": 4.707205084140651e-05, "epoch": 5.094146541137945, "percentage": 15.56, "elapsed_time": "0:42:54", "remaining_time": "3:52:50", "throughput": 787.44, "total_tokens": 2027616} {"current_steps": 6230, "total_steps": 40000, "loss": 0.172, "lr": 4.7067438903060904e-05, "epoch": 5.098239869013508, "percentage": 15.57, "elapsed_time": "0:42:56", "remaining_time": "3:52:46", "throughput": 787.56, "total_tokens": 2029264} {"current_steps": 6235, "total_steps": 40000, "loss": 0.2432, "lr": 4.70628235616389e-05, "epoch": 5.102333196889071, "percentage": 15.59, "elapsed_time": "0:42:58", "remaining_time": "3:52:42", "throughput": 787.66, "total_tokens": 2030880} {"current_steps": 6240, "total_steps": 40000, "loss": 0.201, "lr": 4.7058204817852256e-05, "epoch": 5.106426524764633, "percentage": 15.6, "elapsed_time": "0:43:00", "remaining_time": "3:52:39", "throughput": 787.74, "total_tokens": 2032464} {"current_steps": 6245, "total_steps": 40000, "loss": 0.2195, "lr": 4.705358267241322e-05, "epoch": 5.110519852640197, "percentage": 15.61, "elapsed_time": "0:43:01", "remaining_time": "3:52:35", "throughput": 787.86, "total_tokens": 2034128} {"current_steps": 6250, "total_steps": 40000, "loss": 0.2318, "lr": 4.704895712603459e-05, "epoch": 5.114613180515759, "percentage": 15.62, "elapsed_time": "0:43:03", "remaining_time": "3:52:31", "throughput": 787.94, "total_tokens": 2035680} {"current_steps": 6255, "total_steps": 40000, "loss": 0.1981, "lr": 4.704432817942969e-05, "epoch": 5.118706508391322, "percentage": 15.64, "elapsed_time": "0:43:05", "remaining_time": "3:52:27", "throughput": 788.08, "total_tokens": 2037392} {"current_steps": 6260, "total_steps": 40000, "loss": 0.2348, "lr": 4.703969583331236e-05, "epoch": 5.122799836266885, "percentage": 15.65, "elapsed_time": "0:43:06", "remaining_time": "3:52:23", "throughput": 788.18, "total_tokens": 2039008} {"current_steps": 6265, "total_steps": 40000, "loss": 0.2082, "lr": 4.7035060088396965e-05, "epoch": 5.126893164142448, "percentage": 15.66, "elapsed_time": "0:43:08", "remaining_time": "3:52:19", "throughput": 788.3, "total_tokens": 2040672} {"current_steps": 6270, "total_steps": 40000, "loss": 0.162, "lr": 4.703042094539839e-05, "epoch": 5.13098649201801, "percentage": 15.68, "elapsed_time": "0:43:10", "remaining_time": "3:52:15", "throughput": 788.4, "total_tokens": 2042288} {"current_steps": 6275, "total_steps": 40000, "loss": 0.2358, "lr": 4.702577840503206e-05, "epoch": 5.135079819893574, "percentage": 15.69, "elapsed_time": "0:43:12", "remaining_time": "3:52:11", "throughput": 788.51, "total_tokens": 2043920} {"current_steps": 6280, "total_steps": 40000, "loss": 0.1998, "lr": 4.70211324680139e-05, "epoch": 5.139173147769136, "percentage": 15.7, "elapsed_time": "0:43:13", "remaining_time": "3:52:07", "throughput": 788.65, "total_tokens": 2045632} {"current_steps": 6285, "total_steps": 40000, "loss": 0.2169, "lr": 4.7016483135060386e-05, "epoch": 5.143266475644699, "percentage": 15.71, "elapsed_time": "0:43:15", "remaining_time": "3:52:03", "throughput": 788.75, "total_tokens": 2047264} {"current_steps": 6290, "total_steps": 40000, "loss": 0.1995, "lr": 4.701183040688849e-05, "epoch": 5.147359803520262, "percentage": 15.72, "elapsed_time": "0:43:17", "remaining_time": "3:51:59", "throughput": 788.86, "total_tokens": 2048896} {"current_steps": 6295, "total_steps": 40000, "loss": 0.1962, "lr": 4.700717428421573e-05, "epoch": 5.151453131395825, "percentage": 15.74, "elapsed_time": "0:43:19", "remaining_time": "3:51:55", "throughput": 788.97, "total_tokens": 2050544} {"current_steps": 6300, "total_steps": 40000, "loss": 0.1998, "lr": 4.700251476776014e-05, "epoch": 5.155546459271387, "percentage": 15.75, "elapsed_time": "0:43:20", "remaining_time": "3:51:51", "throughput": 789.08, "total_tokens": 2052192} {"current_steps": 6305, "total_steps": 40000, "loss": 0.1943, "lr": 4.699785185824026e-05, "epoch": 5.159639787146951, "percentage": 15.76, "elapsed_time": "0:43:22", "remaining_time": "3:51:47", "throughput": 789.19, "total_tokens": 2053824} {"current_steps": 6310, "total_steps": 40000, "loss": 0.202, "lr": 4.699318555637519e-05, "epoch": 5.163733115022513, "percentage": 15.78, "elapsed_time": "0:43:24", "remaining_time": "3:51:44", "throughput": 789.28, "total_tokens": 2055424} {"current_steps": 6315, "total_steps": 40000, "loss": 0.1825, "lr": 4.6988515862884525e-05, "epoch": 5.167826442898076, "percentage": 15.79, "elapsed_time": "0:43:25", "remaining_time": "3:51:40", "throughput": 789.37, "total_tokens": 2057008} {"current_steps": 6320, "total_steps": 40000, "loss": 0.1835, "lr": 4.698384277848838e-05, "epoch": 5.171919770773639, "percentage": 15.8, "elapsed_time": "0:43:27", "remaining_time": "3:51:36", "throughput": 789.48, "total_tokens": 2058640} {"current_steps": 6325, "total_steps": 40000, "loss": 0.22, "lr": 4.6979166303907425e-05, "epoch": 5.176013098649202, "percentage": 15.81, "elapsed_time": "0:43:29", "remaining_time": "3:51:32", "throughput": 789.6, "total_tokens": 2060304} {"current_steps": 6330, "total_steps": 40000, "loss": 0.2805, "lr": 4.697448643986281e-05, "epoch": 5.180106426524764, "percentage": 15.82, "elapsed_time": "0:43:31", "remaining_time": "3:51:28", "throughput": 789.7, "total_tokens": 2061936} {"current_steps": 6335, "total_steps": 40000, "loss": 0.2061, "lr": 4.696980318707624e-05, "epoch": 5.1841997544003275, "percentage": 15.84, "elapsed_time": "0:43:32", "remaining_time": "3:51:24", "throughput": 789.8, "total_tokens": 2063552} {"current_steps": 6340, "total_steps": 40000, "loss": 0.2363, "lr": 4.6965116546269924e-05, "epoch": 5.18829308227589, "percentage": 15.85, "elapsed_time": "0:43:34", "remaining_time": "3:51:20", "throughput": 789.9, "total_tokens": 2065168} {"current_steps": 6345, "total_steps": 40000, "loss": 0.161, "lr": 4.6960426518166615e-05, "epoch": 5.192386410151453, "percentage": 15.86, "elapsed_time": "0:43:36", "remaining_time": "3:51:16", "throughput": 790.0, "total_tokens": 2066800} {"current_steps": 6350, "total_steps": 40000, "loss": 0.1708, "lr": 4.6955733103489556e-05, "epoch": 5.196479738027016, "percentage": 15.88, "elapsed_time": "0:43:37", "remaining_time": "3:51:12", "throughput": 790.1, "total_tokens": 2068400} {"current_steps": 6355, "total_steps": 40000, "loss": 0.2104, "lr": 4.695103630296255e-05, "epoch": 5.200573065902579, "percentage": 15.89, "elapsed_time": "0:43:39", "remaining_time": "3:51:08", "throughput": 790.21, "total_tokens": 2070048} {"current_steps": 6360, "total_steps": 40000, "loss": 0.1951, "lr": 4.694633611730988e-05, "epoch": 5.204666393778141, "percentage": 15.9, "elapsed_time": "0:43:41", "remaining_time": "3:51:05", "throughput": 790.33, "total_tokens": 2071728} {"current_steps": 6365, "total_steps": 40000, "loss": 0.1835, "lr": 4.694163254725639e-05, "epoch": 5.2087597216537045, "percentage": 15.91, "elapsed_time": "0:43:43", "remaining_time": "3:51:01", "throughput": 790.43, "total_tokens": 2073344} {"current_steps": 6370, "total_steps": 40000, "loss": 0.1864, "lr": 4.693692559352743e-05, "epoch": 5.212853049529267, "percentage": 15.93, "elapsed_time": "0:43:44", "remaining_time": "3:50:57", "throughput": 790.53, "total_tokens": 2074976} {"current_steps": 6375, "total_steps": 40000, "loss": 0.1865, "lr": 4.693221525684886e-05, "epoch": 5.21694637740483, "percentage": 15.94, "elapsed_time": "0:43:46", "remaining_time": "3:50:53", "throughput": 790.65, "total_tokens": 2076640} {"current_steps": 6380, "total_steps": 40000, "loss": 0.2023, "lr": 4.6927501537947084e-05, "epoch": 5.221039705280393, "percentage": 15.95, "elapsed_time": "0:43:48", "remaining_time": "3:50:49", "throughput": 790.73, "total_tokens": 2078224} {"current_steps": 6385, "total_steps": 40000, "loss": 0.1848, "lr": 4.692278443754901e-05, "epoch": 5.225133033155956, "percentage": 15.96, "elapsed_time": "0:43:49", "remaining_time": "3:50:45", "throughput": 790.83, "total_tokens": 2079824} {"current_steps": 6390, "total_steps": 40000, "loss": 0.2017, "lr": 4.691806395638208e-05, "epoch": 5.229226361031519, "percentage": 15.97, "elapsed_time": "0:43:51", "remaining_time": "3:50:41", "throughput": 790.94, "total_tokens": 2081488} {"current_steps": 6395, "total_steps": 40000, "loss": 0.2374, "lr": 4.6913340095174255e-05, "epoch": 5.233319688907081, "percentage": 15.99, "elapsed_time": "0:43:53", "remaining_time": "3:50:38", "throughput": 791.03, "total_tokens": 2083088} {"current_steps": 6400, "total_steps": 40000, "loss": 0.1902, "lr": 4.690861285465399e-05, "epoch": 5.237413016782645, "percentage": 16.0, "elapsed_time": "0:43:55", "remaining_time": "3:50:34", "throughput": 791.18, "total_tokens": 2084816} {"current_steps": 6400, "total_steps": 40000, "eval_loss": 0.20966507494449615, "epoch": 5.237413016782645, "percentage": 16.0, "elapsed_time": "0:44:07", "remaining_time": "3:51:39", "throughput": 787.44, "total_tokens": 2084816} {"current_steps": 6405, "total_steps": 40000, "loss": 0.1847, "lr": 4.690388223555031e-05, "epoch": 5.241506344658207, "percentage": 16.01, "elapsed_time": "0:44:10", "remaining_time": "3:51:43", "throughput": 787.12, "total_tokens": 2086464} {"current_steps": 6410, "total_steps": 40000, "loss": 0.2233, "lr": 4.689914823859273e-05, "epoch": 5.24559967253377, "percentage": 16.02, "elapsed_time": "0:44:12", "remaining_time": "3:51:39", "throughput": 787.21, "total_tokens": 2088048} {"current_steps": 6415, "total_steps": 40000, "loss": 0.2107, "lr": 4.689441086451129e-05, "epoch": 5.249693000409333, "percentage": 16.04, "elapsed_time": "0:44:14", "remaining_time": "3:51:35", "throughput": 787.33, "total_tokens": 2089728} {"current_steps": 6420, "total_steps": 40000, "loss": 0.1522, "lr": 4.688967011403655e-05, "epoch": 5.253786328284896, "percentage": 16.05, "elapsed_time": "0:44:15", "remaining_time": "3:51:31", "throughput": 787.42, "total_tokens": 2091312} {"current_steps": 6425, "total_steps": 40000, "loss": 0.1983, "lr": 4.68849259878996e-05, "epoch": 5.257879656160458, "percentage": 16.06, "elapsed_time": "0:44:17", "remaining_time": "3:51:27", "throughput": 787.5, "total_tokens": 2092880} {"current_steps": 6430, "total_steps": 40000, "loss": 0.1895, "lr": 4.6880178486832036e-05, "epoch": 5.261972984036022, "percentage": 16.07, "elapsed_time": "0:44:19", "remaining_time": "3:51:24", "throughput": 787.58, "total_tokens": 2094448} {"current_steps": 6435, "total_steps": 40000, "loss": 0.204, "lr": 4.687542761156598e-05, "epoch": 5.266066311911584, "percentage": 16.09, "elapsed_time": "0:44:21", "remaining_time": "3:51:20", "throughput": 787.7, "total_tokens": 2096112} {"current_steps": 6440, "total_steps": 40000, "loss": 0.2298, "lr": 4.6870673362834096e-05, "epoch": 5.270159639787147, "percentage": 16.1, "elapsed_time": "0:44:22", "remaining_time": "3:51:16", "throughput": 787.8, "total_tokens": 2097728} {"current_steps": 6445, "total_steps": 40000, "loss": 0.1542, "lr": 4.6865915741369526e-05, "epoch": 5.27425296766271, "percentage": 16.11, "elapsed_time": "0:44:24", "remaining_time": "3:51:12", "throughput": 787.9, "total_tokens": 2099344} {"current_steps": 6450, "total_steps": 40000, "loss": 0.1579, "lr": 4.686115474790597e-05, "epoch": 5.278346295538273, "percentage": 16.12, "elapsed_time": "0:44:26", "remaining_time": "3:51:08", "throughput": 787.99, "total_tokens": 2100944} {"current_steps": 6455, "total_steps": 40000, "loss": 0.172, "lr": 4.685639038317762e-05, "epoch": 5.282439623413835, "percentage": 16.14, "elapsed_time": "0:44:27", "remaining_time": "3:51:04", "throughput": 788.06, "total_tokens": 2102480} {"current_steps": 6460, "total_steps": 40000, "loss": 0.1509, "lr": 4.685162264791921e-05, "epoch": 5.286532951289399, "percentage": 16.15, "elapsed_time": "0:44:29", "remaining_time": "3:51:00", "throughput": 788.16, "total_tokens": 2104112} {"current_steps": 6465, "total_steps": 40000, "loss": 0.2365, "lr": 4.684685154286599e-05, "epoch": 5.290626279164961, "percentage": 16.16, "elapsed_time": "0:44:31", "remaining_time": "3:50:56", "throughput": 788.31, "total_tokens": 2105872} {"current_steps": 6470, "total_steps": 40000, "loss": 0.1696, "lr": 4.684207706875371e-05, "epoch": 5.294719607040524, "percentage": 16.18, "elapsed_time": "0:44:33", "remaining_time": "3:50:52", "throughput": 788.42, "total_tokens": 2107520} {"current_steps": 6475, "total_steps": 40000, "loss": 0.2, "lr": 4.683729922631866e-05, "epoch": 5.298812934916087, "percentage": 16.19, "elapsed_time": "0:44:34", "remaining_time": "3:50:49", "throughput": 788.53, "total_tokens": 2109152} {"current_steps": 6480, "total_steps": 40000, "loss": 0.22, "lr": 4.683251801629765e-05, "epoch": 5.30290626279165, "percentage": 16.2, "elapsed_time": "0:44:36", "remaining_time": "3:50:45", "throughput": 788.62, "total_tokens": 2110768} {"current_steps": 6485, "total_steps": 40000, "loss": 0.1932, "lr": 4.6827733439428e-05, "epoch": 5.306999590667212, "percentage": 16.21, "elapsed_time": "0:44:38", "remaining_time": "3:50:41", "throughput": 788.71, "total_tokens": 2112352} {"current_steps": 6490, "total_steps": 40000, "loss": 0.2066, "lr": 4.682294549644754e-05, "epoch": 5.3110929185427755, "percentage": 16.23, "elapsed_time": "0:44:39", "remaining_time": "3:50:37", "throughput": 788.83, "total_tokens": 2114016} {"current_steps": 6495, "total_steps": 40000, "loss": 0.1795, "lr": 4.681815418809464e-05, "epoch": 5.315186246418338, "percentage": 16.24, "elapsed_time": "0:44:41", "remaining_time": "3:50:33", "throughput": 788.92, "total_tokens": 2115616} {"current_steps": 6500, "total_steps": 40000, "loss": 0.1393, "lr": 4.681335951510819e-05, "epoch": 5.319279574293901, "percentage": 16.25, "elapsed_time": "0:44:43", "remaining_time": "3:50:29", "throughput": 789.06, "total_tokens": 2117360} {"current_steps": 6505, "total_steps": 40000, "loss": 0.1801, "lr": 4.6808561478227576e-05, "epoch": 5.323372902169464, "percentage": 16.26, "elapsed_time": "0:44:45", "remaining_time": "3:50:25", "throughput": 789.15, "total_tokens": 2118944} {"current_steps": 6510, "total_steps": 40000, "loss": 0.1557, "lr": 4.680376007819271e-05, "epoch": 5.327466230045027, "percentage": 16.28, "elapsed_time": "0:44:46", "remaining_time": "3:50:22", "throughput": 789.22, "total_tokens": 2120480} {"current_steps": 6515, "total_steps": 40000, "loss": 0.1845, "lr": 4.679895531574405e-05, "epoch": 5.331559557920589, "percentage": 16.29, "elapsed_time": "0:44:48", "remaining_time": "3:50:18", "throughput": 789.34, "total_tokens": 2122160} {"current_steps": 6520, "total_steps": 40000, "loss": 0.1842, "lr": 4.679414719162253e-05, "epoch": 5.3356528857961525, "percentage": 16.3, "elapsed_time": "0:44:50", "remaining_time": "3:50:14", "throughput": 789.42, "total_tokens": 2123728} {"current_steps": 6525, "total_steps": 40000, "loss": 0.2091, "lr": 4.6789335706569635e-05, "epoch": 5.339746213671715, "percentage": 16.31, "elapsed_time": "0:44:51", "remaining_time": "3:50:10", "throughput": 789.5, "total_tokens": 2125312} {"current_steps": 6530, "total_steps": 40000, "loss": 0.2159, "lr": 4.678452086132734e-05, "epoch": 5.343839541547278, "percentage": 16.32, "elapsed_time": "0:44:53", "remaining_time": "3:50:06", "throughput": 789.62, "total_tokens": 2126976} {"current_steps": 6535, "total_steps": 40000, "loss": 0.1745, "lr": 4.677970265663818e-05, "epoch": 5.3479328694228405, "percentage": 16.34, "elapsed_time": "0:44:55", "remaining_time": "3:50:02", "throughput": 789.71, "total_tokens": 2128576} {"current_steps": 6540, "total_steps": 40000, "loss": 0.1796, "lr": 4.677488109324517e-05, "epoch": 5.352026197298404, "percentage": 16.35, "elapsed_time": "0:44:57", "remaining_time": "3:49:59", "throughput": 789.79, "total_tokens": 2130160} {"current_steps": 6545, "total_steps": 40000, "loss": 0.2119, "lr": 4.6770056171891846e-05, "epoch": 5.356119525173966, "percentage": 16.36, "elapsed_time": "0:44:58", "remaining_time": "3:49:55", "throughput": 789.9, "total_tokens": 2131808} {"current_steps": 6550, "total_steps": 40000, "loss": 0.2122, "lr": 4.6765227893322286e-05, "epoch": 5.360212853049529, "percentage": 16.38, "elapsed_time": "0:45:00", "remaining_time": "3:49:51", "throughput": 790.0, "total_tokens": 2133440} {"current_steps": 6555, "total_steps": 40000, "loss": 0.1793, "lr": 4.676039625828107e-05, "epoch": 5.364306180925092, "percentage": 16.39, "elapsed_time": "0:45:02", "remaining_time": "3:49:47", "throughput": 790.08, "total_tokens": 2135008} {"current_steps": 6560, "total_steps": 40000, "loss": 0.2426, "lr": 4.675556126751328e-05, "epoch": 5.368399508800655, "percentage": 16.4, "elapsed_time": "0:45:03", "remaining_time": "3:49:43", "throughput": 790.15, "total_tokens": 2136576} {"current_steps": 6565, "total_steps": 40000, "loss": 0.232, "lr": 4.6750722921764556e-05, "epoch": 5.3724928366762175, "percentage": 16.41, "elapsed_time": "0:45:05", "remaining_time": "3:49:40", "throughput": 790.24, "total_tokens": 2138176} {"current_steps": 6570, "total_steps": 40000, "loss": 0.2457, "lr": 4.674588122178102e-05, "epoch": 5.376586164551781, "percentage": 16.43, "elapsed_time": "0:45:07", "remaining_time": "3:49:36", "throughput": 790.34, "total_tokens": 2139792} {"current_steps": 6575, "total_steps": 40000, "loss": 0.1729, "lr": 4.674103616830931e-05, "epoch": 5.380679492427343, "percentage": 16.44, "elapsed_time": "0:45:09", "remaining_time": "3:49:32", "throughput": 790.45, "total_tokens": 2141440} {"current_steps": 6580, "total_steps": 40000, "loss": 0.1992, "lr": 4.673618776209663e-05, "epoch": 5.384772820302906, "percentage": 16.45, "elapsed_time": "0:45:10", "remaining_time": "3:49:28", "throughput": 790.56, "total_tokens": 2143104} {"current_steps": 6585, "total_steps": 40000, "loss": 0.1831, "lr": 4.673133600389063e-05, "epoch": 5.388866148178469, "percentage": 16.46, "elapsed_time": "0:45:12", "remaining_time": "3:49:24", "throughput": 790.68, "total_tokens": 2144784} {"current_steps": 6590, "total_steps": 40000, "loss": 0.1812, "lr": 4.672648089443953e-05, "epoch": 5.392959476054032, "percentage": 16.48, "elapsed_time": "0:45:14", "remaining_time": "3:49:20", "throughput": 790.76, "total_tokens": 2146368} {"current_steps": 6595, "total_steps": 40000, "loss": 0.2145, "lr": 4.672162243449204e-05, "epoch": 5.397052803929594, "percentage": 16.49, "elapsed_time": "0:45:16", "remaining_time": "3:49:17", "throughput": 790.87, "total_tokens": 2148016} {"current_steps": 6600, "total_steps": 40000, "loss": 0.2089, "lr": 4.67167606247974e-05, "epoch": 5.401146131805158, "percentage": 16.5, "elapsed_time": "0:45:17", "remaining_time": "3:49:13", "throughput": 790.96, "total_tokens": 2149632} {"current_steps": 6600, "total_steps": 40000, "eval_loss": 0.2084534615278244, "epoch": 5.401146131805158, "percentage": 16.5, "elapsed_time": "0:45:30", "remaining_time": "3:50:16", "throughput": 787.35, "total_tokens": 2149632} {"current_steps": 6605, "total_steps": 40000, "loss": 0.1928, "lr": 4.671189546610536e-05, "epoch": 5.40523945968072, "percentage": 16.51, "elapsed_time": "0:45:33", "remaining_time": "3:50:22", "throughput": 786.93, "total_tokens": 2151312} {"current_steps": 6610, "total_steps": 40000, "loss": 0.16, "lr": 4.67070269591662e-05, "epoch": 5.409332787556283, "percentage": 16.53, "elapsed_time": "0:45:35", "remaining_time": "3:50:18", "throughput": 787.03, "total_tokens": 2152928} {"current_steps": 6615, "total_steps": 40000, "loss": 0.1805, "lr": 4.670215510473068e-05, "epoch": 5.413426115431846, "percentage": 16.54, "elapsed_time": "0:45:37", "remaining_time": "3:50:14", "throughput": 787.14, "total_tokens": 2154560} {"current_steps": 6620, "total_steps": 40000, "loss": 0.2759, "lr": 4.669727990355013e-05, "epoch": 5.417519443307409, "percentage": 16.55, "elapsed_time": "0:45:38", "remaining_time": "3:50:10", "throughput": 787.23, "total_tokens": 2156176} {"current_steps": 6625, "total_steps": 40000, "loss": 0.2426, "lr": 4.669240135637635e-05, "epoch": 5.421612771182971, "percentage": 16.56, "elapsed_time": "0:45:40", "remaining_time": "3:50:06", "throughput": 787.36, "total_tokens": 2157872} {"current_steps": 6630, "total_steps": 40000, "loss": 0.2442, "lr": 4.6687519463961675e-05, "epoch": 5.425706099058535, "percentage": 16.57, "elapsed_time": "0:45:42", "remaining_time": "3:50:02", "throughput": 787.42, "total_tokens": 2159392} {"current_steps": 6635, "total_steps": 40000, "loss": 0.1838, "lr": 4.668263422705896e-05, "epoch": 5.429799426934097, "percentage": 16.59, "elapsed_time": "0:45:44", "remaining_time": "3:49:58", "throughput": 787.52, "total_tokens": 2161008} {"current_steps": 6640, "total_steps": 40000, "loss": 0.1871, "lr": 4.667774564642156e-05, "epoch": 5.43389275480966, "percentage": 16.6, "elapsed_time": "0:45:45", "remaining_time": "3:49:55", "throughput": 787.62, "total_tokens": 2162656} {"current_steps": 6645, "total_steps": 40000, "loss": 0.2565, "lr": 4.6672853722803365e-05, "epoch": 5.437986082685223, "percentage": 16.61, "elapsed_time": "0:45:47", "remaining_time": "3:49:51", "throughput": 787.7, "total_tokens": 2164224} {"current_steps": 6650, "total_steps": 40000, "loss": 0.2063, "lr": 4.666795845695877e-05, "epoch": 5.442079410560786, "percentage": 16.62, "elapsed_time": "0:45:49", "remaining_time": "3:49:47", "throughput": 787.79, "total_tokens": 2165824} {"current_steps": 6655, "total_steps": 40000, "loss": 0.1966, "lr": 4.666305984964269e-05, "epoch": 5.446172738436349, "percentage": 16.64, "elapsed_time": "0:45:50", "remaining_time": "3:49:43", "throughput": 787.9, "total_tokens": 2167472} {"current_steps": 6660, "total_steps": 40000, "loss": 0.1894, "lr": 4.6658157901610535e-05, "epoch": 5.450266066311912, "percentage": 16.65, "elapsed_time": "0:45:52", "remaining_time": "3:49:39", "throughput": 787.99, "total_tokens": 2169072} {"current_steps": 6665, "total_steps": 40000, "loss": 0.2305, "lr": 4.665325261361826e-05, "epoch": 5.454359394187474, "percentage": 16.66, "elapsed_time": "0:45:54", "remaining_time": "3:49:36", "throughput": 788.1, "total_tokens": 2170720} {"current_steps": 6670, "total_steps": 40000, "loss": 0.1953, "lr": 4.664834398642232e-05, "epoch": 5.458452722063037, "percentage": 16.68, "elapsed_time": "0:45:56", "remaining_time": "3:49:32", "throughput": 788.21, "total_tokens": 2172368} {"current_steps": 6675, "total_steps": 40000, "loss": 0.223, "lr": 4.6643432020779686e-05, "epoch": 5.4625460499386005, "percentage": 16.69, "elapsed_time": "0:45:57", "remaining_time": "3:49:28", "throughput": 788.29, "total_tokens": 2173936} {"current_steps": 6680, "total_steps": 40000, "loss": 0.2806, "lr": 4.663851671744786e-05, "epoch": 5.466639377814163, "percentage": 16.7, "elapsed_time": "0:45:59", "remaining_time": "3:49:24", "throughput": 788.4, "total_tokens": 2175600} {"current_steps": 6685, "total_steps": 40000, "loss": 0.2056, "lr": 4.6633598077184815e-05, "epoch": 5.470732705689726, "percentage": 16.71, "elapsed_time": "0:46:01", "remaining_time": "3:49:20", "throughput": 788.52, "total_tokens": 2177296} {"current_steps": 6690, "total_steps": 40000, "loss": 0.2019, "lr": 4.662867610074908e-05, "epoch": 5.4748260335652885, "percentage": 16.73, "elapsed_time": "0:46:02", "remaining_time": "3:49:17", "throughput": 788.65, "total_tokens": 2179024} {"current_steps": 6695, "total_steps": 40000, "loss": 0.2112, "lr": 4.6623750788899696e-05, "epoch": 5.478919361440852, "percentage": 16.74, "elapsed_time": "0:46:04", "remaining_time": "3:49:13", "throughput": 788.75, "total_tokens": 2180640} {"current_steps": 6700, "total_steps": 40000, "loss": 0.2445, "lr": 4.6618822142396195e-05, "epoch": 5.483012689316414, "percentage": 16.75, "elapsed_time": "0:46:06", "remaining_time": "3:49:09", "throughput": 788.84, "total_tokens": 2182240} {"current_steps": 6705, "total_steps": 40000, "loss": 0.2086, "lr": 4.661389016199864e-05, "epoch": 5.487106017191977, "percentage": 16.76, "elapsed_time": "0:46:08", "remaining_time": "3:49:05", "throughput": 788.96, "total_tokens": 2183920} {"current_steps": 6710, "total_steps": 40000, "loss": 0.2097, "lr": 4.660895484846761e-05, "epoch": 5.49119934506754, "percentage": 16.78, "elapsed_time": "0:46:09", "remaining_time": "3:49:01", "throughput": 789.09, "total_tokens": 2185632} {"current_steps": 6715, "total_steps": 40000, "loss": 0.1887, "lr": 4.660401620256418e-05, "epoch": 5.495292672943103, "percentage": 16.79, "elapsed_time": "0:46:11", "remaining_time": "3:48:58", "throughput": 789.19, "total_tokens": 2187264} {"current_steps": 6720, "total_steps": 40000, "loss": 0.1746, "lr": 4.659907422504997e-05, "epoch": 5.4993860008186655, "percentage": 16.8, "elapsed_time": "0:46:13", "remaining_time": "3:48:54", "throughput": 789.3, "total_tokens": 2188928} {"current_steps": 6725, "total_steps": 40000, "loss": 0.2024, "lr": 4.6594128916687074e-05, "epoch": 5.503479328694229, "percentage": 16.81, "elapsed_time": "0:46:14", "remaining_time": "3:48:50", "throughput": 789.37, "total_tokens": 2190496} {"current_steps": 6730, "total_steps": 40000, "loss": 0.1864, "lr": 4.658918027823813e-05, "epoch": 5.507572656569791, "percentage": 16.83, "elapsed_time": "0:46:16", "remaining_time": "3:48:46", "throughput": 789.47, "total_tokens": 2192112} {"current_steps": 6735, "total_steps": 40000, "loss": 0.1624, "lr": 4.658422831046628e-05, "epoch": 5.511665984445354, "percentage": 16.84, "elapsed_time": "0:46:18", "remaining_time": "3:48:42", "throughput": 789.58, "total_tokens": 2193776} {"current_steps": 6740, "total_steps": 40000, "loss": 0.1472, "lr": 4.657927301413518e-05, "epoch": 5.515759312320917, "percentage": 16.85, "elapsed_time": "0:46:20", "remaining_time": "3:48:39", "throughput": 789.66, "total_tokens": 2195376} {"current_steps": 6745, "total_steps": 40000, "loss": 0.1462, "lr": 4.657431439000901e-05, "epoch": 5.51985264019648, "percentage": 16.86, "elapsed_time": "0:46:21", "remaining_time": "3:48:35", "throughput": 789.75, "total_tokens": 2196976} {"current_steps": 6750, "total_steps": 40000, "loss": 0.2651, "lr": 4.656935243885243e-05, "epoch": 5.523945968072042, "percentage": 16.88, "elapsed_time": "0:46:23", "remaining_time": "3:48:31", "throughput": 789.88, "total_tokens": 2198704} {"current_steps": 6755, "total_steps": 40000, "loss": 0.2003, "lr": 4.656438716143066e-05, "epoch": 5.528039295947606, "percentage": 16.89, "elapsed_time": "0:46:25", "remaining_time": "3:48:27", "throughput": 789.97, "total_tokens": 2200304} {"current_steps": 6760, "total_steps": 40000, "loss": 0.2337, "lr": 4.6559418558509384e-05, "epoch": 5.532132623823168, "percentage": 16.9, "elapsed_time": "0:46:27", "remaining_time": "3:48:24", "throughput": 790.07, "total_tokens": 2201936} {"current_steps": 6765, "total_steps": 40000, "loss": 0.2028, "lr": 4.6554446630854833e-05, "epoch": 5.536225951698731, "percentage": 16.91, "elapsed_time": "0:46:28", "remaining_time": "3:48:20", "throughput": 790.16, "total_tokens": 2203552} {"current_steps": 6770, "total_steps": 40000, "loss": 0.1703, "lr": 4.654947137923374e-05, "epoch": 5.540319279574294, "percentage": 16.93, "elapsed_time": "0:46:30", "remaining_time": "3:48:16", "throughput": 790.26, "total_tokens": 2205200} {"current_steps": 6775, "total_steps": 40000, "loss": 0.2107, "lr": 4.654449280441335e-05, "epoch": 5.544412607449857, "percentage": 16.94, "elapsed_time": "0:46:32", "remaining_time": "3:48:13", "throughput": 790.35, "total_tokens": 2206800} {"current_steps": 6780, "total_steps": 40000, "loss": 0.165, "lr": 4.653951090716143e-05, "epoch": 5.548505935325419, "percentage": 16.95, "elapsed_time": "0:46:33", "remaining_time": "3:48:09", "throughput": 790.44, "total_tokens": 2208416} {"current_steps": 6785, "total_steps": 40000, "loss": 0.2314, "lr": 4.653452568824625e-05, "epoch": 5.552599263200983, "percentage": 16.96, "elapsed_time": "0:46:35", "remaining_time": "3:48:05", "throughput": 790.54, "total_tokens": 2210032} {"current_steps": 6790, "total_steps": 40000, "loss": 0.1924, "lr": 4.6529537148436585e-05, "epoch": 5.556692591076545, "percentage": 16.98, "elapsed_time": "0:46:37", "remaining_time": "3:48:01", "throughput": 790.61, "total_tokens": 2211600} {"current_steps": 6795, "total_steps": 40000, "loss": 0.2258, "lr": 4.6524545288501734e-05, "epoch": 5.560785918952108, "percentage": 16.99, "elapsed_time": "0:46:39", "remaining_time": "3:47:57", "throughput": 790.72, "total_tokens": 2213264} {"current_steps": 6800, "total_steps": 40000, "loss": 0.2047, "lr": 4.6519550109211506e-05, "epoch": 5.564879246827671, "percentage": 17.0, "elapsed_time": "0:46:40", "remaining_time": "3:47:54", "throughput": 790.81, "total_tokens": 2214864} {"current_steps": 6800, "total_steps": 40000, "eval_loss": 0.205253005027771, "epoch": 5.564879246827671, "percentage": 17.0, "elapsed_time": "0:46:53", "remaining_time": "3:48:55", "throughput": 787.31, "total_tokens": 2214864} {"current_steps": 6805, "total_steps": 40000, "loss": 0.2407, "lr": 4.651455161133622e-05, "epoch": 5.568972574703234, "percentage": 17.01, "elapsed_time": "0:46:56", "remaining_time": "3:48:58", "throughput": 787.01, "total_tokens": 2216496} {"current_steps": 6810, "total_steps": 40000, "loss": 0.2045, "lr": 4.6509549795646704e-05, "epoch": 5.573065902578796, "percentage": 17.03, "elapsed_time": "0:46:58", "remaining_time": "3:48:54", "throughput": 787.14, "total_tokens": 2218208} {"current_steps": 6815, "total_steps": 40000, "loss": 0.1931, "lr": 4.6504544662914306e-05, "epoch": 5.57715923045436, "percentage": 17.04, "elapsed_time": "0:46:59", "remaining_time": "3:48:50", "throughput": 787.26, "total_tokens": 2219888} {"current_steps": 6820, "total_steps": 40000, "loss": 0.2167, "lr": 4.6499536213910876e-05, "epoch": 5.581252558329922, "percentage": 17.05, "elapsed_time": "0:47:01", "remaining_time": "3:48:46", "throughput": 787.4, "total_tokens": 2221664} {"current_steps": 6825, "total_steps": 40000, "loss": 0.2294, "lr": 4.6494524449408786e-05, "epoch": 5.585345886205485, "percentage": 17.06, "elapsed_time": "0:47:03", "remaining_time": "3:48:43", "throughput": 787.5, "total_tokens": 2223280} {"current_steps": 6830, "total_steps": 40000, "loss": 0.155, "lr": 4.6489509370180903e-05, "epoch": 5.589439214081048, "percentage": 17.08, "elapsed_time": "0:47:04", "remaining_time": "3:48:39", "throughput": 787.6, "total_tokens": 2224928} {"current_steps": 6835, "total_steps": 40000, "loss": 0.1752, "lr": 4.648449097700063e-05, "epoch": 5.593532541956611, "percentage": 17.09, "elapsed_time": "0:47:06", "remaining_time": "3:48:35", "throughput": 787.75, "total_tokens": 2226704} {"current_steps": 6840, "total_steps": 40000, "loss": 0.235, "lr": 4.647946927064185e-05, "epoch": 5.597625869832173, "percentage": 17.1, "elapsed_time": "0:47:08", "remaining_time": "3:48:31", "throughput": 787.85, "total_tokens": 2228320} {"current_steps": 6845, "total_steps": 40000, "loss": 0.231, "lr": 4.647444425187898e-05, "epoch": 5.6017191977077365, "percentage": 17.11, "elapsed_time": "0:47:10", "remaining_time": "3:48:27", "throughput": 787.95, "total_tokens": 2229952} {"current_steps": 6850, "total_steps": 40000, "loss": 0.1955, "lr": 4.646941592148695e-05, "epoch": 5.605812525583299, "percentage": 17.12, "elapsed_time": "0:47:11", "remaining_time": "3:48:24", "throughput": 788.05, "total_tokens": 2231600} {"current_steps": 6855, "total_steps": 40000, "loss": 0.1922, "lr": 4.646438428024117e-05, "epoch": 5.609905853458862, "percentage": 17.14, "elapsed_time": "0:47:13", "remaining_time": "3:48:20", "throughput": 788.13, "total_tokens": 2233184} {"current_steps": 6860, "total_steps": 40000, "loss": 0.2102, "lr": 4.64593493289176e-05, "epoch": 5.6139991813344245, "percentage": 17.15, "elapsed_time": "0:47:15", "remaining_time": "3:48:16", "throughput": 788.22, "total_tokens": 2234800} {"current_steps": 6865, "total_steps": 40000, "loss": 0.1802, "lr": 4.64543110682927e-05, "epoch": 5.618092509209988, "percentage": 17.16, "elapsed_time": "0:47:16", "remaining_time": "3:48:12", "throughput": 788.31, "total_tokens": 2236400} {"current_steps": 6870, "total_steps": 40000, "loss": 0.1421, "lr": 4.644926949914341e-05, "epoch": 5.62218583708555, "percentage": 17.18, "elapsed_time": "0:47:18", "remaining_time": "3:48:09", "throughput": 788.38, "total_tokens": 2237952} {"current_steps": 6875, "total_steps": 40000, "loss": 0.1736, "lr": 4.644422462224722e-05, "epoch": 5.6262791649611135, "percentage": 17.19, "elapsed_time": "0:47:20", "remaining_time": "3:48:05", "throughput": 788.51, "total_tokens": 2239680} {"current_steps": 6880, "total_steps": 40000, "loss": 0.2799, "lr": 4.643917643838211e-05, "epoch": 5.630372492836676, "percentage": 17.2, "elapsed_time": "0:47:22", "remaining_time": "3:48:01", "throughput": 788.61, "total_tokens": 2241296} {"current_steps": 6885, "total_steps": 40000, "loss": 0.2132, "lr": 4.6434124948326564e-05, "epoch": 5.634465820712239, "percentage": 17.21, "elapsed_time": "0:47:23", "remaining_time": "3:47:57", "throughput": 788.71, "total_tokens": 2242944} {"current_steps": 6890, "total_steps": 40000, "loss": 0.1712, "lr": 4.6429070152859594e-05, "epoch": 5.6385591485878015, "percentage": 17.22, "elapsed_time": "0:47:25", "remaining_time": "3:47:54", "throughput": 788.8, "total_tokens": 2244560} {"current_steps": 6895, "total_steps": 40000, "loss": 0.1699, "lr": 4.6424012052760714e-05, "epoch": 5.642652476463365, "percentage": 17.24, "elapsed_time": "0:47:27", "remaining_time": "3:47:50", "throughput": 788.91, "total_tokens": 2246224} {"current_steps": 6900, "total_steps": 40000, "loss": 0.2153, "lr": 4.6418950648809945e-05, "epoch": 5.646745804338927, "percentage": 17.25, "elapsed_time": "0:47:28", "remaining_time": "3:47:46", "throughput": 788.99, "total_tokens": 2247792} {"current_steps": 6905, "total_steps": 40000, "loss": 0.2205, "lr": 4.641388594178782e-05, "epoch": 5.65083913221449, "percentage": 17.26, "elapsed_time": "0:47:30", "remaining_time": "3:47:43", "throughput": 789.1, "total_tokens": 2249472} {"current_steps": 6910, "total_steps": 40000, "loss": 0.1719, "lr": 4.640881793247538e-05, "epoch": 5.654932460090054, "percentage": 17.27, "elapsed_time": "0:47:32", "remaining_time": "3:47:39", "throughput": 789.2, "total_tokens": 2251120} {"current_steps": 6915, "total_steps": 40000, "loss": 0.2183, "lr": 4.6403746621654173e-05, "epoch": 5.659025787965616, "percentage": 17.29, "elapsed_time": "0:47:34", "remaining_time": "3:47:35", "throughput": 789.28, "total_tokens": 2252688} {"current_steps": 6920, "total_steps": 40000, "loss": 0.207, "lr": 4.639867201010626e-05, "epoch": 5.663119115841178, "percentage": 17.3, "elapsed_time": "0:47:35", "remaining_time": "3:47:31", "throughput": 789.37, "total_tokens": 2254320} {"current_steps": 6925, "total_steps": 40000, "loss": 0.2406, "lr": 4.6393594098614204e-05, "epoch": 5.667212443716742, "percentage": 17.31, "elapsed_time": "0:47:37", "remaining_time": "3:47:28", "throughput": 789.48, "total_tokens": 2255984} {"current_steps": 6930, "total_steps": 40000, "loss": 0.2484, "lr": 4.63885128879611e-05, "epoch": 5.671305771592305, "percentage": 17.32, "elapsed_time": "0:47:39", "remaining_time": "3:47:24", "throughput": 789.58, "total_tokens": 2257616} {"current_steps": 6935, "total_steps": 40000, "loss": 0.2012, "lr": 4.638342837893052e-05, "epoch": 5.675399099467867, "percentage": 17.34, "elapsed_time": "0:47:40", "remaining_time": "3:47:20", "throughput": 789.66, "total_tokens": 2259216} {"current_steps": 6940, "total_steps": 40000, "loss": 0.1889, "lr": 4.6378340572306565e-05, "epoch": 5.67949242734343, "percentage": 17.35, "elapsed_time": "0:47:42", "remaining_time": "3:47:17", "throughput": 789.74, "total_tokens": 2260800} {"current_steps": 6945, "total_steps": 40000, "loss": 0.1927, "lr": 4.6373249468873833e-05, "epoch": 5.683585755218993, "percentage": 17.36, "elapsed_time": "0:47:44", "remaining_time": "3:47:13", "throughput": 789.84, "total_tokens": 2262448} {"current_steps": 6950, "total_steps": 40000, "loss": 0.2307, "lr": 4.636815506941744e-05, "epoch": 5.687679083094556, "percentage": 17.38, "elapsed_time": "0:47:46", "remaining_time": "3:47:09", "throughput": 789.93, "total_tokens": 2264064} {"current_steps": 6955, "total_steps": 40000, "loss": 0.1775, "lr": 4.6363057374723004e-05, "epoch": 5.691772410970119, "percentage": 17.39, "elapsed_time": "0:47:47", "remaining_time": "3:47:06", "throughput": 790.03, "total_tokens": 2265712} {"current_steps": 6960, "total_steps": 40000, "loss": 0.264, "lr": 4.635795638557666e-05, "epoch": 5.695865738845682, "percentage": 17.4, "elapsed_time": "0:47:49", "remaining_time": "3:47:02", "throughput": 790.13, "total_tokens": 2267344} {"current_steps": 6965, "total_steps": 40000, "loss": 0.2229, "lr": 4.635285210276504e-05, "epoch": 5.699959066721244, "percentage": 17.41, "elapsed_time": "0:47:51", "remaining_time": "3:46:58", "throughput": 790.24, "total_tokens": 2269008} {"current_steps": 6970, "total_steps": 40000, "loss": 0.3067, "lr": 4.6347744527075295e-05, "epoch": 5.704052394596808, "percentage": 17.42, "elapsed_time": "0:47:53", "remaining_time": "3:46:54", "throughput": 790.34, "total_tokens": 2270672} {"current_steps": 6975, "total_steps": 40000, "loss": 0.2378, "lr": 4.634263365929506e-05, "epoch": 5.70814572247237, "percentage": 17.44, "elapsed_time": "0:47:54", "remaining_time": "3:46:51", "throughput": 790.46, "total_tokens": 2272352} {"current_steps": 6980, "total_steps": 40000, "loss": 0.2545, "lr": 4.6337519500212515e-05, "epoch": 5.712239050347933, "percentage": 17.45, "elapsed_time": "0:47:56", "remaining_time": "3:46:47", "throughput": 790.56, "total_tokens": 2274000} {"current_steps": 6985, "total_steps": 40000, "loss": 0.2034, "lr": 4.633240205061632e-05, "epoch": 5.716332378223496, "percentage": 17.46, "elapsed_time": "0:47:58", "remaining_time": "3:46:43", "throughput": 790.65, "total_tokens": 2275616} {"current_steps": 6990, "total_steps": 40000, "loss": 0.2056, "lr": 4.632728131129565e-05, "epoch": 5.720425706099059, "percentage": 17.47, "elapsed_time": "0:47:59", "remaining_time": "3:46:40", "throughput": 790.72, "total_tokens": 2277184} {"current_steps": 6995, "total_steps": 40000, "loss": 0.2647, "lr": 4.632215728304018e-05, "epoch": 5.724519033974621, "percentage": 17.49, "elapsed_time": "0:48:01", "remaining_time": "3:46:36", "throughput": 790.81, "total_tokens": 2278784} {"current_steps": 7000, "total_steps": 40000, "loss": 0.228, "lr": 4.63170299666401e-05, "epoch": 5.7286123618501845, "percentage": 17.5, "elapsed_time": "0:48:03", "remaining_time": "3:46:32", "throughput": 790.88, "total_tokens": 2280368} {"current_steps": 7000, "total_steps": 40000, "eval_loss": 0.20489728450775146, "epoch": 5.7286123618501845, "percentage": 17.5, "elapsed_time": "0:48:15", "remaining_time": "3:47:31", "throughput": 787.49, "total_tokens": 2280368} {"current_steps": 7005, "total_steps": 40000, "loss": 0.2237, "lr": 4.631189936288612e-05, "epoch": 5.732705689725747, "percentage": 17.51, "elapsed_time": "0:48:18", "remaining_time": "3:47:34", "throughput": 787.18, "total_tokens": 2281952} {"current_steps": 7010, "total_steps": 40000, "loss": 0.2015, "lr": 4.630676547256944e-05, "epoch": 5.73679901760131, "percentage": 17.52, "elapsed_time": "0:48:20", "remaining_time": "3:47:30", "throughput": 787.27, "total_tokens": 2283552} {"current_steps": 7015, "total_steps": 40000, "loss": 0.2609, "lr": 4.630162829648176e-05, "epoch": 5.7408923454768725, "percentage": 17.54, "elapsed_time": "0:48:22", "remaining_time": "3:47:26", "throughput": 787.36, "total_tokens": 2285168} {"current_steps": 7020, "total_steps": 40000, "loss": 0.1915, "lr": 4.629648783541531e-05, "epoch": 5.744985673352436, "percentage": 17.55, "elapsed_time": "0:48:24", "remaining_time": "3:47:23", "throughput": 787.44, "total_tokens": 2286752} {"current_steps": 7025, "total_steps": 40000, "loss": 0.1975, "lr": 4.6291344090162804e-05, "epoch": 5.749079001227998, "percentage": 17.56, "elapsed_time": "0:48:25", "remaining_time": "3:47:19", "throughput": 787.53, "total_tokens": 2288368} {"current_steps": 7030, "total_steps": 40000, "loss": 0.211, "lr": 4.628619706151748e-05, "epoch": 5.7531723291035615, "percentage": 17.57, "elapsed_time": "0:48:27", "remaining_time": "3:47:15", "throughput": 787.62, "total_tokens": 2290000} {"current_steps": 7035, "total_steps": 40000, "loss": 0.2428, "lr": 4.628104675027306e-05, "epoch": 5.757265656979124, "percentage": 17.59, "elapsed_time": "0:48:29", "remaining_time": "3:47:12", "throughput": 787.72, "total_tokens": 2291632} {"current_steps": 7040, "total_steps": 40000, "loss": 0.1854, "lr": 4.6275893157223805e-05, "epoch": 5.761358984854687, "percentage": 17.6, "elapsed_time": "0:48:30", "remaining_time": "3:47:08", "throughput": 787.83, "total_tokens": 2293312} {"current_steps": 7045, "total_steps": 40000, "loss": 0.2065, "lr": 4.627073628316445e-05, "epoch": 5.7654523127302495, "percentage": 17.61, "elapsed_time": "0:48:32", "remaining_time": "3:47:04", "throughput": 787.91, "total_tokens": 2294912} {"current_steps": 7050, "total_steps": 40000, "loss": 0.2152, "lr": 4.626557612889026e-05, "epoch": 5.769545640605813, "percentage": 17.62, "elapsed_time": "0:48:34", "remaining_time": "3:47:01", "throughput": 788.01, "total_tokens": 2296544} {"current_steps": 7055, "total_steps": 40000, "loss": 0.2266, "lr": 4.626041269519699e-05, "epoch": 5.773638968481375, "percentage": 17.64, "elapsed_time": "0:48:36", "remaining_time": "3:46:57", "throughput": 788.1, "total_tokens": 2298176} {"current_steps": 7060, "total_steps": 40000, "loss": 0.2681, "lr": 4.6255245982880905e-05, "epoch": 5.777732296356938, "percentage": 17.65, "elapsed_time": "0:48:37", "remaining_time": "3:46:53", "throughput": 788.19, "total_tokens": 2299792} {"current_steps": 7065, "total_steps": 40000, "loss": 0.2095, "lr": 4.625007599273879e-05, "epoch": 5.781825624232501, "percentage": 17.66, "elapsed_time": "0:48:39", "remaining_time": "3:46:49", "throughput": 788.29, "total_tokens": 2301424} {"current_steps": 7070, "total_steps": 40000, "loss": 0.1984, "lr": 4.6244902725567895e-05, "epoch": 5.785918952108064, "percentage": 17.68, "elapsed_time": "0:48:41", "remaining_time": "3:46:46", "throughput": 788.42, "total_tokens": 2303168} {"current_steps": 7075, "total_steps": 40000, "loss": 0.2096, "lr": 4.6239726182166024e-05, "epoch": 5.790012279983626, "percentage": 17.69, "elapsed_time": "0:48:42", "remaining_time": "3:46:42", "throughput": 788.51, "total_tokens": 2304768} {"current_steps": 7080, "total_steps": 40000, "loss": 0.1628, "lr": 4.623454636333147e-05, "epoch": 5.79410560785919, "percentage": 17.7, "elapsed_time": "0:48:44", "remaining_time": "3:46:38", "throughput": 788.6, "total_tokens": 2306416} {"current_steps": 7085, "total_steps": 40000, "loss": 0.1962, "lr": 4.622936326986301e-05, "epoch": 5.798198935734752, "percentage": 17.71, "elapsed_time": "0:48:46", "remaining_time": "3:46:35", "throughput": 788.71, "total_tokens": 2308080} {"current_steps": 7090, "total_steps": 40000, "loss": 0.2384, "lr": 4.6224176902559946e-05, "epoch": 5.802292263610315, "percentage": 17.72, "elapsed_time": "0:48:48", "remaining_time": "3:46:31", "throughput": 788.8, "total_tokens": 2309712} {"current_steps": 7095, "total_steps": 40000, "loss": 0.167, "lr": 4.621898726222209e-05, "epoch": 5.806385591485878, "percentage": 17.74, "elapsed_time": "0:48:49", "remaining_time": "3:46:27", "throughput": 788.9, "total_tokens": 2311344} {"current_steps": 7100, "total_steps": 40000, "loss": 0.1641, "lr": 4.6213794349649744e-05, "epoch": 5.810478919361441, "percentage": 17.75, "elapsed_time": "0:48:51", "remaining_time": "3:46:24", "throughput": 789.0, "total_tokens": 2312992} {"current_steps": 7105, "total_steps": 40000, "loss": 0.1988, "lr": 4.6208598165643715e-05, "epoch": 5.814572247237003, "percentage": 17.76, "elapsed_time": "0:48:53", "remaining_time": "3:46:20", "throughput": 789.09, "total_tokens": 2314608} {"current_steps": 7110, "total_steps": 40000, "loss": 0.2979, "lr": 4.620339871100533e-05, "epoch": 5.818665575112567, "percentage": 17.77, "elapsed_time": "0:48:54", "remaining_time": "3:46:16", "throughput": 789.2, "total_tokens": 2316288} {"current_steps": 7115, "total_steps": 40000, "loss": 0.1887, "lr": 4.6198195986536394e-05, "epoch": 5.822758902988129, "percentage": 17.79, "elapsed_time": "0:48:56", "remaining_time": "3:46:13", "throughput": 789.27, "total_tokens": 2317872} {"current_steps": 7120, "total_steps": 40000, "loss": 0.1515, "lr": 4.619298999303926e-05, "epoch": 5.826852230863692, "percentage": 17.8, "elapsed_time": "0:48:58", "remaining_time": "3:46:09", "throughput": 789.37, "total_tokens": 2319520} {"current_steps": 7125, "total_steps": 40000, "loss": 0.231, "lr": 4.618778073131673e-05, "epoch": 5.830945558739255, "percentage": 17.81, "elapsed_time": "0:49:00", "remaining_time": "3:46:06", "throughput": 789.45, "total_tokens": 2321104} {"current_steps": 7130, "total_steps": 40000, "loss": 0.1505, "lr": 4.618256820217215e-05, "epoch": 5.835038886614818, "percentage": 17.82, "elapsed_time": "0:49:01", "remaining_time": "3:46:02", "throughput": 789.53, "total_tokens": 2322688} {"current_steps": 7135, "total_steps": 40000, "loss": 0.2128, "lr": 4.617735240640936e-05, "epoch": 5.83913221449038, "percentage": 17.84, "elapsed_time": "0:49:03", "remaining_time": "3:45:58", "throughput": 789.66, "total_tokens": 2324432} {"current_steps": 7140, "total_steps": 40000, "loss": 0.2311, "lr": 4.6172133344832705e-05, "epoch": 5.843225542365944, "percentage": 17.85, "elapsed_time": "0:49:05", "remaining_time": "3:45:55", "throughput": 789.74, "total_tokens": 2326032} {"current_steps": 7145, "total_steps": 40000, "loss": 0.201, "lr": 4.6166911018247004e-05, "epoch": 5.847318870241506, "percentage": 17.86, "elapsed_time": "0:49:07", "remaining_time": "3:45:51", "throughput": 789.86, "total_tokens": 2327728} {"current_steps": 7150, "total_steps": 40000, "loss": 0.1938, "lr": 4.616168542745764e-05, "epoch": 5.851412198117069, "percentage": 17.88, "elapsed_time": "0:49:08", "remaining_time": "3:45:47", "throughput": 789.95, "total_tokens": 2329360} {"current_steps": 7155, "total_steps": 40000, "loss": 0.1902, "lr": 4.6156456573270446e-05, "epoch": 5.855505525992632, "percentage": 17.89, "elapsed_time": "0:49:10", "remaining_time": "3:45:44", "throughput": 790.03, "total_tokens": 2330960} {"current_steps": 7160, "total_steps": 40000, "loss": 0.1806, "lr": 4.615122445649177e-05, "epoch": 5.859598853868195, "percentage": 17.9, "elapsed_time": "0:49:12", "remaining_time": "3:45:40", "throughput": 790.15, "total_tokens": 2332656} {"current_steps": 7165, "total_steps": 40000, "loss": 0.221, "lr": 4.6145989077928486e-05, "epoch": 5.863692181743758, "percentage": 17.91, "elapsed_time": "0:49:13", "remaining_time": "3:45:36", "throughput": 790.29, "total_tokens": 2334432} {"current_steps": 7170, "total_steps": 40000, "loss": 0.2183, "lr": 4.6140750438387953e-05, "epoch": 5.8677855096193205, "percentage": 17.93, "elapsed_time": "0:49:15", "remaining_time": "3:45:33", "throughput": 790.36, "total_tokens": 2336016} {"current_steps": 7175, "total_steps": 40000, "loss": 0.2183, "lr": 4.613550853867803e-05, "epoch": 5.871878837494883, "percentage": 17.94, "elapsed_time": "0:49:17", "remaining_time": "3:45:29", "throughput": 790.45, "total_tokens": 2337632} {"current_steps": 7180, "total_steps": 40000, "loss": 0.2091, "lr": 4.613026337960708e-05, "epoch": 5.875972165370446, "percentage": 17.95, "elapsed_time": "0:49:19", "remaining_time": "3:45:25", "throughput": 790.52, "total_tokens": 2339184} {"current_steps": 7185, "total_steps": 40000, "loss": 0.224, "lr": 4.612501496198398e-05, "epoch": 5.8800654932460095, "percentage": 17.96, "elapsed_time": "0:49:20", "remaining_time": "3:45:22", "throughput": 790.59, "total_tokens": 2340768} {"current_steps": 7190, "total_steps": 40000, "loss": 0.2107, "lr": 4.61197632866181e-05, "epoch": 5.884158821121572, "percentage": 17.97, "elapsed_time": "0:49:22", "remaining_time": "3:45:18", "throughput": 790.69, "total_tokens": 2342400} {"current_steps": 7195, "total_steps": 40000, "loss": 0.187, "lr": 4.611450835431931e-05, "epoch": 5.888252148997134, "percentage": 17.99, "elapsed_time": "0:49:24", "remaining_time": "3:45:15", "throughput": 790.77, "total_tokens": 2344016} {"current_steps": 7200, "total_steps": 40000, "loss": 0.1863, "lr": 4.6109250165898e-05, "epoch": 5.8923454768726975, "percentage": 18.0, "elapsed_time": "0:49:25", "remaining_time": "3:45:11", "throughput": 790.86, "total_tokens": 2345632} {"current_steps": 7200, "total_steps": 40000, "eval_loss": 0.20470482110977173, "epoch": 5.8923454768726975, "percentage": 18.0, "elapsed_time": "0:49:38", "remaining_time": "3:46:08", "throughput": 787.54, "total_tokens": 2345632} {"current_steps": 7205, "total_steps": 40000, "loss": 0.2585, "lr": 4.610398872216503e-05, "epoch": 5.896438804748261, "percentage": 18.01, "elapsed_time": "0:49:41", "remaining_time": "3:46:12", "throughput": 787.18, "total_tokens": 2347248} {"current_steps": 7210, "total_steps": 40000, "loss": 0.2098, "lr": 4.6098724023931796e-05, "epoch": 5.900532132623823, "percentage": 18.02, "elapsed_time": "0:49:43", "remaining_time": "3:46:08", "throughput": 787.26, "total_tokens": 2348832} {"current_steps": 7215, "total_steps": 40000, "loss": 0.1995, "lr": 4.609345607201017e-05, "epoch": 5.9046254604993855, "percentage": 18.04, "elapsed_time": "0:49:45", "remaining_time": "3:46:05", "throughput": 787.36, "total_tokens": 2350496} {"current_steps": 7220, "total_steps": 40000, "loss": 0.1984, "lr": 4.608818486721254e-05, "epoch": 5.908718788374949, "percentage": 18.05, "elapsed_time": "0:49:47", "remaining_time": "3:46:01", "throughput": 787.45, "total_tokens": 2352144} {"current_steps": 7225, "total_steps": 40000, "loss": 0.167, "lr": 4.608291041035179e-05, "epoch": 5.912812116250512, "percentage": 18.06, "elapsed_time": "0:49:48", "remaining_time": "3:45:57", "throughput": 787.52, "total_tokens": 2353696} {"current_steps": 7230, "total_steps": 40000, "loss": 0.2221, "lr": 4.607763270224132e-05, "epoch": 5.916905444126074, "percentage": 18.07, "elapsed_time": "0:49:50", "remaining_time": "3:45:54", "throughput": 787.61, "total_tokens": 2355312} {"current_steps": 7235, "total_steps": 40000, "loss": 0.2131, "lr": 4.6072351743695e-05, "epoch": 5.920998772001638, "percentage": 18.09, "elapsed_time": "0:49:52", "remaining_time": "3:45:50", "throughput": 787.71, "total_tokens": 2356960} {"current_steps": 7240, "total_steps": 40000, "loss": 0.2193, "lr": 4.606706753552723e-05, "epoch": 5.9250920998772, "percentage": 18.1, "elapsed_time": "0:49:53", "remaining_time": "3:45:46", "throughput": 787.78, "total_tokens": 2358544} {"current_steps": 7245, "total_steps": 40000, "loss": 0.1437, "lr": 4.6061780078552906e-05, "epoch": 5.929185427752763, "percentage": 18.11, "elapsed_time": "0:49:55", "remaining_time": "3:45:43", "throughput": 787.87, "total_tokens": 2360160} {"current_steps": 7250, "total_steps": 40000, "loss": 0.1976, "lr": 4.605648937358742e-05, "epoch": 5.933278755628326, "percentage": 18.12, "elapsed_time": "0:49:57", "remaining_time": "3:45:39", "throughput": 787.97, "total_tokens": 2361824} {"current_steps": 7255, "total_steps": 40000, "loss": 0.2477, "lr": 4.605119542144665e-05, "epoch": 5.937372083503889, "percentage": 18.14, "elapsed_time": "0:49:59", "remaining_time": "3:45:36", "throughput": 788.06, "total_tokens": 2363440} {"current_steps": 7260, "total_steps": 40000, "loss": 0.1978, "lr": 4.604589822294701e-05, "epoch": 5.941465411379451, "percentage": 18.15, "elapsed_time": "0:50:00", "remaining_time": "3:45:32", "throughput": 788.14, "total_tokens": 2365056} {"current_steps": 7265, "total_steps": 40000, "loss": 0.2245, "lr": 4.604059777890537e-05, "epoch": 5.945558739255015, "percentage": 18.16, "elapsed_time": "0:50:02", "remaining_time": "3:45:28", "throughput": 788.23, "total_tokens": 2366656} {"current_steps": 7270, "total_steps": 40000, "loss": 0.1992, "lr": 4.6035294090139145e-05, "epoch": 5.949652067130577, "percentage": 18.18, "elapsed_time": "0:50:04", "remaining_time": "3:45:25", "throughput": 788.31, "total_tokens": 2368272} {"current_steps": 7275, "total_steps": 40000, "loss": 0.1998, "lr": 4.6029987157466226e-05, "epoch": 5.95374539500614, "percentage": 18.19, "elapsed_time": "0:50:05", "remaining_time": "3:45:21", "throughput": 788.4, "total_tokens": 2369888} {"current_steps": 7280, "total_steps": 40000, "loss": 0.1638, "lr": 4.602467698170502e-05, "epoch": 5.957838722881703, "percentage": 18.2, "elapsed_time": "0:50:07", "remaining_time": "3:45:17", "throughput": 788.47, "total_tokens": 2371456} {"current_steps": 7285, "total_steps": 40000, "loss": 0.2712, "lr": 4.601936356367439e-05, "epoch": 5.961932050757266, "percentage": 18.21, "elapsed_time": "0:50:09", "remaining_time": "3:45:14", "throughput": 788.54, "total_tokens": 2373008} {"current_steps": 7290, "total_steps": 40000, "loss": 0.1811, "lr": 4.601404690419377e-05, "epoch": 5.966025378632828, "percentage": 18.22, "elapsed_time": "0:50:11", "remaining_time": "3:45:10", "throughput": 788.64, "total_tokens": 2374672} {"current_steps": 7295, "total_steps": 40000, "loss": 0.158, "lr": 4.600872700408303e-05, "epoch": 5.970118706508392, "percentage": 18.24, "elapsed_time": "0:50:12", "remaining_time": "3:45:07", "throughput": 788.73, "total_tokens": 2376304} {"current_steps": 7300, "total_steps": 40000, "loss": 0.1847, "lr": 4.600340386416258e-05, "epoch": 5.974212034383954, "percentage": 18.25, "elapsed_time": "0:50:14", "remaining_time": "3:45:03", "throughput": 788.8, "total_tokens": 2377888} {"current_steps": 7305, "total_steps": 40000, "loss": 0.1691, "lr": 4.5998077485253296e-05, "epoch": 5.978305362259517, "percentage": 18.26, "elapsed_time": "0:50:16", "remaining_time": "3:44:59", "throughput": 788.88, "total_tokens": 2379488} {"current_steps": 7310, "total_steps": 40000, "loss": 0.1557, "lr": 4.59927478681766e-05, "epoch": 5.98239869013508, "percentage": 18.27, "elapsed_time": "0:50:17", "remaining_time": "3:44:56", "throughput": 788.99, "total_tokens": 2381168} {"current_steps": 7315, "total_steps": 40000, "loss": 0.1978, "lr": 4.5987415013754366e-05, "epoch": 5.986492018010643, "percentage": 18.29, "elapsed_time": "0:50:19", "remaining_time": "3:44:52", "throughput": 789.09, "total_tokens": 2382816} {"current_steps": 7320, "total_steps": 40000, "loss": 0.165, "lr": 4.598207892280899e-05, "epoch": 5.990585345886205, "percentage": 18.3, "elapsed_time": "0:50:21", "remaining_time": "3:44:49", "throughput": 789.18, "total_tokens": 2384448} {"current_steps": 7325, "total_steps": 40000, "loss": 0.1761, "lr": 4.597673959616337e-05, "epoch": 5.9946786737617686, "percentage": 18.31, "elapsed_time": "0:50:23", "remaining_time": "3:44:45", "throughput": 789.3, "total_tokens": 2386176} {"current_steps": 7330, "total_steps": 40000, "loss": 0.1406, "lr": 4.597139703464089e-05, "epoch": 5.998772001637331, "percentage": 18.32, "elapsed_time": "0:50:24", "remaining_time": "3:44:41", "throughput": 789.43, "total_tokens": 2387904} {"current_steps": 7335, "total_steps": 40000, "loss": 0.1905, "lr": 4.596605123906545e-05, "epoch": 6.002455996725338, "percentage": 18.34, "elapsed_time": "0:50:26", "remaining_time": "3:44:39", "throughput": 789.38, "total_tokens": 2389248} {"current_steps": 7340, "total_steps": 40000, "loss": 0.2073, "lr": 4.596070221026143e-05, "epoch": 6.0065493246009005, "percentage": 18.35, "elapsed_time": "0:50:28", "remaining_time": "3:44:35", "throughput": 789.46, "total_tokens": 2390864} {"current_steps": 7345, "total_steps": 40000, "loss": 0.2086, "lr": 4.595534994905372e-05, "epoch": 6.010642652476464, "percentage": 18.36, "elapsed_time": "0:50:30", "remaining_time": "3:44:31", "throughput": 789.56, "total_tokens": 2392512} {"current_steps": 7350, "total_steps": 40000, "loss": 0.2352, "lr": 4.594999445626771e-05, "epoch": 6.014735980352026, "percentage": 18.38, "elapsed_time": "0:50:31", "remaining_time": "3:44:28", "throughput": 789.64, "total_tokens": 2394128} {"current_steps": 7355, "total_steps": 40000, "loss": 0.1856, "lr": 4.5944635732729276e-05, "epoch": 6.018829308227589, "percentage": 18.39, "elapsed_time": "0:50:33", "remaining_time": "3:44:24", "throughput": 789.74, "total_tokens": 2395776} {"current_steps": 7360, "total_steps": 40000, "loss": 0.174, "lr": 4.5939273779264804e-05, "epoch": 6.022922636103152, "percentage": 18.4, "elapsed_time": "0:50:35", "remaining_time": "3:44:21", "throughput": 789.85, "total_tokens": 2397472} {"current_steps": 7365, "total_steps": 40000, "loss": 0.289, "lr": 4.593390859670118e-05, "epoch": 6.027015963978715, "percentage": 18.41, "elapsed_time": "0:50:37", "remaining_time": "3:44:17", "throughput": 789.98, "total_tokens": 2399216} {"current_steps": 7370, "total_steps": 40000, "loss": 0.1517, "lr": 4.5928540185865776e-05, "epoch": 6.0311092918542775, "percentage": 18.43, "elapsed_time": "0:50:38", "remaining_time": "3:44:13", "throughput": 790.06, "total_tokens": 2400832} {"current_steps": 7375, "total_steps": 40000, "loss": 0.2116, "lr": 4.592316854758648e-05, "epoch": 6.035202619729841, "percentage": 18.44, "elapsed_time": "0:50:40", "remaining_time": "3:44:10", "throughput": 790.16, "total_tokens": 2402496} {"current_steps": 7380, "total_steps": 40000, "loss": 0.2137, "lr": 4.5917793682691646e-05, "epoch": 6.039295947605403, "percentage": 18.45, "elapsed_time": "0:50:42", "remaining_time": "3:44:06", "throughput": 790.25, "total_tokens": 2404128} {"current_steps": 7385, "total_steps": 40000, "loss": 0.2198, "lr": 4.5912415592010164e-05, "epoch": 6.043389275480966, "percentage": 18.46, "elapsed_time": "0:50:43", "remaining_time": "3:44:03", "throughput": 790.35, "total_tokens": 2405792} {"current_steps": 7390, "total_steps": 40000, "loss": 0.1987, "lr": 4.5907034276371386e-05, "epoch": 6.047482603356529, "percentage": 18.48, "elapsed_time": "0:50:45", "remaining_time": "3:43:59", "throughput": 790.43, "total_tokens": 2407408} {"current_steps": 7395, "total_steps": 40000, "loss": 0.1788, "lr": 4.5901649736605196e-05, "epoch": 6.051575931232092, "percentage": 18.49, "elapsed_time": "0:50:47", "remaining_time": "3:43:56", "throughput": 790.57, "total_tokens": 2409184} {"current_steps": 7400, "total_steps": 40000, "loss": 0.1874, "lr": 4.589626197354195e-05, "epoch": 6.055669259107654, "percentage": 18.5, "elapsed_time": "0:50:49", "remaining_time": "3:43:52", "throughput": 790.65, "total_tokens": 2410768} {"current_steps": 7400, "total_steps": 40000, "eval_loss": 0.20580840110778809, "epoch": 6.055669259107654, "percentage": 18.5, "elapsed_time": "0:51:01", "remaining_time": "3:44:47", "throughput": 787.42, "total_tokens": 2410768} {"current_steps": 7405, "total_steps": 40000, "loss": 0.2079, "lr": 4.5890870988012504e-05, "epoch": 6.059762586983218, "percentage": 18.51, "elapsed_time": "0:51:05", "remaining_time": "3:44:51", "throughput": 787.04, "total_tokens": 2412384} {"current_steps": 7410, "total_steps": 40000, "loss": 0.2151, "lr": 4.5885476780848226e-05, "epoch": 6.06385591485878, "percentage": 18.52, "elapsed_time": "0:51:06", "remaining_time": "3:44:48", "throughput": 787.13, "total_tokens": 2414000} {"current_steps": 7415, "total_steps": 40000, "loss": 0.1868, "lr": 4.5880079352880964e-05, "epoch": 6.067949242734343, "percentage": 18.54, "elapsed_time": "0:51:08", "remaining_time": "3:44:44", "throughput": 787.22, "total_tokens": 2415632} {"current_steps": 7420, "total_steps": 40000, "loss": 0.2574, "lr": 4.5874678704943065e-05, "epoch": 6.072042570609906, "percentage": 18.55, "elapsed_time": "0:51:10", "remaining_time": "3:44:41", "throughput": 787.32, "total_tokens": 2417280} {"current_steps": 7425, "total_steps": 40000, "loss": 0.1893, "lr": 4.5869274837867394e-05, "epoch": 6.076135898485469, "percentage": 18.56, "elapsed_time": "0:51:12", "remaining_time": "3:44:37", "throughput": 787.39, "total_tokens": 2418880} {"current_steps": 7430, "total_steps": 40000, "loss": 0.137, "lr": 4.5863867752487275e-05, "epoch": 6.080229226361031, "percentage": 18.57, "elapsed_time": "0:51:13", "remaining_time": "3:44:33", "throughput": 787.48, "total_tokens": 2420512} {"current_steps": 7435, "total_steps": 40000, "loss": 0.1927, "lr": 4.5858457449636554e-05, "epoch": 6.084322554236595, "percentage": 18.59, "elapsed_time": "0:51:15", "remaining_time": "3:44:30", "throughput": 787.55, "total_tokens": 2422096} {"current_steps": 7440, "total_steps": 40000, "loss": 0.2354, "lr": 4.5853043930149574e-05, "epoch": 6.088415882112157, "percentage": 18.6, "elapsed_time": "0:51:17", "remaining_time": "3:44:26", "throughput": 787.63, "total_tokens": 2423680} {"current_steps": 7445, "total_steps": 40000, "loss": 0.2667, "lr": 4.584762719486117e-05, "epoch": 6.09250920998772, "percentage": 18.61, "elapsed_time": "0:51:18", "remaining_time": "3:44:23", "throughput": 787.7, "total_tokens": 2425264} {"current_steps": 7450, "total_steps": 40000, "loss": 0.1783, "lr": 4.584220724460665e-05, "epoch": 6.096602537863283, "percentage": 18.62, "elapsed_time": "0:51:20", "remaining_time": "3:44:19", "throughput": 787.8, "total_tokens": 2426928} {"current_steps": 7455, "total_steps": 40000, "loss": 0.1601, "lr": 4.5836784080221865e-05, "epoch": 6.100695865738846, "percentage": 18.64, "elapsed_time": "0:51:22", "remaining_time": "3:44:16", "throughput": 787.9, "total_tokens": 2428560} {"current_steps": 7460, "total_steps": 40000, "loss": 0.2083, "lr": 4.583135770254312e-05, "epoch": 6.104789193614408, "percentage": 18.65, "elapsed_time": "0:51:24", "remaining_time": "3:44:12", "throughput": 787.97, "total_tokens": 2430144} {"current_steps": 7465, "total_steps": 40000, "loss": 0.1842, "lr": 4.5825928112407236e-05, "epoch": 6.108882521489972, "percentage": 18.66, "elapsed_time": "0:51:25", "remaining_time": "3:44:08", "throughput": 788.05, "total_tokens": 2431744} {"current_steps": 7470, "total_steps": 40000, "loss": 0.2185, "lr": 4.582049531065152e-05, "epoch": 6.112975849365534, "percentage": 18.68, "elapsed_time": "0:51:27", "remaining_time": "3:44:05", "throughput": 788.14, "total_tokens": 2433376} {"current_steps": 7475, "total_steps": 40000, "loss": 0.2135, "lr": 4.5815059298113783e-05, "epoch": 6.117069177241097, "percentage": 18.69, "elapsed_time": "0:51:29", "remaining_time": "3:44:01", "throughput": 788.24, "total_tokens": 2435040} {"current_steps": 7480, "total_steps": 40000, "loss": 0.2197, "lr": 4.580962007563232e-05, "epoch": 6.12116250511666, "percentage": 18.7, "elapsed_time": "0:51:30", "remaining_time": "3:43:58", "throughput": 788.36, "total_tokens": 2436768} {"current_steps": 7485, "total_steps": 40000, "loss": 0.2297, "lr": 4.5804177644045935e-05, "epoch": 6.125255832992223, "percentage": 18.71, "elapsed_time": "0:51:32", "remaining_time": "3:43:54", "throughput": 788.44, "total_tokens": 2438368} {"current_steps": 7490, "total_steps": 40000, "loss": 0.1691, "lr": 4.579873200419391e-05, "epoch": 6.129349160867785, "percentage": 18.73, "elapsed_time": "0:51:34", "remaining_time": "3:43:50", "throughput": 788.51, "total_tokens": 2439952} {"current_steps": 7495, "total_steps": 40000, "loss": 0.1852, "lr": 4.5793283156916046e-05, "epoch": 6.1334424887433485, "percentage": 18.74, "elapsed_time": "0:51:36", "remaining_time": "3:43:47", "throughput": 788.61, "total_tokens": 2441616} {"current_steps": 7500, "total_steps": 40000, "loss": 0.1849, "lr": 4.578783110305261e-05, "epoch": 6.137535816618911, "percentage": 18.75, "elapsed_time": "0:51:37", "remaining_time": "3:43:43", "throughput": 788.74, "total_tokens": 2443360} {"current_steps": 7505, "total_steps": 40000, "loss": 0.2185, "lr": 4.578237584344438e-05, "epoch": 6.141629144494474, "percentage": 18.76, "elapsed_time": "0:51:39", "remaining_time": "3:43:40", "throughput": 788.83, "total_tokens": 2445008} {"current_steps": 7510, "total_steps": 40000, "loss": 0.1773, "lr": 4.577691737893263e-05, "epoch": 6.1457224723700365, "percentage": 18.77, "elapsed_time": "0:51:41", "remaining_time": "3:43:36", "throughput": 788.93, "total_tokens": 2446656} {"current_steps": 7515, "total_steps": 40000, "loss": 0.2292, "lr": 4.577145571035912e-05, "epoch": 6.1498158002456, "percentage": 18.79, "elapsed_time": "0:51:42", "remaining_time": "3:43:33", "throughput": 789.01, "total_tokens": 2448256} {"current_steps": 7520, "total_steps": 40000, "loss": 0.2215, "lr": 4.576599083856611e-05, "epoch": 6.153909128121162, "percentage": 18.8, "elapsed_time": "0:51:44", "remaining_time": "3:43:29", "throughput": 789.1, "total_tokens": 2449904} {"current_steps": 7525, "total_steps": 40000, "loss": 0.1555, "lr": 4.576052276439635e-05, "epoch": 6.1580024559967255, "percentage": 18.81, "elapsed_time": "0:51:46", "remaining_time": "3:43:26", "throughput": 789.18, "total_tokens": 2451520} {"current_steps": 7530, "total_steps": 40000, "loss": 0.1774, "lr": 4.575505148869308e-05, "epoch": 6.162095783872288, "percentage": 18.82, "elapsed_time": "0:51:48", "remaining_time": "3:43:22", "throughput": 789.27, "total_tokens": 2453152} {"current_steps": 7535, "total_steps": 40000, "loss": 0.1813, "lr": 4.574957701230006e-05, "epoch": 6.166189111747851, "percentage": 18.84, "elapsed_time": "0:51:49", "remaining_time": "3:43:18", "throughput": 789.37, "total_tokens": 2454800} {"current_steps": 7540, "total_steps": 40000, "loss": 0.1731, "lr": 4.57440993360615e-05, "epoch": 6.1702824396234135, "percentage": 18.85, "elapsed_time": "0:51:51", "remaining_time": "3:43:15", "throughput": 789.46, "total_tokens": 2456432} {"current_steps": 7545, "total_steps": 40000, "loss": 0.2552, "lr": 4.5738618460822134e-05, "epoch": 6.174375767498977, "percentage": 18.86, "elapsed_time": "0:51:53", "remaining_time": "3:43:11", "throughput": 789.55, "total_tokens": 2458080} {"current_steps": 7550, "total_steps": 40000, "loss": 0.2352, "lr": 4.573313438742719e-05, "epoch": 6.178469095374539, "percentage": 18.88, "elapsed_time": "0:51:54", "remaining_time": "3:43:08", "throughput": 789.64, "total_tokens": 2459728} {"current_steps": 7555, "total_steps": 40000, "loss": 0.1422, "lr": 4.5727647116722374e-05, "epoch": 6.182562423250102, "percentage": 18.89, "elapsed_time": "0:51:56", "remaining_time": "3:43:04", "throughput": 789.73, "total_tokens": 2461360} {"current_steps": 7560, "total_steps": 40000, "loss": 0.1818, "lr": 4.5722156649553884e-05, "epoch": 6.186655751125665, "percentage": 18.9, "elapsed_time": "0:51:58", "remaining_time": "3:43:01", "throughput": 789.81, "total_tokens": 2462944} {"current_steps": 7565, "total_steps": 40000, "loss": 0.1793, "lr": 4.571666298676843e-05, "epoch": 6.190749079001228, "percentage": 18.91, "elapsed_time": "0:52:00", "remaining_time": "3:42:57", "throughput": 789.9, "total_tokens": 2464608} {"current_steps": 7570, "total_steps": 40000, "loss": 0.1967, "lr": 4.571116612921321e-05, "epoch": 6.19484240687679, "percentage": 18.93, "elapsed_time": "0:52:01", "remaining_time": "3:42:54", "throughput": 789.99, "total_tokens": 2466224} {"current_steps": 7575, "total_steps": 40000, "loss": 0.1816, "lr": 4.57056660777359e-05, "epoch": 6.198935734752354, "percentage": 18.94, "elapsed_time": "0:52:03", "remaining_time": "3:42:50", "throughput": 790.09, "total_tokens": 2467888} {"current_steps": 7580, "total_steps": 40000, "loss": 0.1988, "lr": 4.5700162833184666e-05, "epoch": 6.203029062627916, "percentage": 18.95, "elapsed_time": "0:52:05", "remaining_time": "3:42:46", "throughput": 790.16, "total_tokens": 2469472} {"current_steps": 7585, "total_steps": 40000, "loss": 0.1715, "lr": 4.5694656396408195e-05, "epoch": 6.207122390503479, "percentage": 18.96, "elapsed_time": "0:52:06", "remaining_time": "3:42:43", "throughput": 790.27, "total_tokens": 2471152} {"current_steps": 7590, "total_steps": 40000, "loss": 0.1528, "lr": 4.5689146768255646e-05, "epoch": 6.211215718379042, "percentage": 18.98, "elapsed_time": "0:52:08", "remaining_time": "3:42:39", "throughput": 790.35, "total_tokens": 2472784} {"current_steps": 7595, "total_steps": 40000, "loss": 0.2321, "lr": 4.568363394957667e-05, "epoch": 6.215309046254605, "percentage": 18.99, "elapsed_time": "0:52:10", "remaining_time": "3:42:36", "throughput": 790.44, "total_tokens": 2474400} {"current_steps": 7600, "total_steps": 40000, "loss": 0.2297, "lr": 4.567811794122141e-05, "epoch": 6.219402374130167, "percentage": 19.0, "elapsed_time": "0:52:12", "remaining_time": "3:42:32", "throughput": 790.55, "total_tokens": 2476096} {"current_steps": 7600, "total_steps": 40000, "eval_loss": 0.21493825316429138, "epoch": 6.219402374130167, "percentage": 19.0, "elapsed_time": "0:52:24", "remaining_time": "3:43:25", "throughput": 787.42, "total_tokens": 2476096} {"current_steps": 7605, "total_steps": 40000, "loss": 0.216, "lr": 4.56725987440405e-05, "epoch": 6.223495702005731, "percentage": 19.01, "elapsed_time": "0:52:27", "remaining_time": "3:43:28", "throughput": 787.15, "total_tokens": 2477728} {"current_steps": 7610, "total_steps": 40000, "loss": 0.2006, "lr": 4.566707635888508e-05, "epoch": 6.227589029881294, "percentage": 19.02, "elapsed_time": "0:52:29", "remaining_time": "3:43:24", "throughput": 787.25, "total_tokens": 2479392} {"current_steps": 7615, "total_steps": 40000, "loss": 0.193, "lr": 4.566155078660677e-05, "epoch": 6.231682357756856, "percentage": 19.04, "elapsed_time": "0:52:31", "remaining_time": "3:43:21", "throughput": 787.33, "total_tokens": 2480992} {"current_steps": 7620, "total_steps": 40000, "loss": 0.1499, "lr": 4.565602202805768e-05, "epoch": 6.23577568563242, "percentage": 19.05, "elapsed_time": "0:52:32", "remaining_time": "3:43:17", "throughput": 787.42, "total_tokens": 2482640} {"current_steps": 7625, "total_steps": 40000, "loss": 0.1803, "lr": 4.56504900840904e-05, "epoch": 6.239869013507982, "percentage": 19.06, "elapsed_time": "0:52:34", "remaining_time": "3:43:14", "throughput": 787.5, "total_tokens": 2484256} {"current_steps": 7630, "total_steps": 40000, "loss": 0.2173, "lr": 4.564495495555805e-05, "epoch": 6.243962341383545, "percentage": 19.07, "elapsed_time": "0:52:36", "remaining_time": "3:43:10", "throughput": 787.6, "total_tokens": 2485920} {"current_steps": 7635, "total_steps": 40000, "loss": 0.1825, "lr": 4.5639416643314204e-05, "epoch": 6.248055669259108, "percentage": 19.09, "elapsed_time": "0:52:38", "remaining_time": "3:43:06", "throughput": 787.68, "total_tokens": 2487520} {"current_steps": 7640, "total_steps": 40000, "loss": 0.1448, "lr": 4.5633875148212946e-05, "epoch": 6.252148997134671, "percentage": 19.1, "elapsed_time": "0:52:39", "remaining_time": "3:43:03", "throughput": 787.76, "total_tokens": 2489104} {"current_steps": 7645, "total_steps": 40000, "loss": 0.2537, "lr": 4.562833047110883e-05, "epoch": 6.256242325010233, "percentage": 19.11, "elapsed_time": "0:52:41", "remaining_time": "3:42:59", "throughput": 787.85, "total_tokens": 2490752} {"current_steps": 7650, "total_steps": 40000, "loss": 0.2454, "lr": 4.5622782612856923e-05, "epoch": 6.2603356528857965, "percentage": 19.12, "elapsed_time": "0:52:43", "remaining_time": "3:42:56", "throughput": 787.94, "total_tokens": 2492384} {"current_steps": 7655, "total_steps": 40000, "loss": 0.2539, "lr": 4.561723157431278e-05, "epoch": 6.264428980761359, "percentage": 19.14, "elapsed_time": "0:52:44", "remaining_time": "3:42:52", "throughput": 788.02, "total_tokens": 2494000} {"current_steps": 7660, "total_steps": 40000, "loss": 0.1862, "lr": 4.5611677356332435e-05, "epoch": 6.268522308636922, "percentage": 19.15, "elapsed_time": "0:52:46", "remaining_time": "3:42:49", "throughput": 788.09, "total_tokens": 2495600} {"current_steps": 7665, "total_steps": 40000, "loss": 0.2784, "lr": 4.560611995977242e-05, "epoch": 6.2726156365124845, "percentage": 19.16, "elapsed_time": "0:52:48", "remaining_time": "3:42:45", "throughput": 788.18, "total_tokens": 2497216} {"current_steps": 7670, "total_steps": 40000, "loss": 0.2875, "lr": 4.560055938548975e-05, "epoch": 6.276708964388048, "percentage": 19.18, "elapsed_time": "0:52:50", "remaining_time": "3:42:42", "throughput": 788.26, "total_tokens": 2498816} {"current_steps": 7675, "total_steps": 40000, "loss": 0.2435, "lr": 4.5594995634341944e-05, "epoch": 6.28080229226361, "percentage": 19.19, "elapsed_time": "0:52:51", "remaining_time": "3:42:38", "throughput": 788.35, "total_tokens": 2500464} {"current_steps": 7680, "total_steps": 40000, "loss": 0.2356, "lr": 4.5589428707187e-05, "epoch": 6.2848956201391735, "percentage": 19.2, "elapsed_time": "0:52:53", "remaining_time": "3:42:35", "throughput": 788.44, "total_tokens": 2502096} {"current_steps": 7685, "total_steps": 40000, "loss": 0.2194, "lr": 4.55838586048834e-05, "epoch": 6.288988948014736, "percentage": 19.21, "elapsed_time": "0:52:55", "remaining_time": "3:42:31", "throughput": 788.52, "total_tokens": 2503728} {"current_steps": 7690, "total_steps": 40000, "loss": 0.1737, "lr": 4.557828532829013e-05, "epoch": 6.293082275890299, "percentage": 19.23, "elapsed_time": "0:52:56", "remaining_time": "3:42:28", "throughput": 788.58, "total_tokens": 2505264} {"current_steps": 7695, "total_steps": 40000, "loss": 0.2228, "lr": 4.557270887826667e-05, "epoch": 6.2971756037658615, "percentage": 19.24, "elapsed_time": "0:52:58", "remaining_time": "3:42:24", "throughput": 788.68, "total_tokens": 2506928} {"current_steps": 7700, "total_steps": 40000, "loss": 0.1948, "lr": 4.556712925567296e-05, "epoch": 6.301268931641425, "percentage": 19.25, "elapsed_time": "0:53:00", "remaining_time": "3:42:21", "throughput": 788.77, "total_tokens": 2508592} {"current_steps": 7705, "total_steps": 40000, "loss": 0.2066, "lr": 4.5561546461369454e-05, "epoch": 6.305362259516987, "percentage": 19.26, "elapsed_time": "0:53:02", "remaining_time": "3:42:17", "throughput": 788.84, "total_tokens": 2510176} {"current_steps": 7710, "total_steps": 40000, "loss": 0.1949, "lr": 4.55559604962171e-05, "epoch": 6.30945558739255, "percentage": 19.28, "elapsed_time": "0:53:03", "remaining_time": "3:42:14", "throughput": 788.92, "total_tokens": 2511776} {"current_steps": 7715, "total_steps": 40000, "loss": 0.2275, "lr": 4.55503713610773e-05, "epoch": 6.313548915268113, "percentage": 19.29, "elapsed_time": "0:53:05", "remaining_time": "3:42:10", "throughput": 788.99, "total_tokens": 2513360} {"current_steps": 7720, "total_steps": 40000, "loss": 0.2251, "lr": 4.5544779056812e-05, "epoch": 6.317642243143676, "percentage": 19.3, "elapsed_time": "0:53:07", "remaining_time": "3:42:06", "throughput": 789.09, "total_tokens": 2515008} {"current_steps": 7725, "total_steps": 40000, "loss": 0.2407, "lr": 4.553918358428358e-05, "epoch": 6.321735571019238, "percentage": 19.31, "elapsed_time": "0:53:08", "remaining_time": "3:42:03", "throughput": 789.17, "total_tokens": 2516624} {"current_steps": 7730, "total_steps": 40000, "loss": 0.2459, "lr": 4.553358494435494e-05, "epoch": 6.325828898894802, "percentage": 19.32, "elapsed_time": "0:53:10", "remaining_time": "3:41:59", "throughput": 789.29, "total_tokens": 2518384} {"current_steps": 7735, "total_steps": 40000, "loss": 0.1944, "lr": 4.5527983137889464e-05, "epoch": 6.329922226770364, "percentage": 19.34, "elapsed_time": "0:53:12", "remaining_time": "3:41:56", "throughput": 789.39, "total_tokens": 2520048} {"current_steps": 7740, "total_steps": 40000, "loss": 0.1767, "lr": 4.5522378165751015e-05, "epoch": 6.334015554645927, "percentage": 19.35, "elapsed_time": "0:53:14", "remaining_time": "3:41:52", "throughput": 789.45, "total_tokens": 2521600} {"current_steps": 7745, "total_steps": 40000, "loss": 0.2852, "lr": 4.5516770028803954e-05, "epoch": 6.33810888252149, "percentage": 19.36, "elapsed_time": "0:53:15", "remaining_time": "3:41:49", "throughput": 789.53, "total_tokens": 2523232} {"current_steps": 7750, "total_steps": 40000, "loss": 0.1781, "lr": 4.5511158727913116e-05, "epoch": 6.342202210397053, "percentage": 19.38, "elapsed_time": "0:53:17", "remaining_time": "3:41:45", "throughput": 789.61, "total_tokens": 2524832} {"current_steps": 7755, "total_steps": 40000, "loss": 0.2062, "lr": 4.5505544263943856e-05, "epoch": 6.346295538272615, "percentage": 19.39, "elapsed_time": "0:53:19", "remaining_time": "3:41:42", "throughput": 789.69, "total_tokens": 2526448} {"current_steps": 7760, "total_steps": 40000, "loss": 0.183, "lr": 4.549992663776197e-05, "epoch": 6.350388866148179, "percentage": 19.4, "elapsed_time": "0:53:21", "remaining_time": "3:41:39", "throughput": 789.79, "total_tokens": 2528112} {"current_steps": 7765, "total_steps": 40000, "loss": 0.1728, "lr": 4.5494305850233786e-05, "epoch": 6.354482194023741, "percentage": 19.41, "elapsed_time": "0:53:22", "remaining_time": "3:41:35", "throughput": 789.87, "total_tokens": 2529728} {"current_steps": 7770, "total_steps": 40000, "loss": 0.1923, "lr": 4.5488681902226094e-05, "epoch": 6.358575521899304, "percentage": 19.43, "elapsed_time": "0:53:24", "remaining_time": "3:41:31", "throughput": 789.93, "total_tokens": 2531280} {"current_steps": 7775, "total_steps": 40000, "loss": 0.1996, "lr": 4.5483054794606174e-05, "epoch": 6.362668849774867, "percentage": 19.44, "elapsed_time": "0:53:26", "remaining_time": "3:41:28", "throughput": 790.01, "total_tokens": 2532880} {"current_steps": 7780, "total_steps": 40000, "loss": 0.1993, "lr": 4.547742452824179e-05, "epoch": 6.36676217765043, "percentage": 19.45, "elapsed_time": "0:53:27", "remaining_time": "3:41:24", "throughput": 790.08, "total_tokens": 2534480} {"current_steps": 7785, "total_steps": 40000, "loss": 0.1603, "lr": 4.5471791104001215e-05, "epoch": 6.370855505525992, "percentage": 19.46, "elapsed_time": "0:53:29", "remaining_time": "3:41:21", "throughput": 790.19, "total_tokens": 2536192} {"current_steps": 7790, "total_steps": 40000, "loss": 0.1612, "lr": 4.546615452275319e-05, "epoch": 6.374948833401556, "percentage": 19.48, "elapsed_time": "0:53:31", "remaining_time": "3:41:18", "throughput": 790.28, "total_tokens": 2537824} {"current_steps": 7795, "total_steps": 40000, "loss": 0.1858, "lr": 4.5460514785366944e-05, "epoch": 6.379042161277118, "percentage": 19.49, "elapsed_time": "0:53:33", "remaining_time": "3:41:14", "throughput": 790.38, "total_tokens": 2539504} {"current_steps": 7800, "total_steps": 40000, "loss": 0.1849, "lr": 4.545487189271219e-05, "epoch": 6.383135489152681, "percentage": 19.5, "elapsed_time": "0:53:34", "remaining_time": "3:41:11", "throughput": 790.47, "total_tokens": 2541152} {"current_steps": 7800, "total_steps": 40000, "eval_loss": 0.2056499719619751, "epoch": 6.383135489152681, "percentage": 19.5, "elapsed_time": "0:53:47", "remaining_time": "3:42:02", "throughput": 787.42, "total_tokens": 2541152} {"current_steps": 7805, "total_steps": 40000, "loss": 0.2306, "lr": 4.544922584565914e-05, "epoch": 6.387228817028244, "percentage": 19.51, "elapsed_time": "0:53:50", "remaining_time": "3:42:04", "throughput": 787.15, "total_tokens": 2542784} {"current_steps": 7810, "total_steps": 40000, "loss": 0.2415, "lr": 4.544357664507848e-05, "epoch": 6.391322144903807, "percentage": 19.53, "elapsed_time": "0:53:52", "remaining_time": "3:42:01", "throughput": 787.24, "total_tokens": 2544416} {"current_steps": 7815, "total_steps": 40000, "loss": 0.201, "lr": 4.54379242918414e-05, "epoch": 6.395415472779369, "percentage": 19.54, "elapsed_time": "0:53:53", "remaining_time": "3:41:57", "throughput": 787.32, "total_tokens": 2546016} {"current_steps": 7820, "total_steps": 40000, "loss": 0.2041, "lr": 4.543226878681955e-05, "epoch": 6.3995088006549325, "percentage": 19.55, "elapsed_time": "0:53:55", "remaining_time": "3:41:54", "throughput": 787.41, "total_tokens": 2547680} {"current_steps": 7825, "total_steps": 40000, "loss": 0.1614, "lr": 4.5426610130885087e-05, "epoch": 6.403602128530495, "percentage": 19.56, "elapsed_time": "0:53:57", "remaining_time": "3:41:50", "throughput": 787.48, "total_tokens": 2549264} {"current_steps": 7830, "total_steps": 40000, "loss": 0.2079, "lr": 4.542094832491064e-05, "epoch": 6.407695456406058, "percentage": 19.57, "elapsed_time": "0:53:58", "remaining_time": "3:41:47", "throughput": 787.58, "total_tokens": 2550912} {"current_steps": 7835, "total_steps": 40000, "loss": 0.1872, "lr": 4.541528336976934e-05, "epoch": 6.411788784281621, "percentage": 19.59, "elapsed_time": "0:54:00", "remaining_time": "3:41:43", "throughput": 787.66, "total_tokens": 2552544} {"current_steps": 7840, "total_steps": 40000, "loss": 0.2258, "lr": 4.540961526633479e-05, "epoch": 6.415882112157184, "percentage": 19.6, "elapsed_time": "0:54:02", "remaining_time": "3:41:40", "throughput": 787.72, "total_tokens": 2554096} {"current_steps": 7845, "total_steps": 40000, "loss": 0.2424, "lr": 4.540394401548108e-05, "epoch": 6.419975440032746, "percentage": 19.61, "elapsed_time": "0:54:04", "remaining_time": "3:41:36", "throughput": 787.79, "total_tokens": 2555680} {"current_steps": 7850, "total_steps": 40000, "loss": 0.2023, "lr": 4.539826961808279e-05, "epoch": 6.4240687679083095, "percentage": 19.62, "elapsed_time": "0:54:05", "remaining_time": "3:41:33", "throughput": 787.88, "total_tokens": 2557328} {"current_steps": 7855, "total_steps": 40000, "loss": 0.18, "lr": 4.5392592075014994e-05, "epoch": 6.428162095783872, "percentage": 19.64, "elapsed_time": "0:54:07", "remaining_time": "3:41:29", "throughput": 787.97, "total_tokens": 2558960} {"current_steps": 7860, "total_steps": 40000, "loss": 0.2232, "lr": 4.538691138715322e-05, "epoch": 6.432255423659435, "percentage": 19.65, "elapsed_time": "0:54:09", "remaining_time": "3:41:26", "throughput": 788.07, "total_tokens": 2560640} {"current_steps": 7865, "total_steps": 40000, "loss": 0.1674, "lr": 4.5381227555373516e-05, "epoch": 6.436348751534998, "percentage": 19.66, "elapsed_time": "0:54:10", "remaining_time": "3:41:22", "throughput": 788.15, "total_tokens": 2562272} {"current_steps": 7870, "total_steps": 40000, "loss": 0.199, "lr": 4.537554058055239e-05, "epoch": 6.440442079410561, "percentage": 19.68, "elapsed_time": "0:54:12", "remaining_time": "3:41:19", "throughput": 788.24, "total_tokens": 2563904} {"current_steps": 7875, "total_steps": 40000, "loss": 0.1693, "lr": 4.5369850463566865e-05, "epoch": 6.444535407286123, "percentage": 19.69, "elapsed_time": "0:54:14", "remaining_time": "3:41:15", "throughput": 788.33, "total_tokens": 2565552} {"current_steps": 7880, "total_steps": 40000, "loss": 0.1593, "lr": 4.5364157205294404e-05, "epoch": 6.448628735161686, "percentage": 19.7, "elapsed_time": "0:54:16", "remaining_time": "3:41:12", "throughput": 788.39, "total_tokens": 2567104} {"current_steps": 7885, "total_steps": 40000, "loss": 0.1363, "lr": 4.5358460806612996e-05, "epoch": 6.45272206303725, "percentage": 19.71, "elapsed_time": "0:54:17", "remaining_time": "3:41:09", "throughput": 788.5, "total_tokens": 2568832} {"current_steps": 7890, "total_steps": 40000, "loss": 0.1612, "lr": 4.535276126840109e-05, "epoch": 6.456815390912812, "percentage": 19.73, "elapsed_time": "0:54:19", "remaining_time": "3:41:05", "throughput": 788.58, "total_tokens": 2570448} {"current_steps": 7895, "total_steps": 40000, "loss": 0.1719, "lr": 4.5347058591537626e-05, "epoch": 6.460908718788375, "percentage": 19.74, "elapsed_time": "0:54:21", "remaining_time": "3:41:02", "throughput": 788.67, "total_tokens": 2572096} {"current_steps": 7900, "total_steps": 40000, "loss": 0.1867, "lr": 4.534135277690203e-05, "epoch": 6.465002046663938, "percentage": 19.75, "elapsed_time": "0:54:23", "remaining_time": "3:40:58", "throughput": 788.75, "total_tokens": 2573712} {"current_steps": 7905, "total_steps": 40000, "loss": 0.2256, "lr": 4.533564382537421e-05, "epoch": 6.469095374539501, "percentage": 19.76, "elapsed_time": "0:54:24", "remaining_time": "3:40:55", "throughput": 788.83, "total_tokens": 2575312} {"current_steps": 7910, "total_steps": 40000, "loss": 0.1628, "lr": 4.532993173783456e-05, "epoch": 6.473188702415063, "percentage": 19.78, "elapsed_time": "0:54:26", "remaining_time": "3:40:51", "throughput": 788.9, "total_tokens": 2576896} {"current_steps": 7915, "total_steps": 40000, "loss": 0.1907, "lr": 4.5324216515163954e-05, "epoch": 6.477282030290627, "percentage": 19.79, "elapsed_time": "0:54:28", "remaining_time": "3:40:48", "throughput": 788.98, "total_tokens": 2578512} {"current_steps": 7920, "total_steps": 40000, "loss": 0.1929, "lr": 4.531849815824375e-05, "epoch": 6.481375358166189, "percentage": 19.8, "elapsed_time": "0:54:29", "remaining_time": "3:40:44", "throughput": 789.05, "total_tokens": 2580112} {"current_steps": 7925, "total_steps": 40000, "loss": 0.222, "lr": 4.5312776667955795e-05, "epoch": 6.485468686041752, "percentage": 19.81, "elapsed_time": "0:54:31", "remaining_time": "3:40:41", "throughput": 789.14, "total_tokens": 2581760} {"current_steps": 7930, "total_steps": 40000, "loss": 0.1837, "lr": 4.5307052045182405e-05, "epoch": 6.489562013917315, "percentage": 19.82, "elapsed_time": "0:54:33", "remaining_time": "3:40:37", "throughput": 789.2, "total_tokens": 2583312} {"current_steps": 7935, "total_steps": 40000, "loss": 0.2067, "lr": 4.53013242908064e-05, "epoch": 6.493655341792878, "percentage": 19.84, "elapsed_time": "0:54:35", "remaining_time": "3:40:34", "throughput": 789.28, "total_tokens": 2584944} {"current_steps": 7940, "total_steps": 40000, "loss": 0.1803, "lr": 4.529559340571107e-05, "epoch": 6.49774866966844, "percentage": 19.85, "elapsed_time": "0:54:36", "remaining_time": "3:40:30", "throughput": 789.36, "total_tokens": 2586560} {"current_steps": 7945, "total_steps": 40000, "loss": 0.2152, "lr": 4.528985939078018e-05, "epoch": 6.501841997544004, "percentage": 19.86, "elapsed_time": "0:54:38", "remaining_time": "3:40:27", "throughput": 789.44, "total_tokens": 2588160} {"current_steps": 7950, "total_steps": 40000, "loss": 0.2104, "lr": 4.5284122246898e-05, "epoch": 6.505935325419566, "percentage": 19.88, "elapsed_time": "0:54:40", "remaining_time": "3:40:23", "throughput": 789.52, "total_tokens": 2589776} {"current_steps": 7955, "total_steps": 40000, "loss": 0.1688, "lr": 4.527838197494926e-05, "epoch": 6.510028653295129, "percentage": 19.89, "elapsed_time": "0:54:41", "remaining_time": "3:40:20", "throughput": 789.58, "total_tokens": 2591360} {"current_steps": 7960, "total_steps": 40000, "loss": 0.2156, "lr": 4.527263857581918e-05, "epoch": 6.514121981170692, "percentage": 19.9, "elapsed_time": "0:54:43", "remaining_time": "3:40:17", "throughput": 789.68, "total_tokens": 2593024} {"current_steps": 7965, "total_steps": 40000, "loss": 0.177, "lr": 4.526689205039347e-05, "epoch": 6.518215309046255, "percentage": 19.91, "elapsed_time": "0:54:45", "remaining_time": "3:40:13", "throughput": 789.76, "total_tokens": 2594672} {"current_steps": 7970, "total_steps": 40000, "loss": 0.2078, "lr": 4.5261142399558324e-05, "epoch": 6.522308636921817, "percentage": 19.93, "elapsed_time": "0:54:47", "remaining_time": "3:40:10", "throughput": 789.85, "total_tokens": 2596304} {"current_steps": 7975, "total_steps": 40000, "loss": 0.1914, "lr": 4.525538962420041e-05, "epoch": 6.5264019647973806, "percentage": 19.94, "elapsed_time": "0:54:48", "remaining_time": "3:40:06", "throughput": 789.92, "total_tokens": 2597888} {"current_steps": 7980, "total_steps": 40000, "loss": 0.1988, "lr": 4.524963372520685e-05, "epoch": 6.530495292672943, "percentage": 19.95, "elapsed_time": "0:54:50", "remaining_time": "3:40:03", "throughput": 790.01, "total_tokens": 2599552} {"current_steps": 7985, "total_steps": 40000, "loss": 0.1955, "lr": 4.524387470346531e-05, "epoch": 6.534588620548506, "percentage": 19.96, "elapsed_time": "0:54:52", "remaining_time": "3:39:59", "throughput": 790.09, "total_tokens": 2601168} {"current_steps": 7990, "total_steps": 40000, "loss": 0.1686, "lr": 4.5238112559863885e-05, "epoch": 6.538681948424069, "percentage": 19.98, "elapsed_time": "0:54:53", "remaining_time": "3:39:56", "throughput": 790.17, "total_tokens": 2602768} {"current_steps": 7995, "total_steps": 40000, "loss": 0.1915, "lr": 4.5232347295291175e-05, "epoch": 6.542775276299632, "percentage": 19.99, "elapsed_time": "0:54:55", "remaining_time": "3:39:52", "throughput": 790.25, "total_tokens": 2604416} {"current_steps": 8000, "total_steps": 40000, "loss": 0.1483, "lr": 4.522657891063626e-05, "epoch": 6.546868604175194, "percentage": 20.0, "elapsed_time": "0:54:57", "remaining_time": "3:39:49", "throughput": 790.33, "total_tokens": 2606016} {"current_steps": 8000, "total_steps": 40000, "eval_loss": 0.20684103667736053, "epoch": 6.546868604175194, "percentage": 20.0, "elapsed_time": "0:55:09", "remaining_time": "3:40:39", "throughput": 787.36, "total_tokens": 2606016} {"current_steps": 8005, "total_steps": 40000, "loss": 0.1675, "lr": 4.52208074067887e-05, "epoch": 6.5509619320507575, "percentage": 20.01, "elapsed_time": "0:55:12", "remaining_time": "3:40:41", "throughput": 787.1, "total_tokens": 2607648} {"current_steps": 8010, "total_steps": 40000, "loss": 0.1514, "lr": 4.5215032784638516e-05, "epoch": 6.55505525992632, "percentage": 20.03, "elapsed_time": "0:55:14", "remaining_time": "3:40:38", "throughput": 787.18, "total_tokens": 2609280} {"current_steps": 8015, "total_steps": 40000, "loss": 0.1968, "lr": 4.5209255045076245e-05, "epoch": 6.559148587801883, "percentage": 20.04, "elapsed_time": "0:55:16", "remaining_time": "3:40:34", "throughput": 787.26, "total_tokens": 2610912} {"current_steps": 8020, "total_steps": 40000, "loss": 0.2993, "lr": 4.5203474188992875e-05, "epoch": 6.5632419156774455, "percentage": 20.05, "elapsed_time": "0:55:18", "remaining_time": "3:40:31", "throughput": 787.33, "total_tokens": 2612496} {"current_steps": 8025, "total_steps": 40000, "loss": 0.1639, "lr": 4.51976902172799e-05, "epoch": 6.567335243553009, "percentage": 20.06, "elapsed_time": "0:55:19", "remaining_time": "3:40:27", "throughput": 787.42, "total_tokens": 2614128} {"current_steps": 8030, "total_steps": 40000, "loss": 0.1868, "lr": 4.519190313082927e-05, "epoch": 6.571428571428571, "percentage": 20.08, "elapsed_time": "0:55:21", "remaining_time": "3:40:24", "throughput": 787.5, "total_tokens": 2615760} {"current_steps": 8035, "total_steps": 40000, "loss": 0.2566, "lr": 4.518611293053343e-05, "epoch": 6.575521899304134, "percentage": 20.09, "elapsed_time": "0:55:23", "remaining_time": "3:40:20", "throughput": 787.59, "total_tokens": 2617392} {"current_steps": 8040, "total_steps": 40000, "loss": 0.1544, "lr": 4.51803196172853e-05, "epoch": 6.579615227179697, "percentage": 20.1, "elapsed_time": "0:55:25", "remaining_time": "3:40:17", "throughput": 787.67, "total_tokens": 2619024} {"current_steps": 8045, "total_steps": 40000, "loss": 0.1611, "lr": 4.517452319197828e-05, "epoch": 6.58370855505526, "percentage": 20.11, "elapsed_time": "0:55:26", "remaining_time": "3:40:13", "throughput": 787.77, "total_tokens": 2620704} {"current_steps": 8050, "total_steps": 40000, "loss": 0.2445, "lr": 4.5168723655506265e-05, "epoch": 6.5878018829308225, "percentage": 20.12, "elapsed_time": "0:55:28", "remaining_time": "3:40:10", "throughput": 787.84, "total_tokens": 2622288} {"current_steps": 8055, "total_steps": 40000, "loss": 0.2118, "lr": 4.51629210087636e-05, "epoch": 6.591895210806386, "percentage": 20.14, "elapsed_time": "0:55:30", "remaining_time": "3:40:07", "throughput": 787.92, "total_tokens": 2623904} {"current_steps": 8060, "total_steps": 40000, "loss": 0.1875, "lr": 4.515711525264513e-05, "epoch": 6.595988538681948, "percentage": 20.15, "elapsed_time": "0:55:31", "remaining_time": "3:40:03", "throughput": 788.0, "total_tokens": 2625536} {"current_steps": 8065, "total_steps": 40000, "loss": 0.1944, "lr": 4.5151306388046175e-05, "epoch": 6.600081866557511, "percentage": 20.16, "elapsed_time": "0:55:33", "remaining_time": "3:40:00", "throughput": 788.07, "total_tokens": 2627136} {"current_steps": 8070, "total_steps": 40000, "loss": 0.2118, "lr": 4.514549441586255e-05, "epoch": 6.604175194433074, "percentage": 20.18, "elapsed_time": "0:55:35", "remaining_time": "3:39:56", "throughput": 788.14, "total_tokens": 2628720} {"current_steps": 8075, "total_steps": 40000, "loss": 0.1886, "lr": 4.513967933699051e-05, "epoch": 6.608268522308637, "percentage": 20.19, "elapsed_time": "0:55:37", "remaining_time": "3:39:53", "throughput": 788.22, "total_tokens": 2630320} {"current_steps": 8080, "total_steps": 40000, "loss": 0.1791, "lr": 4.513386115232684e-05, "epoch": 6.612361850184199, "percentage": 20.2, "elapsed_time": "0:55:38", "remaining_time": "3:39:49", "throughput": 788.29, "total_tokens": 2631920} {"current_steps": 8085, "total_steps": 40000, "loss": 0.207, "lr": 4.5128039862768745e-05, "epoch": 6.616455178059763, "percentage": 20.21, "elapsed_time": "0:55:40", "remaining_time": "3:39:46", "throughput": 788.38, "total_tokens": 2633568} {"current_steps": 8090, "total_steps": 40000, "loss": 0.1959, "lr": 4.512221546921397e-05, "epoch": 6.620548505935325, "percentage": 20.23, "elapsed_time": "0:55:42", "remaining_time": "3:39:42", "throughput": 788.46, "total_tokens": 2635184} {"current_steps": 8095, "total_steps": 40000, "loss": 0.1911, "lr": 4.5116387972560694e-05, "epoch": 6.624641833810888, "percentage": 20.24, "elapsed_time": "0:55:43", "remaining_time": "3:39:39", "throughput": 788.53, "total_tokens": 2636768} {"current_steps": 8100, "total_steps": 40000, "loss": 0.1748, "lr": 4.511055737370759e-05, "epoch": 6.628735161686451, "percentage": 20.25, "elapsed_time": "0:55:45", "remaining_time": "3:39:36", "throughput": 788.62, "total_tokens": 2638416} {"current_steps": 8105, "total_steps": 40000, "loss": 0.2079, "lr": 4.510472367355383e-05, "epoch": 6.632828489562014, "percentage": 20.26, "elapsed_time": "0:55:47", "remaining_time": "3:39:32", "throughput": 788.68, "total_tokens": 2639984} {"current_steps": 8110, "total_steps": 40000, "loss": 0.2082, "lr": 4.509888687299901e-05, "epoch": 6.636921817437576, "percentage": 20.28, "elapsed_time": "0:55:49", "remaining_time": "3:39:29", "throughput": 788.77, "total_tokens": 2641632} {"current_steps": 8115, "total_steps": 40000, "loss": 0.1895, "lr": 4.5093046972943266e-05, "epoch": 6.64101514531314, "percentage": 20.29, "elapsed_time": "0:55:50", "remaining_time": "3:39:25", "throughput": 788.85, "total_tokens": 2643248} {"current_steps": 8120, "total_steps": 40000, "loss": 0.2217, "lr": 4.508720397428717e-05, "epoch": 6.645108473188703, "percentage": 20.3, "elapsed_time": "0:55:52", "remaining_time": "3:39:22", "throughput": 788.92, "total_tokens": 2644864} {"current_steps": 8125, "total_steps": 40000, "loss": 0.1657, "lr": 4.508135787793178e-05, "epoch": 6.649201801064265, "percentage": 20.31, "elapsed_time": "0:55:54", "remaining_time": "3:39:18", "throughput": 789.03, "total_tokens": 2646576} {"current_steps": 8130, "total_steps": 40000, "loss": 0.183, "lr": 4.5075508684778664e-05, "epoch": 6.653295128939828, "percentage": 20.32, "elapsed_time": "0:55:55", "remaining_time": "3:39:15", "throughput": 789.11, "total_tokens": 2648208} {"current_steps": 8135, "total_steps": 40000, "loss": 0.2476, "lr": 4.506965639572982e-05, "epoch": 6.657388456815391, "percentage": 20.34, "elapsed_time": "0:55:57", "remaining_time": "3:39:11", "throughput": 789.19, "total_tokens": 2649808} {"current_steps": 8140, "total_steps": 40000, "loss": 0.2069, "lr": 4.506380101168774e-05, "epoch": 6.661481784690954, "percentage": 20.35, "elapsed_time": "0:55:59", "remaining_time": "3:39:08", "throughput": 789.27, "total_tokens": 2651456} {"current_steps": 8145, "total_steps": 40000, "loss": 0.2041, "lr": 4.505794253355542e-05, "epoch": 6.665575112566517, "percentage": 20.36, "elapsed_time": "0:56:01", "remaining_time": "3:39:05", "throughput": 789.35, "total_tokens": 2653072} {"current_steps": 8150, "total_steps": 40000, "loss": 0.1886, "lr": 4.5052080962236286e-05, "epoch": 6.669668440442079, "percentage": 20.38, "elapsed_time": "0:56:02", "remaining_time": "3:39:01", "throughput": 789.42, "total_tokens": 2654688} {"current_steps": 8155, "total_steps": 40000, "loss": 0.2081, "lr": 4.504621629863428e-05, "epoch": 6.673761768317642, "percentage": 20.39, "elapsed_time": "0:56:04", "remaining_time": "3:38:58", "throughput": 789.48, "total_tokens": 2656240} {"current_steps": 8160, "total_steps": 40000, "loss": 0.2365, "lr": 4.504034854365381e-05, "epoch": 6.6778550961932055, "percentage": 20.4, "elapsed_time": "0:56:06", "remaining_time": "3:38:55", "throughput": 789.55, "total_tokens": 2657840} {"current_steps": 8165, "total_steps": 40000, "loss": 0.1973, "lr": 4.503447769819974e-05, "epoch": 6.681948424068768, "percentage": 20.41, "elapsed_time": "0:56:07", "remaining_time": "3:38:51", "throughput": 789.65, "total_tokens": 2659520} {"current_steps": 8170, "total_steps": 40000, "loss": 0.1598, "lr": 4.502860376317745e-05, "epoch": 6.68604175194433, "percentage": 20.42, "elapsed_time": "0:56:09", "remaining_time": "3:38:48", "throughput": 789.73, "total_tokens": 2661168} {"current_steps": 8175, "total_steps": 40000, "loss": 0.1983, "lr": 4.502272673949276e-05, "epoch": 6.6901350798198935, "percentage": 20.44, "elapsed_time": "0:56:11", "remaining_time": "3:38:44", "throughput": 789.82, "total_tokens": 2662816} {"current_steps": 8180, "total_steps": 40000, "loss": 0.2255, "lr": 4.501684662805199e-05, "epoch": 6.694228407695457, "percentage": 20.45, "elapsed_time": "0:56:13", "remaining_time": "3:38:41", "throughput": 789.91, "total_tokens": 2664464} {"current_steps": 8185, "total_steps": 40000, "loss": 0.2829, "lr": 4.5010963429761924e-05, "epoch": 6.698321735571019, "percentage": 20.46, "elapsed_time": "0:56:14", "remaining_time": "3:38:37", "throughput": 789.97, "total_tokens": 2666032} {"current_steps": 8190, "total_steps": 40000, "loss": 0.2063, "lr": 4.500507714552982e-05, "epoch": 6.702415063446582, "percentage": 20.47, "elapsed_time": "0:56:16", "remaining_time": "3:38:34", "throughput": 790.05, "total_tokens": 2667648} {"current_steps": 8195, "total_steps": 40000, "loss": 0.2097, "lr": 4.499918777626342e-05, "epoch": 6.706508391322145, "percentage": 20.49, "elapsed_time": "0:56:18", "remaining_time": "3:38:31", "throughput": 790.14, "total_tokens": 2669296} {"current_steps": 8200, "total_steps": 40000, "loss": 0.2332, "lr": 4.499329532287093e-05, "epoch": 6.710601719197708, "percentage": 20.5, "elapsed_time": "0:56:19", "remaining_time": "3:38:27", "throughput": 790.21, "total_tokens": 2670896} {"current_steps": 8200, "total_steps": 40000, "eval_loss": 0.20404620468616486, "epoch": 6.710601719197708, "percentage": 20.5, "elapsed_time": "0:56:32", "remaining_time": "3:39:15", "throughput": 787.31, "total_tokens": 2670896} {"current_steps": 8205, "total_steps": 40000, "loss": 0.2047, "lr": 4.4987399786261064e-05, "epoch": 6.7146950470732705, "percentage": 20.51, "elapsed_time": "0:56:35", "remaining_time": "3:39:18", "throughput": 787.09, "total_tokens": 2672624} {"current_steps": 8210, "total_steps": 40000, "loss": 0.178, "lr": 4.498150116734297e-05, "epoch": 6.718788374948834, "percentage": 20.52, "elapsed_time": "0:56:37", "remaining_time": "3:39:14", "throughput": 787.18, "total_tokens": 2674272} {"current_steps": 8215, "total_steps": 40000, "loss": 0.2064, "lr": 4.4975599467026294e-05, "epoch": 6.722881702824396, "percentage": 20.54, "elapsed_time": "0:56:38", "remaining_time": "3:39:11", "throughput": 787.26, "total_tokens": 2675904} {"current_steps": 8220, "total_steps": 40000, "loss": 0.2573, "lr": 4.496969468622114e-05, "epoch": 6.726975030699959, "percentage": 20.55, "elapsed_time": "0:56:40", "remaining_time": "3:39:07", "throughput": 787.34, "total_tokens": 2677520} {"current_steps": 8225, "total_steps": 40000, "loss": 0.1591, "lr": 4.496378682583813e-05, "epoch": 6.731068358575522, "percentage": 20.56, "elapsed_time": "0:56:42", "remaining_time": "3:39:04", "throughput": 787.42, "total_tokens": 2679120} {"current_steps": 8230, "total_steps": 40000, "loss": 0.2263, "lr": 4.495787588678829e-05, "epoch": 6.735161686451085, "percentage": 20.57, "elapsed_time": "0:56:44", "remaining_time": "3:39:00", "throughput": 787.49, "total_tokens": 2680720} {"current_steps": 8235, "total_steps": 40000, "loss": 0.2161, "lr": 4.4951961869983196e-05, "epoch": 6.739255014326647, "percentage": 20.59, "elapsed_time": "0:56:45", "remaining_time": "3:38:57", "throughput": 787.57, "total_tokens": 2682352} {"current_steps": 8240, "total_steps": 40000, "loss": 0.1626, "lr": 4.494604477633485e-05, "epoch": 6.743348342202211, "percentage": 20.6, "elapsed_time": "0:56:47", "remaining_time": "3:38:54", "throughput": 787.66, "total_tokens": 2684016} {"current_steps": 8245, "total_steps": 40000, "loss": 0.2874, "lr": 4.4940124606755734e-05, "epoch": 6.747441670077773, "percentage": 20.61, "elapsed_time": "0:56:49", "remaining_time": "3:38:50", "throughput": 787.73, "total_tokens": 2685600} {"current_steps": 8250, "total_steps": 40000, "loss": 0.18, "lr": 4.493420136215882e-05, "epoch": 6.751534997953336, "percentage": 20.62, "elapsed_time": "0:56:51", "remaining_time": "3:38:47", "throughput": 787.79, "total_tokens": 2687152} {"current_steps": 8255, "total_steps": 40000, "loss": 0.278, "lr": 4.492827504345756e-05, "epoch": 6.755628325828899, "percentage": 20.64, "elapsed_time": "0:56:52", "remaining_time": "3:38:43", "throughput": 787.88, "total_tokens": 2688800} {"current_steps": 8260, "total_steps": 40000, "loss": 0.2334, "lr": 4.492234565156584e-05, "epoch": 6.759721653704462, "percentage": 20.65, "elapsed_time": "0:56:54", "remaining_time": "3:38:40", "throughput": 787.95, "total_tokens": 2690416} {"current_steps": 8265, "total_steps": 40000, "loss": 0.1962, "lr": 4.491641318739807e-05, "epoch": 6.763814981580024, "percentage": 20.66, "elapsed_time": "0:56:56", "remaining_time": "3:38:36", "throughput": 788.03, "total_tokens": 2692032} {"current_steps": 8270, "total_steps": 40000, "loss": 0.1933, "lr": 4.4910477651869096e-05, "epoch": 6.767908309455588, "percentage": 20.67, "elapsed_time": "0:56:57", "remaining_time": "3:38:33", "throughput": 788.09, "total_tokens": 2693600} {"current_steps": 8275, "total_steps": 40000, "loss": 0.1877, "lr": 4.4904539045894254e-05, "epoch": 6.77200163733115, "percentage": 20.69, "elapsed_time": "0:56:59", "remaining_time": "3:38:30", "throughput": 788.16, "total_tokens": 2695200} {"current_steps": 8280, "total_steps": 40000, "loss": 0.1632, "lr": 4.4898597370389364e-05, "epoch": 6.776094965206713, "percentage": 20.7, "elapsed_time": "0:57:01", "remaining_time": "3:38:26", "throughput": 788.25, "total_tokens": 2696864} {"current_steps": 8285, "total_steps": 40000, "loss": 0.1764, "lr": 4.489265262627069e-05, "epoch": 6.780188293082276, "percentage": 20.71, "elapsed_time": "0:57:03", "remaining_time": "3:38:23", "throughput": 788.32, "total_tokens": 2698448} {"current_steps": 8290, "total_steps": 40000, "loss": 0.2163, "lr": 4.488670481445499e-05, "epoch": 6.784281620957839, "percentage": 20.72, "elapsed_time": "0:57:04", "remaining_time": "3:38:19", "throughput": 788.4, "total_tokens": 2700064} {"current_steps": 8295, "total_steps": 40000, "loss": 0.24, "lr": 4.488075393585951e-05, "epoch": 6.788374948833401, "percentage": 20.74, "elapsed_time": "0:57:06", "remaining_time": "3:38:16", "throughput": 788.49, "total_tokens": 2701712} {"current_steps": 8300, "total_steps": 40000, "loss": 0.157, "lr": 4.487479999140193e-05, "epoch": 6.792468276708965, "percentage": 20.75, "elapsed_time": "0:57:08", "remaining_time": "3:38:13", "throughput": 788.59, "total_tokens": 2703440} {"current_steps": 8305, "total_steps": 40000, "loss": 0.1931, "lr": 4.4868842982000425e-05, "epoch": 6.796561604584527, "percentage": 20.76, "elapsed_time": "0:57:09", "remaining_time": "3:38:09", "throughput": 788.68, "total_tokens": 2705088} {"current_steps": 8310, "total_steps": 40000, "loss": 0.129, "lr": 4.486288290857365e-05, "epoch": 6.80065493246009, "percentage": 20.77, "elapsed_time": "0:57:11", "remaining_time": "3:38:06", "throughput": 788.76, "total_tokens": 2706736} {"current_steps": 8315, "total_steps": 40000, "loss": 0.2612, "lr": 4.4856919772040715e-05, "epoch": 6.804748260335653, "percentage": 20.79, "elapsed_time": "0:57:13", "remaining_time": "3:38:02", "throughput": 788.83, "total_tokens": 2708320} {"current_steps": 8320, "total_steps": 40000, "loss": 0.1797, "lr": 4.485095357332122e-05, "epoch": 6.808841588211216, "percentage": 20.8, "elapsed_time": "0:57:15", "remaining_time": "3:37:59", "throughput": 788.91, "total_tokens": 2709936} {"current_steps": 8325, "total_steps": 40000, "loss": 0.2216, "lr": 4.484498431333521e-05, "epoch": 6.812934916086778, "percentage": 20.81, "elapsed_time": "0:57:16", "remaining_time": "3:37:56", "throughput": 788.99, "total_tokens": 2711584} {"current_steps": 8330, "total_steps": 40000, "loss": 0.1969, "lr": 4.4839011993003245e-05, "epoch": 6.8170282439623415, "percentage": 20.82, "elapsed_time": "0:57:18", "remaining_time": "3:37:52", "throughput": 789.07, "total_tokens": 2713200} {"current_steps": 8335, "total_steps": 40000, "loss": 0.2097, "lr": 4.4833036613246305e-05, "epoch": 6.821121571837904, "percentage": 20.84, "elapsed_time": "0:57:20", "remaining_time": "3:37:49", "throughput": 789.14, "total_tokens": 2714816} {"current_steps": 8340, "total_steps": 40000, "loss": 0.1674, "lr": 4.482705817498589e-05, "epoch": 6.825214899713467, "percentage": 20.85, "elapsed_time": "0:57:21", "remaining_time": "3:37:46", "throughput": 789.22, "total_tokens": 2716432} {"current_steps": 8345, "total_steps": 40000, "loss": 0.1863, "lr": 4.4821076679143934e-05, "epoch": 6.82930822758903, "percentage": 20.86, "elapsed_time": "0:57:23", "remaining_time": "3:37:42", "throughput": 789.29, "total_tokens": 2718048} {"current_steps": 8350, "total_steps": 40000, "loss": 0.188, "lr": 4.481509212664288e-05, "epoch": 6.833401555464593, "percentage": 20.88, "elapsed_time": "0:57:25", "remaining_time": "3:37:39", "throughput": 789.37, "total_tokens": 2719680} {"current_steps": 8355, "total_steps": 40000, "loss": 0.2056, "lr": 4.480910451840559e-05, "epoch": 6.837494883340155, "percentage": 20.89, "elapsed_time": "0:57:27", "remaining_time": "3:37:35", "throughput": 789.45, "total_tokens": 2721296} {"current_steps": 8360, "total_steps": 40000, "loss": 0.219, "lr": 4.480311385535546e-05, "epoch": 6.8415882112157185, "percentage": 20.9, "elapsed_time": "0:57:28", "remaining_time": "3:37:32", "throughput": 789.54, "total_tokens": 2722960} {"current_steps": 8365, "total_steps": 40000, "loss": 0.2213, "lr": 4.47971201384163e-05, "epoch": 6.845681539091281, "percentage": 20.91, "elapsed_time": "0:57:30", "remaining_time": "3:37:29", "throughput": 789.6, "total_tokens": 2724528} {"current_steps": 8370, "total_steps": 40000, "loss": 0.1624, "lr": 4.4791123368512446e-05, "epoch": 6.849774866966844, "percentage": 20.93, "elapsed_time": "0:57:32", "remaining_time": "3:37:25", "throughput": 789.68, "total_tokens": 2726176} {"current_steps": 8375, "total_steps": 40000, "loss": 0.1855, "lr": 4.478512354656864e-05, "epoch": 6.8538681948424065, "percentage": 20.94, "elapsed_time": "0:57:33", "remaining_time": "3:37:22", "throughput": 789.79, "total_tokens": 2727888} {"current_steps": 8380, "total_steps": 40000, "loss": 0.1824, "lr": 4.477912067351016e-05, "epoch": 6.85796152271797, "percentage": 20.95, "elapsed_time": "0:57:35", "remaining_time": "3:37:19", "throughput": 789.87, "total_tokens": 2729536} {"current_steps": 8385, "total_steps": 40000, "loss": 0.1841, "lr": 4.477311475026271e-05, "epoch": 6.862054850593532, "percentage": 20.96, "elapsed_time": "0:57:37", "remaining_time": "3:37:15", "throughput": 789.95, "total_tokens": 2731168} {"current_steps": 8390, "total_steps": 40000, "loss": 0.1731, "lr": 4.476710577775248e-05, "epoch": 6.866148178469095, "percentage": 20.97, "elapsed_time": "0:57:39", "remaining_time": "3:37:12", "throughput": 790.03, "total_tokens": 2732800} {"current_steps": 8395, "total_steps": 40000, "loss": 0.1749, "lr": 4.476109375690612e-05, "epoch": 6.870241506344659, "percentage": 20.99, "elapsed_time": "0:57:40", "remaining_time": "3:37:09", "throughput": 790.14, "total_tokens": 2734528} {"current_steps": 8400, "total_steps": 40000, "loss": 0.1563, "lr": 4.4755078688650784e-05, "epoch": 6.874334834220221, "percentage": 21.0, "elapsed_time": "0:57:42", "remaining_time": "3:37:05", "throughput": 790.22, "total_tokens": 2736160} {"current_steps": 8400, "total_steps": 40000, "eval_loss": 0.20534959435462952, "epoch": 6.874334834220221, "percentage": 21.0, "elapsed_time": "0:57:55", "remaining_time": "3:37:52", "throughput": 787.38, "total_tokens": 2736160} {"current_steps": 8405, "total_steps": 40000, "loss": 0.2082, "lr": 4.474906057391406e-05, "epoch": 6.8784281620957834, "percentage": 21.01, "elapsed_time": "0:57:58", "remaining_time": "3:37:54", "throughput": 787.13, "total_tokens": 2737760} {"current_steps": 8410, "total_steps": 40000, "loss": 0.1939, "lr": 4.4743039413624e-05, "epoch": 6.882521489971347, "percentage": 21.02, "elapsed_time": "0:57:59", "remaining_time": "3:37:51", "throughput": 787.2, "total_tokens": 2739376} {"current_steps": 8415, "total_steps": 40000, "loss": 0.1486, "lr": 4.473701520870916e-05, "epoch": 6.88661481784691, "percentage": 21.04, "elapsed_time": "0:58:01", "remaining_time": "3:37:47", "throughput": 787.3, "total_tokens": 2741072} {"current_steps": 8420, "total_steps": 40000, "loss": 0.1889, "lr": 4.4730987960098544e-05, "epoch": 6.890708145722472, "percentage": 21.05, "elapsed_time": "0:58:03", "remaining_time": "3:37:44", "throughput": 787.36, "total_tokens": 2742656} {"current_steps": 8425, "total_steps": 40000, "loss": 0.1524, "lr": 4.4724957668721635e-05, "epoch": 6.894801473598035, "percentage": 21.06, "elapsed_time": "0:58:05", "remaining_time": "3:37:41", "throughput": 787.42, "total_tokens": 2744208} {"current_steps": 8430, "total_steps": 40000, "loss": 0.2063, "lr": 4.471892433550836e-05, "epoch": 6.898894801473598, "percentage": 21.07, "elapsed_time": "0:58:06", "remaining_time": "3:37:37", "throughput": 787.48, "total_tokens": 2745760} {"current_steps": 8435, "total_steps": 40000, "loss": 0.2098, "lr": 4.471288796138916e-05, "epoch": 6.902988129349161, "percentage": 21.09, "elapsed_time": "0:58:08", "remaining_time": "3:37:35", "throughput": 787.49, "total_tokens": 2747376} {"current_steps": 8440, "total_steps": 40000, "loss": 0.2088, "lr": 4.470684854729491e-05, "epoch": 6.907081457224724, "percentage": 21.1, "elapsed_time": "0:58:10", "remaining_time": "3:37:32", "throughput": 787.57, "total_tokens": 2749008} {"current_steps": 8445, "total_steps": 40000, "loss": 0.2178, "lr": 4.4700806094156955e-05, "epoch": 6.911174785100286, "percentage": 21.11, "elapsed_time": "0:58:12", "remaining_time": "3:37:28", "throughput": 787.65, "total_tokens": 2750640} {"current_steps": 8450, "total_steps": 40000, "loss": 0.197, "lr": 4.469476060290713e-05, "epoch": 6.915268112975849, "percentage": 21.12, "elapsed_time": "0:58:13", "remaining_time": "3:37:25", "throughput": 787.74, "total_tokens": 2752304} {"current_steps": 8455, "total_steps": 40000, "loss": 0.1698, "lr": 4.468871207447772e-05, "epoch": 6.919361440851413, "percentage": 21.14, "elapsed_time": "0:58:15", "remaining_time": "3:37:21", "throughput": 787.8, "total_tokens": 2753872} {"current_steps": 8460, "total_steps": 40000, "loss": 0.2377, "lr": 4.4682660509801486e-05, "epoch": 6.923454768726975, "percentage": 21.15, "elapsed_time": "0:58:17", "remaining_time": "3:37:18", "throughput": 787.88, "total_tokens": 2755504} {"current_steps": 8465, "total_steps": 40000, "loss": 0.2191, "lr": 4.467660590981165e-05, "epoch": 6.927548096602538, "percentage": 21.16, "elapsed_time": "0:58:19", "remaining_time": "3:37:15", "throughput": 787.96, "total_tokens": 2757136} {"current_steps": 8470, "total_steps": 40000, "loss": 0.1834, "lr": 4.467054827544191e-05, "epoch": 6.931641424478101, "percentage": 21.18, "elapsed_time": "0:58:20", "remaining_time": "3:37:11", "throughput": 788.05, "total_tokens": 2758784} {"current_steps": 8475, "total_steps": 40000, "loss": 0.2607, "lr": 4.4664487607626434e-05, "epoch": 6.935734752353664, "percentage": 21.19, "elapsed_time": "0:58:22", "remaining_time": "3:37:08", "throughput": 788.15, "total_tokens": 2760512} {"current_steps": 8480, "total_steps": 40000, "loss": 0.2078, "lr": 4.4658423907299845e-05, "epoch": 6.939828080229226, "percentage": 21.2, "elapsed_time": "0:58:24", "remaining_time": "3:37:05", "throughput": 788.24, "total_tokens": 2762160} {"current_steps": 8485, "total_steps": 40000, "loss": 0.201, "lr": 4.465235717539725e-05, "epoch": 6.9439214081047895, "percentage": 21.21, "elapsed_time": "0:58:25", "remaining_time": "3:37:01", "throughput": 788.32, "total_tokens": 2763792} {"current_steps": 8490, "total_steps": 40000, "loss": 0.1848, "lr": 4.464628741285421e-05, "epoch": 6.948014735980352, "percentage": 21.22, "elapsed_time": "0:58:27", "remaining_time": "3:36:58", "throughput": 788.41, "total_tokens": 2765472} {"current_steps": 8495, "total_steps": 40000, "loss": 0.1845, "lr": 4.4640214620606754e-05, "epoch": 6.952108063855915, "percentage": 21.24, "elapsed_time": "0:58:29", "remaining_time": "3:36:55", "throughput": 788.48, "total_tokens": 2767088} {"current_steps": 8500, "total_steps": 40000, "loss": 0.191, "lr": 4.46341387995914e-05, "epoch": 6.956201391731478, "percentage": 21.25, "elapsed_time": "0:58:31", "remaining_time": "3:36:51", "throughput": 788.55, "total_tokens": 2768704} {"current_steps": 8505, "total_steps": 40000, "loss": 0.1811, "lr": 4.4628059950745106e-05, "epoch": 6.960294719607041, "percentage": 21.26, "elapsed_time": "0:58:32", "remaining_time": "3:36:48", "throughput": 788.63, "total_tokens": 2770336} {"current_steps": 8510, "total_steps": 40000, "loss": 0.2109, "lr": 4.4621978075005297e-05, "epoch": 6.964388047482603, "percentage": 21.27, "elapsed_time": "0:58:34", "remaining_time": "3:36:45", "throughput": 788.74, "total_tokens": 2772064} {"current_steps": 8515, "total_steps": 40000, "loss": 0.2056, "lr": 4.461589317330989e-05, "epoch": 6.9684813753581665, "percentage": 21.29, "elapsed_time": "0:58:36", "remaining_time": "3:36:41", "throughput": 788.8, "total_tokens": 2773648} {"current_steps": 8520, "total_steps": 40000, "loss": 0.1837, "lr": 4.460980524659724e-05, "epoch": 6.972574703233729, "percentage": 21.3, "elapsed_time": "0:58:37", "remaining_time": "3:36:38", "throughput": 788.91, "total_tokens": 2775376} {"current_steps": 8525, "total_steps": 40000, "loss": 0.2023, "lr": 4.46037142958062e-05, "epoch": 6.976668031109292, "percentage": 21.31, "elapsed_time": "0:58:39", "remaining_time": "3:36:35", "throughput": 788.97, "total_tokens": 2776928} {"current_steps": 8530, "total_steps": 40000, "loss": 0.2394, "lr": 4.4597620321876046e-05, "epoch": 6.9807613589848545, "percentage": 21.32, "elapsed_time": "0:58:41", "remaining_time": "3:36:31", "throughput": 789.04, "total_tokens": 2778528} {"current_steps": 8535, "total_steps": 40000, "loss": 0.1686, "lr": 4.459152332574656e-05, "epoch": 6.984854686860418, "percentage": 21.34, "elapsed_time": "0:58:43", "remaining_time": "3:36:28", "throughput": 789.1, "total_tokens": 2780112} {"current_steps": 8540, "total_steps": 40000, "loss": 0.2759, "lr": 4.4585423308357985e-05, "epoch": 6.98894801473598, "percentage": 21.35, "elapsed_time": "0:58:44", "remaining_time": "3:36:25", "throughput": 789.17, "total_tokens": 2781728} {"current_steps": 8545, "total_steps": 40000, "loss": 0.1863, "lr": 4.457932027065102e-05, "epoch": 6.993041342611543, "percentage": 21.36, "elapsed_time": "0:58:46", "remaining_time": "3:36:21", "throughput": 789.27, "total_tokens": 2783424} {"current_steps": 8550, "total_steps": 40000, "loss": 0.2219, "lr": 4.45732142135668e-05, "epoch": 6.997134670487106, "percentage": 21.38, "elapsed_time": "0:58:48", "remaining_time": "3:36:18", "throughput": 789.34, "total_tokens": 2785040} {"current_steps": 8555, "total_steps": 40000, "loss": 0.2282, "lr": 4.4567105138046986e-05, "epoch": 7.000818665575113, "percentage": 21.39, "elapsed_time": "0:58:50", "remaining_time": "3:36:15", "throughput": 789.31, "total_tokens": 2786416} {"current_steps": 8560, "total_steps": 40000, "loss": 0.1964, "lr": 4.456099304503365e-05, "epoch": 7.004911993450675, "percentage": 21.4, "elapsed_time": "0:58:51", "remaining_time": "3:36:12", "throughput": 789.4, "total_tokens": 2788080} {"current_steps": 8565, "total_steps": 40000, "loss": 0.2318, "lr": 4.455487793546939e-05, "epoch": 7.009005321326239, "percentage": 21.41, "elapsed_time": "0:58:53", "remaining_time": "3:36:09", "throughput": 789.46, "total_tokens": 2789664} {"current_steps": 8570, "total_steps": 40000, "loss": 0.2217, "lr": 4.454875981029719e-05, "epoch": 7.013098649201801, "percentage": 21.43, "elapsed_time": "0:58:55", "remaining_time": "3:36:05", "throughput": 789.57, "total_tokens": 2791408} {"current_steps": 8575, "total_steps": 40000, "loss": 0.2218, "lr": 4.454263867046057e-05, "epoch": 7.017191977077364, "percentage": 21.44, "elapsed_time": "0:58:57", "remaining_time": "3:36:02", "throughput": 789.65, "total_tokens": 2793040} {"current_steps": 8580, "total_steps": 40000, "loss": 0.1809, "lr": 4.4536514516903484e-05, "epoch": 7.021285304952927, "percentage": 21.45, "elapsed_time": "0:58:58", "remaining_time": "3:35:59", "throughput": 789.71, "total_tokens": 2794624} {"current_steps": 8585, "total_steps": 40000, "loss": 0.2373, "lr": 4.453038735057034e-05, "epoch": 7.02537863282849, "percentage": 21.46, "elapsed_time": "0:59:00", "remaining_time": "3:35:55", "throughput": 789.79, "total_tokens": 2796256} {"current_steps": 8590, "total_steps": 40000, "loss": 0.2136, "lr": 4.4524257172406034e-05, "epoch": 7.029471960704052, "percentage": 21.48, "elapsed_time": "0:59:02", "remaining_time": "3:35:52", "throughput": 789.86, "total_tokens": 2797872} {"current_steps": 8595, "total_steps": 40000, "loss": 0.2006, "lr": 4.451812398335592e-05, "epoch": 7.033565288579616, "percentage": 21.49, "elapsed_time": "0:59:03", "remaining_time": "3:35:49", "throughput": 789.93, "total_tokens": 2799488} {"current_steps": 8600, "total_steps": 40000, "loss": 0.2354, "lr": 4.4511987784365805e-05, "epoch": 7.037658616455178, "percentage": 21.5, "elapsed_time": "0:59:05", "remaining_time": "3:35:45", "throughput": 790.01, "total_tokens": 2801120} {"current_steps": 8600, "total_steps": 40000, "eval_loss": 0.20484226942062378, "epoch": 7.037658616455178, "percentage": 21.5, "elapsed_time": "0:59:18", "remaining_time": "3:36:31", "throughput": 787.25, "total_tokens": 2801120} {"current_steps": 8605, "total_steps": 40000, "loss": 0.2479, "lr": 4.450584857638197e-05, "epoch": 7.041751944330741, "percentage": 21.51, "elapsed_time": "0:59:21", "remaining_time": "3:36:33", "throughput": 786.99, "total_tokens": 2802752} {"current_steps": 8610, "total_steps": 40000, "loss": 0.1616, "lr": 4.449970636035116e-05, "epoch": 7.045845272206304, "percentage": 21.52, "elapsed_time": "0:59:23", "remaining_time": "3:36:30", "throughput": 787.08, "total_tokens": 2804416} {"current_steps": 8615, "total_steps": 40000, "loss": 0.2078, "lr": 4.4493561137220574e-05, "epoch": 7.049938600081867, "percentage": 21.54, "elapsed_time": "0:59:24", "remaining_time": "3:36:26", "throughput": 787.15, "total_tokens": 2806016} {"current_steps": 8620, "total_steps": 40000, "loss": 0.1926, "lr": 4.44874129079379e-05, "epoch": 7.054031927957429, "percentage": 21.55, "elapsed_time": "0:59:26", "remaining_time": "3:36:23", "throughput": 787.21, "total_tokens": 2807600} {"current_steps": 8625, "total_steps": 40000, "loss": 0.1799, "lr": 4.4481261673451255e-05, "epoch": 7.0581252558329926, "percentage": 21.56, "elapsed_time": "0:59:28", "remaining_time": "3:36:20", "throughput": 787.29, "total_tokens": 2809232} {"current_steps": 8630, "total_steps": 40000, "loss": 0.1905, "lr": 4.4475107434709245e-05, "epoch": 7.062218583708555, "percentage": 21.57, "elapsed_time": "0:59:29", "remaining_time": "3:36:16", "throughput": 787.37, "total_tokens": 2810864} {"current_steps": 8635, "total_steps": 40000, "loss": 0.2134, "lr": 4.446895019266093e-05, "epoch": 7.066311911584118, "percentage": 21.59, "elapsed_time": "0:59:31", "remaining_time": "3:36:13", "throughput": 787.44, "total_tokens": 2812480} {"current_steps": 8640, "total_steps": 40000, "loss": 0.1798, "lr": 4.446278994825583e-05, "epoch": 7.070405239459681, "percentage": 21.6, "elapsed_time": "0:59:33", "remaining_time": "3:36:10", "throughput": 787.52, "total_tokens": 2814096} {"current_steps": 8645, "total_steps": 40000, "loss": 0.1541, "lr": 4.445662670244394e-05, "epoch": 7.074498567335244, "percentage": 21.61, "elapsed_time": "0:59:35", "remaining_time": "3:36:06", "throughput": 787.59, "total_tokens": 2815728} {"current_steps": 8650, "total_steps": 40000, "loss": 0.2482, "lr": 4.44504604561757e-05, "epoch": 7.078591895210806, "percentage": 21.62, "elapsed_time": "0:59:36", "remaining_time": "3:36:03", "throughput": 787.67, "total_tokens": 2817344} {"current_steps": 8655, "total_steps": 40000, "loss": 0.1917, "lr": 4.4444291210402035e-05, "epoch": 7.0826852230863695, "percentage": 21.64, "elapsed_time": "0:59:38", "remaining_time": "3:36:00", "throughput": 787.73, "total_tokens": 2818928} {"current_steps": 8660, "total_steps": 40000, "loss": 0.1664, "lr": 4.443811896607431e-05, "epoch": 7.086778550961932, "percentage": 21.65, "elapsed_time": "0:59:40", "remaining_time": "3:35:56", "throughput": 787.81, "total_tokens": 2820560} {"current_steps": 8665, "total_steps": 40000, "loss": 0.1244, "lr": 4.443194372414436e-05, "epoch": 7.090871878837495, "percentage": 21.66, "elapsed_time": "0:59:41", "remaining_time": "3:35:53", "throughput": 787.89, "total_tokens": 2822208} {"current_steps": 8670, "total_steps": 40000, "loss": 0.1973, "lr": 4.442576548556449e-05, "epoch": 7.0949652067130575, "percentage": 21.68, "elapsed_time": "0:59:43", "remaining_time": "3:35:50", "throughput": 787.97, "total_tokens": 2823856} {"current_steps": 8675, "total_steps": 40000, "loss": 0.1591, "lr": 4.441958425128747e-05, "epoch": 7.099058534588621, "percentage": 21.69, "elapsed_time": "0:59:45", "remaining_time": "3:35:46", "throughput": 788.04, "total_tokens": 2825456} {"current_steps": 8680, "total_steps": 40000, "loss": 0.1929, "lr": 4.4413400022266515e-05, "epoch": 7.103151862464183, "percentage": 21.7, "elapsed_time": "0:59:47", "remaining_time": "3:35:43", "throughput": 788.11, "total_tokens": 2827056} {"current_steps": 8685, "total_steps": 40000, "loss": 0.2453, "lr": 4.4407212799455313e-05, "epoch": 7.107245190339746, "percentage": 21.71, "elapsed_time": "0:59:48", "remaining_time": "3:35:40", "throughput": 788.18, "total_tokens": 2828672} {"current_steps": 8690, "total_steps": 40000, "loss": 0.1618, "lr": 4.4401022583808003e-05, "epoch": 7.111338518215309, "percentage": 21.73, "elapsed_time": "0:59:50", "remaining_time": "3:35:36", "throughput": 788.26, "total_tokens": 2830304} {"current_steps": 8695, "total_steps": 40000, "loss": 0.2671, "lr": 4.439482937627921e-05, "epoch": 7.115431846090872, "percentage": 21.74, "elapsed_time": "0:59:52", "remaining_time": "3:35:33", "throughput": 788.33, "total_tokens": 2831920} {"current_steps": 8700, "total_steps": 40000, "loss": 0.2013, "lr": 4.4388633177824004e-05, "epoch": 7.1195251739664345, "percentage": 21.75, "elapsed_time": "0:59:54", "remaining_time": "3:35:30", "throughput": 788.4, "total_tokens": 2833520} {"current_steps": 8705, "total_steps": 40000, "loss": 0.2365, "lr": 4.4382433989397895e-05, "epoch": 7.123618501841998, "percentage": 21.76, "elapsed_time": "0:59:55", "remaining_time": "3:35:26", "throughput": 788.47, "total_tokens": 2835136} {"current_steps": 8710, "total_steps": 40000, "loss": 0.1977, "lr": 4.4376231811956895e-05, "epoch": 7.12771182971756, "percentage": 21.77, "elapsed_time": "0:59:57", "remaining_time": "3:35:23", "throughput": 788.55, "total_tokens": 2836752} {"current_steps": 8715, "total_steps": 40000, "loss": 0.1566, "lr": 4.437002664645745e-05, "epoch": 7.131805157593123, "percentage": 21.79, "elapsed_time": "0:59:59", "remaining_time": "3:35:20", "throughput": 788.61, "total_tokens": 2838352} {"current_steps": 8720, "total_steps": 40000, "loss": 0.2145, "lr": 4.436381849385649e-05, "epoch": 7.135898485468686, "percentage": 21.8, "elapsed_time": "1:00:00", "remaining_time": "3:35:16", "throughput": 788.68, "total_tokens": 2839968} {"current_steps": 8725, "total_steps": 40000, "loss": 0.1969, "lr": 4.435760735511136e-05, "epoch": 7.139991813344249, "percentage": 21.81, "elapsed_time": "1:00:02", "remaining_time": "3:35:13", "throughput": 788.75, "total_tokens": 2841552} {"current_steps": 8730, "total_steps": 40000, "loss": 0.2191, "lr": 4.435139323117992e-05, "epoch": 7.144085141219811, "percentage": 21.82, "elapsed_time": "1:00:04", "remaining_time": "3:35:10", "throughput": 788.85, "total_tokens": 2843280} {"current_steps": 8735, "total_steps": 40000, "loss": 0.1781, "lr": 4.434517612302046e-05, "epoch": 7.148178469095375, "percentage": 21.84, "elapsed_time": "1:00:06", "remaining_time": "3:35:07", "throughput": 788.92, "total_tokens": 2844880} {"current_steps": 8740, "total_steps": 40000, "loss": 0.1515, "lr": 4.433895603159174e-05, "epoch": 7.152271796970937, "percentage": 21.85, "elapsed_time": "1:00:07", "remaining_time": "3:35:03", "throughput": 788.98, "total_tokens": 2846464} {"current_steps": 8745, "total_steps": 40000, "loss": 0.2085, "lr": 4.433273295785296e-05, "epoch": 7.1563651248465, "percentage": 21.86, "elapsed_time": "1:00:09", "remaining_time": "3:35:00", "throughput": 789.05, "total_tokens": 2848064} {"current_steps": 8750, "total_steps": 40000, "loss": 0.2457, "lr": 4.432650690276382e-05, "epoch": 7.160458452722063, "percentage": 21.88, "elapsed_time": "1:00:11", "remaining_time": "3:34:57", "throughput": 789.14, "total_tokens": 2849744} {"current_steps": 8755, "total_steps": 40000, "loss": 0.2013, "lr": 4.4320277867284435e-05, "epoch": 7.164551780597626, "percentage": 21.89, "elapsed_time": "1:00:12", "remaining_time": "3:34:53", "throughput": 789.22, "total_tokens": 2851392} {"current_steps": 8760, "total_steps": 40000, "loss": 0.2166, "lr": 4.431404585237541e-05, "epoch": 7.168645108473188, "percentage": 21.9, "elapsed_time": "1:00:14", "remaining_time": "3:34:50", "throughput": 789.29, "total_tokens": 2852992} {"current_steps": 8765, "total_steps": 40000, "loss": 0.1991, "lr": 4.43078108589978e-05, "epoch": 7.172738436348752, "percentage": 21.91, "elapsed_time": "1:00:16", "remaining_time": "3:34:47", "throughput": 789.37, "total_tokens": 2854656} {"current_steps": 8770, "total_steps": 40000, "loss": 0.2278, "lr": 4.4301572888113116e-05, "epoch": 7.176831764224314, "percentage": 21.93, "elapsed_time": "1:00:18", "remaining_time": "3:34:44", "throughput": 789.43, "total_tokens": 2856224} {"current_steps": 8775, "total_steps": 40000, "loss": 0.2009, "lr": 4.4295331940683337e-05, "epoch": 7.180925092099877, "percentage": 21.94, "elapsed_time": "1:00:19", "remaining_time": "3:34:40", "throughput": 789.51, "total_tokens": 2857872} {"current_steps": 8780, "total_steps": 40000, "loss": 0.1973, "lr": 4.428908801767089e-05, "epoch": 7.18501841997544, "percentage": 21.95, "elapsed_time": "1:00:21", "remaining_time": "3:34:37", "throughput": 789.55, "total_tokens": 2859392} {"current_steps": 8785, "total_steps": 40000, "loss": 0.1343, "lr": 4.428284112003868e-05, "epoch": 7.189111747851003, "percentage": 21.96, "elapsed_time": "1:00:23", "remaining_time": "3:34:34", "throughput": 789.64, "total_tokens": 2861072} {"current_steps": 8790, "total_steps": 40000, "loss": 0.2642, "lr": 4.4276591248750033e-05, "epoch": 7.193205075726565, "percentage": 21.98, "elapsed_time": "1:00:24", "remaining_time": "3:34:30", "throughput": 789.71, "total_tokens": 2862656} {"current_steps": 8795, "total_steps": 40000, "loss": 0.1909, "lr": 4.4270338404768774e-05, "epoch": 7.197298403602129, "percentage": 21.99, "elapsed_time": "1:00:26", "remaining_time": "3:34:27", "throughput": 789.77, "total_tokens": 2864240} {"current_steps": 8800, "total_steps": 40000, "loss": 0.2675, "lr": 4.426408258905917e-05, "epoch": 7.201391731477691, "percentage": 22.0, "elapsed_time": "1:00:28", "remaining_time": "3:34:24", "throughput": 789.85, "total_tokens": 2865872} {"current_steps": 8800, "total_steps": 40000, "eval_loss": 0.20446620881557465, "epoch": 7.201391731477691, "percentage": 22.0, "elapsed_time": "1:00:40", "remaining_time": "3:35:08", "throughput": 787.15, "total_tokens": 2865872} {"current_steps": 8805, "total_steps": 40000, "loss": 0.1805, "lr": 4.425782380258594e-05, "epoch": 7.205485059353254, "percentage": 22.01, "elapsed_time": "1:00:43", "remaining_time": "3:35:10", "throughput": 786.92, "total_tokens": 2867520} {"current_steps": 8810, "total_steps": 40000, "loss": 0.1661, "lr": 4.425156204631427e-05, "epoch": 7.209578387228817, "percentage": 22.02, "elapsed_time": "1:00:45", "remaining_time": "3:35:06", "throughput": 787.0, "total_tokens": 2869168} {"current_steps": 8815, "total_steps": 40000, "loss": 0.1567, "lr": 4.424529732120981e-05, "epoch": 7.21367171510438, "percentage": 22.04, "elapsed_time": "1:00:47", "remaining_time": "3:35:03", "throughput": 787.08, "total_tokens": 2870832} {"current_steps": 8820, "total_steps": 40000, "loss": 0.1673, "lr": 4.423902962823864e-05, "epoch": 7.217765042979943, "percentage": 22.05, "elapsed_time": "1:00:49", "remaining_time": "3:35:00", "throughput": 787.15, "total_tokens": 2872432} {"current_steps": 8825, "total_steps": 40000, "loss": 0.1869, "lr": 4.423275896836733e-05, "epoch": 7.2218583708555055, "percentage": 22.06, "elapsed_time": "1:00:50", "remaining_time": "3:34:57", "throughput": 787.23, "total_tokens": 2874064} {"current_steps": 8830, "total_steps": 40000, "loss": 0.2361, "lr": 4.42264853425629e-05, "epoch": 7.225951698731068, "percentage": 22.07, "elapsed_time": "1:00:52", "remaining_time": "3:34:53", "throughput": 787.3, "total_tokens": 2875696} {"current_steps": 8835, "total_steps": 40000, "loss": 0.2583, "lr": 4.4220208751792816e-05, "epoch": 7.230045026606631, "percentage": 22.09, "elapsed_time": "1:00:54", "remaining_time": "3:34:50", "throughput": 787.37, "total_tokens": 2877280} {"current_steps": 8840, "total_steps": 40000, "loss": 0.2016, "lr": 4.421392919702499e-05, "epoch": 7.234138354482194, "percentage": 22.1, "elapsed_time": "1:00:56", "remaining_time": "3:34:47", "throughput": 787.43, "total_tokens": 2878880} {"current_steps": 8845, "total_steps": 40000, "loss": 0.1941, "lr": 4.4207646679227846e-05, "epoch": 7.238231682357757, "percentage": 22.11, "elapsed_time": "1:00:57", "remaining_time": "3:34:43", "throughput": 787.51, "total_tokens": 2880512} {"current_steps": 8850, "total_steps": 40000, "loss": 0.2011, "lr": 4.42013611993702e-05, "epoch": 7.24232501023332, "percentage": 22.12, "elapsed_time": "1:00:59", "remaining_time": "3:34:40", "throughput": 787.6, "total_tokens": 2882208} {"current_steps": 8855, "total_steps": 40000, "loss": 0.1842, "lr": 4.419507275842135e-05, "epoch": 7.2464183381088825, "percentage": 22.14, "elapsed_time": "1:01:01", "remaining_time": "3:34:37", "throughput": 787.66, "total_tokens": 2883792} {"current_steps": 8860, "total_steps": 40000, "loss": 0.2276, "lr": 4.418878135735106e-05, "epoch": 7.250511665984446, "percentage": 22.15, "elapsed_time": "1:01:02", "remaining_time": "3:34:33", "throughput": 787.73, "total_tokens": 2885392} {"current_steps": 8865, "total_steps": 40000, "loss": 0.1581, "lr": 4.418248699712955e-05, "epoch": 7.254604993860008, "percentage": 22.16, "elapsed_time": "1:01:04", "remaining_time": "3:34:30", "throughput": 787.81, "total_tokens": 2887008} {"current_steps": 8870, "total_steps": 40000, "loss": 0.1963, "lr": 4.417618967872748e-05, "epoch": 7.258698321735571, "percentage": 22.18, "elapsed_time": "1:01:06", "remaining_time": "3:34:27", "throughput": 787.87, "total_tokens": 2888608} {"current_steps": 8875, "total_steps": 40000, "loss": 0.2298, "lr": 4.4169889403115985e-05, "epoch": 7.262791649611134, "percentage": 22.19, "elapsed_time": "1:01:08", "remaining_time": "3:34:24", "throughput": 787.97, "total_tokens": 2890304} {"current_steps": 8880, "total_steps": 40000, "loss": 0.1641, "lr": 4.4163586171266627e-05, "epoch": 7.266884977486697, "percentage": 22.2, "elapsed_time": "1:01:09", "remaining_time": "3:34:20", "throughput": 788.03, "total_tokens": 2891888} {"current_steps": 8885, "total_steps": 40000, "loss": 0.1978, "lr": 4.415727998415147e-05, "epoch": 7.270978305362259, "percentage": 22.21, "elapsed_time": "1:01:11", "remaining_time": "3:34:17", "throughput": 788.1, "total_tokens": 2893488} {"current_steps": 8890, "total_steps": 40000, "loss": 0.1215, "lr": 4.4150970842742985e-05, "epoch": 7.275071633237823, "percentage": 22.23, "elapsed_time": "1:01:13", "remaining_time": "3:34:14", "throughput": 788.17, "total_tokens": 2895104} {"current_steps": 8895, "total_steps": 40000, "loss": 0.2438, "lr": 4.4144658748014134e-05, "epoch": 7.279164961113385, "percentage": 22.24, "elapsed_time": "1:01:14", "remaining_time": "3:34:10", "throughput": 788.24, "total_tokens": 2896736} {"current_steps": 8900, "total_steps": 40000, "loss": 0.2169, "lr": 4.413834370093831e-05, "epoch": 7.283258288988948, "percentage": 22.25, "elapsed_time": "1:01:16", "remaining_time": "3:34:07", "throughput": 788.32, "total_tokens": 2898384} {"current_steps": 8905, "total_steps": 40000, "loss": 0.1936, "lr": 4.413202570248939e-05, "epoch": 7.287351616864511, "percentage": 22.26, "elapsed_time": "1:01:18", "remaining_time": "3:34:04", "throughput": 788.39, "total_tokens": 2899984} {"current_steps": 8910, "total_steps": 40000, "loss": 0.2245, "lr": 4.412570475364167e-05, "epoch": 7.291444944740074, "percentage": 22.27, "elapsed_time": "1:01:20", "remaining_time": "3:34:01", "throughput": 788.46, "total_tokens": 2901600} {"current_steps": 8915, "total_steps": 40000, "loss": 0.2528, "lr": 4.411938085536994e-05, "epoch": 7.295538272615636, "percentage": 22.29, "elapsed_time": "1:01:21", "remaining_time": "3:33:57", "throughput": 788.53, "total_tokens": 2903200} {"current_steps": 8920, "total_steps": 40000, "loss": 0.1727, "lr": 4.41130540086494e-05, "epoch": 7.2996316004912, "percentage": 22.3, "elapsed_time": "1:01:23", "remaining_time": "3:33:54", "throughput": 788.6, "total_tokens": 2904800} {"current_steps": 8925, "total_steps": 40000, "loss": 0.2297, "lr": 4.4106724214455754e-05, "epoch": 7.303724928366762, "percentage": 22.31, "elapsed_time": "1:01:25", "remaining_time": "3:33:51", "throughput": 788.69, "total_tokens": 2906496} {"current_steps": 8930, "total_steps": 40000, "loss": 0.2783, "lr": 4.4100391473765115e-05, "epoch": 7.307818256242325, "percentage": 22.32, "elapsed_time": "1:01:26", "remaining_time": "3:33:47", "throughput": 788.77, "total_tokens": 2908128} {"current_steps": 8935, "total_steps": 40000, "loss": 0.262, "lr": 4.409405578755408e-05, "epoch": 7.311911584117888, "percentage": 22.34, "elapsed_time": "1:01:28", "remaining_time": "3:33:44", "throughput": 788.84, "total_tokens": 2909744} {"current_steps": 8940, "total_steps": 40000, "loss": 0.1694, "lr": 4.4087717156799705e-05, "epoch": 7.316004911993451, "percentage": 22.35, "elapsed_time": "1:01:30", "remaining_time": "3:33:41", "throughput": 788.91, "total_tokens": 2911376} {"current_steps": 8945, "total_steps": 40000, "loss": 0.172, "lr": 4.408137558247946e-05, "epoch": 7.320098239869013, "percentage": 22.36, "elapsed_time": "1:01:32", "remaining_time": "3:33:38", "throughput": 788.98, "total_tokens": 2912976} {"current_steps": 8950, "total_steps": 40000, "loss": 0.1944, "lr": 4.4075031065571306e-05, "epoch": 7.324191567744577, "percentage": 22.38, "elapsed_time": "1:01:33", "remaining_time": "3:33:34", "throughput": 789.05, "total_tokens": 2914592} {"current_steps": 8955, "total_steps": 40000, "loss": 0.2023, "lr": 4.406868360705366e-05, "epoch": 7.328284895620139, "percentage": 22.39, "elapsed_time": "1:01:35", "remaining_time": "3:33:31", "throughput": 789.12, "total_tokens": 2916224} {"current_steps": 8960, "total_steps": 40000, "loss": 0.1572, "lr": 4.406233320790536e-05, "epoch": 7.332378223495702, "percentage": 22.4, "elapsed_time": "1:01:37", "remaining_time": "3:33:28", "throughput": 789.2, "total_tokens": 2917856} {"current_steps": 8965, "total_steps": 40000, "loss": 0.2176, "lr": 4.4055979869105734e-05, "epoch": 7.336471551371265, "percentage": 22.41, "elapsed_time": "1:01:38", "remaining_time": "3:33:25", "throughput": 789.28, "total_tokens": 2919504} {"current_steps": 8970, "total_steps": 40000, "loss": 0.1798, "lr": 4.404962359163454e-05, "epoch": 7.340564879246828, "percentage": 22.43, "elapsed_time": "1:01:40", "remaining_time": "3:33:21", "throughput": 789.36, "total_tokens": 2921152} {"current_steps": 8975, "total_steps": 40000, "loss": 0.2024, "lr": 4.404326437647199e-05, "epoch": 7.34465820712239, "percentage": 22.44, "elapsed_time": "1:01:42", "remaining_time": "3:33:18", "throughput": 789.43, "total_tokens": 2922752} {"current_steps": 8980, "total_steps": 40000, "loss": 0.2124, "lr": 4.403690222459877e-05, "epoch": 7.3487515349979535, "percentage": 22.45, "elapsed_time": "1:01:44", "remaining_time": "3:33:15", "throughput": 789.49, "total_tokens": 2924352} {"current_steps": 8985, "total_steps": 40000, "loss": 0.1879, "lr": 4.4030537136995984e-05, "epoch": 7.352844862873516, "percentage": 22.46, "elapsed_time": "1:01:45", "remaining_time": "3:33:11", "throughput": 789.59, "total_tokens": 2926064} {"current_steps": 8990, "total_steps": 40000, "loss": 0.1887, "lr": 4.402416911464523e-05, "epoch": 7.356938190749079, "percentage": 22.48, "elapsed_time": "1:01:47", "remaining_time": "3:33:08", "throughput": 789.67, "total_tokens": 2927728} {"current_steps": 8995, "total_steps": 40000, "loss": 0.2281, "lr": 4.4017798158528516e-05, "epoch": 7.361031518624642, "percentage": 22.49, "elapsed_time": "1:01:49", "remaining_time": "3:33:05", "throughput": 789.74, "total_tokens": 2929344} {"current_steps": 9000, "total_steps": 40000, "loss": 0.1436, "lr": 4.401142426962834e-05, "epoch": 7.365124846500205, "percentage": 22.5, "elapsed_time": "1:01:50", "remaining_time": "3:33:02", "throughput": 789.84, "total_tokens": 2931072} {"current_steps": 9000, "total_steps": 40000, "eval_loss": 0.2031099945306778, "epoch": 7.365124846500205, "percentage": 22.5, "elapsed_time": "1:02:03", "remaining_time": "3:33:45", "throughput": 787.2, "total_tokens": 2931072} {"current_steps": 9005, "total_steps": 40000, "loss": 0.162, "lr": 4.400504744892763e-05, "epoch": 7.369218174375767, "percentage": 22.51, "elapsed_time": "1:02:06", "remaining_time": "3:33:46", "throughput": 786.96, "total_tokens": 2932672} {"current_steps": 9010, "total_steps": 40000, "loss": 0.2411, "lr": 4.399866769740975e-05, "epoch": 7.3733115022513305, "percentage": 22.53, "elapsed_time": "1:02:08", "remaining_time": "3:33:43", "throughput": 787.04, "total_tokens": 2934304} {"current_steps": 9015, "total_steps": 40000, "loss": 0.1594, "lr": 4.399228501605859e-05, "epoch": 7.377404830126893, "percentage": 22.54, "elapsed_time": "1:02:10", "remaining_time": "3:33:40", "throughput": 787.1, "total_tokens": 2935904} {"current_steps": 9020, "total_steps": 40000, "loss": 0.1802, "lr": 4.398589940585839e-05, "epoch": 7.381498158002456, "percentage": 22.55, "elapsed_time": "1:02:11", "remaining_time": "3:33:36", "throughput": 787.17, "total_tokens": 2937504} {"current_steps": 9025, "total_steps": 40000, "loss": 0.1956, "lr": 4.3979510867793917e-05, "epoch": 7.3855914858780185, "percentage": 22.56, "elapsed_time": "1:02:13", "remaining_time": "3:33:33", "throughput": 787.25, "total_tokens": 2939152} {"current_steps": 9030, "total_steps": 40000, "loss": 0.2436, "lr": 4.3973119402850346e-05, "epoch": 7.389684813753582, "percentage": 22.57, "elapsed_time": "1:02:15", "remaining_time": "3:33:30", "throughput": 787.35, "total_tokens": 2940880} {"current_steps": 9035, "total_steps": 40000, "loss": 0.1387, "lr": 4.396672501201334e-05, "epoch": 7.393778141629144, "percentage": 22.59, "elapsed_time": "1:02:16", "remaining_time": "3:33:27", "throughput": 787.43, "total_tokens": 2942528} {"current_steps": 9040, "total_steps": 40000, "loss": 0.2279, "lr": 4.396032769626899e-05, "epoch": 7.397871469504707, "percentage": 22.6, "elapsed_time": "1:02:18", "remaining_time": "3:33:23", "throughput": 787.48, "total_tokens": 2944096} {"current_steps": 9045, "total_steps": 40000, "loss": 0.1524, "lr": 4.395392745660384e-05, "epoch": 7.40196479738027, "percentage": 22.61, "elapsed_time": "1:02:20", "remaining_time": "3:33:20", "throughput": 787.56, "total_tokens": 2945728} {"current_steps": 9050, "total_steps": 40000, "loss": 0.1845, "lr": 4.394752429400488e-05, "epoch": 7.406058125255833, "percentage": 22.62, "elapsed_time": "1:02:22", "remaining_time": "3:33:17", "throughput": 787.63, "total_tokens": 2947360} {"current_steps": 9055, "total_steps": 40000, "loss": 0.2074, "lr": 4.394111820945957e-05, "epoch": 7.4101514531313954, "percentage": 22.64, "elapsed_time": "1:02:23", "remaining_time": "3:33:14", "throughput": 787.74, "total_tokens": 2949120} {"current_steps": 9060, "total_steps": 40000, "loss": 0.1889, "lr": 4.393470920395579e-05, "epoch": 7.414244781006959, "percentage": 22.65, "elapsed_time": "1:02:25", "remaining_time": "3:33:10", "throughput": 787.81, "total_tokens": 2950736} {"current_steps": 9065, "total_steps": 40000, "loss": 0.2887, "lr": 4.392829727848192e-05, "epoch": 7.418338108882521, "percentage": 22.66, "elapsed_time": "1:02:27", "remaining_time": "3:33:07", "throughput": 787.88, "total_tokens": 2952352} {"current_steps": 9070, "total_steps": 40000, "loss": 0.2198, "lr": 4.392188243402673e-05, "epoch": 7.422431436758084, "percentage": 22.68, "elapsed_time": "1:02:28", "remaining_time": "3:33:04", "throughput": 787.95, "total_tokens": 2953936} {"current_steps": 9075, "total_steps": 40000, "loss": 0.1924, "lr": 4.391546467157949e-05, "epoch": 7.426524764633647, "percentage": 22.69, "elapsed_time": "1:02:30", "remaining_time": "3:33:01", "throughput": 788.01, "total_tokens": 2955552} {"current_steps": 9080, "total_steps": 40000, "loss": 0.155, "lr": 4.390904399212988e-05, "epoch": 7.43061809250921, "percentage": 22.7, "elapsed_time": "1:02:32", "remaining_time": "3:32:57", "throughput": 788.08, "total_tokens": 2957152} {"current_steps": 9085, "total_steps": 40000, "loss": 0.2157, "lr": 4.390262039666807e-05, "epoch": 7.434711420384772, "percentage": 22.71, "elapsed_time": "1:02:34", "remaining_time": "3:32:54", "throughput": 788.15, "total_tokens": 2958768} {"current_steps": 9090, "total_steps": 40000, "loss": 0.1909, "lr": 4.389619388618464e-05, "epoch": 7.438804748260336, "percentage": 22.73, "elapsed_time": "1:02:35", "remaining_time": "3:32:51", "throughput": 788.21, "total_tokens": 2960368} {"current_steps": 9095, "total_steps": 40000, "loss": 0.2148, "lr": 4.3889764461670655e-05, "epoch": 7.442898076135899, "percentage": 22.74, "elapsed_time": "1:02:37", "remaining_time": "3:32:48", "throughput": 788.28, "total_tokens": 2961984} {"current_steps": 9100, "total_steps": 40000, "loss": 0.2173, "lr": 4.38833321241176e-05, "epoch": 7.446991404011461, "percentage": 22.75, "elapsed_time": "1:02:39", "remaining_time": "3:32:44", "throughput": 788.36, "total_tokens": 2963616} {"current_steps": 9105, "total_steps": 40000, "loss": 0.1921, "lr": 4.3876896874517434e-05, "epoch": 7.451084731887024, "percentage": 22.76, "elapsed_time": "1:02:40", "remaining_time": "3:32:41", "throughput": 788.42, "total_tokens": 2965216} {"current_steps": 9110, "total_steps": 40000, "loss": 0.2363, "lr": 4.3870458713862554e-05, "epoch": 7.455178059762587, "percentage": 22.78, "elapsed_time": "1:02:42", "remaining_time": "3:32:38", "throughput": 788.47, "total_tokens": 2966752} {"current_steps": 9115, "total_steps": 40000, "loss": 0.1892, "lr": 4.386401764314579e-05, "epoch": 7.45927138763815, "percentage": 22.79, "elapsed_time": "1:02:44", "remaining_time": "3:32:35", "throughput": 788.55, "total_tokens": 2968384} {"current_steps": 9120, "total_steps": 40000, "loss": 0.1928, "lr": 4.385757366336045e-05, "epoch": 7.463364715513713, "percentage": 22.8, "elapsed_time": "1:02:46", "remaining_time": "3:32:31", "throughput": 788.61, "total_tokens": 2969984} {"current_steps": 9125, "total_steps": 40000, "loss": 0.2203, "lr": 4.385112677550027e-05, "epoch": 7.467458043389276, "percentage": 22.81, "elapsed_time": "1:02:47", "remaining_time": "3:32:28", "throughput": 788.67, "total_tokens": 2971568} {"current_steps": 9130, "total_steps": 40000, "loss": 0.2429, "lr": 4.384467698055945e-05, "epoch": 7.471551371264838, "percentage": 22.82, "elapsed_time": "1:02:49", "remaining_time": "3:32:25", "throughput": 788.75, "total_tokens": 2973200} {"current_steps": 9135, "total_steps": 40000, "loss": 0.2191, "lr": 4.383822427953261e-05, "epoch": 7.4756446991404015, "percentage": 22.84, "elapsed_time": "1:02:51", "remaining_time": "3:32:22", "throughput": 788.82, "total_tokens": 2974832} {"current_steps": 9140, "total_steps": 40000, "loss": 0.164, "lr": 4.3831768673414864e-05, "epoch": 7.479738027015964, "percentage": 22.85, "elapsed_time": "1:02:52", "remaining_time": "3:32:18", "throughput": 788.91, "total_tokens": 2976512} {"current_steps": 9145, "total_steps": 40000, "loss": 0.1275, "lr": 4.382531016320173e-05, "epoch": 7.483831354891527, "percentage": 22.86, "elapsed_time": "1:02:54", "remaining_time": "3:32:15", "throughput": 788.98, "total_tokens": 2978160} {"current_steps": 9150, "total_steps": 40000, "loss": 0.235, "lr": 4.3818848749889184e-05, "epoch": 7.48792468276709, "percentage": 22.88, "elapsed_time": "1:02:56", "remaining_time": "3:32:12", "throughput": 789.06, "total_tokens": 2979824} {"current_steps": 9155, "total_steps": 40000, "loss": 0.1673, "lr": 4.381238443447368e-05, "epoch": 7.492018010642653, "percentage": 22.89, "elapsed_time": "1:02:58", "remaining_time": "3:32:09", "throughput": 789.17, "total_tokens": 2981568} {"current_steps": 9160, "total_steps": 40000, "loss": 0.1434, "lr": 4.380591721795208e-05, "epoch": 7.496111338518215, "percentage": 22.9, "elapsed_time": "1:02:59", "remaining_time": "3:32:06", "throughput": 789.24, "total_tokens": 2983216} {"current_steps": 9165, "total_steps": 40000, "loss": 0.1653, "lr": 4.3799447101321723e-05, "epoch": 7.5002046663937785, "percentage": 22.91, "elapsed_time": "1:03:01", "remaining_time": "3:32:02", "throughput": 789.31, "total_tokens": 2984816} {"current_steps": 9170, "total_steps": 40000, "loss": 0.1916, "lr": 4.379297408558036e-05, "epoch": 7.504297994269341, "percentage": 22.93, "elapsed_time": "1:03:03", "remaining_time": "3:31:59", "throughput": 789.38, "total_tokens": 2986432} {"current_steps": 9175, "total_steps": 40000, "loss": 0.1829, "lr": 4.378649817172624e-05, "epoch": 7.508391322144904, "percentage": 22.94, "elapsed_time": "1:03:04", "remaining_time": "3:31:56", "throughput": 789.44, "total_tokens": 2988032} {"current_steps": 9180, "total_steps": 40000, "loss": 0.165, "lr": 4.378001936075801e-05, "epoch": 7.5124846500204665, "percentage": 22.95, "elapsed_time": "1:03:06", "remaining_time": "3:31:53", "throughput": 789.52, "total_tokens": 2989680} {"current_steps": 9185, "total_steps": 40000, "loss": 0.2157, "lr": 4.377353765367479e-05, "epoch": 7.51657797789603, "percentage": 22.96, "elapsed_time": "1:03:08", "remaining_time": "3:31:49", "throughput": 789.61, "total_tokens": 2991360} {"current_steps": 9190, "total_steps": 40000, "loss": 0.2578, "lr": 4.376705305147614e-05, "epoch": 7.520671305771592, "percentage": 22.98, "elapsed_time": "1:03:10", "remaining_time": "3:31:46", "throughput": 789.68, "total_tokens": 2992992} {"current_steps": 9195, "total_steps": 40000, "loss": 0.2209, "lr": 4.376056555516206e-05, "epoch": 7.524764633647155, "percentage": 22.99, "elapsed_time": "1:03:11", "remaining_time": "3:31:43", "throughput": 789.75, "total_tokens": 2994624} {"current_steps": 9200, "total_steps": 40000, "loss": 0.2574, "lr": 4.375407516573302e-05, "epoch": 7.528857961522718, "percentage": 23.0, "elapsed_time": "1:03:13", "remaining_time": "3:31:40", "throughput": 789.83, "total_tokens": 2996288} {"current_steps": 9200, "total_steps": 40000, "eval_loss": 0.20590226352214813, "epoch": 7.528857961522718, "percentage": 23.0, "elapsed_time": "1:03:26", "remaining_time": "3:32:22", "throughput": 787.24, "total_tokens": 2996288} {"current_steps": 9205, "total_steps": 40000, "loss": 0.1923, "lr": 4.3747581884189913e-05, "epoch": 7.532951289398281, "percentage": 23.01, "elapsed_time": "1:03:29", "remaining_time": "3:32:25", "throughput": 786.92, "total_tokens": 2997904} {"current_steps": 9210, "total_steps": 40000, "loss": 0.1848, "lr": 4.374108571153408e-05, "epoch": 7.5370446172738434, "percentage": 23.03, "elapsed_time": "1:03:31", "remaining_time": "3:32:21", "throughput": 787.0, "total_tokens": 2999568} {"current_steps": 9215, "total_steps": 40000, "loss": 0.1679, "lr": 4.3734586648767316e-05, "epoch": 7.541137945149407, "percentage": 23.04, "elapsed_time": "1:03:33", "remaining_time": "3:32:18", "throughput": 787.09, "total_tokens": 3001264} {"current_steps": 9220, "total_steps": 40000, "loss": 0.2489, "lr": 4.372808469689186e-05, "epoch": 7.545231273024969, "percentage": 23.05, "elapsed_time": "1:03:34", "remaining_time": "3:32:15", "throughput": 787.16, "total_tokens": 3002896} {"current_steps": 9225, "total_steps": 40000, "loss": 0.2383, "lr": 4.372157985691039e-05, "epoch": 7.549324600900532, "percentage": 23.06, "elapsed_time": "1:03:36", "remaining_time": "3:32:12", "throughput": 787.23, "total_tokens": 3004512} {"current_steps": 9230, "total_steps": 40000, "loss": 0.2518, "lr": 4.371507212982603e-05, "epoch": 7.553417928776095, "percentage": 23.08, "elapsed_time": "1:03:38", "remaining_time": "3:32:08", "throughput": 787.31, "total_tokens": 3006144} {"current_steps": 9235, "total_steps": 40000, "loss": 0.2417, "lr": 4.370856151664236e-05, "epoch": 7.557511256651658, "percentage": 23.09, "elapsed_time": "1:03:39", "remaining_time": "3:32:05", "throughput": 787.36, "total_tokens": 3007712} {"current_steps": 9240, "total_steps": 40000, "loss": 0.1859, "lr": 4.3702048018363404e-05, "epoch": 7.56160458452722, "percentage": 23.1, "elapsed_time": "1:03:41", "remaining_time": "3:32:02", "throughput": 787.42, "total_tokens": 3009312} {"current_steps": 9245, "total_steps": 40000, "loss": 0.1804, "lr": 4.369553163599362e-05, "epoch": 7.565697912402784, "percentage": 23.11, "elapsed_time": "1:03:43", "remaining_time": "3:31:59", "throughput": 787.5, "total_tokens": 3010960} {"current_steps": 9250, "total_steps": 40000, "loss": 0.1946, "lr": 4.3689012370537904e-05, "epoch": 7.569791240278346, "percentage": 23.12, "elapsed_time": "1:03:45", "remaining_time": "3:31:56", "throughput": 787.57, "total_tokens": 3012576} {"current_steps": 9255, "total_steps": 40000, "loss": 0.2291, "lr": 4.368249022300164e-05, "epoch": 7.573884568153909, "percentage": 23.14, "elapsed_time": "1:03:46", "remaining_time": "3:31:52", "throughput": 787.66, "total_tokens": 3014272} {"current_steps": 9260, "total_steps": 40000, "loss": 0.2002, "lr": 4.367596519439059e-05, "epoch": 7.577977896029472, "percentage": 23.15, "elapsed_time": "1:03:48", "remaining_time": "3:31:49", "throughput": 787.75, "total_tokens": 3015968} {"current_steps": 9265, "total_steps": 40000, "loss": 0.1705, "lr": 4.366943728571101e-05, "epoch": 7.582071223905035, "percentage": 23.16, "elapsed_time": "1:03:50", "remaining_time": "3:31:46", "throughput": 787.82, "total_tokens": 3017600} {"current_steps": 9270, "total_steps": 40000, "loss": 0.2081, "lr": 4.366290649796959e-05, "epoch": 7.586164551780597, "percentage": 23.18, "elapsed_time": "1:03:52", "remaining_time": "3:31:43", "throughput": 787.9, "total_tokens": 3019264} {"current_steps": 9275, "total_steps": 40000, "loss": 0.1502, "lr": 4.3656372832173456e-05, "epoch": 7.590257879656161, "percentage": 23.19, "elapsed_time": "1:03:53", "remaining_time": "3:31:39", "throughput": 787.97, "total_tokens": 3020880} {"current_steps": 9280, "total_steps": 40000, "loss": 0.1666, "lr": 4.364983628933017e-05, "epoch": 7.594351207531723, "percentage": 23.2, "elapsed_time": "1:03:55", "remaining_time": "3:31:36", "throughput": 788.04, "total_tokens": 3022512} {"current_steps": 9285, "total_steps": 40000, "loss": 0.1876, "lr": 4.364329687044777e-05, "epoch": 7.598444535407286, "percentage": 23.21, "elapsed_time": "1:03:57", "remaining_time": "3:31:33", "throughput": 788.12, "total_tokens": 3024160} {"current_steps": 9290, "total_steps": 40000, "loss": 0.1841, "lr": 4.36367545765347e-05, "epoch": 7.602537863282849, "percentage": 23.23, "elapsed_time": "1:03:58", "remaining_time": "3:31:30", "throughput": 788.2, "total_tokens": 3025808} {"current_steps": 9295, "total_steps": 40000, "loss": 0.1605, "lr": 4.363020940859988e-05, "epoch": 7.606631191158412, "percentage": 23.24, "elapsed_time": "1:04:00", "remaining_time": "3:31:27", "throughput": 788.27, "total_tokens": 3027440} {"current_steps": 9300, "total_steps": 40000, "loss": 0.1769, "lr": 4.362366136765263e-05, "epoch": 7.610724519033974, "percentage": 23.25, "elapsed_time": "1:04:02", "remaining_time": "3:31:23", "throughput": 788.34, "total_tokens": 3029056} {"current_steps": 9305, "total_steps": 40000, "loss": 0.1668, "lr": 4.361711045470278e-05, "epoch": 7.614817846909538, "percentage": 23.26, "elapsed_time": "1:04:04", "remaining_time": "3:31:20", "throughput": 788.4, "total_tokens": 3030656} {"current_steps": 9310, "total_steps": 40000, "loss": 0.1817, "lr": 4.3610556670760524e-05, "epoch": 7.6189111747851, "percentage": 23.28, "elapsed_time": "1:04:05", "remaining_time": "3:31:17", "throughput": 788.46, "total_tokens": 3032240} {"current_steps": 9315, "total_steps": 40000, "loss": 0.21, "lr": 4.360400001683657e-05, "epoch": 7.623004502660663, "percentage": 23.29, "elapsed_time": "1:04:07", "remaining_time": "3:31:14", "throughput": 788.52, "total_tokens": 3033840} {"current_steps": 9320, "total_steps": 40000, "loss": 0.1748, "lr": 4.3597440493942e-05, "epoch": 7.627097830536226, "percentage": 23.3, "elapsed_time": "1:04:09", "remaining_time": "3:31:10", "throughput": 788.61, "total_tokens": 3035520} {"current_steps": 9325, "total_steps": 40000, "loss": 0.2173, "lr": 4.3590878103088405e-05, "epoch": 7.631191158411789, "percentage": 23.31, "elapsed_time": "1:04:10", "remaining_time": "3:31:07", "throughput": 788.68, "total_tokens": 3037136} {"current_steps": 9330, "total_steps": 40000, "loss": 0.1744, "lr": 4.358431284528779e-05, "epoch": 7.635284486287351, "percentage": 23.33, "elapsed_time": "1:04:12", "remaining_time": "3:31:04", "throughput": 788.77, "total_tokens": 3038832} {"current_steps": 9335, "total_steps": 40000, "loss": 0.2108, "lr": 4.357774472155257e-05, "epoch": 7.6393778141629145, "percentage": 23.34, "elapsed_time": "1:04:14", "remaining_time": "3:31:01", "throughput": 788.83, "total_tokens": 3040432} {"current_steps": 9340, "total_steps": 40000, "loss": 0.2366, "lr": 4.3571173732895664e-05, "epoch": 7.643471142038477, "percentage": 23.35, "elapsed_time": "1:04:16", "remaining_time": "3:30:58", "throughput": 788.9, "total_tokens": 3042048} {"current_steps": 9345, "total_steps": 40000, "loss": 0.2051, "lr": 4.356459988033039e-05, "epoch": 7.64756446991404, "percentage": 23.36, "elapsed_time": "1:04:17", "remaining_time": "3:30:54", "throughput": 788.96, "total_tokens": 3043648} {"current_steps": 9350, "total_steps": 40000, "loss": 0.2191, "lr": 4.355802316487051e-05, "epoch": 7.651657797789603, "percentage": 23.38, "elapsed_time": "1:04:19", "remaining_time": "3:30:51", "throughput": 789.03, "total_tokens": 3045264} {"current_steps": 9355, "total_steps": 40000, "loss": 0.222, "lr": 4.355144358753025e-05, "epoch": 7.655751125665166, "percentage": 23.39, "elapsed_time": "1:04:21", "remaining_time": "3:30:48", "throughput": 789.08, "total_tokens": 3046832} {"current_steps": 9360, "total_steps": 40000, "loss": 0.2181, "lr": 4.354486114932425e-05, "epoch": 7.659844453540728, "percentage": 23.4, "elapsed_time": "1:04:22", "remaining_time": "3:30:45", "throughput": 789.17, "total_tokens": 3048528} {"current_steps": 9365, "total_steps": 40000, "loss": 0.1812, "lr": 4.353827585126762e-05, "epoch": 7.6639377814162915, "percentage": 23.41, "elapsed_time": "1:04:24", "remaining_time": "3:30:42", "throughput": 789.26, "total_tokens": 3050208} {"current_steps": 9370, "total_steps": 40000, "loss": 0.1743, "lr": 4.353168769437588e-05, "epoch": 7.668031109291855, "percentage": 23.43, "elapsed_time": "1:04:26", "remaining_time": "3:30:38", "throughput": 789.33, "total_tokens": 3051824} {"current_steps": 9375, "total_steps": 40000, "loss": 0.1704, "lr": 4.3525096679665014e-05, "epoch": 7.672124437167417, "percentage": 23.44, "elapsed_time": "1:04:28", "remaining_time": "3:30:35", "throughput": 789.4, "total_tokens": 3053456} {"current_steps": 9380, "total_steps": 40000, "loss": 0.2646, "lr": 4.351850280815144e-05, "epoch": 7.6762177650429795, "percentage": 23.45, "elapsed_time": "1:04:29", "remaining_time": "3:30:32", "throughput": 789.46, "total_tokens": 3055072} {"current_steps": 9385, "total_steps": 40000, "loss": 0.2235, "lr": 4.3511906080852014e-05, "epoch": 7.680311092918543, "percentage": 23.46, "elapsed_time": "1:04:31", "remaining_time": "3:30:29", "throughput": 789.55, "total_tokens": 3056768} {"current_steps": 9390, "total_steps": 40000, "loss": 0.178, "lr": 4.350530649878404e-05, "epoch": 7.684404420794106, "percentage": 23.47, "elapsed_time": "1:04:33", "remaining_time": "3:30:26", "throughput": 789.65, "total_tokens": 3058512} {"current_steps": 9395, "total_steps": 40000, "loss": 0.1853, "lr": 4.3498704062965246e-05, "epoch": 7.688497748669668, "percentage": 23.49, "elapsed_time": "1:04:34", "remaining_time": "3:30:22", "throughput": 789.73, "total_tokens": 3060176} {"current_steps": 9400, "total_steps": 40000, "loss": 0.2052, "lr": 4.3492098774413815e-05, "epoch": 7.692591076545231, "percentage": 23.5, "elapsed_time": "1:04:36", "remaining_time": "3:30:19", "throughput": 789.79, "total_tokens": 3061744} {"current_steps": 9400, "total_steps": 40000, "eval_loss": 0.2034885585308075, "epoch": 7.692591076545231, "percentage": 23.5, "elapsed_time": "1:04:49", "remaining_time": "3:31:00", "throughput": 787.25, "total_tokens": 3061744} {"current_steps": 9405, "total_steps": 40000, "loss": 0.1732, "lr": 4.3485490634148375e-05, "epoch": 7.696684404420794, "percentage": 23.51, "elapsed_time": "1:04:52", "remaining_time": "3:31:02", "throughput": 787.0, "total_tokens": 3063376} {"current_steps": 9410, "total_steps": 40000, "loss": 0.2105, "lr": 4.347887964318797e-05, "epoch": 7.700777732296357, "percentage": 23.52, "elapsed_time": "1:04:54", "remaining_time": "3:30:59", "throughput": 787.06, "total_tokens": 3064976} {"current_steps": 9415, "total_steps": 40000, "loss": 0.1931, "lr": 4.34722658025521e-05, "epoch": 7.70487106017192, "percentage": 23.54, "elapsed_time": "1:04:55", "remaining_time": "3:30:56", "throughput": 787.14, "total_tokens": 3066656} {"current_steps": 9420, "total_steps": 40000, "loss": 0.1906, "lr": 4.346564911326071e-05, "epoch": 7.708964388047483, "percentage": 23.55, "elapsed_time": "1:04:57", "remaining_time": "3:30:52", "throughput": 787.22, "total_tokens": 3068288} {"current_steps": 9425, "total_steps": 40000, "loss": 0.2179, "lr": 4.345902957633418e-05, "epoch": 7.713057715923045, "percentage": 23.56, "elapsed_time": "1:04:59", "remaining_time": "3:30:49", "throughput": 787.28, "total_tokens": 3069888} {"current_steps": 9430, "total_steps": 40000, "loss": 0.2029, "lr": 4.345240719279331e-05, "epoch": 7.717151043798609, "percentage": 23.57, "elapsed_time": "1:05:01", "remaining_time": "3:30:46", "throughput": 787.35, "total_tokens": 3071536} {"current_steps": 9435, "total_steps": 40000, "loss": 0.1998, "lr": 4.3445781963659374e-05, "epoch": 7.721244371674171, "percentage": 23.59, "elapsed_time": "1:05:02", "remaining_time": "3:30:43", "throughput": 787.42, "total_tokens": 3073136} {"current_steps": 9440, "total_steps": 40000, "loss": 0.1538, "lr": 4.3439153889954045e-05, "epoch": 7.725337699549734, "percentage": 23.6, "elapsed_time": "1:05:04", "remaining_time": "3:30:40", "throughput": 787.48, "total_tokens": 3074752} {"current_steps": 9445, "total_steps": 40000, "loss": 0.2306, "lr": 4.343252297269946e-05, "epoch": 7.729431027425297, "percentage": 23.61, "elapsed_time": "1:05:06", "remaining_time": "3:30:36", "throughput": 787.55, "total_tokens": 3076352} {"current_steps": 9450, "total_steps": 40000, "loss": 0.1846, "lr": 4.342588921291821e-05, "epoch": 7.73352435530086, "percentage": 23.62, "elapsed_time": "1:05:07", "remaining_time": "3:30:33", "throughput": 787.61, "total_tokens": 3077936} {"current_steps": 9455, "total_steps": 40000, "loss": 0.1382, "lr": 4.341925261163328e-05, "epoch": 7.737617683176422, "percentage": 23.64, "elapsed_time": "1:05:09", "remaining_time": "3:30:30", "throughput": 787.69, "total_tokens": 3079616} {"current_steps": 9460, "total_steps": 40000, "loss": 0.1846, "lr": 4.341261316986813e-05, "epoch": 7.741711011051986, "percentage": 23.65, "elapsed_time": "1:05:11", "remaining_time": "3:30:27", "throughput": 787.77, "total_tokens": 3081280} {"current_steps": 9465, "total_steps": 40000, "loss": 0.2097, "lr": 4.340597088864664e-05, "epoch": 7.745804338927548, "percentage": 23.66, "elapsed_time": "1:05:13", "remaining_time": "3:30:24", "throughput": 787.86, "total_tokens": 3082992} {"current_steps": 9470, "total_steps": 40000, "loss": 0.2326, "lr": 4.339932576899313e-05, "epoch": 7.749897666803111, "percentage": 23.67, "elapsed_time": "1:05:14", "remaining_time": "3:30:20", "throughput": 787.93, "total_tokens": 3084624} {"current_steps": 9475, "total_steps": 40000, "loss": 0.2156, "lr": 4.3392677811932375e-05, "epoch": 7.753990994678674, "percentage": 23.69, "elapsed_time": "1:05:16", "remaining_time": "3:30:17", "throughput": 788.0, "total_tokens": 3086240} {"current_steps": 9480, "total_steps": 40000, "loss": 0.138, "lr": 4.338602701848956e-05, "epoch": 7.758084322554237, "percentage": 23.7, "elapsed_time": "1:05:18", "remaining_time": "3:30:14", "throughput": 788.06, "total_tokens": 3087856} {"current_steps": 9485, "total_steps": 40000, "loss": 0.1831, "lr": 4.337937338969033e-05, "epoch": 7.762177650429799, "percentage": 23.71, "elapsed_time": "1:05:20", "remaining_time": "3:30:11", "throughput": 788.14, "total_tokens": 3089520} {"current_steps": 9490, "total_steps": 40000, "loss": 0.2042, "lr": 4.337271692656075e-05, "epoch": 7.7662709783053625, "percentage": 23.72, "elapsed_time": "1:05:21", "remaining_time": "3:30:08", "throughput": 788.21, "total_tokens": 3091152} {"current_steps": 9495, "total_steps": 40000, "loss": 0.1501, "lr": 4.336605763012733e-05, "epoch": 7.770364306180925, "percentage": 23.74, "elapsed_time": "1:05:23", "remaining_time": "3:30:05", "throughput": 788.28, "total_tokens": 3092784} {"current_steps": 9500, "total_steps": 40000, "loss": 0.1848, "lr": 4.3359395501417026e-05, "epoch": 7.774457634056488, "percentage": 23.75, "elapsed_time": "1:05:25", "remaining_time": "3:30:01", "throughput": 788.34, "total_tokens": 3094384} {"current_steps": 9505, "total_steps": 40000, "loss": 0.1677, "lr": 4.335273054145722e-05, "epoch": 7.7785509619320505, "percentage": 23.76, "elapsed_time": "1:05:26", "remaining_time": "3:29:58", "throughput": 788.41, "total_tokens": 3095984} {"current_steps": 9510, "total_steps": 40000, "loss": 0.1494, "lr": 4.334606275127572e-05, "epoch": 7.782644289807614, "percentage": 23.77, "elapsed_time": "1:05:28", "remaining_time": "3:29:55", "throughput": 788.48, "total_tokens": 3097616} {"current_steps": 9515, "total_steps": 40000, "loss": 0.1723, "lr": 4.33393921319008e-05, "epoch": 7.786737617683176, "percentage": 23.79, "elapsed_time": "1:05:30", "remaining_time": "3:29:52", "throughput": 788.53, "total_tokens": 3099184} {"current_steps": 9520, "total_steps": 40000, "loss": 0.1893, "lr": 4.3332718684361146e-05, "epoch": 7.7908309455587395, "percentage": 23.8, "elapsed_time": "1:05:32", "remaining_time": "3:29:49", "throughput": 788.61, "total_tokens": 3100864} {"current_steps": 9525, "total_steps": 40000, "loss": 0.1942, "lr": 4.332604240968588e-05, "epoch": 7.794924273434302, "percentage": 23.81, "elapsed_time": "1:05:33", "remaining_time": "3:29:46", "throughput": 788.68, "total_tokens": 3102480} {"current_steps": 9530, "total_steps": 40000, "loss": 0.2095, "lr": 4.331936330890459e-05, "epoch": 7.799017601309865, "percentage": 23.82, "elapsed_time": "1:05:35", "remaining_time": "3:29:42", "throughput": 788.75, "total_tokens": 3104128} {"current_steps": 9535, "total_steps": 40000, "loss": 0.1884, "lr": 4.331268138304725e-05, "epoch": 7.8031109291854275, "percentage": 23.84, "elapsed_time": "1:05:37", "remaining_time": "3:29:39", "throughput": 788.81, "total_tokens": 3105728} {"current_steps": 9540, "total_steps": 40000, "loss": 0.2576, "lr": 4.330599663314431e-05, "epoch": 7.807204257060991, "percentage": 23.85, "elapsed_time": "1:05:38", "remaining_time": "3:29:36", "throughput": 788.87, "total_tokens": 3107312} {"current_steps": 9545, "total_steps": 40000, "loss": 0.2106, "lr": 4.329930906022665e-05, "epoch": 7.811297584936553, "percentage": 23.86, "elapsed_time": "1:05:40", "remaining_time": "3:29:33", "throughput": 788.93, "total_tokens": 3108896} {"current_steps": 9550, "total_steps": 40000, "loss": 0.1717, "lr": 4.3292618665325564e-05, "epoch": 7.815390912812116, "percentage": 23.88, "elapsed_time": "1:05:42", "remaining_time": "3:29:30", "throughput": 789.0, "total_tokens": 3110544} {"current_steps": 9555, "total_steps": 40000, "loss": 0.1941, "lr": 4.3285925449472796e-05, "epoch": 7.819484240687679, "percentage": 23.89, "elapsed_time": "1:05:44", "remaining_time": "3:29:26", "throughput": 789.07, "total_tokens": 3112160} {"current_steps": 9560, "total_steps": 40000, "loss": 0.2049, "lr": 4.327922941370054e-05, "epoch": 7.823577568563242, "percentage": 23.9, "elapsed_time": "1:05:45", "remaining_time": "3:29:23", "throughput": 789.16, "total_tokens": 3113856} {"current_steps": 9565, "total_steps": 40000, "loss": 0.2189, "lr": 4.3272530559041384e-05, "epoch": 7.827670896438804, "percentage": 23.91, "elapsed_time": "1:05:47", "remaining_time": "3:29:20", "throughput": 789.21, "total_tokens": 3115424} {"current_steps": 9570, "total_steps": 40000, "loss": 0.2155, "lr": 4.32658288865284e-05, "epoch": 7.831764224314368, "percentage": 23.93, "elapsed_time": "1:05:49", "remaining_time": "3:29:17", "throughput": 789.28, "total_tokens": 3117056} {"current_steps": 9575, "total_steps": 40000, "loss": 0.1935, "lr": 4.325912439719505e-05, "epoch": 7.83585755218993, "percentage": 23.94, "elapsed_time": "1:05:50", "remaining_time": "3:29:14", "throughput": 789.34, "total_tokens": 3118640} {"current_steps": 9580, "total_steps": 40000, "loss": 0.211, "lr": 4.3252417092075266e-05, "epoch": 7.839950880065493, "percentage": 23.95, "elapsed_time": "1:05:52", "remaining_time": "3:29:11", "throughput": 789.42, "total_tokens": 3120320} {"current_steps": 9585, "total_steps": 40000, "loss": 0.2463, "lr": 4.3245706972203385e-05, "epoch": 7.844044207941056, "percentage": 23.96, "elapsed_time": "1:05:54", "remaining_time": "3:29:08", "throughput": 789.5, "total_tokens": 3121984} {"current_steps": 9590, "total_steps": 40000, "loss": 0.1262, "lr": 4.323899403861421e-05, "epoch": 7.848137535816619, "percentage": 23.97, "elapsed_time": "1:05:56", "remaining_time": "3:29:04", "throughput": 789.57, "total_tokens": 3123616} {"current_steps": 9595, "total_steps": 40000, "loss": 0.2128, "lr": 4.3232278292342935e-05, "epoch": 7.852230863692181, "percentage": 23.99, "elapsed_time": "1:05:57", "remaining_time": "3:29:01", "throughput": 789.65, "total_tokens": 3125280} {"current_steps": 9600, "total_steps": 40000, "loss": 0.1674, "lr": 4.322555973442524e-05, "epoch": 7.856324191567745, "percentage": 24.0, "elapsed_time": "1:05:59", "remaining_time": "3:28:58", "throughput": 789.71, "total_tokens": 3126896} {"current_steps": 9600, "total_steps": 40000, "eval_loss": 0.20237773656845093, "epoch": 7.856324191567745, "percentage": 24.0, "elapsed_time": "1:06:11", "remaining_time": "3:29:37", "throughput": 787.24, "total_tokens": 3126896} {"current_steps": 9605, "total_steps": 40000, "loss": 0.1886, "lr": 4.3218838365897184e-05, "epoch": 7.860417519443307, "percentage": 24.01, "elapsed_time": "1:06:15", "remaining_time": "3:29:39", "throughput": 787.01, "total_tokens": 3128496} {"current_steps": 9610, "total_steps": 40000, "loss": 0.2453, "lr": 4.3212114187795306e-05, "epoch": 7.86451084731887, "percentage": 24.02, "elapsed_time": "1:06:16", "remaining_time": "3:29:36", "throughput": 787.08, "total_tokens": 3130144} {"current_steps": 9615, "total_steps": 40000, "loss": 0.1681, "lr": 4.320538720115656e-05, "epoch": 7.868604175194433, "percentage": 24.04, "elapsed_time": "1:06:18", "remaining_time": "3:29:33", "throughput": 787.16, "total_tokens": 3131792} {"current_steps": 9620, "total_steps": 40000, "loss": 0.16, "lr": 4.319865740701831e-05, "epoch": 7.872697503069996, "percentage": 24.05, "elapsed_time": "1:06:20", "remaining_time": "3:29:29", "throughput": 787.22, "total_tokens": 3133376} {"current_steps": 9625, "total_steps": 40000, "loss": 0.1435, "lr": 4.3191924806418396e-05, "epoch": 7.876790830945559, "percentage": 24.06, "elapsed_time": "1:06:22", "remaining_time": "3:29:26", "throughput": 787.27, "total_tokens": 3134928} {"current_steps": 9630, "total_steps": 40000, "loss": 0.2132, "lr": 4.318518940039507e-05, "epoch": 7.880884158821122, "percentage": 24.07, "elapsed_time": "1:06:23", "remaining_time": "3:29:23", "throughput": 787.33, "total_tokens": 3136544} {"current_steps": 9635, "total_steps": 40000, "loss": 0.2221, "lr": 4.3178451189987e-05, "epoch": 7.884977486696684, "percentage": 24.09, "elapsed_time": "1:06:25", "remaining_time": "3:29:20", "throughput": 787.39, "total_tokens": 3138144} {"current_steps": 9640, "total_steps": 40000, "loss": 0.1571, "lr": 4.3171710176233315e-05, "epoch": 7.889070814572247, "percentage": 24.1, "elapsed_time": "1:06:27", "remaining_time": "3:29:17", "throughput": 787.46, "total_tokens": 3139744} {"current_steps": 9645, "total_steps": 40000, "loss": 0.1518, "lr": 4.316496636017355e-05, "epoch": 7.8931641424478105, "percentage": 24.11, "elapsed_time": "1:06:28", "remaining_time": "3:29:14", "throughput": 787.53, "total_tokens": 3141408} {"current_steps": 9650, "total_steps": 40000, "loss": 0.184, "lr": 4.315821974284771e-05, "epoch": 7.897257470323373, "percentage": 24.12, "elapsed_time": "1:06:30", "remaining_time": "3:29:10", "throughput": 787.61, "total_tokens": 3143072} {"current_steps": 9655, "total_steps": 40000, "loss": 0.1853, "lr": 4.315147032529619e-05, "epoch": 7.901350798198935, "percentage": 24.14, "elapsed_time": "1:06:32", "remaining_time": "3:29:07", "throughput": 787.69, "total_tokens": 3144736} {"current_steps": 9660, "total_steps": 40000, "loss": 0.199, "lr": 4.3144718108559845e-05, "epoch": 7.9054441260744985, "percentage": 24.15, "elapsed_time": "1:06:34", "remaining_time": "3:29:04", "throughput": 787.78, "total_tokens": 3146464} {"current_steps": 9665, "total_steps": 40000, "loss": 0.2054, "lr": 4.3137963093679945e-05, "epoch": 7.909537453950062, "percentage": 24.16, "elapsed_time": "1:06:35", "remaining_time": "3:29:01", "throughput": 787.86, "total_tokens": 3148144} {"current_steps": 9670, "total_steps": 40000, "loss": 0.2552, "lr": 4.31312052816982e-05, "epoch": 7.913630781825624, "percentage": 24.18, "elapsed_time": "1:06:37", "remaining_time": "3:28:58", "throughput": 787.94, "total_tokens": 3149808} {"current_steps": 9675, "total_steps": 40000, "loss": 0.1808, "lr": 4.312444467365675e-05, "epoch": 7.9177241097011875, "percentage": 24.19, "elapsed_time": "1:06:39", "remaining_time": "3:28:55", "throughput": 788.02, "total_tokens": 3151472} {"current_steps": 9680, "total_steps": 40000, "loss": 0.1819, "lr": 4.311768127059816e-05, "epoch": 7.92181743757675, "percentage": 24.2, "elapsed_time": "1:06:40", "remaining_time": "3:28:51", "throughput": 788.09, "total_tokens": 3153120} {"current_steps": 9685, "total_steps": 40000, "loss": 0.1574, "lr": 4.3110915073565444e-05, "epoch": 7.925910765452313, "percentage": 24.21, "elapsed_time": "1:06:42", "remaining_time": "3:28:48", "throughput": 788.17, "total_tokens": 3154768} {"current_steps": 9690, "total_steps": 40000, "loss": 0.2194, "lr": 4.310414608360203e-05, "epoch": 7.9300040933278755, "percentage": 24.22, "elapsed_time": "1:06:44", "remaining_time": "3:28:45", "throughput": 788.23, "total_tokens": 3156368} {"current_steps": 9695, "total_steps": 40000, "loss": 0.1597, "lr": 4.309737430175177e-05, "epoch": 7.934097421203439, "percentage": 24.24, "elapsed_time": "1:06:46", "remaining_time": "3:28:42", "throughput": 788.28, "total_tokens": 3157952} {"current_steps": 9700, "total_steps": 40000, "loss": 0.1716, "lr": 4.309059972905897e-05, "epoch": 7.938190749079001, "percentage": 24.25, "elapsed_time": "1:06:47", "remaining_time": "3:28:39", "throughput": 788.35, "total_tokens": 3159600} {"current_steps": 9705, "total_steps": 40000, "loss": 0.2125, "lr": 4.308382236656836e-05, "epoch": 7.942284076954564, "percentage": 24.26, "elapsed_time": "1:06:49", "remaining_time": "3:28:36", "throughput": 788.42, "total_tokens": 3161216} {"current_steps": 9710, "total_steps": 40000, "loss": 0.2055, "lr": 4.307704221532507e-05, "epoch": 7.946377404830127, "percentage": 24.27, "elapsed_time": "1:06:51", "remaining_time": "3:28:33", "throughput": 788.51, "total_tokens": 3162944} {"current_steps": 9715, "total_steps": 40000, "loss": 0.1531, "lr": 4.307025927637471e-05, "epoch": 7.95047073270569, "percentage": 24.29, "elapsed_time": "1:06:52", "remaining_time": "3:28:29", "throughput": 788.59, "total_tokens": 3164592} {"current_steps": 9720, "total_steps": 40000, "loss": 0.2255, "lr": 4.306347355076328e-05, "epoch": 7.954564060581252, "percentage": 24.3, "elapsed_time": "1:06:54", "remaining_time": "3:28:26", "throughput": 788.65, "total_tokens": 3166224} {"current_steps": 9725, "total_steps": 40000, "loss": 0.26, "lr": 4.305668503953724e-05, "epoch": 7.958657388456816, "percentage": 24.31, "elapsed_time": "1:06:56", "remaining_time": "3:28:23", "throughput": 788.71, "total_tokens": 3167808} {"current_steps": 9730, "total_steps": 40000, "loss": 0.1926, "lr": 4.3049893743743436e-05, "epoch": 7.962750716332378, "percentage": 24.32, "elapsed_time": "1:06:58", "remaining_time": "3:28:20", "throughput": 788.78, "total_tokens": 3169424} {"current_steps": 9735, "total_steps": 40000, "loss": 0.1973, "lr": 4.304309966442919e-05, "epoch": 7.966844044207941, "percentage": 24.34, "elapsed_time": "1:06:59", "remaining_time": "3:28:17", "throughput": 788.84, "total_tokens": 3171040} {"current_steps": 9740, "total_steps": 40000, "loss": 0.1346, "lr": 4.303630280264224e-05, "epoch": 7.970937372083504, "percentage": 24.35, "elapsed_time": "1:07:01", "remaining_time": "3:28:14", "throughput": 788.89, "total_tokens": 3172608} {"current_steps": 9745, "total_steps": 40000, "loss": 0.1781, "lr": 4.302950315943074e-05, "epoch": 7.975030699959067, "percentage": 24.36, "elapsed_time": "1:07:03", "remaining_time": "3:28:11", "throughput": 788.96, "total_tokens": 3174256} {"current_steps": 9750, "total_steps": 40000, "loss": 0.1576, "lr": 4.3022700735843275e-05, "epoch": 7.979124027834629, "percentage": 24.38, "elapsed_time": "1:07:05", "remaining_time": "3:28:07", "throughput": 789.03, "total_tokens": 3175872} {"current_steps": 9755, "total_steps": 40000, "loss": 0.2032, "lr": 4.301589553292887e-05, "epoch": 7.983217355710193, "percentage": 24.39, "elapsed_time": "1:07:06", "remaining_time": "3:28:04", "throughput": 789.1, "total_tokens": 3177504} {"current_steps": 9760, "total_steps": 40000, "loss": 0.2157, "lr": 4.300908755173697e-05, "epoch": 7.987310683585755, "percentage": 24.4, "elapsed_time": "1:07:08", "remaining_time": "3:28:01", "throughput": 789.18, "total_tokens": 3179168} {"current_steps": 9765, "total_steps": 40000, "loss": 0.2327, "lr": 4.300227679331745e-05, "epoch": 7.991404011461318, "percentage": 24.41, "elapsed_time": "1:07:10", "remaining_time": "3:27:58", "throughput": 789.25, "total_tokens": 3180816} {"current_steps": 9770, "total_steps": 40000, "loss": 0.2757, "lr": 4.299546325872063e-05, "epoch": 7.995497339336881, "percentage": 24.43, "elapsed_time": "1:07:11", "remaining_time": "3:27:55", "throughput": 789.3, "total_tokens": 3182384} {"current_steps": 9775, "total_steps": 40000, "loss": 0.1269, "lr": 4.2988646948997225e-05, "epoch": 7.999590667212444, "percentage": 24.44, "elapsed_time": "1:07:13", "remaining_time": "3:27:52", "throughput": 789.37, "total_tokens": 3184016} {"current_steps": 9780, "total_steps": 40000, "loss": 0.2462, "lr": 4.29818278651984e-05, "epoch": 8.00327466230045, "percentage": 24.45, "elapsed_time": "1:07:15", "remaining_time": "3:27:49", "throughput": 789.35, "total_tokens": 3185416} {"current_steps": 9785, "total_steps": 40000, "loss": 0.216, "lr": 4.297500600837574e-05, "epoch": 8.007367990176013, "percentage": 24.46, "elapsed_time": "1:07:17", "remaining_time": "3:27:46", "throughput": 789.4, "total_tokens": 3187000} {"current_steps": 9790, "total_steps": 40000, "loss": 0.141, "lr": 4.2968181379581276e-05, "epoch": 8.011461318051577, "percentage": 24.47, "elapsed_time": "1:07:18", "remaining_time": "3:27:43", "throughput": 789.47, "total_tokens": 3188616} {"current_steps": 9795, "total_steps": 40000, "loss": 0.189, "lr": 4.296135397986743e-05, "epoch": 8.01555464592714, "percentage": 24.49, "elapsed_time": "1:07:20", "remaining_time": "3:27:40", "throughput": 789.54, "total_tokens": 3190248} {"current_steps": 9800, "total_steps": 40000, "loss": 0.2028, "lr": 4.295452381028709e-05, "epoch": 8.019647973802702, "percentage": 24.5, "elapsed_time": "1:07:22", "remaining_time": "3:27:37", "throughput": 789.59, "total_tokens": 3191832} {"current_steps": 9800, "total_steps": 40000, "eval_loss": 0.203047975897789, "epoch": 8.019647973802702, "percentage": 24.5, "elapsed_time": "1:07:34", "remaining_time": "3:28:15", "throughput": 787.17, "total_tokens": 3191832} {"current_steps": 9805, "total_steps": 40000, "loss": 0.1504, "lr": 4.294769087189354e-05, "epoch": 8.023741301678264, "percentage": 24.51, "elapsed_time": "1:07:37", "remaining_time": "3:28:16", "throughput": 786.96, "total_tokens": 3193464} {"current_steps": 9810, "total_steps": 40000, "loss": 0.1689, "lr": 4.294085516574052e-05, "epoch": 8.027834629553828, "percentage": 24.52, "elapsed_time": "1:07:39", "remaining_time": "3:28:13", "throughput": 787.02, "total_tokens": 3195064} {"current_steps": 9815, "total_steps": 40000, "loss": 0.2061, "lr": 4.2934016692882176e-05, "epoch": 8.03192795742939, "percentage": 24.54, "elapsed_time": "1:07:41", "remaining_time": "3:28:10", "throughput": 787.11, "total_tokens": 3196792} {"current_steps": 9820, "total_steps": 40000, "loss": 0.2254, "lr": 4.292717545437308e-05, "epoch": 8.036021285304953, "percentage": 24.55, "elapsed_time": "1:07:43", "remaining_time": "3:28:07", "throughput": 787.18, "total_tokens": 3198424} {"current_steps": 9825, "total_steps": 40000, "loss": 0.1581, "lr": 4.292033145126825e-05, "epoch": 8.040114613180515, "percentage": 24.56, "elapsed_time": "1:07:44", "remaining_time": "3:28:04", "throughput": 787.24, "total_tokens": 3200008} {"current_steps": 9830, "total_steps": 40000, "loss": 0.217, "lr": 4.29134846846231e-05, "epoch": 8.04420794105608, "percentage": 24.57, "elapsed_time": "1:07:46", "remaining_time": "3:28:01", "throughput": 787.3, "total_tokens": 3201624} {"current_steps": 9835, "total_steps": 40000, "loss": 0.169, "lr": 4.29066351554935e-05, "epoch": 8.048301268931642, "percentage": 24.59, "elapsed_time": "1:07:48", "remaining_time": "3:27:57", "throughput": 787.39, "total_tokens": 3203320} {"current_steps": 9840, "total_steps": 40000, "loss": 0.1857, "lr": 4.289978286493574e-05, "epoch": 8.052394596807204, "percentage": 24.6, "elapsed_time": "1:07:50", "remaining_time": "3:27:54", "throughput": 787.45, "total_tokens": 3204952} {"current_steps": 9845, "total_steps": 40000, "loss": 0.215, "lr": 4.28929278140065e-05, "epoch": 8.056487924682767, "percentage": 24.61, "elapsed_time": "1:07:51", "remaining_time": "3:27:51", "throughput": 787.53, "total_tokens": 3206632} {"current_steps": 9850, "total_steps": 40000, "loss": 0.1839, "lr": 4.288607000376295e-05, "epoch": 8.06058125255833, "percentage": 24.62, "elapsed_time": "1:07:53", "remaining_time": "3:27:48", "throughput": 787.62, "total_tokens": 3208328} {"current_steps": 9855, "total_steps": 40000, "loss": 0.2071, "lr": 4.2879209435262624e-05, "epoch": 8.064674580433893, "percentage": 24.64, "elapsed_time": "1:07:55", "remaining_time": "3:27:45", "throughput": 787.7, "total_tokens": 3210024} {"current_steps": 9860, "total_steps": 40000, "loss": 0.1879, "lr": 4.287234610956353e-05, "epoch": 8.068767908309455, "percentage": 24.65, "elapsed_time": "1:07:56", "remaining_time": "3:27:42", "throughput": 787.79, "total_tokens": 3211720} {"current_steps": 9865, "total_steps": 40000, "loss": 0.1666, "lr": 4.2865480027724056e-05, "epoch": 8.072861236185018, "percentage": 24.66, "elapsed_time": "1:07:58", "remaining_time": "3:27:39", "throughput": 787.88, "total_tokens": 3213448} {"current_steps": 9870, "total_steps": 40000, "loss": 0.2726, "lr": 4.285861119080306e-05, "epoch": 8.076954564060582, "percentage": 24.68, "elapsed_time": "1:08:00", "remaining_time": "3:27:36", "throughput": 787.96, "total_tokens": 3215160} {"current_steps": 9875, "total_steps": 40000, "loss": 0.177, "lr": 4.2851739599859784e-05, "epoch": 8.081047891936144, "percentage": 24.69, "elapsed_time": "1:08:02", "remaining_time": "3:27:32", "throughput": 788.04, "total_tokens": 3216824} {"current_steps": 9880, "total_steps": 40000, "loss": 0.2284, "lr": 4.2844865255953934e-05, "epoch": 8.085141219811707, "percentage": 24.7, "elapsed_time": "1:08:03", "remaining_time": "3:27:29", "throughput": 788.12, "total_tokens": 3218504} {"current_steps": 9885, "total_steps": 40000, "loss": 0.2821, "lr": 4.2837988160145605e-05, "epoch": 8.08923454768727, "percentage": 24.71, "elapsed_time": "1:08:05", "remaining_time": "3:27:26", "throughput": 788.2, "total_tokens": 3220168} {"current_steps": 9890, "total_steps": 40000, "loss": 0.3013, "lr": 4.2831108313495336e-05, "epoch": 8.093327875562833, "percentage": 24.73, "elapsed_time": "1:08:07", "remaining_time": "3:27:23", "throughput": 788.27, "total_tokens": 3221816} {"current_steps": 9895, "total_steps": 40000, "loss": 0.1593, "lr": 4.282422571706408e-05, "epoch": 8.097421203438396, "percentage": 24.74, "elapsed_time": "1:08:08", "remaining_time": "3:27:20", "throughput": 788.33, "total_tokens": 3223432} {"current_steps": 9900, "total_steps": 40000, "loss": 0.1659, "lr": 4.281734037191323e-05, "epoch": 8.101514531313958, "percentage": 24.75, "elapsed_time": "1:08:10", "remaining_time": "3:27:17", "throughput": 788.4, "total_tokens": 3225064} {"current_steps": 9905, "total_steps": 40000, "loss": 0.1871, "lr": 4.281045227910459e-05, "epoch": 8.10560785918952, "percentage": 24.76, "elapsed_time": "1:08:12", "remaining_time": "3:27:14", "throughput": 788.47, "total_tokens": 3226680} {"current_steps": 9910, "total_steps": 40000, "loss": 0.1436, "lr": 4.280356143970038e-05, "epoch": 8.109701187065085, "percentage": 24.77, "elapsed_time": "1:08:14", "remaining_time": "3:27:10", "throughput": 788.53, "total_tokens": 3228312} {"current_steps": 9915, "total_steps": 40000, "loss": 0.2128, "lr": 4.279666785476327e-05, "epoch": 8.113794514940647, "percentage": 24.79, "elapsed_time": "1:08:15", "remaining_time": "3:27:07", "throughput": 788.61, "total_tokens": 3229976} {"current_steps": 9920, "total_steps": 40000, "loss": 0.1988, "lr": 4.2789771525356325e-05, "epoch": 8.11788784281621, "percentage": 24.8, "elapsed_time": "1:08:17", "remaining_time": "3:27:04", "throughput": 788.66, "total_tokens": 3231560} {"current_steps": 9925, "total_steps": 40000, "loss": 0.2003, "lr": 4.2782872452543056e-05, "epoch": 8.121981170691772, "percentage": 24.81, "elapsed_time": "1:08:19", "remaining_time": "3:27:01", "throughput": 788.73, "total_tokens": 3233176} {"current_steps": 9930, "total_steps": 40000, "loss": 0.2773, "lr": 4.2775970637387376e-05, "epoch": 8.126074498567336, "percentage": 24.82, "elapsed_time": "1:08:20", "remaining_time": "3:26:58", "throughput": 788.79, "total_tokens": 3234792} {"current_steps": 9935, "total_steps": 40000, "loss": 0.1785, "lr": 4.276906608095363e-05, "epoch": 8.130167826442898, "percentage": 24.84, "elapsed_time": "1:08:22", "remaining_time": "3:26:55", "throughput": 788.84, "total_tokens": 3236360} {"current_steps": 9940, "total_steps": 40000, "loss": 0.1832, "lr": 4.276215878430661e-05, "epoch": 8.13426115431846, "percentage": 24.85, "elapsed_time": "1:08:24", "remaining_time": "3:26:52", "throughput": 788.9, "total_tokens": 3237960} {"current_steps": 9945, "total_steps": 40000, "loss": 0.212, "lr": 4.275524874851149e-05, "epoch": 8.138354482194023, "percentage": 24.86, "elapsed_time": "1:08:26", "remaining_time": "3:26:49", "throughput": 788.97, "total_tokens": 3239592} {"current_steps": 9950, "total_steps": 40000, "loss": 0.1587, "lr": 4.274833597463388e-05, "epoch": 8.142447810069587, "percentage": 24.88, "elapsed_time": "1:08:27", "remaining_time": "3:26:46", "throughput": 789.05, "total_tokens": 3241256} {"current_steps": 9955, "total_steps": 40000, "loss": 0.2112, "lr": 4.2741420463739824e-05, "epoch": 8.14654113794515, "percentage": 24.89, "elapsed_time": "1:08:29", "remaining_time": "3:26:42", "throughput": 789.11, "total_tokens": 3242872} {"current_steps": 9960, "total_steps": 40000, "loss": 0.1783, "lr": 4.273450221689578e-05, "epoch": 8.150634465820712, "percentage": 24.9, "elapsed_time": "1:08:31", "remaining_time": "3:26:39", "throughput": 789.17, "total_tokens": 3244472} {"current_steps": 9965, "total_steps": 40000, "loss": 0.118, "lr": 4.272758123516863e-05, "epoch": 8.154727793696274, "percentage": 24.91, "elapsed_time": "1:08:32", "remaining_time": "3:26:36", "throughput": 789.24, "total_tokens": 3246120} {"current_steps": 9970, "total_steps": 40000, "loss": 0.2194, "lr": 4.272065751962567e-05, "epoch": 8.158821121571838, "percentage": 24.93, "elapsed_time": "1:08:34", "remaining_time": "3:26:33", "throughput": 789.32, "total_tokens": 3247784} {"current_steps": 9975, "total_steps": 40000, "loss": 0.1882, "lr": 4.271373107133464e-05, "epoch": 8.1629144494474, "percentage": 24.94, "elapsed_time": "1:08:36", "remaining_time": "3:26:30", "throughput": 789.39, "total_tokens": 3249448} {"current_steps": 9980, "total_steps": 40000, "loss": 0.1334, "lr": 4.270680189136366e-05, "epoch": 8.167007777322963, "percentage": 24.95, "elapsed_time": "1:08:38", "remaining_time": "3:26:27", "throughput": 789.45, "total_tokens": 3251048} {"current_steps": 9985, "total_steps": 40000, "loss": 0.2267, "lr": 4.269986998078132e-05, "epoch": 8.171101105198526, "percentage": 24.96, "elapsed_time": "1:08:39", "remaining_time": "3:26:24", "throughput": 789.54, "total_tokens": 3252760} {"current_steps": 9990, "total_steps": 40000, "loss": 0.2091, "lr": 4.2692935340656595e-05, "epoch": 8.17519443307409, "percentage": 24.98, "elapsed_time": "1:08:41", "remaining_time": "3:26:21", "throughput": 789.61, "total_tokens": 3254392} {"current_steps": 9995, "total_steps": 40000, "loss": 0.2298, "lr": 4.26859979720589e-05, "epoch": 8.179287760949652, "percentage": 24.99, "elapsed_time": "1:08:43", "remaining_time": "3:26:17", "throughput": 789.66, "total_tokens": 3255976} {"current_steps": 10000, "total_steps": 40000, "loss": 0.205, "lr": 4.267905787605806e-05, "epoch": 8.183381088825215, "percentage": 25.0, "elapsed_time": "1:08:44", "remaining_time": "3:26:14", "throughput": 789.74, "total_tokens": 3257640} {"current_steps": 10000, "total_steps": 40000, "eval_loss": 0.20341935753822327, "epoch": 8.183381088825215, "percentage": 25.0, "elapsed_time": "1:08:57", "remaining_time": "3:26:52", "throughput": 787.36, "total_tokens": 3257640} {"current_steps": 10005, "total_steps": 40000, "loss": 0.1669, "lr": 4.267211505372433e-05, "epoch": 8.187474416700777, "percentage": 25.01, "elapsed_time": "1:09:01", "remaining_time": "3:26:55", "throughput": 787.04, "total_tokens": 3259272} {"current_steps": 10010, "total_steps": 40000, "loss": 0.1504, "lr": 4.266516950612837e-05, "epoch": 8.191567744576341, "percentage": 25.02, "elapsed_time": "1:09:02", "remaining_time": "3:26:52", "throughput": 787.1, "total_tokens": 3260872} {"current_steps": 10015, "total_steps": 40000, "loss": 0.2234, "lr": 4.265822123434128e-05, "epoch": 8.195661072451903, "percentage": 25.04, "elapsed_time": "1:09:04", "remaining_time": "3:26:49", "throughput": 787.18, "total_tokens": 3262552} {"current_steps": 10020, "total_steps": 40000, "loss": 0.1738, "lr": 4.265127023943457e-05, "epoch": 8.199754400327466, "percentage": 25.05, "elapsed_time": "1:09:06", "remaining_time": "3:26:45", "throughput": 787.24, "total_tokens": 3264152} {"current_steps": 10025, "total_steps": 40000, "loss": 0.2317, "lr": 4.2644316522480176e-05, "epoch": 8.203847728203028, "percentage": 25.06, "elapsed_time": "1:09:08", "remaining_time": "3:26:42", "throughput": 787.3, "total_tokens": 3265768} {"current_steps": 10030, "total_steps": 40000, "loss": 0.2163, "lr": 4.263736008455044e-05, "epoch": 8.207941056078592, "percentage": 25.07, "elapsed_time": "1:09:09", "remaining_time": "3:26:39", "throughput": 787.36, "total_tokens": 3267368} {"current_steps": 10035, "total_steps": 40000, "loss": 0.134, "lr": 4.2630400926718125e-05, "epoch": 8.212034383954155, "percentage": 25.09, "elapsed_time": "1:09:11", "remaining_time": "3:26:36", "throughput": 787.44, "total_tokens": 3269032} {"current_steps": 10040, "total_steps": 40000, "loss": 0.1682, "lr": 4.262343905005644e-05, "epoch": 8.216127711829717, "percentage": 25.1, "elapsed_time": "1:09:13", "remaining_time": "3:26:33", "throughput": 787.51, "total_tokens": 3270696} {"current_steps": 10045, "total_steps": 40000, "loss": 0.2112, "lr": 4.261647445563897e-05, "epoch": 8.22022103970528, "percentage": 25.11, "elapsed_time": "1:09:14", "remaining_time": "3:26:30", "throughput": 787.56, "total_tokens": 3272232} {"current_steps": 10050, "total_steps": 40000, "loss": 0.1886, "lr": 4.260950714453976e-05, "epoch": 8.224314367580844, "percentage": 25.12, "elapsed_time": "1:09:16", "remaining_time": "3:26:27", "throughput": 787.61, "total_tokens": 3273832} {"current_steps": 10055, "total_steps": 40000, "loss": 0.2073, "lr": 4.2602537117833266e-05, "epoch": 8.228407695456406, "percentage": 25.14, "elapsed_time": "1:09:18", "remaining_time": "3:26:24", "throughput": 787.67, "total_tokens": 3275432} {"current_steps": 10060, "total_steps": 40000, "loss": 0.1941, "lr": 4.259556437659433e-05, "epoch": 8.232501023331968, "percentage": 25.15, "elapsed_time": "1:09:20", "remaining_time": "3:26:21", "throughput": 787.73, "total_tokens": 3277032} {"current_steps": 10065, "total_steps": 40000, "loss": 0.2222, "lr": 4.258858892189825e-05, "epoch": 8.236594351207533, "percentage": 25.16, "elapsed_time": "1:09:21", "remaining_time": "3:26:17", "throughput": 787.79, "total_tokens": 3278632} {"current_steps": 10070, "total_steps": 40000, "loss": 0.1943, "lr": 4.2581610754820725e-05, "epoch": 8.240687679083095, "percentage": 25.17, "elapsed_time": "1:09:23", "remaining_time": "3:26:14", "throughput": 787.86, "total_tokens": 3280280} {"current_steps": 10075, "total_steps": 40000, "loss": 0.1463, "lr": 4.2574629876437876e-05, "epoch": 8.244781006958657, "percentage": 25.19, "elapsed_time": "1:09:25", "remaining_time": "3:26:11", "throughput": 787.93, "total_tokens": 3281928} {"current_steps": 10080, "total_steps": 40000, "loss": 0.185, "lr": 4.256764628782625e-05, "epoch": 8.24887433483422, "percentage": 25.2, "elapsed_time": "1:09:26", "remaining_time": "3:26:08", "throughput": 788.0, "total_tokens": 3283560} {"current_steps": 10085, "total_steps": 40000, "loss": 0.1125, "lr": 4.256065999006279e-05, "epoch": 8.252967662709784, "percentage": 25.21, "elapsed_time": "1:09:28", "remaining_time": "3:26:05", "throughput": 788.07, "total_tokens": 3285192} {"current_steps": 10090, "total_steps": 40000, "loss": 0.1604, "lr": 4.2553670984224885e-05, "epoch": 8.257060990585346, "percentage": 25.22, "elapsed_time": "1:09:30", "remaining_time": "3:26:02", "throughput": 788.13, "total_tokens": 3286824} {"current_steps": 10095, "total_steps": 40000, "loss": 0.2031, "lr": 4.254667927139032e-05, "epoch": 8.261154318460909, "percentage": 25.24, "elapsed_time": "1:09:32", "remaining_time": "3:25:59", "throughput": 788.19, "total_tokens": 3288424} {"current_steps": 10100, "total_steps": 40000, "loss": 0.2457, "lr": 4.2539684852637295e-05, "epoch": 8.265247646336471, "percentage": 25.25, "elapsed_time": "1:09:33", "remaining_time": "3:25:56", "throughput": 788.25, "total_tokens": 3290024} {"current_steps": 10105, "total_steps": 40000, "loss": 0.1727, "lr": 4.253268772904446e-05, "epoch": 8.269340974212035, "percentage": 25.26, "elapsed_time": "1:09:35", "remaining_time": "3:25:53", "throughput": 788.31, "total_tokens": 3291640} {"current_steps": 10110, "total_steps": 40000, "loss": 0.2474, "lr": 4.252568790169085e-05, "epoch": 8.273434302087598, "percentage": 25.27, "elapsed_time": "1:09:37", "remaining_time": "3:25:50", "throughput": 788.36, "total_tokens": 3293176} {"current_steps": 10115, "total_steps": 40000, "loss": 0.2255, "lr": 4.251868537165592e-05, "epoch": 8.27752762996316, "percentage": 25.29, "elapsed_time": "1:09:38", "remaining_time": "3:25:46", "throughput": 788.42, "total_tokens": 3294792} {"current_steps": 10120, "total_steps": 40000, "loss": 0.1978, "lr": 4.251168014001955e-05, "epoch": 8.281620957838722, "percentage": 25.3, "elapsed_time": "1:09:40", "remaining_time": "3:25:43", "throughput": 788.48, "total_tokens": 3296392} {"current_steps": 10125, "total_steps": 40000, "loss": 0.1882, "lr": 4.250467220786204e-05, "epoch": 8.285714285714286, "percentage": 25.31, "elapsed_time": "1:09:42", "remaining_time": "3:25:40", "throughput": 788.54, "total_tokens": 3298024} {"current_steps": 10130, "total_steps": 40000, "loss": 0.1504, "lr": 4.249766157626409e-05, "epoch": 8.289807613589849, "percentage": 25.32, "elapsed_time": "1:09:44", "remaining_time": "3:25:37", "throughput": 788.61, "total_tokens": 3299672} {"current_steps": 10135, "total_steps": 40000, "loss": 0.1664, "lr": 4.249064824630684e-05, "epoch": 8.293900941465411, "percentage": 25.34, "elapsed_time": "1:09:45", "remaining_time": "3:25:34", "throughput": 788.68, "total_tokens": 3301320} {"current_steps": 10140, "total_steps": 40000, "loss": 0.1827, "lr": 4.248363221907183e-05, "epoch": 8.297994269340974, "percentage": 25.35, "elapsed_time": "1:09:47", "remaining_time": "3:25:31", "throughput": 788.74, "total_tokens": 3302952} {"current_steps": 10145, "total_steps": 40000, "loss": 0.1464, "lr": 4.2476613495641026e-05, "epoch": 8.302087597216538, "percentage": 25.36, "elapsed_time": "1:09:49", "remaining_time": "3:25:28", "throughput": 788.82, "total_tokens": 3304600} {"current_steps": 10150, "total_steps": 40000, "loss": 0.224, "lr": 4.246959207709679e-05, "epoch": 8.3061809250921, "percentage": 25.37, "elapsed_time": "1:09:51", "remaining_time": "3:25:25", "throughput": 788.89, "total_tokens": 3306280} {"current_steps": 10155, "total_steps": 40000, "loss": 0.2293, "lr": 4.246256796452192e-05, "epoch": 8.310274252967663, "percentage": 25.39, "elapsed_time": "1:09:52", "remaining_time": "3:25:22", "throughput": 788.95, "total_tokens": 3307880} {"current_steps": 10160, "total_steps": 40000, "loss": 0.174, "lr": 4.245554115899962e-05, "epoch": 8.314367580843225, "percentage": 25.4, "elapsed_time": "1:09:54", "remaining_time": "3:25:19", "throughput": 789.01, "total_tokens": 3309480} {"current_steps": 10165, "total_steps": 40000, "loss": 0.2042, "lr": 4.2448511661613514e-05, "epoch": 8.318460908718789, "percentage": 25.41, "elapsed_time": "1:09:56", "remaining_time": "3:25:16", "throughput": 789.06, "total_tokens": 3311064} {"current_steps": 10170, "total_steps": 40000, "loss": 0.2635, "lr": 4.2441479473447635e-05, "epoch": 8.322554236594351, "percentage": 25.42, "elapsed_time": "1:09:57", "remaining_time": "3:25:13", "throughput": 789.15, "total_tokens": 3312760} {"current_steps": 10175, "total_steps": 40000, "loss": 0.1308, "lr": 4.243444459558644e-05, "epoch": 8.326647564469914, "percentage": 25.44, "elapsed_time": "1:09:59", "remaining_time": "3:25:09", "throughput": 789.22, "total_tokens": 3314424} {"current_steps": 10180, "total_steps": 40000, "loss": 0.1566, "lr": 4.24274070291148e-05, "epoch": 8.330740892345476, "percentage": 25.45, "elapsed_time": "1:10:01", "remaining_time": "3:25:06", "throughput": 789.28, "total_tokens": 3316040} {"current_steps": 10185, "total_steps": 40000, "loss": 0.1663, "lr": 4.242036677511798e-05, "epoch": 8.33483422022104, "percentage": 25.46, "elapsed_time": "1:10:03", "remaining_time": "3:25:03", "throughput": 789.34, "total_tokens": 3317656} {"current_steps": 10190, "total_steps": 40000, "loss": 0.1505, "lr": 4.241332383468169e-05, "epoch": 8.338927548096603, "percentage": 25.47, "elapsed_time": "1:10:04", "remaining_time": "3:25:00", "throughput": 789.43, "total_tokens": 3319352} {"current_steps": 10195, "total_steps": 40000, "loss": 0.168, "lr": 4.2406278208892034e-05, "epoch": 8.343020875972165, "percentage": 25.49, "elapsed_time": "1:10:06", "remaining_time": "3:24:57", "throughput": 789.48, "total_tokens": 3320952} {"current_steps": 10200, "total_steps": 40000, "loss": 0.1922, "lr": 4.2399229898835536e-05, "epoch": 8.347114203847728, "percentage": 25.5, "elapsed_time": "1:10:08", "remaining_time": "3:24:54", "throughput": 789.55, "total_tokens": 3322584} {"current_steps": 10200, "total_steps": 40000, "eval_loss": 0.2053452432155609, "epoch": 8.347114203847728, "percentage": 25.5, "elapsed_time": "1:10:20", "remaining_time": "3:25:31", "throughput": 787.21, "total_tokens": 3322584} {"current_steps": 10205, "total_steps": 40000, "loss": 0.1937, "lr": 4.239217890559914e-05, "epoch": 8.351207531723292, "percentage": 25.51, "elapsed_time": "1:10:23", "remaining_time": "3:25:32", "throughput": 786.98, "total_tokens": 3324152} {"current_steps": 10210, "total_steps": 40000, "loss": 0.1625, "lr": 4.238512523027019e-05, "epoch": 8.355300859598854, "percentage": 25.52, "elapsed_time": "1:10:25", "remaining_time": "3:25:29", "throughput": 787.04, "total_tokens": 3325768} {"current_steps": 10215, "total_steps": 40000, "loss": 0.2235, "lr": 4.237806887393645e-05, "epoch": 8.359394187474416, "percentage": 25.54, "elapsed_time": "1:10:27", "remaining_time": "3:25:26", "throughput": 787.1, "total_tokens": 3327384} {"current_steps": 10220, "total_steps": 40000, "loss": 0.2209, "lr": 4.237100983768611e-05, "epoch": 8.363487515349979, "percentage": 25.55, "elapsed_time": "1:10:29", "remaining_time": "3:25:23", "throughput": 787.16, "total_tokens": 3328984} {"current_steps": 10225, "total_steps": 40000, "loss": 0.1807, "lr": 4.2363948122607756e-05, "epoch": 8.367580843225543, "percentage": 25.56, "elapsed_time": "1:10:30", "remaining_time": "3:25:20", "throughput": 787.2, "total_tokens": 3330520} {"current_steps": 10230, "total_steps": 40000, "loss": 0.1967, "lr": 4.235688372979039e-05, "epoch": 8.371674171101105, "percentage": 25.57, "elapsed_time": "1:10:32", "remaining_time": "3:25:17", "throughput": 787.27, "total_tokens": 3332168} {"current_steps": 10235, "total_steps": 40000, "loss": 0.1364, "lr": 4.234981666032343e-05, "epoch": 8.375767498976668, "percentage": 25.59, "elapsed_time": "1:10:34", "remaining_time": "3:25:14", "throughput": 787.33, "total_tokens": 3333800} {"current_steps": 10240, "total_steps": 40000, "loss": 0.1556, "lr": 4.2342746915296704e-05, "epoch": 8.37986082685223, "percentage": 25.6, "elapsed_time": "1:10:36", "remaining_time": "3:25:10", "throughput": 787.4, "total_tokens": 3335432} {"current_steps": 10245, "total_steps": 40000, "loss": 0.1799, "lr": 4.233567449580047e-05, "epoch": 8.383954154727794, "percentage": 25.61, "elapsed_time": "1:10:37", "remaining_time": "3:25:07", "throughput": 787.46, "total_tokens": 3337032} {"current_steps": 10250, "total_steps": 40000, "loss": 0.1823, "lr": 4.232859940292537e-05, "epoch": 8.388047482603357, "percentage": 25.62, "elapsed_time": "1:10:39", "remaining_time": "3:25:04", "throughput": 787.52, "total_tokens": 3338648} {"current_steps": 10255, "total_steps": 40000, "loss": 0.1657, "lr": 4.232152163776248e-05, "epoch": 8.392140810478919, "percentage": 25.64, "elapsed_time": "1:10:41", "remaining_time": "3:25:01", "throughput": 787.57, "total_tokens": 3340232} {"current_steps": 10260, "total_steps": 40000, "loss": 0.1732, "lr": 4.231444120140328e-05, "epoch": 8.396234138354481, "percentage": 25.65, "elapsed_time": "1:10:42", "remaining_time": "3:24:58", "throughput": 787.63, "total_tokens": 3341848} {"current_steps": 10265, "total_steps": 40000, "loss": 0.2498, "lr": 4.230735809493967e-05, "epoch": 8.400327466230046, "percentage": 25.66, "elapsed_time": "1:10:44", "remaining_time": "3:24:55", "throughput": 787.69, "total_tokens": 3343448} {"current_steps": 10270, "total_steps": 40000, "loss": 0.203, "lr": 4.2300272319463926e-05, "epoch": 8.404420794105608, "percentage": 25.67, "elapsed_time": "1:10:46", "remaining_time": "3:24:52", "throughput": 787.76, "total_tokens": 3345096} {"current_steps": 10275, "total_steps": 40000, "loss": 0.2064, "lr": 4.2293183876068786e-05, "epoch": 8.40851412198117, "percentage": 25.69, "elapsed_time": "1:10:48", "remaining_time": "3:24:49", "throughput": 787.83, "total_tokens": 3346760} {"current_steps": 10280, "total_steps": 40000, "loss": 0.1439, "lr": 4.228609276584737e-05, "epoch": 8.412607449856733, "percentage": 25.7, "elapsed_time": "1:10:49", "remaining_time": "3:24:46", "throughput": 787.89, "total_tokens": 3348376} {"current_steps": 10285, "total_steps": 40000, "loss": 0.2078, "lr": 4.227899898989323e-05, "epoch": 8.416700777732297, "percentage": 25.71, "elapsed_time": "1:10:51", "remaining_time": "3:24:43", "throughput": 787.95, "total_tokens": 3349976} {"current_steps": 10290, "total_steps": 40000, "loss": 0.2157, "lr": 4.2271902549300293e-05, "epoch": 8.42079410560786, "percentage": 25.72, "elapsed_time": "1:10:53", "remaining_time": "3:24:40", "throughput": 788.02, "total_tokens": 3351608} {"current_steps": 10295, "total_steps": 40000, "loss": 0.3175, "lr": 4.226480344516294e-05, "epoch": 8.424887433483422, "percentage": 25.74, "elapsed_time": "1:10:54", "remaining_time": "3:24:37", "throughput": 788.09, "total_tokens": 3353256} {"current_steps": 10300, "total_steps": 40000, "loss": 0.1661, "lr": 4.2257701678575925e-05, "epoch": 8.428980761358984, "percentage": 25.75, "elapsed_time": "1:10:56", "remaining_time": "3:24:34", "throughput": 788.14, "total_tokens": 3354824} {"current_steps": 10305, "total_steps": 40000, "loss": 0.1702, "lr": 4.225059725063444e-05, "epoch": 8.433074089234548, "percentage": 25.76, "elapsed_time": "1:10:58", "remaining_time": "3:24:30", "throughput": 788.21, "total_tokens": 3356488} {"current_steps": 10310, "total_steps": 40000, "loss": 0.1847, "lr": 4.2243490162434074e-05, "epoch": 8.43716741711011, "percentage": 25.77, "elapsed_time": "1:11:00", "remaining_time": "3:24:27", "throughput": 788.28, "total_tokens": 3358136} {"current_steps": 10315, "total_steps": 40000, "loss": 0.1976, "lr": 4.223638041507083e-05, "epoch": 8.441260744985673, "percentage": 25.79, "elapsed_time": "1:11:01", "remaining_time": "3:24:24", "throughput": 788.34, "total_tokens": 3359752} {"current_steps": 10320, "total_steps": 40000, "loss": 0.1791, "lr": 4.2229268009641124e-05, "epoch": 8.445354072861235, "percentage": 25.8, "elapsed_time": "1:11:03", "remaining_time": "3:24:21", "throughput": 788.39, "total_tokens": 3361320} {"current_steps": 10325, "total_steps": 40000, "loss": 0.1657, "lr": 4.222215294724177e-05, "epoch": 8.4494474007368, "percentage": 25.81, "elapsed_time": "1:11:05", "remaining_time": "3:24:18", "throughput": 788.45, "total_tokens": 3362968} {"current_steps": 10330, "total_steps": 40000, "loss": 0.2131, "lr": 4.2215035228970005e-05, "epoch": 8.453540728612362, "percentage": 25.82, "elapsed_time": "1:11:06", "remaining_time": "3:24:15", "throughput": 788.51, "total_tokens": 3364568} {"current_steps": 10335, "total_steps": 40000, "loss": 0.2539, "lr": 4.2207914855923464e-05, "epoch": 8.457634056487924, "percentage": 25.84, "elapsed_time": "1:11:08", "remaining_time": "3:24:12", "throughput": 788.59, "total_tokens": 3366248} {"current_steps": 10340, "total_steps": 40000, "loss": 0.207, "lr": 4.220079182920021e-05, "epoch": 8.461727384363488, "percentage": 25.85, "elapsed_time": "1:11:10", "remaining_time": "3:24:09", "throughput": 788.64, "total_tokens": 3367816} {"current_steps": 10345, "total_steps": 40000, "loss": 0.1324, "lr": 4.2193666149898705e-05, "epoch": 8.46582071223905, "percentage": 25.86, "elapsed_time": "1:11:12", "remaining_time": "3:24:06", "throughput": 788.7, "total_tokens": 3369448} {"current_steps": 10350, "total_steps": 40000, "loss": 0.1897, "lr": 4.21865378191178e-05, "epoch": 8.469914040114613, "percentage": 25.87, "elapsed_time": "1:11:14", "remaining_time": "3:24:04", "throughput": 788.72, "total_tokens": 3371080} {"current_steps": 10355, "total_steps": 40000, "loss": 0.2248, "lr": 4.217940683795678e-05, "epoch": 8.474007367990176, "percentage": 25.89, "elapsed_time": "1:11:15", "remaining_time": "3:24:01", "throughput": 788.79, "total_tokens": 3372744} {"current_steps": 10360, "total_steps": 40000, "loss": 0.2237, "lr": 4.217227320751534e-05, "epoch": 8.47810069586574, "percentage": 25.9, "elapsed_time": "1:11:17", "remaining_time": "3:23:58", "throughput": 788.85, "total_tokens": 3374392} {"current_steps": 10365, "total_steps": 40000, "loss": 0.1753, "lr": 4.216513692889358e-05, "epoch": 8.482194023741302, "percentage": 25.91, "elapsed_time": "1:11:19", "remaining_time": "3:23:55", "throughput": 788.92, "total_tokens": 3376040} {"current_steps": 10370, "total_steps": 40000, "loss": 0.2048, "lr": 4.215799800319199e-05, "epoch": 8.486287351616864, "percentage": 25.92, "elapsed_time": "1:11:21", "remaining_time": "3:23:52", "throughput": 789.0, "total_tokens": 3377704} {"current_steps": 10375, "total_steps": 40000, "loss": 0.2342, "lr": 4.2150856431511485e-05, "epoch": 8.490380679492427, "percentage": 25.94, "elapsed_time": "1:11:22", "remaining_time": "3:23:49", "throughput": 789.07, "total_tokens": 3379384} {"current_steps": 10380, "total_steps": 40000, "loss": 0.1589, "lr": 4.214371221495339e-05, "epoch": 8.494474007367991, "percentage": 25.95, "elapsed_time": "1:11:24", "remaining_time": "3:23:45", "throughput": 789.14, "total_tokens": 3381032} {"current_steps": 10385, "total_steps": 40000, "loss": 0.2121, "lr": 4.213656535461942e-05, "epoch": 8.498567335243553, "percentage": 25.96, "elapsed_time": "1:11:26", "remaining_time": "3:23:42", "throughput": 789.21, "total_tokens": 3382696} {"current_steps": 10390, "total_steps": 40000, "loss": 0.2307, "lr": 4.2129415851611734e-05, "epoch": 8.502660663119116, "percentage": 25.97, "elapsed_time": "1:11:27", "remaining_time": "3:23:39", "throughput": 789.3, "total_tokens": 3384424} {"current_steps": 10395, "total_steps": 40000, "loss": 0.1336, "lr": 4.2122263707032855e-05, "epoch": 8.506753990994678, "percentage": 25.99, "elapsed_time": "1:11:29", "remaining_time": "3:23:36", "throughput": 789.37, "total_tokens": 3386088} {"current_steps": 10400, "total_steps": 40000, "loss": 0.1352, "lr": 4.211510892198574e-05, "epoch": 8.510847318870242, "percentage": 26.0, "elapsed_time": "1:11:31", "remaining_time": "3:23:33", "throughput": 789.43, "total_tokens": 3387672} {"current_steps": 10400, "total_steps": 40000, "eval_loss": 0.20806898176670074, "epoch": 8.510847318870242, "percentage": 26.0, "elapsed_time": "1:11:43", "remaining_time": "3:24:09", "throughput": 787.15, "total_tokens": 3387672} {"current_steps": 10405, "total_steps": 40000, "loss": 0.1592, "lr": 4.210795149757375e-05, "epoch": 8.514940646745805, "percentage": 26.01, "elapsed_time": "1:11:46", "remaining_time": "3:24:10", "throughput": 786.95, "total_tokens": 3389320} {"current_steps": 10410, "total_steps": 40000, "loss": 0.2423, "lr": 4.210079143490065e-05, "epoch": 8.519033974621367, "percentage": 26.02, "elapsed_time": "1:11:48", "remaining_time": "3:24:07", "throughput": 787.0, "total_tokens": 3390872} {"current_steps": 10415, "total_steps": 40000, "loss": 0.254, "lr": 4.2093628735070604e-05, "epoch": 8.52312730249693, "percentage": 26.04, "elapsed_time": "1:11:50", "remaining_time": "3:24:03", "throughput": 787.06, "total_tokens": 3392488} {"current_steps": 10420, "total_steps": 40000, "loss": 0.1856, "lr": 4.208646339918819e-05, "epoch": 8.527220630372494, "percentage": 26.05, "elapsed_time": "1:11:52", "remaining_time": "3:24:00", "throughput": 787.12, "total_tokens": 3394104} {"current_steps": 10425, "total_steps": 40000, "loss": 0.1509, "lr": 4.2079295428358414e-05, "epoch": 8.531313958248056, "percentage": 26.06, "elapsed_time": "1:11:53", "remaining_time": "3:23:57", "throughput": 787.19, "total_tokens": 3395752} {"current_steps": 10430, "total_steps": 40000, "loss": 0.213, "lr": 4.207212482368664e-05, "epoch": 8.535407286123618, "percentage": 26.07, "elapsed_time": "1:11:55", "remaining_time": "3:23:54", "throughput": 787.24, "total_tokens": 3397336} {"current_steps": 10435, "total_steps": 40000, "loss": 0.2078, "lr": 4.206495158627867e-05, "epoch": 8.53950061399918, "percentage": 26.09, "elapsed_time": "1:11:57", "remaining_time": "3:23:51", "throughput": 787.3, "total_tokens": 3398920} {"current_steps": 10440, "total_steps": 40000, "loss": 0.2145, "lr": 4.205777571724073e-05, "epoch": 8.543593941874745, "percentage": 26.1, "elapsed_time": "1:11:58", "remaining_time": "3:23:48", "throughput": 787.38, "total_tokens": 3400600} {"current_steps": 10445, "total_steps": 40000, "loss": 0.2074, "lr": 4.20505972176794e-05, "epoch": 8.547687269750307, "percentage": 26.11, "elapsed_time": "1:12:00", "remaining_time": "3:23:45", "throughput": 787.44, "total_tokens": 3402232} {"current_steps": 10450, "total_steps": 40000, "loss": 0.1804, "lr": 4.204341608870171e-05, "epoch": 8.55178059762587, "percentage": 26.12, "elapsed_time": "1:12:02", "remaining_time": "3:23:42", "throughput": 787.51, "total_tokens": 3403880} {"current_steps": 10455, "total_steps": 40000, "loss": 0.2233, "lr": 4.203623233141508e-05, "epoch": 8.555873925501432, "percentage": 26.14, "elapsed_time": "1:12:04", "remaining_time": "3:23:39", "throughput": 787.57, "total_tokens": 3405512} {"current_steps": 10460, "total_steps": 40000, "loss": 0.1961, "lr": 4.2029045946927334e-05, "epoch": 8.559967253376996, "percentage": 26.15, "elapsed_time": "1:12:05", "remaining_time": "3:23:36", "throughput": 787.64, "total_tokens": 3407176} {"current_steps": 10465, "total_steps": 40000, "loss": 0.284, "lr": 4.20218569363467e-05, "epoch": 8.564060581252559, "percentage": 26.16, "elapsed_time": "1:12:07", "remaining_time": "3:23:33", "throughput": 787.71, "total_tokens": 3408792} {"current_steps": 10470, "total_steps": 40000, "loss": 0.1318, "lr": 4.2014665300781834e-05, "epoch": 8.568153909128121, "percentage": 26.17, "elapsed_time": "1:12:09", "remaining_time": "3:23:30", "throughput": 787.78, "total_tokens": 3410440} {"current_steps": 10475, "total_steps": 40000, "loss": 0.1973, "lr": 4.200747104134174e-05, "epoch": 8.572247237003683, "percentage": 26.19, "elapsed_time": "1:12:10", "remaining_time": "3:23:27", "throughput": 787.84, "total_tokens": 3412072} {"current_steps": 10480, "total_steps": 40000, "loss": 0.2276, "lr": 4.200027415913588e-05, "epoch": 8.576340564879247, "percentage": 26.2, "elapsed_time": "1:12:12", "remaining_time": "3:23:24", "throughput": 787.9, "total_tokens": 3413672} {"current_steps": 10485, "total_steps": 40000, "loss": 0.1481, "lr": 4.1993074655274126e-05, "epoch": 8.58043389275481, "percentage": 26.21, "elapsed_time": "1:12:14", "remaining_time": "3:23:21", "throughput": 787.97, "total_tokens": 3415336} {"current_steps": 10490, "total_steps": 40000, "loss": 0.2413, "lr": 4.198587253086669e-05, "epoch": 8.584527220630372, "percentage": 26.22, "elapsed_time": "1:12:16", "remaining_time": "3:23:18", "throughput": 788.03, "total_tokens": 3416936} {"current_steps": 10495, "total_steps": 40000, "loss": 0.1916, "lr": 4.197866778702426e-05, "epoch": 8.588620548505935, "percentage": 26.24, "elapsed_time": "1:12:17", "remaining_time": "3:23:14", "throughput": 788.12, "total_tokens": 3418680} {"current_steps": 10500, "total_steps": 40000, "loss": 0.1376, "lr": 4.197146042485789e-05, "epoch": 8.592713876381499, "percentage": 26.25, "elapsed_time": "1:12:19", "remaining_time": "3:23:11", "throughput": 788.17, "total_tokens": 3420248} {"current_steps": 10505, "total_steps": 40000, "loss": 0.1934, "lr": 4.1964250445479046e-05, "epoch": 8.596807204257061, "percentage": 26.26, "elapsed_time": "1:12:21", "remaining_time": "3:23:08", "throughput": 788.25, "total_tokens": 3421960} {"current_steps": 10510, "total_steps": 40000, "loss": 0.1584, "lr": 4.19570378499996e-05, "epoch": 8.600900532132624, "percentage": 26.27, "elapsed_time": "1:12:22", "remaining_time": "3:23:05", "throughput": 788.32, "total_tokens": 3423624} {"current_steps": 10515, "total_steps": 40000, "loss": 0.2168, "lr": 4.194982263953182e-05, "epoch": 8.604993860008186, "percentage": 26.29, "elapsed_time": "1:12:24", "remaining_time": "3:23:02", "throughput": 788.39, "total_tokens": 3425272} {"current_steps": 10520, "total_steps": 40000, "loss": 0.1833, "lr": 4.194260481518838e-05, "epoch": 8.60908718788375, "percentage": 26.3, "elapsed_time": "1:12:26", "remaining_time": "3:22:59", "throughput": 788.44, "total_tokens": 3426856} {"current_steps": 10525, "total_steps": 40000, "loss": 0.2047, "lr": 4.1935384378082366e-05, "epoch": 8.613180515759312, "percentage": 26.31, "elapsed_time": "1:12:28", "remaining_time": "3:22:56", "throughput": 788.48, "total_tokens": 3428376} {"current_steps": 10530, "total_steps": 40000, "loss": 0.2415, "lr": 4.1928161329327267e-05, "epoch": 8.617273843634875, "percentage": 26.32, "elapsed_time": "1:12:29", "remaining_time": "3:22:53", "throughput": 788.55, "total_tokens": 3430040} {"current_steps": 10535, "total_steps": 40000, "loss": 0.2329, "lr": 4.1920935670036945e-05, "epoch": 8.621367171510437, "percentage": 26.34, "elapsed_time": "1:12:31", "remaining_time": "3:22:50", "throughput": 788.62, "total_tokens": 3431688} {"current_steps": 10540, "total_steps": 40000, "loss": 0.2167, "lr": 4.1913707401325705e-05, "epoch": 8.625460499386001, "percentage": 26.35, "elapsed_time": "1:12:33", "remaining_time": "3:22:47", "throughput": 788.69, "total_tokens": 3433336} {"current_steps": 10545, "total_steps": 40000, "loss": 0.2959, "lr": 4.1906476524308235e-05, "epoch": 8.629553827261564, "percentage": 26.36, "elapsed_time": "1:12:34", "remaining_time": "3:22:44", "throughput": 788.75, "total_tokens": 3434968} {"current_steps": 10550, "total_steps": 40000, "loss": 0.2365, "lr": 4.189924304009962e-05, "epoch": 8.633647155137126, "percentage": 26.38, "elapsed_time": "1:12:36", "remaining_time": "3:22:41", "throughput": 788.82, "total_tokens": 3436632} {"current_steps": 10555, "total_steps": 40000, "loss": 0.1448, "lr": 4.189200694981537e-05, "epoch": 8.637740483012688, "percentage": 26.39, "elapsed_time": "1:12:38", "remaining_time": "3:22:38", "throughput": 788.88, "total_tokens": 3438216} {"current_steps": 10560, "total_steps": 40000, "loss": 0.2557, "lr": 4.188476825457136e-05, "epoch": 8.641833810888253, "percentage": 26.4, "elapsed_time": "1:12:40", "remaining_time": "3:22:35", "throughput": 788.96, "total_tokens": 3439944} {"current_steps": 10565, "total_steps": 40000, "loss": 0.1925, "lr": 4.18775269554839e-05, "epoch": 8.645927138763815, "percentage": 26.41, "elapsed_time": "1:12:41", "remaining_time": "3:22:32", "throughput": 789.03, "total_tokens": 3441592} {"current_steps": 10570, "total_steps": 40000, "loss": 0.182, "lr": 4.187028305366969e-05, "epoch": 8.650020466639377, "percentage": 26.42, "elapsed_time": "1:12:43", "remaining_time": "3:22:29", "throughput": 789.1, "total_tokens": 3443240} {"current_steps": 10575, "total_steps": 40000, "loss": 0.1408, "lr": 4.1863036550245824e-05, "epoch": 8.654113794514942, "percentage": 26.44, "elapsed_time": "1:12:45", "remaining_time": "3:22:26", "throughput": 789.15, "total_tokens": 3444840} {"current_steps": 10580, "total_steps": 40000, "loss": 0.3167, "lr": 4.1855787446329806e-05, "epoch": 8.658207122390504, "percentage": 26.45, "elapsed_time": "1:12:46", "remaining_time": "3:22:23", "throughput": 789.21, "total_tokens": 3446424} {"current_steps": 10585, "total_steps": 40000, "loss": 0.1846, "lr": 4.184853574303955e-05, "epoch": 8.662300450266066, "percentage": 26.46, "elapsed_time": "1:12:48", "remaining_time": "3:22:20", "throughput": 789.27, "total_tokens": 3448040} {"current_steps": 10590, "total_steps": 40000, "loss": 0.2413, "lr": 4.184128144149334e-05, "epoch": 8.666393778141629, "percentage": 26.47, "elapsed_time": "1:12:50", "remaining_time": "3:22:17", "throughput": 789.33, "total_tokens": 3449688} {"current_steps": 10595, "total_steps": 40000, "loss": 0.1652, "lr": 4.1834024542809896e-05, "epoch": 8.670487106017191, "percentage": 26.49, "elapsed_time": "1:12:52", "remaining_time": "3:22:14", "throughput": 789.41, "total_tokens": 3451368} {"current_steps": 10600, "total_steps": 40000, "loss": 0.2004, "lr": 4.1826765048108315e-05, "epoch": 8.674580433892755, "percentage": 26.5, "elapsed_time": "1:12:53", "remaining_time": "3:22:11", "throughput": 789.46, "total_tokens": 3452968} {"current_steps": 10600, "total_steps": 40000, "eval_loss": 0.2052883803844452, "epoch": 8.674580433892755, "percentage": 26.5, "elapsed_time": "1:13:06", "remaining_time": "3:22:45", "throughput": 787.22, "total_tokens": 3452968} {"current_steps": 10605, "total_steps": 40000, "loss": 0.1201, "lr": 4.181950295850811e-05, "epoch": 8.678673761768318, "percentage": 26.51, "elapsed_time": "1:13:09", "remaining_time": "3:22:47", "throughput": 787.0, "total_tokens": 3454680} {"current_steps": 10610, "total_steps": 40000, "loss": 0.2971, "lr": 4.181223827512918e-05, "epoch": 8.68276708964388, "percentage": 26.52, "elapsed_time": "1:13:11", "remaining_time": "3:22:44", "throughput": 787.07, "total_tokens": 3456328} {"current_steps": 10615, "total_steps": 40000, "loss": 0.1901, "lr": 4.180497099909183e-05, "epoch": 8.686860417519444, "percentage": 26.54, "elapsed_time": "1:13:13", "remaining_time": "3:22:41", "throughput": 787.13, "total_tokens": 3457960} {"current_steps": 10620, "total_steps": 40000, "loss": 0.241, "lr": 4.179770113151677e-05, "epoch": 8.690953745395007, "percentage": 26.55, "elapsed_time": "1:13:14", "remaining_time": "3:22:38", "throughput": 787.2, "total_tokens": 3459608} {"current_steps": 10625, "total_steps": 40000, "loss": 0.2037, "lr": 4.179042867352511e-05, "epoch": 8.695047073270569, "percentage": 26.56, "elapsed_time": "1:13:16", "remaining_time": "3:22:35", "throughput": 787.26, "total_tokens": 3461208} {"current_steps": 10630, "total_steps": 40000, "loss": 0.1848, "lr": 4.1783153626238334e-05, "epoch": 8.699140401146131, "percentage": 26.57, "elapsed_time": "1:13:18", "remaining_time": "3:22:32", "throughput": 787.33, "total_tokens": 3462872} {"current_steps": 10635, "total_steps": 40000, "loss": 0.2222, "lr": 4.177587599077836e-05, "epoch": 8.703233729021695, "percentage": 26.59, "elapsed_time": "1:13:19", "remaining_time": "3:22:29", "throughput": 787.39, "total_tokens": 3464504} {"current_steps": 10640, "total_steps": 40000, "loss": 0.1651, "lr": 4.1768595768267494e-05, "epoch": 8.707327056897258, "percentage": 26.6, "elapsed_time": "1:13:21", "remaining_time": "3:22:26", "throughput": 787.45, "total_tokens": 3466136} {"current_steps": 10645, "total_steps": 40000, "loss": 0.1517, "lr": 4.176131295982843e-05, "epoch": 8.71142038477282, "percentage": 26.61, "elapsed_time": "1:13:23", "remaining_time": "3:22:23", "throughput": 787.52, "total_tokens": 3467768} {"current_steps": 10650, "total_steps": 40000, "loss": 0.1956, "lr": 4.1754027566584276e-05, "epoch": 8.715513712648383, "percentage": 26.62, "elapsed_time": "1:13:25", "remaining_time": "3:22:19", "throughput": 787.57, "total_tokens": 3469368} {"current_steps": 10655, "total_steps": 40000, "loss": 0.1762, "lr": 4.174673958965852e-05, "epoch": 8.719607040523947, "percentage": 26.64, "elapsed_time": "1:13:26", "remaining_time": "3:22:16", "throughput": 787.64, "total_tokens": 3471016} {"current_steps": 10660, "total_steps": 40000, "loss": 0.1747, "lr": 4.173944903017507e-05, "epoch": 8.72370036839951, "percentage": 26.65, "elapsed_time": "1:13:28", "remaining_time": "3:22:13", "throughput": 787.69, "total_tokens": 3472600} {"current_steps": 10665, "total_steps": 40000, "loss": 0.1808, "lr": 4.173215588925822e-05, "epoch": 8.727793696275072, "percentage": 26.66, "elapsed_time": "1:13:30", "remaining_time": "3:22:10", "throughput": 787.75, "total_tokens": 3474200} {"current_steps": 10670, "total_steps": 40000, "loss": 0.202, "lr": 4.172486016803266e-05, "epoch": 8.731887024150634, "percentage": 26.67, "elapsed_time": "1:13:32", "remaining_time": "3:22:07", "throughput": 787.82, "total_tokens": 3475848} {"current_steps": 10675, "total_steps": 40000, "loss": 0.2033, "lr": 4.171756186762349e-05, "epoch": 8.735980352026198, "percentage": 26.69, "elapsed_time": "1:13:33", "remaining_time": "3:22:04", "throughput": 787.88, "total_tokens": 3477480} {"current_steps": 10680, "total_steps": 40000, "loss": 0.1436, "lr": 4.171026098915619e-05, "epoch": 8.74007367990176, "percentage": 26.7, "elapsed_time": "1:13:35", "remaining_time": "3:22:01", "throughput": 787.94, "total_tokens": 3479112} {"current_steps": 10685, "total_steps": 40000, "loss": 0.2369, "lr": 4.170295753375665e-05, "epoch": 8.744167007777323, "percentage": 26.71, "elapsed_time": "1:13:37", "remaining_time": "3:21:58", "throughput": 788.0, "total_tokens": 3480696} {"current_steps": 10690, "total_steps": 40000, "loss": 0.208, "lr": 4.169565150255117e-05, "epoch": 8.748260335652885, "percentage": 26.72, "elapsed_time": "1:13:38", "remaining_time": "3:21:55", "throughput": 788.06, "total_tokens": 3482344} {"current_steps": 10695, "total_steps": 40000, "loss": 0.2095, "lr": 4.16883428966664e-05, "epoch": 8.75235366352845, "percentage": 26.74, "elapsed_time": "1:13:40", "remaining_time": "3:21:52", "throughput": 788.11, "total_tokens": 3483912} {"current_steps": 10700, "total_steps": 40000, "loss": 0.1244, "lr": 4.168103171722944e-05, "epoch": 8.756446991404012, "percentage": 26.75, "elapsed_time": "1:13:42", "remaining_time": "3:21:49", "throughput": 788.18, "total_tokens": 3485544} {"current_steps": 10705, "total_steps": 40000, "loss": 0.2125, "lr": 4.167371796536777e-05, "epoch": 8.760540319279574, "percentage": 26.76, "elapsed_time": "1:13:44", "remaining_time": "3:21:46", "throughput": 788.23, "total_tokens": 3487128} {"current_steps": 10710, "total_steps": 40000, "loss": 0.1695, "lr": 4.166640164220924e-05, "epoch": 8.764633647155136, "percentage": 26.77, "elapsed_time": "1:13:45", "remaining_time": "3:21:43", "throughput": 788.29, "total_tokens": 3488744} {"current_steps": 10715, "total_steps": 40000, "loss": 0.14, "lr": 4.1659082748882144e-05, "epoch": 8.7687269750307, "percentage": 26.79, "elapsed_time": "1:13:47", "remaining_time": "3:21:40", "throughput": 788.34, "total_tokens": 3490360} {"current_steps": 10720, "total_steps": 40000, "loss": 0.2094, "lr": 4.1651761286515135e-05, "epoch": 8.772820302906263, "percentage": 26.8, "elapsed_time": "1:13:49", "remaining_time": "3:21:37", "throughput": 788.4, "total_tokens": 3491960} {"current_steps": 10725, "total_steps": 40000, "loss": 0.1807, "lr": 4.164443725623728e-05, "epoch": 8.776913630781825, "percentage": 26.81, "elapsed_time": "1:13:50", "remaining_time": "3:21:34", "throughput": 788.46, "total_tokens": 3493576} {"current_steps": 10730, "total_steps": 40000, "loss": 0.2032, "lr": 4.163711065917802e-05, "epoch": 8.781006958657388, "percentage": 26.82, "elapsed_time": "1:13:52", "remaining_time": "3:21:31", "throughput": 788.52, "total_tokens": 3495176} {"current_steps": 10735, "total_steps": 40000, "loss": 0.1842, "lr": 4.1629781496467234e-05, "epoch": 8.785100286532952, "percentage": 26.84, "elapsed_time": "1:13:54", "remaining_time": "3:21:28", "throughput": 788.58, "total_tokens": 3496808} {"current_steps": 10740, "total_steps": 40000, "loss": 0.1645, "lr": 4.1622449769235164e-05, "epoch": 8.789193614408514, "percentage": 26.85, "elapsed_time": "1:13:56", "remaining_time": "3:21:25", "throughput": 788.66, "total_tokens": 3498504} {"current_steps": 10745, "total_steps": 40000, "loss": 0.219, "lr": 4.161511547861243e-05, "epoch": 8.793286942284077, "percentage": 26.86, "elapsed_time": "1:13:57", "remaining_time": "3:21:22", "throughput": 788.71, "total_tokens": 3500088} {"current_steps": 10750, "total_steps": 40000, "loss": 0.149, "lr": 4.1607778625730104e-05, "epoch": 8.797380270159639, "percentage": 26.88, "elapsed_time": "1:13:59", "remaining_time": "3:21:19", "throughput": 788.77, "total_tokens": 3501704} {"current_steps": 10755, "total_steps": 40000, "loss": 0.2471, "lr": 4.160043921171961e-05, "epoch": 8.801473598035203, "percentage": 26.89, "elapsed_time": "1:14:01", "remaining_time": "3:21:16", "throughput": 788.84, "total_tokens": 3503384} {"current_steps": 10760, "total_steps": 40000, "loss": 0.1776, "lr": 4.159309723771276e-05, "epoch": 8.805566925910766, "percentage": 26.9, "elapsed_time": "1:14:02", "remaining_time": "3:21:13", "throughput": 788.91, "total_tokens": 3505048} {"current_steps": 10765, "total_steps": 40000, "loss": 0.1807, "lr": 4.158575270484181e-05, "epoch": 8.809660253786328, "percentage": 26.91, "elapsed_time": "1:14:04", "remaining_time": "3:21:10", "throughput": 788.97, "total_tokens": 3506696} {"current_steps": 10770, "total_steps": 40000, "loss": 0.2101, "lr": 4.157840561423936e-05, "epoch": 8.81375358166189, "percentage": 26.92, "elapsed_time": "1:14:06", "remaining_time": "3:21:07", "throughput": 789.04, "total_tokens": 3508360} {"current_steps": 10775, "total_steps": 40000, "loss": 0.1885, "lr": 4.1571055967038416e-05, "epoch": 8.817846909537455, "percentage": 26.94, "elapsed_time": "1:14:08", "remaining_time": "3:21:04", "throughput": 789.11, "total_tokens": 3509992} {"current_steps": 10780, "total_steps": 40000, "loss": 0.1692, "lr": 4.156370376437241e-05, "epoch": 8.821940237413017, "percentage": 26.95, "elapsed_time": "1:14:09", "remaining_time": "3:21:01", "throughput": 789.18, "total_tokens": 3511656} {"current_steps": 10785, "total_steps": 40000, "loss": 0.224, "lr": 4.155634900737513e-05, "epoch": 8.82603356528858, "percentage": 26.96, "elapsed_time": "1:14:11", "remaining_time": "3:20:58", "throughput": 789.23, "total_tokens": 3513256} {"current_steps": 10790, "total_steps": 40000, "loss": 0.2009, "lr": 4.1548991697180764e-05, "epoch": 8.830126893164142, "percentage": 26.97, "elapsed_time": "1:14:13", "remaining_time": "3:20:55", "throughput": 789.29, "total_tokens": 3514856} {"current_steps": 10795, "total_steps": 40000, "loss": 0.2049, "lr": 4.1541631834923914e-05, "epoch": 8.834220221039706, "percentage": 26.99, "elapsed_time": "1:14:14", "remaining_time": "3:20:52", "throughput": 789.35, "total_tokens": 3516504} {"current_steps": 10800, "total_steps": 40000, "loss": 0.1564, "lr": 4.153426942173956e-05, "epoch": 8.838313548915268, "percentage": 27.0, "elapsed_time": "1:14:16", "remaining_time": "3:20:49", "throughput": 789.41, "total_tokens": 3518104} {"current_steps": 10800, "total_steps": 40000, "eval_loss": 0.2046450972557068, "epoch": 8.838313548915268, "percentage": 27.0, "elapsed_time": "1:14:29", "remaining_time": "3:21:23", "throughput": 787.21, "total_tokens": 3518104} {"current_steps": 10805, "total_steps": 40000, "loss": 0.2259, "lr": 4.152690445876308e-05, "epoch": 8.84240687679083, "percentage": 27.01, "elapsed_time": "1:14:32", "remaining_time": "3:21:24", "throughput": 787.0, "total_tokens": 3519720} {"current_steps": 10810, "total_steps": 40000, "loss": 0.1961, "lr": 4.1519536947130245e-05, "epoch": 8.846500204666393, "percentage": 27.02, "elapsed_time": "1:14:34", "remaining_time": "3:21:21", "throughput": 787.06, "total_tokens": 3521352} {"current_steps": 10815, "total_steps": 40000, "loss": 0.1907, "lr": 4.151216688797722e-05, "epoch": 8.850593532541957, "percentage": 27.04, "elapsed_time": "1:14:35", "remaining_time": "3:21:18", "throughput": 787.11, "total_tokens": 3522920} {"current_steps": 10820, "total_steps": 40000, "loss": 0.235, "lr": 4.150479428244054e-05, "epoch": 8.85468686041752, "percentage": 27.05, "elapsed_time": "1:14:37", "remaining_time": "3:21:15", "throughput": 787.17, "total_tokens": 3524552} {"current_steps": 10825, "total_steps": 40000, "loss": 0.1558, "lr": 4.1497419131657176e-05, "epoch": 8.858780188293082, "percentage": 27.06, "elapsed_time": "1:14:39", "remaining_time": "3:21:12", "throughput": 787.24, "total_tokens": 3526200} {"current_steps": 10830, "total_steps": 40000, "loss": 0.1797, "lr": 4.149004143676447e-05, "epoch": 8.862873516168644, "percentage": 27.07, "elapsed_time": "1:14:40", "remaining_time": "3:21:09", "throughput": 787.29, "total_tokens": 3527816} {"current_steps": 10835, "total_steps": 40000, "loss": 0.2134, "lr": 4.148266119890015e-05, "epoch": 8.866966844044208, "percentage": 27.09, "elapsed_time": "1:14:42", "remaining_time": "3:21:06", "throughput": 787.36, "total_tokens": 3529448} {"current_steps": 10840, "total_steps": 40000, "loss": 0.2079, "lr": 4.1475278419202324e-05, "epoch": 8.87106017191977, "percentage": 27.1, "elapsed_time": "1:14:44", "remaining_time": "3:21:03", "throughput": 787.43, "total_tokens": 3531112} {"current_steps": 10845, "total_steps": 40000, "loss": 0.2151, "lr": 4.146789309880953e-05, "epoch": 8.875153499795333, "percentage": 27.11, "elapsed_time": "1:14:46", "remaining_time": "3:21:00", "throughput": 787.49, "total_tokens": 3532744} {"current_steps": 10850, "total_steps": 40000, "loss": 0.2238, "lr": 4.146050523886068e-05, "epoch": 8.879246827670897, "percentage": 27.12, "elapsed_time": "1:14:47", "remaining_time": "3:20:57", "throughput": 787.55, "total_tokens": 3534392} {"current_steps": 10855, "total_steps": 40000, "loss": 0.2686, "lr": 4.1453114840495055e-05, "epoch": 8.88334015554646, "percentage": 27.14, "elapsed_time": "1:14:49", "remaining_time": "3:20:54", "throughput": 787.61, "total_tokens": 3536024} {"current_steps": 10860, "total_steps": 40000, "loss": 0.2397, "lr": 4.1445721904852364e-05, "epoch": 8.887433483422022, "percentage": 27.15, "elapsed_time": "1:14:51", "remaining_time": "3:20:51", "throughput": 787.68, "total_tokens": 3537688} {"current_steps": 10865, "total_steps": 40000, "loss": 0.1633, "lr": 4.143832643307269e-05, "epoch": 8.891526811297584, "percentage": 27.16, "elapsed_time": "1:14:52", "remaining_time": "3:20:48", "throughput": 787.74, "total_tokens": 3539272} {"current_steps": 10870, "total_steps": 40000, "loss": 0.1643, "lr": 4.1430928426296503e-05, "epoch": 8.895620139173147, "percentage": 27.18, "elapsed_time": "1:14:54", "remaining_time": "3:20:45", "throughput": 787.8, "total_tokens": 3540904} {"current_steps": 10875, "total_steps": 40000, "loss": 0.2129, "lr": 4.142352788566466e-05, "epoch": 8.899713467048711, "percentage": 27.19, "elapsed_time": "1:14:56", "remaining_time": "3:20:42", "throughput": 787.86, "total_tokens": 3542536} {"current_steps": 10880, "total_steps": 40000, "loss": 0.222, "lr": 4.1416124812318424e-05, "epoch": 8.903806794924273, "percentage": 27.2, "elapsed_time": "1:14:58", "remaining_time": "3:20:39", "throughput": 787.93, "total_tokens": 3544200} {"current_steps": 10885, "total_steps": 40000, "loss": 0.2015, "lr": 4.1408719207399453e-05, "epoch": 8.907900122799836, "percentage": 27.21, "elapsed_time": "1:14:59", "remaining_time": "3:20:36", "throughput": 787.99, "total_tokens": 3545832} {"current_steps": 10890, "total_steps": 40000, "loss": 0.165, "lr": 4.140131107204978e-05, "epoch": 8.9119934506754, "percentage": 27.22, "elapsed_time": "1:15:01", "remaining_time": "3:20:33", "throughput": 788.04, "total_tokens": 3547432} {"current_steps": 10895, "total_steps": 40000, "loss": 0.1918, "lr": 4.139390040741182e-05, "epoch": 8.916086778550962, "percentage": 27.24, "elapsed_time": "1:15:03", "remaining_time": "3:20:30", "throughput": 788.11, "total_tokens": 3549080} {"current_steps": 10900, "total_steps": 40000, "loss": 0.1988, "lr": 4.1386487214628396e-05, "epoch": 8.920180106426525, "percentage": 27.25, "elapsed_time": "1:15:05", "remaining_time": "3:20:27", "throughput": 788.17, "total_tokens": 3550696} {"current_steps": 10905, "total_steps": 40000, "loss": 0.2146, "lr": 4.137907149484272e-05, "epoch": 8.924273434302087, "percentage": 27.26, "elapsed_time": "1:15:06", "remaining_time": "3:20:24", "throughput": 788.23, "total_tokens": 3552328} {"current_steps": 10910, "total_steps": 40000, "loss": 0.1924, "lr": 4.137165324919839e-05, "epoch": 8.928366762177651, "percentage": 27.27, "elapsed_time": "1:15:08", "remaining_time": "3:20:21", "throughput": 788.28, "total_tokens": 3553928} {"current_steps": 10915, "total_steps": 40000, "loss": 0.2681, "lr": 4.136423247883939e-05, "epoch": 8.932460090053214, "percentage": 27.29, "elapsed_time": "1:15:10", "remaining_time": "3:20:18", "throughput": 788.37, "total_tokens": 3555688} {"current_steps": 10920, "total_steps": 40000, "loss": 0.2085, "lr": 4.135680918491009e-05, "epoch": 8.936553417928776, "percentage": 27.3, "elapsed_time": "1:15:11", "remaining_time": "3:20:15", "throughput": 788.44, "total_tokens": 3557336} {"current_steps": 10925, "total_steps": 40000, "loss": 0.1664, "lr": 4.1349383368555265e-05, "epoch": 8.940646745804338, "percentage": 27.31, "elapsed_time": "1:15:13", "remaining_time": "3:20:12", "throughput": 788.51, "total_tokens": 3559000} {"current_steps": 10930, "total_steps": 40000, "loss": 0.1505, "lr": 4.1341955030920065e-05, "epoch": 8.944740073679903, "percentage": 27.32, "elapsed_time": "1:15:15", "remaining_time": "3:20:09", "throughput": 788.57, "total_tokens": 3560648} {"current_steps": 10935, "total_steps": 40000, "loss": 0.2, "lr": 4.1334524173150036e-05, "epoch": 8.948833401555465, "percentage": 27.34, "elapsed_time": "1:15:17", "remaining_time": "3:20:06", "throughput": 788.64, "total_tokens": 3562312} {"current_steps": 10940, "total_steps": 40000, "loss": 0.2039, "lr": 4.13270907963911e-05, "epoch": 8.952926729431027, "percentage": 27.35, "elapsed_time": "1:15:18", "remaining_time": "3:20:03", "throughput": 788.7, "total_tokens": 3563944} {"current_steps": 10945, "total_steps": 40000, "loss": 0.1736, "lr": 4.131965490178959e-05, "epoch": 8.95702005730659, "percentage": 27.36, "elapsed_time": "1:15:20", "remaining_time": "3:20:00", "throughput": 788.75, "total_tokens": 3565544} {"current_steps": 10950, "total_steps": 40000, "loss": 0.1555, "lr": 4.131221649049222e-05, "epoch": 8.961113385182154, "percentage": 27.38, "elapsed_time": "1:15:22", "remaining_time": "3:19:57", "throughput": 788.81, "total_tokens": 3567144} {"current_steps": 10955, "total_steps": 40000, "loss": 0.2183, "lr": 4.130477556364606e-05, "epoch": 8.965206713057716, "percentage": 27.39, "elapsed_time": "1:15:23", "remaining_time": "3:19:54", "throughput": 788.87, "total_tokens": 3568792} {"current_steps": 10960, "total_steps": 40000, "loss": 0.2008, "lr": 4.129733212239861e-05, "epoch": 8.969300040933279, "percentage": 27.4, "elapsed_time": "1:15:25", "remaining_time": "3:19:51", "throughput": 788.93, "total_tokens": 3570424} {"current_steps": 10965, "total_steps": 40000, "loss": 0.1739, "lr": 4.128988616789774e-05, "epoch": 8.973393368808841, "percentage": 27.41, "elapsed_time": "1:15:27", "remaining_time": "3:19:48", "throughput": 788.98, "total_tokens": 3572008} {"current_steps": 10970, "total_steps": 40000, "loss": 0.2101, "lr": 4.1282437701291724e-05, "epoch": 8.977486696684405, "percentage": 27.43, "elapsed_time": "1:15:29", "remaining_time": "3:19:45", "throughput": 789.05, "total_tokens": 3573688} {"current_steps": 10975, "total_steps": 40000, "loss": 0.1987, "lr": 4.1274986723729184e-05, "epoch": 8.981580024559968, "percentage": 27.44, "elapsed_time": "1:15:30", "remaining_time": "3:19:42", "throughput": 789.12, "total_tokens": 3575352} {"current_steps": 10980, "total_steps": 40000, "loss": 0.1933, "lr": 4.126753323635917e-05, "epoch": 8.98567335243553, "percentage": 27.45, "elapsed_time": "1:15:32", "remaining_time": "3:19:39", "throughput": 789.19, "total_tokens": 3577032} {"current_steps": 10985, "total_steps": 40000, "loss": 0.1931, "lr": 4.12600772403311e-05, "epoch": 8.989766680311092, "percentage": 27.46, "elapsed_time": "1:15:34", "remaining_time": "3:19:36", "throughput": 789.25, "total_tokens": 3578648} {"current_steps": 10990, "total_steps": 40000, "loss": 0.1913, "lr": 4.125261873679479e-05, "epoch": 8.993860008186656, "percentage": 27.47, "elapsed_time": "1:15:35", "remaining_time": "3:19:33", "throughput": 789.32, "total_tokens": 3580296} {"current_steps": 10995, "total_steps": 40000, "loss": 0.2392, "lr": 4.124515772690042e-05, "epoch": 8.997953336062219, "percentage": 27.49, "elapsed_time": "1:15:37", "remaining_time": "3:19:30", "throughput": 789.37, "total_tokens": 3581880} {"current_steps": 11000, "total_steps": 40000, "loss": 0.1142, "lr": 4.123769421179858e-05, "epoch": 9.001637331150226, "percentage": 27.5, "elapsed_time": "1:15:39", "remaining_time": "3:19:27", "throughput": 789.33, "total_tokens": 3583216} {"current_steps": 11000, "total_steps": 40000, "eval_loss": 0.2019941657781601, "epoch": 9.001637331150226, "percentage": 27.5, "elapsed_time": "1:15:52", "remaining_time": "3:20:00", "throughput": 787.17, "total_tokens": 3583216} {"current_steps": 11005, "total_steps": 40000, "loss": 0.2215, "lr": 4.1230228192640236e-05, "epoch": 9.005730659025788, "percentage": 27.51, "elapsed_time": "1:15:55", "remaining_time": "3:20:01", "throughput": 787.0, "total_tokens": 3584928} {"current_steps": 11010, "total_steps": 40000, "loss": 0.2198, "lr": 4.122275967057675e-05, "epoch": 9.00982398690135, "percentage": 27.52, "elapsed_time": "1:15:56", "remaining_time": "3:19:58", "throughput": 787.07, "total_tokens": 3586608} {"current_steps": 11015, "total_steps": 40000, "loss": 0.2587, "lr": 4.1215288646759846e-05, "epoch": 9.013917314776913, "percentage": 27.54, "elapsed_time": "1:15:58", "remaining_time": "3:19:55", "throughput": 787.13, "total_tokens": 3588240} {"current_steps": 11020, "total_steps": 40000, "loss": 0.1943, "lr": 4.120781512234166e-05, "epoch": 9.018010642652477, "percentage": 27.55, "elapsed_time": "1:16:00", "remaining_time": "3:19:52", "throughput": 787.19, "total_tokens": 3589888} {"current_steps": 11025, "total_steps": 40000, "loss": 0.2588, "lr": 4.120033909847471e-05, "epoch": 9.02210397052804, "percentage": 27.56, "elapsed_time": "1:16:02", "remaining_time": "3:19:49", "throughput": 787.25, "total_tokens": 3591488} {"current_steps": 11030, "total_steps": 40000, "loss": 0.1809, "lr": 4.119286057631187e-05, "epoch": 9.026197298403602, "percentage": 27.57, "elapsed_time": "1:16:03", "remaining_time": "3:19:46", "throughput": 787.3, "total_tokens": 3593088} {"current_steps": 11035, "total_steps": 40000, "loss": 0.2036, "lr": 4.118537955700646e-05, "epoch": 9.030290626279164, "percentage": 27.59, "elapsed_time": "1:16:05", "remaining_time": "3:19:43", "throughput": 787.38, "total_tokens": 3594800} {"current_steps": 11040, "total_steps": 40000, "loss": 0.1994, "lr": 4.11778960417121e-05, "epoch": 9.034383954154729, "percentage": 27.6, "elapsed_time": "1:16:07", "remaining_time": "3:19:40", "throughput": 787.44, "total_tokens": 3596432} {"current_steps": 11045, "total_steps": 40000, "loss": 0.1991, "lr": 4.117041003158288e-05, "epoch": 9.038477282030291, "percentage": 27.61, "elapsed_time": "1:16:08", "remaining_time": "3:19:37", "throughput": 787.51, "total_tokens": 3598080} {"current_steps": 11050, "total_steps": 40000, "loss": 0.2271, "lr": 4.1162921527773215e-05, "epoch": 9.042570609905853, "percentage": 27.62, "elapsed_time": "1:16:10", "remaining_time": "3:19:34", "throughput": 787.57, "total_tokens": 3599728} {"current_steps": 11055, "total_steps": 40000, "loss": 0.1987, "lr": 4.115543053143794e-05, "epoch": 9.046663937781416, "percentage": 27.64, "elapsed_time": "1:16:12", "remaining_time": "3:19:31", "throughput": 787.63, "total_tokens": 3601344} {"current_steps": 11060, "total_steps": 40000, "loss": 0.139, "lr": 4.114793704373226e-05, "epoch": 9.05075726565698, "percentage": 27.65, "elapsed_time": "1:16:14", "remaining_time": "3:19:28", "throughput": 787.7, "total_tokens": 3603008} {"current_steps": 11065, "total_steps": 40000, "loss": 0.1894, "lr": 4.114044106581175e-05, "epoch": 9.054850593532542, "percentage": 27.66, "elapsed_time": "1:16:15", "remaining_time": "3:19:25", "throughput": 787.74, "total_tokens": 3604576} {"current_steps": 11070, "total_steps": 40000, "loss": 0.1688, "lr": 4.11329425988324e-05, "epoch": 9.058943921408105, "percentage": 27.68, "elapsed_time": "1:16:17", "remaining_time": "3:19:22", "throughput": 787.81, "total_tokens": 3606224} {"current_steps": 11075, "total_steps": 40000, "loss": 0.1611, "lr": 4.112544164395056e-05, "epoch": 9.063037249283667, "percentage": 27.69, "elapsed_time": "1:16:19", "remaining_time": "3:19:19", "throughput": 787.88, "total_tokens": 3607904} {"current_steps": 11080, "total_steps": 40000, "loss": 0.1998, "lr": 4.111793820232297e-05, "epoch": 9.067130577159231, "percentage": 27.7, "elapsed_time": "1:16:20", "remaining_time": "3:19:16", "throughput": 787.94, "total_tokens": 3609536} {"current_steps": 11085, "total_steps": 40000, "loss": 0.1958, "lr": 4.1110432275106767e-05, "epoch": 9.071223905034794, "percentage": 27.71, "elapsed_time": "1:16:22", "remaining_time": "3:19:13", "throughput": 787.99, "total_tokens": 3611152} {"current_steps": 11090, "total_steps": 40000, "loss": 0.1907, "lr": 4.110292386345944e-05, "epoch": 9.075317232910356, "percentage": 27.73, "elapsed_time": "1:16:24", "remaining_time": "3:19:10", "throughput": 788.05, "total_tokens": 3612784} {"current_steps": 11095, "total_steps": 40000, "loss": 0.2099, "lr": 4.109541296853891e-05, "epoch": 9.079410560785918, "percentage": 27.74, "elapsed_time": "1:16:26", "remaining_time": "3:19:07", "throughput": 788.11, "total_tokens": 3614384} {"current_steps": 11100, "total_steps": 40000, "loss": 0.1742, "lr": 4.108789959150341e-05, "epoch": 9.083503888661483, "percentage": 27.75, "elapsed_time": "1:16:27", "remaining_time": "3:19:04", "throughput": 788.17, "total_tokens": 3616000} {"current_steps": 11105, "total_steps": 40000, "loss": 0.1797, "lr": 4.108038373351163e-05, "epoch": 9.087597216537045, "percentage": 27.76, "elapsed_time": "1:16:29", "remaining_time": "3:19:02", "throughput": 788.23, "total_tokens": 3617648} {"current_steps": 11110, "total_steps": 40000, "loss": 0.1817, "lr": 4.10728653957226e-05, "epoch": 9.091690544412607, "percentage": 27.77, "elapsed_time": "1:16:31", "remaining_time": "3:18:59", "throughput": 788.28, "total_tokens": 3619264} {"current_steps": 11115, "total_steps": 40000, "loss": 0.2607, "lr": 4.106534457929575e-05, "epoch": 9.09578387228817, "percentage": 27.79, "elapsed_time": "1:16:33", "remaining_time": "3:18:56", "throughput": 788.35, "total_tokens": 3620912} {"current_steps": 11120, "total_steps": 40000, "loss": 0.1941, "lr": 4.105782128539086e-05, "epoch": 9.099877200163734, "percentage": 27.8, "elapsed_time": "1:16:34", "remaining_time": "3:18:53", "throughput": 788.41, "total_tokens": 3622544} {"current_steps": 11125, "total_steps": 40000, "loss": 0.2389, "lr": 4.1050295515168144e-05, "epoch": 9.103970528039296, "percentage": 27.81, "elapsed_time": "1:16:36", "remaining_time": "3:18:50", "throughput": 788.47, "total_tokens": 3624176} {"current_steps": 11130, "total_steps": 40000, "loss": 0.1895, "lr": 4.1042767269788155e-05, "epoch": 9.108063855914859, "percentage": 27.82, "elapsed_time": "1:16:38", "remaining_time": "3:18:47", "throughput": 788.53, "total_tokens": 3625808} {"current_steps": 11135, "total_steps": 40000, "loss": 0.162, "lr": 4.103523655041185e-05, "epoch": 9.112157183790421, "percentage": 27.84, "elapsed_time": "1:16:39", "remaining_time": "3:18:44", "throughput": 788.59, "total_tokens": 3627456} {"current_steps": 11140, "total_steps": 40000, "loss": 0.1998, "lr": 4.102770335820055e-05, "epoch": 9.116250511665985, "percentage": 27.85, "elapsed_time": "1:16:41", "remaining_time": "3:18:41", "throughput": 788.65, "total_tokens": 3629088} {"current_steps": 11145, "total_steps": 40000, "loss": 0.2075, "lr": 4.1020167694315984e-05, "epoch": 9.120343839541547, "percentage": 27.86, "elapsed_time": "1:16:43", "remaining_time": "3:18:38", "throughput": 788.73, "total_tokens": 3630768} {"current_steps": 11150, "total_steps": 40000, "loss": 0.2272, "lr": 4.101262955992023e-05, "epoch": 9.12443716741711, "percentage": 27.88, "elapsed_time": "1:16:45", "remaining_time": "3:18:35", "throughput": 788.79, "total_tokens": 3632432} {"current_steps": 11155, "total_steps": 40000, "loss": 0.1699, "lr": 4.100508895617578e-05, "epoch": 9.128530495292672, "percentage": 27.89, "elapsed_time": "1:16:46", "remaining_time": "3:18:32", "throughput": 788.85, "total_tokens": 3634080} {"current_steps": 11160, "total_steps": 40000, "loss": 0.1592, "lr": 4.099754588424547e-05, "epoch": 9.132623823168236, "percentage": 27.9, "elapsed_time": "1:16:48", "remaining_time": "3:18:29", "throughput": 788.91, "total_tokens": 3635680} {"current_steps": 11165, "total_steps": 40000, "loss": 0.1553, "lr": 4.0990000345292546e-05, "epoch": 9.136717151043799, "percentage": 27.91, "elapsed_time": "1:16:50", "remaining_time": "3:18:26", "throughput": 788.98, "total_tokens": 3637360} {"current_steps": 11170, "total_steps": 40000, "loss": 0.1948, "lr": 4.098245234048064e-05, "epoch": 9.140810478919361, "percentage": 27.93, "elapsed_time": "1:16:51", "remaining_time": "3:18:23", "throughput": 789.03, "total_tokens": 3638944} {"current_steps": 11175, "total_steps": 40000, "loss": 0.1793, "lr": 4.0974901870973726e-05, "epoch": 9.144903806794924, "percentage": 27.94, "elapsed_time": "1:16:53", "remaining_time": "3:18:20", "throughput": 789.09, "total_tokens": 3640560} {"current_steps": 11180, "total_steps": 40000, "loss": 0.141, "lr": 4.096734893793619e-05, "epoch": 9.148997134670488, "percentage": 27.95, "elapsed_time": "1:16:55", "remaining_time": "3:18:17", "throughput": 789.15, "total_tokens": 3642208} {"current_steps": 11185, "total_steps": 40000, "loss": 0.2752, "lr": 4.095979354253279e-05, "epoch": 9.15309046254605, "percentage": 27.96, "elapsed_time": "1:16:57", "remaining_time": "3:18:14", "throughput": 789.22, "total_tokens": 3643856} {"current_steps": 11190, "total_steps": 40000, "loss": 0.2237, "lr": 4.0952235685928656e-05, "epoch": 9.157183790421612, "percentage": 27.98, "elapsed_time": "1:16:58", "remaining_time": "3:18:11", "throughput": 789.26, "total_tokens": 3645424} {"current_steps": 11195, "total_steps": 40000, "loss": 0.137, "lr": 4.094467536928932e-05, "epoch": 9.161277118297175, "percentage": 27.99, "elapsed_time": "1:17:00", "remaining_time": "3:18:08", "throughput": 789.3, "total_tokens": 3646960} {"current_steps": 11200, "total_steps": 40000, "loss": 0.2136, "lr": 4.093711259378067e-05, "epoch": 9.165370446172739, "percentage": 28.0, "elapsed_time": "1:17:02", "remaining_time": "3:18:05", "throughput": 789.36, "total_tokens": 3648592} {"current_steps": 11200, "total_steps": 40000, "eval_loss": 0.20421774685382843, "epoch": 9.165370446172739, "percentage": 28.0, "elapsed_time": "1:17:14", "remaining_time": "3:18:37", "throughput": 787.24, "total_tokens": 3648592} {"current_steps": 11205, "total_steps": 40000, "loss": 0.1865, "lr": 4.092954736056897e-05, "epoch": 9.169463774048301, "percentage": 28.01, "elapsed_time": "1:17:17", "remaining_time": "3:18:38", "throughput": 787.05, "total_tokens": 3650224} {"current_steps": 11210, "total_steps": 40000, "loss": 0.1916, "lr": 4.09219796708209e-05, "epoch": 9.173557101923864, "percentage": 28.02, "elapsed_time": "1:17:19", "remaining_time": "3:18:35", "throughput": 787.12, "total_tokens": 3651872} {"current_steps": 11215, "total_steps": 40000, "loss": 0.2232, "lr": 4.0914409525703464e-05, "epoch": 9.177650429799426, "percentage": 28.04, "elapsed_time": "1:17:21", "remaining_time": "3:18:32", "throughput": 787.18, "total_tokens": 3653520} {"current_steps": 11220, "total_steps": 40000, "loss": 0.1559, "lr": 4.090683692638408e-05, "epoch": 9.18174375767499, "percentage": 28.05, "elapsed_time": "1:17:23", "remaining_time": "3:18:29", "throughput": 787.23, "total_tokens": 3655120} {"current_steps": 11225, "total_steps": 40000, "loss": 0.137, "lr": 4.089926187403056e-05, "epoch": 9.185837085550553, "percentage": 28.06, "elapsed_time": "1:17:24", "remaining_time": "3:18:26", "throughput": 787.28, "total_tokens": 3656704} {"current_steps": 11230, "total_steps": 40000, "loss": 0.2117, "lr": 4.0891684369811044e-05, "epoch": 9.189930413426115, "percentage": 28.07, "elapsed_time": "1:17:26", "remaining_time": "3:18:23", "throughput": 787.34, "total_tokens": 3658336} {"current_steps": 11235, "total_steps": 40000, "loss": 0.1876, "lr": 4.0884104414894107e-05, "epoch": 9.194023741301677, "percentage": 28.09, "elapsed_time": "1:17:28", "remaining_time": "3:18:20", "throughput": 787.41, "total_tokens": 3660016} {"current_steps": 11240, "total_steps": 40000, "loss": 0.1899, "lr": 4.087652201044864e-05, "epoch": 9.198117069177242, "percentage": 28.1, "elapsed_time": "1:17:29", "remaining_time": "3:18:17", "throughput": 787.46, "total_tokens": 3661616} {"current_steps": 11245, "total_steps": 40000, "loss": 0.2201, "lr": 4.086893715764397e-05, "epoch": 9.202210397052804, "percentage": 28.11, "elapsed_time": "1:17:31", "remaining_time": "3:18:14", "throughput": 787.51, "total_tokens": 3663200} {"current_steps": 11250, "total_steps": 40000, "loss": 0.2056, "lr": 4.086134985764977e-05, "epoch": 9.206303724928366, "percentage": 28.12, "elapsed_time": "1:17:33", "remaining_time": "3:18:11", "throughput": 787.56, "total_tokens": 3664800} {"current_steps": 11255, "total_steps": 40000, "loss": 0.151, "lr": 4.0853760111636085e-05, "epoch": 9.210397052803929, "percentage": 28.14, "elapsed_time": "1:17:35", "remaining_time": "3:18:08", "throughput": 787.62, "total_tokens": 3666432} {"current_steps": 11260, "total_steps": 40000, "loss": 0.1999, "lr": 4.084616792077337e-05, "epoch": 9.214490380679493, "percentage": 28.15, "elapsed_time": "1:17:36", "remaining_time": "3:18:05", "throughput": 787.67, "total_tokens": 3668016} {"current_steps": 11265, "total_steps": 40000, "loss": 0.1735, "lr": 4.083857328623243e-05, "epoch": 9.218583708555055, "percentage": 28.16, "elapsed_time": "1:17:38", "remaining_time": "3:18:02", "throughput": 787.72, "total_tokens": 3669600} {"current_steps": 11270, "total_steps": 40000, "loss": 0.1854, "lr": 4.083097620918444e-05, "epoch": 9.222677036430618, "percentage": 28.18, "elapsed_time": "1:17:40", "remaining_time": "3:18:00", "throughput": 787.78, "total_tokens": 3671216} {"current_steps": 11275, "total_steps": 40000, "loss": 0.1997, "lr": 4.082337669080097e-05, "epoch": 9.22677036430618, "percentage": 28.19, "elapsed_time": "1:17:41", "remaining_time": "3:17:57", "throughput": 787.85, "total_tokens": 3672912} {"current_steps": 11280, "total_steps": 40000, "loss": 0.2033, "lr": 4.081577473225398e-05, "epoch": 9.230863692181744, "percentage": 28.2, "elapsed_time": "1:17:43", "remaining_time": "3:17:54", "throughput": 787.9, "total_tokens": 3674496} {"current_steps": 11285, "total_steps": 40000, "loss": 0.1899, "lr": 4.080817033471577e-05, "epoch": 9.234957020057307, "percentage": 28.21, "elapsed_time": "1:17:45", "remaining_time": "3:17:51", "throughput": 787.96, "total_tokens": 3676144} {"current_steps": 11290, "total_steps": 40000, "loss": 0.1992, "lr": 4.080056349935903e-05, "epoch": 9.239050347932869, "percentage": 28.23, "elapsed_time": "1:17:47", "remaining_time": "3:17:48", "throughput": 788.02, "total_tokens": 3677776} {"current_steps": 11295, "total_steps": 40000, "loss": 0.1697, "lr": 4.079295422735684e-05, "epoch": 9.243143675808433, "percentage": 28.24, "elapsed_time": "1:17:48", "remaining_time": "3:17:45", "throughput": 788.08, "total_tokens": 3679424} {"current_steps": 11300, "total_steps": 40000, "loss": 0.172, "lr": 4.078534251988264e-05, "epoch": 9.247237003683995, "percentage": 28.25, "elapsed_time": "1:17:50", "remaining_time": "3:17:42", "throughput": 788.14, "total_tokens": 3681040} {"current_steps": 11305, "total_steps": 40000, "loss": 0.1588, "lr": 4.077772837811025e-05, "epoch": 9.251330331559558, "percentage": 28.26, "elapsed_time": "1:17:52", "remaining_time": "3:17:39", "throughput": 788.19, "total_tokens": 3682608} {"current_steps": 11310, "total_steps": 40000, "loss": 0.1993, "lr": 4.0770111803213874e-05, "epoch": 9.25542365943512, "percentage": 28.27, "elapsed_time": "1:17:53", "remaining_time": "3:17:36", "throughput": 788.26, "total_tokens": 3684304} {"current_steps": 11315, "total_steps": 40000, "loss": 0.2152, "lr": 4.076249279636807e-05, "epoch": 9.259516987310684, "percentage": 28.29, "elapsed_time": "1:17:55", "remaining_time": "3:17:33", "throughput": 788.33, "total_tokens": 3685968} {"current_steps": 11320, "total_steps": 40000, "loss": 0.2106, "lr": 4.075487135874781e-05, "epoch": 9.263610315186247, "percentage": 28.3, "elapsed_time": "1:17:57", "remaining_time": "3:17:30", "throughput": 788.39, "total_tokens": 3687616} {"current_steps": 11325, "total_steps": 40000, "loss": 0.1723, "lr": 4.074724749152837e-05, "epoch": 9.26770364306181, "percentage": 28.31, "elapsed_time": "1:17:59", "remaining_time": "3:17:27", "throughput": 788.44, "total_tokens": 3689232} {"current_steps": 11330, "total_steps": 40000, "loss": 0.2216, "lr": 4.07396211958855e-05, "epoch": 9.271796970937372, "percentage": 28.32, "elapsed_time": "1:18:00", "remaining_time": "3:17:24", "throughput": 788.48, "total_tokens": 3690784} {"current_steps": 11335, "total_steps": 40000, "loss": 0.2059, "lr": 4.073199247299523e-05, "epoch": 9.275890298812936, "percentage": 28.34, "elapsed_time": "1:18:02", "remaining_time": "3:17:21", "throughput": 788.54, "total_tokens": 3692416} {"current_steps": 11340, "total_steps": 40000, "loss": 0.2217, "lr": 4.072436132403403e-05, "epoch": 9.279983626688498, "percentage": 28.35, "elapsed_time": "1:18:04", "remaining_time": "3:17:18", "throughput": 788.6, "total_tokens": 3694048} {"current_steps": 11345, "total_steps": 40000, "loss": 0.1493, "lr": 4.0716727750178704e-05, "epoch": 9.28407695456406, "percentage": 28.36, "elapsed_time": "1:18:06", "remaining_time": "3:17:15", "throughput": 788.66, "total_tokens": 3695680} {"current_steps": 11350, "total_steps": 40000, "loss": 0.1717, "lr": 4.0709091752606455e-05, "epoch": 9.288170282439623, "percentage": 28.38, "elapsed_time": "1:18:07", "remaining_time": "3:17:12", "throughput": 788.72, "total_tokens": 3697312} {"current_steps": 11355, "total_steps": 40000, "loss": 0.1925, "lr": 4.070145333249484e-05, "epoch": 9.292263610315187, "percentage": 28.39, "elapsed_time": "1:18:09", "remaining_time": "3:17:09", "throughput": 788.77, "total_tokens": 3698912} {"current_steps": 11360, "total_steps": 40000, "loss": 0.1715, "lr": 4.069381249102181e-05, "epoch": 9.29635693819075, "percentage": 28.4, "elapsed_time": "1:18:11", "remaining_time": "3:17:07", "throughput": 788.83, "total_tokens": 3700544} {"current_steps": 11365, "total_steps": 40000, "loss": 0.1831, "lr": 4.0686169229365665e-05, "epoch": 9.300450266066312, "percentage": 28.41, "elapsed_time": "1:18:12", "remaining_time": "3:17:04", "throughput": 788.9, "total_tokens": 3702224} {"current_steps": 11370, "total_steps": 40000, "loss": 0.2089, "lr": 4.067852354870511e-05, "epoch": 9.304543593941874, "percentage": 28.43, "elapsed_time": "1:18:14", "remaining_time": "3:17:01", "throughput": 788.97, "total_tokens": 3703888} {"current_steps": 11375, "total_steps": 40000, "loss": 0.1769, "lr": 4.067087545021919e-05, "epoch": 9.308636921817438, "percentage": 28.44, "elapsed_time": "1:18:16", "remaining_time": "3:16:58", "throughput": 789.03, "total_tokens": 3705552} {"current_steps": 11380, "total_steps": 40000, "loss": 0.2217, "lr": 4.066322493508734e-05, "epoch": 9.312730249693, "percentage": 28.45, "elapsed_time": "1:18:18", "remaining_time": "3:16:55", "throughput": 789.1, "total_tokens": 3707232} {"current_steps": 11385, "total_steps": 40000, "loss": 0.1764, "lr": 4.065557200448937e-05, "epoch": 9.316823577568563, "percentage": 28.46, "elapsed_time": "1:18:19", "remaining_time": "3:16:52", "throughput": 789.15, "total_tokens": 3708832} {"current_steps": 11390, "total_steps": 40000, "loss": 0.2042, "lr": 4.064791665960546e-05, "epoch": 9.320916905444125, "percentage": 28.48, "elapsed_time": "1:18:21", "remaining_time": "3:16:49", "throughput": 789.21, "total_tokens": 3710480} {"current_steps": 11395, "total_steps": 40000, "loss": 0.2358, "lr": 4.064025890161615e-05, "epoch": 9.32501023331969, "percentage": 28.49, "elapsed_time": "1:18:23", "remaining_time": "3:16:46", "throughput": 789.28, "total_tokens": 3712144} {"current_steps": 11400, "total_steps": 40000, "loss": 0.2067, "lr": 4.0632598731702373e-05, "epoch": 9.329103561195252, "percentage": 28.5, "elapsed_time": "1:18:24", "remaining_time": "3:16:43", "throughput": 789.34, "total_tokens": 3713808} {"current_steps": 11400, "total_steps": 40000, "eval_loss": 0.2021624743938446, "epoch": 9.329103561195252, "percentage": 28.5, "elapsed_time": "1:18:37", "remaining_time": "3:17:14", "throughput": 787.26, "total_tokens": 3713808} {"current_steps": 11405, "total_steps": 40000, "loss": 0.211, "lr": 4.0624936151045426e-05, "epoch": 9.333196889070814, "percentage": 28.51, "elapsed_time": "1:18:40", "remaining_time": "3:17:15", "throughput": 787.06, "total_tokens": 3715376} {"current_steps": 11410, "total_steps": 40000, "loss": 0.1498, "lr": 4.061727116082696e-05, "epoch": 9.337290216946377, "percentage": 28.52, "elapsed_time": "1:18:42", "remaining_time": "3:17:12", "throughput": 787.12, "total_tokens": 3716976} {"current_steps": 11415, "total_steps": 40000, "loss": 0.2052, "lr": 4.060960376222903e-05, "epoch": 9.34138354482194, "percentage": 28.54, "elapsed_time": "1:18:43", "remaining_time": "3:17:09", "throughput": 787.16, "total_tokens": 3718560} {"current_steps": 11420, "total_steps": 40000, "loss": 0.1954, "lr": 4.0601933956434034e-05, "epoch": 9.345476872697503, "percentage": 28.55, "elapsed_time": "1:18:45", "remaining_time": "3:17:06", "throughput": 787.2, "total_tokens": 3720112} {"current_steps": 11425, "total_steps": 40000, "loss": 0.2152, "lr": 4.059426174462476e-05, "epoch": 9.349570200573066, "percentage": 28.56, "elapsed_time": "1:18:47", "remaining_time": "3:17:03", "throughput": 787.26, "total_tokens": 3721744} {"current_steps": 11430, "total_steps": 40000, "loss": 0.1551, "lr": 4.058658712798435e-05, "epoch": 9.353663528448628, "percentage": 28.57, "elapsed_time": "1:18:49", "remaining_time": "3:17:00", "throughput": 787.32, "total_tokens": 3723376} {"current_steps": 11435, "total_steps": 40000, "loss": 0.229, "lr": 4.0578910107696336e-05, "epoch": 9.357756856324192, "percentage": 28.59, "elapsed_time": "1:18:50", "remaining_time": "3:16:57", "throughput": 787.38, "total_tokens": 3725008} {"current_steps": 11440, "total_steps": 40000, "loss": 0.1669, "lr": 4.05712306849446e-05, "epoch": 9.361850184199755, "percentage": 28.6, "elapsed_time": "1:18:52", "remaining_time": "3:16:54", "throughput": 787.45, "total_tokens": 3726688} {"current_steps": 11445, "total_steps": 40000, "loss": 0.2378, "lr": 4.0563548860913415e-05, "epoch": 9.365943512075317, "percentage": 28.61, "elapsed_time": "1:18:54", "remaining_time": "3:16:52", "throughput": 787.51, "total_tokens": 3728320} {"current_steps": 11450, "total_steps": 40000, "loss": 0.2689, "lr": 4.0555864636787414e-05, "epoch": 9.37003683995088, "percentage": 28.62, "elapsed_time": "1:18:56", "remaining_time": "3:16:49", "throughput": 787.58, "total_tokens": 3730016} {"current_steps": 11455, "total_steps": 40000, "loss": 0.1983, "lr": 4.054817801375159e-05, "epoch": 9.374130167826443, "percentage": 28.64, "elapsed_time": "1:18:57", "remaining_time": "3:16:46", "throughput": 787.64, "total_tokens": 3731648} {"current_steps": 11460, "total_steps": 40000, "loss": 0.1713, "lr": 4.054048899299134e-05, "epoch": 9.378223495702006, "percentage": 28.65, "elapsed_time": "1:18:59", "remaining_time": "3:16:43", "throughput": 787.69, "total_tokens": 3733280} {"current_steps": 11465, "total_steps": 40000, "loss": 0.1606, "lr": 4.0532797575692385e-05, "epoch": 9.382316823577568, "percentage": 28.66, "elapsed_time": "1:19:01", "remaining_time": "3:16:40", "throughput": 787.76, "total_tokens": 3734960} {"current_steps": 11470, "total_steps": 40000, "loss": 0.1235, "lr": 4.052510376304085e-05, "epoch": 9.38641015145313, "percentage": 28.68, "elapsed_time": "1:19:02", "remaining_time": "3:16:37", "throughput": 787.82, "total_tokens": 3736608} {"current_steps": 11475, "total_steps": 40000, "loss": 0.2448, "lr": 4.051740755622321e-05, "epoch": 9.390503479328695, "percentage": 28.69, "elapsed_time": "1:19:04", "remaining_time": "3:16:34", "throughput": 787.89, "total_tokens": 3738272} {"current_steps": 11480, "total_steps": 40000, "loss": 0.2894, "lr": 4.050970895642632e-05, "epoch": 9.394596807204257, "percentage": 28.7, "elapsed_time": "1:19:06", "remaining_time": "3:16:31", "throughput": 787.95, "total_tokens": 3739936} {"current_steps": 11485, "total_steps": 40000, "loss": 0.1763, "lr": 4.050200796483741e-05, "epoch": 9.39869013507982, "percentage": 28.71, "elapsed_time": "1:19:08", "remaining_time": "3:16:28", "throughput": 788.03, "total_tokens": 3741632} {"current_steps": 11490, "total_steps": 40000, "loss": 0.1715, "lr": 4.049430458264405e-05, "epoch": 9.402783462955382, "percentage": 28.73, "elapsed_time": "1:19:09", "remaining_time": "3:16:25", "throughput": 788.08, "total_tokens": 3743248} {"current_steps": 11495, "total_steps": 40000, "loss": 0.2122, "lr": 4.048659881103422e-05, "epoch": 9.406876790830946, "percentage": 28.74, "elapsed_time": "1:19:11", "remaining_time": "3:16:22", "throughput": 788.14, "total_tokens": 3744864} {"current_steps": 11500, "total_steps": 40000, "loss": 0.2239, "lr": 4.0478890651196235e-05, "epoch": 9.410970118706508, "percentage": 28.75, "elapsed_time": "1:19:13", "remaining_time": "3:16:19", "throughput": 788.19, "total_tokens": 3746464} {"current_steps": 11505, "total_steps": 40000, "loss": 0.1961, "lr": 4.047118010431879e-05, "epoch": 9.41506344658207, "percentage": 28.76, "elapsed_time": "1:19:14", "remaining_time": "3:16:16", "throughput": 788.24, "total_tokens": 3748048} {"current_steps": 11510, "total_steps": 40000, "loss": 0.3051, "lr": 4.046346717159094e-05, "epoch": 9.419156774457633, "percentage": 28.78, "elapsed_time": "1:19:16", "remaining_time": "3:16:13", "throughput": 788.29, "total_tokens": 3749664} {"current_steps": 11515, "total_steps": 40000, "loss": 0.2127, "lr": 4.045575185420214e-05, "epoch": 9.423250102333197, "percentage": 28.79, "elapsed_time": "1:19:18", "remaining_time": "3:16:11", "throughput": 788.34, "total_tokens": 3751264} {"current_steps": 11520, "total_steps": 40000, "loss": 0.16, "lr": 4.0448034153342165e-05, "epoch": 9.42734343020876, "percentage": 28.8, "elapsed_time": "1:19:20", "remaining_time": "3:16:08", "throughput": 788.4, "total_tokens": 3752912} {"current_steps": 11525, "total_steps": 40000, "loss": 0.3385, "lr": 4.0440314070201194e-05, "epoch": 9.431436758084322, "percentage": 28.81, "elapsed_time": "1:19:21", "remaining_time": "3:16:05", "throughput": 788.45, "total_tokens": 3754496} {"current_steps": 11530, "total_steps": 40000, "loss": 0.1465, "lr": 4.043259160596976e-05, "epoch": 9.435530085959886, "percentage": 28.82, "elapsed_time": "1:19:23", "remaining_time": "3:16:02", "throughput": 788.5, "total_tokens": 3756096} {"current_steps": 11535, "total_steps": 40000, "loss": 0.2452, "lr": 4.0424866761838767e-05, "epoch": 9.439623413835449, "percentage": 28.84, "elapsed_time": "1:19:25", "remaining_time": "3:15:59", "throughput": 788.56, "total_tokens": 3757744} {"current_steps": 11540, "total_steps": 40000, "loss": 0.1506, "lr": 4.041713953899948e-05, "epoch": 9.443716741711011, "percentage": 28.85, "elapsed_time": "1:19:27", "remaining_time": "3:15:56", "throughput": 788.61, "total_tokens": 3759312} {"current_steps": 11545, "total_steps": 40000, "loss": 0.1519, "lr": 4.0409409938643515e-05, "epoch": 9.447810069586573, "percentage": 28.86, "elapsed_time": "1:19:28", "remaining_time": "3:15:53", "throughput": 788.67, "total_tokens": 3760976} {"current_steps": 11550, "total_steps": 40000, "loss": 0.2156, "lr": 4.0401677961962904e-05, "epoch": 9.451903397462136, "percentage": 28.88, "elapsed_time": "1:19:30", "remaining_time": "3:15:50", "throughput": 788.74, "total_tokens": 3762656} {"current_steps": 11555, "total_steps": 40000, "loss": 0.1471, "lr": 4.039394361015001e-05, "epoch": 9.4559967253377, "percentage": 28.89, "elapsed_time": "1:19:32", "remaining_time": "3:15:47", "throughput": 788.78, "total_tokens": 3764208} {"current_steps": 11560, "total_steps": 40000, "loss": 0.2048, "lr": 4.038620688439755e-05, "epoch": 9.460090053213262, "percentage": 28.9, "elapsed_time": "1:19:33", "remaining_time": "3:15:44", "throughput": 788.84, "total_tokens": 3765824} {"current_steps": 11565, "total_steps": 40000, "loss": 0.1989, "lr": 4.037846778589862e-05, "epoch": 9.464183381088825, "percentage": 28.91, "elapsed_time": "1:19:35", "remaining_time": "3:15:41", "throughput": 788.9, "total_tokens": 3767472} {"current_steps": 11570, "total_steps": 40000, "loss": 0.2251, "lr": 4.0370726315846715e-05, "epoch": 9.468276708964389, "percentage": 28.93, "elapsed_time": "1:19:37", "remaining_time": "3:15:38", "throughput": 788.95, "total_tokens": 3769056} {"current_steps": 11575, "total_steps": 40000, "loss": 0.2115, "lr": 4.036298247543565e-05, "epoch": 9.472370036839951, "percentage": 28.94, "elapsed_time": "1:19:39", "remaining_time": "3:15:36", "throughput": 789.01, "total_tokens": 3770704} {"current_steps": 11580, "total_steps": 40000, "loss": 0.1792, "lr": 4.035523626585962e-05, "epoch": 9.476463364715514, "percentage": 28.95, "elapsed_time": "1:19:40", "remaining_time": "3:15:33", "throughput": 789.06, "total_tokens": 3772304} {"current_steps": 11585, "total_steps": 40000, "loss": 0.1517, "lr": 4.0347487688313194e-05, "epoch": 9.480556692591076, "percentage": 28.96, "elapsed_time": "1:19:42", "remaining_time": "3:15:30", "throughput": 789.12, "total_tokens": 3773936} {"current_steps": 11590, "total_steps": 40000, "loss": 0.23, "lr": 4.0339736743991296e-05, "epoch": 9.48465002046664, "percentage": 28.98, "elapsed_time": "1:19:44", "remaining_time": "3:15:27", "throughput": 789.18, "total_tokens": 3775584} {"current_steps": 11595, "total_steps": 40000, "loss": 0.1892, "lr": 4.0331983434089227e-05, "epoch": 9.488743348342203, "percentage": 28.99, "elapsed_time": "1:19:45", "remaining_time": "3:15:24", "throughput": 789.23, "total_tokens": 3777168} {"current_steps": 11600, "total_steps": 40000, "loss": 0.1872, "lr": 4.032422775980264e-05, "epoch": 9.492836676217765, "percentage": 29.0, "elapsed_time": "1:19:47", "remaining_time": "3:15:21", "throughput": 789.29, "total_tokens": 3778848} {"current_steps": 11600, "total_steps": 40000, "eval_loss": 0.2017771452665329, "epoch": 9.492836676217765, "percentage": 29.0, "elapsed_time": "1:20:00", "remaining_time": "3:15:51", "throughput": 787.25, "total_tokens": 3778848} {"current_steps": 11605, "total_steps": 40000, "loss": 0.1901, "lr": 4.031646972232754e-05, "epoch": 9.496930004093327, "percentage": 29.01, "elapsed_time": "1:20:03", "remaining_time": "3:15:52", "throughput": 787.07, "total_tokens": 3780544} {"current_steps": 11610, "total_steps": 40000, "loss": 0.2408, "lr": 4.0308709322860344e-05, "epoch": 9.501023331968891, "percentage": 29.03, "elapsed_time": "1:20:05", "remaining_time": "3:15:49", "throughput": 787.15, "total_tokens": 3782240} {"current_steps": 11615, "total_steps": 40000, "loss": 0.1961, "lr": 4.0300946562597784e-05, "epoch": 9.505116659844454, "percentage": 29.04, "elapsed_time": "1:20:06", "remaining_time": "3:15:46", "throughput": 787.2, "total_tokens": 3783856} {"current_steps": 11620, "total_steps": 40000, "loss": 0.1213, "lr": 4.029318144273698e-05, "epoch": 9.509209987720016, "percentage": 29.05, "elapsed_time": "1:20:08", "remaining_time": "3:15:43", "throughput": 787.25, "total_tokens": 3785440} {"current_steps": 11625, "total_steps": 40000, "loss": 0.212, "lr": 4.0285413964475415e-05, "epoch": 9.513303315595579, "percentage": 29.06, "elapsed_time": "1:20:10", "remaining_time": "3:15:40", "throughput": 787.31, "total_tokens": 3787104} {"current_steps": 11630, "total_steps": 40000, "loss": 0.1996, "lr": 4.0277644129010927e-05, "epoch": 9.517396643471143, "percentage": 29.07, "elapsed_time": "1:20:11", "remaining_time": "3:15:37", "throughput": 787.37, "total_tokens": 3788704} {"current_steps": 11635, "total_steps": 40000, "loss": 0.1527, "lr": 4.0269871937541724e-05, "epoch": 9.521489971346705, "percentage": 29.09, "elapsed_time": "1:20:13", "remaining_time": "3:15:35", "throughput": 787.41, "total_tokens": 3790288} {"current_steps": 11640, "total_steps": 40000, "loss": 0.2149, "lr": 4.026209739126637e-05, "epoch": 9.525583299222268, "percentage": 29.1, "elapsed_time": "1:20:15", "remaining_time": "3:15:32", "throughput": 787.47, "total_tokens": 3791904} {"current_steps": 11645, "total_steps": 40000, "loss": 0.2152, "lr": 4.025432049138381e-05, "epoch": 9.52967662709783, "percentage": 29.11, "elapsed_time": "1:20:17", "remaining_time": "3:15:29", "throughput": 787.53, "total_tokens": 3793568} {"current_steps": 11650, "total_steps": 40000, "loss": 0.1817, "lr": 4.0246541239093325e-05, "epoch": 9.533769954973394, "percentage": 29.12, "elapsed_time": "1:20:18", "remaining_time": "3:15:26", "throughput": 787.6, "total_tokens": 3795248} {"current_steps": 11655, "total_steps": 40000, "loss": 0.1514, "lr": 4.023875963559459e-05, "epoch": 9.537863282848956, "percentage": 29.14, "elapsed_time": "1:20:20", "remaining_time": "3:15:23", "throughput": 787.64, "total_tokens": 3796800} {"current_steps": 11660, "total_steps": 40000, "loss": 0.235, "lr": 4.023097568208761e-05, "epoch": 9.541956610724519, "percentage": 29.15, "elapsed_time": "1:20:22", "remaining_time": "3:15:20", "throughput": 787.7, "total_tokens": 3798448} {"current_steps": 11665, "total_steps": 40000, "loss": 0.1527, "lr": 4.022318937977277e-05, "epoch": 9.546049938600081, "percentage": 29.16, "elapsed_time": "1:20:23", "remaining_time": "3:15:17", "throughput": 787.76, "total_tokens": 3800112} {"current_steps": 11670, "total_steps": 40000, "loss": 0.2664, "lr": 4.021540072985084e-05, "epoch": 9.550143266475645, "percentage": 29.18, "elapsed_time": "1:20:25", "remaining_time": "3:15:14", "throughput": 787.82, "total_tokens": 3801712} {"current_steps": 11675, "total_steps": 40000, "loss": 0.2256, "lr": 4.020760973352289e-05, "epoch": 9.554236594351208, "percentage": 29.19, "elapsed_time": "1:20:27", "remaining_time": "3:15:11", "throughput": 787.88, "total_tokens": 3803376} {"current_steps": 11680, "total_steps": 40000, "loss": 0.1575, "lr": 4.019981639199042e-05, "epoch": 9.55832992222677, "percentage": 29.2, "elapsed_time": "1:20:29", "remaining_time": "3:15:08", "throughput": 787.95, "total_tokens": 3805072} {"current_steps": 11685, "total_steps": 40000, "loss": 0.1591, "lr": 4.0192020706455245e-05, "epoch": 9.562423250102333, "percentage": 29.21, "elapsed_time": "1:20:30", "remaining_time": "3:15:05", "throughput": 788.01, "total_tokens": 3806736} {"current_steps": 11690, "total_steps": 40000, "loss": 0.2342, "lr": 4.018422267811956e-05, "epoch": 9.566516577977897, "percentage": 29.23, "elapsed_time": "1:20:32", "remaining_time": "3:15:03", "throughput": 788.07, "total_tokens": 3808384} {"current_steps": 11695, "total_steps": 40000, "loss": 0.1751, "lr": 4.017642230818592e-05, "epoch": 9.570609905853459, "percentage": 29.24, "elapsed_time": "1:20:34", "remaining_time": "3:15:00", "throughput": 788.12, "total_tokens": 3809968} {"current_steps": 11700, "total_steps": 40000, "loss": 0.1772, "lr": 4.0168619597857246e-05, "epoch": 9.574703233729021, "percentage": 29.25, "elapsed_time": "1:20:35", "remaining_time": "3:14:57", "throughput": 788.17, "total_tokens": 3811568} {"current_steps": 11705, "total_steps": 40000, "loss": 0.1559, "lr": 4.016081454833681e-05, "epoch": 9.578796561604584, "percentage": 29.26, "elapsed_time": "1:20:37", "remaining_time": "3:14:54", "throughput": 788.22, "total_tokens": 3813152} {"current_steps": 11710, "total_steps": 40000, "loss": 0.1518, "lr": 4.0153007160828245e-05, "epoch": 9.582889889480148, "percentage": 29.28, "elapsed_time": "1:20:39", "remaining_time": "3:14:51", "throughput": 788.28, "total_tokens": 3814816} {"current_steps": 11715, "total_steps": 40000, "loss": 0.2129, "lr": 4.0145197436535555e-05, "epoch": 9.58698321735571, "percentage": 29.29, "elapsed_time": "1:20:41", "remaining_time": "3:14:48", "throughput": 788.33, "total_tokens": 3816400} {"current_steps": 11720, "total_steps": 40000, "loss": 0.1971, "lr": 4.0137385376663095e-05, "epoch": 9.591076545231273, "percentage": 29.3, "elapsed_time": "1:20:42", "remaining_time": "3:14:45", "throughput": 788.37, "total_tokens": 3817952} {"current_steps": 11725, "total_steps": 40000, "loss": 0.1884, "lr": 4.012957098241558e-05, "epoch": 9.595169873106835, "percentage": 29.31, "elapsed_time": "1:20:44", "remaining_time": "3:14:42", "throughput": 788.44, "total_tokens": 3819632} {"current_steps": 11730, "total_steps": 40000, "loss": 0.1828, "lr": 4.0121754254998076e-05, "epoch": 9.5992632009824, "percentage": 29.33, "elapsed_time": "1:20:46", "remaining_time": "3:14:39", "throughput": 788.49, "total_tokens": 3821264} {"current_steps": 11735, "total_steps": 40000, "loss": 0.2048, "lr": 4.011393519561606e-05, "epoch": 9.603356528857962, "percentage": 29.34, "elapsed_time": "1:20:47", "remaining_time": "3:14:36", "throughput": 788.54, "total_tokens": 3822848} {"current_steps": 11740, "total_steps": 40000, "loss": 0.1878, "lr": 4.010611380547529e-05, "epoch": 9.607449856733524, "percentage": 29.35, "elapsed_time": "1:20:49", "remaining_time": "3:14:34", "throughput": 788.59, "total_tokens": 3824448} {"current_steps": 11745, "total_steps": 40000, "loss": 0.1491, "lr": 4.009829008578192e-05, "epoch": 9.611543184609086, "percentage": 29.36, "elapsed_time": "1:20:51", "remaining_time": "3:14:31", "throughput": 788.66, "total_tokens": 3826144} {"current_steps": 11750, "total_steps": 40000, "loss": 0.1617, "lr": 4.00904640377425e-05, "epoch": 9.61563651248465, "percentage": 29.38, "elapsed_time": "1:20:53", "remaining_time": "3:14:28", "throughput": 788.71, "total_tokens": 3827744} {"current_steps": 11755, "total_steps": 40000, "loss": 0.2497, "lr": 4.0082635662563886e-05, "epoch": 9.619729840360213, "percentage": 29.39, "elapsed_time": "1:20:54", "remaining_time": "3:14:25", "throughput": 788.78, "total_tokens": 3829392} {"current_steps": 11760, "total_steps": 40000, "loss": 0.2457, "lr": 4.007480496145331e-05, "epoch": 9.623823168235775, "percentage": 29.4, "elapsed_time": "1:20:56", "remaining_time": "3:14:22", "throughput": 788.83, "total_tokens": 3830992} {"current_steps": 11765, "total_steps": 40000, "loss": 0.2208, "lr": 4.006697193561837e-05, "epoch": 9.627916496111338, "percentage": 29.41, "elapsed_time": "1:20:58", "remaining_time": "3:14:19", "throughput": 788.9, "total_tokens": 3832688} {"current_steps": 11770, "total_steps": 40000, "loss": 0.2621, "lr": 4.005913658626701e-05, "epoch": 9.632009823986902, "percentage": 29.43, "elapsed_time": "1:21:00", "remaining_time": "3:14:16", "throughput": 788.95, "total_tokens": 3834320} {"current_steps": 11775, "total_steps": 40000, "loss": 0.179, "lr": 4.005129891460754e-05, "epoch": 9.636103151862464, "percentage": 29.44, "elapsed_time": "1:21:01", "remaining_time": "3:14:13", "throughput": 789.01, "total_tokens": 3835968} {"current_steps": 11780, "total_steps": 40000, "loss": 0.2437, "lr": 4.004345892184864e-05, "epoch": 9.640196479738027, "percentage": 29.45, "elapsed_time": "1:21:03", "remaining_time": "3:14:10", "throughput": 789.09, "total_tokens": 3837696} {"current_steps": 11785, "total_steps": 40000, "loss": 0.2012, "lr": 4.003561660919932e-05, "epoch": 9.644289807613589, "percentage": 29.46, "elapsed_time": "1:21:05", "remaining_time": "3:14:07", "throughput": 789.15, "total_tokens": 3839328} {"current_steps": 11790, "total_steps": 40000, "loss": 0.2151, "lr": 4.002777197786897e-05, "epoch": 9.648383135489153, "percentage": 29.48, "elapsed_time": "1:21:06", "remaining_time": "3:14:04", "throughput": 789.21, "total_tokens": 3840992} {"current_steps": 11795, "total_steps": 40000, "loss": 0.2026, "lr": 4.0019925029067326e-05, "epoch": 9.652476463364716, "percentage": 29.49, "elapsed_time": "1:21:08", "remaining_time": "3:14:02", "throughput": 789.24, "total_tokens": 3842688} {"current_steps": 11800, "total_steps": 40000, "loss": 0.1867, "lr": 4.0012075764004495e-05, "epoch": 9.656569791240278, "percentage": 29.5, "elapsed_time": "1:21:10", "remaining_time": "3:13:59", "throughput": 789.28, "total_tokens": 3844208} {"current_steps": 11800, "total_steps": 40000, "eval_loss": 0.2008524090051651, "epoch": 9.656569791240278, "percentage": 29.5, "elapsed_time": "1:21:22", "remaining_time": "3:14:29", "throughput": 787.27, "total_tokens": 3844208} {"current_steps": 11805, "total_steps": 40000, "loss": 0.2252, "lr": 4.000422418389094e-05, "epoch": 9.660663119115842, "percentage": 29.51, "elapsed_time": "1:21:26", "remaining_time": "3:14:30", "throughput": 787.1, "total_tokens": 3845888} {"current_steps": 11810, "total_steps": 40000, "loss": 0.1823, "lr": 3.999637028993744e-05, "epoch": 9.664756446991404, "percentage": 29.53, "elapsed_time": "1:21:27", "remaining_time": "3:14:27", "throughput": 787.15, "total_tokens": 3847504} {"current_steps": 11815, "total_steps": 40000, "loss": 0.2511, "lr": 3.99885140833552e-05, "epoch": 9.668849774866967, "percentage": 29.54, "elapsed_time": "1:21:29", "remaining_time": "3:14:24", "throughput": 787.21, "total_tokens": 3849152} {"current_steps": 11820, "total_steps": 40000, "loss": 0.1603, "lr": 3.998065556535572e-05, "epoch": 9.67294310274253, "percentage": 29.55, "elapsed_time": "1:21:31", "remaining_time": "3:14:21", "throughput": 787.27, "total_tokens": 3850800} {"current_steps": 11825, "total_steps": 40000, "loss": 0.1701, "lr": 3.9972794737150895e-05, "epoch": 9.677036430618092, "percentage": 29.56, "elapsed_time": "1:21:33", "remaining_time": "3:14:18", "throughput": 787.33, "total_tokens": 3852416} {"current_steps": 11830, "total_steps": 40000, "loss": 0.2349, "lr": 3.996493159995297e-05, "epoch": 9.681129758493656, "percentage": 29.58, "elapsed_time": "1:21:34", "remaining_time": "3:14:15", "throughput": 787.37, "total_tokens": 3853984} {"current_steps": 11835, "total_steps": 40000, "loss": 0.1855, "lr": 3.995706615497453e-05, "epoch": 9.685223086369218, "percentage": 29.59, "elapsed_time": "1:21:36", "remaining_time": "3:14:12", "throughput": 787.43, "total_tokens": 3855600} {"current_steps": 11840, "total_steps": 40000, "loss": 0.2708, "lr": 3.994919840342852e-05, "epoch": 9.68931641424478, "percentage": 29.6, "elapsed_time": "1:21:38", "remaining_time": "3:14:09", "throughput": 787.49, "total_tokens": 3857248} {"current_steps": 11845, "total_steps": 40000, "loss": 0.1989, "lr": 3.994132834652825e-05, "epoch": 9.693409742120345, "percentage": 29.61, "elapsed_time": "1:21:39", "remaining_time": "3:14:06", "throughput": 787.54, "total_tokens": 3858832} {"current_steps": 11850, "total_steps": 40000, "loss": 0.1925, "lr": 3.99334559854874e-05, "epoch": 9.697503069995907, "percentage": 29.62, "elapsed_time": "1:21:41", "remaining_time": "3:14:03", "throughput": 787.57, "total_tokens": 3860352} {"current_steps": 11855, "total_steps": 40000, "loss": 0.1734, "lr": 3.9925581321519955e-05, "epoch": 9.70159639787147, "percentage": 29.64, "elapsed_time": "1:21:43", "remaining_time": "3:14:00", "throughput": 787.62, "total_tokens": 3861936} {"current_steps": 11860, "total_steps": 40000, "loss": 0.1881, "lr": 3.991770435584031e-05, "epoch": 9.705689725747032, "percentage": 29.65, "elapsed_time": "1:21:45", "remaining_time": "3:13:58", "throughput": 787.71, "total_tokens": 3863728} {"current_steps": 11865, "total_steps": 40000, "loss": 0.1474, "lr": 3.990982508966319e-05, "epoch": 9.709783053622596, "percentage": 29.66, "elapsed_time": "1:21:46", "remaining_time": "3:13:55", "throughput": 787.77, "total_tokens": 3865376} {"current_steps": 11870, "total_steps": 40000, "loss": 0.1416, "lr": 3.990194352420367e-05, "epoch": 9.713876381498158, "percentage": 29.68, "elapsed_time": "1:21:48", "remaining_time": "3:13:52", "throughput": 787.81, "total_tokens": 3866960} {"current_steps": 11875, "total_steps": 40000, "loss": 0.2241, "lr": 3.9894059660677184e-05, "epoch": 9.71796970937372, "percentage": 29.69, "elapsed_time": "1:21:50", "remaining_time": "3:13:49", "throughput": 787.87, "total_tokens": 3868608} {"current_steps": 11880, "total_steps": 40000, "loss": 0.1797, "lr": 3.9886173500299526e-05, "epoch": 9.722063037249283, "percentage": 29.7, "elapsed_time": "1:21:51", "remaining_time": "3:13:46", "throughput": 787.93, "total_tokens": 3870208} {"current_steps": 11885, "total_steps": 40000, "loss": 0.1999, "lr": 3.987828504428685e-05, "epoch": 9.726156365124847, "percentage": 29.71, "elapsed_time": "1:21:53", "remaining_time": "3:13:43", "throughput": 787.99, "total_tokens": 3871856} {"current_steps": 11890, "total_steps": 40000, "loss": 0.1647, "lr": 3.987039429385565e-05, "epoch": 9.73024969300041, "percentage": 29.73, "elapsed_time": "1:21:55", "remaining_time": "3:13:40", "throughput": 788.04, "total_tokens": 3873472} {"current_steps": 11895, "total_steps": 40000, "loss": 0.1914, "lr": 3.986250125022277e-05, "epoch": 9.734343020875972, "percentage": 29.74, "elapsed_time": "1:21:57", "remaining_time": "3:13:37", "throughput": 788.09, "total_tokens": 3875056} {"current_steps": 11900, "total_steps": 40000, "loss": 0.1458, "lr": 3.985460591460544e-05, "epoch": 9.738436348751534, "percentage": 29.75, "elapsed_time": "1:21:58", "remaining_time": "3:13:34", "throughput": 788.14, "total_tokens": 3876672} {"current_steps": 11905, "total_steps": 40000, "loss": 0.1609, "lr": 3.984670828822118e-05, "epoch": 9.742529676627099, "percentage": 29.76, "elapsed_time": "1:22:00", "remaining_time": "3:13:32", "throughput": 788.19, "total_tokens": 3878288} {"current_steps": 11910, "total_steps": 40000, "loss": 0.1227, "lr": 3.983880837228794e-05, "epoch": 9.746623004502661, "percentage": 29.78, "elapsed_time": "1:22:02", "remaining_time": "3:13:29", "throughput": 788.24, "total_tokens": 3879856} {"current_steps": 11915, "total_steps": 40000, "loss": 0.1722, "lr": 3.983090616802396e-05, "epoch": 9.750716332378223, "percentage": 29.79, "elapsed_time": "1:22:03", "remaining_time": "3:13:26", "throughput": 788.3, "total_tokens": 3881536} {"current_steps": 11920, "total_steps": 40000, "loss": 0.1392, "lr": 3.982300167664788e-05, "epoch": 9.754809660253786, "percentage": 29.8, "elapsed_time": "1:22:05", "remaining_time": "3:13:23", "throughput": 788.35, "total_tokens": 3883136} {"current_steps": 11925, "total_steps": 40000, "loss": 0.2473, "lr": 3.981509489937868e-05, "epoch": 9.75890298812935, "percentage": 29.81, "elapsed_time": "1:22:07", "remaining_time": "3:13:20", "throughput": 788.41, "total_tokens": 3884768} {"current_steps": 11930, "total_steps": 40000, "loss": 0.1861, "lr": 3.9807185837435643e-05, "epoch": 9.762996316004912, "percentage": 29.83, "elapsed_time": "1:22:09", "remaining_time": "3:13:17", "throughput": 788.47, "total_tokens": 3886432} {"current_steps": 11935, "total_steps": 40000, "loss": 0.2161, "lr": 3.9799274492038484e-05, "epoch": 9.767089643880475, "percentage": 29.84, "elapsed_time": "1:22:10", "remaining_time": "3:13:14", "throughput": 788.52, "total_tokens": 3888032} {"current_steps": 11940, "total_steps": 40000, "loss": 0.1608, "lr": 3.979136086440722e-05, "epoch": 9.771182971756037, "percentage": 29.85, "elapsed_time": "1:22:12", "remaining_time": "3:13:11", "throughput": 788.57, "total_tokens": 3889616} {"current_steps": 11945, "total_steps": 40000, "loss": 0.2114, "lr": 3.9783444955762226e-05, "epoch": 9.775276299631601, "percentage": 29.86, "elapsed_time": "1:22:14", "remaining_time": "3:13:08", "throughput": 788.62, "total_tokens": 3891216} {"current_steps": 11950, "total_steps": 40000, "loss": 0.1858, "lr": 3.977552676732424e-05, "epoch": 9.779369627507164, "percentage": 29.88, "elapsed_time": "1:22:15", "remaining_time": "3:13:06", "throughput": 788.68, "total_tokens": 3892864} {"current_steps": 11955, "total_steps": 40000, "loss": 0.1719, "lr": 3.976760630031435e-05, "epoch": 9.783462955382726, "percentage": 29.89, "elapsed_time": "1:22:17", "remaining_time": "3:13:03", "throughput": 788.73, "total_tokens": 3894496} {"current_steps": 11960, "total_steps": 40000, "loss": 0.2124, "lr": 3.975968355595398e-05, "epoch": 9.787556283258288, "percentage": 29.9, "elapsed_time": "1:22:19", "remaining_time": "3:13:00", "throughput": 788.79, "total_tokens": 3896112} {"current_steps": 11965, "total_steps": 40000, "loss": 0.1449, "lr": 3.9751758535464935e-05, "epoch": 9.791649611133852, "percentage": 29.91, "elapsed_time": "1:22:21", "remaining_time": "3:12:57", "throughput": 788.84, "total_tokens": 3897744} {"current_steps": 11970, "total_steps": 40000, "loss": 0.1475, "lr": 3.9743831240069326e-05, "epoch": 9.795742939009415, "percentage": 29.93, "elapsed_time": "1:22:22", "remaining_time": "3:12:54", "throughput": 788.9, "total_tokens": 3899376} {"current_steps": 11975, "total_steps": 40000, "loss": 0.1458, "lr": 3.9735901670989675e-05, "epoch": 9.799836266884977, "percentage": 29.94, "elapsed_time": "1:22:24", "remaining_time": "3:12:51", "throughput": 788.96, "total_tokens": 3901008} {"current_steps": 11980, "total_steps": 40000, "loss": 0.2006, "lr": 3.97279698294488e-05, "epoch": 9.80392959476054, "percentage": 29.95, "elapsed_time": "1:22:26", "remaining_time": "3:12:48", "throughput": 789.0, "total_tokens": 3902576} {"current_steps": 11985, "total_steps": 40000, "loss": 0.191, "lr": 3.9720035716669876e-05, "epoch": 9.808022922636104, "percentage": 29.96, "elapsed_time": "1:22:27", "remaining_time": "3:12:45", "throughput": 789.07, "total_tokens": 3904272} {"current_steps": 11990, "total_steps": 40000, "loss": 0.1983, "lr": 3.9712099333876474e-05, "epoch": 9.812116250511666, "percentage": 29.98, "elapsed_time": "1:22:29", "remaining_time": "3:12:42", "throughput": 789.13, "total_tokens": 3905936} {"current_steps": 11995, "total_steps": 40000, "loss": 0.1539, "lr": 3.9704160682292475e-05, "epoch": 9.816209578387229, "percentage": 29.99, "elapsed_time": "1:22:31", "remaining_time": "3:12:40", "throughput": 789.19, "total_tokens": 3907584} {"current_steps": 12000, "total_steps": 40000, "loss": 0.1377, "lr": 3.9696219763142106e-05, "epoch": 9.820302906262791, "percentage": 30.0, "elapsed_time": "1:22:33", "remaining_time": "3:12:37", "throughput": 789.26, "total_tokens": 3909264} {"current_steps": 12000, "total_steps": 40000, "eval_loss": 0.2024000734090805, "epoch": 9.820302906262791, "percentage": 30.0, "elapsed_time": "1:22:45", "remaining_time": "3:13:06", "throughput": 787.28, "total_tokens": 3909264} {"current_steps": 12005, "total_steps": 40000, "loss": 0.2118, "lr": 3.968827657764997e-05, "epoch": 9.824396234138355, "percentage": 30.01, "elapsed_time": "1:22:48", "remaining_time": "3:13:06", "throughput": 787.1, "total_tokens": 3910864} {"current_steps": 12010, "total_steps": 40000, "loss": 0.2385, "lr": 3.9680331127041e-05, "epoch": 9.828489562013917, "percentage": 30.03, "elapsed_time": "1:22:50", "remaining_time": "3:13:03", "throughput": 787.15, "total_tokens": 3912432} {"current_steps": 12015, "total_steps": 40000, "loss": 0.2376, "lr": 3.9672383412540495e-05, "epoch": 9.83258288988948, "percentage": 30.04, "elapsed_time": "1:22:52", "remaining_time": "3:13:00", "throughput": 787.21, "total_tokens": 3914080} {"current_steps": 12020, "total_steps": 40000, "loss": 0.2081, "lr": 3.966443343537407e-05, "epoch": 9.836676217765042, "percentage": 30.05, "elapsed_time": "1:22:53", "remaining_time": "3:12:58", "throughput": 787.25, "total_tokens": 3915664} {"current_steps": 12025, "total_steps": 40000, "loss": 0.1446, "lr": 3.965648119676772e-05, "epoch": 9.840769545640606, "percentage": 30.06, "elapsed_time": "1:22:55", "remaining_time": "3:12:55", "throughput": 787.3, "total_tokens": 3917264} {"current_steps": 12030, "total_steps": 40000, "loss": 0.1721, "lr": 3.96485266979478e-05, "epoch": 9.844862873516169, "percentage": 30.08, "elapsed_time": "1:22:57", "remaining_time": "3:12:52", "throughput": 787.36, "total_tokens": 3918896} {"current_steps": 12035, "total_steps": 40000, "loss": 0.1612, "lr": 3.9640569940140974e-05, "epoch": 9.848956201391731, "percentage": 30.09, "elapsed_time": "1:22:58", "remaining_time": "3:12:49", "throughput": 787.42, "total_tokens": 3920544} {"current_steps": 12040, "total_steps": 40000, "loss": 0.2312, "lr": 3.963261092457428e-05, "epoch": 9.853049529267293, "percentage": 30.1, "elapsed_time": "1:23:00", "remaining_time": "3:12:46", "throughput": 787.48, "total_tokens": 3922192} {"current_steps": 12045, "total_steps": 40000, "loss": 0.1663, "lr": 3.962464965247509e-05, "epoch": 9.857142857142858, "percentage": 30.11, "elapsed_time": "1:23:02", "remaining_time": "3:12:43", "throughput": 787.53, "total_tokens": 3923808} {"current_steps": 12050, "total_steps": 40000, "loss": 0.2022, "lr": 3.9616686125071135e-05, "epoch": 9.86123618501842, "percentage": 30.12, "elapsed_time": "1:23:04", "remaining_time": "3:12:40", "throughput": 787.58, "total_tokens": 3925392} {"current_steps": 12055, "total_steps": 40000, "loss": 0.181, "lr": 3.9608720343590506e-05, "epoch": 9.865329512893982, "percentage": 30.14, "elapsed_time": "1:23:05", "remaining_time": "3:12:37", "throughput": 787.66, "total_tokens": 3927152} {"current_steps": 12060, "total_steps": 40000, "loss": 0.1842, "lr": 3.960075230926161e-05, "epoch": 9.869422840769545, "percentage": 30.15, "elapsed_time": "1:23:07", "remaining_time": "3:12:34", "throughput": 787.7, "total_tokens": 3928704} {"current_steps": 12065, "total_steps": 40000, "loss": 0.1871, "lr": 3.959278202331322e-05, "epoch": 9.873516168645109, "percentage": 30.16, "elapsed_time": "1:23:09", "remaining_time": "3:12:32", "throughput": 787.76, "total_tokens": 3930336} {"current_steps": 12070, "total_steps": 40000, "loss": 0.1877, "lr": 3.958480948697446e-05, "epoch": 9.877609496520671, "percentage": 30.18, "elapsed_time": "1:23:10", "remaining_time": "3:12:29", "throughput": 787.81, "total_tokens": 3931968} {"current_steps": 12075, "total_steps": 40000, "loss": 0.2189, "lr": 3.95768347014748e-05, "epoch": 9.881702824396234, "percentage": 30.19, "elapsed_time": "1:23:12", "remaining_time": "3:12:26", "throughput": 787.86, "total_tokens": 3933568} {"current_steps": 12080, "total_steps": 40000, "loss": 0.1464, "lr": 3.956885766804404e-05, "epoch": 9.885796152271798, "percentage": 30.2, "elapsed_time": "1:23:14", "remaining_time": "3:12:23", "throughput": 787.91, "total_tokens": 3935152} {"current_steps": 12085, "total_steps": 40000, "loss": 0.1488, "lr": 3.956087838791235e-05, "epoch": 9.88988948014736, "percentage": 30.21, "elapsed_time": "1:23:16", "remaining_time": "3:12:20", "throughput": 787.96, "total_tokens": 3936768} {"current_steps": 12090, "total_steps": 40000, "loss": 0.2279, "lr": 3.955289686231022e-05, "epoch": 9.893982808022923, "percentage": 30.23, "elapsed_time": "1:23:17", "remaining_time": "3:12:17", "throughput": 788.02, "total_tokens": 3938400} {"current_steps": 12095, "total_steps": 40000, "loss": 0.2162, "lr": 3.9544913092468504e-05, "epoch": 9.898076135898485, "percentage": 30.24, "elapsed_time": "1:23:19", "remaining_time": "3:12:14", "throughput": 788.07, "total_tokens": 3940000} {"current_steps": 12100, "total_steps": 40000, "loss": 0.2206, "lr": 3.9536927079618425e-05, "epoch": 9.902169463774047, "percentage": 30.25, "elapsed_time": "1:23:21", "remaining_time": "3:12:11", "throughput": 788.12, "total_tokens": 3941632} {"current_steps": 12105, "total_steps": 40000, "loss": 0.2138, "lr": 3.9528938824991494e-05, "epoch": 9.906262791649612, "percentage": 30.26, "elapsed_time": "1:23:23", "remaining_time": "3:12:09", "throughput": 788.18, "total_tokens": 3943280} {"current_steps": 12110, "total_steps": 40000, "loss": 0.2254, "lr": 3.952094832981962e-05, "epoch": 9.910356119525174, "percentage": 30.28, "elapsed_time": "1:23:24", "remaining_time": "3:12:06", "throughput": 788.23, "total_tokens": 3944880} {"current_steps": 12115, "total_steps": 40000, "loss": 0.1959, "lr": 3.951295559533503e-05, "epoch": 9.914449447400736, "percentage": 30.29, "elapsed_time": "1:23:26", "remaining_time": "3:12:03", "throughput": 788.29, "total_tokens": 3946544} {"current_steps": 12120, "total_steps": 40000, "loss": 0.2186, "lr": 3.95049606227703e-05, "epoch": 9.9185427752763, "percentage": 30.3, "elapsed_time": "1:23:28", "remaining_time": "3:12:00", "throughput": 788.36, "total_tokens": 3948224} {"current_steps": 12125, "total_steps": 40000, "loss": 0.2359, "lr": 3.949696341335838e-05, "epoch": 9.922636103151863, "percentage": 30.31, "elapsed_time": "1:23:29", "remaining_time": "3:11:57", "throughput": 788.41, "total_tokens": 3949872} {"current_steps": 12130, "total_steps": 40000, "loss": 0.1955, "lr": 3.9488963968332503e-05, "epoch": 9.926729431027425, "percentage": 30.33, "elapsed_time": "1:23:31", "remaining_time": "3:11:54", "throughput": 788.46, "total_tokens": 3951456} {"current_steps": 12135, "total_steps": 40000, "loss": 0.1741, "lr": 3.948096228892631e-05, "epoch": 9.930822758902988, "percentage": 30.34, "elapsed_time": "1:23:33", "remaining_time": "3:11:51", "throughput": 788.52, "total_tokens": 3953120} {"current_steps": 12140, "total_steps": 40000, "loss": 0.205, "lr": 3.947295837637375e-05, "epoch": 9.934916086778552, "percentage": 30.35, "elapsed_time": "1:23:35", "remaining_time": "3:11:49", "throughput": 788.58, "total_tokens": 3954768} {"current_steps": 12145, "total_steps": 40000, "loss": 0.13, "lr": 3.9464952231909135e-05, "epoch": 9.939009414654114, "percentage": 30.36, "elapsed_time": "1:23:36", "remaining_time": "3:11:46", "throughput": 788.64, "total_tokens": 3956400} {"current_steps": 12150, "total_steps": 40000, "loss": 0.1719, "lr": 3.945694385676711e-05, "epoch": 9.943102742529677, "percentage": 30.38, "elapsed_time": "1:23:38", "remaining_time": "3:11:43", "throughput": 788.68, "total_tokens": 3957984} {"current_steps": 12155, "total_steps": 40000, "loss": 0.1995, "lr": 3.944893325218265e-05, "epoch": 9.947196070405239, "percentage": 30.39, "elapsed_time": "1:23:40", "remaining_time": "3:11:40", "throughput": 788.74, "total_tokens": 3959616} {"current_steps": 12160, "total_steps": 40000, "loss": 0.221, "lr": 3.944092041939112e-05, "epoch": 9.951289398280803, "percentage": 30.4, "elapsed_time": "1:23:41", "remaining_time": "3:11:37", "throughput": 788.79, "total_tokens": 3961216} {"current_steps": 12165, "total_steps": 40000, "loss": 0.153, "lr": 3.943290535962818e-05, "epoch": 9.955382726156365, "percentage": 30.41, "elapsed_time": "1:23:43", "remaining_time": "3:11:34", "throughput": 788.84, "total_tokens": 3962848} {"current_steps": 12170, "total_steps": 40000, "loss": 0.1652, "lr": 3.942488807412985e-05, "epoch": 9.959476054031928, "percentage": 30.43, "elapsed_time": "1:23:45", "remaining_time": "3:11:31", "throughput": 788.9, "total_tokens": 3964496} {"current_steps": 12175, "total_steps": 40000, "loss": 0.1309, "lr": 3.941686856413251e-05, "epoch": 9.96356938190749, "percentage": 30.44, "elapsed_time": "1:23:47", "remaining_time": "3:11:28", "throughput": 788.95, "total_tokens": 3966096} {"current_steps": 12180, "total_steps": 40000, "loss": 0.219, "lr": 3.9408846830872874e-05, "epoch": 9.967662709783054, "percentage": 30.45, "elapsed_time": "1:23:48", "remaining_time": "3:11:26", "throughput": 789.01, "total_tokens": 3967744} {"current_steps": 12185, "total_steps": 40000, "loss": 0.2576, "lr": 3.940082287558798e-05, "epoch": 9.971756037658617, "percentage": 30.46, "elapsed_time": "1:23:50", "remaining_time": "3:11:23", "throughput": 789.06, "total_tokens": 3969344} {"current_steps": 12190, "total_steps": 40000, "loss": 0.1651, "lr": 3.939279669951522e-05, "epoch": 9.97584936553418, "percentage": 30.48, "elapsed_time": "1:23:52", "remaining_time": "3:11:20", "throughput": 789.12, "total_tokens": 3970992} {"current_steps": 12195, "total_steps": 40000, "loss": 0.1397, "lr": 3.938476830389234e-05, "epoch": 9.979942693409741, "percentage": 30.49, "elapsed_time": "1:23:53", "remaining_time": "3:11:17", "throughput": 789.17, "total_tokens": 3972624} {"current_steps": 12200, "total_steps": 40000, "loss": 0.1594, "lr": 3.937673768995742e-05, "epoch": 9.984036021285306, "percentage": 30.5, "elapsed_time": "1:23:55", "remaining_time": "3:11:14", "throughput": 789.22, "total_tokens": 3974224} {"current_steps": 12200, "total_steps": 40000, "eval_loss": 0.20200207829475403, "epoch": 9.984036021285306, "percentage": 30.5, "elapsed_time": "1:24:08", "remaining_time": "3:11:42", "throughput": 787.28, "total_tokens": 3974224} {"current_steps": 12205, "total_steps": 40000, "loss": 0.2116, "lr": 3.936870485894888e-05, "epoch": 9.988129349160868, "percentage": 30.51, "elapsed_time": "1:24:11", "remaining_time": "3:11:43", "throughput": 787.08, "total_tokens": 3975824} {"current_steps": 12210, "total_steps": 40000, "loss": 0.1575, "lr": 3.9360669812105475e-05, "epoch": 9.99222267703643, "percentage": 30.53, "elapsed_time": "1:24:13", "remaining_time": "3:11:40", "throughput": 787.13, "total_tokens": 3977456} {"current_steps": 12215, "total_steps": 40000, "loss": 0.1905, "lr": 3.9352632550666325e-05, "epoch": 9.996316004911993, "percentage": 30.54, "elapsed_time": "1:24:14", "remaining_time": "3:11:38", "throughput": 787.2, "total_tokens": 3979136} {"current_steps": 12220, "total_steps": 40000, "loss": 0.1124, "lr": 3.9344593075870866e-05, "epoch": 10.0, "percentage": 30.55, "elapsed_time": "1:24:16", "remaining_time": "3:11:35", "throughput": 787.2, "total_tokens": 3980496} {"current_steps": 12225, "total_steps": 40000, "loss": 0.1569, "lr": 3.933655138895889e-05, "epoch": 10.004093327875562, "percentage": 30.56, "elapsed_time": "1:24:18", "remaining_time": "3:11:32", "throughput": 787.22, "total_tokens": 3982096} {"current_steps": 12230, "total_steps": 40000, "loss": 0.1997, "lr": 3.932850749117053e-05, "epoch": 10.008186655751127, "percentage": 30.58, "elapsed_time": "1:24:20", "remaining_time": "3:11:29", "throughput": 787.27, "total_tokens": 3983728} {"current_steps": 12235, "total_steps": 40000, "loss": 0.135, "lr": 3.932046138374624e-05, "epoch": 10.012279983626689, "percentage": 30.59, "elapsed_time": "1:24:21", "remaining_time": "3:11:26", "throughput": 787.34, "total_tokens": 3985424} {"current_steps": 12240, "total_steps": 40000, "loss": 0.16, "lr": 3.9312413067926854e-05, "epoch": 10.016373311502251, "percentage": 30.6, "elapsed_time": "1:24:23", "remaining_time": "3:11:24", "throughput": 787.41, "total_tokens": 3987120} {"current_steps": 12245, "total_steps": 40000, "loss": 0.1845, "lr": 3.9304362544953506e-05, "epoch": 10.020466639377814, "percentage": 30.61, "elapsed_time": "1:24:25", "remaining_time": "3:11:21", "throughput": 787.46, "total_tokens": 3988720} {"current_steps": 12250, "total_steps": 40000, "loss": 0.185, "lr": 3.929630981606769e-05, "epoch": 10.024559967253378, "percentage": 30.63, "elapsed_time": "1:24:27", "remaining_time": "3:11:18", "throughput": 787.51, "total_tokens": 3990352} {"current_steps": 12255, "total_steps": 40000, "loss": 0.2186, "lr": 3.928825488251124e-05, "epoch": 10.02865329512894, "percentage": 30.64, "elapsed_time": "1:24:28", "remaining_time": "3:11:15", "throughput": 787.56, "total_tokens": 3991952} {"current_steps": 12260, "total_steps": 40000, "loss": 0.2317, "lr": 3.9280197745526344e-05, "epoch": 10.032746623004503, "percentage": 30.65, "elapsed_time": "1:24:30", "remaining_time": "3:11:12", "throughput": 787.62, "total_tokens": 3993584} {"current_steps": 12265, "total_steps": 40000, "loss": 0.2175, "lr": 3.9272138406355495e-05, "epoch": 10.036839950880065, "percentage": 30.66, "elapsed_time": "1:24:32", "remaining_time": "3:11:09", "throughput": 787.67, "total_tokens": 3995232} {"current_steps": 12270, "total_steps": 40000, "loss": 0.1589, "lr": 3.926407686624154e-05, "epoch": 10.04093327875563, "percentage": 30.68, "elapsed_time": "1:24:33", "remaining_time": "3:11:06", "throughput": 787.73, "total_tokens": 3996864} {"current_steps": 12275, "total_steps": 40000, "loss": 0.2175, "lr": 3.9256013126427684e-05, "epoch": 10.045026606631192, "percentage": 30.69, "elapsed_time": "1:24:35", "remaining_time": "3:11:04", "throughput": 787.8, "total_tokens": 3998560} {"current_steps": 12280, "total_steps": 40000, "loss": 0.1848, "lr": 3.9247947188157455e-05, "epoch": 10.049119934506754, "percentage": 30.7, "elapsed_time": "1:24:37", "remaining_time": "3:11:01", "throughput": 787.85, "total_tokens": 4000176} {"current_steps": 12285, "total_steps": 40000, "loss": 0.2238, "lr": 3.9239879052674715e-05, "epoch": 10.053213262382316, "percentage": 30.71, "elapsed_time": "1:24:39", "remaining_time": "3:10:58", "throughput": 787.9, "total_tokens": 4001808} {"current_steps": 12290, "total_steps": 40000, "loss": 0.1639, "lr": 3.9231808721223673e-05, "epoch": 10.05730659025788, "percentage": 30.73, "elapsed_time": "1:24:40", "remaining_time": "3:10:55", "throughput": 787.96, "total_tokens": 4003472} {"current_steps": 12295, "total_steps": 40000, "loss": 0.1402, "lr": 3.9223736195048886e-05, "epoch": 10.061399918133443, "percentage": 30.74, "elapsed_time": "1:24:42", "remaining_time": "3:10:52", "throughput": 788.02, "total_tokens": 4005120} {"current_steps": 12300, "total_steps": 40000, "loss": 0.201, "lr": 3.921566147539523e-05, "epoch": 10.065493246009005, "percentage": 30.75, "elapsed_time": "1:24:44", "remaining_time": "3:10:49", "throughput": 788.08, "total_tokens": 4006768} {"current_steps": 12305, "total_steps": 40000, "loss": 0.2161, "lr": 3.920758456350792e-05, "epoch": 10.069586573884568, "percentage": 30.76, "elapsed_time": "1:24:45", "remaining_time": "3:10:47", "throughput": 788.13, "total_tokens": 4008432} {"current_steps": 12310, "total_steps": 40000, "loss": 0.2027, "lr": 3.919950546063253e-05, "epoch": 10.073679901760132, "percentage": 30.78, "elapsed_time": "1:24:47", "remaining_time": "3:10:44", "throughput": 788.19, "total_tokens": 4010080} {"current_steps": 12315, "total_steps": 40000, "loss": 0.1772, "lr": 3.919142416801496e-05, "epoch": 10.077773229635694, "percentage": 30.79, "elapsed_time": "1:24:49", "remaining_time": "3:10:41", "throughput": 788.25, "total_tokens": 4011744} {"current_steps": 12320, "total_steps": 40000, "loss": 0.1408, "lr": 3.918334068690144e-05, "epoch": 10.081866557511256, "percentage": 30.8, "elapsed_time": "1:24:51", "remaining_time": "3:10:38", "throughput": 788.32, "total_tokens": 4013440} {"current_steps": 12325, "total_steps": 40000, "loss": 0.2084, "lr": 3.917525501853855e-05, "epoch": 10.085959885386819, "percentage": 30.81, "elapsed_time": "1:24:52", "remaining_time": "3:10:35", "throughput": 788.37, "total_tokens": 4015056} {"current_steps": 12330, "total_steps": 40000, "loss": 0.1524, "lr": 3.916716716417319e-05, "epoch": 10.090053213262383, "percentage": 30.83, "elapsed_time": "1:24:54", "remaining_time": "3:10:32", "throughput": 788.43, "total_tokens": 4016688} {"current_steps": 12335, "total_steps": 40000, "loss": 0.1834, "lr": 3.915907712505263e-05, "epoch": 10.094146541137945, "percentage": 30.84, "elapsed_time": "1:24:56", "remaining_time": "3:10:29", "throughput": 788.47, "total_tokens": 4018240} {"current_steps": 12340, "total_steps": 40000, "loss": 0.1797, "lr": 3.915098490242444e-05, "epoch": 10.098239869013508, "percentage": 30.85, "elapsed_time": "1:24:57", "remaining_time": "3:10:27", "throughput": 788.53, "total_tokens": 4019904} {"current_steps": 12345, "total_steps": 40000, "loss": 0.1709, "lr": 3.914289049753654e-05, "epoch": 10.10233319688907, "percentage": 30.86, "elapsed_time": "1:24:59", "remaining_time": "3:10:24", "throughput": 788.58, "total_tokens": 4021552} {"current_steps": 12350, "total_steps": 40000, "loss": 0.1532, "lr": 3.913479391163719e-05, "epoch": 10.106426524764634, "percentage": 30.88, "elapsed_time": "1:25:01", "remaining_time": "3:10:21", "throughput": 788.66, "total_tokens": 4023296} {"current_steps": 12355, "total_steps": 40000, "loss": 0.1325, "lr": 3.9126695145975e-05, "epoch": 10.110519852640197, "percentage": 30.89, "elapsed_time": "1:25:03", "remaining_time": "3:10:18", "throughput": 788.71, "total_tokens": 4024896} {"current_steps": 12360, "total_steps": 40000, "loss": 0.2185, "lr": 3.911859420179889e-05, "epoch": 10.114613180515759, "percentage": 30.9, "elapsed_time": "1:25:04", "remaining_time": "3:10:15", "throughput": 788.76, "total_tokens": 4026544} {"current_steps": 12365, "total_steps": 40000, "loss": 0.1842, "lr": 3.911049108035813e-05, "epoch": 10.118706508391321, "percentage": 30.91, "elapsed_time": "1:25:06", "remaining_time": "3:10:12", "throughput": 788.81, "total_tokens": 4028128} {"current_steps": 12370, "total_steps": 40000, "loss": 0.2396, "lr": 3.910238578290232e-05, "epoch": 10.122799836266886, "percentage": 30.93, "elapsed_time": "1:25:08", "remaining_time": "3:10:10", "throughput": 788.86, "total_tokens": 4029744} {"current_steps": 12375, "total_steps": 40000, "loss": 0.1943, "lr": 3.90942783106814e-05, "epoch": 10.126893164142448, "percentage": 30.94, "elapsed_time": "1:25:10", "remaining_time": "3:10:07", "throughput": 788.91, "total_tokens": 4031344} {"current_steps": 12380, "total_steps": 40000, "loss": 0.1701, "lr": 3.908616866494564e-05, "epoch": 10.13098649201801, "percentage": 30.95, "elapsed_time": "1:25:11", "remaining_time": "3:10:04", "throughput": 788.96, "total_tokens": 4032976} {"current_steps": 12385, "total_steps": 40000, "loss": 0.2216, "lr": 3.907805684694566e-05, "epoch": 10.135079819893573, "percentage": 30.96, "elapsed_time": "1:25:13", "remaining_time": "3:10:01", "throughput": 789.01, "total_tokens": 4034576} {"current_steps": 12390, "total_steps": 40000, "loss": 0.2043, "lr": 3.90699428579324e-05, "epoch": 10.139173147769137, "percentage": 30.98, "elapsed_time": "1:25:15", "remaining_time": "3:09:58", "throughput": 789.08, "total_tokens": 4036272} {"current_steps": 12395, "total_steps": 40000, "loss": 0.1644, "lr": 3.906182669915713e-05, "epoch": 10.1432664756447, "percentage": 30.99, "elapsed_time": "1:25:16", "remaining_time": "3:09:55", "throughput": 789.12, "total_tokens": 4037872} {"current_steps": 12400, "total_steps": 40000, "loss": 0.2307, "lr": 3.9053708371871476e-05, "epoch": 10.147359803520262, "percentage": 31.0, "elapsed_time": "1:25:18", "remaining_time": "3:09:53", "throughput": 789.18, "total_tokens": 4039488} {"current_steps": 12400, "total_steps": 40000, "eval_loss": 0.21049709618091583, "epoch": 10.147359803520262, "percentage": 31.0, "elapsed_time": "1:25:31", "remaining_time": "3:10:20", "throughput": 787.26, "total_tokens": 4039488} {"current_steps": 12405, "total_steps": 40000, "loss": 0.2111, "lr": 3.904558787732738e-05, "epoch": 10.151453131395824, "percentage": 31.01, "elapsed_time": "1:25:34", "remaining_time": "3:10:21", "throughput": 787.09, "total_tokens": 4041088} {"current_steps": 12410, "total_steps": 40000, "loss": 0.1898, "lr": 3.9037465216777135e-05, "epoch": 10.155546459271388, "percentage": 31.03, "elapsed_time": "1:25:35", "remaining_time": "3:10:18", "throughput": 787.14, "total_tokens": 4042720} {"current_steps": 12415, "total_steps": 40000, "loss": 0.2608, "lr": 3.902934039147334e-05, "epoch": 10.15963978714695, "percentage": 31.04, "elapsed_time": "1:25:37", "remaining_time": "3:10:15", "throughput": 787.2, "total_tokens": 4044384} {"current_steps": 12420, "total_steps": 40000, "loss": 0.2786, "lr": 3.902121340266894e-05, "epoch": 10.163733115022513, "percentage": 31.05, "elapsed_time": "1:25:39", "remaining_time": "3:10:12", "throughput": 787.25, "total_tokens": 4045984} {"current_steps": 12425, "total_steps": 40000, "loss": 0.1483, "lr": 3.9013084251617246e-05, "epoch": 10.167826442898075, "percentage": 31.06, "elapsed_time": "1:25:41", "remaining_time": "3:10:09", "throughput": 787.3, "total_tokens": 4047584} {"current_steps": 12430, "total_steps": 40000, "loss": 0.2605, "lr": 3.9004952939571865e-05, "epoch": 10.17191977077364, "percentage": 31.08, "elapsed_time": "1:25:42", "remaining_time": "3:10:06", "throughput": 787.35, "total_tokens": 4049184} {"current_steps": 12435, "total_steps": 40000, "loss": 0.1643, "lr": 3.899681946778673e-05, "epoch": 10.176013098649202, "percentage": 31.09, "elapsed_time": "1:25:44", "remaining_time": "3:10:04", "throughput": 787.4, "total_tokens": 4050800} {"current_steps": 12440, "total_steps": 40000, "loss": 0.1919, "lr": 3.898868383751615e-05, "epoch": 10.180106426524764, "percentage": 31.1, "elapsed_time": "1:25:46", "remaining_time": "3:10:01", "throughput": 787.44, "total_tokens": 4052384} {"current_steps": 12445, "total_steps": 40000, "loss": 0.191, "lr": 3.8980546050014724e-05, "epoch": 10.184199754400327, "percentage": 31.11, "elapsed_time": "1:25:47", "remaining_time": "3:09:58", "throughput": 787.5, "total_tokens": 4054048} {"current_steps": 12450, "total_steps": 40000, "loss": 0.17, "lr": 3.897240610653741e-05, "epoch": 10.18829308227589, "percentage": 31.13, "elapsed_time": "1:25:49", "remaining_time": "3:09:55", "throughput": 787.57, "total_tokens": 4055728} {"current_steps": 12455, "total_steps": 40000, "loss": 0.1606, "lr": 3.896426400833948e-05, "epoch": 10.192386410151453, "percentage": 31.14, "elapsed_time": "1:25:51", "remaining_time": "3:09:52", "throughput": 787.61, "total_tokens": 4057328} {"current_steps": 12460, "total_steps": 40000, "loss": 0.2113, "lr": 3.895611975667656e-05, "epoch": 10.196479738027016, "percentage": 31.15, "elapsed_time": "1:25:53", "remaining_time": "3:09:49", "throughput": 787.66, "total_tokens": 4058928} {"current_steps": 12465, "total_steps": 40000, "loss": 0.2053, "lr": 3.8947973352804584e-05, "epoch": 10.200573065902578, "percentage": 31.16, "elapsed_time": "1:25:54", "remaining_time": "3:09:46", "throughput": 787.71, "total_tokens": 4060512} {"current_steps": 12470, "total_steps": 40000, "loss": 0.2087, "lr": 3.893982479797984e-05, "epoch": 10.204666393778142, "percentage": 31.18, "elapsed_time": "1:25:56", "remaining_time": "3:09:44", "throughput": 787.75, "total_tokens": 4062112} {"current_steps": 12475, "total_steps": 40000, "loss": 0.2379, "lr": 3.8931674093458926e-05, "epoch": 10.208759721653704, "percentage": 31.19, "elapsed_time": "1:25:58", "remaining_time": "3:09:41", "throughput": 787.81, "total_tokens": 4063744} {"current_steps": 12480, "total_steps": 40000, "loss": 0.1124, "lr": 3.89235212404988e-05, "epoch": 10.212853049529267, "percentage": 31.2, "elapsed_time": "1:26:00", "remaining_time": "3:09:38", "throughput": 787.86, "total_tokens": 4065344} {"current_steps": 12485, "total_steps": 40000, "loss": 0.2562, "lr": 3.891536624035672e-05, "epoch": 10.216946377404831, "percentage": 31.21, "elapsed_time": "1:26:01", "remaining_time": "3:09:35", "throughput": 787.91, "total_tokens": 4066960} {"current_steps": 12490, "total_steps": 40000, "loss": 0.1602, "lr": 3.8907209094290295e-05, "epoch": 10.221039705280393, "percentage": 31.23, "elapsed_time": "1:26:03", "remaining_time": "3:09:32", "throughput": 787.96, "total_tokens": 4068576} {"current_steps": 12495, "total_steps": 40000, "loss": 0.2372, "lr": 3.8899049803557466e-05, "epoch": 10.225133033155956, "percentage": 31.24, "elapsed_time": "1:26:05", "remaining_time": "3:09:30", "throughput": 788.02, "total_tokens": 4070256} {"current_steps": 12500, "total_steps": 40000, "loss": 0.1561, "lr": 3.889088836941648e-05, "epoch": 10.229226361031518, "percentage": 31.25, "elapsed_time": "1:26:06", "remaining_time": "3:09:27", "throughput": 788.08, "total_tokens": 4071952} {"current_steps": 12505, "total_steps": 40000, "loss": 0.1498, "lr": 3.8882724793125946e-05, "epoch": 10.233319688907082, "percentage": 31.26, "elapsed_time": "1:26:08", "remaining_time": "3:09:24", "throughput": 788.15, "total_tokens": 4073632} {"current_steps": 12510, "total_steps": 40000, "loss": 0.2481, "lr": 3.8874559075944794e-05, "epoch": 10.237413016782645, "percentage": 31.27, "elapsed_time": "1:26:10", "remaining_time": "3:09:21", "throughput": 788.19, "total_tokens": 4075232} {"current_steps": 12515, "total_steps": 40000, "loss": 0.22, "lr": 3.886639121913227e-05, "epoch": 10.241506344658207, "percentage": 31.29, "elapsed_time": "1:26:12", "remaining_time": "3:09:18", "throughput": 788.24, "total_tokens": 4076832} {"current_steps": 12520, "total_steps": 40000, "loss": 0.2389, "lr": 3.885822122394797e-05, "epoch": 10.24559967253377, "percentage": 31.3, "elapsed_time": "1:26:13", "remaining_time": "3:09:15", "throughput": 788.29, "total_tokens": 4078432} {"current_steps": 12525, "total_steps": 40000, "loss": 0.1297, "lr": 3.8850049091651794e-05, "epoch": 10.249693000409334, "percentage": 31.31, "elapsed_time": "1:26:15", "remaining_time": "3:09:13", "throughput": 788.35, "total_tokens": 4080112} {"current_steps": 12530, "total_steps": 40000, "loss": 0.2236, "lr": 3.8841874823504e-05, "epoch": 10.253786328284896, "percentage": 31.32, "elapsed_time": "1:26:17", "remaining_time": "3:09:10", "throughput": 788.4, "total_tokens": 4081712} {"current_steps": 12535, "total_steps": 40000, "loss": 0.2584, "lr": 3.8833698420765157e-05, "epoch": 10.257879656160458, "percentage": 31.34, "elapsed_time": "1:26:18", "remaining_time": "3:09:07", "throughput": 788.47, "total_tokens": 4083424} {"current_steps": 12540, "total_steps": 40000, "loss": 0.1375, "lr": 3.882551988469618e-05, "epoch": 10.26197298403602, "percentage": 31.35, "elapsed_time": "1:26:20", "remaining_time": "3:09:04", "throughput": 788.51, "total_tokens": 4085008} {"current_steps": 12545, "total_steps": 40000, "loss": 0.169, "lr": 3.881733921655829e-05, "epoch": 10.266066311911585, "percentage": 31.36, "elapsed_time": "1:26:22", "remaining_time": "3:09:01", "throughput": 788.57, "total_tokens": 4086672} {"current_steps": 12550, "total_steps": 40000, "loss": 0.1544, "lr": 3.8809156417613054e-05, "epoch": 10.270159639787147, "percentage": 31.37, "elapsed_time": "1:26:24", "remaining_time": "3:08:58", "throughput": 788.61, "total_tokens": 4088240} {"current_steps": 12555, "total_steps": 40000, "loss": 0.1474, "lr": 3.8800971489122364e-05, "epoch": 10.27425296766271, "percentage": 31.39, "elapsed_time": "1:26:25", "remaining_time": "3:08:56", "throughput": 788.68, "total_tokens": 4089936} {"current_steps": 12560, "total_steps": 40000, "loss": 0.2095, "lr": 3.8792784432348434e-05, "epoch": 10.278346295538272, "percentage": 31.4, "elapsed_time": "1:26:27", "remaining_time": "3:08:53", "throughput": 788.71, "total_tokens": 4091472} {"current_steps": 12565, "total_steps": 40000, "loss": 0.1898, "lr": 3.878459524855381e-05, "epoch": 10.282439623413836, "percentage": 31.41, "elapsed_time": "1:26:29", "remaining_time": "3:08:50", "throughput": 788.76, "total_tokens": 4093088} {"current_steps": 12570, "total_steps": 40000, "loss": 0.1795, "lr": 3.8776403939001384e-05, "epoch": 10.286532951289399, "percentage": 31.42, "elapsed_time": "1:26:30", "remaining_time": "3:08:47", "throughput": 788.82, "total_tokens": 4094736} {"current_steps": 12575, "total_steps": 40000, "loss": 0.2464, "lr": 3.876821050495433e-05, "epoch": 10.290626279164961, "percentage": 31.44, "elapsed_time": "1:26:32", "remaining_time": "3:08:44", "throughput": 788.87, "total_tokens": 4096368} {"current_steps": 12580, "total_steps": 40000, "loss": 0.1968, "lr": 3.87600149476762e-05, "epoch": 10.294719607040523, "percentage": 31.45, "elapsed_time": "1:26:34", "remaining_time": "3:08:42", "throughput": 788.94, "total_tokens": 4098064} {"current_steps": 12585, "total_steps": 40000, "loss": 0.2206, "lr": 3.8751817268430843e-05, "epoch": 10.298812934916088, "percentage": 31.46, "elapsed_time": "1:26:36", "remaining_time": "3:08:39", "throughput": 789.0, "total_tokens": 4099744} {"current_steps": 12590, "total_steps": 40000, "loss": 0.1752, "lr": 3.8743617468482464e-05, "epoch": 10.30290626279165, "percentage": 31.47, "elapsed_time": "1:26:37", "remaining_time": "3:08:36", "throughput": 789.04, "total_tokens": 4101312} {"current_steps": 12595, "total_steps": 40000, "loss": 0.2218, "lr": 3.8735415549095535e-05, "epoch": 10.306999590667212, "percentage": 31.49, "elapsed_time": "1:26:39", "remaining_time": "3:08:33", "throughput": 789.09, "total_tokens": 4102928} {"current_steps": 12600, "total_steps": 40000, "loss": 0.1741, "lr": 3.8727211511534934e-05, "epoch": 10.311092918542775, "percentage": 31.5, "elapsed_time": "1:26:41", "remaining_time": "3:08:30", "throughput": 789.14, "total_tokens": 4104512} {"current_steps": 12600, "total_steps": 40000, "eval_loss": 0.20251239836215973, "epoch": 10.311092918542775, "percentage": 31.5, "elapsed_time": "1:26:53", "remaining_time": "3:08:57", "throughput": 787.25, "total_tokens": 4104512} {"current_steps": 12605, "total_steps": 40000, "loss": 0.2068, "lr": 3.8719005357065804e-05, "epoch": 10.315186246418339, "percentage": 31.51, "elapsed_time": "1:26:56", "remaining_time": "3:08:58", "throughput": 787.09, "total_tokens": 4106192} {"current_steps": 12610, "total_steps": 40000, "loss": 0.1386, "lr": 3.8710797086953645e-05, "epoch": 10.319279574293901, "percentage": 31.52, "elapsed_time": "1:26:58", "remaining_time": "3:08:55", "throughput": 787.17, "total_tokens": 4107952} {"current_steps": 12615, "total_steps": 40000, "loss": 0.1936, "lr": 3.870258670246427e-05, "epoch": 10.323372902169464, "percentage": 31.54, "elapsed_time": "1:27:00", "remaining_time": "3:08:52", "throughput": 787.23, "total_tokens": 4109600} {"current_steps": 12620, "total_steps": 40000, "loss": 0.2231, "lr": 3.869437420486384e-05, "epoch": 10.327466230045026, "percentage": 31.55, "elapsed_time": "1:27:02", "remaining_time": "3:08:49", "throughput": 787.29, "total_tokens": 4111264} {"current_steps": 12625, "total_steps": 40000, "loss": 0.1966, "lr": 3.8686159595418805e-05, "epoch": 10.33155955792059, "percentage": 31.56, "elapsed_time": "1:27:03", "remaining_time": "3:08:46", "throughput": 787.34, "total_tokens": 4112928} {"current_steps": 12630, "total_steps": 40000, "loss": 0.1366, "lr": 3.867794287539597e-05, "epoch": 10.335652885796152, "percentage": 31.57, "elapsed_time": "1:27:05", "remaining_time": "3:08:44", "throughput": 787.4, "total_tokens": 4114560} {"current_steps": 12635, "total_steps": 40000, "loss": 0.1877, "lr": 3.866972404606245e-05, "epoch": 10.339746213671715, "percentage": 31.59, "elapsed_time": "1:27:07", "remaining_time": "3:08:41", "throughput": 787.45, "total_tokens": 4116176} {"current_steps": 12640, "total_steps": 40000, "loss": 0.204, "lr": 3.866150310868571e-05, "epoch": 10.343839541547277, "percentage": 31.6, "elapsed_time": "1:27:08", "remaining_time": "3:08:38", "throughput": 787.49, "total_tokens": 4117744} {"current_steps": 12645, "total_steps": 40000, "loss": 0.171, "lr": 3.8653280064533506e-05, "epoch": 10.347932869422841, "percentage": 31.61, "elapsed_time": "1:27:10", "remaining_time": "3:08:35", "throughput": 787.54, "total_tokens": 4119376} {"current_steps": 12650, "total_steps": 40000, "loss": 0.2265, "lr": 3.864505491487394e-05, "epoch": 10.352026197298404, "percentage": 31.62, "elapsed_time": "1:27:12", "remaining_time": "3:08:32", "throughput": 787.59, "total_tokens": 4120992} {"current_steps": 12655, "total_steps": 40000, "loss": 0.1626, "lr": 3.8636827660975414e-05, "epoch": 10.356119525173966, "percentage": 31.64, "elapsed_time": "1:27:14", "remaining_time": "3:08:29", "throughput": 787.64, "total_tokens": 4122576} {"current_steps": 12660, "total_steps": 40000, "loss": 0.161, "lr": 3.862859830410671e-05, "epoch": 10.360212853049529, "percentage": 31.65, "elapsed_time": "1:27:15", "remaining_time": "3:08:27", "throughput": 787.68, "total_tokens": 4124176} {"current_steps": 12665, "total_steps": 40000, "loss": 0.2009, "lr": 3.862036684553688e-05, "epoch": 10.364306180925093, "percentage": 31.66, "elapsed_time": "1:27:17", "remaining_time": "3:08:24", "throughput": 787.74, "total_tokens": 4125808} {"current_steps": 12670, "total_steps": 40000, "loss": 0.1645, "lr": 3.8612133286535314e-05, "epoch": 10.368399508800655, "percentage": 31.67, "elapsed_time": "1:27:19", "remaining_time": "3:08:21", "throughput": 787.8, "total_tokens": 4127504} {"current_steps": 12675, "total_steps": 40000, "loss": 0.1901, "lr": 3.860389762837173e-05, "epoch": 10.372492836676217, "percentage": 31.69, "elapsed_time": "1:27:21", "remaining_time": "3:08:18", "throughput": 787.85, "total_tokens": 4129120} {"current_steps": 12680, "total_steps": 40000, "loss": 0.2217, "lr": 3.859565987231618e-05, "epoch": 10.37658616455178, "percentage": 31.7, "elapsed_time": "1:27:22", "remaining_time": "3:08:15", "throughput": 787.9, "total_tokens": 4130736} {"current_steps": 12685, "total_steps": 40000, "loss": 0.175, "lr": 3.858742001963902e-05, "epoch": 10.380679492427344, "percentage": 31.71, "elapsed_time": "1:27:24", "remaining_time": "3:08:13", "throughput": 787.95, "total_tokens": 4132368} {"current_steps": 12690, "total_steps": 40000, "loss": 0.1926, "lr": 3.857917807161094e-05, "epoch": 10.384772820302906, "percentage": 31.72, "elapsed_time": "1:27:26", "remaining_time": "3:08:10", "throughput": 787.99, "total_tokens": 4133952} {"current_steps": 12695, "total_steps": 40000, "loss": 0.21, "lr": 3.857093402950296e-05, "epoch": 10.388866148178469, "percentage": 31.74, "elapsed_time": "1:27:27", "remaining_time": "3:08:07", "throughput": 788.05, "total_tokens": 4135584} {"current_steps": 12700, "total_steps": 40000, "loss": 0.1668, "lr": 3.8562687894586414e-05, "epoch": 10.392959476054031, "percentage": 31.75, "elapsed_time": "1:27:29", "remaining_time": "3:08:04", "throughput": 788.1, "total_tokens": 4137216} {"current_steps": 12705, "total_steps": 40000, "loss": 0.1392, "lr": 3.8554439668132946e-05, "epoch": 10.397052803929595, "percentage": 31.76, "elapsed_time": "1:27:31", "remaining_time": "3:08:01", "throughput": 788.15, "total_tokens": 4138864} {"current_steps": 12710, "total_steps": 40000, "loss": 0.2777, "lr": 3.854618935141455e-05, "epoch": 10.401146131805158, "percentage": 31.77, "elapsed_time": "1:27:33", "remaining_time": "3:07:59", "throughput": 788.19, "total_tokens": 4140448} {"current_steps": 12715, "total_steps": 40000, "loss": 0.2167, "lr": 3.8537936945703525e-05, "epoch": 10.40523945968072, "percentage": 31.79, "elapsed_time": "1:27:34", "remaining_time": "3:07:56", "throughput": 788.26, "total_tokens": 4142128} {"current_steps": 12720, "total_steps": 40000, "loss": 0.2192, "lr": 3.852968245227249e-05, "epoch": 10.409332787556282, "percentage": 31.8, "elapsed_time": "1:27:36", "remaining_time": "3:07:53", "throughput": 788.32, "total_tokens": 4143808} {"current_steps": 12725, "total_steps": 40000, "loss": 0.2188, "lr": 3.85214258723944e-05, "epoch": 10.413426115431847, "percentage": 31.81, "elapsed_time": "1:27:38", "remaining_time": "3:07:50", "throughput": 788.37, "total_tokens": 4145440} {"current_steps": 12730, "total_steps": 40000, "loss": 0.214, "lr": 3.8513167207342524e-05, "epoch": 10.417519443307409, "percentage": 31.82, "elapsed_time": "1:27:39", "remaining_time": "3:07:47", "throughput": 788.4, "total_tokens": 4146960} {"current_steps": 12735, "total_steps": 40000, "loss": 0.1997, "lr": 3.850490645839044e-05, "epoch": 10.421612771182971, "percentage": 31.84, "elapsed_time": "1:27:41", "remaining_time": "3:07:45", "throughput": 788.46, "total_tokens": 4148624} {"current_steps": 12740, "total_steps": 40000, "loss": 0.1993, "lr": 3.849664362681207e-05, "epoch": 10.425706099058534, "percentage": 31.85, "elapsed_time": "1:27:43", "remaining_time": "3:07:42", "throughput": 788.5, "total_tokens": 4150208} {"current_steps": 12745, "total_steps": 40000, "loss": 0.1664, "lr": 3.848837871388165e-05, "epoch": 10.429799426934098, "percentage": 31.86, "elapsed_time": "1:27:45", "remaining_time": "3:07:39", "throughput": 788.55, "total_tokens": 4151808} {"current_steps": 12750, "total_steps": 40000, "loss": 0.1754, "lr": 3.848011172087371e-05, "epoch": 10.43389275480966, "percentage": 31.87, "elapsed_time": "1:27:46", "remaining_time": "3:07:36", "throughput": 788.61, "total_tokens": 4153504} {"current_steps": 12755, "total_steps": 40000, "loss": 0.1539, "lr": 3.847184264906315e-05, "epoch": 10.437986082685223, "percentage": 31.89, "elapsed_time": "1:27:48", "remaining_time": "3:07:33", "throughput": 788.66, "total_tokens": 4155104} {"current_steps": 12760, "total_steps": 40000, "loss": 0.174, "lr": 3.846357149972516e-05, "epoch": 10.442079410560787, "percentage": 31.9, "elapsed_time": "1:27:50", "remaining_time": "3:07:31", "throughput": 788.71, "total_tokens": 4156736} {"current_steps": 12765, "total_steps": 40000, "loss": 0.1786, "lr": 3.8455298274135246e-05, "epoch": 10.44617273843635, "percentage": 31.91, "elapsed_time": "1:27:52", "remaining_time": "3:07:28", "throughput": 788.77, "total_tokens": 4158400} {"current_steps": 12770, "total_steps": 40000, "loss": 0.2577, "lr": 3.8447022973569254e-05, "epoch": 10.450266066311912, "percentage": 31.92, "elapsed_time": "1:27:53", "remaining_time": "3:07:25", "throughput": 788.81, "total_tokens": 4160000} {"current_steps": 12775, "total_steps": 40000, "loss": 0.2092, "lr": 3.843874559930332e-05, "epoch": 10.454359394187474, "percentage": 31.94, "elapsed_time": "1:27:55", "remaining_time": "3:07:22", "throughput": 788.86, "total_tokens": 4161616} {"current_steps": 12780, "total_steps": 40000, "loss": 0.1955, "lr": 3.843046615261394e-05, "epoch": 10.458452722063038, "percentage": 31.95, "elapsed_time": "1:27:57", "remaining_time": "3:07:19", "throughput": 788.92, "total_tokens": 4163264} {"current_steps": 12785, "total_steps": 40000, "loss": 0.1985, "lr": 3.842218463477791e-05, "epoch": 10.4625460499386, "percentage": 31.96, "elapsed_time": "1:27:58", "remaining_time": "3:07:17", "throughput": 788.97, "total_tokens": 4164864} {"current_steps": 12790, "total_steps": 40000, "loss": 0.1367, "lr": 3.841390104707233e-05, "epoch": 10.466639377814163, "percentage": 31.97, "elapsed_time": "1:28:00", "remaining_time": "3:07:14", "throughput": 789.02, "total_tokens": 4166496} {"current_steps": 12795, "total_steps": 40000, "loss": 0.2089, "lr": 3.8405615390774643e-05, "epoch": 10.470732705689725, "percentage": 31.99, "elapsed_time": "1:28:02", "remaining_time": "3:07:11", "throughput": 789.08, "total_tokens": 4168192} {"current_steps": 12800, "total_steps": 40000, "loss": 0.1612, "lr": 3.839732766716259e-05, "epoch": 10.47482603356529, "percentage": 32.0, "elapsed_time": "1:28:04", "remaining_time": "3:07:08", "throughput": 789.14, "total_tokens": 4169856} {"current_steps": 12800, "total_steps": 40000, "eval_loss": 0.20237939059734344, "epoch": 10.47482603356529, "percentage": 32.0, "elapsed_time": "1:28:16", "remaining_time": "3:07:35", "throughput": 787.28, "total_tokens": 4169856} {"current_steps": 12805, "total_steps": 40000, "loss": 0.1608, "lr": 3.838903787751425e-05, "epoch": 10.478919361440852, "percentage": 32.01, "elapsed_time": "1:28:19", "remaining_time": "3:07:35", "throughput": 787.11, "total_tokens": 4171472} {"current_steps": 12810, "total_steps": 40000, "loss": 0.2018, "lr": 3.838074602310802e-05, "epoch": 10.483012689316414, "percentage": 32.02, "elapsed_time": "1:28:21", "remaining_time": "3:07:32", "throughput": 787.15, "total_tokens": 4173040} {"current_steps": 12815, "total_steps": 40000, "loss": 0.2386, "lr": 3.837245210522258e-05, "epoch": 10.487106017191977, "percentage": 32.04, "elapsed_time": "1:28:23", "remaining_time": "3:07:29", "throughput": 787.19, "total_tokens": 4174608} {"current_steps": 12820, "total_steps": 40000, "loss": 0.2184, "lr": 3.8364156125136996e-05, "epoch": 10.49119934506754, "percentage": 32.05, "elapsed_time": "1:28:24", "remaining_time": "3:07:26", "throughput": 787.24, "total_tokens": 4176208} {"current_steps": 12825, "total_steps": 40000, "loss": 0.2092, "lr": 3.835585808413059e-05, "epoch": 10.495292672943103, "percentage": 32.06, "elapsed_time": "1:28:26", "remaining_time": "3:07:24", "throughput": 787.29, "total_tokens": 4177808} {"current_steps": 12830, "total_steps": 40000, "loss": 0.177, "lr": 3.8347557983483024e-05, "epoch": 10.499386000818665, "percentage": 32.07, "elapsed_time": "1:28:28", "remaining_time": "3:07:21", "throughput": 787.36, "total_tokens": 4179552} {"current_steps": 12835, "total_steps": 40000, "loss": 0.2016, "lr": 3.833925582447428e-05, "epoch": 10.503479328694228, "percentage": 32.09, "elapsed_time": "1:28:30", "remaining_time": "3:07:18", "throughput": 787.41, "total_tokens": 4181168} {"current_steps": 12840, "total_steps": 40000, "loss": 0.2105, "lr": 3.8330951608384656e-05, "epoch": 10.507572656569792, "percentage": 32.1, "elapsed_time": "1:28:31", "remaining_time": "3:07:15", "throughput": 787.46, "total_tokens": 4182816} {"current_steps": 12845, "total_steps": 40000, "loss": 0.2012, "lr": 3.832264533649477e-05, "epoch": 10.511665984445354, "percentage": 32.11, "elapsed_time": "1:28:33", "remaining_time": "3:07:12", "throughput": 787.51, "total_tokens": 4184432} {"current_steps": 12850, "total_steps": 40000, "loss": 0.123, "lr": 3.8314337010085555e-05, "epoch": 10.515759312320917, "percentage": 32.12, "elapsed_time": "1:28:35", "remaining_time": "3:07:10", "throughput": 787.55, "total_tokens": 4186000} {"current_steps": 12855, "total_steps": 40000, "loss": 0.2547, "lr": 3.830602663043824e-05, "epoch": 10.51985264019648, "percentage": 32.14, "elapsed_time": "1:28:36", "remaining_time": "3:07:07", "throughput": 787.62, "total_tokens": 4187728} {"current_steps": 12860, "total_steps": 40000, "loss": 0.1772, "lr": 3.8297714198834414e-05, "epoch": 10.523945968072043, "percentage": 32.15, "elapsed_time": "1:28:38", "remaining_time": "3:07:04", "throughput": 787.68, "total_tokens": 4189392} {"current_steps": 12865, "total_steps": 40000, "loss": 0.1601, "lr": 3.828939971655595e-05, "epoch": 10.528039295947606, "percentage": 32.16, "elapsed_time": "1:28:40", "remaining_time": "3:07:01", "throughput": 787.73, "total_tokens": 4190992} {"current_steps": 12870, "total_steps": 40000, "loss": 0.153, "lr": 3.828108318488505e-05, "epoch": 10.532132623823168, "percentage": 32.17, "elapsed_time": "1:28:42", "remaining_time": "3:06:58", "throughput": 787.78, "total_tokens": 4192608} {"current_steps": 12875, "total_steps": 40000, "loss": 0.1326, "lr": 3.8272764605104216e-05, "epoch": 10.53622595169873, "percentage": 32.19, "elapsed_time": "1:28:43", "remaining_time": "3:06:56", "throughput": 787.82, "total_tokens": 4194208} {"current_steps": 12880, "total_steps": 40000, "loss": 0.1504, "lr": 3.826444397849628e-05, "epoch": 10.540319279574295, "percentage": 32.2, "elapsed_time": "1:28:45", "remaining_time": "3:06:53", "throughput": 787.88, "total_tokens": 4195872} {"current_steps": 12885, "total_steps": 40000, "loss": 0.1425, "lr": 3.825612130634439e-05, "epoch": 10.544412607449857, "percentage": 32.21, "elapsed_time": "1:28:47", "remaining_time": "3:06:50", "throughput": 787.93, "total_tokens": 4197472} {"current_steps": 12890, "total_steps": 40000, "loss": 0.2142, "lr": 3.824779658993202e-05, "epoch": 10.54850593532542, "percentage": 32.23, "elapsed_time": "1:28:48", "remaining_time": "3:06:47", "throughput": 787.98, "total_tokens": 4199104} {"current_steps": 12895, "total_steps": 40000, "loss": 0.177, "lr": 3.823946983054292e-05, "epoch": 10.552599263200982, "percentage": 32.24, "elapsed_time": "1:28:50", "remaining_time": "3:06:44", "throughput": 788.02, "total_tokens": 4200672} {"current_steps": 12900, "total_steps": 40000, "loss": 0.2075, "lr": 3.82311410294612e-05, "epoch": 10.556692591076546, "percentage": 32.25, "elapsed_time": "1:28:52", "remaining_time": "3:06:42", "throughput": 788.07, "total_tokens": 4202272} {"current_steps": 12905, "total_steps": 40000, "loss": 0.1702, "lr": 3.822281018797127e-05, "epoch": 10.560785918952108, "percentage": 32.26, "elapsed_time": "1:28:54", "remaining_time": "3:06:39", "throughput": 788.12, "total_tokens": 4203936} {"current_steps": 12910, "total_steps": 40000, "loss": 0.1636, "lr": 3.821447730735783e-05, "epoch": 10.56487924682767, "percentage": 32.27, "elapsed_time": "1:28:55", "remaining_time": "3:06:36", "throughput": 788.17, "total_tokens": 4205536} {"current_steps": 12915, "total_steps": 40000, "loss": 0.1617, "lr": 3.820614238890592e-05, "epoch": 10.568972574703233, "percentage": 32.29, "elapsed_time": "1:28:57", "remaining_time": "3:06:33", "throughput": 788.21, "total_tokens": 4207104} {"current_steps": 12920, "total_steps": 40000, "loss": 0.2007, "lr": 3.819780543390091e-05, "epoch": 10.573065902578797, "percentage": 32.3, "elapsed_time": "1:28:59", "remaining_time": "3:06:30", "throughput": 788.26, "total_tokens": 4208736} {"current_steps": 12925, "total_steps": 40000, "loss": 0.2218, "lr": 3.818946644362844e-05, "epoch": 10.57715923045436, "percentage": 32.31, "elapsed_time": "1:29:00", "remaining_time": "3:06:28", "throughput": 788.31, "total_tokens": 4210352} {"current_steps": 12930, "total_steps": 40000, "loss": 0.1666, "lr": 3.81811254193745e-05, "epoch": 10.581252558329922, "percentage": 32.32, "elapsed_time": "1:29:02", "remaining_time": "3:06:25", "throughput": 788.36, "total_tokens": 4212000} {"current_steps": 12935, "total_steps": 40000, "loss": 0.1174, "lr": 3.8172782362425366e-05, "epoch": 10.585345886205484, "percentage": 32.34, "elapsed_time": "1:29:04", "remaining_time": "3:06:22", "throughput": 788.41, "total_tokens": 4213584} {"current_steps": 12940, "total_steps": 40000, "loss": 0.1818, "lr": 3.816443727406765e-05, "epoch": 10.589439214081048, "percentage": 32.35, "elapsed_time": "1:29:06", "remaining_time": "3:06:19", "throughput": 788.46, "total_tokens": 4215232} {"current_steps": 12945, "total_steps": 40000, "loss": 0.1991, "lr": 3.815609015558829e-05, "epoch": 10.59353254195661, "percentage": 32.36, "elapsed_time": "1:29:07", "remaining_time": "3:06:17", "throughput": 788.51, "total_tokens": 4216864} {"current_steps": 12950, "total_steps": 40000, "loss": 0.2097, "lr": 3.814774100827448e-05, "epoch": 10.597625869832173, "percentage": 32.38, "elapsed_time": "1:29:09", "remaining_time": "3:06:14", "throughput": 788.57, "total_tokens": 4218528} {"current_steps": 12955, "total_steps": 40000, "loss": 0.1859, "lr": 3.813938983341379e-05, "epoch": 10.601719197707736, "percentage": 32.39, "elapsed_time": "1:29:11", "remaining_time": "3:06:11", "throughput": 788.62, "total_tokens": 4220144} {"current_steps": 12960, "total_steps": 40000, "loss": 0.1163, "lr": 3.813103663229407e-05, "epoch": 10.6058125255833, "percentage": 32.4, "elapsed_time": "1:29:13", "remaining_time": "3:06:08", "throughput": 788.66, "total_tokens": 4221728} {"current_steps": 12965, "total_steps": 40000, "loss": 0.1456, "lr": 3.812268140620349e-05, "epoch": 10.609905853458862, "percentage": 32.41, "elapsed_time": "1:29:14", "remaining_time": "3:06:05", "throughput": 788.72, "total_tokens": 4223408} {"current_steps": 12970, "total_steps": 40000, "loss": 0.2375, "lr": 3.811432415643051e-05, "epoch": 10.613999181334425, "percentage": 32.42, "elapsed_time": "1:29:16", "remaining_time": "3:06:03", "throughput": 788.77, "total_tokens": 4225024} {"current_steps": 12975, "total_steps": 40000, "loss": 0.1329, "lr": 3.8105964884263954e-05, "epoch": 10.618092509209987, "percentage": 32.44, "elapsed_time": "1:29:18", "remaining_time": "3:06:00", "throughput": 788.83, "total_tokens": 4226688} {"current_steps": 12980, "total_steps": 40000, "loss": 0.1738, "lr": 3.809760359099291e-05, "epoch": 10.622185837085551, "percentage": 32.45, "elapsed_time": "1:29:19", "remaining_time": "3:05:57", "throughput": 788.86, "total_tokens": 4228224} {"current_steps": 12985, "total_steps": 40000, "loss": 0.2356, "lr": 3.8089240277906804e-05, "epoch": 10.626279164961113, "percentage": 32.46, "elapsed_time": "1:29:21", "remaining_time": "3:05:54", "throughput": 788.93, "total_tokens": 4229952} {"current_steps": 12990, "total_steps": 40000, "loss": 0.2221, "lr": 3.808087494629535e-05, "epoch": 10.630372492836676, "percentage": 32.48, "elapsed_time": "1:29:23", "remaining_time": "3:05:51", "throughput": 789.0, "total_tokens": 4231648} {"current_steps": 12995, "total_steps": 40000, "loss": 0.2075, "lr": 3.8072507597448595e-05, "epoch": 10.634465820712238, "percentage": 32.49, "elapsed_time": "1:29:25", "remaining_time": "3:05:49", "throughput": 789.04, "total_tokens": 4233248} {"current_steps": 13000, "total_steps": 40000, "loss": 0.2859, "lr": 3.806413823265689e-05, "epoch": 10.638559148587802, "percentage": 32.5, "elapsed_time": "1:29:26", "remaining_time": "3:05:46", "throughput": 789.09, "total_tokens": 4234864} {"current_steps": 13000, "total_steps": 40000, "eval_loss": 0.20075057446956635, "epoch": 10.638559148587802, "percentage": 32.5, "elapsed_time": "1:29:39", "remaining_time": "3:06:12", "throughput": 787.26, "total_tokens": 4234864} {"current_steps": 13005, "total_steps": 40000, "loss": 0.2201, "lr": 3.805576685321089e-05, "epoch": 10.642652476463365, "percentage": 32.51, "elapsed_time": "1:29:42", "remaining_time": "3:06:12", "throughput": 787.1, "total_tokens": 4236496} {"current_steps": 13010, "total_steps": 40000, "loss": 0.2208, "lr": 3.804739346040158e-05, "epoch": 10.646745804338927, "percentage": 32.52, "elapsed_time": "1:29:44", "remaining_time": "3:06:09", "throughput": 787.15, "total_tokens": 4238128} {"current_steps": 13015, "total_steps": 40000, "loss": 0.2103, "lr": 3.8039018055520234e-05, "epoch": 10.65083913221449, "percentage": 32.54, "elapsed_time": "1:29:45", "remaining_time": "3:06:06", "throughput": 787.21, "total_tokens": 4239776} {"current_steps": 13020, "total_steps": 40000, "loss": 0.1801, "lr": 3.803064063985844e-05, "epoch": 10.654932460090054, "percentage": 32.55, "elapsed_time": "1:29:47", "remaining_time": "3:06:04", "throughput": 787.26, "total_tokens": 4241440} {"current_steps": 13025, "total_steps": 40000, "loss": 0.1813, "lr": 3.802226121470811e-05, "epoch": 10.659025787965616, "percentage": 32.56, "elapsed_time": "1:29:49", "remaining_time": "3:06:01", "throughput": 787.32, "total_tokens": 4243088} {"current_steps": 13030, "total_steps": 40000, "loss": 0.1463, "lr": 3.801387978136145e-05, "epoch": 10.663119115841178, "percentage": 32.57, "elapsed_time": "1:29:51", "remaining_time": "3:05:58", "throughput": 787.37, "total_tokens": 4244736} {"current_steps": 13035, "total_steps": 40000, "loss": 0.2285, "lr": 3.800549634111099e-05, "epoch": 10.667212443716743, "percentage": 32.59, "elapsed_time": "1:29:52", "remaining_time": "3:05:55", "throughput": 787.42, "total_tokens": 4246368} {"current_steps": 13040, "total_steps": 40000, "loss": 0.1482, "lr": 3.799711089524955e-05, "epoch": 10.671305771592305, "percentage": 32.6, "elapsed_time": "1:29:54", "remaining_time": "3:05:52", "throughput": 787.47, "total_tokens": 4247968} {"current_steps": 13045, "total_steps": 40000, "loss": 0.1639, "lr": 3.7988723445070285e-05, "epoch": 10.675399099467867, "percentage": 32.61, "elapsed_time": "1:29:56", "remaining_time": "3:05:50", "throughput": 787.52, "total_tokens": 4249584} {"current_steps": 13050, "total_steps": 40000, "loss": 0.216, "lr": 3.798033399186663e-05, "epoch": 10.67949242734343, "percentage": 32.62, "elapsed_time": "1:29:57", "remaining_time": "3:05:47", "throughput": 787.57, "total_tokens": 4251216} {"current_steps": 13055, "total_steps": 40000, "loss": 0.2114, "lr": 3.797194253693237e-05, "epoch": 10.683585755218992, "percentage": 32.64, "elapsed_time": "1:29:59", "remaining_time": "3:05:44", "throughput": 787.63, "total_tokens": 4252880} {"current_steps": 13060, "total_steps": 40000, "loss": 0.1632, "lr": 3.796354908156153e-05, "epoch": 10.687679083094556, "percentage": 32.65, "elapsed_time": "1:30:01", "remaining_time": "3:05:41", "throughput": 787.67, "total_tokens": 4254496} {"current_steps": 13065, "total_steps": 40000, "loss": 0.2194, "lr": 3.795515362704853e-05, "epoch": 10.691772410970119, "percentage": 32.66, "elapsed_time": "1:30:03", "remaining_time": "3:05:39", "throughput": 787.72, "total_tokens": 4256112} {"current_steps": 13070, "total_steps": 40000, "loss": 0.1991, "lr": 3.794675617468803e-05, "epoch": 10.695865738845681, "percentage": 32.67, "elapsed_time": "1:30:04", "remaining_time": "3:05:36", "throughput": 787.77, "total_tokens": 4257728} {"current_steps": 13075, "total_steps": 40000, "loss": 0.2102, "lr": 3.793835672577503e-05, "epoch": 10.699959066721245, "percentage": 32.69, "elapsed_time": "1:30:06", "remaining_time": "3:05:33", "throughput": 787.81, "total_tokens": 4259296} {"current_steps": 13080, "total_steps": 40000, "loss": 0.141, "lr": 3.7929955281604826e-05, "epoch": 10.704052394596808, "percentage": 32.7, "elapsed_time": "1:30:08", "remaining_time": "3:05:30", "throughput": 787.87, "total_tokens": 4260976} {"current_steps": 13085, "total_steps": 40000, "loss": 0.2208, "lr": 3.7921551843473036e-05, "epoch": 10.70814572247237, "percentage": 32.71, "elapsed_time": "1:30:09", "remaining_time": "3:05:27", "throughput": 787.92, "total_tokens": 4262608} {"current_steps": 13090, "total_steps": 40000, "loss": 0.1822, "lr": 3.791314641267557e-05, "epoch": 10.712239050347932, "percentage": 32.73, "elapsed_time": "1:30:11", "remaining_time": "3:05:25", "throughput": 787.98, "total_tokens": 4264288} {"current_steps": 13095, "total_steps": 40000, "loss": 0.1596, "lr": 3.790473899050864e-05, "epoch": 10.716332378223496, "percentage": 32.74, "elapsed_time": "1:30:13", "remaining_time": "3:05:22", "throughput": 788.03, "total_tokens": 4265920} {"current_steps": 13100, "total_steps": 40000, "loss": 0.2117, "lr": 3.7896329578268794e-05, "epoch": 10.720425706099059, "percentage": 32.75, "elapsed_time": "1:30:15", "remaining_time": "3:05:19", "throughput": 788.08, "total_tokens": 4267520} {"current_steps": 13105, "total_steps": 40000, "loss": 0.2547, "lr": 3.7887918177252855e-05, "epoch": 10.724519033974621, "percentage": 32.76, "elapsed_time": "1:30:16", "remaining_time": "3:05:16", "throughput": 788.14, "total_tokens": 4269184} {"current_steps": 13110, "total_steps": 40000, "loss": 0.1518, "lr": 3.787950478875798e-05, "epoch": 10.728612361850184, "percentage": 32.77, "elapsed_time": "1:30:18", "remaining_time": "3:05:13", "throughput": 788.19, "total_tokens": 4270816} {"current_steps": 13115, "total_steps": 40000, "loss": 0.1773, "lr": 3.787108941408162e-05, "epoch": 10.732705689725748, "percentage": 32.79, "elapsed_time": "1:30:20", "remaining_time": "3:05:11", "throughput": 788.24, "total_tokens": 4272432} {"current_steps": 13120, "total_steps": 40000, "loss": 0.129, "lr": 3.786267205452151e-05, "epoch": 10.73679901760131, "percentage": 32.8, "elapsed_time": "1:30:21", "remaining_time": "3:05:08", "throughput": 788.3, "total_tokens": 4274128} {"current_steps": 13125, "total_steps": 40000, "loss": 0.2141, "lr": 3.785425271137573e-05, "epoch": 10.740892345476873, "percentage": 32.81, "elapsed_time": "1:30:23", "remaining_time": "3:05:05", "throughput": 788.35, "total_tokens": 4275744} {"current_steps": 13130, "total_steps": 40000, "loss": 0.1935, "lr": 3.7845831385942655e-05, "epoch": 10.744985673352435, "percentage": 32.82, "elapsed_time": "1:30:25", "remaining_time": "3:05:02", "throughput": 788.4, "total_tokens": 4277376} {"current_steps": 13135, "total_steps": 40000, "loss": 0.1797, "lr": 3.7837408079520944e-05, "epoch": 10.749079001227999, "percentage": 32.84, "elapsed_time": "1:30:27", "remaining_time": "3:05:00", "throughput": 788.45, "total_tokens": 4279008} {"current_steps": 13140, "total_steps": 40000, "loss": 0.2038, "lr": 3.782898279340957e-05, "epoch": 10.753172329103561, "percentage": 32.85, "elapsed_time": "1:30:28", "remaining_time": "3:04:57", "throughput": 788.49, "total_tokens": 4280608} {"current_steps": 13145, "total_steps": 40000, "loss": 0.2158, "lr": 3.782055552890784e-05, "epoch": 10.757265656979124, "percentage": 32.86, "elapsed_time": "1:30:30", "remaining_time": "3:04:54", "throughput": 788.54, "total_tokens": 4282208} {"current_steps": 13150, "total_steps": 40000, "loss": 0.178, "lr": 3.781212628731534e-05, "epoch": 10.761358984854686, "percentage": 32.88, "elapsed_time": "1:30:32", "remaining_time": "3:04:51", "throughput": 788.57, "total_tokens": 4283760} {"current_steps": 13155, "total_steps": 40000, "loss": 0.258, "lr": 3.7803695069931946e-05, "epoch": 10.76545231273025, "percentage": 32.89, "elapsed_time": "1:30:34", "remaining_time": "3:04:49", "throughput": 788.62, "total_tokens": 4285392} {"current_steps": 13160, "total_steps": 40000, "loss": 0.2047, "lr": 3.779526187805789e-05, "epoch": 10.769545640605813, "percentage": 32.9, "elapsed_time": "1:30:35", "remaining_time": "3:04:46", "throughput": 788.68, "total_tokens": 4287040} {"current_steps": 13165, "total_steps": 40000, "loss": 0.1913, "lr": 3.778682671299364e-05, "epoch": 10.773638968481375, "percentage": 32.91, "elapsed_time": "1:30:37", "remaining_time": "3:04:43", "throughput": 788.75, "total_tokens": 4288768} {"current_steps": 13170, "total_steps": 40000, "loss": 0.1792, "lr": 3.777838957604003e-05, "epoch": 10.777732296356938, "percentage": 32.92, "elapsed_time": "1:30:39", "remaining_time": "3:04:40", "throughput": 788.79, "total_tokens": 4290368} {"current_steps": 13175, "total_steps": 40000, "loss": 0.1941, "lr": 3.776995046849816e-05, "epoch": 10.781825624232502, "percentage": 32.94, "elapsed_time": "1:30:40", "remaining_time": "3:04:37", "throughput": 788.84, "total_tokens": 4292000} {"current_steps": 13180, "total_steps": 40000, "loss": 0.1857, "lr": 3.776150939166945e-05, "epoch": 10.785918952108064, "percentage": 32.95, "elapsed_time": "1:30:42", "remaining_time": "3:04:35", "throughput": 788.89, "total_tokens": 4293616} {"current_steps": 13185, "total_steps": 40000, "loss": 0.2298, "lr": 3.775306634685562e-05, "epoch": 10.790012279983626, "percentage": 32.96, "elapsed_time": "1:30:44", "remaining_time": "3:04:32", "throughput": 788.94, "total_tokens": 4295248} {"current_steps": 13190, "total_steps": 40000, "loss": 0.1833, "lr": 3.7744621335358696e-05, "epoch": 10.794105607859189, "percentage": 32.98, "elapsed_time": "1:30:46", "remaining_time": "3:04:29", "throughput": 788.99, "total_tokens": 4296864} {"current_steps": 13195, "total_steps": 40000, "loss": 0.1744, "lr": 3.7736174358481e-05, "epoch": 10.798198935734753, "percentage": 32.99, "elapsed_time": "1:30:47", "remaining_time": "3:04:26", "throughput": 789.04, "total_tokens": 4298480} {"current_steps": 13200, "total_steps": 40000, "loss": 0.1327, "lr": 3.7727725417525175e-05, "epoch": 10.802292263610315, "percentage": 33.0, "elapsed_time": "1:30:49", "remaining_time": "3:04:24", "throughput": 789.09, "total_tokens": 4300144} {"current_steps": 13200, "total_steps": 40000, "eval_loss": 0.20271533727645874, "epoch": 10.802292263610315, "percentage": 33.0, "elapsed_time": "1:31:01", "remaining_time": "3:04:49", "throughput": 787.3, "total_tokens": 4300144} {"current_steps": 13205, "total_steps": 40000, "loss": 0.1757, "lr": 3.771927451379414e-05, "epoch": 10.806385591485878, "percentage": 33.01, "elapsed_time": "1:31:05", "remaining_time": "3:04:49", "throughput": 787.13, "total_tokens": 4301744} {"current_steps": 13210, "total_steps": 40000, "loss": 0.1822, "lr": 3.7710821648591135e-05, "epoch": 10.81047891936144, "percentage": 33.02, "elapsed_time": "1:31:06", "remaining_time": "3:04:46", "throughput": 787.17, "total_tokens": 4303328} {"current_steps": 13215, "total_steps": 40000, "loss": 0.213, "lr": 3.7702366823219694e-05, "epoch": 10.814572247237004, "percentage": 33.04, "elapsed_time": "1:31:08", "remaining_time": "3:04:43", "throughput": 787.24, "total_tokens": 4305024} {"current_steps": 13220, "total_steps": 40000, "loss": 0.17, "lr": 3.769391003898366e-05, "epoch": 10.818665575112567, "percentage": 33.05, "elapsed_time": "1:31:10", "remaining_time": "3:04:41", "throughput": 787.28, "total_tokens": 4306592} {"current_steps": 13225, "total_steps": 40000, "loss": 0.2331, "lr": 3.768545129718718e-05, "epoch": 10.822758902988129, "percentage": 33.06, "elapsed_time": "1:31:11", "remaining_time": "3:04:38", "throughput": 787.32, "total_tokens": 4308208} {"current_steps": 13230, "total_steps": 40000, "loss": 0.1955, "lr": 3.7676990599134686e-05, "epoch": 10.826852230863691, "percentage": 33.07, "elapsed_time": "1:31:13", "remaining_time": "3:04:35", "throughput": 787.38, "total_tokens": 4309872} {"current_steps": 13235, "total_steps": 40000, "loss": 0.2266, "lr": 3.766852794613095e-05, "epoch": 10.830945558739256, "percentage": 33.09, "elapsed_time": "1:31:15", "remaining_time": "3:04:32", "throughput": 787.45, "total_tokens": 4311600} {"current_steps": 13240, "total_steps": 40000, "loss": 0.138, "lr": 3.766006333948099e-05, "epoch": 10.835038886614818, "percentage": 33.1, "elapsed_time": "1:31:17", "remaining_time": "3:04:30", "throughput": 787.49, "total_tokens": 4313200} {"current_steps": 13245, "total_steps": 40000, "loss": 0.2531, "lr": 3.765159678049017e-05, "epoch": 10.83913221449038, "percentage": 33.11, "elapsed_time": "1:31:18", "remaining_time": "3:04:27", "throughput": 787.55, "total_tokens": 4314864} {"current_steps": 13250, "total_steps": 40000, "loss": 0.182, "lr": 3.7643128270464134e-05, "epoch": 10.843225542365943, "percentage": 33.12, "elapsed_time": "1:31:20", "remaining_time": "3:04:24", "throughput": 787.61, "total_tokens": 4316528} {"current_steps": 13255, "total_steps": 40000, "loss": 0.2144, "lr": 3.763465781070884e-05, "epoch": 10.847318870241507, "percentage": 33.14, "elapsed_time": "1:31:22", "remaining_time": "3:04:21", "throughput": 787.65, "total_tokens": 4318112} {"current_steps": 13260, "total_steps": 40000, "loss": 0.1577, "lr": 3.762618540253052e-05, "epoch": 10.85141219811707, "percentage": 33.15, "elapsed_time": "1:31:24", "remaining_time": "3:04:19", "throughput": 787.7, "total_tokens": 4319760} {"current_steps": 13265, "total_steps": 40000, "loss": 0.1899, "lr": 3.761771104723576e-05, "epoch": 10.855505525992632, "percentage": 33.16, "elapsed_time": "1:31:25", "remaining_time": "3:04:16", "throughput": 787.75, "total_tokens": 4321376} {"current_steps": 13270, "total_steps": 40000, "loss": 0.207, "lr": 3.7609234746131386e-05, "epoch": 10.859598853868194, "percentage": 33.17, "elapsed_time": "1:31:27", "remaining_time": "3:04:13", "throughput": 787.8, "total_tokens": 4323024} {"current_steps": 13275, "total_steps": 40000, "loss": 0.1735, "lr": 3.7600756500524556e-05, "epoch": 10.863692181743758, "percentage": 33.19, "elapsed_time": "1:31:29", "remaining_time": "3:04:10", "throughput": 787.85, "total_tokens": 4324624} {"current_steps": 13280, "total_steps": 40000, "loss": 0.136, "lr": 3.759227631172271e-05, "epoch": 10.86778550961932, "percentage": 33.2, "elapsed_time": "1:31:30", "remaining_time": "3:04:07", "throughput": 787.88, "total_tokens": 4326144} {"current_steps": 13285, "total_steps": 40000, "loss": 0.1996, "lr": 3.758379418103363e-05, "epoch": 10.871878837494883, "percentage": 33.21, "elapsed_time": "1:31:32", "remaining_time": "3:04:05", "throughput": 787.92, "total_tokens": 4327760} {"current_steps": 13290, "total_steps": 40000, "loss": 0.2316, "lr": 3.757531010976534e-05, "epoch": 10.875972165370445, "percentage": 33.23, "elapsed_time": "1:31:34", "remaining_time": "3:04:02", "throughput": 787.98, "total_tokens": 4329408} {"current_steps": 13295, "total_steps": 40000, "loss": 0.2266, "lr": 3.75668240992262e-05, "epoch": 10.88006549324601, "percentage": 33.24, "elapsed_time": "1:31:36", "remaining_time": "3:03:59", "throughput": 788.02, "total_tokens": 4331024} {"current_steps": 13300, "total_steps": 40000, "loss": 0.1636, "lr": 3.7558336150724865e-05, "epoch": 10.884158821121572, "percentage": 33.25, "elapsed_time": "1:31:37", "remaining_time": "3:03:56", "throughput": 788.06, "total_tokens": 4332576} {"current_steps": 13305, "total_steps": 40000, "loss": 0.1767, "lr": 3.754984626557028e-05, "epoch": 10.888252148997134, "percentage": 33.26, "elapsed_time": "1:31:39", "remaining_time": "3:03:54", "throughput": 788.09, "total_tokens": 4334096} {"current_steps": 13310, "total_steps": 40000, "loss": 0.1694, "lr": 3.754135444507168e-05, "epoch": 10.892345476872698, "percentage": 33.27, "elapsed_time": "1:31:41", "remaining_time": "3:03:51", "throughput": 788.15, "total_tokens": 4335776} {"current_steps": 13315, "total_steps": 40000, "loss": 0.1567, "lr": 3.753286069053863e-05, "epoch": 10.89643880474826, "percentage": 33.29, "elapsed_time": "1:31:42", "remaining_time": "3:03:48", "throughput": 788.23, "total_tokens": 4337568} {"current_steps": 13320, "total_steps": 40000, "loss": 0.2663, "lr": 3.7524365003280945e-05, "epoch": 10.900532132623823, "percentage": 33.3, "elapsed_time": "1:31:44", "remaining_time": "3:03:45", "throughput": 788.28, "total_tokens": 4339184} {"current_steps": 13325, "total_steps": 40000, "loss": 0.1536, "lr": 3.75158673846088e-05, "epoch": 10.904625460499386, "percentage": 33.31, "elapsed_time": "1:31:46", "remaining_time": "3:03:43", "throughput": 788.32, "total_tokens": 4340800} {"current_steps": 13330, "total_steps": 40000, "loss": 0.1262, "lr": 3.750736783583262e-05, "epoch": 10.908718788374948, "percentage": 33.32, "elapsed_time": "1:31:48", "remaining_time": "3:03:40", "throughput": 788.38, "total_tokens": 4342464} {"current_steps": 13335, "total_steps": 40000, "loss": 0.2896, "lr": 3.7498866358263144e-05, "epoch": 10.912812116250512, "percentage": 33.34, "elapsed_time": "1:31:49", "remaining_time": "3:03:37", "throughput": 788.44, "total_tokens": 4344144} {"current_steps": 13340, "total_steps": 40000, "loss": 0.1478, "lr": 3.74903629532114e-05, "epoch": 10.916905444126074, "percentage": 33.35, "elapsed_time": "1:31:51", "remaining_time": "3:03:34", "throughput": 788.49, "total_tokens": 4345792} {"current_steps": 13345, "total_steps": 40000, "loss": 0.2105, "lr": 3.748185762198873e-05, "epoch": 10.920998772001637, "percentage": 33.36, "elapsed_time": "1:31:53", "remaining_time": "3:03:32", "throughput": 788.54, "total_tokens": 4347408} {"current_steps": 13350, "total_steps": 40000, "loss": 0.1263, "lr": 3.747335036590676e-05, "epoch": 10.925092099877201, "percentage": 33.38, "elapsed_time": "1:31:55", "remaining_time": "3:03:29", "throughput": 788.54, "total_tokens": 4349008} {"current_steps": 13355, "total_steps": 40000, "loss": 0.2196, "lr": 3.7464841186277405e-05, "epoch": 10.929185427752763, "percentage": 33.39, "elapsed_time": "1:31:56", "remaining_time": "3:03:27", "throughput": 788.59, "total_tokens": 4350624} {"current_steps": 13360, "total_steps": 40000, "loss": 0.2268, "lr": 3.7456330084412896e-05, "epoch": 10.933278755628326, "percentage": 33.4, "elapsed_time": "1:31:58", "remaining_time": "3:03:24", "throughput": 788.65, "total_tokens": 4352288} {"current_steps": 13365, "total_steps": 40000, "loss": 0.2536, "lr": 3.744781706162576e-05, "epoch": 10.937372083503888, "percentage": 33.41, "elapsed_time": "1:32:00", "remaining_time": "3:03:21", "throughput": 788.7, "total_tokens": 4353952} {"current_steps": 13370, "total_steps": 40000, "loss": 0.1627, "lr": 3.743930211922879e-05, "epoch": 10.941465411379452, "percentage": 33.42, "elapsed_time": "1:32:02", "remaining_time": "3:03:18", "throughput": 788.75, "total_tokens": 4355568} {"current_steps": 13375, "total_steps": 40000, "loss": 0.161, "lr": 3.743078525853513e-05, "epoch": 10.945558739255015, "percentage": 33.44, "elapsed_time": "1:32:03", "remaining_time": "3:03:16", "throughput": 788.82, "total_tokens": 4357280} {"current_steps": 13380, "total_steps": 40000, "loss": 0.1722, "lr": 3.7422266480858154e-05, "epoch": 10.949652067130577, "percentage": 33.45, "elapsed_time": "1:32:05", "remaining_time": "3:03:13", "throughput": 788.86, "total_tokens": 4358880} {"current_steps": 13385, "total_steps": 40000, "loss": 0.1749, "lr": 3.741374578751158e-05, "epoch": 10.95374539500614, "percentage": 33.46, "elapsed_time": "1:32:07", "remaining_time": "3:03:10", "throughput": 788.91, "total_tokens": 4360528} {"current_steps": 13390, "total_steps": 40000, "loss": 0.1861, "lr": 3.740522317980941e-05, "epoch": 10.957838722881704, "percentage": 33.48, "elapsed_time": "1:32:08", "remaining_time": "3:03:07", "throughput": 788.97, "total_tokens": 4362192} {"current_steps": 13395, "total_steps": 40000, "loss": 0.1598, "lr": 3.739669865906593e-05, "epoch": 10.961932050757266, "percentage": 33.49, "elapsed_time": "1:32:10", "remaining_time": "3:03:04", "throughput": 789.02, "total_tokens": 4363824} {"current_steps": 13400, "total_steps": 40000, "loss": 0.1475, "lr": 3.738817222659573e-05, "epoch": 10.966025378632828, "percentage": 33.5, "elapsed_time": "1:32:12", "remaining_time": "3:03:02", "throughput": 789.07, "total_tokens": 4365440} {"current_steps": 13400, "total_steps": 40000, "eval_loss": 0.2011559158563614, "epoch": 10.966025378632828, "percentage": 33.5, "elapsed_time": "1:32:24", "remaining_time": "3:03:26", "throughput": 787.3, "total_tokens": 4365440} {"current_steps": 13405, "total_steps": 40000, "loss": 0.2348, "lr": 3.73796438837137e-05, "epoch": 10.97011870650839, "percentage": 33.51, "elapsed_time": "1:32:28", "remaining_time": "3:03:27", "throughput": 787.15, "total_tokens": 4367120} {"current_steps": 13410, "total_steps": 40000, "loss": 0.1638, "lr": 3.7371113631735e-05, "epoch": 10.974212034383955, "percentage": 33.52, "elapsed_time": "1:32:29", "remaining_time": "3:03:24", "throughput": 787.2, "total_tokens": 4368768} {"current_steps": 13415, "total_steps": 40000, "loss": 0.2296, "lr": 3.736258147197512e-05, "epoch": 10.978305362259517, "percentage": 33.54, "elapsed_time": "1:32:31", "remaining_time": "3:03:21", "throughput": 787.25, "total_tokens": 4370368} {"current_steps": 13420, "total_steps": 40000, "loss": 0.3494, "lr": 3.735404740574981e-05, "epoch": 10.98239869013508, "percentage": 33.55, "elapsed_time": "1:32:33", "remaining_time": "3:03:18", "throughput": 787.3, "total_tokens": 4372000} {"current_steps": 13425, "total_steps": 40000, "loss": 0.1921, "lr": 3.7345511434375145e-05, "epoch": 10.986492018010642, "percentage": 33.56, "elapsed_time": "1:32:34", "remaining_time": "3:03:16", "throughput": 787.34, "total_tokens": 4373616} {"current_steps": 13430, "total_steps": 40000, "loss": 0.1521, "lr": 3.733697355916748e-05, "epoch": 10.990585345886206, "percentage": 33.58, "elapsed_time": "1:32:36", "remaining_time": "3:03:13", "throughput": 787.38, "total_tokens": 4375184} {"current_steps": 13435, "total_steps": 40000, "loss": 0.1944, "lr": 3.732843378144345e-05, "epoch": 10.994678673761769, "percentage": 33.59, "elapsed_time": "1:32:38", "remaining_time": "3:03:10", "throughput": 787.43, "total_tokens": 4376816} {"current_steps": 13440, "total_steps": 40000, "loss": 0.1757, "lr": 3.7319892102519995e-05, "epoch": 10.998772001637331, "percentage": 33.6, "elapsed_time": "1:32:40", "remaining_time": "3:03:07", "throughput": 787.48, "total_tokens": 4378448} {"current_steps": 13445, "total_steps": 40000, "loss": 0.1569, "lr": 3.731134852371436e-05, "epoch": 11.002455996725338, "percentage": 33.61, "elapsed_time": "1:32:41", "remaining_time": "3:03:05", "throughput": 787.46, "total_tokens": 4379832} {"current_steps": 13450, "total_steps": 40000, "loss": 0.225, "lr": 3.730280304634408e-05, "epoch": 11.0065493246009, "percentage": 33.62, "elapsed_time": "1:32:43", "remaining_time": "3:03:02", "throughput": 787.52, "total_tokens": 4381480} {"current_steps": 13455, "total_steps": 40000, "loss": 0.1578, "lr": 3.729425567172696e-05, "epoch": 11.010642652476463, "percentage": 33.64, "elapsed_time": "1:32:45", "remaining_time": "3:02:59", "throughput": 787.57, "total_tokens": 4383112} {"current_steps": 13460, "total_steps": 40000, "loss": 0.1474, "lr": 3.728570640118111e-05, "epoch": 11.014735980352027, "percentage": 33.65, "elapsed_time": "1:32:47", "remaining_time": "3:02:57", "throughput": 787.6, "total_tokens": 4384680} {"current_steps": 13465, "total_steps": 40000, "loss": 0.2126, "lr": 3.727715523602494e-05, "epoch": 11.01882930822759, "percentage": 33.66, "elapsed_time": "1:32:48", "remaining_time": "3:02:54", "throughput": 787.65, "total_tokens": 4386280} {"current_steps": 13470, "total_steps": 40000, "loss": 0.1388, "lr": 3.726860217757715e-05, "epoch": 11.022922636103152, "percentage": 33.67, "elapsed_time": "1:32:50", "remaining_time": "3:02:51", "throughput": 787.72, "total_tokens": 4388040} {"current_steps": 13475, "total_steps": 40000, "loss": 0.1589, "lr": 3.726004722715673e-05, "epoch": 11.027015963978714, "percentage": 33.69, "elapsed_time": "1:32:52", "remaining_time": "3:02:48", "throughput": 787.76, "total_tokens": 4389592} {"current_steps": 13480, "total_steps": 40000, "loss": 0.2393, "lr": 3.725149038608296e-05, "epoch": 11.031109291854278, "percentage": 33.7, "elapsed_time": "1:32:53", "remaining_time": "3:02:46", "throughput": 787.8, "total_tokens": 4391192} {"current_steps": 13485, "total_steps": 40000, "loss": 0.1768, "lr": 3.7242931655675404e-05, "epoch": 11.03520261972984, "percentage": 33.71, "elapsed_time": "1:32:55", "remaining_time": "3:02:43", "throughput": 787.86, "total_tokens": 4392856} {"current_steps": 13490, "total_steps": 40000, "loss": 0.1248, "lr": 3.7234371037253937e-05, "epoch": 11.039295947605403, "percentage": 33.73, "elapsed_time": "1:32:57", "remaining_time": "3:02:40", "throughput": 787.92, "total_tokens": 4394568} {"current_steps": 13495, "total_steps": 40000, "loss": 0.1476, "lr": 3.7225808532138705e-05, "epoch": 11.043389275480965, "percentage": 33.74, "elapsed_time": "1:32:59", "remaining_time": "3:02:37", "throughput": 787.97, "total_tokens": 4396168} {"current_steps": 13500, "total_steps": 40000, "loss": 0.1593, "lr": 3.721724414165016e-05, "epoch": 11.04748260335653, "percentage": 33.75, "elapsed_time": "1:33:00", "remaining_time": "3:02:35", "throughput": 788.01, "total_tokens": 4397752} {"current_steps": 13505, "total_steps": 40000, "loss": 0.2146, "lr": 3.720867786710904e-05, "epoch": 11.051575931232092, "percentage": 33.76, "elapsed_time": "1:33:02", "remaining_time": "3:02:32", "throughput": 788.05, "total_tokens": 4399368} {"current_steps": 13510, "total_steps": 40000, "loss": 0.2781, "lr": 3.7200109709836366e-05, "epoch": 11.055669259107654, "percentage": 33.77, "elapsed_time": "1:33:04", "remaining_time": "3:02:29", "throughput": 788.09, "total_tokens": 4400952} {"current_steps": 13515, "total_steps": 40000, "loss": 0.1917, "lr": 3.7191539671153465e-05, "epoch": 11.059762586983217, "percentage": 33.79, "elapsed_time": "1:33:06", "remaining_time": "3:02:26", "throughput": 788.15, "total_tokens": 4402616} {"current_steps": 13520, "total_steps": 40000, "loss": 0.2117, "lr": 3.718296775238193e-05, "epoch": 11.063855914858781, "percentage": 33.8, "elapsed_time": "1:33:07", "remaining_time": "3:02:24", "throughput": 788.2, "total_tokens": 4404248} {"current_steps": 13525, "total_steps": 40000, "loss": 0.2089, "lr": 3.7174393954843675e-05, "epoch": 11.067949242734343, "percentage": 33.81, "elapsed_time": "1:33:09", "remaining_time": "3:02:21", "throughput": 788.24, "total_tokens": 4405848} {"current_steps": 13530, "total_steps": 40000, "loss": 0.2005, "lr": 3.716581827986087e-05, "epoch": 11.072042570609906, "percentage": 33.83, "elapsed_time": "1:33:11", "remaining_time": "3:02:18", "throughput": 788.3, "total_tokens": 4407512} {"current_steps": 13535, "total_steps": 40000, "loss": 0.2005, "lr": 3.7157240728756004e-05, "epoch": 11.076135898485468, "percentage": 33.84, "elapsed_time": "1:33:12", "remaining_time": "3:02:15", "throughput": 788.35, "total_tokens": 4409128} {"current_steps": 13540, "total_steps": 40000, "loss": 0.1435, "lr": 3.714866130285184e-05, "epoch": 11.080229226361032, "percentage": 33.85, "elapsed_time": "1:33:14", "remaining_time": "3:02:13", "throughput": 788.39, "total_tokens": 4410728} {"current_steps": 13545, "total_steps": 40000, "loss": 0.211, "lr": 3.714008000347143e-05, "epoch": 11.084322554236595, "percentage": 33.86, "elapsed_time": "1:33:16", "remaining_time": "3:02:10", "throughput": 788.44, "total_tokens": 4412392} {"current_steps": 13550, "total_steps": 40000, "loss": 0.1914, "lr": 3.7131496831938126e-05, "epoch": 11.088415882112157, "percentage": 33.88, "elapsed_time": "1:33:18", "remaining_time": "3:02:07", "throughput": 788.51, "total_tokens": 4414120} {"current_steps": 13555, "total_steps": 40000, "loss": 0.1867, "lr": 3.7122911789575565e-05, "epoch": 11.09250920998772, "percentage": 33.89, "elapsed_time": "1:33:19", "remaining_time": "3:02:04", "throughput": 788.57, "total_tokens": 4415816} {"current_steps": 13560, "total_steps": 40000, "loss": 0.2127, "lr": 3.711432487770765e-05, "epoch": 11.096602537863284, "percentage": 33.9, "elapsed_time": "1:33:21", "remaining_time": "3:02:02", "throughput": 788.62, "total_tokens": 4417416} {"current_steps": 13565, "total_steps": 40000, "loss": 0.1548, "lr": 3.710573609765861e-05, "epoch": 11.100695865738846, "percentage": 33.91, "elapsed_time": "1:33:23", "remaining_time": "3:01:59", "throughput": 788.66, "total_tokens": 4419016} {"current_steps": 13570, "total_steps": 40000, "loss": 0.1593, "lr": 3.709714545075292e-05, "epoch": 11.104789193614408, "percentage": 33.92, "elapsed_time": "1:33:24", "remaining_time": "3:01:56", "throughput": 788.71, "total_tokens": 4420648} {"current_steps": 13575, "total_steps": 40000, "loss": 0.1667, "lr": 3.708855293831538e-05, "epoch": 11.10888252148997, "percentage": 33.94, "elapsed_time": "1:33:26", "remaining_time": "3:01:53", "throughput": 788.76, "total_tokens": 4422264} {"current_steps": 13580, "total_steps": 40000, "loss": 0.3284, "lr": 3.707995856167107e-05, "epoch": 11.112975849365535, "percentage": 33.95, "elapsed_time": "1:33:28", "remaining_time": "3:01:51", "throughput": 788.81, "total_tokens": 4423896} {"current_steps": 13585, "total_steps": 40000, "loss": 0.157, "lr": 3.707136232214534e-05, "epoch": 11.117069177241097, "percentage": 33.96, "elapsed_time": "1:33:30", "remaining_time": "3:01:48", "throughput": 788.86, "total_tokens": 4425576} {"current_steps": 13590, "total_steps": 40000, "loss": 0.2013, "lr": 3.7062764221063844e-05, "epoch": 11.12116250511666, "percentage": 33.98, "elapsed_time": "1:33:31", "remaining_time": "3:01:45", "throughput": 788.91, "total_tokens": 4427176} {"current_steps": 13595, "total_steps": 40000, "loss": 0.2257, "lr": 3.705416425975252e-05, "epoch": 11.125255832992222, "percentage": 33.99, "elapsed_time": "1:33:33", "remaining_time": "3:01:42", "throughput": 788.95, "total_tokens": 4428792} {"current_steps": 13600, "total_steps": 40000, "loss": 0.163, "lr": 3.704556243953758e-05, "epoch": 11.129349160867786, "percentage": 34.0, "elapsed_time": "1:33:35", "remaining_time": "3:01:40", "throughput": 789.0, "total_tokens": 4430440} {"current_steps": 13600, "total_steps": 40000, "eval_loss": 0.20043665170669556, "epoch": 11.129349160867786, "percentage": 34.0, "elapsed_time": "1:33:47", "remaining_time": "3:02:04", "throughput": 787.25, "total_tokens": 4430440} {"current_steps": 13605, "total_steps": 40000, "loss": 0.1748, "lr": 3.7036958761745535e-05, "epoch": 11.133442488743349, "percentage": 34.01, "elapsed_time": "1:33:50", "remaining_time": "3:02:04", "throughput": 787.09, "total_tokens": 4432024} {"current_steps": 13610, "total_steps": 40000, "loss": 0.1528, "lr": 3.702835322770318e-05, "epoch": 11.137535816618911, "percentage": 34.02, "elapsed_time": "1:33:52", "remaining_time": "3:02:01", "throughput": 787.14, "total_tokens": 4433672} {"current_steps": 13615, "total_steps": 40000, "loss": 0.2917, "lr": 3.701974583873761e-05, "epoch": 11.141629144494473, "percentage": 34.04, "elapsed_time": "1:33:54", "remaining_time": "3:01:59", "throughput": 787.2, "total_tokens": 4435384} {"current_steps": 13620, "total_steps": 40000, "loss": 0.17, "lr": 3.701113659617618e-05, "epoch": 11.145722472370037, "percentage": 34.05, "elapsed_time": "1:33:56", "remaining_time": "3:01:56", "throughput": 787.25, "total_tokens": 4436968} {"current_steps": 13625, "total_steps": 40000, "loss": 0.2151, "lr": 3.7002525501346535e-05, "epoch": 11.1498158002456, "percentage": 34.06, "elapsed_time": "1:33:57", "remaining_time": "3:01:53", "throughput": 787.3, "total_tokens": 4438616} {"current_steps": 13630, "total_steps": 40000, "loss": 0.2206, "lr": 3.699391255557664e-05, "epoch": 11.153909128121162, "percentage": 34.08, "elapsed_time": "1:33:59", "remaining_time": "3:01:50", "throughput": 787.35, "total_tokens": 4440280} {"current_steps": 13635, "total_steps": 40000, "loss": 0.1201, "lr": 3.69852977601947e-05, "epoch": 11.158002455996725, "percentage": 34.09, "elapsed_time": "1:34:01", "remaining_time": "3:01:48", "throughput": 787.4, "total_tokens": 4441896} {"current_steps": 13640, "total_steps": 40000, "loss": 0.1644, "lr": 3.697668111652922e-05, "epoch": 11.162095783872289, "percentage": 34.1, "elapsed_time": "1:34:02", "remaining_time": "3:01:45", "throughput": 787.45, "total_tokens": 4443512} {"current_steps": 13645, "total_steps": 40000, "loss": 0.1489, "lr": 3.6968062625909005e-05, "epoch": 11.166189111747851, "percentage": 34.11, "elapsed_time": "1:34:04", "remaining_time": "3:01:42", "throughput": 787.5, "total_tokens": 4445144} {"current_steps": 13650, "total_steps": 40000, "loss": 0.1879, "lr": 3.6959442289663135e-05, "epoch": 11.170282439623413, "percentage": 34.12, "elapsed_time": "1:34:06", "remaining_time": "3:01:39", "throughput": 787.54, "total_tokens": 4446744} {"current_steps": 13655, "total_steps": 40000, "loss": 0.2169, "lr": 3.695082010912098e-05, "epoch": 11.174375767498976, "percentage": 34.14, "elapsed_time": "1:34:08", "remaining_time": "3:01:37", "throughput": 787.59, "total_tokens": 4448392} {"current_steps": 13660, "total_steps": 40000, "loss": 0.1704, "lr": 3.694219608561217e-05, "epoch": 11.17846909537454, "percentage": 34.15, "elapsed_time": "1:34:09", "remaining_time": "3:01:34", "throughput": 787.65, "total_tokens": 4450072} {"current_steps": 13665, "total_steps": 40000, "loss": 0.1189, "lr": 3.693357022046665e-05, "epoch": 11.182562423250102, "percentage": 34.16, "elapsed_time": "1:34:11", "remaining_time": "3:01:31", "throughput": 787.69, "total_tokens": 4451656} {"current_steps": 13670, "total_steps": 40000, "loss": 0.1655, "lr": 3.6924942515014644e-05, "epoch": 11.186655751125665, "percentage": 34.17, "elapsed_time": "1:34:13", "remaining_time": "3:01:28", "throughput": 787.75, "total_tokens": 4453336} {"current_steps": 13675, "total_steps": 40000, "loss": 0.1995, "lr": 3.691631297058664e-05, "epoch": 11.190749079001227, "percentage": 34.19, "elapsed_time": "1:34:14", "remaining_time": "3:01:26", "throughput": 787.79, "total_tokens": 4454952} {"current_steps": 13680, "total_steps": 40000, "loss": 0.1583, "lr": 3.6907681588513424e-05, "epoch": 11.194842406876791, "percentage": 34.2, "elapsed_time": "1:34:16", "remaining_time": "3:01:23", "throughput": 787.83, "total_tokens": 4456552} {"current_steps": 13685, "total_steps": 40000, "loss": 0.189, "lr": 3.689904837012606e-05, "epoch": 11.198935734752354, "percentage": 34.21, "elapsed_time": "1:34:18", "remaining_time": "3:01:20", "throughput": 787.87, "total_tokens": 4458120} {"current_steps": 13690, "total_steps": 40000, "loss": 0.1155, "lr": 3.689041331675591e-05, "epoch": 11.203029062627916, "percentage": 34.23, "elapsed_time": "1:34:20", "remaining_time": "3:01:17", "throughput": 787.92, "total_tokens": 4459736} {"current_steps": 13695, "total_steps": 40000, "loss": 0.1844, "lr": 3.688177642973461e-05, "epoch": 11.207122390503478, "percentage": 34.24, "elapsed_time": "1:34:21", "remaining_time": "3:01:15", "throughput": 787.95, "total_tokens": 4461304} {"current_steps": 13700, "total_steps": 40000, "loss": 0.1692, "lr": 3.687313771039406e-05, "epoch": 11.211215718379043, "percentage": 34.25, "elapsed_time": "1:34:23", "remaining_time": "3:01:12", "throughput": 788.01, "total_tokens": 4462952} {"current_steps": 13705, "total_steps": 40000, "loss": 0.258, "lr": 3.686449716006647e-05, "epoch": 11.215309046254605, "percentage": 34.26, "elapsed_time": "1:34:25", "remaining_time": "3:01:09", "throughput": 788.05, "total_tokens": 4464536} {"current_steps": 13710, "total_steps": 40000, "loss": 0.1576, "lr": 3.685585478008432e-05, "epoch": 11.219402374130167, "percentage": 34.27, "elapsed_time": "1:34:27", "remaining_time": "3:01:06", "throughput": 788.11, "total_tokens": 4466232} {"current_steps": 13715, "total_steps": 40000, "loss": 0.1555, "lr": 3.6847210571780364e-05, "epoch": 11.223495702005732, "percentage": 34.29, "elapsed_time": "1:34:28", "remaining_time": "3:01:04", "throughput": 788.15, "total_tokens": 4467816} {"current_steps": 13720, "total_steps": 40000, "loss": 0.1323, "lr": 3.683856453648767e-05, "epoch": 11.227589029881294, "percentage": 34.3, "elapsed_time": "1:34:30", "remaining_time": "3:01:01", "throughput": 788.22, "total_tokens": 4469560} {"current_steps": 13725, "total_steps": 40000, "loss": 0.1372, "lr": 3.682991667553954e-05, "epoch": 11.231682357756856, "percentage": 34.31, "elapsed_time": "1:34:32", "remaining_time": "3:00:58", "throughput": 788.28, "total_tokens": 4471256} {"current_steps": 13730, "total_steps": 40000, "loss": 0.1792, "lr": 3.6821266990269606e-05, "epoch": 11.235775685632419, "percentage": 34.33, "elapsed_time": "1:34:33", "remaining_time": "3:00:56", "throughput": 788.32, "total_tokens": 4472840} {"current_steps": 13735, "total_steps": 40000, "loss": 0.2268, "lr": 3.681261548201174e-05, "epoch": 11.239869013507983, "percentage": 34.34, "elapsed_time": "1:34:35", "remaining_time": "3:00:53", "throughput": 788.37, "total_tokens": 4474472} {"current_steps": 13740, "total_steps": 40000, "loss": 0.2775, "lr": 3.6803962152100125e-05, "epoch": 11.243962341383545, "percentage": 34.35, "elapsed_time": "1:34:37", "remaining_time": "3:00:50", "throughput": 788.42, "total_tokens": 4476104} {"current_steps": 13745, "total_steps": 40000, "loss": 0.2416, "lr": 3.67953070018692e-05, "epoch": 11.248055669259108, "percentage": 34.36, "elapsed_time": "1:34:39", "remaining_time": "3:00:47", "throughput": 788.47, "total_tokens": 4477768} {"current_steps": 13750, "total_steps": 40000, "loss": 0.1703, "lr": 3.678665003265371e-05, "epoch": 11.25214899713467, "percentage": 34.38, "elapsed_time": "1:34:40", "remaining_time": "3:00:45", "throughput": 788.51, "total_tokens": 4479352} {"current_steps": 13755, "total_steps": 40000, "loss": 0.1707, "lr": 3.677799124578867e-05, "epoch": 11.256242325010234, "percentage": 34.39, "elapsed_time": "1:34:42", "remaining_time": "3:00:42", "throughput": 788.55, "total_tokens": 4480952} {"current_steps": 13760, "total_steps": 40000, "loss": 0.1831, "lr": 3.676933064260937e-05, "epoch": 11.260335652885797, "percentage": 34.4, "elapsed_time": "1:34:44", "remaining_time": "3:00:39", "throughput": 788.61, "total_tokens": 4482600} {"current_steps": 13765, "total_steps": 40000, "loss": 0.2465, "lr": 3.6760668224451365e-05, "epoch": 11.264428980761359, "percentage": 34.41, "elapsed_time": "1:34:45", "remaining_time": "3:00:36", "throughput": 788.65, "total_tokens": 4484232} {"current_steps": 13770, "total_steps": 40000, "loss": 0.1595, "lr": 3.675200399265054e-05, "epoch": 11.268522308636921, "percentage": 34.42, "elapsed_time": "1:34:47", "remaining_time": "3:00:34", "throughput": 788.7, "total_tokens": 4485864} {"current_steps": 13775, "total_steps": 40000, "loss": 0.2064, "lr": 3.6743337948543014e-05, "epoch": 11.272615636512485, "percentage": 34.44, "elapsed_time": "1:34:49", "remaining_time": "3:00:31", "throughput": 788.76, "total_tokens": 4487528} {"current_steps": 13780, "total_steps": 40000, "loss": 0.1762, "lr": 3.6734670093465204e-05, "epoch": 11.276708964388048, "percentage": 34.45, "elapsed_time": "1:34:51", "remaining_time": "3:00:28", "throughput": 788.81, "total_tokens": 4489192} {"current_steps": 13785, "total_steps": 40000, "loss": 0.1824, "lr": 3.672600042875379e-05, "epoch": 11.28080229226361, "percentage": 34.46, "elapsed_time": "1:34:52", "remaining_time": "3:00:26", "throughput": 788.87, "total_tokens": 4490856} {"current_steps": 13790, "total_steps": 40000, "loss": 0.2057, "lr": 3.671732895574575e-05, "epoch": 11.284895620139173, "percentage": 34.48, "elapsed_time": "1:34:54", "remaining_time": "3:00:23", "throughput": 788.93, "total_tokens": 4492552} {"current_steps": 13795, "total_steps": 40000, "loss": 0.2123, "lr": 3.670865567577834e-05, "epoch": 11.288988948014737, "percentage": 34.49, "elapsed_time": "1:34:56", "remaining_time": "3:00:20", "throughput": 788.97, "total_tokens": 4494136} {"current_steps": 13800, "total_steps": 40000, "loss": 0.2207, "lr": 3.669998059018909e-05, "epoch": 11.2930822758903, "percentage": 34.5, "elapsed_time": "1:34:57", "remaining_time": "3:00:17", "throughput": 789.02, "total_tokens": 4495784} {"current_steps": 13800, "total_steps": 40000, "eval_loss": 0.20311228930950165, "epoch": 11.2930822758903, "percentage": 34.5, "elapsed_time": "1:35:10", "remaining_time": "3:00:41", "throughput": 787.3, "total_tokens": 4495784} {"current_steps": 13805, "total_steps": 40000, "loss": 0.1789, "lr": 3.6691303700315796e-05, "epoch": 11.297175603765861, "percentage": 34.51, "elapsed_time": "1:35:13", "remaining_time": "3:00:41", "throughput": 787.16, "total_tokens": 4497480} {"current_steps": 13810, "total_steps": 40000, "loss": 0.2345, "lr": 3.668262500749655e-05, "epoch": 11.301268931641424, "percentage": 34.52, "elapsed_time": "1:35:15", "remaining_time": "3:00:38", "throughput": 787.21, "total_tokens": 4499144} {"current_steps": 13815, "total_steps": 40000, "loss": 0.1623, "lr": 3.667394451306971e-05, "epoch": 11.305362259516988, "percentage": 34.54, "elapsed_time": "1:35:16", "remaining_time": "3:00:36", "throughput": 787.27, "total_tokens": 4500808} {"current_steps": 13820, "total_steps": 40000, "loss": 0.2219, "lr": 3.666526221837393e-05, "epoch": 11.30945558739255, "percentage": 34.55, "elapsed_time": "1:35:18", "remaining_time": "3:00:33", "throughput": 787.31, "total_tokens": 4502424} {"current_steps": 13825, "total_steps": 40000, "loss": 0.1682, "lr": 3.665657812474812e-05, "epoch": 11.313548915268113, "percentage": 34.56, "elapsed_time": "1:35:20", "remaining_time": "3:00:30", "throughput": 787.37, "total_tokens": 4504088} {"current_steps": 13830, "total_steps": 40000, "loss": 0.2184, "lr": 3.664789223353147e-05, "epoch": 11.317642243143675, "percentage": 34.58, "elapsed_time": "1:35:22", "remaining_time": "3:00:27", "throughput": 787.43, "total_tokens": 4505784} {"current_steps": 13835, "total_steps": 40000, "loss": 0.1869, "lr": 3.663920454606347e-05, "epoch": 11.32173557101924, "percentage": 34.59, "elapsed_time": "1:35:23", "remaining_time": "3:00:25", "throughput": 787.47, "total_tokens": 4507384} {"current_steps": 13840, "total_steps": 40000, "loss": 0.1356, "lr": 3.6630515063683856e-05, "epoch": 11.325828898894802, "percentage": 34.6, "elapsed_time": "1:35:25", "remaining_time": "3:00:22", "throughput": 787.51, "total_tokens": 4508984} {"current_steps": 13845, "total_steps": 40000, "loss": 0.1758, "lr": 3.662182378773267e-05, "epoch": 11.329922226770364, "percentage": 34.61, "elapsed_time": "1:35:27", "remaining_time": "3:00:19", "throughput": 787.56, "total_tokens": 4510600} {"current_steps": 13850, "total_steps": 40000, "loss": 0.1814, "lr": 3.66131307195502e-05, "epoch": 11.334015554645926, "percentage": 34.62, "elapsed_time": "1:35:29", "remaining_time": "3:00:16", "throughput": 787.61, "total_tokens": 4512216} {"current_steps": 13855, "total_steps": 40000, "loss": 0.1563, "lr": 3.6604435860477034e-05, "epoch": 11.33810888252149, "percentage": 34.64, "elapsed_time": "1:35:30", "remaining_time": "3:00:14", "throughput": 787.65, "total_tokens": 4513848} {"current_steps": 13860, "total_steps": 40000, "loss": 0.1817, "lr": 3.6595739211854025e-05, "epoch": 11.342202210397053, "percentage": 34.65, "elapsed_time": "1:35:32", "remaining_time": "3:00:11", "throughput": 787.7, "total_tokens": 4515464} {"current_steps": 13865, "total_steps": 40000, "loss": 0.1523, "lr": 3.658704077502231e-05, "epoch": 11.346295538272615, "percentage": 34.66, "elapsed_time": "1:35:34", "remaining_time": "3:00:08", "throughput": 787.74, "total_tokens": 4517048} {"current_steps": 13870, "total_steps": 40000, "loss": 0.1667, "lr": 3.65783405513233e-05, "epoch": 11.350388866148178, "percentage": 34.67, "elapsed_time": "1:35:35", "remaining_time": "3:00:05", "throughput": 787.79, "total_tokens": 4518712} {"current_steps": 13875, "total_steps": 40000, "loss": 0.2153, "lr": 3.656963854209867e-05, "epoch": 11.354482194023742, "percentage": 34.69, "elapsed_time": "1:35:37", "remaining_time": "3:00:03", "throughput": 787.84, "total_tokens": 4520312} {"current_steps": 13880, "total_steps": 40000, "loss": 0.1848, "lr": 3.656093474869038e-05, "epoch": 11.358575521899304, "percentage": 34.7, "elapsed_time": "1:35:39", "remaining_time": "3:00:00", "throughput": 787.88, "total_tokens": 4521944} {"current_steps": 13885, "total_steps": 40000, "loss": 0.2311, "lr": 3.655222917244068e-05, "epoch": 11.362668849774867, "percentage": 34.71, "elapsed_time": "1:35:41", "remaining_time": "2:59:57", "throughput": 787.94, "total_tokens": 4523592} {"current_steps": 13890, "total_steps": 40000, "loss": 0.192, "lr": 3.6543521814692054e-05, "epoch": 11.366762177650429, "percentage": 34.73, "elapsed_time": "1:35:42", "remaining_time": "2:59:55", "throughput": 787.98, "total_tokens": 4525208} {"current_steps": 13895, "total_steps": 40000, "loss": 0.204, "lr": 3.653481267678731e-05, "epoch": 11.370855505525993, "percentage": 34.74, "elapsed_time": "1:35:44", "remaining_time": "2:59:52", "throughput": 788.04, "total_tokens": 4526888} {"current_steps": 13900, "total_steps": 40000, "loss": 0.2242, "lr": 3.652610176006949e-05, "epoch": 11.374948833401556, "percentage": 34.75, "elapsed_time": "1:35:46", "remaining_time": "2:59:49", "throughput": 788.08, "total_tokens": 4528472} {"current_steps": 13905, "total_steps": 40000, "loss": 0.2447, "lr": 3.6517389065881925e-05, "epoch": 11.379042161277118, "percentage": 34.76, "elapsed_time": "1:35:47", "remaining_time": "2:59:46", "throughput": 788.11, "total_tokens": 4530040} {"current_steps": 13910, "total_steps": 40000, "loss": 0.0914, "lr": 3.650867459556824e-05, "epoch": 11.38313548915268, "percentage": 34.77, "elapsed_time": "1:35:49", "remaining_time": "2:59:44", "throughput": 788.15, "total_tokens": 4531624} {"current_steps": 13915, "total_steps": 40000, "loss": 0.2113, "lr": 3.64999583504723e-05, "epoch": 11.387228817028245, "percentage": 34.79, "elapsed_time": "1:35:51", "remaining_time": "2:59:41", "throughput": 788.2, "total_tokens": 4533224} {"current_steps": 13920, "total_steps": 40000, "loss": 0.1991, "lr": 3.649124033193827e-05, "epoch": 11.391322144903807, "percentage": 34.8, "elapsed_time": "1:35:53", "remaining_time": "2:59:38", "throughput": 788.25, "total_tokens": 4534904} {"current_steps": 13925, "total_steps": 40000, "loss": 0.169, "lr": 3.648252054131057e-05, "epoch": 11.39541547277937, "percentage": 34.81, "elapsed_time": "1:35:54", "remaining_time": "2:59:36", "throughput": 788.3, "total_tokens": 4536536} {"current_steps": 13930, "total_steps": 40000, "loss": 0.1773, "lr": 3.647379897993391e-05, "epoch": 11.399508800654932, "percentage": 34.83, "elapsed_time": "1:35:56", "remaining_time": "2:59:33", "throughput": 788.35, "total_tokens": 4538168} {"current_steps": 13935, "total_steps": 40000, "loss": 0.2093, "lr": 3.646507564915325e-05, "epoch": 11.403602128530496, "percentage": 34.84, "elapsed_time": "1:35:58", "remaining_time": "2:59:30", "throughput": 788.4, "total_tokens": 4539784} {"current_steps": 13940, "total_steps": 40000, "loss": 0.1701, "lr": 3.645635055031385e-05, "epoch": 11.407695456406058, "percentage": 34.85, "elapsed_time": "1:35:59", "remaining_time": "2:59:27", "throughput": 788.44, "total_tokens": 4541400} {"current_steps": 13945, "total_steps": 40000, "loss": 0.2031, "lr": 3.6447623684761224e-05, "epoch": 11.41178878428162, "percentage": 34.86, "elapsed_time": "1:36:01", "remaining_time": "2:59:25", "throughput": 788.48, "total_tokens": 4543000} {"current_steps": 13950, "total_steps": 40000, "loss": 0.1518, "lr": 3.643889505384117e-05, "epoch": 11.415882112157183, "percentage": 34.88, "elapsed_time": "1:36:03", "remaining_time": "2:59:22", "throughput": 788.53, "total_tokens": 4544632} {"current_steps": 13955, "total_steps": 40000, "loss": 0.1547, "lr": 3.6430164658899744e-05, "epoch": 11.419975440032747, "percentage": 34.89, "elapsed_time": "1:36:05", "remaining_time": "2:59:19", "throughput": 788.57, "total_tokens": 4546216} {"current_steps": 13960, "total_steps": 40000, "loss": 0.168, "lr": 3.642143250128329e-05, "epoch": 11.42406876790831, "percentage": 34.9, "elapsed_time": "1:36:06", "remaining_time": "2:59:17", "throughput": 788.61, "total_tokens": 4547832} {"current_steps": 13965, "total_steps": 40000, "loss": 0.1359, "lr": 3.641269858233841e-05, "epoch": 11.428162095783872, "percentage": 34.91, "elapsed_time": "1:36:08", "remaining_time": "2:59:14", "throughput": 788.66, "total_tokens": 4549448} {"current_steps": 13970, "total_steps": 40000, "loss": 0.1472, "lr": 3.640396290341199e-05, "epoch": 11.432255423659434, "percentage": 34.92, "elapsed_time": "1:36:10", "remaining_time": "2:59:11", "throughput": 788.7, "total_tokens": 4551048} {"current_steps": 13975, "total_steps": 40000, "loss": 0.2273, "lr": 3.639522546585118e-05, "epoch": 11.436348751534998, "percentage": 34.94, "elapsed_time": "1:36:12", "remaining_time": "2:59:08", "throughput": 788.75, "total_tokens": 4552664} {"current_steps": 13980, "total_steps": 40000, "loss": 0.1695, "lr": 3.6386486271003404e-05, "epoch": 11.44044207941056, "percentage": 34.95, "elapsed_time": "1:36:13", "remaining_time": "2:59:06", "throughput": 788.79, "total_tokens": 4554264} {"current_steps": 13985, "total_steps": 40000, "loss": 0.1607, "lr": 3.6377745320216346e-05, "epoch": 11.444535407286123, "percentage": 34.96, "elapsed_time": "1:36:15", "remaining_time": "2:59:03", "throughput": 788.84, "total_tokens": 4555912} {"current_steps": 13990, "total_steps": 40000, "loss": 0.2445, "lr": 3.636900261483798e-05, "epoch": 11.448628735161687, "percentage": 34.98, "elapsed_time": "1:36:17", "remaining_time": "2:59:00", "throughput": 788.9, "total_tokens": 4557592} {"current_steps": 13995, "total_steps": 40000, "loss": 0.1841, "lr": 3.636025815621654e-05, "epoch": 11.45272206303725, "percentage": 34.99, "elapsed_time": "1:36:18", "remaining_time": "2:58:58", "throughput": 788.94, "total_tokens": 4559176} {"current_steps": 14000, "total_steps": 40000, "loss": 0.1531, "lr": 3.635151194570054e-05, "epoch": 11.456815390912812, "percentage": 35.0, "elapsed_time": "1:36:20", "remaining_time": "2:58:55", "throughput": 788.98, "total_tokens": 4560792} {"current_steps": 14000, "total_steps": 40000, "eval_loss": 0.2057567834854126, "epoch": 11.456815390912812, "percentage": 35.0, "elapsed_time": "1:36:33", "remaining_time": "2:59:18", "throughput": 787.28, "total_tokens": 4560792} {"current_steps": 14005, "total_steps": 40000, "loss": 0.2343, "lr": 3.634276398463873e-05, "epoch": 11.460908718788374, "percentage": 35.01, "elapsed_time": "1:36:36", "remaining_time": "2:59:18", "throughput": 787.11, "total_tokens": 4562440} {"current_steps": 14010, "total_steps": 40000, "loss": 0.1736, "lr": 3.633401427438018e-05, "epoch": 11.465002046663939, "percentage": 35.02, "elapsed_time": "1:36:38", "remaining_time": "2:59:16", "throughput": 787.15, "total_tokens": 4564072} {"current_steps": 14015, "total_steps": 40000, "loss": 0.1836, "lr": 3.63252628162742e-05, "epoch": 11.469095374539501, "percentage": 35.04, "elapsed_time": "1:36:39", "remaining_time": "2:59:13", "throughput": 787.2, "total_tokens": 4565688} {"current_steps": 14020, "total_steps": 40000, "loss": 0.1418, "lr": 3.6316509611670364e-05, "epoch": 11.473188702415063, "percentage": 35.05, "elapsed_time": "1:36:41", "remaining_time": "2:59:10", "throughput": 787.24, "total_tokens": 4567256} {"current_steps": 14025, "total_steps": 40000, "loss": 0.1431, "lr": 3.630775466191854e-05, "epoch": 11.477282030290626, "percentage": 35.06, "elapsed_time": "1:36:43", "remaining_time": "2:59:08", "throughput": 787.28, "total_tokens": 4568856} {"current_steps": 14030, "total_steps": 40000, "loss": 0.2041, "lr": 3.629899796836884e-05, "epoch": 11.48137535816619, "percentage": 35.08, "elapsed_time": "1:36:45", "remaining_time": "2:59:05", "throughput": 787.32, "total_tokens": 4570472} {"current_steps": 14035, "total_steps": 40000, "loss": 0.1927, "lr": 3.6290239532371666e-05, "epoch": 11.485468686041752, "percentage": 35.09, "elapsed_time": "1:36:46", "remaining_time": "2:59:02", "throughput": 787.37, "total_tokens": 4572120} {"current_steps": 14040, "total_steps": 40000, "loss": 0.2, "lr": 3.628147935527767e-05, "epoch": 11.489562013917315, "percentage": 35.1, "elapsed_time": "1:36:48", "remaining_time": "2:58:59", "throughput": 787.41, "total_tokens": 4573704} {"current_steps": 14045, "total_steps": 40000, "loss": 0.1647, "lr": 3.627271743843779e-05, "epoch": 11.493655341792877, "percentage": 35.11, "elapsed_time": "1:36:50", "remaining_time": "2:58:57", "throughput": 787.46, "total_tokens": 4575304} {"current_steps": 14050, "total_steps": 40000, "loss": 0.175, "lr": 3.626395378320321e-05, "epoch": 11.497748669668441, "percentage": 35.12, "elapsed_time": "1:36:51", "remaining_time": "2:58:54", "throughput": 787.5, "total_tokens": 4576888} {"current_steps": 14055, "total_steps": 40000, "loss": 0.1865, "lr": 3.625518839092541e-05, "epoch": 11.501841997544004, "percentage": 35.14, "elapsed_time": "1:36:53", "remaining_time": "2:58:51", "throughput": 787.54, "total_tokens": 4578504} {"current_steps": 14060, "total_steps": 40000, "loss": 0.2292, "lr": 3.624642126295612e-05, "epoch": 11.505935325419566, "percentage": 35.15, "elapsed_time": "1:36:55", "remaining_time": "2:58:49", "throughput": 787.58, "total_tokens": 4580104} {"current_steps": 14065, "total_steps": 40000, "loss": 0.2218, "lr": 3.6237652400647345e-05, "epoch": 11.510028653295128, "percentage": 35.16, "elapsed_time": "1:36:57", "remaining_time": "2:58:46", "throughput": 787.62, "total_tokens": 4581640} {"current_steps": 14070, "total_steps": 40000, "loss": 0.2473, "lr": 3.622888180535134e-05, "epoch": 11.514121981170693, "percentage": 35.17, "elapsed_time": "1:36:58", "remaining_time": "2:58:43", "throughput": 787.67, "total_tokens": 4583304} {"current_steps": 14075, "total_steps": 40000, "loss": 0.1665, "lr": 3.6220109478420655e-05, "epoch": 11.518215309046255, "percentage": 35.19, "elapsed_time": "1:37:00", "remaining_time": "2:58:40", "throughput": 787.71, "total_tokens": 4584904} {"current_steps": 14080, "total_steps": 40000, "loss": 0.2022, "lr": 3.6211335421208084e-05, "epoch": 11.522308636921817, "percentage": 35.2, "elapsed_time": "1:37:02", "remaining_time": "2:58:38", "throughput": 787.76, "total_tokens": 4586552} {"current_steps": 14085, "total_steps": 40000, "loss": 0.1238, "lr": 3.62025596350667e-05, "epoch": 11.52640196479738, "percentage": 35.21, "elapsed_time": "1:37:03", "remaining_time": "2:58:35", "throughput": 787.8, "total_tokens": 4588136} {"current_steps": 14090, "total_steps": 40000, "loss": 0.1814, "lr": 3.619378212134984e-05, "epoch": 11.530495292672944, "percentage": 35.23, "elapsed_time": "1:37:05", "remaining_time": "2:58:32", "throughput": 787.85, "total_tokens": 4589784} {"current_steps": 14095, "total_steps": 40000, "loss": 0.198, "lr": 3.618500288141111e-05, "epoch": 11.534588620548506, "percentage": 35.24, "elapsed_time": "1:37:07", "remaining_time": "2:58:30", "throughput": 787.9, "total_tokens": 4591400} {"current_steps": 14100, "total_steps": 40000, "loss": 0.1745, "lr": 3.617622191660438e-05, "epoch": 11.538681948424069, "percentage": 35.25, "elapsed_time": "1:37:09", "remaining_time": "2:58:27", "throughput": 787.95, "total_tokens": 4593064} {"current_steps": 14105, "total_steps": 40000, "loss": 0.2021, "lr": 3.616743922828377e-05, "epoch": 11.542775276299631, "percentage": 35.26, "elapsed_time": "1:37:10", "remaining_time": "2:58:24", "throughput": 787.99, "total_tokens": 4594680} {"current_steps": 14110, "total_steps": 40000, "loss": 0.1536, "lr": 3.615865481780371e-05, "epoch": 11.546868604175195, "percentage": 35.27, "elapsed_time": "1:37:12", "remaining_time": "2:58:22", "throughput": 788.04, "total_tokens": 4596280} {"current_steps": 14115, "total_steps": 40000, "loss": 0.215, "lr": 3.614986868651883e-05, "epoch": 11.550961932050757, "percentage": 35.29, "elapsed_time": "1:37:14", "remaining_time": "2:58:19", "throughput": 788.09, "total_tokens": 4597944} {"current_steps": 14120, "total_steps": 40000, "loss": 0.1536, "lr": 3.614108083578409e-05, "epoch": 11.55505525992632, "percentage": 35.3, "elapsed_time": "1:37:16", "remaining_time": "2:58:16", "throughput": 788.14, "total_tokens": 4599592} {"current_steps": 14125, "total_steps": 40000, "loss": 0.2101, "lr": 3.613229126695467e-05, "epoch": 11.559148587801882, "percentage": 35.31, "elapsed_time": "1:37:17", "remaining_time": "2:58:13", "throughput": 788.19, "total_tokens": 4601240} {"current_steps": 14130, "total_steps": 40000, "loss": 0.1365, "lr": 3.612349998138605e-05, "epoch": 11.563241915677446, "percentage": 35.33, "elapsed_time": "1:37:19", "remaining_time": "2:58:11", "throughput": 788.23, "total_tokens": 4602824} {"current_steps": 14135, "total_steps": 40000, "loss": 0.2033, "lr": 3.6114706980433946e-05, "epoch": 11.567335243553009, "percentage": 35.34, "elapsed_time": "1:37:21", "remaining_time": "2:58:08", "throughput": 788.28, "total_tokens": 4604472} {"current_steps": 14140, "total_steps": 40000, "loss": 0.2222, "lr": 3.610591226545435e-05, "epoch": 11.571428571428571, "percentage": 35.35, "elapsed_time": "1:37:22", "remaining_time": "2:58:05", "throughput": 788.33, "total_tokens": 4606136} {"current_steps": 14145, "total_steps": 40000, "loss": 0.1844, "lr": 3.6097115837803505e-05, "epoch": 11.575521899304134, "percentage": 35.36, "elapsed_time": "1:37:24", "remaining_time": "2:58:03", "throughput": 788.37, "total_tokens": 4607736} {"current_steps": 14150, "total_steps": 40000, "loss": 0.1932, "lr": 3.608831769883795e-05, "epoch": 11.579615227179698, "percentage": 35.38, "elapsed_time": "1:37:26", "remaining_time": "2:58:00", "throughput": 788.42, "total_tokens": 4609368} {"current_steps": 14155, "total_steps": 40000, "loss": 0.2462, "lr": 3.607951784991446e-05, "epoch": 11.58370855505526, "percentage": 35.39, "elapsed_time": "1:37:28", "remaining_time": "2:57:57", "throughput": 788.47, "total_tokens": 4611016} {"current_steps": 14160, "total_steps": 40000, "loss": 0.2101, "lr": 3.6070716292390085e-05, "epoch": 11.587801882930822, "percentage": 35.4, "elapsed_time": "1:37:29", "remaining_time": "2:57:54", "throughput": 788.52, "total_tokens": 4612632} {"current_steps": 14165, "total_steps": 40000, "loss": 0.2439, "lr": 3.606191302762213e-05, "epoch": 11.591895210806385, "percentage": 35.41, "elapsed_time": "1:37:31", "remaining_time": "2:57:52", "throughput": 788.58, "total_tokens": 4614360} {"current_steps": 14170, "total_steps": 40000, "loss": 0.1367, "lr": 3.605310805696818e-05, "epoch": 11.595988538681949, "percentage": 35.43, "elapsed_time": "1:37:33", "remaining_time": "2:57:49", "throughput": 788.63, "total_tokens": 4616008} {"current_steps": 14175, "total_steps": 40000, "loss": 0.1639, "lr": 3.6044301381786067e-05, "epoch": 11.600081866557511, "percentage": 35.44, "elapsed_time": "1:37:34", "remaining_time": "2:57:46", "throughput": 788.68, "total_tokens": 4617640} {"current_steps": 14180, "total_steps": 40000, "loss": 0.2359, "lr": 3.6035493003433883e-05, "epoch": 11.604175194433074, "percentage": 35.45, "elapsed_time": "1:37:36", "remaining_time": "2:57:44", "throughput": 788.72, "total_tokens": 4619256} {"current_steps": 14185, "total_steps": 40000, "loss": 0.1743, "lr": 3.6026682923269994e-05, "epoch": 11.608268522308636, "percentage": 35.46, "elapsed_time": "1:37:38", "remaining_time": "2:57:41", "throughput": 788.77, "total_tokens": 4620856} {"current_steps": 14190, "total_steps": 40000, "loss": 0.2585, "lr": 3.6017871142653034e-05, "epoch": 11.6123618501842, "percentage": 35.48, "elapsed_time": "1:37:40", "remaining_time": "2:57:38", "throughput": 788.82, "total_tokens": 4622504} {"current_steps": 14195, "total_steps": 40000, "loss": 0.177, "lr": 3.600905766294189e-05, "epoch": 11.616455178059763, "percentage": 35.49, "elapsed_time": "1:37:41", "remaining_time": "2:57:36", "throughput": 788.86, "total_tokens": 4624088} {"current_steps": 14200, "total_steps": 40000, "loss": 0.2296, "lr": 3.60002424854957e-05, "epoch": 11.620548505935325, "percentage": 35.5, "elapsed_time": "1:37:43", "remaining_time": "2:57:33", "throughput": 788.9, "total_tokens": 4625720} {"current_steps": 14200, "total_steps": 40000, "eval_loss": 0.20331040024757385, "epoch": 11.620548505935325, "percentage": 35.5, "elapsed_time": "1:37:55", "remaining_time": "2:57:55", "throughput": 787.24, "total_tokens": 4625720} {"current_steps": 14205, "total_steps": 40000, "loss": 0.2367, "lr": 3.5991425611673876e-05, "epoch": 11.624641833810887, "percentage": 35.51, "elapsed_time": "1:37:59", "remaining_time": "2:57:55", "throughput": 787.1, "total_tokens": 4627400} {"current_steps": 14210, "total_steps": 40000, "loss": 0.2037, "lr": 3.5982607042836105e-05, "epoch": 11.628735161686452, "percentage": 35.52, "elapsed_time": "1:38:00", "remaining_time": "2:57:53", "throughput": 787.14, "total_tokens": 4628984} {"current_steps": 14215, "total_steps": 40000, "loss": 0.1822, "lr": 3.597378678034231e-05, "epoch": 11.632828489562014, "percentage": 35.54, "elapsed_time": "1:38:02", "remaining_time": "2:57:50", "throughput": 787.18, "total_tokens": 4630616} {"current_steps": 14220, "total_steps": 40000, "loss": 0.1584, "lr": 3.596496482555269e-05, "epoch": 11.636921817437576, "percentage": 35.55, "elapsed_time": "1:38:04", "remaining_time": "2:57:47", "throughput": 787.23, "total_tokens": 4632232} {"current_steps": 14225, "total_steps": 40000, "loss": 0.1629, "lr": 3.595614117982769e-05, "epoch": 11.64101514531314, "percentage": 35.56, "elapsed_time": "1:38:05", "remaining_time": "2:57:45", "throughput": 787.27, "total_tokens": 4633832} {"current_steps": 14230, "total_steps": 40000, "loss": 0.1947, "lr": 3.594731584452805e-05, "epoch": 11.645108473188703, "percentage": 35.58, "elapsed_time": "1:38:07", "remaining_time": "2:57:42", "throughput": 787.33, "total_tokens": 4635512} {"current_steps": 14235, "total_steps": 40000, "loss": 0.1916, "lr": 3.593848882101472e-05, "epoch": 11.649201801064265, "percentage": 35.59, "elapsed_time": "1:38:09", "remaining_time": "2:57:39", "throughput": 787.38, "total_tokens": 4637176} {"current_steps": 14240, "total_steps": 40000, "loss": 0.2084, "lr": 3.592966011064896e-05, "epoch": 11.653295128939828, "percentage": 35.6, "elapsed_time": "1:38:11", "remaining_time": "2:57:36", "throughput": 787.43, "total_tokens": 4638840} {"current_steps": 14245, "total_steps": 40000, "loss": 0.184, "lr": 3.592082971479226e-05, "epoch": 11.65738845681539, "percentage": 35.61, "elapsed_time": "1:38:12", "remaining_time": "2:57:34", "throughput": 787.49, "total_tokens": 4640488} {"current_steps": 14250, "total_steps": 40000, "loss": 0.2303, "lr": 3.5911997634806385e-05, "epoch": 11.661481784690954, "percentage": 35.62, "elapsed_time": "1:38:14", "remaining_time": "2:57:31", "throughput": 787.54, "total_tokens": 4642152} {"current_steps": 14255, "total_steps": 40000, "loss": 0.1748, "lr": 3.5903163872053336e-05, "epoch": 11.665575112566517, "percentage": 35.64, "elapsed_time": "1:38:16", "remaining_time": "2:57:28", "throughput": 787.58, "total_tokens": 4643768} {"current_steps": 14260, "total_steps": 40000, "loss": 0.2346, "lr": 3.58943284278954e-05, "epoch": 11.669668440442079, "percentage": 35.65, "elapsed_time": "1:38:17", "remaining_time": "2:57:26", "throughput": 787.64, "total_tokens": 4645464} {"current_steps": 14265, "total_steps": 40000, "loss": 0.1353, "lr": 3.588549130369512e-05, "epoch": 11.673761768317643, "percentage": 35.66, "elapsed_time": "1:38:19", "remaining_time": "2:57:23", "throughput": 787.68, "total_tokens": 4647032} {"current_steps": 14270, "total_steps": 40000, "loss": 0.1516, "lr": 3.5876652500815274e-05, "epoch": 11.677855096193205, "percentage": 35.68, "elapsed_time": "1:38:21", "remaining_time": "2:57:20", "throughput": 787.73, "total_tokens": 4648712} {"current_steps": 14275, "total_steps": 40000, "loss": 0.1382, "lr": 3.586781202061894e-05, "epoch": 11.681948424068768, "percentage": 35.69, "elapsed_time": "1:38:23", "remaining_time": "2:57:17", "throughput": 787.77, "total_tokens": 4650312} {"current_steps": 14280, "total_steps": 40000, "loss": 0.1846, "lr": 3.585896986446942e-05, "epoch": 11.68604175194433, "percentage": 35.7, "elapsed_time": "1:38:24", "remaining_time": "2:57:15", "throughput": 787.82, "total_tokens": 4651912} {"current_steps": 14285, "total_steps": 40000, "loss": 0.1841, "lr": 3.585012603373028e-05, "epoch": 11.690135079819893, "percentage": 35.71, "elapsed_time": "1:38:26", "remaining_time": "2:57:12", "throughput": 787.86, "total_tokens": 4653560} {"current_steps": 14290, "total_steps": 40000, "loss": 0.2285, "lr": 3.584128052976535e-05, "epoch": 11.694228407695457, "percentage": 35.73, "elapsed_time": "1:38:28", "remaining_time": "2:57:09", "throughput": 787.91, "total_tokens": 4655192} {"current_steps": 14295, "total_steps": 40000, "loss": 0.1733, "lr": 3.5832433353938724e-05, "epoch": 11.69832173557102, "percentage": 35.74, "elapsed_time": "1:38:29", "remaining_time": "2:57:07", "throughput": 787.94, "total_tokens": 4656744} {"current_steps": 14300, "total_steps": 40000, "loss": 0.2234, "lr": 3.5823584507614746e-05, "epoch": 11.702415063446582, "percentage": 35.75, "elapsed_time": "1:38:31", "remaining_time": "2:57:04", "throughput": 787.98, "total_tokens": 4658328} {"current_steps": 14305, "total_steps": 40000, "loss": 0.139, "lr": 3.581473399215802e-05, "epoch": 11.706508391322146, "percentage": 35.76, "elapsed_time": "1:38:33", "remaining_time": "2:57:01", "throughput": 788.02, "total_tokens": 4659912} {"current_steps": 14310, "total_steps": 40000, "loss": 0.2334, "lr": 3.580588180893341e-05, "epoch": 11.710601719197708, "percentage": 35.77, "elapsed_time": "1:38:35", "remaining_time": "2:56:59", "throughput": 788.07, "total_tokens": 4661544} {"current_steps": 14315, "total_steps": 40000, "loss": 0.1883, "lr": 3.579702795930602e-05, "epoch": 11.71469504707327, "percentage": 35.79, "elapsed_time": "1:38:36", "remaining_time": "2:56:56", "throughput": 788.11, "total_tokens": 4663144} {"current_steps": 14320, "total_steps": 40000, "loss": 0.2161, "lr": 3.578817244464125e-05, "epoch": 11.718788374948833, "percentage": 35.8, "elapsed_time": "1:38:38", "remaining_time": "2:56:53", "throughput": 788.16, "total_tokens": 4664760} {"current_steps": 14325, "total_steps": 40000, "loss": 0.2254, "lr": 3.577931526630471e-05, "epoch": 11.722881702824397, "percentage": 35.81, "elapsed_time": "1:38:40", "remaining_time": "2:56:51", "throughput": 788.2, "total_tokens": 4666376} {"current_steps": 14330, "total_steps": 40000, "loss": 0.1639, "lr": 3.577045642566229e-05, "epoch": 11.72697503069996, "percentage": 35.83, "elapsed_time": "1:38:42", "remaining_time": "2:56:48", "throughput": 788.25, "total_tokens": 4668008} {"current_steps": 14335, "total_steps": 40000, "loss": 0.1783, "lr": 3.576159592408014e-05, "epoch": 11.731068358575522, "percentage": 35.84, "elapsed_time": "1:38:43", "remaining_time": "2:56:45", "throughput": 788.29, "total_tokens": 4669592} {"current_steps": 14340, "total_steps": 40000, "loss": 0.2348, "lr": 3.575273376292466e-05, "epoch": 11.735161686451084, "percentage": 35.85, "elapsed_time": "1:38:45", "remaining_time": "2:56:42", "throughput": 788.32, "total_tokens": 4671176} {"current_steps": 14345, "total_steps": 40000, "loss": 0.2196, "lr": 3.574386994356251e-05, "epoch": 11.739255014326648, "percentage": 35.86, "elapsed_time": "1:38:47", "remaining_time": "2:56:40", "throughput": 788.37, "total_tokens": 4672808} {"current_steps": 14350, "total_steps": 40000, "loss": 0.1768, "lr": 3.573500446736059e-05, "epoch": 11.74334834220221, "percentage": 35.88, "elapsed_time": "1:38:48", "remaining_time": "2:56:37", "throughput": 788.43, "total_tokens": 4674504} {"current_steps": 14355, "total_steps": 40000, "loss": 0.2427, "lr": 3.5726137335686094e-05, "epoch": 11.747441670077773, "percentage": 35.89, "elapsed_time": "1:38:50", "remaining_time": "2:56:34", "throughput": 788.46, "total_tokens": 4676024} {"current_steps": 14360, "total_steps": 40000, "loss": 0.2191, "lr": 3.571726854990642e-05, "epoch": 11.751534997953335, "percentage": 35.9, "elapsed_time": "1:38:52", "remaining_time": "2:56:32", "throughput": 788.51, "total_tokens": 4677672} {"current_steps": 14365, "total_steps": 40000, "loss": 0.1348, "lr": 3.570839811138925e-05, "epoch": 11.7556283258289, "percentage": 35.91, "elapsed_time": "1:38:54", "remaining_time": "2:56:29", "throughput": 788.57, "total_tokens": 4679384} {"current_steps": 14370, "total_steps": 40000, "loss": 0.1743, "lr": 3.569952602150252e-05, "epoch": 11.759721653704462, "percentage": 35.93, "elapsed_time": "1:38:55", "remaining_time": "2:56:26", "throughput": 788.61, "total_tokens": 4680984} {"current_steps": 14375, "total_steps": 40000, "loss": 0.1811, "lr": 3.569065228161442e-05, "epoch": 11.763814981580024, "percentage": 35.94, "elapsed_time": "1:38:57", "remaining_time": "2:56:24", "throughput": 788.65, "total_tokens": 4682552} {"current_steps": 14380, "total_steps": 40000, "loss": 0.1686, "lr": 3.5681776893093395e-05, "epoch": 11.767908309455587, "percentage": 35.95, "elapsed_time": "1:38:59", "remaining_time": "2:56:21", "throughput": 788.72, "total_tokens": 4684344} {"current_steps": 14385, "total_steps": 40000, "loss": 0.168, "lr": 3.5672899857308134e-05, "epoch": 11.772001637331151, "percentage": 35.96, "elapsed_time": "1:39:00", "remaining_time": "2:56:18", "throughput": 788.75, "total_tokens": 4685928} {"current_steps": 14390, "total_steps": 40000, "loss": 0.1966, "lr": 3.566402117562759e-05, "epoch": 11.776094965206713, "percentage": 35.98, "elapsed_time": "1:39:02", "remaining_time": "2:56:16", "throughput": 788.79, "total_tokens": 4687480} {"current_steps": 14395, "total_steps": 40000, "loss": 0.145, "lr": 3.565514084942097e-05, "epoch": 11.780188293082276, "percentage": 35.99, "elapsed_time": "1:39:04", "remaining_time": "2:56:13", "throughput": 788.84, "total_tokens": 4689128} {"current_steps": 14400, "total_steps": 40000, "loss": 0.1961, "lr": 3.564625888005773e-05, "epoch": 11.784281620957838, "percentage": 36.0, "elapsed_time": "1:39:06", "remaining_time": "2:56:10", "throughput": 788.88, "total_tokens": 4690744} {"current_steps": 14400, "total_steps": 40000, "eval_loss": 0.20582790672779083, "epoch": 11.784281620957838, "percentage": 36.0, "elapsed_time": "1:39:18", "remaining_time": "2:56:32", "throughput": 787.23, "total_tokens": 4690744} {"current_steps": 14405, "total_steps": 40000, "loss": 0.1818, "lr": 3.563737526890759e-05, "epoch": 11.788374948833402, "percentage": 36.01, "elapsed_time": "1:39:21", "remaining_time": "2:56:33", "throughput": 787.08, "total_tokens": 4692408} {"current_steps": 14410, "total_steps": 40000, "loss": 0.2252, "lr": 3.562849001734049e-05, "epoch": 11.792468276708965, "percentage": 36.02, "elapsed_time": "1:39:23", "remaining_time": "2:56:30", "throughput": 787.14, "total_tokens": 4694136} {"current_steps": 14415, "total_steps": 40000, "loss": 0.2066, "lr": 3.561960312672667e-05, "epoch": 11.796561604584527, "percentage": 36.04, "elapsed_time": "1:39:25", "remaining_time": "2:56:27", "throughput": 787.2, "total_tokens": 4695816} {"current_steps": 14420, "total_steps": 40000, "loss": 0.1866, "lr": 3.5610714598436596e-05, "epoch": 11.80065493246009, "percentage": 36.05, "elapsed_time": "1:39:26", "remaining_time": "2:56:24", "throughput": 787.24, "total_tokens": 4697432} {"current_steps": 14425, "total_steps": 40000, "loss": 0.168, "lr": 3.5601824433840986e-05, "epoch": 11.804748260335653, "percentage": 36.06, "elapsed_time": "1:39:28", "remaining_time": "2:56:22", "throughput": 787.29, "total_tokens": 4699096} {"current_steps": 14430, "total_steps": 40000, "loss": 0.148, "lr": 3.559293263431082e-05, "epoch": 11.808841588211216, "percentage": 36.08, "elapsed_time": "1:39:30", "remaining_time": "2:56:19", "throughput": 787.34, "total_tokens": 4700744} {"current_steps": 14435, "total_steps": 40000, "loss": 0.1611, "lr": 3.558403920121732e-05, "epoch": 11.812934916086778, "percentage": 36.09, "elapsed_time": "1:39:32", "remaining_time": "2:56:16", "throughput": 787.38, "total_tokens": 4702376} {"current_steps": 14440, "total_steps": 40000, "loss": 0.2256, "lr": 3.557514413593197e-05, "epoch": 11.81702824396234, "percentage": 36.1, "elapsed_time": "1:39:33", "remaining_time": "2:56:14", "throughput": 787.44, "total_tokens": 4704056} {"current_steps": 14445, "total_steps": 40000, "loss": 0.2317, "lr": 3.55662474398265e-05, "epoch": 11.821121571837905, "percentage": 36.11, "elapsed_time": "1:39:35", "remaining_time": "2:56:11", "throughput": 787.48, "total_tokens": 4705656} {"current_steps": 14450, "total_steps": 40000, "loss": 0.2778, "lr": 3.555734911427288e-05, "epoch": 11.825214899713467, "percentage": 36.12, "elapsed_time": "1:39:37", "remaining_time": "2:56:08", "throughput": 787.52, "total_tokens": 4707240} {"current_steps": 14455, "total_steps": 40000, "loss": 0.1767, "lr": 3.5548449160643363e-05, "epoch": 11.82930822758903, "percentage": 36.14, "elapsed_time": "1:39:39", "remaining_time": "2:56:06", "throughput": 787.58, "total_tokens": 4708936} {"current_steps": 14460, "total_steps": 40000, "loss": 0.1821, "lr": 3.553954758031043e-05, "epoch": 11.833401555464592, "percentage": 36.15, "elapsed_time": "1:39:40", "remaining_time": "2:56:03", "throughput": 787.62, "total_tokens": 4710536} {"current_steps": 14465, "total_steps": 40000, "loss": 0.1781, "lr": 3.5530644374646815e-05, "epoch": 11.837494883340156, "percentage": 36.16, "elapsed_time": "1:39:42", "remaining_time": "2:56:00", "throughput": 787.66, "total_tokens": 4712136} {"current_steps": 14470, "total_steps": 40000, "loss": 0.1972, "lr": 3.552173954502549e-05, "epoch": 11.841588211215718, "percentage": 36.18, "elapsed_time": "1:39:44", "remaining_time": "2:55:58", "throughput": 787.71, "total_tokens": 4713768} {"current_steps": 14475, "total_steps": 40000, "loss": 0.1506, "lr": 3.55128330928197e-05, "epoch": 11.84568153909128, "percentage": 36.19, "elapsed_time": "1:39:45", "remaining_time": "2:55:55", "throughput": 787.75, "total_tokens": 4715384} {"current_steps": 14480, "total_steps": 40000, "loss": 0.176, "lr": 3.550392501940294e-05, "epoch": 11.849774866966843, "percentage": 36.2, "elapsed_time": "1:39:47", "remaining_time": "2:55:52", "throughput": 787.79, "total_tokens": 4716968} {"current_steps": 14485, "total_steps": 40000, "loss": 0.1617, "lr": 3.5495015326148945e-05, "epoch": 11.853868194842407, "percentage": 36.21, "elapsed_time": "1:39:49", "remaining_time": "2:55:50", "throughput": 787.83, "total_tokens": 4718600} {"current_steps": 14490, "total_steps": 40000, "loss": 0.1762, "lr": 3.548610401443169e-05, "epoch": 11.85796152271797, "percentage": 36.23, "elapsed_time": "1:39:51", "remaining_time": "2:55:47", "throughput": 787.89, "total_tokens": 4720264} {"current_steps": 14495, "total_steps": 40000, "loss": 0.2431, "lr": 3.547719108562543e-05, "epoch": 11.862054850593532, "percentage": 36.24, "elapsed_time": "1:39:52", "remaining_time": "2:55:44", "throughput": 787.93, "total_tokens": 4721864} {"current_steps": 14500, "total_steps": 40000, "loss": 0.1699, "lr": 3.546827654110464e-05, "epoch": 11.866148178469096, "percentage": 36.25, "elapsed_time": "1:39:54", "remaining_time": "2:55:42", "throughput": 787.97, "total_tokens": 4723464} {"current_steps": 14505, "total_steps": 40000, "loss": 0.1768, "lr": 3.545936038224405e-05, "epoch": 11.870241506344659, "percentage": 36.26, "elapsed_time": "1:39:56", "remaining_time": "2:55:39", "throughput": 788.02, "total_tokens": 4725160} {"current_steps": 14510, "total_steps": 40000, "loss": 0.2144, "lr": 3.545044261041864e-05, "epoch": 11.874334834220221, "percentage": 36.27, "elapsed_time": "1:39:57", "remaining_time": "2:55:36", "throughput": 788.07, "total_tokens": 4726808} {"current_steps": 14515, "total_steps": 40000, "loss": 0.1521, "lr": 3.5441523227003657e-05, "epoch": 11.878428162095783, "percentage": 36.29, "elapsed_time": "1:39:59", "remaining_time": "2:55:33", "throughput": 788.12, "total_tokens": 4728424} {"current_steps": 14520, "total_steps": 40000, "loss": 0.1601, "lr": 3.543260223337459e-05, "epoch": 11.882521489971346, "percentage": 36.3, "elapsed_time": "1:40:01", "remaining_time": "2:55:31", "throughput": 788.15, "total_tokens": 4729960} {"current_steps": 14525, "total_steps": 40000, "loss": 0.24, "lr": 3.542367963090714e-05, "epoch": 11.88661481784691, "percentage": 36.31, "elapsed_time": "1:40:03", "remaining_time": "2:55:28", "throughput": 788.19, "total_tokens": 4731576} {"current_steps": 14530, "total_steps": 40000, "loss": 0.2291, "lr": 3.5414755420977295e-05, "epoch": 11.890708145722472, "percentage": 36.33, "elapsed_time": "1:40:04", "remaining_time": "2:55:25", "throughput": 788.24, "total_tokens": 4733240} {"current_steps": 14535, "total_steps": 40000, "loss": 0.1717, "lr": 3.54058296049613e-05, "epoch": 11.894801473598035, "percentage": 36.34, "elapsed_time": "1:40:06", "remaining_time": "2:55:23", "throughput": 788.3, "total_tokens": 4734920} {"current_steps": 14540, "total_steps": 40000, "loss": 0.1887, "lr": 3.53969021842356e-05, "epoch": 11.898894801473599, "percentage": 36.35, "elapsed_time": "1:40:08", "remaining_time": "2:55:20", "throughput": 788.34, "total_tokens": 4736568} {"current_steps": 14545, "total_steps": 40000, "loss": 0.163, "lr": 3.5387973160176926e-05, "epoch": 11.902988129349161, "percentage": 36.36, "elapsed_time": "1:40:09", "remaining_time": "2:55:17", "throughput": 788.39, "total_tokens": 4738232} {"current_steps": 14550, "total_steps": 40000, "loss": 0.2801, "lr": 3.537904253416224e-05, "epoch": 11.907081457224724, "percentage": 36.38, "elapsed_time": "1:40:11", "remaining_time": "2:55:15", "throughput": 788.45, "total_tokens": 4739912} {"current_steps": 14555, "total_steps": 40000, "loss": 0.1301, "lr": 3.537011030756878e-05, "epoch": 11.911174785100286, "percentage": 36.39, "elapsed_time": "1:40:13", "remaining_time": "2:55:12", "throughput": 788.5, "total_tokens": 4741560} {"current_steps": 14560, "total_steps": 40000, "loss": 0.1342, "lr": 3.536117648177399e-05, "epoch": 11.915268112975848, "percentage": 36.4, "elapsed_time": "1:40:15", "remaining_time": "2:55:09", "throughput": 788.54, "total_tokens": 4743192} {"current_steps": 14565, "total_steps": 40000, "loss": 0.2118, "lr": 3.535224105815558e-05, "epoch": 11.919361440851413, "percentage": 36.41, "elapsed_time": "1:40:16", "remaining_time": "2:55:07", "throughput": 788.59, "total_tokens": 4744824} {"current_steps": 14570, "total_steps": 40000, "loss": 0.1693, "lr": 3.5343304038091494e-05, "epoch": 11.923454768726975, "percentage": 36.43, "elapsed_time": "1:40:18", "remaining_time": "2:55:04", "throughput": 788.63, "total_tokens": 4746440} {"current_steps": 14575, "total_steps": 40000, "loss": 0.2031, "lr": 3.5334365422959955e-05, "epoch": 11.927548096602537, "percentage": 36.44, "elapsed_time": "1:40:20", "remaining_time": "2:55:01", "throughput": 788.67, "total_tokens": 4748040} {"current_steps": 14580, "total_steps": 40000, "loss": 0.1993, "lr": 3.5325425214139396e-05, "epoch": 11.931641424478101, "percentage": 36.45, "elapsed_time": "1:40:22", "remaining_time": "2:54:59", "throughput": 788.72, "total_tokens": 4749672} {"current_steps": 14585, "total_steps": 40000, "loss": 0.2483, "lr": 3.531648341300851e-05, "epoch": 11.935734752353664, "percentage": 36.46, "elapsed_time": "1:40:23", "remaining_time": "2:54:56", "throughput": 788.77, "total_tokens": 4751304} {"current_steps": 14590, "total_steps": 40000, "loss": 0.2163, "lr": 3.530754002094623e-05, "epoch": 11.939828080229226, "percentage": 36.48, "elapsed_time": "1:40:25", "remaining_time": "2:54:53", "throughput": 788.82, "total_tokens": 4752952} {"current_steps": 14595, "total_steps": 40000, "loss": 0.1645, "lr": 3.529859503933175e-05, "epoch": 11.943921408104789, "percentage": 36.49, "elapsed_time": "1:40:27", "remaining_time": "2:54:51", "throughput": 788.85, "total_tokens": 4754536} {"current_steps": 14600, "total_steps": 40000, "loss": 0.2351, "lr": 3.52896484695445e-05, "epoch": 11.948014735980353, "percentage": 36.5, "elapsed_time": "1:40:28", "remaining_time": "2:54:48", "throughput": 788.9, "total_tokens": 4756152} {"current_steps": 14600, "total_steps": 40000, "eval_loss": 0.21336980164051056, "epoch": 11.948014735980353, "percentage": 36.5, "elapsed_time": "1:40:41", "remaining_time": "2:55:10", "throughput": 787.27, "total_tokens": 4756152} {"current_steps": 14605, "total_steps": 40000, "loss": 0.188, "lr": 3.528070031296414e-05, "epoch": 11.952108063855915, "percentage": 36.51, "elapsed_time": "1:40:44", "remaining_time": "2:55:10", "throughput": 787.1, "total_tokens": 4757800} {"current_steps": 14610, "total_steps": 40000, "loss": 0.2003, "lr": 3.5271750570970605e-05, "epoch": 11.956201391731478, "percentage": 36.52, "elapsed_time": "1:40:46", "remaining_time": "2:55:07", "throughput": 787.15, "total_tokens": 4759448} {"current_steps": 14615, "total_steps": 40000, "loss": 0.1851, "lr": 3.526279924494405e-05, "epoch": 11.96029471960704, "percentage": 36.54, "elapsed_time": "1:40:48", "remaining_time": "2:55:05", "throughput": 787.19, "total_tokens": 4761048} {"current_steps": 14620, "total_steps": 40000, "loss": 0.2424, "lr": 3.5253846336264874e-05, "epoch": 11.964388047482604, "percentage": 36.55, "elapsed_time": "1:40:49", "remaining_time": "2:55:02", "throughput": 787.23, "total_tokens": 4762664} {"current_steps": 14625, "total_steps": 40000, "loss": 0.1647, "lr": 3.5244891846313736e-05, "epoch": 11.968481375358166, "percentage": 36.56, "elapsed_time": "1:40:51", "remaining_time": "2:54:59", "throughput": 787.28, "total_tokens": 4764296} {"current_steps": 14630, "total_steps": 40000, "loss": 0.1496, "lr": 3.5235935776471527e-05, "epoch": 11.972574703233729, "percentage": 36.58, "elapsed_time": "1:40:53", "remaining_time": "2:54:57", "throughput": 787.32, "total_tokens": 4765928} {"current_steps": 14635, "total_steps": 40000, "loss": 0.2147, "lr": 3.522697812811939e-05, "epoch": 11.976668031109291, "percentage": 36.59, "elapsed_time": "1:40:55", "remaining_time": "2:54:54", "throughput": 787.38, "total_tokens": 4767640} {"current_steps": 14640, "total_steps": 40000, "loss": 0.1424, "lr": 3.521801890263871e-05, "epoch": 11.980761358984855, "percentage": 36.6, "elapsed_time": "1:40:56", "remaining_time": "2:54:51", "throughput": 787.43, "total_tokens": 4769288} {"current_steps": 14645, "total_steps": 40000, "loss": 0.156, "lr": 3.5209058101411114e-05, "epoch": 11.984854686860418, "percentage": 36.61, "elapsed_time": "1:40:58", "remaining_time": "2:54:49", "throughput": 787.48, "total_tokens": 4770920} {"current_steps": 14650, "total_steps": 40000, "loss": 0.1463, "lr": 3.520009572581845e-05, "epoch": 11.98894801473598, "percentage": 36.62, "elapsed_time": "1:41:00", "remaining_time": "2:54:46", "throughput": 787.52, "total_tokens": 4772520} {"current_steps": 14655, "total_steps": 40000, "loss": 0.1637, "lr": 3.519113177724285e-05, "epoch": 11.993041342611543, "percentage": 36.64, "elapsed_time": "1:41:01", "remaining_time": "2:54:43", "throughput": 787.56, "total_tokens": 4774152} {"current_steps": 14660, "total_steps": 40000, "loss": 0.1939, "lr": 3.5182166257066656e-05, "epoch": 11.997134670487107, "percentage": 36.65, "elapsed_time": "1:41:03", "remaining_time": "2:54:41", "throughput": 787.61, "total_tokens": 4775784} {"current_steps": 14665, "total_steps": 40000, "loss": 0.2605, "lr": 3.517319916667247e-05, "epoch": 12.000818665575112, "percentage": 36.66, "elapsed_time": "1:41:05", "remaining_time": "2:54:38", "throughput": 787.59, "total_tokens": 4777176} {"current_steps": 14670, "total_steps": 40000, "loss": 0.1886, "lr": 3.516423050744313e-05, "epoch": 12.004911993450676, "percentage": 36.68, "elapsed_time": "1:41:07", "remaining_time": "2:54:36", "throughput": 787.63, "total_tokens": 4778776} {"current_steps": 14675, "total_steps": 40000, "loss": 0.2093, "lr": 3.5155260280761704e-05, "epoch": 12.009005321326239, "percentage": 36.69, "elapsed_time": "1:41:08", "remaining_time": "2:54:33", "throughput": 787.69, "total_tokens": 4780456} {"current_steps": 14680, "total_steps": 40000, "loss": 0.2203, "lr": 3.514628848801154e-05, "epoch": 12.013098649201801, "percentage": 36.7, "elapsed_time": "1:41:10", "remaining_time": "2:54:30", "throughput": 787.73, "total_tokens": 4782088} {"current_steps": 14685, "total_steps": 40000, "loss": 0.2513, "lr": 3.5137315130576174e-05, "epoch": 12.017191977077363, "percentage": 36.71, "elapsed_time": "1:41:12", "remaining_time": "2:54:28", "throughput": 787.8, "total_tokens": 4783848} {"current_steps": 14690, "total_steps": 40000, "loss": 0.1849, "lr": 3.512834020983942e-05, "epoch": 12.021285304952928, "percentage": 36.73, "elapsed_time": "1:41:14", "remaining_time": "2:54:25", "throughput": 787.85, "total_tokens": 4785512} {"current_steps": 14695, "total_steps": 40000, "loss": 0.232, "lr": 3.5119363727185334e-05, "epoch": 12.02537863282849, "percentage": 36.74, "elapsed_time": "1:41:15", "remaining_time": "2:54:22", "throughput": 787.9, "total_tokens": 4787160} {"current_steps": 14700, "total_steps": 40000, "loss": 0.176, "lr": 3.511038568399819e-05, "epoch": 12.029471960704052, "percentage": 36.75, "elapsed_time": "1:41:17", "remaining_time": "2:54:20", "throughput": 787.94, "total_tokens": 4788808} {"current_steps": 14705, "total_steps": 40000, "loss": 0.0973, "lr": 3.510140608166251e-05, "epoch": 12.033565288579615, "percentage": 36.76, "elapsed_time": "1:41:19", "remaining_time": "2:54:17", "throughput": 787.98, "total_tokens": 4790408} {"current_steps": 14710, "total_steps": 40000, "loss": 0.1107, "lr": 3.509242492156308e-05, "epoch": 12.037658616455179, "percentage": 36.78, "elapsed_time": "1:41:21", "remaining_time": "2:54:14", "throughput": 788.04, "total_tokens": 4792088} {"current_steps": 14715, "total_steps": 40000, "loss": 0.1764, "lr": 3.5083442205084896e-05, "epoch": 12.041751944330741, "percentage": 36.79, "elapsed_time": "1:41:22", "remaining_time": "2:54:12", "throughput": 788.09, "total_tokens": 4793736} {"current_steps": 14720, "total_steps": 40000, "loss": 0.2067, "lr": 3.507445793361321e-05, "epoch": 12.045845272206304, "percentage": 36.8, "elapsed_time": "1:41:24", "remaining_time": "2:54:09", "throughput": 788.13, "total_tokens": 4795368} {"current_steps": 14725, "total_steps": 40000, "loss": 0.2366, "lr": 3.5065472108533505e-05, "epoch": 12.049938600081866, "percentage": 36.81, "elapsed_time": "1:41:26", "remaining_time": "2:54:06", "throughput": 788.17, "total_tokens": 4796984} {"current_steps": 14730, "total_steps": 40000, "loss": 0.2295, "lr": 3.5056484731231504e-05, "epoch": 12.05403192795743, "percentage": 36.83, "elapsed_time": "1:41:27", "remaining_time": "2:54:04", "throughput": 788.2, "total_tokens": 4798520} {"current_steps": 14735, "total_steps": 40000, "loss": 0.2022, "lr": 3.504749580309319e-05, "epoch": 12.058125255832993, "percentage": 36.84, "elapsed_time": "1:41:29", "remaining_time": "2:54:01", "throughput": 788.24, "total_tokens": 4800088} {"current_steps": 14740, "total_steps": 40000, "loss": 0.1214, "lr": 3.5038505325504753e-05, "epoch": 12.062218583708555, "percentage": 36.85, "elapsed_time": "1:41:31", "remaining_time": "2:53:58", "throughput": 788.29, "total_tokens": 4801768} {"current_steps": 14745, "total_steps": 40000, "loss": 0.2072, "lr": 3.502951329985264e-05, "epoch": 12.066311911584117, "percentage": 36.86, "elapsed_time": "1:41:33", "remaining_time": "2:53:56", "throughput": 788.33, "total_tokens": 4803352} {"current_steps": 14750, "total_steps": 40000, "loss": 0.2248, "lr": 3.502051972752354e-05, "epoch": 12.070405239459681, "percentage": 36.88, "elapsed_time": "1:41:34", "remaining_time": "2:53:53", "throughput": 788.37, "total_tokens": 4804952} {"current_steps": 14755, "total_steps": 40000, "loss": 0.148, "lr": 3.5011524609904374e-05, "epoch": 12.074498567335244, "percentage": 36.89, "elapsed_time": "1:41:36", "remaining_time": "2:53:50", "throughput": 788.41, "total_tokens": 4806552} {"current_steps": 14760, "total_steps": 40000, "loss": 0.2114, "lr": 3.50025279483823e-05, "epoch": 12.078591895210806, "percentage": 36.9, "elapsed_time": "1:41:38", "remaining_time": "2:53:48", "throughput": 788.44, "total_tokens": 4808120} {"current_steps": 14765, "total_steps": 40000, "loss": 0.269, "lr": 3.499352974434472e-05, "epoch": 12.082685223086369, "percentage": 36.91, "elapsed_time": "1:41:39", "remaining_time": "2:53:45", "throughput": 788.48, "total_tokens": 4809704} {"current_steps": 14770, "total_steps": 40000, "loss": 0.141, "lr": 3.498452999917926e-05, "epoch": 12.086778550961933, "percentage": 36.93, "elapsed_time": "1:41:41", "remaining_time": "2:53:42", "throughput": 788.54, "total_tokens": 4811432} {"current_steps": 14775, "total_steps": 40000, "loss": 0.1921, "lr": 3.4975528714273795e-05, "epoch": 12.090871878837495, "percentage": 36.94, "elapsed_time": "1:41:43", "remaining_time": "2:53:40", "throughput": 788.59, "total_tokens": 4813112} {"current_steps": 14780, "total_steps": 40000, "loss": 0.2022, "lr": 3.4966525891016454e-05, "epoch": 12.094965206713058, "percentage": 36.95, "elapsed_time": "1:41:45", "remaining_time": "2:53:37", "throughput": 788.64, "total_tokens": 4814744} {"current_steps": 14785, "total_steps": 40000, "loss": 0.1652, "lr": 3.495752153079557e-05, "epoch": 12.09905853458862, "percentage": 36.96, "elapsed_time": "1:41:46", "remaining_time": "2:53:34", "throughput": 788.68, "total_tokens": 4816376} {"current_steps": 14790, "total_steps": 40000, "loss": 0.1806, "lr": 3.494851563499974e-05, "epoch": 12.103151862464184, "percentage": 36.98, "elapsed_time": "1:41:48", "remaining_time": "2:53:32", "throughput": 788.72, "total_tokens": 4817960} {"current_steps": 14795, "total_steps": 40000, "loss": 0.2217, "lr": 3.493950820501777e-05, "epoch": 12.107245190339746, "percentage": 36.99, "elapsed_time": "1:41:50", "remaining_time": "2:53:29", "throughput": 788.77, "total_tokens": 4819608} {"current_steps": 14800, "total_steps": 40000, "loss": 0.2088, "lr": 3.493049924223872e-05, "epoch": 12.111338518215309, "percentage": 37.0, "elapsed_time": "1:41:52", "remaining_time": "2:53:26", "throughput": 788.82, "total_tokens": 4821256} {"current_steps": 14800, "total_steps": 40000, "eval_loss": 0.20307381451129913, "epoch": 12.111338518215309, "percentage": 37.0, "elapsed_time": "1:42:04", "remaining_time": "2:53:48", "throughput": 787.21, "total_tokens": 4821256} {"current_steps": 14805, "total_steps": 40000, "loss": 0.2442, "lr": 3.49214887480519e-05, "epoch": 12.115431846090871, "percentage": 37.01, "elapsed_time": "1:42:07", "remaining_time": "2:53:48", "throughput": 787.06, "total_tokens": 4822872} {"current_steps": 14810, "total_steps": 40000, "loss": 0.2162, "lr": 3.4912476723846834e-05, "epoch": 12.119525173966435, "percentage": 37.03, "elapsed_time": "1:42:09", "remaining_time": "2:53:45", "throughput": 787.12, "total_tokens": 4824568} {"current_steps": 14815, "total_steps": 40000, "loss": 0.1521, "lr": 3.490346317101328e-05, "epoch": 12.123618501841998, "percentage": 37.04, "elapsed_time": "1:42:11", "remaining_time": "2:53:42", "throughput": 787.17, "total_tokens": 4826232} {"current_steps": 14820, "total_steps": 40000, "loss": 0.2247, "lr": 3.4894448090941266e-05, "epoch": 12.12771182971756, "percentage": 37.05, "elapsed_time": "1:42:12", "remaining_time": "2:53:40", "throughput": 787.21, "total_tokens": 4827864} {"current_steps": 14825, "total_steps": 40000, "loss": 0.2336, "lr": 3.488543148502101e-05, "epoch": 12.131805157593123, "percentage": 37.06, "elapsed_time": "1:42:14", "remaining_time": "2:53:37", "throughput": 787.26, "total_tokens": 4829528} {"current_steps": 14830, "total_steps": 40000, "loss": 0.1819, "lr": 3.487641335464299e-05, "epoch": 12.135898485468687, "percentage": 37.08, "elapsed_time": "1:42:16", "remaining_time": "2:53:34", "throughput": 787.3, "total_tokens": 4831112} {"current_steps": 14835, "total_steps": 40000, "loss": 0.1643, "lr": 3.4867393701197914e-05, "epoch": 12.139991813344249, "percentage": 37.09, "elapsed_time": "1:42:18", "remaining_time": "2:53:32", "throughput": 787.34, "total_tokens": 4832696} {"current_steps": 14840, "total_steps": 40000, "loss": 0.1991, "lr": 3.485837252607673e-05, "epoch": 12.144085141219811, "percentage": 37.1, "elapsed_time": "1:42:19", "remaining_time": "2:53:29", "throughput": 787.38, "total_tokens": 4834312} {"current_steps": 14845, "total_steps": 40000, "loss": 0.1524, "lr": 3.4849349830670615e-05, "epoch": 12.148178469095374, "percentage": 37.11, "elapsed_time": "1:42:21", "remaining_time": "2:53:26", "throughput": 787.43, "total_tokens": 4835976} {"current_steps": 14850, "total_steps": 40000, "loss": 0.1553, "lr": 3.4840325616370976e-05, "epoch": 12.152271796970938, "percentage": 37.12, "elapsed_time": "1:42:23", "remaining_time": "2:53:24", "throughput": 787.48, "total_tokens": 4837592} {"current_steps": 14855, "total_steps": 40000, "loss": 0.1594, "lr": 3.483129988456947e-05, "epoch": 12.1563651248465, "percentage": 37.14, "elapsed_time": "1:42:24", "remaining_time": "2:53:21", "throughput": 787.51, "total_tokens": 4839160} {"current_steps": 14860, "total_steps": 40000, "loss": 0.1914, "lr": 3.482227263665797e-05, "epoch": 12.160458452722063, "percentage": 37.15, "elapsed_time": "1:42:26", "remaining_time": "2:53:18", "throughput": 787.55, "total_tokens": 4840760} {"current_steps": 14865, "total_steps": 40000, "loss": 0.1871, "lr": 3.48132438740286e-05, "epoch": 12.164551780597625, "percentage": 37.16, "elapsed_time": "1:42:28", "remaining_time": "2:53:16", "throughput": 787.59, "total_tokens": 4842376} {"current_steps": 14870, "total_steps": 40000, "loss": 0.1889, "lr": 3.48042135980737e-05, "epoch": 12.16864510847319, "percentage": 37.18, "elapsed_time": "1:42:30", "remaining_time": "2:53:13", "throughput": 787.64, "total_tokens": 4843992} {"current_steps": 14875, "total_steps": 40000, "loss": 0.258, "lr": 3.479518181018586e-05, "epoch": 12.172738436348752, "percentage": 37.19, "elapsed_time": "1:42:32", "remaining_time": "2:53:11", "throughput": 787.64, "total_tokens": 4845608} {"current_steps": 14880, "total_steps": 40000, "loss": 0.2147, "lr": 3.4786148511757886e-05, "epoch": 12.176831764224314, "percentage": 37.2, "elapsed_time": "1:42:33", "remaining_time": "2:53:08", "throughput": 787.69, "total_tokens": 4847224} {"current_steps": 14885, "total_steps": 40000, "loss": 0.2324, "lr": 3.477711370418284e-05, "epoch": 12.180925092099876, "percentage": 37.21, "elapsed_time": "1:42:35", "remaining_time": "2:53:05", "throughput": 787.73, "total_tokens": 4848856} {"current_steps": 14890, "total_steps": 40000, "loss": 0.1657, "lr": 3.476807738885399e-05, "epoch": 12.18501841997544, "percentage": 37.23, "elapsed_time": "1:42:37", "remaining_time": "2:53:03", "throughput": 787.77, "total_tokens": 4850456} {"current_steps": 14895, "total_steps": 40000, "loss": 0.1741, "lr": 3.475903956716485e-05, "epoch": 12.189111747851003, "percentage": 37.24, "elapsed_time": "1:42:38", "remaining_time": "2:53:00", "throughput": 787.82, "total_tokens": 4852088} {"current_steps": 14900, "total_steps": 40000, "loss": 0.2524, "lr": 3.475000024050917e-05, "epoch": 12.193205075726565, "percentage": 37.25, "elapsed_time": "1:42:40", "remaining_time": "2:52:57", "throughput": 787.87, "total_tokens": 4853752} {"current_steps": 14905, "total_steps": 40000, "loss": 0.1284, "lr": 3.4740959410280926e-05, "epoch": 12.197298403602128, "percentage": 37.26, "elapsed_time": "1:42:42", "remaining_time": "2:52:55", "throughput": 787.91, "total_tokens": 4855336} {"current_steps": 14910, "total_steps": 40000, "loss": 0.1847, "lr": 3.4731917077874324e-05, "epoch": 12.201391731477692, "percentage": 37.28, "elapsed_time": "1:42:44", "remaining_time": "2:52:52", "throughput": 787.94, "total_tokens": 4856904} {"current_steps": 14915, "total_steps": 40000, "loss": 0.2581, "lr": 3.4722873244683816e-05, "epoch": 12.205485059353254, "percentage": 37.29, "elapsed_time": "1:42:45", "remaining_time": "2:52:49", "throughput": 787.99, "total_tokens": 4858552} {"current_steps": 14920, "total_steps": 40000, "loss": 0.1546, "lr": 3.4713827912104065e-05, "epoch": 12.209578387228817, "percentage": 37.3, "elapsed_time": "1:42:47", "remaining_time": "2:52:47", "throughput": 788.02, "total_tokens": 4860120} {"current_steps": 14925, "total_steps": 40000, "loss": 0.1546, "lr": 3.470478108152998e-05, "epoch": 12.213671715104379, "percentage": 37.31, "elapsed_time": "1:42:49", "remaining_time": "2:52:44", "throughput": 788.06, "total_tokens": 4861720} {"current_steps": 14930, "total_steps": 40000, "loss": 0.1984, "lr": 3.4695732754356695e-05, "epoch": 12.217765042979943, "percentage": 37.33, "elapsed_time": "1:42:50", "remaining_time": "2:52:41", "throughput": 788.11, "total_tokens": 4863336} {"current_steps": 14935, "total_steps": 40000, "loss": 0.2788, "lr": 3.4686682931979576e-05, "epoch": 12.221858370855506, "percentage": 37.34, "elapsed_time": "1:42:52", "remaining_time": "2:52:39", "throughput": 788.16, "total_tokens": 4865016} {"current_steps": 14940, "total_steps": 40000, "loss": 0.2561, "lr": 3.467763161579422e-05, "epoch": 12.225951698731068, "percentage": 37.35, "elapsed_time": "1:42:54", "remaining_time": "2:52:36", "throughput": 788.21, "total_tokens": 4866696} {"current_steps": 14945, "total_steps": 40000, "loss": 0.1617, "lr": 3.466857880719645e-05, "epoch": 12.230045026606632, "percentage": 37.36, "elapsed_time": "1:42:56", "remaining_time": "2:52:34", "throughput": 788.25, "total_tokens": 4868280} {"current_steps": 14950, "total_steps": 40000, "loss": 0.099, "lr": 3.465952450758233e-05, "epoch": 12.234138354482194, "percentage": 37.38, "elapsed_time": "1:42:57", "remaining_time": "2:52:31", "throughput": 788.3, "total_tokens": 4869928} {"current_steps": 14955, "total_steps": 40000, "loss": 0.1401, "lr": 3.4650468718348126e-05, "epoch": 12.238231682357757, "percentage": 37.39, "elapsed_time": "1:42:59", "remaining_time": "2:52:28", "throughput": 788.34, "total_tokens": 4871528} {"current_steps": 14960, "total_steps": 40000, "loss": 0.1683, "lr": 3.464141144089038e-05, "epoch": 12.24232501023332, "percentage": 37.4, "elapsed_time": "1:43:01", "remaining_time": "2:52:26", "throughput": 788.38, "total_tokens": 4873160} {"current_steps": 14965, "total_steps": 40000, "loss": 0.216, "lr": 3.463235267660583e-05, "epoch": 12.246418338108883, "percentage": 37.41, "elapsed_time": "1:43:02", "remaining_time": "2:52:23", "throughput": 788.44, "total_tokens": 4874872} {"current_steps": 14970, "total_steps": 40000, "loss": 0.1639, "lr": 3.462329242689145e-05, "epoch": 12.250511665984446, "percentage": 37.43, "elapsed_time": "1:43:04", "remaining_time": "2:52:20", "throughput": 788.49, "total_tokens": 4876504} {"current_steps": 14975, "total_steps": 40000, "loss": 0.1657, "lr": 3.461423069314444e-05, "epoch": 12.254604993860008, "percentage": 37.44, "elapsed_time": "1:43:06", "remaining_time": "2:52:18", "throughput": 788.54, "total_tokens": 4878200} {"current_steps": 14980, "total_steps": 40000, "loss": 0.1203, "lr": 3.460516747676224e-05, "epoch": 12.25869832173557, "percentage": 37.45, "elapsed_time": "1:43:08", "remaining_time": "2:52:15", "throughput": 788.59, "total_tokens": 4879816} {"current_steps": 14985, "total_steps": 40000, "loss": 0.1617, "lr": 3.459610277914251e-05, "epoch": 12.262791649611135, "percentage": 37.46, "elapsed_time": "1:43:09", "remaining_time": "2:52:12", "throughput": 788.63, "total_tokens": 4881432} {"current_steps": 14990, "total_steps": 40000, "loss": 0.2644, "lr": 3.458703660168314e-05, "epoch": 12.266884977486697, "percentage": 37.48, "elapsed_time": "1:43:11", "remaining_time": "2:52:10", "throughput": 788.67, "total_tokens": 4883032} {"current_steps": 14995, "total_steps": 40000, "loss": 0.154, "lr": 3.457796894578224e-05, "epoch": 12.27097830536226, "percentage": 37.49, "elapsed_time": "1:43:13", "remaining_time": "2:52:07", "throughput": 788.72, "total_tokens": 4884696} {"current_steps": 15000, "total_steps": 40000, "loss": 0.3128, "lr": 3.456889981283817e-05, "epoch": 12.275071633237822, "percentage": 37.5, "elapsed_time": "1:43:14", "remaining_time": "2:52:04", "throughput": 788.77, "total_tokens": 4886344} {"current_steps": 15000, "total_steps": 40000, "eval_loss": 0.20614469051361084, "epoch": 12.275071633237822, "percentage": 37.5, "elapsed_time": "1:43:27", "remaining_time": "2:52:25", "throughput": 787.19, "total_tokens": 4886344} {"current_steps": 15005, "total_steps": 40000, "loss": 0.1328, "lr": 3.45598292042495e-05, "epoch": 12.279164961113386, "percentage": 37.51, "elapsed_time": "1:43:30", "remaining_time": "2:52:25", "throughput": 787.06, "total_tokens": 4888040} {"current_steps": 15010, "total_steps": 40000, "loss": 0.2418, "lr": 3.4550757121415035e-05, "epoch": 12.283258288988948, "percentage": 37.52, "elapsed_time": "1:43:32", "remaining_time": "2:52:22", "throughput": 787.11, "total_tokens": 4889704} {"current_steps": 15015, "total_steps": 40000, "loss": 0.152, "lr": 3.454168356573378e-05, "epoch": 12.28735161686451, "percentage": 37.54, "elapsed_time": "1:43:33", "remaining_time": "2:52:20", "throughput": 787.14, "total_tokens": 4891288} {"current_steps": 15020, "total_steps": 40000, "loss": 0.2071, "lr": 3.453260853860503e-05, "epoch": 12.291444944740073, "percentage": 37.55, "elapsed_time": "1:43:35", "remaining_time": "2:52:17", "throughput": 787.2, "total_tokens": 4892984} {"current_steps": 15025, "total_steps": 40000, "loss": 0.1657, "lr": 3.452353204142824e-05, "epoch": 12.295538272615637, "percentage": 37.56, "elapsed_time": "1:43:37", "remaining_time": "2:52:14", "throughput": 787.24, "total_tokens": 4894568} {"current_steps": 15030, "total_steps": 40000, "loss": 0.1591, "lr": 3.4514454075603136e-05, "epoch": 12.2996316004912, "percentage": 37.57, "elapsed_time": "1:43:39", "remaining_time": "2:52:12", "throughput": 787.29, "total_tokens": 4896216} {"current_steps": 15035, "total_steps": 40000, "loss": 0.1697, "lr": 3.450537464252964e-05, "epoch": 12.303724928366762, "percentage": 37.59, "elapsed_time": "1:43:40", "remaining_time": "2:52:09", "throughput": 787.33, "total_tokens": 4897832} {"current_steps": 15040, "total_steps": 40000, "loss": 0.2327, "lr": 3.4496293743607925e-05, "epoch": 12.307818256242324, "percentage": 37.6, "elapsed_time": "1:43:42", "remaining_time": "2:52:06", "throughput": 787.37, "total_tokens": 4899448} {"current_steps": 15045, "total_steps": 40000, "loss": 0.2564, "lr": 3.448721138023838e-05, "epoch": 12.311911584117889, "percentage": 37.61, "elapsed_time": "1:43:44", "remaining_time": "2:52:04", "throughput": 787.41, "total_tokens": 4901064} {"current_steps": 15050, "total_steps": 40000, "loss": 0.1716, "lr": 3.447812755382162e-05, "epoch": 12.316004911993451, "percentage": 37.62, "elapsed_time": "1:43:45", "remaining_time": "2:52:01", "throughput": 787.45, "total_tokens": 4902664} {"current_steps": 15055, "total_steps": 40000, "loss": 0.1355, "lr": 3.446904226575847e-05, "epoch": 12.320098239869013, "percentage": 37.64, "elapsed_time": "1:43:47", "remaining_time": "2:51:58", "throughput": 787.49, "total_tokens": 4904280} {"current_steps": 15060, "total_steps": 40000, "loss": 0.2085, "lr": 3.445995551745002e-05, "epoch": 12.324191567744576, "percentage": 37.65, "elapsed_time": "1:43:49", "remaining_time": "2:51:56", "throughput": 787.54, "total_tokens": 4905912} {"current_steps": 15065, "total_steps": 40000, "loss": 0.1521, "lr": 3.445086731029753e-05, "epoch": 12.32828489562014, "percentage": 37.66, "elapsed_time": "1:43:51", "remaining_time": "2:51:53", "throughput": 787.58, "total_tokens": 4907512} {"current_steps": 15070, "total_steps": 40000, "loss": 0.2031, "lr": 3.444177764570255e-05, "epoch": 12.332378223495702, "percentage": 37.67, "elapsed_time": "1:43:52", "remaining_time": "2:51:50", "throughput": 787.62, "total_tokens": 4909112} {"current_steps": 15075, "total_steps": 40000, "loss": 0.1536, "lr": 3.44326865250668e-05, "epoch": 12.336471551371265, "percentage": 37.69, "elapsed_time": "1:43:54", "remaining_time": "2:51:48", "throughput": 787.67, "total_tokens": 4910792} {"current_steps": 15080, "total_steps": 40000, "loss": 0.1302, "lr": 3.442359394979225e-05, "epoch": 12.340564879246827, "percentage": 37.7, "elapsed_time": "1:43:56", "remaining_time": "2:51:45", "throughput": 787.73, "total_tokens": 4912504} {"current_steps": 15085, "total_steps": 40000, "loss": 0.1744, "lr": 3.441449992128108e-05, "epoch": 12.344658207122391, "percentage": 37.71, "elapsed_time": "1:43:58", "remaining_time": "2:51:42", "throughput": 787.78, "total_tokens": 4914152} {"current_steps": 15090, "total_steps": 40000, "loss": 0.1877, "lr": 3.440540444093573e-05, "epoch": 12.348751534997954, "percentage": 37.72, "elapsed_time": "1:43:59", "remaining_time": "2:51:40", "throughput": 787.81, "total_tokens": 4915736} {"current_steps": 15095, "total_steps": 40000, "loss": 0.254, "lr": 3.43963075101588e-05, "epoch": 12.352844862873516, "percentage": 37.74, "elapsed_time": "1:44:01", "remaining_time": "2:51:37", "throughput": 787.86, "total_tokens": 4917384} {"current_steps": 15100, "total_steps": 40000, "loss": 0.1416, "lr": 3.438720913035318e-05, "epoch": 12.356938190749078, "percentage": 37.75, "elapsed_time": "1:44:03", "remaining_time": "2:51:35", "throughput": 787.91, "total_tokens": 4919080} {"current_steps": 15105, "total_steps": 40000, "loss": 0.1837, "lr": 3.437810930292195e-05, "epoch": 12.361031518624642, "percentage": 37.76, "elapsed_time": "1:44:04", "remaining_time": "2:51:32", "throughput": 787.97, "total_tokens": 4920808} {"current_steps": 15110, "total_steps": 40000, "loss": 0.2322, "lr": 3.43690080292684e-05, "epoch": 12.365124846500205, "percentage": 37.77, "elapsed_time": "1:44:06", "remaining_time": "2:51:29", "throughput": 788.01, "total_tokens": 4922392} {"current_steps": 15115, "total_steps": 40000, "loss": 0.1869, "lr": 3.435990531079608e-05, "epoch": 12.369218174375767, "percentage": 37.79, "elapsed_time": "1:44:08", "remaining_time": "2:51:27", "throughput": 788.07, "total_tokens": 4924120} {"current_steps": 15120, "total_steps": 40000, "loss": 0.1335, "lr": 3.435080114890874e-05, "epoch": 12.37331150225133, "percentage": 37.8, "elapsed_time": "1:44:10", "remaining_time": "2:51:24", "throughput": 788.11, "total_tokens": 4925736} {"current_steps": 15125, "total_steps": 40000, "loss": 0.2405, "lr": 3.434169554501035e-05, "epoch": 12.377404830126894, "percentage": 37.81, "elapsed_time": "1:44:11", "remaining_time": "2:51:21", "throughput": 788.16, "total_tokens": 4927384} {"current_steps": 15130, "total_steps": 40000, "loss": 0.1649, "lr": 3.433258850050511e-05, "epoch": 12.381498158002456, "percentage": 37.82, "elapsed_time": "1:44:13", "remaining_time": "2:51:19", "throughput": 788.2, "total_tokens": 4929016} {"current_steps": 15135, "total_steps": 40000, "loss": 0.1699, "lr": 3.4323480016797446e-05, "epoch": 12.385591485878019, "percentage": 37.84, "elapsed_time": "1:44:15", "remaining_time": "2:51:16", "throughput": 788.24, "total_tokens": 4930616} {"current_steps": 15140, "total_steps": 40000, "loss": 0.1709, "lr": 3.4314370095291995e-05, "epoch": 12.38968481375358, "percentage": 37.85, "elapsed_time": "1:44:16", "remaining_time": "2:51:13", "throughput": 788.29, "total_tokens": 4932296} {"current_steps": 15145, "total_steps": 40000, "loss": 0.1791, "lr": 3.430525873739363e-05, "epoch": 12.393778141629145, "percentage": 37.86, "elapsed_time": "1:44:18", "remaining_time": "2:51:11", "throughput": 788.33, "total_tokens": 4933864} {"current_steps": 15150, "total_steps": 40000, "loss": 0.1894, "lr": 3.429614594450743e-05, "epoch": 12.397871469504707, "percentage": 37.88, "elapsed_time": "1:44:20", "remaining_time": "2:51:08", "throughput": 788.37, "total_tokens": 4935464} {"current_steps": 15155, "total_steps": 40000, "loss": 0.1852, "lr": 3.428703171803869e-05, "epoch": 12.40196479738027, "percentage": 37.89, "elapsed_time": "1:44:22", "remaining_time": "2:51:06", "throughput": 788.42, "total_tokens": 4937144} {"current_steps": 15160, "total_steps": 40000, "loss": 0.1671, "lr": 3.4277916059392964e-05, "epoch": 12.406058125255832, "percentage": 37.9, "elapsed_time": "1:44:23", "remaining_time": "2:51:03", "throughput": 788.46, "total_tokens": 4938776} {"current_steps": 15165, "total_steps": 40000, "loss": 0.1922, "lr": 3.426879896997598e-05, "epoch": 12.410151453131396, "percentage": 37.91, "elapsed_time": "1:44:25", "remaining_time": "2:51:00", "throughput": 788.51, "total_tokens": 4940424} {"current_steps": 15170, "total_steps": 40000, "loss": 0.2186, "lr": 3.425968045119372e-05, "epoch": 12.414244781006959, "percentage": 37.92, "elapsed_time": "1:44:27", "remaining_time": "2:50:58", "throughput": 788.56, "total_tokens": 4942104} {"current_steps": 15175, "total_steps": 40000, "loss": 0.1836, "lr": 3.425056050445237e-05, "epoch": 12.418338108882521, "percentage": 37.94, "elapsed_time": "1:44:28", "remaining_time": "2:50:55", "throughput": 788.61, "total_tokens": 4943752} {"current_steps": 15180, "total_steps": 40000, "loss": 0.236, "lr": 3.4241439131158336e-05, "epoch": 12.422431436758083, "percentage": 37.95, "elapsed_time": "1:44:30", "remaining_time": "2:50:52", "throughput": 788.65, "total_tokens": 4945352} {"current_steps": 15185, "total_steps": 40000, "loss": 0.2146, "lr": 3.423231633271825e-05, "epoch": 12.426524764633648, "percentage": 37.96, "elapsed_time": "1:44:32", "remaining_time": "2:50:50", "throughput": 788.69, "total_tokens": 4946984} {"current_steps": 15190, "total_steps": 40000, "loss": 0.1706, "lr": 3.4223192110538985e-05, "epoch": 12.43061809250921, "percentage": 37.97, "elapsed_time": "1:44:34", "remaining_time": "2:50:47", "throughput": 788.75, "total_tokens": 4948712} {"current_steps": 15195, "total_steps": 40000, "loss": 0.2725, "lr": 3.4214066466027575e-05, "epoch": 12.434711420384772, "percentage": 37.99, "elapsed_time": "1:44:35", "remaining_time": "2:50:44", "throughput": 788.8, "total_tokens": 4950376} {"current_steps": 15200, "total_steps": 40000, "loss": 0.1364, "lr": 3.4204939400591325e-05, "epoch": 12.438804748260335, "percentage": 38.0, "elapsed_time": "1:44:37", "remaining_time": "2:50:42", "throughput": 788.84, "total_tokens": 4951960} {"current_steps": 15200, "total_steps": 40000, "eval_loss": 0.20280703902244568, "epoch": 12.438804748260335, "percentage": 38.0, "elapsed_time": "1:44:50", "remaining_time": "2:51:02", "throughput": 787.27, "total_tokens": 4951960} {"current_steps": 15205, "total_steps": 40000, "loss": 0.2062, "lr": 3.419581091563775e-05, "epoch": 12.442898076135899, "percentage": 38.01, "elapsed_time": "1:44:53", "remaining_time": "2:51:02", "throughput": 787.14, "total_tokens": 4953672} {"current_steps": 15210, "total_steps": 40000, "loss": 0.1748, "lr": 3.418668101257456e-05, "epoch": 12.446991404011461, "percentage": 38.02, "elapsed_time": "1:44:54", "remaining_time": "2:50:59", "throughput": 787.18, "total_tokens": 4955272} {"current_steps": 15215, "total_steps": 40000, "loss": 0.1403, "lr": 3.417754969280971e-05, "epoch": 12.451084731887024, "percentage": 38.04, "elapsed_time": "1:44:56", "remaining_time": "2:50:57", "throughput": 787.23, "total_tokens": 4956936} {"current_steps": 15220, "total_steps": 40000, "loss": 0.138, "lr": 3.416841695775137e-05, "epoch": 12.455178059762588, "percentage": 38.05, "elapsed_time": "1:44:58", "remaining_time": "2:50:54", "throughput": 787.27, "total_tokens": 4958504} {"current_steps": 15225, "total_steps": 40000, "loss": 0.2072, "lr": 3.415928280880792e-05, "epoch": 12.45927138763815, "percentage": 38.06, "elapsed_time": "1:45:00", "remaining_time": "2:50:51", "throughput": 787.32, "total_tokens": 4960200} {"current_steps": 15230, "total_steps": 40000, "loss": 0.1459, "lr": 3.4150147247387965e-05, "epoch": 12.463364715513713, "percentage": 38.07, "elapsed_time": "1:45:01", "remaining_time": "2:50:49", "throughput": 787.37, "total_tokens": 4961848} {"current_steps": 15235, "total_steps": 40000, "loss": 0.1764, "lr": 3.4141010274900306e-05, "epoch": 12.467458043389275, "percentage": 38.09, "elapsed_time": "1:45:03", "remaining_time": "2:50:46", "throughput": 787.4, "total_tokens": 4963432} {"current_steps": 15240, "total_steps": 40000, "loss": 0.1534, "lr": 3.413187189275399e-05, "epoch": 12.47155137126484, "percentage": 38.1, "elapsed_time": "1:45:05", "remaining_time": "2:50:43", "throughput": 787.44, "total_tokens": 4965032} {"current_steps": 15245, "total_steps": 40000, "loss": 0.2014, "lr": 3.4122732102358265e-05, "epoch": 12.475644699140402, "percentage": 38.11, "elapsed_time": "1:45:06", "remaining_time": "2:50:41", "throughput": 787.49, "total_tokens": 4966664} {"current_steps": 15250, "total_steps": 40000, "loss": 0.1839, "lr": 3.411359090512261e-05, "epoch": 12.479738027015964, "percentage": 38.12, "elapsed_time": "1:45:08", "remaining_time": "2:50:38", "throughput": 787.53, "total_tokens": 4968280} {"current_steps": 15255, "total_steps": 40000, "loss": 0.1922, "lr": 3.410444830245672e-05, "epoch": 12.483831354891526, "percentage": 38.14, "elapsed_time": "1:45:10", "remaining_time": "2:50:36", "throughput": 787.56, "total_tokens": 4969848} {"current_steps": 15260, "total_steps": 40000, "loss": 0.1537, "lr": 3.409530429577048e-05, "epoch": 12.48792468276709, "percentage": 38.15, "elapsed_time": "1:45:12", "remaining_time": "2:50:33", "throughput": 787.6, "total_tokens": 4971432} {"current_steps": 15265, "total_steps": 40000, "loss": 0.1519, "lr": 3.408615888647402e-05, "epoch": 12.492018010642653, "percentage": 38.16, "elapsed_time": "1:45:13", "remaining_time": "2:50:30", "throughput": 787.64, "total_tokens": 4973032} {"current_steps": 15270, "total_steps": 40000, "loss": 0.1521, "lr": 3.4077012075977675e-05, "epoch": 12.496111338518215, "percentage": 38.17, "elapsed_time": "1:45:15", "remaining_time": "2:50:28", "throughput": 787.68, "total_tokens": 4974664} {"current_steps": 15275, "total_steps": 40000, "loss": 0.2543, "lr": 3.4067863865692e-05, "epoch": 12.500204666393778, "percentage": 38.19, "elapsed_time": "1:45:17", "remaining_time": "2:50:25", "throughput": 787.72, "total_tokens": 4976248} {"current_steps": 15280, "total_steps": 40000, "loss": 0.2041, "lr": 3.4058714257027755e-05, "epoch": 12.504297994269342, "percentage": 38.2, "elapsed_time": "1:45:19", "remaining_time": "2:50:22", "throughput": 787.78, "total_tokens": 4977960} {"current_steps": 15285, "total_steps": 40000, "loss": 0.1491, "lr": 3.404956325139594e-05, "epoch": 12.508391322144904, "percentage": 38.21, "elapsed_time": "1:45:20", "remaining_time": "2:50:20", "throughput": 787.81, "total_tokens": 4979560} {"current_steps": 15290, "total_steps": 40000, "loss": 0.2147, "lr": 3.404041085020775e-05, "epoch": 12.512484650020467, "percentage": 38.22, "elapsed_time": "1:45:22", "remaining_time": "2:50:17", "throughput": 787.86, "total_tokens": 4981224} {"current_steps": 15295, "total_steps": 40000, "loss": 0.1668, "lr": 3.403125705487459e-05, "epoch": 12.516577977896029, "percentage": 38.24, "elapsed_time": "1:45:24", "remaining_time": "2:50:14", "throughput": 787.91, "total_tokens": 4982888} {"current_steps": 15300, "total_steps": 40000, "loss": 0.1786, "lr": 3.402210186680811e-05, "epoch": 12.520671305771593, "percentage": 38.25, "elapsed_time": "1:45:25", "remaining_time": "2:50:12", "throughput": 787.98, "total_tokens": 4984648} {"current_steps": 15305, "total_steps": 40000, "loss": 0.1586, "lr": 3.4012945287420137e-05, "epoch": 12.524764633647155, "percentage": 38.26, "elapsed_time": "1:45:27", "remaining_time": "2:50:09", "throughput": 788.02, "total_tokens": 4986248} {"current_steps": 15310, "total_steps": 40000, "loss": 0.1936, "lr": 3.400378731812274e-05, "epoch": 12.528857961522718, "percentage": 38.27, "elapsed_time": "1:45:29", "remaining_time": "2:50:07", "throughput": 788.06, "total_tokens": 4987880} {"current_steps": 15315, "total_steps": 40000, "loss": 0.2083, "lr": 3.399462796032817e-05, "epoch": 12.53295128939828, "percentage": 38.29, "elapsed_time": "1:45:31", "remaining_time": "2:50:04", "throughput": 788.11, "total_tokens": 4989544} {"current_steps": 15320, "total_steps": 40000, "loss": 0.1357, "lr": 3.3985467215448954e-05, "epoch": 12.537044617273844, "percentage": 38.3, "elapsed_time": "1:45:32", "remaining_time": "2:50:01", "throughput": 788.15, "total_tokens": 4991160} {"current_steps": 15325, "total_steps": 40000, "loss": 0.1601, "lr": 3.3976305084897776e-05, "epoch": 12.541137945149407, "percentage": 38.31, "elapsed_time": "1:45:34", "remaining_time": "2:49:59", "throughput": 788.19, "total_tokens": 4992760} {"current_steps": 15330, "total_steps": 40000, "loss": 0.1298, "lr": 3.3967141570087544e-05, "epoch": 12.545231273024969, "percentage": 38.32, "elapsed_time": "1:45:36", "remaining_time": "2:49:56", "throughput": 788.23, "total_tokens": 4994344} {"current_steps": 15335, "total_steps": 40000, "loss": 0.2183, "lr": 3.39579766724314e-05, "epoch": 12.549324600900531, "percentage": 38.34, "elapsed_time": "1:45:37", "remaining_time": "2:49:53", "throughput": 788.27, "total_tokens": 4995960} {"current_steps": 15340, "total_steps": 40000, "loss": 0.1896, "lr": 3.3948810393342677e-05, "epoch": 12.553417928776096, "percentage": 38.35, "elapsed_time": "1:45:39", "remaining_time": "2:49:51", "throughput": 788.31, "total_tokens": 4997576} {"current_steps": 15345, "total_steps": 40000, "loss": 0.1262, "lr": 3.3939642734234936e-05, "epoch": 12.557511256651658, "percentage": 38.36, "elapsed_time": "1:45:41", "remaining_time": "2:49:48", "throughput": 788.35, "total_tokens": 4999192} {"current_steps": 15350, "total_steps": 40000, "loss": 0.1648, "lr": 3.393047369652194e-05, "epoch": 12.56160458452722, "percentage": 38.38, "elapsed_time": "1:45:43", "remaining_time": "2:49:46", "throughput": 788.38, "total_tokens": 5000760} {"current_steps": 15355, "total_steps": 40000, "loss": 0.2377, "lr": 3.3921303281617664e-05, "epoch": 12.565697912402783, "percentage": 38.39, "elapsed_time": "1:45:44", "remaining_time": "2:49:43", "throughput": 788.42, "total_tokens": 5002376} {"current_steps": 15360, "total_steps": 40000, "loss": 0.113, "lr": 3.391213149093632e-05, "epoch": 12.569791240278347, "percentage": 38.4, "elapsed_time": "1:45:46", "remaining_time": "2:49:40", "throughput": 788.45, "total_tokens": 5003928} {"current_steps": 15365, "total_steps": 40000, "loss": 0.2452, "lr": 3.3902958325892303e-05, "epoch": 12.57388456815391, "percentage": 38.41, "elapsed_time": "1:45:48", "remaining_time": "2:49:38", "throughput": 788.5, "total_tokens": 5005560} {"current_steps": 15370, "total_steps": 40000, "loss": 0.1713, "lr": 3.389378378790023e-05, "epoch": 12.577977896029472, "percentage": 38.42, "elapsed_time": "1:45:49", "remaining_time": "2:49:35", "throughput": 788.54, "total_tokens": 5007192} {"current_steps": 15375, "total_steps": 40000, "loss": 0.1661, "lr": 3.388460787837493e-05, "epoch": 12.582071223905034, "percentage": 38.44, "elapsed_time": "1:45:51", "remaining_time": "2:49:32", "throughput": 788.59, "total_tokens": 5008824} {"current_steps": 15380, "total_steps": 40000, "loss": 0.2027, "lr": 3.387543059873145e-05, "epoch": 12.586164551780598, "percentage": 38.45, "elapsed_time": "1:45:53", "remaining_time": "2:49:30", "throughput": 788.62, "total_tokens": 5010408} {"current_steps": 15385, "total_steps": 40000, "loss": 0.1777, "lr": 3.386625195038503e-05, "epoch": 12.59025787965616, "percentage": 38.46, "elapsed_time": "1:45:55", "remaining_time": "2:49:27", "throughput": 788.67, "total_tokens": 5012040} {"current_steps": 15390, "total_steps": 40000, "loss": 0.2808, "lr": 3.3857071934751136e-05, "epoch": 12.594351207531723, "percentage": 38.48, "elapsed_time": "1:45:56", "remaining_time": "2:49:25", "throughput": 788.71, "total_tokens": 5013656} {"current_steps": 15395, "total_steps": 40000, "loss": 0.1488, "lr": 3.384789055324544e-05, "epoch": 12.598444535407285, "percentage": 38.49, "elapsed_time": "1:45:58", "remaining_time": "2:49:22", "throughput": 788.74, "total_tokens": 5015224} {"current_steps": 15400, "total_steps": 40000, "loss": 0.1291, "lr": 3.3838707807283843e-05, "epoch": 12.60253786328285, "percentage": 38.5, "elapsed_time": "1:46:00", "remaining_time": "2:49:19", "throughput": 788.78, "total_tokens": 5016856} {"current_steps": 15400, "total_steps": 40000, "eval_loss": 0.20341677963733673, "epoch": 12.60253786328285, "percentage": 38.5, "elapsed_time": "1:46:12", "remaining_time": "2:49:39", "throughput": 787.25, "total_tokens": 5016856} {"current_steps": 15405, "total_steps": 40000, "loss": 0.1366, "lr": 3.382952369828243e-05, "epoch": 12.606631191158412, "percentage": 38.51, "elapsed_time": "1:46:15", "remaining_time": "2:49:39", "throughput": 787.11, "total_tokens": 5018504} {"current_steps": 15410, "total_steps": 40000, "loss": 0.217, "lr": 3.38203382276575e-05, "epoch": 12.610724519033974, "percentage": 38.52, "elapsed_time": "1:46:17", "remaining_time": "2:49:36", "throughput": 787.17, "total_tokens": 5020216} {"current_steps": 15415, "total_steps": 40000, "loss": 0.1658, "lr": 3.381115139682557e-05, "epoch": 12.614817846909537, "percentage": 38.54, "elapsed_time": "1:46:19", "remaining_time": "2:49:34", "throughput": 787.21, "total_tokens": 5021832} {"current_steps": 15420, "total_steps": 40000, "loss": 0.2079, "lr": 3.3801963207203366e-05, "epoch": 12.6189111747851, "percentage": 38.55, "elapsed_time": "1:46:20", "remaining_time": "2:49:31", "throughput": 787.25, "total_tokens": 5023416} {"current_steps": 15425, "total_steps": 40000, "loss": 0.1586, "lr": 3.379277366020782e-05, "epoch": 12.623004502660663, "percentage": 38.56, "elapsed_time": "1:46:22", "remaining_time": "2:49:28", "throughput": 787.29, "total_tokens": 5025048} {"current_steps": 15430, "total_steps": 40000, "loss": 0.1473, "lr": 3.3783582757256085e-05, "epoch": 12.627097830536226, "percentage": 38.57, "elapsed_time": "1:46:24", "remaining_time": "2:49:26", "throughput": 787.34, "total_tokens": 5026680} {"current_steps": 15435, "total_steps": 40000, "loss": 0.1657, "lr": 3.3774390499765504e-05, "epoch": 12.631191158411788, "percentage": 38.59, "elapsed_time": "1:46:26", "remaining_time": "2:49:23", "throughput": 787.37, "total_tokens": 5028280} {"current_steps": 15440, "total_steps": 40000, "loss": 0.1853, "lr": 3.376519688915364e-05, "epoch": 12.635284486287352, "percentage": 38.6, "elapsed_time": "1:46:27", "remaining_time": "2:49:20", "throughput": 787.43, "total_tokens": 5029960} {"current_steps": 15445, "total_steps": 40000, "loss": 0.2743, "lr": 3.3756001926838273e-05, "epoch": 12.639377814162915, "percentage": 38.61, "elapsed_time": "1:46:29", "remaining_time": "2:49:18", "throughput": 787.48, "total_tokens": 5031640} {"current_steps": 15450, "total_steps": 40000, "loss": 0.1833, "lr": 3.374680561423737e-05, "epoch": 12.643471142038477, "percentage": 38.62, "elapsed_time": "1:46:31", "remaining_time": "2:49:15", "throughput": 787.53, "total_tokens": 5033336} {"current_steps": 15455, "total_steps": 40000, "loss": 0.2604, "lr": 3.373760795276912e-05, "epoch": 12.647564469914041, "percentage": 38.64, "elapsed_time": "1:46:33", "remaining_time": "2:49:13", "throughput": 787.57, "total_tokens": 5034952} {"current_steps": 15460, "total_steps": 40000, "loss": 0.206, "lr": 3.372840894385192e-05, "epoch": 12.651657797789603, "percentage": 38.65, "elapsed_time": "1:46:34", "remaining_time": "2:49:10", "throughput": 787.61, "total_tokens": 5036584} {"current_steps": 15465, "total_steps": 40000, "loss": 0.2019, "lr": 3.3719208588904375e-05, "epoch": 12.655751125665166, "percentage": 38.66, "elapsed_time": "1:46:36", "remaining_time": "2:49:07", "throughput": 787.67, "total_tokens": 5038280} {"current_steps": 15470, "total_steps": 40000, "loss": 0.1652, "lr": 3.371000688934529e-05, "epoch": 12.659844453540728, "percentage": 38.67, "elapsed_time": "1:46:38", "remaining_time": "2:49:05", "throughput": 787.7, "total_tokens": 5039832} {"current_steps": 15475, "total_steps": 40000, "loss": 0.2549, "lr": 3.370080384659369e-05, "epoch": 12.66393778141629, "percentage": 38.69, "elapsed_time": "1:46:39", "remaining_time": "2:49:02", "throughput": 787.74, "total_tokens": 5041432} {"current_steps": 15480, "total_steps": 40000, "loss": 0.1769, "lr": 3.36915994620688e-05, "epoch": 12.668031109291855, "percentage": 38.7, "elapsed_time": "1:46:41", "remaining_time": "2:48:59", "throughput": 787.78, "total_tokens": 5043080} {"current_steps": 15485, "total_steps": 40000, "loss": 0.2281, "lr": 3.3682393737190035e-05, "epoch": 12.672124437167417, "percentage": 38.71, "elapsed_time": "1:46:43", "remaining_time": "2:48:57", "throughput": 787.82, "total_tokens": 5044664} {"current_steps": 15490, "total_steps": 40000, "loss": 0.2689, "lr": 3.3673186673377054e-05, "epoch": 12.67621776504298, "percentage": 38.73, "elapsed_time": "1:46:45", "remaining_time": "2:48:54", "throughput": 787.85, "total_tokens": 5046216} {"current_steps": 15495, "total_steps": 40000, "loss": 0.1216, "lr": 3.366397827204969e-05, "epoch": 12.680311092918544, "percentage": 38.74, "elapsed_time": "1:46:46", "remaining_time": "2:48:52", "throughput": 787.9, "total_tokens": 5047864} {"current_steps": 15500, "total_steps": 40000, "loss": 0.2503, "lr": 3.3654768534628e-05, "epoch": 12.684404420794106, "percentage": 38.75, "elapsed_time": "1:46:48", "remaining_time": "2:48:49", "throughput": 787.94, "total_tokens": 5049480} {"current_steps": 15505, "total_steps": 40000, "loss": 0.1843, "lr": 3.3645557462532245e-05, "epoch": 12.688497748669668, "percentage": 38.76, "elapsed_time": "1:46:50", "remaining_time": "2:48:46", "throughput": 787.98, "total_tokens": 5051112} {"current_steps": 15510, "total_steps": 40000, "loss": 0.2006, "lr": 3.363634505718288e-05, "epoch": 12.69259107654523, "percentage": 38.77, "elapsed_time": "1:46:51", "remaining_time": "2:48:44", "throughput": 788.03, "total_tokens": 5052792} {"current_steps": 15515, "total_steps": 40000, "loss": 0.1769, "lr": 3.362713132000057e-05, "epoch": 12.696684404420795, "percentage": 38.79, "elapsed_time": "1:46:53", "remaining_time": "2:48:41", "throughput": 788.08, "total_tokens": 5054472} {"current_steps": 15520, "total_steps": 40000, "loss": 0.2141, "lr": 3.36179162524062e-05, "epoch": 12.700777732296357, "percentage": 38.8, "elapsed_time": "1:46:55", "remaining_time": "2:48:39", "throughput": 788.12, "total_tokens": 5056088} {"current_steps": 15525, "total_steps": 40000, "loss": 0.1943, "lr": 3.3608699855820846e-05, "epoch": 12.70487106017192, "percentage": 38.81, "elapsed_time": "1:46:57", "remaining_time": "2:48:36", "throughput": 788.18, "total_tokens": 5057768} {"current_steps": 15530, "total_steps": 40000, "loss": 0.1442, "lr": 3.359948213166578e-05, "epoch": 12.708964388047482, "percentage": 38.82, "elapsed_time": "1:46:58", "remaining_time": "2:48:33", "throughput": 788.21, "total_tokens": 5059368} {"current_steps": 15535, "total_steps": 40000, "loss": 0.193, "lr": 3.359026308136252e-05, "epoch": 12.713057715923046, "percentage": 38.84, "elapsed_time": "1:47:00", "remaining_time": "2:48:31", "throughput": 788.25, "total_tokens": 5060968} {"current_steps": 15540, "total_steps": 40000, "loss": 0.12, "lr": 3.358104270633272e-05, "epoch": 12.717151043798609, "percentage": 38.85, "elapsed_time": "1:47:02", "remaining_time": "2:48:28", "throughput": 788.3, "total_tokens": 5062616} {"current_steps": 15545, "total_steps": 40000, "loss": 0.1528, "lr": 3.357182100799831e-05, "epoch": 12.721244371674171, "percentage": 38.86, "elapsed_time": "1:47:03", "remaining_time": "2:48:25", "throughput": 788.34, "total_tokens": 5064248} {"current_steps": 15550, "total_steps": 40000, "loss": 0.1467, "lr": 3.3562597987781384e-05, "epoch": 12.725337699549733, "percentage": 38.88, "elapsed_time": "1:47:05", "remaining_time": "2:48:23", "throughput": 788.38, "total_tokens": 5065864} {"current_steps": 15555, "total_steps": 40000, "loss": 0.1928, "lr": 3.355337364710424e-05, "epoch": 12.729431027425298, "percentage": 38.89, "elapsed_time": "1:47:07", "remaining_time": "2:48:20", "throughput": 788.43, "total_tokens": 5067560} {"current_steps": 15560, "total_steps": 40000, "loss": 0.2919, "lr": 3.354414798738939e-05, "epoch": 12.73352435530086, "percentage": 38.9, "elapsed_time": "1:47:09", "remaining_time": "2:48:18", "throughput": 788.48, "total_tokens": 5069224} {"current_steps": 15565, "total_steps": 40000, "loss": 0.2632, "lr": 3.353492101005955e-05, "epoch": 12.737617683176422, "percentage": 38.91, "elapsed_time": "1:47:10", "remaining_time": "2:48:15", "throughput": 788.53, "total_tokens": 5070904} {"current_steps": 15570, "total_steps": 40000, "loss": 0.2093, "lr": 3.352569271653763e-05, "epoch": 12.741711011051985, "percentage": 38.92, "elapsed_time": "1:47:12", "remaining_time": "2:48:12", "throughput": 788.57, "total_tokens": 5072472} {"current_steps": 15575, "total_steps": 40000, "loss": 0.1783, "lr": 3.351646310824675e-05, "epoch": 12.745804338927549, "percentage": 38.94, "elapsed_time": "1:47:14", "remaining_time": "2:48:10", "throughput": 788.61, "total_tokens": 5074072} {"current_steps": 15580, "total_steps": 40000, "loss": 0.153, "lr": 3.350723218661023e-05, "epoch": 12.749897666803111, "percentage": 38.95, "elapsed_time": "1:47:15", "remaining_time": "2:48:07", "throughput": 788.64, "total_tokens": 5075656} {"current_steps": 15585, "total_steps": 40000, "loss": 0.1812, "lr": 3.349799995305162e-05, "epoch": 12.753990994678674, "percentage": 38.96, "elapsed_time": "1:47:17", "remaining_time": "2:48:05", "throughput": 788.7, "total_tokens": 5077384} {"current_steps": 15590, "total_steps": 40000, "loss": 0.1643, "lr": 3.348876640899461e-05, "epoch": 12.758084322554236, "percentage": 38.98, "elapsed_time": "1:47:19", "remaining_time": "2:48:02", "throughput": 788.74, "total_tokens": 5079000} {"current_steps": 15595, "total_steps": 40000, "loss": 0.1277, "lr": 3.3479531555863144e-05, "epoch": 12.7621776504298, "percentage": 38.99, "elapsed_time": "1:47:21", "remaining_time": "2:47:59", "throughput": 788.78, "total_tokens": 5080600} {"current_steps": 15600, "total_steps": 40000, "loss": 0.1437, "lr": 3.3470295395081344e-05, "epoch": 12.766270978305363, "percentage": 39.0, "elapsed_time": "1:47:22", "remaining_time": "2:47:57", "throughput": 788.82, "total_tokens": 5082248} {"current_steps": 15600, "total_steps": 40000, "eval_loss": 0.20600585639476776, "epoch": 12.766270978305363, "percentage": 39.0, "elapsed_time": "1:47:35", "remaining_time": "2:48:16", "throughput": 787.3, "total_tokens": 5082248} {"current_steps": 15605, "total_steps": 40000, "loss": 0.2277, "lr": 3.3461057928073556e-05, "epoch": 12.770364306180925, "percentage": 39.01, "elapsed_time": "1:47:38", "remaining_time": "2:48:16", "throughput": 787.14, "total_tokens": 5083912} {"current_steps": 15610, "total_steps": 40000, "loss": 0.2164, "lr": 3.345181915626431e-05, "epoch": 12.774457634056487, "percentage": 39.02, "elapsed_time": "1:47:40", "remaining_time": "2:48:14", "throughput": 787.18, "total_tokens": 5085496} {"current_steps": 15615, "total_steps": 40000, "loss": 0.2181, "lr": 3.344257908107834e-05, "epoch": 12.778550961932051, "percentage": 39.04, "elapsed_time": "1:47:42", "remaining_time": "2:48:11", "throughput": 787.23, "total_tokens": 5087176} {"current_steps": 15620, "total_steps": 40000, "loss": 0.1679, "lr": 3.343333770394058e-05, "epoch": 12.782644289807614, "percentage": 39.05, "elapsed_time": "1:47:43", "remaining_time": "2:48:08", "throughput": 787.28, "total_tokens": 5088824} {"current_steps": 15625, "total_steps": 40000, "loss": 0.1941, "lr": 3.342409502627616e-05, "epoch": 12.786737617683176, "percentage": 39.06, "elapsed_time": "1:47:45", "remaining_time": "2:48:06", "throughput": 787.32, "total_tokens": 5090472} {"current_steps": 15630, "total_steps": 40000, "loss": 0.1507, "lr": 3.341485104951043e-05, "epoch": 12.790830945558739, "percentage": 39.07, "elapsed_time": "1:47:47", "remaining_time": "2:48:03", "throughput": 787.36, "total_tokens": 5092056} {"current_steps": 15635, "total_steps": 40000, "loss": 0.0993, "lr": 3.340560577506892e-05, "epoch": 12.794924273434303, "percentage": 39.09, "elapsed_time": "1:47:49", "remaining_time": "2:48:01", "throughput": 787.4, "total_tokens": 5093704} {"current_steps": 15640, "total_steps": 40000, "loss": 0.2224, "lr": 3.339635920437735e-05, "epoch": 12.799017601309865, "percentage": 39.1, "elapsed_time": "1:47:50", "remaining_time": "2:47:58", "throughput": 787.45, "total_tokens": 5095352} {"current_steps": 15645, "total_steps": 40000, "loss": 0.1705, "lr": 3.338711133886169e-05, "epoch": 12.803110929185427, "percentage": 39.11, "elapsed_time": "1:47:52", "remaining_time": "2:47:55", "throughput": 787.49, "total_tokens": 5097000} {"current_steps": 15650, "total_steps": 40000, "loss": 0.2146, "lr": 3.3377862179948064e-05, "epoch": 12.80720425706099, "percentage": 39.12, "elapsed_time": "1:47:54", "remaining_time": "2:47:53", "throughput": 787.53, "total_tokens": 5098616} {"current_steps": 15655, "total_steps": 40000, "loss": 0.207, "lr": 3.336861172906281e-05, "epoch": 12.811297584936554, "percentage": 39.14, "elapsed_time": "1:47:55", "remaining_time": "2:47:50", "throughput": 787.57, "total_tokens": 5100184} {"current_steps": 15660, "total_steps": 40000, "loss": 0.1814, "lr": 3.335935998763245e-05, "epoch": 12.815390912812116, "percentage": 39.15, "elapsed_time": "1:47:57", "remaining_time": "2:47:47", "throughput": 787.61, "total_tokens": 5101832} {"current_steps": 15665, "total_steps": 40000, "loss": 0.1422, "lr": 3.3350106957083744e-05, "epoch": 12.819484240687679, "percentage": 39.16, "elapsed_time": "1:47:59", "remaining_time": "2:47:45", "throughput": 787.65, "total_tokens": 5103432} {"current_steps": 15670, "total_steps": 40000, "loss": 0.1522, "lr": 3.33408526388436e-05, "epoch": 12.823577568563241, "percentage": 39.17, "elapsed_time": "1:48:01", "remaining_time": "2:47:42", "throughput": 787.69, "total_tokens": 5105032} {"current_steps": 15675, "total_steps": 40000, "loss": 0.2006, "lr": 3.3331597034339166e-05, "epoch": 12.827670896438805, "percentage": 39.19, "elapsed_time": "1:48:02", "remaining_time": "2:47:40", "throughput": 787.74, "total_tokens": 5106696} {"current_steps": 15680, "total_steps": 40000, "loss": 0.1945, "lr": 3.3322340144997764e-05, "epoch": 12.831764224314368, "percentage": 39.2, "elapsed_time": "1:48:04", "remaining_time": "2:47:37", "throughput": 787.78, "total_tokens": 5108328} {"current_steps": 15685, "total_steps": 40000, "loss": 0.1811, "lr": 3.331308197224693e-05, "epoch": 12.83585755218993, "percentage": 39.21, "elapsed_time": "1:48:06", "remaining_time": "2:47:34", "throughput": 787.83, "total_tokens": 5109992} {"current_steps": 15690, "total_steps": 40000, "loss": 0.1642, "lr": 3.330382251751438e-05, "epoch": 12.839950880065492, "percentage": 39.23, "elapsed_time": "1:48:07", "remaining_time": "2:47:32", "throughput": 787.86, "total_tokens": 5111592} {"current_steps": 15695, "total_steps": 40000, "loss": 0.1506, "lr": 3.3294561782228054e-05, "epoch": 12.844044207941057, "percentage": 39.24, "elapsed_time": "1:48:09", "remaining_time": "2:47:29", "throughput": 787.9, "total_tokens": 5113208} {"current_steps": 15700, "total_steps": 40000, "loss": 0.2408, "lr": 3.328529976781607e-05, "epoch": 12.848137535816619, "percentage": 39.25, "elapsed_time": "1:48:11", "remaining_time": "2:47:27", "throughput": 787.95, "total_tokens": 5114840} {"current_steps": 15705, "total_steps": 40000, "loss": 0.1356, "lr": 3.327603647570673e-05, "epoch": 12.852230863692181, "percentage": 39.26, "elapsed_time": "1:48:13", "remaining_time": "2:47:24", "throughput": 787.99, "total_tokens": 5116456} {"current_steps": 15710, "total_steps": 40000, "loss": 0.2621, "lr": 3.326677190732857e-05, "epoch": 12.856324191567744, "percentage": 39.27, "elapsed_time": "1:48:14", "remaining_time": "2:47:21", "throughput": 788.04, "total_tokens": 5118136} {"current_steps": 15715, "total_steps": 40000, "loss": 0.2081, "lr": 3.325750606411029e-05, "epoch": 12.860417519443308, "percentage": 39.29, "elapsed_time": "1:48:16", "remaining_time": "2:47:19", "throughput": 788.07, "total_tokens": 5119720} {"current_steps": 15720, "total_steps": 40000, "loss": 0.1978, "lr": 3.3248238947480804e-05, "epoch": 12.86451084731887, "percentage": 39.3, "elapsed_time": "1:48:18", "remaining_time": "2:47:16", "throughput": 788.1, "total_tokens": 5121224} {"current_steps": 15725, "total_steps": 40000, "loss": 0.1565, "lr": 3.323897055886922e-05, "epoch": 12.868604175194433, "percentage": 39.31, "elapsed_time": "1:48:19", "remaining_time": "2:47:14", "throughput": 788.13, "total_tokens": 5122808} {"current_steps": 15730, "total_steps": 40000, "loss": 0.2215, "lr": 3.322970089970484e-05, "epoch": 12.872697503069997, "percentage": 39.32, "elapsed_time": "1:48:21", "remaining_time": "2:47:11", "throughput": 788.18, "total_tokens": 5124456} {"current_steps": 15735, "total_steps": 40000, "loss": 0.1377, "lr": 3.3220429971417165e-05, "epoch": 12.87679083094556, "percentage": 39.34, "elapsed_time": "1:48:23", "remaining_time": "2:47:08", "throughput": 788.22, "total_tokens": 5126072} {"current_steps": 15740, "total_steps": 40000, "loss": 0.1677, "lr": 3.321115777543588e-05, "epoch": 12.880884158821122, "percentage": 39.35, "elapsed_time": "1:48:25", "remaining_time": "2:47:06", "throughput": 788.26, "total_tokens": 5127704} {"current_steps": 15745, "total_steps": 40000, "loss": 0.2886, "lr": 3.320188431319088e-05, "epoch": 12.884977486696684, "percentage": 39.36, "elapsed_time": "1:48:26", "remaining_time": "2:47:03", "throughput": 788.31, "total_tokens": 5129368} {"current_steps": 15750, "total_steps": 40000, "loss": 0.1744, "lr": 3.319260958611224e-05, "epoch": 12.889070814572246, "percentage": 39.38, "elapsed_time": "1:48:28", "remaining_time": "2:47:01", "throughput": 788.34, "total_tokens": 5130936} {"current_steps": 15755, "total_steps": 40000, "loss": 0.178, "lr": 3.3183333595630256e-05, "epoch": 12.89316414244781, "percentage": 39.39, "elapsed_time": "1:48:30", "remaining_time": "2:46:58", "throughput": 788.38, "total_tokens": 5132568} {"current_steps": 15760, "total_steps": 40000, "loss": 0.1926, "lr": 3.317405634317538e-05, "epoch": 12.897257470323373, "percentage": 39.4, "elapsed_time": "1:48:32", "remaining_time": "2:46:55", "throughput": 788.41, "total_tokens": 5134152} {"current_steps": 15765, "total_steps": 40000, "loss": 0.1585, "lr": 3.3164777830178315e-05, "epoch": 12.901350798198935, "percentage": 39.41, "elapsed_time": "1:48:33", "remaining_time": "2:46:53", "throughput": 788.45, "total_tokens": 5135736} {"current_steps": 15770, "total_steps": 40000, "loss": 0.1693, "lr": 3.315549805806989e-05, "epoch": 12.9054441260745, "percentage": 39.42, "elapsed_time": "1:48:35", "remaining_time": "2:46:50", "throughput": 788.5, "total_tokens": 5137416} {"current_steps": 15775, "total_steps": 40000, "loss": 0.1746, "lr": 3.314621702828118e-05, "epoch": 12.909537453950062, "percentage": 39.44, "elapsed_time": "1:48:37", "remaining_time": "2:46:48", "throughput": 788.54, "total_tokens": 5139064} {"current_steps": 15780, "total_steps": 40000, "loss": 0.1947, "lr": 3.313693474224342e-05, "epoch": 12.913630781825624, "percentage": 39.45, "elapsed_time": "1:48:38", "remaining_time": "2:46:45", "throughput": 788.58, "total_tokens": 5140680} {"current_steps": 15785, "total_steps": 40000, "loss": 0.1852, "lr": 3.312765120138809e-05, "epoch": 12.917724109701187, "percentage": 39.46, "elapsed_time": "1:48:40", "remaining_time": "2:46:42", "throughput": 788.63, "total_tokens": 5142296} {"current_steps": 15790, "total_steps": 40000, "loss": 0.159, "lr": 3.311836640714679e-05, "epoch": 12.92181743757675, "percentage": 39.48, "elapsed_time": "1:48:42", "remaining_time": "2:46:40", "throughput": 788.68, "total_tokens": 5144008} {"current_steps": 15795, "total_steps": 40000, "loss": 0.1919, "lr": 3.310908036095137e-05, "epoch": 12.925910765452313, "percentage": 39.49, "elapsed_time": "1:48:44", "remaining_time": "2:46:37", "throughput": 788.72, "total_tokens": 5145640} {"current_steps": 15800, "total_steps": 40000, "loss": 0.2195, "lr": 3.309979306423386e-05, "epoch": 12.930004093327875, "percentage": 39.5, "elapsed_time": "1:48:45", "remaining_time": "2:46:35", "throughput": 788.76, "total_tokens": 5147240} {"current_steps": 15800, "total_steps": 40000, "eval_loss": 0.20526544749736786, "epoch": 12.930004093327875, "percentage": 39.5, "elapsed_time": "1:48:58", "remaining_time": "2:46:54", "throughput": 787.25, "total_tokens": 5147240} {"current_steps": 15805, "total_steps": 40000, "loss": 0.1959, "lr": 3.309050451842647e-05, "epoch": 12.934097421203438, "percentage": 39.51, "elapsed_time": "1:49:01", "remaining_time": "2:46:53", "throughput": 787.12, "total_tokens": 5148872} {"current_steps": 15810, "total_steps": 40000, "loss": 0.1489, "lr": 3.3081214724961604e-05, "epoch": 12.938190749079002, "percentage": 39.52, "elapsed_time": "1:49:03", "remaining_time": "2:46:51", "throughput": 787.15, "total_tokens": 5150456} {"current_steps": 15815, "total_steps": 40000, "loss": 0.1676, "lr": 3.307192368527188e-05, "epoch": 12.942284076954564, "percentage": 39.54, "elapsed_time": "1:49:04", "remaining_time": "2:46:48", "throughput": 787.19, "total_tokens": 5152056} {"current_steps": 15820, "total_steps": 40000, "loss": 0.2251, "lr": 3.306263140079008e-05, "epoch": 12.946377404830127, "percentage": 39.55, "elapsed_time": "1:49:06", "remaining_time": "2:46:46", "throughput": 787.24, "total_tokens": 5153704} {"current_steps": 15825, "total_steps": 40000, "loss": 0.182, "lr": 3.30533378729492e-05, "epoch": 12.95047073270569, "percentage": 39.56, "elapsed_time": "1:49:08", "remaining_time": "2:46:43", "throughput": 787.29, "total_tokens": 5155400} {"current_steps": 15830, "total_steps": 40000, "loss": 0.1116, "lr": 3.304404310318242e-05, "epoch": 12.954564060581253, "percentage": 39.57, "elapsed_time": "1:49:10", "remaining_time": "2:46:40", "throughput": 787.34, "total_tokens": 5157064} {"current_steps": 15835, "total_steps": 40000, "loss": 0.2489, "lr": 3.3034747092923105e-05, "epoch": 12.958657388456816, "percentage": 39.59, "elapsed_time": "1:49:11", "remaining_time": "2:46:38", "throughput": 787.39, "total_tokens": 5158760} {"current_steps": 15840, "total_steps": 40000, "loss": 0.1723, "lr": 3.3025449843604806e-05, "epoch": 12.962750716332378, "percentage": 39.6, "elapsed_time": "1:49:13", "remaining_time": "2:46:35", "throughput": 787.43, "total_tokens": 5160376} {"current_steps": 15845, "total_steps": 40000, "loss": 0.2335, "lr": 3.30161513566613e-05, "epoch": 12.96684404420794, "percentage": 39.61, "elapsed_time": "1:49:15", "remaining_time": "2:46:33", "throughput": 787.46, "total_tokens": 5161960} {"current_steps": 15850, "total_steps": 40000, "loss": 0.158, "lr": 3.3006851633526506e-05, "epoch": 12.970937372083505, "percentage": 39.62, "elapsed_time": "1:49:16", "remaining_time": "2:46:30", "throughput": 787.51, "total_tokens": 5163592} {"current_steps": 15855, "total_steps": 40000, "loss": 0.1284, "lr": 3.2997550675634584e-05, "epoch": 12.975030699959067, "percentage": 39.64, "elapsed_time": "1:49:18", "remaining_time": "2:46:27", "throughput": 787.54, "total_tokens": 5165192} {"current_steps": 15860, "total_steps": 40000, "loss": 0.1971, "lr": 3.2988248484419825e-05, "epoch": 12.97912402783463, "percentage": 39.65, "elapsed_time": "1:49:20", "remaining_time": "2:46:25", "throughput": 787.58, "total_tokens": 5166824} {"current_steps": 15865, "total_steps": 40000, "loss": 0.2499, "lr": 3.2978945061316776e-05, "epoch": 12.983217355710192, "percentage": 39.66, "elapsed_time": "1:49:22", "remaining_time": "2:46:22", "throughput": 787.63, "total_tokens": 5168456} {"current_steps": 15870, "total_steps": 40000, "loss": 0.1711, "lr": 3.296964040776013e-05, "epoch": 12.987310683585756, "percentage": 39.67, "elapsed_time": "1:49:23", "remaining_time": "2:46:20", "throughput": 787.66, "total_tokens": 5170056} {"current_steps": 15875, "total_steps": 40000, "loss": 0.1335, "lr": 3.296033452518478e-05, "epoch": 12.991404011461318, "percentage": 39.69, "elapsed_time": "1:49:25", "remaining_time": "2:46:17", "throughput": 787.71, "total_tokens": 5171704} {"current_steps": 15880, "total_steps": 40000, "loss": 0.1989, "lr": 3.2951027415025806e-05, "epoch": 12.99549733933688, "percentage": 39.7, "elapsed_time": "1:49:27", "remaining_time": "2:46:14", "throughput": 787.75, "total_tokens": 5173304} {"current_steps": 15885, "total_steps": 40000, "loss": 0.1775, "lr": 3.294171907871849e-05, "epoch": 12.999590667212443, "percentage": 39.71, "elapsed_time": "1:49:28", "remaining_time": "2:46:12", "throughput": 787.79, "total_tokens": 5174936} {"current_steps": 15890, "total_steps": 40000, "loss": 0.2151, "lr": 3.293240951769828e-05, "epoch": 13.00327466230045, "percentage": 39.73, "elapsed_time": "1:49:30", "remaining_time": "2:46:09", "throughput": 787.78, "total_tokens": 5176344} {"current_steps": 15895, "total_steps": 40000, "loss": 0.1713, "lr": 3.2923098733400846e-05, "epoch": 13.007367990176013, "percentage": 39.74, "elapsed_time": "1:49:32", "remaining_time": "2:46:07", "throughput": 787.82, "total_tokens": 5177976} {"current_steps": 15900, "total_steps": 40000, "loss": 0.1106, "lr": 3.291378672726202e-05, "epoch": 13.011461318051577, "percentage": 39.75, "elapsed_time": "1:49:34", "remaining_time": "2:46:04", "throughput": 787.88, "total_tokens": 5179736} {"current_steps": 15905, "total_steps": 40000, "loss": 0.193, "lr": 3.2904473500717824e-05, "epoch": 13.01555464592714, "percentage": 39.76, "elapsed_time": "1:49:36", "remaining_time": "2:46:02", "throughput": 787.92, "total_tokens": 5181368} {"current_steps": 15910, "total_steps": 40000, "loss": 0.1665, "lr": 3.289515905520449e-05, "epoch": 13.019647973802702, "percentage": 39.77, "elapsed_time": "1:49:37", "remaining_time": "2:45:59", "throughput": 787.98, "total_tokens": 5183096} {"current_steps": 15915, "total_steps": 40000, "loss": 0.2222, "lr": 3.288584339215841e-05, "epoch": 13.023741301678264, "percentage": 39.79, "elapsed_time": "1:49:39", "remaining_time": "2:45:57", "throughput": 788.02, "total_tokens": 5184728} {"current_steps": 15920, "total_steps": 40000, "loss": 0.2508, "lr": 3.287652651301617e-05, "epoch": 13.027834629553828, "percentage": 39.8, "elapsed_time": "1:49:41", "remaining_time": "2:45:54", "throughput": 788.05, "total_tokens": 5186312} {"current_steps": 15925, "total_steps": 40000, "loss": 0.174, "lr": 3.286720841921457e-05, "epoch": 13.03192795742939, "percentage": 39.81, "elapsed_time": "1:49:42", "remaining_time": "2:45:51", "throughput": 788.11, "total_tokens": 5188024} {"current_steps": 15930, "total_steps": 40000, "loss": 0.1955, "lr": 3.285788911219056e-05, "epoch": 13.036021285304953, "percentage": 39.83, "elapsed_time": "1:49:44", "remaining_time": "2:45:49", "throughput": 788.15, "total_tokens": 5189656} {"current_steps": 15935, "total_steps": 40000, "loss": 0.1728, "lr": 3.284856859338131e-05, "epoch": 13.040114613180515, "percentage": 39.84, "elapsed_time": "1:49:46", "remaining_time": "2:45:46", "throughput": 788.19, "total_tokens": 5191256} {"current_steps": 15940, "total_steps": 40000, "loss": 0.2132, "lr": 3.283924686422414e-05, "epoch": 13.04420794105608, "percentage": 39.85, "elapsed_time": "1:49:48", "remaining_time": "2:45:44", "throughput": 788.22, "total_tokens": 5192840} {"current_steps": 15945, "total_steps": 40000, "loss": 0.1377, "lr": 3.282992392615659e-05, "epoch": 13.048301268931642, "percentage": 39.86, "elapsed_time": "1:49:49", "remaining_time": "2:45:41", "throughput": 788.26, "total_tokens": 5194440} {"current_steps": 15950, "total_steps": 40000, "loss": 0.1926, "lr": 3.282059978061638e-05, "epoch": 13.052394596807204, "percentage": 39.88, "elapsed_time": "1:49:51", "remaining_time": "2:45:38", "throughput": 788.3, "total_tokens": 5196088} {"current_steps": 15955, "total_steps": 40000, "loss": 0.1638, "lr": 3.28112744290414e-05, "epoch": 13.056487924682767, "percentage": 39.89, "elapsed_time": "1:49:53", "remaining_time": "2:45:36", "throughput": 788.36, "total_tokens": 5197800} {"current_steps": 15960, "total_steps": 40000, "loss": 0.1449, "lr": 3.280194787286974e-05, "epoch": 13.06058125255833, "percentage": 39.9, "elapsed_time": "1:49:54", "remaining_time": "2:45:33", "throughput": 788.4, "total_tokens": 5199464} {"current_steps": 15965, "total_steps": 40000, "loss": 0.1461, "lr": 3.2792620113539674e-05, "epoch": 13.064674580433893, "percentage": 39.91, "elapsed_time": "1:49:56", "remaining_time": "2:45:31", "throughput": 788.44, "total_tokens": 5201080} {"current_steps": 15970, "total_steps": 40000, "loss": 0.1886, "lr": 3.278329115248966e-05, "epoch": 13.068767908309455, "percentage": 39.92, "elapsed_time": "1:49:58", "remaining_time": "2:45:28", "throughput": 788.49, "total_tokens": 5202728} {"current_steps": 15975, "total_steps": 40000, "loss": 0.191, "lr": 3.277396099115834e-05, "epoch": 13.072861236185018, "percentage": 39.94, "elapsed_time": "1:50:00", "remaining_time": "2:45:25", "throughput": 788.52, "total_tokens": 5204328} {"current_steps": 15980, "total_steps": 40000, "loss": 0.192, "lr": 3.276462963098454e-05, "epoch": 13.076954564060582, "percentage": 39.95, "elapsed_time": "1:50:01", "remaining_time": "2:45:23", "throughput": 788.55, "total_tokens": 5205896} {"current_steps": 15985, "total_steps": 40000, "loss": 0.1391, "lr": 3.275529707340728e-05, "epoch": 13.081047891936144, "percentage": 39.96, "elapsed_time": "1:50:03", "remaining_time": "2:45:20", "throughput": 788.59, "total_tokens": 5207496} {"current_steps": 15990, "total_steps": 40000, "loss": 0.2767, "lr": 3.274596331986574e-05, "epoch": 13.085141219811707, "percentage": 39.98, "elapsed_time": "1:50:05", "remaining_time": "2:45:18", "throughput": 788.64, "total_tokens": 5209160} {"current_steps": 15995, "total_steps": 40000, "loss": 0.1861, "lr": 3.273662837179932e-05, "epoch": 13.08923454768727, "percentage": 39.99, "elapsed_time": "1:50:06", "remaining_time": "2:45:15", "throughput": 788.68, "total_tokens": 5210776} {"current_steps": 16000, "total_steps": 40000, "loss": 0.248, "lr": 3.272729223064758e-05, "epoch": 13.093327875562833, "percentage": 40.0, "elapsed_time": "1:50:08", "remaining_time": "2:45:13", "throughput": 788.72, "total_tokens": 5212440} {"current_steps": 16000, "total_steps": 40000, "eval_loss": 0.20550315082073212, "epoch": 13.093327875562833, "percentage": 40.0, "elapsed_time": "1:50:21", "remaining_time": "2:45:31", "throughput": 787.24, "total_tokens": 5212440} {"current_steps": 16005, "total_steps": 40000, "loss": 0.1347, "lr": 3.2717954897850264e-05, "epoch": 13.097421203438396, "percentage": 40.01, "elapsed_time": "1:50:24", "remaining_time": "2:45:31", "throughput": 787.07, "total_tokens": 5214008} {"current_steps": 16010, "total_steps": 40000, "loss": 0.1473, "lr": 3.270861637484733e-05, "epoch": 13.101514531313958, "percentage": 40.02, "elapsed_time": "1:50:26", "remaining_time": "2:45:29", "throughput": 787.1, "total_tokens": 5215592} {"current_steps": 16015, "total_steps": 40000, "loss": 0.2019, "lr": 3.2699276663078867e-05, "epoch": 13.10560785918952, "percentage": 40.04, "elapsed_time": "1:50:28", "remaining_time": "2:45:26", "throughput": 787.15, "total_tokens": 5217224} {"current_steps": 16020, "total_steps": 40000, "loss": 0.2049, "lr": 3.268993576398519e-05, "epoch": 13.109701187065085, "percentage": 40.05, "elapsed_time": "1:50:29", "remaining_time": "2:45:23", "throughput": 787.18, "total_tokens": 5218824} {"current_steps": 16025, "total_steps": 40000, "loss": 0.1875, "lr": 3.268059367900678e-05, "epoch": 13.113794514940647, "percentage": 40.06, "elapsed_time": "1:50:31", "remaining_time": "2:45:21", "throughput": 787.22, "total_tokens": 5220424} {"current_steps": 16030, "total_steps": 40000, "loss": 0.1179, "lr": 3.26712504095843e-05, "epoch": 13.11788784281621, "percentage": 40.08, "elapsed_time": "1:50:33", "remaining_time": "2:45:18", "throughput": 787.26, "total_tokens": 5222056} {"current_steps": 16035, "total_steps": 40000, "loss": 0.249, "lr": 3.2661905957158615e-05, "epoch": 13.121981170691772, "percentage": 40.09, "elapsed_time": "1:50:34", "remaining_time": "2:45:16", "throughput": 787.3, "total_tokens": 5223688} {"current_steps": 16040, "total_steps": 40000, "loss": 0.1672, "lr": 3.2652560323170734e-05, "epoch": 13.126074498567336, "percentage": 40.1, "elapsed_time": "1:50:36", "remaining_time": "2:45:13", "throughput": 787.34, "total_tokens": 5225304} {"current_steps": 16045, "total_steps": 40000, "loss": 0.1308, "lr": 3.264321350906189e-05, "epoch": 13.130167826442898, "percentage": 40.11, "elapsed_time": "1:50:38", "remaining_time": "2:45:11", "throughput": 787.39, "total_tokens": 5227000} {"current_steps": 16050, "total_steps": 40000, "loss": 0.1362, "lr": 3.263386551627346e-05, "epoch": 13.13426115431846, "percentage": 40.12, "elapsed_time": "1:50:40", "remaining_time": "2:45:08", "throughput": 787.45, "total_tokens": 5228712} {"current_steps": 16055, "total_steps": 40000, "loss": 0.1672, "lr": 3.2624516346247055e-05, "epoch": 13.138354482194023, "percentage": 40.14, "elapsed_time": "1:50:41", "remaining_time": "2:45:05", "throughput": 787.5, "total_tokens": 5230440} {"current_steps": 16060, "total_steps": 40000, "loss": 0.2583, "lr": 3.2615166000424404e-05, "epoch": 13.142447810069587, "percentage": 40.15, "elapsed_time": "1:50:43", "remaining_time": "2:45:03", "throughput": 787.54, "total_tokens": 5232072} {"current_steps": 16065, "total_steps": 40000, "loss": 0.2421, "lr": 3.260581448024745e-05, "epoch": 13.14654113794515, "percentage": 40.16, "elapsed_time": "1:50:45", "remaining_time": "2:45:00", "throughput": 787.59, "total_tokens": 5233720} {"current_steps": 16070, "total_steps": 40000, "loss": 0.2089, "lr": 3.2596461787158335e-05, "epoch": 13.150634465820712, "percentage": 40.17, "elapsed_time": "1:50:46", "remaining_time": "2:44:58", "throughput": 787.62, "total_tokens": 5235304} {"current_steps": 16075, "total_steps": 40000, "loss": 0.1359, "lr": 3.258710792259934e-05, "epoch": 13.154727793696274, "percentage": 40.19, "elapsed_time": "1:50:48", "remaining_time": "2:44:55", "throughput": 787.67, "total_tokens": 5236984} {"current_steps": 16080, "total_steps": 40000, "loss": 0.2271, "lr": 3.257775288801296e-05, "epoch": 13.158821121571838, "percentage": 40.2, "elapsed_time": "1:50:50", "remaining_time": "2:44:52", "throughput": 787.71, "total_tokens": 5238616} {"current_steps": 16085, "total_steps": 40000, "loss": 0.1913, "lr": 3.256839668484186e-05, "epoch": 13.1629144494474, "percentage": 40.21, "elapsed_time": "1:50:52", "remaining_time": "2:44:50", "throughput": 787.75, "total_tokens": 5240232} {"current_steps": 16090, "total_steps": 40000, "loss": 0.1552, "lr": 3.255903931452888e-05, "epoch": 13.167007777322963, "percentage": 40.23, "elapsed_time": "1:50:53", "remaining_time": "2:44:47", "throughput": 787.79, "total_tokens": 5241848} {"current_steps": 16095, "total_steps": 40000, "loss": 0.2094, "lr": 3.2549680778517045e-05, "epoch": 13.171101105198526, "percentage": 40.24, "elapsed_time": "1:50:55", "remaining_time": "2:44:45", "throughput": 787.83, "total_tokens": 5243464} {"current_steps": 16100, "total_steps": 40000, "loss": 0.1273, "lr": 3.2540321078249556e-05, "epoch": 13.17519443307409, "percentage": 40.25, "elapsed_time": "1:50:57", "remaining_time": "2:44:42", "throughput": 787.87, "total_tokens": 5245096} {"current_steps": 16105, "total_steps": 40000, "loss": 0.121, "lr": 3.2530960215169795e-05, "epoch": 13.179287760949652, "percentage": 40.26, "elapsed_time": "1:50:58", "remaining_time": "2:44:39", "throughput": 787.93, "total_tokens": 5246792} {"current_steps": 16110, "total_steps": 40000, "loss": 0.1951, "lr": 3.2521598190721345e-05, "epoch": 13.183381088825215, "percentage": 40.27, "elapsed_time": "1:51:00", "remaining_time": "2:44:37", "throughput": 787.96, "total_tokens": 5248392} {"current_steps": 16115, "total_steps": 40000, "loss": 0.1865, "lr": 3.251223500634792e-05, "epoch": 13.187474416700777, "percentage": 40.29, "elapsed_time": "1:51:02", "remaining_time": "2:44:34", "throughput": 788.0, "total_tokens": 5250040} {"current_steps": 16120, "total_steps": 40000, "loss": 0.1221, "lr": 3.2502870663493445e-05, "epoch": 13.191567744576341, "percentage": 40.3, "elapsed_time": "1:51:04", "remaining_time": "2:44:32", "throughput": 788.06, "total_tokens": 5251736} {"current_steps": 16125, "total_steps": 40000, "loss": 0.1729, "lr": 3.249350516360203e-05, "epoch": 13.195661072451903, "percentage": 40.31, "elapsed_time": "1:51:05", "remaining_time": "2:44:29", "throughput": 788.1, "total_tokens": 5253384} {"current_steps": 16130, "total_steps": 40000, "loss": 0.1611, "lr": 3.248413850811797e-05, "epoch": 13.199754400327466, "percentage": 40.33, "elapsed_time": "1:51:07", "remaining_time": "2:44:27", "throughput": 788.15, "total_tokens": 5255096} {"current_steps": 16135, "total_steps": 40000, "loss": 0.1578, "lr": 3.2474770698485677e-05, "epoch": 13.203847728203028, "percentage": 40.34, "elapsed_time": "1:51:09", "remaining_time": "2:44:24", "throughput": 788.19, "total_tokens": 5256712} {"current_steps": 16140, "total_steps": 40000, "loss": 0.1944, "lr": 3.246540173614983e-05, "epoch": 13.207941056078592, "percentage": 40.35, "elapsed_time": "1:51:11", "remaining_time": "2:44:21", "throughput": 788.23, "total_tokens": 5258328} {"current_steps": 16145, "total_steps": 40000, "loss": 0.1492, "lr": 3.2456031622555197e-05, "epoch": 13.212034383954155, "percentage": 40.36, "elapsed_time": "1:51:12", "remaining_time": "2:44:19", "throughput": 788.27, "total_tokens": 5259912} {"current_steps": 16150, "total_steps": 40000, "loss": 0.186, "lr": 3.2446660359146794e-05, "epoch": 13.216127711829717, "percentage": 40.38, "elapsed_time": "1:51:14", "remaining_time": "2:44:16", "throughput": 788.31, "total_tokens": 5261560} {"current_steps": 16155, "total_steps": 40000, "loss": 0.2099, "lr": 3.2437287947369786e-05, "epoch": 13.22022103970528, "percentage": 40.39, "elapsed_time": "1:51:16", "remaining_time": "2:44:14", "throughput": 788.35, "total_tokens": 5263176} {"current_steps": 16160, "total_steps": 40000, "loss": 0.12, "lr": 3.2427914388669525e-05, "epoch": 13.224314367580844, "percentage": 40.4, "elapsed_time": "1:51:17", "remaining_time": "2:44:11", "throughput": 788.4, "total_tokens": 5264840} {"current_steps": 16165, "total_steps": 40000, "loss": 0.1477, "lr": 3.241853968449151e-05, "epoch": 13.228407695456406, "percentage": 40.41, "elapsed_time": "1:51:19", "remaining_time": "2:44:08", "throughput": 788.43, "total_tokens": 5266424} {"current_steps": 16170, "total_steps": 40000, "loss": 0.1425, "lr": 3.240916383628144e-05, "epoch": 13.232501023331968, "percentage": 40.42, "elapsed_time": "1:51:21", "remaining_time": "2:44:06", "throughput": 788.45, "total_tokens": 5267928} {"current_steps": 16175, "total_steps": 40000, "loss": 0.1602, "lr": 3.239978684548521e-05, "epoch": 13.236594351207533, "percentage": 40.44, "elapsed_time": "1:51:23", "remaining_time": "2:44:03", "throughput": 788.49, "total_tokens": 5269512} {"current_steps": 16180, "total_steps": 40000, "loss": 0.1396, "lr": 3.239040871354885e-05, "epoch": 13.240687679083095, "percentage": 40.45, "elapsed_time": "1:51:24", "remaining_time": "2:44:01", "throughput": 788.53, "total_tokens": 5271160} {"current_steps": 16185, "total_steps": 40000, "loss": 0.2224, "lr": 3.2381029441918596e-05, "epoch": 13.244781006958657, "percentage": 40.46, "elapsed_time": "1:51:26", "remaining_time": "2:43:58", "throughput": 788.58, "total_tokens": 5272856} {"current_steps": 16190, "total_steps": 40000, "loss": 0.1607, "lr": 3.2371649032040845e-05, "epoch": 13.24887433483422, "percentage": 40.48, "elapsed_time": "1:51:28", "remaining_time": "2:43:56", "throughput": 788.63, "total_tokens": 5274504} {"current_steps": 16195, "total_steps": 40000, "loss": 0.1805, "lr": 3.2362267485362174e-05, "epoch": 13.252967662709784, "percentage": 40.49, "elapsed_time": "1:51:29", "remaining_time": "2:43:53", "throughput": 788.67, "total_tokens": 5276152} {"current_steps": 16200, "total_steps": 40000, "loss": 0.2462, "lr": 3.235288480332934e-05, "epoch": 13.257060990585346, "percentage": 40.5, "elapsed_time": "1:51:31", "remaining_time": "2:43:50", "throughput": 788.72, "total_tokens": 5277800} {"current_steps": 16200, "total_steps": 40000, "eval_loss": 0.2062339186668396, "epoch": 13.257060990585346, "percentage": 40.5, "elapsed_time": "1:51:44", "remaining_time": "2:44:09", "throughput": 787.25, "total_tokens": 5277800} {"current_steps": 16205, "total_steps": 40000, "loss": 0.1048, "lr": 3.234350098738927e-05, "epoch": 13.261154318460909, "percentage": 40.51, "elapsed_time": "1:51:47", "remaining_time": "2:44:08", "throughput": 787.11, "total_tokens": 5279432} {"current_steps": 16210, "total_steps": 40000, "loss": 0.25, "lr": 3.233411603898906e-05, "epoch": 13.265247646336471, "percentage": 40.52, "elapsed_time": "1:51:49", "remaining_time": "2:44:06", "throughput": 787.15, "total_tokens": 5281032} {"current_steps": 16215, "total_steps": 40000, "loss": 0.2898, "lr": 3.232472995957599e-05, "epoch": 13.269340974212035, "percentage": 40.54, "elapsed_time": "1:51:50", "remaining_time": "2:44:03", "throughput": 787.18, "total_tokens": 5282584} {"current_steps": 16220, "total_steps": 40000, "loss": 0.1727, "lr": 3.231534275059751e-05, "epoch": 13.273434302087598, "percentage": 40.55, "elapsed_time": "1:51:52", "remaining_time": "2:44:01", "throughput": 787.22, "total_tokens": 5284232} {"current_steps": 16225, "total_steps": 40000, "loss": 0.2177, "lr": 3.230595441350125e-05, "epoch": 13.27752762996316, "percentage": 40.56, "elapsed_time": "1:51:54", "remaining_time": "2:43:58", "throughput": 787.26, "total_tokens": 5285800} {"current_steps": 16230, "total_steps": 40000, "loss": 0.2444, "lr": 3.2296564949735e-05, "epoch": 13.281620957838722, "percentage": 40.58, "elapsed_time": "1:51:55", "remaining_time": "2:43:55", "throughput": 787.29, "total_tokens": 5287400} {"current_steps": 16235, "total_steps": 40000, "loss": 0.2857, "lr": 3.228717436074675e-05, "epoch": 13.285714285714286, "percentage": 40.59, "elapsed_time": "1:51:57", "remaining_time": "2:43:53", "throughput": 787.34, "total_tokens": 5289048} {"current_steps": 16240, "total_steps": 40000, "loss": 0.1642, "lr": 3.227778264798463e-05, "epoch": 13.289807613589849, "percentage": 40.6, "elapsed_time": "1:51:59", "remaining_time": "2:43:50", "throughput": 787.38, "total_tokens": 5290680} {"current_steps": 16245, "total_steps": 40000, "loss": 0.1598, "lr": 3.226838981289698e-05, "epoch": 13.293900941465411, "percentage": 40.61, "elapsed_time": "1:52:01", "remaining_time": "2:43:48", "throughput": 787.41, "total_tokens": 5292248} {"current_steps": 16250, "total_steps": 40000, "loss": 0.1847, "lr": 3.225899585693227e-05, "epoch": 13.297994269340974, "percentage": 40.62, "elapsed_time": "1:52:02", "remaining_time": "2:43:45", "throughput": 787.47, "total_tokens": 5293992} {"current_steps": 16255, "total_steps": 40000, "loss": 0.1765, "lr": 3.224960078153918e-05, "epoch": 13.302087597216538, "percentage": 40.64, "elapsed_time": "1:52:04", "remaining_time": "2:43:43", "throughput": 787.5, "total_tokens": 5295544} {"current_steps": 16260, "total_steps": 40000, "loss": 0.2456, "lr": 3.224020458816655e-05, "epoch": 13.3061809250921, "percentage": 40.65, "elapsed_time": "1:52:06", "remaining_time": "2:43:40", "throughput": 787.53, "total_tokens": 5297144} {"current_steps": 16265, "total_steps": 40000, "loss": 0.2753, "lr": 3.223080727826337e-05, "epoch": 13.310274252967663, "percentage": 40.66, "elapsed_time": "1:52:07", "remaining_time": "2:43:37", "throughput": 787.58, "total_tokens": 5298808} {"current_steps": 16270, "total_steps": 40000, "loss": 0.1901, "lr": 3.222140885327885e-05, "epoch": 13.314367580843225, "percentage": 40.67, "elapsed_time": "1:52:09", "remaining_time": "2:43:35", "throughput": 787.63, "total_tokens": 5300472} {"current_steps": 16275, "total_steps": 40000, "loss": 0.1816, "lr": 3.221200931466234e-05, "epoch": 13.318460908718789, "percentage": 40.69, "elapsed_time": "1:52:11", "remaining_time": "2:43:32", "throughput": 787.66, "total_tokens": 5302040} {"current_steps": 16280, "total_steps": 40000, "loss": 0.1981, "lr": 3.220260866386336e-05, "epoch": 13.322554236594351, "percentage": 40.7, "elapsed_time": "1:52:13", "remaining_time": "2:43:30", "throughput": 787.7, "total_tokens": 5303688} {"current_steps": 16285, "total_steps": 40000, "loss": 0.2297, "lr": 3.21932069023316e-05, "epoch": 13.326647564469914, "percentage": 40.71, "elapsed_time": "1:52:14", "remaining_time": "2:43:27", "throughput": 787.74, "total_tokens": 5305304} {"current_steps": 16290, "total_steps": 40000, "loss": 0.21, "lr": 3.218380403151695e-05, "epoch": 13.330740892345476, "percentage": 40.73, "elapsed_time": "1:52:16", "remaining_time": "2:43:25", "throughput": 787.78, "total_tokens": 5306920} {"current_steps": 16295, "total_steps": 40000, "loss": 0.14, "lr": 3.217440005286943e-05, "epoch": 13.33483422022104, "percentage": 40.74, "elapsed_time": "1:52:18", "remaining_time": "2:43:22", "throughput": 787.82, "total_tokens": 5308520} {"current_steps": 16300, "total_steps": 40000, "loss": 0.2293, "lr": 3.216499496783928e-05, "epoch": 13.338927548096603, "percentage": 40.75, "elapsed_time": "1:52:19", "remaining_time": "2:43:19", "throughput": 787.87, "total_tokens": 5310200} {"current_steps": 16305, "total_steps": 40000, "loss": 0.1942, "lr": 3.2155588777876856e-05, "epoch": 13.343020875972165, "percentage": 40.76, "elapsed_time": "1:52:21", "remaining_time": "2:43:17", "throughput": 787.91, "total_tokens": 5311848} {"current_steps": 16310, "total_steps": 40000, "loss": 0.2678, "lr": 3.214618148443273e-05, "epoch": 13.347114203847728, "percentage": 40.77, "elapsed_time": "1:52:23", "remaining_time": "2:43:14", "throughput": 787.95, "total_tokens": 5313496} {"current_steps": 16315, "total_steps": 40000, "loss": 0.1727, "lr": 3.2136773088957595e-05, "epoch": 13.351207531723292, "percentage": 40.79, "elapsed_time": "1:52:25", "remaining_time": "2:43:12", "throughput": 787.99, "total_tokens": 5315096} {"current_steps": 16320, "total_steps": 40000, "loss": 0.1807, "lr": 3.2127363592902374e-05, "epoch": 13.355300859598854, "percentage": 40.8, "elapsed_time": "1:52:26", "remaining_time": "2:43:09", "throughput": 788.03, "total_tokens": 5316680} {"current_steps": 16325, "total_steps": 40000, "loss": 0.1369, "lr": 3.211795299771812e-05, "epoch": 13.359394187474416, "percentage": 40.81, "elapsed_time": "1:52:28", "remaining_time": "2:43:06", "throughput": 788.07, "total_tokens": 5318360} {"current_steps": 16330, "total_steps": 40000, "loss": 0.1566, "lr": 3.210854130485605e-05, "epoch": 13.363487515349979, "percentage": 40.83, "elapsed_time": "1:52:30", "remaining_time": "2:43:04", "throughput": 788.11, "total_tokens": 5319944} {"current_steps": 16335, "total_steps": 40000, "loss": 0.1611, "lr": 3.209912851576759e-05, "epoch": 13.367580843225543, "percentage": 40.84, "elapsed_time": "1:52:32", "remaining_time": "2:43:01", "throughput": 788.15, "total_tokens": 5321560} {"current_steps": 16340, "total_steps": 40000, "loss": 0.1461, "lr": 3.208971463190431e-05, "epoch": 13.371674171101105, "percentage": 40.85, "elapsed_time": "1:52:33", "remaining_time": "2:42:59", "throughput": 788.18, "total_tokens": 5323176} {"current_steps": 16345, "total_steps": 40000, "loss": 0.1956, "lr": 3.208029965471793e-05, "epoch": 13.375767498976668, "percentage": 40.86, "elapsed_time": "1:52:35", "remaining_time": "2:42:56", "throughput": 788.22, "total_tokens": 5324808} {"current_steps": 16350, "total_steps": 40000, "loss": 0.1728, "lr": 3.2070883585660364e-05, "epoch": 13.37986082685223, "percentage": 40.88, "elapsed_time": "1:52:37", "remaining_time": "2:42:54", "throughput": 788.27, "total_tokens": 5326456} {"current_steps": 16355, "total_steps": 40000, "loss": 0.1794, "lr": 3.20614664261837e-05, "epoch": 13.383954154727794, "percentage": 40.89, "elapsed_time": "1:52:38", "remaining_time": "2:42:51", "throughput": 788.3, "total_tokens": 5328056} {"current_steps": 16360, "total_steps": 40000, "loss": 0.1735, "lr": 3.205204817774016e-05, "epoch": 13.388047482603357, "percentage": 40.9, "elapsed_time": "1:52:40", "remaining_time": "2:42:48", "throughput": 788.34, "total_tokens": 5329624} {"current_steps": 16365, "total_steps": 40000, "loss": 0.1207, "lr": 3.204262884178218e-05, "epoch": 13.392140810478919, "percentage": 40.91, "elapsed_time": "1:52:42", "remaining_time": "2:42:46", "throughput": 788.38, "total_tokens": 5331272} {"current_steps": 16370, "total_steps": 40000, "loss": 0.1233, "lr": 3.2033208419762314e-05, "epoch": 13.396234138354481, "percentage": 40.92, "elapsed_time": "1:52:44", "remaining_time": "2:42:43", "throughput": 788.43, "total_tokens": 5332952} {"current_steps": 16375, "total_steps": 40000, "loss": 0.1795, "lr": 3.2023786913133344e-05, "epoch": 13.400327466230046, "percentage": 40.94, "elapsed_time": "1:52:45", "remaining_time": "2:42:41", "throughput": 788.47, "total_tokens": 5334568} {"current_steps": 16380, "total_steps": 40000, "loss": 0.1776, "lr": 3.201436432334816e-05, "epoch": 13.404420794105608, "percentage": 40.95, "elapsed_time": "1:52:47", "remaining_time": "2:42:38", "throughput": 788.52, "total_tokens": 5336312} {"current_steps": 16385, "total_steps": 40000, "loss": 0.2061, "lr": 3.2004940651859844e-05, "epoch": 13.40851412198117, "percentage": 40.96, "elapsed_time": "1:52:49", "remaining_time": "2:42:36", "throughput": 788.57, "total_tokens": 5337960} {"current_steps": 16390, "total_steps": 40000, "loss": 0.1205, "lr": 3.1995515900121655e-05, "epoch": 13.412607449856733, "percentage": 40.98, "elapsed_time": "1:52:50", "remaining_time": "2:42:33", "throughput": 788.6, "total_tokens": 5339560} {"current_steps": 16395, "total_steps": 40000, "loss": 0.2524, "lr": 3.1986090069587e-05, "epoch": 13.416700777732297, "percentage": 40.99, "elapsed_time": "1:52:52", "remaining_time": "2:42:30", "throughput": 788.64, "total_tokens": 5341160} {"current_steps": 16400, "total_steps": 40000, "loss": 0.2249, "lr": 3.1976663161709466e-05, "epoch": 13.42079410560786, "percentage": 41.0, "elapsed_time": "1:52:54", "remaining_time": "2:42:28", "throughput": 788.68, "total_tokens": 5342760} {"current_steps": 16400, "total_steps": 40000, "eval_loss": 0.20671316981315613, "epoch": 13.42079410560786, "percentage": 41.0, "elapsed_time": "1:53:06", "remaining_time": "2:42:46", "throughput": 787.23, "total_tokens": 5342760} {"current_steps": 16405, "total_steps": 40000, "loss": 0.2135, "lr": 3.196723517794279e-05, "epoch": 13.424887433483422, "percentage": 41.01, "elapsed_time": "1:53:10", "remaining_time": "2:42:46", "throughput": 787.04, "total_tokens": 5344344} {"current_steps": 16410, "total_steps": 40000, "loss": 0.1848, "lr": 3.19578061197409e-05, "epoch": 13.428980761358984, "percentage": 41.02, "elapsed_time": "1:53:12", "remaining_time": "2:42:43", "throughput": 787.08, "total_tokens": 5345928} {"current_steps": 16415, "total_steps": 40000, "loss": 0.1746, "lr": 3.194837598855787e-05, "epoch": 13.433074089234548, "percentage": 41.04, "elapsed_time": "1:53:13", "remaining_time": "2:42:41", "throughput": 787.11, "total_tokens": 5347528} {"current_steps": 16420, "total_steps": 40000, "loss": 0.1501, "lr": 3.193894478584794e-05, "epoch": 13.43716741711011, "percentage": 41.05, "elapsed_time": "1:53:15", "remaining_time": "2:42:38", "throughput": 787.15, "total_tokens": 5349144} {"current_steps": 16425, "total_steps": 40000, "loss": 0.1637, "lr": 3.192951251306553e-05, "epoch": 13.441260744985673, "percentage": 41.06, "elapsed_time": "1:53:17", "remaining_time": "2:42:36", "throughput": 787.2, "total_tokens": 5350808} {"current_steps": 16430, "total_steps": 40000, "loss": 0.1906, "lr": 3.192007917166521e-05, "epoch": 13.445354072861235, "percentage": 41.08, "elapsed_time": "1:53:19", "remaining_time": "2:42:33", "throughput": 787.24, "total_tokens": 5352440} {"current_steps": 16435, "total_steps": 40000, "loss": 0.1787, "lr": 3.191064476310171e-05, "epoch": 13.4494474007368, "percentage": 41.09, "elapsed_time": "1:53:20", "remaining_time": "2:42:31", "throughput": 787.28, "total_tokens": 5354088} {"current_steps": 16440, "total_steps": 40000, "loss": 0.1489, "lr": 3.1901209288829944e-05, "epoch": 13.453540728612362, "percentage": 41.1, "elapsed_time": "1:53:22", "remaining_time": "2:42:28", "throughput": 787.32, "total_tokens": 5355704} {"current_steps": 16445, "total_steps": 40000, "loss": 0.2522, "lr": 3.1891772750304985e-05, "epoch": 13.457634056487924, "percentage": 41.11, "elapsed_time": "1:53:24", "remaining_time": "2:42:25", "throughput": 787.35, "total_tokens": 5357256} {"current_steps": 16450, "total_steps": 40000, "loss": 0.1458, "lr": 3.188233514898206e-05, "epoch": 13.461727384363488, "percentage": 41.12, "elapsed_time": "1:53:25", "remaining_time": "2:42:23", "throughput": 787.39, "total_tokens": 5358872} {"current_steps": 16455, "total_steps": 40000, "loss": 0.2053, "lr": 3.187289648631657e-05, "epoch": 13.46582071223905, "percentage": 41.14, "elapsed_time": "1:53:27", "remaining_time": "2:42:20", "throughput": 787.44, "total_tokens": 5360552} {"current_steps": 16460, "total_steps": 40000, "loss": 0.1687, "lr": 3.186345676376406e-05, "epoch": 13.469914040114613, "percentage": 41.15, "elapsed_time": "1:53:29", "remaining_time": "2:42:18", "throughput": 787.48, "total_tokens": 5362184} {"current_steps": 16465, "total_steps": 40000, "loss": 0.2439, "lr": 3.1854015982780275e-05, "epoch": 13.474007367990176, "percentage": 41.16, "elapsed_time": "1:53:31", "remaining_time": "2:42:15", "throughput": 787.51, "total_tokens": 5363784} {"current_steps": 16470, "total_steps": 40000, "loss": 0.2212, "lr": 3.1844574144821084e-05, "epoch": 13.47810069586574, "percentage": 41.17, "elapsed_time": "1:53:32", "remaining_time": "2:42:13", "throughput": 787.56, "total_tokens": 5365432} {"current_steps": 16475, "total_steps": 40000, "loss": 0.2283, "lr": 3.1835131251342554e-05, "epoch": 13.482194023741302, "percentage": 41.19, "elapsed_time": "1:53:34", "remaining_time": "2:42:10", "throughput": 787.6, "total_tokens": 5367064} {"current_steps": 16480, "total_steps": 40000, "loss": 0.1547, "lr": 3.182568730380089e-05, "epoch": 13.486287351616864, "percentage": 41.2, "elapsed_time": "1:53:36", "remaining_time": "2:42:07", "throughput": 787.63, "total_tokens": 5368648} {"current_steps": 16485, "total_steps": 40000, "loss": 0.1993, "lr": 3.181624230365245e-05, "epoch": 13.490380679492427, "percentage": 41.21, "elapsed_time": "1:53:37", "remaining_time": "2:42:05", "throughput": 787.68, "total_tokens": 5370312} {"current_steps": 16490, "total_steps": 40000, "loss": 0.1376, "lr": 3.180679625235381e-05, "epoch": 13.494474007367991, "percentage": 41.23, "elapsed_time": "1:53:39", "remaining_time": "2:42:02", "throughput": 787.72, "total_tokens": 5371976} {"current_steps": 16495, "total_steps": 40000, "loss": 0.2058, "lr": 3.1797349151361646e-05, "epoch": 13.498567335243553, "percentage": 41.24, "elapsed_time": "1:53:41", "remaining_time": "2:42:00", "throughput": 787.76, "total_tokens": 5373576} {"current_steps": 16500, "total_steps": 40000, "loss": 0.1963, "lr": 3.178790100213281e-05, "epoch": 13.502660663119116, "percentage": 41.25, "elapsed_time": "1:53:43", "remaining_time": "2:41:57", "throughput": 787.8, "total_tokens": 5375208} {"current_steps": 16505, "total_steps": 40000, "loss": 0.2648, "lr": 3.1778451806124346e-05, "epoch": 13.506753990994678, "percentage": 41.26, "elapsed_time": "1:53:44", "remaining_time": "2:41:55", "throughput": 787.84, "total_tokens": 5376872} {"current_steps": 16510, "total_steps": 40000, "loss": 0.1436, "lr": 3.176900156479342e-05, "epoch": 13.510847318870242, "percentage": 41.27, "elapsed_time": "1:53:46", "remaining_time": "2:41:52", "throughput": 787.88, "total_tokens": 5378488} {"current_steps": 16515, "total_steps": 40000, "loss": 0.1428, "lr": 3.17595502795974e-05, "epoch": 13.514940646745805, "percentage": 41.29, "elapsed_time": "1:53:48", "remaining_time": "2:41:50", "throughput": 787.92, "total_tokens": 5380104} {"current_steps": 16520, "total_steps": 40000, "loss": 0.2771, "lr": 3.175009795199377e-05, "epoch": 13.519033974621367, "percentage": 41.3, "elapsed_time": "1:53:49", "remaining_time": "2:41:47", "throughput": 787.96, "total_tokens": 5381720} {"current_steps": 16525, "total_steps": 40000, "loss": 0.2222, "lr": 3.1740644583440224e-05, "epoch": 13.52312730249693, "percentage": 41.31, "elapsed_time": "1:53:51", "remaining_time": "2:41:44", "throughput": 788.0, "total_tokens": 5383336} {"current_steps": 16530, "total_steps": 40000, "loss": 0.1702, "lr": 3.173119017539457e-05, "epoch": 13.527220630372494, "percentage": 41.33, "elapsed_time": "1:53:53", "remaining_time": "2:41:42", "throughput": 788.04, "total_tokens": 5384968} {"current_steps": 16535, "total_steps": 40000, "loss": 0.2196, "lr": 3.172173472931479e-05, "epoch": 13.531313958248056, "percentage": 41.34, "elapsed_time": "1:53:55", "remaining_time": "2:41:39", "throughput": 788.08, "total_tokens": 5386632} {"current_steps": 16540, "total_steps": 40000, "loss": 0.2091, "lr": 3.1712278246659055e-05, "epoch": 13.535407286123618, "percentage": 41.35, "elapsed_time": "1:53:56", "remaining_time": "2:41:37", "throughput": 788.13, "total_tokens": 5388264} {"current_steps": 16545, "total_steps": 40000, "loss": 0.2549, "lr": 3.170282072888566e-05, "epoch": 13.53950061399918, "percentage": 41.36, "elapsed_time": "1:53:58", "remaining_time": "2:41:34", "throughput": 788.16, "total_tokens": 5389832} {"current_steps": 16550, "total_steps": 40000, "loss": 0.1737, "lr": 3.169336217745307e-05, "epoch": 13.543593941874745, "percentage": 41.38, "elapsed_time": "1:54:00", "remaining_time": "2:41:32", "throughput": 788.19, "total_tokens": 5391448} {"current_steps": 16555, "total_steps": 40000, "loss": 0.2342, "lr": 3.1683902593819924e-05, "epoch": 13.547687269750307, "percentage": 41.39, "elapsed_time": "1:54:01", "remaining_time": "2:41:29", "throughput": 788.24, "total_tokens": 5393096} {"current_steps": 16560, "total_steps": 40000, "loss": 0.1854, "lr": 3.1674441979445e-05, "epoch": 13.55178059762587, "percentage": 41.4, "elapsed_time": "1:54:03", "remaining_time": "2:41:26", "throughput": 788.28, "total_tokens": 5394728} {"current_steps": 16565, "total_steps": 40000, "loss": 0.1911, "lr": 3.166498033578725e-05, "epoch": 13.555873925501432, "percentage": 41.41, "elapsed_time": "1:54:05", "remaining_time": "2:41:24", "throughput": 788.32, "total_tokens": 5396344} {"current_steps": 16570, "total_steps": 40000, "loss": 0.1651, "lr": 3.165551766430578e-05, "epoch": 13.559967253376996, "percentage": 41.42, "elapsed_time": "1:54:07", "remaining_time": "2:41:21", "throughput": 788.36, "total_tokens": 5398024} {"current_steps": 16575, "total_steps": 40000, "loss": 0.1818, "lr": 3.164605396645984e-05, "epoch": 13.564060581252559, "percentage": 41.44, "elapsed_time": "1:54:08", "remaining_time": "2:41:19", "throughput": 788.4, "total_tokens": 5399640} {"current_steps": 16580, "total_steps": 40000, "loss": 0.2033, "lr": 3.163658924370886e-05, "epoch": 13.568153909128121, "percentage": 41.45, "elapsed_time": "1:54:10", "remaining_time": "2:41:16", "throughput": 788.44, "total_tokens": 5401256} {"current_steps": 16585, "total_steps": 40000, "loss": 0.2139, "lr": 3.1627123497512415e-05, "epoch": 13.572247237003683, "percentage": 41.46, "elapsed_time": "1:54:12", "remaining_time": "2:41:14", "throughput": 788.49, "total_tokens": 5402920} {"current_steps": 16590, "total_steps": 40000, "loss": 0.1467, "lr": 3.1617656729330245e-05, "epoch": 13.576340564879247, "percentage": 41.48, "elapsed_time": "1:54:13", "remaining_time": "2:41:11", "throughput": 788.52, "total_tokens": 5404536} {"current_steps": 16595, "total_steps": 40000, "loss": 0.1592, "lr": 3.1608188940622255e-05, "epoch": 13.58043389275481, "percentage": 41.49, "elapsed_time": "1:54:15", "remaining_time": "2:41:09", "throughput": 788.57, "total_tokens": 5406184} {"current_steps": 16600, "total_steps": 40000, "loss": 0.1858, "lr": 3.159872013284847e-05, "epoch": 13.584527220630372, "percentage": 41.5, "elapsed_time": "1:54:17", "remaining_time": "2:41:06", "throughput": 788.61, "total_tokens": 5407816} {"current_steps": 16600, "total_steps": 40000, "eval_loss": 0.2061193436384201, "epoch": 13.584527220630372, "percentage": 41.5, "elapsed_time": "1:54:29", "remaining_time": "2:41:24", "throughput": 787.18, "total_tokens": 5407816} {"current_steps": 16605, "total_steps": 40000, "loss": 0.1627, "lr": 3.1589250307469134e-05, "epoch": 13.588620548505935, "percentage": 41.51, "elapsed_time": "1:54:33", "remaining_time": "2:41:23", "throughput": 787.05, "total_tokens": 5409448} {"current_steps": 16610, "total_steps": 40000, "loss": 0.2418, "lr": 3.1579779465944586e-05, "epoch": 13.592713876381499, "percentage": 41.52, "elapsed_time": "1:54:34", "remaining_time": "2:41:21", "throughput": 787.09, "total_tokens": 5411080} {"current_steps": 16615, "total_steps": 40000, "loss": 0.1995, "lr": 3.1570307609735363e-05, "epoch": 13.596807204257061, "percentage": 41.54, "elapsed_time": "1:54:36", "remaining_time": "2:41:18", "throughput": 787.13, "total_tokens": 5412744} {"current_steps": 16620, "total_steps": 40000, "loss": 0.1766, "lr": 3.156083474030213e-05, "epoch": 13.600900532132624, "percentage": 41.55, "elapsed_time": "1:54:38", "remaining_time": "2:41:15", "throughput": 787.17, "total_tokens": 5414360} {"current_steps": 16625, "total_steps": 40000, "loss": 0.1417, "lr": 3.155136085910573e-05, "epoch": 13.604993860008186, "percentage": 41.56, "elapsed_time": "1:54:39", "remaining_time": "2:41:13", "throughput": 787.21, "total_tokens": 5416008} {"current_steps": 16630, "total_steps": 40000, "loss": 0.1815, "lr": 3.154188596760717e-05, "epoch": 13.60908718788375, "percentage": 41.58, "elapsed_time": "1:54:41", "remaining_time": "2:41:10", "throughput": 787.26, "total_tokens": 5417656} {"current_steps": 16635, "total_steps": 40000, "loss": 0.1845, "lr": 3.153241006726757e-05, "epoch": 13.613180515759312, "percentage": 41.59, "elapsed_time": "1:54:43", "remaining_time": "2:41:08", "throughput": 787.3, "total_tokens": 5419272} {"current_steps": 16640, "total_steps": 40000, "loss": 0.2101, "lr": 3.152293315954825e-05, "epoch": 13.617273843634875, "percentage": 41.6, "elapsed_time": "1:54:45", "remaining_time": "2:41:05", "throughput": 787.34, "total_tokens": 5420904} {"current_steps": 16645, "total_steps": 40000, "loss": 0.1859, "lr": 3.1513455245910666e-05, "epoch": 13.621367171510437, "percentage": 41.61, "elapsed_time": "1:54:46", "remaining_time": "2:41:03", "throughput": 787.38, "total_tokens": 5422568} {"current_steps": 16650, "total_steps": 40000, "loss": 0.213, "lr": 3.150397632781643e-05, "epoch": 13.625460499386001, "percentage": 41.62, "elapsed_time": "1:54:48", "remaining_time": "2:41:00", "throughput": 787.42, "total_tokens": 5424200} {"current_steps": 16655, "total_steps": 40000, "loss": 0.1163, "lr": 3.149449640672731e-05, "epoch": 13.629553827261564, "percentage": 41.64, "elapsed_time": "1:54:50", "remaining_time": "2:40:57", "throughput": 787.47, "total_tokens": 5425848} {"current_steps": 16660, "total_steps": 40000, "loss": 0.1803, "lr": 3.148501548410523e-05, "epoch": 13.633647155137126, "percentage": 41.65, "elapsed_time": "1:54:51", "remaining_time": "2:40:55", "throughput": 787.51, "total_tokens": 5427496} {"current_steps": 16665, "total_steps": 40000, "loss": 0.1568, "lr": 3.1475533561412256e-05, "epoch": 13.637740483012688, "percentage": 41.66, "elapsed_time": "1:54:53", "remaining_time": "2:40:52", "throughput": 787.54, "total_tokens": 5429096} {"current_steps": 16670, "total_steps": 40000, "loss": 0.1857, "lr": 3.146605064011065e-05, "epoch": 13.641833810888253, "percentage": 41.68, "elapsed_time": "1:54:55", "remaining_time": "2:40:50", "throughput": 787.58, "total_tokens": 5430664} {"current_steps": 16675, "total_steps": 40000, "loss": 0.1573, "lr": 3.145656672166277e-05, "epoch": 13.645927138763815, "percentage": 41.69, "elapsed_time": "1:54:57", "remaining_time": "2:40:47", "throughput": 787.61, "total_tokens": 5432280} {"current_steps": 16680, "total_steps": 40000, "loss": 0.1575, "lr": 3.144708180753116e-05, "epoch": 13.650020466639377, "percentage": 41.7, "elapsed_time": "1:54:58", "remaining_time": "2:40:45", "throughput": 787.66, "total_tokens": 5433912} {"current_steps": 16685, "total_steps": 40000, "loss": 0.1525, "lr": 3.143759589917851e-05, "epoch": 13.654113794514942, "percentage": 41.71, "elapsed_time": "1:55:00", "remaining_time": "2:40:42", "throughput": 787.7, "total_tokens": 5435576} {"current_steps": 16690, "total_steps": 40000, "loss": 0.1129, "lr": 3.142810899806768e-05, "epoch": 13.658207122390504, "percentage": 41.73, "elapsed_time": "1:55:02", "remaining_time": "2:40:40", "throughput": 787.74, "total_tokens": 5437240} {"current_steps": 16695, "total_steps": 40000, "loss": 0.1919, "lr": 3.141862110566166e-05, "epoch": 13.662300450266066, "percentage": 41.74, "elapsed_time": "1:55:04", "remaining_time": "2:40:37", "throughput": 787.79, "total_tokens": 5438904} {"current_steps": 16700, "total_steps": 40000, "loss": 0.233, "lr": 3.1409132223423606e-05, "epoch": 13.666393778141629, "percentage": 41.75, "elapsed_time": "1:55:05", "remaining_time": "2:40:34", "throughput": 787.83, "total_tokens": 5440536} {"current_steps": 16705, "total_steps": 40000, "loss": 0.2172, "lr": 3.139964235281682e-05, "epoch": 13.670487106017191, "percentage": 41.76, "elapsed_time": "1:55:07", "remaining_time": "2:40:32", "throughput": 787.86, "total_tokens": 5442120} {"current_steps": 16710, "total_steps": 40000, "loss": 0.1613, "lr": 3.139015149530476e-05, "epoch": 13.674580433892755, "percentage": 41.77, "elapsed_time": "1:55:09", "remaining_time": "2:40:29", "throughput": 787.9, "total_tokens": 5443752} {"current_steps": 16715, "total_steps": 40000, "loss": 0.2124, "lr": 3.1380659652351034e-05, "epoch": 13.678673761768318, "percentage": 41.79, "elapsed_time": "1:55:10", "remaining_time": "2:40:27", "throughput": 787.95, "total_tokens": 5445432} {"current_steps": 16720, "total_steps": 40000, "loss": 0.1586, "lr": 3.137116682541941e-05, "epoch": 13.68276708964388, "percentage": 41.8, "elapsed_time": "1:55:12", "remaining_time": "2:40:24", "throughput": 788.0, "total_tokens": 5447112} {"current_steps": 16725, "total_steps": 40000, "loss": 0.232, "lr": 3.136167301597379e-05, "epoch": 13.686860417519444, "percentage": 41.81, "elapsed_time": "1:55:14", "remaining_time": "2:40:22", "throughput": 788.04, "total_tokens": 5448712} {"current_steps": 16730, "total_steps": 40000, "loss": 0.1944, "lr": 3.1352178225478254e-05, "epoch": 13.690953745395007, "percentage": 41.83, "elapsed_time": "1:55:16", "remaining_time": "2:40:19", "throughput": 788.07, "total_tokens": 5450328} {"current_steps": 16735, "total_steps": 40000, "loss": 0.1665, "lr": 3.1342682455396996e-05, "epoch": 13.695047073270569, "percentage": 41.84, "elapsed_time": "1:55:17", "remaining_time": "2:40:17", "throughput": 788.12, "total_tokens": 5452040} {"current_steps": 16740, "total_steps": 40000, "loss": 0.1761, "lr": 3.133318570719441e-05, "epoch": 13.699140401146131, "percentage": 41.85, "elapsed_time": "1:55:19", "remaining_time": "2:40:14", "throughput": 788.16, "total_tokens": 5453672} {"current_steps": 16745, "total_steps": 40000, "loss": 0.282, "lr": 3.132368798233499e-05, "epoch": 13.703233729021695, "percentage": 41.86, "elapsed_time": "1:55:21", "remaining_time": "2:40:11", "throughput": 788.21, "total_tokens": 5455304} {"current_steps": 16750, "total_steps": 40000, "loss": 0.2721, "lr": 3.131418928228342e-05, "epoch": 13.707327056897258, "percentage": 41.88, "elapsed_time": "1:55:22", "remaining_time": "2:40:09", "throughput": 788.25, "total_tokens": 5456984} {"current_steps": 16755, "total_steps": 40000, "loss": 0.1675, "lr": 3.1304689608504514e-05, "epoch": 13.71142038477282, "percentage": 41.89, "elapsed_time": "1:55:24", "remaining_time": "2:40:06", "throughput": 788.3, "total_tokens": 5458648} {"current_steps": 16760, "total_steps": 40000, "loss": 0.1733, "lr": 3.129518896246324e-05, "epoch": 13.715513712648383, "percentage": 41.9, "elapsed_time": "1:55:26", "remaining_time": "2:40:04", "throughput": 788.33, "total_tokens": 5460248} {"current_steps": 16765, "total_steps": 40000, "loss": 0.2466, "lr": 3.128568734562472e-05, "epoch": 13.719607040523947, "percentage": 41.91, "elapsed_time": "1:55:28", "remaining_time": "2:40:01", "throughput": 788.38, "total_tokens": 5461912} {"current_steps": 16770, "total_steps": 40000, "loss": 0.1582, "lr": 3.127618475945421e-05, "epoch": 13.72370036839951, "percentage": 41.93, "elapsed_time": "1:55:29", "remaining_time": "2:39:59", "throughput": 788.43, "total_tokens": 5463624} {"current_steps": 16775, "total_steps": 40000, "loss": 0.1783, "lr": 3.126668120541715e-05, "epoch": 13.727793696275072, "percentage": 41.94, "elapsed_time": "1:55:31", "remaining_time": "2:39:56", "throughput": 788.48, "total_tokens": 5465336} {"current_steps": 16780, "total_steps": 40000, "loss": 0.1496, "lr": 3.1257176684979096e-05, "epoch": 13.731887024150634, "percentage": 41.95, "elapsed_time": "1:55:33", "remaining_time": "2:39:54", "throughput": 788.53, "total_tokens": 5467032} {"current_steps": 16785, "total_steps": 40000, "loss": 0.2337, "lr": 3.124767119960576e-05, "epoch": 13.735980352026198, "percentage": 41.96, "elapsed_time": "1:55:34", "remaining_time": "2:39:51", "throughput": 788.57, "total_tokens": 5468680} {"current_steps": 16790, "total_steps": 40000, "loss": 0.186, "lr": 3.123816475076301e-05, "epoch": 13.74007367990176, "percentage": 41.98, "elapsed_time": "1:55:36", "remaining_time": "2:39:48", "throughput": 788.61, "total_tokens": 5470328} {"current_steps": 16795, "total_steps": 40000, "loss": 0.2016, "lr": 3.122865733991687e-05, "epoch": 13.744167007777323, "percentage": 41.99, "elapsed_time": "1:55:38", "remaining_time": "2:39:46", "throughput": 788.66, "total_tokens": 5472008} {"current_steps": 16800, "total_steps": 40000, "loss": 0.1693, "lr": 3.1219148968533486e-05, "epoch": 13.748260335652885, "percentage": 42.0, "elapsed_time": "1:55:40", "remaining_time": "2:39:43", "throughput": 788.71, "total_tokens": 5473672} {"current_steps": 16800, "total_steps": 40000, "eval_loss": 0.20590022206306458, "epoch": 13.748260335652885, "percentage": 42.0, "elapsed_time": "1:55:52", "remaining_time": "2:40:01", "throughput": 787.29, "total_tokens": 5473672} {"current_steps": 16805, "total_steps": 40000, "loss": 0.2001, "lr": 3.120963963807918e-05, "epoch": 13.75235366352845, "percentage": 42.01, "elapsed_time": "1:55:55", "remaining_time": "2:40:00", "throughput": 787.16, "total_tokens": 5475256} {"current_steps": 16810, "total_steps": 40000, "loss": 0.1225, "lr": 3.12001293500204e-05, "epoch": 13.756446991404012, "percentage": 42.02, "elapsed_time": "1:55:57", "remaining_time": "2:39:58", "throughput": 787.2, "total_tokens": 5476888} {"current_steps": 16815, "total_steps": 40000, "loss": 0.1913, "lr": 3.1190618105823765e-05, "epoch": 13.760540319279574, "percentage": 42.04, "elapsed_time": "1:55:59", "remaining_time": "2:39:55", "throughput": 787.23, "total_tokens": 5478472} {"current_steps": 16820, "total_steps": 40000, "loss": 0.1889, "lr": 3.118110590695603e-05, "epoch": 13.764633647155136, "percentage": 42.05, "elapsed_time": "1:56:00", "remaining_time": "2:39:52", "throughput": 787.26, "total_tokens": 5480056} {"current_steps": 16825, "total_steps": 40000, "loss": 0.1554, "lr": 3.117159275488407e-05, "epoch": 13.7687269750307, "percentage": 42.06, "elapsed_time": "1:56:02", "remaining_time": "2:39:50", "throughput": 787.31, "total_tokens": 5481720} {"current_steps": 16830, "total_steps": 40000, "loss": 0.1593, "lr": 3.1162078651074956e-05, "epoch": 13.772820302906263, "percentage": 42.08, "elapsed_time": "1:56:04", "remaining_time": "2:39:47", "throughput": 787.34, "total_tokens": 5483304} {"current_steps": 16835, "total_steps": 40000, "loss": 0.2336, "lr": 3.1152563596995885e-05, "epoch": 13.776913630781825, "percentage": 42.09, "elapsed_time": "1:56:06", "remaining_time": "2:39:45", "throughput": 787.39, "total_tokens": 5484984} {"current_steps": 16840, "total_steps": 40000, "loss": 0.2328, "lr": 3.1143047594114186e-05, "epoch": 13.781006958657388, "percentage": 42.1, "elapsed_time": "1:56:07", "remaining_time": "2:39:42", "throughput": 787.43, "total_tokens": 5486616} {"current_steps": 16845, "total_steps": 40000, "loss": 0.1992, "lr": 3.113353064389734e-05, "epoch": 13.785100286532952, "percentage": 42.11, "elapsed_time": "1:56:09", "remaining_time": "2:39:40", "throughput": 787.46, "total_tokens": 5488216} {"current_steps": 16850, "total_steps": 40000, "loss": 0.2172, "lr": 3.1124012747812993e-05, "epoch": 13.789193614408514, "percentage": 42.12, "elapsed_time": "1:56:11", "remaining_time": "2:39:37", "throughput": 787.5, "total_tokens": 5489832} {"current_steps": 16855, "total_steps": 40000, "loss": 0.1532, "lr": 3.1114493907328936e-05, "epoch": 13.793286942284077, "percentage": 42.14, "elapsed_time": "1:56:12", "remaining_time": "2:39:35", "throughput": 787.55, "total_tokens": 5491528} {"current_steps": 16860, "total_steps": 40000, "loss": 0.1861, "lr": 3.110497412391306e-05, "epoch": 13.797380270159639, "percentage": 42.15, "elapsed_time": "1:56:14", "remaining_time": "2:39:32", "throughput": 787.58, "total_tokens": 5493096} {"current_steps": 16865, "total_steps": 40000, "loss": 0.1782, "lr": 3.1095453399033466e-05, "epoch": 13.801473598035203, "percentage": 42.16, "elapsed_time": "1:56:16", "remaining_time": "2:39:29", "throughput": 787.63, "total_tokens": 5494792} {"current_steps": 16870, "total_steps": 40000, "loss": 0.183, "lr": 3.108593173415835e-05, "epoch": 13.805566925910766, "percentage": 42.18, "elapsed_time": "1:56:18", "remaining_time": "2:39:27", "throughput": 787.66, "total_tokens": 5496376} {"current_steps": 16875, "total_steps": 40000, "loss": 0.1846, "lr": 3.107640913075609e-05, "epoch": 13.809660253786328, "percentage": 42.19, "elapsed_time": "1:56:19", "remaining_time": "2:39:24", "throughput": 787.7, "total_tokens": 5498008} {"current_steps": 16880, "total_steps": 40000, "loss": 0.1834, "lr": 3.106688559029517e-05, "epoch": 13.81375358166189, "percentage": 42.2, "elapsed_time": "1:56:21", "remaining_time": "2:39:22", "throughput": 787.74, "total_tokens": 5499624} {"current_steps": 16885, "total_steps": 40000, "loss": 0.1861, "lr": 3.105736111424425e-05, "epoch": 13.817846909537455, "percentage": 42.21, "elapsed_time": "1:56:23", "remaining_time": "2:39:19", "throughput": 787.78, "total_tokens": 5501256} {"current_steps": 16890, "total_steps": 40000, "loss": 0.1818, "lr": 3.1047835704072136e-05, "epoch": 13.821940237413017, "percentage": 42.23, "elapsed_time": "1:56:24", "remaining_time": "2:39:17", "throughput": 787.82, "total_tokens": 5502904} {"current_steps": 16895, "total_steps": 40000, "loss": 0.1394, "lr": 3.103830936124775e-05, "epoch": 13.82603356528858, "percentage": 42.24, "elapsed_time": "1:56:26", "remaining_time": "2:39:14", "throughput": 787.85, "total_tokens": 5504456} {"current_steps": 16900, "total_steps": 40000, "loss": 0.1726, "lr": 3.102878208724018e-05, "epoch": 13.830126893164142, "percentage": 42.25, "elapsed_time": "1:56:28", "remaining_time": "2:39:12", "throughput": 787.88, "total_tokens": 5506024} {"current_steps": 16905, "total_steps": 40000, "loss": 0.1554, "lr": 3.101925388351865e-05, "epoch": 13.834220221039706, "percentage": 42.26, "elapsed_time": "1:56:30", "remaining_time": "2:39:09", "throughput": 787.92, "total_tokens": 5507624} {"current_steps": 16910, "total_steps": 40000, "loss": 0.2217, "lr": 3.1009724751552515e-05, "epoch": 13.838313548915268, "percentage": 42.27, "elapsed_time": "1:56:31", "remaining_time": "2:39:07", "throughput": 787.96, "total_tokens": 5509288} {"current_steps": 16915, "total_steps": 40000, "loss": 0.2539, "lr": 3.100019469281131e-05, "epoch": 13.84240687679083, "percentage": 42.29, "elapsed_time": "1:56:33", "remaining_time": "2:39:04", "throughput": 788.0, "total_tokens": 5510920} {"current_steps": 16920, "total_steps": 40000, "loss": 0.1409, "lr": 3.0990663708764685e-05, "epoch": 13.846500204666393, "percentage": 42.3, "elapsed_time": "1:56:35", "remaining_time": "2:39:01", "throughput": 788.03, "total_tokens": 5512488} {"current_steps": 16925, "total_steps": 40000, "loss": 0.1294, "lr": 3.098113180088243e-05, "epoch": 13.850593532541957, "percentage": 42.31, "elapsed_time": "1:56:36", "remaining_time": "2:38:59", "throughput": 788.08, "total_tokens": 5514200} {"current_steps": 16930, "total_steps": 40000, "loss": 0.2042, "lr": 3.097159897063448e-05, "epoch": 13.85468686041752, "percentage": 42.33, "elapsed_time": "1:56:38", "remaining_time": "2:38:56", "throughput": 788.12, "total_tokens": 5515800} {"current_steps": 16935, "total_steps": 40000, "loss": 0.1624, "lr": 3.096206521949094e-05, "epoch": 13.858780188293082, "percentage": 42.34, "elapsed_time": "1:56:40", "remaining_time": "2:38:54", "throughput": 788.16, "total_tokens": 5517448} {"current_steps": 16940, "total_steps": 40000, "loss": 0.1634, "lr": 3.0952530548922006e-05, "epoch": 13.862873516168644, "percentage": 42.35, "elapsed_time": "1:56:42", "remaining_time": "2:38:51", "throughput": 788.2, "total_tokens": 5519064} {"current_steps": 16945, "total_steps": 40000, "loss": 0.1958, "lr": 3.0942994960398064e-05, "epoch": 13.866966844044208, "percentage": 42.36, "elapsed_time": "1:56:43", "remaining_time": "2:38:49", "throughput": 788.23, "total_tokens": 5520664} {"current_steps": 16950, "total_steps": 40000, "loss": 0.2098, "lr": 3.093345845538961e-05, "epoch": 13.87106017191977, "percentage": 42.38, "elapsed_time": "1:56:45", "remaining_time": "2:38:46", "throughput": 788.27, "total_tokens": 5522280} {"current_steps": 16955, "total_steps": 40000, "loss": 0.1758, "lr": 3.09239210353673e-05, "epoch": 13.875153499795333, "percentage": 42.39, "elapsed_time": "1:56:47", "remaining_time": "2:38:44", "throughput": 788.32, "total_tokens": 5523992} {"current_steps": 16960, "total_steps": 40000, "loss": 0.1693, "lr": 3.0914382701801926e-05, "epoch": 13.879246827670897, "percentage": 42.4, "elapsed_time": "1:56:49", "remaining_time": "2:38:41", "throughput": 788.35, "total_tokens": 5525576} {"current_steps": 16965, "total_steps": 40000, "loss": 0.1635, "lr": 3.090484345616441e-05, "epoch": 13.88334015554646, "percentage": 42.41, "elapsed_time": "1:56:50", "remaining_time": "2:38:39", "throughput": 788.39, "total_tokens": 5527192} {"current_steps": 16970, "total_steps": 40000, "loss": 0.2381, "lr": 3.0895303299925825e-05, "epoch": 13.887433483422022, "percentage": 42.43, "elapsed_time": "1:56:52", "remaining_time": "2:38:36", "throughput": 788.42, "total_tokens": 5528776} {"current_steps": 16975, "total_steps": 40000, "loss": 0.2289, "lr": 3.0885762234557393e-05, "epoch": 13.891526811297584, "percentage": 42.44, "elapsed_time": "1:56:54", "remaining_time": "2:38:34", "throughput": 788.46, "total_tokens": 5530376} {"current_steps": 16980, "total_steps": 40000, "loss": 0.2535, "lr": 3.087622026153045e-05, "epoch": 13.895620139173147, "percentage": 42.45, "elapsed_time": "1:56:55", "remaining_time": "2:38:31", "throughput": 788.49, "total_tokens": 5531992} {"current_steps": 16985, "total_steps": 40000, "loss": 0.1691, "lr": 3.086667738231651e-05, "epoch": 13.899713467048711, "percentage": 42.46, "elapsed_time": "1:56:57", "remaining_time": "2:38:28", "throughput": 788.54, "total_tokens": 5533640} {"current_steps": 16990, "total_steps": 40000, "loss": 0.1961, "lr": 3.085713359838718e-05, "epoch": 13.903806794924273, "percentage": 42.48, "elapsed_time": "1:56:59", "remaining_time": "2:38:26", "throughput": 788.57, "total_tokens": 5535240} {"current_steps": 16995, "total_steps": 40000, "loss": 0.1306, "lr": 3.084758891121425e-05, "epoch": 13.907900122799836, "percentage": 42.49, "elapsed_time": "1:57:01", "remaining_time": "2:38:23", "throughput": 788.61, "total_tokens": 5536840} {"current_steps": 17000, "total_steps": 40000, "loss": 0.162, "lr": 3.083804332226963e-05, "epoch": 13.9119934506754, "percentage": 42.5, "elapsed_time": "1:57:02", "remaining_time": "2:38:21", "throughput": 788.64, "total_tokens": 5538456} {"current_steps": 17000, "total_steps": 40000, "eval_loss": 0.20422865450382233, "epoch": 13.9119934506754, "percentage": 42.5, "elapsed_time": "1:57:15", "remaining_time": "2:38:38", "throughput": 787.24, "total_tokens": 5538456} {"current_steps": 17005, "total_steps": 40000, "loss": 0.2224, "lr": 3.082849683302536e-05, "epoch": 13.916086778550962, "percentage": 42.51, "elapsed_time": "1:57:18", "remaining_time": "2:38:37", "throughput": 787.11, "total_tokens": 5540056} {"current_steps": 17010, "total_steps": 40000, "loss": 0.2037, "lr": 3.081894944495363e-05, "epoch": 13.920180106426525, "percentage": 42.52, "elapsed_time": "1:57:20", "remaining_time": "2:38:35", "throughput": 787.15, "total_tokens": 5541688} {"current_steps": 17015, "total_steps": 40000, "loss": 0.1118, "lr": 3.080940115952677e-05, "epoch": 13.924273434302087, "percentage": 42.54, "elapsed_time": "1:57:21", "remaining_time": "2:38:32", "throughput": 787.19, "total_tokens": 5543288} {"current_steps": 17020, "total_steps": 40000, "loss": 0.1877, "lr": 3.0799851978217245e-05, "epoch": 13.928366762177651, "percentage": 42.55, "elapsed_time": "1:57:23", "remaining_time": "2:38:30", "throughput": 787.23, "total_tokens": 5544936} {"current_steps": 17025, "total_steps": 40000, "loss": 0.1641, "lr": 3.0790301902497666e-05, "epoch": 13.932460090053214, "percentage": 42.56, "elapsed_time": "1:57:25", "remaining_time": "2:38:27", "throughput": 787.27, "total_tokens": 5546552} {"current_steps": 17030, "total_steps": 40000, "loss": 0.1787, "lr": 3.078075093384076e-05, "epoch": 13.936553417928776, "percentage": 42.58, "elapsed_time": "1:57:27", "remaining_time": "2:38:25", "throughput": 787.31, "total_tokens": 5548200} {"current_steps": 17035, "total_steps": 40000, "loss": 0.1724, "lr": 3.077119907371942e-05, "epoch": 13.940646745804338, "percentage": 42.59, "elapsed_time": "1:57:28", "remaining_time": "2:38:22", "throughput": 787.34, "total_tokens": 5549768} {"current_steps": 17040, "total_steps": 40000, "loss": 0.1281, "lr": 3.076164632360666e-05, "epoch": 13.944740073679903, "percentage": 42.6, "elapsed_time": "1:57:30", "remaining_time": "2:38:19", "throughput": 787.38, "total_tokens": 5551432} {"current_steps": 17045, "total_steps": 40000, "loss": 0.2009, "lr": 3.075209268497563e-05, "epoch": 13.948833401555465, "percentage": 42.61, "elapsed_time": "1:57:32", "remaining_time": "2:38:17", "throughput": 787.42, "total_tokens": 5553064} {"current_steps": 17050, "total_steps": 40000, "loss": 0.1983, "lr": 3.074253815929961e-05, "epoch": 13.952926729431027, "percentage": 42.62, "elapsed_time": "1:57:33", "remaining_time": "2:38:14", "throughput": 787.46, "total_tokens": 5554696} {"current_steps": 17055, "total_steps": 40000, "loss": 0.1396, "lr": 3.0732982748052054e-05, "epoch": 13.95702005730659, "percentage": 42.64, "elapsed_time": "1:57:35", "remaining_time": "2:38:12", "throughput": 787.5, "total_tokens": 5556328} {"current_steps": 17060, "total_steps": 40000, "loss": 0.2162, "lr": 3.072342645270651e-05, "epoch": 13.961113385182154, "percentage": 42.65, "elapsed_time": "1:57:37", "remaining_time": "2:38:09", "throughput": 787.54, "total_tokens": 5557960} {"current_steps": 17065, "total_steps": 40000, "loss": 0.2504, "lr": 3.071386927473668e-05, "epoch": 13.965206713057716, "percentage": 42.66, "elapsed_time": "1:57:39", "remaining_time": "2:38:07", "throughput": 787.58, "total_tokens": 5559608} {"current_steps": 17070, "total_steps": 40000, "loss": 0.1767, "lr": 3.0704311215616404e-05, "epoch": 13.969300040933279, "percentage": 42.68, "elapsed_time": "1:57:40", "remaining_time": "2:38:04", "throughput": 787.61, "total_tokens": 5561208} {"current_steps": 17075, "total_steps": 40000, "loss": 0.2213, "lr": 3.0694752276819656e-05, "epoch": 13.973393368808841, "percentage": 42.69, "elapsed_time": "1:57:42", "remaining_time": "2:38:02", "throughput": 787.65, "total_tokens": 5562808} {"current_steps": 17080, "total_steps": 40000, "loss": 0.1865, "lr": 3.068519245982054e-05, "epoch": 13.977486696684405, "percentage": 42.7, "elapsed_time": "1:57:44", "remaining_time": "2:37:59", "throughput": 787.69, "total_tokens": 5564472} {"current_steps": 17085, "total_steps": 40000, "loss": 0.2432, "lr": 3.0675631766093304e-05, "epoch": 13.981580024559968, "percentage": 42.71, "elapsed_time": "1:57:45", "remaining_time": "2:37:57", "throughput": 787.73, "total_tokens": 5566120} {"current_steps": 17090, "total_steps": 40000, "loss": 0.1889, "lr": 3.066607019711232e-05, "epoch": 13.98567335243553, "percentage": 42.73, "elapsed_time": "1:57:47", "remaining_time": "2:37:54", "throughput": 787.78, "total_tokens": 5567768} {"current_steps": 17095, "total_steps": 40000, "loss": 0.1938, "lr": 3.065650775435211e-05, "epoch": 13.989766680311092, "percentage": 42.74, "elapsed_time": "1:57:49", "remaining_time": "2:37:52", "throughput": 787.81, "total_tokens": 5569384} {"current_steps": 17100, "total_steps": 40000, "loss": 0.2081, "lr": 3.0646944439287326e-05, "epoch": 13.993860008186656, "percentage": 42.75, "elapsed_time": "1:57:51", "remaining_time": "2:37:49", "throughput": 787.84, "total_tokens": 5570952} {"current_steps": 17105, "total_steps": 40000, "loss": 0.1592, "lr": 3.0637380253392736e-05, "epoch": 13.997953336062219, "percentage": 42.76, "elapsed_time": "1:57:52", "remaining_time": "2:37:47", "throughput": 787.89, "total_tokens": 5572648} {"current_steps": 17110, "total_steps": 40000, "loss": 0.105, "lr": 3.062781519814327e-05, "epoch": 14.001637331150226, "percentage": 42.77, "elapsed_time": "1:57:54", "remaining_time": "2:37:44", "throughput": 787.88, "total_tokens": 5574032} {"current_steps": 17115, "total_steps": 40000, "loss": 0.2416, "lr": 3.0618249275013985e-05, "epoch": 14.005730659025788, "percentage": 42.79, "elapsed_time": "1:57:56", "remaining_time": "2:37:42", "throughput": 787.92, "total_tokens": 5575712} {"current_steps": 17120, "total_steps": 40000, "loss": 0.1642, "lr": 3.060868248548005e-05, "epoch": 14.00982398690135, "percentage": 42.8, "elapsed_time": "1:57:58", "remaining_time": "2:37:39", "throughput": 787.97, "total_tokens": 5577376} {"current_steps": 17125, "total_steps": 40000, "loss": 0.1278, "lr": 3.0599114831016796e-05, "epoch": 14.013917314776913, "percentage": 42.81, "elapsed_time": "1:57:59", "remaining_time": "2:37:37", "throughput": 788.0, "total_tokens": 5578992} {"current_steps": 17130, "total_steps": 40000, "loss": 0.1415, "lr": 3.0589546313099666e-05, "epoch": 14.018010642652477, "percentage": 42.83, "elapsed_time": "1:58:01", "remaining_time": "2:37:34", "throughput": 788.03, "total_tokens": 5580576} {"current_steps": 17135, "total_steps": 40000, "loss": 0.1397, "lr": 3.0579976933204255e-05, "epoch": 14.02210397052804, "percentage": 42.84, "elapsed_time": "1:58:03", "remaining_time": "2:37:32", "throughput": 788.07, "total_tokens": 5582192} {"current_steps": 17140, "total_steps": 40000, "loss": 0.1985, "lr": 3.0570406692806284e-05, "epoch": 14.026197298403602, "percentage": 42.85, "elapsed_time": "1:58:05", "remaining_time": "2:37:29", "throughput": 788.1, "total_tokens": 5583760} {"current_steps": 17145, "total_steps": 40000, "loss": 0.1827, "lr": 3.05608355933816e-05, "epoch": 14.030290626279164, "percentage": 42.86, "elapsed_time": "1:58:06", "remaining_time": "2:37:27", "throughput": 788.13, "total_tokens": 5585376} {"current_steps": 17150, "total_steps": 40000, "loss": 0.2082, "lr": 3.055126363640618e-05, "epoch": 14.034383954154729, "percentage": 42.88, "elapsed_time": "1:58:08", "remaining_time": "2:37:24", "throughput": 788.17, "total_tokens": 5586992} {"current_steps": 17155, "total_steps": 40000, "loss": 0.1745, "lr": 3.0541690823356146e-05, "epoch": 14.038477282030291, "percentage": 42.89, "elapsed_time": "1:58:10", "remaining_time": "2:37:21", "throughput": 788.2, "total_tokens": 5588576} {"current_steps": 17160, "total_steps": 40000, "loss": 0.1485, "lr": 3.053211715570775e-05, "epoch": 14.042570609905853, "percentage": 42.9, "elapsed_time": "1:58:11", "remaining_time": "2:37:19", "throughput": 788.25, "total_tokens": 5590256} {"current_steps": 17165, "total_steps": 40000, "loss": 0.1695, "lr": 3.052254263493736e-05, "epoch": 14.046663937781416, "percentage": 42.91, "elapsed_time": "1:58:13", "remaining_time": "2:37:16", "throughput": 788.29, "total_tokens": 5591888} {"current_steps": 17170, "total_steps": 40000, "loss": 0.1897, "lr": 3.0512967262521498e-05, "epoch": 14.05075726565698, "percentage": 42.93, "elapsed_time": "1:58:15", "remaining_time": "2:37:14", "throughput": 788.32, "total_tokens": 5593488} {"current_steps": 17175, "total_steps": 40000, "loss": 0.1599, "lr": 3.0503391039936803e-05, "epoch": 14.054850593532542, "percentage": 42.94, "elapsed_time": "1:58:17", "remaining_time": "2:37:11", "throughput": 788.37, "total_tokens": 5595152} {"current_steps": 17180, "total_steps": 40000, "loss": 0.1604, "lr": 3.0493813968660056e-05, "epoch": 14.058943921408105, "percentage": 42.95, "elapsed_time": "1:58:18", "remaining_time": "2:37:09", "throughput": 788.4, "total_tokens": 5596720} {"current_steps": 17185, "total_steps": 40000, "loss": 0.2223, "lr": 3.0484236050168153e-05, "epoch": 14.063037249283667, "percentage": 42.96, "elapsed_time": "1:58:20", "remaining_time": "2:37:06", "throughput": 788.43, "total_tokens": 5598304} {"current_steps": 17190, "total_steps": 40000, "loss": 0.1603, "lr": 3.0474657285938123e-05, "epoch": 14.067130577159231, "percentage": 42.98, "elapsed_time": "1:58:22", "remaining_time": "2:37:04", "throughput": 788.48, "total_tokens": 5600000} {"current_steps": 17195, "total_steps": 40000, "loss": 0.245, "lr": 3.046507767744715e-05, "epoch": 14.071223905034794, "percentage": 42.99, "elapsed_time": "1:58:24", "remaining_time": "2:37:01", "throughput": 788.51, "total_tokens": 5601616} {"current_steps": 17200, "total_steps": 40000, "loss": 0.1208, "lr": 3.045549722617252e-05, "epoch": 14.075317232910356, "percentage": 43.0, "elapsed_time": "1:58:25", "remaining_time": "2:36:59", "throughput": 788.54, "total_tokens": 5603152} {"current_steps": 17200, "total_steps": 40000, "eval_loss": 0.20403429865837097, "epoch": 14.075317232910356, "percentage": 43.0, "elapsed_time": "1:58:38", "remaining_time": "2:37:15", "throughput": 787.16, "total_tokens": 5603152} {"current_steps": 17205, "total_steps": 40000, "loss": 0.1436, "lr": 3.0445915933591658e-05, "epoch": 14.079410560785918, "percentage": 43.01, "elapsed_time": "1:58:41", "remaining_time": "2:37:15", "throughput": 787.03, "total_tokens": 5604768} {"current_steps": 17210, "total_steps": 40000, "loss": 0.1835, "lr": 3.0436333801182114e-05, "epoch": 14.083503888661483, "percentage": 43.03, "elapsed_time": "1:58:43", "remaining_time": "2:37:12", "throughput": 787.07, "total_tokens": 5606368} {"current_steps": 17215, "total_steps": 40000, "loss": 0.1298, "lr": 3.0426750830421596e-05, "epoch": 14.087597216537045, "percentage": 43.04, "elapsed_time": "1:58:44", "remaining_time": "2:37:10", "throughput": 787.11, "total_tokens": 5608064} {"current_steps": 17220, "total_steps": 40000, "loss": 0.228, "lr": 3.0417167022787897e-05, "epoch": 14.091690544412607, "percentage": 43.05, "elapsed_time": "1:58:46", "remaining_time": "2:37:07", "throughput": 787.15, "total_tokens": 5609648} {"current_steps": 17225, "total_steps": 40000, "loss": 0.1227, "lr": 3.0407582379758966e-05, "epoch": 14.09578387228817, "percentage": 43.06, "elapsed_time": "1:58:48", "remaining_time": "2:37:05", "throughput": 787.18, "total_tokens": 5611248} {"current_steps": 17230, "total_steps": 40000, "loss": 0.2655, "lr": 3.039799690281287e-05, "epoch": 14.099877200163734, "percentage": 43.08, "elapsed_time": "1:58:50", "remaining_time": "2:37:02", "throughput": 787.22, "total_tokens": 5612880} {"current_steps": 17235, "total_steps": 40000, "loss": 0.2569, "lr": 3.0388410593427823e-05, "epoch": 14.103970528039296, "percentage": 43.09, "elapsed_time": "1:58:51", "remaining_time": "2:36:59", "throughput": 787.25, "total_tokens": 5614480} {"current_steps": 17240, "total_steps": 40000, "loss": 0.2488, "lr": 3.0378823453082146e-05, "epoch": 14.108063855914859, "percentage": 43.1, "elapsed_time": "1:58:53", "remaining_time": "2:36:57", "throughput": 787.3, "total_tokens": 5616128} {"current_steps": 17245, "total_steps": 40000, "loss": 0.1491, "lr": 3.03692354832543e-05, "epoch": 14.112157183790421, "percentage": 43.11, "elapsed_time": "1:58:55", "remaining_time": "2:36:54", "throughput": 787.33, "total_tokens": 5617744} {"current_steps": 17250, "total_steps": 40000, "loss": 0.2315, "lr": 3.0359646685422865e-05, "epoch": 14.116250511665985, "percentage": 43.12, "elapsed_time": "1:58:56", "remaining_time": "2:36:52", "throughput": 787.37, "total_tokens": 5619344} {"current_steps": 17255, "total_steps": 40000, "loss": 0.0996, "lr": 3.035005706106656e-05, "epoch": 14.120343839541547, "percentage": 43.14, "elapsed_time": "1:58:58", "remaining_time": "2:36:49", "throughput": 787.4, "total_tokens": 5620960} {"current_steps": 17260, "total_steps": 40000, "loss": 0.1836, "lr": 3.034046661166422e-05, "epoch": 14.12443716741711, "percentage": 43.15, "elapsed_time": "1:59:00", "remaining_time": "2:36:47", "throughput": 787.44, "total_tokens": 5622576} {"current_steps": 17265, "total_steps": 40000, "loss": 0.2369, "lr": 3.033087533869482e-05, "epoch": 14.128530495292672, "percentage": 43.16, "elapsed_time": "1:59:02", "remaining_time": "2:36:44", "throughput": 787.48, "total_tokens": 5624240} {"current_steps": 17270, "total_steps": 40000, "loss": 0.2052, "lr": 3.0321283243637444e-05, "epoch": 14.132623823168236, "percentage": 43.18, "elapsed_time": "1:59:03", "remaining_time": "2:36:42", "throughput": 787.52, "total_tokens": 5625840} {"current_steps": 17275, "total_steps": 40000, "loss": 0.132, "lr": 3.0311690327971326e-05, "epoch": 14.136717151043799, "percentage": 43.19, "elapsed_time": "1:59:05", "remaining_time": "2:36:39", "throughput": 787.55, "total_tokens": 5627424} {"current_steps": 17280, "total_steps": 40000, "loss": 0.1856, "lr": 3.030209659317581e-05, "epoch": 14.140810478919361, "percentage": 43.2, "elapsed_time": "1:59:07", "remaining_time": "2:36:37", "throughput": 787.59, "total_tokens": 5629088} {"current_steps": 17285, "total_steps": 40000, "loss": 0.1862, "lr": 3.0292502040730362e-05, "epoch": 14.144903806794924, "percentage": 43.21, "elapsed_time": "1:59:08", "remaining_time": "2:36:34", "throughput": 787.63, "total_tokens": 5630736} {"current_steps": 17290, "total_steps": 40000, "loss": 0.2043, "lr": 3.0282906672114597e-05, "epoch": 14.148997134670488, "percentage": 43.23, "elapsed_time": "1:59:10", "remaining_time": "2:36:32", "throughput": 787.66, "total_tokens": 5632304} {"current_steps": 17295, "total_steps": 40000, "loss": 0.2029, "lr": 3.027331048880823e-05, "epoch": 14.15309046254605, "percentage": 43.24, "elapsed_time": "1:59:12", "remaining_time": "2:36:29", "throughput": 787.73, "total_tokens": 5634096} {"current_steps": 17300, "total_steps": 40000, "loss": 0.167, "lr": 3.0263713492291123e-05, "epoch": 14.157183790421612, "percentage": 43.25, "elapsed_time": "1:59:14", "remaining_time": "2:36:27", "throughput": 787.76, "total_tokens": 5635696} {"current_steps": 17305, "total_steps": 40000, "loss": 0.1515, "lr": 3.0254115684043242e-05, "epoch": 14.161277118297175, "percentage": 43.26, "elapsed_time": "1:59:15", "remaining_time": "2:36:24", "throughput": 787.81, "total_tokens": 5637376} {"current_steps": 17310, "total_steps": 40000, "loss": 0.2844, "lr": 3.024451706554469e-05, "epoch": 14.165370446172739, "percentage": 43.28, "elapsed_time": "1:59:17", "remaining_time": "2:36:22", "throughput": 787.84, "total_tokens": 5639008} {"current_steps": 17315, "total_steps": 40000, "loss": 0.2149, "lr": 3.0234917638275705e-05, "epoch": 14.169463774048301, "percentage": 43.29, "elapsed_time": "1:59:19", "remaining_time": "2:36:19", "throughput": 787.89, "total_tokens": 5640656} {"current_steps": 17320, "total_steps": 40000, "loss": 0.1888, "lr": 3.0225317403716635e-05, "epoch": 14.173557101923864, "percentage": 43.3, "elapsed_time": "1:59:20", "remaining_time": "2:36:17", "throughput": 787.93, "total_tokens": 5642320} {"current_steps": 17325, "total_steps": 40000, "loss": 0.242, "lr": 3.0215716363347956e-05, "epoch": 14.177650429799426, "percentage": 43.31, "elapsed_time": "1:59:22", "remaining_time": "2:36:14", "throughput": 787.97, "total_tokens": 5644000} {"current_steps": 17330, "total_steps": 40000, "loss": 0.162, "lr": 3.0206114518650275e-05, "epoch": 14.18174375767499, "percentage": 43.33, "elapsed_time": "1:59:24", "remaining_time": "2:36:11", "throughput": 788.01, "total_tokens": 5645600} {"current_steps": 17335, "total_steps": 40000, "loss": 0.1759, "lr": 3.0196511871104304e-05, "epoch": 14.185837085550553, "percentage": 43.34, "elapsed_time": "1:59:26", "remaining_time": "2:36:09", "throughput": 788.05, "total_tokens": 5647216} {"current_steps": 17340, "total_steps": 40000, "loss": 0.2236, "lr": 3.01869084221909e-05, "epoch": 14.189930413426115, "percentage": 43.35, "elapsed_time": "1:59:27", "remaining_time": "2:36:06", "throughput": 788.09, "total_tokens": 5648848} {"current_steps": 17345, "total_steps": 40000, "loss": 0.12, "lr": 3.0177304173391037e-05, "epoch": 14.194023741301677, "percentage": 43.36, "elapsed_time": "1:59:29", "remaining_time": "2:36:04", "throughput": 788.13, "total_tokens": 5650512} {"current_steps": 17350, "total_steps": 40000, "loss": 0.2321, "lr": 3.01676991261858e-05, "epoch": 14.198117069177242, "percentage": 43.38, "elapsed_time": "1:59:31", "remaining_time": "2:36:01", "throughput": 788.16, "total_tokens": 5652096} {"current_steps": 17355, "total_steps": 40000, "loss": 0.2692, "lr": 3.015809328205642e-05, "epoch": 14.202210397052804, "percentage": 43.39, "elapsed_time": "1:59:32", "remaining_time": "2:35:59", "throughput": 788.19, "total_tokens": 5653696} {"current_steps": 17360, "total_steps": 40000, "loss": 0.2085, "lr": 3.0148486642484248e-05, "epoch": 14.206303724928366, "percentage": 43.4, "elapsed_time": "1:59:34", "remaining_time": "2:35:56", "throughput": 788.23, "total_tokens": 5655312} {"current_steps": 17365, "total_steps": 40000, "loss": 0.1409, "lr": 3.0138879208950722e-05, "epoch": 14.210397052803929, "percentage": 43.41, "elapsed_time": "1:59:36", "remaining_time": "2:35:54", "throughput": 788.26, "total_tokens": 5656880} {"current_steps": 17370, "total_steps": 40000, "loss": 0.1843, "lr": 3.012927098293744e-05, "epoch": 14.214490380679493, "percentage": 43.43, "elapsed_time": "1:59:38", "remaining_time": "2:35:51", "throughput": 788.29, "total_tokens": 5658432} {"current_steps": 17375, "total_steps": 40000, "loss": 0.2686, "lr": 3.0119661965926123e-05, "epoch": 14.218583708555055, "percentage": 43.44, "elapsed_time": "1:59:39", "remaining_time": "2:35:49", "throughput": 788.33, "total_tokens": 5660096} {"current_steps": 17380, "total_steps": 40000, "loss": 0.2219, "lr": 3.0110052159398587e-05, "epoch": 14.222677036430618, "percentage": 43.45, "elapsed_time": "1:59:41", "remaining_time": "2:35:46", "throughput": 788.36, "total_tokens": 5661632} {"current_steps": 17385, "total_steps": 40000, "loss": 0.2092, "lr": 3.0100441564836802e-05, "epoch": 14.22677036430618, "percentage": 43.46, "elapsed_time": "1:59:43", "remaining_time": "2:35:44", "throughput": 788.39, "total_tokens": 5663200} {"current_steps": 17390, "total_steps": 40000, "loss": 0.1885, "lr": 3.0090830183722817e-05, "epoch": 14.230863692181744, "percentage": 43.48, "elapsed_time": "1:59:44", "remaining_time": "2:35:41", "throughput": 788.42, "total_tokens": 5664784} {"current_steps": 17395, "total_steps": 40000, "loss": 0.1195, "lr": 3.0081218017538852e-05, "epoch": 14.234957020057307, "percentage": 43.49, "elapsed_time": "1:59:46", "remaining_time": "2:35:39", "throughput": 788.45, "total_tokens": 5666384} {"current_steps": 17400, "total_steps": 40000, "loss": 0.2128, "lr": 3.0071605067767212e-05, "epoch": 14.239050347932869, "percentage": 43.5, "elapsed_time": "1:59:48", "remaining_time": "2:35:36", "throughput": 788.5, "total_tokens": 5668048} {"current_steps": 17400, "total_steps": 40000, "eval_loss": 0.20697011053562164, "epoch": 14.239050347932869, "percentage": 43.5, "elapsed_time": "2:00:00", "remaining_time": "2:35:52", "throughput": 787.13, "total_tokens": 5668048} {"current_steps": 17405, "total_steps": 40000, "loss": 0.2466, "lr": 3.006199133589034e-05, "epoch": 14.243143675808433, "percentage": 43.51, "elapsed_time": "2:00:04", "remaining_time": "2:35:52", "throughput": 787.0, "total_tokens": 5669664} {"current_steps": 17410, "total_steps": 40000, "loss": 0.1929, "lr": 3.005237682339079e-05, "epoch": 14.247237003683995, "percentage": 43.53, "elapsed_time": "2:00:05", "remaining_time": "2:35:49", "throughput": 787.04, "total_tokens": 5671312} {"current_steps": 17415, "total_steps": 40000, "loss": 0.1918, "lr": 3.0042761531751228e-05, "epoch": 14.251330331559558, "percentage": 43.54, "elapsed_time": "2:00:07", "remaining_time": "2:35:47", "throughput": 787.08, "total_tokens": 5672960} {"current_steps": 17420, "total_steps": 40000, "loss": 0.1069, "lr": 3.0033145462454482e-05, "epoch": 14.25542365943512, "percentage": 43.55, "elapsed_time": "2:00:09", "remaining_time": "2:35:44", "throughput": 787.12, "total_tokens": 5674560} {"current_steps": 17425, "total_steps": 40000, "loss": 0.1854, "lr": 3.002352861698345e-05, "epoch": 14.259516987310684, "percentage": 43.56, "elapsed_time": "2:00:11", "remaining_time": "2:35:42", "throughput": 787.15, "total_tokens": 5676160} {"current_steps": 17430, "total_steps": 40000, "loss": 0.1999, "lr": 3.0013910996821178e-05, "epoch": 14.263610315186247, "percentage": 43.58, "elapsed_time": "2:00:12", "remaining_time": "2:35:39", "throughput": 787.2, "total_tokens": 5677872} {"current_steps": 17435, "total_steps": 40000, "loss": 0.1551, "lr": 3.0004292603450817e-05, "epoch": 14.26770364306181, "percentage": 43.59, "elapsed_time": "2:00:14", "remaining_time": "2:35:37", "throughput": 787.24, "total_tokens": 5679488} {"current_steps": 17440, "total_steps": 40000, "loss": 0.1675, "lr": 2.9994673438355653e-05, "epoch": 14.271796970937372, "percentage": 43.6, "elapsed_time": "2:00:16", "remaining_time": "2:35:34", "throughput": 787.28, "total_tokens": 5681136} {"current_steps": 17445, "total_steps": 40000, "loss": 0.199, "lr": 2.9985053503019078e-05, "epoch": 14.275890298812936, "percentage": 43.61, "elapsed_time": "2:00:17", "remaining_time": "2:35:32", "throughput": 787.31, "total_tokens": 5682752} {"current_steps": 17450, "total_steps": 40000, "loss": 0.1933, "lr": 2.99754327989246e-05, "epoch": 14.279983626688498, "percentage": 43.62, "elapsed_time": "2:00:19", "remaining_time": "2:35:29", "throughput": 787.34, "total_tokens": 5684320} {"current_steps": 17455, "total_steps": 40000, "loss": 0.1958, "lr": 2.9965811327555864e-05, "epoch": 14.28407695456406, "percentage": 43.64, "elapsed_time": "2:00:21", "remaining_time": "2:35:27", "throughput": 787.38, "total_tokens": 5685920} {"current_steps": 17460, "total_steps": 40000, "loss": 0.1754, "lr": 2.995618909039662e-05, "epoch": 14.288170282439623, "percentage": 43.65, "elapsed_time": "2:00:23", "remaining_time": "2:35:24", "throughput": 787.41, "total_tokens": 5687520} {"current_steps": 17465, "total_steps": 40000, "loss": 0.1483, "lr": 2.9946566088930727e-05, "epoch": 14.292263610315187, "percentage": 43.66, "elapsed_time": "2:00:24", "remaining_time": "2:35:22", "throughput": 787.45, "total_tokens": 5689136} {"current_steps": 17470, "total_steps": 40000, "loss": 0.227, "lr": 2.9936942324642192e-05, "epoch": 14.29635693819075, "percentage": 43.68, "elapsed_time": "2:00:26", "remaining_time": "2:35:19", "throughput": 787.49, "total_tokens": 5690784} {"current_steps": 17475, "total_steps": 40000, "loss": 0.1902, "lr": 2.9927317799015097e-05, "epoch": 14.300450266066312, "percentage": 43.69, "elapsed_time": "2:00:28", "remaining_time": "2:35:17", "throughput": 787.52, "total_tokens": 5692400} {"current_steps": 17480, "total_steps": 40000, "loss": 0.1593, "lr": 2.9917692513533685e-05, "epoch": 14.304543593941874, "percentage": 43.7, "elapsed_time": "2:00:29", "remaining_time": "2:35:14", "throughput": 787.56, "total_tokens": 5694000} {"current_steps": 17485, "total_steps": 40000, "loss": 0.1646, "lr": 2.990806646968229e-05, "epoch": 14.308636921817438, "percentage": 43.71, "elapsed_time": "2:00:31", "remaining_time": "2:35:12", "throughput": 787.59, "total_tokens": 5695632} {"current_steps": 17490, "total_steps": 40000, "loss": 0.2112, "lr": 2.989843966894536e-05, "epoch": 14.312730249693, "percentage": 43.73, "elapsed_time": "2:00:33", "remaining_time": "2:35:09", "throughput": 787.63, "total_tokens": 5697248} {"current_steps": 17495, "total_steps": 40000, "loss": 0.2107, "lr": 2.9888812112807472e-05, "epoch": 14.316823577568563, "percentage": 43.74, "elapsed_time": "2:00:35", "remaining_time": "2:35:07", "throughput": 787.67, "total_tokens": 5698864} {"current_steps": 17500, "total_steps": 40000, "loss": 0.1754, "lr": 2.987918380275333e-05, "epoch": 14.320916905444125, "percentage": 43.75, "elapsed_time": "2:00:36", "remaining_time": "2:35:04", "throughput": 787.7, "total_tokens": 5700480} {"current_steps": 17505, "total_steps": 40000, "loss": 0.1961, "lr": 2.9869554740267724e-05, "epoch": 14.32501023331969, "percentage": 43.76, "elapsed_time": "2:00:38", "remaining_time": "2:35:02", "throughput": 787.74, "total_tokens": 5702096} {"current_steps": 17510, "total_steps": 40000, "loss": 0.2151, "lr": 2.9859924926835585e-05, "epoch": 14.329103561195252, "percentage": 43.77, "elapsed_time": "2:00:40", "remaining_time": "2:34:59", "throughput": 787.77, "total_tokens": 5703680} {"current_steps": 17515, "total_steps": 40000, "loss": 0.2122, "lr": 2.9850294363941944e-05, "epoch": 14.333196889070814, "percentage": 43.79, "elapsed_time": "2:00:42", "remaining_time": "2:34:56", "throughput": 787.81, "total_tokens": 5705312} {"current_steps": 17520, "total_steps": 40000, "loss": 0.1634, "lr": 2.9840663053071967e-05, "epoch": 14.337290216946377, "percentage": 43.8, "elapsed_time": "2:00:43", "remaining_time": "2:34:54", "throughput": 787.84, "total_tokens": 5706912} {"current_steps": 17525, "total_steps": 40000, "loss": 0.153, "lr": 2.983103099571091e-05, "epoch": 14.34138354482194, "percentage": 43.81, "elapsed_time": "2:00:45", "remaining_time": "2:34:51", "throughput": 787.88, "total_tokens": 5708544} {"current_steps": 17530, "total_steps": 40000, "loss": 0.1163, "lr": 2.9821398193344164e-05, "epoch": 14.345476872697503, "percentage": 43.82, "elapsed_time": "2:00:47", "remaining_time": "2:34:49", "throughput": 787.91, "total_tokens": 5710144} {"current_steps": 17535, "total_steps": 40000, "loss": 0.166, "lr": 2.9811764647457226e-05, "epoch": 14.349570200573066, "percentage": 43.84, "elapsed_time": "2:00:48", "remaining_time": "2:34:46", "throughput": 787.95, "total_tokens": 5711760} {"current_steps": 17540, "total_steps": 40000, "loss": 0.2345, "lr": 2.9802130359535714e-05, "epoch": 14.353663528448628, "percentage": 43.85, "elapsed_time": "2:00:50", "remaining_time": "2:34:44", "throughput": 787.99, "total_tokens": 5713440} {"current_steps": 17545, "total_steps": 40000, "loss": 0.2171, "lr": 2.979249533106535e-05, "epoch": 14.357756856324192, "percentage": 43.86, "elapsed_time": "2:00:52", "remaining_time": "2:34:41", "throughput": 788.03, "total_tokens": 5715088} {"current_steps": 17550, "total_steps": 40000, "loss": 0.1459, "lr": 2.9782859563531986e-05, "epoch": 14.361850184199755, "percentage": 43.88, "elapsed_time": "2:00:54", "remaining_time": "2:34:39", "throughput": 788.06, "total_tokens": 5716656} {"current_steps": 17555, "total_steps": 40000, "loss": 0.2169, "lr": 2.977322305842156e-05, "epoch": 14.365943512075317, "percentage": 43.89, "elapsed_time": "2:00:55", "remaining_time": "2:34:36", "throughput": 788.1, "total_tokens": 5718304} {"current_steps": 17560, "total_steps": 40000, "loss": 0.1767, "lr": 2.9763585817220162e-05, "epoch": 14.37003683995088, "percentage": 43.9, "elapsed_time": "2:00:57", "remaining_time": "2:34:34", "throughput": 788.15, "total_tokens": 5719968} {"current_steps": 17565, "total_steps": 40000, "loss": 0.1635, "lr": 2.975394784141397e-05, "epoch": 14.374130167826443, "percentage": 43.91, "elapsed_time": "2:00:59", "remaining_time": "2:34:31", "throughput": 788.19, "total_tokens": 5721600} {"current_steps": 17570, "total_steps": 40000, "loss": 0.228, "lr": 2.974430913248928e-05, "epoch": 14.378223495702006, "percentage": 43.92, "elapsed_time": "2:01:00", "remaining_time": "2:34:29", "throughput": 788.22, "total_tokens": 5723216} {"current_steps": 17575, "total_steps": 40000, "loss": 0.1789, "lr": 2.9734669691932497e-05, "epoch": 14.382316823577568, "percentage": 43.94, "elapsed_time": "2:01:02", "remaining_time": "2:34:26", "throughput": 788.25, "total_tokens": 5724784} {"current_steps": 17580, "total_steps": 40000, "loss": 0.1374, "lr": 2.9725029521230147e-05, "epoch": 14.38641015145313, "percentage": 43.95, "elapsed_time": "2:01:04", "remaining_time": "2:34:24", "throughput": 788.29, "total_tokens": 5726464} {"current_steps": 17585, "total_steps": 40000, "loss": 0.2079, "lr": 2.9715388621868873e-05, "epoch": 14.390503479328695, "percentage": 43.96, "elapsed_time": "2:01:06", "remaining_time": "2:34:21", "throughput": 788.33, "total_tokens": 5728048} {"current_steps": 17590, "total_steps": 40000, "loss": 0.1982, "lr": 2.970574699533541e-05, "epoch": 14.394596807204257, "percentage": 43.97, "elapsed_time": "2:01:07", "remaining_time": "2:34:19", "throughput": 788.36, "total_tokens": 5729648} {"current_steps": 17595, "total_steps": 40000, "loss": 0.1797, "lr": 2.969610464311662e-05, "epoch": 14.39869013507982, "percentage": 43.99, "elapsed_time": "2:01:09", "remaining_time": "2:34:16", "throughput": 788.39, "total_tokens": 5731232} {"current_steps": 17600, "total_steps": 40000, "loss": 0.2558, "lr": 2.9686461566699487e-05, "epoch": 14.402783462955382, "percentage": 44.0, "elapsed_time": "2:01:11", "remaining_time": "2:34:14", "throughput": 788.42, "total_tokens": 5732816} {"current_steps": 17600, "total_steps": 40000, "eval_loss": 0.20306673645973206, "epoch": 14.402783462955382, "percentage": 44.0, "elapsed_time": "2:01:23", "remaining_time": "2:34:30", "throughput": 787.07, "total_tokens": 5732816} {"current_steps": 17605, "total_steps": 40000, "loss": 0.2577, "lr": 2.9676817767571086e-05, "epoch": 14.406876790830946, "percentage": 44.01, "elapsed_time": "2:01:27", "remaining_time": "2:34:30", "throughput": 786.9, "total_tokens": 5734480} {"current_steps": 17610, "total_steps": 40000, "loss": 0.1802, "lr": 2.966717324721861e-05, "epoch": 14.410970118706508, "percentage": 44.02, "elapsed_time": "2:01:29", "remaining_time": "2:34:27", "throughput": 786.94, "total_tokens": 5736096} {"current_steps": 17615, "total_steps": 40000, "loss": 0.2216, "lr": 2.9657528007129366e-05, "epoch": 14.41506344658207, "percentage": 44.04, "elapsed_time": "2:01:30", "remaining_time": "2:34:25", "throughput": 786.98, "total_tokens": 5737760} {"current_steps": 17620, "total_steps": 40000, "loss": 0.1623, "lr": 2.9647882048790777e-05, "epoch": 14.419156774457633, "percentage": 44.05, "elapsed_time": "2:01:32", "remaining_time": "2:34:22", "throughput": 787.02, "total_tokens": 5739392} {"current_steps": 17625, "total_steps": 40000, "loss": 0.2645, "lr": 2.963823537369037e-05, "epoch": 14.423250102333197, "percentage": 44.06, "elapsed_time": "2:01:34", "remaining_time": "2:34:20", "throughput": 787.05, "total_tokens": 5740976} {"current_steps": 17630, "total_steps": 40000, "loss": 0.1601, "lr": 2.9628587983315775e-05, "epoch": 14.42734343020876, "percentage": 44.07, "elapsed_time": "2:01:36", "remaining_time": "2:34:17", "throughput": 787.08, "total_tokens": 5742560} {"current_steps": 17635, "total_steps": 40000, "loss": 0.165, "lr": 2.9618939879154746e-05, "epoch": 14.431436758084322, "percentage": 44.09, "elapsed_time": "2:01:37", "remaining_time": "2:34:15", "throughput": 787.13, "total_tokens": 5744288} {"current_steps": 17640, "total_steps": 40000, "loss": 0.1742, "lr": 2.9609291062695143e-05, "epoch": 14.435530085959886, "percentage": 44.1, "elapsed_time": "2:01:39", "remaining_time": "2:34:12", "throughput": 787.17, "total_tokens": 5745936} {"current_steps": 17645, "total_steps": 40000, "loss": 0.1583, "lr": 2.9599641535424938e-05, "epoch": 14.439623413835449, "percentage": 44.11, "elapsed_time": "2:01:41", "remaining_time": "2:34:10", "throughput": 787.21, "total_tokens": 5747584} {"current_steps": 17650, "total_steps": 40000, "loss": 0.1548, "lr": 2.9589991298832202e-05, "epoch": 14.443716741711011, "percentage": 44.12, "elapsed_time": "2:01:42", "remaining_time": "2:34:07", "throughput": 787.25, "total_tokens": 5749200} {"current_steps": 17655, "total_steps": 40000, "loss": 0.1993, "lr": 2.958034035440513e-05, "epoch": 14.447810069586573, "percentage": 44.14, "elapsed_time": "2:01:44", "remaining_time": "2:34:05", "throughput": 787.28, "total_tokens": 5750816} {"current_steps": 17660, "total_steps": 40000, "loss": 0.1538, "lr": 2.957068870363201e-05, "epoch": 14.451903397462136, "percentage": 44.15, "elapsed_time": "2:01:46", "remaining_time": "2:34:02", "throughput": 787.32, "total_tokens": 5752432} {"current_steps": 17665, "total_steps": 40000, "loss": 0.1263, "lr": 2.956103634800126e-05, "epoch": 14.4559967253377, "percentage": 44.16, "elapsed_time": "2:01:48", "remaining_time": "2:34:00", "throughput": 787.36, "total_tokens": 5754064} {"current_steps": 17670, "total_steps": 40000, "loss": 0.2317, "lr": 2.9551383289001384e-05, "epoch": 14.460090053213262, "percentage": 44.17, "elapsed_time": "2:01:49", "remaining_time": "2:33:57", "throughput": 787.4, "total_tokens": 5755712} {"current_steps": 17675, "total_steps": 40000, "loss": 0.2038, "lr": 2.9541729528121005e-05, "epoch": 14.464183381088825, "percentage": 44.19, "elapsed_time": "2:01:51", "remaining_time": "2:33:55", "throughput": 787.43, "total_tokens": 5757312} {"current_steps": 17680, "total_steps": 40000, "loss": 0.2048, "lr": 2.9532075066848856e-05, "epoch": 14.468276708964389, "percentage": 44.2, "elapsed_time": "2:01:53", "remaining_time": "2:33:52", "throughput": 787.47, "total_tokens": 5758928} {"current_steps": 17685, "total_steps": 40000, "loss": 0.1645, "lr": 2.9522419906673786e-05, "epoch": 14.472370036839951, "percentage": 44.21, "elapsed_time": "2:01:54", "remaining_time": "2:33:49", "throughput": 787.51, "total_tokens": 5760592} {"current_steps": 17690, "total_steps": 40000, "loss": 0.1754, "lr": 2.951276404908474e-05, "epoch": 14.476463364715514, "percentage": 44.22, "elapsed_time": "2:01:56", "remaining_time": "2:33:47", "throughput": 787.55, "total_tokens": 5762240} {"current_steps": 17695, "total_steps": 40000, "loss": 0.2072, "lr": 2.9503107495570752e-05, "epoch": 14.480556692591076, "percentage": 44.24, "elapsed_time": "2:01:58", "remaining_time": "2:33:44", "throughput": 787.59, "total_tokens": 5763888} {"current_steps": 17700, "total_steps": 40000, "loss": 0.1906, "lr": 2.9493450247621003e-05, "epoch": 14.48465002046664, "percentage": 44.25, "elapsed_time": "2:02:00", "remaining_time": "2:33:42", "throughput": 787.64, "total_tokens": 5765568} {"current_steps": 17705, "total_steps": 40000, "loss": 0.1688, "lr": 2.948379230672476e-05, "epoch": 14.488743348342203, "percentage": 44.26, "elapsed_time": "2:02:01", "remaining_time": "2:33:39", "throughput": 787.68, "total_tokens": 5767216} {"current_steps": 17710, "total_steps": 40000, "loss": 0.1436, "lr": 2.9474133674371396e-05, "epoch": 14.492836676217765, "percentage": 44.27, "elapsed_time": "2:02:03", "remaining_time": "2:33:37", "throughput": 787.71, "total_tokens": 5768832} {"current_steps": 17715, "total_steps": 40000, "loss": 0.1675, "lr": 2.9464474352050387e-05, "epoch": 14.496930004093327, "percentage": 44.29, "elapsed_time": "2:02:05", "remaining_time": "2:33:34", "throughput": 787.75, "total_tokens": 5770480} {"current_steps": 17720, "total_steps": 40000, "loss": 0.1317, "lr": 2.9454814341251336e-05, "epoch": 14.501023331968891, "percentage": 44.3, "elapsed_time": "2:02:06", "remaining_time": "2:33:32", "throughput": 787.79, "total_tokens": 5772080} {"current_steps": 17725, "total_steps": 40000, "loss": 0.1056, "lr": 2.9445153643463942e-05, "epoch": 14.505116659844454, "percentage": 44.31, "elapsed_time": "2:02:08", "remaining_time": "2:33:29", "throughput": 787.82, "total_tokens": 5773696} {"current_steps": 17730, "total_steps": 40000, "loss": 0.2412, "lr": 2.943549226017798e-05, "epoch": 14.509209987720016, "percentage": 44.32, "elapsed_time": "2:02:10", "remaining_time": "2:33:27", "throughput": 787.86, "total_tokens": 5775312} {"current_steps": 17735, "total_steps": 40000, "loss": 0.222, "lr": 2.942583019288337e-05, "epoch": 14.513303315595579, "percentage": 44.34, "elapsed_time": "2:02:12", "remaining_time": "2:33:24", "throughput": 787.91, "total_tokens": 5777024} {"current_steps": 17740, "total_steps": 40000, "loss": 0.1923, "lr": 2.9416167443070132e-05, "epoch": 14.517396643471143, "percentage": 44.35, "elapsed_time": "2:02:13", "remaining_time": "2:33:22", "throughput": 787.96, "total_tokens": 5778720} {"current_steps": 17745, "total_steps": 40000, "loss": 0.1524, "lr": 2.9406504012228375e-05, "epoch": 14.521489971346705, "percentage": 44.36, "elapsed_time": "2:02:15", "remaining_time": "2:33:19", "throughput": 788.0, "total_tokens": 5780384} {"current_steps": 17750, "total_steps": 40000, "loss": 0.1885, "lr": 2.939683990184832e-05, "epoch": 14.525583299222268, "percentage": 44.38, "elapsed_time": "2:02:17", "remaining_time": "2:33:17", "throughput": 788.03, "total_tokens": 5781984} {"current_steps": 17755, "total_steps": 40000, "loss": 0.2376, "lr": 2.93871751134203e-05, "epoch": 14.52967662709783, "percentage": 44.39, "elapsed_time": "2:02:18", "remaining_time": "2:33:14", "throughput": 788.07, "total_tokens": 5783616} {"current_steps": 17760, "total_steps": 40000, "loss": 0.147, "lr": 2.9377509648434752e-05, "epoch": 14.533769954973394, "percentage": 44.4, "elapsed_time": "2:02:20", "remaining_time": "2:33:12", "throughput": 788.11, "total_tokens": 5785264} {"current_steps": 17765, "total_steps": 40000, "loss": 0.201, "lr": 2.9367843508382203e-05, "epoch": 14.537863282848956, "percentage": 44.41, "elapsed_time": "2:02:22", "remaining_time": "2:33:09", "throughput": 788.15, "total_tokens": 5786880} {"current_steps": 17770, "total_steps": 40000, "loss": 0.1419, "lr": 2.9358176694753293e-05, "epoch": 14.541956610724519, "percentage": 44.42, "elapsed_time": "2:02:24", "remaining_time": "2:33:07", "throughput": 788.19, "total_tokens": 5788528} {"current_steps": 17775, "total_steps": 40000, "loss": 0.1678, "lr": 2.9348509209038766e-05, "epoch": 14.546049938600081, "percentage": 44.44, "elapsed_time": "2:02:25", "remaining_time": "2:33:04", "throughput": 788.22, "total_tokens": 5790128} {"current_steps": 17780, "total_steps": 40000, "loss": 0.2463, "lr": 2.933884105272947e-05, "epoch": 14.550143266475645, "percentage": 44.45, "elapsed_time": "2:02:27", "remaining_time": "2:33:02", "throughput": 788.26, "total_tokens": 5791760} {"current_steps": 17785, "total_steps": 40000, "loss": 0.1734, "lr": 2.9329172227316366e-05, "epoch": 14.554236594351208, "percentage": 44.46, "elapsed_time": "2:02:29", "remaining_time": "2:32:59", "throughput": 788.3, "total_tokens": 5793392} {"current_steps": 17790, "total_steps": 40000, "loss": 0.222, "lr": 2.93195027342905e-05, "epoch": 14.55832992222677, "percentage": 44.47, "elapsed_time": "2:02:30", "remaining_time": "2:32:57", "throughput": 788.34, "total_tokens": 5795040} {"current_steps": 17795, "total_steps": 40000, "loss": 0.1439, "lr": 2.9309832575143024e-05, "epoch": 14.562423250102333, "percentage": 44.49, "elapsed_time": "2:02:32", "remaining_time": "2:32:54", "throughput": 788.37, "total_tokens": 5796656} {"current_steps": 17800, "total_steps": 40000, "loss": 0.1512, "lr": 2.930016175136521e-05, "epoch": 14.566516577977897, "percentage": 44.5, "elapsed_time": "2:02:34", "remaining_time": "2:32:52", "throughput": 788.4, "total_tokens": 5798240} {"current_steps": 17800, "total_steps": 40000, "eval_loss": 0.2071571946144104, "epoch": 14.566516577977897, "percentage": 44.5, "elapsed_time": "2:02:46", "remaining_time": "2:33:07", "throughput": 787.07, "total_tokens": 5798240} {"current_steps": 17805, "total_steps": 40000, "loss": 0.1683, "lr": 2.9290490264448412e-05, "epoch": 14.570609905853459, "percentage": 44.51, "elapsed_time": "2:02:50", "remaining_time": "2:33:07", "throughput": 786.91, "total_tokens": 5799808} {"current_steps": 17810, "total_steps": 40000, "loss": 0.1632, "lr": 2.9280818115884094e-05, "epoch": 14.574703233729021, "percentage": 44.52, "elapsed_time": "2:02:52", "remaining_time": "2:33:05", "throughput": 786.95, "total_tokens": 5801472} {"current_steps": 17815, "total_steps": 40000, "loss": 0.1553, "lr": 2.9271145307163828e-05, "epoch": 14.578796561604584, "percentage": 44.54, "elapsed_time": "2:02:53", "remaining_time": "2:33:02", "throughput": 786.99, "total_tokens": 5803120} {"current_steps": 17820, "total_steps": 40000, "loss": 0.1492, "lr": 2.9261471839779287e-05, "epoch": 14.582889889480148, "percentage": 44.55, "elapsed_time": "2:02:55", "remaining_time": "2:33:00", "throughput": 787.03, "total_tokens": 5804768} {"current_steps": 17825, "total_steps": 40000, "loss": 0.1262, "lr": 2.925179771522223e-05, "epoch": 14.58698321735571, "percentage": 44.56, "elapsed_time": "2:02:57", "remaining_time": "2:32:57", "throughput": 787.07, "total_tokens": 5806416} {"current_steps": 17830, "total_steps": 40000, "loss": 0.1626, "lr": 2.9242122934984535e-05, "epoch": 14.591076545231273, "percentage": 44.57, "elapsed_time": "2:02:58", "remaining_time": "2:32:55", "throughput": 787.12, "total_tokens": 5808080} {"current_steps": 17835, "total_steps": 40000, "loss": 0.154, "lr": 2.9232447500558176e-05, "epoch": 14.595169873106835, "percentage": 44.59, "elapsed_time": "2:03:00", "remaining_time": "2:32:52", "throughput": 787.15, "total_tokens": 5809712} {"current_steps": 17840, "total_steps": 40000, "loss": 0.1914, "lr": 2.9222771413435225e-05, "epoch": 14.5992632009824, "percentage": 44.6, "elapsed_time": "2:03:02", "remaining_time": "2:32:50", "throughput": 787.2, "total_tokens": 5811392} {"current_steps": 17845, "total_steps": 40000, "loss": 0.1632, "lr": 2.9213094675107848e-05, "epoch": 14.603356528857962, "percentage": 44.61, "elapsed_time": "2:03:04", "remaining_time": "2:32:47", "throughput": 787.23, "total_tokens": 5813008} {"current_steps": 17850, "total_steps": 40000, "loss": 0.2, "lr": 2.9203417287068335e-05, "epoch": 14.607449856733524, "percentage": 44.62, "elapsed_time": "2:03:05", "remaining_time": "2:32:45", "throughput": 787.27, "total_tokens": 5814640} {"current_steps": 17855, "total_steps": 40000, "loss": 0.1556, "lr": 2.9193739250809042e-05, "epoch": 14.611543184609086, "percentage": 44.64, "elapsed_time": "2:03:07", "remaining_time": "2:32:42", "throughput": 787.32, "total_tokens": 5816368} {"current_steps": 17860, "total_steps": 40000, "loss": 0.1802, "lr": 2.9184060567822463e-05, "epoch": 14.61563651248465, "percentage": 44.65, "elapsed_time": "2:03:09", "remaining_time": "2:32:40", "throughput": 787.36, "total_tokens": 5818016} {"current_steps": 17865, "total_steps": 40000, "loss": 0.0887, "lr": 2.9174381239601166e-05, "epoch": 14.619729840360213, "percentage": 44.66, "elapsed_time": "2:03:10", "remaining_time": "2:32:37", "throughput": 787.4, "total_tokens": 5819632} {"current_steps": 17870, "total_steps": 40000, "loss": 0.1575, "lr": 2.916470126763783e-05, "epoch": 14.623823168235775, "percentage": 44.67, "elapsed_time": "2:03:12", "remaining_time": "2:32:35", "throughput": 787.44, "total_tokens": 5821280} {"current_steps": 17875, "total_steps": 40000, "loss": 0.1623, "lr": 2.9155020653425203e-05, "epoch": 14.627916496111338, "percentage": 44.69, "elapsed_time": "2:03:14", "remaining_time": "2:32:32", "throughput": 787.48, "total_tokens": 5822944} {"current_steps": 17880, "total_steps": 40000, "loss": 0.137, "lr": 2.9145339398456184e-05, "epoch": 14.632009823986902, "percentage": 44.7, "elapsed_time": "2:03:16", "remaining_time": "2:32:30", "throughput": 787.51, "total_tokens": 5824560} {"current_steps": 17885, "total_steps": 40000, "loss": 0.2248, "lr": 2.913565750422374e-05, "epoch": 14.636103151862464, "percentage": 44.71, "elapsed_time": "2:03:17", "remaining_time": "2:32:27", "throughput": 787.56, "total_tokens": 5826240} {"current_steps": 17890, "total_steps": 40000, "loss": 0.1372, "lr": 2.9125974972220938e-05, "epoch": 14.640196479738027, "percentage": 44.73, "elapsed_time": "2:03:19", "remaining_time": "2:32:25", "throughput": 787.6, "total_tokens": 5827920} {"current_steps": 17895, "total_steps": 40000, "loss": 0.0992, "lr": 2.9116291803940932e-05, "epoch": 14.644289807613589, "percentage": 44.74, "elapsed_time": "2:03:21", "remaining_time": "2:32:22", "throughput": 787.64, "total_tokens": 5829552} {"current_steps": 17900, "total_steps": 40000, "loss": 0.1491, "lr": 2.910660800087701e-05, "epoch": 14.648383135489153, "percentage": 44.75, "elapsed_time": "2:03:23", "remaining_time": "2:32:20", "throughput": 787.68, "total_tokens": 5831216} {"current_steps": 17905, "total_steps": 40000, "loss": 0.1481, "lr": 2.909692356452254e-05, "epoch": 14.652476463364716, "percentage": 44.76, "elapsed_time": "2:03:24", "remaining_time": "2:32:17", "throughput": 787.72, "total_tokens": 5832816} {"current_steps": 17910, "total_steps": 40000, "loss": 0.2239, "lr": 2.9087238496370962e-05, "epoch": 14.656569791240278, "percentage": 44.77, "elapsed_time": "2:03:26", "remaining_time": "2:32:15", "throughput": 787.77, "total_tokens": 5834544} {"current_steps": 17915, "total_steps": 40000, "loss": 0.1577, "lr": 2.907755279791583e-05, "epoch": 14.660663119115842, "percentage": 44.79, "elapsed_time": "2:03:28", "remaining_time": "2:32:12", "throughput": 787.8, "total_tokens": 5836160} {"current_steps": 17920, "total_steps": 40000, "loss": 0.1651, "lr": 2.906786647065083e-05, "epoch": 14.664756446991404, "percentage": 44.8, "elapsed_time": "2:03:29", "remaining_time": "2:32:10", "throughput": 787.83, "total_tokens": 5837760} {"current_steps": 17925, "total_steps": 40000, "loss": 0.1771, "lr": 2.9058179516069695e-05, "epoch": 14.668849774866967, "percentage": 44.81, "elapsed_time": "2:03:31", "remaining_time": "2:32:07", "throughput": 787.87, "total_tokens": 5839392} {"current_steps": 17930, "total_steps": 40000, "loss": 0.1577, "lr": 2.9048491935666282e-05, "epoch": 14.67294310274253, "percentage": 44.82, "elapsed_time": "2:03:33", "remaining_time": "2:32:05", "throughput": 787.91, "total_tokens": 5841024} {"current_steps": 17935, "total_steps": 40000, "loss": 0.1606, "lr": 2.9038803730934534e-05, "epoch": 14.677036430618092, "percentage": 44.84, "elapsed_time": "2:03:35", "remaining_time": "2:32:02", "throughput": 787.95, "total_tokens": 5842672} {"current_steps": 17940, "total_steps": 40000, "loss": 0.2462, "lr": 2.9029114903368503e-05, "epoch": 14.681129758493656, "percentage": 44.85, "elapsed_time": "2:03:36", "remaining_time": "2:32:00", "throughput": 787.99, "total_tokens": 5844336} {"current_steps": 17945, "total_steps": 40000, "loss": 0.1429, "lr": 2.9019425454462318e-05, "epoch": 14.685223086369218, "percentage": 44.86, "elapsed_time": "2:03:38", "remaining_time": "2:31:57", "throughput": 788.02, "total_tokens": 5845920} {"current_steps": 17950, "total_steps": 40000, "loss": 0.2077, "lr": 2.9009735385710212e-05, "epoch": 14.68931641424478, "percentage": 44.88, "elapsed_time": "2:03:40", "remaining_time": "2:31:55", "throughput": 788.07, "total_tokens": 5847616} {"current_steps": 17955, "total_steps": 40000, "loss": 0.218, "lr": 2.900004469860652e-05, "epoch": 14.693409742120345, "percentage": 44.89, "elapsed_time": "2:03:41", "remaining_time": "2:31:52", "throughput": 788.1, "total_tokens": 5849216} {"current_steps": 17960, "total_steps": 40000, "loss": 0.2108, "lr": 2.8990353394645668e-05, "epoch": 14.697503069995907, "percentage": 44.9, "elapsed_time": "2:03:43", "remaining_time": "2:31:50", "throughput": 788.14, "total_tokens": 5850848} {"current_steps": 17965, "total_steps": 40000, "loss": 0.1756, "lr": 2.8980661475322186e-05, "epoch": 14.70159639787147, "percentage": 44.91, "elapsed_time": "2:03:45", "remaining_time": "2:31:47", "throughput": 788.17, "total_tokens": 5852464} {"current_steps": 17970, "total_steps": 40000, "loss": 0.1712, "lr": 2.897096894213067e-05, "epoch": 14.705689725747032, "percentage": 44.92, "elapsed_time": "2:03:47", "remaining_time": "2:31:45", "throughput": 788.22, "total_tokens": 5854160} {"current_steps": 17975, "total_steps": 40000, "loss": 0.212, "lr": 2.8961275796565845e-05, "epoch": 14.709783053622596, "percentage": 44.94, "elapsed_time": "2:03:48", "remaining_time": "2:31:42", "throughput": 788.26, "total_tokens": 5855792} {"current_steps": 17980, "total_steps": 40000, "loss": 0.1439, "lr": 2.8951582040122517e-05, "epoch": 14.713876381498158, "percentage": 44.95, "elapsed_time": "2:03:50", "remaining_time": "2:31:40", "throughput": 788.29, "total_tokens": 5857408} {"current_steps": 17985, "total_steps": 40000, "loss": 0.1758, "lr": 2.894188767429557e-05, "epoch": 14.71796970937372, "percentage": 44.96, "elapsed_time": "2:03:52", "remaining_time": "2:31:37", "throughput": 788.33, "total_tokens": 5859040} {"current_steps": 17990, "total_steps": 40000, "loss": 0.1549, "lr": 2.8932192700580014e-05, "epoch": 14.722063037249283, "percentage": 44.98, "elapsed_time": "2:03:53", "remaining_time": "2:31:35", "throughput": 788.37, "total_tokens": 5860688} {"current_steps": 17995, "total_steps": 40000, "loss": 0.1333, "lr": 2.8922497120470916e-05, "epoch": 14.726156365124847, "percentage": 44.99, "elapsed_time": "2:03:55", "remaining_time": "2:31:32", "throughput": 788.4, "total_tokens": 5862288} {"current_steps": 18000, "total_steps": 40000, "loss": 0.2159, "lr": 2.891280093546348e-05, "epoch": 14.73024969300041, "percentage": 45.0, "elapsed_time": "2:03:57", "remaining_time": "2:31:30", "throughput": 788.44, "total_tokens": 5863936} {"current_steps": 18000, "total_steps": 40000, "eval_loss": 0.2110905647277832, "epoch": 14.73024969300041, "percentage": 45.0, "elapsed_time": "2:04:09", "remaining_time": "2:31:45", "throughput": 787.12, "total_tokens": 5863936} {"current_steps": 18005, "total_steps": 40000, "loss": 0.2133, "lr": 2.890310414705297e-05, "epoch": 14.734343020875972, "percentage": 45.01, "elapsed_time": "2:04:13", "remaining_time": "2:31:45", "throughput": 786.95, "total_tokens": 5865584} {"current_steps": 18010, "total_steps": 40000, "loss": 0.2225, "lr": 2.8893406756734742e-05, "epoch": 14.738436348751534, "percentage": 45.02, "elapsed_time": "2:04:15", "remaining_time": "2:31:42", "throughput": 786.97, "total_tokens": 5867088} {"current_steps": 18015, "total_steps": 40000, "loss": 0.1397, "lr": 2.888370876600427e-05, "epoch": 14.742529676627099, "percentage": 45.04, "elapsed_time": "2:04:16", "remaining_time": "2:31:40", "throughput": 787.01, "total_tokens": 5868720} {"current_steps": 18020, "total_steps": 40000, "loss": 0.2033, "lr": 2.8874010176357104e-05, "epoch": 14.746623004502661, "percentage": 45.05, "elapsed_time": "2:04:18", "remaining_time": "2:31:37", "throughput": 787.05, "total_tokens": 5870384} {"current_steps": 18025, "total_steps": 40000, "loss": 0.1632, "lr": 2.886431098928888e-05, "epoch": 14.750716332378223, "percentage": 45.06, "elapsed_time": "2:04:20", "remaining_time": "2:31:35", "throughput": 787.09, "total_tokens": 5872000} {"current_steps": 18030, "total_steps": 40000, "loss": 0.1383, "lr": 2.885461120629534e-05, "epoch": 14.754809660253786, "percentage": 45.07, "elapsed_time": "2:04:22", "remaining_time": "2:31:32", "throughput": 787.12, "total_tokens": 5873600} {"current_steps": 18035, "total_steps": 40000, "loss": 0.1687, "lr": 2.8844910828872317e-05, "epoch": 14.75890298812935, "percentage": 45.09, "elapsed_time": "2:04:23", "remaining_time": "2:31:30", "throughput": 787.17, "total_tokens": 5875296} {"current_steps": 18040, "total_steps": 40000, "loss": 0.3013, "lr": 2.8835209858515715e-05, "epoch": 14.762996316004912, "percentage": 45.1, "elapsed_time": "2:04:25", "remaining_time": "2:31:27", "throughput": 787.21, "total_tokens": 5876960} {"current_steps": 18045, "total_steps": 40000, "loss": 0.1875, "lr": 2.8825508296721566e-05, "epoch": 14.767089643880475, "percentage": 45.11, "elapsed_time": "2:04:27", "remaining_time": "2:31:25", "throughput": 787.25, "total_tokens": 5878608} {"current_steps": 18050, "total_steps": 40000, "loss": 0.207, "lr": 2.881580614498596e-05, "epoch": 14.771182971756037, "percentage": 45.12, "elapsed_time": "2:04:28", "remaining_time": "2:31:22", "throughput": 787.29, "total_tokens": 5880256} {"current_steps": 18055, "total_steps": 40000, "loss": 0.1514, "lr": 2.8806103404805103e-05, "epoch": 14.775276299631601, "percentage": 45.14, "elapsed_time": "2:04:30", "remaining_time": "2:31:20", "throughput": 787.33, "total_tokens": 5881952} {"current_steps": 18060, "total_steps": 40000, "loss": 0.3533, "lr": 2.8796400077675257e-05, "epoch": 14.779369627507164, "percentage": 45.15, "elapsed_time": "2:04:32", "remaining_time": "2:31:17", "throughput": 787.37, "total_tokens": 5883552} {"current_steps": 18065, "total_steps": 40000, "loss": 0.2453, "lr": 2.8786696165092812e-05, "epoch": 14.783462955382726, "percentage": 45.16, "elapsed_time": "2:04:34", "remaining_time": "2:31:15", "throughput": 787.38, "total_tokens": 5885200} {"current_steps": 18070, "total_steps": 40000, "loss": 0.2056, "lr": 2.8776991668554236e-05, "epoch": 14.787556283258288, "percentage": 45.17, "elapsed_time": "2:04:36", "remaining_time": "2:31:13", "throughput": 787.42, "total_tokens": 5886864} {"current_steps": 18075, "total_steps": 40000, "loss": 0.1616, "lr": 2.876728658955608e-05, "epoch": 14.791649611133852, "percentage": 45.19, "elapsed_time": "2:04:37", "remaining_time": "2:31:10", "throughput": 787.46, "total_tokens": 5888512} {"current_steps": 18080, "total_steps": 40000, "loss": 0.2598, "lr": 2.8757580929594986e-05, "epoch": 14.795742939009415, "percentage": 45.2, "elapsed_time": "2:04:39", "remaining_time": "2:31:08", "throughput": 787.49, "total_tokens": 5890112} {"current_steps": 18085, "total_steps": 40000, "loss": 0.2276, "lr": 2.87478746901677e-05, "epoch": 14.799836266884977, "percentage": 45.21, "elapsed_time": "2:04:41", "remaining_time": "2:31:05", "throughput": 787.54, "total_tokens": 5891792} {"current_steps": 18090, "total_steps": 40000, "loss": 0.1684, "lr": 2.873816787277103e-05, "epoch": 14.80392959476054, "percentage": 45.23, "elapsed_time": "2:04:43", "remaining_time": "2:31:03", "throughput": 787.57, "total_tokens": 5893424} {"current_steps": 18095, "total_steps": 40000, "loss": 0.1677, "lr": 2.8728460478901903e-05, "epoch": 14.808022922636104, "percentage": 45.24, "elapsed_time": "2:04:44", "remaining_time": "2:31:00", "throughput": 787.61, "total_tokens": 5895056} {"current_steps": 18100, "total_steps": 40000, "loss": 0.1972, "lr": 2.8718752510057307e-05, "epoch": 14.812116250511666, "percentage": 45.25, "elapsed_time": "2:04:46", "remaining_time": "2:30:58", "throughput": 787.65, "total_tokens": 5896704} {"current_steps": 18105, "total_steps": 40000, "loss": 0.1523, "lr": 2.870904396773435e-05, "epoch": 14.816209578387229, "percentage": 45.26, "elapsed_time": "2:04:48", "remaining_time": "2:30:55", "throughput": 787.68, "total_tokens": 5898304} {"current_steps": 18110, "total_steps": 40000, "loss": 0.1974, "lr": 2.86993348534302e-05, "epoch": 14.820302906262791, "percentage": 45.27, "elapsed_time": "2:04:49", "remaining_time": "2:30:53", "throughput": 787.72, "total_tokens": 5899920} {"current_steps": 18115, "total_steps": 40000, "loss": 0.1806, "lr": 2.868962516864212e-05, "epoch": 14.824396234138355, "percentage": 45.29, "elapsed_time": "2:04:51", "remaining_time": "2:30:50", "throughput": 787.75, "total_tokens": 5901488} {"current_steps": 18120, "total_steps": 40000, "loss": 0.221, "lr": 2.8679914914867477e-05, "epoch": 14.828489562013917, "percentage": 45.3, "elapsed_time": "2:04:53", "remaining_time": "2:30:48", "throughput": 787.79, "total_tokens": 5903184} {"current_steps": 18125, "total_steps": 40000, "loss": 0.2232, "lr": 2.8670204093603713e-05, "epoch": 14.83258288988948, "percentage": 45.31, "elapsed_time": "2:04:55", "remaining_time": "2:30:45", "throughput": 787.83, "total_tokens": 5904832} {"current_steps": 18130, "total_steps": 40000, "loss": 0.1437, "lr": 2.8660492706348357e-05, "epoch": 14.836676217765042, "percentage": 45.32, "elapsed_time": "2:04:56", "remaining_time": "2:30:43", "throughput": 787.88, "total_tokens": 5906528} {"current_steps": 18135, "total_steps": 40000, "loss": 0.2063, "lr": 2.8650780754599022e-05, "epoch": 14.840769545640606, "percentage": 45.34, "elapsed_time": "2:04:58", "remaining_time": "2:30:40", "throughput": 787.91, "total_tokens": 5908144} {"current_steps": 18140, "total_steps": 40000, "loss": 0.2222, "lr": 2.8641068239853407e-05, "epoch": 14.844862873516169, "percentage": 45.35, "elapsed_time": "2:05:00", "remaining_time": "2:30:38", "throughput": 787.95, "total_tokens": 5909808} {"current_steps": 18145, "total_steps": 40000, "loss": 0.1871, "lr": 2.863135516360932e-05, "epoch": 14.848956201391731, "percentage": 45.36, "elapsed_time": "2:05:01", "remaining_time": "2:30:35", "throughput": 787.99, "total_tokens": 5911456} {"current_steps": 18150, "total_steps": 40000, "loss": 0.152, "lr": 2.8621641527364633e-05, "epoch": 14.853049529267293, "percentage": 45.38, "elapsed_time": "2:05:03", "remaining_time": "2:30:33", "throughput": 788.02, "total_tokens": 5913040} {"current_steps": 18155, "total_steps": 40000, "loss": 0.2321, "lr": 2.8611927332617313e-05, "epoch": 14.857142857142858, "percentage": 45.39, "elapsed_time": "2:05:05", "remaining_time": "2:30:30", "throughput": 788.06, "total_tokens": 5914624} {"current_steps": 18160, "total_steps": 40000, "loss": 0.2093, "lr": 2.8602212580865405e-05, "epoch": 14.86123618501842, "percentage": 45.4, "elapsed_time": "2:05:07", "remaining_time": "2:30:28", "throughput": 788.09, "total_tokens": 5916272} {"current_steps": 18165, "total_steps": 40000, "loss": 0.1755, "lr": 2.859249727360705e-05, "epoch": 14.865329512893982, "percentage": 45.41, "elapsed_time": "2:05:08", "remaining_time": "2:30:25", "throughput": 788.13, "total_tokens": 5917920} {"current_steps": 18170, "total_steps": 40000, "loss": 0.2422, "lr": 2.8582781412340465e-05, "epoch": 14.869422840769545, "percentage": 45.42, "elapsed_time": "2:05:10", "remaining_time": "2:30:23", "throughput": 788.17, "total_tokens": 5919520} {"current_steps": 18175, "total_steps": 40000, "loss": 0.1713, "lr": 2.857306499856397e-05, "epoch": 14.873516168645109, "percentage": 45.44, "elapsed_time": "2:05:12", "remaining_time": "2:30:20", "throughput": 788.2, "total_tokens": 5921136} {"current_steps": 18180, "total_steps": 40000, "loss": 0.1657, "lr": 2.856334803377594e-05, "epoch": 14.877609496520671, "percentage": 45.45, "elapsed_time": "2:05:13", "remaining_time": "2:30:18", "throughput": 788.22, "total_tokens": 5922656} {"current_steps": 18185, "total_steps": 40000, "loss": 0.2472, "lr": 2.8553630519474867e-05, "epoch": 14.881702824396234, "percentage": 45.46, "elapsed_time": "2:05:15", "remaining_time": "2:30:15", "throughput": 788.26, "total_tokens": 5924272} {"current_steps": 18190, "total_steps": 40000, "loss": 0.1598, "lr": 2.8543912457159317e-05, "epoch": 14.885796152271798, "percentage": 45.48, "elapsed_time": "2:05:17", "remaining_time": "2:30:13", "throughput": 788.29, "total_tokens": 5925856} {"current_steps": 18195, "total_steps": 40000, "loss": 0.279, "lr": 2.853419384832792e-05, "epoch": 14.88988948014736, "percentage": 45.49, "elapsed_time": "2:05:19", "remaining_time": "2:30:10", "throughput": 788.34, "total_tokens": 5927584} {"current_steps": 18200, "total_steps": 40000, "loss": 0.1695, "lr": 2.8524474694479423e-05, "epoch": 14.893982808022923, "percentage": 45.5, "elapsed_time": "2:05:20", "remaining_time": "2:30:08", "throughput": 788.37, "total_tokens": 5929216} {"current_steps": 18200, "total_steps": 40000, "eval_loss": 0.2062707245349884, "epoch": 14.893982808022923, "percentage": 45.5, "elapsed_time": "2:05:33", "remaining_time": "2:30:23", "throughput": 787.07, "total_tokens": 5929216} {"current_steps": 18205, "total_steps": 40000, "loss": 0.1593, "lr": 2.851475499711264e-05, "epoch": 14.898076135898485, "percentage": 45.51, "elapsed_time": "2:05:36", "remaining_time": "2:30:22", "throughput": 786.98, "total_tokens": 5930976} {"current_steps": 18210, "total_steps": 40000, "loss": 0.1888, "lr": 2.8505034757726468e-05, "epoch": 14.902169463774047, "percentage": 45.52, "elapsed_time": "2:05:38", "remaining_time": "2:30:20", "throughput": 787.0, "total_tokens": 5932560} {"current_steps": 18215, "total_steps": 40000, "loss": 0.1214, "lr": 2.8495313977819886e-05, "epoch": 14.906262791649612, "percentage": 45.54, "elapsed_time": "2:05:39", "remaining_time": "2:30:17", "throughput": 787.04, "total_tokens": 5934192} {"current_steps": 18220, "total_steps": 40000, "loss": 0.1953, "lr": 2.8485592658891956e-05, "epoch": 14.910356119525174, "percentage": 45.55, "elapsed_time": "2:05:41", "remaining_time": "2:30:15", "throughput": 787.08, "total_tokens": 5935840} {"current_steps": 18225, "total_steps": 40000, "loss": 0.1989, "lr": 2.8475870802441844e-05, "epoch": 14.914449447400736, "percentage": 45.56, "elapsed_time": "2:05:43", "remaining_time": "2:30:12", "throughput": 787.11, "total_tokens": 5937440} {"current_steps": 18230, "total_steps": 40000, "loss": 0.1611, "lr": 2.8466148409968774e-05, "epoch": 14.9185427752763, "percentage": 45.57, "elapsed_time": "2:05:45", "remaining_time": "2:30:10", "throughput": 787.15, "total_tokens": 5939104} {"current_steps": 18235, "total_steps": 40000, "loss": 0.1097, "lr": 2.8456425482972067e-05, "epoch": 14.922636103151863, "percentage": 45.59, "elapsed_time": "2:05:46", "remaining_time": "2:30:07", "throughput": 787.19, "total_tokens": 5940704} {"current_steps": 18240, "total_steps": 40000, "loss": 0.1546, "lr": 2.84467020229511e-05, "epoch": 14.926729431027425, "percentage": 45.6, "elapsed_time": "2:05:48", "remaining_time": "2:30:05", "throughput": 787.23, "total_tokens": 5942352} {"current_steps": 18245, "total_steps": 40000, "loss": 0.1645, "lr": 2.8436978031405375e-05, "epoch": 14.930822758902988, "percentage": 45.61, "elapsed_time": "2:05:50", "remaining_time": "2:30:02", "throughput": 787.27, "total_tokens": 5944016} {"current_steps": 18250, "total_steps": 40000, "loss": 0.1829, "lr": 2.842725350983445e-05, "epoch": 14.934916086778552, "percentage": 45.62, "elapsed_time": "2:05:51", "remaining_time": "2:30:00", "throughput": 787.3, "total_tokens": 5945632} {"current_steps": 18255, "total_steps": 40000, "loss": 0.1995, "lr": 2.8417528459737957e-05, "epoch": 14.939009414654114, "percentage": 45.64, "elapsed_time": "2:05:53", "remaining_time": "2:29:57", "throughput": 787.34, "total_tokens": 5947280} {"current_steps": 18260, "total_steps": 40000, "loss": 0.2181, "lr": 2.8407802882615624e-05, "epoch": 14.943102742529677, "percentage": 45.65, "elapsed_time": "2:05:55", "remaining_time": "2:29:55", "throughput": 787.38, "total_tokens": 5948928} {"current_steps": 18265, "total_steps": 40000, "loss": 0.1918, "lr": 2.8398076779967277e-05, "epoch": 14.947196070405239, "percentage": 45.66, "elapsed_time": "2:05:57", "remaining_time": "2:29:52", "throughput": 787.41, "total_tokens": 5950512} {"current_steps": 18270, "total_steps": 40000, "loss": 0.1756, "lr": 2.8388350153292774e-05, "epoch": 14.951289398280803, "percentage": 45.67, "elapsed_time": "2:05:58", "remaining_time": "2:29:50", "throughput": 787.46, "total_tokens": 5952208} {"current_steps": 18275, "total_steps": 40000, "loss": 0.1711, "lr": 2.8378623004092103e-05, "epoch": 14.955382726156365, "percentage": 45.69, "elapsed_time": "2:06:00", "remaining_time": "2:29:47", "throughput": 787.49, "total_tokens": 5953840} {"current_steps": 18280, "total_steps": 40000, "loss": 0.1682, "lr": 2.8368895333865302e-05, "epoch": 14.959476054031928, "percentage": 45.7, "elapsed_time": "2:06:02", "remaining_time": "2:29:45", "throughput": 787.52, "total_tokens": 5955408} {"current_steps": 18285, "total_steps": 40000, "loss": 0.1571, "lr": 2.835916714411251e-05, "epoch": 14.96356938190749, "percentage": 45.71, "elapsed_time": "2:06:03", "remaining_time": "2:29:42", "throughput": 787.56, "total_tokens": 5957024} {"current_steps": 18290, "total_steps": 40000, "loss": 0.2129, "lr": 2.8349438436333926e-05, "epoch": 14.967662709783054, "percentage": 45.73, "elapsed_time": "2:06:05", "remaining_time": "2:29:40", "throughput": 787.59, "total_tokens": 5958656} {"current_steps": 18295, "total_steps": 40000, "loss": 0.1145, "lr": 2.833970921202984e-05, "epoch": 14.971756037658617, "percentage": 45.74, "elapsed_time": "2:06:07", "remaining_time": "2:29:37", "throughput": 787.63, "total_tokens": 5960304} {"current_steps": 18300, "total_steps": 40000, "loss": 0.1804, "lr": 2.8329979472700628e-05, "epoch": 14.97584936553418, "percentage": 45.75, "elapsed_time": "2:06:09", "remaining_time": "2:29:35", "throughput": 787.67, "total_tokens": 5961920} {"current_steps": 18305, "total_steps": 40000, "loss": 0.1949, "lr": 2.832024921984674e-05, "epoch": 14.979942693409741, "percentage": 45.76, "elapsed_time": "2:06:10", "remaining_time": "2:29:32", "throughput": 787.71, "total_tokens": 5963568} {"current_steps": 18310, "total_steps": 40000, "loss": 0.1652, "lr": 2.8310518454968693e-05, "epoch": 14.984036021285306, "percentage": 45.77, "elapsed_time": "2:06:12", "remaining_time": "2:29:30", "throughput": 787.75, "total_tokens": 5965248} {"current_steps": 18315, "total_steps": 40000, "loss": 0.1351, "lr": 2.8300787179567095e-05, "epoch": 14.988129349160868, "percentage": 45.79, "elapsed_time": "2:06:14", "remaining_time": "2:29:27", "throughput": 787.79, "total_tokens": 5966912} {"current_steps": 18320, "total_steps": 40000, "loss": 0.1707, "lr": 2.8291055395142636e-05, "epoch": 14.99222267703643, "percentage": 45.8, "elapsed_time": "2:06:15", "remaining_time": "2:29:25", "throughput": 787.83, "total_tokens": 5968528} {"current_steps": 18325, "total_steps": 40000, "loss": 0.1561, "lr": 2.8281323103196073e-05, "epoch": 14.996316004911993, "percentage": 45.81, "elapsed_time": "2:06:17", "remaining_time": "2:29:22", "throughput": 787.87, "total_tokens": 5970208} {"current_steps": 18330, "total_steps": 40000, "loss": 0.22, "lr": 2.8271590305228256e-05, "epoch": 15.0, "percentage": 45.82, "elapsed_time": "2:06:19", "remaining_time": "2:29:20", "throughput": 787.87, "total_tokens": 5971576} {"current_steps": 18335, "total_steps": 40000, "loss": 0.1721, "lr": 2.82618570027401e-05, "epoch": 15.004093327875562, "percentage": 45.84, "elapsed_time": "2:06:21", "remaining_time": "2:29:18", "throughput": 787.89, "total_tokens": 5973240} {"current_steps": 18340, "total_steps": 40000, "loss": 0.1826, "lr": 2.8252123197232604e-05, "epoch": 15.008186655751127, "percentage": 45.85, "elapsed_time": "2:06:22", "remaining_time": "2:29:15", "throughput": 787.93, "total_tokens": 5974856} {"current_steps": 18345, "total_steps": 40000, "loss": 0.1841, "lr": 2.8242388890206843e-05, "epoch": 15.012279983626689, "percentage": 45.86, "elapsed_time": "2:06:24", "remaining_time": "2:29:13", "throughput": 787.97, "total_tokens": 5976552} {"current_steps": 18350, "total_steps": 40000, "loss": 0.1927, "lr": 2.8232654083163967e-05, "epoch": 15.016373311502251, "percentage": 45.88, "elapsed_time": "2:06:26", "remaining_time": "2:29:10", "throughput": 788.01, "total_tokens": 5978200} {"current_steps": 18355, "total_steps": 40000, "loss": 0.1372, "lr": 2.822291877760521e-05, "epoch": 15.020466639377814, "percentage": 45.89, "elapsed_time": "2:06:28", "remaining_time": "2:29:08", "throughput": 788.04, "total_tokens": 5979784} {"current_steps": 18360, "total_steps": 40000, "loss": 0.2318, "lr": 2.8213182975031864e-05, "epoch": 15.024559967253378, "percentage": 45.9, "elapsed_time": "2:06:29", "remaining_time": "2:29:05", "throughput": 788.07, "total_tokens": 5981384} {"current_steps": 18365, "total_steps": 40000, "loss": 0.3085, "lr": 2.8203446676945337e-05, "epoch": 15.02865329512894, "percentage": 45.91, "elapsed_time": "2:06:31", "remaining_time": "2:29:03", "throughput": 788.1, "total_tokens": 5982968} {"current_steps": 18370, "total_steps": 40000, "loss": 0.1446, "lr": 2.8193709884847075e-05, "epoch": 15.032746623004503, "percentage": 45.92, "elapsed_time": "2:06:33", "remaining_time": "2:29:00", "throughput": 788.14, "total_tokens": 5984584} {"current_steps": 18375, "total_steps": 40000, "loss": 0.1756, "lr": 2.8183972600238605e-05, "epoch": 15.036839950880065, "percentage": 45.94, "elapsed_time": "2:06:35", "remaining_time": "2:28:58", "throughput": 788.17, "total_tokens": 5986200} {"current_steps": 18380, "total_steps": 40000, "loss": 0.1647, "lr": 2.817423482462156e-05, "epoch": 15.04093327875563, "percentage": 45.95, "elapsed_time": "2:06:36", "remaining_time": "2:28:55", "throughput": 788.21, "total_tokens": 5987832} {"current_steps": 18385, "total_steps": 40000, "loss": 0.183, "lr": 2.8164496559497605e-05, "epoch": 15.045026606631192, "percentage": 45.96, "elapsed_time": "2:06:38", "remaining_time": "2:28:53", "throughput": 788.25, "total_tokens": 5989496} {"current_steps": 18390, "total_steps": 40000, "loss": 0.2253, "lr": 2.815475780636852e-05, "epoch": 15.049119934506754, "percentage": 45.98, "elapsed_time": "2:06:40", "remaining_time": "2:28:50", "throughput": 788.29, "total_tokens": 5991144} {"current_steps": 18395, "total_steps": 40000, "loss": 0.1712, "lr": 2.814501856673613e-05, "epoch": 15.053213262382316, "percentage": 45.99, "elapsed_time": "2:06:41", "remaining_time": "2:28:48", "throughput": 788.33, "total_tokens": 5992792} {"current_steps": 18400, "total_steps": 40000, "loss": 0.2496, "lr": 2.8135278842102353e-05, "epoch": 15.05730659025788, "percentage": 46.0, "elapsed_time": "2:06:43", "remaining_time": "2:28:45", "throughput": 788.36, "total_tokens": 5994376} {"current_steps": 18400, "total_steps": 40000, "eval_loss": 0.2050824612379074, "epoch": 15.05730659025788, "percentage": 46.0, "elapsed_time": "2:06:56", "remaining_time": "2:29:00", "throughput": 787.07, "total_tokens": 5994376} {"current_steps": 18405, "total_steps": 40000, "loss": 0.1458, "lr": 2.8125538633969183e-05, "epoch": 15.061399918133443, "percentage": 46.01, "elapsed_time": "2:06:59", "remaining_time": "2:29:00", "throughput": 786.94, "total_tokens": 5996024} {"current_steps": 18410, "total_steps": 40000, "loss": 0.1963, "lr": 2.8115797943838677e-05, "epoch": 15.065493246009005, "percentage": 46.02, "elapsed_time": "2:07:01", "remaining_time": "2:28:57", "throughput": 786.96, "total_tokens": 5997608} {"current_steps": 18415, "total_steps": 40000, "loss": 0.2154, "lr": 2.810605677321298e-05, "epoch": 15.069586573884568, "percentage": 46.04, "elapsed_time": "2:07:02", "remaining_time": "2:28:55", "throughput": 787.0, "total_tokens": 5999224} {"current_steps": 18420, "total_steps": 40000, "loss": 0.1548, "lr": 2.809631512359428e-05, "epoch": 15.073679901760132, "percentage": 46.05, "elapsed_time": "2:07:04", "remaining_time": "2:28:52", "throughput": 787.02, "total_tokens": 6000760} {"current_steps": 18425, "total_steps": 40000, "loss": 0.1427, "lr": 2.8086572996484884e-05, "epoch": 15.077773229635694, "percentage": 46.06, "elapsed_time": "2:07:06", "remaining_time": "2:28:50", "throughput": 787.06, "total_tokens": 6002360} {"current_steps": 18430, "total_steps": 40000, "loss": 0.215, "lr": 2.8076830393387143e-05, "epoch": 15.081866557511256, "percentage": 46.08, "elapsed_time": "2:07:08", "remaining_time": "2:28:47", "throughput": 787.08, "total_tokens": 6003896} {"current_steps": 18435, "total_steps": 40000, "loss": 0.2066, "lr": 2.8067087315803497e-05, "epoch": 15.085959885386819, "percentage": 46.09, "elapsed_time": "2:07:09", "remaining_time": "2:28:45", "throughput": 787.12, "total_tokens": 6005576} {"current_steps": 18440, "total_steps": 40000, "loss": 0.2575, "lr": 2.8057343765236433e-05, "epoch": 15.090053213262383, "percentage": 46.1, "elapsed_time": "2:07:11", "remaining_time": "2:28:42", "throughput": 787.17, "total_tokens": 6007288} {"current_steps": 18445, "total_steps": 40000, "loss": 0.2251, "lr": 2.804759974318854e-05, "epoch": 15.094146541137945, "percentage": 46.11, "elapsed_time": "2:07:13", "remaining_time": "2:28:40", "throughput": 787.21, "total_tokens": 6008936} {"current_steps": 18450, "total_steps": 40000, "loss": 0.1922, "lr": 2.8037855251162482e-05, "epoch": 15.098239869013508, "percentage": 46.12, "elapsed_time": "2:07:14", "remaining_time": "2:28:37", "throughput": 787.24, "total_tokens": 6010568} {"current_steps": 18455, "total_steps": 40000, "loss": 0.2293, "lr": 2.802811029066096e-05, "epoch": 15.10233319688907, "percentage": 46.14, "elapsed_time": "2:07:16", "remaining_time": "2:28:35", "throughput": 787.29, "total_tokens": 6012248} {"current_steps": 18460, "total_steps": 40000, "loss": 0.1004, "lr": 2.8018364863186764e-05, "epoch": 15.106426524764634, "percentage": 46.15, "elapsed_time": "2:07:18", "remaining_time": "2:28:32", "throughput": 787.32, "total_tokens": 6013832} {"current_steps": 18465, "total_steps": 40000, "loss": 0.2382, "lr": 2.800861897024279e-05, "epoch": 15.110519852640197, "percentage": 46.16, "elapsed_time": "2:07:20", "remaining_time": "2:28:30", "throughput": 787.35, "total_tokens": 6015464} {"current_steps": 18470, "total_steps": 40000, "loss": 0.1762, "lr": 2.799887261333196e-05, "epoch": 15.114613180515759, "percentage": 46.17, "elapsed_time": "2:07:21", "remaining_time": "2:28:27", "throughput": 787.39, "total_tokens": 6017128} {"current_steps": 18475, "total_steps": 40000, "loss": 0.2108, "lr": 2.798912579395728e-05, "epoch": 15.118706508391321, "percentage": 46.19, "elapsed_time": "2:07:23", "remaining_time": "2:28:25", "throughput": 787.43, "total_tokens": 6018744} {"current_steps": 18480, "total_steps": 40000, "loss": 0.2341, "lr": 2.797937851362185e-05, "epoch": 15.122799836266886, "percentage": 46.2, "elapsed_time": "2:07:25", "remaining_time": "2:28:22", "throughput": 787.46, "total_tokens": 6020376} {"current_steps": 18485, "total_steps": 40000, "loss": 0.1964, "lr": 2.7969630773828802e-05, "epoch": 15.126893164142448, "percentage": 46.21, "elapsed_time": "2:07:26", "remaining_time": "2:28:20", "throughput": 787.5, "total_tokens": 6022008} {"current_steps": 18490, "total_steps": 40000, "loss": 0.2177, "lr": 2.7959882576081382e-05, "epoch": 15.13098649201801, "percentage": 46.23, "elapsed_time": "2:07:28", "remaining_time": "2:28:17", "throughput": 787.53, "total_tokens": 6023608} {"current_steps": 18495, "total_steps": 40000, "loss": 0.2176, "lr": 2.795013392188286e-05, "epoch": 15.135079819893573, "percentage": 46.24, "elapsed_time": "2:07:30", "remaining_time": "2:28:15", "throughput": 787.57, "total_tokens": 6025240} {"current_steps": 18500, "total_steps": 40000, "loss": 0.2435, "lr": 2.7940384812736614e-05, "epoch": 15.139173147769137, "percentage": 46.25, "elapsed_time": "2:07:32", "remaining_time": "2:28:13", "throughput": 787.6, "total_tokens": 6026840} {"current_steps": 18505, "total_steps": 40000, "loss": 0.2182, "lr": 2.7930635250146087e-05, "epoch": 15.1432664756447, "percentage": 46.26, "elapsed_time": "2:07:33", "remaining_time": "2:28:10", "throughput": 787.64, "total_tokens": 6028520} {"current_steps": 18510, "total_steps": 40000, "loss": 0.2035, "lr": 2.792088523561477e-05, "epoch": 15.147359803520262, "percentage": 46.27, "elapsed_time": "2:07:35", "remaining_time": "2:28:08", "throughput": 787.68, "total_tokens": 6030120} {"current_steps": 18515, "total_steps": 40000, "loss": 0.1954, "lr": 2.7911134770646246e-05, "epoch": 15.151453131395824, "percentage": 46.29, "elapsed_time": "2:07:37", "remaining_time": "2:28:05", "throughput": 787.71, "total_tokens": 6031768} {"current_steps": 18520, "total_steps": 40000, "loss": 0.2379, "lr": 2.7901383856744157e-05, "epoch": 15.155546459271388, "percentage": 46.3, "elapsed_time": "2:07:39", "remaining_time": "2:28:03", "throughput": 787.74, "total_tokens": 6033368} {"current_steps": 18525, "total_steps": 40000, "loss": 0.1778, "lr": 2.7891632495412217e-05, "epoch": 15.15963978714695, "percentage": 46.31, "elapsed_time": "2:07:40", "remaining_time": "2:28:00", "throughput": 787.77, "total_tokens": 6034952} {"current_steps": 18530, "total_steps": 40000, "loss": 0.1624, "lr": 2.7881880688154205e-05, "epoch": 15.163733115022513, "percentage": 46.33, "elapsed_time": "2:07:42", "remaining_time": "2:27:58", "throughput": 787.81, "total_tokens": 6036568} {"current_steps": 18535, "total_steps": 40000, "loss": 0.1416, "lr": 2.7872128436473977e-05, "epoch": 15.167826442898075, "percentage": 46.34, "elapsed_time": "2:07:44", "remaining_time": "2:27:55", "throughput": 787.85, "total_tokens": 6038280} {"current_steps": 18540, "total_steps": 40000, "loss": 0.2009, "lr": 2.7862375741875448e-05, "epoch": 15.17191977077364, "percentage": 46.35, "elapsed_time": "2:07:45", "remaining_time": "2:27:53", "throughput": 787.9, "total_tokens": 6039976} {"current_steps": 18545, "total_steps": 40000, "loss": 0.1818, "lr": 2.785262260586261e-05, "epoch": 15.176013098649202, "percentage": 46.36, "elapsed_time": "2:07:47", "remaining_time": "2:27:50", "throughput": 787.93, "total_tokens": 6041560} {"current_steps": 18550, "total_steps": 40000, "loss": 0.1346, "lr": 2.7842869029939517e-05, "epoch": 15.180106426524764, "percentage": 46.38, "elapsed_time": "2:07:49", "remaining_time": "2:27:48", "throughput": 787.97, "total_tokens": 6043224} {"current_steps": 18555, "total_steps": 40000, "loss": 0.2211, "lr": 2.7833115015610296e-05, "epoch": 15.184199754400327, "percentage": 46.39, "elapsed_time": "2:07:51", "remaining_time": "2:27:45", "throughput": 788.0, "total_tokens": 6044840} {"current_steps": 18560, "total_steps": 40000, "loss": 0.1576, "lr": 2.7823360564379136e-05, "epoch": 15.18829308227589, "percentage": 46.4, "elapsed_time": "2:07:52", "remaining_time": "2:27:43", "throughput": 788.04, "total_tokens": 6046536} {"current_steps": 18565, "total_steps": 40000, "loss": 0.1705, "lr": 2.7813605677750297e-05, "epoch": 15.192386410151453, "percentage": 46.41, "elapsed_time": "2:07:54", "remaining_time": "2:27:40", "throughput": 788.08, "total_tokens": 6048168} {"current_steps": 18570, "total_steps": 40000, "loss": 0.2405, "lr": 2.7803850357228102e-05, "epoch": 15.196479738027016, "percentage": 46.42, "elapsed_time": "2:07:56", "remaining_time": "2:27:38", "throughput": 788.11, "total_tokens": 6049736} {"current_steps": 18575, "total_steps": 40000, "loss": 0.1597, "lr": 2.779409460431695e-05, "epoch": 15.200573065902578, "percentage": 46.44, "elapsed_time": "2:07:57", "remaining_time": "2:27:36", "throughput": 788.14, "total_tokens": 6051320} {"current_steps": 18580, "total_steps": 40000, "loss": 0.166, "lr": 2.778433842052129e-05, "epoch": 15.204666393778142, "percentage": 46.45, "elapsed_time": "2:07:59", "remaining_time": "2:27:33", "throughput": 788.18, "total_tokens": 6052984} {"current_steps": 18585, "total_steps": 40000, "loss": 0.1322, "lr": 2.7774581807345664e-05, "epoch": 15.208759721653704, "percentage": 46.46, "elapsed_time": "2:08:01", "remaining_time": "2:27:31", "throughput": 788.21, "total_tokens": 6054616} {"current_steps": 18590, "total_steps": 40000, "loss": 0.2303, "lr": 2.776482476629465e-05, "epoch": 15.212853049529267, "percentage": 46.48, "elapsed_time": "2:08:03", "remaining_time": "2:27:28", "throughput": 788.25, "total_tokens": 6056280} {"current_steps": 18595, "total_steps": 40000, "loss": 0.1675, "lr": 2.7755067298872924e-05, "epoch": 15.216946377404831, "percentage": 46.49, "elapsed_time": "2:08:04", "remaining_time": "2:27:26", "throughput": 788.28, "total_tokens": 6057816} {"current_steps": 18600, "total_steps": 40000, "loss": 0.1911, "lr": 2.774530940658518e-05, "epoch": 15.221039705280393, "percentage": 46.5, "elapsed_time": "2:08:06", "remaining_time": "2:27:23", "throughput": 788.32, "total_tokens": 6059464} {"current_steps": 18600, "total_steps": 40000, "eval_loss": 0.21152842044830322, "epoch": 15.221039705280393, "percentage": 46.5, "elapsed_time": "2:08:19", "remaining_time": "2:27:38", "throughput": 787.04, "total_tokens": 6059464} {"current_steps": 18605, "total_steps": 40000, "loss": 0.146, "lr": 2.7735551090936236e-05, "epoch": 15.225133033155956, "percentage": 46.51, "elapsed_time": "2:08:22", "remaining_time": "2:27:37", "throughput": 786.87, "total_tokens": 6061160} {"current_steps": 18610, "total_steps": 40000, "loss": 0.2027, "lr": 2.7725792353430934e-05, "epoch": 15.229226361031518, "percentage": 46.52, "elapsed_time": "2:08:24", "remaining_time": "2:27:35", "throughput": 786.92, "total_tokens": 6062840} {"current_steps": 18615, "total_steps": 40000, "loss": 0.1603, "lr": 2.77160331955742e-05, "epoch": 15.233319688907082, "percentage": 46.54, "elapsed_time": "2:08:26", "remaining_time": "2:27:33", "throughput": 786.97, "total_tokens": 6064584} {"current_steps": 18620, "total_steps": 40000, "loss": 0.1506, "lr": 2.7706273618871008e-05, "epoch": 15.237413016782645, "percentage": 46.55, "elapsed_time": "2:08:27", "remaining_time": "2:27:30", "throughput": 787.0, "total_tokens": 6066200} {"current_steps": 18625, "total_steps": 40000, "loss": 0.1199, "lr": 2.769651362482642e-05, "epoch": 15.241506344658207, "percentage": 46.56, "elapsed_time": "2:08:29", "remaining_time": "2:27:28", "throughput": 787.04, "total_tokens": 6067848} {"current_steps": 18630, "total_steps": 40000, "loss": 0.1738, "lr": 2.768675321494555e-05, "epoch": 15.24559967253377, "percentage": 46.58, "elapsed_time": "2:08:31", "remaining_time": "2:27:25", "throughput": 787.07, "total_tokens": 6069432} {"current_steps": 18635, "total_steps": 40000, "loss": 0.1946, "lr": 2.7676992390733565e-05, "epoch": 15.249693000409334, "percentage": 46.59, "elapsed_time": "2:08:33", "remaining_time": "2:27:23", "throughput": 787.11, "total_tokens": 6071080} {"current_steps": 18640, "total_steps": 40000, "loss": 0.2486, "lr": 2.766723115369571e-05, "epoch": 15.253786328284896, "percentage": 46.6, "elapsed_time": "2:08:34", "remaining_time": "2:27:20", "throughput": 787.15, "total_tokens": 6072776} {"current_steps": 18645, "total_steps": 40000, "loss": 0.158, "lr": 2.765746950533729e-05, "epoch": 15.257879656160458, "percentage": 46.61, "elapsed_time": "2:08:36", "remaining_time": "2:27:18", "throughput": 787.19, "total_tokens": 6074408} {"current_steps": 18650, "total_steps": 40000, "loss": 0.1802, "lr": 2.7647707447163684e-05, "epoch": 15.26197298403602, "percentage": 46.62, "elapsed_time": "2:08:38", "remaining_time": "2:27:15", "throughput": 787.23, "total_tokens": 6076056} {"current_steps": 18655, "total_steps": 40000, "loss": 0.1907, "lr": 2.7637944980680315e-05, "epoch": 15.266066311911585, "percentage": 46.64, "elapsed_time": "2:08:40", "remaining_time": "2:27:13", "throughput": 787.27, "total_tokens": 6077752} {"current_steps": 18660, "total_steps": 40000, "loss": 0.2095, "lr": 2.762818210739268e-05, "epoch": 15.270159639787147, "percentage": 46.65, "elapsed_time": "2:08:41", "remaining_time": "2:27:10", "throughput": 787.3, "total_tokens": 6079368} {"current_steps": 18665, "total_steps": 40000, "loss": 0.2045, "lr": 2.7618418828806332e-05, "epoch": 15.27425296766271, "percentage": 46.66, "elapsed_time": "2:08:43", "remaining_time": "2:27:08", "throughput": 787.33, "total_tokens": 6080904} {"current_steps": 18670, "total_steps": 40000, "loss": 0.1943, "lr": 2.76086551464269e-05, "epoch": 15.278346295538272, "percentage": 46.67, "elapsed_time": "2:08:45", "remaining_time": "2:27:05", "throughput": 787.36, "total_tokens": 6082504} {"current_steps": 18675, "total_steps": 40000, "loss": 0.2313, "lr": 2.759889106176006e-05, "epoch": 15.282439623413836, "percentage": 46.69, "elapsed_time": "2:08:46", "remaining_time": "2:27:03", "throughput": 787.4, "total_tokens": 6084168} {"current_steps": 18680, "total_steps": 40000, "loss": 0.183, "lr": 2.758912657631156e-05, "epoch": 15.286532951289399, "percentage": 46.7, "elapsed_time": "2:08:48", "remaining_time": "2:27:00", "throughput": 787.44, "total_tokens": 6085832} {"current_steps": 18685, "total_steps": 40000, "loss": 0.1667, "lr": 2.7579361691587198e-05, "epoch": 15.290626279164961, "percentage": 46.71, "elapsed_time": "2:08:50", "remaining_time": "2:26:58", "throughput": 787.47, "total_tokens": 6087432} {"current_steps": 18690, "total_steps": 40000, "loss": 0.2253, "lr": 2.756959640909285e-05, "epoch": 15.294719607040523, "percentage": 46.73, "elapsed_time": "2:08:52", "remaining_time": "2:26:55", "throughput": 787.5, "total_tokens": 6089048} {"current_steps": 18695, "total_steps": 40000, "loss": 0.2261, "lr": 2.7559830730334452e-05, "epoch": 15.298812934916088, "percentage": 46.74, "elapsed_time": "2:08:53", "remaining_time": "2:26:53", "throughput": 787.55, "total_tokens": 6090728} {"current_steps": 18700, "total_steps": 40000, "loss": 0.1597, "lr": 2.7550064656817988e-05, "epoch": 15.30290626279165, "percentage": 46.75, "elapsed_time": "2:08:55", "remaining_time": "2:26:51", "throughput": 787.58, "total_tokens": 6092360} {"current_steps": 18705, "total_steps": 40000, "loss": 0.1909, "lr": 2.7540298190049503e-05, "epoch": 15.306999590667212, "percentage": 46.76, "elapsed_time": "2:08:57", "remaining_time": "2:26:48", "throughput": 787.62, "total_tokens": 6093992} {"current_steps": 18710, "total_steps": 40000, "loss": 0.1659, "lr": 2.7530531331535107e-05, "epoch": 15.311092918542775, "percentage": 46.77, "elapsed_time": "2:08:58", "remaining_time": "2:26:46", "throughput": 787.65, "total_tokens": 6095608} {"current_steps": 18715, "total_steps": 40000, "loss": 0.1471, "lr": 2.752076408278099e-05, "epoch": 15.315186246418339, "percentage": 46.79, "elapsed_time": "2:09:00", "remaining_time": "2:26:43", "throughput": 787.68, "total_tokens": 6097208} {"current_steps": 18720, "total_steps": 40000, "loss": 0.2211, "lr": 2.751099644529337e-05, "epoch": 15.319279574293901, "percentage": 46.8, "elapsed_time": "2:09:02", "remaining_time": "2:26:41", "throughput": 787.73, "total_tokens": 6098936} {"current_steps": 18725, "total_steps": 40000, "loss": 0.2004, "lr": 2.7501228420578533e-05, "epoch": 15.323372902169464, "percentage": 46.81, "elapsed_time": "2:09:04", "remaining_time": "2:26:38", "throughput": 787.77, "total_tokens": 6100568} {"current_steps": 18730, "total_steps": 40000, "loss": 0.143, "lr": 2.7491460010142857e-05, "epoch": 15.327466230045026, "percentage": 46.83, "elapsed_time": "2:09:05", "remaining_time": "2:26:36", "throughput": 787.81, "total_tokens": 6102264} {"current_steps": 18735, "total_steps": 40000, "loss": 0.1914, "lr": 2.7481691215492727e-05, "epoch": 15.33155955792059, "percentage": 46.84, "elapsed_time": "2:09:07", "remaining_time": "2:26:33", "throughput": 787.86, "total_tokens": 6104008} {"current_steps": 18740, "total_steps": 40000, "loss": 0.1856, "lr": 2.747192203813463e-05, "epoch": 15.335652885796152, "percentage": 46.85, "elapsed_time": "2:09:09", "remaining_time": "2:26:31", "throughput": 787.9, "total_tokens": 6105656} {"current_steps": 18745, "total_steps": 40000, "loss": 0.1939, "lr": 2.7462152479575087e-05, "epoch": 15.339746213671715, "percentage": 46.86, "elapsed_time": "2:09:10", "remaining_time": "2:26:28", "throughput": 787.94, "total_tokens": 6107320} {"current_steps": 18750, "total_steps": 40000, "loss": 0.1412, "lr": 2.7452382541320697e-05, "epoch": 15.343839541547277, "percentage": 46.88, "elapsed_time": "2:09:12", "remaining_time": "2:26:26", "throughput": 787.97, "total_tokens": 6108936} {"current_steps": 18755, "total_steps": 40000, "loss": 0.1569, "lr": 2.7442612224878096e-05, "epoch": 15.347932869422841, "percentage": 46.89, "elapsed_time": "2:09:14", "remaining_time": "2:26:23", "throughput": 788.01, "total_tokens": 6110568} {"current_steps": 18760, "total_steps": 40000, "loss": 0.2167, "lr": 2.7432841531753994e-05, "epoch": 15.352026197298404, "percentage": 46.9, "elapsed_time": "2:09:16", "remaining_time": "2:26:21", "throughput": 788.05, "total_tokens": 6112216} {"current_steps": 18765, "total_steps": 40000, "loss": 0.1503, "lr": 2.7423070463455147e-05, "epoch": 15.356119525173966, "percentage": 46.91, "elapsed_time": "2:09:17", "remaining_time": "2:26:19", "throughput": 788.09, "total_tokens": 6113864} {"current_steps": 18770, "total_steps": 40000, "loss": 0.1449, "lr": 2.7413299021488397e-05, "epoch": 15.360212853049529, "percentage": 46.92, "elapsed_time": "2:09:19", "remaining_time": "2:26:16", "throughput": 788.12, "total_tokens": 6115528} {"current_steps": 18775, "total_steps": 40000, "loss": 0.1387, "lr": 2.7403527207360615e-05, "epoch": 15.364306180925093, "percentage": 46.94, "elapsed_time": "2:09:21", "remaining_time": "2:26:14", "throughput": 788.17, "total_tokens": 6117224} {"current_steps": 18780, "total_steps": 40000, "loss": 0.1816, "lr": 2.7393755022578722e-05, "epoch": 15.368399508800655, "percentage": 46.95, "elapsed_time": "2:09:23", "remaining_time": "2:26:11", "throughput": 788.2, "total_tokens": 6118792} {"current_steps": 18785, "total_steps": 40000, "loss": 0.2395, "lr": 2.7383982468649714e-05, "epoch": 15.372492836676217, "percentage": 46.96, "elapsed_time": "2:09:24", "remaining_time": "2:26:09", "throughput": 788.23, "total_tokens": 6120392} {"current_steps": 18790, "total_steps": 40000, "loss": 0.2003, "lr": 2.7374209547080665e-05, "epoch": 15.37658616455178, "percentage": 46.98, "elapsed_time": "2:09:26", "remaining_time": "2:26:06", "throughput": 788.26, "total_tokens": 6121992} {"current_steps": 18795, "total_steps": 40000, "loss": 0.31, "lr": 2.7364436259378663e-05, "epoch": 15.380679492427344, "percentage": 46.99, "elapsed_time": "2:09:28", "remaining_time": "2:26:04", "throughput": 788.3, "total_tokens": 6123608} {"current_steps": 18800, "total_steps": 40000, "loss": 0.1756, "lr": 2.735466260705088e-05, "epoch": 15.384772820302906, "percentage": 47.0, "elapsed_time": "2:09:29", "remaining_time": "2:26:01", "throughput": 788.33, "total_tokens": 6125240} {"current_steps": 18800, "total_steps": 40000, "eval_loss": 0.20537984371185303, "epoch": 15.384772820302906, "percentage": 47.0, "elapsed_time": "2:09:42", "remaining_time": "2:26:15", "throughput": 787.07, "total_tokens": 6125240} {"current_steps": 18805, "total_steps": 40000, "loss": 0.1337, "lr": 2.7344888591604524e-05, "epoch": 15.388866148178469, "percentage": 47.01, "elapsed_time": "2:09:45", "remaining_time": "2:26:15", "throughput": 786.95, "total_tokens": 6126872} {"current_steps": 18810, "total_steps": 40000, "loss": 0.2768, "lr": 2.7335114214546893e-05, "epoch": 15.392959476054031, "percentage": 47.02, "elapsed_time": "2:09:47", "remaining_time": "2:26:12", "throughput": 787.0, "total_tokens": 6128648} {"current_steps": 18815, "total_steps": 40000, "loss": 0.2007, "lr": 2.7325339477385293e-05, "epoch": 15.397052803929595, "percentage": 47.04, "elapsed_time": "2:09:49", "remaining_time": "2:26:10", "throughput": 787.05, "total_tokens": 6130344} {"current_steps": 18820, "total_steps": 40000, "loss": 0.1003, "lr": 2.7315564381627128e-05, "epoch": 15.401146131805158, "percentage": 47.05, "elapsed_time": "2:09:50", "remaining_time": "2:26:07", "throughput": 787.08, "total_tokens": 6131944} {"current_steps": 18825, "total_steps": 40000, "loss": 0.1419, "lr": 2.7305788928779835e-05, "epoch": 15.40523945968072, "percentage": 47.06, "elapsed_time": "2:09:52", "remaining_time": "2:26:05", "throughput": 787.11, "total_tokens": 6133544} {"current_steps": 18830, "total_steps": 40000, "loss": 0.2145, "lr": 2.729601312035091e-05, "epoch": 15.409332787556282, "percentage": 47.08, "elapsed_time": "2:09:54", "remaining_time": "2:26:02", "throughput": 787.15, "total_tokens": 6135176} {"current_steps": 18835, "total_steps": 40000, "loss": 0.237, "lr": 2.7286236957847915e-05, "epoch": 15.413426115431847, "percentage": 47.09, "elapsed_time": "2:09:55", "remaining_time": "2:26:00", "throughput": 787.18, "total_tokens": 6136776} {"current_steps": 18840, "total_steps": 40000, "loss": 0.1516, "lr": 2.7276460442778446e-05, "epoch": 15.417519443307409, "percentage": 47.1, "elapsed_time": "2:09:57", "remaining_time": "2:25:57", "throughput": 787.22, "total_tokens": 6138440} {"current_steps": 18845, "total_steps": 40000, "loss": 0.1378, "lr": 2.726668357665017e-05, "epoch": 15.421612771182971, "percentage": 47.11, "elapsed_time": "2:09:59", "remaining_time": "2:25:55", "throughput": 787.24, "total_tokens": 6140008} {"current_steps": 18850, "total_steps": 40000, "loss": 0.1284, "lr": 2.7256906360970808e-05, "epoch": 15.425706099058534, "percentage": 47.12, "elapsed_time": "2:10:01", "remaining_time": "2:25:52", "throughput": 787.28, "total_tokens": 6141656} {"current_steps": 18855, "total_steps": 40000, "loss": 0.1751, "lr": 2.7247128797248117e-05, "epoch": 15.429799426934098, "percentage": 47.14, "elapsed_time": "2:10:02", "remaining_time": "2:25:50", "throughput": 787.31, "total_tokens": 6143256} {"current_steps": 18860, "total_steps": 40000, "loss": 0.2127, "lr": 2.7237350886989925e-05, "epoch": 15.43389275480966, "percentage": 47.15, "elapsed_time": "2:10:04", "remaining_time": "2:25:48", "throughput": 787.34, "total_tokens": 6144856} {"current_steps": 18865, "total_steps": 40000, "loss": 0.1642, "lr": 2.7227572631704107e-05, "epoch": 15.437986082685223, "percentage": 47.16, "elapsed_time": "2:10:06", "remaining_time": "2:25:45", "throughput": 787.38, "total_tokens": 6146472} {"current_steps": 18870, "total_steps": 40000, "loss": 0.223, "lr": 2.7217794032898596e-05, "epoch": 15.442079410560787, "percentage": 47.17, "elapsed_time": "2:10:07", "remaining_time": "2:25:43", "throughput": 787.41, "total_tokens": 6148040} {"current_steps": 18875, "total_steps": 40000, "loss": 0.1463, "lr": 2.7208015092081384e-05, "epoch": 15.44617273843635, "percentage": 47.19, "elapsed_time": "2:10:09", "remaining_time": "2:25:40", "throughput": 787.44, "total_tokens": 6149640} {"current_steps": 18880, "total_steps": 40000, "loss": 0.1945, "lr": 2.719823581076049e-05, "epoch": 15.450266066311912, "percentage": 47.2, "elapsed_time": "2:10:11", "remaining_time": "2:25:38", "throughput": 787.49, "total_tokens": 6151416} {"current_steps": 18885, "total_steps": 40000, "loss": 0.2783, "lr": 2.718845619044401e-05, "epoch": 15.454359394187474, "percentage": 47.21, "elapsed_time": "2:10:13", "remaining_time": "2:25:35", "throughput": 787.53, "total_tokens": 6153064} {"current_steps": 18890, "total_steps": 40000, "loss": 0.1459, "lr": 2.7178676232640088e-05, "epoch": 15.458452722063038, "percentage": 47.23, "elapsed_time": "2:10:14", "remaining_time": "2:25:33", "throughput": 787.57, "total_tokens": 6154712} {"current_steps": 18895, "total_steps": 40000, "loss": 0.2437, "lr": 2.716889593885691e-05, "epoch": 15.4625460499386, "percentage": 47.24, "elapsed_time": "2:10:16", "remaining_time": "2:25:30", "throughput": 787.6, "total_tokens": 6156344} {"current_steps": 18900, "total_steps": 40000, "loss": 0.1962, "lr": 2.7159115310602716e-05, "epoch": 15.466639377814163, "percentage": 47.25, "elapsed_time": "2:10:18", "remaining_time": "2:25:28", "throughput": 787.64, "total_tokens": 6157976} {"current_steps": 18905, "total_steps": 40000, "loss": 0.1286, "lr": 2.7149334349385814e-05, "epoch": 15.470732705689725, "percentage": 47.26, "elapsed_time": "2:10:20", "remaining_time": "2:25:25", "throughput": 787.67, "total_tokens": 6159560} {"current_steps": 18910, "total_steps": 40000, "loss": 0.2846, "lr": 2.713955305671454e-05, "epoch": 15.47482603356529, "percentage": 47.27, "elapsed_time": "2:10:21", "remaining_time": "2:25:23", "throughput": 787.7, "total_tokens": 6161208} {"current_steps": 18915, "total_steps": 40000, "loss": 0.1607, "lr": 2.71297714340973e-05, "epoch": 15.478919361440852, "percentage": 47.29, "elapsed_time": "2:10:23", "remaining_time": "2:25:20", "throughput": 787.74, "total_tokens": 6162840} {"current_steps": 18920, "total_steps": 40000, "loss": 0.1451, "lr": 2.7119989483042545e-05, "epoch": 15.483012689316414, "percentage": 47.3, "elapsed_time": "2:10:25", "remaining_time": "2:25:18", "throughput": 787.78, "total_tokens": 6164488} {"current_steps": 18925, "total_steps": 40000, "loss": 0.1966, "lr": 2.7110207205058768e-05, "epoch": 15.487106017191977, "percentage": 47.31, "elapsed_time": "2:10:26", "remaining_time": "2:25:16", "throughput": 787.81, "total_tokens": 6166136} {"current_steps": 18930, "total_steps": 40000, "loss": 0.1665, "lr": 2.7100424601654517e-05, "epoch": 15.49119934506754, "percentage": 47.33, "elapsed_time": "2:10:28", "remaining_time": "2:25:13", "throughput": 787.85, "total_tokens": 6167768} {"current_steps": 18935, "total_steps": 40000, "loss": 0.1265, "lr": 2.7090641674338403e-05, "epoch": 15.495292672943103, "percentage": 47.34, "elapsed_time": "2:10:30", "remaining_time": "2:25:11", "throughput": 787.88, "total_tokens": 6169368} {"current_steps": 18940, "total_steps": 40000, "loss": 0.1319, "lr": 2.7080858424619072e-05, "epoch": 15.499386000818665, "percentage": 47.35, "elapsed_time": "2:10:32", "remaining_time": "2:25:08", "throughput": 787.91, "total_tokens": 6170984} {"current_steps": 18945, "total_steps": 40000, "loss": 0.1076, "lr": 2.707107485400521e-05, "epoch": 15.503479328694228, "percentage": 47.36, "elapsed_time": "2:10:33", "remaining_time": "2:25:06", "throughput": 787.94, "total_tokens": 6172552} {"current_steps": 18950, "total_steps": 40000, "loss": 0.1344, "lr": 2.7061290964005586e-05, "epoch": 15.507572656569792, "percentage": 47.38, "elapsed_time": "2:10:35", "remaining_time": "2:25:03", "throughput": 787.97, "total_tokens": 6174152} {"current_steps": 18955, "total_steps": 40000, "loss": 0.2093, "lr": 2.7051506756129e-05, "epoch": 15.511665984445354, "percentage": 47.39, "elapsed_time": "2:10:37", "remaining_time": "2:25:01", "throughput": 788.01, "total_tokens": 6175832} {"current_steps": 18960, "total_steps": 40000, "loss": 0.1957, "lr": 2.704172223188428e-05, "epoch": 15.515759312320917, "percentage": 47.4, "elapsed_time": "2:10:38", "remaining_time": "2:24:58", "throughput": 788.06, "total_tokens": 6177512} {"current_steps": 18965, "total_steps": 40000, "loss": 0.0938, "lr": 2.7031937392780334e-05, "epoch": 15.51985264019648, "percentage": 47.41, "elapsed_time": "2:10:40", "remaining_time": "2:24:56", "throughput": 788.09, "total_tokens": 6179112} {"current_steps": 18970, "total_steps": 40000, "loss": 0.1196, "lr": 2.702215224032611e-05, "epoch": 15.523945968072043, "percentage": 47.42, "elapsed_time": "2:10:42", "remaining_time": "2:24:53", "throughput": 788.12, "total_tokens": 6180728} {"current_steps": 18975, "total_steps": 40000, "loss": 0.279, "lr": 2.70123667760306e-05, "epoch": 15.528039295947606, "percentage": 47.44, "elapsed_time": "2:10:44", "remaining_time": "2:24:51", "throughput": 788.16, "total_tokens": 6182424} {"current_steps": 18980, "total_steps": 40000, "loss": 0.1312, "lr": 2.7002581001402845e-05, "epoch": 15.532132623823168, "percentage": 47.45, "elapsed_time": "2:10:45", "remaining_time": "2:24:49", "throughput": 788.21, "total_tokens": 6184152} {"current_steps": 18985, "total_steps": 40000, "loss": 0.1713, "lr": 2.6992794917951923e-05, "epoch": 15.53622595169873, "percentage": 47.46, "elapsed_time": "2:10:47", "remaining_time": "2:24:46", "throughput": 788.24, "total_tokens": 6185720} {"current_steps": 18990, "total_steps": 40000, "loss": 0.1406, "lr": 2.6983008527187e-05, "epoch": 15.540319279574295, "percentage": 47.48, "elapsed_time": "2:10:49", "remaining_time": "2:24:44", "throughput": 788.27, "total_tokens": 6187320} {"current_steps": 18995, "total_steps": 40000, "loss": 0.1934, "lr": 2.697322183061723e-05, "epoch": 15.544412607449857, "percentage": 47.49, "elapsed_time": "2:10:50", "remaining_time": "2:24:41", "throughput": 788.3, "total_tokens": 6188936} {"current_steps": 19000, "total_steps": 40000, "loss": 0.1436, "lr": 2.696343482975186e-05, "epoch": 15.54850593532542, "percentage": 47.5, "elapsed_time": "2:10:52", "remaining_time": "2:24:39", "throughput": 788.34, "total_tokens": 6190600} {"current_steps": 19000, "total_steps": 40000, "eval_loss": 0.20481052994728088, "epoch": 15.54850593532542, "percentage": 47.5, "elapsed_time": "2:11:05", "remaining_time": "2:24:53", "throughput": 787.1, "total_tokens": 6190600} {"current_steps": 19005, "total_steps": 40000, "loss": 0.1495, "lr": 2.695364752610016e-05, "epoch": 15.552599263200982, "percentage": 47.51, "elapsed_time": "2:11:08", "remaining_time": "2:24:52", "throughput": 786.99, "total_tokens": 6192232} {"current_steps": 19010, "total_steps": 40000, "loss": 0.1964, "lr": 2.6943859921171467e-05, "epoch": 15.556692591076546, "percentage": 47.52, "elapsed_time": "2:11:10", "remaining_time": "2:24:49", "throughput": 787.01, "total_tokens": 6193768} {"current_steps": 19015, "total_steps": 40000, "loss": 0.2645, "lr": 2.6934072016475143e-05, "epoch": 15.560785918952108, "percentage": 47.54, "elapsed_time": "2:11:11", "remaining_time": "2:24:47", "throughput": 787.04, "total_tokens": 6195384} {"current_steps": 19020, "total_steps": 40000, "loss": 0.1444, "lr": 2.6924283813520606e-05, "epoch": 15.56487924682767, "percentage": 47.55, "elapsed_time": "2:11:13", "remaining_time": "2:24:44", "throughput": 787.08, "total_tokens": 6197016} {"current_steps": 19025, "total_steps": 40000, "loss": 0.2091, "lr": 2.691449531381733e-05, "epoch": 15.568972574703233, "percentage": 47.56, "elapsed_time": "2:11:15", "remaining_time": "2:24:42", "throughput": 787.11, "total_tokens": 6198600} {"current_steps": 19030, "total_steps": 40000, "loss": 0.292, "lr": 2.6904706518874816e-05, "epoch": 15.573065902578797, "percentage": 47.58, "elapsed_time": "2:11:16", "remaining_time": "2:24:39", "throughput": 787.14, "total_tokens": 6200248} {"current_steps": 19035, "total_steps": 40000, "loss": 0.1384, "lr": 2.6894917430202615e-05, "epoch": 15.57715923045436, "percentage": 47.59, "elapsed_time": "2:11:18", "remaining_time": "2:24:37", "throughput": 787.17, "total_tokens": 6201832} {"current_steps": 19040, "total_steps": 40000, "loss": 0.2012, "lr": 2.6885128049310343e-05, "epoch": 15.581252558329922, "percentage": 47.6, "elapsed_time": "2:11:20", "remaining_time": "2:24:34", "throughput": 787.2, "total_tokens": 6203416} {"current_steps": 19045, "total_steps": 40000, "loss": 0.137, "lr": 2.687533837770762e-05, "epoch": 15.585345886205484, "percentage": 47.61, "elapsed_time": "2:11:22", "remaining_time": "2:24:32", "throughput": 787.23, "total_tokens": 6205032} {"current_steps": 19050, "total_steps": 40000, "loss": 0.2151, "lr": 2.6865548416904162e-05, "epoch": 15.589439214081048, "percentage": 47.62, "elapsed_time": "2:11:23", "remaining_time": "2:24:30", "throughput": 787.27, "total_tokens": 6206632} {"current_steps": 19055, "total_steps": 40000, "loss": 0.2265, "lr": 2.68557581684097e-05, "epoch": 15.59353254195661, "percentage": 47.64, "elapsed_time": "2:11:25", "remaining_time": "2:24:27", "throughput": 787.3, "total_tokens": 6208280} {"current_steps": 19060, "total_steps": 40000, "loss": 0.1788, "lr": 2.6845967633733998e-05, "epoch": 15.597625869832173, "percentage": 47.65, "elapsed_time": "2:11:27", "remaining_time": "2:24:25", "throughput": 787.34, "total_tokens": 6209880} {"current_steps": 19065, "total_steps": 40000, "loss": 0.1792, "lr": 2.683617681438689e-05, "epoch": 15.601719197707736, "percentage": 47.66, "elapsed_time": "2:11:28", "remaining_time": "2:24:22", "throughput": 787.37, "total_tokens": 6211496} {"current_steps": 19070, "total_steps": 40000, "loss": 0.2149, "lr": 2.682638571187825e-05, "epoch": 15.6058125255833, "percentage": 47.67, "elapsed_time": "2:11:30", "remaining_time": "2:24:20", "throughput": 787.41, "total_tokens": 6213144} {"current_steps": 19075, "total_steps": 40000, "loss": 0.1756, "lr": 2.6816594327717976e-05, "epoch": 15.609905853458862, "percentage": 47.69, "elapsed_time": "2:11:32", "remaining_time": "2:24:17", "throughput": 787.44, "total_tokens": 6214776} {"current_steps": 19080, "total_steps": 40000, "loss": 0.1764, "lr": 2.680680266341603e-05, "epoch": 15.613999181334425, "percentage": 47.7, "elapsed_time": "2:11:34", "remaining_time": "2:24:15", "throughput": 787.47, "total_tokens": 6216392} {"current_steps": 19085, "total_steps": 40000, "loss": 0.1227, "lr": 2.67970107204824e-05, "epoch": 15.618092509209987, "percentage": 47.71, "elapsed_time": "2:11:35", "remaining_time": "2:24:12", "throughput": 787.51, "total_tokens": 6218008} {"current_steps": 19090, "total_steps": 40000, "loss": 0.254, "lr": 2.6787218500427142e-05, "epoch": 15.622185837085551, "percentage": 47.73, "elapsed_time": "2:11:37", "remaining_time": "2:24:10", "throughput": 787.54, "total_tokens": 6219576} {"current_steps": 19095, "total_steps": 40000, "loss": 0.2059, "lr": 2.6777426004760332e-05, "epoch": 15.626279164961113, "percentage": 47.74, "elapsed_time": "2:11:39", "remaining_time": "2:24:08", "throughput": 787.56, "total_tokens": 6221144} {"current_steps": 19100, "total_steps": 40000, "loss": 0.1915, "lr": 2.6767633234992094e-05, "epoch": 15.630372492836676, "percentage": 47.75, "elapsed_time": "2:11:40", "remaining_time": "2:24:05", "throughput": 787.6, "total_tokens": 6222760} {"current_steps": 19105, "total_steps": 40000, "loss": 0.1791, "lr": 2.6757840192632598e-05, "epoch": 15.634465820712238, "percentage": 47.76, "elapsed_time": "2:11:42", "remaining_time": "2:24:03", "throughput": 787.63, "total_tokens": 6224376} {"current_steps": 19110, "total_steps": 40000, "loss": 0.2113, "lr": 2.6748046879192052e-05, "epoch": 15.638559148587802, "percentage": 47.77, "elapsed_time": "2:11:44", "remaining_time": "2:24:00", "throughput": 787.65, "total_tokens": 6225928} {"current_steps": 19115, "total_steps": 40000, "loss": 0.2084, "lr": 2.673825329618071e-05, "epoch": 15.642652476463365, "percentage": 47.79, "elapsed_time": "2:11:46", "remaining_time": "2:23:58", "throughput": 787.69, "total_tokens": 6227560} {"current_steps": 19120, "total_steps": 40000, "loss": 0.1977, "lr": 2.6728459445108866e-05, "epoch": 15.646745804338927, "percentage": 47.8, "elapsed_time": "2:11:47", "remaining_time": "2:23:55", "throughput": 787.73, "total_tokens": 6229208} {"current_steps": 19125, "total_steps": 40000, "loss": 0.2108, "lr": 2.6718665327486854e-05, "epoch": 15.65083913221449, "percentage": 47.81, "elapsed_time": "2:11:49", "remaining_time": "2:23:53", "throughput": 787.76, "total_tokens": 6230824} {"current_steps": 19130, "total_steps": 40000, "loss": 0.1313, "lr": 2.6708870944825048e-05, "epoch": 15.654932460090054, "percentage": 47.83, "elapsed_time": "2:11:51", "remaining_time": "2:23:50", "throughput": 787.79, "total_tokens": 6232456} {"current_steps": 19135, "total_steps": 40000, "loss": 0.1068, "lr": 2.6699076298633874e-05, "epoch": 15.659025787965616, "percentage": 47.84, "elapsed_time": "2:11:52", "remaining_time": "2:23:48", "throughput": 787.82, "total_tokens": 6234040} {"current_steps": 19140, "total_steps": 40000, "loss": 0.2019, "lr": 2.6689281390423788e-05, "epoch": 15.663119115841178, "percentage": 47.85, "elapsed_time": "2:11:54", "remaining_time": "2:23:45", "throughput": 787.87, "total_tokens": 6235768} {"current_steps": 19145, "total_steps": 40000, "loss": 0.1458, "lr": 2.667948622170527e-05, "epoch": 15.667212443716743, "percentage": 47.86, "elapsed_time": "2:11:56", "remaining_time": "2:23:43", "throughput": 787.91, "total_tokens": 6237416} {"current_steps": 19150, "total_steps": 40000, "loss": 0.1831, "lr": 2.6669690793988873e-05, "epoch": 15.671305771592305, "percentage": 47.88, "elapsed_time": "2:11:58", "remaining_time": "2:23:41", "throughput": 787.95, "total_tokens": 6239064} {"current_steps": 19155, "total_steps": 40000, "loss": 0.1756, "lr": 2.665989510878518e-05, "epoch": 15.675399099467867, "percentage": 47.89, "elapsed_time": "2:11:59", "remaining_time": "2:23:38", "throughput": 787.98, "total_tokens": 6240696} {"current_steps": 19160, "total_steps": 40000, "loss": 0.2053, "lr": 2.6650099167604793e-05, "epoch": 15.67949242734343, "percentage": 47.9, "elapsed_time": "2:12:01", "remaining_time": "2:23:36", "throughput": 788.02, "total_tokens": 6242376} {"current_steps": 19165, "total_steps": 40000, "loss": 0.1178, "lr": 2.6640302971958376e-05, "epoch": 15.683585755218992, "percentage": 47.91, "elapsed_time": "2:12:03", "remaining_time": "2:23:33", "throughput": 788.05, "total_tokens": 6243928} {"current_steps": 19170, "total_steps": 40000, "loss": 0.1285, "lr": 2.6630506523356635e-05, "epoch": 15.687679083094556, "percentage": 47.93, "elapsed_time": "2:12:05", "remaining_time": "2:23:31", "throughput": 788.08, "total_tokens": 6245512} {"current_steps": 19175, "total_steps": 40000, "loss": 0.1906, "lr": 2.6620709823310297e-05, "epoch": 15.691772410970119, "percentage": 47.94, "elapsed_time": "2:12:06", "remaining_time": "2:23:28", "throughput": 788.11, "total_tokens": 6247144} {"current_steps": 19180, "total_steps": 40000, "loss": 0.1271, "lr": 2.661091287333014e-05, "epoch": 15.695865738845681, "percentage": 47.95, "elapsed_time": "2:12:08", "remaining_time": "2:23:26", "throughput": 788.14, "total_tokens": 6248712} {"current_steps": 19185, "total_steps": 40000, "loss": 0.1306, "lr": 2.660111567492696e-05, "epoch": 15.699959066721245, "percentage": 47.96, "elapsed_time": "2:12:10", "remaining_time": "2:23:23", "throughput": 788.16, "total_tokens": 6250264} {"current_steps": 19190, "total_steps": 40000, "loss": 0.1705, "lr": 2.6591318229611635e-05, "epoch": 15.704052394596808, "percentage": 47.98, "elapsed_time": "2:12:11", "remaining_time": "2:23:21", "throughput": 788.19, "total_tokens": 6251864} {"current_steps": 19195, "total_steps": 40000, "loss": 0.2497, "lr": 2.6581520538895037e-05, "epoch": 15.70814572247237, "percentage": 47.99, "elapsed_time": "2:12:13", "remaining_time": "2:23:19", "throughput": 788.23, "total_tokens": 6253544} {"current_steps": 19200, "total_steps": 40000, "loss": 0.1537, "lr": 2.6571722604288102e-05, "epoch": 15.712239050347932, "percentage": 48.0, "elapsed_time": "2:12:15", "remaining_time": "2:23:16", "throughput": 788.28, "total_tokens": 6255240} {"current_steps": 19200, "total_steps": 40000, "eval_loss": 0.2067692130804062, "epoch": 15.712239050347932, "percentage": 48.0, "elapsed_time": "2:12:27", "remaining_time": "2:23:30", "throughput": 787.04, "total_tokens": 6255240} {"current_steps": 19205, "total_steps": 40000, "loss": 0.1468, "lr": 2.656192442730179e-05, "epoch": 15.716332378223496, "percentage": 48.01, "elapsed_time": "2:12:30", "remaining_time": "2:23:29", "throughput": 786.94, "total_tokens": 6256968} {"current_steps": 19210, "total_steps": 40000, "loss": 0.2551, "lr": 2.6552126009447098e-05, "epoch": 15.720425706099059, "percentage": 48.02, "elapsed_time": "2:12:32", "remaining_time": "2:23:26", "throughput": 786.98, "total_tokens": 6258616} {"current_steps": 19215, "total_steps": 40000, "loss": 0.2927, "lr": 2.654232735223507e-05, "epoch": 15.724519033974621, "percentage": 48.04, "elapsed_time": "2:12:34", "remaining_time": "2:23:24", "throughput": 787.02, "total_tokens": 6260264} {"current_steps": 19220, "total_steps": 40000, "loss": 0.1775, "lr": 2.6532528457176787e-05, "epoch": 15.728612361850184, "percentage": 48.05, "elapsed_time": "2:12:36", "remaining_time": "2:23:21", "throughput": 787.05, "total_tokens": 6261912} {"current_steps": 19225, "total_steps": 40000, "loss": 0.1301, "lr": 2.6522729325783348e-05, "epoch": 15.732705689725748, "percentage": 48.06, "elapsed_time": "2:12:37", "remaining_time": "2:23:19", "throughput": 787.09, "total_tokens": 6263560} {"current_steps": 19230, "total_steps": 40000, "loss": 0.2209, "lr": 2.6512929959565914e-05, "epoch": 15.73679901760131, "percentage": 48.08, "elapsed_time": "2:12:39", "remaining_time": "2:23:17", "throughput": 787.12, "total_tokens": 6265160} {"current_steps": 19235, "total_steps": 40000, "loss": 0.2021, "lr": 2.6503130360035673e-05, "epoch": 15.740892345476873, "percentage": 48.09, "elapsed_time": "2:12:41", "remaining_time": "2:23:14", "throughput": 787.15, "total_tokens": 6266744} {"current_steps": 19240, "total_steps": 40000, "loss": 0.1882, "lr": 2.6493330528703835e-05, "epoch": 15.744985673352435, "percentage": 48.1, "elapsed_time": "2:12:43", "remaining_time": "2:23:12", "throughput": 787.18, "total_tokens": 6268344} {"current_steps": 19245, "total_steps": 40000, "loss": 0.1692, "lr": 2.648353046708167e-05, "epoch": 15.749079001227999, "percentage": 48.11, "elapsed_time": "2:12:44", "remaining_time": "2:23:09", "throughput": 787.21, "total_tokens": 6269944} {"current_steps": 19250, "total_steps": 40000, "loss": 0.1768, "lr": 2.647373017668046e-05, "epoch": 15.753172329103561, "percentage": 48.12, "elapsed_time": "2:12:46", "remaining_time": "2:23:07", "throughput": 787.25, "total_tokens": 6271576} {"current_steps": 19255, "total_steps": 40000, "loss": 0.1803, "lr": 2.6463929659011537e-05, "epoch": 15.757265656979124, "percentage": 48.14, "elapsed_time": "2:12:48", "remaining_time": "2:23:04", "throughput": 787.28, "total_tokens": 6273208} {"current_steps": 19260, "total_steps": 40000, "loss": 0.1457, "lr": 2.6454128915586262e-05, "epoch": 15.761358984854686, "percentage": 48.15, "elapsed_time": "2:12:49", "remaining_time": "2:23:02", "throughput": 787.31, "total_tokens": 6274792} {"current_steps": 19265, "total_steps": 40000, "loss": 0.1502, "lr": 2.6444327947916036e-05, "epoch": 15.76545231273025, "percentage": 48.16, "elapsed_time": "2:12:51", "remaining_time": "2:22:59", "throughput": 787.34, "total_tokens": 6276392} {"current_steps": 19270, "total_steps": 40000, "loss": 0.1556, "lr": 2.6434526757512292e-05, "epoch": 15.769545640605813, "percentage": 48.18, "elapsed_time": "2:12:53", "remaining_time": "2:22:57", "throughput": 787.38, "total_tokens": 6278056} {"current_steps": 19275, "total_steps": 40000, "loss": 0.1431, "lr": 2.6424725345886486e-05, "epoch": 15.773638968481375, "percentage": 48.19, "elapsed_time": "2:12:55", "remaining_time": "2:22:54", "throughput": 787.42, "total_tokens": 6279672} {"current_steps": 19280, "total_steps": 40000, "loss": 0.1959, "lr": 2.641492371455014e-05, "epoch": 15.777732296356938, "percentage": 48.2, "elapsed_time": "2:12:56", "remaining_time": "2:22:52", "throughput": 787.45, "total_tokens": 6281304} {"current_steps": 19285, "total_steps": 40000, "loss": 0.2178, "lr": 2.640512186501477e-05, "epoch": 15.781825624232502, "percentage": 48.21, "elapsed_time": "2:12:58", "remaining_time": "2:22:50", "throughput": 787.48, "total_tokens": 6282872} {"current_steps": 19290, "total_steps": 40000, "loss": 0.1607, "lr": 2.639531979879195e-05, "epoch": 15.785918952108064, "percentage": 48.23, "elapsed_time": "2:13:00", "remaining_time": "2:22:47", "throughput": 787.51, "total_tokens": 6284456} {"current_steps": 19295, "total_steps": 40000, "loss": 0.1081, "lr": 2.638551751739328e-05, "epoch": 15.790012279983626, "percentage": 48.24, "elapsed_time": "2:13:01", "remaining_time": "2:22:45", "throughput": 787.55, "total_tokens": 6286136} {"current_steps": 19300, "total_steps": 40000, "loss": 0.1594, "lr": 2.6375715022330404e-05, "epoch": 15.794105607859189, "percentage": 48.25, "elapsed_time": "2:13:03", "remaining_time": "2:22:42", "throughput": 787.58, "total_tokens": 6287704} {"current_steps": 19305, "total_steps": 40000, "loss": 0.1671, "lr": 2.6365912315114976e-05, "epoch": 15.798198935734753, "percentage": 48.26, "elapsed_time": "2:13:05", "remaining_time": "2:22:40", "throughput": 787.61, "total_tokens": 6289336} {"current_steps": 19310, "total_steps": 40000, "loss": 0.178, "lr": 2.6356109397258704e-05, "epoch": 15.802292263610315, "percentage": 48.27, "elapsed_time": "2:13:07", "remaining_time": "2:22:37", "throughput": 787.65, "total_tokens": 6291016} {"current_steps": 19315, "total_steps": 40000, "loss": 0.2168, "lr": 2.6346306270273325e-05, "epoch": 15.806385591485878, "percentage": 48.29, "elapsed_time": "2:13:08", "remaining_time": "2:22:35", "throughput": 787.69, "total_tokens": 6292696} {"current_steps": 19320, "total_steps": 40000, "loss": 0.1337, "lr": 2.6336502935670608e-05, "epoch": 15.81047891936144, "percentage": 48.3, "elapsed_time": "2:13:10", "remaining_time": "2:22:32", "throughput": 787.73, "total_tokens": 6294312} {"current_steps": 19325, "total_steps": 40000, "loss": 0.1225, "lr": 2.6326699394962333e-05, "epoch": 15.814572247237004, "percentage": 48.31, "elapsed_time": "2:13:12", "remaining_time": "2:22:30", "throughput": 787.76, "total_tokens": 6295896} {"current_steps": 19330, "total_steps": 40000, "loss": 0.2005, "lr": 2.6316895649660334e-05, "epoch": 15.818665575112567, "percentage": 48.33, "elapsed_time": "2:13:13", "remaining_time": "2:22:28", "throughput": 787.8, "total_tokens": 6297560} {"current_steps": 19335, "total_steps": 40000, "loss": 0.2315, "lr": 2.6307091701276486e-05, "epoch": 15.822758902988129, "percentage": 48.34, "elapsed_time": "2:13:15", "remaining_time": "2:22:25", "throughput": 787.83, "total_tokens": 6299176} {"current_steps": 19340, "total_steps": 40000, "loss": 0.2112, "lr": 2.629728755132267e-05, "epoch": 15.826852230863691, "percentage": 48.35, "elapsed_time": "2:13:17", "remaining_time": "2:22:23", "throughput": 787.86, "total_tokens": 6300792} {"current_steps": 19345, "total_steps": 40000, "loss": 0.2284, "lr": 2.628748320131081e-05, "epoch": 15.830945558739256, "percentage": 48.36, "elapsed_time": "2:13:19", "remaining_time": "2:22:20", "throughput": 787.9, "total_tokens": 6302456} {"current_steps": 19350, "total_steps": 40000, "loss": 0.1288, "lr": 2.6277678652752856e-05, "epoch": 15.835038886614818, "percentage": 48.38, "elapsed_time": "2:13:20", "remaining_time": "2:22:18", "throughput": 787.93, "total_tokens": 6304088} {"current_steps": 19355, "total_steps": 40000, "loss": 0.1828, "lr": 2.6267873907160807e-05, "epoch": 15.83913221449038, "percentage": 48.39, "elapsed_time": "2:13:22", "remaining_time": "2:22:15", "throughput": 787.97, "total_tokens": 6305720} {"current_steps": 19360, "total_steps": 40000, "loss": 0.1878, "lr": 2.6258068966046668e-05, "epoch": 15.843225542365943, "percentage": 48.4, "elapsed_time": "2:13:24", "remaining_time": "2:22:13", "throughput": 788.01, "total_tokens": 6307368} {"current_steps": 19365, "total_steps": 40000, "loss": 0.1543, "lr": 2.6248263830922475e-05, "epoch": 15.847318870241507, "percentage": 48.41, "elapsed_time": "2:13:25", "remaining_time": "2:22:10", "throughput": 788.03, "total_tokens": 6308936} {"current_steps": 19370, "total_steps": 40000, "loss": 0.1496, "lr": 2.6238458503300318e-05, "epoch": 15.85141219811707, "percentage": 48.43, "elapsed_time": "2:13:27", "remaining_time": "2:22:08", "throughput": 788.07, "total_tokens": 6310552} {"current_steps": 19375, "total_steps": 40000, "loss": 0.1623, "lr": 2.6228652984692292e-05, "epoch": 15.855505525992632, "percentage": 48.44, "elapsed_time": "2:13:29", "remaining_time": "2:22:06", "throughput": 788.1, "total_tokens": 6312184} {"current_steps": 19380, "total_steps": 40000, "loss": 0.1843, "lr": 2.621884727661054e-05, "epoch": 15.859598853868194, "percentage": 48.45, "elapsed_time": "2:13:31", "remaining_time": "2:22:03", "throughput": 788.13, "total_tokens": 6313800} {"current_steps": 19385, "total_steps": 40000, "loss": 0.2067, "lr": 2.6209041380567222e-05, "epoch": 15.863692181743758, "percentage": 48.46, "elapsed_time": "2:13:32", "remaining_time": "2:22:01", "throughput": 788.16, "total_tokens": 6315384} {"current_steps": 19390, "total_steps": 40000, "loss": 0.2059, "lr": 2.6199235298074527e-05, "epoch": 15.86778550961932, "percentage": 48.48, "elapsed_time": "2:13:34", "remaining_time": "2:21:58", "throughput": 788.2, "total_tokens": 6317016} {"current_steps": 19395, "total_steps": 40000, "loss": 0.1796, "lr": 2.618942903064468e-05, "epoch": 15.871878837494883, "percentage": 48.49, "elapsed_time": "2:13:36", "remaining_time": "2:21:56", "throughput": 788.24, "total_tokens": 6318680} {"current_steps": 19400, "total_steps": 40000, "loss": 0.2514, "lr": 2.6179622579789932e-05, "epoch": 15.875972165370445, "percentage": 48.5, "elapsed_time": "2:13:37", "remaining_time": "2:21:53", "throughput": 788.27, "total_tokens": 6320328} {"current_steps": 19400, "total_steps": 40000, "eval_loss": 0.2061070054769516, "epoch": 15.875972165370445, "percentage": 48.5, "elapsed_time": "2:13:50", "remaining_time": "2:22:07", "throughput": 787.05, "total_tokens": 6320328} {"current_steps": 19405, "total_steps": 40000, "loss": 0.1862, "lr": 2.6169815947022553e-05, "epoch": 15.88006549324601, "percentage": 48.51, "elapsed_time": "2:13:53", "remaining_time": "2:22:06", "throughput": 786.94, "total_tokens": 6321960} {"current_steps": 19410, "total_steps": 40000, "loss": 0.2122, "lr": 2.6160009133854853e-05, "epoch": 15.884158821121572, "percentage": 48.52, "elapsed_time": "2:13:55", "remaining_time": "2:22:03", "throughput": 786.98, "total_tokens": 6323608} {"current_steps": 19415, "total_steps": 40000, "loss": 0.2333, "lr": 2.6150202141799168e-05, "epoch": 15.888252148997134, "percentage": 48.54, "elapsed_time": "2:13:57", "remaining_time": "2:22:01", "throughput": 787.01, "total_tokens": 6325192} {"current_steps": 19420, "total_steps": 40000, "loss": 0.2683, "lr": 2.614039497236786e-05, "epoch": 15.892345476872698, "percentage": 48.55, "elapsed_time": "2:13:58", "remaining_time": "2:21:58", "throughput": 787.04, "total_tokens": 6326776} {"current_steps": 19425, "total_steps": 40000, "loss": 0.138, "lr": 2.6130587627073315e-05, "epoch": 15.89643880474826, "percentage": 48.56, "elapsed_time": "2:14:00", "remaining_time": "2:21:56", "throughput": 787.07, "total_tokens": 6328440} {"current_steps": 19430, "total_steps": 40000, "loss": 0.1755, "lr": 2.6120780107427956e-05, "epoch": 15.900532132623823, "percentage": 48.58, "elapsed_time": "2:14:02", "remaining_time": "2:21:54", "throughput": 787.11, "total_tokens": 6330072} {"current_steps": 19435, "total_steps": 40000, "loss": 0.1413, "lr": 2.6110972414944214e-05, "epoch": 15.904625460499386, "percentage": 48.59, "elapsed_time": "2:14:03", "remaining_time": "2:21:51", "throughput": 787.14, "total_tokens": 6331688} {"current_steps": 19440, "total_steps": 40000, "loss": 0.1266, "lr": 2.6101164551134565e-05, "epoch": 15.908718788374948, "percentage": 48.6, "elapsed_time": "2:14:05", "remaining_time": "2:21:49", "throughput": 787.18, "total_tokens": 6333336} {"current_steps": 19445, "total_steps": 40000, "loss": 0.1223, "lr": 2.6091356517511505e-05, "epoch": 15.912812116250512, "percentage": 48.61, "elapsed_time": "2:14:07", "remaining_time": "2:21:46", "throughput": 787.22, "total_tokens": 6335016} {"current_steps": 19450, "total_steps": 40000, "loss": 0.1854, "lr": 2.608154831558755e-05, "epoch": 15.916905444126074, "percentage": 48.62, "elapsed_time": "2:14:09", "remaining_time": "2:21:44", "throughput": 787.25, "total_tokens": 6336584} {"current_steps": 19455, "total_steps": 40000, "loss": 0.1971, "lr": 2.607173994687526e-05, "epoch": 15.920998772001637, "percentage": 48.64, "elapsed_time": "2:14:10", "remaining_time": "2:21:41", "throughput": 787.28, "total_tokens": 6338200} {"current_steps": 19460, "total_steps": 40000, "loss": 0.1489, "lr": 2.6061931412887196e-05, "epoch": 15.925092099877201, "percentage": 48.65, "elapsed_time": "2:14:12", "remaining_time": "2:21:39", "throughput": 787.31, "total_tokens": 6339816} {"current_steps": 19465, "total_steps": 40000, "loss": 0.1081, "lr": 2.6052122715135973e-05, "epoch": 15.929185427752763, "percentage": 48.66, "elapsed_time": "2:14:14", "remaining_time": "2:21:36", "throughput": 787.35, "total_tokens": 6341432} {"current_steps": 19470, "total_steps": 40000, "loss": 0.1691, "lr": 2.60423138551342e-05, "epoch": 15.933278755628326, "percentage": 48.68, "elapsed_time": "2:14:15", "remaining_time": "2:21:34", "throughput": 787.38, "total_tokens": 6343096} {"current_steps": 19475, "total_steps": 40000, "loss": 0.1488, "lr": 2.6032504834394527e-05, "epoch": 15.937372083503888, "percentage": 48.69, "elapsed_time": "2:14:17", "remaining_time": "2:21:32", "throughput": 787.41, "total_tokens": 6344696} {"current_steps": 19480, "total_steps": 40000, "loss": 0.2521, "lr": 2.602269565442964e-05, "epoch": 15.941465411379452, "percentage": 48.7, "elapsed_time": "2:14:19", "remaining_time": "2:21:29", "throughput": 787.45, "total_tokens": 6346296} {"current_steps": 19485, "total_steps": 40000, "loss": 0.1888, "lr": 2.6012886316752227e-05, "epoch": 15.945558739255015, "percentage": 48.71, "elapsed_time": "2:14:21", "remaining_time": "2:21:27", "throughput": 787.48, "total_tokens": 6347912} {"current_steps": 19490, "total_steps": 40000, "loss": 0.2457, "lr": 2.6003076822875018e-05, "epoch": 15.949652067130577, "percentage": 48.73, "elapsed_time": "2:14:22", "remaining_time": "2:21:24", "throughput": 787.51, "total_tokens": 6349528} {"current_steps": 19495, "total_steps": 40000, "loss": 0.1018, "lr": 2.5993267174310755e-05, "epoch": 15.95374539500614, "percentage": 48.74, "elapsed_time": "2:14:24", "remaining_time": "2:21:22", "throughput": 787.54, "total_tokens": 6351112} {"current_steps": 19500, "total_steps": 40000, "loss": 0.2034, "lr": 2.5983457372572218e-05, "epoch": 15.957838722881704, "percentage": 48.75, "elapsed_time": "2:14:26", "remaining_time": "2:21:19", "throughput": 787.57, "total_tokens": 6352728} {"current_steps": 19505, "total_steps": 40000, "loss": 0.1955, "lr": 2.597364741917219e-05, "epoch": 15.961932050757266, "percentage": 48.76, "elapsed_time": "2:14:27", "remaining_time": "2:21:17", "throughput": 787.61, "total_tokens": 6354408} {"current_steps": 19510, "total_steps": 40000, "loss": 0.1481, "lr": 2.5963837315623492e-05, "epoch": 15.966025378632828, "percentage": 48.77, "elapsed_time": "2:14:29", "remaining_time": "2:21:15", "throughput": 787.65, "total_tokens": 6356040} {"current_steps": 19515, "total_steps": 40000, "loss": 0.2925, "lr": 2.595402706343897e-05, "epoch": 15.97011870650839, "percentage": 48.79, "elapsed_time": "2:14:31", "remaining_time": "2:21:12", "throughput": 787.67, "total_tokens": 6357608} {"current_steps": 19520, "total_steps": 40000, "loss": 0.2073, "lr": 2.594421666413148e-05, "epoch": 15.974212034383955, "percentage": 48.8, "elapsed_time": "2:14:33", "remaining_time": "2:21:10", "throughput": 787.71, "total_tokens": 6359256} {"current_steps": 19525, "total_steps": 40000, "loss": 0.1117, "lr": 2.5934406119213928e-05, "epoch": 15.978305362259517, "percentage": 48.81, "elapsed_time": "2:14:34", "remaining_time": "2:21:07", "throughput": 787.75, "total_tokens": 6360920} {"current_steps": 19530, "total_steps": 40000, "loss": 0.1982, "lr": 2.5924595430199193e-05, "epoch": 15.98239869013508, "percentage": 48.83, "elapsed_time": "2:14:36", "remaining_time": "2:21:05", "throughput": 787.78, "total_tokens": 6362568} {"current_steps": 19535, "total_steps": 40000, "loss": 0.1396, "lr": 2.5914784598600238e-05, "epoch": 15.986492018010642, "percentage": 48.84, "elapsed_time": "2:14:38", "remaining_time": "2:21:02", "throughput": 787.82, "total_tokens": 6364232} {"current_steps": 19540, "total_steps": 40000, "loss": 0.1708, "lr": 2.5904973625930002e-05, "epoch": 15.990585345886206, "percentage": 48.85, "elapsed_time": "2:14:39", "remaining_time": "2:21:00", "throughput": 787.86, "total_tokens": 6365912} {"current_steps": 19545, "total_steps": 40000, "loss": 0.1531, "lr": 2.5895162513701456e-05, "epoch": 15.994678673761769, "percentage": 48.86, "elapsed_time": "2:14:41", "remaining_time": "2:20:57", "throughput": 787.89, "total_tokens": 6367512} {"current_steps": 19550, "total_steps": 40000, "loss": 0.1448, "lr": 2.5885351263427593e-05, "epoch": 15.998772001637331, "percentage": 48.88, "elapsed_time": "2:14:43", "remaining_time": "2:20:55", "throughput": 787.93, "total_tokens": 6369176} {"current_steps": 19555, "total_steps": 40000, "loss": 0.0839, "lr": 2.5875539876621448e-05, "epoch": 16.002455996725338, "percentage": 48.89, "elapsed_time": "2:14:45", "remaining_time": "2:20:53", "throughput": 787.92, "total_tokens": 6370584} {"current_steps": 19560, "total_steps": 40000, "loss": 0.1555, "lr": 2.586572835479605e-05, "epoch": 16.0065493246009, "percentage": 48.9, "elapsed_time": "2:14:47", "remaining_time": "2:20:50", "throughput": 787.96, "total_tokens": 6372216} {"current_steps": 19565, "total_steps": 40000, "loss": 0.1818, "lr": 2.585591669946446e-05, "epoch": 16.010642652476463, "percentage": 48.91, "elapsed_time": "2:14:48", "remaining_time": "2:20:48", "throughput": 787.98, "total_tokens": 6373800} {"current_steps": 19570, "total_steps": 40000, "loss": 0.1277, "lr": 2.5846104912139756e-05, "epoch": 16.014735980352025, "percentage": 48.93, "elapsed_time": "2:14:50", "remaining_time": "2:20:46", "throughput": 788.02, "total_tokens": 6375464} {"current_steps": 19575, "total_steps": 40000, "loss": 0.1201, "lr": 2.583629299433505e-05, "epoch": 16.018829308227588, "percentage": 48.94, "elapsed_time": "2:14:52", "remaining_time": "2:20:43", "throughput": 788.05, "total_tokens": 6377080} {"current_steps": 19580, "total_steps": 40000, "loss": 0.2654, "lr": 2.582648094756345e-05, "epoch": 16.022922636103154, "percentage": 48.95, "elapsed_time": "2:14:53", "remaining_time": "2:20:41", "throughput": 788.1, "total_tokens": 6378792} {"current_steps": 19585, "total_steps": 40000, "loss": 0.1569, "lr": 2.5816668773338098e-05, "epoch": 16.027015963978716, "percentage": 48.96, "elapsed_time": "2:14:55", "remaining_time": "2:20:38", "throughput": 788.13, "total_tokens": 6380424} {"current_steps": 19590, "total_steps": 40000, "loss": 0.1708, "lr": 2.580685647317216e-05, "epoch": 16.03110929185428, "percentage": 48.98, "elapsed_time": "2:14:57", "remaining_time": "2:20:36", "throughput": 788.16, "total_tokens": 6381992} {"current_steps": 19595, "total_steps": 40000, "loss": 0.2208, "lr": 2.5797044048578818e-05, "epoch": 16.03520261972984, "percentage": 48.99, "elapsed_time": "2:14:59", "remaining_time": "2:20:33", "throughput": 788.19, "total_tokens": 6383624} {"current_steps": 19600, "total_steps": 40000, "loss": 0.2055, "lr": 2.5787231501071262e-05, "epoch": 16.039295947605403, "percentage": 49.0, "elapsed_time": "2:15:00", "remaining_time": "2:20:31", "throughput": 788.22, "total_tokens": 6385240} {"current_steps": 19600, "total_steps": 40000, "eval_loss": 0.2098853886127472, "epoch": 16.039295947605403, "percentage": 49.0, "elapsed_time": "2:15:13", "remaining_time": "2:20:44", "throughput": 787.02, "total_tokens": 6385240} {"current_steps": 19605, "total_steps": 40000, "loss": 0.1486, "lr": 2.577741883216272e-05, "epoch": 16.043389275480965, "percentage": 49.01, "elapsed_time": "2:15:16", "remaining_time": "2:20:43", "throughput": 786.9, "total_tokens": 6386872} {"current_steps": 19610, "total_steps": 40000, "loss": 0.1566, "lr": 2.576760604336642e-05, "epoch": 16.047482603356528, "percentage": 49.02, "elapsed_time": "2:15:18", "remaining_time": "2:20:41", "throughput": 786.94, "total_tokens": 6388552} {"current_steps": 19615, "total_steps": 40000, "loss": 0.1705, "lr": 2.575779313619563e-05, "epoch": 16.05157593123209, "percentage": 49.04, "elapsed_time": "2:15:19", "remaining_time": "2:20:38", "throughput": 786.98, "total_tokens": 6390184} {"current_steps": 19620, "total_steps": 40000, "loss": 0.124, "lr": 2.5747980112163605e-05, "epoch": 16.055669259107656, "percentage": 49.05, "elapsed_time": "2:15:21", "remaining_time": "2:20:36", "throughput": 787.01, "total_tokens": 6391768} {"current_steps": 19625, "total_steps": 40000, "loss": 0.288, "lr": 2.5738166972783656e-05, "epoch": 16.05976258698322, "percentage": 49.06, "elapsed_time": "2:15:23", "remaining_time": "2:20:33", "throughput": 787.05, "total_tokens": 6393432} {"current_steps": 19630, "total_steps": 40000, "loss": 0.2082, "lr": 2.5728353719569075e-05, "epoch": 16.06385591485878, "percentage": 49.08, "elapsed_time": "2:15:25", "remaining_time": "2:20:31", "throughput": 787.09, "total_tokens": 6395112} {"current_steps": 19635, "total_steps": 40000, "loss": 0.1895, "lr": 2.57185403540332e-05, "epoch": 16.067949242734343, "percentage": 49.09, "elapsed_time": "2:15:26", "remaining_time": "2:20:28", "throughput": 787.11, "total_tokens": 6396664} {"current_steps": 19640, "total_steps": 40000, "loss": 0.156, "lr": 2.5708726877689375e-05, "epoch": 16.072042570609906, "percentage": 49.1, "elapsed_time": "2:15:28", "remaining_time": "2:20:26", "throughput": 787.14, "total_tokens": 6398232} {"current_steps": 19645, "total_steps": 40000, "loss": 0.195, "lr": 2.5698913292050964e-05, "epoch": 16.076135898485468, "percentage": 49.11, "elapsed_time": "2:15:30", "remaining_time": "2:20:24", "throughput": 787.17, "total_tokens": 6399864} {"current_steps": 19650, "total_steps": 40000, "loss": 0.1494, "lr": 2.568909959863133e-05, "epoch": 16.08022922636103, "percentage": 49.12, "elapsed_time": "2:15:31", "remaining_time": "2:20:21", "throughput": 787.2, "total_tokens": 6401464} {"current_steps": 19655, "total_steps": 40000, "loss": 0.2154, "lr": 2.5679285798943887e-05, "epoch": 16.084322554236593, "percentage": 49.14, "elapsed_time": "2:15:33", "remaining_time": "2:20:19", "throughput": 787.24, "total_tokens": 6403160} {"current_steps": 19660, "total_steps": 40000, "loss": 0.2546, "lr": 2.5669471894502035e-05, "epoch": 16.08841588211216, "percentage": 49.15, "elapsed_time": "2:15:35", "remaining_time": "2:20:16", "throughput": 787.28, "total_tokens": 6404792} {"current_steps": 19665, "total_steps": 40000, "loss": 0.2003, "lr": 2.56596578868192e-05, "epoch": 16.09250920998772, "percentage": 49.16, "elapsed_time": "2:15:37", "remaining_time": "2:20:14", "throughput": 787.3, "total_tokens": 6406360} {"current_steps": 19670, "total_steps": 40000, "loss": 0.1559, "lr": 2.564984377740883e-05, "epoch": 16.096602537863284, "percentage": 49.18, "elapsed_time": "2:15:38", "remaining_time": "2:20:11", "throughput": 787.35, "total_tokens": 6408056} {"current_steps": 19675, "total_steps": 40000, "loss": 0.2059, "lr": 2.564002956778438e-05, "epoch": 16.100695865738846, "percentage": 49.19, "elapsed_time": "2:15:40", "remaining_time": "2:20:09", "throughput": 787.38, "total_tokens": 6409688} {"current_steps": 19680, "total_steps": 40000, "loss": 0.1616, "lr": 2.563021525945934e-05, "epoch": 16.10478919361441, "percentage": 49.2, "elapsed_time": "2:15:42", "remaining_time": "2:20:07", "throughput": 787.41, "total_tokens": 6411304} {"current_steps": 19685, "total_steps": 40000, "loss": 0.1339, "lr": 2.562040085394718e-05, "epoch": 16.10888252148997, "percentage": 49.21, "elapsed_time": "2:15:43", "remaining_time": "2:20:04", "throughput": 787.45, "total_tokens": 6412968} {"current_steps": 19690, "total_steps": 40000, "loss": 0.2252, "lr": 2.56105863527614e-05, "epoch": 16.112975849365533, "percentage": 49.23, "elapsed_time": "2:15:45", "remaining_time": "2:20:02", "throughput": 787.48, "total_tokens": 6414584} {"current_steps": 19695, "total_steps": 40000, "loss": 0.2277, "lr": 2.5600771757415548e-05, "epoch": 16.117069177241095, "percentage": 49.24, "elapsed_time": "2:15:47", "remaining_time": "2:19:59", "throughput": 787.52, "total_tokens": 6416232} {"current_steps": 19700, "total_steps": 40000, "loss": 0.1177, "lr": 2.5590957069423134e-05, "epoch": 16.12116250511666, "percentage": 49.25, "elapsed_time": "2:15:49", "remaining_time": "2:19:57", "throughput": 787.55, "total_tokens": 6417848} {"current_steps": 19705, "total_steps": 40000, "loss": 0.1828, "lr": 2.5581142290297716e-05, "epoch": 16.125255832992224, "percentage": 49.26, "elapsed_time": "2:15:50", "remaining_time": "2:19:54", "throughput": 787.58, "total_tokens": 6419464} {"current_steps": 19710, "total_steps": 40000, "loss": 0.1922, "lr": 2.557132742155285e-05, "epoch": 16.129349160867786, "percentage": 49.28, "elapsed_time": "2:15:52", "remaining_time": "2:19:52", "throughput": 787.62, "total_tokens": 6421096} {"current_steps": 19715, "total_steps": 40000, "loss": 0.1982, "lr": 2.556151246470212e-05, "epoch": 16.13344248874335, "percentage": 49.29, "elapsed_time": "2:15:54", "remaining_time": "2:19:50", "throughput": 787.65, "total_tokens": 6422712} {"current_steps": 19720, "total_steps": 40000, "loss": 0.1757, "lr": 2.5551697421259114e-05, "epoch": 16.13753581661891, "percentage": 49.3, "elapsed_time": "2:15:55", "remaining_time": "2:19:47", "throughput": 787.69, "total_tokens": 6424408} {"current_steps": 19725, "total_steps": 40000, "loss": 0.1871, "lr": 2.554188229273743e-05, "epoch": 16.141629144494473, "percentage": 49.31, "elapsed_time": "2:15:57", "remaining_time": "2:19:45", "throughput": 787.72, "total_tokens": 6425992} {"current_steps": 19730, "total_steps": 40000, "loss": 0.1522, "lr": 2.5532067080650678e-05, "epoch": 16.145722472370036, "percentage": 49.33, "elapsed_time": "2:15:59", "remaining_time": "2:19:42", "throughput": 787.76, "total_tokens": 6427656} {"current_steps": 19735, "total_steps": 40000, "loss": 0.343, "lr": 2.55222517865125e-05, "epoch": 16.149815800245598, "percentage": 49.34, "elapsed_time": "2:16:01", "remaining_time": "2:19:40", "throughput": 787.79, "total_tokens": 6429256} {"current_steps": 19740, "total_steps": 40000, "loss": 0.1432, "lr": 2.5512436411836538e-05, "epoch": 16.153909128121164, "percentage": 49.35, "elapsed_time": "2:16:02", "remaining_time": "2:19:37", "throughput": 787.84, "total_tokens": 6431000} {"current_steps": 19745, "total_steps": 40000, "loss": 0.1815, "lr": 2.5502620958136443e-05, "epoch": 16.158002455996726, "percentage": 49.36, "elapsed_time": "2:16:04", "remaining_time": "2:19:35", "throughput": 787.87, "total_tokens": 6432648} {"current_steps": 19750, "total_steps": 40000, "loss": 0.17, "lr": 2.5492805426925874e-05, "epoch": 16.16209578387229, "percentage": 49.38, "elapsed_time": "2:16:06", "remaining_time": "2:19:33", "throughput": 787.9, "total_tokens": 6434232} {"current_steps": 19755, "total_steps": 40000, "loss": 0.1115, "lr": 2.5482989819718523e-05, "epoch": 16.16618911174785, "percentage": 49.39, "elapsed_time": "2:16:08", "remaining_time": "2:19:30", "throughput": 787.94, "total_tokens": 6435880} {"current_steps": 19760, "total_steps": 40000, "loss": 0.1173, "lr": 2.5473174138028065e-05, "epoch": 16.170282439623413, "percentage": 49.4, "elapsed_time": "2:16:09", "remaining_time": "2:19:28", "throughput": 787.97, "total_tokens": 6437544} {"current_steps": 19765, "total_steps": 40000, "loss": 0.1757, "lr": 2.5463358383368212e-05, "epoch": 16.174375767498976, "percentage": 49.41, "elapsed_time": "2:16:11", "remaining_time": "2:19:25", "throughput": 788.0, "total_tokens": 6439128} {"current_steps": 19770, "total_steps": 40000, "loss": 0.2265, "lr": 2.545354255725267e-05, "epoch": 16.17846909537454, "percentage": 49.43, "elapsed_time": "2:16:13", "remaining_time": "2:19:23", "throughput": 788.04, "total_tokens": 6440776} {"current_steps": 19775, "total_steps": 40000, "loss": 0.1684, "lr": 2.5443726661195165e-05, "epoch": 16.1825624232501, "percentage": 49.44, "elapsed_time": "2:16:14", "remaining_time": "2:19:20", "throughput": 788.08, "total_tokens": 6442440} {"current_steps": 19780, "total_steps": 40000, "loss": 0.2405, "lr": 2.543391069670944e-05, "epoch": 16.186655751125667, "percentage": 49.45, "elapsed_time": "2:16:16", "remaining_time": "2:19:18", "throughput": 788.11, "total_tokens": 6444056} {"current_steps": 19785, "total_steps": 40000, "loss": 0.177, "lr": 2.5424094665309228e-05, "epoch": 16.19074907900123, "percentage": 49.46, "elapsed_time": "2:16:18", "remaining_time": "2:19:16", "throughput": 788.14, "total_tokens": 6445640} {"current_steps": 19790, "total_steps": 40000, "loss": 0.236, "lr": 2.5414278568508292e-05, "epoch": 16.19484240687679, "percentage": 49.48, "elapsed_time": "2:16:20", "remaining_time": "2:19:13", "throughput": 788.16, "total_tokens": 6447208} {"current_steps": 19795, "total_steps": 40000, "loss": 0.1755, "lr": 2.540446240782039e-05, "epoch": 16.198935734752354, "percentage": 49.49, "elapsed_time": "2:16:21", "remaining_time": "2:19:11", "throughput": 788.19, "total_tokens": 6448808} {"current_steps": 19800, "total_steps": 40000, "loss": 0.1238, "lr": 2.5394646184759307e-05, "epoch": 16.203029062627916, "percentage": 49.5, "elapsed_time": "2:16:23", "remaining_time": "2:19:08", "throughput": 788.23, "total_tokens": 6450424} {"current_steps": 19800, "total_steps": 40000, "eval_loss": 0.204514741897583, "epoch": 16.203029062627916, "percentage": 49.5, "elapsed_time": "2:16:35", "remaining_time": "2:19:21", "throughput": 787.03, "total_tokens": 6450424} {"current_steps": 19805, "total_steps": 40000, "loss": 0.1395, "lr": 2.538482990083882e-05, "epoch": 16.20712239050348, "percentage": 49.51, "elapsed_time": "2:16:39", "remaining_time": "2:19:20", "throughput": 786.93, "total_tokens": 6452056} {"current_steps": 19810, "total_steps": 40000, "loss": 0.1718, "lr": 2.5375013557572725e-05, "epoch": 16.21121571837904, "percentage": 49.53, "elapsed_time": "2:16:40", "remaining_time": "2:19:18", "throughput": 786.96, "total_tokens": 6453704} {"current_steps": 19815, "total_steps": 40000, "loss": 0.2197, "lr": 2.536519715647483e-05, "epoch": 16.215309046254603, "percentage": 49.54, "elapsed_time": "2:16:42", "remaining_time": "2:19:15", "throughput": 786.97, "total_tokens": 6455368} {"current_steps": 19820, "total_steps": 40000, "loss": 0.2312, "lr": 2.535538069905894e-05, "epoch": 16.21940237413017, "percentage": 49.55, "elapsed_time": "2:16:44", "remaining_time": "2:19:13", "throughput": 787.01, "total_tokens": 6457016} {"current_steps": 19825, "total_steps": 40000, "loss": 0.1799, "lr": 2.534556418683888e-05, "epoch": 16.22349570200573, "percentage": 49.56, "elapsed_time": "2:16:46", "remaining_time": "2:19:11", "throughput": 787.04, "total_tokens": 6458632} {"current_steps": 19830, "total_steps": 40000, "loss": 0.2395, "lr": 2.5335747621328486e-05, "epoch": 16.227589029881294, "percentage": 49.58, "elapsed_time": "2:16:47", "remaining_time": "2:19:08", "throughput": 787.08, "total_tokens": 6460296} {"current_steps": 19835, "total_steps": 40000, "loss": 0.1659, "lr": 2.5325931004041586e-05, "epoch": 16.231682357756856, "percentage": 49.59, "elapsed_time": "2:16:49", "remaining_time": "2:19:06", "throughput": 787.11, "total_tokens": 6461944} {"current_steps": 19840, "total_steps": 40000, "loss": 0.1924, "lr": 2.5316114336492032e-05, "epoch": 16.23577568563242, "percentage": 49.6, "elapsed_time": "2:16:51", "remaining_time": "2:19:03", "throughput": 787.16, "total_tokens": 6463656} {"current_steps": 19845, "total_steps": 40000, "loss": 0.2011, "lr": 2.530629762019367e-05, "epoch": 16.23986901350798, "percentage": 49.61, "elapsed_time": "2:16:53", "remaining_time": "2:19:01", "throughput": 787.2, "total_tokens": 6465320} {"current_steps": 19850, "total_steps": 40000, "loss": 0.1388, "lr": 2.5296480856660364e-05, "epoch": 16.243962341383543, "percentage": 49.62, "elapsed_time": "2:16:54", "remaining_time": "2:18:58", "throughput": 787.22, "total_tokens": 6466888} {"current_steps": 19855, "total_steps": 40000, "loss": 0.222, "lr": 2.528666404740599e-05, "epoch": 16.24805566925911, "percentage": 49.64, "elapsed_time": "2:16:56", "remaining_time": "2:18:56", "throughput": 787.26, "total_tokens": 6468536} {"current_steps": 19860, "total_steps": 40000, "loss": 0.2527, "lr": 2.527684719394442e-05, "epoch": 16.25214899713467, "percentage": 49.65, "elapsed_time": "2:16:58", "remaining_time": "2:18:54", "throughput": 787.31, "total_tokens": 6470264} {"current_steps": 19865, "total_steps": 40000, "loss": 0.2036, "lr": 2.526703029778953e-05, "epoch": 16.256242325010234, "percentage": 49.66, "elapsed_time": "2:16:59", "remaining_time": "2:18:51", "throughput": 787.35, "total_tokens": 6471960} {"current_steps": 19870, "total_steps": 40000, "loss": 0.104, "lr": 2.5257213360455208e-05, "epoch": 16.260335652885797, "percentage": 49.68, "elapsed_time": "2:17:01", "remaining_time": "2:18:49", "throughput": 787.38, "total_tokens": 6473560} {"current_steps": 19875, "total_steps": 40000, "loss": 0.205, "lr": 2.5247396383455353e-05, "epoch": 16.26442898076136, "percentage": 49.69, "elapsed_time": "2:17:03", "remaining_time": "2:18:46", "throughput": 787.4, "total_tokens": 6475112} {"current_steps": 19880, "total_steps": 40000, "loss": 0.1636, "lr": 2.523757936830387e-05, "epoch": 16.26852230863692, "percentage": 49.7, "elapsed_time": "2:17:05", "remaining_time": "2:18:44", "throughput": 787.43, "total_tokens": 6476712} {"current_steps": 19885, "total_steps": 40000, "loss": 0.1739, "lr": 2.5227762316514662e-05, "epoch": 16.272615636512484, "percentage": 49.71, "elapsed_time": "2:17:06", "remaining_time": "2:18:41", "throughput": 787.46, "total_tokens": 6478328} {"current_steps": 19890, "total_steps": 40000, "loss": 0.1806, "lr": 2.5217945229601648e-05, "epoch": 16.276708964388046, "percentage": 49.73, "elapsed_time": "2:17:08", "remaining_time": "2:18:39", "throughput": 787.5, "total_tokens": 6479960} {"current_steps": 19895, "total_steps": 40000, "loss": 0.1277, "lr": 2.5208128109078738e-05, "epoch": 16.280802292263612, "percentage": 49.74, "elapsed_time": "2:17:10", "remaining_time": "2:18:37", "throughput": 787.53, "total_tokens": 6481576} {"current_steps": 19900, "total_steps": 40000, "loss": 0.1872, "lr": 2.5198310956459853e-05, "epoch": 16.284895620139174, "percentage": 49.75, "elapsed_time": "2:17:11", "remaining_time": "2:18:34", "throughput": 787.56, "total_tokens": 6483128} {"current_steps": 19905, "total_steps": 40000, "loss": 0.1936, "lr": 2.518849377325893e-05, "epoch": 16.288988948014737, "percentage": 49.76, "elapsed_time": "2:17:13", "remaining_time": "2:18:32", "throughput": 787.59, "total_tokens": 6484744} {"current_steps": 19910, "total_steps": 40000, "loss": 0.1665, "lr": 2.51786765609899e-05, "epoch": 16.2930822758903, "percentage": 49.78, "elapsed_time": "2:17:15", "remaining_time": "2:18:29", "throughput": 787.62, "total_tokens": 6486360} {"current_steps": 19915, "total_steps": 40000, "loss": 0.1775, "lr": 2.5168859321166694e-05, "epoch": 16.29717560376586, "percentage": 49.79, "elapsed_time": "2:17:17", "remaining_time": "2:18:27", "throughput": 787.65, "total_tokens": 6487976} {"current_steps": 19920, "total_steps": 40000, "loss": 0.1662, "lr": 2.515904205530326e-05, "epoch": 16.301268931641424, "percentage": 49.8, "elapsed_time": "2:17:18", "remaining_time": "2:18:25", "throughput": 787.68, "total_tokens": 6489576} {"current_steps": 19925, "total_steps": 40000, "loss": 0.1405, "lr": 2.514922476491355e-05, "epoch": 16.305362259516986, "percentage": 49.81, "elapsed_time": "2:17:20", "remaining_time": "2:18:22", "throughput": 787.72, "total_tokens": 6491256} {"current_steps": 19930, "total_steps": 40000, "loss": 0.2125, "lr": 2.51394074515115e-05, "epoch": 16.30945558739255, "percentage": 49.83, "elapsed_time": "2:17:22", "remaining_time": "2:18:20", "throughput": 787.76, "total_tokens": 6492920} {"current_steps": 19935, "total_steps": 40000, "loss": 0.1505, "lr": 2.5129590116611067e-05, "epoch": 16.313548915268115, "percentage": 49.84, "elapsed_time": "2:17:23", "remaining_time": "2:18:17", "throughput": 787.8, "total_tokens": 6494600} {"current_steps": 19940, "total_steps": 40000, "loss": 0.1606, "lr": 2.5119772761726212e-05, "epoch": 16.317642243143677, "percentage": 49.85, "elapsed_time": "2:17:25", "remaining_time": "2:18:15", "throughput": 787.83, "total_tokens": 6496248} {"current_steps": 19945, "total_steps": 40000, "loss": 0.156, "lr": 2.5109955388370893e-05, "epoch": 16.32173557101924, "percentage": 49.86, "elapsed_time": "2:17:27", "remaining_time": "2:18:12", "throughput": 787.87, "total_tokens": 6497880} {"current_steps": 19950, "total_steps": 40000, "loss": 0.2283, "lr": 2.510013799805907e-05, "epoch": 16.3258288988948, "percentage": 49.88, "elapsed_time": "2:17:29", "remaining_time": "2:18:10", "throughput": 787.9, "total_tokens": 6499480} {"current_steps": 19955, "total_steps": 40000, "loss": 0.1682, "lr": 2.5090320592304706e-05, "epoch": 16.329922226770364, "percentage": 49.89, "elapsed_time": "2:17:30", "remaining_time": "2:18:08", "throughput": 787.93, "total_tokens": 6501080} {"current_steps": 19960, "total_steps": 40000, "loss": 0.1817, "lr": 2.5080503172621777e-05, "epoch": 16.334015554645926, "percentage": 49.9, "elapsed_time": "2:17:32", "remaining_time": "2:18:05", "throughput": 787.96, "total_tokens": 6502712} {"current_steps": 19965, "total_steps": 40000, "loss": 0.2794, "lr": 2.5070685740524246e-05, "epoch": 16.33810888252149, "percentage": 49.91, "elapsed_time": "2:17:34", "remaining_time": "2:18:03", "throughput": 787.99, "total_tokens": 6504296} {"current_steps": 19970, "total_steps": 40000, "loss": 0.2256, "lr": 2.5060868297526084e-05, "epoch": 16.34220221039705, "percentage": 49.93, "elapsed_time": "2:17:35", "remaining_time": "2:18:00", "throughput": 788.02, "total_tokens": 6505880} {"current_steps": 19975, "total_steps": 40000, "loss": 0.2279, "lr": 2.5051050845141267e-05, "epoch": 16.346295538272617, "percentage": 49.94, "elapsed_time": "2:17:37", "remaining_time": "2:17:58", "throughput": 788.06, "total_tokens": 6507544} {"current_steps": 19980, "total_steps": 40000, "loss": 0.2082, "lr": 2.5041233384883765e-05, "epoch": 16.35038886614818, "percentage": 49.95, "elapsed_time": "2:17:39", "remaining_time": "2:17:55", "throughput": 788.09, "total_tokens": 6509176} {"current_steps": 19985, "total_steps": 40000, "loss": 0.1285, "lr": 2.5031415918267564e-05, "epoch": 16.354482194023742, "percentage": 49.96, "elapsed_time": "2:17:41", "remaining_time": "2:17:53", "throughput": 788.12, "total_tokens": 6510744} {"current_steps": 19990, "total_steps": 40000, "loss": 0.1403, "lr": 2.5021598446806626e-05, "epoch": 16.358575521899304, "percentage": 49.98, "elapsed_time": "2:17:42", "remaining_time": "2:17:51", "throughput": 788.15, "total_tokens": 6512392} {"current_steps": 19995, "total_steps": 40000, "loss": 0.2176, "lr": 2.5011780972014937e-05, "epoch": 16.362668849774867, "percentage": 49.99, "elapsed_time": "2:17:44", "remaining_time": "2:17:48", "throughput": 788.19, "total_tokens": 6514056} {"current_steps": 20000, "total_steps": 40000, "loss": 0.1912, "lr": 2.5001963495406478e-05, "epoch": 16.36676217765043, "percentage": 50.0, "elapsed_time": "2:17:46", "remaining_time": "2:17:46", "throughput": 788.22, "total_tokens": 6515688} {"current_steps": 20000, "total_steps": 40000, "eval_loss": 0.20628339052200317, "epoch": 16.36676217765043, "percentage": 50.0, "elapsed_time": "2:17:58", "remaining_time": "2:17:58", "throughput": 787.04, "total_tokens": 6515688} {"current_steps": 20005, "total_steps": 40000, "loss": 0.1886, "lr": 2.499214601849522e-05, "epoch": 16.37085550552599, "percentage": 50.01, "elapsed_time": "2:18:02", "remaining_time": "2:17:57", "throughput": 786.92, "total_tokens": 6517336} {"current_steps": 20010, "total_steps": 40000, "loss": 0.1488, "lr": 2.4982328542795148e-05, "epoch": 16.374948833401554, "percentage": 50.02, "elapsed_time": "2:18:03", "remaining_time": "2:17:55", "throughput": 786.95, "total_tokens": 6518936} {"current_steps": 20015, "total_steps": 40000, "loss": 0.1903, "lr": 2.497251106982024e-05, "epoch": 16.37904216127712, "percentage": 50.04, "elapsed_time": "2:18:05", "remaining_time": "2:17:53", "throughput": 786.99, "total_tokens": 6520600} {"current_steps": 20020, "total_steps": 40000, "loss": 0.2154, "lr": 2.4962693601084458e-05, "epoch": 16.383135489152682, "percentage": 50.05, "elapsed_time": "2:18:07", "remaining_time": "2:17:50", "throughput": 787.02, "total_tokens": 6522168} {"current_steps": 20025, "total_steps": 40000, "loss": 0.166, "lr": 2.4952876138101794e-05, "epoch": 16.387228817028245, "percentage": 50.06, "elapsed_time": "2:18:08", "remaining_time": "2:17:48", "throughput": 787.06, "total_tokens": 6523848} {"current_steps": 20030, "total_steps": 40000, "loss": 0.1035, "lr": 2.4943058682386233e-05, "epoch": 16.391322144903807, "percentage": 50.08, "elapsed_time": "2:18:10", "remaining_time": "2:17:45", "throughput": 787.08, "total_tokens": 6525416} {"current_steps": 20035, "total_steps": 40000, "loss": 0.172, "lr": 2.493324123545173e-05, "epoch": 16.39541547277937, "percentage": 50.09, "elapsed_time": "2:18:12", "remaining_time": "2:17:43", "throughput": 787.12, "total_tokens": 6527032} {"current_steps": 20040, "total_steps": 40000, "loss": 0.242, "lr": 2.4923423798812272e-05, "epoch": 16.39950880065493, "percentage": 50.1, "elapsed_time": "2:18:14", "remaining_time": "2:17:40", "throughput": 787.15, "total_tokens": 6528632} {"current_steps": 20045, "total_steps": 40000, "loss": 0.1369, "lr": 2.4913606373981825e-05, "epoch": 16.403602128530494, "percentage": 50.11, "elapsed_time": "2:18:15", "remaining_time": "2:17:38", "throughput": 787.17, "total_tokens": 6530216} {"current_steps": 20050, "total_steps": 40000, "loss": 0.1943, "lr": 2.4903788962474357e-05, "epoch": 16.407695456406056, "percentage": 50.12, "elapsed_time": "2:18:17", "remaining_time": "2:17:36", "throughput": 787.21, "total_tokens": 6531864} {"current_steps": 20055, "total_steps": 40000, "loss": 0.1617, "lr": 2.489397156580385e-05, "epoch": 16.411788784281622, "percentage": 50.14, "elapsed_time": "2:18:19", "remaining_time": "2:17:33", "throughput": 787.24, "total_tokens": 6533512} {"current_steps": 20060, "total_steps": 40000, "loss": 0.2045, "lr": 2.4884154185484246e-05, "epoch": 16.415882112157185, "percentage": 50.15, "elapsed_time": "2:18:20", "remaining_time": "2:17:31", "throughput": 787.28, "total_tokens": 6535160} {"current_steps": 20065, "total_steps": 40000, "loss": 0.2638, "lr": 2.4874336823029526e-05, "epoch": 16.419975440032747, "percentage": 50.16, "elapsed_time": "2:18:22", "remaining_time": "2:17:28", "throughput": 787.31, "total_tokens": 6536760} {"current_steps": 20070, "total_steps": 40000, "loss": 0.1413, "lr": 2.4864519479953656e-05, "epoch": 16.42406876790831, "percentage": 50.18, "elapsed_time": "2:18:24", "remaining_time": "2:17:26", "throughput": 787.34, "total_tokens": 6538408} {"current_steps": 20075, "total_steps": 40000, "loss": 0.1715, "lr": 2.485470215777058e-05, "epoch": 16.428162095783872, "percentage": 50.19, "elapsed_time": "2:18:26", "remaining_time": "2:17:24", "throughput": 787.37, "total_tokens": 6540008} {"current_steps": 20080, "total_steps": 40000, "loss": 0.2029, "lr": 2.4844884857994258e-05, "epoch": 16.432255423659434, "percentage": 50.2, "elapsed_time": "2:18:27", "remaining_time": "2:17:21", "throughput": 787.41, "total_tokens": 6541640} {"current_steps": 20085, "total_steps": 40000, "loss": 0.1269, "lr": 2.4835067582138638e-05, "epoch": 16.436348751534997, "percentage": 50.21, "elapsed_time": "2:18:29", "remaining_time": "2:17:19", "throughput": 787.44, "total_tokens": 6543224} {"current_steps": 20090, "total_steps": 40000, "loss": 0.1421, "lr": 2.4825250331717666e-05, "epoch": 16.44044207941056, "percentage": 50.22, "elapsed_time": "2:18:31", "remaining_time": "2:17:16", "throughput": 787.47, "total_tokens": 6544856} {"current_steps": 20095, "total_steps": 40000, "loss": 0.119, "lr": 2.4815433108245298e-05, "epoch": 16.444535407286125, "percentage": 50.24, "elapsed_time": "2:18:32", "remaining_time": "2:17:14", "throughput": 787.5, "total_tokens": 6546504} {"current_steps": 20100, "total_steps": 40000, "loss": 0.1695, "lr": 2.4805615913235456e-05, "epoch": 16.448628735161687, "percentage": 50.25, "elapsed_time": "2:18:34", "remaining_time": "2:17:11", "throughput": 787.54, "total_tokens": 6548136} {"current_steps": 20105, "total_steps": 40000, "loss": 0.1657, "lr": 2.479579874820208e-05, "epoch": 16.45272206303725, "percentage": 50.26, "elapsed_time": "2:18:36", "remaining_time": "2:17:09", "throughput": 787.58, "total_tokens": 6549816} {"current_steps": 20110, "total_steps": 40000, "loss": 0.1643, "lr": 2.4785981614659115e-05, "epoch": 16.456815390912812, "percentage": 50.28, "elapsed_time": "2:18:38", "remaining_time": "2:17:07", "throughput": 787.61, "total_tokens": 6551464} {"current_steps": 20115, "total_steps": 40000, "loss": 0.1937, "lr": 2.477616451412047e-05, "epoch": 16.460908718788374, "percentage": 50.29, "elapsed_time": "2:18:39", "remaining_time": "2:17:04", "throughput": 787.65, "total_tokens": 6553160} {"current_steps": 20120, "total_steps": 40000, "loss": 0.177, "lr": 2.476634744810007e-05, "epoch": 16.465002046663937, "percentage": 50.3, "elapsed_time": "2:18:41", "remaining_time": "2:17:02", "throughput": 787.68, "total_tokens": 6554728} {"current_steps": 20125, "total_steps": 40000, "loss": 0.2426, "lr": 2.475653041811183e-05, "epoch": 16.4690953745395, "percentage": 50.31, "elapsed_time": "2:18:43", "remaining_time": "2:16:59", "throughput": 787.72, "total_tokens": 6556440} {"current_steps": 20130, "total_steps": 40000, "loss": 0.1561, "lr": 2.4746713425669652e-05, "epoch": 16.473188702415065, "percentage": 50.32, "elapsed_time": "2:18:44", "remaining_time": "2:16:57", "throughput": 787.75, "total_tokens": 6558056} {"current_steps": 20135, "total_steps": 40000, "loss": 0.2823, "lr": 2.4736896472287458e-05, "epoch": 16.477282030290628, "percentage": 50.34, "elapsed_time": "2:18:46", "remaining_time": "2:16:55", "throughput": 787.79, "total_tokens": 6559688} {"current_steps": 20140, "total_steps": 40000, "loss": 0.1652, "lr": 2.4727079559479124e-05, "epoch": 16.48137535816619, "percentage": 50.35, "elapsed_time": "2:18:48", "remaining_time": "2:16:52", "throughput": 787.82, "total_tokens": 6561288} {"current_steps": 20145, "total_steps": 40000, "loss": 0.134, "lr": 2.4717262688758557e-05, "epoch": 16.485468686041752, "percentage": 50.36, "elapsed_time": "2:18:50", "remaining_time": "2:16:50", "throughput": 787.85, "total_tokens": 6562888} {"current_steps": 20150, "total_steps": 40000, "loss": 0.2405, "lr": 2.4707445861639637e-05, "epoch": 16.489562013917315, "percentage": 50.38, "elapsed_time": "2:18:51", "remaining_time": "2:16:47", "throughput": 787.88, "total_tokens": 6564552} {"current_steps": 20155, "total_steps": 40000, "loss": 0.1833, "lr": 2.4697629079636244e-05, "epoch": 16.493655341792877, "percentage": 50.39, "elapsed_time": "2:18:53", "remaining_time": "2:16:45", "throughput": 787.92, "total_tokens": 6566200} {"current_steps": 20160, "total_steps": 40000, "loss": 0.1711, "lr": 2.4687812344262244e-05, "epoch": 16.49774866966844, "percentage": 50.4, "elapsed_time": "2:18:55", "remaining_time": "2:16:42", "throughput": 787.95, "total_tokens": 6567784} {"current_steps": 20165, "total_steps": 40000, "loss": 0.1037, "lr": 2.46779956570315e-05, "epoch": 16.501841997544002, "percentage": 50.41, "elapsed_time": "2:18:57", "remaining_time": "2:16:40", "throughput": 787.97, "total_tokens": 6569352} {"current_steps": 20170, "total_steps": 40000, "loss": 0.1403, "lr": 2.466817901945787e-05, "epoch": 16.505935325419568, "percentage": 50.42, "elapsed_time": "2:18:58", "remaining_time": "2:16:38", "throughput": 788.01, "total_tokens": 6570984} {"current_steps": 20175, "total_steps": 40000, "loss": 0.1502, "lr": 2.4658362433055217e-05, "epoch": 16.51002865329513, "percentage": 50.44, "elapsed_time": "2:19:00", "remaining_time": "2:16:35", "throughput": 788.04, "total_tokens": 6572600} {"current_steps": 20180, "total_steps": 40000, "loss": 0.2035, "lr": 2.4648545899337356e-05, "epoch": 16.514121981170693, "percentage": 50.45, "elapsed_time": "2:19:02", "remaining_time": "2:16:33", "throughput": 788.07, "total_tokens": 6574232} {"current_steps": 20185, "total_steps": 40000, "loss": 0.1467, "lr": 2.4638729419818143e-05, "epoch": 16.518215309046255, "percentage": 50.46, "elapsed_time": "2:19:03", "remaining_time": "2:16:30", "throughput": 788.1, "total_tokens": 6575816} {"current_steps": 20190, "total_steps": 40000, "loss": 0.2452, "lr": 2.46289129960114e-05, "epoch": 16.522308636921817, "percentage": 50.48, "elapsed_time": "2:19:05", "remaining_time": "2:16:28", "throughput": 788.13, "total_tokens": 6577416} {"current_steps": 20195, "total_steps": 40000, "loss": 0.1324, "lr": 2.4619096629430924e-05, "epoch": 16.52640196479738, "percentage": 50.49, "elapsed_time": "2:19:07", "remaining_time": "2:16:26", "throughput": 788.16, "total_tokens": 6579032} {"current_steps": 20200, "total_steps": 40000, "loss": 0.2017, "lr": 2.4609280321590543e-05, "epoch": 16.530495292672942, "percentage": 50.5, "elapsed_time": "2:19:09", "remaining_time": "2:16:23", "throughput": 788.2, "total_tokens": 6580712} {"current_steps": 20200, "total_steps": 40000, "eval_loss": 0.20829834043979645, "epoch": 16.530495292672942, "percentage": 50.5, "elapsed_time": "2:19:21", "remaining_time": "2:16:35", "throughput": 787.03, "total_tokens": 6580712} {"current_steps": 20205, "total_steps": 40000, "loss": 0.1673, "lr": 2.4599464074004037e-05, "epoch": 16.534588620548504, "percentage": 50.51, "elapsed_time": "2:19:24", "remaining_time": "2:16:34", "throughput": 786.92, "total_tokens": 6582312} {"current_steps": 20210, "total_steps": 40000, "loss": 0.1895, "lr": 2.4589647888185204e-05, "epoch": 16.53868194842407, "percentage": 50.52, "elapsed_time": "2:19:26", "remaining_time": "2:16:32", "throughput": 786.96, "total_tokens": 6583992} {"current_steps": 20215, "total_steps": 40000, "loss": 0.1361, "lr": 2.4579831765647836e-05, "epoch": 16.542775276299633, "percentage": 50.54, "elapsed_time": "2:19:28", "remaining_time": "2:16:30", "throughput": 786.99, "total_tokens": 6585592} {"current_steps": 20220, "total_steps": 40000, "loss": 0.1424, "lr": 2.4570015707905676e-05, "epoch": 16.546868604175195, "percentage": 50.55, "elapsed_time": "2:19:29", "remaining_time": "2:16:27", "throughput": 787.02, "total_tokens": 6587192} {"current_steps": 20225, "total_steps": 40000, "loss": 0.2215, "lr": 2.4560199716472508e-05, "epoch": 16.550961932050757, "percentage": 50.56, "elapsed_time": "2:19:31", "remaining_time": "2:16:25", "throughput": 787.06, "total_tokens": 6588888} {"current_steps": 20230, "total_steps": 40000, "loss": 0.2291, "lr": 2.455038379286207e-05, "epoch": 16.55505525992632, "percentage": 50.58, "elapsed_time": "2:19:33", "remaining_time": "2:16:22", "throughput": 787.1, "total_tokens": 6590520} {"current_steps": 20235, "total_steps": 40000, "loss": 0.1569, "lr": 2.4540567938588095e-05, "epoch": 16.559148587801882, "percentage": 50.59, "elapsed_time": "2:19:34", "remaining_time": "2:16:20", "throughput": 787.12, "total_tokens": 6592120} {"current_steps": 20240, "total_steps": 40000, "loss": 0.1774, "lr": 2.4530752155164328e-05, "epoch": 16.563241915677445, "percentage": 50.6, "elapsed_time": "2:19:36", "remaining_time": "2:16:18", "throughput": 787.15, "total_tokens": 6593704} {"current_steps": 20245, "total_steps": 40000, "loss": 0.2923, "lr": 2.4520936444104463e-05, "epoch": 16.567335243553007, "percentage": 50.61, "elapsed_time": "2:19:38", "remaining_time": "2:16:15", "throughput": 787.19, "total_tokens": 6595400} {"current_steps": 20250, "total_steps": 40000, "loss": 0.1132, "lr": 2.4511120806922218e-05, "epoch": 16.571428571428573, "percentage": 50.62, "elapsed_time": "2:19:40", "remaining_time": "2:16:13", "throughput": 787.23, "total_tokens": 6597064} {"current_steps": 20255, "total_steps": 40000, "loss": 0.1745, "lr": 2.45013052451313e-05, "epoch": 16.575521899304135, "percentage": 50.64, "elapsed_time": "2:19:41", "remaining_time": "2:16:10", "throughput": 787.26, "total_tokens": 6598712} {"current_steps": 20260, "total_steps": 40000, "loss": 0.186, "lr": 2.4491489760245376e-05, "epoch": 16.579615227179698, "percentage": 50.65, "elapsed_time": "2:19:43", "remaining_time": "2:16:08", "throughput": 787.29, "total_tokens": 6600312} {"current_steps": 20265, "total_steps": 40000, "loss": 0.1125, "lr": 2.4481674353778115e-05, "epoch": 16.58370855505526, "percentage": 50.66, "elapsed_time": "2:19:45", "remaining_time": "2:16:05", "throughput": 787.33, "total_tokens": 6601976} {"current_steps": 20270, "total_steps": 40000, "loss": 0.1665, "lr": 2.447185902724319e-05, "epoch": 16.587801882930822, "percentage": 50.68, "elapsed_time": "2:19:46", "remaining_time": "2:16:03", "throughput": 787.37, "total_tokens": 6603656} {"current_steps": 20275, "total_steps": 40000, "loss": 0.1315, "lr": 2.4462043782154233e-05, "epoch": 16.591895210806385, "percentage": 50.69, "elapsed_time": "2:19:48", "remaining_time": "2:16:01", "throughput": 787.41, "total_tokens": 6605352} {"current_steps": 20280, "total_steps": 40000, "loss": 0.1783, "lr": 2.4452228620024895e-05, "epoch": 16.595988538681947, "percentage": 50.7, "elapsed_time": "2:19:50", "remaining_time": "2:15:58", "throughput": 787.44, "total_tokens": 6606984} {"current_steps": 20285, "total_steps": 40000, "loss": 0.1552, "lr": 2.4442413542368776e-05, "epoch": 16.60008186655751, "percentage": 50.71, "elapsed_time": "2:19:52", "remaining_time": "2:15:56", "throughput": 787.47, "total_tokens": 6608600} {"current_steps": 20290, "total_steps": 40000, "loss": 0.1579, "lr": 2.4432598550699502e-05, "epoch": 16.604175194433076, "percentage": 50.72, "elapsed_time": "2:19:53", "remaining_time": "2:15:53", "throughput": 787.5, "total_tokens": 6610184} {"current_steps": 20295, "total_steps": 40000, "loss": 0.1884, "lr": 2.4422783646530663e-05, "epoch": 16.608268522308638, "percentage": 50.74, "elapsed_time": "2:19:55", "remaining_time": "2:15:51", "throughput": 787.54, "total_tokens": 6611832} {"current_steps": 20300, "total_steps": 40000, "loss": 0.2859, "lr": 2.441296883137584e-05, "epoch": 16.6123618501842, "percentage": 50.75, "elapsed_time": "2:19:57", "remaining_time": "2:15:49", "throughput": 787.58, "total_tokens": 6613528} {"current_steps": 20305, "total_steps": 40000, "loss": 0.1752, "lr": 2.4403154106748592e-05, "epoch": 16.616455178059763, "percentage": 50.76, "elapsed_time": "2:19:59", "remaining_time": "2:15:46", "throughput": 787.62, "total_tokens": 6615240} {"current_steps": 20310, "total_steps": 40000, "loss": 0.2745, "lr": 2.4393339474162494e-05, "epoch": 16.620548505935325, "percentage": 50.78, "elapsed_time": "2:20:00", "remaining_time": "2:15:44", "throughput": 787.65, "total_tokens": 6616824} {"current_steps": 20315, "total_steps": 40000, "loss": 0.1678, "lr": 2.4383524935131062e-05, "epoch": 16.624641833810887, "percentage": 50.79, "elapsed_time": "2:20:02", "remaining_time": "2:15:41", "throughput": 787.68, "total_tokens": 6618440} {"current_steps": 20320, "total_steps": 40000, "loss": 0.1677, "lr": 2.437371049116784e-05, "epoch": 16.62873516168645, "percentage": 50.8, "elapsed_time": "2:20:04", "remaining_time": "2:15:39", "throughput": 787.71, "total_tokens": 6620008} {"current_steps": 20325, "total_steps": 40000, "loss": 0.1539, "lr": 2.436389614378632e-05, "epoch": 16.632828489562012, "percentage": 50.81, "elapsed_time": "2:20:05", "remaining_time": "2:15:37", "throughput": 787.74, "total_tokens": 6621640} {"current_steps": 20330, "total_steps": 40000, "loss": 0.2028, "lr": 2.435408189450002e-05, "epoch": 16.636921817437578, "percentage": 50.82, "elapsed_time": "2:20:07", "remaining_time": "2:15:34", "throughput": 787.77, "total_tokens": 6623256} {"current_steps": 20335, "total_steps": 40000, "loss": 0.1431, "lr": 2.4344267744822406e-05, "epoch": 16.64101514531314, "percentage": 50.84, "elapsed_time": "2:20:09", "remaining_time": "2:15:32", "throughput": 787.81, "total_tokens": 6624920} {"current_steps": 20340, "total_steps": 40000, "loss": 0.1372, "lr": 2.4334453696266944e-05, "epoch": 16.645108473188703, "percentage": 50.85, "elapsed_time": "2:20:11", "remaining_time": "2:15:29", "throughput": 787.85, "total_tokens": 6626600} {"current_steps": 20345, "total_steps": 40000, "loss": 0.1714, "lr": 2.432463975034708e-05, "epoch": 16.649201801064265, "percentage": 50.86, "elapsed_time": "2:20:12", "remaining_time": "2:15:27", "throughput": 787.89, "total_tokens": 6628312} {"current_steps": 20350, "total_steps": 40000, "loss": 0.1576, "lr": 2.4314825908576265e-05, "epoch": 16.653295128939828, "percentage": 50.88, "elapsed_time": "2:20:14", "remaining_time": "2:15:25", "throughput": 787.93, "total_tokens": 6629992} {"current_steps": 20355, "total_steps": 40000, "loss": 0.1814, "lr": 2.4305012172467897e-05, "epoch": 16.65738845681539, "percentage": 50.89, "elapsed_time": "2:20:16", "remaining_time": "2:15:22", "throughput": 787.95, "total_tokens": 6631576} {"current_steps": 20360, "total_steps": 40000, "loss": 0.1291, "lr": 2.4295198543535393e-05, "epoch": 16.661481784690952, "percentage": 50.9, "elapsed_time": "2:20:17", "remaining_time": "2:15:20", "throughput": 787.99, "total_tokens": 6633208} {"current_steps": 20365, "total_steps": 40000, "loss": 0.1813, "lr": 2.4285385023292124e-05, "epoch": 16.665575112566515, "percentage": 50.91, "elapsed_time": "2:20:19", "remaining_time": "2:15:17", "throughput": 788.02, "total_tokens": 6634840} {"current_steps": 20370, "total_steps": 40000, "loss": 0.2193, "lr": 2.427557161325147e-05, "epoch": 16.66966844044208, "percentage": 50.92, "elapsed_time": "2:20:21", "remaining_time": "2:15:15", "throughput": 788.05, "total_tokens": 6636456} {"current_steps": 20375, "total_steps": 40000, "loss": 0.1652, "lr": 2.4265758314926778e-05, "epoch": 16.673761768317643, "percentage": 50.94, "elapsed_time": "2:20:23", "remaining_time": "2:15:12", "throughput": 788.08, "total_tokens": 6638072} {"current_steps": 20380, "total_steps": 40000, "loss": 0.1024, "lr": 2.4255945129831373e-05, "epoch": 16.677855096193205, "percentage": 50.95, "elapsed_time": "2:20:24", "remaining_time": "2:15:10", "throughput": 788.12, "total_tokens": 6639736} {"current_steps": 20385, "total_steps": 40000, "loss": 0.2589, "lr": 2.4246132059478578e-05, "epoch": 16.681948424068768, "percentage": 50.96, "elapsed_time": "2:20:26", "remaining_time": "2:15:08", "throughput": 788.16, "total_tokens": 6641400} {"current_steps": 20390, "total_steps": 40000, "loss": 0.1686, "lr": 2.4236319105381706e-05, "epoch": 16.68604175194433, "percentage": 50.98, "elapsed_time": "2:20:28", "remaining_time": "2:15:05", "throughput": 788.18, "total_tokens": 6642968} {"current_steps": 20395, "total_steps": 40000, "loss": 0.2001, "lr": 2.422650626905401e-05, "epoch": 16.690135079819893, "percentage": 50.99, "elapsed_time": "2:20:29", "remaining_time": "2:15:03", "throughput": 788.21, "total_tokens": 6644536} {"current_steps": 20400, "total_steps": 40000, "loss": 0.0828, "lr": 2.4216693552008785e-05, "epoch": 16.694228407695455, "percentage": 51.0, "elapsed_time": "2:20:31", "remaining_time": "2:15:00", "throughput": 788.24, "total_tokens": 6646184} {"current_steps": 20400, "total_steps": 40000, "eval_loss": 0.21357190608978271, "epoch": 16.694228407695455, "percentage": 51.0, "elapsed_time": "2:20:44", "remaining_time": "2:15:12", "throughput": 787.09, "total_tokens": 6646184} {"current_steps": 20405, "total_steps": 40000, "loss": 0.1645, "lr": 2.4206880955759247e-05, "epoch": 16.69832173557102, "percentage": 51.01, "elapsed_time": "2:20:47", "remaining_time": "2:15:11", "throughput": 786.98, "total_tokens": 6647800} {"current_steps": 20410, "total_steps": 40000, "loss": 0.1978, "lr": 2.419706848181863e-05, "epoch": 16.702415063446583, "percentage": 51.02, "elapsed_time": "2:20:48", "remaining_time": "2:15:09", "throughput": 787.01, "total_tokens": 6649400} {"current_steps": 20415, "total_steps": 40000, "loss": 0.1263, "lr": 2.4187256131700153e-05, "epoch": 16.706508391322146, "percentage": 51.04, "elapsed_time": "2:20:50", "remaining_time": "2:15:07", "throughput": 787.04, "total_tokens": 6651000} {"current_steps": 20420, "total_steps": 40000, "loss": 0.1694, "lr": 2.4177443906916985e-05, "epoch": 16.710601719197708, "percentage": 51.05, "elapsed_time": "2:20:52", "remaining_time": "2:15:04", "throughput": 787.08, "total_tokens": 6652712} {"current_steps": 20425, "total_steps": 40000, "loss": 0.1597, "lr": 2.4167631808982303e-05, "epoch": 16.71469504707327, "percentage": 51.06, "elapsed_time": "2:20:54", "remaining_time": "2:15:02", "throughput": 787.11, "total_tokens": 6654360} {"current_steps": 20430, "total_steps": 40000, "loss": 0.2681, "lr": 2.4157819839409264e-05, "epoch": 16.718788374948833, "percentage": 51.08, "elapsed_time": "2:20:55", "remaining_time": "2:14:59", "throughput": 787.15, "total_tokens": 6655992} {"current_steps": 20435, "total_steps": 40000, "loss": 0.1206, "lr": 2.414800799971098e-05, "epoch": 16.722881702824395, "percentage": 51.09, "elapsed_time": "2:20:57", "remaining_time": "2:14:57", "throughput": 787.17, "total_tokens": 6657560} {"current_steps": 20440, "total_steps": 40000, "loss": 0.1357, "lr": 2.4138196291400582e-05, "epoch": 16.726975030699958, "percentage": 51.1, "elapsed_time": "2:20:59", "remaining_time": "2:14:55", "throughput": 787.2, "total_tokens": 6659192} {"current_steps": 20445, "total_steps": 40000, "loss": 0.1819, "lr": 2.412838471599114e-05, "epoch": 16.731068358575524, "percentage": 51.11, "elapsed_time": "2:21:01", "remaining_time": "2:14:52", "throughput": 787.24, "total_tokens": 6660888} {"current_steps": 20450, "total_steps": 40000, "loss": 0.1665, "lr": 2.411857327499572e-05, "epoch": 16.735161686451086, "percentage": 51.12, "elapsed_time": "2:21:02", "remaining_time": "2:14:50", "throughput": 787.27, "total_tokens": 6662488} {"current_steps": 20455, "total_steps": 40000, "loss": 0.1793, "lr": 2.410876196992739e-05, "epoch": 16.73925501432665, "percentage": 51.14, "elapsed_time": "2:21:04", "remaining_time": "2:14:47", "throughput": 787.31, "total_tokens": 6664120} {"current_steps": 20460, "total_steps": 40000, "loss": 0.2268, "lr": 2.4098950802299156e-05, "epoch": 16.74334834220221, "percentage": 51.15, "elapsed_time": "2:21:06", "remaining_time": "2:14:45", "throughput": 787.34, "total_tokens": 6665736} {"current_steps": 20465, "total_steps": 40000, "loss": 0.1544, "lr": 2.4089139773624027e-05, "epoch": 16.747441670077773, "percentage": 51.16, "elapsed_time": "2:21:07", "remaining_time": "2:14:43", "throughput": 787.36, "total_tokens": 6667288} {"current_steps": 20470, "total_steps": 40000, "loss": 0.2344, "lr": 2.4079328885415007e-05, "epoch": 16.751534997953335, "percentage": 51.18, "elapsed_time": "2:21:09", "remaining_time": "2:14:40", "throughput": 787.4, "total_tokens": 6668952} {"current_steps": 20475, "total_steps": 40000, "loss": 0.2018, "lr": 2.4069518139185036e-05, "epoch": 16.755628325828898, "percentage": 51.19, "elapsed_time": "2:21:11", "remaining_time": "2:14:38", "throughput": 787.43, "total_tokens": 6670600} {"current_steps": 20480, "total_steps": 40000, "loss": 0.1749, "lr": 2.405970753644706e-05, "epoch": 16.75972165370446, "percentage": 51.2, "elapsed_time": "2:21:13", "remaining_time": "2:14:35", "throughput": 787.46, "total_tokens": 6672200} {"current_steps": 20485, "total_steps": 40000, "loss": 0.1678, "lr": 2.4049897078714e-05, "epoch": 16.763814981580026, "percentage": 51.21, "elapsed_time": "2:21:14", "remaining_time": "2:14:33", "throughput": 787.49, "total_tokens": 6673800} {"current_steps": 20490, "total_steps": 40000, "loss": 0.1395, "lr": 2.404008676749874e-05, "epoch": 16.76790830945559, "percentage": 51.23, "elapsed_time": "2:21:16", "remaining_time": "2:14:31", "throughput": 787.53, "total_tokens": 6675448} {"current_steps": 20495, "total_steps": 40000, "loss": 0.2946, "lr": 2.403027660431418e-05, "epoch": 16.77200163733115, "percentage": 51.24, "elapsed_time": "2:21:18", "remaining_time": "2:14:28", "throughput": 787.56, "total_tokens": 6677112} {"current_steps": 20500, "total_steps": 40000, "loss": 0.2155, "lr": 2.402046659067314e-05, "epoch": 16.776094965206713, "percentage": 51.25, "elapsed_time": "2:21:19", "remaining_time": "2:14:26", "throughput": 787.59, "total_tokens": 6678712} {"current_steps": 20505, "total_steps": 40000, "loss": 0.1742, "lr": 2.401065672808847e-05, "epoch": 16.780188293082276, "percentage": 51.26, "elapsed_time": "2:21:21", "remaining_time": "2:14:23", "throughput": 787.62, "total_tokens": 6680328} {"current_steps": 20510, "total_steps": 40000, "loss": 0.2365, "lr": 2.400084701807296e-05, "epoch": 16.784281620957838, "percentage": 51.28, "elapsed_time": "2:21:23", "remaining_time": "2:14:21", "throughput": 787.65, "total_tokens": 6681896} {"current_steps": 20515, "total_steps": 40000, "loss": 0.1591, "lr": 2.39910374621394e-05, "epoch": 16.7883749488334, "percentage": 51.29, "elapsed_time": "2:21:25", "remaining_time": "2:14:19", "throughput": 787.68, "total_tokens": 6683528} {"current_steps": 20520, "total_steps": 40000, "loss": 0.1661, "lr": 2.3981228061800544e-05, "epoch": 16.792468276708963, "percentage": 51.3, "elapsed_time": "2:21:26", "remaining_time": "2:14:16", "throughput": 787.72, "total_tokens": 6685208} {"current_steps": 20525, "total_steps": 40000, "loss": 0.1854, "lr": 2.3971418818569115e-05, "epoch": 16.79656160458453, "percentage": 51.31, "elapsed_time": "2:21:28", "remaining_time": "2:14:14", "throughput": 787.77, "total_tokens": 6686936} {"current_steps": 20530, "total_steps": 40000, "loss": 0.1522, "lr": 2.3961609733957832e-05, "epoch": 16.80065493246009, "percentage": 51.32, "elapsed_time": "2:21:30", "remaining_time": "2:14:11", "throughput": 787.8, "total_tokens": 6688552} {"current_steps": 20535, "total_steps": 40000, "loss": 0.2052, "lr": 2.395180080947939e-05, "epoch": 16.804748260335653, "percentage": 51.34, "elapsed_time": "2:21:31", "remaining_time": "2:14:09", "throughput": 787.84, "total_tokens": 6690248} {"current_steps": 20540, "total_steps": 40000, "loss": 0.1766, "lr": 2.394199204664642e-05, "epoch": 16.808841588211216, "percentage": 51.35, "elapsed_time": "2:21:33", "remaining_time": "2:14:07", "throughput": 787.87, "total_tokens": 6691848} {"current_steps": 20545, "total_steps": 40000, "loss": 0.1928, "lr": 2.3932183446971583e-05, "epoch": 16.81293491608678, "percentage": 51.36, "elapsed_time": "2:21:35", "remaining_time": "2:14:04", "throughput": 787.9, "total_tokens": 6693480} {"current_steps": 20550, "total_steps": 40000, "loss": 0.1174, "lr": 2.3922375011967473e-05, "epoch": 16.81702824396234, "percentage": 51.38, "elapsed_time": "2:21:37", "remaining_time": "2:14:02", "throughput": 787.93, "total_tokens": 6695112} {"current_steps": 20555, "total_steps": 40000, "loss": 0.1839, "lr": 2.3912566743146676e-05, "epoch": 16.821121571837903, "percentage": 51.39, "elapsed_time": "2:21:38", "remaining_time": "2:13:59", "throughput": 787.97, "total_tokens": 6696760} {"current_steps": 20560, "total_steps": 40000, "loss": 0.2383, "lr": 2.390275864202176e-05, "epoch": 16.825214899713465, "percentage": 51.4, "elapsed_time": "2:21:40", "remaining_time": "2:13:57", "throughput": 788.0, "total_tokens": 6698408} {"current_steps": 20565, "total_steps": 40000, "loss": 0.1809, "lr": 2.3892950710105243e-05, "epoch": 16.82930822758903, "percentage": 51.41, "elapsed_time": "2:21:42", "remaining_time": "2:13:55", "throughput": 788.04, "total_tokens": 6700056} {"current_steps": 20570, "total_steps": 40000, "loss": 0.2251, "lr": 2.3883142948909635e-05, "epoch": 16.833401555464594, "percentage": 51.42, "elapsed_time": "2:21:43", "remaining_time": "2:13:52", "throughput": 788.07, "total_tokens": 6701704} {"current_steps": 20575, "total_steps": 40000, "loss": 0.1852, "lr": 2.3873335359947433e-05, "epoch": 16.837494883340156, "percentage": 51.44, "elapsed_time": "2:21:45", "remaining_time": "2:13:50", "throughput": 788.11, "total_tokens": 6703336} {"current_steps": 20580, "total_steps": 40000, "loss": 0.2367, "lr": 2.3863527944731066e-05, "epoch": 16.84158821121572, "percentage": 51.45, "elapsed_time": "2:21:47", "remaining_time": "2:13:47", "throughput": 788.14, "total_tokens": 6704952} {"current_steps": 20585, "total_steps": 40000, "loss": 0.1346, "lr": 2.385372070477298e-05, "epoch": 16.84568153909128, "percentage": 51.46, "elapsed_time": "2:21:49", "remaining_time": "2:13:45", "throughput": 788.16, "total_tokens": 6706520} {"current_steps": 20590, "total_steps": 40000, "loss": 0.0921, "lr": 2.384391364158556e-05, "epoch": 16.849774866966843, "percentage": 51.48, "elapsed_time": "2:21:50", "remaining_time": "2:13:43", "throughput": 788.2, "total_tokens": 6708200} {"current_steps": 20595, "total_steps": 40000, "loss": 0.2126, "lr": 2.3834106756681185e-05, "epoch": 16.853868194842406, "percentage": 51.49, "elapsed_time": "2:21:52", "remaining_time": "2:13:40", "throughput": 788.23, "total_tokens": 6709816} {"current_steps": 20600, "total_steps": 40000, "loss": 0.1354, "lr": 2.3824300051572206e-05, "epoch": 16.857961522717968, "percentage": 51.5, "elapsed_time": "2:21:54", "remaining_time": "2:13:38", "throughput": 788.27, "total_tokens": 6711480} {"current_steps": 20600, "total_steps": 40000, "eval_loss": 0.20618575811386108, "epoch": 16.857961522717968, "percentage": 51.5, "elapsed_time": "2:22:06", "remaining_time": "2:13:49", "throughput": 787.12, "total_tokens": 6711480} {"current_steps": 20605, "total_steps": 40000, "loss": 0.1831, "lr": 2.3814493527770923e-05, "epoch": 16.862054850593534, "percentage": 51.51, "elapsed_time": "2:22:10", "remaining_time": "2:13:49", "throughput": 787.0, "total_tokens": 6713112} {"current_steps": 20610, "total_steps": 40000, "loss": 0.2028, "lr": 2.3804687186789637e-05, "epoch": 16.866148178469096, "percentage": 51.52, "elapsed_time": "2:22:11", "remaining_time": "2:13:46", "throughput": 787.02, "total_tokens": 6714680} {"current_steps": 20615, "total_steps": 40000, "loss": 0.1753, "lr": 2.379488103014062e-05, "epoch": 16.87024150634466, "percentage": 51.54, "elapsed_time": "2:22:13", "remaining_time": "2:13:44", "throughput": 787.06, "total_tokens": 6716376} {"current_steps": 20620, "total_steps": 40000, "loss": 0.2411, "lr": 2.3785075059336086e-05, "epoch": 16.87433483422022, "percentage": 51.55, "elapsed_time": "2:22:15", "remaining_time": "2:13:41", "throughput": 787.09, "total_tokens": 6717992} {"current_steps": 20625, "total_steps": 40000, "loss": 0.1663, "lr": 2.3775269275888248e-05, "epoch": 16.878428162095783, "percentage": 51.56, "elapsed_time": "2:22:16", "remaining_time": "2:13:39", "throughput": 787.12, "total_tokens": 6719624} {"current_steps": 20630, "total_steps": 40000, "loss": 0.1536, "lr": 2.3765463681309274e-05, "epoch": 16.882521489971346, "percentage": 51.58, "elapsed_time": "2:22:18", "remaining_time": "2:13:37", "throughput": 787.16, "total_tokens": 6721240} {"current_steps": 20635, "total_steps": 40000, "loss": 0.1689, "lr": 2.3755658277111313e-05, "epoch": 16.886614817846908, "percentage": 51.59, "elapsed_time": "2:22:20", "remaining_time": "2:13:34", "throughput": 787.19, "total_tokens": 6722872} {"current_steps": 20640, "total_steps": 40000, "loss": 0.1773, "lr": 2.374585306480649e-05, "epoch": 16.89070814572247, "percentage": 51.6, "elapsed_time": "2:22:22", "remaining_time": "2:13:32", "throughput": 787.21, "total_tokens": 6724440} {"current_steps": 20645, "total_steps": 40000, "loss": 0.2513, "lr": 2.3736048045906877e-05, "epoch": 16.894801473598037, "percentage": 51.61, "elapsed_time": "2:22:23", "remaining_time": "2:13:29", "throughput": 787.24, "total_tokens": 6726040} {"current_steps": 20650, "total_steps": 40000, "loss": 0.1277, "lr": 2.372624322192454e-05, "epoch": 16.8988948014736, "percentage": 51.62, "elapsed_time": "2:22:25", "remaining_time": "2:13:27", "throughput": 787.27, "total_tokens": 6727672} {"current_steps": 20655, "total_steps": 40000, "loss": 0.282, "lr": 2.3716438594371516e-05, "epoch": 16.90298812934916, "percentage": 51.64, "elapsed_time": "2:22:27", "remaining_time": "2:13:25", "throughput": 787.31, "total_tokens": 6729288} {"current_steps": 20660, "total_steps": 40000, "loss": 0.2352, "lr": 2.3706634164759784e-05, "epoch": 16.907081457224724, "percentage": 51.65, "elapsed_time": "2:22:28", "remaining_time": "2:13:22", "throughput": 787.34, "total_tokens": 6730952} {"current_steps": 20665, "total_steps": 40000, "loss": 0.161, "lr": 2.3696829934601323e-05, "epoch": 16.911174785100286, "percentage": 51.66, "elapsed_time": "2:22:30", "remaining_time": "2:13:20", "throughput": 787.37, "total_tokens": 6732552} {"current_steps": 20670, "total_steps": 40000, "loss": 0.2003, "lr": 2.3687025905408053e-05, "epoch": 16.91526811297585, "percentage": 51.68, "elapsed_time": "2:22:32", "remaining_time": "2:13:17", "throughput": 787.4, "total_tokens": 6734184} {"current_steps": 20675, "total_steps": 40000, "loss": 0.1842, "lr": 2.3677222078691886e-05, "epoch": 16.91936144085141, "percentage": 51.69, "elapsed_time": "2:22:34", "remaining_time": "2:13:15", "throughput": 787.44, "total_tokens": 6735832} {"current_steps": 20680, "total_steps": 40000, "loss": 0.1523, "lr": 2.366741845596471e-05, "epoch": 16.923454768726977, "percentage": 51.7, "elapsed_time": "2:22:35", "remaining_time": "2:13:13", "throughput": 787.46, "total_tokens": 6737416} {"current_steps": 20685, "total_steps": 40000, "loss": 0.1542, "lr": 2.3657615038738343e-05, "epoch": 16.92754809660254, "percentage": 51.71, "elapsed_time": "2:22:37", "remaining_time": "2:13:10", "throughput": 787.5, "total_tokens": 6739048} {"current_steps": 20690, "total_steps": 40000, "loss": 0.2004, "lr": 2.3647811828524614e-05, "epoch": 16.9316414244781, "percentage": 51.73, "elapsed_time": "2:22:39", "remaining_time": "2:13:08", "throughput": 787.54, "total_tokens": 6740744} {"current_steps": 20695, "total_steps": 40000, "loss": 0.1691, "lr": 2.363800882683529e-05, "epoch": 16.935734752353664, "percentage": 51.74, "elapsed_time": "2:22:40", "remaining_time": "2:13:05", "throughput": 787.56, "total_tokens": 6742312} {"current_steps": 20700, "total_steps": 40000, "loss": 0.1953, "lr": 2.3628206035182125e-05, "epoch": 16.939828080229226, "percentage": 51.75, "elapsed_time": "2:22:42", "remaining_time": "2:13:03", "throughput": 787.59, "total_tokens": 6743928} {"current_steps": 20705, "total_steps": 40000, "loss": 0.1496, "lr": 2.361840345507683e-05, "epoch": 16.94392140810479, "percentage": 51.76, "elapsed_time": "2:22:44", "remaining_time": "2:13:01", "throughput": 787.62, "total_tokens": 6745544} {"current_steps": 20710, "total_steps": 40000, "loss": 0.1999, "lr": 2.3608601088031073e-05, "epoch": 16.94801473598035, "percentage": 51.78, "elapsed_time": "2:22:46", "remaining_time": "2:12:58", "throughput": 787.65, "total_tokens": 6747176} {"current_steps": 20715, "total_steps": 40000, "loss": 0.1692, "lr": 2.3598798935556516e-05, "epoch": 16.952108063855913, "percentage": 51.79, "elapsed_time": "2:22:47", "remaining_time": "2:12:56", "throughput": 787.7, "total_tokens": 6748888} {"current_steps": 20720, "total_steps": 40000, "loss": 0.2001, "lr": 2.3588996999164784e-05, "epoch": 16.95620139173148, "percentage": 51.8, "elapsed_time": "2:22:49", "remaining_time": "2:12:54", "throughput": 787.72, "total_tokens": 6750456} {"current_steps": 20725, "total_steps": 40000, "loss": 0.2842, "lr": 2.3579195280367434e-05, "epoch": 16.96029471960704, "percentage": 51.81, "elapsed_time": "2:22:51", "remaining_time": "2:12:51", "throughput": 787.75, "total_tokens": 6752088} {"current_steps": 20730, "total_steps": 40000, "loss": 0.2606, "lr": 2.356939378067603e-05, "epoch": 16.964388047482604, "percentage": 51.82, "elapsed_time": "2:22:53", "remaining_time": "2:12:49", "throughput": 787.78, "total_tokens": 6753704} {"current_steps": 20735, "total_steps": 40000, "loss": 0.1357, "lr": 2.3559592501602092e-05, "epoch": 16.968481375358166, "percentage": 51.84, "elapsed_time": "2:22:54", "remaining_time": "2:12:46", "throughput": 787.82, "total_tokens": 6755336} {"current_steps": 20740, "total_steps": 40000, "loss": 0.1785, "lr": 2.3549791444657076e-05, "epoch": 16.97257470323373, "percentage": 51.85, "elapsed_time": "2:22:56", "remaining_time": "2:12:44", "throughput": 787.85, "total_tokens": 6756936} {"current_steps": 20745, "total_steps": 40000, "loss": 0.1424, "lr": 2.353999061135246e-05, "epoch": 16.97666803110929, "percentage": 51.86, "elapsed_time": "2:22:58", "remaining_time": "2:12:42", "throughput": 787.89, "total_tokens": 6758648} {"current_steps": 20750, "total_steps": 40000, "loss": 0.1009, "lr": 2.3530190003199626e-05, "epoch": 16.980761358984854, "percentage": 51.88, "elapsed_time": "2:22:59", "remaining_time": "2:12:39", "throughput": 787.92, "total_tokens": 6760280} {"current_steps": 20755, "total_steps": 40000, "loss": 0.1875, "lr": 2.3520389621709965e-05, "epoch": 16.984854686860416, "percentage": 51.89, "elapsed_time": "2:23:01", "remaining_time": "2:12:37", "throughput": 787.95, "total_tokens": 6761880} {"current_steps": 20760, "total_steps": 40000, "loss": 0.1804, "lr": 2.351058946839483e-05, "epoch": 16.988948014735982, "percentage": 51.9, "elapsed_time": "2:23:03", "remaining_time": "2:12:34", "throughput": 787.97, "total_tokens": 6763432} {"current_steps": 20765, "total_steps": 40000, "loss": 0.1755, "lr": 2.350078954476551e-05, "epoch": 16.993041342611544, "percentage": 51.91, "elapsed_time": "2:23:05", "remaining_time": "2:12:32", "throughput": 788.0, "total_tokens": 6765048} {"current_steps": 20770, "total_steps": 40000, "loss": 0.1652, "lr": 2.3490989852333272e-05, "epoch": 16.997134670487107, "percentage": 51.92, "elapsed_time": "2:23:06", "remaining_time": "2:12:30", "throughput": 788.03, "total_tokens": 6766648} {"current_steps": 20775, "total_steps": 40000, "loss": 0.2887, "lr": 2.3481190392609377e-05, "epoch": 17.000818665575114, "percentage": 51.94, "elapsed_time": "2:23:08", "remaining_time": "2:12:27", "throughput": 788.02, "total_tokens": 6768016} {"current_steps": 20780, "total_steps": 40000, "loss": 0.1773, "lr": 2.3471391167105e-05, "epoch": 17.004911993450676, "percentage": 51.95, "elapsed_time": "2:23:10", "remaining_time": "2:12:25", "throughput": 788.04, "total_tokens": 6769600} {"current_steps": 20785, "total_steps": 40000, "loss": 0.2166, "lr": 2.3461592177331325e-05, "epoch": 17.00900532132624, "percentage": 51.96, "elapsed_time": "2:23:12", "remaining_time": "2:12:23", "throughput": 788.08, "total_tokens": 6771248} {"current_steps": 20790, "total_steps": 40000, "loss": 0.1408, "lr": 2.345179342479946e-05, "epoch": 17.0130986492018, "percentage": 51.98, "elapsed_time": "2:23:13", "remaining_time": "2:12:20", "throughput": 788.1, "total_tokens": 6772832} {"current_steps": 20795, "total_steps": 40000, "loss": 0.1783, "lr": 2.3441994911020503e-05, "epoch": 17.017191977077363, "percentage": 51.99, "elapsed_time": "2:23:15", "remaining_time": "2:12:18", "throughput": 788.13, "total_tokens": 6774432} {"current_steps": 20800, "total_steps": 40000, "loss": 0.204, "lr": 2.3432196637505522e-05, "epoch": 17.021285304952926, "percentage": 52.0, "elapsed_time": "2:23:17", "remaining_time": "2:12:15", "throughput": 788.18, "total_tokens": 6776176} {"current_steps": 20800, "total_steps": 40000, "eval_loss": 0.20858870446681976, "epoch": 17.021285304952926, "percentage": 52.0, "elapsed_time": "2:23:29", "remaining_time": "2:12:27", "throughput": 787.04, "total_tokens": 6776176} {"current_steps": 20805, "total_steps": 40000, "loss": 0.1281, "lr": 2.3422398605765515e-05, "epoch": 17.025378632828488, "percentage": 52.01, "elapsed_time": "2:23:32", "remaining_time": "2:12:26", "throughput": 786.93, "total_tokens": 6777792} {"current_steps": 20810, "total_steps": 40000, "loss": 0.1425, "lr": 2.3412600817311462e-05, "epoch": 17.029471960704054, "percentage": 52.02, "elapsed_time": "2:23:34", "remaining_time": "2:12:24", "throughput": 786.96, "total_tokens": 6779392} {"current_steps": 20815, "total_steps": 40000, "loss": 0.1549, "lr": 2.3402803273654326e-05, "epoch": 17.033565288579616, "percentage": 52.04, "elapsed_time": "2:23:36", "remaining_time": "2:12:21", "throughput": 786.99, "total_tokens": 6780992} {"current_steps": 20820, "total_steps": 40000, "loss": 0.1607, "lr": 2.3393005976304983e-05, "epoch": 17.03765861645518, "percentage": 52.05, "elapsed_time": "2:23:38", "remaining_time": "2:12:19", "throughput": 787.02, "total_tokens": 6782592} {"current_steps": 20825, "total_steps": 40000, "loss": 0.1921, "lr": 2.338320892677432e-05, "epoch": 17.04175194433074, "percentage": 52.06, "elapsed_time": "2:23:39", "remaining_time": "2:12:16", "throughput": 787.05, "total_tokens": 6784272} {"current_steps": 20830, "total_steps": 40000, "loss": 0.1388, "lr": 2.3373412126573155e-05, "epoch": 17.045845272206304, "percentage": 52.08, "elapsed_time": "2:23:41", "remaining_time": "2:12:14", "throughput": 787.08, "total_tokens": 6785888} {"current_steps": 20835, "total_steps": 40000, "loss": 0.188, "lr": 2.3363615577212285e-05, "epoch": 17.049938600081866, "percentage": 52.09, "elapsed_time": "2:23:43", "remaining_time": "2:12:12", "throughput": 787.12, "total_tokens": 6787504} {"current_steps": 20840, "total_steps": 40000, "loss": 0.2742, "lr": 2.3353819280202455e-05, "epoch": 17.05403192795743, "percentage": 52.1, "elapsed_time": "2:23:44", "remaining_time": "2:12:09", "throughput": 787.15, "total_tokens": 6789120} {"current_steps": 20845, "total_steps": 40000, "loss": 0.1604, "lr": 2.334402323705438e-05, "epoch": 17.05812525583299, "percentage": 52.11, "elapsed_time": "2:23:46", "remaining_time": "2:12:07", "throughput": 787.17, "total_tokens": 6790720} {"current_steps": 20850, "total_steps": 40000, "loss": 0.1903, "lr": 2.3334227449278725e-05, "epoch": 17.062218583708557, "percentage": 52.12, "elapsed_time": "2:23:48", "remaining_time": "2:12:04", "throughput": 787.2, "total_tokens": 6792320} {"current_steps": 20855, "total_steps": 40000, "loss": 0.1066, "lr": 2.3324431918386143e-05, "epoch": 17.06631191158412, "percentage": 52.14, "elapsed_time": "2:23:50", "remaining_time": "2:12:02", "throughput": 787.23, "total_tokens": 6793920} {"current_steps": 20860, "total_steps": 40000, "loss": 0.1638, "lr": 2.3314636645887207e-05, "epoch": 17.07040523945968, "percentage": 52.15, "elapsed_time": "2:23:51", "remaining_time": "2:12:00", "throughput": 787.26, "total_tokens": 6795552} {"current_steps": 20865, "total_steps": 40000, "loss": 0.1972, "lr": 2.3304841633292487e-05, "epoch": 17.074498567335244, "percentage": 52.16, "elapsed_time": "2:23:53", "remaining_time": "2:11:57", "throughput": 787.3, "total_tokens": 6797216} {"current_steps": 20870, "total_steps": 40000, "loss": 0.166, "lr": 2.329504688211248e-05, "epoch": 17.078591895210806, "percentage": 52.18, "elapsed_time": "2:23:55", "remaining_time": "2:11:55", "throughput": 787.33, "total_tokens": 6798864} {"current_steps": 20875, "total_steps": 40000, "loss": 0.2035, "lr": 2.3285252393857677e-05, "epoch": 17.08268522308637, "percentage": 52.19, "elapsed_time": "2:23:57", "remaining_time": "2:11:52", "throughput": 787.36, "total_tokens": 6800448} {"current_steps": 20880, "total_steps": 40000, "loss": 0.1982, "lr": 2.327545817003851e-05, "epoch": 17.08677855096193, "percentage": 52.2, "elapsed_time": "2:23:58", "remaining_time": "2:11:50", "throughput": 787.39, "total_tokens": 6802064} {"current_steps": 20885, "total_steps": 40000, "loss": 0.1446, "lr": 2.326566421216535e-05, "epoch": 17.090871878837493, "percentage": 52.21, "elapsed_time": "2:24:00", "remaining_time": "2:11:48", "throughput": 787.42, "total_tokens": 6803664} {"current_steps": 20890, "total_steps": 40000, "loss": 0.0963, "lr": 2.3255870521748565e-05, "epoch": 17.09496520671306, "percentage": 52.23, "elapsed_time": "2:24:02", "remaining_time": "2:11:45", "throughput": 787.45, "total_tokens": 6805264} {"current_steps": 20895, "total_steps": 40000, "loss": 0.1301, "lr": 2.3246077100298474e-05, "epoch": 17.09905853458862, "percentage": 52.24, "elapsed_time": "2:24:03", "remaining_time": "2:11:43", "throughput": 787.47, "total_tokens": 6806832} {"current_steps": 20900, "total_steps": 40000, "loss": 0.133, "lr": 2.3236283949325328e-05, "epoch": 17.103151862464184, "percentage": 52.25, "elapsed_time": "2:24:05", "remaining_time": "2:11:41", "throughput": 787.51, "total_tokens": 6808496} {"current_steps": 20905, "total_steps": 40000, "loss": 0.1902, "lr": 2.3226491070339368e-05, "epoch": 17.107245190339746, "percentage": 52.26, "elapsed_time": "2:24:07", "remaining_time": "2:11:38", "throughput": 787.54, "total_tokens": 6810112} {"current_steps": 20910, "total_steps": 40000, "loss": 0.1615, "lr": 2.3216698464850762e-05, "epoch": 17.11133851821531, "percentage": 52.28, "elapsed_time": "2:24:09", "remaining_time": "2:11:36", "throughput": 787.58, "total_tokens": 6811792} {"current_steps": 20915, "total_steps": 40000, "loss": 0.0795, "lr": 2.320690613436967e-05, "epoch": 17.11543184609087, "percentage": 52.29, "elapsed_time": "2:24:10", "remaining_time": "2:11:33", "throughput": 787.61, "total_tokens": 6813472} {"current_steps": 20920, "total_steps": 40000, "loss": 0.2346, "lr": 2.3197114080406192e-05, "epoch": 17.119525173966434, "percentage": 52.3, "elapsed_time": "2:24:12", "remaining_time": "2:11:31", "throughput": 787.65, "total_tokens": 6815168} {"current_steps": 20925, "total_steps": 40000, "loss": 0.1487, "lr": 2.3187322304470365e-05, "epoch": 17.123618501841996, "percentage": 52.31, "elapsed_time": "2:24:14", "remaining_time": "2:11:29", "throughput": 787.69, "total_tokens": 6816800} {"current_steps": 20930, "total_steps": 40000, "loss": 0.2574, "lr": 2.3177530808072222e-05, "epoch": 17.127711829717562, "percentage": 52.33, "elapsed_time": "2:24:15", "remaining_time": "2:11:26", "throughput": 787.72, "total_tokens": 6818448} {"current_steps": 20935, "total_steps": 40000, "loss": 0.1616, "lr": 2.316773959272174e-05, "epoch": 17.131805157593124, "percentage": 52.34, "elapsed_time": "2:24:17", "remaining_time": "2:11:24", "throughput": 787.76, "total_tokens": 6820176} {"current_steps": 20940, "total_steps": 40000, "loss": 0.1245, "lr": 2.3157948659928823e-05, "epoch": 17.135898485468687, "percentage": 52.35, "elapsed_time": "2:24:19", "remaining_time": "2:11:21", "throughput": 787.79, "total_tokens": 6821760} {"current_steps": 20945, "total_steps": 40000, "loss": 0.2081, "lr": 2.3148158011203388e-05, "epoch": 17.13999181334425, "percentage": 52.36, "elapsed_time": "2:24:21", "remaining_time": "2:11:19", "throughput": 787.82, "total_tokens": 6823376} {"current_steps": 20950, "total_steps": 40000, "loss": 0.1225, "lr": 2.3138367648055253e-05, "epoch": 17.14408514121981, "percentage": 52.38, "elapsed_time": "2:24:22", "remaining_time": "2:11:17", "throughput": 787.85, "total_tokens": 6824976} {"current_steps": 20955, "total_steps": 40000, "loss": 0.2013, "lr": 2.312857757199422e-05, "epoch": 17.148178469095374, "percentage": 52.39, "elapsed_time": "2:24:24", "remaining_time": "2:11:14", "throughput": 787.88, "total_tokens": 6826624} {"current_steps": 20960, "total_steps": 40000, "loss": 0.1228, "lr": 2.3118787784530048e-05, "epoch": 17.152271796970936, "percentage": 52.4, "elapsed_time": "2:24:26", "remaining_time": "2:11:12", "throughput": 787.91, "total_tokens": 6828224} {"current_steps": 20965, "total_steps": 40000, "loss": 0.1538, "lr": 2.310899828717243e-05, "epoch": 17.1563651248465, "percentage": 52.41, "elapsed_time": "2:24:27", "remaining_time": "2:11:10", "throughput": 787.94, "total_tokens": 6829808} {"current_steps": 20970, "total_steps": 40000, "loss": 0.253, "lr": 2.309920908143104e-05, "epoch": 17.160458452722064, "percentage": 52.42, "elapsed_time": "2:24:29", "remaining_time": "2:11:07", "throughput": 787.96, "total_tokens": 6831392} {"current_steps": 20975, "total_steps": 40000, "loss": 0.1516, "lr": 2.308942016881551e-05, "epoch": 17.164551780597627, "percentage": 52.44, "elapsed_time": "2:24:31", "remaining_time": "2:11:05", "throughput": 787.99, "total_tokens": 6833008} {"current_steps": 20980, "total_steps": 40000, "loss": 0.1815, "lr": 2.307963155083539e-05, "epoch": 17.16864510847319, "percentage": 52.45, "elapsed_time": "2:24:33", "remaining_time": "2:11:02", "throughput": 788.02, "total_tokens": 6834608} {"current_steps": 20985, "total_steps": 40000, "loss": 0.2752, "lr": 2.306984322900022e-05, "epoch": 17.17273843634875, "percentage": 52.46, "elapsed_time": "2:24:34", "remaining_time": "2:11:00", "throughput": 788.07, "total_tokens": 6836336} {"current_steps": 20990, "total_steps": 40000, "loss": 0.127, "lr": 2.3060055204819482e-05, "epoch": 17.176831764224314, "percentage": 52.48, "elapsed_time": "2:24:36", "remaining_time": "2:10:58", "throughput": 788.1, "total_tokens": 6837984} {"current_steps": 20995, "total_steps": 40000, "loss": 0.1267, "lr": 2.3050267479802604e-05, "epoch": 17.180925092099876, "percentage": 52.49, "elapsed_time": "2:24:38", "remaining_time": "2:10:55", "throughput": 788.12, "total_tokens": 6839552} {"current_steps": 21000, "total_steps": 40000, "loss": 0.1822, "lr": 2.304048005545899e-05, "epoch": 17.18501841997544, "percentage": 52.5, "elapsed_time": "2:24:39", "remaining_time": "2:10:53", "throughput": 788.15, "total_tokens": 6841120} {"current_steps": 21000, "total_steps": 40000, "eval_loss": 0.21111226081848145, "epoch": 17.18501841997544, "percentage": 52.5, "elapsed_time": "2:24:52", "remaining_time": "2:11:04", "throughput": 787.02, "total_tokens": 6841120} {"current_steps": 21005, "total_steps": 40000, "loss": 0.2399, "lr": 2.3030692933297972e-05, "epoch": 17.189111747851, "percentage": 52.51, "elapsed_time": "2:24:55", "remaining_time": "2:11:03", "throughput": 786.92, "total_tokens": 6842736} {"current_steps": 21010, "total_steps": 40000, "loss": 0.207, "lr": 2.3020906114828843e-05, "epoch": 17.193205075726567, "percentage": 52.52, "elapsed_time": "2:24:57", "remaining_time": "2:11:01", "throughput": 786.94, "total_tokens": 6844320} {"current_steps": 21015, "total_steps": 40000, "loss": 0.1595, "lr": 2.301111960156088e-05, "epoch": 17.19729840360213, "percentage": 52.54, "elapsed_time": "2:24:59", "remaining_time": "2:10:58", "throughput": 786.98, "total_tokens": 6846000} {"current_steps": 21020, "total_steps": 40000, "loss": 0.273, "lr": 2.300133339500326e-05, "epoch": 17.201391731477692, "percentage": 52.55, "elapsed_time": "2:25:00", "remaining_time": "2:10:56", "throughput": 787.02, "total_tokens": 6847680} {"current_steps": 21025, "total_steps": 40000, "loss": 0.1853, "lr": 2.2991547496665148e-05, "epoch": 17.205485059353254, "percentage": 52.56, "elapsed_time": "2:25:02", "remaining_time": "2:10:54", "throughput": 787.05, "total_tokens": 6849328} {"current_steps": 21030, "total_steps": 40000, "loss": 0.1982, "lr": 2.298176190805565e-05, "epoch": 17.209578387228817, "percentage": 52.58, "elapsed_time": "2:25:04", "remaining_time": "2:10:51", "throughput": 787.08, "total_tokens": 6850976} {"current_steps": 21035, "total_steps": 40000, "loss": 0.1866, "lr": 2.2971976630683826e-05, "epoch": 17.21367171510438, "percentage": 52.59, "elapsed_time": "2:25:05", "remaining_time": "2:10:49", "throughput": 787.12, "total_tokens": 6852640} {"current_steps": 21040, "total_steps": 40000, "loss": 0.2376, "lr": 2.29621916660587e-05, "epoch": 17.21776504297994, "percentage": 52.6, "elapsed_time": "2:25:07", "remaining_time": "2:10:46", "throughput": 787.15, "total_tokens": 6854240} {"current_steps": 21045, "total_steps": 40000, "loss": 0.1908, "lr": 2.295240701568922e-05, "epoch": 17.221858370855507, "percentage": 52.61, "elapsed_time": "2:25:09", "remaining_time": "2:10:44", "throughput": 787.18, "total_tokens": 6855904} {"current_steps": 21050, "total_steps": 40000, "loss": 0.164, "lr": 2.2942622681084312e-05, "epoch": 17.22595169873107, "percentage": 52.62, "elapsed_time": "2:25:11", "remaining_time": "2:10:42", "throughput": 787.22, "total_tokens": 6857536} {"current_steps": 21055, "total_steps": 40000, "loss": 0.1609, "lr": 2.293283866375284e-05, "epoch": 17.230045026606632, "percentage": 52.64, "elapsed_time": "2:25:12", "remaining_time": "2:10:39", "throughput": 787.25, "total_tokens": 6859168} {"current_steps": 21060, "total_steps": 40000, "loss": 0.1942, "lr": 2.2923054965203627e-05, "epoch": 17.234138354482194, "percentage": 52.65, "elapsed_time": "2:25:14", "remaining_time": "2:10:37", "throughput": 787.28, "total_tokens": 6860832} {"current_steps": 21065, "total_steps": 40000, "loss": 0.2768, "lr": 2.2913271586945443e-05, "epoch": 17.238231682357757, "percentage": 52.66, "elapsed_time": "2:25:16", "remaining_time": "2:10:34", "throughput": 787.32, "total_tokens": 6862464} {"current_steps": 21070, "total_steps": 40000, "loss": 0.2175, "lr": 2.290348853048699e-05, "epoch": 17.24232501023332, "percentage": 52.68, "elapsed_time": "2:25:17", "remaining_time": "2:10:32", "throughput": 787.34, "total_tokens": 6864064} {"current_steps": 21075, "total_steps": 40000, "loss": 0.1581, "lr": 2.2893705797336956e-05, "epoch": 17.24641833810888, "percentage": 52.69, "elapsed_time": "2:25:19", "remaining_time": "2:10:30", "throughput": 787.37, "total_tokens": 6865680} {"current_steps": 21080, "total_steps": 40000, "loss": 0.1684, "lr": 2.288392338900397e-05, "epoch": 17.250511665984444, "percentage": 52.7, "elapsed_time": "2:25:21", "remaining_time": "2:10:27", "throughput": 787.41, "total_tokens": 6867328} {"current_steps": 21085, "total_steps": 40000, "loss": 0.1395, "lr": 2.2874141306996576e-05, "epoch": 17.25460499386001, "percentage": 52.71, "elapsed_time": "2:25:23", "remaining_time": "2:10:25", "throughput": 787.43, "total_tokens": 6868896} {"current_steps": 21090, "total_steps": 40000, "loss": 0.1021, "lr": 2.2864359552823312e-05, "epoch": 17.258698321735572, "percentage": 52.73, "elapsed_time": "2:25:24", "remaining_time": "2:10:23", "throughput": 787.47, "total_tokens": 6870528} {"current_steps": 21095, "total_steps": 40000, "loss": 0.2244, "lr": 2.2854578127992648e-05, "epoch": 17.262791649611135, "percentage": 52.74, "elapsed_time": "2:25:26", "remaining_time": "2:10:20", "throughput": 787.5, "total_tokens": 6872160} {"current_steps": 21100, "total_steps": 40000, "loss": 0.2921, "lr": 2.2844797034012988e-05, "epoch": 17.266884977486697, "percentage": 52.75, "elapsed_time": "2:25:28", "remaining_time": "2:10:18", "throughput": 787.52, "total_tokens": 6873744} {"current_steps": 21105, "total_steps": 40000, "loss": 0.1113, "lr": 2.2835016272392722e-05, "epoch": 17.27097830536226, "percentage": 52.76, "elapsed_time": "2:25:30", "remaining_time": "2:10:15", "throughput": 787.58, "total_tokens": 6875552} {"current_steps": 21110, "total_steps": 40000, "loss": 0.1614, "lr": 2.2825235844640142e-05, "epoch": 17.275071633237822, "percentage": 52.78, "elapsed_time": "2:25:31", "remaining_time": "2:10:13", "throughput": 787.61, "total_tokens": 6877216} {"current_steps": 21115, "total_steps": 40000, "loss": 0.1633, "lr": 2.2815455752263522e-05, "epoch": 17.279164961113384, "percentage": 52.79, "elapsed_time": "2:25:33", "remaining_time": "2:10:11", "throughput": 787.64, "total_tokens": 6878784} {"current_steps": 21120, "total_steps": 40000, "loss": 0.164, "lr": 2.2805675996771092e-05, "epoch": 17.283258288988947, "percentage": 52.8, "elapsed_time": "2:25:35", "remaining_time": "2:10:08", "throughput": 787.67, "total_tokens": 6880400} {"current_steps": 21125, "total_steps": 40000, "loss": 0.1689, "lr": 2.2795896579670987e-05, "epoch": 17.287351616864512, "percentage": 52.81, "elapsed_time": "2:25:36", "remaining_time": "2:10:06", "throughput": 787.71, "total_tokens": 6882112} {"current_steps": 21130, "total_steps": 40000, "loss": 0.1887, "lr": 2.2786117502471337e-05, "epoch": 17.291444944740075, "percentage": 52.83, "elapsed_time": "2:25:38", "remaining_time": "2:10:03", "throughput": 787.74, "total_tokens": 6883760} {"current_steps": 21135, "total_steps": 40000, "loss": 0.2548, "lr": 2.2776338766680185e-05, "epoch": 17.295538272615637, "percentage": 52.84, "elapsed_time": "2:25:40", "remaining_time": "2:10:01", "throughput": 787.77, "total_tokens": 6885392} {"current_steps": 21140, "total_steps": 40000, "loss": 0.1642, "lr": 2.2766560373805533e-05, "epoch": 17.2996316004912, "percentage": 52.85, "elapsed_time": "2:25:42", "remaining_time": "2:09:59", "throughput": 787.81, "total_tokens": 6887024} {"current_steps": 21145, "total_steps": 40000, "loss": 0.2121, "lr": 2.2756782325355353e-05, "epoch": 17.303724928366762, "percentage": 52.86, "elapsed_time": "2:25:43", "remaining_time": "2:09:56", "throughput": 787.84, "total_tokens": 6888656} {"current_steps": 21150, "total_steps": 40000, "loss": 0.1655, "lr": 2.2747004622837514e-05, "epoch": 17.307818256242324, "percentage": 52.88, "elapsed_time": "2:25:45", "remaining_time": "2:09:54", "throughput": 787.86, "total_tokens": 6890240} {"current_steps": 21155, "total_steps": 40000, "loss": 0.2047, "lr": 2.2737227267759878e-05, "epoch": 17.311911584117887, "percentage": 52.89, "elapsed_time": "2:25:47", "remaining_time": "2:09:52", "throughput": 787.9, "total_tokens": 6891952} {"current_steps": 21160, "total_steps": 40000, "loss": 0.3014, "lr": 2.272745026163024e-05, "epoch": 17.31600491199345, "percentage": 52.9, "elapsed_time": "2:25:48", "remaining_time": "2:09:49", "throughput": 787.93, "total_tokens": 6893520} {"current_steps": 21165, "total_steps": 40000, "loss": 0.1313, "lr": 2.271767360595633e-05, "epoch": 17.320098239869015, "percentage": 52.91, "elapsed_time": "2:25:50", "remaining_time": "2:09:47", "throughput": 787.96, "total_tokens": 6895168} {"current_steps": 21170, "total_steps": 40000, "loss": 0.1231, "lr": 2.270789730224583e-05, "epoch": 17.324191567744577, "percentage": 52.92, "elapsed_time": "2:25:52", "remaining_time": "2:09:44", "throughput": 787.99, "total_tokens": 6896784} {"current_steps": 21175, "total_steps": 40000, "loss": 0.171, "lr": 2.2698121352006367e-05, "epoch": 17.32828489562014, "percentage": 52.94, "elapsed_time": "2:25:54", "remaining_time": "2:09:42", "throughput": 788.02, "total_tokens": 6898384} {"current_steps": 21180, "total_steps": 40000, "loss": 0.2258, "lr": 2.2688345756745517e-05, "epoch": 17.332378223495702, "percentage": 52.95, "elapsed_time": "2:25:55", "remaining_time": "2:09:40", "throughput": 788.05, "total_tokens": 6900000} {"current_steps": 21185, "total_steps": 40000, "loss": 0.1493, "lr": 2.267857051797081e-05, "epoch": 17.336471551371265, "percentage": 52.96, "elapsed_time": "2:25:57", "remaining_time": "2:09:37", "throughput": 788.09, "total_tokens": 6901664} {"current_steps": 21190, "total_steps": 40000, "loss": 0.1901, "lr": 2.2668795637189695e-05, "epoch": 17.340564879246827, "percentage": 52.98, "elapsed_time": "2:25:59", "remaining_time": "2:09:35", "throughput": 788.11, "total_tokens": 6903248} {"current_steps": 21195, "total_steps": 40000, "loss": 0.2105, "lr": 2.2659021115909586e-05, "epoch": 17.34465820712239, "percentage": 52.99, "elapsed_time": "2:26:00", "remaining_time": "2:09:33", "throughput": 788.15, "total_tokens": 6904928} {"current_steps": 21200, "total_steps": 40000, "loss": 0.221, "lr": 2.2649246955637847e-05, "epoch": 17.34875153499795, "percentage": 53.0, "elapsed_time": "2:26:02", "remaining_time": "2:09:30", "throughput": 788.18, "total_tokens": 6906528} {"current_steps": 21200, "total_steps": 40000, "eval_loss": 0.2141224890947342, "epoch": 17.34875153499795, "percentage": 53.0, "elapsed_time": "2:26:15", "remaining_time": "2:09:41", "throughput": 787.06, "total_tokens": 6906528} {"current_steps": 21205, "total_steps": 40000, "loss": 0.1578, "lr": 2.2639473157881766e-05, "epoch": 17.352844862873518, "percentage": 53.01, "elapsed_time": "2:26:18", "remaining_time": "2:09:40", "throughput": 786.95, "total_tokens": 6908176} {"current_steps": 21210, "total_steps": 40000, "loss": 0.1866, "lr": 2.2629699724148594e-05, "epoch": 17.35693819074908, "percentage": 53.02, "elapsed_time": "2:26:20", "remaining_time": "2:09:38", "throughput": 786.99, "total_tokens": 6909824} {"current_steps": 21215, "total_steps": 40000, "loss": 0.1446, "lr": 2.26199266559455e-05, "epoch": 17.361031518624642, "percentage": 53.04, "elapsed_time": "2:26:21", "remaining_time": "2:09:35", "throughput": 787.02, "total_tokens": 6911440} {"current_steps": 21220, "total_steps": 40000, "loss": 0.2758, "lr": 2.2610153954779625e-05, "epoch": 17.365124846500205, "percentage": 53.05, "elapsed_time": "2:26:23", "remaining_time": "2:09:33", "throughput": 787.05, "total_tokens": 6913056} {"current_steps": 21225, "total_steps": 40000, "loss": 0.189, "lr": 2.2600381622158056e-05, "epoch": 17.369218174375767, "percentage": 53.06, "elapsed_time": "2:26:25", "remaining_time": "2:09:31", "throughput": 787.07, "total_tokens": 6914640} {"current_steps": 21230, "total_steps": 40000, "loss": 0.1686, "lr": 2.2590609659587783e-05, "epoch": 17.37331150225133, "percentage": 53.08, "elapsed_time": "2:26:26", "remaining_time": "2:09:28", "throughput": 787.11, "total_tokens": 6916304} {"current_steps": 21235, "total_steps": 40000, "loss": 0.0815, "lr": 2.2580838068575787e-05, "epoch": 17.377404830126892, "percentage": 53.09, "elapsed_time": "2:26:28", "remaining_time": "2:09:26", "throughput": 787.13, "total_tokens": 6917872} {"current_steps": 21240, "total_steps": 40000, "loss": 0.1202, "lr": 2.257106685062896e-05, "epoch": 17.381498158002454, "percentage": 53.1, "elapsed_time": "2:26:30", "remaining_time": "2:09:24", "throughput": 787.17, "total_tokens": 6919552} {"current_steps": 21245, "total_steps": 40000, "loss": 0.2616, "lr": 2.256129600725415e-05, "epoch": 17.38559148587802, "percentage": 53.11, "elapsed_time": "2:26:32", "remaining_time": "2:09:21", "throughput": 787.2, "total_tokens": 6921136} {"current_steps": 21250, "total_steps": 40000, "loss": 0.1542, "lr": 2.2551525539958145e-05, "epoch": 17.389684813753583, "percentage": 53.12, "elapsed_time": "2:26:33", "remaining_time": "2:09:19", "throughput": 787.22, "total_tokens": 6922688} {"current_steps": 21255, "total_steps": 40000, "loss": 0.1681, "lr": 2.2541755450247663e-05, "epoch": 17.393778141629145, "percentage": 53.14, "elapsed_time": "2:26:35", "remaining_time": "2:09:16", "throughput": 787.25, "total_tokens": 6924272} {"current_steps": 21260, "total_steps": 40000, "loss": 0.2236, "lr": 2.2531985739629382e-05, "epoch": 17.397871469504707, "percentage": 53.15, "elapsed_time": "2:26:37", "remaining_time": "2:09:14", "throughput": 787.28, "total_tokens": 6925888} {"current_steps": 21265, "total_steps": 40000, "loss": 0.1701, "lr": 2.2522216409609924e-05, "epoch": 17.40196479738027, "percentage": 53.16, "elapsed_time": "2:26:38", "remaining_time": "2:09:12", "throughput": 787.31, "total_tokens": 6927536} {"current_steps": 21270, "total_steps": 40000, "loss": 0.1191, "lr": 2.2512447461695826e-05, "epoch": 17.406058125255832, "percentage": 53.17, "elapsed_time": "2:26:40", "remaining_time": "2:09:09", "throughput": 787.35, "total_tokens": 6929200} {"current_steps": 21275, "total_steps": 40000, "loss": 0.2246, "lr": 2.2502678897393593e-05, "epoch": 17.410151453131395, "percentage": 53.19, "elapsed_time": "2:26:42", "remaining_time": "2:09:07", "throughput": 787.38, "total_tokens": 6930816} {"current_steps": 21280, "total_steps": 40000, "loss": 0.2156, "lr": 2.2492910718209665e-05, "epoch": 17.414244781006957, "percentage": 53.2, "elapsed_time": "2:26:44", "remaining_time": "2:09:04", "throughput": 787.4, "total_tokens": 6932416} {"current_steps": 21285, "total_steps": 40000, "loss": 0.1661, "lr": 2.2483142925650398e-05, "epoch": 17.418338108882523, "percentage": 53.21, "elapsed_time": "2:26:45", "remaining_time": "2:09:02", "throughput": 787.43, "total_tokens": 6934016} {"current_steps": 21290, "total_steps": 40000, "loss": 0.2164, "lr": 2.247337552122213e-05, "epoch": 17.422431436758085, "percentage": 53.23, "elapsed_time": "2:26:47", "remaining_time": "2:09:00", "throughput": 787.46, "total_tokens": 6935664} {"current_steps": 21295, "total_steps": 40000, "loss": 0.1574, "lr": 2.24636085064311e-05, "epoch": 17.426524764633648, "percentage": 53.24, "elapsed_time": "2:26:49", "remaining_time": "2:08:57", "throughput": 787.5, "total_tokens": 6937312} {"current_steps": 21300, "total_steps": 40000, "loss": 0.176, "lr": 2.245384188278351e-05, "epoch": 17.43061809250921, "percentage": 53.25, "elapsed_time": "2:26:51", "remaining_time": "2:08:55", "throughput": 787.53, "total_tokens": 6938960} {"current_steps": 21305, "total_steps": 40000, "loss": 0.2217, "lr": 2.2444075651785513e-05, "epoch": 17.434711420384772, "percentage": 53.26, "elapsed_time": "2:26:52", "remaining_time": "2:08:53", "throughput": 787.56, "total_tokens": 6940608} {"current_steps": 21310, "total_steps": 40000, "loss": 0.2552, "lr": 2.243430981494316e-05, "epoch": 17.438804748260335, "percentage": 53.27, "elapsed_time": "2:26:54", "remaining_time": "2:08:50", "throughput": 787.59, "total_tokens": 6942224} {"current_steps": 21315, "total_steps": 40000, "loss": 0.2052, "lr": 2.2424544373762475e-05, "epoch": 17.442898076135897, "percentage": 53.29, "elapsed_time": "2:26:56", "remaining_time": "2:08:48", "throughput": 787.62, "total_tokens": 6943840} {"current_steps": 21320, "total_steps": 40000, "loss": 0.1901, "lr": 2.2414779329749418e-05, "epoch": 17.446991404011463, "percentage": 53.3, "elapsed_time": "2:26:57", "remaining_time": "2:08:46", "throughput": 787.65, "total_tokens": 6945440} {"current_steps": 21325, "total_steps": 40000, "loss": 0.2775, "lr": 2.2405014684409873e-05, "epoch": 17.451084731887025, "percentage": 53.31, "elapsed_time": "2:26:59", "remaining_time": "2:08:43", "throughput": 787.68, "total_tokens": 6947040} {"current_steps": 21330, "total_steps": 40000, "loss": 0.1899, "lr": 2.239525043924968e-05, "epoch": 17.455178059762588, "percentage": 53.33, "elapsed_time": "2:27:01", "remaining_time": "2:08:41", "throughput": 787.71, "total_tokens": 6948672} {"current_steps": 21335, "total_steps": 40000, "loss": 0.1481, "lr": 2.2385486595774592e-05, "epoch": 17.45927138763815, "percentage": 53.34, "elapsed_time": "2:27:03", "remaining_time": "2:08:38", "throughput": 787.74, "total_tokens": 6950272} {"current_steps": 21340, "total_steps": 40000, "loss": 0.2154, "lr": 2.237572315549033e-05, "epoch": 17.463364715513713, "percentage": 53.35, "elapsed_time": "2:27:04", "remaining_time": "2:08:36", "throughput": 787.77, "total_tokens": 6951920} {"current_steps": 21345, "total_steps": 40000, "loss": 0.144, "lr": 2.2365960119902545e-05, "epoch": 17.467458043389275, "percentage": 53.36, "elapsed_time": "2:27:06", "remaining_time": "2:08:34", "throughput": 787.79, "total_tokens": 6953456} {"current_steps": 21350, "total_steps": 40000, "loss": 0.2108, "lr": 2.2356197490516806e-05, "epoch": 17.471551371264837, "percentage": 53.37, "elapsed_time": "2:27:08", "remaining_time": "2:08:31", "throughput": 787.82, "total_tokens": 6955088} {"current_steps": 21355, "total_steps": 40000, "loss": 0.1243, "lr": 2.234643526883863e-05, "epoch": 17.4756446991404, "percentage": 53.39, "elapsed_time": "2:27:09", "remaining_time": "2:08:29", "throughput": 787.84, "total_tokens": 6956624} {"current_steps": 21360, "total_steps": 40000, "loss": 0.2496, "lr": 2.2336673456373497e-05, "epoch": 17.479738027015966, "percentage": 53.4, "elapsed_time": "2:27:11", "remaining_time": "2:08:27", "throughput": 787.88, "total_tokens": 6958288} {"current_steps": 21365, "total_steps": 40000, "loss": 0.1907, "lr": 2.2326912054626772e-05, "epoch": 17.483831354891528, "percentage": 53.41, "elapsed_time": "2:27:13", "remaining_time": "2:08:24", "throughput": 787.91, "total_tokens": 6959888} {"current_steps": 21370, "total_steps": 40000, "loss": 0.1822, "lr": 2.2317151065103813e-05, "epoch": 17.48792468276709, "percentage": 53.42, "elapsed_time": "2:27:15", "remaining_time": "2:08:22", "throughput": 787.94, "total_tokens": 6961536} {"current_steps": 21375, "total_steps": 40000, "loss": 0.1617, "lr": 2.2307390489309865e-05, "epoch": 17.492018010642653, "percentage": 53.44, "elapsed_time": "2:27:16", "remaining_time": "2:08:19", "throughput": 787.98, "total_tokens": 6963232} {"current_steps": 21380, "total_steps": 40000, "loss": 0.2832, "lr": 2.2297630328750146e-05, "epoch": 17.496111338518215, "percentage": 53.45, "elapsed_time": "2:27:18", "remaining_time": "2:08:17", "throughput": 788.02, "total_tokens": 6964912} {"current_steps": 21385, "total_steps": 40000, "loss": 0.1562, "lr": 2.228787058492979e-05, "epoch": 17.500204666393778, "percentage": 53.46, "elapsed_time": "2:27:20", "remaining_time": "2:08:15", "throughput": 788.05, "total_tokens": 6966528} {"current_steps": 21390, "total_steps": 40000, "loss": 0.1442, "lr": 2.2278111259353875e-05, "epoch": 17.50429799426934, "percentage": 53.47, "elapsed_time": "2:27:21", "remaining_time": "2:08:12", "throughput": 788.08, "total_tokens": 6968192} {"current_steps": 21395, "total_steps": 40000, "loss": 0.1248, "lr": 2.2268352353527395e-05, "epoch": 17.508391322144902, "percentage": 53.49, "elapsed_time": "2:27:23", "remaining_time": "2:08:10", "throughput": 788.12, "total_tokens": 6969840} {"current_steps": 21400, "total_steps": 40000, "loss": 0.2017, "lr": 2.225859386895533e-05, "epoch": 17.51248465002047, "percentage": 53.5, "elapsed_time": "2:27:25", "remaining_time": "2:08:08", "throughput": 788.16, "total_tokens": 6971568} {"current_steps": 21400, "total_steps": 40000, "eval_loss": 0.2066720724105835, "epoch": 17.51248465002047, "percentage": 53.5, "elapsed_time": "2:27:37", "remaining_time": "2:08:18", "throughput": 787.05, "total_tokens": 6971568} {"current_steps": 21405, "total_steps": 40000, "loss": 0.1658, "lr": 2.2248835807142525e-05, "epoch": 17.51657797789603, "percentage": 53.51, "elapsed_time": "2:27:41", "remaining_time": "2:08:18", "throughput": 786.93, "total_tokens": 6973200} {"current_steps": 21410, "total_steps": 40000, "loss": 0.2081, "lr": 2.2239078169593826e-05, "epoch": 17.520671305771593, "percentage": 53.52, "elapsed_time": "2:27:43", "remaining_time": "2:08:15", "throughput": 786.96, "total_tokens": 6974832} {"current_steps": 21415, "total_steps": 40000, "loss": 0.2173, "lr": 2.222932095781396e-05, "epoch": 17.524764633647155, "percentage": 53.54, "elapsed_time": "2:27:44", "remaining_time": "2:08:13", "throughput": 786.99, "total_tokens": 6976448} {"current_steps": 21420, "total_steps": 40000, "loss": 0.1954, "lr": 2.221956417330762e-05, "epoch": 17.528857961522718, "percentage": 53.55, "elapsed_time": "2:27:46", "remaining_time": "2:08:10", "throughput": 787.02, "total_tokens": 6978048} {"current_steps": 21425, "total_steps": 40000, "loss": 0.1331, "lr": 2.2209807817579438e-05, "epoch": 17.53295128939828, "percentage": 53.56, "elapsed_time": "2:27:48", "remaining_time": "2:08:08", "throughput": 787.05, "total_tokens": 6979680} {"current_steps": 21430, "total_steps": 40000, "loss": 0.187, "lr": 2.220005189213394e-05, "epoch": 17.537044617273843, "percentage": 53.57, "elapsed_time": "2:27:49", "remaining_time": "2:08:06", "throughput": 787.08, "total_tokens": 6981280} {"current_steps": 21435, "total_steps": 40000, "loss": 0.2728, "lr": 2.2190296398475624e-05, "epoch": 17.541137945149405, "percentage": 53.59, "elapsed_time": "2:27:51", "remaining_time": "2:08:03", "throughput": 787.11, "total_tokens": 6982944} {"current_steps": 21440, "total_steps": 40000, "loss": 0.1445, "lr": 2.2180541338108926e-05, "epoch": 17.54523127302497, "percentage": 53.6, "elapsed_time": "2:27:53", "remaining_time": "2:08:01", "throughput": 787.15, "total_tokens": 6984608} {"current_steps": 21445, "total_steps": 40000, "loss": 0.1853, "lr": 2.2170786712538176e-05, "epoch": 17.549324600900533, "percentage": 53.61, "elapsed_time": "2:27:55", "remaining_time": "2:07:58", "throughput": 787.19, "total_tokens": 6986288} {"current_steps": 21450, "total_steps": 40000, "loss": 0.1703, "lr": 2.216103252326768e-05, "epoch": 17.553417928776096, "percentage": 53.62, "elapsed_time": "2:27:56", "remaining_time": "2:07:56", "throughput": 787.21, "total_tokens": 6987872} {"current_steps": 21455, "total_steps": 40000, "loss": 0.1971, "lr": 2.2151278771801635e-05, "epoch": 17.557511256651658, "percentage": 53.64, "elapsed_time": "2:27:58", "remaining_time": "2:07:54", "throughput": 787.24, "total_tokens": 6989504} {"current_steps": 21460, "total_steps": 40000, "loss": 0.1484, "lr": 2.21415254596442e-05, "epoch": 17.56160458452722, "percentage": 53.65, "elapsed_time": "2:28:00", "remaining_time": "2:07:51", "throughput": 787.27, "total_tokens": 6991136} {"current_steps": 21465, "total_steps": 40000, "loss": 0.127, "lr": 2.213177258829947e-05, "epoch": 17.565697912402783, "percentage": 53.66, "elapsed_time": "2:28:01", "remaining_time": "2:07:49", "throughput": 787.31, "total_tokens": 6992784} {"current_steps": 21470, "total_steps": 40000, "loss": 0.1806, "lr": 2.2122020159271445e-05, "epoch": 17.569791240278345, "percentage": 53.67, "elapsed_time": "2:28:03", "remaining_time": "2:07:47", "throughput": 787.34, "total_tokens": 6994464} {"current_steps": 21475, "total_steps": 40000, "loss": 0.1273, "lr": 2.2112268174064075e-05, "epoch": 17.573884568153908, "percentage": 53.69, "elapsed_time": "2:28:05", "remaining_time": "2:07:44", "throughput": 787.39, "total_tokens": 6996192} {"current_steps": 21480, "total_steps": 40000, "loss": 0.2185, "lr": 2.2102516634181253e-05, "epoch": 17.577977896029473, "percentage": 53.7, "elapsed_time": "2:28:07", "remaining_time": "2:07:42", "throughput": 787.42, "total_tokens": 6997824} {"current_steps": 21485, "total_steps": 40000, "loss": 0.1901, "lr": 2.209276554112677e-05, "epoch": 17.582071223905036, "percentage": 53.71, "elapsed_time": "2:28:08", "remaining_time": "2:07:40", "throughput": 787.45, "total_tokens": 6999440} {"current_steps": 21490, "total_steps": 40000, "loss": 0.2036, "lr": 2.2083014896404384e-05, "epoch": 17.5861645517806, "percentage": 53.73, "elapsed_time": "2:28:10", "remaining_time": "2:07:37", "throughput": 787.48, "total_tokens": 7001072} {"current_steps": 21495, "total_steps": 40000, "loss": 0.1983, "lr": 2.207326470151775e-05, "epoch": 17.59025787965616, "percentage": 53.74, "elapsed_time": "2:28:12", "remaining_time": "2:07:35", "throughput": 787.51, "total_tokens": 7002672} {"current_steps": 21500, "total_steps": 40000, "loss": 0.2025, "lr": 2.2063514957970477e-05, "epoch": 17.594351207531723, "percentage": 53.75, "elapsed_time": "2:28:13", "remaining_time": "2:07:32", "throughput": 787.54, "total_tokens": 7004272} {"current_steps": 21505, "total_steps": 40000, "loss": 0.2024, "lr": 2.205376566726611e-05, "epoch": 17.598444535407285, "percentage": 53.76, "elapsed_time": "2:28:15", "remaining_time": "2:07:30", "throughput": 787.56, "total_tokens": 7005808} {"current_steps": 21510, "total_steps": 40000, "loss": 0.1954, "lr": 2.204401683090809e-05, "epoch": 17.602537863282848, "percentage": 53.77, "elapsed_time": "2:28:17", "remaining_time": "2:07:28", "throughput": 787.58, "total_tokens": 7007408} {"current_steps": 21515, "total_steps": 40000, "loss": 0.2329, "lr": 2.203426845039982e-05, "epoch": 17.60663119115841, "percentage": 53.79, "elapsed_time": "2:28:19", "remaining_time": "2:07:25", "throughput": 787.62, "total_tokens": 7009104} {"current_steps": 21520, "total_steps": 40000, "loss": 0.1177, "lr": 2.202452052724464e-05, "epoch": 17.610724519033976, "percentage": 53.8, "elapsed_time": "2:28:20", "remaining_time": "2:07:23", "throughput": 787.65, "total_tokens": 7010720} {"current_steps": 21525, "total_steps": 40000, "loss": 0.2288, "lr": 2.2014773062945777e-05, "epoch": 17.61481784690954, "percentage": 53.81, "elapsed_time": "2:28:22", "remaining_time": "2:07:21", "throughput": 787.68, "total_tokens": 7012352} {"current_steps": 21530, "total_steps": 40000, "loss": 0.1761, "lr": 2.2005026059006427e-05, "epoch": 17.6189111747851, "percentage": 53.83, "elapsed_time": "2:28:24", "remaining_time": "2:07:18", "throughput": 787.71, "total_tokens": 7013904} {"current_steps": 21535, "total_steps": 40000, "loss": 0.1876, "lr": 2.1995279516929695e-05, "epoch": 17.623004502660663, "percentage": 53.84, "elapsed_time": "2:28:25", "remaining_time": "2:07:16", "throughput": 787.74, "total_tokens": 7015520} {"current_steps": 21540, "total_steps": 40000, "loss": 0.2119, "lr": 2.1985533438218613e-05, "epoch": 17.627097830536226, "percentage": 53.85, "elapsed_time": "2:28:27", "remaining_time": "2:07:13", "throughput": 787.76, "total_tokens": 7017120} {"current_steps": 21545, "total_steps": 40000, "loss": 0.1227, "lr": 2.197578782437617e-05, "epoch": 17.631191158411788, "percentage": 53.86, "elapsed_time": "2:28:29", "remaining_time": "2:07:11", "throughput": 787.8, "total_tokens": 7018752} {"current_steps": 21550, "total_steps": 40000, "loss": 0.1816, "lr": 2.196604267690524e-05, "epoch": 17.63528448628735, "percentage": 53.87, "elapsed_time": "2:28:31", "remaining_time": "2:07:09", "throughput": 787.83, "total_tokens": 7020400} {"current_steps": 21555, "total_steps": 40000, "loss": 0.2196, "lr": 2.195629799730865e-05, "epoch": 17.639377814162913, "percentage": 53.89, "elapsed_time": "2:28:32", "remaining_time": "2:07:06", "throughput": 787.86, "total_tokens": 7022064} {"current_steps": 21560, "total_steps": 40000, "loss": 0.0913, "lr": 2.1946553787089173e-05, "epoch": 17.64347114203848, "percentage": 53.9, "elapsed_time": "2:28:34", "remaining_time": "2:07:04", "throughput": 787.9, "total_tokens": 7023728} {"current_steps": 21565, "total_steps": 40000, "loss": 0.1364, "lr": 2.193681004774947e-05, "epoch": 17.64756446991404, "percentage": 53.91, "elapsed_time": "2:28:36", "remaining_time": "2:07:02", "throughput": 787.92, "total_tokens": 7025280} {"current_steps": 21570, "total_steps": 40000, "loss": 0.0845, "lr": 2.1927066780792154e-05, "epoch": 17.651657797789603, "percentage": 53.92, "elapsed_time": "2:28:37", "remaining_time": "2:06:59", "throughput": 787.96, "total_tokens": 7026976} {"current_steps": 21575, "total_steps": 40000, "loss": 0.161, "lr": 2.191732398771975e-05, "epoch": 17.655751125665166, "percentage": 53.94, "elapsed_time": "2:28:39", "remaining_time": "2:06:57", "throughput": 788.0, "total_tokens": 7028656} {"current_steps": 21580, "total_steps": 40000, "loss": 0.1628, "lr": 2.1907581670034725e-05, "epoch": 17.659844453540728, "percentage": 53.95, "elapsed_time": "2:28:41", "remaining_time": "2:06:54", "throughput": 788.03, "total_tokens": 7030304} {"current_steps": 21585, "total_steps": 40000, "loss": 0.2224, "lr": 2.189783982923948e-05, "epoch": 17.66393778141629, "percentage": 53.96, "elapsed_time": "2:28:43", "remaining_time": "2:06:52", "throughput": 788.06, "total_tokens": 7031952} {"current_steps": 21590, "total_steps": 40000, "loss": 0.116, "lr": 2.1888098466836303e-05, "epoch": 17.668031109291853, "percentage": 53.97, "elapsed_time": "2:28:44", "remaining_time": "2:06:50", "throughput": 788.1, "total_tokens": 7033616} {"current_steps": 21595, "total_steps": 40000, "loss": 0.1649, "lr": 2.1878357584327457e-05, "epoch": 17.67212443716742, "percentage": 53.99, "elapsed_time": "2:28:46", "remaining_time": "2:06:47", "throughput": 788.13, "total_tokens": 7035216} {"current_steps": 21600, "total_steps": 40000, "loss": 0.1142, "lr": 2.1868617183215103e-05, "epoch": 17.67621776504298, "percentage": 54.0, "elapsed_time": "2:28:48", "remaining_time": "2:06:45", "throughput": 788.16, "total_tokens": 7036832} {"current_steps": 21600, "total_steps": 40000, "eval_loss": 0.206340029835701, "epoch": 17.67621776504298, "percentage": 54.0, "elapsed_time": "2:29:00", "remaining_time": "2:06:56", "throughput": 787.06, "total_tokens": 7036832} {"current_steps": 21605, "total_steps": 40000, "loss": 0.1386, "lr": 2.1858877265001327e-05, "epoch": 17.680311092918544, "percentage": 54.01, "elapsed_time": "2:29:04", "remaining_time": "2:06:55", "throughput": 786.91, "total_tokens": 7038448} {"current_steps": 21610, "total_steps": 40000, "loss": 0.204, "lr": 2.184913783118816e-05, "epoch": 17.684404420794106, "percentage": 54.02, "elapsed_time": "2:29:06", "remaining_time": "2:06:53", "throughput": 786.95, "total_tokens": 7040128} {"current_steps": 21615, "total_steps": 40000, "loss": 0.1166, "lr": 2.1839398883277522e-05, "epoch": 17.68849774866967, "percentage": 54.04, "elapsed_time": "2:29:07", "remaining_time": "2:06:50", "throughput": 786.98, "total_tokens": 7041760} {"current_steps": 21620, "total_steps": 40000, "loss": 0.1106, "lr": 2.182966042277129e-05, "epoch": 17.69259107654523, "percentage": 54.05, "elapsed_time": "2:29:09", "remaining_time": "2:06:48", "throughput": 787.01, "total_tokens": 7043424} {"current_steps": 21625, "total_steps": 40000, "loss": 0.2012, "lr": 2.181992245117128e-05, "epoch": 17.696684404420793, "percentage": 54.06, "elapsed_time": "2:29:11", "remaining_time": "2:06:46", "throughput": 787.04, "total_tokens": 7045056} {"current_steps": 21630, "total_steps": 40000, "loss": 0.2062, "lr": 2.181018496997918e-05, "epoch": 17.700777732296356, "percentage": 54.07, "elapsed_time": "2:29:13", "remaining_time": "2:06:43", "throughput": 787.08, "total_tokens": 7046720} {"current_steps": 21635, "total_steps": 40000, "loss": 0.162, "lr": 2.1800447980696648e-05, "epoch": 17.70487106017192, "percentage": 54.09, "elapsed_time": "2:29:14", "remaining_time": "2:06:41", "throughput": 787.11, "total_tokens": 7048320} {"current_steps": 21640, "total_steps": 40000, "loss": 0.1851, "lr": 2.1790711484825248e-05, "epoch": 17.708964388047484, "percentage": 54.1, "elapsed_time": "2:29:16", "remaining_time": "2:06:38", "throughput": 787.14, "total_tokens": 7049968} {"current_steps": 21645, "total_steps": 40000, "loss": 0.1888, "lr": 2.178097548386646e-05, "epoch": 17.713057715923046, "percentage": 54.11, "elapsed_time": "2:29:18", "remaining_time": "2:06:36", "throughput": 787.17, "total_tokens": 7051584} {"current_steps": 21650, "total_steps": 40000, "loss": 0.1887, "lr": 2.1771239979321712e-05, "epoch": 17.71715104379861, "percentage": 54.12, "elapsed_time": "2:29:19", "remaining_time": "2:06:34", "throughput": 787.2, "total_tokens": 7053200} {"current_steps": 21655, "total_steps": 40000, "loss": 0.1681, "lr": 2.1761504972692327e-05, "epoch": 17.72124437167417, "percentage": 54.14, "elapsed_time": "2:29:21", "remaining_time": "2:06:31", "throughput": 787.24, "total_tokens": 7054880} {"current_steps": 21660, "total_steps": 40000, "loss": 0.2845, "lr": 2.1751770465479572e-05, "epoch": 17.725337699549733, "percentage": 54.15, "elapsed_time": "2:29:23", "remaining_time": "2:06:29", "throughput": 787.27, "total_tokens": 7056528} {"current_steps": 21665, "total_steps": 40000, "loss": 0.1771, "lr": 2.174203645918464e-05, "epoch": 17.729431027425296, "percentage": 54.16, "elapsed_time": "2:29:25", "remaining_time": "2:06:27", "throughput": 787.3, "total_tokens": 7058176} {"current_steps": 21670, "total_steps": 40000, "loss": 0.1687, "lr": 2.1732302955308624e-05, "epoch": 17.733524355300858, "percentage": 54.17, "elapsed_time": "2:29:26", "remaining_time": "2:06:24", "throughput": 787.33, "total_tokens": 7059776} {"current_steps": 21675, "total_steps": 40000, "loss": 0.1717, "lr": 2.172256995535255e-05, "epoch": 17.737617683176424, "percentage": 54.19, "elapsed_time": "2:29:28", "remaining_time": "2:06:22", "throughput": 787.36, "total_tokens": 7061376} {"current_steps": 21680, "total_steps": 40000, "loss": 0.1095, "lr": 2.171283746081739e-05, "epoch": 17.741711011051986, "percentage": 54.2, "elapsed_time": "2:29:30", "remaining_time": "2:06:19", "throughput": 787.38, "total_tokens": 7062960} {"current_steps": 21685, "total_steps": 40000, "loss": 0.1488, "lr": 2.1703105473203988e-05, "epoch": 17.74580433892755, "percentage": 54.21, "elapsed_time": "2:29:31", "remaining_time": "2:06:17", "throughput": 787.41, "total_tokens": 7064576} {"current_steps": 21690, "total_steps": 40000, "loss": 0.1027, "lr": 2.1693373994013168e-05, "epoch": 17.74989766680311, "percentage": 54.23, "elapsed_time": "2:29:33", "remaining_time": "2:06:15", "throughput": 787.44, "total_tokens": 7066192} {"current_steps": 21695, "total_steps": 40000, "loss": 0.1773, "lr": 2.168364302474562e-05, "epoch": 17.753990994678674, "percentage": 54.24, "elapsed_time": "2:29:35", "remaining_time": "2:06:12", "throughput": 787.47, "total_tokens": 7067760} {"current_steps": 21700, "total_steps": 40000, "loss": 0.221, "lr": 2.167391256690199e-05, "epoch": 17.758084322554236, "percentage": 54.25, "elapsed_time": "2:29:37", "remaining_time": "2:06:10", "throughput": 787.5, "total_tokens": 7069408} {"current_steps": 21705, "total_steps": 40000, "loss": 0.2512, "lr": 2.1664182621982855e-05, "epoch": 17.7621776504298, "percentage": 54.26, "elapsed_time": "2:29:38", "remaining_time": "2:06:08", "throughput": 787.55, "total_tokens": 7071200} {"current_steps": 21710, "total_steps": 40000, "loss": 0.2782, "lr": 2.1654453191488673e-05, "epoch": 17.76627097830536, "percentage": 54.27, "elapsed_time": "2:29:40", "remaining_time": "2:06:05", "throughput": 787.59, "total_tokens": 7072960} {"current_steps": 21715, "total_steps": 40000, "loss": 0.1998, "lr": 2.1644724276919846e-05, "epoch": 17.770364306180927, "percentage": 54.29, "elapsed_time": "2:29:42", "remaining_time": "2:06:03", "throughput": 787.63, "total_tokens": 7074608} {"current_steps": 21720, "total_steps": 40000, "loss": 0.1376, "lr": 2.1634995879776715e-05, "epoch": 17.77445763405649, "percentage": 54.3, "elapsed_time": "2:29:43", "remaining_time": "2:06:01", "throughput": 787.66, "total_tokens": 7076224} {"current_steps": 21725, "total_steps": 40000, "loss": 0.1838, "lr": 2.162526800155949e-05, "epoch": 17.77855096193205, "percentage": 54.31, "elapsed_time": "2:29:45", "remaining_time": "2:05:58", "throughput": 787.69, "total_tokens": 7077840} {"current_steps": 21730, "total_steps": 40000, "loss": 0.1672, "lr": 2.1615540643768363e-05, "epoch": 17.782644289807614, "percentage": 54.33, "elapsed_time": "2:29:47", "remaining_time": "2:05:56", "throughput": 787.72, "total_tokens": 7079456} {"current_steps": 21735, "total_steps": 40000, "loss": 0.1724, "lr": 2.160581380790339e-05, "epoch": 17.786737617683176, "percentage": 54.34, "elapsed_time": "2:29:49", "remaining_time": "2:05:53", "throughput": 787.74, "total_tokens": 7081056} {"current_steps": 21740, "total_steps": 40000, "loss": 0.1729, "lr": 2.1596087495464586e-05, "epoch": 17.79083094555874, "percentage": 54.35, "elapsed_time": "2:29:50", "remaining_time": "2:05:51", "throughput": 787.77, "total_tokens": 7082624} {"current_steps": 21745, "total_steps": 40000, "loss": 0.3218, "lr": 2.1586361707951866e-05, "epoch": 17.7949242734343, "percentage": 54.36, "elapsed_time": "2:29:52", "remaining_time": "2:05:49", "throughput": 787.79, "total_tokens": 7084208} {"current_steps": 21750, "total_steps": 40000, "loss": 0.1317, "lr": 2.157663644686507e-05, "epoch": 17.799017601309863, "percentage": 54.37, "elapsed_time": "2:29:54", "remaining_time": "2:05:46", "throughput": 787.83, "total_tokens": 7085872} {"current_steps": 21755, "total_steps": 40000, "loss": 0.134, "lr": 2.156691171370396e-05, "epoch": 17.80311092918543, "percentage": 54.39, "elapsed_time": "2:29:55", "remaining_time": "2:05:44", "throughput": 787.86, "total_tokens": 7087520} {"current_steps": 21760, "total_steps": 40000, "loss": 0.2403, "lr": 2.1557187509968195e-05, "epoch": 17.80720425706099, "percentage": 54.4, "elapsed_time": "2:29:57", "remaining_time": "2:05:42", "throughput": 787.89, "total_tokens": 7089152} {"current_steps": 21765, "total_steps": 40000, "loss": 0.2556, "lr": 2.1547463837157382e-05, "epoch": 17.811297584936554, "percentage": 54.41, "elapsed_time": "2:29:59", "remaining_time": "2:05:39", "throughput": 787.93, "total_tokens": 7090800} {"current_steps": 21770, "total_steps": 40000, "loss": 0.1284, "lr": 2.1537740696771045e-05, "epoch": 17.815390912812116, "percentage": 54.43, "elapsed_time": "2:30:01", "remaining_time": "2:05:37", "throughput": 787.95, "total_tokens": 7092416} {"current_steps": 21775, "total_steps": 40000, "loss": 0.1626, "lr": 2.1528018090308587e-05, "epoch": 17.81948424068768, "percentage": 54.44, "elapsed_time": "2:30:02", "remaining_time": "2:05:35", "throughput": 787.98, "total_tokens": 7094032} {"current_steps": 21780, "total_steps": 40000, "loss": 0.1322, "lr": 2.151829601926938e-05, "epoch": 17.82357756856324, "percentage": 54.45, "elapsed_time": "2:30:04", "remaining_time": "2:05:32", "throughput": 788.02, "total_tokens": 7095712} {"current_steps": 21785, "total_steps": 40000, "loss": 0.1625, "lr": 2.1508574485152684e-05, "epoch": 17.827670896438804, "percentage": 54.46, "elapsed_time": "2:30:06", "remaining_time": "2:05:30", "throughput": 788.05, "total_tokens": 7097328} {"current_steps": 21790, "total_steps": 40000, "loss": 0.1908, "lr": 2.1498853489457667e-05, "epoch": 17.831764224314366, "percentage": 54.47, "elapsed_time": "2:30:07", "remaining_time": "2:05:27", "throughput": 788.08, "total_tokens": 7098944} {"current_steps": 21795, "total_steps": 40000, "loss": 0.1726, "lr": 2.1489133033683455e-05, "epoch": 17.835857552189932, "percentage": 54.49, "elapsed_time": "2:30:09", "remaining_time": "2:05:25", "throughput": 788.11, "total_tokens": 7100544} {"current_steps": 21800, "total_steps": 40000, "loss": 0.1921, "lr": 2.1479413119329038e-05, "epoch": 17.839950880065494, "percentage": 54.5, "elapsed_time": "2:30:11", "remaining_time": "2:05:23", "throughput": 788.14, "total_tokens": 7102176} {"current_steps": 21800, "total_steps": 40000, "eval_loss": 0.21019791066646576, "epoch": 17.839950880065494, "percentage": 54.5, "elapsed_time": "2:30:23", "remaining_time": "2:05:33", "throughput": 787.05, "total_tokens": 7102176} {"current_steps": 21805, "total_steps": 40000, "loss": 0.1555, "lr": 2.1469693747893355e-05, "epoch": 17.844044207941057, "percentage": 54.51, "elapsed_time": "2:30:26", "remaining_time": "2:05:32", "throughput": 786.96, "total_tokens": 7103840} {"current_steps": 21810, "total_steps": 40000, "loss": 0.1166, "lr": 2.1459974920875274e-05, "epoch": 17.84813753581662, "percentage": 54.52, "elapsed_time": "2:30:28", "remaining_time": "2:05:30", "throughput": 786.99, "total_tokens": 7105456} {"current_steps": 21815, "total_steps": 40000, "loss": 0.2158, "lr": 2.145025663977354e-05, "epoch": 17.85223086369218, "percentage": 54.54, "elapsed_time": "2:30:30", "remaining_time": "2:05:27", "throughput": 787.01, "total_tokens": 7107072} {"current_steps": 21820, "total_steps": 40000, "loss": 0.1596, "lr": 2.1440538906086844e-05, "epoch": 17.856324191567744, "percentage": 54.55, "elapsed_time": "2:30:32", "remaining_time": "2:05:25", "throughput": 787.04, "total_tokens": 7108656} {"current_steps": 21825, "total_steps": 40000, "loss": 0.2035, "lr": 2.1430821721313782e-05, "epoch": 17.860417519443306, "percentage": 54.56, "elapsed_time": "2:30:33", "remaining_time": "2:05:23", "throughput": 787.07, "total_tokens": 7110256} {"current_steps": 21830, "total_steps": 40000, "loss": 0.1309, "lr": 2.142110508695286e-05, "epoch": 17.86451084731887, "percentage": 54.57, "elapsed_time": "2:30:35", "remaining_time": "2:05:20", "throughput": 787.1, "total_tokens": 7111920} {"current_steps": 21835, "total_steps": 40000, "loss": 0.1913, "lr": 2.1411389004502515e-05, "epoch": 17.868604175194434, "percentage": 54.59, "elapsed_time": "2:30:37", "remaining_time": "2:05:18", "throughput": 787.13, "total_tokens": 7113504} {"current_steps": 21840, "total_steps": 40000, "loss": 0.1503, "lr": 2.140167347546107e-05, "epoch": 17.872697503069997, "percentage": 54.6, "elapsed_time": "2:30:39", "remaining_time": "2:05:15", "throughput": 787.16, "total_tokens": 7115168} {"current_steps": 21845, "total_steps": 40000, "loss": 0.1154, "lr": 2.1391958501326793e-05, "epoch": 17.87679083094556, "percentage": 54.61, "elapsed_time": "2:30:40", "remaining_time": "2:05:13", "throughput": 787.19, "total_tokens": 7116784} {"current_steps": 21850, "total_steps": 40000, "loss": 0.2184, "lr": 2.1382244083597873e-05, "epoch": 17.88088415882112, "percentage": 54.62, "elapsed_time": "2:30:42", "remaining_time": "2:05:11", "throughput": 787.22, "total_tokens": 7118400} {"current_steps": 21855, "total_steps": 40000, "loss": 0.1469, "lr": 2.137253022377237e-05, "epoch": 17.884977486696684, "percentage": 54.64, "elapsed_time": "2:30:44", "remaining_time": "2:05:08", "throughput": 787.25, "total_tokens": 7120064} {"current_steps": 21860, "total_steps": 40000, "loss": 0.1219, "lr": 2.136281692334829e-05, "epoch": 17.889070814572246, "percentage": 54.65, "elapsed_time": "2:30:45", "remaining_time": "2:05:06", "throughput": 787.29, "total_tokens": 7121712} {"current_steps": 21865, "total_steps": 40000, "loss": 0.1315, "lr": 2.135310418382356e-05, "epoch": 17.89316414244781, "percentage": 54.66, "elapsed_time": "2:30:47", "remaining_time": "2:05:04", "throughput": 787.32, "total_tokens": 7123392} {"current_steps": 21870, "total_steps": 40000, "loss": 0.2103, "lr": 2.134339200669598e-05, "epoch": 17.897257470323375, "percentage": 54.67, "elapsed_time": "2:30:49", "remaining_time": "2:05:01", "throughput": 787.35, "total_tokens": 7125008} {"current_steps": 21875, "total_steps": 40000, "loss": 0.2851, "lr": 2.133368039346331e-05, "epoch": 17.901350798198937, "percentage": 54.69, "elapsed_time": "2:30:51", "remaining_time": "2:04:59", "throughput": 787.38, "total_tokens": 7126640} {"current_steps": 21880, "total_steps": 40000, "loss": 0.2724, "lr": 2.1323969345623195e-05, "epoch": 17.9054441260745, "percentage": 54.7, "elapsed_time": "2:30:52", "remaining_time": "2:04:57", "throughput": 787.42, "total_tokens": 7128288} {"current_steps": 21885, "total_steps": 40000, "loss": 0.1232, "lr": 2.1314258864673207e-05, "epoch": 17.909537453950062, "percentage": 54.71, "elapsed_time": "2:30:54", "remaining_time": "2:04:54", "throughput": 787.45, "total_tokens": 7129952} {"current_steps": 21890, "total_steps": 40000, "loss": 0.1556, "lr": 2.130454895211082e-05, "epoch": 17.913630781825624, "percentage": 54.73, "elapsed_time": "2:30:56", "remaining_time": "2:04:52", "throughput": 787.48, "total_tokens": 7131600} {"current_steps": 21895, "total_steps": 40000, "loss": 0.175, "lr": 2.129483960943342e-05, "epoch": 17.917724109701187, "percentage": 54.74, "elapsed_time": "2:30:57", "remaining_time": "2:04:50", "throughput": 787.51, "total_tokens": 7133168} {"current_steps": 21900, "total_steps": 40000, "loss": 0.3761, "lr": 2.128513083813831e-05, "epoch": 17.92181743757675, "percentage": 54.75, "elapsed_time": "2:30:59", "remaining_time": "2:04:47", "throughput": 787.54, "total_tokens": 7134800} {"current_steps": 21905, "total_steps": 40000, "loss": 0.291, "lr": 2.1275422639722724e-05, "epoch": 17.92591076545231, "percentage": 54.76, "elapsed_time": "2:31:01", "remaining_time": "2:04:45", "throughput": 787.56, "total_tokens": 7136368} {"current_steps": 21910, "total_steps": 40000, "loss": 0.12, "lr": 2.126571501568376e-05, "epoch": 17.930004093327877, "percentage": 54.77, "elapsed_time": "2:31:03", "remaining_time": "2:04:42", "throughput": 787.59, "total_tokens": 7138016} {"current_steps": 21915, "total_steps": 40000, "loss": 0.1483, "lr": 2.1256007967518478e-05, "epoch": 17.93409742120344, "percentage": 54.79, "elapsed_time": "2:31:04", "remaining_time": "2:04:40", "throughput": 787.62, "total_tokens": 7139600} {"current_steps": 21920, "total_steps": 40000, "loss": 0.2026, "lr": 2.124630149672381e-05, "epoch": 17.938190749079002, "percentage": 54.8, "elapsed_time": "2:31:06", "remaining_time": "2:04:38", "throughput": 787.65, "total_tokens": 7141264} {"current_steps": 21925, "total_steps": 40000, "loss": 0.2732, "lr": 2.1236595604796624e-05, "epoch": 17.942284076954564, "percentage": 54.81, "elapsed_time": "2:31:08", "remaining_time": "2:04:35", "throughput": 787.68, "total_tokens": 7142832} {"current_steps": 21930, "total_steps": 40000, "loss": 0.2278, "lr": 2.1226890293233693e-05, "epoch": 17.946377404830127, "percentage": 54.83, "elapsed_time": "2:31:09", "remaining_time": "2:04:33", "throughput": 787.71, "total_tokens": 7144464} {"current_steps": 21935, "total_steps": 40000, "loss": 0.1845, "lr": 2.1217185563531694e-05, "epoch": 17.95047073270569, "percentage": 54.84, "elapsed_time": "2:31:11", "remaining_time": "2:04:31", "throughput": 787.73, "total_tokens": 7146064} {"current_steps": 21940, "total_steps": 40000, "loss": 0.1539, "lr": 2.120748141718721e-05, "epoch": 17.95456406058125, "percentage": 54.85, "elapsed_time": "2:31:13", "remaining_time": "2:04:28", "throughput": 787.77, "total_tokens": 7147744} {"current_steps": 21945, "total_steps": 40000, "loss": 0.233, "lr": 2.1197777855696765e-05, "epoch": 17.958657388456814, "percentage": 54.86, "elapsed_time": "2:31:15", "remaining_time": "2:04:26", "throughput": 787.8, "total_tokens": 7149408} {"current_steps": 21950, "total_steps": 40000, "loss": 0.1979, "lr": 2.1188074880556746e-05, "epoch": 17.96275071633238, "percentage": 54.87, "elapsed_time": "2:31:16", "remaining_time": "2:04:24", "throughput": 787.84, "total_tokens": 7151040} {"current_steps": 21955, "total_steps": 40000, "loss": 0.1919, "lr": 2.1178372493263495e-05, "epoch": 17.966844044207942, "percentage": 54.89, "elapsed_time": "2:31:18", "remaining_time": "2:04:21", "throughput": 787.86, "total_tokens": 7152624} {"current_steps": 21960, "total_steps": 40000, "loss": 0.1802, "lr": 2.116867069531322e-05, "epoch": 17.970937372083505, "percentage": 54.9, "elapsed_time": "2:31:20", "remaining_time": "2:04:19", "throughput": 787.89, "total_tokens": 7154272} {"current_steps": 21965, "total_steps": 40000, "loss": 0.2432, "lr": 2.1158969488202073e-05, "epoch": 17.975030699959067, "percentage": 54.91, "elapsed_time": "2:31:21", "remaining_time": "2:04:17", "throughput": 787.93, "total_tokens": 7155920} {"current_steps": 21970, "total_steps": 40000, "loss": 0.1505, "lr": 2.114926887342611e-05, "epoch": 17.97912402783463, "percentage": 54.93, "elapsed_time": "2:31:23", "remaining_time": "2:04:14", "throughput": 787.96, "total_tokens": 7157536} {"current_steps": 21975, "total_steps": 40000, "loss": 0.0885, "lr": 2.113956885248127e-05, "epoch": 17.98321735571019, "percentage": 54.94, "elapsed_time": "2:31:25", "remaining_time": "2:04:12", "throughput": 787.99, "total_tokens": 7159168} {"current_steps": 21980, "total_steps": 40000, "loss": 0.1646, "lr": 2.112986942686342e-05, "epoch": 17.987310683585754, "percentage": 54.95, "elapsed_time": "2:31:27", "remaining_time": "2:04:09", "throughput": 788.02, "total_tokens": 7160784} {"current_steps": 21985, "total_steps": 40000, "loss": 0.1586, "lr": 2.112017059806835e-05, "epoch": 17.991404011461317, "percentage": 54.96, "elapsed_time": "2:31:28", "remaining_time": "2:04:07", "throughput": 788.05, "total_tokens": 7162480} {"current_steps": 21990, "total_steps": 40000, "loss": 0.2039, "lr": 2.1110472367591724e-05, "epoch": 17.995497339336882, "percentage": 54.97, "elapsed_time": "2:31:30", "remaining_time": "2:04:05", "throughput": 788.08, "total_tokens": 7164112} {"current_steps": 21995, "total_steps": 40000, "loss": 0.1894, "lr": 2.1100774736929145e-05, "epoch": 17.999590667212445, "percentage": 54.99, "elapsed_time": "2:31:32", "remaining_time": "2:04:02", "throughput": 788.12, "total_tokens": 7165776} {"current_steps": 22000, "total_steps": 40000, "loss": 0.1601, "lr": 2.10910777075761e-05, "epoch": 18.003274662300452, "percentage": 55.0, "elapsed_time": "2:31:34", "remaining_time": "2:04:00", "throughput": 788.11, "total_tokens": 7167168} {"current_steps": 22000, "total_steps": 40000, "eval_loss": 0.21044917404651642, "epoch": 18.003274662300452, "percentage": 55.0, "elapsed_time": "2:31:46", "remaining_time": "2:04:10", "throughput": 787.02, "total_tokens": 7167168} {"current_steps": 22005, "total_steps": 40000, "loss": 0.1565, "lr": 2.108138128102799e-05, "epoch": 18.007367990176014, "percentage": 55.01, "elapsed_time": "2:31:49", "remaining_time": "2:04:09", "throughput": 786.93, "total_tokens": 7168816} {"current_steps": 22010, "total_steps": 40000, "loss": 0.186, "lr": 2.107168545878014e-05, "epoch": 18.011461318051577, "percentage": 55.02, "elapsed_time": "2:31:51", "remaining_time": "2:04:07", "throughput": 786.96, "total_tokens": 7170496} {"current_steps": 22015, "total_steps": 40000, "loss": 0.2178, "lr": 2.106199024232775e-05, "epoch": 18.01555464592714, "percentage": 55.04, "elapsed_time": "2:31:53", "remaining_time": "2:04:05", "throughput": 786.99, "total_tokens": 7172112} {"current_steps": 22020, "total_steps": 40000, "loss": 0.1319, "lr": 2.105229563316595e-05, "epoch": 18.0196479738027, "percentage": 55.05, "elapsed_time": "2:31:55", "remaining_time": "2:04:02", "throughput": 787.02, "total_tokens": 7173696} {"current_steps": 22025, "total_steps": 40000, "loss": 0.1772, "lr": 2.1042601632789784e-05, "epoch": 18.023741301678264, "percentage": 55.06, "elapsed_time": "2:31:56", "remaining_time": "2:04:00", "throughput": 787.05, "total_tokens": 7175328} {"current_steps": 22030, "total_steps": 40000, "loss": 0.1573, "lr": 2.103290824269417e-05, "epoch": 18.027834629553826, "percentage": 55.07, "elapsed_time": "2:31:58", "remaining_time": "2:03:58", "throughput": 787.07, "total_tokens": 7176928} {"current_steps": 22035, "total_steps": 40000, "loss": 0.1148, "lr": 2.1023215464373965e-05, "epoch": 18.03192795742939, "percentage": 55.09, "elapsed_time": "2:32:00", "remaining_time": "2:03:55", "throughput": 787.1, "total_tokens": 7178576} {"current_steps": 22040, "total_steps": 40000, "loss": 0.2281, "lr": 2.1013523299323908e-05, "epoch": 18.036021285304955, "percentage": 55.1, "elapsed_time": "2:32:01", "remaining_time": "2:03:53", "throughput": 787.14, "total_tokens": 7180272} {"current_steps": 22045, "total_steps": 40000, "loss": 0.1602, "lr": 2.1003831749038654e-05, "epoch": 18.040114613180517, "percentage": 55.11, "elapsed_time": "2:32:03", "remaining_time": "2:03:50", "throughput": 787.17, "total_tokens": 7181920} {"current_steps": 22050, "total_steps": 40000, "loss": 0.2236, "lr": 2.099414081501277e-05, "epoch": 18.04420794105608, "percentage": 55.12, "elapsed_time": "2:32:05", "remaining_time": "2:03:48", "throughput": 787.21, "total_tokens": 7183584} {"current_steps": 22055, "total_steps": 40000, "loss": 0.2089, "lr": 2.09844504987407e-05, "epoch": 18.04830126893164, "percentage": 55.14, "elapsed_time": "2:32:07", "remaining_time": "2:03:46", "throughput": 787.24, "total_tokens": 7185232} {"current_steps": 22060, "total_steps": 40000, "loss": 0.1798, "lr": 2.097476080171683e-05, "epoch": 18.052394596807204, "percentage": 55.15, "elapsed_time": "2:32:08", "remaining_time": "2:03:43", "throughput": 787.27, "total_tokens": 7186832} {"current_steps": 22065, "total_steps": 40000, "loss": 0.1282, "lr": 2.0965071725435436e-05, "epoch": 18.056487924682767, "percentage": 55.16, "elapsed_time": "2:32:10", "remaining_time": "2:03:41", "throughput": 787.29, "total_tokens": 7188416} {"current_steps": 22070, "total_steps": 40000, "loss": 0.1461, "lr": 2.0955383271390684e-05, "epoch": 18.06058125255833, "percentage": 55.17, "elapsed_time": "2:32:12", "remaining_time": "2:03:39", "throughput": 787.32, "total_tokens": 7190048} {"current_steps": 22075, "total_steps": 40000, "loss": 0.1634, "lr": 2.094569544107666e-05, "epoch": 18.06467458043389, "percentage": 55.19, "elapsed_time": "2:32:13", "remaining_time": "2:03:36", "throughput": 787.35, "total_tokens": 7191632} {"current_steps": 22080, "total_steps": 40000, "loss": 0.1927, "lr": 2.093600823598735e-05, "epoch": 18.068767908309457, "percentage": 55.2, "elapsed_time": "2:32:15", "remaining_time": "2:03:34", "throughput": 787.37, "total_tokens": 7193216} {"current_steps": 22085, "total_steps": 40000, "loss": 0.116, "lr": 2.092632165761663e-05, "epoch": 18.07286123618502, "percentage": 55.21, "elapsed_time": "2:32:17", "remaining_time": "2:03:32", "throughput": 787.41, "total_tokens": 7194880} {"current_steps": 22090, "total_steps": 40000, "loss": 0.3118, "lr": 2.091663570745832e-05, "epoch": 18.076954564060582, "percentage": 55.23, "elapsed_time": "2:32:19", "remaining_time": "2:03:29", "throughput": 787.44, "total_tokens": 7196512} {"current_steps": 22095, "total_steps": 40000, "loss": 0.2232, "lr": 2.0906950387006086e-05, "epoch": 18.081047891936144, "percentage": 55.24, "elapsed_time": "2:32:20", "remaining_time": "2:03:27", "throughput": 787.47, "total_tokens": 7198176} {"current_steps": 22100, "total_steps": 40000, "loss": 0.1159, "lr": 2.0897265697753543e-05, "epoch": 18.085141219811707, "percentage": 55.25, "elapsed_time": "2:32:22", "remaining_time": "2:03:25", "throughput": 787.5, "total_tokens": 7199824} {"current_steps": 22105, "total_steps": 40000, "loss": 0.208, "lr": 2.088758164119419e-05, "epoch": 18.08923454768727, "percentage": 55.26, "elapsed_time": "2:32:24", "remaining_time": "2:03:22", "throughput": 787.54, "total_tokens": 7201488} {"current_steps": 22110, "total_steps": 40000, "loss": 0.2342, "lr": 2.0877898218821428e-05, "epoch": 18.09332787556283, "percentage": 55.27, "elapsed_time": "2:32:26", "remaining_time": "2:03:20", "throughput": 787.56, "total_tokens": 7203088} {"current_steps": 22115, "total_steps": 40000, "loss": 0.1926, "lr": 2.0868215432128565e-05, "epoch": 18.097421203438394, "percentage": 55.29, "elapsed_time": "2:32:27", "remaining_time": "2:03:18", "throughput": 787.59, "total_tokens": 7204688} {"current_steps": 22120, "total_steps": 40000, "loss": 0.1432, "lr": 2.0858533282608796e-05, "epoch": 18.10151453131396, "percentage": 55.3, "elapsed_time": "2:32:29", "remaining_time": "2:03:15", "throughput": 787.62, "total_tokens": 7206336} {"current_steps": 22125, "total_steps": 40000, "loss": 0.2369, "lr": 2.084885177175524e-05, "epoch": 18.105607859189522, "percentage": 55.31, "elapsed_time": "2:32:31", "remaining_time": "2:03:13", "throughput": 787.66, "total_tokens": 7208048} {"current_steps": 22130, "total_steps": 40000, "loss": 0.2712, "lr": 2.0839170901060917e-05, "epoch": 18.109701187065085, "percentage": 55.33, "elapsed_time": "2:32:32", "remaining_time": "2:03:11", "throughput": 787.69, "total_tokens": 7209680} {"current_steps": 22135, "total_steps": 40000, "loss": 0.2186, "lr": 2.082949067201872e-05, "epoch": 18.113794514940647, "percentage": 55.34, "elapsed_time": "2:32:34", "remaining_time": "2:03:08", "throughput": 787.72, "total_tokens": 7211344} {"current_steps": 22140, "total_steps": 40000, "loss": 0.1581, "lr": 2.0819811086121475e-05, "epoch": 18.11788784281621, "percentage": 55.35, "elapsed_time": "2:32:36", "remaining_time": "2:03:06", "throughput": 787.76, "total_tokens": 7212992} {"current_steps": 22145, "total_steps": 40000, "loss": 0.2586, "lr": 2.08101321448619e-05, "epoch": 18.12198117069177, "percentage": 55.36, "elapsed_time": "2:32:38", "remaining_time": "2:03:03", "throughput": 787.79, "total_tokens": 7214672} {"current_steps": 22150, "total_steps": 40000, "loss": 0.1601, "lr": 2.080045384973259e-05, "epoch": 18.126074498567334, "percentage": 55.38, "elapsed_time": "2:32:39", "remaining_time": "2:03:01", "throughput": 787.83, "total_tokens": 7216368} {"current_steps": 22155, "total_steps": 40000, "loss": 0.1679, "lr": 2.0790776202226082e-05, "epoch": 18.130167826442896, "percentage": 55.39, "elapsed_time": "2:32:41", "remaining_time": "2:02:59", "throughput": 787.87, "total_tokens": 7218064} {"current_steps": 22160, "total_steps": 40000, "loss": 0.1789, "lr": 2.078109920383477e-05, "epoch": 18.134261154318462, "percentage": 55.4, "elapsed_time": "2:32:43", "remaining_time": "2:02:56", "throughput": 787.9, "total_tokens": 7219728} {"current_steps": 22165, "total_steps": 40000, "loss": 0.1763, "lr": 2.0771422856050978e-05, "epoch": 18.138354482194025, "percentage": 55.41, "elapsed_time": "2:32:44", "remaining_time": "2:02:54", "throughput": 787.93, "total_tokens": 7221360} {"current_steps": 22170, "total_steps": 40000, "loss": 0.2033, "lr": 2.076174716036693e-05, "epoch": 18.142447810069587, "percentage": 55.43, "elapsed_time": "2:32:46", "remaining_time": "2:02:52", "throughput": 787.97, "total_tokens": 7223056} {"current_steps": 22175, "total_steps": 40000, "loss": 0.1383, "lr": 2.075207211827472e-05, "epoch": 18.14654113794515, "percentage": 55.44, "elapsed_time": "2:32:48", "remaining_time": "2:02:49", "throughput": 788.0, "total_tokens": 7224704} {"current_steps": 22180, "total_steps": 40000, "loss": 0.1627, "lr": 2.074239773126638e-05, "epoch": 18.150634465820712, "percentage": 55.45, "elapsed_time": "2:32:50", "remaining_time": "2:02:47", "throughput": 788.02, "total_tokens": 7226272} {"current_steps": 22185, "total_steps": 40000, "loss": 0.1421, "lr": 2.073272400083382e-05, "epoch": 18.154727793696274, "percentage": 55.46, "elapsed_time": "2:32:51", "remaining_time": "2:02:45", "throughput": 788.05, "total_tokens": 7227888} {"current_steps": 22190, "total_steps": 40000, "loss": 0.1255, "lr": 2.072305092846883e-05, "epoch": 18.158821121571837, "percentage": 55.47, "elapsed_time": "2:32:53", "remaining_time": "2:02:42", "throughput": 788.08, "total_tokens": 7229488} {"current_steps": 22195, "total_steps": 40000, "loss": 0.1987, "lr": 2.0713378515663152e-05, "epoch": 18.1629144494474, "percentage": 55.49, "elapsed_time": "2:32:55", "remaining_time": "2:02:40", "throughput": 788.11, "total_tokens": 7231104} {"current_steps": 22200, "total_steps": 40000, "loss": 0.1581, "lr": 2.070370676390836e-05, "epoch": 18.167007777322965, "percentage": 55.5, "elapsed_time": "2:32:56", "remaining_time": "2:02:38", "throughput": 788.14, "total_tokens": 7232736} {"current_steps": 22200, "total_steps": 40000, "eval_loss": 0.20839092135429382, "epoch": 18.167007777322965, "percentage": 55.5, "elapsed_time": "2:33:09", "remaining_time": "2:02:48", "throughput": 787.07, "total_tokens": 7232736} {"current_steps": 22205, "total_steps": 40000, "loss": 0.1265, "lr": 2.0694035674695974e-05, "epoch": 18.171101105198527, "percentage": 55.51, "elapsed_time": "2:33:12", "remaining_time": "2:02:46", "throughput": 786.96, "total_tokens": 7234320} {"current_steps": 22210, "total_steps": 40000, "loss": 0.2727, "lr": 2.0684365249517416e-05, "epoch": 18.17519443307409, "percentage": 55.53, "elapsed_time": "2:33:14", "remaining_time": "2:02:44", "throughput": 786.99, "total_tokens": 7235936} {"current_steps": 22215, "total_steps": 40000, "loss": 0.2672, "lr": 2.067469548986396e-05, "epoch": 18.179287760949652, "percentage": 55.54, "elapsed_time": "2:33:16", "remaining_time": "2:02:42", "throughput": 787.02, "total_tokens": 7237568} {"current_steps": 22220, "total_steps": 40000, "loss": 0.1392, "lr": 2.066502639722681e-05, "epoch": 18.183381088825215, "percentage": 55.55, "elapsed_time": "2:33:17", "remaining_time": "2:02:39", "throughput": 787.05, "total_tokens": 7239200} {"current_steps": 22225, "total_steps": 40000, "loss": 0.1217, "lr": 2.065535797309708e-05, "epoch": 18.187474416700777, "percentage": 55.56, "elapsed_time": "2:33:19", "remaining_time": "2:02:37", "throughput": 787.07, "total_tokens": 7240768} {"current_steps": 22230, "total_steps": 40000, "loss": 0.1783, "lr": 2.0645690218965736e-05, "epoch": 18.19156774457634, "percentage": 55.57, "elapsed_time": "2:33:21", "remaining_time": "2:02:35", "throughput": 787.1, "total_tokens": 7242352} {"current_steps": 22235, "total_steps": 40000, "loss": 0.1979, "lr": 2.063602313632369e-05, "epoch": 18.1956610724519, "percentage": 55.59, "elapsed_time": "2:33:23", "remaining_time": "2:02:32", "throughput": 787.14, "total_tokens": 7244064} {"current_steps": 22240, "total_steps": 40000, "loss": 0.156, "lr": 2.0626356726661704e-05, "epoch": 18.199754400327468, "percentage": 55.6, "elapsed_time": "2:33:24", "remaining_time": "2:02:30", "throughput": 787.17, "total_tokens": 7245712} {"current_steps": 22245, "total_steps": 40000, "loss": 0.2296, "lr": 2.0616690991470477e-05, "epoch": 18.20384772820303, "percentage": 55.61, "elapsed_time": "2:33:26", "remaining_time": "2:02:28", "throughput": 787.2, "total_tokens": 7247360} {"current_steps": 22250, "total_steps": 40000, "loss": 0.1992, "lr": 2.0607025932240595e-05, "epoch": 18.207941056078592, "percentage": 55.62, "elapsed_time": "2:33:28", "remaining_time": "2:02:25", "throughput": 787.23, "total_tokens": 7248992} {"current_steps": 22255, "total_steps": 40000, "loss": 0.194, "lr": 2.059736155046251e-05, "epoch": 18.212034383954155, "percentage": 55.64, "elapsed_time": "2:33:29", "remaining_time": "2:02:23", "throughput": 787.26, "total_tokens": 7250640} {"current_steps": 22260, "total_steps": 40000, "loss": 0.1393, "lr": 2.0587697847626603e-05, "epoch": 18.216127711829717, "percentage": 55.65, "elapsed_time": "2:33:31", "remaining_time": "2:02:21", "throughput": 787.29, "total_tokens": 7252288} {"current_steps": 22265, "total_steps": 40000, "loss": 0.1587, "lr": 2.057803482522314e-05, "epoch": 18.22022103970528, "percentage": 55.66, "elapsed_time": "2:33:33", "remaining_time": "2:02:18", "throughput": 787.32, "total_tokens": 7253872} {"current_steps": 22270, "total_steps": 40000, "loss": 0.215, "lr": 2.056837248474227e-05, "epoch": 18.224314367580842, "percentage": 55.67, "elapsed_time": "2:33:35", "remaining_time": "2:02:16", "throughput": 787.35, "total_tokens": 7255488} {"current_steps": 22275, "total_steps": 40000, "loss": 0.1912, "lr": 2.0558710827674064e-05, "epoch": 18.228407695456404, "percentage": 55.69, "elapsed_time": "2:33:36", "remaining_time": "2:02:14", "throughput": 787.38, "total_tokens": 7257136} {"current_steps": 22280, "total_steps": 40000, "loss": 0.2849, "lr": 2.054904985550845e-05, "epoch": 18.23250102333197, "percentage": 55.7, "elapsed_time": "2:33:38", "remaining_time": "2:02:11", "throughput": 787.4, "total_tokens": 7258672} {"current_steps": 22285, "total_steps": 40000, "loss": 0.1945, "lr": 2.0539389569735287e-05, "epoch": 18.236594351207533, "percentage": 55.71, "elapsed_time": "2:33:40", "remaining_time": "2:02:09", "throughput": 787.44, "total_tokens": 7260352} {"current_steps": 22290, "total_steps": 40000, "loss": 0.1776, "lr": 2.052972997184431e-05, "epoch": 18.240687679083095, "percentage": 55.73, "elapsed_time": "2:33:41", "remaining_time": "2:02:07", "throughput": 787.47, "total_tokens": 7262000} {"current_steps": 22295, "total_steps": 40000, "loss": 0.1343, "lr": 2.0520071063325146e-05, "epoch": 18.244781006958657, "percentage": 55.74, "elapsed_time": "2:33:43", "remaining_time": "2:02:04", "throughput": 787.5, "total_tokens": 7263680} {"current_steps": 22300, "total_steps": 40000, "loss": 0.2256, "lr": 2.051041284566732e-05, "epoch": 18.24887433483422, "percentage": 55.75, "elapsed_time": "2:33:45", "remaining_time": "2:02:02", "throughput": 787.53, "total_tokens": 7265264} {"current_steps": 22305, "total_steps": 40000, "loss": 0.2164, "lr": 2.050075532036026e-05, "epoch": 18.252967662709782, "percentage": 55.76, "elapsed_time": "2:33:47", "remaining_time": "2:02:00", "throughput": 787.56, "total_tokens": 7266928} {"current_steps": 22310, "total_steps": 40000, "loss": 0.2066, "lr": 2.0491098488893264e-05, "epoch": 18.257060990585344, "percentage": 55.77, "elapsed_time": "2:33:48", "remaining_time": "2:01:57", "throughput": 787.59, "total_tokens": 7268560} {"current_steps": 22315, "total_steps": 40000, "loss": 0.231, "lr": 2.0481442352755546e-05, "epoch": 18.26115431846091, "percentage": 55.79, "elapsed_time": "2:33:50", "remaining_time": "2:01:55", "throughput": 787.62, "total_tokens": 7270208} {"current_steps": 22320, "total_steps": 40000, "loss": 0.1556, "lr": 2.0471786913436198e-05, "epoch": 18.265247646336473, "percentage": 55.8, "elapsed_time": "2:33:52", "remaining_time": "2:01:53", "throughput": 787.65, "total_tokens": 7271840} {"current_steps": 22325, "total_steps": 40000, "loss": 0.0792, "lr": 2.0462132172424218e-05, "epoch": 18.269340974212035, "percentage": 55.81, "elapsed_time": "2:33:54", "remaining_time": "2:01:50", "throughput": 787.67, "total_tokens": 7273392} {"current_steps": 22330, "total_steps": 40000, "loss": 0.1902, "lr": 2.0452478131208484e-05, "epoch": 18.273434302087598, "percentage": 55.83, "elapsed_time": "2:33:55", "remaining_time": "2:01:48", "throughput": 787.71, "total_tokens": 7275072} {"current_steps": 22335, "total_steps": 40000, "loss": 0.1018, "lr": 2.0442824791277765e-05, "epoch": 18.27752762996316, "percentage": 55.84, "elapsed_time": "2:33:57", "remaining_time": "2:01:45", "throughput": 787.74, "total_tokens": 7276688} {"current_steps": 22340, "total_steps": 40000, "loss": 0.2001, "lr": 2.0433172154120727e-05, "epoch": 18.281620957838722, "percentage": 55.85, "elapsed_time": "2:33:59", "remaining_time": "2:01:43", "throughput": 787.78, "total_tokens": 7278384} {"current_steps": 22345, "total_steps": 40000, "loss": 0.1976, "lr": 2.0423520221225947e-05, "epoch": 18.285714285714285, "percentage": 55.86, "elapsed_time": "2:34:00", "remaining_time": "2:01:41", "throughput": 787.8, "total_tokens": 7280000} {"current_steps": 22350, "total_steps": 40000, "loss": 0.1962, "lr": 2.0413868994081848e-05, "epoch": 18.289807613589847, "percentage": 55.88, "elapsed_time": "2:34:02", "remaining_time": "2:01:38", "throughput": 787.83, "total_tokens": 7281600} {"current_steps": 22355, "total_steps": 40000, "loss": 0.1258, "lr": 2.0404218474176795e-05, "epoch": 18.293900941465413, "percentage": 55.89, "elapsed_time": "2:34:04", "remaining_time": "2:01:36", "throughput": 787.86, "total_tokens": 7283248} {"current_steps": 22360, "total_steps": 40000, "loss": 0.2571, "lr": 2.0394568662999002e-05, "epoch": 18.297994269340975, "percentage": 55.9, "elapsed_time": "2:34:06", "remaining_time": "2:01:34", "throughput": 787.89, "total_tokens": 7284880} {"current_steps": 22365, "total_steps": 40000, "loss": 0.3175, "lr": 2.0384919562036593e-05, "epoch": 18.302087597216538, "percentage": 55.91, "elapsed_time": "2:34:07", "remaining_time": "2:01:31", "throughput": 787.92, "total_tokens": 7286512} {"current_steps": 22370, "total_steps": 40000, "loss": 0.2308, "lr": 2.0375271172777593e-05, "epoch": 18.3061809250921, "percentage": 55.93, "elapsed_time": "2:34:09", "remaining_time": "2:01:29", "throughput": 787.95, "total_tokens": 7288096} {"current_steps": 22375, "total_steps": 40000, "loss": 0.1372, "lr": 2.0365623496709885e-05, "epoch": 18.310274252967663, "percentage": 55.94, "elapsed_time": "2:34:11", "remaining_time": "2:01:27", "throughput": 787.98, "total_tokens": 7289712} {"current_steps": 22380, "total_steps": 40000, "loss": 0.1759, "lr": 2.0355976535321283e-05, "epoch": 18.314367580843225, "percentage": 55.95, "elapsed_time": "2:34:12", "remaining_time": "2:01:24", "throughput": 788.01, "total_tokens": 7291376} {"current_steps": 22385, "total_steps": 40000, "loss": 0.1991, "lr": 2.034633029009945e-05, "epoch": 18.318460908718787, "percentage": 55.96, "elapsed_time": "2:34:14", "remaining_time": "2:01:22", "throughput": 788.05, "total_tokens": 7293088} {"current_steps": 22390, "total_steps": 40000, "loss": 0.2022, "lr": 2.0336684762531972e-05, "epoch": 18.32255423659435, "percentage": 55.97, "elapsed_time": "2:34:16", "remaining_time": "2:01:20", "throughput": 788.07, "total_tokens": 7294672} {"current_steps": 22395, "total_steps": 40000, "loss": 0.1221, "lr": 2.032703995410631e-05, "epoch": 18.326647564469916, "percentage": 55.99, "elapsed_time": "2:34:18", "remaining_time": "2:01:17", "throughput": 788.1, "total_tokens": 7296304} {"current_steps": 22400, "total_steps": 40000, "loss": 0.1955, "lr": 2.031739586630981e-05, "epoch": 18.330740892345478, "percentage": 56.0, "elapsed_time": "2:34:19", "remaining_time": "2:01:15", "throughput": 788.14, "total_tokens": 7297984} {"current_steps": 22400, "total_steps": 40000, "eval_loss": 0.2127838432788849, "epoch": 18.330740892345478, "percentage": 56.0, "elapsed_time": "2:34:32", "remaining_time": "2:01:25", "throughput": 787.08, "total_tokens": 7297984} {"current_steps": 22405, "total_steps": 40000, "loss": 0.1571, "lr": 2.0307752500629707e-05, "epoch": 18.33483422022104, "percentage": 56.01, "elapsed_time": "2:34:35", "remaining_time": "2:01:24", "throughput": 786.98, "total_tokens": 7299568} {"current_steps": 22410, "total_steps": 40000, "loss": 0.2239, "lr": 2.0298109858553144e-05, "epoch": 18.338927548096603, "percentage": 56.03, "elapsed_time": "2:34:37", "remaining_time": "2:01:21", "throughput": 787.01, "total_tokens": 7301168} {"current_steps": 22415, "total_steps": 40000, "loss": 0.1346, "lr": 2.028846794156712e-05, "epoch": 18.343020875972165, "percentage": 56.04, "elapsed_time": "2:34:38", "remaining_time": "2:01:19", "throughput": 787.05, "total_tokens": 7302880} {"current_steps": 22420, "total_steps": 40000, "loss": 0.1668, "lr": 2.027882675115856e-05, "epoch": 18.347114203847728, "percentage": 56.05, "elapsed_time": "2:34:40", "remaining_time": "2:01:17", "throughput": 787.08, "total_tokens": 7304544} {"current_steps": 22425, "total_steps": 40000, "loss": 0.1195, "lr": 2.026918628881423e-05, "epoch": 18.35120753172329, "percentage": 56.06, "elapsed_time": "2:34:42", "remaining_time": "2:01:14", "throughput": 787.11, "total_tokens": 7306192} {"current_steps": 22430, "total_steps": 40000, "loss": 0.1878, "lr": 2.0259546556020833e-05, "epoch": 18.355300859598852, "percentage": 56.07, "elapsed_time": "2:34:43", "remaining_time": "2:01:12", "throughput": 787.14, "total_tokens": 7307808} {"current_steps": 22435, "total_steps": 40000, "loss": 0.1559, "lr": 2.024990755426493e-05, "epoch": 18.359394187474418, "percentage": 56.09, "elapsed_time": "2:34:45", "remaining_time": "2:01:10", "throughput": 787.17, "total_tokens": 7309440} {"current_steps": 22440, "total_steps": 40000, "loss": 0.2034, "lr": 2.0240269285032975e-05, "epoch": 18.36348751534998, "percentage": 56.1, "elapsed_time": "2:34:47", "remaining_time": "2:01:07", "throughput": 787.2, "total_tokens": 7311104} {"current_steps": 22445, "total_steps": 40000, "loss": 0.1895, "lr": 2.0230631749811306e-05, "epoch": 18.367580843225543, "percentage": 56.11, "elapsed_time": "2:34:49", "remaining_time": "2:01:05", "throughput": 787.23, "total_tokens": 7312704} {"current_steps": 22450, "total_steps": 40000, "loss": 0.0971, "lr": 2.0220994950086162e-05, "epoch": 18.371674171101105, "percentage": 56.12, "elapsed_time": "2:34:50", "remaining_time": "2:01:03", "throughput": 787.25, "total_tokens": 7314272} {"current_steps": 22455, "total_steps": 40000, "loss": 0.1955, "lr": 2.021135888734365e-05, "epoch": 18.375767498976668, "percentage": 56.14, "elapsed_time": "2:34:52", "remaining_time": "2:01:00", "throughput": 787.28, "total_tokens": 7315840} {"current_steps": 22460, "total_steps": 40000, "loss": 0.1862, "lr": 2.0201723563069783e-05, "epoch": 18.37986082685223, "percentage": 56.15, "elapsed_time": "2:34:54", "remaining_time": "2:00:58", "throughput": 787.3, "total_tokens": 7317456} {"current_steps": 22465, "total_steps": 40000, "loss": 0.1412, "lr": 2.0192088978750433e-05, "epoch": 18.383954154727792, "percentage": 56.16, "elapsed_time": "2:34:56", "remaining_time": "2:00:55", "throughput": 787.33, "total_tokens": 7319088} {"current_steps": 22470, "total_steps": 40000, "loss": 0.1805, "lr": 2.0182455135871385e-05, "epoch": 18.388047482603355, "percentage": 56.17, "elapsed_time": "2:34:57", "remaining_time": "2:00:53", "throughput": 787.37, "total_tokens": 7320736} {"current_steps": 22475, "total_steps": 40000, "loss": 0.1773, "lr": 2.0172822035918305e-05, "epoch": 18.39214081047892, "percentage": 56.19, "elapsed_time": "2:34:59", "remaining_time": "2:00:51", "throughput": 787.4, "total_tokens": 7322368} {"current_steps": 22480, "total_steps": 40000, "loss": 0.1919, "lr": 2.016318968037671e-05, "epoch": 18.396234138354483, "percentage": 56.2, "elapsed_time": "2:35:01", "remaining_time": "2:00:48", "throughput": 787.42, "total_tokens": 7323968} {"current_steps": 22485, "total_steps": 40000, "loss": 0.1503, "lr": 2.015355807073206e-05, "epoch": 18.400327466230046, "percentage": 56.21, "elapsed_time": "2:35:02", "remaining_time": "2:00:46", "throughput": 787.45, "total_tokens": 7325552} {"current_steps": 22490, "total_steps": 40000, "loss": 0.1502, "lr": 2.0143927208469664e-05, "epoch": 18.404420794105608, "percentage": 56.23, "elapsed_time": "2:35:04", "remaining_time": "2:00:44", "throughput": 787.47, "total_tokens": 7327152} {"current_steps": 22495, "total_steps": 40000, "loss": 0.2034, "lr": 2.0134297095074708e-05, "epoch": 18.40851412198117, "percentage": 56.24, "elapsed_time": "2:35:06", "remaining_time": "2:00:41", "throughput": 787.5, "total_tokens": 7328768} {"current_steps": 22500, "total_steps": 40000, "loss": 0.1517, "lr": 2.0124667732032297e-05, "epoch": 18.412607449856733, "percentage": 56.25, "elapsed_time": "2:35:08", "remaining_time": "2:00:39", "throughput": 787.53, "total_tokens": 7330416} {"current_steps": 22505, "total_steps": 40000, "loss": 0.1909, "lr": 2.011503912082738e-05, "epoch": 18.416700777732295, "percentage": 56.26, "elapsed_time": "2:35:09", "remaining_time": "2:00:37", "throughput": 787.56, "total_tokens": 7332032} {"current_steps": 22510, "total_steps": 40000, "loss": 0.2331, "lr": 2.0105411262944823e-05, "epoch": 18.420794105607857, "percentage": 56.27, "elapsed_time": "2:35:11", "remaining_time": "2:00:34", "throughput": 787.59, "total_tokens": 7333664} {"current_steps": 22515, "total_steps": 40000, "loss": 0.1631, "lr": 2.0095784159869366e-05, "epoch": 18.424887433483423, "percentage": 56.29, "elapsed_time": "2:35:13", "remaining_time": "2:00:32", "throughput": 787.62, "total_tokens": 7335248} {"current_steps": 22520, "total_steps": 40000, "loss": 0.1964, "lr": 2.0086157813085608e-05, "epoch": 18.428980761358986, "percentage": 56.3, "elapsed_time": "2:35:14", "remaining_time": "2:00:30", "throughput": 787.64, "total_tokens": 7336848} {"current_steps": 22525, "total_steps": 40000, "loss": 0.1316, "lr": 2.0076532224078068e-05, "epoch": 18.433074089234548, "percentage": 56.31, "elapsed_time": "2:35:16", "remaining_time": "2:00:27", "throughput": 787.67, "total_tokens": 7338496} {"current_steps": 22530, "total_steps": 40000, "loss": 0.2803, "lr": 2.0066907394331142e-05, "epoch": 18.43716741711011, "percentage": 56.33, "elapsed_time": "2:35:18", "remaining_time": "2:00:25", "throughput": 787.7, "total_tokens": 7340096} {"current_steps": 22535, "total_steps": 40000, "loss": 0.2196, "lr": 2.0057283325329077e-05, "epoch": 18.441260744985673, "percentage": 56.34, "elapsed_time": "2:35:20", "remaining_time": "2:00:23", "throughput": 787.74, "total_tokens": 7341792} {"current_steps": 22540, "total_steps": 40000, "loss": 0.2867, "lr": 2.0047660018556047e-05, "epoch": 18.445354072861235, "percentage": 56.35, "elapsed_time": "2:35:21", "remaining_time": "2:00:20", "throughput": 787.77, "total_tokens": 7343424} {"current_steps": 22545, "total_steps": 40000, "loss": 0.2175, "lr": 2.0038037475496075e-05, "epoch": 18.449447400736798, "percentage": 56.36, "elapsed_time": "2:35:23", "remaining_time": "2:00:18", "throughput": 787.8, "total_tokens": 7345072} {"current_steps": 22550, "total_steps": 40000, "loss": 0.1433, "lr": 2.0028415697633073e-05, "epoch": 18.45354072861236, "percentage": 56.38, "elapsed_time": "2:35:25", "remaining_time": "2:00:16", "throughput": 787.83, "total_tokens": 7346688} {"current_steps": 22555, "total_steps": 40000, "loss": 0.1482, "lr": 2.0018794686450858e-05, "epoch": 18.457634056487926, "percentage": 56.39, "elapsed_time": "2:35:26", "remaining_time": "2:00:13", "throughput": 787.85, "total_tokens": 7348272} {"current_steps": 22560, "total_steps": 40000, "loss": 0.1614, "lr": 2.0009174443433088e-05, "epoch": 18.46172738436349, "percentage": 56.4, "elapsed_time": "2:35:28", "remaining_time": "2:00:11", "throughput": 787.88, "total_tokens": 7349936} {"current_steps": 22565, "total_steps": 40000, "loss": 0.2077, "lr": 1.999955497006334e-05, "epoch": 18.46582071223905, "percentage": 56.41, "elapsed_time": "2:35:30", "remaining_time": "2:00:09", "throughput": 787.91, "total_tokens": 7351536} {"current_steps": 22570, "total_steps": 40000, "loss": 0.1255, "lr": 1.9989936267825067e-05, "epoch": 18.469914040114613, "percentage": 56.43, "elapsed_time": "2:35:32", "remaining_time": "2:00:06", "throughput": 787.93, "total_tokens": 7353104} {"current_steps": 22575, "total_steps": 40000, "loss": 0.1914, "lr": 1.9980318338201572e-05, "epoch": 18.474007367990176, "percentage": 56.44, "elapsed_time": "2:35:33", "remaining_time": "2:00:04", "throughput": 787.96, "total_tokens": 7354688} {"current_steps": 22580, "total_steps": 40000, "loss": 0.176, "lr": 1.997070118267607e-05, "epoch": 18.478100695865738, "percentage": 56.45, "elapsed_time": "2:35:35", "remaining_time": "2:00:02", "throughput": 787.99, "total_tokens": 7356304} {"current_steps": 22585, "total_steps": 40000, "loss": 0.17, "lr": 1.9961084802731654e-05, "epoch": 18.4821940237413, "percentage": 56.46, "elapsed_time": "2:35:37", "remaining_time": "1:59:59", "throughput": 788.01, "total_tokens": 7357888} {"current_steps": 22590, "total_steps": 40000, "loss": 0.1833, "lr": 1.9951469199851273e-05, "epoch": 18.486287351616866, "percentage": 56.47, "elapsed_time": "2:35:39", "remaining_time": "1:59:57", "throughput": 788.04, "total_tokens": 7359520} {"current_steps": 22595, "total_steps": 40000, "loss": 0.1585, "lr": 1.99418543755178e-05, "epoch": 18.49038067949243, "percentage": 56.49, "elapsed_time": "2:35:40", "remaining_time": "1:59:55", "throughput": 788.08, "total_tokens": 7361200} {"current_steps": 22600, "total_steps": 40000, "loss": 0.2257, "lr": 1.9932240331213936e-05, "epoch": 18.49447400736799, "percentage": 56.5, "elapsed_time": "2:35:42", "remaining_time": "1:59:52", "throughput": 788.11, "total_tokens": 7362832} {"current_steps": 22600, "total_steps": 40000, "eval_loss": 0.20643968880176544, "epoch": 18.49447400736799, "percentage": 56.5, "elapsed_time": "2:35:54", "remaining_time": "2:00:02", "throughput": 787.06, "total_tokens": 7362832} {"current_steps": 22605, "total_steps": 40000, "loss": 0.2325, "lr": 1.9922627068422297e-05, "epoch": 18.498567335243553, "percentage": 56.51, "elapsed_time": "2:35:58", "remaining_time": "2:00:01", "throughput": 786.95, "total_tokens": 7364464} {"current_steps": 22610, "total_steps": 40000, "loss": 0.1769, "lr": 1.991301458862538e-05, "epoch": 18.502660663119116, "percentage": 56.53, "elapsed_time": "2:35:59", "remaining_time": "1:59:58", "throughput": 786.98, "total_tokens": 7366048} {"current_steps": 22615, "total_steps": 40000, "loss": 0.1628, "lr": 1.9903402893305536e-05, "epoch": 18.506753990994678, "percentage": 56.54, "elapsed_time": "2:36:01", "remaining_time": "1:59:56", "throughput": 787.01, "total_tokens": 7367680} {"current_steps": 22620, "total_steps": 40000, "loss": 0.2495, "lr": 1.9893791983945016e-05, "epoch": 18.51084731887024, "percentage": 56.55, "elapsed_time": "2:36:03", "remaining_time": "1:59:54", "throughput": 787.05, "total_tokens": 7369392} {"current_steps": 22625, "total_steps": 40000, "loss": 0.2017, "lr": 1.988418186202594e-05, "epoch": 18.514940646745803, "percentage": 56.56, "elapsed_time": "2:36:05", "remaining_time": "1:59:51", "throughput": 787.07, "total_tokens": 7371008} {"current_steps": 22630, "total_steps": 40000, "loss": 0.217, "lr": 1.98745725290303e-05, "epoch": 18.51903397462137, "percentage": 56.57, "elapsed_time": "2:36:06", "remaining_time": "1:59:49", "throughput": 787.1, "total_tokens": 7372624} {"current_steps": 22635, "total_steps": 40000, "loss": 0.1673, "lr": 1.986496398644e-05, "epoch": 18.52312730249693, "percentage": 56.59, "elapsed_time": "2:36:08", "remaining_time": "1:59:47", "throughput": 787.14, "total_tokens": 7374304} {"current_steps": 22640, "total_steps": 40000, "loss": 0.16, "lr": 1.9855356235736777e-05, "epoch": 18.527220630372494, "percentage": 56.6, "elapsed_time": "2:36:10", "remaining_time": "1:59:44", "throughput": 787.17, "total_tokens": 7375936} {"current_steps": 22645, "total_steps": 40000, "loss": 0.1645, "lr": 1.9845749278402277e-05, "epoch": 18.531313958248056, "percentage": 56.61, "elapsed_time": "2:36:11", "remaining_time": "1:59:42", "throughput": 787.2, "total_tokens": 7377552} {"current_steps": 22650, "total_steps": 40000, "loss": 0.0946, "lr": 1.9836143115918006e-05, "epoch": 18.53540728612362, "percentage": 56.62, "elapsed_time": "2:36:13", "remaining_time": "1:59:40", "throughput": 787.23, "total_tokens": 7379184} {"current_steps": 22655, "total_steps": 40000, "loss": 0.1787, "lr": 1.9826537749765367e-05, "epoch": 18.53950061399918, "percentage": 56.64, "elapsed_time": "2:36:15", "remaining_time": "1:59:37", "throughput": 787.25, "total_tokens": 7380816} {"current_steps": 22660, "total_steps": 40000, "loss": 0.1851, "lr": 1.9816933181425625e-05, "epoch": 18.543593941874743, "percentage": 56.65, "elapsed_time": "2:36:17", "remaining_time": "1:59:35", "throughput": 787.29, "total_tokens": 7382496} {"current_steps": 22665, "total_steps": 40000, "loss": 0.226, "lr": 1.9807329412379903e-05, "epoch": 18.547687269750305, "percentage": 56.66, "elapsed_time": "2:36:18", "remaining_time": "1:59:33", "throughput": 787.31, "total_tokens": 7384032} {"current_steps": 22670, "total_steps": 40000, "loss": 0.1858, "lr": 1.9797726444109247e-05, "epoch": 18.55178059762587, "percentage": 56.67, "elapsed_time": "2:36:20", "remaining_time": "1:59:30", "throughput": 787.35, "total_tokens": 7385744} {"current_steps": 22675, "total_steps": 40000, "loss": 0.1356, "lr": 1.9788124278094557e-05, "epoch": 18.555873925501434, "percentage": 56.69, "elapsed_time": "2:36:22", "remaining_time": "1:59:28", "throughput": 787.39, "total_tokens": 7387456} {"current_steps": 22680, "total_steps": 40000, "loss": 0.2123, "lr": 1.9778522915816594e-05, "epoch": 18.559967253376996, "percentage": 56.7, "elapsed_time": "2:36:23", "remaining_time": "1:59:26", "throughput": 787.41, "total_tokens": 7389072} {"current_steps": 22685, "total_steps": 40000, "loss": 0.2428, "lr": 1.9768922358756014e-05, "epoch": 18.56406058125256, "percentage": 56.71, "elapsed_time": "2:36:25", "remaining_time": "1:59:23", "throughput": 787.44, "total_tokens": 7390688} {"current_steps": 22690, "total_steps": 40000, "loss": 0.1044, "lr": 1.9759322608393353e-05, "epoch": 18.56815390912812, "percentage": 56.73, "elapsed_time": "2:36:27", "remaining_time": "1:59:21", "throughput": 787.47, "total_tokens": 7392320} {"current_steps": 22695, "total_steps": 40000, "loss": 0.1617, "lr": 1.9749723666208992e-05, "epoch": 18.572247237003683, "percentage": 56.74, "elapsed_time": "2:36:29", "remaining_time": "1:59:19", "throughput": 787.51, "total_tokens": 7394032} {"current_steps": 22700, "total_steps": 40000, "loss": 0.2939, "lr": 1.9740125533683235e-05, "epoch": 18.576340564879246, "percentage": 56.75, "elapsed_time": "2:36:30", "remaining_time": "1:59:16", "throughput": 787.54, "total_tokens": 7395664} {"current_steps": 22705, "total_steps": 40000, "loss": 0.2948, "lr": 1.9730528212296208e-05, "epoch": 18.580433892754808, "percentage": 56.76, "elapsed_time": "2:36:32", "remaining_time": "1:59:14", "throughput": 787.57, "total_tokens": 7397296} {"current_steps": 22710, "total_steps": 40000, "loss": 0.1312, "lr": 1.9720931703527945e-05, "epoch": 18.584527220630374, "percentage": 56.77, "elapsed_time": "2:36:34", "remaining_time": "1:59:12", "throughput": 787.6, "total_tokens": 7398944} {"current_steps": 22715, "total_steps": 40000, "loss": 0.2028, "lr": 1.9711336008858373e-05, "epoch": 18.588620548505936, "percentage": 56.79, "elapsed_time": "2:36:36", "remaining_time": "1:59:09", "throughput": 787.64, "total_tokens": 7400736} {"current_steps": 22720, "total_steps": 40000, "loss": 0.1183, "lr": 1.9701741129767233e-05, "epoch": 18.5927138763815, "percentage": 56.8, "elapsed_time": "2:36:37", "remaining_time": "1:59:07", "throughput": 787.68, "total_tokens": 7402464} {"current_steps": 22725, "total_steps": 40000, "loss": 0.1687, "lr": 1.9692147067734202e-05, "epoch": 18.59680720425706, "percentage": 56.81, "elapsed_time": "2:36:39", "remaining_time": "1:59:05", "throughput": 787.71, "total_tokens": 7404016} {"current_steps": 22730, "total_steps": 40000, "loss": 0.1615, "lr": 1.96825538242388e-05, "epoch": 18.600900532132624, "percentage": 56.83, "elapsed_time": "2:36:41", "remaining_time": "1:59:02", "throughput": 787.74, "total_tokens": 7405696} {"current_steps": 22735, "total_steps": 40000, "loss": 0.2296, "lr": 1.967296140076041e-05, "epoch": 18.604993860008186, "percentage": 56.84, "elapsed_time": "2:36:42", "remaining_time": "1:59:00", "throughput": 787.77, "total_tokens": 7407312} {"current_steps": 22740, "total_steps": 40000, "loss": 0.1509, "lr": 1.966336979877833e-05, "epoch": 18.60908718788375, "percentage": 56.85, "elapsed_time": "2:36:44", "remaining_time": "1:58:58", "throughput": 787.8, "total_tokens": 7408976} {"current_steps": 22745, "total_steps": 40000, "loss": 0.2027, "lr": 1.9653779019771678e-05, "epoch": 18.61318051575931, "percentage": 56.86, "elapsed_time": "2:36:46", "remaining_time": "1:58:55", "throughput": 787.83, "total_tokens": 7410624} {"current_steps": 22750, "total_steps": 40000, "loss": 0.1567, "lr": 1.9644189065219488e-05, "epoch": 18.617273843634877, "percentage": 56.88, "elapsed_time": "2:36:48", "remaining_time": "1:58:53", "throughput": 787.86, "total_tokens": 7412288} {"current_steps": 22755, "total_steps": 40000, "loss": 0.1032, "lr": 1.9634599936600655e-05, "epoch": 18.62136717151044, "percentage": 56.89, "elapsed_time": "2:36:49", "remaining_time": "1:58:51", "throughput": 787.89, "total_tokens": 7413920} {"current_steps": 22760, "total_steps": 40000, "loss": 0.2145, "lr": 1.9625011635393935e-05, "epoch": 18.625460499386, "percentage": 56.9, "elapsed_time": "2:36:51", "remaining_time": "1:58:48", "throughput": 787.93, "total_tokens": 7415584} {"current_steps": 22765, "total_steps": 40000, "loss": 0.1421, "lr": 1.9615424163077963e-05, "epoch": 18.629553827261564, "percentage": 56.91, "elapsed_time": "2:36:53", "remaining_time": "1:58:46", "throughput": 787.96, "total_tokens": 7417232} {"current_steps": 22770, "total_steps": 40000, "loss": 0.2074, "lr": 1.9605837521131263e-05, "epoch": 18.633647155137126, "percentage": 56.93, "elapsed_time": "2:36:54", "remaining_time": "1:58:44", "throughput": 788.0, "total_tokens": 7418928} {"current_steps": 22775, "total_steps": 40000, "loss": 0.2388, "lr": 1.9596251711032192e-05, "epoch": 18.63774048301269, "percentage": 56.94, "elapsed_time": "2:36:56", "remaining_time": "1:58:41", "throughput": 788.03, "total_tokens": 7420576} {"current_steps": 22780, "total_steps": 40000, "loss": 0.2001, "lr": 1.958666673425903e-05, "epoch": 18.64183381088825, "percentage": 56.95, "elapsed_time": "2:36:58", "remaining_time": "1:58:39", "throughput": 788.06, "total_tokens": 7422240} {"current_steps": 22785, "total_steps": 40000, "loss": 0.1792, "lr": 1.957708259228987e-05, "epoch": 18.645927138763817, "percentage": 56.96, "elapsed_time": "2:37:00", "remaining_time": "1:58:37", "throughput": 788.08, "total_tokens": 7423792} {"current_steps": 22790, "total_steps": 40000, "loss": 0.1542, "lr": 1.956749928660273e-05, "epoch": 18.65002046663938, "percentage": 56.97, "elapsed_time": "2:37:01", "remaining_time": "1:58:34", "throughput": 788.11, "total_tokens": 7425408} {"current_steps": 22795, "total_steps": 40000, "loss": 0.2787, "lr": 1.955791681867547e-05, "epoch": 18.65411379451494, "percentage": 56.99, "elapsed_time": "2:37:03", "remaining_time": "1:58:32", "throughput": 788.13, "total_tokens": 7426992} {"current_steps": 22800, "total_steps": 40000, "loss": 0.1878, "lr": 1.9548335189985824e-05, "epoch": 18.658207122390504, "percentage": 57.0, "elapsed_time": "2:37:05", "remaining_time": "1:58:30", "throughput": 788.17, "total_tokens": 7428672} {"current_steps": 22800, "total_steps": 40000, "eval_loss": 0.21000702679157257, "epoch": 18.658207122390504, "percentage": 57.0, "elapsed_time": "2:37:17", "remaining_time": "1:58:39", "throughput": 787.13, "total_tokens": 7428672} {"current_steps": 22805, "total_steps": 40000, "loss": 0.1163, "lr": 1.9538754402011396e-05, "epoch": 18.662300450266066, "percentage": 57.01, "elapsed_time": "2:37:20", "remaining_time": "1:58:38", "throughput": 787.04, "total_tokens": 7430352} {"current_steps": 22810, "total_steps": 40000, "loss": 0.1497, "lr": 1.952917445622968e-05, "epoch": 18.66639377814163, "percentage": 57.03, "elapsed_time": "2:37:22", "remaining_time": "1:58:36", "throughput": 787.06, "total_tokens": 7431936} {"current_steps": 22815, "total_steps": 40000, "loss": 0.142, "lr": 1.9519595354118005e-05, "epoch": 18.67048710601719, "percentage": 57.04, "elapsed_time": "2:37:24", "remaining_time": "1:58:33", "throughput": 787.09, "total_tokens": 7433552} {"current_steps": 22820, "total_steps": 40000, "loss": 0.2401, "lr": 1.951001709715361e-05, "epoch": 18.674580433892753, "percentage": 57.05, "elapsed_time": "2:37:26", "remaining_time": "1:58:31", "throughput": 787.12, "total_tokens": 7435152} {"current_steps": 22825, "total_steps": 40000, "loss": 0.2736, "lr": 1.9500439686813556e-05, "epoch": 18.678673761768316, "percentage": 57.06, "elapsed_time": "2:37:27", "remaining_time": "1:58:29", "throughput": 787.15, "total_tokens": 7436800} {"current_steps": 22830, "total_steps": 40000, "loss": 0.2183, "lr": 1.949086312457482e-05, "epoch": 18.68276708964388, "percentage": 57.07, "elapsed_time": "2:37:29", "remaining_time": "1:58:26", "throughput": 787.18, "total_tokens": 7438416} {"current_steps": 22835, "total_steps": 40000, "loss": 0.1624, "lr": 1.9481287411914223e-05, "epoch": 18.686860417519444, "percentage": 57.09, "elapsed_time": "2:37:31", "remaining_time": "1:58:24", "throughput": 787.2, "total_tokens": 7439984} {"current_steps": 22840, "total_steps": 40000, "loss": 0.2053, "lr": 1.9471712550308457e-05, "epoch": 18.690953745395007, "percentage": 57.1, "elapsed_time": "2:37:32", "remaining_time": "1:58:22", "throughput": 787.23, "total_tokens": 7441600} {"current_steps": 22845, "total_steps": 40000, "loss": 0.1465, "lr": 1.946213854123409e-05, "epoch": 18.69504707327057, "percentage": 57.11, "elapsed_time": "2:37:34", "remaining_time": "1:58:19", "throughput": 787.26, "total_tokens": 7443248} {"current_steps": 22850, "total_steps": 40000, "loss": 0.1935, "lr": 1.9452565386167554e-05, "epoch": 18.69914040114613, "percentage": 57.12, "elapsed_time": "2:37:36", "remaining_time": "1:58:17", "throughput": 787.28, "total_tokens": 7444832} {"current_steps": 22855, "total_steps": 40000, "loss": 0.2133, "lr": 1.9442993086585142e-05, "epoch": 18.703233729021694, "percentage": 57.14, "elapsed_time": "2:37:38", "remaining_time": "1:58:15", "throughput": 787.32, "total_tokens": 7446512} {"current_steps": 22860, "total_steps": 40000, "loss": 0.1919, "lr": 1.9433421643963043e-05, "epoch": 18.707327056897256, "percentage": 57.15, "elapsed_time": "2:37:39", "remaining_time": "1:58:12", "throughput": 787.34, "total_tokens": 7448096} {"current_steps": 22865, "total_steps": 40000, "loss": 0.2305, "lr": 1.942385105977727e-05, "epoch": 18.711420384772822, "percentage": 57.16, "elapsed_time": "2:37:41", "remaining_time": "1:58:10", "throughput": 787.37, "total_tokens": 7449712} {"current_steps": 22870, "total_steps": 40000, "loss": 0.1656, "lr": 1.9414281335503743e-05, "epoch": 18.715513712648384, "percentage": 57.17, "elapsed_time": "2:37:43", "remaining_time": "1:58:08", "throughput": 787.39, "total_tokens": 7451312} {"current_steps": 22875, "total_steps": 40000, "loss": 0.1865, "lr": 1.9404712472618232e-05, "epoch": 18.719607040523947, "percentage": 57.19, "elapsed_time": "2:37:44", "remaining_time": "1:58:05", "throughput": 787.43, "total_tokens": 7453024} {"current_steps": 22880, "total_steps": 40000, "loss": 0.1898, "lr": 1.939514447259636e-05, "epoch": 18.72370036839951, "percentage": 57.2, "elapsed_time": "2:37:46", "remaining_time": "1:58:03", "throughput": 787.46, "total_tokens": 7454672} {"current_steps": 22885, "total_steps": 40000, "loss": 0.1493, "lr": 1.938557733691365e-05, "epoch": 18.72779369627507, "percentage": 57.21, "elapsed_time": "2:37:48", "remaining_time": "1:58:01", "throughput": 787.48, "total_tokens": 7456240} {"current_steps": 22890, "total_steps": 40000, "loss": 0.126, "lr": 1.9376011067045476e-05, "epoch": 18.731887024150634, "percentage": 57.23, "elapsed_time": "2:37:50", "remaining_time": "1:57:58", "throughput": 787.51, "total_tokens": 7457824} {"current_steps": 22895, "total_steps": 40000, "loss": 0.2089, "lr": 1.9366445664467065e-05, "epoch": 18.735980352026196, "percentage": 57.24, "elapsed_time": "2:37:51", "remaining_time": "1:57:56", "throughput": 787.54, "total_tokens": 7459440} {"current_steps": 22900, "total_steps": 40000, "loss": 0.1767, "lr": 1.9356881130653533e-05, "epoch": 18.74007367990176, "percentage": 57.25, "elapsed_time": "2:37:53", "remaining_time": "1:57:54", "throughput": 787.57, "total_tokens": 7461072} {"current_steps": 22905, "total_steps": 40000, "loss": 0.1687, "lr": 1.9347317467079846e-05, "epoch": 18.744167007777325, "percentage": 57.26, "elapsed_time": "2:37:55", "remaining_time": "1:57:51", "throughput": 787.6, "total_tokens": 7462704} {"current_steps": 22910, "total_steps": 40000, "loss": 0.1624, "lr": 1.9337754675220836e-05, "epoch": 18.748260335652887, "percentage": 57.27, "elapsed_time": "2:37:57", "remaining_time": "1:57:49", "throughput": 787.62, "total_tokens": 7464304} {"current_steps": 22915, "total_steps": 40000, "loss": 0.1154, "lr": 1.9328192756551218e-05, "epoch": 18.75235366352845, "percentage": 57.29, "elapsed_time": "2:37:58", "remaining_time": "1:57:47", "throughput": 787.65, "total_tokens": 7465936} {"current_steps": 22920, "total_steps": 40000, "loss": 0.1248, "lr": 1.931863171254555e-05, "epoch": 18.75644699140401, "percentage": 57.3, "elapsed_time": "2:38:00", "remaining_time": "1:57:44", "throughput": 787.67, "total_tokens": 7467488} {"current_steps": 22925, "total_steps": 40000, "loss": 0.1694, "lr": 1.930907154467826e-05, "epoch": 18.760540319279574, "percentage": 57.31, "elapsed_time": "2:38:02", "remaining_time": "1:57:42", "throughput": 787.7, "total_tokens": 7469120} {"current_steps": 22930, "total_steps": 40000, "loss": 0.1907, "lr": 1.9299512254423673e-05, "epoch": 18.764633647155136, "percentage": 57.33, "elapsed_time": "2:38:03", "remaining_time": "1:57:40", "throughput": 787.74, "total_tokens": 7470832} {"current_steps": 22935, "total_steps": 40000, "loss": 0.0749, "lr": 1.9289953843255914e-05, "epoch": 18.7687269750307, "percentage": 57.34, "elapsed_time": "2:38:05", "remaining_time": "1:57:37", "throughput": 787.77, "total_tokens": 7472448} {"current_steps": 22940, "total_steps": 40000, "loss": 0.2533, "lr": 1.9280396312649048e-05, "epoch": 18.77282030290626, "percentage": 57.35, "elapsed_time": "2:38:07", "remaining_time": "1:57:35", "throughput": 787.79, "total_tokens": 7474032} {"current_steps": 22945, "total_steps": 40000, "loss": 0.1303, "lr": 1.9270839664076936e-05, "epoch": 18.776913630781827, "percentage": 57.36, "elapsed_time": "2:38:09", "remaining_time": "1:57:33", "throughput": 787.82, "total_tokens": 7475680} {"current_steps": 22950, "total_steps": 40000, "loss": 0.1089, "lr": 1.9261283899013345e-05, "epoch": 18.78100695865739, "percentage": 57.38, "elapsed_time": "2:38:10", "remaining_time": "1:57:30", "throughput": 787.84, "total_tokens": 7477232} {"current_steps": 22955, "total_steps": 40000, "loss": 0.1615, "lr": 1.92517290189319e-05, "epoch": 18.785100286532952, "percentage": 57.39, "elapsed_time": "2:38:12", "remaining_time": "1:57:28", "throughput": 787.87, "total_tokens": 7478832} {"current_steps": 22960, "total_steps": 40000, "loss": 0.1204, "lr": 1.924217502530607e-05, "epoch": 18.789193614408514, "percentage": 57.4, "elapsed_time": "2:38:14", "remaining_time": "1:57:26", "throughput": 787.9, "total_tokens": 7480480} {"current_steps": 22965, "total_steps": 40000, "loss": 0.1282, "lr": 1.9232621919609207e-05, "epoch": 18.793286942284077, "percentage": 57.41, "elapsed_time": "2:38:15", "remaining_time": "1:57:23", "throughput": 787.94, "total_tokens": 7482256} {"current_steps": 22970, "total_steps": 40000, "loss": 0.135, "lr": 1.9223069703314534e-05, "epoch": 18.79738027015964, "percentage": 57.43, "elapsed_time": "2:38:17", "remaining_time": "1:57:21", "throughput": 787.97, "total_tokens": 7483840} {"current_steps": 22975, "total_steps": 40000, "loss": 0.2483, "lr": 1.92135183778951e-05, "epoch": 18.8014735980352, "percentage": 57.44, "elapsed_time": "2:38:19", "remaining_time": "1:57:19", "throughput": 787.99, "total_tokens": 7485408} {"current_steps": 22980, "total_steps": 40000, "loss": 0.1592, "lr": 1.9203967944823857e-05, "epoch": 18.805566925910764, "percentage": 57.45, "elapsed_time": "2:38:21", "remaining_time": "1:57:16", "throughput": 788.02, "total_tokens": 7487024} {"current_steps": 22985, "total_steps": 40000, "loss": 0.132, "lr": 1.9194418405573588e-05, "epoch": 18.80966025378633, "percentage": 57.46, "elapsed_time": "2:38:22", "remaining_time": "1:57:14", "throughput": 788.05, "total_tokens": 7488672} {"current_steps": 22990, "total_steps": 40000, "loss": 0.1022, "lr": 1.9184869761616954e-05, "epoch": 18.813753581661892, "percentage": 57.48, "elapsed_time": "2:38:24", "remaining_time": "1:57:12", "throughput": 788.08, "total_tokens": 7490288} {"current_steps": 22995, "total_steps": 40000, "loss": 0.2044, "lr": 1.9175322014426495e-05, "epoch": 18.817846909537455, "percentage": 57.49, "elapsed_time": "2:38:26", "remaining_time": "1:57:09", "throughput": 788.1, "total_tokens": 7491888} {"current_steps": 23000, "total_steps": 40000, "loss": 0.1361, "lr": 1.9165775165474565e-05, "epoch": 18.821940237413017, "percentage": 57.5, "elapsed_time": "2:38:27", "remaining_time": "1:57:07", "throughput": 788.13, "total_tokens": 7493504} {"current_steps": 23000, "total_steps": 40000, "eval_loss": 0.21250493824481964, "epoch": 18.821940237413017, "percentage": 57.5, "elapsed_time": "2:38:40", "remaining_time": "1:57:16", "throughput": 787.1, "total_tokens": 7493504} {"current_steps": 23005, "total_steps": 40000, "loss": 0.1292, "lr": 1.9156229216233434e-05, "epoch": 18.82603356528858, "percentage": 57.51, "elapsed_time": "2:38:43", "remaining_time": "1:57:15", "throughput": 787.01, "total_tokens": 7495152} {"current_steps": 23010, "total_steps": 40000, "loss": 0.1114, "lr": 1.9146684168175184e-05, "epoch": 18.83012689316414, "percentage": 57.53, "elapsed_time": "2:38:45", "remaining_time": "1:57:13", "throughput": 787.04, "total_tokens": 7496800} {"current_steps": 23015, "total_steps": 40000, "loss": 0.226, "lr": 1.9137140022771796e-05, "epoch": 18.834220221039704, "percentage": 57.54, "elapsed_time": "2:38:47", "remaining_time": "1:57:10", "throughput": 787.06, "total_tokens": 7498384} {"current_steps": 23020, "total_steps": 40000, "loss": 0.2295, "lr": 1.9127596781495103e-05, "epoch": 18.838313548915266, "percentage": 57.55, "elapsed_time": "2:38:48", "remaining_time": "1:57:08", "throughput": 787.09, "total_tokens": 7499984} {"current_steps": 23025, "total_steps": 40000, "loss": 0.1802, "lr": 1.9118054445816767e-05, "epoch": 18.842406876790832, "percentage": 57.56, "elapsed_time": "2:38:50", "remaining_time": "1:57:06", "throughput": 787.11, "total_tokens": 7501552} {"current_steps": 23030, "total_steps": 40000, "loss": 0.1204, "lr": 1.9108513017208356e-05, "epoch": 18.846500204666395, "percentage": 57.57, "elapsed_time": "2:38:52", "remaining_time": "1:57:03", "throughput": 787.13, "total_tokens": 7503136} {"current_steps": 23035, "total_steps": 40000, "loss": 0.1852, "lr": 1.9098972497141287e-05, "epoch": 18.850593532541957, "percentage": 57.59, "elapsed_time": "2:38:53", "remaining_time": "1:57:01", "throughput": 787.16, "total_tokens": 7504720} {"current_steps": 23040, "total_steps": 40000, "loss": 0.1328, "lr": 1.9089432887086806e-05, "epoch": 18.85468686041752, "percentage": 57.6, "elapsed_time": "2:38:55", "remaining_time": "1:56:59", "throughput": 787.19, "total_tokens": 7506352} {"current_steps": 23045, "total_steps": 40000, "loss": 0.1724, "lr": 1.9079894188516056e-05, "epoch": 18.858780188293082, "percentage": 57.61, "elapsed_time": "2:38:57", "remaining_time": "1:56:57", "throughput": 787.2, "total_tokens": 7508016} {"current_steps": 23050, "total_steps": 40000, "loss": 0.226, "lr": 1.907035640290002e-05, "epoch": 18.862873516168644, "percentage": 57.63, "elapsed_time": "2:38:59", "remaining_time": "1:56:54", "throughput": 787.22, "total_tokens": 7509616} {"current_steps": 23055, "total_steps": 40000, "loss": 0.1719, "lr": 1.9060819531709534e-05, "epoch": 18.866966844044207, "percentage": 57.64, "elapsed_time": "2:39:01", "remaining_time": "1:56:52", "throughput": 787.25, "total_tokens": 7511216} {"current_steps": 23060, "total_steps": 40000, "loss": 0.2052, "lr": 1.9051283576415325e-05, "epoch": 18.871060171919773, "percentage": 57.65, "elapsed_time": "2:39:02", "remaining_time": "1:56:50", "throughput": 787.27, "total_tokens": 7512816} {"current_steps": 23065, "total_steps": 40000, "loss": 0.2278, "lr": 1.904174853848793e-05, "epoch": 18.875153499795335, "percentage": 57.66, "elapsed_time": "2:39:04", "remaining_time": "1:56:47", "throughput": 787.3, "total_tokens": 7514448} {"current_steps": 23070, "total_steps": 40000, "loss": 0.1512, "lr": 1.903221441939779e-05, "epoch": 18.879246827670897, "percentage": 57.67, "elapsed_time": "2:39:06", "remaining_time": "1:56:45", "throughput": 787.33, "total_tokens": 7516016} {"current_steps": 23075, "total_steps": 40000, "loss": 0.1533, "lr": 1.9022681220615194e-05, "epoch": 18.88334015554646, "percentage": 57.69, "elapsed_time": "2:39:07", "remaining_time": "1:56:43", "throughput": 787.36, "total_tokens": 7517680} {"current_steps": 23080, "total_steps": 40000, "loss": 0.1119, "lr": 1.9013148943610255e-05, "epoch": 18.887433483422022, "percentage": 57.7, "elapsed_time": "2:39:09", "remaining_time": "1:56:40", "throughput": 787.39, "total_tokens": 7519328} {"current_steps": 23085, "total_steps": 40000, "loss": 0.2023, "lr": 1.9003617589852998e-05, "epoch": 18.891526811297584, "percentage": 57.71, "elapsed_time": "2:39:11", "remaining_time": "1:56:38", "throughput": 787.42, "total_tokens": 7520992} {"current_steps": 23090, "total_steps": 40000, "loss": 0.1843, "lr": 1.899408716081326e-05, "epoch": 18.895620139173147, "percentage": 57.73, "elapsed_time": "2:39:13", "remaining_time": "1:56:36", "throughput": 787.44, "total_tokens": 7522560} {"current_steps": 23095, "total_steps": 40000, "loss": 0.1427, "lr": 1.898455765796075e-05, "epoch": 18.89971346704871, "percentage": 57.74, "elapsed_time": "2:39:14", "remaining_time": "1:56:33", "throughput": 787.48, "total_tokens": 7524208} {"current_steps": 23100, "total_steps": 40000, "loss": 0.1356, "lr": 1.8975029082765053e-05, "epoch": 18.90380679492427, "percentage": 57.75, "elapsed_time": "2:39:16", "remaining_time": "1:56:31", "throughput": 787.5, "total_tokens": 7525840} {"current_steps": 23105, "total_steps": 40000, "loss": 0.115, "lr": 1.8965501436695577e-05, "epoch": 18.907900122799838, "percentage": 57.76, "elapsed_time": "2:39:18", "remaining_time": "1:56:29", "throughput": 787.53, "total_tokens": 7527424} {"current_steps": 23110, "total_steps": 40000, "loss": 0.1835, "lr": 1.895597472122161e-05, "epoch": 18.9119934506754, "percentage": 57.77, "elapsed_time": "2:39:19", "remaining_time": "1:56:26", "throughput": 787.56, "total_tokens": 7529040} {"current_steps": 23115, "total_steps": 40000, "loss": 0.2128, "lr": 1.894644893781231e-05, "epoch": 18.916086778550962, "percentage": 57.79, "elapsed_time": "2:39:21", "remaining_time": "1:56:24", "throughput": 787.58, "total_tokens": 7530656} {"current_steps": 23120, "total_steps": 40000, "loss": 0.1311, "lr": 1.893692408793665e-05, "epoch": 18.920180106426525, "percentage": 57.8, "elapsed_time": "2:39:23", "remaining_time": "1:56:22", "throughput": 787.61, "total_tokens": 7532288} {"current_steps": 23125, "total_steps": 40000, "loss": 0.1668, "lr": 1.8927400173063493e-05, "epoch": 18.924273434302087, "percentage": 57.81, "elapsed_time": "2:39:25", "remaining_time": "1:56:19", "throughput": 787.64, "total_tokens": 7533936} {"current_steps": 23130, "total_steps": 40000, "loss": 0.1277, "lr": 1.891787719466154e-05, "epoch": 18.92836676217765, "percentage": 57.83, "elapsed_time": "2:39:26", "remaining_time": "1:56:17", "throughput": 787.68, "total_tokens": 7535664} {"current_steps": 23135, "total_steps": 40000, "loss": 0.1901, "lr": 1.8908355154199346e-05, "epoch": 18.932460090053212, "percentage": 57.84, "elapsed_time": "2:39:28", "remaining_time": "1:56:15", "throughput": 787.72, "total_tokens": 7537312} {"current_steps": 23140, "total_steps": 40000, "loss": 0.1664, "lr": 1.8898834053145357e-05, "epoch": 18.936553417928778, "percentage": 57.85, "elapsed_time": "2:39:30", "remaining_time": "1:56:13", "throughput": 787.74, "total_tokens": 7538928} {"current_steps": 23145, "total_steps": 40000, "loss": 0.1602, "lr": 1.8889313892967813e-05, "epoch": 18.94064674580434, "percentage": 57.86, "elapsed_time": "2:39:32", "remaining_time": "1:56:10", "throughput": 787.77, "total_tokens": 7540592} {"current_steps": 23150, "total_steps": 40000, "loss": 0.169, "lr": 1.8879794675134863e-05, "epoch": 18.944740073679903, "percentage": 57.88, "elapsed_time": "2:39:33", "remaining_time": "1:56:08", "throughput": 787.8, "total_tokens": 7542192} {"current_steps": 23155, "total_steps": 40000, "loss": 0.1322, "lr": 1.8870276401114494e-05, "epoch": 18.948833401555465, "percentage": 57.89, "elapsed_time": "2:39:35", "remaining_time": "1:56:06", "throughput": 787.83, "total_tokens": 7543824} {"current_steps": 23160, "total_steps": 40000, "loss": 0.2302, "lr": 1.886075907237453e-05, "epoch": 18.952926729431027, "percentage": 57.9, "elapsed_time": "2:39:37", "remaining_time": "1:56:03", "throughput": 787.85, "total_tokens": 7545424} {"current_steps": 23165, "total_steps": 40000, "loss": 0.1944, "lr": 1.8851242690382672e-05, "epoch": 18.95702005730659, "percentage": 57.91, "elapsed_time": "2:39:38", "remaining_time": "1:56:01", "throughput": 787.89, "total_tokens": 7547120} {"current_steps": 23170, "total_steps": 40000, "loss": 0.2443, "lr": 1.884172725660645e-05, "epoch": 18.961113385182152, "percentage": 57.93, "elapsed_time": "2:39:40", "remaining_time": "1:55:59", "throughput": 787.92, "total_tokens": 7548736} {"current_steps": 23175, "total_steps": 40000, "loss": 0.1357, "lr": 1.8832212772513277e-05, "epoch": 18.965206713057714, "percentage": 57.94, "elapsed_time": "2:39:42", "remaining_time": "1:55:56", "throughput": 787.95, "total_tokens": 7550352} {"current_steps": 23180, "total_steps": 40000, "loss": 0.1604, "lr": 1.8822699239570414e-05, "epoch": 18.96930004093328, "percentage": 57.95, "elapsed_time": "2:39:44", "remaining_time": "1:55:54", "throughput": 787.98, "total_tokens": 7552032} {"current_steps": 23185, "total_steps": 40000, "loss": 0.1085, "lr": 1.8813186659244943e-05, "epoch": 18.973393368808843, "percentage": 57.96, "elapsed_time": "2:39:45", "remaining_time": "1:55:52", "throughput": 788.01, "total_tokens": 7553648} {"current_steps": 23190, "total_steps": 40000, "loss": 0.2011, "lr": 1.880367503300385e-05, "epoch": 18.977486696684405, "percentage": 57.98, "elapsed_time": "2:39:47", "remaining_time": "1:55:49", "throughput": 788.03, "total_tokens": 7555248} {"current_steps": 23195, "total_steps": 40000, "loss": 0.1985, "lr": 1.8794164362313927e-05, "epoch": 18.981580024559968, "percentage": 57.99, "elapsed_time": "2:39:49", "remaining_time": "1:55:47", "throughput": 788.06, "total_tokens": 7556832} {"current_steps": 23200, "total_steps": 40000, "loss": 0.2363, "lr": 1.878465464864185e-05, "epoch": 18.98567335243553, "percentage": 58.0, "elapsed_time": "2:39:50", "remaining_time": "1:55:45", "throughput": 788.08, "total_tokens": 7558400} {"current_steps": 23200, "total_steps": 40000, "eval_loss": 0.2082197368144989, "epoch": 18.98567335243553, "percentage": 58.0, "elapsed_time": "2:40:03", "remaining_time": "1:55:54", "throughput": 787.06, "total_tokens": 7558400} {"current_steps": 23205, "total_steps": 40000, "loss": 0.2201, "lr": 1.877514589345414e-05, "epoch": 18.989766680311092, "percentage": 58.01, "elapsed_time": "2:40:07", "remaining_time": "1:55:53", "throughput": 786.92, "total_tokens": 7559984} {"current_steps": 23210, "total_steps": 40000, "loss": 0.115, "lr": 1.876563809821715e-05, "epoch": 18.993860008186655, "percentage": 58.03, "elapsed_time": "2:40:08", "remaining_time": "1:55:50", "throughput": 786.96, "total_tokens": 7561648} {"current_steps": 23215, "total_steps": 40000, "loss": 0.1455, "lr": 1.8756131264397106e-05, "epoch": 18.997953336062217, "percentage": 58.04, "elapsed_time": "2:40:10", "remaining_time": "1:55:48", "throughput": 786.99, "total_tokens": 7563328} {"current_steps": 23220, "total_steps": 40000, "loss": 0.3401, "lr": 1.87466253934601e-05, "epoch": 19.001637331150224, "percentage": 58.05, "elapsed_time": "2:40:12", "remaining_time": "1:55:46", "throughput": 786.97, "total_tokens": 7564656} {"current_steps": 23225, "total_steps": 40000, "loss": 0.1274, "lr": 1.8737120486872033e-05, "epoch": 19.005730659025787, "percentage": 58.06, "elapsed_time": "2:40:14", "remaining_time": "1:55:44", "throughput": 787.0, "total_tokens": 7566304} {"current_steps": 23230, "total_steps": 40000, "loss": 0.0948, "lr": 1.8727616546098696e-05, "epoch": 19.009823986901353, "percentage": 58.07, "elapsed_time": "2:40:15", "remaining_time": "1:55:41", "throughput": 787.03, "total_tokens": 7567920} {"current_steps": 23235, "total_steps": 40000, "loss": 0.2741, "lr": 1.8718113572605716e-05, "epoch": 19.013917314776915, "percentage": 58.09, "elapsed_time": "2:40:17", "remaining_time": "1:55:39", "throughput": 787.06, "total_tokens": 7569552} {"current_steps": 23240, "total_steps": 40000, "loss": 0.1879, "lr": 1.8708611567858554e-05, "epoch": 19.018010642652477, "percentage": 58.1, "elapsed_time": "2:40:19", "remaining_time": "1:55:37", "throughput": 787.09, "total_tokens": 7571216} {"current_steps": 23245, "total_steps": 40000, "loss": 0.2742, "lr": 1.8699110533322565e-05, "epoch": 19.02210397052804, "percentage": 58.11, "elapsed_time": "2:40:20", "remaining_time": "1:55:34", "throughput": 787.11, "total_tokens": 7572800} {"current_steps": 23250, "total_steps": 40000, "loss": 0.1258, "lr": 1.8689610470462897e-05, "epoch": 19.026197298403602, "percentage": 58.13, "elapsed_time": "2:40:22", "remaining_time": "1:55:32", "throughput": 787.14, "total_tokens": 7574416} {"current_steps": 23255, "total_steps": 40000, "loss": 0.1765, "lr": 1.8680111380744604e-05, "epoch": 19.030290626279164, "percentage": 58.14, "elapsed_time": "2:40:24", "remaining_time": "1:55:30", "throughput": 787.18, "total_tokens": 7576096} {"current_steps": 23260, "total_steps": 40000, "loss": 0.1405, "lr": 1.8670613265632564e-05, "epoch": 19.034383954154727, "percentage": 58.15, "elapsed_time": "2:40:26", "remaining_time": "1:55:27", "throughput": 787.21, "total_tokens": 7577760} {"current_steps": 23265, "total_steps": 40000, "loss": 0.1903, "lr": 1.866111612659149e-05, "epoch": 19.03847728203029, "percentage": 58.16, "elapsed_time": "2:40:27", "remaining_time": "1:55:25", "throughput": 787.24, "total_tokens": 7579424} {"current_steps": 23270, "total_steps": 40000, "loss": 0.214, "lr": 1.8651619965085967e-05, "epoch": 19.042570609905855, "percentage": 58.17, "elapsed_time": "2:40:29", "remaining_time": "1:55:23", "throughput": 787.27, "total_tokens": 7581040} {"current_steps": 23275, "total_steps": 40000, "loss": 0.1783, "lr": 1.8642124782580433e-05, "epoch": 19.046663937781418, "percentage": 58.19, "elapsed_time": "2:40:31", "remaining_time": "1:55:20", "throughput": 787.3, "total_tokens": 7582704} {"current_steps": 23280, "total_steps": 40000, "loss": 0.2574, "lr": 1.8632630580539144e-05, "epoch": 19.05075726565698, "percentage": 58.2, "elapsed_time": "2:40:33", "remaining_time": "1:55:18", "throughput": 787.32, "total_tokens": 7584288} {"current_steps": 23285, "total_steps": 40000, "loss": 0.106, "lr": 1.862313736042625e-05, "epoch": 19.054850593532542, "percentage": 58.21, "elapsed_time": "2:40:34", "remaining_time": "1:55:16", "throughput": 787.36, "total_tokens": 7585952} {"current_steps": 23290, "total_steps": 40000, "loss": 0.1881, "lr": 1.8613645123705703e-05, "epoch": 19.058943921408105, "percentage": 58.23, "elapsed_time": "2:40:36", "remaining_time": "1:55:13", "throughput": 787.38, "total_tokens": 7587536} {"current_steps": 23295, "total_steps": 40000, "loss": 0.166, "lr": 1.8604153871841328e-05, "epoch": 19.063037249283667, "percentage": 58.24, "elapsed_time": "2:40:38", "remaining_time": "1:55:11", "throughput": 787.41, "total_tokens": 7589168} {"current_steps": 23300, "total_steps": 40000, "loss": 0.1768, "lr": 1.859466360629682e-05, "epoch": 19.06713057715923, "percentage": 58.25, "elapsed_time": "2:40:39", "remaining_time": "1:55:09", "throughput": 787.44, "total_tokens": 7590784} {"current_steps": 23305, "total_steps": 40000, "loss": 0.1776, "lr": 1.8585174328535666e-05, "epoch": 19.071223905034792, "percentage": 58.26, "elapsed_time": "2:40:41", "remaining_time": "1:55:06", "throughput": 787.47, "total_tokens": 7592432} {"current_steps": 23310, "total_steps": 40000, "loss": 0.163, "lr": 1.857568604002124e-05, "epoch": 19.075317232910358, "percentage": 58.27, "elapsed_time": "2:40:43", "remaining_time": "1:55:04", "throughput": 787.49, "total_tokens": 7594064} {"current_steps": 23315, "total_steps": 40000, "loss": 0.1841, "lr": 1.8566198742216774e-05, "epoch": 19.07941056078592, "percentage": 58.29, "elapsed_time": "2:40:45", "remaining_time": "1:55:02", "throughput": 787.52, "total_tokens": 7595632} {"current_steps": 23320, "total_steps": 40000, "loss": 0.2203, "lr": 1.85567124365853e-05, "epoch": 19.083503888661483, "percentage": 58.3, "elapsed_time": "2:40:46", "remaining_time": "1:55:00", "throughput": 787.54, "total_tokens": 7597200} {"current_steps": 23325, "total_steps": 40000, "loss": 0.1805, "lr": 1.854722712458975e-05, "epoch": 19.087597216537045, "percentage": 58.31, "elapsed_time": "2:40:48", "remaining_time": "1:54:57", "throughput": 787.57, "total_tokens": 7598864} {"current_steps": 23330, "total_steps": 40000, "loss": 0.1286, "lr": 1.853774280769286e-05, "epoch": 19.091690544412607, "percentage": 58.33, "elapsed_time": "2:40:50", "remaining_time": "1:54:55", "throughput": 787.6, "total_tokens": 7600496} {"current_steps": 23335, "total_steps": 40000, "loss": 0.1824, "lr": 1.852825948735724e-05, "epoch": 19.09578387228817, "percentage": 58.34, "elapsed_time": "2:40:51", "remaining_time": "1:54:53", "throughput": 787.63, "total_tokens": 7602176} {"current_steps": 23340, "total_steps": 40000, "loss": 0.1781, "lr": 1.851877716504534e-05, "epoch": 19.099877200163732, "percentage": 58.35, "elapsed_time": "2:40:53", "remaining_time": "1:54:50", "throughput": 787.66, "total_tokens": 7603776} {"current_steps": 23345, "total_steps": 40000, "loss": 0.1438, "lr": 1.8509295842219448e-05, "epoch": 19.103970528039294, "percentage": 58.36, "elapsed_time": "2:40:55", "remaining_time": "1:54:48", "throughput": 787.69, "total_tokens": 7605424} {"current_steps": 23350, "total_steps": 40000, "loss": 0.2151, "lr": 1.8499815520341697e-05, "epoch": 19.10806385591486, "percentage": 58.38, "elapsed_time": "2:40:57", "remaining_time": "1:54:46", "throughput": 787.72, "total_tokens": 7607120} {"current_steps": 23355, "total_steps": 40000, "loss": 0.2395, "lr": 1.8490336200874094e-05, "epoch": 19.112157183790423, "percentage": 58.39, "elapsed_time": "2:40:58", "remaining_time": "1:54:43", "throughput": 787.75, "total_tokens": 7608720} {"current_steps": 23360, "total_steps": 40000, "loss": 0.2267, "lr": 1.848085788527844e-05, "epoch": 19.116250511665985, "percentage": 58.4, "elapsed_time": "2:41:00", "remaining_time": "1:54:41", "throughput": 787.77, "total_tokens": 7610320} {"current_steps": 23365, "total_steps": 40000, "loss": 0.1675, "lr": 1.847138057501644e-05, "epoch": 19.120343839541547, "percentage": 58.41, "elapsed_time": "2:41:02", "remaining_time": "1:54:39", "throughput": 787.81, "total_tokens": 7612000} {"current_steps": 23370, "total_steps": 40000, "loss": 0.1728, "lr": 1.8461904271549582e-05, "epoch": 19.12443716741711, "percentage": 58.43, "elapsed_time": "2:41:03", "remaining_time": "1:54:36", "throughput": 787.83, "total_tokens": 7613584} {"current_steps": 23375, "total_steps": 40000, "loss": 0.1937, "lr": 1.845242897633926e-05, "epoch": 19.128530495292672, "percentage": 58.44, "elapsed_time": "2:41:05", "remaining_time": "1:54:34", "throughput": 787.86, "total_tokens": 7615168} {"current_steps": 23380, "total_steps": 40000, "loss": 0.169, "lr": 1.844295469084667e-05, "epoch": 19.132623823168235, "percentage": 58.45, "elapsed_time": "2:41:07", "remaining_time": "1:54:32", "throughput": 787.89, "total_tokens": 7616832} {"current_steps": 23385, "total_steps": 40000, "loss": 0.1433, "lr": 1.843348141653286e-05, "epoch": 19.136717151043797, "percentage": 58.46, "elapsed_time": "2:41:09", "remaining_time": "1:54:29", "throughput": 787.91, "total_tokens": 7618416} {"current_steps": 23390, "total_steps": 40000, "loss": 0.1241, "lr": 1.842400915485874e-05, "epoch": 19.140810478919363, "percentage": 58.48, "elapsed_time": "2:41:10", "remaining_time": "1:54:27", "throughput": 787.94, "total_tokens": 7620032} {"current_steps": 23395, "total_steps": 40000, "loss": 0.1703, "lr": 1.8414537907285053e-05, "epoch": 19.144903806794925, "percentage": 58.49, "elapsed_time": "2:41:12", "remaining_time": "1:54:25", "throughput": 787.97, "total_tokens": 7621664} {"current_steps": 23400, "total_steps": 40000, "loss": 0.1438, "lr": 1.840506767527237e-05, "epoch": 19.148997134670488, "percentage": 58.5, "elapsed_time": "2:41:14", "remaining_time": "1:54:22", "throughput": 788.0, "total_tokens": 7623392} {"current_steps": 23400, "total_steps": 40000, "eval_loss": 0.20850802958011627, "epoch": 19.148997134670488, "percentage": 58.5, "elapsed_time": "2:41:26", "remaining_time": "1:54:31", "throughput": 786.99, "total_tokens": 7623392} {"current_steps": 23405, "total_steps": 40000, "loss": 0.1223, "lr": 1.8395598460281137e-05, "epoch": 19.15309046254605, "percentage": 58.51, "elapsed_time": "2:41:30", "remaining_time": "1:54:30", "throughput": 786.89, "total_tokens": 7624976} {"current_steps": 23410, "total_steps": 40000, "loss": 0.1394, "lr": 1.838613026377161e-05, "epoch": 19.157183790421612, "percentage": 58.53, "elapsed_time": "2:41:31", "remaining_time": "1:54:28", "throughput": 786.92, "total_tokens": 7626608} {"current_steps": 23415, "total_steps": 40000, "loss": 0.095, "lr": 1.8376663087203917e-05, "epoch": 19.161277118297175, "percentage": 58.54, "elapsed_time": "2:41:33", "remaining_time": "1:54:25", "throughput": 786.94, "total_tokens": 7628160} {"current_steps": 23420, "total_steps": 40000, "loss": 0.2398, "lr": 1.8367196932038014e-05, "epoch": 19.165370446172737, "percentage": 58.55, "elapsed_time": "2:41:35", "remaining_time": "1:54:23", "throughput": 786.97, "total_tokens": 7629888} {"current_steps": 23425, "total_steps": 40000, "loss": 0.1802, "lr": 1.8357731799733686e-05, "epoch": 19.1694637740483, "percentage": 58.56, "elapsed_time": "2:41:36", "remaining_time": "1:54:21", "throughput": 787.0, "total_tokens": 7631488} {"current_steps": 23430, "total_steps": 40000, "loss": 0.0823, "lr": 1.8348267691750586e-05, "epoch": 19.173557101923866, "percentage": 58.58, "elapsed_time": "2:41:38", "remaining_time": "1:54:19", "throughput": 787.03, "total_tokens": 7633152} {"current_steps": 23435, "total_steps": 40000, "loss": 0.1795, "lr": 1.833880460954821e-05, "epoch": 19.177650429799428, "percentage": 58.59, "elapsed_time": "2:41:40", "remaining_time": "1:54:16", "throughput": 787.06, "total_tokens": 7634816} {"current_steps": 23440, "total_steps": 40000, "loss": 0.2214, "lr": 1.8329342554585866e-05, "epoch": 19.18174375767499, "percentage": 58.6, "elapsed_time": "2:41:42", "remaining_time": "1:54:14", "throughput": 787.09, "total_tokens": 7636448} {"current_steps": 23445, "total_steps": 40000, "loss": 0.2762, "lr": 1.8319881528322735e-05, "epoch": 19.185837085550553, "percentage": 58.61, "elapsed_time": "2:41:43", "remaining_time": "1:54:12", "throughput": 787.13, "total_tokens": 7638128} {"current_steps": 23450, "total_steps": 40000, "loss": 0.1721, "lr": 1.8310421532217815e-05, "epoch": 19.189930413426115, "percentage": 58.63, "elapsed_time": "2:41:45", "remaining_time": "1:54:09", "throughput": 787.16, "total_tokens": 7639792} {"current_steps": 23455, "total_steps": 40000, "loss": 0.2251, "lr": 1.8300962567729958e-05, "epoch": 19.194023741301677, "percentage": 58.64, "elapsed_time": "2:41:47", "remaining_time": "1:54:07", "throughput": 787.18, "total_tokens": 7641408} {"current_steps": 23460, "total_steps": 40000, "loss": 0.1026, "lr": 1.8291504636317866e-05, "epoch": 19.19811706917724, "percentage": 58.65, "elapsed_time": "2:41:48", "remaining_time": "1:54:05", "throughput": 787.21, "total_tokens": 7643040} {"current_steps": 23465, "total_steps": 40000, "loss": 0.3217, "lr": 1.8282047739440055e-05, "epoch": 19.202210397052802, "percentage": 58.66, "elapsed_time": "2:41:50", "remaining_time": "1:54:02", "throughput": 787.25, "total_tokens": 7644736} {"current_steps": 23470, "total_steps": 40000, "loss": 0.1555, "lr": 1.8272591878554903e-05, "epoch": 19.206303724928368, "percentage": 58.67, "elapsed_time": "2:41:52", "remaining_time": "1:54:00", "throughput": 787.28, "total_tokens": 7646352} {"current_steps": 23475, "total_steps": 40000, "loss": 0.1156, "lr": 1.8263137055120638e-05, "epoch": 19.21039705280393, "percentage": 58.69, "elapsed_time": "2:41:54", "remaining_time": "1:53:58", "throughput": 787.31, "total_tokens": 7648000} {"current_steps": 23480, "total_steps": 40000, "loss": 0.1181, "lr": 1.8253683270595295e-05, "epoch": 19.214490380679493, "percentage": 58.7, "elapsed_time": "2:41:55", "remaining_time": "1:53:55", "throughput": 787.33, "total_tokens": 7649632} {"current_steps": 23485, "total_steps": 40000, "loss": 0.1888, "lr": 1.824423052643677e-05, "epoch": 19.218583708555055, "percentage": 58.71, "elapsed_time": "2:41:57", "remaining_time": "1:53:53", "throughput": 787.37, "total_tokens": 7651360} {"current_steps": 23490, "total_steps": 40000, "loss": 0.259, "lr": 1.82347788241028e-05, "epoch": 19.222677036430618, "percentage": 58.73, "elapsed_time": "2:41:59", "remaining_time": "1:53:51", "throughput": 787.4, "total_tokens": 7652976} {"current_steps": 23495, "total_steps": 40000, "loss": 0.2317, "lr": 1.8225328165050942e-05, "epoch": 19.22677036430618, "percentage": 58.74, "elapsed_time": "2:42:01", "remaining_time": "1:53:48", "throughput": 787.42, "total_tokens": 7654576} {"current_steps": 23500, "total_steps": 40000, "loss": 0.1415, "lr": 1.821587855073863e-05, "epoch": 19.230863692181742, "percentage": 58.75, "elapsed_time": "2:42:02", "remaining_time": "1:53:46", "throughput": 787.45, "total_tokens": 7656208} {"current_steps": 23505, "total_steps": 40000, "loss": 0.1112, "lr": 1.8206429982623086e-05, "epoch": 19.23495702005731, "percentage": 58.76, "elapsed_time": "2:42:04", "remaining_time": "1:53:44", "throughput": 787.48, "total_tokens": 7657792} {"current_steps": 23510, "total_steps": 40000, "loss": 0.1773, "lr": 1.8196982462161416e-05, "epoch": 19.23905034793287, "percentage": 58.77, "elapsed_time": "2:42:06", "remaining_time": "1:53:41", "throughput": 787.51, "total_tokens": 7659440} {"current_steps": 23515, "total_steps": 40000, "loss": 0.1624, "lr": 1.818753599081055e-05, "epoch": 19.243143675808433, "percentage": 58.79, "elapsed_time": "2:42:07", "remaining_time": "1:53:39", "throughput": 787.53, "total_tokens": 7661056} {"current_steps": 23520, "total_steps": 40000, "loss": 0.2038, "lr": 1.817809057002724e-05, "epoch": 19.247237003683995, "percentage": 58.8, "elapsed_time": "2:42:09", "remaining_time": "1:53:37", "throughput": 787.57, "total_tokens": 7662800} {"current_steps": 23525, "total_steps": 40000, "loss": 0.2069, "lr": 1.8168646201268096e-05, "epoch": 19.251330331559558, "percentage": 58.81, "elapsed_time": "2:42:11", "remaining_time": "1:53:35", "throughput": 787.59, "total_tokens": 7664352} {"current_steps": 23530, "total_steps": 40000, "loss": 0.1683, "lr": 1.8159202885989557e-05, "epoch": 19.25542365943512, "percentage": 58.83, "elapsed_time": "2:42:13", "remaining_time": "1:53:32", "throughput": 787.63, "total_tokens": 7666016} {"current_steps": 23535, "total_steps": 40000, "loss": 0.2288, "lr": 1.814976062564789e-05, "epoch": 19.259516987310683, "percentage": 58.84, "elapsed_time": "2:42:14", "remaining_time": "1:53:30", "throughput": 787.65, "total_tokens": 7667632} {"current_steps": 23540, "total_steps": 40000, "loss": 0.1999, "lr": 1.8140319421699234e-05, "epoch": 19.263610315186245, "percentage": 58.85, "elapsed_time": "2:42:16", "remaining_time": "1:53:28", "throughput": 787.67, "total_tokens": 7669184} {"current_steps": 23545, "total_steps": 40000, "loss": 0.1732, "lr": 1.8130879275599515e-05, "epoch": 19.26770364306181, "percentage": 58.86, "elapsed_time": "2:42:18", "remaining_time": "1:53:25", "throughput": 787.7, "total_tokens": 7670832} {"current_steps": 23550, "total_steps": 40000, "loss": 0.1482, "lr": 1.8121440188804544e-05, "epoch": 19.271796970937373, "percentage": 58.88, "elapsed_time": "2:42:19", "remaining_time": "1:53:23", "throughput": 787.73, "total_tokens": 7672464} {"current_steps": 23555, "total_steps": 40000, "loss": 0.1521, "lr": 1.811200216276993e-05, "epoch": 19.275890298812936, "percentage": 58.89, "elapsed_time": "2:42:21", "remaining_time": "1:53:21", "throughput": 787.76, "total_tokens": 7674080} {"current_steps": 23560, "total_steps": 40000, "loss": 0.153, "lr": 1.810256519895115e-05, "epoch": 19.279983626688498, "percentage": 58.9, "elapsed_time": "2:42:23", "remaining_time": "1:53:18", "throughput": 787.78, "total_tokens": 7675696} {"current_steps": 23565, "total_steps": 40000, "loss": 0.207, "lr": 1.8093129298803494e-05, "epoch": 19.28407695456406, "percentage": 58.91, "elapsed_time": "2:42:25", "remaining_time": "1:53:16", "throughput": 787.82, "total_tokens": 7677408} {"current_steps": 23570, "total_steps": 40000, "loss": 0.1971, "lr": 1.808369446378209e-05, "epoch": 19.288170282439623, "percentage": 58.93, "elapsed_time": "2:42:26", "remaining_time": "1:53:14", "throughput": 787.84, "total_tokens": 7678944} {"current_steps": 23575, "total_steps": 40000, "loss": 0.2359, "lr": 1.8074260695341914e-05, "epoch": 19.292263610315185, "percentage": 58.94, "elapsed_time": "2:42:28", "remaining_time": "1:53:11", "throughput": 787.87, "total_tokens": 7680576} {"current_steps": 23580, "total_steps": 40000, "loss": 0.1947, "lr": 1.8064827994937782e-05, "epoch": 19.296356938190748, "percentage": 58.95, "elapsed_time": "2:42:30", "remaining_time": "1:53:09", "throughput": 787.9, "total_tokens": 7682256} {"current_steps": 23585, "total_steps": 40000, "loss": 0.1621, "lr": 1.8055396364024317e-05, "epoch": 19.300450266066314, "percentage": 58.96, "elapsed_time": "2:42:32", "remaining_time": "1:53:07", "throughput": 787.92, "total_tokens": 7683792} {"current_steps": 23590, "total_steps": 40000, "loss": 0.2075, "lr": 1.804596580405601e-05, "epoch": 19.304543593941876, "percentage": 58.98, "elapsed_time": "2:42:33", "remaining_time": "1:53:05", "throughput": 787.94, "total_tokens": 7685344} {"current_steps": 23595, "total_steps": 40000, "loss": 0.1199, "lr": 1.8036536316487174e-05, "epoch": 19.30863692181744, "percentage": 58.99, "elapsed_time": "2:42:35", "remaining_time": "1:53:02", "throughput": 787.96, "total_tokens": 7686928} {"current_steps": 23600, "total_steps": 40000, "loss": 0.2128, "lr": 1.802710790277193e-05, "epoch": 19.312730249693, "percentage": 59.0, "elapsed_time": "2:42:37", "remaining_time": "1:53:00", "throughput": 788.0, "total_tokens": 7688624} {"current_steps": 23600, "total_steps": 40000, "eval_loss": 0.20771414041519165, "epoch": 19.312730249693, "percentage": 59.0, "elapsed_time": "2:42:49", "remaining_time": "1:53:09", "throughput": 786.99, "total_tokens": 7688624} {"current_steps": 23605, "total_steps": 40000, "loss": 0.1236, "lr": 1.801768056436429e-05, "epoch": 19.316823577568563, "percentage": 59.01, "elapsed_time": "2:42:53", "remaining_time": "1:53:08", "throughput": 786.87, "total_tokens": 7690224} {"current_steps": 23610, "total_steps": 40000, "loss": 0.1437, "lr": 1.8008254302718035e-05, "epoch": 19.320916905444125, "percentage": 59.03, "elapsed_time": "2:42:54", "remaining_time": "1:53:05", "throughput": 786.89, "total_tokens": 7691840} {"current_steps": 23615, "total_steps": 40000, "loss": 0.1819, "lr": 1.7998829119286837e-05, "epoch": 19.325010233319688, "percentage": 59.04, "elapsed_time": "2:42:56", "remaining_time": "1:53:03", "throughput": 786.92, "total_tokens": 7693488} {"current_steps": 23620, "total_steps": 40000, "loss": 0.1841, "lr": 1.798940501552418e-05, "epoch": 19.32910356119525, "percentage": 59.05, "elapsed_time": "2:42:58", "remaining_time": "1:53:01", "throughput": 786.95, "total_tokens": 7695104} {"current_steps": 23625, "total_steps": 40000, "loss": 0.2104, "lr": 1.797998199288336e-05, "epoch": 19.333196889070816, "percentage": 59.06, "elapsed_time": "2:43:00", "remaining_time": "1:52:58", "throughput": 786.98, "total_tokens": 7696720} {"current_steps": 23630, "total_steps": 40000, "loss": 0.1541, "lr": 1.7970560052817543e-05, "epoch": 19.33729021694638, "percentage": 59.08, "elapsed_time": "2:43:01", "remaining_time": "1:52:56", "throughput": 787.01, "total_tokens": 7698432} {"current_steps": 23635, "total_steps": 40000, "loss": 0.2564, "lr": 1.7961139196779702e-05, "epoch": 19.34138354482194, "percentage": 59.09, "elapsed_time": "2:43:03", "remaining_time": "1:52:54", "throughput": 787.04, "total_tokens": 7700016} {"current_steps": 23640, "total_steps": 40000, "loss": 0.1873, "lr": 1.7951719426222647e-05, "epoch": 19.345476872697503, "percentage": 59.1, "elapsed_time": "2:43:05", "remaining_time": "1:52:51", "throughput": 787.07, "total_tokens": 7701680} {"current_steps": 23645, "total_steps": 40000, "loss": 0.1642, "lr": 1.794230074259904e-05, "epoch": 19.349570200573066, "percentage": 59.11, "elapsed_time": "2:43:06", "remaining_time": "1:52:49", "throughput": 787.1, "total_tokens": 7703280} {"current_steps": 23650, "total_steps": 40000, "loss": 0.1838, "lr": 1.7932883147361336e-05, "epoch": 19.353663528448628, "percentage": 59.13, "elapsed_time": "2:43:08", "remaining_time": "1:52:47", "throughput": 787.12, "total_tokens": 7704896} {"current_steps": 23655, "total_steps": 40000, "loss": 0.18, "lr": 1.7923466641961865e-05, "epoch": 19.35775685632419, "percentage": 59.14, "elapsed_time": "2:43:10", "remaining_time": "1:52:44", "throughput": 787.16, "total_tokens": 7706576} {"current_steps": 23660, "total_steps": 40000, "loss": 0.171, "lr": 1.791405122785278e-05, "epoch": 19.361850184199753, "percentage": 59.15, "elapsed_time": "2:43:12", "remaining_time": "1:52:42", "throughput": 787.19, "total_tokens": 7708288} {"current_steps": 23665, "total_steps": 40000, "loss": 0.1971, "lr": 1.7904636906486037e-05, "epoch": 19.36594351207532, "percentage": 59.16, "elapsed_time": "2:43:13", "remaining_time": "1:52:40", "throughput": 787.21, "total_tokens": 7709824} {"current_steps": 23670, "total_steps": 40000, "loss": 0.1348, "lr": 1.7895223679313448e-05, "epoch": 19.37003683995088, "percentage": 59.17, "elapsed_time": "2:43:15", "remaining_time": "1:52:37", "throughput": 787.23, "total_tokens": 7711408} {"current_steps": 23675, "total_steps": 40000, "loss": 0.1552, "lr": 1.7885811547786653e-05, "epoch": 19.374130167826443, "percentage": 59.19, "elapsed_time": "2:43:17", "remaining_time": "1:52:35", "throughput": 787.26, "total_tokens": 7713056} {"current_steps": 23680, "total_steps": 40000, "loss": 0.133, "lr": 1.7876400513357115e-05, "epoch": 19.378223495702006, "percentage": 59.2, "elapsed_time": "2:43:19", "remaining_time": "1:52:33", "throughput": 787.29, "total_tokens": 7714672} {"current_steps": 23685, "total_steps": 40000, "loss": 0.1699, "lr": 1.7866990577476146e-05, "epoch": 19.38231682357757, "percentage": 59.21, "elapsed_time": "2:43:20", "remaining_time": "1:52:31", "throughput": 787.32, "total_tokens": 7716288} {"current_steps": 23690, "total_steps": 40000, "loss": 0.1184, "lr": 1.7857581741594863e-05, "epoch": 19.38641015145313, "percentage": 59.23, "elapsed_time": "2:43:22", "remaining_time": "1:52:28", "throughput": 787.35, "total_tokens": 7717920} {"current_steps": 23695, "total_steps": 40000, "loss": 0.219, "lr": 1.7848174007164237e-05, "epoch": 19.390503479328693, "percentage": 59.24, "elapsed_time": "2:43:24", "remaining_time": "1:52:26", "throughput": 787.37, "total_tokens": 7719552} {"current_steps": 23700, "total_steps": 40000, "loss": 0.1726, "lr": 1.7838767375635052e-05, "epoch": 19.394596807204255, "percentage": 59.25, "elapsed_time": "2:43:25", "remaining_time": "1:52:24", "throughput": 787.4, "total_tokens": 7721200} {"current_steps": 23705, "total_steps": 40000, "loss": 0.2228, "lr": 1.782936184845793e-05, "epoch": 19.39869013507982, "percentage": 59.26, "elapsed_time": "2:43:27", "remaining_time": "1:52:21", "throughput": 787.43, "total_tokens": 7722832} {"current_steps": 23710, "total_steps": 40000, "loss": 0.166, "lr": 1.7819957427083334e-05, "epoch": 19.402783462955384, "percentage": 59.27, "elapsed_time": "2:43:29", "remaining_time": "1:52:19", "throughput": 787.46, "total_tokens": 7724432} {"current_steps": 23715, "total_steps": 40000, "loss": 0.0714, "lr": 1.7810554112961516e-05, "epoch": 19.406876790830946, "percentage": 59.29, "elapsed_time": "2:43:31", "remaining_time": "1:52:17", "throughput": 787.48, "total_tokens": 7726048} {"current_steps": 23720, "total_steps": 40000, "loss": 0.1943, "lr": 1.7801151907542607e-05, "epoch": 19.41097011870651, "percentage": 59.3, "elapsed_time": "2:43:32", "remaining_time": "1:52:14", "throughput": 787.51, "total_tokens": 7727696} {"current_steps": 23725, "total_steps": 40000, "loss": 0.1448, "lr": 1.7791750812276547e-05, "epoch": 19.41506344658207, "percentage": 59.31, "elapsed_time": "2:43:34", "remaining_time": "1:52:12", "throughput": 787.54, "total_tokens": 7729280} {"current_steps": 23730, "total_steps": 40000, "loss": 0.1046, "lr": 1.778235082861309e-05, "epoch": 19.419156774457633, "percentage": 59.33, "elapsed_time": "2:43:36", "remaining_time": "1:52:10", "throughput": 787.57, "total_tokens": 7730928} {"current_steps": 23735, "total_steps": 40000, "loss": 0.1126, "lr": 1.777295195800184e-05, "epoch": 19.423250102333196, "percentage": 59.34, "elapsed_time": "2:43:37", "remaining_time": "1:52:07", "throughput": 787.59, "total_tokens": 7732528} {"current_steps": 23740, "total_steps": 40000, "loss": 0.2028, "lr": 1.7763554201892215e-05, "epoch": 19.427343430208758, "percentage": 59.35, "elapsed_time": "2:43:39", "remaining_time": "1:52:05", "throughput": 787.62, "total_tokens": 7734160} {"current_steps": 23745, "total_steps": 40000, "loss": 0.1587, "lr": 1.7754157561733476e-05, "epoch": 19.431436758084324, "percentage": 59.36, "elapsed_time": "2:43:41", "remaining_time": "1:52:03", "throughput": 787.65, "total_tokens": 7735792} {"current_steps": 23750, "total_steps": 40000, "loss": 0.1947, "lr": 1.7744762038974702e-05, "epoch": 19.435530085959886, "percentage": 59.38, "elapsed_time": "2:43:43", "remaining_time": "1:52:01", "throughput": 787.68, "total_tokens": 7737472} {"current_steps": 23755, "total_steps": 40000, "loss": 0.1547, "lr": 1.7735367635064788e-05, "epoch": 19.43962341383545, "percentage": 59.39, "elapsed_time": "2:43:44", "remaining_time": "1:51:58", "throughput": 787.71, "total_tokens": 7739088} {"current_steps": 23760, "total_steps": 40000, "loss": 0.1643, "lr": 1.7725974351452474e-05, "epoch": 19.44371674171101, "percentage": 59.4, "elapsed_time": "2:43:46", "remaining_time": "1:51:56", "throughput": 787.73, "total_tokens": 7740672} {"current_steps": 23765, "total_steps": 40000, "loss": 0.1711, "lr": 1.771658218958634e-05, "epoch": 19.447810069586573, "percentage": 59.41, "elapsed_time": "2:43:48", "remaining_time": "1:51:54", "throughput": 787.76, "total_tokens": 7742272} {"current_steps": 23770, "total_steps": 40000, "loss": 0.1102, "lr": 1.770719115091475e-05, "epoch": 19.451903397462136, "percentage": 59.42, "elapsed_time": "2:43:49", "remaining_time": "1:51:51", "throughput": 787.79, "total_tokens": 7743952} {"current_steps": 23775, "total_steps": 40000, "loss": 0.1286, "lr": 1.7697801236885935e-05, "epoch": 19.455996725337698, "percentage": 59.44, "elapsed_time": "2:43:51", "remaining_time": "1:51:49", "throughput": 787.82, "total_tokens": 7745648} {"current_steps": 23780, "total_steps": 40000, "loss": 0.177, "lr": 1.7688412448947944e-05, "epoch": 19.460090053213264, "percentage": 59.45, "elapsed_time": "2:43:53", "remaining_time": "1:51:47", "throughput": 787.85, "total_tokens": 7747232} {"current_steps": 23785, "total_steps": 40000, "loss": 0.2798, "lr": 1.767902478854862e-05, "epoch": 19.464183381088827, "percentage": 59.46, "elapsed_time": "2:43:55", "remaining_time": "1:51:44", "throughput": 787.87, "total_tokens": 7748848} {"current_steps": 23790, "total_steps": 40000, "loss": 0.1903, "lr": 1.766963825713569e-05, "epoch": 19.46827670896439, "percentage": 59.48, "elapsed_time": "2:43:56", "remaining_time": "1:51:42", "throughput": 787.9, "total_tokens": 7750432} {"current_steps": 23795, "total_steps": 40000, "loss": 0.1992, "lr": 1.766025285615665e-05, "epoch": 19.47237003683995, "percentage": 59.49, "elapsed_time": "2:43:58", "remaining_time": "1:51:40", "throughput": 787.92, "total_tokens": 7752000} {"current_steps": 23800, "total_steps": 40000, "loss": 0.2493, "lr": 1.7650868587058854e-05, "epoch": 19.476463364715514, "percentage": 59.5, "elapsed_time": "2:44:00", "remaining_time": "1:51:38", "throughput": 787.95, "total_tokens": 7753632} {"current_steps": 23800, "total_steps": 40000, "eval_loss": 0.21255095303058624, "epoch": 19.476463364715514, "percentage": 59.5, "elapsed_time": "2:44:12", "remaining_time": "1:51:46", "throughput": 786.95, "total_tokens": 7753632} {"current_steps": 23805, "total_steps": 40000, "loss": 0.1629, "lr": 1.7641485451289484e-05, "epoch": 19.480556692591076, "percentage": 59.51, "elapsed_time": "2:44:15", "remaining_time": "1:51:45", "throughput": 786.86, "total_tokens": 7755232} {"current_steps": 23810, "total_steps": 40000, "loss": 0.2499, "lr": 1.7632103450295534e-05, "epoch": 19.48465002046664, "percentage": 59.52, "elapsed_time": "2:44:17", "remaining_time": "1:51:42", "throughput": 786.9, "total_tokens": 7756992} {"current_steps": 23815, "total_steps": 40000, "loss": 0.1689, "lr": 1.762272258552381e-05, "epoch": 19.4887433483422, "percentage": 59.54, "elapsed_time": "2:44:19", "remaining_time": "1:51:40", "throughput": 786.93, "total_tokens": 7758656} {"current_steps": 23820, "total_steps": 40000, "loss": 0.2042, "lr": 1.7613342858420988e-05, "epoch": 19.492836676217767, "percentage": 59.55, "elapsed_time": "2:44:21", "remaining_time": "1:51:38", "throughput": 786.96, "total_tokens": 7760320} {"current_steps": 23825, "total_steps": 40000, "loss": 0.2556, "lr": 1.760396427043351e-05, "epoch": 19.49693000409333, "percentage": 59.56, "elapsed_time": "2:44:22", "remaining_time": "1:51:35", "throughput": 786.99, "total_tokens": 7761936} {"current_steps": 23830, "total_steps": 40000, "loss": 0.1432, "lr": 1.7594586823007696e-05, "epoch": 19.50102333196889, "percentage": 59.58, "elapsed_time": "2:44:24", "remaining_time": "1:51:33", "throughput": 787.01, "total_tokens": 7763520} {"current_steps": 23835, "total_steps": 40000, "loss": 0.1985, "lr": 1.7585210517589646e-05, "epoch": 19.505116659844454, "percentage": 59.59, "elapsed_time": "2:44:26", "remaining_time": "1:51:31", "throughput": 787.03, "total_tokens": 7765088} {"current_steps": 23840, "total_steps": 40000, "loss": 0.1475, "lr": 1.7575835355625314e-05, "epoch": 19.509209987720016, "percentage": 59.6, "elapsed_time": "2:44:27", "remaining_time": "1:51:29", "throughput": 787.06, "total_tokens": 7766720} {"current_steps": 23845, "total_steps": 40000, "loss": 0.1718, "lr": 1.756646133856048e-05, "epoch": 19.51330331559558, "percentage": 59.61, "elapsed_time": "2:44:29", "remaining_time": "1:51:26", "throughput": 787.09, "total_tokens": 7768368} {"current_steps": 23850, "total_steps": 40000, "loss": 0.2952, "lr": 1.7557088467840714e-05, "epoch": 19.51739664347114, "percentage": 59.62, "elapsed_time": "2:44:31", "remaining_time": "1:51:24", "throughput": 787.12, "total_tokens": 7770016} {"current_steps": 23855, "total_steps": 40000, "loss": 0.0972, "lr": 1.7547716744911438e-05, "epoch": 19.521489971346703, "percentage": 59.64, "elapsed_time": "2:44:33", "remaining_time": "1:51:22", "throughput": 787.14, "total_tokens": 7771600} {"current_steps": 23860, "total_steps": 40000, "loss": 0.1987, "lr": 1.7538346171217902e-05, "epoch": 19.52558329922227, "percentage": 59.65, "elapsed_time": "2:44:34", "remaining_time": "1:51:19", "throughput": 787.18, "total_tokens": 7773296} {"current_steps": 23865, "total_steps": 40000, "loss": 0.1341, "lr": 1.7528976748205146e-05, "epoch": 19.52967662709783, "percentage": 59.66, "elapsed_time": "2:44:36", "remaining_time": "1:51:17", "throughput": 787.21, "total_tokens": 7774928} {"current_steps": 23870, "total_steps": 40000, "loss": 0.1689, "lr": 1.751960847731807e-05, "epoch": 19.533769954973394, "percentage": 59.67, "elapsed_time": "2:44:38", "remaining_time": "1:51:15", "throughput": 787.24, "total_tokens": 7776624} {"current_steps": 23875, "total_steps": 40000, "loss": 0.1822, "lr": 1.7510241360001362e-05, "epoch": 19.537863282848956, "percentage": 59.69, "elapsed_time": "2:44:40", "remaining_time": "1:51:12", "throughput": 787.27, "total_tokens": 7778288} {"current_steps": 23880, "total_steps": 40000, "loss": 0.0898, "lr": 1.7500875397699562e-05, "epoch": 19.54195661072452, "percentage": 59.7, "elapsed_time": "2:44:41", "remaining_time": "1:51:10", "throughput": 787.3, "total_tokens": 7779936} {"current_steps": 23885, "total_steps": 40000, "loss": 0.2163, "lr": 1.7491510591857015e-05, "epoch": 19.54604993860008, "percentage": 59.71, "elapsed_time": "2:44:43", "remaining_time": "1:51:08", "throughput": 787.34, "total_tokens": 7781616} {"current_steps": 23890, "total_steps": 40000, "loss": 0.1065, "lr": 1.7482146943917896e-05, "epoch": 19.550143266475644, "percentage": 59.72, "elapsed_time": "2:44:45", "remaining_time": "1:51:05", "throughput": 787.36, "total_tokens": 7783232} {"current_steps": 23895, "total_steps": 40000, "loss": 0.1122, "lr": 1.7472784455326185e-05, "epoch": 19.554236594351206, "percentage": 59.74, "elapsed_time": "2:44:46", "remaining_time": "1:51:03", "throughput": 787.39, "total_tokens": 7784832} {"current_steps": 23900, "total_steps": 40000, "loss": 0.1148, "lr": 1.746342312752572e-05, "epoch": 19.558329922226772, "percentage": 59.75, "elapsed_time": "2:44:48", "remaining_time": "1:51:01", "throughput": 787.42, "total_tokens": 7786448} {"current_steps": 23905, "total_steps": 40000, "loss": 0.1317, "lr": 1.74540629619601e-05, "epoch": 19.562423250102334, "percentage": 59.76, "elapsed_time": "2:44:50", "remaining_time": "1:50:59", "throughput": 787.44, "total_tokens": 7788064} {"current_steps": 23910, "total_steps": 40000, "loss": 0.2105, "lr": 1.7444703960072815e-05, "epoch": 19.566516577977897, "percentage": 59.77, "elapsed_time": "2:44:52", "remaining_time": "1:50:56", "throughput": 787.47, "total_tokens": 7789680} {"current_steps": 23915, "total_steps": 40000, "loss": 0.2524, "lr": 1.7435346123307118e-05, "epoch": 19.57060990585346, "percentage": 59.79, "elapsed_time": "2:44:53", "remaining_time": "1:50:54", "throughput": 787.5, "total_tokens": 7791344} {"current_steps": 23920, "total_steps": 40000, "loss": 0.2136, "lr": 1.742598945310611e-05, "epoch": 19.57470323372902, "percentage": 59.8, "elapsed_time": "2:44:55", "remaining_time": "1:50:52", "throughput": 787.53, "total_tokens": 7793024} {"current_steps": 23925, "total_steps": 40000, "loss": 0.1437, "lr": 1.741663395091272e-05, "epoch": 19.578796561604584, "percentage": 59.81, "elapsed_time": "2:44:57", "remaining_time": "1:50:49", "throughput": 787.56, "total_tokens": 7794672} {"current_steps": 23930, "total_steps": 40000, "loss": 0.255, "lr": 1.7407279618169657e-05, "epoch": 19.582889889480146, "percentage": 59.82, "elapsed_time": "2:44:58", "remaining_time": "1:50:47", "throughput": 787.59, "total_tokens": 7796304} {"current_steps": 23935, "total_steps": 40000, "loss": 0.192, "lr": 1.73979264563195e-05, "epoch": 19.58698321735571, "percentage": 59.84, "elapsed_time": "2:45:00", "remaining_time": "1:50:45", "throughput": 787.62, "total_tokens": 7797952} {"current_steps": 23940, "total_steps": 40000, "loss": 0.191, "lr": 1.7388574466804625e-05, "epoch": 19.591076545231275, "percentage": 59.85, "elapsed_time": "2:45:02", "remaining_time": "1:50:42", "throughput": 787.65, "total_tokens": 7799568} {"current_steps": 23945, "total_steps": 40000, "loss": 0.1582, "lr": 1.7379223651067207e-05, "epoch": 19.595169873106837, "percentage": 59.86, "elapsed_time": "2:45:04", "remaining_time": "1:50:40", "throughput": 787.67, "total_tokens": 7801168} {"current_steps": 23950, "total_steps": 40000, "loss": 0.2047, "lr": 1.736987401054928e-05, "epoch": 19.5992632009824, "percentage": 59.88, "elapsed_time": "2:45:05", "remaining_time": "1:50:38", "throughput": 787.7, "total_tokens": 7802800} {"current_steps": 23955, "total_steps": 40000, "loss": 0.1767, "lr": 1.736052554669266e-05, "epoch": 19.60335652885796, "percentage": 59.89, "elapsed_time": "2:45:07", "remaining_time": "1:50:36", "throughput": 787.73, "total_tokens": 7804496} {"current_steps": 23960, "total_steps": 40000, "loss": 0.1939, "lr": 1.7351178260939007e-05, "epoch": 19.607449856733524, "percentage": 59.9, "elapsed_time": "2:45:09", "remaining_time": "1:50:33", "throughput": 787.76, "total_tokens": 7806112} {"current_steps": 23965, "total_steps": 40000, "loss": 0.1026, "lr": 1.7341832154729794e-05, "epoch": 19.611543184609086, "percentage": 59.91, "elapsed_time": "2:45:10", "remaining_time": "1:50:31", "throughput": 787.78, "total_tokens": 7807680} {"current_steps": 23970, "total_steps": 40000, "loss": 0.1523, "lr": 1.7332487229506286e-05, "epoch": 19.61563651248465, "percentage": 59.92, "elapsed_time": "2:45:12", "remaining_time": "1:50:29", "throughput": 787.82, "total_tokens": 7809376} {"current_steps": 23975, "total_steps": 40000, "loss": 0.121, "lr": 1.732314348670961e-05, "epoch": 19.61972984036021, "percentage": 59.94, "elapsed_time": "2:45:14", "remaining_time": "1:50:26", "throughput": 787.85, "total_tokens": 7811024} {"current_steps": 23980, "total_steps": 40000, "loss": 0.1753, "lr": 1.7313800927780686e-05, "epoch": 19.623823168235777, "percentage": 59.95, "elapsed_time": "2:45:16", "remaining_time": "1:50:24", "throughput": 787.87, "total_tokens": 7812656} {"current_steps": 23985, "total_steps": 40000, "loss": 0.2166, "lr": 1.7304459554160245e-05, "epoch": 19.62791649611134, "percentage": 59.96, "elapsed_time": "2:45:17", "remaining_time": "1:50:22", "throughput": 787.9, "total_tokens": 7814256} {"current_steps": 23990, "total_steps": 40000, "loss": 0.1809, "lr": 1.7295119367288853e-05, "epoch": 19.632009823986902, "percentage": 59.98, "elapsed_time": "2:45:19", "remaining_time": "1:50:19", "throughput": 787.93, "total_tokens": 7815872} {"current_steps": 23995, "total_steps": 40000, "loss": 0.2375, "lr": 1.728578036860688e-05, "epoch": 19.636103151862464, "percentage": 59.99, "elapsed_time": "2:45:21", "remaining_time": "1:50:17", "throughput": 787.95, "total_tokens": 7817504} {"current_steps": 24000, "total_steps": 40000, "loss": 0.1422, "lr": 1.7276442559554513e-05, "epoch": 19.640196479738027, "percentage": 60.0, "elapsed_time": "2:45:22", "remaining_time": "1:50:15", "throughput": 787.98, "total_tokens": 7819136} {"current_steps": 24000, "total_steps": 40000, "eval_loss": 0.21188834309577942, "epoch": 19.640196479738027, "percentage": 60.0, "elapsed_time": "2:45:35", "remaining_time": "1:50:23", "throughput": 787.0, "total_tokens": 7819136} {"current_steps": 24005, "total_steps": 40000, "loss": 0.1513, "lr": 1.726710594157177e-05, "epoch": 19.64428980761359, "percentage": 60.01, "elapsed_time": "2:45:38", "remaining_time": "1:50:22", "throughput": 786.89, "total_tokens": 7820752} {"current_steps": 24010, "total_steps": 40000, "loss": 0.2126, "lr": 1.725777051609846e-05, "epoch": 19.64838313548915, "percentage": 60.02, "elapsed_time": "2:45:40", "remaining_time": "1:50:20", "throughput": 786.92, "total_tokens": 7822336} {"current_steps": 24015, "total_steps": 40000, "loss": 0.1594, "lr": 1.7248436284574228e-05, "epoch": 19.652476463364714, "percentage": 60.04, "elapsed_time": "2:45:42", "remaining_time": "1:50:17", "throughput": 786.94, "total_tokens": 7823920} {"current_steps": 24020, "total_steps": 40000, "loss": 0.1567, "lr": 1.723910324843855e-05, "epoch": 19.65656979124028, "percentage": 60.05, "elapsed_time": "2:45:43", "remaining_time": "1:50:15", "throughput": 786.96, "total_tokens": 7825520} {"current_steps": 24025, "total_steps": 40000, "loss": 0.2343, "lr": 1.722977140913067e-05, "epoch": 19.660663119115842, "percentage": 60.06, "elapsed_time": "2:45:45", "remaining_time": "1:50:13", "throughput": 786.98, "total_tokens": 7827088} {"current_steps": 24030, "total_steps": 40000, "loss": 0.1485, "lr": 1.7220440768089688e-05, "epoch": 19.664756446991404, "percentage": 60.08, "elapsed_time": "2:45:47", "remaining_time": "1:50:10", "throughput": 787.01, "total_tokens": 7828736} {"current_steps": 24035, "total_steps": 40000, "loss": 0.128, "lr": 1.7211111326754505e-05, "epoch": 19.668849774866967, "percentage": 60.09, "elapsed_time": "2:45:49", "remaining_time": "1:50:08", "throughput": 787.04, "total_tokens": 7830368} {"current_steps": 24040, "total_steps": 40000, "loss": 0.1416, "lr": 1.720178308656383e-05, "epoch": 19.67294310274253, "percentage": 60.1, "elapsed_time": "2:45:50", "remaining_time": "1:50:06", "throughput": 787.07, "total_tokens": 7832032} {"current_steps": 24045, "total_steps": 40000, "loss": 0.1336, "lr": 1.719245604895621e-05, "epoch": 19.67703643061809, "percentage": 60.11, "elapsed_time": "2:45:52", "remaining_time": "1:50:03", "throughput": 787.1, "total_tokens": 7833696} {"current_steps": 24050, "total_steps": 40000, "loss": 0.1542, "lr": 1.7183130215369972e-05, "epoch": 19.681129758493654, "percentage": 60.12, "elapsed_time": "2:45:54", "remaining_time": "1:50:01", "throughput": 787.13, "total_tokens": 7835296} {"current_steps": 24055, "total_steps": 40000, "loss": 0.1774, "lr": 1.7173805587243292e-05, "epoch": 19.68522308636922, "percentage": 60.14, "elapsed_time": "2:45:55", "remaining_time": "1:49:59", "throughput": 787.16, "total_tokens": 7836976} {"current_steps": 24060, "total_steps": 40000, "loss": 0.14, "lr": 1.7164482166014147e-05, "epoch": 19.689316414244782, "percentage": 60.15, "elapsed_time": "2:45:57", "remaining_time": "1:49:57", "throughput": 787.19, "total_tokens": 7838608} {"current_steps": 24065, "total_steps": 40000, "loss": 0.213, "lr": 1.7155159953120313e-05, "epoch": 19.693409742120345, "percentage": 60.16, "elapsed_time": "2:45:59", "remaining_time": "1:49:54", "throughput": 787.21, "total_tokens": 7840208} {"current_steps": 24070, "total_steps": 40000, "loss": 0.0914, "lr": 1.714583894999941e-05, "epoch": 19.697503069995907, "percentage": 60.17, "elapsed_time": "2:46:01", "remaining_time": "1:49:52", "throughput": 787.24, "total_tokens": 7841840} {"current_steps": 24075, "total_steps": 40000, "loss": 0.1596, "lr": 1.7136519158088826e-05, "epoch": 19.70159639787147, "percentage": 60.19, "elapsed_time": "2:46:02", "remaining_time": "1:49:50", "throughput": 787.26, "total_tokens": 7843424} {"current_steps": 24080, "total_steps": 40000, "loss": 0.3302, "lr": 1.712720057882581e-05, "epoch": 19.705689725747032, "percentage": 60.2, "elapsed_time": "2:46:04", "remaining_time": "1:49:47", "throughput": 787.29, "total_tokens": 7845072} {"current_steps": 24085, "total_steps": 40000, "loss": 0.1277, "lr": 1.7117883213647413e-05, "epoch": 19.709783053622594, "percentage": 60.21, "elapsed_time": "2:46:06", "remaining_time": "1:49:45", "throughput": 787.31, "total_tokens": 7846640} {"current_steps": 24090, "total_steps": 40000, "loss": 0.258, "lr": 1.710856706399046e-05, "epoch": 19.713876381498157, "percentage": 60.22, "elapsed_time": "2:46:08", "remaining_time": "1:49:43", "throughput": 787.34, "total_tokens": 7848208} {"current_steps": 24095, "total_steps": 40000, "loss": 0.1822, "lr": 1.7099252131291648e-05, "epoch": 19.717969709373723, "percentage": 60.24, "elapsed_time": "2:46:09", "remaining_time": "1:49:41", "throughput": 787.37, "total_tokens": 7849920} {"current_steps": 24100, "total_steps": 40000, "loss": 0.1417, "lr": 1.708993841698744e-05, "epoch": 19.722063037249285, "percentage": 60.25, "elapsed_time": "2:46:11", "remaining_time": "1:49:38", "throughput": 787.41, "total_tokens": 7851616} {"current_steps": 24105, "total_steps": 40000, "loss": 0.1898, "lr": 1.7080625922514132e-05, "epoch": 19.726156365124847, "percentage": 60.26, "elapsed_time": "2:46:13", "remaining_time": "1:49:36", "throughput": 787.44, "total_tokens": 7853280} {"current_steps": 24110, "total_steps": 40000, "loss": 0.1763, "lr": 1.7071314649307836e-05, "epoch": 19.73024969300041, "percentage": 60.27, "elapsed_time": "2:46:14", "remaining_time": "1:49:34", "throughput": 787.46, "total_tokens": 7854864} {"current_steps": 24115, "total_steps": 40000, "loss": 0.1572, "lr": 1.7062004598804448e-05, "epoch": 19.734343020875972, "percentage": 60.29, "elapsed_time": "2:46:16", "remaining_time": "1:49:31", "throughput": 787.49, "total_tokens": 7856480} {"current_steps": 24120, "total_steps": 40000, "loss": 0.1157, "lr": 1.7052695772439702e-05, "epoch": 19.738436348751534, "percentage": 60.3, "elapsed_time": "2:46:18", "remaining_time": "1:49:29", "throughput": 787.52, "total_tokens": 7858128} {"current_steps": 24125, "total_steps": 40000, "loss": 0.1862, "lr": 1.7043388171649154e-05, "epoch": 19.742529676627097, "percentage": 60.31, "elapsed_time": "2:46:20", "remaining_time": "1:49:27", "throughput": 787.53, "total_tokens": 7859648} {"current_steps": 24130, "total_steps": 40000, "loss": 0.2253, "lr": 1.7034081797868127e-05, "epoch": 19.74662300450266, "percentage": 60.32, "elapsed_time": "2:46:21", "remaining_time": "1:49:24", "throughput": 787.55, "total_tokens": 7861232} {"current_steps": 24135, "total_steps": 40000, "loss": 0.1541, "lr": 1.70247766525318e-05, "epoch": 19.750716332378225, "percentage": 60.34, "elapsed_time": "2:46:23", "remaining_time": "1:49:22", "throughput": 787.59, "total_tokens": 7862896} {"current_steps": 24140, "total_steps": 40000, "loss": 0.1504, "lr": 1.701547273707514e-05, "epoch": 19.754809660253787, "percentage": 60.35, "elapsed_time": "2:46:25", "remaining_time": "1:49:20", "throughput": 787.62, "total_tokens": 7864576} {"current_steps": 24145, "total_steps": 40000, "loss": 0.2085, "lr": 1.7006170052932916e-05, "epoch": 19.75890298812935, "percentage": 60.36, "elapsed_time": "2:46:26", "remaining_time": "1:49:18", "throughput": 787.64, "total_tokens": 7866176} {"current_steps": 24150, "total_steps": 40000, "loss": 0.1293, "lr": 1.6996868601539735e-05, "epoch": 19.762996316004912, "percentage": 60.38, "elapsed_time": "2:46:28", "remaining_time": "1:49:15", "throughput": 787.68, "total_tokens": 7867856} {"current_steps": 24155, "total_steps": 40000, "loss": 0.1097, "lr": 1.6987568384329977e-05, "epoch": 19.767089643880475, "percentage": 60.39, "elapsed_time": "2:46:30", "remaining_time": "1:49:13", "throughput": 787.71, "total_tokens": 7869600} {"current_steps": 24160, "total_steps": 40000, "loss": 0.1404, "lr": 1.6978269402737866e-05, "epoch": 19.771182971756037, "percentage": 60.4, "elapsed_time": "2:46:32", "remaining_time": "1:49:11", "throughput": 787.74, "total_tokens": 7871200} {"current_steps": 24165, "total_steps": 40000, "loss": 0.2334, "lr": 1.696897165819743e-05, "epoch": 19.7752762996316, "percentage": 60.41, "elapsed_time": "2:46:33", "remaining_time": "1:49:08", "throughput": 787.76, "total_tokens": 7872800} {"current_steps": 24170, "total_steps": 40000, "loss": 0.2345, "lr": 1.6959675152142487e-05, "epoch": 19.77936962750716, "percentage": 60.42, "elapsed_time": "2:46:35", "remaining_time": "1:49:06", "throughput": 787.79, "total_tokens": 7874416} {"current_steps": 24175, "total_steps": 40000, "loss": 0.1471, "lr": 1.6950379886006667e-05, "epoch": 19.783462955382728, "percentage": 60.44, "elapsed_time": "2:46:37", "remaining_time": "1:49:04", "throughput": 787.82, "total_tokens": 7876064} {"current_steps": 24180, "total_steps": 40000, "loss": 0.137, "lr": 1.6941085861223438e-05, "epoch": 19.78755628325829, "percentage": 60.45, "elapsed_time": "2:46:39", "remaining_time": "1:49:01", "throughput": 787.85, "total_tokens": 7877696} {"current_steps": 24185, "total_steps": 40000, "loss": 0.1181, "lr": 1.6931793079226034e-05, "epoch": 19.791649611133852, "percentage": 60.46, "elapsed_time": "2:46:40", "remaining_time": "1:48:59", "throughput": 787.88, "total_tokens": 7879328} {"current_steps": 24190, "total_steps": 40000, "loss": 0.2444, "lr": 1.692250154144754e-05, "epoch": 19.795742939009415, "percentage": 60.48, "elapsed_time": "2:46:42", "remaining_time": "1:48:57", "throughput": 787.9, "total_tokens": 7880960} {"current_steps": 24195, "total_steps": 40000, "loss": 0.1996, "lr": 1.6913211249320807e-05, "epoch": 19.799836266884977, "percentage": 60.49, "elapsed_time": "2:46:44", "remaining_time": "1:48:55", "throughput": 787.94, "total_tokens": 7882624} {"current_steps": 24200, "total_steps": 40000, "loss": 0.135, "lr": 1.6903922204278522e-05, "epoch": 19.80392959476054, "percentage": 60.5, "elapsed_time": "2:46:45", "remaining_time": "1:48:52", "throughput": 787.96, "total_tokens": 7884272} {"current_steps": 24200, "total_steps": 40000, "eval_loss": 0.21123003959655762, "epoch": 19.80392959476054, "percentage": 60.5, "elapsed_time": "2:46:58", "remaining_time": "1:49:00", "throughput": 786.98, "total_tokens": 7884272} {"current_steps": 24205, "total_steps": 40000, "loss": 0.1359, "lr": 1.6894634407753186e-05, "epoch": 19.808022922636102, "percentage": 60.51, "elapsed_time": "2:47:01", "remaining_time": "1:48:59", "throughput": 786.89, "total_tokens": 7885904} {"current_steps": 24210, "total_steps": 40000, "loss": 0.2315, "lr": 1.6885347861177077e-05, "epoch": 19.812116250511664, "percentage": 60.52, "elapsed_time": "2:47:03", "remaining_time": "1:48:57", "throughput": 786.92, "total_tokens": 7887552} {"current_steps": 24215, "total_steps": 40000, "loss": 0.1483, "lr": 1.6876062565982298e-05, "epoch": 19.81620957838723, "percentage": 60.54, "elapsed_time": "2:47:05", "remaining_time": "1:48:55", "throughput": 786.95, "total_tokens": 7889232} {"current_steps": 24220, "total_steps": 40000, "loss": 0.1266, "lr": 1.6866778523600774e-05, "epoch": 19.820302906262793, "percentage": 60.55, "elapsed_time": "2:47:06", "remaining_time": "1:48:52", "throughput": 786.98, "total_tokens": 7890896} {"current_steps": 24225, "total_steps": 40000, "loss": 0.1487, "lr": 1.6857495735464195e-05, "epoch": 19.824396234138355, "percentage": 60.56, "elapsed_time": "2:47:08", "remaining_time": "1:48:50", "throughput": 787.01, "total_tokens": 7892496} {"current_steps": 24230, "total_steps": 40000, "loss": 0.1689, "lr": 1.6848214203004115e-05, "epoch": 19.828489562013917, "percentage": 60.58, "elapsed_time": "2:47:10", "remaining_time": "1:48:48", "throughput": 787.03, "total_tokens": 7894112} {"current_steps": 24235, "total_steps": 40000, "loss": 0.1554, "lr": 1.6838933927651835e-05, "epoch": 19.83258288988948, "percentage": 60.59, "elapsed_time": "2:47:11", "remaining_time": "1:48:45", "throughput": 787.07, "total_tokens": 7895776} {"current_steps": 24240, "total_steps": 40000, "loss": 0.3089, "lr": 1.6829654910838506e-05, "epoch": 19.836676217765042, "percentage": 60.6, "elapsed_time": "2:47:13", "remaining_time": "1:48:43", "throughput": 787.1, "total_tokens": 7897440} {"current_steps": 24245, "total_steps": 40000, "loss": 0.1383, "lr": 1.6820377153995065e-05, "epoch": 19.840769545640605, "percentage": 60.61, "elapsed_time": "2:47:15", "remaining_time": "1:48:41", "throughput": 787.12, "total_tokens": 7899040} {"current_steps": 24250, "total_steps": 40000, "loss": 0.1683, "lr": 1.681110065855226e-05, "epoch": 19.844862873516167, "percentage": 60.62, "elapsed_time": "2:47:17", "remaining_time": "1:48:38", "throughput": 787.15, "total_tokens": 7900688} {"current_steps": 24255, "total_steps": 40000, "loss": 0.2044, "lr": 1.6801825425940642e-05, "epoch": 19.848956201391733, "percentage": 60.64, "elapsed_time": "2:47:18", "remaining_time": "1:48:36", "throughput": 787.17, "total_tokens": 7902272} {"current_steps": 24260, "total_steps": 40000, "loss": 0.1378, "lr": 1.679255145759056e-05, "epoch": 19.853049529267295, "percentage": 60.65, "elapsed_time": "2:47:20", "remaining_time": "1:48:34", "throughput": 787.2, "total_tokens": 7903920} {"current_steps": 24265, "total_steps": 40000, "loss": 0.1758, "lr": 1.6783278754932187e-05, "epoch": 19.857142857142858, "percentage": 60.66, "elapsed_time": "2:47:22", "remaining_time": "1:48:32", "throughput": 787.23, "total_tokens": 7905552} {"current_steps": 24270, "total_steps": 40000, "loss": 0.2247, "lr": 1.6774007319395496e-05, "epoch": 19.86123618501842, "percentage": 60.68, "elapsed_time": "2:47:23", "remaining_time": "1:48:29", "throughput": 787.26, "total_tokens": 7907200} {"current_steps": 24275, "total_steps": 40000, "loss": 0.2252, "lr": 1.6764737152410243e-05, "epoch": 19.865329512893982, "percentage": 60.69, "elapsed_time": "2:47:25", "remaining_time": "1:48:27", "throughput": 787.29, "total_tokens": 7908832} {"current_steps": 24280, "total_steps": 40000, "loss": 0.1932, "lr": 1.6755468255406016e-05, "epoch": 19.869422840769545, "percentage": 60.7, "elapsed_time": "2:47:27", "remaining_time": "1:48:25", "throughput": 787.31, "total_tokens": 7910448} {"current_steps": 24285, "total_steps": 40000, "loss": 0.1691, "lr": 1.674620062981219e-05, "epoch": 19.873516168645107, "percentage": 60.71, "elapsed_time": "2:47:29", "remaining_time": "1:48:22", "throughput": 787.34, "total_tokens": 7912080} {"current_steps": 24290, "total_steps": 40000, "loss": 0.2404, "lr": 1.6736934277057947e-05, "epoch": 19.87760949652067, "percentage": 60.72, "elapsed_time": "2:47:30", "remaining_time": "1:48:20", "throughput": 787.37, "total_tokens": 7913760} {"current_steps": 24295, "total_steps": 40000, "loss": 0.2211, "lr": 1.6727669198572286e-05, "epoch": 19.881702824396235, "percentage": 60.74, "elapsed_time": "2:47:32", "remaining_time": "1:48:18", "throughput": 787.4, "total_tokens": 7915392} {"current_steps": 24300, "total_steps": 40000, "loss": 0.2017, "lr": 1.6718405395783984e-05, "epoch": 19.885796152271798, "percentage": 60.75, "elapsed_time": "2:47:34", "remaining_time": "1:48:15", "throughput": 787.42, "total_tokens": 7916992} {"current_steps": 24305, "total_steps": 40000, "loss": 0.2443, "lr": 1.6709142870121643e-05, "epoch": 19.88988948014736, "percentage": 60.76, "elapsed_time": "2:47:36", "remaining_time": "1:48:13", "throughput": 787.45, "total_tokens": 7918608} {"current_steps": 24310, "total_steps": 40000, "loss": 0.1252, "lr": 1.669988162301367e-05, "epoch": 19.893982808022923, "percentage": 60.77, "elapsed_time": "2:47:37", "remaining_time": "1:48:11", "throughput": 787.48, "total_tokens": 7920240} {"current_steps": 24315, "total_steps": 40000, "loss": 0.2165, "lr": 1.6690621655888243e-05, "epoch": 19.898076135898485, "percentage": 60.79, "elapsed_time": "2:47:39", "remaining_time": "1:48:09", "throughput": 787.5, "total_tokens": 7921872} {"current_steps": 24320, "total_steps": 40000, "loss": 0.2608, "lr": 1.6681362970173386e-05, "epoch": 19.902169463774047, "percentage": 60.8, "elapsed_time": "2:47:41", "remaining_time": "1:48:06", "throughput": 787.53, "total_tokens": 7923456} {"current_steps": 24325, "total_steps": 40000, "loss": 0.1433, "lr": 1.6672105567296904e-05, "epoch": 19.90626279164961, "percentage": 60.81, "elapsed_time": "2:47:42", "remaining_time": "1:48:04", "throughput": 787.56, "total_tokens": 7925088} {"current_steps": 24330, "total_steps": 40000, "loss": 0.2321, "lr": 1.666284944868639e-05, "epoch": 19.910356119525176, "percentage": 60.82, "elapsed_time": "2:47:44", "remaining_time": "1:48:02", "throughput": 787.58, "total_tokens": 7926688} {"current_steps": 24335, "total_steps": 40000, "loss": 0.2512, "lr": 1.665359461576927e-05, "epoch": 19.914449447400738, "percentage": 60.84, "elapsed_time": "2:47:46", "remaining_time": "1:47:59", "throughput": 787.6, "total_tokens": 7928288} {"current_steps": 24340, "total_steps": 40000, "loss": 0.2666, "lr": 1.6644341069972736e-05, "epoch": 19.9185427752763, "percentage": 60.85, "elapsed_time": "2:47:48", "remaining_time": "1:47:57", "throughput": 787.63, "total_tokens": 7929936} {"current_steps": 24345, "total_steps": 40000, "loss": 0.2066, "lr": 1.6635088812723813e-05, "epoch": 19.922636103151863, "percentage": 60.86, "elapsed_time": "2:47:49", "remaining_time": "1:47:55", "throughput": 787.66, "total_tokens": 7931584} {"current_steps": 24350, "total_steps": 40000, "loss": 0.1156, "lr": 1.6625837845449328e-05, "epoch": 19.926729431027425, "percentage": 60.88, "elapsed_time": "2:47:51", "remaining_time": "1:47:53", "throughput": 787.7, "total_tokens": 7933296} {"current_steps": 24355, "total_steps": 40000, "loss": 0.1902, "lr": 1.6616588169575874e-05, "epoch": 19.930822758902988, "percentage": 60.89, "elapsed_time": "2:47:53", "remaining_time": "1:47:50", "throughput": 787.72, "total_tokens": 7934912} {"current_steps": 24360, "total_steps": 40000, "loss": 0.1969, "lr": 1.6607339786529878e-05, "epoch": 19.93491608677855, "percentage": 60.9, "elapsed_time": "2:47:54", "remaining_time": "1:47:48", "throughput": 787.75, "total_tokens": 7936544} {"current_steps": 24365, "total_steps": 40000, "loss": 0.2304, "lr": 1.659809269773756e-05, "epoch": 19.939009414654112, "percentage": 60.91, "elapsed_time": "2:47:56", "remaining_time": "1:47:46", "throughput": 787.78, "total_tokens": 7938144} {"current_steps": 24370, "total_steps": 40000, "loss": 0.2043, "lr": 1.658884690462493e-05, "epoch": 19.94310274252968, "percentage": 60.92, "elapsed_time": "2:47:58", "remaining_time": "1:47:43", "throughput": 787.81, "total_tokens": 7939808} {"current_steps": 24375, "total_steps": 40000, "loss": 0.1766, "lr": 1.6579602408617813e-05, "epoch": 19.94719607040524, "percentage": 60.94, "elapsed_time": "2:48:00", "remaining_time": "1:47:41", "throughput": 787.83, "total_tokens": 7941424} {"current_steps": 24380, "total_steps": 40000, "loss": 0.1341, "lr": 1.657035921114181e-05, "epoch": 19.951289398280803, "percentage": 60.95, "elapsed_time": "2:48:01", "remaining_time": "1:47:39", "throughput": 787.87, "total_tokens": 7943104} {"current_steps": 24385, "total_steps": 40000, "loss": 0.1933, "lr": 1.656111731362236e-05, "epoch": 19.955382726156365, "percentage": 60.96, "elapsed_time": "2:48:03", "remaining_time": "1:47:37", "throughput": 787.89, "total_tokens": 7944656} {"current_steps": 24390, "total_steps": 40000, "loss": 0.1801, "lr": 1.6551876717484666e-05, "epoch": 19.959476054031928, "percentage": 60.98, "elapsed_time": "2:48:05", "remaining_time": "1:47:34", "throughput": 787.91, "total_tokens": 7946256} {"current_steps": 24395, "total_steps": 40000, "loss": 0.2115, "lr": 1.6542637424153752e-05, "epoch": 19.96356938190749, "percentage": 60.99, "elapsed_time": "2:48:06", "remaining_time": "1:47:32", "throughput": 787.94, "total_tokens": 7947872} {"current_steps": 24400, "total_steps": 40000, "loss": 0.1307, "lr": 1.6533399435054418e-05, "epoch": 19.967662709783053, "percentage": 61.0, "elapsed_time": "2:48:08", "remaining_time": "1:47:30", "throughput": 787.96, "total_tokens": 7949504} {"current_steps": 24400, "total_steps": 40000, "eval_loss": 0.21109998226165771, "epoch": 19.967662709783053, "percentage": 61.0, "elapsed_time": "2:48:21", "remaining_time": "1:47:38", "throughput": 786.99, "total_tokens": 7949504} {"current_steps": 24405, "total_steps": 40000, "loss": 0.0829, "lr": 1.6524162751611304e-05, "epoch": 19.971756037658615, "percentage": 61.01, "elapsed_time": "2:48:24", "remaining_time": "1:47:36", "throughput": 786.9, "total_tokens": 7951152} {"current_steps": 24410, "total_steps": 40000, "loss": 0.1751, "lr": 1.6514927375248796e-05, "epoch": 19.97584936553418, "percentage": 61.02, "elapsed_time": "2:48:26", "remaining_time": "1:47:34", "throughput": 786.93, "total_tokens": 7952768} {"current_steps": 24415, "total_steps": 40000, "loss": 0.2309, "lr": 1.6505693307391127e-05, "epoch": 19.979942693409743, "percentage": 61.04, "elapsed_time": "2:48:27", "remaining_time": "1:47:32", "throughput": 786.96, "total_tokens": 7954448} {"current_steps": 24420, "total_steps": 40000, "loss": 0.2341, "lr": 1.6496460549462288e-05, "epoch": 19.984036021285306, "percentage": 61.05, "elapsed_time": "2:48:29", "remaining_time": "1:47:29", "throughput": 786.99, "total_tokens": 7956096} {"current_steps": 24425, "total_steps": 40000, "loss": 0.2032, "lr": 1.6487229102886097e-05, "epoch": 19.988129349160868, "percentage": 61.06, "elapsed_time": "2:48:31", "remaining_time": "1:47:27", "throughput": 787.02, "total_tokens": 7957776} {"current_steps": 24430, "total_steps": 40000, "loss": 0.1889, "lr": 1.6477998969086155e-05, "epoch": 19.99222267703643, "percentage": 61.08, "elapsed_time": "2:48:32", "remaining_time": "1:47:25", "throughput": 787.05, "total_tokens": 7959392} {"current_steps": 24435, "total_steps": 40000, "loss": 0.164, "lr": 1.646877014948587e-05, "epoch": 19.996316004911993, "percentage": 61.09, "elapsed_time": "2:48:34", "remaining_time": "1:47:23", "throughput": 787.07, "total_tokens": 7960960} {"current_steps": 24440, "total_steps": 40000, "loss": 0.1692, "lr": 1.6459542645508433e-05, "epoch": 20.0, "percentage": 61.1, "elapsed_time": "2:48:36", "remaining_time": "1:47:20", "throughput": 787.07, "total_tokens": 7962304} {"current_steps": 24445, "total_steps": 40000, "loss": 0.1481, "lr": 1.6450316458576852e-05, "epoch": 20.004093327875562, "percentage": 61.11, "elapsed_time": "2:48:38", "remaining_time": "1:47:18", "throughput": 787.08, "total_tokens": 7963952} {"current_steps": 24450, "total_steps": 40000, "loss": 0.1233, "lr": 1.6441091590113912e-05, "epoch": 20.008186655751125, "percentage": 61.12, "elapsed_time": "2:48:40", "remaining_time": "1:47:16", "throughput": 787.11, "total_tokens": 7965568} {"current_steps": 24455, "total_steps": 40000, "loss": 0.1243, "lr": 1.6431868041542213e-05, "epoch": 20.012279983626687, "percentage": 61.14, "elapsed_time": "2:48:41", "remaining_time": "1:47:13", "throughput": 787.14, "total_tokens": 7967216} {"current_steps": 24460, "total_steps": 40000, "loss": 0.1995, "lr": 1.6422645814284123e-05, "epoch": 20.016373311502253, "percentage": 61.15, "elapsed_time": "2:48:43", "remaining_time": "1:47:11", "throughput": 787.17, "total_tokens": 7968864} {"current_steps": 24465, "total_steps": 40000, "loss": 0.1313, "lr": 1.6413424909761846e-05, "epoch": 20.020466639377815, "percentage": 61.16, "elapsed_time": "2:48:45", "remaining_time": "1:47:09", "throughput": 787.2, "total_tokens": 7970560} {"current_steps": 24470, "total_steps": 40000, "loss": 0.1943, "lr": 1.640420532939736e-05, "epoch": 20.024559967253378, "percentage": 61.18, "elapsed_time": "2:48:46", "remaining_time": "1:47:07", "throughput": 787.23, "total_tokens": 7972240} {"current_steps": 24475, "total_steps": 40000, "loss": 0.1386, "lr": 1.639498707461242e-05, "epoch": 20.02865329512894, "percentage": 61.19, "elapsed_time": "2:48:48", "remaining_time": "1:47:04", "throughput": 787.27, "total_tokens": 7973984} {"current_steps": 24480, "total_steps": 40000, "loss": 0.1564, "lr": 1.6385770146828614e-05, "epoch": 20.032746623004503, "percentage": 61.2, "elapsed_time": "2:48:50", "remaining_time": "1:47:02", "throughput": 787.3, "total_tokens": 7975600} {"current_steps": 24485, "total_steps": 40000, "loss": 0.1379, "lr": 1.637655454746731e-05, "epoch": 20.036839950880065, "percentage": 61.21, "elapsed_time": "2:48:52", "remaining_time": "1:47:00", "throughput": 787.32, "total_tokens": 7977216} {"current_steps": 24490, "total_steps": 40000, "loss": 0.2, "lr": 1.6367340277949658e-05, "epoch": 20.040933278755627, "percentage": 61.22, "elapsed_time": "2:48:53", "remaining_time": "1:46:57", "throughput": 787.35, "total_tokens": 7978816} {"current_steps": 24495, "total_steps": 40000, "loss": 0.2203, "lr": 1.635812733969663e-05, "epoch": 20.04502660663119, "percentage": 61.24, "elapsed_time": "2:48:55", "remaining_time": "1:46:55", "throughput": 787.38, "total_tokens": 7980480} {"current_steps": 24500, "total_steps": 40000, "loss": 0.183, "lr": 1.634891573412896e-05, "epoch": 20.049119934506756, "percentage": 61.25, "elapsed_time": "2:48:57", "remaining_time": "1:46:53", "throughput": 787.41, "total_tokens": 7982160} {"current_steps": 24505, "total_steps": 40000, "loss": 0.3672, "lr": 1.6339705462667196e-05, "epoch": 20.053213262382318, "percentage": 61.26, "elapsed_time": "2:48:58", "remaining_time": "1:46:51", "throughput": 787.44, "total_tokens": 7983824} {"current_steps": 24510, "total_steps": 40000, "loss": 0.1716, "lr": 1.633049652673169e-05, "epoch": 20.05730659025788, "percentage": 61.27, "elapsed_time": "2:49:00", "remaining_time": "1:46:48", "throughput": 787.47, "total_tokens": 7985440} {"current_steps": 24515, "total_steps": 40000, "loss": 0.1637, "lr": 1.632128892774256e-05, "epoch": 20.061399918133443, "percentage": 61.29, "elapsed_time": "2:49:02", "remaining_time": "1:46:46", "throughput": 787.49, "total_tokens": 7986992} {"current_steps": 24520, "total_steps": 40000, "loss": 0.229, "lr": 1.6312082667119737e-05, "epoch": 20.065493246009005, "percentage": 61.3, "elapsed_time": "2:49:04", "remaining_time": "1:46:44", "throughput": 787.51, "total_tokens": 7988608} {"current_steps": 24525, "total_steps": 40000, "loss": 0.1225, "lr": 1.630287774628296e-05, "epoch": 20.069586573884568, "percentage": 61.31, "elapsed_time": "2:49:05", "remaining_time": "1:46:41", "throughput": 787.53, "total_tokens": 7990128} {"current_steps": 24530, "total_steps": 40000, "loss": 0.0993, "lr": 1.6293674166651718e-05, "epoch": 20.07367990176013, "percentage": 61.32, "elapsed_time": "2:49:07", "remaining_time": "1:46:39", "throughput": 787.55, "total_tokens": 7991744} {"current_steps": 24535, "total_steps": 40000, "loss": 0.3233, "lr": 1.6284471929645338e-05, "epoch": 20.077773229635692, "percentage": 61.34, "elapsed_time": "2:49:09", "remaining_time": "1:46:37", "throughput": 787.58, "total_tokens": 7993376} {"current_steps": 24540, "total_steps": 40000, "loss": 0.1292, "lr": 1.627527103668291e-05, "epoch": 20.08186655751126, "percentage": 61.35, "elapsed_time": "2:49:10", "remaining_time": "1:46:35", "throughput": 787.6, "total_tokens": 7994960} {"current_steps": 24545, "total_steps": 40000, "loss": 0.1456, "lr": 1.6266071489183327e-05, "epoch": 20.08595988538682, "percentage": 61.36, "elapsed_time": "2:49:12", "remaining_time": "1:46:32", "throughput": 787.64, "total_tokens": 7996624} {"current_steps": 24550, "total_steps": 40000, "loss": 0.1539, "lr": 1.6256873288565283e-05, "epoch": 20.090053213262383, "percentage": 61.38, "elapsed_time": "2:49:14", "remaining_time": "1:46:30", "throughput": 787.67, "total_tokens": 7998288} {"current_steps": 24555, "total_steps": 40000, "loss": 0.2148, "lr": 1.6247676436247245e-05, "epoch": 20.094146541137945, "percentage": 61.39, "elapsed_time": "2:49:16", "remaining_time": "1:46:28", "throughput": 787.7, "total_tokens": 8000000} {"current_steps": 24560, "total_steps": 40000, "loss": 0.1573, "lr": 1.6238480933647486e-05, "epoch": 20.098239869013508, "percentage": 61.4, "elapsed_time": "2:49:17", "remaining_time": "1:46:25", "throughput": 787.73, "total_tokens": 8001632} {"current_steps": 24565, "total_steps": 40000, "loss": 0.1234, "lr": 1.6229286782184083e-05, "epoch": 20.10233319688907, "percentage": 61.41, "elapsed_time": "2:49:19", "remaining_time": "1:46:23", "throughput": 787.75, "total_tokens": 8003232} {"current_steps": 24570, "total_steps": 40000, "loss": 0.1776, "lr": 1.622009398327487e-05, "epoch": 20.106426524764633, "percentage": 61.42, "elapsed_time": "2:49:21", "remaining_time": "1:46:21", "throughput": 787.78, "total_tokens": 8004864} {"current_steps": 24575, "total_steps": 40000, "loss": 0.2092, "lr": 1.6210902538337502e-05, "epoch": 20.110519852640195, "percentage": 61.44, "elapsed_time": "2:49:23", "remaining_time": "1:46:19", "throughput": 787.8, "total_tokens": 8006432} {"current_steps": 24580, "total_steps": 40000, "loss": 0.2264, "lr": 1.6201712448789413e-05, "epoch": 20.11461318051576, "percentage": 61.45, "elapsed_time": "2:49:24", "remaining_time": "1:46:16", "throughput": 787.84, "total_tokens": 8008192} {"current_steps": 24585, "total_steps": 40000, "loss": 0.1653, "lr": 1.6192523716047827e-05, "epoch": 20.118706508391323, "percentage": 61.46, "elapsed_time": "2:49:26", "remaining_time": "1:46:14", "throughput": 787.87, "total_tokens": 8009808} {"current_steps": 24590, "total_steps": 40000, "loss": 0.1672, "lr": 1.6183336341529776e-05, "epoch": 20.122799836266886, "percentage": 61.48, "elapsed_time": "2:49:28", "remaining_time": "1:46:12", "throughput": 787.89, "total_tokens": 8011392} {"current_steps": 24595, "total_steps": 40000, "loss": 0.1187, "lr": 1.6174150326652047e-05, "epoch": 20.126893164142448, "percentage": 61.49, "elapsed_time": "2:49:29", "remaining_time": "1:46:09", "throughput": 787.91, "total_tokens": 8012960} {"current_steps": 24600, "total_steps": 40000, "loss": 0.1891, "lr": 1.6164965672831256e-05, "epoch": 20.13098649201801, "percentage": 61.5, "elapsed_time": "2:49:31", "remaining_time": "1:46:07", "throughput": 787.93, "total_tokens": 8014544} {"current_steps": 24600, "total_steps": 40000, "eval_loss": 0.21140170097351074, "epoch": 20.13098649201801, "percentage": 61.5, "elapsed_time": "2:49:44", "remaining_time": "1:46:15", "throughput": 786.97, "total_tokens": 8014544} {"current_steps": 24605, "total_steps": 40000, "loss": 0.2384, "lr": 1.6155782381483784e-05, "epoch": 20.135079819893573, "percentage": 61.51, "elapsed_time": "2:49:47", "remaining_time": "1:46:14", "throughput": 786.88, "total_tokens": 8016160} {"current_steps": 24610, "total_steps": 40000, "loss": 0.2606, "lr": 1.6146600454025813e-05, "epoch": 20.139173147769135, "percentage": 61.52, "elapsed_time": "2:49:49", "remaining_time": "1:46:11", "throughput": 786.91, "total_tokens": 8017808} {"current_steps": 24615, "total_steps": 40000, "loss": 0.1277, "lr": 1.6137419891873317e-05, "epoch": 20.143266475644698, "percentage": 61.54, "elapsed_time": "2:49:50", "remaining_time": "1:46:09", "throughput": 786.94, "total_tokens": 8019456} {"current_steps": 24620, "total_steps": 40000, "loss": 0.1593, "lr": 1.6128240696442038e-05, "epoch": 20.147359803520263, "percentage": 61.55, "elapsed_time": "2:49:52", "remaining_time": "1:46:07", "throughput": 786.97, "total_tokens": 8021136} {"current_steps": 24625, "total_steps": 40000, "loss": 0.1568, "lr": 1.611906286914753e-05, "epoch": 20.151453131395826, "percentage": 61.56, "elapsed_time": "2:49:54", "remaining_time": "1:46:04", "throughput": 787.0, "total_tokens": 8022768} {"current_steps": 24630, "total_steps": 40000, "loss": 0.1363, "lr": 1.6109886411405144e-05, "epoch": 20.155546459271388, "percentage": 61.58, "elapsed_time": "2:49:55", "remaining_time": "1:46:02", "throughput": 787.03, "total_tokens": 8024448} {"current_steps": 24635, "total_steps": 40000, "loss": 0.1363, "lr": 1.6100711324629985e-05, "epoch": 20.15963978714695, "percentage": 61.59, "elapsed_time": "2:49:57", "remaining_time": "1:46:00", "throughput": 787.05, "total_tokens": 8026000} {"current_steps": 24640, "total_steps": 40000, "loss": 0.1318, "lr": 1.609153761023698e-05, "epoch": 20.163733115022513, "percentage": 61.6, "elapsed_time": "2:49:59", "remaining_time": "1:45:58", "throughput": 787.07, "total_tokens": 8027600} {"current_steps": 24645, "total_steps": 40000, "loss": 0.1062, "lr": 1.608236526964083e-05, "epoch": 20.167826442898075, "percentage": 61.61, "elapsed_time": "2:50:01", "remaining_time": "1:45:55", "throughput": 787.09, "total_tokens": 8029200} {"current_steps": 24650, "total_steps": 40000, "loss": 0.2637, "lr": 1.607319430425601e-05, "epoch": 20.171919770773638, "percentage": 61.62, "elapsed_time": "2:50:02", "remaining_time": "1:45:53", "throughput": 787.12, "total_tokens": 8030848} {"current_steps": 24655, "total_steps": 40000, "loss": 0.1947, "lr": 1.606402471549682e-05, "epoch": 20.1760130986492, "percentage": 61.64, "elapsed_time": "2:50:04", "remaining_time": "1:45:51", "throughput": 787.15, "total_tokens": 8032448} {"current_steps": 24660, "total_steps": 40000, "loss": 0.2471, "lr": 1.6054856504777312e-05, "epoch": 20.180106426524766, "percentage": 61.65, "elapsed_time": "2:50:06", "remaining_time": "1:45:48", "throughput": 787.18, "total_tokens": 8034112} {"current_steps": 24665, "total_steps": 40000, "loss": 0.1658, "lr": 1.6045689673511334e-05, "epoch": 20.18419975440033, "percentage": 61.66, "elapsed_time": "2:50:07", "remaining_time": "1:45:46", "throughput": 787.21, "total_tokens": 8035760} {"current_steps": 24670, "total_steps": 40000, "loss": 0.1529, "lr": 1.6036524223112548e-05, "epoch": 20.18829308227589, "percentage": 61.68, "elapsed_time": "2:50:09", "remaining_time": "1:45:44", "throughput": 787.24, "total_tokens": 8037392} {"current_steps": 24675, "total_steps": 40000, "loss": 0.1561, "lr": 1.602736015499436e-05, "epoch": 20.192386410151453, "percentage": 61.69, "elapsed_time": "2:50:11", "remaining_time": "1:45:42", "throughput": 787.26, "total_tokens": 8038976} {"current_steps": 24680, "total_steps": 40000, "loss": 0.1572, "lr": 1.601819747057e-05, "epoch": 20.196479738027016, "percentage": 61.7, "elapsed_time": "2:50:13", "remaining_time": "1:45:39", "throughput": 787.28, "total_tokens": 8040608} {"current_steps": 24685, "total_steps": 40000, "loss": 0.226, "lr": 1.6009036171252465e-05, "epoch": 20.200573065902578, "percentage": 61.71, "elapsed_time": "2:50:14", "remaining_time": "1:45:37", "throughput": 787.32, "total_tokens": 8042336} {"current_steps": 24690, "total_steps": 40000, "loss": 0.2494, "lr": 1.599987625845453e-05, "epoch": 20.20466639377814, "percentage": 61.72, "elapsed_time": "2:50:16", "remaining_time": "1:45:35", "throughput": 787.35, "total_tokens": 8044016} {"current_steps": 24695, "total_steps": 40000, "loss": 0.2402, "lr": 1.599071773358879e-05, "epoch": 20.208759721653703, "percentage": 61.74, "elapsed_time": "2:50:18", "remaining_time": "1:45:32", "throughput": 787.38, "total_tokens": 8045632} {"current_steps": 24700, "total_steps": 40000, "loss": 0.1196, "lr": 1.598156059806758e-05, "epoch": 20.21285304952927, "percentage": 61.75, "elapsed_time": "2:50:19", "remaining_time": "1:45:30", "throughput": 787.41, "total_tokens": 8047312} {"current_steps": 24705, "total_steps": 40000, "loss": 0.1727, "lr": 1.5972404853303062e-05, "epoch": 20.21694637740483, "percentage": 61.76, "elapsed_time": "2:50:21", "remaining_time": "1:45:28", "throughput": 787.44, "total_tokens": 8048960} {"current_steps": 24710, "total_steps": 40000, "loss": 0.192, "lr": 1.5963250500707172e-05, "epoch": 20.221039705280393, "percentage": 61.78, "elapsed_time": "2:50:23", "remaining_time": "1:45:26", "throughput": 787.47, "total_tokens": 8050640} {"current_steps": 24715, "total_steps": 40000, "loss": 0.1985, "lr": 1.5954097541691612e-05, "epoch": 20.225133033155956, "percentage": 61.79, "elapsed_time": "2:50:25", "remaining_time": "1:45:23", "throughput": 787.5, "total_tokens": 8052288} {"current_steps": 24720, "total_steps": 40000, "loss": 0.1376, "lr": 1.5944945977667884e-05, "epoch": 20.229226361031518, "percentage": 61.8, "elapsed_time": "2:50:26", "remaining_time": "1:45:21", "throughput": 787.52, "total_tokens": 8053888} {"current_steps": 24725, "total_steps": 40000, "loss": 0.2311, "lr": 1.593579581004729e-05, "epoch": 20.23331968890708, "percentage": 61.81, "elapsed_time": "2:50:28", "remaining_time": "1:45:19", "throughput": 787.53, "total_tokens": 8055488} {"current_steps": 24730, "total_steps": 40000, "loss": 0.1335, "lr": 1.592664704024088e-05, "epoch": 20.237413016782643, "percentage": 61.82, "elapsed_time": "2:50:30", "remaining_time": "1:45:17", "throughput": 787.55, "total_tokens": 8057120} {"current_steps": 24735, "total_steps": 40000, "loss": 0.1804, "lr": 1.591749966965953e-05, "epoch": 20.24150634465821, "percentage": 61.84, "elapsed_time": "2:50:32", "remaining_time": "1:45:14", "throughput": 787.58, "total_tokens": 8058688} {"current_steps": 24740, "total_steps": 40000, "loss": 0.1567, "lr": 1.5908353699713856e-05, "epoch": 20.24559967253377, "percentage": 61.85, "elapsed_time": "2:50:33", "remaining_time": "1:45:12", "throughput": 787.6, "total_tokens": 8060304} {"current_steps": 24745, "total_steps": 40000, "loss": 0.2337, "lr": 1.5899209131814298e-05, "epoch": 20.249693000409334, "percentage": 61.86, "elapsed_time": "2:50:35", "remaining_time": "1:45:10", "throughput": 787.63, "total_tokens": 8061920} {"current_steps": 24750, "total_steps": 40000, "loss": 0.1316, "lr": 1.5890065967371067e-05, "epoch": 20.253786328284896, "percentage": 61.88, "elapsed_time": "2:50:37", "remaining_time": "1:45:07", "throughput": 787.65, "total_tokens": 8063552} {"current_steps": 24755, "total_steps": 40000, "loss": 0.1294, "lr": 1.5880924207794144e-05, "epoch": 20.25787965616046, "percentage": 61.89, "elapsed_time": "2:50:39", "remaining_time": "1:45:05", "throughput": 787.68, "total_tokens": 8065168} {"current_steps": 24760, "total_steps": 40000, "loss": 0.1669, "lr": 1.5871783854493298e-05, "epoch": 20.26197298403602, "percentage": 61.9, "elapsed_time": "2:50:40", "remaining_time": "1:45:03", "throughput": 787.71, "total_tokens": 8066816} {"current_steps": 24765, "total_steps": 40000, "loss": 0.1322, "lr": 1.5862644908878106e-05, "epoch": 20.266066311911583, "percentage": 61.91, "elapsed_time": "2:50:42", "remaining_time": "1:45:01", "throughput": 787.74, "total_tokens": 8068464} {"current_steps": 24770, "total_steps": 40000, "loss": 0.1376, "lr": 1.5853507372357885e-05, "epoch": 20.270159639787146, "percentage": 61.92, "elapsed_time": "2:50:44", "remaining_time": "1:44:58", "throughput": 787.76, "total_tokens": 8070064} {"current_steps": 24775, "total_steps": 40000, "loss": 0.1462, "lr": 1.5844371246341776e-05, "epoch": 20.27425296766271, "percentage": 61.94, "elapsed_time": "2:50:46", "remaining_time": "1:44:56", "throughput": 787.79, "total_tokens": 8071680} {"current_steps": 24780, "total_steps": 40000, "loss": 0.1452, "lr": 1.5835236532238674e-05, "epoch": 20.278346295538274, "percentage": 61.95, "elapsed_time": "2:50:47", "remaining_time": "1:44:54", "throughput": 787.82, "total_tokens": 8073360} {"current_steps": 24785, "total_steps": 40000, "loss": 0.1385, "lr": 1.582610323145727e-05, "epoch": 20.282439623413836, "percentage": 61.96, "elapsed_time": "2:50:49", "remaining_time": "1:44:51", "throughput": 787.85, "total_tokens": 8075008} {"current_steps": 24790, "total_steps": 40000, "loss": 0.2775, "lr": 1.5816971345406035e-05, "epoch": 20.2865329512894, "percentage": 61.98, "elapsed_time": "2:50:51", "remaining_time": "1:44:49", "throughput": 787.88, "total_tokens": 8076640} {"current_steps": 24795, "total_steps": 40000, "loss": 0.1074, "lr": 1.5807840875493225e-05, "epoch": 20.29062627916496, "percentage": 61.99, "elapsed_time": "2:50:52", "remaining_time": "1:44:47", "throughput": 787.9, "total_tokens": 8078240} {"current_steps": 24800, "total_steps": 40000, "loss": 0.2689, "lr": 1.5798711823126854e-05, "epoch": 20.294719607040523, "percentage": 62.0, "elapsed_time": "2:50:54", "remaining_time": "1:44:45", "throughput": 787.93, "total_tokens": 8079920} {"current_steps": 24800, "total_steps": 40000, "eval_loss": 0.21319489181041718, "epoch": 20.294719607040523, "percentage": 62.0, "elapsed_time": "2:51:07", "remaining_time": "1:44:52", "throughput": 786.98, "total_tokens": 8079920} {"current_steps": 24805, "total_steps": 40000, "loss": 0.1746, "lr": 1.578958418971477e-05, "epoch": 20.298812934916086, "percentage": 62.01, "elapsed_time": "2:51:10", "remaining_time": "1:44:51", "throughput": 786.9, "total_tokens": 8081680} {"current_steps": 24810, "total_steps": 40000, "loss": 0.2632, "lr": 1.578045797666453e-05, "epoch": 20.302906262791648, "percentage": 62.02, "elapsed_time": "2:51:11", "remaining_time": "1:44:49", "throughput": 786.93, "total_tokens": 8083328} {"current_steps": 24815, "total_steps": 40000, "loss": 0.2043, "lr": 1.5771333185383548e-05, "epoch": 20.306999590667214, "percentage": 62.04, "elapsed_time": "2:51:13", "remaining_time": "1:44:46", "throughput": 786.97, "total_tokens": 8085024} {"current_steps": 24820, "total_steps": 40000, "loss": 0.1426, "lr": 1.576220981727895e-05, "epoch": 20.311092918542776, "percentage": 62.05, "elapsed_time": "2:51:15", "remaining_time": "1:44:44", "throughput": 786.99, "total_tokens": 8086688} {"current_steps": 24825, "total_steps": 40000, "loss": 0.1171, "lr": 1.575308787375769e-05, "epoch": 20.31518624641834, "percentage": 62.06, "elapsed_time": "2:51:17", "remaining_time": "1:44:42", "throughput": 787.02, "total_tokens": 8088272} {"current_steps": 24830, "total_steps": 40000, "loss": 0.1878, "lr": 1.5743967356226492e-05, "epoch": 20.3192795742939, "percentage": 62.08, "elapsed_time": "2:51:18", "remaining_time": "1:44:39", "throughput": 787.05, "total_tokens": 8089936} {"current_steps": 24835, "total_steps": 40000, "loss": 0.191, "lr": 1.5734848266091835e-05, "epoch": 20.323372902169464, "percentage": 62.09, "elapsed_time": "2:51:20", "remaining_time": "1:44:37", "throughput": 787.07, "total_tokens": 8091536} {"current_steps": 24840, "total_steps": 40000, "loss": 0.1636, "lr": 1.572573060476001e-05, "epoch": 20.327466230045026, "percentage": 62.1, "elapsed_time": "2:51:22", "remaining_time": "1:44:35", "throughput": 787.11, "total_tokens": 8093248} {"current_steps": 24845, "total_steps": 40000, "loss": 0.1861, "lr": 1.5716614373637085e-05, "epoch": 20.33155955792059, "percentage": 62.11, "elapsed_time": "2:51:23", "remaining_time": "1:44:33", "throughput": 787.13, "total_tokens": 8094880} {"current_steps": 24850, "total_steps": 40000, "loss": 0.2532, "lr": 1.570749957412887e-05, "epoch": 20.33565288579615, "percentage": 62.12, "elapsed_time": "2:51:25", "remaining_time": "1:44:30", "throughput": 787.17, "total_tokens": 8096560} {"current_steps": 24855, "total_steps": 40000, "loss": 0.1739, "lr": 1.5698386207641013e-05, "epoch": 20.339746213671717, "percentage": 62.14, "elapsed_time": "2:51:27", "remaining_time": "1:44:28", "throughput": 787.19, "total_tokens": 8098176} {"current_steps": 24860, "total_steps": 40000, "loss": 0.1368, "lr": 1.5689274275578884e-05, "epoch": 20.34383954154728, "percentage": 62.15, "elapsed_time": "2:51:29", "remaining_time": "1:44:26", "throughput": 787.23, "total_tokens": 8099904} {"current_steps": 24865, "total_steps": 40000, "loss": 0.1507, "lr": 1.5680163779347667e-05, "epoch": 20.34793286942284, "percentage": 62.16, "elapsed_time": "2:51:30", "remaining_time": "1:44:23", "throughput": 787.26, "total_tokens": 8101552} {"current_steps": 24870, "total_steps": 40000, "loss": 0.1664, "lr": 1.5671054720352327e-05, "epoch": 20.352026197298404, "percentage": 62.18, "elapsed_time": "2:51:32", "remaining_time": "1:44:21", "throughput": 787.28, "total_tokens": 8103120} {"current_steps": 24875, "total_steps": 40000, "loss": 0.1406, "lr": 1.566194709999757e-05, "epoch": 20.356119525173966, "percentage": 62.19, "elapsed_time": "2:51:34", "remaining_time": "1:44:19", "throughput": 787.31, "total_tokens": 8104816} {"current_steps": 24880, "total_steps": 40000, "loss": 0.2394, "lr": 1.5652840919687933e-05, "epoch": 20.36021285304953, "percentage": 62.2, "elapsed_time": "2:51:36", "remaining_time": "1:44:17", "throughput": 787.34, "total_tokens": 8106464} {"current_steps": 24885, "total_steps": 40000, "loss": 0.2184, "lr": 1.5643736180827676e-05, "epoch": 20.36430618092509, "percentage": 62.21, "elapsed_time": "2:51:37", "remaining_time": "1:44:14", "throughput": 787.36, "total_tokens": 8108048} {"current_steps": 24890, "total_steps": 40000, "loss": 0.1884, "lr": 1.5634632884820878e-05, "epoch": 20.368399508800653, "percentage": 62.22, "elapsed_time": "2:51:39", "remaining_time": "1:44:12", "throughput": 787.4, "total_tokens": 8109744} {"current_steps": 24895, "total_steps": 40000, "loss": 0.1366, "lr": 1.5625531033071395e-05, "epoch": 20.37249283667622, "percentage": 62.24, "elapsed_time": "2:51:41", "remaining_time": "1:44:10", "throughput": 787.42, "total_tokens": 8111344} {"current_steps": 24900, "total_steps": 40000, "loss": 0.1486, "lr": 1.5616430626982828e-05, "epoch": 20.37658616455178, "percentage": 62.25, "elapsed_time": "2:51:42", "remaining_time": "1:44:07", "throughput": 787.44, "total_tokens": 8112944} {"current_steps": 24905, "total_steps": 40000, "loss": 0.188, "lr": 1.5607331667958575e-05, "epoch": 20.380679492427344, "percentage": 62.26, "elapsed_time": "2:51:44", "remaining_time": "1:44:05", "throughput": 787.47, "total_tokens": 8114560} {"current_steps": 24910, "total_steps": 40000, "loss": 0.2322, "lr": 1.5598234157401824e-05, "epoch": 20.384772820302906, "percentage": 62.28, "elapsed_time": "2:51:46", "remaining_time": "1:44:03", "throughput": 787.49, "total_tokens": 8116176} {"current_steps": 24915, "total_steps": 40000, "loss": 0.2077, "lr": 1.5589138096715503e-05, "epoch": 20.38886614817847, "percentage": 62.29, "elapsed_time": "2:51:48", "remaining_time": "1:44:01", "throughput": 787.52, "total_tokens": 8117824} {"current_steps": 24920, "total_steps": 40000, "loss": 0.1309, "lr": 1.5580043487302365e-05, "epoch": 20.39295947605403, "percentage": 62.3, "elapsed_time": "2:51:49", "remaining_time": "1:43:58", "throughput": 787.55, "total_tokens": 8119472} {"current_steps": 24925, "total_steps": 40000, "loss": 0.1826, "lr": 1.5570950330564888e-05, "epoch": 20.397052803929594, "percentage": 62.31, "elapsed_time": "2:51:51", "remaining_time": "1:43:56", "throughput": 787.58, "total_tokens": 8121120} {"current_steps": 24930, "total_steps": 40000, "loss": 0.1635, "lr": 1.5561858627905367e-05, "epoch": 20.401146131805156, "percentage": 62.32, "elapsed_time": "2:51:53", "remaining_time": "1:43:54", "throughput": 787.61, "total_tokens": 8122784} {"current_steps": 24935, "total_steps": 40000, "loss": 0.2218, "lr": 1.5552768380725857e-05, "epoch": 20.405239459680722, "percentage": 62.34, "elapsed_time": "2:51:54", "remaining_time": "1:43:51", "throughput": 787.63, "total_tokens": 8124336} {"current_steps": 24940, "total_steps": 40000, "loss": 0.129, "lr": 1.5543679590428183e-05, "epoch": 20.409332787556284, "percentage": 62.35, "elapsed_time": "2:51:56", "remaining_time": "1:43:49", "throughput": 787.65, "total_tokens": 8125968} {"current_steps": 24945, "total_steps": 40000, "loss": 0.2352, "lr": 1.5534592258413943e-05, "epoch": 20.413426115431847, "percentage": 62.36, "elapsed_time": "2:51:58", "remaining_time": "1:43:47", "throughput": 787.68, "total_tokens": 8127584} {"current_steps": 24950, "total_steps": 40000, "loss": 0.2052, "lr": 1.5525506386084538e-05, "epoch": 20.41751944330741, "percentage": 62.38, "elapsed_time": "2:52:00", "remaining_time": "1:43:45", "throughput": 787.71, "total_tokens": 8129248} {"current_steps": 24955, "total_steps": 40000, "loss": 0.2505, "lr": 1.55164219748411e-05, "epoch": 20.42161277118297, "percentage": 62.39, "elapsed_time": "2:52:01", "remaining_time": "1:43:42", "throughput": 787.74, "total_tokens": 8130912} {"current_steps": 24960, "total_steps": 40000, "loss": 0.1481, "lr": 1.550733902608459e-05, "epoch": 20.425706099058534, "percentage": 62.4, "elapsed_time": "2:52:03", "remaining_time": "1:43:40", "throughput": 787.77, "total_tokens": 8132576} {"current_steps": 24965, "total_steps": 40000, "loss": 0.178, "lr": 1.549825754121568e-05, "epoch": 20.429799426934096, "percentage": 62.41, "elapsed_time": "2:52:05", "remaining_time": "1:43:38", "throughput": 787.8, "total_tokens": 8134224} {"current_steps": 24970, "total_steps": 40000, "loss": 0.1512, "lr": 1.5489177521634864e-05, "epoch": 20.433892754809662, "percentage": 62.42, "elapsed_time": "2:52:06", "remaining_time": "1:43:36", "throughput": 787.82, "total_tokens": 8135840} {"current_steps": 24975, "total_steps": 40000, "loss": 0.2579, "lr": 1.5480098968742402e-05, "epoch": 20.437986082685224, "percentage": 62.44, "elapsed_time": "2:52:08", "remaining_time": "1:43:33", "throughput": 787.84, "total_tokens": 8137408} {"current_steps": 24980, "total_steps": 40000, "loss": 0.1201, "lr": 1.5471021883938304e-05, "epoch": 20.442079410560787, "percentage": 62.45, "elapsed_time": "2:52:10", "remaining_time": "1:43:31", "throughput": 787.87, "total_tokens": 8139024} {"current_steps": 24985, "total_steps": 40000, "loss": 0.1412, "lr": 1.546194626862238e-05, "epoch": 20.44617273843635, "percentage": 62.46, "elapsed_time": "2:52:12", "remaining_time": "1:43:29", "throughput": 787.9, "total_tokens": 8140688} {"current_steps": 24990, "total_steps": 40000, "loss": 0.237, "lr": 1.5452872124194216e-05, "epoch": 20.45026606631191, "percentage": 62.48, "elapsed_time": "2:52:13", "remaining_time": "1:43:26", "throughput": 787.92, "total_tokens": 8142304} {"current_steps": 24995, "total_steps": 40000, "loss": 0.099, "lr": 1.5443799452053136e-05, "epoch": 20.454359394187474, "percentage": 62.49, "elapsed_time": "2:52:15", "remaining_time": "1:43:24", "throughput": 787.95, "total_tokens": 8143952} {"current_steps": 25000, "total_steps": 40000, "loss": 0.1624, "lr": 1.543472825359828e-05, "epoch": 20.458452722063036, "percentage": 62.5, "elapsed_time": "2:52:17", "remaining_time": "1:43:22", "throughput": 787.98, "total_tokens": 8145552} {"current_steps": 25000, "total_steps": 40000, "eval_loss": 0.21017824113368988, "epoch": 20.458452722063036, "percentage": 62.5, "elapsed_time": "2:52:29", "remaining_time": "1:43:29", "throughput": 787.03, "total_tokens": 8145552} {"current_steps": 25005, "total_steps": 40000, "loss": 0.1058, "lr": 1.5425658530228522e-05, "epoch": 20.4625460499386, "percentage": 62.51, "elapsed_time": "2:52:33", "remaining_time": "1:43:28", "throughput": 786.93, "total_tokens": 8147152} {"current_steps": 25010, "total_steps": 40000, "loss": 0.216, "lr": 1.5416590283342546e-05, "epoch": 20.466639377814165, "percentage": 62.52, "elapsed_time": "2:52:34", "remaining_time": "1:43:26", "throughput": 786.96, "total_tokens": 8148832} {"current_steps": 25015, "total_steps": 40000, "loss": 0.1811, "lr": 1.5407523514338783e-05, "epoch": 20.470732705689727, "percentage": 62.54, "elapsed_time": "2:52:36", "remaining_time": "1:43:23", "throughput": 786.99, "total_tokens": 8150480} {"current_steps": 25020, "total_steps": 40000, "loss": 0.197, "lr": 1.539845822461543e-05, "epoch": 20.47482603356529, "percentage": 62.55, "elapsed_time": "2:52:38", "remaining_time": "1:43:21", "throughput": 787.02, "total_tokens": 8152144} {"current_steps": 25025, "total_steps": 40000, "loss": 0.1721, "lr": 1.538939441557048e-05, "epoch": 20.478919361440852, "percentage": 62.56, "elapsed_time": "2:52:39", "remaining_time": "1:43:19", "throughput": 787.05, "total_tokens": 8153760} {"current_steps": 25030, "total_steps": 40000, "loss": 0.2342, "lr": 1.5380332088601696e-05, "epoch": 20.483012689316414, "percentage": 62.58, "elapsed_time": "2:52:41", "remaining_time": "1:43:17", "throughput": 787.08, "total_tokens": 8155392} {"current_steps": 25035, "total_steps": 40000, "loss": 0.1966, "lr": 1.537127124510658e-05, "epoch": 20.487106017191977, "percentage": 62.59, "elapsed_time": "2:52:43", "remaining_time": "1:43:14", "throughput": 787.1, "total_tokens": 8156976} {"current_steps": 25040, "total_steps": 40000, "loss": 0.1635, "lr": 1.5362211886482457e-05, "epoch": 20.49119934506754, "percentage": 62.6, "elapsed_time": "2:52:45", "remaining_time": "1:43:12", "throughput": 787.12, "total_tokens": 8158576} {"current_steps": 25045, "total_steps": 40000, "loss": 0.1419, "lr": 1.5353154014126363e-05, "epoch": 20.4952926729431, "percentage": 62.61, "elapsed_time": "2:52:46", "remaining_time": "1:43:10", "throughput": 787.15, "total_tokens": 8160224} {"current_steps": 25050, "total_steps": 40000, "loss": 0.2348, "lr": 1.534409762943515e-05, "epoch": 20.499386000818667, "percentage": 62.62, "elapsed_time": "2:52:48", "remaining_time": "1:43:08", "throughput": 787.18, "total_tokens": 8161856} {"current_steps": 25055, "total_steps": 40000, "loss": 0.2006, "lr": 1.5335042733805438e-05, "epoch": 20.50347932869423, "percentage": 62.64, "elapsed_time": "2:52:50", "remaining_time": "1:43:05", "throughput": 787.21, "total_tokens": 8163520} {"current_steps": 25060, "total_steps": 40000, "loss": 0.1581, "lr": 1.532598932863358e-05, "epoch": 20.507572656569792, "percentage": 62.65, "elapsed_time": "2:52:51", "remaining_time": "1:43:03", "throughput": 787.23, "total_tokens": 8165072} {"current_steps": 25065, "total_steps": 40000, "loss": 0.1894, "lr": 1.531693741531574e-05, "epoch": 20.511665984445354, "percentage": 62.66, "elapsed_time": "2:52:53", "remaining_time": "1:43:01", "throughput": 787.26, "total_tokens": 8166768} {"current_steps": 25070, "total_steps": 40000, "loss": 0.1403, "lr": 1.5307886995247844e-05, "epoch": 20.515759312320917, "percentage": 62.68, "elapsed_time": "2:52:55", "remaining_time": "1:42:58", "throughput": 787.29, "total_tokens": 8168400} {"current_steps": 25075, "total_steps": 40000, "loss": 0.1692, "lr": 1.529883806982557e-05, "epoch": 20.51985264019648, "percentage": 62.69, "elapsed_time": "2:52:57", "remaining_time": "1:42:56", "throughput": 787.31, "total_tokens": 8170000} {"current_steps": 25080, "total_steps": 40000, "loss": 0.1936, "lr": 1.5289790640444376e-05, "epoch": 20.52394596807204, "percentage": 62.7, "elapsed_time": "2:52:58", "remaining_time": "1:42:54", "throughput": 787.34, "total_tokens": 8171648} {"current_steps": 25085, "total_steps": 40000, "loss": 0.1251, "lr": 1.5280744708499494e-05, "epoch": 20.528039295947604, "percentage": 62.71, "elapsed_time": "2:53:00", "remaining_time": "1:42:52", "throughput": 787.36, "total_tokens": 8173264} {"current_steps": 25090, "total_steps": 40000, "loss": 0.1475, "lr": 1.527170027538591e-05, "epoch": 20.53213262382317, "percentage": 62.72, "elapsed_time": "2:53:02", "remaining_time": "1:42:49", "throughput": 787.39, "total_tokens": 8174864} {"current_steps": 25095, "total_steps": 40000, "loss": 0.1855, "lr": 1.5262657342498407e-05, "epoch": 20.536225951698732, "percentage": 62.74, "elapsed_time": "2:53:03", "remaining_time": "1:42:47", "throughput": 787.41, "total_tokens": 8176464} {"current_steps": 25100, "total_steps": 40000, "loss": 0.1745, "lr": 1.52536159112315e-05, "epoch": 20.540319279574295, "percentage": 62.75, "elapsed_time": "2:53:05", "remaining_time": "1:42:45", "throughput": 787.44, "total_tokens": 8178112} {"current_steps": 25105, "total_steps": 40000, "loss": 0.2248, "lr": 1.5244575982979497e-05, "epoch": 20.544412607449857, "percentage": 62.76, "elapsed_time": "2:53:07", "remaining_time": "1:42:42", "throughput": 787.47, "total_tokens": 8179744} {"current_steps": 25110, "total_steps": 40000, "loss": 0.2002, "lr": 1.5235537559136487e-05, "epoch": 20.54850593532542, "percentage": 62.78, "elapsed_time": "2:53:09", "remaining_time": "1:42:40", "throughput": 787.49, "total_tokens": 8181360} {"current_steps": 25115, "total_steps": 40000, "loss": 0.2513, "lr": 1.5226500641096286e-05, "epoch": 20.55259926320098, "percentage": 62.79, "elapsed_time": "2:53:10", "remaining_time": "1:42:38", "throughput": 787.52, "total_tokens": 8183040} {"current_steps": 25120, "total_steps": 40000, "loss": 0.1713, "lr": 1.5217465230252509e-05, "epoch": 20.556692591076544, "percentage": 62.8, "elapsed_time": "2:53:12", "remaining_time": "1:42:36", "throughput": 787.55, "total_tokens": 8184688} {"current_steps": 25125, "total_steps": 40000, "loss": 0.13, "lr": 1.5208431327998523e-05, "epoch": 20.560785918952106, "percentage": 62.81, "elapsed_time": "2:53:14", "remaining_time": "1:42:33", "throughput": 787.58, "total_tokens": 8186368} {"current_steps": 25130, "total_steps": 40000, "loss": 0.194, "lr": 1.5199398935727477e-05, "epoch": 20.564879246827672, "percentage": 62.82, "elapsed_time": "2:53:16", "remaining_time": "1:42:31", "throughput": 787.61, "total_tokens": 8187968} {"current_steps": 25135, "total_steps": 40000, "loss": 0.1267, "lr": 1.5190368054832282e-05, "epoch": 20.568972574703235, "percentage": 62.84, "elapsed_time": "2:53:17", "remaining_time": "1:42:29", "throughput": 787.63, "total_tokens": 8189600} {"current_steps": 25140, "total_steps": 40000, "loss": 0.1716, "lr": 1.5181338686705601e-05, "epoch": 20.573065902578797, "percentage": 62.85, "elapsed_time": "2:53:19", "remaining_time": "1:42:27", "throughput": 787.66, "total_tokens": 8191248} {"current_steps": 25145, "total_steps": 40000, "loss": 0.1308, "lr": 1.5172310832739889e-05, "epoch": 20.57715923045436, "percentage": 62.86, "elapsed_time": "2:53:21", "remaining_time": "1:42:24", "throughput": 787.69, "total_tokens": 8192864} {"current_steps": 25150, "total_steps": 40000, "loss": 0.1732, "lr": 1.5163284494327346e-05, "epoch": 20.581252558329922, "percentage": 62.88, "elapsed_time": "2:53:22", "remaining_time": "1:42:22", "throughput": 787.72, "total_tokens": 8194544} {"current_steps": 25155, "total_steps": 40000, "loss": 0.2135, "lr": 1.5154259672859952e-05, "epoch": 20.585345886205484, "percentage": 62.89, "elapsed_time": "2:53:24", "remaining_time": "1:42:20", "throughput": 787.74, "total_tokens": 8196160} {"current_steps": 25160, "total_steps": 40000, "loss": 0.2264, "lr": 1.5145236369729452e-05, "epoch": 20.589439214081047, "percentage": 62.9, "elapsed_time": "2:53:26", "remaining_time": "1:42:17", "throughput": 787.77, "total_tokens": 8197824} {"current_steps": 25165, "total_steps": 40000, "loss": 0.2534, "lr": 1.5136214586327335e-05, "epoch": 20.59353254195661, "percentage": 62.91, "elapsed_time": "2:53:28", "remaining_time": "1:42:15", "throughput": 787.8, "total_tokens": 8199424} {"current_steps": 25170, "total_steps": 40000, "loss": 0.1411, "lr": 1.5127194324044885e-05, "epoch": 20.597625869832175, "percentage": 62.92, "elapsed_time": "2:53:29", "remaining_time": "1:42:13", "throughput": 787.82, "total_tokens": 8201024} {"current_steps": 25175, "total_steps": 40000, "loss": 0.145, "lr": 1.5118175584273148e-05, "epoch": 20.601719197707737, "percentage": 62.94, "elapsed_time": "2:53:31", "remaining_time": "1:42:11", "throughput": 787.85, "total_tokens": 8202640} {"current_steps": 25180, "total_steps": 40000, "loss": 0.1794, "lr": 1.5109158368402909e-05, "epoch": 20.6058125255833, "percentage": 62.95, "elapsed_time": "2:53:33", "remaining_time": "1:42:08", "throughput": 787.87, "total_tokens": 8204288} {"current_steps": 25185, "total_steps": 40000, "loss": 0.1798, "lr": 1.5100142677824753e-05, "epoch": 20.609905853458862, "percentage": 62.96, "elapsed_time": "2:53:34", "remaining_time": "1:42:06", "throughput": 787.9, "total_tokens": 8205904} {"current_steps": 25190, "total_steps": 40000, "loss": 0.1775, "lr": 1.509112851392901e-05, "epoch": 20.613999181334425, "percentage": 62.98, "elapsed_time": "2:53:36", "remaining_time": "1:42:04", "throughput": 787.92, "total_tokens": 8207472} {"current_steps": 25195, "total_steps": 40000, "loss": 0.2425, "lr": 1.5082115878105763e-05, "epoch": 20.618092509209987, "percentage": 62.99, "elapsed_time": "2:53:38", "remaining_time": "1:42:01", "throughput": 787.94, "total_tokens": 8209040} {"current_steps": 25200, "total_steps": 40000, "loss": 0.228, "lr": 1.5073104771744892e-05, "epoch": 20.62218583708555, "percentage": 63.0, "elapsed_time": "2:53:40", "remaining_time": "1:41:59", "throughput": 787.97, "total_tokens": 8210688} {"current_steps": 25200, "total_steps": 40000, "eval_loss": 0.20949143171310425, "epoch": 20.62218583708555, "percentage": 63.0, "elapsed_time": "2:53:52", "remaining_time": "1:42:07", "throughput": 787.03, "total_tokens": 8210688} {"current_steps": 25205, "total_steps": 40000, "loss": 0.2219, "lr": 1.5064095196236006e-05, "epoch": 20.62627916496111, "percentage": 63.01, "elapsed_time": "2:53:55", "remaining_time": "1:42:05", "throughput": 786.94, "total_tokens": 8212336} {"current_steps": 25210, "total_steps": 40000, "loss": 0.173, "lr": 1.50550871529685e-05, "epoch": 20.630372492836678, "percentage": 63.02, "elapsed_time": "2:53:57", "remaining_time": "1:42:03", "throughput": 786.96, "total_tokens": 8213936} {"current_steps": 25215, "total_steps": 40000, "loss": 0.1907, "lr": 1.5046080643331546e-05, "epoch": 20.63446582071224, "percentage": 63.04, "elapsed_time": "2:53:59", "remaining_time": "1:42:01", "throughput": 786.99, "total_tokens": 8215552} {"current_steps": 25220, "total_steps": 40000, "loss": 0.1649, "lr": 1.5037075668714028e-05, "epoch": 20.638559148587802, "percentage": 63.05, "elapsed_time": "2:54:00", "remaining_time": "1:41:58", "throughput": 787.01, "total_tokens": 8217152} {"current_steps": 25225, "total_steps": 40000, "loss": 0.1139, "lr": 1.5028072230504656e-05, "epoch": 20.642652476463365, "percentage": 63.06, "elapsed_time": "2:54:02", "remaining_time": "1:41:56", "throughput": 787.04, "total_tokens": 8218832} {"current_steps": 25230, "total_steps": 40000, "loss": 0.2127, "lr": 1.5019070330091861e-05, "epoch": 20.646745804338927, "percentage": 63.08, "elapsed_time": "2:54:04", "remaining_time": "1:41:54", "throughput": 787.07, "total_tokens": 8220416} {"current_steps": 25235, "total_steps": 40000, "loss": 0.2304, "lr": 1.5010069968863843e-05, "epoch": 20.65083913221449, "percentage": 63.09, "elapsed_time": "2:54:06", "remaining_time": "1:41:52", "throughput": 787.09, "total_tokens": 8222016} {"current_steps": 25240, "total_steps": 40000, "loss": 0.1734, "lr": 1.5001071148208584e-05, "epoch": 20.654932460090052, "percentage": 63.1, "elapsed_time": "2:54:07", "remaining_time": "1:41:49", "throughput": 787.12, "total_tokens": 8223632} {"current_steps": 25245, "total_steps": 40000, "loss": 0.1821, "lr": 1.49920738695138e-05, "epoch": 20.659025787965618, "percentage": 63.11, "elapsed_time": "2:54:09", "remaining_time": "1:41:47", "throughput": 787.14, "total_tokens": 8225264} {"current_steps": 25250, "total_steps": 40000, "loss": 0.2213, "lr": 1.4983078134166995e-05, "epoch": 20.66311911584118, "percentage": 63.12, "elapsed_time": "2:54:11", "remaining_time": "1:41:45", "throughput": 787.18, "total_tokens": 8226992} {"current_steps": 25255, "total_steps": 40000, "loss": 0.1529, "lr": 1.4974083943555428e-05, "epoch": 20.667212443716743, "percentage": 63.14, "elapsed_time": "2:54:12", "remaining_time": "1:41:42", "throughput": 787.2, "total_tokens": 8228608} {"current_steps": 25260, "total_steps": 40000, "loss": 0.1386, "lr": 1.496509129906611e-05, "epoch": 20.671305771592305, "percentage": 63.15, "elapsed_time": "2:54:14", "remaining_time": "1:41:40", "throughput": 787.23, "total_tokens": 8230256} {"current_steps": 25265, "total_steps": 40000, "loss": 0.1612, "lr": 1.4956100202085809e-05, "epoch": 20.675399099467867, "percentage": 63.16, "elapsed_time": "2:54:16", "remaining_time": "1:41:38", "throughput": 787.25, "total_tokens": 8231856} {"current_steps": 25270, "total_steps": 40000, "loss": 0.1508, "lr": 1.4947110654001093e-05, "epoch": 20.67949242734343, "percentage": 63.18, "elapsed_time": "2:54:18", "remaining_time": "1:41:36", "throughput": 787.28, "total_tokens": 8233472} {"current_steps": 25275, "total_steps": 40000, "loss": 0.1361, "lr": 1.4938122656198234e-05, "epoch": 20.683585755218992, "percentage": 63.19, "elapsed_time": "2:54:19", "remaining_time": "1:41:33", "throughput": 787.3, "total_tokens": 8235088} {"current_steps": 25280, "total_steps": 40000, "loss": 0.081, "lr": 1.4929136210063316e-05, "epoch": 20.687679083094554, "percentage": 63.2, "elapsed_time": "2:54:21", "remaining_time": "1:41:31", "throughput": 787.33, "total_tokens": 8236704} {"current_steps": 25285, "total_steps": 40000, "loss": 0.0924, "lr": 1.4920151316982146e-05, "epoch": 20.691772410970117, "percentage": 63.21, "elapsed_time": "2:54:23", "remaining_time": "1:41:29", "throughput": 787.36, "total_tokens": 8238384} {"current_steps": 25290, "total_steps": 40000, "loss": 0.3229, "lr": 1.4911167978340312e-05, "epoch": 20.695865738845683, "percentage": 63.22, "elapsed_time": "2:54:25", "remaining_time": "1:41:27", "throughput": 787.38, "total_tokens": 8239968} {"current_steps": 25295, "total_steps": 40000, "loss": 0.1751, "lr": 1.4902186195523166e-05, "epoch": 20.699959066721245, "percentage": 63.24, "elapsed_time": "2:54:26", "remaining_time": "1:41:24", "throughput": 787.41, "total_tokens": 8241648} {"current_steps": 25300, "total_steps": 40000, "loss": 0.1259, "lr": 1.4893205969915805e-05, "epoch": 20.704052394596808, "percentage": 63.25, "elapsed_time": "2:54:28", "remaining_time": "1:41:22", "throughput": 787.44, "total_tokens": 8243280} {"current_steps": 25305, "total_steps": 40000, "loss": 0.1611, "lr": 1.4884227302903086e-05, "epoch": 20.70814572247237, "percentage": 63.26, "elapsed_time": "2:54:30", "remaining_time": "1:41:20", "throughput": 787.46, "total_tokens": 8244880} {"current_steps": 25310, "total_steps": 40000, "loss": 0.15, "lr": 1.4875250195869653e-05, "epoch": 20.712239050347932, "percentage": 63.28, "elapsed_time": "2:54:31", "remaining_time": "1:41:17", "throughput": 787.49, "total_tokens": 8246528} {"current_steps": 25315, "total_steps": 40000, "loss": 0.1866, "lr": 1.4866274650199862e-05, "epoch": 20.716332378223495, "percentage": 63.29, "elapsed_time": "2:54:33", "remaining_time": "1:41:15", "throughput": 787.51, "total_tokens": 8248096} {"current_steps": 25320, "total_steps": 40000, "loss": 0.1157, "lr": 1.485730066727788e-05, "epoch": 20.720425706099057, "percentage": 63.3, "elapsed_time": "2:54:35", "remaining_time": "1:41:13", "throughput": 787.54, "total_tokens": 8249744} {"current_steps": 25325, "total_steps": 40000, "loss": 0.1965, "lr": 1.4848328248487586e-05, "epoch": 20.724519033974623, "percentage": 63.31, "elapsed_time": "2:54:37", "remaining_time": "1:41:11", "throughput": 787.57, "total_tokens": 8251376} {"current_steps": 25330, "total_steps": 40000, "loss": 0.2051, "lr": 1.4839357395212656e-05, "epoch": 20.728612361850185, "percentage": 63.32, "elapsed_time": "2:54:38", "remaining_time": "1:41:08", "throughput": 787.59, "total_tokens": 8252992} {"current_steps": 25335, "total_steps": 40000, "loss": 0.2392, "lr": 1.4830388108836502e-05, "epoch": 20.732705689725748, "percentage": 63.34, "elapsed_time": "2:54:40", "remaining_time": "1:41:06", "throughput": 787.62, "total_tokens": 8254624} {"current_steps": 25340, "total_steps": 40000, "loss": 0.1099, "lr": 1.4821420390742299e-05, "epoch": 20.73679901760131, "percentage": 63.35, "elapsed_time": "2:54:42", "remaining_time": "1:41:04", "throughput": 787.64, "total_tokens": 8256256} {"current_steps": 25345, "total_steps": 40000, "loss": 0.1556, "lr": 1.4812454242312979e-05, "epoch": 20.740892345476873, "percentage": 63.36, "elapsed_time": "2:54:43", "remaining_time": "1:41:02", "throughput": 787.67, "total_tokens": 8257840} {"current_steps": 25350, "total_steps": 40000, "loss": 0.1829, "lr": 1.4803489664931253e-05, "epoch": 20.744985673352435, "percentage": 63.38, "elapsed_time": "2:54:45", "remaining_time": "1:40:59", "throughput": 787.69, "total_tokens": 8259456} {"current_steps": 25355, "total_steps": 40000, "loss": 0.1351, "lr": 1.4794526659979544e-05, "epoch": 20.749079001227997, "percentage": 63.39, "elapsed_time": "2:54:47", "remaining_time": "1:40:57", "throughput": 787.71, "total_tokens": 8261040} {"current_steps": 25360, "total_steps": 40000, "loss": 0.1752, "lr": 1.4785565228840086e-05, "epoch": 20.75317232910356, "percentage": 63.4, "elapsed_time": "2:54:49", "remaining_time": "1:40:55", "throughput": 787.74, "total_tokens": 8262656} {"current_steps": 25365, "total_steps": 40000, "loss": 0.1392, "lr": 1.4776605372894819e-05, "epoch": 20.757265656979126, "percentage": 63.41, "elapsed_time": "2:54:50", "remaining_time": "1:40:52", "throughput": 787.76, "total_tokens": 8264256} {"current_steps": 25370, "total_steps": 40000, "loss": 0.1354, "lr": 1.4767647093525488e-05, "epoch": 20.761358984854688, "percentage": 63.42, "elapsed_time": "2:54:52", "remaining_time": "1:40:50", "throughput": 787.79, "total_tokens": 8265968} {"current_steps": 25375, "total_steps": 40000, "loss": 0.2806, "lr": 1.4758690392113566e-05, "epoch": 20.76545231273025, "percentage": 63.44, "elapsed_time": "2:54:54", "remaining_time": "1:40:48", "throughput": 787.82, "total_tokens": 8267584} {"current_steps": 25380, "total_steps": 40000, "loss": 0.0922, "lr": 1.4749735270040276e-05, "epoch": 20.769545640605813, "percentage": 63.45, "elapsed_time": "2:54:56", "remaining_time": "1:40:46", "throughput": 787.84, "total_tokens": 8269168} {"current_steps": 25385, "total_steps": 40000, "loss": 0.1369, "lr": 1.4740781728686623e-05, "epoch": 20.773638968481375, "percentage": 63.46, "elapsed_time": "2:54:57", "remaining_time": "1:40:43", "throughput": 787.87, "total_tokens": 8270800} {"current_steps": 25390, "total_steps": 40000, "loss": 0.1763, "lr": 1.4731829769433358e-05, "epoch": 20.777732296356938, "percentage": 63.48, "elapsed_time": "2:54:59", "remaining_time": "1:40:41", "throughput": 787.89, "total_tokens": 8272432} {"current_steps": 25395, "total_steps": 40000, "loss": 0.1126, "lr": 1.4722879393660976e-05, "epoch": 20.7818256242325, "percentage": 63.49, "elapsed_time": "2:55:01", "remaining_time": "1:40:39", "throughput": 787.92, "total_tokens": 8274048} {"current_steps": 25400, "total_steps": 40000, "loss": 0.1237, "lr": 1.4713930602749748e-05, "epoch": 20.785918952108062, "percentage": 63.5, "elapsed_time": "2:55:02", "remaining_time": "1:40:37", "throughput": 787.95, "total_tokens": 8275760} {"current_steps": 25400, "total_steps": 40000, "eval_loss": 0.2140841782093048, "epoch": 20.785918952108062, "percentage": 63.5, "elapsed_time": "2:55:15", "remaining_time": "1:40:44", "throughput": 787.02, "total_tokens": 8275760} {"current_steps": 25405, "total_steps": 40000, "loss": 0.1754, "lr": 1.470498339807968e-05, "epoch": 20.790012279983628, "percentage": 63.51, "elapsed_time": "2:55:18", "remaining_time": "1:40:42", "throughput": 786.93, "total_tokens": 8277344} {"current_steps": 25410, "total_steps": 40000, "loss": 0.2435, "lr": 1.4696037781030542e-05, "epoch": 20.79410560785919, "percentage": 63.52, "elapsed_time": "2:55:20", "remaining_time": "1:40:40", "throughput": 786.96, "total_tokens": 8278992} {"current_steps": 25415, "total_steps": 40000, "loss": 0.2253, "lr": 1.4687093752981876e-05, "epoch": 20.798198935734753, "percentage": 63.54, "elapsed_time": "2:55:21", "remaining_time": "1:40:38", "throughput": 786.99, "total_tokens": 8280656} {"current_steps": 25420, "total_steps": 40000, "loss": 0.1442, "lr": 1.4678151315312943e-05, "epoch": 20.802292263610315, "percentage": 63.55, "elapsed_time": "2:55:23", "remaining_time": "1:40:36", "throughput": 787.01, "total_tokens": 8282304} {"current_steps": 25425, "total_steps": 40000, "loss": 0.1388, "lr": 1.4669210469402789e-05, "epoch": 20.806385591485878, "percentage": 63.56, "elapsed_time": "2:55:25", "remaining_time": "1:40:33", "throughput": 787.04, "total_tokens": 8283904} {"current_steps": 25430, "total_steps": 40000, "loss": 0.1863, "lr": 1.4660271216630218e-05, "epoch": 20.81047891936144, "percentage": 63.58, "elapsed_time": "2:55:27", "remaining_time": "1:40:31", "throughput": 787.07, "total_tokens": 8285552} {"current_steps": 25435, "total_steps": 40000, "loss": 0.1705, "lr": 1.4651333558373748e-05, "epoch": 20.814572247237003, "percentage": 63.59, "elapsed_time": "2:55:28", "remaining_time": "1:40:29", "throughput": 787.09, "total_tokens": 8287152} {"current_steps": 25440, "total_steps": 40000, "loss": 0.1182, "lr": 1.4642397496011707e-05, "epoch": 20.818665575112565, "percentage": 63.6, "elapsed_time": "2:55:30", "remaining_time": "1:40:26", "throughput": 787.12, "total_tokens": 8288832} {"current_steps": 25445, "total_steps": 40000, "loss": 0.2317, "lr": 1.4633463030922129e-05, "epoch": 20.82275890298813, "percentage": 63.61, "elapsed_time": "2:55:32", "remaining_time": "1:40:24", "throughput": 787.14, "total_tokens": 8290384} {"current_steps": 25450, "total_steps": 40000, "loss": 0.1484, "lr": 1.462453016448282e-05, "epoch": 20.826852230863693, "percentage": 63.62, "elapsed_time": "2:55:34", "remaining_time": "1:40:22", "throughput": 787.16, "total_tokens": 8292016} {"current_steps": 25455, "total_steps": 40000, "loss": 0.2361, "lr": 1.4615598898071354e-05, "epoch": 20.830945558739256, "percentage": 63.64, "elapsed_time": "2:55:35", "remaining_time": "1:40:20", "throughput": 787.19, "total_tokens": 8293680} {"current_steps": 25460, "total_steps": 40000, "loss": 0.1053, "lr": 1.4606669233065026e-05, "epoch": 20.835038886614818, "percentage": 63.65, "elapsed_time": "2:55:37", "remaining_time": "1:40:17", "throughput": 787.21, "total_tokens": 8295248} {"current_steps": 25465, "total_steps": 40000, "loss": 0.1993, "lr": 1.4597741170840914e-05, "epoch": 20.83913221449038, "percentage": 63.66, "elapsed_time": "2:55:39", "remaining_time": "1:40:15", "throughput": 787.24, "total_tokens": 8296848} {"current_steps": 25470, "total_steps": 40000, "loss": 0.1631, "lr": 1.4588814712775853e-05, "epoch": 20.843225542365943, "percentage": 63.68, "elapsed_time": "2:55:40", "remaining_time": "1:40:13", "throughput": 787.26, "total_tokens": 8298448} {"current_steps": 25475, "total_steps": 40000, "loss": 0.1706, "lr": 1.4579889860246382e-05, "epoch": 20.847318870241505, "percentage": 63.69, "elapsed_time": "2:55:42", "remaining_time": "1:40:11", "throughput": 787.28, "total_tokens": 8300000} {"current_steps": 25480, "total_steps": 40000, "loss": 0.1306, "lr": 1.457096661462885e-05, "epoch": 20.851412198117067, "percentage": 63.7, "elapsed_time": "2:55:44", "remaining_time": "1:40:08", "throughput": 787.31, "total_tokens": 8301664} {"current_steps": 25485, "total_steps": 40000, "loss": 0.2009, "lr": 1.4562044977299322e-05, "epoch": 20.855505525992633, "percentage": 63.71, "elapsed_time": "2:55:46", "remaining_time": "1:40:06", "throughput": 787.33, "total_tokens": 8303280} {"current_steps": 25490, "total_steps": 40000, "loss": 0.2403, "lr": 1.4553124949633623e-05, "epoch": 20.859598853868196, "percentage": 63.73, "elapsed_time": "2:55:47", "remaining_time": "1:40:04", "throughput": 787.36, "total_tokens": 8304880} {"current_steps": 25495, "total_steps": 40000, "loss": 0.1813, "lr": 1.4544206533007354e-05, "epoch": 20.863692181743758, "percentage": 63.74, "elapsed_time": "2:55:49", "remaining_time": "1:40:01", "throughput": 787.38, "total_tokens": 8306464} {"current_steps": 25500, "total_steps": 40000, "loss": 0.1756, "lr": 1.4535289728795821e-05, "epoch": 20.86778550961932, "percentage": 63.75, "elapsed_time": "2:55:51", "remaining_time": "1:39:59", "throughput": 787.4, "total_tokens": 8308016} {"current_steps": 25505, "total_steps": 40000, "loss": 0.1936, "lr": 1.4526374538374132e-05, "epoch": 20.871878837494883, "percentage": 63.76, "elapsed_time": "2:55:52", "remaining_time": "1:39:57", "throughput": 787.42, "total_tokens": 8309600} {"current_steps": 25510, "total_steps": 40000, "loss": 0.1544, "lr": 1.4517460963117097e-05, "epoch": 20.875972165370445, "percentage": 63.78, "elapsed_time": "2:55:54", "remaining_time": "1:39:55", "throughput": 787.44, "total_tokens": 8311216} {"current_steps": 25515, "total_steps": 40000, "loss": 0.2316, "lr": 1.4508549004399314e-05, "epoch": 20.880065493246008, "percentage": 63.79, "elapsed_time": "2:55:56", "remaining_time": "1:39:52", "throughput": 787.46, "total_tokens": 8312784} {"current_steps": 25520, "total_steps": 40000, "loss": 0.1636, "lr": 1.449963866359513e-05, "epoch": 20.884158821121574, "percentage": 63.8, "elapsed_time": "2:55:58", "remaining_time": "1:39:50", "throughput": 787.5, "total_tokens": 8314496} {"current_steps": 25525, "total_steps": 40000, "loss": 0.2172, "lr": 1.4490729942078607e-05, "epoch": 20.888252148997136, "percentage": 63.81, "elapsed_time": "2:55:59", "remaining_time": "1:39:48", "throughput": 787.52, "total_tokens": 8316144} {"current_steps": 25530, "total_steps": 40000, "loss": 0.1644, "lr": 1.4481822841223608e-05, "epoch": 20.8923454768727, "percentage": 63.82, "elapsed_time": "2:56:01", "remaining_time": "1:39:46", "throughput": 787.55, "total_tokens": 8317824} {"current_steps": 25535, "total_steps": 40000, "loss": 0.1703, "lr": 1.4472917362403704e-05, "epoch": 20.89643880474826, "percentage": 63.84, "elapsed_time": "2:56:03", "remaining_time": "1:39:43", "throughput": 787.58, "total_tokens": 8319504} {"current_steps": 25540, "total_steps": 40000, "loss": 0.1849, "lr": 1.4464013506992224e-05, "epoch": 20.900532132623823, "percentage": 63.85, "elapsed_time": "2:56:05", "remaining_time": "1:39:41", "throughput": 787.61, "total_tokens": 8321152} {"current_steps": 25545, "total_steps": 40000, "loss": 0.2534, "lr": 1.4455111276362277e-05, "epoch": 20.904625460499386, "percentage": 63.86, "elapsed_time": "2:56:06", "remaining_time": "1:39:39", "throughput": 787.64, "total_tokens": 8322816} {"current_steps": 25550, "total_steps": 40000, "loss": 0.1879, "lr": 1.4446210671886676e-05, "epoch": 20.908718788374948, "percentage": 63.88, "elapsed_time": "2:56:08", "remaining_time": "1:39:37", "throughput": 787.66, "total_tokens": 8324400} {"current_steps": 25555, "total_steps": 40000, "loss": 0.1376, "lr": 1.4437311694938015e-05, "epoch": 20.91281211625051, "percentage": 63.89, "elapsed_time": "2:56:10", "remaining_time": "1:39:34", "throughput": 787.69, "total_tokens": 8326016} {"current_steps": 25560, "total_steps": 40000, "loss": 0.1369, "lr": 1.442841434688864e-05, "epoch": 20.916905444126076, "percentage": 63.9, "elapsed_time": "2:56:11", "remaining_time": "1:39:32", "throughput": 787.72, "total_tokens": 8327664} {"current_steps": 25565, "total_steps": 40000, "loss": 0.1544, "lr": 1.4419518629110615e-05, "epoch": 20.92099877200164, "percentage": 63.91, "elapsed_time": "2:56:13", "remaining_time": "1:39:30", "throughput": 787.74, "total_tokens": 8329280} {"current_steps": 25570, "total_steps": 40000, "loss": 0.1572, "lr": 1.4410624542975778e-05, "epoch": 20.9250920998772, "percentage": 63.92, "elapsed_time": "2:56:15", "remaining_time": "1:39:28", "throughput": 787.77, "total_tokens": 8330912} {"current_steps": 25575, "total_steps": 40000, "loss": 0.162, "lr": 1.4401732089855724e-05, "epoch": 20.929185427752763, "percentage": 63.94, "elapsed_time": "2:56:17", "remaining_time": "1:39:25", "throughput": 787.79, "total_tokens": 8332560} {"current_steps": 25580, "total_steps": 40000, "loss": 0.2209, "lr": 1.4392841271121754e-05, "epoch": 20.933278755628326, "percentage": 63.95, "elapsed_time": "2:56:18", "remaining_time": "1:39:23", "throughput": 787.82, "total_tokens": 8334192} {"current_steps": 25585, "total_steps": 40000, "loss": 0.2044, "lr": 1.438395208814497e-05, "epoch": 20.937372083503888, "percentage": 63.96, "elapsed_time": "2:56:20", "remaining_time": "1:39:21", "throughput": 787.84, "total_tokens": 8335808} {"current_steps": 25590, "total_steps": 40000, "loss": 0.1272, "lr": 1.4375064542296174e-05, "epoch": 20.94146541137945, "percentage": 63.98, "elapsed_time": "2:56:22", "remaining_time": "1:39:18", "throughput": 787.87, "total_tokens": 8337456} {"current_steps": 25595, "total_steps": 40000, "loss": 0.1762, "lr": 1.4366178634945946e-05, "epoch": 20.945558739255013, "percentage": 63.99, "elapsed_time": "2:56:23", "remaining_time": "1:39:16", "throughput": 787.9, "total_tokens": 8339120} {"current_steps": 25600, "total_steps": 40000, "loss": 0.1324, "lr": 1.4357294367464616e-05, "epoch": 20.94965206713058, "percentage": 64.0, "elapsed_time": "2:56:25", "remaining_time": "1:39:14", "throughput": 787.93, "total_tokens": 8340784} {"current_steps": 25600, "total_steps": 40000, "eval_loss": 0.21327368915081024, "epoch": 20.94965206713058, "percentage": 64.0, "elapsed_time": "2:56:38", "remaining_time": "1:39:21", "throughput": 787.0, "total_tokens": 8340784} {"current_steps": 25605, "total_steps": 40000, "loss": 0.2206, "lr": 1.434841174122224e-05, "epoch": 20.95374539500614, "percentage": 64.01, "elapsed_time": "2:56:41", "remaining_time": "1:39:20", "throughput": 786.92, "total_tokens": 8342416} {"current_steps": 25610, "total_steps": 40000, "loss": 0.19, "lr": 1.4339530757588615e-05, "epoch": 20.957838722881704, "percentage": 64.03, "elapsed_time": "2:56:43", "remaining_time": "1:39:17", "throughput": 786.94, "total_tokens": 8343984} {"current_steps": 25615, "total_steps": 40000, "loss": 0.1813, "lr": 1.433065141793333e-05, "epoch": 20.961932050757266, "percentage": 64.04, "elapsed_time": "2:56:44", "remaining_time": "1:39:15", "throughput": 786.96, "total_tokens": 8345600} {"current_steps": 25620, "total_steps": 40000, "loss": 0.1609, "lr": 1.4321773723625665e-05, "epoch": 20.96602537863283, "percentage": 64.05, "elapsed_time": "2:56:46", "remaining_time": "1:39:13", "throughput": 786.98, "total_tokens": 8347168} {"current_steps": 25625, "total_steps": 40000, "loss": 0.1418, "lr": 1.4312897676034693e-05, "epoch": 20.97011870650839, "percentage": 64.06, "elapsed_time": "2:56:48", "remaining_time": "1:39:10", "throughput": 787.01, "total_tokens": 8348784} {"current_steps": 25630, "total_steps": 40000, "loss": 0.2151, "lr": 1.4304023276529188e-05, "epoch": 20.974212034383953, "percentage": 64.08, "elapsed_time": "2:56:49", "remaining_time": "1:39:08", "throughput": 787.04, "total_tokens": 8350432} {"current_steps": 25635, "total_steps": 40000, "loss": 0.1157, "lr": 1.4295150526477712e-05, "epoch": 20.978305362259515, "percentage": 64.09, "elapsed_time": "2:56:51", "remaining_time": "1:39:06", "throughput": 787.06, "total_tokens": 8352016} {"current_steps": 25640, "total_steps": 40000, "loss": 0.1668, "lr": 1.4286279427248562e-05, "epoch": 20.98239869013508, "percentage": 64.1, "elapsed_time": "2:56:53", "remaining_time": "1:39:04", "throughput": 787.09, "total_tokens": 8353648} {"current_steps": 25645, "total_steps": 40000, "loss": 0.2509, "lr": 1.4277409980209747e-05, "epoch": 20.986492018010644, "percentage": 64.11, "elapsed_time": "2:56:55", "remaining_time": "1:39:01", "throughput": 787.13, "total_tokens": 8355424} {"current_steps": 25650, "total_steps": 40000, "loss": 0.1685, "lr": 1.4268542186729061e-05, "epoch": 20.990585345886206, "percentage": 64.12, "elapsed_time": "2:56:56", "remaining_time": "1:38:59", "throughput": 787.15, "total_tokens": 8357072} {"current_steps": 25655, "total_steps": 40000, "loss": 0.1963, "lr": 1.4259676048174043e-05, "epoch": 20.99467867376177, "percentage": 64.14, "elapsed_time": "2:56:58", "remaining_time": "1:38:57", "throughput": 787.18, "total_tokens": 8358672} {"current_steps": 25660, "total_steps": 40000, "loss": 0.2039, "lr": 1.4250811565911937e-05, "epoch": 20.99877200163733, "percentage": 64.15, "elapsed_time": "2:57:00", "remaining_time": "1:38:55", "throughput": 787.2, "total_tokens": 8360288} {"current_steps": 25665, "total_steps": 40000, "loss": 0.1286, "lr": 1.4241948741309782e-05, "epoch": 21.002455996725338, "percentage": 64.16, "elapsed_time": "2:57:02", "remaining_time": "1:38:52", "throughput": 787.19, "total_tokens": 8361656} {"current_steps": 25670, "total_steps": 40000, "loss": 0.2099, "lr": 1.4233087575734317e-05, "epoch": 21.0065493246009, "percentage": 64.18, "elapsed_time": "2:57:03", "remaining_time": "1:38:50", "throughput": 787.22, "total_tokens": 8363304} {"current_steps": 25675, "total_steps": 40000, "loss": 0.2337, "lr": 1.422422807055206e-05, "epoch": 21.010642652476463, "percentage": 64.19, "elapsed_time": "2:57:05", "remaining_time": "1:38:48", "throughput": 787.24, "total_tokens": 8364904} {"current_steps": 25680, "total_steps": 40000, "loss": 0.1615, "lr": 1.4215370227129243e-05, "epoch": 21.014735980352025, "percentage": 64.2, "elapsed_time": "2:57:07", "remaining_time": "1:38:46", "throughput": 787.27, "total_tokens": 8366536} {"current_steps": 25685, "total_steps": 40000, "loss": 0.1821, "lr": 1.4206514046831876e-05, "epoch": 21.018829308227588, "percentage": 64.21, "elapsed_time": "2:57:09", "remaining_time": "1:38:43", "throughput": 787.29, "total_tokens": 8368168} {"current_steps": 25690, "total_steps": 40000, "loss": 0.2746, "lr": 1.419765953102567e-05, "epoch": 21.022922636103154, "percentage": 64.22, "elapsed_time": "2:57:10", "remaining_time": "1:38:41", "throughput": 787.32, "total_tokens": 8369832} {"current_steps": 25695, "total_steps": 40000, "loss": 0.1617, "lr": 1.4188806681076125e-05, "epoch": 21.027015963978716, "percentage": 64.24, "elapsed_time": "2:57:12", "remaining_time": "1:38:39", "throughput": 787.35, "total_tokens": 8371448} {"current_steps": 25700, "total_steps": 40000, "loss": 0.1416, "lr": 1.4179955498348443e-05, "epoch": 21.03110929185428, "percentage": 64.25, "elapsed_time": "2:57:14", "remaining_time": "1:38:37", "throughput": 787.37, "total_tokens": 8373048} {"current_steps": 25705, "total_steps": 40000, "loss": 0.1449, "lr": 1.4171105984207605e-05, "epoch": 21.03520261972984, "percentage": 64.26, "elapsed_time": "2:57:15", "remaining_time": "1:38:34", "throughput": 787.39, "total_tokens": 8374632} {"current_steps": 25710, "total_steps": 40000, "loss": 0.1151, "lr": 1.4162258140018304e-05, "epoch": 21.039295947605403, "percentage": 64.28, "elapsed_time": "2:57:17", "remaining_time": "1:38:32", "throughput": 787.41, "total_tokens": 8376232} {"current_steps": 25715, "total_steps": 40000, "loss": 0.1183, "lr": 1.4153411967144986e-05, "epoch": 21.043389275480965, "percentage": 64.29, "elapsed_time": "2:57:19", "remaining_time": "1:38:30", "throughput": 787.45, "total_tokens": 8377928} {"current_steps": 25720, "total_steps": 40000, "loss": 0.2317, "lr": 1.4144567466951864e-05, "epoch": 21.047482603356528, "percentage": 64.3, "elapsed_time": "2:57:21", "remaining_time": "1:38:28", "throughput": 787.47, "total_tokens": 8379496} {"current_steps": 25725, "total_steps": 40000, "loss": 0.1534, "lr": 1.4135724640802844e-05, "epoch": 21.05157593123209, "percentage": 64.31, "elapsed_time": "2:57:22", "remaining_time": "1:38:25", "throughput": 787.5, "total_tokens": 8381192} {"current_steps": 25730, "total_steps": 40000, "loss": 0.1588, "lr": 1.4126883490061615e-05, "epoch": 21.055669259107656, "percentage": 64.33, "elapsed_time": "2:57:24", "remaining_time": "1:38:23", "throughput": 787.52, "total_tokens": 8382824} {"current_steps": 25735, "total_steps": 40000, "loss": 0.16, "lr": 1.4118044016091603e-05, "epoch": 21.05976258698322, "percentage": 64.34, "elapsed_time": "2:57:26", "remaining_time": "1:38:21", "throughput": 787.55, "total_tokens": 8384424} {"current_steps": 25740, "total_steps": 40000, "loss": 0.0989, "lr": 1.410920622025594e-05, "epoch": 21.06385591485878, "percentage": 64.35, "elapsed_time": "2:57:27", "remaining_time": "1:38:18", "throughput": 787.57, "total_tokens": 8386056} {"current_steps": 25745, "total_steps": 40000, "loss": 0.1656, "lr": 1.4100370103917554e-05, "epoch": 21.067949242734343, "percentage": 64.36, "elapsed_time": "2:57:29", "remaining_time": "1:38:16", "throughput": 787.6, "total_tokens": 8387720} {"current_steps": 25750, "total_steps": 40000, "loss": 0.217, "lr": 1.409153566843907e-05, "epoch": 21.072042570609906, "percentage": 64.38, "elapsed_time": "2:57:31", "remaining_time": "1:38:14", "throughput": 787.62, "total_tokens": 8389320} {"current_steps": 25755, "total_steps": 40000, "loss": 0.1267, "lr": 1.408270291518286e-05, "epoch": 21.076135898485468, "percentage": 64.39, "elapsed_time": "2:57:33", "remaining_time": "1:38:12", "throughput": 787.65, "total_tokens": 8390952} {"current_steps": 25760, "total_steps": 40000, "loss": 0.1589, "lr": 1.407387184551107e-05, "epoch": 21.08022922636103, "percentage": 64.4, "elapsed_time": "2:57:34", "remaining_time": "1:38:09", "throughput": 787.69, "total_tokens": 8392696} {"current_steps": 25765, "total_steps": 40000, "loss": 0.1702, "lr": 1.4065042460785532e-05, "epoch": 21.084322554236593, "percentage": 64.41, "elapsed_time": "2:57:36", "remaining_time": "1:38:07", "throughput": 787.71, "total_tokens": 8394328} {"current_steps": 25770, "total_steps": 40000, "loss": 0.2544, "lr": 1.405621476236787e-05, "epoch": 21.08841588211216, "percentage": 64.42, "elapsed_time": "2:57:38", "remaining_time": "1:38:05", "throughput": 787.74, "total_tokens": 8395976} {"current_steps": 25775, "total_steps": 40000, "loss": 0.1631, "lr": 1.4047388751619423e-05, "epoch": 21.09250920998772, "percentage": 64.44, "elapsed_time": "2:57:40", "remaining_time": "1:38:03", "throughput": 787.76, "total_tokens": 8397560} {"current_steps": 25780, "total_steps": 40000, "loss": 0.1352, "lr": 1.4038564429901264e-05, "epoch": 21.096602537863284, "percentage": 64.45, "elapsed_time": "2:57:41", "remaining_time": "1:38:00", "throughput": 787.79, "total_tokens": 8399192} {"current_steps": 25785, "total_steps": 40000, "loss": 0.1343, "lr": 1.4029741798574227e-05, "epoch": 21.100695865738846, "percentage": 64.46, "elapsed_time": "2:57:43", "remaining_time": "1:37:58", "throughput": 787.81, "total_tokens": 8400776} {"current_steps": 25790, "total_steps": 40000, "loss": 0.1891, "lr": 1.402092085899886e-05, "epoch": 21.10478919361441, "percentage": 64.48, "elapsed_time": "2:57:45", "remaining_time": "1:37:56", "throughput": 787.84, "total_tokens": 8402472} {"current_steps": 25795, "total_steps": 40000, "loss": 0.131, "lr": 1.4012101612535464e-05, "epoch": 21.10888252148997, "percentage": 64.49, "elapsed_time": "2:57:46", "remaining_time": "1:37:54", "throughput": 787.87, "total_tokens": 8404136} {"current_steps": 25800, "total_steps": 40000, "loss": 0.1542, "lr": 1.4003284060544092e-05, "epoch": 21.112975849365533, "percentage": 64.5, "elapsed_time": "2:57:48", "remaining_time": "1:37:51", "throughput": 787.89, "total_tokens": 8405688} {"current_steps": 25800, "total_steps": 40000, "eval_loss": 0.21323822438716888, "epoch": 21.112975849365533, "percentage": 64.5, "elapsed_time": "2:58:01", "remaining_time": "1:37:58", "throughput": 786.97, "total_tokens": 8405688} {"current_steps": 25805, "total_steps": 40000, "loss": 0.1614, "lr": 1.3994468204384504e-05, "epoch": 21.117069177241095, "percentage": 64.51, "elapsed_time": "2:58:04", "remaining_time": "1:37:57", "throughput": 786.88, "total_tokens": 8407352} {"current_steps": 25810, "total_steps": 40000, "loss": 0.1752, "lr": 1.398565404541622e-05, "epoch": 21.12116250511666, "percentage": 64.53, "elapsed_time": "2:58:06", "remaining_time": "1:37:55", "throughput": 786.9, "total_tokens": 8408984} {"current_steps": 25815, "total_steps": 40000, "loss": 0.208, "lr": 1.3976841584998513e-05, "epoch": 21.125255832992224, "percentage": 64.54, "elapsed_time": "2:58:07", "remaining_time": "1:37:52", "throughput": 786.93, "total_tokens": 8410648} {"current_steps": 25820, "total_steps": 40000, "loss": 0.1218, "lr": 1.3968030824490352e-05, "epoch": 21.129349160867786, "percentage": 64.55, "elapsed_time": "2:58:09", "remaining_time": "1:37:50", "throughput": 786.96, "total_tokens": 8412264} {"current_steps": 25825, "total_steps": 40000, "loss": 0.1539, "lr": 1.3959221765250469e-05, "epoch": 21.13344248874335, "percentage": 64.56, "elapsed_time": "2:58:11", "remaining_time": "1:37:48", "throughput": 786.99, "total_tokens": 8413912} {"current_steps": 25830, "total_steps": 40000, "loss": 0.2344, "lr": 1.3950414408637343e-05, "epoch": 21.13753581661891, "percentage": 64.58, "elapsed_time": "2:58:13", "remaining_time": "1:37:46", "throughput": 787.01, "total_tokens": 8415560} {"current_steps": 25835, "total_steps": 40000, "loss": 0.1438, "lr": 1.3941608756009166e-05, "epoch": 21.141629144494473, "percentage": 64.59, "elapsed_time": "2:58:14", "remaining_time": "1:37:43", "throughput": 787.04, "total_tokens": 8417224} {"current_steps": 25840, "total_steps": 40000, "loss": 0.2311, "lr": 1.3932804808723898e-05, "epoch": 21.145722472370036, "percentage": 64.6, "elapsed_time": "2:58:16", "remaining_time": "1:37:41", "throughput": 787.07, "total_tokens": 8418856} {"current_steps": 25845, "total_steps": 40000, "loss": 0.23, "lr": 1.3924002568139194e-05, "epoch": 21.149815800245598, "percentage": 64.61, "elapsed_time": "2:58:18", "remaining_time": "1:37:39", "throughput": 787.09, "total_tokens": 8420456} {"current_steps": 25850, "total_steps": 40000, "loss": 0.2092, "lr": 1.3915202035612485e-05, "epoch": 21.153909128121164, "percentage": 64.62, "elapsed_time": "2:58:19", "remaining_time": "1:37:37", "throughput": 787.11, "total_tokens": 8422024} {"current_steps": 25855, "total_steps": 40000, "loss": 0.1517, "lr": 1.3906403212500935e-05, "epoch": 21.158002455996726, "percentage": 64.64, "elapsed_time": "2:58:21", "remaining_time": "1:37:34", "throughput": 787.14, "total_tokens": 8423672} {"current_steps": 25860, "total_steps": 40000, "loss": 0.296, "lr": 1.3897606100161409e-05, "epoch": 21.16209578387229, "percentage": 64.65, "elapsed_time": "2:58:23", "remaining_time": "1:37:32", "throughput": 787.17, "total_tokens": 8425304} {"current_steps": 25865, "total_steps": 40000, "loss": 0.1906, "lr": 1.388881069995055e-05, "epoch": 21.16618911174785, "percentage": 64.66, "elapsed_time": "2:58:25", "remaining_time": "1:37:30", "throughput": 787.19, "total_tokens": 8426952} {"current_steps": 25870, "total_steps": 40000, "loss": 0.1194, "lr": 1.3880017013224708e-05, "epoch": 21.170282439623413, "percentage": 64.68, "elapsed_time": "2:58:26", "remaining_time": "1:37:27", "throughput": 787.22, "total_tokens": 8428584} {"current_steps": 25875, "total_steps": 40000, "loss": 0.2534, "lr": 1.3871225041339984e-05, "epoch": 21.174375767498976, "percentage": 64.69, "elapsed_time": "2:58:28", "remaining_time": "1:37:25", "throughput": 787.25, "total_tokens": 8430216} {"current_steps": 25880, "total_steps": 40000, "loss": 0.1133, "lr": 1.386243478565222e-05, "epoch": 21.17846909537454, "percentage": 64.7, "elapsed_time": "2:58:30", "remaining_time": "1:37:23", "throughput": 787.28, "total_tokens": 8431896} {"current_steps": 25885, "total_steps": 40000, "loss": 0.1315, "lr": 1.3853646247516966e-05, "epoch": 21.1825624232501, "percentage": 64.71, "elapsed_time": "2:58:31", "remaining_time": "1:37:21", "throughput": 787.3, "total_tokens": 8433480} {"current_steps": 25890, "total_steps": 40000, "loss": 0.2027, "lr": 1.3844859428289545e-05, "epoch": 21.186655751125667, "percentage": 64.72, "elapsed_time": "2:58:33", "remaining_time": "1:37:18", "throughput": 787.32, "total_tokens": 8435064} {"current_steps": 25895, "total_steps": 40000, "loss": 0.159, "lr": 1.3836074329324984e-05, "epoch": 21.19074907900123, "percentage": 64.74, "elapsed_time": "2:58:35", "remaining_time": "1:37:16", "throughput": 787.34, "total_tokens": 8436648} {"current_steps": 25900, "total_steps": 40000, "loss": 0.132, "lr": 1.3827290951978044e-05, "epoch": 21.19484240687679, "percentage": 64.75, "elapsed_time": "2:58:37", "remaining_time": "1:37:14", "throughput": 787.37, "total_tokens": 8438264} {"current_steps": 25905, "total_steps": 40000, "loss": 0.1289, "lr": 1.381850929760326e-05, "epoch": 21.198935734752354, "percentage": 64.76, "elapsed_time": "2:58:38", "remaining_time": "1:37:12", "throughput": 787.39, "total_tokens": 8439912} {"current_steps": 25910, "total_steps": 40000, "loss": 0.1128, "lr": 1.3809729367554842e-05, "epoch": 21.203029062627916, "percentage": 64.78, "elapsed_time": "2:58:40", "remaining_time": "1:37:09", "throughput": 787.42, "total_tokens": 8441512} {"current_steps": 25915, "total_steps": 40000, "loss": 0.1601, "lr": 1.3800951163186784e-05, "epoch": 21.20712239050348, "percentage": 64.79, "elapsed_time": "2:58:42", "remaining_time": "1:37:07", "throughput": 787.44, "total_tokens": 8443112} {"current_steps": 25920, "total_steps": 40000, "loss": 0.2189, "lr": 1.3792174685852801e-05, "epoch": 21.21121571837904, "percentage": 64.8, "elapsed_time": "2:58:43", "remaining_time": "1:37:05", "throughput": 787.46, "total_tokens": 8444728} {"current_steps": 25925, "total_steps": 40000, "loss": 0.1874, "lr": 1.378339993690632e-05, "epoch": 21.215309046254603, "percentage": 64.81, "elapsed_time": "2:58:45", "remaining_time": "1:37:03", "throughput": 787.49, "total_tokens": 8446360} {"current_steps": 25930, "total_steps": 40000, "loss": 0.2211, "lr": 1.3774626917700523e-05, "epoch": 21.21940237413017, "percentage": 64.83, "elapsed_time": "2:58:47", "remaining_time": "1:37:00", "throughput": 787.51, "total_tokens": 8447976} {"current_steps": 25935, "total_steps": 40000, "loss": 0.1183, "lr": 1.3765855629588334e-05, "epoch": 21.22349570200573, "percentage": 64.84, "elapsed_time": "2:58:49", "remaining_time": "1:36:58", "throughput": 787.54, "total_tokens": 8449560} {"current_steps": 25940, "total_steps": 40000, "loss": 0.2106, "lr": 1.3757086073922374e-05, "epoch": 21.227589029881294, "percentage": 64.85, "elapsed_time": "2:58:50", "remaining_time": "1:36:56", "throughput": 787.57, "total_tokens": 8451240} {"current_steps": 25945, "total_steps": 40000, "loss": 0.2095, "lr": 1.3748318252055038e-05, "epoch": 21.231682357756856, "percentage": 64.86, "elapsed_time": "2:58:52", "remaining_time": "1:36:54", "throughput": 787.59, "total_tokens": 8452872} {"current_steps": 25950, "total_steps": 40000, "loss": 0.1676, "lr": 1.3739552165338416e-05, "epoch": 21.23577568563242, "percentage": 64.88, "elapsed_time": "2:58:54", "remaining_time": "1:36:51", "throughput": 787.62, "total_tokens": 8454472} {"current_steps": 25955, "total_steps": 40000, "loss": 0.1287, "lr": 1.3730787815124354e-05, "epoch": 21.23986901350798, "percentage": 64.89, "elapsed_time": "2:58:55", "remaining_time": "1:36:49", "throughput": 787.64, "total_tokens": 8456072} {"current_steps": 25960, "total_steps": 40000, "loss": 0.1185, "lr": 1.3722025202764443e-05, "epoch": 21.243962341383543, "percentage": 64.9, "elapsed_time": "2:58:57", "remaining_time": "1:36:47", "throughput": 787.66, "total_tokens": 8457624} {"current_steps": 25965, "total_steps": 40000, "loss": 0.2295, "lr": 1.371326432960997e-05, "epoch": 21.24805566925911, "percentage": 64.91, "elapsed_time": "2:58:59", "remaining_time": "1:36:45", "throughput": 787.68, "total_tokens": 8459192} {"current_steps": 25970, "total_steps": 40000, "loss": 0.2145, "lr": 1.3704505197011969e-05, "epoch": 21.25214899713467, "percentage": 64.92, "elapsed_time": "2:59:01", "remaining_time": "1:36:42", "throughput": 787.71, "total_tokens": 8460920} {"current_steps": 25975, "total_steps": 40000, "loss": 0.2052, "lr": 1.3695747806321224e-05, "epoch": 21.256242325010234, "percentage": 64.94, "elapsed_time": "2:59:02", "remaining_time": "1:36:40", "throughput": 787.74, "total_tokens": 8462584} {"current_steps": 25980, "total_steps": 40000, "loss": 0.2177, "lr": 1.3686992158888212e-05, "epoch": 21.260335652885797, "percentage": 64.95, "elapsed_time": "2:59:04", "remaining_time": "1:36:38", "throughput": 787.76, "total_tokens": 8464184} {"current_steps": 25985, "total_steps": 40000, "loss": 0.1572, "lr": 1.367823825606319e-05, "epoch": 21.26442898076136, "percentage": 64.96, "elapsed_time": "2:59:06", "remaining_time": "1:36:36", "throughput": 787.79, "total_tokens": 8465784} {"current_steps": 25990, "total_steps": 40000, "loss": 0.0878, "lr": 1.36694860991961e-05, "epoch": 21.26852230863692, "percentage": 64.98, "elapsed_time": "2:59:07", "remaining_time": "1:36:33", "throughput": 787.81, "total_tokens": 8467368} {"current_steps": 25995, "total_steps": 40000, "loss": 0.1258, "lr": 1.3660735689636636e-05, "epoch": 21.272615636512484, "percentage": 64.99, "elapsed_time": "2:59:09", "remaining_time": "1:36:31", "throughput": 787.84, "total_tokens": 8469000} {"current_steps": 26000, "total_steps": 40000, "loss": 0.227, "lr": 1.365198702873424e-05, "epoch": 21.276708964388046, "percentage": 65.0, "elapsed_time": "2:59:11", "remaining_time": "1:36:29", "throughput": 787.86, "total_tokens": 8470664} {"current_steps": 26000, "total_steps": 40000, "eval_loss": 0.21174614131450653, "epoch": 21.276708964388046, "percentage": 65.0, "elapsed_time": "2:59:23", "remaining_time": "1:36:35", "throughput": 786.95, "total_tokens": 8470664} {"current_steps": 26005, "total_steps": 40000, "loss": 0.261, "lr": 1.364324011783804e-05, "epoch": 21.280802292263612, "percentage": 65.01, "elapsed_time": "2:59:27", "remaining_time": "1:36:34", "throughput": 786.86, "total_tokens": 8472232} {"current_steps": 26010, "total_steps": 40000, "loss": 0.2154, "lr": 1.3634494958296934e-05, "epoch": 21.284895620139174, "percentage": 65.03, "elapsed_time": "2:59:28", "remaining_time": "1:36:32", "throughput": 786.88, "total_tokens": 8473848} {"current_steps": 26015, "total_steps": 40000, "loss": 0.221, "lr": 1.3625751551459542e-05, "epoch": 21.288988948014737, "percentage": 65.04, "elapsed_time": "2:59:30", "remaining_time": "1:36:30", "throughput": 786.91, "total_tokens": 8475480} {"current_steps": 26020, "total_steps": 40000, "loss": 0.1708, "lr": 1.3617009898674188e-05, "epoch": 21.2930822758903, "percentage": 65.05, "elapsed_time": "2:59:32", "remaining_time": "1:36:27", "throughput": 786.94, "total_tokens": 8477160} {"current_steps": 26025, "total_steps": 40000, "loss": 0.2063, "lr": 1.3608270001288967e-05, "epoch": 21.29717560376586, "percentage": 65.06, "elapsed_time": "2:59:34", "remaining_time": "1:36:25", "throughput": 786.96, "total_tokens": 8478792} {"current_steps": 26030, "total_steps": 40000, "loss": 0.1665, "lr": 1.359953186065166e-05, "epoch": 21.301268931641424, "percentage": 65.08, "elapsed_time": "2:59:35", "remaining_time": "1:36:23", "throughput": 786.99, "total_tokens": 8480456} {"current_steps": 26035, "total_steps": 40000, "loss": 0.2345, "lr": 1.3590795478109814e-05, "epoch": 21.305362259516986, "percentage": 65.09, "elapsed_time": "2:59:37", "remaining_time": "1:36:20", "throughput": 787.02, "total_tokens": 8482088} {"current_steps": 26040, "total_steps": 40000, "loss": 0.1311, "lr": 1.3582060855010675e-05, "epoch": 21.30945558739255, "percentage": 65.1, "elapsed_time": "2:59:39", "remaining_time": "1:36:18", "throughput": 787.04, "total_tokens": 8483704} {"current_steps": 26045, "total_steps": 40000, "loss": 0.1614, "lr": 1.3573327992701245e-05, "epoch": 21.313548915268115, "percentage": 65.11, "elapsed_time": "2:59:40", "remaining_time": "1:36:16", "throughput": 787.06, "total_tokens": 8485256} {"current_steps": 26050, "total_steps": 40000, "loss": 0.2063, "lr": 1.356459689252823e-05, "epoch": 21.317642243143677, "percentage": 65.12, "elapsed_time": "2:59:42", "remaining_time": "1:36:14", "throughput": 787.08, "total_tokens": 8486840} {"current_steps": 26055, "total_steps": 40000, "loss": 0.2403, "lr": 1.3555867555838087e-05, "epoch": 21.32173557101924, "percentage": 65.14, "elapsed_time": "2:59:44", "remaining_time": "1:36:11", "throughput": 787.12, "total_tokens": 8488536} {"current_steps": 26060, "total_steps": 40000, "loss": 0.1573, "lr": 1.3547139983976975e-05, "epoch": 21.3258288988948, "percentage": 65.15, "elapsed_time": "2:59:46", "remaining_time": "1:36:09", "throughput": 787.14, "total_tokens": 8490120} {"current_steps": 26065, "total_steps": 40000, "loss": 0.1571, "lr": 1.3538414178290815e-05, "epoch": 21.329922226770364, "percentage": 65.16, "elapsed_time": "2:59:47", "remaining_time": "1:36:07", "throughput": 787.16, "total_tokens": 8491720} {"current_steps": 26070, "total_steps": 40000, "loss": 0.1354, "lr": 1.3529690140125209e-05, "epoch": 21.334015554645926, "percentage": 65.18, "elapsed_time": "2:59:49", "remaining_time": "1:36:05", "throughput": 787.18, "total_tokens": 8493320} {"current_steps": 26075, "total_steps": 40000, "loss": 0.151, "lr": 1.352096787082553e-05, "epoch": 21.33810888252149, "percentage": 65.19, "elapsed_time": "2:59:51", "remaining_time": "1:36:02", "throughput": 787.21, "total_tokens": 8494984} {"current_steps": 26080, "total_steps": 40000, "loss": 0.1846, "lr": 1.3512247371736871e-05, "epoch": 21.34220221039705, "percentage": 65.2, "elapsed_time": "2:59:52", "remaining_time": "1:36:00", "throughput": 787.24, "total_tokens": 8496600} {"current_steps": 26085, "total_steps": 40000, "loss": 0.175, "lr": 1.3503528644204022e-05, "epoch": 21.346295538272617, "percentage": 65.21, "elapsed_time": "2:59:54", "remaining_time": "1:35:58", "throughput": 787.27, "total_tokens": 8498280} {"current_steps": 26090, "total_steps": 40000, "loss": 0.1776, "lr": 1.349481168957153e-05, "epoch": 21.35038886614818, "percentage": 65.22, "elapsed_time": "2:59:56", "remaining_time": "1:35:56", "throughput": 787.29, "total_tokens": 8499928} {"current_steps": 26095, "total_steps": 40000, "loss": 0.1548, "lr": 1.3486096509183665e-05, "epoch": 21.354482194023742, "percentage": 65.24, "elapsed_time": "2:59:58", "remaining_time": "1:35:53", "throughput": 787.32, "total_tokens": 8501592} {"current_steps": 26100, "total_steps": 40000, "loss": 0.1503, "lr": 1.3477383104384406e-05, "epoch": 21.358575521899304, "percentage": 65.25, "elapsed_time": "2:59:59", "remaining_time": "1:35:51", "throughput": 787.34, "total_tokens": 8503192} {"current_steps": 26105, "total_steps": 40000, "loss": 0.1569, "lr": 1.3468671476517481e-05, "epoch": 21.362668849774867, "percentage": 65.26, "elapsed_time": "3:00:01", "remaining_time": "1:35:49", "throughput": 787.37, "total_tokens": 8504840} {"current_steps": 26110, "total_steps": 40000, "loss": 0.2485, "lr": 1.3459961626926326e-05, "epoch": 21.36676217765043, "percentage": 65.28, "elapsed_time": "3:00:03", "remaining_time": "1:35:47", "throughput": 787.39, "total_tokens": 8506440} {"current_steps": 26115, "total_steps": 40000, "loss": 0.1271, "lr": 1.3451253556954101e-05, "epoch": 21.37085550552599, "percentage": 65.29, "elapsed_time": "3:00:04", "remaining_time": "1:35:44", "throughput": 787.42, "total_tokens": 8508072} {"current_steps": 26120, "total_steps": 40000, "loss": 0.2297, "lr": 1.3442547267943717e-05, "epoch": 21.374948833401554, "percentage": 65.3, "elapsed_time": "3:00:06", "remaining_time": "1:35:42", "throughput": 787.45, "total_tokens": 8509736} {"current_steps": 26125, "total_steps": 40000, "loss": 0.2014, "lr": 1.3433842761237774e-05, "epoch": 21.37904216127712, "percentage": 65.31, "elapsed_time": "3:00:08", "remaining_time": "1:35:40", "throughput": 787.47, "total_tokens": 8511304} {"current_steps": 26130, "total_steps": 40000, "loss": 0.2346, "lr": 1.3425140038178639e-05, "epoch": 21.383135489152682, "percentage": 65.33, "elapsed_time": "3:00:10", "remaining_time": "1:35:38", "throughput": 787.5, "total_tokens": 8512968} {"current_steps": 26135, "total_steps": 40000, "loss": 0.1248, "lr": 1.3416439100108358e-05, "epoch": 21.387228817028245, "percentage": 65.34, "elapsed_time": "3:00:11", "remaining_time": "1:35:35", "throughput": 787.52, "total_tokens": 8514568} {"current_steps": 26140, "total_steps": 40000, "loss": 0.2433, "lr": 1.3407739948368734e-05, "epoch": 21.391322144903807, "percentage": 65.35, "elapsed_time": "3:00:13", "remaining_time": "1:35:33", "throughput": 787.55, "total_tokens": 8516264} {"current_steps": 26145, "total_steps": 40000, "loss": 0.107, "lr": 1.3399042584301298e-05, "epoch": 21.39541547277937, "percentage": 65.36, "elapsed_time": "3:00:15", "remaining_time": "1:35:31", "throughput": 787.58, "total_tokens": 8517976} {"current_steps": 26150, "total_steps": 40000, "loss": 0.2038, "lr": 1.3390347009247272e-05, "epoch": 21.39950880065493, "percentage": 65.38, "elapsed_time": "3:00:17", "remaining_time": "1:35:29", "throughput": 787.61, "total_tokens": 8519656} {"current_steps": 26155, "total_steps": 40000, "loss": 0.1457, "lr": 1.3381653224547635e-05, "epoch": 21.403602128530494, "percentage": 65.39, "elapsed_time": "3:00:18", "remaining_time": "1:35:26", "throughput": 787.63, "total_tokens": 8521192} {"current_steps": 26160, "total_steps": 40000, "loss": 0.1434, "lr": 1.3372961231543086e-05, "epoch": 21.407695456406056, "percentage": 65.4, "elapsed_time": "3:00:20", "remaining_time": "1:35:24", "throughput": 787.65, "total_tokens": 8522824} {"current_steps": 26165, "total_steps": 40000, "loss": 0.2262, "lr": 1.3364271031574016e-05, "epoch": 21.411788784281622, "percentage": 65.41, "elapsed_time": "3:00:22", "remaining_time": "1:35:22", "throughput": 787.68, "total_tokens": 8524440} {"current_steps": 26170, "total_steps": 40000, "loss": 0.1337, "lr": 1.335558262598059e-05, "epoch": 21.415882112157185, "percentage": 65.42, "elapsed_time": "3:00:23", "remaining_time": "1:35:20", "throughput": 787.71, "total_tokens": 8526088} {"current_steps": 26175, "total_steps": 40000, "loss": 0.1907, "lr": 1.3346896016102645e-05, "epoch": 21.419975440032747, "percentage": 65.44, "elapsed_time": "3:00:25", "remaining_time": "1:35:17", "throughput": 787.73, "total_tokens": 8527672} {"current_steps": 26180, "total_steps": 40000, "loss": 0.1577, "lr": 1.3338211203279788e-05, "epoch": 21.42406876790831, "percentage": 65.45, "elapsed_time": "3:00:27", "remaining_time": "1:35:15", "throughput": 787.75, "total_tokens": 8529208} {"current_steps": 26185, "total_steps": 40000, "loss": 0.1112, "lr": 1.3329528188851303e-05, "epoch": 21.428162095783872, "percentage": 65.46, "elapsed_time": "3:00:29", "remaining_time": "1:35:13", "throughput": 787.77, "total_tokens": 8530792} {"current_steps": 26190, "total_steps": 40000, "loss": 0.1709, "lr": 1.3320846974156242e-05, "epoch": 21.432255423659434, "percentage": 65.48, "elapsed_time": "3:00:30", "remaining_time": "1:35:11", "throughput": 787.79, "total_tokens": 8532408} {"current_steps": 26195, "total_steps": 40000, "loss": 0.1866, "lr": 1.3312167560533337e-05, "epoch": 21.436348751534997, "percentage": 65.49, "elapsed_time": "3:00:32", "remaining_time": "1:35:08", "throughput": 787.82, "total_tokens": 8534056} {"current_steps": 26200, "total_steps": 40000, "loss": 0.1897, "lr": 1.3303489949321082e-05, "epoch": 21.44044207941056, "percentage": 65.5, "elapsed_time": "3:00:34", "remaining_time": "1:35:06", "throughput": 787.85, "total_tokens": 8535736} {"current_steps": 26200, "total_steps": 40000, "eval_loss": 0.21141910552978516, "epoch": 21.44044207941056, "percentage": 65.5, "elapsed_time": "3:00:46", "remaining_time": "1:35:13", "throughput": 786.95, "total_tokens": 8535736} {"current_steps": 26205, "total_steps": 40000, "loss": 0.1311, "lr": 1.3294814141857653e-05, "epoch": 21.444535407286125, "percentage": 65.51, "elapsed_time": "3:00:49", "remaining_time": "1:35:11", "throughput": 786.86, "total_tokens": 8537352} {"current_steps": 26210, "total_steps": 40000, "loss": 0.2487, "lr": 1.3286140139480992e-05, "epoch": 21.448628735161687, "percentage": 65.53, "elapsed_time": "3:00:51", "remaining_time": "1:35:09", "throughput": 786.89, "total_tokens": 8538984} {"current_steps": 26215, "total_steps": 40000, "loss": 0.181, "lr": 1.3277467943528719e-05, "epoch": 21.45272206303725, "percentage": 65.54, "elapsed_time": "3:00:53", "remaining_time": "1:35:07", "throughput": 786.92, "total_tokens": 8540680} {"current_steps": 26220, "total_steps": 40000, "loss": 0.1819, "lr": 1.3268797555338203e-05, "epoch": 21.456815390912812, "percentage": 65.55, "elapsed_time": "3:00:55", "remaining_time": "1:35:04", "throughput": 786.94, "total_tokens": 8542312} {"current_steps": 26225, "total_steps": 40000, "loss": 0.1725, "lr": 1.3260128976246533e-05, "epoch": 21.460908718788374, "percentage": 65.56, "elapsed_time": "3:00:56", "remaining_time": "1:35:02", "throughput": 786.97, "total_tokens": 8543944} {"current_steps": 26230, "total_steps": 40000, "loss": 0.1765, "lr": 1.32514622075905e-05, "epoch": 21.465002046663937, "percentage": 65.58, "elapsed_time": "3:00:58", "remaining_time": "1:35:00", "throughput": 787.0, "total_tokens": 8545608} {"current_steps": 26235, "total_steps": 40000, "loss": 0.2163, "lr": 1.3242797250706638e-05, "epoch": 21.4690953745395, "percentage": 65.59, "elapsed_time": "3:01:00", "remaining_time": "1:34:58", "throughput": 787.02, "total_tokens": 8547256} {"current_steps": 26240, "total_steps": 40000, "loss": 0.1881, "lr": 1.3234134106931195e-05, "epoch": 21.473188702415065, "percentage": 65.6, "elapsed_time": "3:01:01", "remaining_time": "1:34:55", "throughput": 787.05, "total_tokens": 8548920} {"current_steps": 26245, "total_steps": 40000, "loss": 0.1628, "lr": 1.322547277760013e-05, "epoch": 21.477282030290628, "percentage": 65.61, "elapsed_time": "3:01:03", "remaining_time": "1:34:53", "throughput": 787.08, "total_tokens": 8550536} {"current_steps": 26250, "total_steps": 40000, "loss": 0.1249, "lr": 1.3216813264049132e-05, "epoch": 21.48137535816619, "percentage": 65.62, "elapsed_time": "3:01:05", "remaining_time": "1:34:51", "throughput": 787.1, "total_tokens": 8552104} {"current_steps": 26255, "total_steps": 40000, "loss": 0.1763, "lr": 1.32081555676136e-05, "epoch": 21.485468686041752, "percentage": 65.64, "elapsed_time": "3:01:07", "remaining_time": "1:34:49", "throughput": 787.12, "total_tokens": 8553752} {"current_steps": 26260, "total_steps": 40000, "loss": 0.1452, "lr": 1.3199499689628674e-05, "epoch": 21.489562013917315, "percentage": 65.65, "elapsed_time": "3:01:08", "remaining_time": "1:34:46", "throughput": 787.15, "total_tokens": 8555384} {"current_steps": 26265, "total_steps": 40000, "loss": 0.1049, "lr": 1.3190845631429192e-05, "epoch": 21.493655341792877, "percentage": 65.66, "elapsed_time": "3:01:10", "remaining_time": "1:34:44", "throughput": 787.18, "total_tokens": 8557048} {"current_steps": 26270, "total_steps": 40000, "loss": 0.1274, "lr": 1.3182193394349704e-05, "epoch": 21.49774866966844, "percentage": 65.67, "elapsed_time": "3:01:12", "remaining_time": "1:34:42", "throughput": 787.2, "total_tokens": 8558664} {"current_steps": 26275, "total_steps": 40000, "loss": 0.1564, "lr": 1.3173542979724507e-05, "epoch": 21.501841997544002, "percentage": 65.69, "elapsed_time": "3:01:13", "remaining_time": "1:34:40", "throughput": 787.23, "total_tokens": 8560312} {"current_steps": 26280, "total_steps": 40000, "loss": 0.1213, "lr": 1.3164894388887617e-05, "epoch": 21.505935325419568, "percentage": 65.7, "elapsed_time": "3:01:15", "remaining_time": "1:34:37", "throughput": 787.25, "total_tokens": 8561912} {"current_steps": 26285, "total_steps": 40000, "loss": 0.2217, "lr": 1.3156247623172727e-05, "epoch": 21.51002865329513, "percentage": 65.71, "elapsed_time": "3:01:17", "remaining_time": "1:34:35", "throughput": 787.28, "total_tokens": 8563528} {"current_steps": 26290, "total_steps": 40000, "loss": 0.1395, "lr": 1.3147602683913302e-05, "epoch": 21.514121981170693, "percentage": 65.72, "elapsed_time": "3:01:19", "remaining_time": "1:34:33", "throughput": 787.3, "total_tokens": 8565160} {"current_steps": 26295, "total_steps": 40000, "loss": 0.2603, "lr": 1.3138959572442481e-05, "epoch": 21.518215309046255, "percentage": 65.74, "elapsed_time": "3:01:20", "remaining_time": "1:34:31", "throughput": 787.32, "total_tokens": 8566728} {"current_steps": 26300, "total_steps": 40000, "loss": 0.125, "lr": 1.3130318290093146e-05, "epoch": 21.522308636921817, "percentage": 65.75, "elapsed_time": "3:01:22", "remaining_time": "1:34:28", "throughput": 787.35, "total_tokens": 8568360} {"current_steps": 26305, "total_steps": 40000, "loss": 0.1669, "lr": 1.3121678838197909e-05, "epoch": 21.52640196479738, "percentage": 65.76, "elapsed_time": "3:01:24", "remaining_time": "1:34:26", "throughput": 787.37, "total_tokens": 8569992} {"current_steps": 26310, "total_steps": 40000, "loss": 0.1422, "lr": 1.3113041218089056e-05, "epoch": 21.530495292672942, "percentage": 65.77, "elapsed_time": "3:01:25", "remaining_time": "1:34:24", "throughput": 787.39, "total_tokens": 8571496} {"current_steps": 26315, "total_steps": 40000, "loss": 0.1503, "lr": 1.3104405431098626e-05, "epoch": 21.534588620548504, "percentage": 65.79, "elapsed_time": "3:01:27", "remaining_time": "1:34:22", "throughput": 787.41, "total_tokens": 8573096} {"current_steps": 26320, "total_steps": 40000, "loss": 0.2563, "lr": 1.3095771478558377e-05, "epoch": 21.53868194842407, "percentage": 65.8, "elapsed_time": "3:01:29", "remaining_time": "1:34:19", "throughput": 787.43, "total_tokens": 8574680} {"current_steps": 26325, "total_steps": 40000, "loss": 0.2601, "lr": 1.3087139361799766e-05, "epoch": 21.542775276299633, "percentage": 65.81, "elapsed_time": "3:01:31", "remaining_time": "1:34:17", "throughput": 787.46, "total_tokens": 8576312} {"current_steps": 26330, "total_steps": 40000, "loss": 0.1473, "lr": 1.3078509082153964e-05, "epoch": 21.546868604175195, "percentage": 65.83, "elapsed_time": "3:01:32", "remaining_time": "1:34:15", "throughput": 787.48, "total_tokens": 8577960} {"current_steps": 26335, "total_steps": 40000, "loss": 0.1568, "lr": 1.3069880640951885e-05, "epoch": 21.550961932050757, "percentage": 65.84, "elapsed_time": "3:01:34", "remaining_time": "1:34:13", "throughput": 787.51, "total_tokens": 8579560} {"current_steps": 26340, "total_steps": 40000, "loss": 0.2393, "lr": 1.3061254039524123e-05, "epoch": 21.55505525992632, "percentage": 65.85, "elapsed_time": "3:01:36", "remaining_time": "1:34:10", "throughput": 787.53, "total_tokens": 8581160} {"current_steps": 26345, "total_steps": 40000, "loss": 0.198, "lr": 1.3052629279201028e-05, "epoch": 21.559148587801882, "percentage": 65.86, "elapsed_time": "3:01:38", "remaining_time": "1:34:08", "throughput": 787.55, "total_tokens": 8582744} {"current_steps": 26350, "total_steps": 40000, "loss": 0.1435, "lr": 1.3044006361312633e-05, "epoch": 21.563241915677445, "percentage": 65.88, "elapsed_time": "3:01:39", "remaining_time": "1:34:06", "throughput": 787.58, "total_tokens": 8584376} {"current_steps": 26355, "total_steps": 40000, "loss": 0.1209, "lr": 1.30353852871887e-05, "epoch": 21.567335243553007, "percentage": 65.89, "elapsed_time": "3:01:41", "remaining_time": "1:34:04", "throughput": 787.6, "total_tokens": 8586024} {"current_steps": 26360, "total_steps": 40000, "loss": 0.2086, "lr": 1.302676605815873e-05, "epoch": 21.571428571428573, "percentage": 65.9, "elapsed_time": "3:01:43", "remaining_time": "1:34:01", "throughput": 787.64, "total_tokens": 8587800} {"current_steps": 26365, "total_steps": 40000, "loss": 0.1301, "lr": 1.3018148675551884e-05, "epoch": 21.575521899304135, "percentage": 65.91, "elapsed_time": "3:01:44", "remaining_time": "1:33:59", "throughput": 787.66, "total_tokens": 8589368} {"current_steps": 26370, "total_steps": 40000, "loss": 0.1914, "lr": 1.3009533140697094e-05, "epoch": 21.579615227179698, "percentage": 65.92, "elapsed_time": "3:01:46", "remaining_time": "1:33:57", "throughput": 787.69, "total_tokens": 8591048} {"current_steps": 26375, "total_steps": 40000, "loss": 0.1355, "lr": 1.3000919454922966e-05, "epoch": 21.58370855505526, "percentage": 65.94, "elapsed_time": "3:01:48", "remaining_time": "1:33:55", "throughput": 787.72, "total_tokens": 8592648} {"current_steps": 26380, "total_steps": 40000, "loss": 0.1671, "lr": 1.299230761955785e-05, "epoch": 21.587801882930822, "percentage": 65.95, "elapsed_time": "3:01:50", "remaining_time": "1:33:52", "throughput": 787.74, "total_tokens": 8594216} {"current_steps": 26385, "total_steps": 40000, "loss": 0.189, "lr": 1.2983697635929807e-05, "epoch": 21.591895210806385, "percentage": 65.96, "elapsed_time": "3:01:51", "remaining_time": "1:33:50", "throughput": 787.75, "total_tokens": 8595784} {"current_steps": 26390, "total_steps": 40000, "loss": 0.1575, "lr": 1.2975089505366584e-05, "epoch": 21.595988538681947, "percentage": 65.97, "elapsed_time": "3:01:53", "remaining_time": "1:33:48", "throughput": 787.78, "total_tokens": 8597464} {"current_steps": 26395, "total_steps": 40000, "loss": 0.1447, "lr": 1.2966483229195683e-05, "epoch": 21.60008186655751, "percentage": 65.99, "elapsed_time": "3:01:55", "remaining_time": "1:33:46", "throughput": 787.81, "total_tokens": 8599064} {"current_steps": 26400, "total_steps": 40000, "loss": 0.1911, "lr": 1.2957878808744283e-05, "epoch": 21.604175194433076, "percentage": 66.0, "elapsed_time": "3:01:56", "remaining_time": "1:33:43", "throughput": 787.84, "total_tokens": 8600728} {"current_steps": 26400, "total_steps": 40000, "eval_loss": 0.21126152575016022, "epoch": 21.604175194433076, "percentage": 66.0, "elapsed_time": "3:02:09", "remaining_time": "1:33:50", "throughput": 786.94, "total_tokens": 8600728} {"current_steps": 26405, "total_steps": 40000, "loss": 0.1426, "lr": 1.294927624533931e-05, "epoch": 21.608268522308638, "percentage": 66.01, "elapsed_time": "3:02:13", "remaining_time": "1:33:49", "throughput": 786.82, "total_tokens": 8602424} {"current_steps": 26410, "total_steps": 40000, "loss": 0.1832, "lr": 1.2940675540307378e-05, "epoch": 21.6123618501842, "percentage": 66.03, "elapsed_time": "3:02:14", "remaining_time": "1:33:46", "throughput": 786.85, "total_tokens": 8604072} {"current_steps": 26415, "total_steps": 40000, "loss": 0.1703, "lr": 1.2932076694974814e-05, "epoch": 21.616455178059763, "percentage": 66.04, "elapsed_time": "3:02:16", "remaining_time": "1:33:44", "throughput": 786.89, "total_tokens": 8605832} {"current_steps": 26420, "total_steps": 40000, "loss": 0.1425, "lr": 1.2923479710667682e-05, "epoch": 21.620548505935325, "percentage": 66.05, "elapsed_time": "3:02:18", "remaining_time": "1:33:42", "throughput": 786.92, "total_tokens": 8607496} {"current_steps": 26425, "total_steps": 40000, "loss": 0.1156, "lr": 1.2914884588711751e-05, "epoch": 21.624641833810887, "percentage": 66.06, "elapsed_time": "3:02:19", "remaining_time": "1:33:40", "throughput": 786.95, "total_tokens": 8609176} {"current_steps": 26430, "total_steps": 40000, "loss": 0.1876, "lr": 1.2906291330432475e-05, "epoch": 21.62873516168645, "percentage": 66.07, "elapsed_time": "3:02:21", "remaining_time": "1:33:37", "throughput": 786.97, "total_tokens": 8610840} {"current_steps": 26435, "total_steps": 40000, "loss": 0.163, "lr": 1.2897699937155055e-05, "epoch": 21.632828489562012, "percentage": 66.09, "elapsed_time": "3:02:23", "remaining_time": "1:33:35", "throughput": 787.0, "total_tokens": 8612456} {"current_steps": 26440, "total_steps": 40000, "loss": 0.2705, "lr": 1.2889110410204403e-05, "epoch": 21.636921817437578, "percentage": 66.1, "elapsed_time": "3:02:25", "remaining_time": "1:33:33", "throughput": 787.02, "total_tokens": 8614088} {"current_steps": 26445, "total_steps": 40000, "loss": 0.2, "lr": 1.2880522750905111e-05, "epoch": 21.64101514531314, "percentage": 66.11, "elapsed_time": "3:02:26", "remaining_time": "1:33:31", "throughput": 787.05, "total_tokens": 8615688} {"current_steps": 26450, "total_steps": 40000, "loss": 0.1113, "lr": 1.2871936960581523e-05, "epoch": 21.645108473188703, "percentage": 66.12, "elapsed_time": "3:02:28", "remaining_time": "1:33:28", "throughput": 787.07, "total_tokens": 8617336} {"current_steps": 26455, "total_steps": 40000, "loss": 0.2242, "lr": 1.2863353040557658e-05, "epoch": 21.649201801064265, "percentage": 66.14, "elapsed_time": "3:02:30", "remaining_time": "1:33:26", "throughput": 787.1, "total_tokens": 8618968} {"current_steps": 26460, "total_steps": 40000, "loss": 0.1749, "lr": 1.2854770992157273e-05, "epoch": 21.653295128939828, "percentage": 66.15, "elapsed_time": "3:02:32", "remaining_time": "1:33:24", "throughput": 787.13, "total_tokens": 8620664} {"current_steps": 26465, "total_steps": 40000, "loss": 0.1771, "lr": 1.2846190816703835e-05, "epoch": 21.65738845681539, "percentage": 66.16, "elapsed_time": "3:02:33", "remaining_time": "1:33:22", "throughput": 787.15, "total_tokens": 8622248} {"current_steps": 26470, "total_steps": 40000, "loss": 0.1817, "lr": 1.2837612515520498e-05, "epoch": 21.661481784690952, "percentage": 66.17, "elapsed_time": "3:02:35", "remaining_time": "1:33:19", "throughput": 787.18, "total_tokens": 8623912} {"current_steps": 26475, "total_steps": 40000, "loss": 0.1284, "lr": 1.2829036089930163e-05, "epoch": 21.665575112566515, "percentage": 66.19, "elapsed_time": "3:02:37", "remaining_time": "1:33:17", "throughput": 787.2, "total_tokens": 8625512} {"current_steps": 26480, "total_steps": 40000, "loss": 0.192, "lr": 1.2820461541255412e-05, "epoch": 21.66966844044208, "percentage": 66.2, "elapsed_time": "3:02:38", "remaining_time": "1:33:15", "throughput": 787.23, "total_tokens": 8627176} {"current_steps": 26485, "total_steps": 40000, "loss": 0.0897, "lr": 1.2811888870818543e-05, "epoch": 21.673761768317643, "percentage": 66.21, "elapsed_time": "3:02:40", "remaining_time": "1:33:13", "throughput": 787.26, "total_tokens": 8628808} {"current_steps": 26490, "total_steps": 40000, "loss": 0.1392, "lr": 1.2803318079941581e-05, "epoch": 21.677855096193205, "percentage": 66.22, "elapsed_time": "3:02:42", "remaining_time": "1:33:10", "throughput": 787.28, "total_tokens": 8630376} {"current_steps": 26495, "total_steps": 40000, "loss": 0.1178, "lr": 1.2794749169946235e-05, "epoch": 21.681948424068768, "percentage": 66.24, "elapsed_time": "3:02:44", "remaining_time": "1:33:08", "throughput": 787.3, "total_tokens": 8632024} {"current_steps": 26500, "total_steps": 40000, "loss": 0.1989, "lr": 1.2786182142153952e-05, "epoch": 21.68604175194433, "percentage": 66.25, "elapsed_time": "3:02:45", "remaining_time": "1:33:06", "throughput": 787.33, "total_tokens": 8633672} {"current_steps": 26505, "total_steps": 40000, "loss": 0.2043, "lr": 1.2777616997885878e-05, "epoch": 21.690135079819893, "percentage": 66.26, "elapsed_time": "3:02:47", "remaining_time": "1:33:04", "throughput": 787.36, "total_tokens": 8635320} {"current_steps": 26510, "total_steps": 40000, "loss": 0.1551, "lr": 1.2769053738462847e-05, "epoch": 21.694228407695455, "percentage": 66.27, "elapsed_time": "3:02:49", "remaining_time": "1:33:01", "throughput": 787.38, "total_tokens": 8636952} {"current_steps": 26515, "total_steps": 40000, "loss": 0.2034, "lr": 1.2760492365205434e-05, "epoch": 21.69832173557102, "percentage": 66.29, "elapsed_time": "3:02:50", "remaining_time": "1:32:59", "throughput": 787.41, "total_tokens": 8638584} {"current_steps": 26520, "total_steps": 40000, "loss": 0.2473, "lr": 1.2751932879433919e-05, "epoch": 21.702415063446583, "percentage": 66.3, "elapsed_time": "3:02:52", "remaining_time": "1:32:57", "throughput": 787.43, "total_tokens": 8640200} {"current_steps": 26525, "total_steps": 40000, "loss": 0.1325, "lr": 1.2743375282468267e-05, "epoch": 21.706508391322146, "percentage": 66.31, "elapsed_time": "3:02:54", "remaining_time": "1:32:55", "throughput": 787.46, "total_tokens": 8641832} {"current_steps": 26530, "total_steps": 40000, "loss": 0.1125, "lr": 1.2734819575628182e-05, "epoch": 21.710601719197708, "percentage": 66.33, "elapsed_time": "3:02:56", "remaining_time": "1:32:52", "throughput": 787.48, "total_tokens": 8643432} {"current_steps": 26535, "total_steps": 40000, "loss": 0.155, "lr": 1.2726265760233039e-05, "epoch": 21.71469504707327, "percentage": 66.34, "elapsed_time": "3:02:57", "remaining_time": "1:32:50", "throughput": 787.5, "total_tokens": 8645016} {"current_steps": 26540, "total_steps": 40000, "loss": 0.2033, "lr": 1.271771383760197e-05, "epoch": 21.718788374948833, "percentage": 66.35, "elapsed_time": "3:02:59", "remaining_time": "1:32:48", "throughput": 787.54, "total_tokens": 8646760} {"current_steps": 26545, "total_steps": 40000, "loss": 0.1357, "lr": 1.2709163809053764e-05, "epoch": 21.722881702824395, "percentage": 66.36, "elapsed_time": "3:03:01", "remaining_time": "1:32:46", "throughput": 787.56, "total_tokens": 8648408} {"current_steps": 26550, "total_steps": 40000, "loss": 0.1648, "lr": 1.2700615675906963e-05, "epoch": 21.726975030699958, "percentage": 66.38, "elapsed_time": "3:03:02", "remaining_time": "1:32:43", "throughput": 787.59, "total_tokens": 8650024} {"current_steps": 26555, "total_steps": 40000, "loss": 0.3148, "lr": 1.269206943947978e-05, "epoch": 21.731068358575524, "percentage": 66.39, "elapsed_time": "3:03:04", "remaining_time": "1:32:41", "throughput": 787.61, "total_tokens": 8651624} {"current_steps": 26560, "total_steps": 40000, "loss": 0.1842, "lr": 1.2683525101090177e-05, "epoch": 21.735161686451086, "percentage": 66.4, "elapsed_time": "3:03:06", "remaining_time": "1:32:39", "throughput": 787.64, "total_tokens": 8653272} {"current_steps": 26565, "total_steps": 40000, "loss": 0.1185, "lr": 1.2674982662055765e-05, "epoch": 21.73925501432665, "percentage": 66.41, "elapsed_time": "3:03:08", "remaining_time": "1:32:37", "throughput": 787.67, "total_tokens": 8654984} {"current_steps": 26570, "total_steps": 40000, "loss": 0.1763, "lr": 1.2666442123693922e-05, "epoch": 21.74334834220221, "percentage": 66.42, "elapsed_time": "3:03:09", "remaining_time": "1:32:34", "throughput": 787.69, "total_tokens": 8656600} {"current_steps": 26575, "total_steps": 40000, "loss": 0.2008, "lr": 1.265790348732169e-05, "epoch": 21.747441670077773, "percentage": 66.44, "elapsed_time": "3:03:11", "remaining_time": "1:32:32", "throughput": 787.72, "total_tokens": 8658232} {"current_steps": 26580, "total_steps": 40000, "loss": 0.1673, "lr": 1.264936675425584e-05, "epoch": 21.751534997953335, "percentage": 66.45, "elapsed_time": "3:03:13", "remaining_time": "1:32:30", "throughput": 787.75, "total_tokens": 8659880} {"current_steps": 26585, "total_steps": 40000, "loss": 0.1278, "lr": 1.2640831925812852e-05, "epoch": 21.755628325828898, "percentage": 66.46, "elapsed_time": "3:03:14", "remaining_time": "1:32:28", "throughput": 787.77, "total_tokens": 8661496} {"current_steps": 26590, "total_steps": 40000, "loss": 0.1607, "lr": 1.263229900330889e-05, "epoch": 21.75972165370446, "percentage": 66.47, "elapsed_time": "3:03:16", "remaining_time": "1:32:25", "throughput": 787.8, "total_tokens": 8663112} {"current_steps": 26595, "total_steps": 40000, "loss": 0.0929, "lr": 1.2623767988059843e-05, "epoch": 21.763814981580026, "percentage": 66.49, "elapsed_time": "3:03:18", "remaining_time": "1:32:23", "throughput": 787.82, "total_tokens": 8664712} {"current_steps": 26600, "total_steps": 40000, "loss": 0.2505, "lr": 1.2615238881381309e-05, "epoch": 21.76790830945559, "percentage": 66.5, "elapsed_time": "3:03:20", "remaining_time": "1:32:21", "throughput": 787.84, "total_tokens": 8666296} {"current_steps": 26600, "total_steps": 40000, "eval_loss": 0.22005319595336914, "epoch": 21.76790830945559, "percentage": 66.5, "elapsed_time": "3:03:32", "remaining_time": "1:32:27", "throughput": 786.95, "total_tokens": 8666296} {"current_steps": 26605, "total_steps": 40000, "loss": 0.2291, "lr": 1.2606711684588568e-05, "epoch": 21.77200163733115, "percentage": 66.51, "elapsed_time": "3:03:36", "remaining_time": "1:32:26", "throughput": 786.84, "total_tokens": 8667928} {"current_steps": 26610, "total_steps": 40000, "loss": 0.2193, "lr": 1.2598186398996636e-05, "epoch": 21.776094965206713, "percentage": 66.53, "elapsed_time": "3:03:37", "remaining_time": "1:32:24", "throughput": 786.86, "total_tokens": 8669560} {"current_steps": 26615, "total_steps": 40000, "loss": 0.2521, "lr": 1.2589663025920207e-05, "epoch": 21.780188293082276, "percentage": 66.54, "elapsed_time": "3:03:39", "remaining_time": "1:32:21", "throughput": 786.89, "total_tokens": 8671192} {"current_steps": 26620, "total_steps": 40000, "loss": 0.1557, "lr": 1.2581141566673705e-05, "epoch": 21.784281620957838, "percentage": 66.55, "elapsed_time": "3:03:41", "remaining_time": "1:32:19", "throughput": 786.91, "total_tokens": 8672760} {"current_steps": 26625, "total_steps": 40000, "loss": 0.1678, "lr": 1.257262202257124e-05, "epoch": 21.7883749488334, "percentage": 66.56, "elapsed_time": "3:03:43", "remaining_time": "1:32:17", "throughput": 786.94, "total_tokens": 8674424} {"current_steps": 26630, "total_steps": 40000, "loss": 0.2287, "lr": 1.2564104394926618e-05, "epoch": 21.792468276708963, "percentage": 66.57, "elapsed_time": "3:03:44", "remaining_time": "1:32:15", "throughput": 786.96, "total_tokens": 8676008} {"current_steps": 26635, "total_steps": 40000, "loss": 0.1398, "lr": 1.2555588685053383e-05, "epoch": 21.79656160458453, "percentage": 66.59, "elapsed_time": "3:03:46", "remaining_time": "1:32:12", "throughput": 786.98, "total_tokens": 8677656} {"current_steps": 26640, "total_steps": 40000, "loss": 0.1484, "lr": 1.2547074894264762e-05, "epoch": 21.80065493246009, "percentage": 66.6, "elapsed_time": "3:03:48", "remaining_time": "1:32:10", "throughput": 787.01, "total_tokens": 8679304} {"current_steps": 26645, "total_steps": 40000, "loss": 0.1844, "lr": 1.2538563023873679e-05, "epoch": 21.804748260335653, "percentage": 66.61, "elapsed_time": "3:03:49", "remaining_time": "1:32:08", "throughput": 787.03, "total_tokens": 8680904} {"current_steps": 26650, "total_steps": 40000, "loss": 0.1499, "lr": 1.2530053075192789e-05, "epoch": 21.808841588211216, "percentage": 66.62, "elapsed_time": "3:03:51", "remaining_time": "1:32:06", "throughput": 787.07, "total_tokens": 8682616} {"current_steps": 26655, "total_steps": 40000, "loss": 0.2464, "lr": 1.252154504953441e-05, "epoch": 21.81293491608678, "percentage": 66.64, "elapsed_time": "3:03:53", "remaining_time": "1:32:03", "throughput": 787.09, "total_tokens": 8684232} {"current_steps": 26660, "total_steps": 40000, "loss": 0.109, "lr": 1.25130389482106e-05, "epoch": 21.81702824396234, "percentage": 66.65, "elapsed_time": "3:03:55", "remaining_time": "1:32:01", "throughput": 787.12, "total_tokens": 8685928} {"current_steps": 26665, "total_steps": 40000, "loss": 0.2537, "lr": 1.2504534772533116e-05, "epoch": 21.821121571837903, "percentage": 66.66, "elapsed_time": "3:03:56", "remaining_time": "1:31:59", "throughput": 787.15, "total_tokens": 8687592} {"current_steps": 26670, "total_steps": 40000, "loss": 0.1851, "lr": 1.2496032523813387e-05, "epoch": 21.825214899713465, "percentage": 66.67, "elapsed_time": "3:03:58", "remaining_time": "1:31:57", "throughput": 787.17, "total_tokens": 8689176} {"current_steps": 26675, "total_steps": 40000, "loss": 0.2175, "lr": 1.2487532203362576e-05, "epoch": 21.82930822758903, "percentage": 66.69, "elapsed_time": "3:04:00", "remaining_time": "1:31:54", "throughput": 787.19, "total_tokens": 8690776} {"current_steps": 26680, "total_steps": 40000, "loss": 0.1975, "lr": 1.247903381249155e-05, "epoch": 21.833401555464594, "percentage": 66.7, "elapsed_time": "3:04:01", "remaining_time": "1:31:52", "throughput": 787.22, "total_tokens": 8692440} {"current_steps": 26685, "total_steps": 40000, "loss": 0.2277, "lr": 1.2470537352510853e-05, "epoch": 21.837494883340156, "percentage": 66.71, "elapsed_time": "3:04:03", "remaining_time": "1:31:50", "throughput": 787.24, "total_tokens": 8694040} {"current_steps": 26690, "total_steps": 40000, "loss": 0.2012, "lr": 1.2462042824730758e-05, "epoch": 21.84158821121572, "percentage": 66.72, "elapsed_time": "3:04:05", "remaining_time": "1:31:48", "throughput": 787.27, "total_tokens": 8695672} {"current_steps": 26695, "total_steps": 40000, "loss": 0.1435, "lr": 1.245355023046122e-05, "epoch": 21.84568153909128, "percentage": 66.74, "elapsed_time": "3:04:07", "remaining_time": "1:31:45", "throughput": 787.3, "total_tokens": 8697336} {"current_steps": 26700, "total_steps": 40000, "loss": 0.1702, "lr": 1.2445059571011896e-05, "epoch": 21.849774866966843, "percentage": 66.75, "elapsed_time": "3:04:08", "remaining_time": "1:31:43", "throughput": 787.33, "total_tokens": 8699016} {"current_steps": 26705, "total_steps": 40000, "loss": 0.1299, "lr": 1.2436570847692173e-05, "epoch": 21.853868194842406, "percentage": 66.76, "elapsed_time": "3:04:10", "remaining_time": "1:31:41", "throughput": 787.35, "total_tokens": 8700600} {"current_steps": 26710, "total_steps": 40000, "loss": 0.2113, "lr": 1.2428084061811096e-05, "epoch": 21.857961522717968, "percentage": 66.77, "elapsed_time": "3:04:12", "remaining_time": "1:31:39", "throughput": 787.37, "total_tokens": 8702248} {"current_steps": 26715, "total_steps": 40000, "loss": 0.2379, "lr": 1.2419599214677447e-05, "epoch": 21.862054850593534, "percentage": 66.79, "elapsed_time": "3:04:13", "remaining_time": "1:31:36", "throughput": 787.4, "total_tokens": 8703864} {"current_steps": 26720, "total_steps": 40000, "loss": 0.1289, "lr": 1.2411116307599702e-05, "epoch": 21.866148178469096, "percentage": 66.8, "elapsed_time": "3:04:15", "remaining_time": "1:31:34", "throughput": 787.42, "total_tokens": 8705496} {"current_steps": 26725, "total_steps": 40000, "loss": 0.239, "lr": 1.2402635341886016e-05, "epoch": 21.87024150634466, "percentage": 66.81, "elapsed_time": "3:04:17", "remaining_time": "1:31:32", "throughput": 787.44, "total_tokens": 8707096} {"current_steps": 26730, "total_steps": 40000, "loss": 0.1983, "lr": 1.2394156318844278e-05, "epoch": 21.87433483422022, "percentage": 66.83, "elapsed_time": "3:04:19", "remaining_time": "1:31:30", "throughput": 787.47, "total_tokens": 8708728} {"current_steps": 26735, "total_steps": 40000, "loss": 0.2469, "lr": 1.2385679239782039e-05, "epoch": 21.878428162095783, "percentage": 66.84, "elapsed_time": "3:04:20", "remaining_time": "1:31:28", "throughput": 787.5, "total_tokens": 8710408} {"current_steps": 26740, "total_steps": 40000, "loss": 0.1447, "lr": 1.2377204106006585e-05, "epoch": 21.882521489971346, "percentage": 66.85, "elapsed_time": "3:04:22", "remaining_time": "1:31:25", "throughput": 787.52, "total_tokens": 8712024} {"current_steps": 26745, "total_steps": 40000, "loss": 0.1593, "lr": 1.2368730918824891e-05, "epoch": 21.886614817846908, "percentage": 66.86, "elapsed_time": "3:04:24", "remaining_time": "1:31:23", "throughput": 787.55, "total_tokens": 8713688} {"current_steps": 26750, "total_steps": 40000, "loss": 0.1715, "lr": 1.236025967954362e-05, "epoch": 21.89070814572247, "percentage": 66.88, "elapsed_time": "3:04:26", "remaining_time": "1:31:21", "throughput": 787.58, "total_tokens": 8715320} {"current_steps": 26755, "total_steps": 40000, "loss": 0.1196, "lr": 1.2351790389469153e-05, "epoch": 21.894801473598037, "percentage": 66.89, "elapsed_time": "3:04:27", "remaining_time": "1:31:19", "throughput": 787.6, "total_tokens": 8716968} {"current_steps": 26760, "total_steps": 40000, "loss": 0.1031, "lr": 1.234332304990755e-05, "epoch": 21.8988948014736, "percentage": 66.9, "elapsed_time": "3:04:29", "remaining_time": "1:31:16", "throughput": 787.63, "total_tokens": 8718584} {"current_steps": 26765, "total_steps": 40000, "loss": 0.1264, "lr": 1.2334857662164593e-05, "epoch": 21.90298812934916, "percentage": 66.91, "elapsed_time": "3:04:31", "remaining_time": "1:31:14", "throughput": 787.65, "total_tokens": 8720184} {"current_steps": 26770, "total_steps": 40000, "loss": 0.1761, "lr": 1.2326394227545743e-05, "epoch": 21.907081457224724, "percentage": 66.92, "elapsed_time": "3:04:32", "remaining_time": "1:31:12", "throughput": 787.67, "total_tokens": 8721816} {"current_steps": 26775, "total_steps": 40000, "loss": 0.1621, "lr": 1.2317932747356162e-05, "epoch": 21.911174785100286, "percentage": 66.94, "elapsed_time": "3:04:34", "remaining_time": "1:31:10", "throughput": 787.7, "total_tokens": 8723416} {"current_steps": 26780, "total_steps": 40000, "loss": 0.2687, "lr": 1.2309473222900726e-05, "epoch": 21.91526811297585, "percentage": 66.95, "elapsed_time": "3:04:36", "remaining_time": "1:31:07", "throughput": 787.72, "total_tokens": 8725064} {"current_steps": 26785, "total_steps": 40000, "loss": 0.1048, "lr": 1.2301015655484006e-05, "epoch": 21.91936144085141, "percentage": 66.96, "elapsed_time": "3:04:38", "remaining_time": "1:31:05", "throughput": 787.75, "total_tokens": 8726728} {"current_steps": 26790, "total_steps": 40000, "loss": 0.3349, "lr": 1.2292560046410245e-05, "epoch": 21.923454768726977, "percentage": 66.97, "elapsed_time": "3:04:39", "remaining_time": "1:31:03", "throughput": 787.78, "total_tokens": 8728392} {"current_steps": 26795, "total_steps": 40000, "loss": 0.2012, "lr": 1.228410639698343e-05, "epoch": 21.92754809660254, "percentage": 66.99, "elapsed_time": "3:04:41", "remaining_time": "1:31:01", "throughput": 787.81, "total_tokens": 8730056} {"current_steps": 26800, "total_steps": 40000, "loss": 0.2853, "lr": 1.2275654708507195e-05, "epoch": 21.9316414244781, "percentage": 67.0, "elapsed_time": "3:04:43", "remaining_time": "1:30:58", "throughput": 787.83, "total_tokens": 8731640} {"current_steps": 26800, "total_steps": 40000, "eval_loss": 0.21036650240421295, "epoch": 21.9316414244781, "percentage": 67.0, "elapsed_time": "3:04:55", "remaining_time": "1:31:05", "throughput": 786.94, "total_tokens": 8731640} {"current_steps": 26805, "total_steps": 40000, "loss": 0.1821, "lr": 1.2267204982284908e-05, "epoch": 21.935734752353664, "percentage": 67.01, "elapsed_time": "3:04:58", "remaining_time": "1:31:03", "throughput": 786.86, "total_tokens": 8733288} {"current_steps": 26810, "total_steps": 40000, "loss": 0.1068, "lr": 1.2258757219619635e-05, "epoch": 21.939828080229226, "percentage": 67.03, "elapsed_time": "3:05:00", "remaining_time": "1:31:01", "throughput": 786.88, "total_tokens": 8734968} {"current_steps": 26815, "total_steps": 40000, "loss": 0.1965, "lr": 1.2250311421814104e-05, "epoch": 21.94392140810479, "percentage": 67.04, "elapsed_time": "3:05:02", "remaining_time": "1:30:59", "throughput": 786.92, "total_tokens": 8736664} {"current_steps": 26820, "total_steps": 40000, "loss": 0.1874, "lr": 1.2241867590170772e-05, "epoch": 21.94801473598035, "percentage": 67.05, "elapsed_time": "3:05:04", "remaining_time": "1:30:56", "throughput": 786.94, "total_tokens": 8738264} {"current_steps": 26825, "total_steps": 40000, "loss": 0.1771, "lr": 1.2233425725991799e-05, "epoch": 21.952108063855913, "percentage": 67.06, "elapsed_time": "3:05:05", "remaining_time": "1:30:54", "throughput": 786.97, "total_tokens": 8739944} {"current_steps": 26830, "total_steps": 40000, "loss": 0.1654, "lr": 1.2224985830579003e-05, "epoch": 21.95620139173148, "percentage": 67.07, "elapsed_time": "3:05:07", "remaining_time": "1:30:52", "throughput": 786.99, "total_tokens": 8741592} {"current_steps": 26835, "total_steps": 40000, "loss": 0.2401, "lr": 1.2216547905233944e-05, "epoch": 21.96029471960704, "percentage": 67.09, "elapsed_time": "3:05:09", "remaining_time": "1:30:50", "throughput": 787.02, "total_tokens": 8743192} {"current_steps": 26840, "total_steps": 40000, "loss": 0.2138, "lr": 1.2208111951257842e-05, "epoch": 21.964388047482604, "percentage": 67.1, "elapsed_time": "3:05:11", "remaining_time": "1:30:47", "throughput": 787.04, "total_tokens": 8744824} {"current_steps": 26845, "total_steps": 40000, "loss": 0.1647, "lr": 1.2199677969951622e-05, "epoch": 21.968481375358166, "percentage": 67.11, "elapsed_time": "3:05:12", "remaining_time": "1:30:45", "throughput": 787.07, "total_tokens": 8746456} {"current_steps": 26850, "total_steps": 40000, "loss": 0.1837, "lr": 1.2191245962615927e-05, "epoch": 21.97257470323373, "percentage": 67.12, "elapsed_time": "3:05:14", "remaining_time": "1:30:43", "throughput": 787.1, "total_tokens": 8748152} {"current_steps": 26855, "total_steps": 40000, "loss": 0.1678, "lr": 1.218281593055106e-05, "epoch": 21.97666803110929, "percentage": 67.14, "elapsed_time": "3:05:16", "remaining_time": "1:30:41", "throughput": 787.12, "total_tokens": 8749800} {"current_steps": 26860, "total_steps": 40000, "loss": 0.1756, "lr": 1.217438787505705e-05, "epoch": 21.980761358984854, "percentage": 67.15, "elapsed_time": "3:05:17", "remaining_time": "1:30:38", "throughput": 787.14, "total_tokens": 8751368} {"current_steps": 26865, "total_steps": 40000, "loss": 0.2004, "lr": 1.2165961797433615e-05, "epoch": 21.984854686860416, "percentage": 67.16, "elapsed_time": "3:05:19", "remaining_time": "1:30:36", "throughput": 787.17, "total_tokens": 8753032} {"current_steps": 26870, "total_steps": 40000, "loss": 0.1466, "lr": 1.215753769898014e-05, "epoch": 21.988948014735982, "percentage": 67.17, "elapsed_time": "3:05:21", "remaining_time": "1:30:34", "throughput": 787.19, "total_tokens": 8754648} {"current_steps": 26875, "total_steps": 40000, "loss": 0.2316, "lr": 1.2149115580995755e-05, "epoch": 21.993041342611544, "percentage": 67.19, "elapsed_time": "3:05:23", "remaining_time": "1:30:32", "throughput": 787.22, "total_tokens": 8756248} {"current_steps": 26880, "total_steps": 40000, "loss": 0.1771, "lr": 1.2140695444779227e-05, "epoch": 21.997134670487107, "percentage": 67.2, "elapsed_time": "3:05:24", "remaining_time": "1:30:29", "throughput": 787.24, "total_tokens": 8757864} {"current_steps": 26885, "total_steps": 40000, "loss": 0.1887, "lr": 1.2132277291629066e-05, "epoch": 22.000818665575114, "percentage": 67.21, "elapsed_time": "3:05:26", "remaining_time": "1:30:27", "throughput": 787.23, "total_tokens": 8759264} {"current_steps": 26890, "total_steps": 40000, "loss": 0.1969, "lr": 1.2123861122843458e-05, "epoch": 22.004911993450676, "percentage": 67.22, "elapsed_time": "3:05:28", "remaining_time": "1:30:25", "throughput": 787.25, "total_tokens": 8760864} {"current_steps": 26895, "total_steps": 40000, "loss": 0.136, "lr": 1.2115446939720271e-05, "epoch": 22.00900532132624, "percentage": 67.24, "elapsed_time": "3:05:30", "remaining_time": "1:30:23", "throughput": 787.27, "total_tokens": 8762480} {"current_steps": 26900, "total_steps": 40000, "loss": 0.2203, "lr": 1.210703474355708e-05, "epoch": 22.0130986492018, "percentage": 67.25, "elapsed_time": "3:05:31", "remaining_time": "1:30:21", "throughput": 787.3, "total_tokens": 8764128} {"current_steps": 26905, "total_steps": 40000, "loss": 0.2477, "lr": 1.2098624535651164e-05, "epoch": 22.017191977077363, "percentage": 67.26, "elapsed_time": "3:05:33", "remaining_time": "1:30:18", "throughput": 787.32, "total_tokens": 8765712} {"current_steps": 26910, "total_steps": 40000, "loss": 0.2599, "lr": 1.2090216317299477e-05, "epoch": 22.021285304952926, "percentage": 67.27, "elapsed_time": "3:05:35", "remaining_time": "1:30:16", "throughput": 787.35, "total_tokens": 8767376} {"current_steps": 26915, "total_steps": 40000, "loss": 0.2674, "lr": 1.2081810089798668e-05, "epoch": 22.025378632828488, "percentage": 67.29, "elapsed_time": "3:05:37", "remaining_time": "1:30:14", "throughput": 787.37, "total_tokens": 8769008} {"current_steps": 26920, "total_steps": 40000, "loss": 0.1755, "lr": 1.2073405854445072e-05, "epoch": 22.029471960704054, "percentage": 67.3, "elapsed_time": "3:05:38", "remaining_time": "1:30:12", "throughput": 787.4, "total_tokens": 8770672} {"current_steps": 26925, "total_steps": 40000, "loss": 0.1502, "lr": 1.206500361253474e-05, "epoch": 22.033565288579616, "percentage": 67.31, "elapsed_time": "3:05:40", "remaining_time": "1:30:09", "throughput": 787.43, "total_tokens": 8772304} {"current_steps": 26930, "total_steps": 40000, "loss": 0.2056, "lr": 1.2056603365363409e-05, "epoch": 22.03765861645518, "percentage": 67.33, "elapsed_time": "3:05:42", "remaining_time": "1:30:07", "throughput": 787.44, "total_tokens": 8773856} {"current_steps": 26935, "total_steps": 40000, "loss": 0.1438, "lr": 1.2048205114226487e-05, "epoch": 22.04175194433074, "percentage": 67.34, "elapsed_time": "3:05:43", "remaining_time": "1:30:05", "throughput": 787.47, "total_tokens": 8775456} {"current_steps": 26940, "total_steps": 40000, "loss": 0.2077, "lr": 1.2039808860419102e-05, "epoch": 22.045845272206304, "percentage": 67.35, "elapsed_time": "3:05:45", "remaining_time": "1:30:03", "throughput": 787.5, "total_tokens": 8777168} {"current_steps": 26945, "total_steps": 40000, "loss": 0.1505, "lr": 1.2031414605236066e-05, "epoch": 22.049938600081866, "percentage": 67.36, "elapsed_time": "3:05:47", "remaining_time": "1:30:00", "throughput": 787.52, "total_tokens": 8778784} {"current_steps": 26950, "total_steps": 40000, "loss": 0.1878, "lr": 1.2023022349971862e-05, "epoch": 22.05403192795743, "percentage": 67.38, "elapsed_time": "3:05:49", "remaining_time": "1:29:58", "throughput": 787.55, "total_tokens": 8780416} {"current_steps": 26955, "total_steps": 40000, "loss": 0.1669, "lr": 1.20146320959207e-05, "epoch": 22.05812525583299, "percentage": 67.39, "elapsed_time": "3:05:50", "remaining_time": "1:29:56", "throughput": 787.56, "total_tokens": 8781968} {"current_steps": 26960, "total_steps": 40000, "loss": 0.1937, "lr": 1.2006243844376445e-05, "epoch": 22.062218583708557, "percentage": 67.4, "elapsed_time": "3:05:52", "remaining_time": "1:29:54", "throughput": 787.59, "total_tokens": 8783568} {"current_steps": 26965, "total_steps": 40000, "loss": 0.2054, "lr": 1.1997857596632678e-05, "epoch": 22.06631191158412, "percentage": 67.41, "elapsed_time": "3:05:54", "remaining_time": "1:29:52", "throughput": 787.61, "total_tokens": 8785200} {"current_steps": 26970, "total_steps": 40000, "loss": 0.2365, "lr": 1.1989473353982672e-05, "epoch": 22.07040523945968, "percentage": 67.42, "elapsed_time": "3:05:55", "remaining_time": "1:29:49", "throughput": 787.63, "total_tokens": 8786832} {"current_steps": 26975, "total_steps": 40000, "loss": 0.1653, "lr": 1.198109111771937e-05, "epoch": 22.074498567335244, "percentage": 67.44, "elapsed_time": "3:05:57", "remaining_time": "1:29:47", "throughput": 787.66, "total_tokens": 8788512} {"current_steps": 26980, "total_steps": 40000, "loss": 0.2376, "lr": 1.197271088913543e-05, "epoch": 22.078591895210806, "percentage": 67.45, "elapsed_time": "3:05:59", "remaining_time": "1:29:45", "throughput": 787.7, "total_tokens": 8790224} {"current_steps": 26985, "total_steps": 40000, "loss": 0.2267, "lr": 1.1964332669523182e-05, "epoch": 22.08268522308637, "percentage": 67.46, "elapsed_time": "3:06:01", "remaining_time": "1:29:43", "throughput": 787.72, "total_tokens": 8791840} {"current_steps": 26990, "total_steps": 40000, "loss": 0.1546, "lr": 1.1955956460174645e-05, "epoch": 22.08677855096193, "percentage": 67.47, "elapsed_time": "3:06:02", "remaining_time": "1:29:40", "throughput": 787.75, "total_tokens": 8793504} {"current_steps": 26995, "total_steps": 40000, "loss": 0.142, "lr": 1.1947582262381552e-05, "epoch": 22.090871878837493, "percentage": 67.49, "elapsed_time": "3:06:04", "remaining_time": "1:29:38", "throughput": 787.77, "total_tokens": 8795104} {"current_steps": 27000, "total_steps": 40000, "loss": 0.1856, "lr": 1.1939210077435293e-05, "epoch": 22.09496520671306, "percentage": 67.5, "elapsed_time": "3:06:06", "remaining_time": "1:29:36", "throughput": 787.79, "total_tokens": 8796704} {"current_steps": 27000, "total_steps": 40000, "eval_loss": 0.21445810794830322, "epoch": 22.09496520671306, "percentage": 67.5, "elapsed_time": "3:06:18", "remaining_time": "1:29:42", "throughput": 786.91, "total_tokens": 8796704} {"current_steps": 27005, "total_steps": 40000, "loss": 0.1909, "lr": 1.193083990662697e-05, "epoch": 22.09905853458862, "percentage": 67.51, "elapsed_time": "3:06:22", "remaining_time": "1:29:40", "throughput": 786.83, "total_tokens": 8798320} {"current_steps": 27010, "total_steps": 40000, "loss": 0.164, "lr": 1.192247175124738e-05, "epoch": 22.103151862464184, "percentage": 67.53, "elapsed_time": "3:06:23", "remaining_time": "1:29:38", "throughput": 786.85, "total_tokens": 8799888} {"current_steps": 27015, "total_steps": 40000, "loss": 0.1789, "lr": 1.191410561258698e-05, "epoch": 22.107245190339746, "percentage": 67.54, "elapsed_time": "3:06:25", "remaining_time": "1:29:36", "throughput": 786.87, "total_tokens": 8801520} {"current_steps": 27020, "total_steps": 40000, "loss": 0.1537, "lr": 1.1905741491935944e-05, "epoch": 22.11133851821531, "percentage": 67.55, "elapsed_time": "3:06:27", "remaining_time": "1:29:34", "throughput": 786.89, "total_tokens": 8803120} {"current_steps": 27025, "total_steps": 40000, "loss": 0.1998, "lr": 1.1897379390584129e-05, "epoch": 22.11543184609087, "percentage": 67.56, "elapsed_time": "3:06:28", "remaining_time": "1:29:31", "throughput": 786.92, "total_tokens": 8804752} {"current_steps": 27030, "total_steps": 40000, "loss": 0.1555, "lr": 1.1889019309821062e-05, "epoch": 22.119525173966434, "percentage": 67.58, "elapsed_time": "3:06:30", "remaining_time": "1:29:29", "throughput": 786.94, "total_tokens": 8806400} {"current_steps": 27035, "total_steps": 40000, "loss": 0.2256, "lr": 1.188066125093599e-05, "epoch": 22.123618501841996, "percentage": 67.59, "elapsed_time": "3:06:32", "remaining_time": "1:29:27", "throughput": 786.98, "total_tokens": 8808112} {"current_steps": 27040, "total_steps": 40000, "loss": 0.2309, "lr": 1.1872305215217811e-05, "epoch": 22.127711829717562, "percentage": 67.6, "elapsed_time": "3:06:34", "remaining_time": "1:29:25", "throughput": 787.01, "total_tokens": 8809824} {"current_steps": 27045, "total_steps": 40000, "loss": 0.1623, "lr": 1.186395120395514e-05, "epoch": 22.131805157593124, "percentage": 67.61, "elapsed_time": "3:06:35", "remaining_time": "1:29:22", "throughput": 787.03, "total_tokens": 8811376} {"current_steps": 27050, "total_steps": 40000, "loss": 0.1287, "lr": 1.1855599218436283e-05, "epoch": 22.135898485468687, "percentage": 67.62, "elapsed_time": "3:06:37", "remaining_time": "1:29:20", "throughput": 787.05, "total_tokens": 8813008} {"current_steps": 27055, "total_steps": 40000, "loss": 0.1841, "lr": 1.1847249259949209e-05, "epoch": 22.13999181334425, "percentage": 67.64, "elapsed_time": "3:06:39", "remaining_time": "1:29:18", "throughput": 787.08, "total_tokens": 8814688} {"current_steps": 27060, "total_steps": 40000, "loss": 0.1734, "lr": 1.1838901329781574e-05, "epoch": 22.14408514121981, "percentage": 67.65, "elapsed_time": "3:06:40", "remaining_time": "1:29:16", "throughput": 787.11, "total_tokens": 8816352} {"current_steps": 27065, "total_steps": 40000, "loss": 0.1345, "lr": 1.1830555429220758e-05, "epoch": 22.148178469095374, "percentage": 67.66, "elapsed_time": "3:06:42", "remaining_time": "1:29:14", "throughput": 787.13, "total_tokens": 8817952} {"current_steps": 27070, "total_steps": 40000, "loss": 0.1731, "lr": 1.1822211559553784e-05, "epoch": 22.152271796970936, "percentage": 67.67, "elapsed_time": "3:06:44", "remaining_time": "1:29:11", "throughput": 787.16, "total_tokens": 8819600} {"current_steps": 27075, "total_steps": 40000, "loss": 0.2262, "lr": 1.18138697220674e-05, "epoch": 22.1563651248465, "percentage": 67.69, "elapsed_time": "3:06:46", "remaining_time": "1:29:09", "throughput": 787.18, "total_tokens": 8821248} {"current_steps": 27080, "total_steps": 40000, "loss": 0.1483, "lr": 1.1805529918048e-05, "epoch": 22.160458452722064, "percentage": 67.7, "elapsed_time": "3:06:47", "remaining_time": "1:29:07", "throughput": 787.21, "total_tokens": 8822880} {"current_steps": 27085, "total_steps": 40000, "loss": 0.1549, "lr": 1.1797192148781702e-05, "epoch": 22.164551780597627, "percentage": 67.71, "elapsed_time": "3:06:49", "remaining_time": "1:29:05", "throughput": 787.23, "total_tokens": 8824480} {"current_steps": 27090, "total_steps": 40000, "loss": 0.1695, "lr": 1.1788856415554297e-05, "epoch": 22.16864510847319, "percentage": 67.73, "elapsed_time": "3:06:51", "remaining_time": "1:29:02", "throughput": 787.25, "total_tokens": 8826096} {"current_steps": 27095, "total_steps": 40000, "loss": 0.2073, "lr": 1.1780522719651249e-05, "epoch": 22.17273843634875, "percentage": 67.74, "elapsed_time": "3:06:52", "remaining_time": "1:29:00", "throughput": 787.28, "total_tokens": 8827712} {"current_steps": 27100, "total_steps": 40000, "loss": 0.163, "lr": 1.1772191062357721e-05, "epoch": 22.176831764224314, "percentage": 67.75, "elapsed_time": "3:06:54", "remaining_time": "1:28:58", "throughput": 787.3, "total_tokens": 8829296} {"current_steps": 27105, "total_steps": 40000, "loss": 0.1879, "lr": 1.1763861444958573e-05, "epoch": 22.180925092099876, "percentage": 67.76, "elapsed_time": "3:06:56", "remaining_time": "1:28:56", "throughput": 787.32, "total_tokens": 8830928} {"current_steps": 27110, "total_steps": 40000, "loss": 0.1255, "lr": 1.1755533868738317e-05, "epoch": 22.18501841997544, "percentage": 67.77, "elapsed_time": "3:06:58", "remaining_time": "1:28:53", "throughput": 787.35, "total_tokens": 8832560} {"current_steps": 27115, "total_steps": 40000, "loss": 0.0813, "lr": 1.1747208334981185e-05, "epoch": 22.189111747851, "percentage": 67.79, "elapsed_time": "3:06:59", "remaining_time": "1:28:51", "throughput": 787.38, "total_tokens": 8834240} {"current_steps": 27120, "total_steps": 40000, "loss": 0.1854, "lr": 1.1738884844971067e-05, "epoch": 22.193205075726567, "percentage": 67.8, "elapsed_time": "3:07:01", "remaining_time": "1:28:49", "throughput": 787.4, "total_tokens": 8835888} {"current_steps": 27125, "total_steps": 40000, "loss": 0.1618, "lr": 1.1730563399991563e-05, "epoch": 22.19729840360213, "percentage": 67.81, "elapsed_time": "3:07:03", "remaining_time": "1:28:47", "throughput": 787.42, "total_tokens": 8837488} {"current_steps": 27130, "total_steps": 40000, "loss": 0.18, "lr": 1.1722244001325938e-05, "epoch": 22.201391731477692, "percentage": 67.83, "elapsed_time": "3:07:05", "remaining_time": "1:28:44", "throughput": 787.45, "total_tokens": 8839120} {"current_steps": 27135, "total_steps": 40000, "loss": 0.1855, "lr": 1.1713926650257137e-05, "epoch": 22.205485059353254, "percentage": 67.84, "elapsed_time": "3:07:06", "remaining_time": "1:28:42", "throughput": 787.47, "total_tokens": 8840720} {"current_steps": 27140, "total_steps": 40000, "loss": 0.1475, "lr": 1.170561134806781e-05, "epoch": 22.209578387228817, "percentage": 67.85, "elapsed_time": "3:07:08", "remaining_time": "1:28:40", "throughput": 787.49, "total_tokens": 8842336} {"current_steps": 27145, "total_steps": 40000, "loss": 0.1604, "lr": 1.1697298096040287e-05, "epoch": 22.21367171510438, "percentage": 67.86, "elapsed_time": "3:07:10", "remaining_time": "1:28:38", "throughput": 787.51, "total_tokens": 8843904} {"current_steps": 27150, "total_steps": 40000, "loss": 0.1711, "lr": 1.1688986895456567e-05, "epoch": 22.21776504297994, "percentage": 67.88, "elapsed_time": "3:07:11", "remaining_time": "1:28:36", "throughput": 787.54, "total_tokens": 8845504} {"current_steps": 27155, "total_steps": 40000, "loss": 0.1537, "lr": 1.1680677747598349e-05, "epoch": 22.221858370855507, "percentage": 67.89, "elapsed_time": "3:07:13", "remaining_time": "1:28:33", "throughput": 787.57, "total_tokens": 8847216} {"current_steps": 27160, "total_steps": 40000, "loss": 0.1177, "lr": 1.1672370653746995e-05, "epoch": 22.22595169873107, "percentage": 67.9, "elapsed_time": "3:07:15", "remaining_time": "1:28:31", "throughput": 787.59, "total_tokens": 8848848} {"current_steps": 27165, "total_steps": 40000, "loss": 0.2151, "lr": 1.166406561518357e-05, "epoch": 22.230045026606632, "percentage": 67.91, "elapsed_time": "3:07:17", "remaining_time": "1:28:29", "throughput": 787.62, "total_tokens": 8850528} {"current_steps": 27170, "total_steps": 40000, "loss": 0.1835, "lr": 1.1655762633188826e-05, "epoch": 22.234138354482194, "percentage": 67.92, "elapsed_time": "3:07:18", "remaining_time": "1:28:27", "throughput": 787.64, "total_tokens": 8852128} {"current_steps": 27175, "total_steps": 40000, "loss": 0.1632, "lr": 1.1647461709043172e-05, "epoch": 22.238231682357757, "percentage": 67.94, "elapsed_time": "3:07:20", "remaining_time": "1:28:24", "throughput": 787.67, "total_tokens": 8853728} {"current_steps": 27180, "total_steps": 40000, "loss": 0.1433, "lr": 1.1639162844026722e-05, "epoch": 22.24232501023332, "percentage": 67.95, "elapsed_time": "3:07:22", "remaining_time": "1:28:22", "throughput": 787.69, "total_tokens": 8855328} {"current_steps": 27185, "total_steps": 40000, "loss": 0.2419, "lr": 1.163086603941927e-05, "epoch": 22.24641833810888, "percentage": 67.96, "elapsed_time": "3:07:23", "remaining_time": "1:28:20", "throughput": 787.71, "total_tokens": 8856928} {"current_steps": 27190, "total_steps": 40000, "loss": 0.1334, "lr": 1.1622571296500273e-05, "epoch": 22.250511665984444, "percentage": 67.97, "elapsed_time": "3:07:25", "remaining_time": "1:28:18", "throughput": 787.73, "total_tokens": 8858528} {"current_steps": 27195, "total_steps": 40000, "loss": 0.1582, "lr": 1.1614278616548904e-05, "epoch": 22.25460499386001, "percentage": 67.99, "elapsed_time": "3:07:27", "remaining_time": "1:28:15", "throughput": 787.76, "total_tokens": 8860176} {"current_steps": 27200, "total_steps": 40000, "loss": 0.146, "lr": 1.1605988000843986e-05, "epoch": 22.258698321735572, "percentage": 68.0, "elapsed_time": "3:07:29", "remaining_time": "1:28:13", "throughput": 787.78, "total_tokens": 8861792} {"current_steps": 27200, "total_steps": 40000, "eval_loss": 0.21010160446166992, "epoch": 22.258698321735572, "percentage": 68.0, "elapsed_time": "3:07:41", "remaining_time": "1:28:19", "throughput": 786.91, "total_tokens": 8861792} {"current_steps": 27205, "total_steps": 40000, "loss": 0.2072, "lr": 1.1597699450664028e-05, "epoch": 22.262791649611135, "percentage": 68.01, "elapsed_time": "3:07:44", "remaining_time": "1:28:18", "throughput": 786.83, "total_tokens": 8863440} {"current_steps": 27210, "total_steps": 40000, "loss": 0.183, "lr": 1.1589412967287252e-05, "epoch": 22.266884977486697, "percentage": 68.03, "elapsed_time": "3:07:46", "remaining_time": "1:28:15", "throughput": 786.86, "total_tokens": 8865088} {"current_steps": 27215, "total_steps": 40000, "loss": 0.1571, "lr": 1.1581128551991514e-05, "epoch": 22.27097830536226, "percentage": 68.04, "elapsed_time": "3:07:48", "remaining_time": "1:28:13", "throughput": 786.89, "total_tokens": 8866816} {"current_steps": 27220, "total_steps": 40000, "loss": 0.1132, "lr": 1.1572846206054383e-05, "epoch": 22.275071633237822, "percentage": 68.05, "elapsed_time": "3:07:49", "remaining_time": "1:28:11", "throughput": 786.92, "total_tokens": 8868480} {"current_steps": 27225, "total_steps": 40000, "loss": 0.3282, "lr": 1.1564565930753113e-05, "epoch": 22.279164961113384, "percentage": 68.06, "elapsed_time": "3:07:51", "remaining_time": "1:28:09", "throughput": 786.94, "total_tokens": 8870096} {"current_steps": 27230, "total_steps": 40000, "loss": 0.247, "lr": 1.1556287727364606e-05, "epoch": 22.283258288988947, "percentage": 68.08, "elapsed_time": "3:07:53", "remaining_time": "1:28:06", "throughput": 786.96, "total_tokens": 8871680} {"current_steps": 27235, "total_steps": 40000, "loss": 0.1968, "lr": 1.1548011597165489e-05, "epoch": 22.287351616864512, "percentage": 68.09, "elapsed_time": "3:07:55", "remaining_time": "1:28:04", "throughput": 786.98, "total_tokens": 8873280} {"current_steps": 27240, "total_steps": 40000, "loss": 0.1533, "lr": 1.1539737541432019e-05, "epoch": 22.291444944740075, "percentage": 68.1, "elapsed_time": "3:07:56", "remaining_time": "1:28:02", "throughput": 787.01, "total_tokens": 8874912} {"current_steps": 27245, "total_steps": 40000, "loss": 0.1771, "lr": 1.1531465561440174e-05, "epoch": 22.295538272615637, "percentage": 68.11, "elapsed_time": "3:07:58", "remaining_time": "1:28:00", "throughput": 787.03, "total_tokens": 8876512} {"current_steps": 27250, "total_steps": 40000, "loss": 0.1305, "lr": 1.1523195658465605e-05, "epoch": 22.2996316004912, "percentage": 68.12, "elapsed_time": "3:08:00", "remaining_time": "1:27:57", "throughput": 787.05, "total_tokens": 8878096} {"current_steps": 27255, "total_steps": 40000, "loss": 0.2254, "lr": 1.1514927833783618e-05, "epoch": 22.303724928366762, "percentage": 68.14, "elapsed_time": "3:08:01", "remaining_time": "1:27:55", "throughput": 787.07, "total_tokens": 8879728} {"current_steps": 27260, "total_steps": 40000, "loss": 0.1949, "lr": 1.150666208866922e-05, "epoch": 22.307818256242324, "percentage": 68.15, "elapsed_time": "3:08:03", "remaining_time": "1:27:53", "throughput": 787.1, "total_tokens": 8881312} {"current_steps": 27265, "total_steps": 40000, "loss": 0.2093, "lr": 1.1498398424397106e-05, "epoch": 22.311911584117887, "percentage": 68.16, "elapsed_time": "3:08:05", "remaining_time": "1:27:51", "throughput": 787.13, "total_tokens": 8883008} {"current_steps": 27270, "total_steps": 40000, "loss": 0.1607, "lr": 1.1490136842241628e-05, "epoch": 22.31600491199345, "percentage": 68.17, "elapsed_time": "3:08:07", "remaining_time": "1:27:48", "throughput": 787.15, "total_tokens": 8884656} {"current_steps": 27275, "total_steps": 40000, "loss": 0.1233, "lr": 1.1481877343476813e-05, "epoch": 22.320098239869015, "percentage": 68.19, "elapsed_time": "3:08:08", "remaining_time": "1:27:46", "throughput": 787.18, "total_tokens": 8886320} {"current_steps": 27280, "total_steps": 40000, "loss": 0.1339, "lr": 1.14736199293764e-05, "epoch": 22.324191567744577, "percentage": 68.2, "elapsed_time": "3:08:10", "remaining_time": "1:27:44", "throughput": 787.2, "total_tokens": 8887936} {"current_steps": 27285, "total_steps": 40000, "loss": 0.0943, "lr": 1.1465364601213771e-05, "epoch": 22.32828489562014, "percentage": 68.21, "elapsed_time": "3:08:12", "remaining_time": "1:27:42", "throughput": 787.23, "total_tokens": 8889584} {"current_steps": 27290, "total_steps": 40000, "loss": 0.2255, "lr": 1.1457111360262012e-05, "epoch": 22.332378223495702, "percentage": 68.23, "elapsed_time": "3:08:13", "remaining_time": "1:27:40", "throughput": 787.25, "total_tokens": 8891184} {"current_steps": 27295, "total_steps": 40000, "loss": 0.1187, "lr": 1.1448860207793869e-05, "epoch": 22.336471551371265, "percentage": 68.24, "elapsed_time": "3:08:15", "remaining_time": "1:27:37", "throughput": 787.27, "total_tokens": 8892816} {"current_steps": 27300, "total_steps": 40000, "loss": 0.2128, "lr": 1.144061114508177e-05, "epoch": 22.340564879246827, "percentage": 68.25, "elapsed_time": "3:08:17", "remaining_time": "1:27:35", "throughput": 787.3, "total_tokens": 8894448} {"current_steps": 27305, "total_steps": 40000, "loss": 0.1683, "lr": 1.1432364173397842e-05, "epoch": 22.34465820712239, "percentage": 68.26, "elapsed_time": "3:08:19", "remaining_time": "1:27:33", "throughput": 787.32, "total_tokens": 8896048} {"current_steps": 27310, "total_steps": 40000, "loss": 0.155, "lr": 1.1424119294013852e-05, "epoch": 22.34875153499795, "percentage": 68.27, "elapsed_time": "3:08:20", "remaining_time": "1:27:31", "throughput": 787.34, "total_tokens": 8897664} {"current_steps": 27315, "total_steps": 40000, "loss": 0.1589, "lr": 1.1415876508201279e-05, "epoch": 22.352844862873518, "percentage": 68.29, "elapsed_time": "3:08:22", "remaining_time": "1:27:28", "throughput": 787.37, "total_tokens": 8899344} {"current_steps": 27320, "total_steps": 40000, "loss": 0.1721, "lr": 1.140763581723125e-05, "epoch": 22.35693819074908, "percentage": 68.3, "elapsed_time": "3:08:24", "remaining_time": "1:27:26", "throughput": 787.39, "total_tokens": 8900928} {"current_steps": 27325, "total_steps": 40000, "loss": 0.1587, "lr": 1.1399397222374588e-05, "epoch": 22.361031518624642, "percentage": 68.31, "elapsed_time": "3:08:26", "remaining_time": "1:27:24", "throughput": 787.42, "total_tokens": 8902576} {"current_steps": 27330, "total_steps": 40000, "loss": 0.1338, "lr": 1.1391160724901804e-05, "epoch": 22.365124846500205, "percentage": 68.33, "elapsed_time": "3:08:27", "remaining_time": "1:27:22", "throughput": 787.45, "total_tokens": 8904256} {"current_steps": 27335, "total_steps": 40000, "loss": 0.1917, "lr": 1.138292632608304e-05, "epoch": 22.369218174375767, "percentage": 68.34, "elapsed_time": "3:08:29", "remaining_time": "1:27:19", "throughput": 787.49, "total_tokens": 8906048} {"current_steps": 27340, "total_steps": 40000, "loss": 0.1358, "lr": 1.1374694027188174e-05, "epoch": 22.37331150225133, "percentage": 68.35, "elapsed_time": "3:08:31", "remaining_time": "1:27:17", "throughput": 787.5, "total_tokens": 8907616} {"current_steps": 27345, "total_steps": 40000, "loss": 0.2808, "lr": 1.1366463829486711e-05, "epoch": 22.377404830126892, "percentage": 68.36, "elapsed_time": "3:08:32", "remaining_time": "1:27:15", "throughput": 787.53, "total_tokens": 8909264} {"current_steps": 27350, "total_steps": 40000, "loss": 0.1615, "lr": 1.1358235734247849e-05, "epoch": 22.381498158002454, "percentage": 68.38, "elapsed_time": "3:08:34", "remaining_time": "1:27:13", "throughput": 787.56, "total_tokens": 8910944} {"current_steps": 27355, "total_steps": 40000, "loss": 0.0999, "lr": 1.1350009742740478e-05, "epoch": 22.38559148587802, "percentage": 68.39, "elapsed_time": "3:08:36", "remaining_time": "1:27:11", "throughput": 787.59, "total_tokens": 8912592} {"current_steps": 27360, "total_steps": 40000, "loss": 0.1618, "lr": 1.134178585623313e-05, "epoch": 22.389684813753583, "percentage": 68.4, "elapsed_time": "3:08:38", "remaining_time": "1:27:08", "throughput": 787.61, "total_tokens": 8914208} {"current_steps": 27365, "total_steps": 40000, "loss": 0.1864, "lr": 1.1333564075994047e-05, "epoch": 22.393778141629145, "percentage": 68.41, "elapsed_time": "3:08:39", "remaining_time": "1:27:06", "throughput": 787.63, "total_tokens": 8915808} {"current_steps": 27370, "total_steps": 40000, "loss": 0.1623, "lr": 1.1325344403291133e-05, "epoch": 22.397871469504707, "percentage": 68.42, "elapsed_time": "3:08:41", "remaining_time": "1:27:04", "throughput": 787.65, "total_tokens": 8917376} {"current_steps": 27375, "total_steps": 40000, "loss": 0.2026, "lr": 1.1317126839391951e-05, "epoch": 22.40196479738027, "percentage": 68.44, "elapsed_time": "3:08:43", "remaining_time": "1:27:02", "throughput": 787.67, "total_tokens": 8918944} {"current_steps": 27380, "total_steps": 40000, "loss": 0.1941, "lr": 1.1308911385563766e-05, "epoch": 22.406058125255832, "percentage": 68.45, "elapsed_time": "3:08:44", "remaining_time": "1:26:59", "throughput": 787.7, "total_tokens": 8920640} {"current_steps": 27385, "total_steps": 40000, "loss": 0.2006, "lr": 1.1300698043073494e-05, "epoch": 22.410151453131395, "percentage": 68.46, "elapsed_time": "3:08:46", "remaining_time": "1:26:57", "throughput": 787.73, "total_tokens": 8922320} {"current_steps": 27390, "total_steps": 40000, "loss": 0.1504, "lr": 1.1292486813187736e-05, "epoch": 22.414244781006957, "percentage": 68.47, "elapsed_time": "3:08:48", "remaining_time": "1:26:55", "throughput": 787.75, "total_tokens": 8923904} {"current_steps": 27395, "total_steps": 40000, "loss": 0.2053, "lr": 1.1284277697172782e-05, "epoch": 22.418338108882523, "percentage": 68.49, "elapsed_time": "3:08:50", "remaining_time": "1:26:53", "throughput": 787.77, "total_tokens": 8925536} {"current_steps": 27400, "total_steps": 40000, "loss": 0.1597, "lr": 1.127607069629456e-05, "epoch": 22.422431436758085, "percentage": 68.5, "elapsed_time": "3:08:51", "remaining_time": "1:26:50", "throughput": 787.8, "total_tokens": 8927168} {"current_steps": 27400, "total_steps": 40000, "eval_loss": 0.21204757690429688, "epoch": 22.422431436758085, "percentage": 68.5, "elapsed_time": "3:09:04", "remaining_time": "1:26:56", "throughput": 786.93, "total_tokens": 8927168} {"current_steps": 27405, "total_steps": 40000, "loss": 0.1268, "lr": 1.1267865811818701e-05, "epoch": 22.426524764633648, "percentage": 68.51, "elapsed_time": "3:09:07", "remaining_time": "1:26:55", "throughput": 786.85, "total_tokens": 8928784} {"current_steps": 27410, "total_steps": 40000, "loss": 0.1404, "lr": 1.1259663045010513e-05, "epoch": 22.43061809250921, "percentage": 68.53, "elapsed_time": "3:09:09", "remaining_time": "1:26:52", "throughput": 786.87, "total_tokens": 8930416} {"current_steps": 27415, "total_steps": 40000, "loss": 0.1656, "lr": 1.1251462397134957e-05, "epoch": 22.434711420384772, "percentage": 68.54, "elapsed_time": "3:09:11", "remaining_time": "1:26:50", "throughput": 786.89, "total_tokens": 8931968} {"current_steps": 27420, "total_steps": 40000, "loss": 0.1654, "lr": 1.1243263869456664e-05, "epoch": 22.438804748260335, "percentage": 68.55, "elapsed_time": "3:09:12", "remaining_time": "1:26:48", "throughput": 786.92, "total_tokens": 8933664} {"current_steps": 27425, "total_steps": 40000, "loss": 0.1297, "lr": 1.1235067463239967e-05, "epoch": 22.442898076135897, "percentage": 68.56, "elapsed_time": "3:09:14", "remaining_time": "1:26:46", "throughput": 786.94, "total_tokens": 8935264} {"current_steps": 27430, "total_steps": 40000, "loss": 0.1298, "lr": 1.122687317974884e-05, "epoch": 22.446991404011463, "percentage": 68.58, "elapsed_time": "3:09:16", "remaining_time": "1:26:44", "throughput": 786.96, "total_tokens": 8936848} {"current_steps": 27435, "total_steps": 40000, "loss": 0.1344, "lr": 1.1218681020246963e-05, "epoch": 22.451084731887025, "percentage": 68.59, "elapsed_time": "3:09:17", "remaining_time": "1:26:41", "throughput": 786.98, "total_tokens": 8938432} {"current_steps": 27440, "total_steps": 40000, "loss": 0.1506, "lr": 1.1210490985997652e-05, "epoch": 22.455178059762588, "percentage": 68.6, "elapsed_time": "3:09:19", "remaining_time": "1:26:39", "throughput": 787.0, "total_tokens": 8940032} {"current_steps": 27445, "total_steps": 40000, "loss": 0.2524, "lr": 1.1202303078263917e-05, "epoch": 22.45927138763815, "percentage": 68.61, "elapsed_time": "3:09:21", "remaining_time": "1:26:37", "throughput": 787.02, "total_tokens": 8941648} {"current_steps": 27450, "total_steps": 40000, "loss": 0.2161, "lr": 1.1194117298308451e-05, "epoch": 22.463364715513713, "percentage": 68.62, "elapsed_time": "3:09:23", "remaining_time": "1:26:35", "throughput": 787.05, "total_tokens": 8943264} {"current_steps": 27455, "total_steps": 40000, "loss": 0.1859, "lr": 1.1185933647393585e-05, "epoch": 22.467458043389275, "percentage": 68.64, "elapsed_time": "3:09:24", "remaining_time": "1:26:32", "throughput": 787.08, "total_tokens": 8944928} {"current_steps": 27460, "total_steps": 40000, "loss": 0.1349, "lr": 1.1177752126781354e-05, "epoch": 22.471551371264837, "percentage": 68.65, "elapsed_time": "3:09:26", "remaining_time": "1:26:30", "throughput": 787.1, "total_tokens": 8946544} {"current_steps": 27465, "total_steps": 40000, "loss": 0.1558, "lr": 1.1169572737733441e-05, "epoch": 22.4756446991404, "percentage": 68.66, "elapsed_time": "3:09:28", "remaining_time": "1:26:28", "throughput": 787.12, "total_tokens": 8948160} {"current_steps": 27470, "total_steps": 40000, "loss": 0.1514, "lr": 1.1161395481511216e-05, "epoch": 22.479738027015966, "percentage": 68.67, "elapsed_time": "3:09:29", "remaining_time": "1:26:26", "throughput": 787.15, "total_tokens": 8949792} {"current_steps": 27475, "total_steps": 40000, "loss": 0.1216, "lr": 1.1153220359375722e-05, "epoch": 22.483831354891528, "percentage": 68.69, "elapsed_time": "3:09:31", "remaining_time": "1:26:23", "throughput": 787.18, "total_tokens": 8951536} {"current_steps": 27480, "total_steps": 40000, "loss": 0.3191, "lr": 1.114504737258765e-05, "epoch": 22.48792468276709, "percentage": 68.7, "elapsed_time": "3:09:33", "remaining_time": "1:26:21", "throughput": 787.2, "total_tokens": 8953152} {"current_steps": 27485, "total_steps": 40000, "loss": 0.2381, "lr": 1.1136876522407393e-05, "epoch": 22.492018010642653, "percentage": 68.71, "elapsed_time": "3:09:35", "remaining_time": "1:26:19", "throughput": 787.23, "total_tokens": 8954800} {"current_steps": 27490, "total_steps": 40000, "loss": 0.1118, "lr": 1.1128707810094985e-05, "epoch": 22.496111338518215, "percentage": 68.73, "elapsed_time": "3:09:36", "remaining_time": "1:26:17", "throughput": 787.25, "total_tokens": 8956432} {"current_steps": 27495, "total_steps": 40000, "loss": 0.2335, "lr": 1.1120541236910157e-05, "epoch": 22.500204666393778, "percentage": 68.74, "elapsed_time": "3:09:38", "remaining_time": "1:26:15", "throughput": 787.28, "total_tokens": 8958096} {"current_steps": 27500, "total_steps": 40000, "loss": 0.1999, "lr": 1.111237680411229e-05, "epoch": 22.50429799426934, "percentage": 68.75, "elapsed_time": "3:09:40", "remaining_time": "1:26:12", "throughput": 787.31, "total_tokens": 8959744} {"current_steps": 27505, "total_steps": 40000, "loss": 0.1711, "lr": 1.1104214512960433e-05, "epoch": 22.508391322144902, "percentage": 68.76, "elapsed_time": "3:09:41", "remaining_time": "1:26:10", "throughput": 787.33, "total_tokens": 8961376} {"current_steps": 27510, "total_steps": 40000, "loss": 0.2286, "lr": 1.1096054364713327e-05, "epoch": 22.51248465002047, "percentage": 68.77, "elapsed_time": "3:09:43", "remaining_time": "1:26:08", "throughput": 787.36, "total_tokens": 8963040} {"current_steps": 27515, "total_steps": 40000, "loss": 0.1165, "lr": 1.1087896360629371e-05, "epoch": 22.51657797789603, "percentage": 68.79, "elapsed_time": "3:09:45", "remaining_time": "1:26:06", "throughput": 787.38, "total_tokens": 8964656} {"current_steps": 27520, "total_steps": 40000, "loss": 0.1686, "lr": 1.107974050196662e-05, "epoch": 22.520671305771593, "percentage": 68.8, "elapsed_time": "3:09:47", "remaining_time": "1:26:03", "throughput": 787.4, "total_tokens": 8966240} {"current_steps": 27525, "total_steps": 40000, "loss": 0.1457, "lr": 1.1071586789982816e-05, "epoch": 22.524764633647155, "percentage": 68.81, "elapsed_time": "3:09:48", "remaining_time": "1:26:01", "throughput": 787.42, "total_tokens": 8967840} {"current_steps": 27530, "total_steps": 40000, "loss": 0.2649, "lr": 1.1063435225935373e-05, "epoch": 22.528857961522718, "percentage": 68.83, "elapsed_time": "3:09:50", "remaining_time": "1:25:59", "throughput": 787.45, "total_tokens": 8969456} {"current_steps": 27535, "total_steps": 40000, "loss": 0.2315, "lr": 1.1055285811081348e-05, "epoch": 22.53295128939828, "percentage": 68.84, "elapsed_time": "3:09:52", "remaining_time": "1:25:57", "throughput": 787.47, "total_tokens": 8971072} {"current_steps": 27540, "total_steps": 40000, "loss": 0.1932, "lr": 1.1047138546677499e-05, "epoch": 22.537044617273843, "percentage": 68.85, "elapsed_time": "3:09:54", "remaining_time": "1:25:55", "throughput": 787.5, "total_tokens": 8972752} {"current_steps": 27545, "total_steps": 40000, "loss": 0.3212, "lr": 1.1038993433980219e-05, "epoch": 22.541137945149405, "percentage": 68.86, "elapsed_time": "3:09:55", "remaining_time": "1:25:52", "throughput": 787.52, "total_tokens": 8974400} {"current_steps": 27550, "total_steps": 40000, "loss": 0.2091, "lr": 1.1030850474245597e-05, "epoch": 22.54523127302497, "percentage": 68.88, "elapsed_time": "3:09:57", "remaining_time": "1:25:50", "throughput": 787.54, "total_tokens": 8976016} {"current_steps": 27555, "total_steps": 40000, "loss": 0.2795, "lr": 1.102270966872939e-05, "epoch": 22.549324600900533, "percentage": 68.89, "elapsed_time": "3:09:59", "remaining_time": "1:25:48", "throughput": 787.57, "total_tokens": 8977632} {"current_steps": 27560, "total_steps": 40000, "loss": 0.1482, "lr": 1.1014571018687e-05, "epoch": 22.553417928776096, "percentage": 68.9, "elapsed_time": "3:10:00", "remaining_time": "1:25:46", "throughput": 787.59, "total_tokens": 8979216} {"current_steps": 27565, "total_steps": 40000, "loss": 0.2008, "lr": 1.1006434525373502e-05, "epoch": 22.557511256651658, "percentage": 68.91, "elapsed_time": "3:10:02", "remaining_time": "1:25:43", "throughput": 787.61, "total_tokens": 8980816} {"current_steps": 27570, "total_steps": 40000, "loss": 0.1723, "lr": 1.0998300190043664e-05, "epoch": 22.56160458452722, "percentage": 68.92, "elapsed_time": "3:10:04", "remaining_time": "1:25:41", "throughput": 787.63, "total_tokens": 8982432} {"current_steps": 27575, "total_steps": 40000, "loss": 0.1879, "lr": 1.0990168013951882e-05, "epoch": 22.565697912402783, "percentage": 68.94, "elapsed_time": "3:10:06", "remaining_time": "1:25:39", "throughput": 787.66, "total_tokens": 8984096} {"current_steps": 27580, "total_steps": 40000, "loss": 0.0959, "lr": 1.0982037998352263e-05, "epoch": 22.569791240278345, "percentage": 68.95, "elapsed_time": "3:10:07", "remaining_time": "1:25:37", "throughput": 787.69, "total_tokens": 8985824} {"current_steps": 27585, "total_steps": 40000, "loss": 0.1014, "lr": 1.0973910144498534e-05, "epoch": 22.573884568153908, "percentage": 68.96, "elapsed_time": "3:10:09", "remaining_time": "1:25:35", "throughput": 787.71, "total_tokens": 8987376} {"current_steps": 27590, "total_steps": 40000, "loss": 0.1375, "lr": 1.0965784453644123e-05, "epoch": 22.577977896029473, "percentage": 68.97, "elapsed_time": "3:10:11", "remaining_time": "1:25:32", "throughput": 787.73, "total_tokens": 8988976} {"current_steps": 27595, "total_steps": 40000, "loss": 0.1353, "lr": 1.0957660927042127e-05, "epoch": 22.582071223905036, "percentage": 68.99, "elapsed_time": "3:10:12", "remaining_time": "1:25:30", "throughput": 787.76, "total_tokens": 8990624} {"current_steps": 27600, "total_steps": 40000, "loss": 0.18, "lr": 1.094953956594527e-05, "epoch": 22.5861645517806, "percentage": 69.0, "elapsed_time": "3:10:14", "remaining_time": "1:25:28", "throughput": 787.78, "total_tokens": 8992240} {"current_steps": 27600, "total_steps": 40000, "eval_loss": 0.2123422920703888, "epoch": 22.5861645517806, "percentage": 69.0, "elapsed_time": "3:10:27", "remaining_time": "1:25:33", "throughput": 786.92, "total_tokens": 8992240} {"current_steps": 27605, "total_steps": 40000, "loss": 0.1374, "lr": 1.0941420371605981e-05, "epoch": 22.59025787965616, "percentage": 69.01, "elapsed_time": "3:10:30", "remaining_time": "1:25:32", "throughput": 786.84, "total_tokens": 8993888} {"current_steps": 27610, "total_steps": 40000, "loss": 0.2063, "lr": 1.0933303345276354e-05, "epoch": 22.594351207531723, "percentage": 69.03, "elapsed_time": "3:10:32", "remaining_time": "1:25:30", "throughput": 786.86, "total_tokens": 8995520} {"current_steps": 27615, "total_steps": 40000, "loss": 0.0952, "lr": 1.0925188488208112e-05, "epoch": 22.598444535407285, "percentage": 69.04, "elapsed_time": "3:10:33", "remaining_time": "1:25:27", "throughput": 786.88, "total_tokens": 8997104} {"current_steps": 27620, "total_steps": 40000, "loss": 0.1243, "lr": 1.0917075801652694e-05, "epoch": 22.602537863282848, "percentage": 69.05, "elapsed_time": "3:10:35", "remaining_time": "1:25:25", "throughput": 786.91, "total_tokens": 8998736} {"current_steps": 27625, "total_steps": 40000, "loss": 0.1377, "lr": 1.0908965286861151e-05, "epoch": 22.60663119115841, "percentage": 69.06, "elapsed_time": "3:10:37", "remaining_time": "1:25:23", "throughput": 786.93, "total_tokens": 9000368} {"current_steps": 27630, "total_steps": 40000, "loss": 0.0871, "lr": 1.090085694508425e-05, "epoch": 22.610724519033976, "percentage": 69.08, "elapsed_time": "3:10:38", "remaining_time": "1:25:21", "throughput": 786.96, "total_tokens": 9002064} {"current_steps": 27635, "total_steps": 40000, "loss": 0.1846, "lr": 1.089275077757238e-05, "epoch": 22.61481784690954, "percentage": 69.09, "elapsed_time": "3:10:40", "remaining_time": "1:25:19", "throughput": 786.99, "total_tokens": 9003760} {"current_steps": 27640, "total_steps": 40000, "loss": 0.1344, "lr": 1.0884646785575633e-05, "epoch": 22.6189111747851, "percentage": 69.1, "elapsed_time": "3:10:42", "remaining_time": "1:25:16", "throughput": 787.02, "total_tokens": 9005376} {"current_steps": 27645, "total_steps": 40000, "loss": 0.1673, "lr": 1.0876544970343728e-05, "epoch": 22.623004502660663, "percentage": 69.11, "elapsed_time": "3:10:44", "remaining_time": "1:25:14", "throughput": 787.04, "total_tokens": 9007040} {"current_steps": 27650, "total_steps": 40000, "loss": 0.1016, "lr": 1.0868445333126082e-05, "epoch": 22.627097830536226, "percentage": 69.12, "elapsed_time": "3:10:45", "remaining_time": "1:25:12", "throughput": 787.06, "total_tokens": 9008640} {"current_steps": 27655, "total_steps": 40000, "loss": 0.094, "lr": 1.0860347875171745e-05, "epoch": 22.631191158411788, "percentage": 69.14, "elapsed_time": "3:10:47", "remaining_time": "1:25:10", "throughput": 787.1, "total_tokens": 9010368} {"current_steps": 27660, "total_steps": 40000, "loss": 0.1902, "lr": 1.0852252597729465e-05, "epoch": 22.63528448628735, "percentage": 69.15, "elapsed_time": "3:10:49", "remaining_time": "1:25:07", "throughput": 787.12, "total_tokens": 9011984} {"current_steps": 27665, "total_steps": 40000, "loss": 0.1448, "lr": 1.0844159502047615e-05, "epoch": 22.639377814162913, "percentage": 69.16, "elapsed_time": "3:10:51", "remaining_time": "1:25:05", "throughput": 787.15, "total_tokens": 9013648} {"current_steps": 27670, "total_steps": 40000, "loss": 0.1346, "lr": 1.0836068589374265e-05, "epoch": 22.64347114203848, "percentage": 69.17, "elapsed_time": "3:10:52", "remaining_time": "1:25:03", "throughput": 787.17, "total_tokens": 9015280} {"current_steps": 27675, "total_steps": 40000, "loss": 0.1372, "lr": 1.0827979860957144e-05, "epoch": 22.64756446991404, "percentage": 69.19, "elapsed_time": "3:10:54", "remaining_time": "1:25:01", "throughput": 787.2, "total_tokens": 9016960} {"current_steps": 27680, "total_steps": 40000, "loss": 0.1738, "lr": 1.0819893318043615e-05, "epoch": 22.651657797789603, "percentage": 69.2, "elapsed_time": "3:10:56", "remaining_time": "1:24:59", "throughput": 787.23, "total_tokens": 9018608} {"current_steps": 27685, "total_steps": 40000, "loss": 0.1283, "lr": 1.0811808961880734e-05, "epoch": 22.655751125665166, "percentage": 69.21, "elapsed_time": "3:10:57", "remaining_time": "1:24:56", "throughput": 787.25, "total_tokens": 9020224} {"current_steps": 27690, "total_steps": 40000, "loss": 0.2567, "lr": 1.080372679371522e-05, "epoch": 22.659844453540728, "percentage": 69.23, "elapsed_time": "3:10:59", "remaining_time": "1:24:54", "throughput": 787.27, "total_tokens": 9021824} {"current_steps": 27695, "total_steps": 40000, "loss": 0.2155, "lr": 1.0795646814793428e-05, "epoch": 22.66393778141629, "percentage": 69.24, "elapsed_time": "3:11:01", "remaining_time": "1:24:52", "throughput": 787.29, "total_tokens": 9023408} {"current_steps": 27700, "total_steps": 40000, "loss": 0.2165, "lr": 1.078756902636141e-05, "epoch": 22.668031109291853, "percentage": 69.25, "elapsed_time": "3:11:03", "remaining_time": "1:24:50", "throughput": 787.31, "total_tokens": 9025008} {"current_steps": 27705, "total_steps": 40000, "loss": 0.2273, "lr": 1.077949342966485e-05, "epoch": 22.67212443716742, "percentage": 69.26, "elapsed_time": "3:11:04", "remaining_time": "1:24:47", "throughput": 787.33, "total_tokens": 9026624} {"current_steps": 27710, "total_steps": 40000, "loss": 0.1291, "lr": 1.0771420025949103e-05, "epoch": 22.67621776504298, "percentage": 69.27, "elapsed_time": "3:11:06", "remaining_time": "1:24:45", "throughput": 787.35, "total_tokens": 9028224} {"current_steps": 27715, "total_steps": 40000, "loss": 0.1239, "lr": 1.0763348816459204e-05, "epoch": 22.680311092918544, "percentage": 69.29, "elapsed_time": "3:11:08", "remaining_time": "1:24:43", "throughput": 787.38, "total_tokens": 9029872} {"current_steps": 27720, "total_steps": 40000, "loss": 0.1825, "lr": 1.0755279802439816e-05, "epoch": 22.684404420794106, "percentage": 69.3, "elapsed_time": "3:11:09", "remaining_time": "1:24:41", "throughput": 787.4, "total_tokens": 9031504} {"current_steps": 27725, "total_steps": 40000, "loss": 0.1512, "lr": 1.0747212985135293e-05, "epoch": 22.68849774866967, "percentage": 69.31, "elapsed_time": "3:11:11", "remaining_time": "1:24:38", "throughput": 787.43, "total_tokens": 9033104} {"current_steps": 27730, "total_steps": 40000, "loss": 0.1873, "lr": 1.073914836578965e-05, "epoch": 22.69259107654523, "percentage": 69.33, "elapsed_time": "3:11:13", "remaining_time": "1:24:36", "throughput": 787.45, "total_tokens": 9034688} {"current_steps": 27735, "total_steps": 40000, "loss": 0.2442, "lr": 1.0731085945646529e-05, "epoch": 22.696684404420793, "percentage": 69.34, "elapsed_time": "3:11:15", "remaining_time": "1:24:34", "throughput": 787.46, "total_tokens": 9036272} {"current_steps": 27740, "total_steps": 40000, "loss": 0.1909, "lr": 1.0723025725949285e-05, "epoch": 22.700777732296356, "percentage": 69.35, "elapsed_time": "3:11:16", "remaining_time": "1:24:32", "throughput": 787.49, "total_tokens": 9037920} {"current_steps": 27745, "total_steps": 40000, "loss": 0.2097, "lr": 1.0714967707940875e-05, "epoch": 22.70487106017192, "percentage": 69.36, "elapsed_time": "3:11:18", "remaining_time": "1:24:30", "throughput": 787.52, "total_tokens": 9039568} {"current_steps": 27750, "total_steps": 40000, "loss": 0.1528, "lr": 1.0706911892863963e-05, "epoch": 22.708964388047484, "percentage": 69.38, "elapsed_time": "3:11:20", "remaining_time": "1:24:27", "throughput": 787.54, "total_tokens": 9041168} {"current_steps": 27755, "total_steps": 40000, "loss": 0.1643, "lr": 1.0698858281960866e-05, "epoch": 22.713057715923046, "percentage": 69.39, "elapsed_time": "3:11:22", "remaining_time": "1:24:25", "throughput": 787.57, "total_tokens": 9042912} {"current_steps": 27760, "total_steps": 40000, "loss": 0.1522, "lr": 1.069080687647353e-05, "epoch": 22.71715104379861, "percentage": 69.4, "elapsed_time": "3:11:23", "remaining_time": "1:24:23", "throughput": 787.6, "total_tokens": 9044544} {"current_steps": 27765, "total_steps": 40000, "loss": 0.208, "lr": 1.0682757677643596e-05, "epoch": 22.72124437167417, "percentage": 69.41, "elapsed_time": "3:11:25", "remaining_time": "1:24:21", "throughput": 787.62, "total_tokens": 9046192} {"current_steps": 27770, "total_steps": 40000, "loss": 0.1693, "lr": 1.0674710686712359e-05, "epoch": 22.725337699549733, "percentage": 69.42, "elapsed_time": "3:11:27", "remaining_time": "1:24:18", "throughput": 787.65, "total_tokens": 9047840} {"current_steps": 27775, "total_steps": 40000, "loss": 0.3304, "lr": 1.0666665904920756e-05, "epoch": 22.729431027425296, "percentage": 69.44, "elapsed_time": "3:11:28", "remaining_time": "1:24:16", "throughput": 787.68, "total_tokens": 9049504} {"current_steps": 27780, "total_steps": 40000, "loss": 0.1919, "lr": 1.0658623333509385e-05, "epoch": 22.733524355300858, "percentage": 69.45, "elapsed_time": "3:11:30", "remaining_time": "1:24:14", "throughput": 787.7, "total_tokens": 9051152} {"current_steps": 27785, "total_steps": 40000, "loss": 0.1763, "lr": 1.0650582973718532e-05, "epoch": 22.737617683176424, "percentage": 69.46, "elapsed_time": "3:11:32", "remaining_time": "1:24:12", "throughput": 787.72, "total_tokens": 9052752} {"current_steps": 27790, "total_steps": 40000, "loss": 0.1343, "lr": 1.0642544826788098e-05, "epoch": 22.741711011051986, "percentage": 69.47, "elapsed_time": "3:11:34", "remaining_time": "1:24:10", "throughput": 787.75, "total_tokens": 9054384} {"current_steps": 27795, "total_steps": 40000, "loss": 0.115, "lr": 1.063450889395769e-05, "epoch": 22.74580433892755, "percentage": 69.49, "elapsed_time": "3:11:35", "remaining_time": "1:24:07", "throughput": 787.76, "total_tokens": 9055952} {"current_steps": 27800, "total_steps": 40000, "loss": 0.1666, "lr": 1.062647517646653e-05, "epoch": 22.74989766680311, "percentage": 69.5, "elapsed_time": "3:11:37", "remaining_time": "1:24:05", "throughput": 787.79, "total_tokens": 9057600} {"current_steps": 27800, "total_steps": 40000, "eval_loss": 0.2116551399230957, "epoch": 22.74989766680311, "percentage": 69.5, "elapsed_time": "3:11:49", "remaining_time": "1:24:11", "throughput": 786.94, "total_tokens": 9057600} {"current_steps": 27805, "total_steps": 40000, "loss": 0.1835, "lr": 1.0618443675553527e-05, "epoch": 22.753990994678674, "percentage": 69.51, "elapsed_time": "3:11:53", "remaining_time": "1:24:09", "throughput": 786.85, "total_tokens": 9059216} {"current_steps": 27810, "total_steps": 40000, "loss": 0.1516, "lr": 1.0610414392457247e-05, "epoch": 22.758084322554236, "percentage": 69.53, "elapsed_time": "3:11:54", "remaining_time": "1:24:07", "throughput": 786.87, "total_tokens": 9060800} {"current_steps": 27815, "total_steps": 40000, "loss": 0.1763, "lr": 1.0602387328415888e-05, "epoch": 22.7621776504298, "percentage": 69.54, "elapsed_time": "3:11:56", "remaining_time": "1:24:05", "throughput": 786.9, "total_tokens": 9062480} {"current_steps": 27820, "total_steps": 40000, "loss": 0.1389, "lr": 1.0594362484667347e-05, "epoch": 22.76627097830536, "percentage": 69.55, "elapsed_time": "3:11:58", "remaining_time": "1:24:02", "throughput": 786.92, "total_tokens": 9064064} {"current_steps": 27825, "total_steps": 40000, "loss": 0.1374, "lr": 1.0586339862449132e-05, "epoch": 22.770364306180927, "percentage": 69.56, "elapsed_time": "3:12:00", "remaining_time": "1:24:00", "throughput": 786.95, "total_tokens": 9065712} {"current_steps": 27830, "total_steps": 40000, "loss": 0.1123, "lr": 1.0578319462998445e-05, "epoch": 22.77445763405649, "percentage": 69.58, "elapsed_time": "3:12:01", "remaining_time": "1:23:58", "throughput": 786.98, "total_tokens": 9067456} {"current_steps": 27835, "total_steps": 40000, "loss": 0.1448, "lr": 1.057030128755214e-05, "epoch": 22.77855096193205, "percentage": 69.59, "elapsed_time": "3:12:03", "remaining_time": "1:23:56", "throughput": 787.0, "total_tokens": 9069056} {"current_steps": 27840, "total_steps": 40000, "loss": 0.2638, "lr": 1.0562285337346703e-05, "epoch": 22.782644289807614, "percentage": 69.6, "elapsed_time": "3:12:05", "remaining_time": "1:23:54", "throughput": 787.03, "total_tokens": 9070672} {"current_steps": 27845, "total_steps": 40000, "loss": 0.2063, "lr": 1.0554271613618308e-05, "epoch": 22.786737617683176, "percentage": 69.61, "elapsed_time": "3:12:06", "remaining_time": "1:23:51", "throughput": 787.05, "total_tokens": 9072320} {"current_steps": 27850, "total_steps": 40000, "loss": 0.1512, "lr": 1.054626011760276e-05, "epoch": 22.79083094555874, "percentage": 69.62, "elapsed_time": "3:12:08", "remaining_time": "1:23:49", "throughput": 787.08, "total_tokens": 9074000} {"current_steps": 27855, "total_steps": 40000, "loss": 0.1127, "lr": 1.0538250850535549e-05, "epoch": 22.7949242734343, "percentage": 69.64, "elapsed_time": "3:12:10", "remaining_time": "1:23:47", "throughput": 787.1, "total_tokens": 9075632} {"current_steps": 27860, "total_steps": 40000, "loss": 0.2365, "lr": 1.0530243813651794e-05, "epoch": 22.799017601309863, "percentage": 69.65, "elapsed_time": "3:12:12", "remaining_time": "1:23:45", "throughput": 787.13, "total_tokens": 9077296} {"current_steps": 27865, "total_steps": 40000, "loss": 0.1956, "lr": 1.0522239008186271e-05, "epoch": 22.80311092918543, "percentage": 69.66, "elapsed_time": "3:12:13", "remaining_time": "1:23:42", "throughput": 787.16, "total_tokens": 9078960} {"current_steps": 27870, "total_steps": 40000, "loss": 0.1895, "lr": 1.0514236435373434e-05, "epoch": 22.80720425706099, "percentage": 69.67, "elapsed_time": "3:12:15", "remaining_time": "1:23:40", "throughput": 787.18, "total_tokens": 9080544} {"current_steps": 27875, "total_steps": 40000, "loss": 0.228, "lr": 1.0506236096447386e-05, "epoch": 22.811297584936554, "percentage": 69.69, "elapsed_time": "3:12:17", "remaining_time": "1:23:38", "throughput": 787.2, "total_tokens": 9082192} {"current_steps": 27880, "total_steps": 40000, "loss": 0.2341, "lr": 1.049823799264186e-05, "epoch": 22.815390912812116, "percentage": 69.7, "elapsed_time": "3:12:19", "remaining_time": "1:23:36", "throughput": 787.23, "total_tokens": 9083840} {"current_steps": 27885, "total_steps": 40000, "loss": 0.1328, "lr": 1.049024212519028e-05, "epoch": 22.81948424068768, "percentage": 69.71, "elapsed_time": "3:12:20", "remaining_time": "1:23:34", "throughput": 787.25, "total_tokens": 9085408} {"current_steps": 27890, "total_steps": 40000, "loss": 0.1211, "lr": 1.0482248495325713e-05, "epoch": 22.82357756856324, "percentage": 69.73, "elapsed_time": "3:12:22", "remaining_time": "1:23:31", "throughput": 787.27, "total_tokens": 9087072} {"current_steps": 27895, "total_steps": 40000, "loss": 0.19, "lr": 1.047425710428086e-05, "epoch": 22.827670896438804, "percentage": 69.74, "elapsed_time": "3:12:24", "remaining_time": "1:23:29", "throughput": 787.3, "total_tokens": 9088768} {"current_steps": 27900, "total_steps": 40000, "loss": 0.1975, "lr": 1.0466267953288114e-05, "epoch": 22.831764224314366, "percentage": 69.75, "elapsed_time": "3:12:25", "remaining_time": "1:23:27", "throughput": 787.33, "total_tokens": 9090464} {"current_steps": 27905, "total_steps": 40000, "loss": 0.161, "lr": 1.0458281043579482e-05, "epoch": 22.835857552189932, "percentage": 69.76, "elapsed_time": "3:12:27", "remaining_time": "1:23:25", "throughput": 787.36, "total_tokens": 9092096} {"current_steps": 27910, "total_steps": 40000, "loss": 0.1513, "lr": 1.0450296376386657e-05, "epoch": 22.839950880065494, "percentage": 69.77, "elapsed_time": "3:12:29", "remaining_time": "1:23:22", "throughput": 787.38, "total_tokens": 9093664} {"current_steps": 27915, "total_steps": 40000, "loss": 0.1418, "lr": 1.044231395294098e-05, "epoch": 22.844044207941057, "percentage": 69.79, "elapsed_time": "3:12:31", "remaining_time": "1:23:20", "throughput": 787.4, "total_tokens": 9095248} {"current_steps": 27920, "total_steps": 40000, "loss": 0.1255, "lr": 1.0434333774473435e-05, "epoch": 22.84813753581662, "percentage": 69.8, "elapsed_time": "3:12:32", "remaining_time": "1:23:18", "throughput": 787.42, "total_tokens": 9096848} {"current_steps": 27925, "total_steps": 40000, "loss": 0.1468, "lr": 1.0426355842214657e-05, "epoch": 22.85223086369218, "percentage": 69.81, "elapsed_time": "3:12:34", "remaining_time": "1:23:16", "throughput": 787.44, "total_tokens": 9098464} {"current_steps": 27930, "total_steps": 40000, "loss": 0.1586, "lr": 1.0418380157394963e-05, "epoch": 22.856324191567744, "percentage": 69.83, "elapsed_time": "3:12:36", "remaining_time": "1:23:14", "throughput": 787.47, "total_tokens": 9100144} {"current_steps": 27935, "total_steps": 40000, "loss": 0.2624, "lr": 1.0410406721244281e-05, "epoch": 22.860417519443306, "percentage": 69.84, "elapsed_time": "3:12:37", "remaining_time": "1:23:11", "throughput": 787.49, "total_tokens": 9101792} {"current_steps": 27940, "total_steps": 40000, "loss": 0.1304, "lr": 1.0402435534992238e-05, "epoch": 22.86451084731887, "percentage": 69.85, "elapsed_time": "3:12:39", "remaining_time": "1:23:09", "throughput": 787.52, "total_tokens": 9103440} {"current_steps": 27945, "total_steps": 40000, "loss": 0.1609, "lr": 1.0394466599868071e-05, "epoch": 22.868604175194434, "percentage": 69.86, "elapsed_time": "3:12:41", "remaining_time": "1:23:07", "throughput": 787.54, "total_tokens": 9105056} {"current_steps": 27950, "total_steps": 40000, "loss": 0.1439, "lr": 1.0386499917100697e-05, "epoch": 22.872697503069997, "percentage": 69.88, "elapsed_time": "3:12:43", "remaining_time": "1:23:05", "throughput": 787.57, "total_tokens": 9106672} {"current_steps": 27955, "total_steps": 40000, "loss": 0.1782, "lr": 1.0378535487918692e-05, "epoch": 22.87679083094556, "percentage": 69.89, "elapsed_time": "3:12:44", "remaining_time": "1:23:02", "throughput": 787.59, "total_tokens": 9108336} {"current_steps": 27960, "total_steps": 40000, "loss": 0.2658, "lr": 1.037057331355025e-05, "epoch": 22.88088415882112, "percentage": 69.9, "elapsed_time": "3:12:46", "remaining_time": "1:23:00", "throughput": 787.62, "total_tokens": 9110000} {"current_steps": 27965, "total_steps": 40000, "loss": 0.1457, "lr": 1.0362613395223247e-05, "epoch": 22.884977486696684, "percentage": 69.91, "elapsed_time": "3:12:48", "remaining_time": "1:22:58", "throughput": 787.64, "total_tokens": 9111616} {"current_steps": 27970, "total_steps": 40000, "loss": 0.2225, "lr": 1.0354655734165212e-05, "epoch": 22.889070814572246, "percentage": 69.92, "elapsed_time": "3:12:49", "remaining_time": "1:22:56", "throughput": 787.66, "total_tokens": 9113248} {"current_steps": 27975, "total_steps": 40000, "loss": 0.1503, "lr": 1.03467003316033e-05, "epoch": 22.89316414244781, "percentage": 69.94, "elapsed_time": "3:12:51", "remaining_time": "1:22:54", "throughput": 787.69, "total_tokens": 9114912} {"current_steps": 27980, "total_steps": 40000, "loss": 0.1816, "lr": 1.033874718876435e-05, "epoch": 22.897257470323375, "percentage": 69.95, "elapsed_time": "3:12:53", "remaining_time": "1:22:51", "throughput": 787.72, "total_tokens": 9116576} {"current_steps": 27985, "total_steps": 40000, "loss": 0.1772, "lr": 1.0330796306874818e-05, "epoch": 22.901350798198937, "percentage": 69.96, "elapsed_time": "3:12:55", "remaining_time": "1:22:49", "throughput": 787.74, "total_tokens": 9118208} {"current_steps": 27990, "total_steps": 40000, "loss": 0.1852, "lr": 1.032284768716085e-05, "epoch": 22.9054441260745, "percentage": 69.97, "elapsed_time": "3:12:56", "remaining_time": "1:22:47", "throughput": 787.76, "total_tokens": 9119808} {"current_steps": 27995, "total_steps": 40000, "loss": 0.2163, "lr": 1.0314901330848206e-05, "epoch": 22.909537453950062, "percentage": 69.99, "elapsed_time": "3:12:58", "remaining_time": "1:22:45", "throughput": 787.79, "total_tokens": 9121424} {"current_steps": 28000, "total_steps": 40000, "loss": 0.1416, "lr": 1.030695723916233e-05, "epoch": 22.913630781825624, "percentage": 70.0, "elapsed_time": "3:13:00", "remaining_time": "1:22:42", "throughput": 787.8, "total_tokens": 9122992} {"current_steps": 28000, "total_steps": 40000, "eval_loss": 0.21159517765045166, "epoch": 22.913630781825624, "percentage": 70.0, "elapsed_time": "3:13:12", "remaining_time": "1:22:48", "throughput": 786.96, "total_tokens": 9122992} {"current_steps": 28005, "total_steps": 40000, "loss": 0.1197, "lr": 1.0299015413328289e-05, "epoch": 22.917724109701187, "percentage": 70.01, "elapsed_time": "3:13:16", "remaining_time": "1:22:46", "throughput": 786.88, "total_tokens": 9124768} {"current_steps": 28010, "total_steps": 40000, "loss": 0.2207, "lr": 1.0291075854570809e-05, "epoch": 22.92181743757675, "percentage": 70.03, "elapsed_time": "3:13:17", "remaining_time": "1:22:44", "throughput": 786.91, "total_tokens": 9126416} {"current_steps": 28015, "total_steps": 40000, "loss": 0.1715, "lr": 1.0283138564114275e-05, "epoch": 22.92591076545231, "percentage": 70.04, "elapsed_time": "3:13:19", "remaining_time": "1:22:42", "throughput": 786.93, "total_tokens": 9128048} {"current_steps": 28020, "total_steps": 40000, "loss": 0.1715, "lr": 1.027520354318273e-05, "epoch": 22.930004093327877, "percentage": 70.05, "elapsed_time": "3:13:21", "remaining_time": "1:22:40", "throughput": 786.95, "total_tokens": 9129632} {"current_steps": 28025, "total_steps": 40000, "loss": 0.2058, "lr": 1.0267270792999828e-05, "epoch": 22.93409742120344, "percentage": 70.06, "elapsed_time": "3:13:22", "remaining_time": "1:22:37", "throughput": 786.97, "total_tokens": 9131248} {"current_steps": 28030, "total_steps": 40000, "loss": 0.3496, "lr": 1.0259340314788919e-05, "epoch": 22.938190749079002, "percentage": 70.08, "elapsed_time": "3:13:24", "remaining_time": "1:22:35", "throughput": 787.0, "total_tokens": 9132896} {"current_steps": 28035, "total_steps": 40000, "loss": 0.1403, "lr": 1.0251412109772979e-05, "epoch": 22.942284076954564, "percentage": 70.09, "elapsed_time": "3:13:26", "remaining_time": "1:22:33", "throughput": 787.02, "total_tokens": 9134496} {"current_steps": 28040, "total_steps": 40000, "loss": 0.207, "lr": 1.0243486179174627e-05, "epoch": 22.946377404830127, "percentage": 70.1, "elapsed_time": "3:13:28", "remaining_time": "1:22:31", "throughput": 787.04, "total_tokens": 9136096} {"current_steps": 28045, "total_steps": 40000, "loss": 0.1821, "lr": 1.0235562524216158e-05, "epoch": 22.95047073270569, "percentage": 70.11, "elapsed_time": "3:13:29", "remaining_time": "1:22:29", "throughput": 787.07, "total_tokens": 9137776} {"current_steps": 28050, "total_steps": 40000, "loss": 0.1178, "lr": 1.022764114611948e-05, "epoch": 22.95456406058125, "percentage": 70.12, "elapsed_time": "3:13:31", "remaining_time": "1:22:26", "throughput": 787.09, "total_tokens": 9139408} {"current_steps": 28055, "total_steps": 40000, "loss": 0.154, "lr": 1.0219722046106178e-05, "epoch": 22.958657388456814, "percentage": 70.14, "elapsed_time": "3:13:33", "remaining_time": "1:22:24", "throughput": 787.12, "total_tokens": 9141008} {"current_steps": 28060, "total_steps": 40000, "loss": 0.2416, "lr": 1.0211805225397486e-05, "epoch": 22.96275071633238, "percentage": 70.15, "elapsed_time": "3:13:35", "remaining_time": "1:22:22", "throughput": 787.14, "total_tokens": 9142640} {"current_steps": 28065, "total_steps": 40000, "loss": 0.2485, "lr": 1.020389068521426e-05, "epoch": 22.966844044207942, "percentage": 70.16, "elapsed_time": "3:13:36", "remaining_time": "1:22:20", "throughput": 787.16, "total_tokens": 9144256} {"current_steps": 28070, "total_steps": 40000, "loss": 0.1593, "lr": 1.0195978426777039e-05, "epoch": 22.970937372083505, "percentage": 70.17, "elapsed_time": "3:13:38", "remaining_time": "1:22:17", "throughput": 787.18, "total_tokens": 9145872} {"current_steps": 28075, "total_steps": 40000, "loss": 0.1534, "lr": 1.0188068451305982e-05, "epoch": 22.975030699959067, "percentage": 70.19, "elapsed_time": "3:13:40", "remaining_time": "1:22:15", "throughput": 787.21, "total_tokens": 9147504} {"current_steps": 28080, "total_steps": 40000, "loss": 0.2156, "lr": 1.0180160760020902e-05, "epoch": 22.97912402783463, "percentage": 70.2, "elapsed_time": "3:13:42", "remaining_time": "1:22:13", "throughput": 787.22, "total_tokens": 9149200} {"current_steps": 28085, "total_steps": 40000, "loss": 0.1803, "lr": 1.0172255354141278e-05, "epoch": 22.98321735571019, "percentage": 70.21, "elapsed_time": "3:13:43", "remaining_time": "1:22:11", "throughput": 787.24, "total_tokens": 9150832} {"current_steps": 28090, "total_steps": 40000, "loss": 0.2244, "lr": 1.0164352234886205e-05, "epoch": 22.987310683585754, "percentage": 70.23, "elapsed_time": "3:13:45", "remaining_time": "1:22:09", "throughput": 787.27, "total_tokens": 9152496} {"current_steps": 28095, "total_steps": 40000, "loss": 0.184, "lr": 1.0156451403474454e-05, "epoch": 22.991404011461317, "percentage": 70.24, "elapsed_time": "3:13:47", "remaining_time": "1:22:06", "throughput": 787.3, "total_tokens": 9154144} {"current_steps": 28100, "total_steps": 40000, "loss": 0.1998, "lr": 1.0148552861124443e-05, "epoch": 22.995497339336882, "percentage": 70.25, "elapsed_time": "3:13:49", "remaining_time": "1:22:04", "throughput": 787.32, "total_tokens": 9155824} {"current_steps": 28105, "total_steps": 40000, "loss": 0.1234, "lr": 1.0140656609054205e-05, "epoch": 22.999590667212445, "percentage": 70.26, "elapsed_time": "3:13:50", "remaining_time": "1:22:02", "throughput": 787.35, "total_tokens": 9157424} {"current_steps": 28110, "total_steps": 40000, "loss": 0.1527, "lr": 1.0132762648481455e-05, "epoch": 23.003274662300452, "percentage": 70.28, "elapsed_time": "3:13:52", "remaining_time": "1:22:00", "throughput": 787.33, "total_tokens": 9158792} {"current_steps": 28115, "total_steps": 40000, "loss": 0.1452, "lr": 1.0124870980623543e-05, "epoch": 23.007367990176014, "percentage": 70.29, "elapsed_time": "3:13:54", "remaining_time": "1:21:58", "throughput": 787.36, "total_tokens": 9160488} {"current_steps": 28120, "total_steps": 40000, "loss": 0.1348, "lr": 1.0116981606697453e-05, "epoch": 23.011461318051577, "percentage": 70.3, "elapsed_time": "3:13:56", "remaining_time": "1:21:55", "throughput": 787.39, "total_tokens": 9162120} {"current_steps": 28125, "total_steps": 40000, "loss": 0.1428, "lr": 1.0109094527919838e-05, "epoch": 23.01555464592714, "percentage": 70.31, "elapsed_time": "3:13:57", "remaining_time": "1:21:53", "throughput": 787.41, "total_tokens": 9163688} {"current_steps": 28130, "total_steps": 40000, "loss": 0.0941, "lr": 1.010120974550697e-05, "epoch": 23.0196479738027, "percentage": 70.33, "elapsed_time": "3:13:59", "remaining_time": "1:21:51", "throughput": 787.43, "total_tokens": 9165288} {"current_steps": 28135, "total_steps": 40000, "loss": 0.2117, "lr": 1.0093327260674795e-05, "epoch": 23.023741301678264, "percentage": 70.34, "elapsed_time": "3:14:01", "remaining_time": "1:21:49", "throughput": 787.45, "total_tokens": 9166904} {"current_steps": 28140, "total_steps": 40000, "loss": 0.1513, "lr": 1.0085447074638878e-05, "epoch": 23.027834629553826, "percentage": 70.35, "elapsed_time": "3:14:02", "remaining_time": "1:21:47", "throughput": 787.48, "total_tokens": 9168616} {"current_steps": 28145, "total_steps": 40000, "loss": 0.1324, "lr": 1.0077569188614461e-05, "epoch": 23.03192795742939, "percentage": 70.36, "elapsed_time": "3:14:04", "remaining_time": "1:21:44", "throughput": 787.5, "total_tokens": 9170216} {"current_steps": 28150, "total_steps": 40000, "loss": 0.1799, "lr": 1.0069693603816393e-05, "epoch": 23.036021285304955, "percentage": 70.38, "elapsed_time": "3:14:06", "remaining_time": "1:21:42", "throughput": 787.53, "total_tokens": 9171880} {"current_steps": 28155, "total_steps": 40000, "loss": 0.164, "lr": 1.0061820321459204e-05, "epoch": 23.040114613180517, "percentage": 70.39, "elapsed_time": "3:14:08", "remaining_time": "1:21:40", "throughput": 787.56, "total_tokens": 9173544} {"current_steps": 28160, "total_steps": 40000, "loss": 0.1561, "lr": 1.0053949342757038e-05, "epoch": 23.04420794105608, "percentage": 70.4, "elapsed_time": "3:14:09", "remaining_time": "1:21:38", "throughput": 787.57, "total_tokens": 9175112} {"current_steps": 28165, "total_steps": 40000, "loss": 0.1635, "lr": 1.0046080668923717e-05, "epoch": 23.04830126893164, "percentage": 70.41, "elapsed_time": "3:14:11", "remaining_time": "1:21:36", "throughput": 787.6, "total_tokens": 9176760} {"current_steps": 28170, "total_steps": 40000, "loss": 0.1632, "lr": 1.003821430117267e-05, "epoch": 23.052394596807204, "percentage": 70.43, "elapsed_time": "3:14:13", "remaining_time": "1:21:33", "throughput": 787.62, "total_tokens": 9178392} {"current_steps": 28175, "total_steps": 40000, "loss": 0.1639, "lr": 1.0030350240716999e-05, "epoch": 23.056487924682767, "percentage": 70.44, "elapsed_time": "3:14:15", "remaining_time": "1:21:31", "throughput": 787.65, "total_tokens": 9180040} {"current_steps": 28180, "total_steps": 40000, "loss": 0.2111, "lr": 1.0022488488769449e-05, "epoch": 23.06058125255833, "percentage": 70.45, "elapsed_time": "3:14:16", "remaining_time": "1:21:29", "throughput": 787.67, "total_tokens": 9181640} {"current_steps": 28185, "total_steps": 40000, "loss": 0.24, "lr": 1.0014629046542387e-05, "epoch": 23.06467458043389, "percentage": 70.46, "elapsed_time": "3:14:18", "remaining_time": "1:21:27", "throughput": 787.69, "total_tokens": 9183224} {"current_steps": 28190, "total_steps": 40000, "loss": 0.1424, "lr": 1.0006771915247842e-05, "epoch": 23.068767908309457, "percentage": 70.47, "elapsed_time": "3:14:20", "remaining_time": "1:21:24", "throughput": 787.71, "total_tokens": 9184808} {"current_steps": 28195, "total_steps": 40000, "loss": 0.1415, "lr": 9.998917096097495e-06, "epoch": 23.07286123618502, "percentage": 70.49, "elapsed_time": "3:14:21", "remaining_time": "1:21:22", "throughput": 787.73, "total_tokens": 9186408} {"current_steps": 28200, "total_steps": 40000, "loss": 0.1501, "lr": 9.991064590302638e-06, "epoch": 23.076954564060582, "percentage": 70.5, "elapsed_time": "3:14:23", "remaining_time": "1:21:20", "throughput": 787.75, "total_tokens": 9187992} {"current_steps": 28200, "total_steps": 40000, "eval_loss": 0.2138190120458603, "epoch": 23.076954564060582, "percentage": 70.5, "elapsed_time": "3:14:36", "remaining_time": "1:21:25", "throughput": 786.91, "total_tokens": 9187992} {"current_steps": 28205, "total_steps": 40000, "loss": 0.1286, "lr": 9.983214399074241e-06, "epoch": 23.081047891936144, "percentage": 70.51, "elapsed_time": "3:14:39", "remaining_time": "1:21:24", "throughput": 786.8, "total_tokens": 9189544} {"current_steps": 28210, "total_steps": 40000, "loss": 0.1659, "lr": 9.975366523622893e-06, "epoch": 23.085141219811707, "percentage": 70.53, "elapsed_time": "3:14:41", "remaining_time": "1:21:22", "throughput": 786.82, "total_tokens": 9191176} {"current_steps": 28215, "total_steps": 40000, "loss": 0.1452, "lr": 9.967520965158841e-06, "epoch": 23.08923454768727, "percentage": 70.54, "elapsed_time": "3:14:43", "remaining_time": "1:21:19", "throughput": 786.85, "total_tokens": 9192824} {"current_steps": 28220, "total_steps": 40000, "loss": 0.1763, "lr": 9.95967772489197e-06, "epoch": 23.09332787556283, "percentage": 70.55, "elapsed_time": "3:14:44", "remaining_time": "1:21:17", "throughput": 786.87, "total_tokens": 9194456} {"current_steps": 28225, "total_steps": 40000, "loss": 0.1836, "lr": 9.951836804031794e-06, "epoch": 23.097421203438394, "percentage": 70.56, "elapsed_time": "3:14:46", "remaining_time": "1:21:15", "throughput": 786.89, "total_tokens": 9196024} {"current_steps": 28230, "total_steps": 40000, "loss": 0.1304, "lr": 9.943998203787489e-06, "epoch": 23.10151453131396, "percentage": 70.58, "elapsed_time": "3:14:48", "remaining_time": "1:21:13", "throughput": 786.92, "total_tokens": 9197672} {"current_steps": 28235, "total_steps": 40000, "loss": 0.1294, "lr": 9.936161925367874e-06, "epoch": 23.105607859189522, "percentage": 70.59, "elapsed_time": "3:14:49", "remaining_time": "1:21:10", "throughput": 786.94, "total_tokens": 9199288} {"current_steps": 28240, "total_steps": 40000, "loss": 0.2384, "lr": 9.928327969981386e-06, "epoch": 23.109701187065085, "percentage": 70.6, "elapsed_time": "3:14:51", "remaining_time": "1:21:08", "throughput": 786.96, "total_tokens": 9200888} {"current_steps": 28245, "total_steps": 40000, "loss": 0.1299, "lr": 9.920496338836135e-06, "epoch": 23.113794514940647, "percentage": 70.61, "elapsed_time": "3:14:53", "remaining_time": "1:21:06", "throughput": 786.98, "total_tokens": 9202520} {"current_steps": 28250, "total_steps": 40000, "loss": 0.2183, "lr": 9.912667033139844e-06, "epoch": 23.11788784281621, "percentage": 70.62, "elapsed_time": "3:14:55", "remaining_time": "1:21:04", "throughput": 787.0, "total_tokens": 9204088} {"current_steps": 28255, "total_steps": 40000, "loss": 0.1091, "lr": 9.904840054099893e-06, "epoch": 23.12198117069177, "percentage": 70.64, "elapsed_time": "3:14:56", "remaining_time": "1:21:02", "throughput": 787.02, "total_tokens": 9205688} {"current_steps": 28260, "total_steps": 40000, "loss": 0.12, "lr": 9.897015402923312e-06, "epoch": 23.126074498567334, "percentage": 70.65, "elapsed_time": "3:14:58", "remaining_time": "1:20:59", "throughput": 787.05, "total_tokens": 9207304} {"current_steps": 28265, "total_steps": 40000, "loss": 0.1167, "lr": 9.889193080816744e-06, "epoch": 23.130167826442896, "percentage": 70.66, "elapsed_time": "3:15:00", "remaining_time": "1:20:57", "throughput": 787.07, "total_tokens": 9208888} {"current_steps": 28270, "total_steps": 40000, "loss": 0.1882, "lr": 9.881373088986498e-06, "epoch": 23.134261154318462, "percentage": 70.67, "elapsed_time": "3:15:01", "remaining_time": "1:20:55", "throughput": 787.09, "total_tokens": 9210568} {"current_steps": 28275, "total_steps": 40000, "loss": 0.0856, "lr": 9.873555428638523e-06, "epoch": 23.138354482194025, "percentage": 70.69, "elapsed_time": "3:15:03", "remaining_time": "1:20:53", "throughput": 787.12, "total_tokens": 9212168} {"current_steps": 28280, "total_steps": 40000, "loss": 0.1262, "lr": 9.865740100978383e-06, "epoch": 23.142447810069587, "percentage": 70.7, "elapsed_time": "3:15:05", "remaining_time": "1:20:51", "throughput": 787.14, "total_tokens": 9213784} {"current_steps": 28285, "total_steps": 40000, "loss": 0.1793, "lr": 9.857927107211315e-06, "epoch": 23.14654113794515, "percentage": 70.71, "elapsed_time": "3:15:07", "remaining_time": "1:20:48", "throughput": 787.16, "total_tokens": 9215400} {"current_steps": 28290, "total_steps": 40000, "loss": 0.1558, "lr": 9.850116448542177e-06, "epoch": 23.150634465820712, "percentage": 70.73, "elapsed_time": "3:15:08", "remaining_time": "1:20:46", "throughput": 787.19, "total_tokens": 9217080} {"current_steps": 28295, "total_steps": 40000, "loss": 0.1365, "lr": 9.842308126175457e-06, "epoch": 23.154727793696274, "percentage": 70.74, "elapsed_time": "3:15:10", "remaining_time": "1:20:44", "throughput": 787.21, "total_tokens": 9218712} {"current_steps": 28300, "total_steps": 40000, "loss": 0.1393, "lr": 9.834502141315315e-06, "epoch": 23.158821121571837, "percentage": 70.75, "elapsed_time": "3:15:12", "remaining_time": "1:20:42", "throughput": 787.24, "total_tokens": 9220392} {"current_steps": 28305, "total_steps": 40000, "loss": 0.1228, "lr": 9.82669849516552e-06, "epoch": 23.1629144494474, "percentage": 70.76, "elapsed_time": "3:15:14", "remaining_time": "1:20:39", "throughput": 787.27, "total_tokens": 9222056} {"current_steps": 28310, "total_steps": 40000, "loss": 0.1526, "lr": 9.818897188929493e-06, "epoch": 23.167007777322965, "percentage": 70.78, "elapsed_time": "3:15:15", "remaining_time": "1:20:37", "throughput": 787.29, "total_tokens": 9223720} {"current_steps": 28315, "total_steps": 40000, "loss": 0.3226, "lr": 9.811098223810309e-06, "epoch": 23.171101105198527, "percentage": 70.79, "elapsed_time": "3:15:17", "remaining_time": "1:20:35", "throughput": 787.31, "total_tokens": 9225320} {"current_steps": 28320, "total_steps": 40000, "loss": 0.1859, "lr": 9.803301601010641e-06, "epoch": 23.17519443307409, "percentage": 70.8, "elapsed_time": "3:15:19", "remaining_time": "1:20:33", "throughput": 787.33, "total_tokens": 9226872} {"current_steps": 28325, "total_steps": 40000, "loss": 0.2191, "lr": 9.795507321732853e-06, "epoch": 23.179287760949652, "percentage": 70.81, "elapsed_time": "3:15:20", "remaining_time": "1:20:31", "throughput": 787.36, "total_tokens": 9228536} {"current_steps": 28330, "total_steps": 40000, "loss": 0.1785, "lr": 9.787715387178898e-06, "epoch": 23.183381088825215, "percentage": 70.83, "elapsed_time": "3:15:22", "remaining_time": "1:20:28", "throughput": 787.39, "total_tokens": 9230264} {"current_steps": 28335, "total_steps": 40000, "loss": 0.1214, "lr": 9.779925798550399e-06, "epoch": 23.187474416700777, "percentage": 70.84, "elapsed_time": "3:15:24", "remaining_time": "1:20:26", "throughput": 787.41, "total_tokens": 9231880} {"current_steps": 28340, "total_steps": 40000, "loss": 0.165, "lr": 9.772138557048619e-06, "epoch": 23.19156774457634, "percentage": 70.85, "elapsed_time": "3:15:26", "remaining_time": "1:20:24", "throughput": 787.44, "total_tokens": 9233544} {"current_steps": 28345, "total_steps": 40000, "loss": 0.1792, "lr": 9.764353663874426e-06, "epoch": 23.1956610724519, "percentage": 70.86, "elapsed_time": "3:15:27", "remaining_time": "1:20:22", "throughput": 787.46, "total_tokens": 9235176} {"current_steps": 28350, "total_steps": 40000, "loss": 0.1912, "lr": 9.756571120228375e-06, "epoch": 23.199754400327468, "percentage": 70.88, "elapsed_time": "3:15:29", "remaining_time": "1:20:20", "throughput": 787.48, "total_tokens": 9236776} {"current_steps": 28355, "total_steps": 40000, "loss": 0.1549, "lr": 9.748790927310605e-06, "epoch": 23.20384772820303, "percentage": 70.89, "elapsed_time": "3:15:31", "remaining_time": "1:20:17", "throughput": 787.51, "total_tokens": 9238424} {"current_steps": 28360, "total_steps": 40000, "loss": 0.1744, "lr": 9.741013086320946e-06, "epoch": 23.207941056078592, "percentage": 70.9, "elapsed_time": "3:15:32", "remaining_time": "1:20:15", "throughput": 787.54, "total_tokens": 9240120} {"current_steps": 28365, "total_steps": 40000, "loss": 0.1514, "lr": 9.733237598458821e-06, "epoch": 23.212034383954155, "percentage": 70.91, "elapsed_time": "3:15:34", "remaining_time": "1:20:13", "throughput": 787.56, "total_tokens": 9241736} {"current_steps": 28370, "total_steps": 40000, "loss": 0.1757, "lr": 9.725464464923308e-06, "epoch": 23.216127711829717, "percentage": 70.93, "elapsed_time": "3:15:36", "remaining_time": "1:20:11", "throughput": 787.58, "total_tokens": 9243352} {"current_steps": 28375, "total_steps": 40000, "loss": 0.2369, "lr": 9.717693686913123e-06, "epoch": 23.22022103970528, "percentage": 70.94, "elapsed_time": "3:15:38", "remaining_time": "1:20:08", "throughput": 787.61, "total_tokens": 9245016} {"current_steps": 28380, "total_steps": 40000, "loss": 0.114, "lr": 9.709925265626632e-06, "epoch": 23.224314367580842, "percentage": 70.95, "elapsed_time": "3:15:39", "remaining_time": "1:20:06", "throughput": 787.64, "total_tokens": 9246680} {"current_steps": 28385, "total_steps": 40000, "loss": 0.1987, "lr": 9.702159202261801e-06, "epoch": 23.228407695456404, "percentage": 70.96, "elapsed_time": "3:15:41", "remaining_time": "1:20:04", "throughput": 787.66, "total_tokens": 9248280} {"current_steps": 28390, "total_steps": 40000, "loss": 0.1435, "lr": 9.694395498016268e-06, "epoch": 23.23250102333197, "percentage": 70.97, "elapsed_time": "3:15:43", "remaining_time": "1:20:02", "throughput": 787.68, "total_tokens": 9249880} {"current_steps": 28395, "total_steps": 40000, "loss": 0.1767, "lr": 9.686634154087298e-06, "epoch": 23.236594351207533, "percentage": 70.99, "elapsed_time": "3:15:44", "remaining_time": "1:20:00", "throughput": 787.7, "total_tokens": 9251512} {"current_steps": 28400, "total_steps": 40000, "loss": 0.1208, "lr": 9.678875171671776e-06, "epoch": 23.240687679083095, "percentage": 71.0, "elapsed_time": "3:15:46", "remaining_time": "1:19:57", "throughput": 787.72, "total_tokens": 9253112} {"current_steps": 28400, "total_steps": 40000, "eval_loss": 0.21118207275867462, "epoch": 23.240687679083095, "percentage": 71.0, "elapsed_time": "3:15:59", "remaining_time": "1:20:03", "throughput": 786.89, "total_tokens": 9253112} {"current_steps": 28405, "total_steps": 40000, "loss": 0.1366, "lr": 9.671118551966246e-06, "epoch": 23.244781006958657, "percentage": 71.01, "elapsed_time": "3:16:02", "remaining_time": "1:20:01", "throughput": 786.8, "total_tokens": 9254712} {"current_steps": 28410, "total_steps": 40000, "loss": 0.1722, "lr": 9.66336429616686e-06, "epoch": 23.24887433483422, "percentage": 71.03, "elapsed_time": "3:16:04", "remaining_time": "1:19:59", "throughput": 786.82, "total_tokens": 9256312} {"current_steps": 28415, "total_steps": 40000, "loss": 0.1963, "lr": 9.655612405469436e-06, "epoch": 23.252967662709782, "percentage": 71.04, "elapsed_time": "3:16:05", "remaining_time": "1:19:57", "throughput": 786.84, "total_tokens": 9257944} {"current_steps": 28420, "total_steps": 40000, "loss": 0.2014, "lr": 9.647862881069413e-06, "epoch": 23.257060990585344, "percentage": 71.05, "elapsed_time": "3:16:07", "remaining_time": "1:19:54", "throughput": 786.87, "total_tokens": 9259656} {"current_steps": 28425, "total_steps": 40000, "loss": 0.1843, "lr": 9.640115724161855e-06, "epoch": 23.26115431846091, "percentage": 71.06, "elapsed_time": "3:16:09", "remaining_time": "1:19:52", "throughput": 786.89, "total_tokens": 9261272} {"current_steps": 28430, "total_steps": 40000, "loss": 0.2045, "lr": 9.632370935941483e-06, "epoch": 23.265247646336473, "percentage": 71.08, "elapsed_time": "3:16:11", "remaining_time": "1:19:50", "throughput": 786.91, "total_tokens": 9262872} {"current_steps": 28435, "total_steps": 40000, "loss": 0.1445, "lr": 9.624628517602634e-06, "epoch": 23.269340974212035, "percentage": 71.09, "elapsed_time": "3:16:12", "remaining_time": "1:19:48", "throughput": 786.93, "total_tokens": 9264456} {"current_steps": 28440, "total_steps": 40000, "loss": 0.208, "lr": 9.61688847033928e-06, "epoch": 23.273434302087598, "percentage": 71.1, "elapsed_time": "3:16:14", "remaining_time": "1:19:46", "throughput": 786.95, "total_tokens": 9266072} {"current_steps": 28445, "total_steps": 40000, "loss": 0.1838, "lr": 9.609150795345051e-06, "epoch": 23.27752762996316, "percentage": 71.11, "elapsed_time": "3:16:16", "remaining_time": "1:19:43", "throughput": 786.97, "total_tokens": 9267640} {"current_steps": 28450, "total_steps": 40000, "loss": 0.1704, "lr": 9.601415493813171e-06, "epoch": 23.281620957838722, "percentage": 71.12, "elapsed_time": "3:16:18", "remaining_time": "1:19:41", "throughput": 786.99, "total_tokens": 9269240} {"current_steps": 28455, "total_steps": 40000, "loss": 0.0932, "lr": 9.593682566936533e-06, "epoch": 23.285714285714285, "percentage": 71.14, "elapsed_time": "3:16:19", "remaining_time": "1:19:39", "throughput": 787.02, "total_tokens": 9270856} {"current_steps": 28460, "total_steps": 40000, "loss": 0.2141, "lr": 9.58595201590766e-06, "epoch": 23.289807613589847, "percentage": 71.15, "elapsed_time": "3:16:21", "remaining_time": "1:19:37", "throughput": 787.04, "total_tokens": 9272520} {"current_steps": 28465, "total_steps": 40000, "loss": 0.2408, "lr": 9.578223841918681e-06, "epoch": 23.293900941465413, "percentage": 71.16, "elapsed_time": "3:16:23", "remaining_time": "1:19:34", "throughput": 787.07, "total_tokens": 9274152} {"current_steps": 28470, "total_steps": 40000, "loss": 0.1386, "lr": 9.570498046161389e-06, "epoch": 23.297994269340975, "percentage": 71.17, "elapsed_time": "3:16:24", "remaining_time": "1:19:32", "throughput": 787.09, "total_tokens": 9275752} {"current_steps": 28475, "total_steps": 40000, "loss": 0.2101, "lr": 9.562774629827206e-06, "epoch": 23.302087597216538, "percentage": 71.19, "elapsed_time": "3:16:26", "remaining_time": "1:19:30", "throughput": 787.11, "total_tokens": 9277416} {"current_steps": 28480, "total_steps": 40000, "loss": 0.1336, "lr": 9.555053594107163e-06, "epoch": 23.3061809250921, "percentage": 71.2, "elapsed_time": "3:16:28", "remaining_time": "1:19:28", "throughput": 787.14, "total_tokens": 9279096} {"current_steps": 28485, "total_steps": 40000, "loss": 0.2096, "lr": 9.547334940191957e-06, "epoch": 23.310274252967663, "percentage": 71.21, "elapsed_time": "3:16:30", "remaining_time": "1:19:26", "throughput": 787.16, "total_tokens": 9280696} {"current_steps": 28490, "total_steps": 40000, "loss": 0.1673, "lr": 9.539618669271886e-06, "epoch": 23.314367580843225, "percentage": 71.23, "elapsed_time": "3:16:31", "remaining_time": "1:19:23", "throughput": 787.18, "total_tokens": 9282280} {"current_steps": 28495, "total_steps": 40000, "loss": 0.2465, "lr": 9.531904782536904e-06, "epoch": 23.318460908718787, "percentage": 71.24, "elapsed_time": "3:16:33", "remaining_time": "1:19:21", "throughput": 787.21, "total_tokens": 9283928} {"current_steps": 28500, "total_steps": 40000, "loss": 0.1952, "lr": 9.524193281176597e-06, "epoch": 23.32255423659435, "percentage": 71.25, "elapsed_time": "3:16:35", "remaining_time": "1:19:19", "throughput": 787.23, "total_tokens": 9285512} {"current_steps": 28505, "total_steps": 40000, "loss": 0.1808, "lr": 9.516484166380165e-06, "epoch": 23.326647564469916, "percentage": 71.26, "elapsed_time": "3:16:36", "remaining_time": "1:19:17", "throughput": 787.25, "total_tokens": 9287176} {"current_steps": 28510, "total_steps": 40000, "loss": 0.1366, "lr": 9.508777439336447e-06, "epoch": 23.330740892345478, "percentage": 71.28, "elapsed_time": "3:16:38", "remaining_time": "1:19:15", "throughput": 787.28, "total_tokens": 9288824} {"current_steps": 28515, "total_steps": 40000, "loss": 0.1466, "lr": 9.50107310123393e-06, "epoch": 23.33483422022104, "percentage": 71.29, "elapsed_time": "3:16:40", "remaining_time": "1:19:12", "throughput": 787.3, "total_tokens": 9290440} {"current_steps": 28520, "total_steps": 40000, "loss": 0.2483, "lr": 9.493371153260702e-06, "epoch": 23.338927548096603, "percentage": 71.3, "elapsed_time": "3:16:42", "remaining_time": "1:19:10", "throughput": 787.33, "total_tokens": 9292104} {"current_steps": 28525, "total_steps": 40000, "loss": 0.1612, "lr": 9.485671596604523e-06, "epoch": 23.343020875972165, "percentage": 71.31, "elapsed_time": "3:16:43", "remaining_time": "1:19:08", "throughput": 787.35, "total_tokens": 9293736} {"current_steps": 28530, "total_steps": 40000, "loss": 0.1527, "lr": 9.477974432452738e-06, "epoch": 23.347114203847728, "percentage": 71.33, "elapsed_time": "3:16:45", "remaining_time": "1:19:06", "throughput": 787.37, "total_tokens": 9295384} {"current_steps": 28535, "total_steps": 40000, "loss": 0.1603, "lr": 9.470279661992356e-06, "epoch": 23.35120753172329, "percentage": 71.34, "elapsed_time": "3:16:47", "remaining_time": "1:19:04", "throughput": 787.4, "total_tokens": 9297096} {"current_steps": 28540, "total_steps": 40000, "loss": 0.1875, "lr": 9.462587286410021e-06, "epoch": 23.355300859598852, "percentage": 71.35, "elapsed_time": "3:16:49", "remaining_time": "1:19:01", "throughput": 787.43, "total_tokens": 9298776} {"current_steps": 28545, "total_steps": 40000, "loss": 0.2033, "lr": 9.454897306891972e-06, "epoch": 23.359394187474418, "percentage": 71.36, "elapsed_time": "3:16:50", "remaining_time": "1:18:59", "throughput": 787.45, "total_tokens": 9300376} {"current_steps": 28550, "total_steps": 40000, "loss": 0.1549, "lr": 9.44720972462411e-06, "epoch": 23.36348751534998, "percentage": 71.38, "elapsed_time": "3:16:52", "remaining_time": "1:18:57", "throughput": 787.48, "total_tokens": 9302088} {"current_steps": 28555, "total_steps": 40000, "loss": 0.1564, "lr": 9.439524540791964e-06, "epoch": 23.367580843225543, "percentage": 71.39, "elapsed_time": "3:16:54", "remaining_time": "1:18:55", "throughput": 787.5, "total_tokens": 9303704} {"current_steps": 28560, "total_steps": 40000, "loss": 0.1493, "lr": 9.431841756580673e-06, "epoch": 23.371674171101105, "percentage": 71.4, "elapsed_time": "3:16:55", "remaining_time": "1:18:52", "throughput": 787.53, "total_tokens": 9305336} {"current_steps": 28565, "total_steps": 40000, "loss": 0.2497, "lr": 9.42416137317503e-06, "epoch": 23.375767498976668, "percentage": 71.41, "elapsed_time": "3:16:57", "remaining_time": "1:18:50", "throughput": 787.55, "total_tokens": 9306968} {"current_steps": 28570, "total_steps": 40000, "loss": 0.2325, "lr": 9.416483391759437e-06, "epoch": 23.37986082685223, "percentage": 71.43, "elapsed_time": "3:16:59", "remaining_time": "1:18:48", "throughput": 787.58, "total_tokens": 9308664} {"current_steps": 28575, "total_steps": 40000, "loss": 0.1749, "lr": 9.408807813517945e-06, "epoch": 23.383954154727792, "percentage": 71.44, "elapsed_time": "3:17:01", "remaining_time": "1:18:46", "throughput": 787.6, "total_tokens": 9310296} {"current_steps": 28580, "total_steps": 40000, "loss": 0.1929, "lr": 9.401134639634221e-06, "epoch": 23.388047482603355, "percentage": 71.45, "elapsed_time": "3:17:02", "remaining_time": "1:18:44", "throughput": 787.63, "total_tokens": 9311928} {"current_steps": 28585, "total_steps": 40000, "loss": 0.1679, "lr": 9.393463871291555e-06, "epoch": 23.39214081047892, "percentage": 71.46, "elapsed_time": "3:17:04", "remaining_time": "1:18:41", "throughput": 787.65, "total_tokens": 9313560} {"current_steps": 28590, "total_steps": 40000, "loss": 0.1491, "lr": 9.385795509672881e-06, "epoch": 23.396234138354483, "percentage": 71.47, "elapsed_time": "3:17:06", "remaining_time": "1:18:39", "throughput": 787.67, "total_tokens": 9315128} {"current_steps": 28595, "total_steps": 40000, "loss": 0.2418, "lr": 9.378129555960771e-06, "epoch": 23.400327466230046, "percentage": 71.49, "elapsed_time": "3:17:07", "remaining_time": "1:18:37", "throughput": 787.7, "total_tokens": 9316840} {"current_steps": 28600, "total_steps": 40000, "loss": 0.2732, "lr": 9.370466011337392e-06, "epoch": 23.404420794105608, "percentage": 71.5, "elapsed_time": "3:17:09", "remaining_time": "1:18:35", "throughput": 787.72, "total_tokens": 9318440} {"current_steps": 28600, "total_steps": 40000, "eval_loss": 0.2154008448123932, "epoch": 23.404420794105608, "percentage": 71.5, "elapsed_time": "3:17:22", "remaining_time": "1:18:40", "throughput": 786.89, "total_tokens": 9318440} {"current_steps": 28605, "total_steps": 40000, "loss": 0.236, "lr": 9.362804876984573e-06, "epoch": 23.40851412198117, "percentage": 71.51, "elapsed_time": "3:17:25", "remaining_time": "1:18:38", "throughput": 786.81, "total_tokens": 9320088} {"current_steps": 28610, "total_steps": 40000, "loss": 0.2118, "lr": 9.355146154083747e-06, "epoch": 23.412607449856733, "percentage": 71.53, "elapsed_time": "3:17:27", "remaining_time": "1:18:36", "throughput": 786.84, "total_tokens": 9321752} {"current_steps": 28615, "total_steps": 40000, "loss": 0.1657, "lr": 9.347489843815987e-06, "epoch": 23.416700777732295, "percentage": 71.54, "elapsed_time": "3:17:28", "remaining_time": "1:18:34", "throughput": 786.86, "total_tokens": 9323384} {"current_steps": 28620, "total_steps": 40000, "loss": 0.1207, "lr": 9.339835947362002e-06, "epoch": 23.420794105607857, "percentage": 71.55, "elapsed_time": "3:17:30", "remaining_time": "1:18:32", "throughput": 786.88, "total_tokens": 9324952} {"current_steps": 28625, "total_steps": 40000, "loss": 0.1393, "lr": 9.332184465902105e-06, "epoch": 23.424887433483423, "percentage": 71.56, "elapsed_time": "3:17:32", "remaining_time": "1:18:29", "throughput": 786.9, "total_tokens": 9326552} {"current_steps": 28630, "total_steps": 40000, "loss": 0.1949, "lr": 9.324535400616266e-06, "epoch": 23.428980761358986, "percentage": 71.58, "elapsed_time": "3:17:33", "remaining_time": "1:18:27", "throughput": 786.92, "total_tokens": 9328152} {"current_steps": 28635, "total_steps": 40000, "loss": 0.1916, "lr": 9.31688875268405e-06, "epoch": 23.433074089234548, "percentage": 71.59, "elapsed_time": "3:17:35", "remaining_time": "1:18:25", "throughput": 786.94, "total_tokens": 9329736} {"current_steps": 28640, "total_steps": 40000, "loss": 0.1423, "lr": 9.309244523284674e-06, "epoch": 23.43716741711011, "percentage": 71.6, "elapsed_time": "3:17:37", "remaining_time": "1:18:23", "throughput": 786.96, "total_tokens": 9331352} {"current_steps": 28645, "total_steps": 40000, "loss": 0.1556, "lr": 9.301602713596982e-06, "epoch": 23.441260744985673, "percentage": 71.61, "elapsed_time": "3:17:39", "remaining_time": "1:18:21", "throughput": 786.99, "total_tokens": 9332984} {"current_steps": 28650, "total_steps": 40000, "loss": 0.1899, "lr": 9.293963324799432e-06, "epoch": 23.445354072861235, "percentage": 71.62, "elapsed_time": "3:17:40", "remaining_time": "1:18:18", "throughput": 787.02, "total_tokens": 9334712} {"current_steps": 28655, "total_steps": 40000, "loss": 0.221, "lr": 9.286326358070104e-06, "epoch": 23.449447400736798, "percentage": 71.64, "elapsed_time": "3:17:42", "remaining_time": "1:18:16", "throughput": 787.04, "total_tokens": 9336312} {"current_steps": 28660, "total_steps": 40000, "loss": 0.1606, "lr": 9.278691814586729e-06, "epoch": 23.45354072861236, "percentage": 71.65, "elapsed_time": "3:17:44", "remaining_time": "1:18:14", "throughput": 787.06, "total_tokens": 9337864} {"current_steps": 28665, "total_steps": 40000, "loss": 0.1634, "lr": 9.271059695526635e-06, "epoch": 23.457634056487926, "percentage": 71.66, "elapsed_time": "3:17:46", "remaining_time": "1:18:12", "throughput": 787.09, "total_tokens": 9339576} {"current_steps": 28670, "total_steps": 40000, "loss": 0.2091, "lr": 9.263430002066805e-06, "epoch": 23.46172738436349, "percentage": 71.67, "elapsed_time": "3:17:47", "remaining_time": "1:18:09", "throughput": 787.11, "total_tokens": 9341176} {"current_steps": 28675, "total_steps": 40000, "loss": 0.191, "lr": 9.25580273538382e-06, "epoch": 23.46582071223905, "percentage": 71.69, "elapsed_time": "3:17:49", "remaining_time": "1:18:07", "throughput": 787.13, "total_tokens": 9342776} {"current_steps": 28680, "total_steps": 40000, "loss": 0.1939, "lr": 9.248177896653907e-06, "epoch": 23.469914040114613, "percentage": 71.7, "elapsed_time": "3:17:51", "remaining_time": "1:18:05", "throughput": 787.15, "total_tokens": 9344344} {"current_steps": 28685, "total_steps": 40000, "loss": 0.1276, "lr": 9.240555487052918e-06, "epoch": 23.474007367990176, "percentage": 71.71, "elapsed_time": "3:17:52", "remaining_time": "1:18:03", "throughput": 787.16, "total_tokens": 9345928} {"current_steps": 28690, "total_steps": 40000, "loss": 0.1711, "lr": 9.232935507756313e-06, "epoch": 23.478100695865738, "percentage": 71.73, "elapsed_time": "3:17:54", "remaining_time": "1:18:01", "throughput": 787.19, "total_tokens": 9347576} {"current_steps": 28695, "total_steps": 40000, "loss": 0.1831, "lr": 9.225317959939193e-06, "epoch": 23.4821940237413, "percentage": 71.74, "elapsed_time": "3:17:56", "remaining_time": "1:17:58", "throughput": 787.22, "total_tokens": 9349256} {"current_steps": 28700, "total_steps": 40000, "loss": 0.2641, "lr": 9.217702844776287e-06, "epoch": 23.486287351616866, "percentage": 71.75, "elapsed_time": "3:17:58", "remaining_time": "1:17:56", "throughput": 787.24, "total_tokens": 9350920} {"current_steps": 28705, "total_steps": 40000, "loss": 0.1401, "lr": 9.210090163441929e-06, "epoch": 23.49038067949243, "percentage": 71.76, "elapsed_time": "3:17:59", "remaining_time": "1:17:54", "throughput": 787.27, "total_tokens": 9352584} {"current_steps": 28710, "total_steps": 40000, "loss": 0.1901, "lr": 9.202479917110105e-06, "epoch": 23.49447400736799, "percentage": 71.78, "elapsed_time": "3:18:01", "remaining_time": "1:17:52", "throughput": 787.29, "total_tokens": 9354232} {"current_steps": 28715, "total_steps": 40000, "loss": 0.1653, "lr": 9.194872106954392e-06, "epoch": 23.498567335243553, "percentage": 71.79, "elapsed_time": "3:18:03", "remaining_time": "1:17:50", "throughput": 787.31, "total_tokens": 9355768} {"current_steps": 28720, "total_steps": 40000, "loss": 0.1456, "lr": 9.187266734148029e-06, "epoch": 23.502660663119116, "percentage": 71.8, "elapsed_time": "3:18:04", "remaining_time": "1:17:47", "throughput": 787.33, "total_tokens": 9357352} {"current_steps": 28725, "total_steps": 40000, "loss": 0.1892, "lr": 9.179663799863849e-06, "epoch": 23.506753990994678, "percentage": 71.81, "elapsed_time": "3:18:06", "remaining_time": "1:17:45", "throughput": 787.36, "total_tokens": 9359032} {"current_steps": 28730, "total_steps": 40000, "loss": 0.1622, "lr": 9.172063305274317e-06, "epoch": 23.51084731887024, "percentage": 71.83, "elapsed_time": "3:18:08", "remaining_time": "1:17:43", "throughput": 787.39, "total_tokens": 9360808} {"current_steps": 28735, "total_steps": 40000, "loss": 0.2101, "lr": 9.164465251551527e-06, "epoch": 23.514940646745803, "percentage": 71.84, "elapsed_time": "3:18:10", "remaining_time": "1:17:41", "throughput": 787.42, "total_tokens": 9362504} {"current_steps": 28740, "total_steps": 40000, "loss": 0.1544, "lr": 9.156869639867205e-06, "epoch": 23.51903397462137, "percentage": 71.85, "elapsed_time": "3:18:11", "remaining_time": "1:17:39", "throughput": 787.44, "total_tokens": 9364088} {"current_steps": 28745, "total_steps": 40000, "loss": 0.2262, "lr": 9.149276471392677e-06, "epoch": 23.52312730249693, "percentage": 71.86, "elapsed_time": "3:18:13", "remaining_time": "1:17:36", "throughput": 787.46, "total_tokens": 9365720} {"current_steps": 28750, "total_steps": 40000, "loss": 0.191, "lr": 9.141685747298914e-06, "epoch": 23.527220630372494, "percentage": 71.88, "elapsed_time": "3:18:15", "remaining_time": "1:17:34", "throughput": 787.49, "total_tokens": 9367368} {"current_steps": 28755, "total_steps": 40000, "loss": 0.1229, "lr": 9.13409746875649e-06, "epoch": 23.531313958248056, "percentage": 71.89, "elapsed_time": "3:18:16", "remaining_time": "1:17:32", "throughput": 787.51, "total_tokens": 9369000} {"current_steps": 28760, "total_steps": 40000, "loss": 0.0999, "lr": 9.12651163693562e-06, "epoch": 23.53540728612362, "percentage": 71.9, "elapsed_time": "3:18:18", "remaining_time": "1:17:30", "throughput": 787.53, "total_tokens": 9370616} {"current_steps": 28765, "total_steps": 40000, "loss": 0.2655, "lr": 9.11892825300614e-06, "epoch": 23.53950061399918, "percentage": 71.91, "elapsed_time": "3:18:20", "remaining_time": "1:17:28", "throughput": 787.56, "total_tokens": 9372248} {"current_steps": 28770, "total_steps": 40000, "loss": 0.1041, "lr": 9.111347318137491e-06, "epoch": 23.543593941874743, "percentage": 71.92, "elapsed_time": "3:18:22", "remaining_time": "1:17:25", "throughput": 787.58, "total_tokens": 9373864} {"current_steps": 28775, "total_steps": 40000, "loss": 0.1872, "lr": 9.103768833498755e-06, "epoch": 23.547687269750305, "percentage": 71.94, "elapsed_time": "3:18:23", "remaining_time": "1:17:23", "throughput": 787.6, "total_tokens": 9375448} {"current_steps": 28780, "total_steps": 40000, "loss": 0.124, "lr": 9.096192800258639e-06, "epoch": 23.55178059762587, "percentage": 71.95, "elapsed_time": "3:18:25", "remaining_time": "1:17:21", "throughput": 787.62, "total_tokens": 9377064} {"current_steps": 28785, "total_steps": 40000, "loss": 0.1694, "lr": 9.088619219585443e-06, "epoch": 23.555873925501434, "percentage": 71.96, "elapsed_time": "3:18:27", "remaining_time": "1:17:19", "throughput": 787.65, "total_tokens": 9378728} {"current_steps": 28790, "total_steps": 40000, "loss": 0.1167, "lr": 9.081048092647127e-06, "epoch": 23.559967253376996, "percentage": 71.97, "elapsed_time": "3:18:28", "remaining_time": "1:17:17", "throughput": 787.67, "total_tokens": 9380296} {"current_steps": 28795, "total_steps": 40000, "loss": 0.1589, "lr": 9.073479420611245e-06, "epoch": 23.56406058125256, "percentage": 71.99, "elapsed_time": "3:18:30", "remaining_time": "1:17:14", "throughput": 787.69, "total_tokens": 9381960} {"current_steps": 28800, "total_steps": 40000, "loss": 0.1733, "lr": 9.065913204644974e-06, "epoch": 23.56815390912812, "percentage": 72.0, "elapsed_time": "3:18:32", "remaining_time": "1:17:12", "throughput": 787.72, "total_tokens": 9383656} {"current_steps": 28800, "total_steps": 40000, "eval_loss": 0.20979543030261993, "epoch": 23.56815390912812, "percentage": 72.0, "elapsed_time": "3:18:44", "remaining_time": "1:17:17", "throughput": 786.89, "total_tokens": 9383656} {"current_steps": 28805, "total_steps": 40000, "loss": 0.1125, "lr": 9.058349445915135e-06, "epoch": 23.572247237003683, "percentage": 72.01, "elapsed_time": "3:18:48", "remaining_time": "1:17:15", "throughput": 786.8, "total_tokens": 9385336} {"current_steps": 28810, "total_steps": 40000, "loss": 0.1479, "lr": 9.050788145588138e-06, "epoch": 23.576340564879246, "percentage": 72.02, "elapsed_time": "3:18:50", "remaining_time": "1:17:13", "throughput": 786.82, "total_tokens": 9386920} {"current_steps": 28815, "total_steps": 40000, "loss": 0.2505, "lr": 9.043229304830039e-06, "epoch": 23.580433892754808, "percentage": 72.04, "elapsed_time": "3:18:51", "remaining_time": "1:17:11", "throughput": 786.85, "total_tokens": 9388616} {"current_steps": 28820, "total_steps": 40000, "loss": 0.1827, "lr": 9.035672924806515e-06, "epoch": 23.584527220630374, "percentage": 72.05, "elapsed_time": "3:18:53", "remaining_time": "1:17:09", "throughput": 786.87, "total_tokens": 9390296} {"current_steps": 28825, "total_steps": 40000, "loss": 0.1814, "lr": 9.028119006682839e-06, "epoch": 23.588620548505936, "percentage": 72.06, "elapsed_time": "3:18:55", "remaining_time": "1:17:07", "throughput": 786.89, "total_tokens": 9391864} {"current_steps": 28830, "total_steps": 40000, "loss": 0.2275, "lr": 9.020567551623935e-06, "epoch": 23.5927138763815, "percentage": 72.08, "elapsed_time": "3:18:57", "remaining_time": "1:17:04", "throughput": 786.91, "total_tokens": 9393480} {"current_steps": 28835, "total_steps": 40000, "loss": 0.1156, "lr": 9.013018560794318e-06, "epoch": 23.59680720425706, "percentage": 72.09, "elapsed_time": "3:18:58", "remaining_time": "1:17:02", "throughput": 786.94, "total_tokens": 9395080} {"current_steps": 28840, "total_steps": 40000, "loss": 0.2343, "lr": 9.005472035358139e-06, "epoch": 23.600900532132624, "percentage": 72.1, "elapsed_time": "3:19:00", "remaining_time": "1:17:00", "throughput": 786.96, "total_tokens": 9396680} {"current_steps": 28845, "total_steps": 40000, "loss": 0.2345, "lr": 8.997927976479185e-06, "epoch": 23.604993860008186, "percentage": 72.11, "elapsed_time": "3:19:02", "remaining_time": "1:16:58", "throughput": 786.98, "total_tokens": 9398328} {"current_steps": 28850, "total_steps": 40000, "loss": 0.2267, "lr": 8.99038638532082e-06, "epoch": 23.60908718788375, "percentage": 72.12, "elapsed_time": "3:19:03", "remaining_time": "1:16:56", "throughput": 787.0, "total_tokens": 9399960} {"current_steps": 28855, "total_steps": 40000, "loss": 0.1276, "lr": 8.982847263046065e-06, "epoch": 23.61318051575931, "percentage": 72.14, "elapsed_time": "3:19:05", "remaining_time": "1:16:53", "throughput": 787.02, "total_tokens": 9401560} {"current_steps": 28860, "total_steps": 40000, "loss": 0.2874, "lr": 8.975310610817555e-06, "epoch": 23.617273843634877, "percentage": 72.15, "elapsed_time": "3:19:07", "remaining_time": "1:16:51", "throughput": 787.05, "total_tokens": 9403176} {"current_steps": 28865, "total_steps": 40000, "loss": 0.2434, "lr": 8.967776429797528e-06, "epoch": 23.62136717151044, "percentage": 72.16, "elapsed_time": "3:19:09", "remaining_time": "1:16:49", "throughput": 787.07, "total_tokens": 9404824} {"current_steps": 28870, "total_steps": 40000, "loss": 0.1802, "lr": 8.960244721147842e-06, "epoch": 23.625460499386, "percentage": 72.17, "elapsed_time": "3:19:10", "remaining_time": "1:16:47", "throughput": 787.1, "total_tokens": 9406488} {"current_steps": 28875, "total_steps": 40000, "loss": 0.1266, "lr": 8.952715486029995e-06, "epoch": 23.629553827261564, "percentage": 72.19, "elapsed_time": "3:19:12", "remaining_time": "1:16:45", "throughput": 787.12, "total_tokens": 9408136} {"current_steps": 28880, "total_steps": 40000, "loss": 0.1747, "lr": 8.945188725605075e-06, "epoch": 23.633647155137126, "percentage": 72.2, "elapsed_time": "3:19:14", "remaining_time": "1:16:42", "throughput": 787.14, "total_tokens": 9409736} {"current_steps": 28885, "total_steps": 40000, "loss": 0.2396, "lr": 8.937664441033817e-06, "epoch": 23.63774048301269, "percentage": 72.21, "elapsed_time": "3:19:16", "remaining_time": "1:16:40", "throughput": 787.16, "total_tokens": 9411352} {"current_steps": 28890, "total_steps": 40000, "loss": 0.15, "lr": 8.930142633476549e-06, "epoch": 23.64183381088825, "percentage": 72.22, "elapsed_time": "3:19:17", "remaining_time": "1:16:38", "throughput": 787.18, "total_tokens": 9412968} {"current_steps": 28895, "total_steps": 40000, "loss": 0.1652, "lr": 8.92262330409323e-06, "epoch": 23.645927138763817, "percentage": 72.24, "elapsed_time": "3:19:19", "remaining_time": "1:16:36", "throughput": 787.21, "total_tokens": 9414600} {"current_steps": 28900, "total_steps": 40000, "loss": 0.2186, "lr": 8.915106454043448e-06, "epoch": 23.65002046663938, "percentage": 72.25, "elapsed_time": "3:19:21", "remaining_time": "1:16:34", "throughput": 787.23, "total_tokens": 9416216} {"current_steps": 28905, "total_steps": 40000, "loss": 0.1852, "lr": 8.90759208448638e-06, "epoch": 23.65411379451494, "percentage": 72.26, "elapsed_time": "3:19:22", "remaining_time": "1:16:31", "throughput": 787.25, "total_tokens": 9417800} {"current_steps": 28910, "total_steps": 40000, "loss": 0.1551, "lr": 8.900080196580848e-06, "epoch": 23.658207122390504, "percentage": 72.28, "elapsed_time": "3:19:24", "remaining_time": "1:16:29", "throughput": 787.26, "total_tokens": 9419336} {"current_steps": 28915, "total_steps": 40000, "loss": 0.236, "lr": 8.892570791485267e-06, "epoch": 23.662300450266066, "percentage": 72.29, "elapsed_time": "3:19:26", "remaining_time": "1:16:27", "throughput": 787.28, "total_tokens": 9420936} {"current_steps": 28920, "total_steps": 40000, "loss": 0.1614, "lr": 8.885063870357688e-06, "epoch": 23.66639377814163, "percentage": 72.3, "elapsed_time": "3:19:28", "remaining_time": "1:16:25", "throughput": 787.31, "total_tokens": 9422600} {"current_steps": 28925, "total_steps": 40000, "loss": 0.2021, "lr": 8.87755943435578e-06, "epoch": 23.67048710601719, "percentage": 72.31, "elapsed_time": "3:19:29", "remaining_time": "1:16:23", "throughput": 787.33, "total_tokens": 9424232} {"current_steps": 28930, "total_steps": 40000, "loss": 0.2326, "lr": 8.87005748463681e-06, "epoch": 23.674580433892753, "percentage": 72.32, "elapsed_time": "3:19:31", "remaining_time": "1:16:20", "throughput": 787.36, "total_tokens": 9425896} {"current_steps": 28935, "total_steps": 40000, "loss": 0.1922, "lr": 8.862558022357681e-06, "epoch": 23.678673761768316, "percentage": 72.34, "elapsed_time": "3:19:33", "remaining_time": "1:16:18", "throughput": 787.39, "total_tokens": 9427608} {"current_steps": 28940, "total_steps": 40000, "loss": 0.219, "lr": 8.855061048674903e-06, "epoch": 23.68276708964388, "percentage": 72.35, "elapsed_time": "3:19:34", "remaining_time": "1:16:16", "throughput": 787.41, "total_tokens": 9429192} {"current_steps": 28945, "total_steps": 40000, "loss": 0.1676, "lr": 8.847566564744595e-06, "epoch": 23.686860417519444, "percentage": 72.36, "elapsed_time": "3:19:36", "remaining_time": "1:16:14", "throughput": 787.43, "total_tokens": 9430856} {"current_steps": 28950, "total_steps": 40000, "loss": 0.1721, "lr": 8.840074571722512e-06, "epoch": 23.690953745395007, "percentage": 72.38, "elapsed_time": "3:19:38", "remaining_time": "1:16:12", "throughput": 787.45, "total_tokens": 9432440} {"current_steps": 28955, "total_steps": 40000, "loss": 0.1937, "lr": 8.832585070764002e-06, "epoch": 23.69504707327057, "percentage": 72.39, "elapsed_time": "3:19:40", "remaining_time": "1:16:09", "throughput": 787.48, "total_tokens": 9434072} {"current_steps": 28960, "total_steps": 40000, "loss": 0.2204, "lr": 8.825098063024045e-06, "epoch": 23.69914040114613, "percentage": 72.4, "elapsed_time": "3:19:41", "remaining_time": "1:16:07", "throughput": 787.5, "total_tokens": 9435656} {"current_steps": 28965, "total_steps": 40000, "loss": 0.173, "lr": 8.817613549657244e-06, "epoch": 23.703233729021694, "percentage": 72.41, "elapsed_time": "3:19:43", "remaining_time": "1:16:05", "throughput": 787.51, "total_tokens": 9437208} {"current_steps": 28970, "total_steps": 40000, "loss": 0.2552, "lr": 8.810131531817783e-06, "epoch": 23.707327056897256, "percentage": 72.42, "elapsed_time": "3:19:45", "remaining_time": "1:16:03", "throughput": 787.53, "total_tokens": 9438840} {"current_steps": 28975, "total_steps": 40000, "loss": 0.131, "lr": 8.802652010659496e-06, "epoch": 23.711420384772822, "percentage": 72.44, "elapsed_time": "3:19:47", "remaining_time": "1:16:01", "throughput": 787.56, "total_tokens": 9440488} {"current_steps": 28980, "total_steps": 40000, "loss": 0.154, "lr": 8.795174987335827e-06, "epoch": 23.715513712648384, "percentage": 72.45, "elapsed_time": "3:19:48", "remaining_time": "1:15:58", "throughput": 787.58, "total_tokens": 9442088} {"current_steps": 28985, "total_steps": 40000, "loss": 0.1531, "lr": 8.787700462999807e-06, "epoch": 23.719607040523947, "percentage": 72.46, "elapsed_time": "3:19:50", "remaining_time": "1:15:56", "throughput": 787.61, "total_tokens": 9443768} {"current_steps": 28990, "total_steps": 40000, "loss": 0.1965, "lr": 8.780228438804122e-06, "epoch": 23.72370036839951, "percentage": 72.47, "elapsed_time": "3:19:52", "remaining_time": "1:15:54", "throughput": 787.63, "total_tokens": 9445432} {"current_steps": 28995, "total_steps": 40000, "loss": 0.1095, "lr": 8.772758915901032e-06, "epoch": 23.72779369627507, "percentage": 72.49, "elapsed_time": "3:19:53", "remaining_time": "1:15:52", "throughput": 787.65, "total_tokens": 9447032} {"current_steps": 29000, "total_steps": 40000, "loss": 0.1701, "lr": 8.765291895442443e-06, "epoch": 23.731887024150634, "percentage": 72.5, "elapsed_time": "3:19:55", "remaining_time": "1:15:50", "throughput": 787.67, "total_tokens": 9448616} {"current_steps": 29000, "total_steps": 40000, "eval_loss": 0.21464170515537262, "epoch": 23.731887024150634, "percentage": 72.5, "elapsed_time": "3:20:08", "remaining_time": "1:15:54", "throughput": 786.86, "total_tokens": 9448616} {"current_steps": 29005, "total_steps": 40000, "loss": 0.1424, "lr": 8.75782737857987e-06, "epoch": 23.735980352026196, "percentage": 72.51, "elapsed_time": "3:20:11", "remaining_time": "1:15:53", "throughput": 786.78, "total_tokens": 9450216} {"current_steps": 29010, "total_steps": 40000, "loss": 0.1271, "lr": 8.750365366464425e-06, "epoch": 23.74007367990176, "percentage": 72.52, "elapsed_time": "3:20:13", "remaining_time": "1:15:50", "throughput": 786.79, "total_tokens": 9451784} {"current_steps": 29015, "total_steps": 40000, "loss": 0.1745, "lr": 8.742905860246838e-06, "epoch": 23.744167007777325, "percentage": 72.54, "elapsed_time": "3:20:14", "remaining_time": "1:15:48", "throughput": 786.82, "total_tokens": 9453432} {"current_steps": 29020, "total_steps": 40000, "loss": 0.1956, "lr": 8.735448861077478e-06, "epoch": 23.748260335652887, "percentage": 72.55, "elapsed_time": "3:20:16", "remaining_time": "1:15:46", "throughput": 786.84, "total_tokens": 9455048} {"current_steps": 29025, "total_steps": 40000, "loss": 0.1788, "lr": 8.727994370106288e-06, "epoch": 23.75235366352845, "percentage": 72.56, "elapsed_time": "3:20:18", "remaining_time": "1:15:44", "throughput": 786.86, "total_tokens": 9456680} {"current_steps": 29030, "total_steps": 40000, "loss": 0.1155, "lr": 8.720542388482861e-06, "epoch": 23.75644699140401, "percentage": 72.58, "elapsed_time": "3:20:19", "remaining_time": "1:15:42", "throughput": 786.89, "total_tokens": 9458328} {"current_steps": 29035, "total_steps": 40000, "loss": 0.1345, "lr": 8.71309291735637e-06, "epoch": 23.760540319279574, "percentage": 72.59, "elapsed_time": "3:20:21", "remaining_time": "1:15:39", "throughput": 786.91, "total_tokens": 9459944} {"current_steps": 29040, "total_steps": 40000, "loss": 0.1501, "lr": 8.705645957875621e-06, "epoch": 23.764633647155136, "percentage": 72.6, "elapsed_time": "3:20:23", "remaining_time": "1:15:37", "throughput": 786.93, "total_tokens": 9461528} {"current_steps": 29045, "total_steps": 40000, "loss": 0.1337, "lr": 8.698201511189048e-06, "epoch": 23.7687269750307, "percentage": 72.61, "elapsed_time": "3:20:25", "remaining_time": "1:15:35", "throughput": 786.95, "total_tokens": 9463160} {"current_steps": 29050, "total_steps": 40000, "loss": 0.1331, "lr": 8.690759578444649e-06, "epoch": 23.77282030290626, "percentage": 72.62, "elapsed_time": "3:20:26", "remaining_time": "1:15:33", "throughput": 786.98, "total_tokens": 9464808} {"current_steps": 29055, "total_steps": 40000, "loss": 0.2533, "lr": 8.68332016079008e-06, "epoch": 23.776913630781827, "percentage": 72.64, "elapsed_time": "3:20:28", "remaining_time": "1:15:31", "throughput": 787.0, "total_tokens": 9466472} {"current_steps": 29060, "total_steps": 40000, "loss": 0.1334, "lr": 8.6758832593726e-06, "epoch": 23.78100695865739, "percentage": 72.65, "elapsed_time": "3:20:30", "remaining_time": "1:15:28", "throughput": 787.02, "total_tokens": 9468072} {"current_steps": 29065, "total_steps": 40000, "loss": 0.1032, "lr": 8.668448875339053e-06, "epoch": 23.785100286532952, "percentage": 72.66, "elapsed_time": "3:20:31", "remaining_time": "1:15:26", "throughput": 787.05, "total_tokens": 9469784} {"current_steps": 29070, "total_steps": 40000, "loss": 0.1856, "lr": 8.661017009835933e-06, "epoch": 23.789193614408514, "percentage": 72.67, "elapsed_time": "3:20:33", "remaining_time": "1:15:24", "throughput": 787.08, "total_tokens": 9471432} {"current_steps": 29075, "total_steps": 40000, "loss": 0.0804, "lr": 8.653587664009311e-06, "epoch": 23.793286942284077, "percentage": 72.69, "elapsed_time": "3:20:35", "remaining_time": "1:15:22", "throughput": 787.11, "total_tokens": 9473160} {"current_steps": 29080, "total_steps": 40000, "loss": 0.1415, "lr": 8.646160839004902e-06, "epoch": 23.79738027015964, "percentage": 72.7, "elapsed_time": "3:20:37", "remaining_time": "1:15:20", "throughput": 787.13, "total_tokens": 9474776} {"current_steps": 29085, "total_steps": 40000, "loss": 0.2023, "lr": 8.638736535967998e-06, "epoch": 23.8014735980352, "percentage": 72.71, "elapsed_time": "3:20:38", "remaining_time": "1:15:17", "throughput": 787.15, "total_tokens": 9476360} {"current_steps": 29090, "total_steps": 40000, "loss": 0.1556, "lr": 8.631314756043535e-06, "epoch": 23.805566925910764, "percentage": 72.72, "elapsed_time": "3:20:40", "remaining_time": "1:15:15", "throughput": 787.18, "total_tokens": 9478040} {"current_steps": 29095, "total_steps": 40000, "loss": 0.1856, "lr": 8.62389550037603e-06, "epoch": 23.80966025378633, "percentage": 72.74, "elapsed_time": "3:20:42", "remaining_time": "1:15:13", "throughput": 787.2, "total_tokens": 9479704} {"current_steps": 29100, "total_steps": 40000, "loss": 0.2058, "lr": 8.616478770109646e-06, "epoch": 23.813753581661892, "percentage": 72.75, "elapsed_time": "3:20:43", "remaining_time": "1:15:11", "throughput": 787.23, "total_tokens": 9481352} {"current_steps": 29105, "total_steps": 40000, "loss": 0.1728, "lr": 8.609064566388111e-06, "epoch": 23.817846909537455, "percentage": 72.76, "elapsed_time": "3:20:45", "remaining_time": "1:15:09", "throughput": 787.25, "total_tokens": 9482968} {"current_steps": 29110, "total_steps": 40000, "loss": 0.1863, "lr": 8.601652890354815e-06, "epoch": 23.821940237413017, "percentage": 72.78, "elapsed_time": "3:20:47", "remaining_time": "1:15:06", "throughput": 787.27, "total_tokens": 9484568} {"current_steps": 29115, "total_steps": 40000, "loss": 0.2185, "lr": 8.594243743152705e-06, "epoch": 23.82603356528858, "percentage": 72.79, "elapsed_time": "3:20:49", "remaining_time": "1:15:04", "throughput": 787.29, "total_tokens": 9486184} {"current_steps": 29120, "total_steps": 40000, "loss": 0.1728, "lr": 8.58683712592438e-06, "epoch": 23.83012689316414, "percentage": 72.8, "elapsed_time": "3:20:50", "remaining_time": "1:15:02", "throughput": 787.31, "total_tokens": 9487784} {"current_steps": 29125, "total_steps": 40000, "loss": 0.228, "lr": 8.579433039812037e-06, "epoch": 23.834220221039704, "percentage": 72.81, "elapsed_time": "3:20:52", "remaining_time": "1:15:00", "throughput": 787.34, "total_tokens": 9489448} {"current_steps": 29130, "total_steps": 40000, "loss": 0.1687, "lr": 8.572031485957466e-06, "epoch": 23.838313548915266, "percentage": 72.82, "elapsed_time": "3:20:54", "remaining_time": "1:14:58", "throughput": 787.36, "total_tokens": 9491128} {"current_steps": 29135, "total_steps": 40000, "loss": 0.0888, "lr": 8.564632465502084e-06, "epoch": 23.842406876790832, "percentage": 72.84, "elapsed_time": "3:20:56", "remaining_time": "1:14:55", "throughput": 787.38, "total_tokens": 9492728} {"current_steps": 29140, "total_steps": 40000, "loss": 0.2263, "lr": 8.557235979586928e-06, "epoch": 23.846500204666395, "percentage": 72.85, "elapsed_time": "3:20:57", "remaining_time": "1:14:53", "throughput": 787.41, "total_tokens": 9494360} {"current_steps": 29145, "total_steps": 40000, "loss": 0.2172, "lr": 8.549842029352606e-06, "epoch": 23.850593532541957, "percentage": 72.86, "elapsed_time": "3:20:59", "remaining_time": "1:14:51", "throughput": 787.43, "total_tokens": 9495976} {"current_steps": 29150, "total_steps": 40000, "loss": 0.3032, "lr": 8.542450615939376e-06, "epoch": 23.85468686041752, "percentage": 72.88, "elapsed_time": "3:21:01", "remaining_time": "1:14:49", "throughput": 787.45, "total_tokens": 9497592} {"current_steps": 29155, "total_steps": 40000, "loss": 0.1805, "lr": 8.535061740487082e-06, "epoch": 23.858780188293082, "percentage": 72.89, "elapsed_time": "3:21:02", "remaining_time": "1:14:47", "throughput": 787.47, "total_tokens": 9499176} {"current_steps": 29160, "total_steps": 40000, "loss": 0.1646, "lr": 8.527675404135168e-06, "epoch": 23.862873516168644, "percentage": 72.9, "elapsed_time": "3:21:04", "remaining_time": "1:14:44", "throughput": 787.49, "total_tokens": 9500792} {"current_steps": 29165, "total_steps": 40000, "loss": 0.2424, "lr": 8.520291608022724e-06, "epoch": 23.866966844044207, "percentage": 72.91, "elapsed_time": "3:21:06", "remaining_time": "1:14:42", "throughput": 787.52, "total_tokens": 9502488} {"current_steps": 29170, "total_steps": 40000, "loss": 0.1439, "lr": 8.512910353288398e-06, "epoch": 23.871060171919773, "percentage": 72.92, "elapsed_time": "3:21:08", "remaining_time": "1:14:40", "throughput": 787.54, "total_tokens": 9504104} {"current_steps": 29175, "total_steps": 40000, "loss": 0.1224, "lr": 8.505531641070486e-06, "epoch": 23.875153499795335, "percentage": 72.94, "elapsed_time": "3:21:09", "remaining_time": "1:14:38", "throughput": 787.57, "total_tokens": 9505784} {"current_steps": 29180, "total_steps": 40000, "loss": 0.3132, "lr": 8.498155472506885e-06, "epoch": 23.879246827670897, "percentage": 72.95, "elapsed_time": "3:21:11", "remaining_time": "1:14:36", "throughput": 787.6, "total_tokens": 9507448} {"current_steps": 29185, "total_steps": 40000, "loss": 0.1085, "lr": 8.49078184873508e-06, "epoch": 23.88334015554646, "percentage": 72.96, "elapsed_time": "3:21:13", "remaining_time": "1:14:33", "throughput": 787.62, "total_tokens": 9509128} {"current_steps": 29190, "total_steps": 40000, "loss": 0.1816, "lr": 8.483410770892188e-06, "epoch": 23.887433483422022, "percentage": 72.97, "elapsed_time": "3:21:14", "remaining_time": "1:14:31", "throughput": 787.64, "total_tokens": 9510744} {"current_steps": 29195, "total_steps": 40000, "loss": 0.1681, "lr": 8.476042240114909e-06, "epoch": 23.891526811297584, "percentage": 72.99, "elapsed_time": "3:21:16", "remaining_time": "1:14:29", "throughput": 787.67, "total_tokens": 9512376} {"current_steps": 29200, "total_steps": 40000, "loss": 0.1345, "lr": 8.468676257539568e-06, "epoch": 23.895620139173147, "percentage": 73.0, "elapsed_time": "3:21:18", "remaining_time": "1:14:27", "throughput": 787.69, "total_tokens": 9513976} {"current_steps": 29200, "total_steps": 40000, "eval_loss": 0.21363358199596405, "epoch": 23.895620139173147, "percentage": 73.0, "elapsed_time": "3:21:30", "remaining_time": "1:14:31", "throughput": 786.87, "total_tokens": 9513976} {"current_steps": 29205, "total_steps": 40000, "loss": 0.1748, "lr": 8.4613128243021e-06, "epoch": 23.89971346704871, "percentage": 73.01, "elapsed_time": "3:21:34", "remaining_time": "1:14:30", "throughput": 786.78, "total_tokens": 9515608} {"current_steps": 29210, "total_steps": 40000, "loss": 0.1858, "lr": 8.453951941538028e-06, "epoch": 23.90380679492427, "percentage": 73.02, "elapsed_time": "3:21:36", "remaining_time": "1:14:28", "throughput": 786.81, "total_tokens": 9517304} {"current_steps": 29215, "total_steps": 40000, "loss": 0.1346, "lr": 8.446593610382495e-06, "epoch": 23.907900122799838, "percentage": 73.04, "elapsed_time": "3:21:37", "remaining_time": "1:14:26", "throughput": 786.83, "total_tokens": 9518936} {"current_steps": 29220, "total_steps": 40000, "loss": 0.1194, "lr": 8.439237831970259e-06, "epoch": 23.9119934506754, "percentage": 73.05, "elapsed_time": "3:21:39", "remaining_time": "1:14:23", "throughput": 786.85, "total_tokens": 9520568} {"current_steps": 29225, "total_steps": 40000, "loss": 0.1432, "lr": 8.431884607435667e-06, "epoch": 23.916086778550962, "percentage": 73.06, "elapsed_time": "3:21:41", "remaining_time": "1:14:21", "throughput": 786.88, "total_tokens": 9522216} {"current_steps": 29230, "total_steps": 40000, "loss": 0.1947, "lr": 8.424533937912665e-06, "epoch": 23.920180106426525, "percentage": 73.08, "elapsed_time": "3:21:42", "remaining_time": "1:14:19", "throughput": 786.9, "total_tokens": 9523816} {"current_steps": 29235, "total_steps": 40000, "loss": 0.1536, "lr": 8.41718582453484e-06, "epoch": 23.924273434302087, "percentage": 73.09, "elapsed_time": "3:21:44", "remaining_time": "1:14:17", "throughput": 786.92, "total_tokens": 9525448} {"current_steps": 29240, "total_steps": 40000, "loss": 0.164, "lr": 8.409840268435346e-06, "epoch": 23.92836676217765, "percentage": 73.1, "elapsed_time": "3:21:46", "remaining_time": "1:14:15", "throughput": 786.94, "total_tokens": 9527064} {"current_steps": 29245, "total_steps": 40000, "loss": 0.1397, "lr": 8.402497270746976e-06, "epoch": 23.932460090053212, "percentage": 73.11, "elapsed_time": "3:21:48", "remaining_time": "1:14:12", "throughput": 786.96, "total_tokens": 9528664} {"current_steps": 29250, "total_steps": 40000, "loss": 0.1119, "lr": 8.395156832602095e-06, "epoch": 23.936553417928778, "percentage": 73.12, "elapsed_time": "3:21:49", "remaining_time": "1:14:10", "throughput": 786.98, "total_tokens": 9530296} {"current_steps": 29255, "total_steps": 40000, "loss": 0.2443, "lr": 8.387818955132707e-06, "epoch": 23.94064674580434, "percentage": 73.14, "elapsed_time": "3:21:51", "remaining_time": "1:14:08", "throughput": 787.01, "total_tokens": 9531960} {"current_steps": 29260, "total_steps": 40000, "loss": 0.1041, "lr": 8.38048363947039e-06, "epoch": 23.944740073679903, "percentage": 73.15, "elapsed_time": "3:21:53", "remaining_time": "1:14:06", "throughput": 787.03, "total_tokens": 9533576} {"current_steps": 29265, "total_steps": 40000, "loss": 0.1559, "lr": 8.373150886746351e-06, "epoch": 23.948833401555465, "percentage": 73.16, "elapsed_time": "3:21:55", "remaining_time": "1:14:04", "throughput": 787.06, "total_tokens": 9535256} {"current_steps": 29270, "total_steps": 40000, "loss": 0.1881, "lr": 8.365820698091397e-06, "epoch": 23.952926729431027, "percentage": 73.17, "elapsed_time": "3:21:56", "remaining_time": "1:14:01", "throughput": 787.09, "total_tokens": 9536952} {"current_steps": 29275, "total_steps": 40000, "loss": 0.072, "lr": 8.358493074635922e-06, "epoch": 23.95702005730659, "percentage": 73.19, "elapsed_time": "3:21:58", "remaining_time": "1:13:59", "throughput": 787.11, "total_tokens": 9538552} {"current_steps": 29280, "total_steps": 40000, "loss": 0.1764, "lr": 8.351168017509948e-06, "epoch": 23.961113385182152, "percentage": 73.2, "elapsed_time": "3:22:00", "remaining_time": "1:13:57", "throughput": 787.13, "total_tokens": 9540152} {"current_steps": 29285, "total_steps": 40000, "loss": 0.1916, "lr": 8.343845527843094e-06, "epoch": 23.965206713057714, "percentage": 73.21, "elapsed_time": "3:22:01", "remaining_time": "1:13:55", "throughput": 787.16, "total_tokens": 9541864} {"current_steps": 29290, "total_steps": 40000, "loss": 0.1934, "lr": 8.336525606764566e-06, "epoch": 23.96930004093328, "percentage": 73.22, "elapsed_time": "3:22:03", "remaining_time": "1:13:53", "throughput": 787.18, "total_tokens": 9543528} {"current_steps": 29295, "total_steps": 40000, "loss": 0.3157, "lr": 8.329208255403204e-06, "epoch": 23.973393368808843, "percentage": 73.24, "elapsed_time": "3:22:05", "remaining_time": "1:13:50", "throughput": 787.2, "total_tokens": 9545112} {"current_steps": 29300, "total_steps": 40000, "loss": 0.2445, "lr": 8.321893474887426e-06, "epoch": 23.977486696684405, "percentage": 73.25, "elapsed_time": "3:22:07", "remaining_time": "1:13:48", "throughput": 787.22, "total_tokens": 9546728} {"current_steps": 29305, "total_steps": 40000, "loss": 0.2709, "lr": 8.31458126634526e-06, "epoch": 23.981580024559968, "percentage": 73.26, "elapsed_time": "3:22:08", "remaining_time": "1:13:46", "throughput": 787.25, "total_tokens": 9548376} {"current_steps": 29310, "total_steps": 40000, "loss": 0.2785, "lr": 8.30727163090435e-06, "epoch": 23.98567335243553, "percentage": 73.28, "elapsed_time": "3:22:10", "remaining_time": "1:13:44", "throughput": 787.27, "total_tokens": 9550056} {"current_steps": 29315, "total_steps": 40000, "loss": 0.1879, "lr": 8.29996456969192e-06, "epoch": 23.989766680311092, "percentage": 73.29, "elapsed_time": "3:22:12", "remaining_time": "1:13:42", "throughput": 787.3, "total_tokens": 9551736} {"current_steps": 29320, "total_steps": 40000, "loss": 0.1359, "lr": 8.292660083834818e-06, "epoch": 23.993860008186655, "percentage": 73.3, "elapsed_time": "3:22:13", "remaining_time": "1:13:39", "throughput": 787.33, "total_tokens": 9553416} {"current_steps": 29325, "total_steps": 40000, "loss": 0.1885, "lr": 8.2853581744595e-06, "epoch": 23.997953336062217, "percentage": 73.31, "elapsed_time": "3:22:15", "remaining_time": "1:13:37", "throughput": 787.35, "total_tokens": 9555096} {"current_steps": 29330, "total_steps": 40000, "loss": 0.2394, "lr": 8.278058842691991e-06, "epoch": 24.001637331150224, "percentage": 73.32, "elapsed_time": "3:22:17", "remaining_time": "1:13:35", "throughput": 787.35, "total_tokens": 9556520} {"current_steps": 29335, "total_steps": 40000, "loss": 0.1542, "lr": 8.27076208965796e-06, "epoch": 24.005730659025787, "percentage": 73.34, "elapsed_time": "3:22:19", "remaining_time": "1:13:33", "throughput": 787.37, "total_tokens": 9558200} {"current_steps": 29340, "total_steps": 40000, "loss": 0.1287, "lr": 8.263467916482637e-06, "epoch": 24.009823986901353, "percentage": 73.35, "elapsed_time": "3:22:21", "remaining_time": "1:13:31", "throughput": 787.39, "total_tokens": 9559784} {"current_steps": 29345, "total_steps": 40000, "loss": 0.1184, "lr": 8.256176324290885e-06, "epoch": 24.013917314776915, "percentage": 73.36, "elapsed_time": "3:22:22", "remaining_time": "1:13:28", "throughput": 787.41, "total_tokens": 9561352} {"current_steps": 29350, "total_steps": 40000, "loss": 0.2076, "lr": 8.248887314207168e-06, "epoch": 24.018010642652477, "percentage": 73.38, "elapsed_time": "3:22:24", "remaining_time": "1:13:26", "throughput": 787.43, "total_tokens": 9562936} {"current_steps": 29355, "total_steps": 40000, "loss": 0.2019, "lr": 8.24160088735553e-06, "epoch": 24.02210397052804, "percentage": 73.39, "elapsed_time": "3:22:26", "remaining_time": "1:13:24", "throughput": 787.45, "total_tokens": 9564552} {"current_steps": 29360, "total_steps": 40000, "loss": 0.1499, "lr": 8.234317044859629e-06, "epoch": 24.026197298403602, "percentage": 73.4, "elapsed_time": "3:22:27", "remaining_time": "1:13:22", "throughput": 787.48, "total_tokens": 9566216} {"current_steps": 29365, "total_steps": 40000, "loss": 0.1353, "lr": 8.227035787842744e-06, "epoch": 24.030290626279164, "percentage": 73.41, "elapsed_time": "3:22:29", "remaining_time": "1:13:20", "throughput": 787.51, "total_tokens": 9567928} {"current_steps": 29370, "total_steps": 40000, "loss": 0.1981, "lr": 8.219757117427721e-06, "epoch": 24.034383954154727, "percentage": 73.42, "elapsed_time": "3:22:31", "remaining_time": "1:13:17", "throughput": 787.53, "total_tokens": 9569608} {"current_steps": 29375, "total_steps": 40000, "loss": 0.1965, "lr": 8.212481034737014e-06, "epoch": 24.03847728203029, "percentage": 73.44, "elapsed_time": "3:22:33", "remaining_time": "1:13:15", "throughput": 787.56, "total_tokens": 9571240} {"current_steps": 29380, "total_steps": 40000, "loss": 0.1784, "lr": 8.205207540892707e-06, "epoch": 24.042570609905855, "percentage": 73.45, "elapsed_time": "3:22:34", "remaining_time": "1:13:13", "throughput": 787.58, "total_tokens": 9572856} {"current_steps": 29385, "total_steps": 40000, "loss": 0.2006, "lr": 8.197936637016442e-06, "epoch": 24.046663937781418, "percentage": 73.46, "elapsed_time": "3:22:36", "remaining_time": "1:13:11", "throughput": 787.6, "total_tokens": 9574504} {"current_steps": 29390, "total_steps": 40000, "loss": 0.1685, "lr": 8.190668324229508e-06, "epoch": 24.05075726565698, "percentage": 73.47, "elapsed_time": "3:22:38", "remaining_time": "1:13:09", "throughput": 787.63, "total_tokens": 9576152} {"current_steps": 29395, "total_steps": 40000, "loss": 0.2917, "lr": 8.183402603652749e-06, "epoch": 24.054850593532542, "percentage": 73.49, "elapsed_time": "3:22:39", "remaining_time": "1:13:07", "throughput": 787.66, "total_tokens": 9577880} {"current_steps": 29400, "total_steps": 40000, "loss": 0.1873, "lr": 8.176139476406635e-06, "epoch": 24.058943921408105, "percentage": 73.5, "elapsed_time": "3:22:41", "remaining_time": "1:13:04", "throughput": 787.67, "total_tokens": 9579416} {"current_steps": 29400, "total_steps": 40000, "eval_loss": 0.21184076368808746, "epoch": 24.058943921408105, "percentage": 73.5, "elapsed_time": "3:22:54", "remaining_time": "1:13:09", "throughput": 786.86, "total_tokens": 9579416} {"current_steps": 29405, "total_steps": 40000, "loss": 0.1109, "lr": 8.16887894361125e-06, "epoch": 24.063037249283667, "percentage": 73.51, "elapsed_time": "3:22:57", "remaining_time": "1:13:07", "throughput": 786.78, "total_tokens": 9581048} {"current_steps": 29410, "total_steps": 40000, "loss": 0.1621, "lr": 8.161621006386233e-06, "epoch": 24.06713057715923, "percentage": 73.52, "elapsed_time": "3:22:59", "remaining_time": "1:13:05", "throughput": 786.8, "total_tokens": 9582632} {"current_steps": 29415, "total_steps": 40000, "loss": 0.1494, "lr": 8.154365665850869e-06, "epoch": 24.071223905034792, "percentage": 73.54, "elapsed_time": "3:23:00", "remaining_time": "1:13:03", "throughput": 786.82, "total_tokens": 9584248} {"current_steps": 29420, "total_steps": 40000, "loss": 0.2227, "lr": 8.147112923124005e-06, "epoch": 24.075317232910358, "percentage": 73.55, "elapsed_time": "3:23:02", "remaining_time": "1:13:01", "throughput": 786.84, "total_tokens": 9585816} {"current_steps": 29425, "total_steps": 40000, "loss": 0.2008, "lr": 8.13986277932412e-06, "epoch": 24.07941056078592, "percentage": 73.56, "elapsed_time": "3:23:04", "remaining_time": "1:12:58", "throughput": 786.86, "total_tokens": 9587432} {"current_steps": 29430, "total_steps": 40000, "loss": 0.0938, "lr": 8.132615235569277e-06, "epoch": 24.083503888661483, "percentage": 73.58, "elapsed_time": "3:23:06", "remaining_time": "1:12:56", "throughput": 786.89, "total_tokens": 9589080} {"current_steps": 29435, "total_steps": 40000, "loss": 0.1218, "lr": 8.125370292977124e-06, "epoch": 24.087597216537045, "percentage": 73.59, "elapsed_time": "3:23:07", "remaining_time": "1:12:54", "throughput": 786.91, "total_tokens": 9590664} {"current_steps": 29440, "total_steps": 40000, "loss": 0.2157, "lr": 8.118127952664944e-06, "epoch": 24.091690544412607, "percentage": 73.6, "elapsed_time": "3:23:09", "remaining_time": "1:12:52", "throughput": 786.93, "total_tokens": 9592328} {"current_steps": 29445, "total_steps": 40000, "loss": 0.1195, "lr": 8.110888215749574e-06, "epoch": 24.09578387228817, "percentage": 73.61, "elapsed_time": "3:23:11", "remaining_time": "1:12:50", "throughput": 786.95, "total_tokens": 9593944} {"current_steps": 29450, "total_steps": 40000, "loss": 0.1067, "lr": 8.10365108334749e-06, "epoch": 24.099877200163732, "percentage": 73.62, "elapsed_time": "3:23:12", "remaining_time": "1:12:47", "throughput": 786.98, "total_tokens": 9595608} {"current_steps": 29455, "total_steps": 40000, "loss": 0.1245, "lr": 8.096416556574743e-06, "epoch": 24.103970528039294, "percentage": 73.64, "elapsed_time": "3:23:14", "remaining_time": "1:12:45", "throughput": 787.0, "total_tokens": 9597224} {"current_steps": 29460, "total_steps": 40000, "loss": 0.1621, "lr": 8.08918463654698e-06, "epoch": 24.10806385591486, "percentage": 73.65, "elapsed_time": "3:23:16", "remaining_time": "1:12:43", "throughput": 787.02, "total_tokens": 9598840} {"current_steps": 29465, "total_steps": 40000, "loss": 0.1495, "lr": 8.081955324379458e-06, "epoch": 24.112157183790423, "percentage": 73.66, "elapsed_time": "3:23:18", "remaining_time": "1:12:41", "throughput": 787.05, "total_tokens": 9600552} {"current_steps": 29470, "total_steps": 40000, "loss": 0.1517, "lr": 8.074728621187039e-06, "epoch": 24.116250511665985, "percentage": 73.67, "elapsed_time": "3:23:19", "remaining_time": "1:12:39", "throughput": 787.08, "total_tokens": 9602232} {"current_steps": 29475, "total_steps": 40000, "loss": 0.1209, "lr": 8.067504528084158e-06, "epoch": 24.120343839541547, "percentage": 73.69, "elapsed_time": "3:23:21", "remaining_time": "1:12:36", "throughput": 787.09, "total_tokens": 9603768} {"current_steps": 29480, "total_steps": 40000, "loss": 0.1569, "lr": 8.060283046184861e-06, "epoch": 24.12443716741711, "percentage": 73.7, "elapsed_time": "3:23:23", "remaining_time": "1:12:34", "throughput": 787.11, "total_tokens": 9605384} {"current_steps": 29485, "total_steps": 40000, "loss": 0.0804, "lr": 8.053064176602806e-06, "epoch": 24.128530495292672, "percentage": 73.71, "elapsed_time": "3:23:25", "remaining_time": "1:12:32", "throughput": 787.14, "total_tokens": 9607032} {"current_steps": 29490, "total_steps": 40000, "loss": 0.2299, "lr": 8.045847920451216e-06, "epoch": 24.132623823168235, "percentage": 73.72, "elapsed_time": "3:23:26", "remaining_time": "1:12:30", "throughput": 787.17, "total_tokens": 9608760} {"current_steps": 29495, "total_steps": 40000, "loss": 0.2779, "lr": 8.038634278842944e-06, "epoch": 24.136717151043797, "percentage": 73.74, "elapsed_time": "3:23:28", "remaining_time": "1:12:28", "throughput": 787.19, "total_tokens": 9610344} {"current_steps": 29500, "total_steps": 40000, "loss": 0.1636, "lr": 8.031423252890408e-06, "epoch": 24.140810478919363, "percentage": 73.75, "elapsed_time": "3:23:30", "remaining_time": "1:12:25", "throughput": 787.21, "total_tokens": 9612024} {"current_steps": 29505, "total_steps": 40000, "loss": 0.1344, "lr": 8.024214843705646e-06, "epoch": 24.144903806794925, "percentage": 73.76, "elapsed_time": "3:23:31", "remaining_time": "1:12:23", "throughput": 787.23, "total_tokens": 9613624} {"current_steps": 29510, "total_steps": 40000, "loss": 0.1962, "lr": 8.017009052400295e-06, "epoch": 24.148997134670488, "percentage": 73.78, "elapsed_time": "3:23:33", "remaining_time": "1:12:21", "throughput": 787.25, "total_tokens": 9615208} {"current_steps": 29515, "total_steps": 40000, "loss": 0.2118, "lr": 8.00980588008557e-06, "epoch": 24.15309046254605, "percentage": 73.79, "elapsed_time": "3:23:35", "remaining_time": "1:12:19", "throughput": 787.28, "total_tokens": 9616840} {"current_steps": 29520, "total_steps": 40000, "loss": 0.1281, "lr": 8.002605327872282e-06, "epoch": 24.157183790421612, "percentage": 73.8, "elapsed_time": "3:23:37", "remaining_time": "1:12:17", "throughput": 787.3, "total_tokens": 9618456} {"current_steps": 29525, "total_steps": 40000, "loss": 0.2268, "lr": 7.995407396870862e-06, "epoch": 24.161277118297175, "percentage": 73.81, "elapsed_time": "3:23:38", "remaining_time": "1:12:15", "throughput": 787.32, "total_tokens": 9620088} {"current_steps": 29530, "total_steps": 40000, "loss": 0.2828, "lr": 7.988212088191307e-06, "epoch": 24.165370446172737, "percentage": 73.83, "elapsed_time": "3:23:40", "remaining_time": "1:12:12", "throughput": 787.34, "total_tokens": 9621736} {"current_steps": 29535, "total_steps": 40000, "loss": 0.2124, "lr": 7.98101940294324e-06, "epoch": 24.1694637740483, "percentage": 73.84, "elapsed_time": "3:23:42", "remaining_time": "1:12:10", "throughput": 787.37, "total_tokens": 9623352} {"current_steps": 29540, "total_steps": 40000, "loss": 0.1863, "lr": 7.973829342235847e-06, "epoch": 24.173557101923866, "percentage": 73.85, "elapsed_time": "3:23:43", "remaining_time": "1:12:08", "throughput": 787.39, "total_tokens": 9624968} {"current_steps": 29545, "total_steps": 40000, "loss": 0.1517, "lr": 7.966641907177936e-06, "epoch": 24.177650429799428, "percentage": 73.86, "elapsed_time": "3:23:45", "remaining_time": "1:12:06", "throughput": 787.41, "total_tokens": 9626568} {"current_steps": 29550, "total_steps": 40000, "loss": 0.2018, "lr": 7.959457098877901e-06, "epoch": 24.18174375767499, "percentage": 73.88, "elapsed_time": "3:23:47", "remaining_time": "1:12:04", "throughput": 787.43, "total_tokens": 9628184} {"current_steps": 29555, "total_steps": 40000, "loss": 0.1926, "lr": 7.952274918443719e-06, "epoch": 24.185837085550553, "percentage": 73.89, "elapsed_time": "3:23:49", "remaining_time": "1:12:01", "throughput": 787.45, "total_tokens": 9629880} {"current_steps": 29560, "total_steps": 40000, "loss": 0.1107, "lr": 7.945095366982983e-06, "epoch": 24.189930413426115, "percentage": 73.9, "elapsed_time": "3:23:50", "remaining_time": "1:11:59", "throughput": 787.48, "total_tokens": 9631496} {"current_steps": 29565, "total_steps": 40000, "loss": 0.1568, "lr": 7.937918445602871e-06, "epoch": 24.194023741301677, "percentage": 73.91, "elapsed_time": "3:23:52", "remaining_time": "1:11:57", "throughput": 787.5, "total_tokens": 9633192} {"current_steps": 29570, "total_steps": 40000, "loss": 0.2069, "lr": 7.930744155410145e-06, "epoch": 24.19811706917724, "percentage": 73.92, "elapsed_time": "3:23:54", "remaining_time": "1:11:55", "throughput": 787.52, "total_tokens": 9634792} {"current_steps": 29575, "total_steps": 40000, "loss": 0.1423, "lr": 7.923572497511181e-06, "epoch": 24.202210397052802, "percentage": 73.94, "elapsed_time": "3:23:55", "remaining_time": "1:11:53", "throughput": 787.55, "total_tokens": 9636472} {"current_steps": 29580, "total_steps": 40000, "loss": 0.0954, "lr": 7.916403473011927e-06, "epoch": 24.206303724928368, "percentage": 73.95, "elapsed_time": "3:23:57", "remaining_time": "1:11:50", "throughput": 787.57, "total_tokens": 9638088} {"current_steps": 29585, "total_steps": 40000, "loss": 0.169, "lr": 7.909237083017953e-06, "epoch": 24.21039705280393, "percentage": 73.96, "elapsed_time": "3:23:59", "remaining_time": "1:11:48", "throughput": 787.6, "total_tokens": 9639720} {"current_steps": 29590, "total_steps": 40000, "loss": 0.1282, "lr": 7.902073328634389e-06, "epoch": 24.214490380679493, "percentage": 73.98, "elapsed_time": "3:24:01", "remaining_time": "1:11:46", "throughput": 787.62, "total_tokens": 9641336} {"current_steps": 29595, "total_steps": 40000, "loss": 0.1648, "lr": 7.894912210965987e-06, "epoch": 24.218583708555055, "percentage": 73.99, "elapsed_time": "3:24:02", "remaining_time": "1:11:44", "throughput": 787.64, "total_tokens": 9643000} {"current_steps": 29600, "total_steps": 40000, "loss": 0.1737, "lr": 7.887753731117075e-06, "epoch": 24.222677036430618, "percentage": 74.0, "elapsed_time": "3:24:04", "remaining_time": "1:11:42", "throughput": 787.67, "total_tokens": 9644664} {"current_steps": 29600, "total_steps": 40000, "eval_loss": 0.2130264788866043, "epoch": 24.222677036430618, "percentage": 74.0, "elapsed_time": "3:24:17", "remaining_time": "1:11:46", "throughput": 786.87, "total_tokens": 9644664} {"current_steps": 29605, "total_steps": 40000, "loss": 0.2546, "lr": 7.880597890191587e-06, "epoch": 24.22677036430618, "percentage": 74.01, "elapsed_time": "3:24:20", "remaining_time": "1:11:44", "throughput": 786.79, "total_tokens": 9646312} {"current_steps": 29610, "total_steps": 40000, "loss": 0.2042, "lr": 7.873444689293036e-06, "epoch": 24.230863692181742, "percentage": 74.02, "elapsed_time": "3:24:21", "remaining_time": "1:11:42", "throughput": 786.82, "total_tokens": 9647928} {"current_steps": 29615, "total_steps": 40000, "loss": 0.183, "lr": 7.866294129524548e-06, "epoch": 24.23495702005731, "percentage": 74.04, "elapsed_time": "3:24:23", "remaining_time": "1:11:40", "throughput": 786.84, "total_tokens": 9649560} {"current_steps": 29620, "total_steps": 40000, "loss": 0.1252, "lr": 7.859146211988811e-06, "epoch": 24.23905034793287, "percentage": 74.05, "elapsed_time": "3:24:25", "remaining_time": "1:11:38", "throughput": 786.87, "total_tokens": 9651240} {"current_steps": 29625, "total_steps": 40000, "loss": 0.1585, "lr": 7.852000937788134e-06, "epoch": 24.243143675808433, "percentage": 74.06, "elapsed_time": "3:24:27", "remaining_time": "1:11:36", "throughput": 786.89, "total_tokens": 9652872} {"current_steps": 29630, "total_steps": 40000, "loss": 0.1075, "lr": 7.844858308024416e-06, "epoch": 24.247237003683995, "percentage": 74.08, "elapsed_time": "3:24:28", "remaining_time": "1:11:33", "throughput": 786.91, "total_tokens": 9654520} {"current_steps": 29635, "total_steps": 40000, "loss": 0.1709, "lr": 7.837718323799122e-06, "epoch": 24.251330331559558, "percentage": 74.09, "elapsed_time": "3:24:30", "remaining_time": "1:11:31", "throughput": 786.93, "total_tokens": 9656152} {"current_steps": 29640, "total_steps": 40000, "loss": 0.1283, "lr": 7.83058098621334e-06, "epoch": 24.25542365943512, "percentage": 74.1, "elapsed_time": "3:24:32", "remaining_time": "1:11:29", "throughput": 786.95, "total_tokens": 9657720} {"current_steps": 29645, "total_steps": 40000, "loss": 0.2284, "lr": 7.823446296367739e-06, "epoch": 24.259516987310683, "percentage": 74.11, "elapsed_time": "3:24:34", "remaining_time": "1:11:27", "throughput": 786.97, "total_tokens": 9659320} {"current_steps": 29650, "total_steps": 40000, "loss": 0.2036, "lr": 7.81631425536257e-06, "epoch": 24.263610315186245, "percentage": 74.12, "elapsed_time": "3:24:35", "remaining_time": "1:11:25", "throughput": 787.0, "total_tokens": 9660968} {"current_steps": 29655, "total_steps": 40000, "loss": 0.284, "lr": 7.809184864297689e-06, "epoch": 24.26770364306181, "percentage": 74.14, "elapsed_time": "3:24:37", "remaining_time": "1:11:22", "throughput": 787.02, "total_tokens": 9662584} {"current_steps": 29660, "total_steps": 40000, "loss": 0.1364, "lr": 7.802058124272532e-06, "epoch": 24.271796970937373, "percentage": 74.15, "elapsed_time": "3:24:39", "remaining_time": "1:11:20", "throughput": 787.04, "total_tokens": 9664248} {"current_steps": 29665, "total_steps": 40000, "loss": 0.1945, "lr": 7.79493403638614e-06, "epoch": 24.275890298812936, "percentage": 74.16, "elapsed_time": "3:24:40", "remaining_time": "1:11:18", "throughput": 787.06, "total_tokens": 9665848} {"current_steps": 29670, "total_steps": 40000, "loss": 0.1381, "lr": 7.787812601737132e-06, "epoch": 24.279983626688498, "percentage": 74.17, "elapsed_time": "3:24:42", "remaining_time": "1:11:16", "throughput": 787.09, "total_tokens": 9667544} {"current_steps": 29675, "total_steps": 40000, "loss": 0.1922, "lr": 7.780693821423715e-06, "epoch": 24.28407695456406, "percentage": 74.19, "elapsed_time": "3:24:44", "remaining_time": "1:11:14", "throughput": 787.1, "total_tokens": 9669208} {"current_steps": 29680, "total_steps": 40000, "loss": 0.0856, "lr": 7.773577696543705e-06, "epoch": 24.288170282439623, "percentage": 74.2, "elapsed_time": "3:24:46", "remaining_time": "1:11:12", "throughput": 787.12, "total_tokens": 9670840} {"current_steps": 29685, "total_steps": 40000, "loss": 0.2646, "lr": 7.7664642281945e-06, "epoch": 24.292263610315185, "percentage": 74.21, "elapsed_time": "3:24:48", "remaining_time": "1:11:09", "throughput": 787.15, "total_tokens": 9672552} {"current_steps": 29690, "total_steps": 40000, "loss": 0.2424, "lr": 7.759353417473072e-06, "epoch": 24.296356938190748, "percentage": 74.22, "elapsed_time": "3:24:49", "remaining_time": "1:11:07", "throughput": 787.17, "total_tokens": 9674168} {"current_steps": 29695, "total_steps": 40000, "loss": 0.1749, "lr": 7.752245265476016e-06, "epoch": 24.300450266066314, "percentage": 74.24, "elapsed_time": "3:24:51", "remaining_time": "1:11:05", "throughput": 787.19, "total_tokens": 9675768} {"current_steps": 29700, "total_steps": 40000, "loss": 0.1577, "lr": 7.745139773299481e-06, "epoch": 24.304543593941876, "percentage": 74.25, "elapsed_time": "3:24:53", "remaining_time": "1:11:03", "throughput": 787.22, "total_tokens": 9677384} {"current_steps": 29705, "total_steps": 40000, "loss": 0.1582, "lr": 7.738036942039232e-06, "epoch": 24.30863692181744, "percentage": 74.26, "elapsed_time": "3:24:54", "remaining_time": "1:11:01", "throughput": 787.24, "total_tokens": 9679032} {"current_steps": 29710, "total_steps": 40000, "loss": 0.1228, "lr": 7.73093677279062e-06, "epoch": 24.312730249693, "percentage": 74.28, "elapsed_time": "3:24:56", "remaining_time": "1:10:58", "throughput": 787.26, "total_tokens": 9680664} {"current_steps": 29715, "total_steps": 40000, "loss": 0.1455, "lr": 7.72383926664857e-06, "epoch": 24.316823577568563, "percentage": 74.29, "elapsed_time": "3:24:58", "remaining_time": "1:10:56", "throughput": 787.28, "total_tokens": 9682296} {"current_steps": 29720, "total_steps": 40000, "loss": 0.1307, "lr": 7.716744424707606e-06, "epoch": 24.320916905444125, "percentage": 74.3, "elapsed_time": "3:25:00", "remaining_time": "1:10:54", "throughput": 787.31, "total_tokens": 9683928} {"current_steps": 29725, "total_steps": 40000, "loss": 0.2299, "lr": 7.709652248061858e-06, "epoch": 24.325010233319688, "percentage": 74.31, "elapsed_time": "3:25:01", "remaining_time": "1:10:52", "throughput": 787.33, "total_tokens": 9685576} {"current_steps": 29730, "total_steps": 40000, "loss": 0.1503, "lr": 7.702562737805017e-06, "epoch": 24.32910356119525, "percentage": 74.33, "elapsed_time": "3:25:03", "remaining_time": "1:10:50", "throughput": 787.35, "total_tokens": 9687160} {"current_steps": 29735, "total_steps": 40000, "loss": 0.1334, "lr": 7.695475895030365e-06, "epoch": 24.333196889070816, "percentage": 74.34, "elapsed_time": "3:25:05", "remaining_time": "1:10:47", "throughput": 787.37, "total_tokens": 9688792} {"current_steps": 29740, "total_steps": 40000, "loss": 0.23, "lr": 7.6883917208308e-06, "epoch": 24.33729021694638, "percentage": 74.35, "elapsed_time": "3:25:06", "remaining_time": "1:10:45", "throughput": 787.39, "total_tokens": 9690392} {"current_steps": 29745, "total_steps": 40000, "loss": 0.1441, "lr": 7.681310216298778e-06, "epoch": 24.34138354482194, "percentage": 74.36, "elapsed_time": "3:25:08", "remaining_time": "1:10:43", "throughput": 787.42, "total_tokens": 9692120} {"current_steps": 29750, "total_steps": 40000, "loss": 0.2485, "lr": 7.674231382526367e-06, "epoch": 24.345476872697503, "percentage": 74.38, "elapsed_time": "3:25:10", "remaining_time": "1:10:41", "throughput": 787.44, "total_tokens": 9693720} {"current_steps": 29755, "total_steps": 40000, "loss": 0.1649, "lr": 7.667155220605198e-06, "epoch": 24.349570200573066, "percentage": 74.39, "elapsed_time": "3:25:12", "remaining_time": "1:10:39", "throughput": 787.47, "total_tokens": 9695400} {"current_steps": 29760, "total_steps": 40000, "loss": 0.1651, "lr": 7.660081731626515e-06, "epoch": 24.353663528448628, "percentage": 74.4, "elapsed_time": "3:25:13", "remaining_time": "1:10:37", "throughput": 787.49, "total_tokens": 9697048} {"current_steps": 29765, "total_steps": 40000, "loss": 0.1534, "lr": 7.653010916681141e-06, "epoch": 24.35775685632419, "percentage": 74.41, "elapsed_time": "3:25:15", "remaining_time": "1:10:34", "throughput": 787.52, "total_tokens": 9698712} {"current_steps": 29770, "total_steps": 40000, "loss": 0.1779, "lr": 7.645942776859472e-06, "epoch": 24.361850184199753, "percentage": 74.42, "elapsed_time": "3:25:17", "remaining_time": "1:10:32", "throughput": 787.54, "total_tokens": 9700360} {"current_steps": 29775, "total_steps": 40000, "loss": 0.1173, "lr": 7.63887731325152e-06, "epoch": 24.36594351207532, "percentage": 74.44, "elapsed_time": "3:25:18", "remaining_time": "1:10:30", "throughput": 787.56, "total_tokens": 9701944} {"current_steps": 29780, "total_steps": 40000, "loss": 0.2212, "lr": 7.63181452694685e-06, "epoch": 24.37003683995088, "percentage": 74.45, "elapsed_time": "3:25:20", "remaining_time": "1:10:28", "throughput": 787.58, "total_tokens": 9703496} {"current_steps": 29785, "total_steps": 40000, "loss": 0.1954, "lr": 7.624754419034644e-06, "epoch": 24.374130167826443, "percentage": 74.46, "elapsed_time": "3:25:22", "remaining_time": "1:10:26", "throughput": 787.6, "total_tokens": 9705128} {"current_steps": 29790, "total_steps": 40000, "loss": 0.2997, "lr": 7.6176969906036645e-06, "epoch": 24.378223495702006, "percentage": 74.48, "elapsed_time": "3:25:24", "remaining_time": "1:10:23", "throughput": 787.63, "total_tokens": 9706792} {"current_steps": 29795, "total_steps": 40000, "loss": 0.2052, "lr": 7.610642242742242e-06, "epoch": 24.38231682357757, "percentage": 74.49, "elapsed_time": "3:25:25", "remaining_time": "1:10:21", "throughput": 787.65, "total_tokens": 9708408} {"current_steps": 29800, "total_steps": 40000, "loss": 0.1702, "lr": 7.603590176538322e-06, "epoch": 24.38641015145313, "percentage": 74.5, "elapsed_time": "3:25:27", "remaining_time": "1:10:19", "throughput": 787.67, "total_tokens": 9710056} {"current_steps": 29800, "total_steps": 40000, "eval_loss": 0.21572551131248474, "epoch": 24.38641015145313, "percentage": 74.5, "elapsed_time": "3:25:39", "remaining_time": "1:10:23", "throughput": 786.88, "total_tokens": 9710056} {"current_steps": 29805, "total_steps": 40000, "loss": 0.0968, "lr": 7.596540793079404e-06, "epoch": 24.390503479328693, "percentage": 74.51, "elapsed_time": "3:25:43", "remaining_time": "1:10:22", "throughput": 786.8, "total_tokens": 9711688} {"current_steps": 29810, "total_steps": 40000, "loss": 0.2335, "lr": 7.5894940934526125e-06, "epoch": 24.394596807204255, "percentage": 74.52, "elapsed_time": "3:25:44", "remaining_time": "1:10:19", "throughput": 786.82, "total_tokens": 9713256} {"current_steps": 29815, "total_steps": 40000, "loss": 0.1856, "lr": 7.582450078744621e-06, "epoch": 24.39869013507982, "percentage": 74.54, "elapsed_time": "3:25:46", "remaining_time": "1:10:17", "throughput": 786.85, "total_tokens": 9714952} {"current_steps": 29820, "total_steps": 40000, "loss": 0.1549, "lr": 7.575408750041707e-06, "epoch": 24.402783462955384, "percentage": 74.55, "elapsed_time": "3:25:48", "remaining_time": "1:10:15", "throughput": 786.87, "total_tokens": 9716616} {"current_steps": 29825, "total_steps": 40000, "loss": 0.2359, "lr": 7.568370108429732e-06, "epoch": 24.406876790830946, "percentage": 74.56, "elapsed_time": "3:25:50", "remaining_time": "1:10:13", "throughput": 786.89, "total_tokens": 9718248} {"current_steps": 29830, "total_steps": 40000, "loss": 0.1648, "lr": 7.561334154994154e-06, "epoch": 24.41097011870651, "percentage": 74.58, "elapsed_time": "3:25:51", "remaining_time": "1:10:11", "throughput": 786.92, "total_tokens": 9719880} {"current_steps": 29835, "total_steps": 40000, "loss": 0.19, "lr": 7.55430089081999e-06, "epoch": 24.41506344658207, "percentage": 74.59, "elapsed_time": "3:25:53", "remaining_time": "1:10:08", "throughput": 786.94, "total_tokens": 9721480} {"current_steps": 29840, "total_steps": 40000, "loss": 0.1668, "lr": 7.547270316991864e-06, "epoch": 24.419156774457633, "percentage": 74.6, "elapsed_time": "3:25:55", "remaining_time": "1:10:06", "throughput": 786.96, "total_tokens": 9723080} {"current_steps": 29845, "total_steps": 40000, "loss": 0.2061, "lr": 7.5402424345939884e-06, "epoch": 24.423250102333196, "percentage": 74.61, "elapsed_time": "3:25:56", "remaining_time": "1:10:04", "throughput": 786.98, "total_tokens": 9724648} {"current_steps": 29850, "total_steps": 40000, "loss": 0.1758, "lr": 7.533217244710133e-06, "epoch": 24.427343430208758, "percentage": 74.62, "elapsed_time": "3:25:58", "remaining_time": "1:10:02", "throughput": 787.0, "total_tokens": 9726296} {"current_steps": 29855, "total_steps": 40000, "loss": 0.2009, "lr": 7.52619474842369e-06, "epoch": 24.431436758084324, "percentage": 74.64, "elapsed_time": "3:26:00", "remaining_time": "1:10:00", "throughput": 787.02, "total_tokens": 9727960} {"current_steps": 29860, "total_steps": 40000, "loss": 0.1936, "lr": 7.519174946817597e-06, "epoch": 24.435530085959886, "percentage": 74.65, "elapsed_time": "3:26:02", "remaining_time": "1:09:57", "throughput": 787.05, "total_tokens": 9729656} {"current_steps": 29865, "total_steps": 40000, "loss": 0.1467, "lr": 7.512157840974407e-06, "epoch": 24.43962341383545, "percentage": 74.66, "elapsed_time": "3:26:03", "remaining_time": "1:09:55", "throughput": 787.08, "total_tokens": 9731336} {"current_steps": 29870, "total_steps": 40000, "loss": 0.1787, "lr": 7.5051434319762496e-06, "epoch": 24.44371674171101, "percentage": 74.67, "elapsed_time": "3:26:05", "remaining_time": "1:09:53", "throughput": 787.1, "total_tokens": 9732920} {"current_steps": 29875, "total_steps": 40000, "loss": 0.2814, "lr": 7.498131720904822e-06, "epoch": 24.447810069586573, "percentage": 74.69, "elapsed_time": "3:26:07", "remaining_time": "1:09:51", "throughput": 787.12, "total_tokens": 9734536} {"current_steps": 29880, "total_steps": 40000, "loss": 0.1513, "lr": 7.491122708841433e-06, "epoch": 24.451903397462136, "percentage": 74.7, "elapsed_time": "3:26:09", "remaining_time": "1:09:49", "throughput": 787.14, "total_tokens": 9736200} {"current_steps": 29885, "total_steps": 40000, "loss": 0.1191, "lr": 7.4841163968669524e-06, "epoch": 24.455996725337698, "percentage": 74.71, "elapsed_time": "3:26:10", "remaining_time": "1:09:47", "throughput": 787.16, "total_tokens": 9737800} {"current_steps": 29890, "total_steps": 40000, "loss": 0.2503, "lr": 7.4771127860618355e-06, "epoch": 24.460090053213264, "percentage": 74.72, "elapsed_time": "3:26:12", "remaining_time": "1:09:44", "throughput": 787.18, "total_tokens": 9739384} {"current_steps": 29895, "total_steps": 40000, "loss": 0.1773, "lr": 7.470111877506139e-06, "epoch": 24.464183381088827, "percentage": 74.74, "elapsed_time": "3:26:14", "remaining_time": "1:09:42", "throughput": 787.21, "total_tokens": 9741048} {"current_steps": 29900, "total_steps": 40000, "loss": 0.228, "lr": 7.463113672279479e-06, "epoch": 24.46827670896439, "percentage": 74.75, "elapsed_time": "3:26:15", "remaining_time": "1:09:40", "throughput": 787.23, "total_tokens": 9742728} {"current_steps": 29905, "total_steps": 40000, "loss": 0.1665, "lr": 7.456118171461071e-06, "epoch": 24.47237003683995, "percentage": 74.76, "elapsed_time": "3:26:17", "remaining_time": "1:09:38", "throughput": 787.26, "total_tokens": 9744360} {"current_steps": 29910, "total_steps": 40000, "loss": 0.1869, "lr": 7.449125376129721e-06, "epoch": 24.476463364715514, "percentage": 74.78, "elapsed_time": "3:26:19", "remaining_time": "1:09:36", "throughput": 787.28, "total_tokens": 9745992} {"current_steps": 29915, "total_steps": 40000, "loss": 0.1198, "lr": 7.442135287363788e-06, "epoch": 24.480556692591076, "percentage": 74.79, "elapsed_time": "3:26:21", "remaining_time": "1:09:33", "throughput": 787.3, "total_tokens": 9747560} {"current_steps": 29920, "total_steps": 40000, "loss": 0.2014, "lr": 7.435147906241247e-06, "epoch": 24.48465002046664, "percentage": 74.8, "elapsed_time": "3:26:22", "remaining_time": "1:09:31", "throughput": 787.32, "total_tokens": 9749192} {"current_steps": 29925, "total_steps": 40000, "loss": 0.2359, "lr": 7.428163233839624e-06, "epoch": 24.4887433483422, "percentage": 74.81, "elapsed_time": "3:26:24", "remaining_time": "1:09:29", "throughput": 787.34, "total_tokens": 9750808} {"current_steps": 29930, "total_steps": 40000, "loss": 0.1307, "lr": 7.4211812712360525e-06, "epoch": 24.492836676217767, "percentage": 74.83, "elapsed_time": "3:26:26", "remaining_time": "1:09:27", "throughput": 787.36, "total_tokens": 9752408} {"current_steps": 29935, "total_steps": 40000, "loss": 0.1198, "lr": 7.4142020195072464e-06, "epoch": 24.49693000409333, "percentage": 74.84, "elapsed_time": "3:26:27", "remaining_time": "1:09:25", "throughput": 787.39, "total_tokens": 9754120} {"current_steps": 29940, "total_steps": 40000, "loss": 0.1408, "lr": 7.407225479729479e-06, "epoch": 24.50102333196889, "percentage": 74.85, "elapsed_time": "3:26:29", "remaining_time": "1:09:22", "throughput": 787.41, "total_tokens": 9755736} {"current_steps": 29945, "total_steps": 40000, "loss": 0.1812, "lr": 7.400251652978632e-06, "epoch": 24.505116659844454, "percentage": 74.86, "elapsed_time": "3:26:31", "remaining_time": "1:09:20", "throughput": 787.43, "total_tokens": 9757368} {"current_steps": 29950, "total_steps": 40000, "loss": 0.1871, "lr": 7.393280540330147e-06, "epoch": 24.509209987720016, "percentage": 74.88, "elapsed_time": "3:26:33", "remaining_time": "1:09:18", "throughput": 787.46, "total_tokens": 9759080} {"current_steps": 29955, "total_steps": 40000, "loss": 0.0725, "lr": 7.386312142859069e-06, "epoch": 24.51330331559558, "percentage": 74.89, "elapsed_time": "3:26:34", "remaining_time": "1:09:16", "throughput": 787.48, "total_tokens": 9760712} {"current_steps": 29960, "total_steps": 40000, "loss": 0.2373, "lr": 7.379346461640008e-06, "epoch": 24.51739664347114, "percentage": 74.9, "elapsed_time": "3:26:36", "remaining_time": "1:09:14", "throughput": 787.5, "total_tokens": 9762312} {"current_steps": 29965, "total_steps": 40000, "loss": 0.1613, "lr": 7.372383497747149e-06, "epoch": 24.521489971346703, "percentage": 74.91, "elapsed_time": "3:26:38", "remaining_time": "1:09:12", "throughput": 787.52, "total_tokens": 9763880} {"current_steps": 29970, "total_steps": 40000, "loss": 0.2445, "lr": 7.3654232522542775e-06, "epoch": 24.52558329922227, "percentage": 74.92, "elapsed_time": "3:26:39", "remaining_time": "1:09:09", "throughput": 787.54, "total_tokens": 9765512} {"current_steps": 29975, "total_steps": 40000, "loss": 0.2034, "lr": 7.358465726234756e-06, "epoch": 24.52967662709783, "percentage": 74.94, "elapsed_time": "3:26:41", "remaining_time": "1:09:07", "throughput": 787.57, "total_tokens": 9767160} {"current_steps": 29980, "total_steps": 40000, "loss": 0.2178, "lr": 7.351510920761512e-06, "epoch": 24.533769954973394, "percentage": 74.95, "elapsed_time": "3:26:43", "remaining_time": "1:09:05", "throughput": 787.59, "total_tokens": 9768744} {"current_steps": 29985, "total_steps": 40000, "loss": 0.1901, "lr": 7.344558836907067e-06, "epoch": 24.537863282848956, "percentage": 74.96, "elapsed_time": "3:26:45", "remaining_time": "1:09:03", "throughput": 787.61, "total_tokens": 9770360} {"current_steps": 29990, "total_steps": 40000, "loss": 0.2275, "lr": 7.3376094757435285e-06, "epoch": 24.54195661072452, "percentage": 74.98, "elapsed_time": "3:26:46", "remaining_time": "1:09:01", "throughput": 787.63, "total_tokens": 9772024} {"current_steps": 29995, "total_steps": 40000, "loss": 0.1907, "lr": 7.330662838342561e-06, "epoch": 24.54604993860008, "percentage": 74.99, "elapsed_time": "3:26:48", "remaining_time": "1:08:58", "throughput": 787.65, "total_tokens": 9773640} {"current_steps": 30000, "total_steps": 40000, "loss": 0.1531, "lr": 7.323718925775438e-06, "epoch": 24.550143266475644, "percentage": 75.0, "elapsed_time": "3:26:50", "remaining_time": "1:08:56", "throughput": 787.68, "total_tokens": 9775272} {"current_steps": 30000, "total_steps": 40000, "eval_loss": 0.21408569812774658, "epoch": 24.550143266475644, "percentage": 75.0, "elapsed_time": "3:27:02", "remaining_time": "1:09:00", "throughput": 786.89, "total_tokens": 9775272} {"current_steps": 30005, "total_steps": 40000, "loss": 0.1635, "lr": 7.316777739112985e-06, "epoch": 24.554236594351206, "percentage": 75.01, "elapsed_time": "3:27:05", "remaining_time": "1:08:59", "throughput": 786.81, "total_tokens": 9776904} {"current_steps": 30010, "total_steps": 40000, "loss": 0.187, "lr": 7.309839279425626e-06, "epoch": 24.558329922226772, "percentage": 75.02, "elapsed_time": "3:27:07", "remaining_time": "1:08:57", "throughput": 786.83, "total_tokens": 9778536} {"current_steps": 30015, "total_steps": 40000, "loss": 0.1936, "lr": 7.302903547783366e-06, "epoch": 24.562423250102334, "percentage": 75.04, "elapsed_time": "3:27:09", "remaining_time": "1:08:54", "throughput": 786.85, "total_tokens": 9780136} {"current_steps": 30020, "total_steps": 40000, "loss": 0.1645, "lr": 7.2959705452557644e-06, "epoch": 24.566516577977897, "percentage": 75.05, "elapsed_time": "3:27:11", "remaining_time": "1:08:52", "throughput": 786.88, "total_tokens": 9781816} {"current_steps": 30025, "total_steps": 40000, "loss": 0.1541, "lr": 7.289040272911996e-06, "epoch": 24.57060990585346, "percentage": 75.06, "elapsed_time": "3:27:12", "remaining_time": "1:08:50", "throughput": 786.91, "total_tokens": 9783512} {"current_steps": 30030, "total_steps": 40000, "loss": 0.184, "lr": 7.282112731820789e-06, "epoch": 24.57470323372902, "percentage": 75.08, "elapsed_time": "3:27:14", "remaining_time": "1:08:48", "throughput": 786.93, "total_tokens": 9785096} {"current_steps": 30035, "total_steps": 40000, "loss": 0.1508, "lr": 7.275187923050447e-06, "epoch": 24.578796561604584, "percentage": 75.09, "elapsed_time": "3:27:16", "remaining_time": "1:08:46", "throughput": 786.95, "total_tokens": 9786728} {"current_steps": 30040, "total_steps": 40000, "loss": 0.1801, "lr": 7.268265847668879e-06, "epoch": 24.582889889480146, "percentage": 75.1, "elapsed_time": "3:27:18", "remaining_time": "1:08:43", "throughput": 786.97, "total_tokens": 9788312} {"current_steps": 30045, "total_steps": 40000, "loss": 0.1547, "lr": 7.261346506743538e-06, "epoch": 24.58698321735571, "percentage": 75.11, "elapsed_time": "3:27:19", "remaining_time": "1:08:41", "throughput": 786.99, "total_tokens": 9789912} {"current_steps": 30050, "total_steps": 40000, "loss": 0.2167, "lr": 7.254429901341486e-06, "epoch": 24.591076545231275, "percentage": 75.12, "elapsed_time": "3:27:21", "remaining_time": "1:08:39", "throughput": 787.01, "total_tokens": 9791528} {"current_steps": 30055, "total_steps": 40000, "loss": 0.1305, "lr": 7.247516032529356e-06, "epoch": 24.595169873106837, "percentage": 75.14, "elapsed_time": "3:27:23", "remaining_time": "1:08:37", "throughput": 787.03, "total_tokens": 9793112} {"current_steps": 30060, "total_steps": 40000, "loss": 0.1142, "lr": 7.240604901373338e-06, "epoch": 24.5992632009824, "percentage": 75.15, "elapsed_time": "3:27:24", "remaining_time": "1:08:35", "throughput": 787.05, "total_tokens": 9794728} {"current_steps": 30065, "total_steps": 40000, "loss": 0.1835, "lr": 7.233696508939223e-06, "epoch": 24.60335652885796, "percentage": 75.16, "elapsed_time": "3:27:26", "remaining_time": "1:08:32", "throughput": 787.07, "total_tokens": 9796296} {"current_steps": 30070, "total_steps": 40000, "loss": 0.1918, "lr": 7.226790856292376e-06, "epoch": 24.607449856733524, "percentage": 75.17, "elapsed_time": "3:27:28", "remaining_time": "1:08:30", "throughput": 787.09, "total_tokens": 9797960} {"current_steps": 30075, "total_steps": 40000, "loss": 0.1693, "lr": 7.219887944497727e-06, "epoch": 24.611543184609086, "percentage": 75.19, "elapsed_time": "3:27:30", "remaining_time": "1:08:28", "throughput": 787.11, "total_tokens": 9799560} {"current_steps": 30080, "total_steps": 40000, "loss": 0.1926, "lr": 7.2129877746198e-06, "epoch": 24.61563651248465, "percentage": 75.2, "elapsed_time": "3:27:31", "remaining_time": "1:08:26", "throughput": 787.13, "total_tokens": 9801144} {"current_steps": 30085, "total_steps": 40000, "loss": 0.1812, "lr": 7.20609034772268e-06, "epoch": 24.61972984036021, "percentage": 75.21, "elapsed_time": "3:27:33", "remaining_time": "1:08:24", "throughput": 787.15, "total_tokens": 9802824} {"current_steps": 30090, "total_steps": 40000, "loss": 0.0916, "lr": 7.19919566487004e-06, "epoch": 24.623823168235777, "percentage": 75.22, "elapsed_time": "3:27:35", "remaining_time": "1:08:22", "throughput": 787.18, "total_tokens": 9804504} {"current_steps": 30095, "total_steps": 40000, "loss": 0.1893, "lr": 7.192303727125132e-06, "epoch": 24.62791649611134, "percentage": 75.24, "elapsed_time": "3:27:36", "remaining_time": "1:08:19", "throughput": 787.2, "total_tokens": 9806104} {"current_steps": 30100, "total_steps": 40000, "loss": 0.1589, "lr": 7.185414535550777e-06, "epoch": 24.632009823986902, "percentage": 75.25, "elapsed_time": "3:27:38", "remaining_time": "1:08:17", "throughput": 787.22, "total_tokens": 9807736} {"current_steps": 30105, "total_steps": 40000, "loss": 0.1671, "lr": 7.178528091209363e-06, "epoch": 24.636103151862464, "percentage": 75.26, "elapsed_time": "3:27:40", "remaining_time": "1:08:15", "throughput": 787.24, "total_tokens": 9809336} {"current_steps": 30110, "total_steps": 40000, "loss": 0.1491, "lr": 7.171644395162888e-06, "epoch": 24.640196479738027, "percentage": 75.28, "elapsed_time": "3:27:42", "remaining_time": "1:08:13", "throughput": 787.27, "total_tokens": 9810968} {"current_steps": 30115, "total_steps": 40000, "loss": 0.1539, "lr": 7.164763448472881e-06, "epoch": 24.64428980761359, "percentage": 75.29, "elapsed_time": "3:27:43", "remaining_time": "1:08:11", "throughput": 787.29, "total_tokens": 9812600} {"current_steps": 30120, "total_steps": 40000, "loss": 0.1228, "lr": 7.157885252200491e-06, "epoch": 24.64838313548915, "percentage": 75.3, "elapsed_time": "3:27:45", "remaining_time": "1:08:08", "throughput": 787.32, "total_tokens": 9814344} {"current_steps": 30125, "total_steps": 40000, "loss": 0.0953, "lr": 7.151009807406403e-06, "epoch": 24.652476463364714, "percentage": 75.31, "elapsed_time": "3:27:47", "remaining_time": "1:08:06", "throughput": 787.34, "total_tokens": 9815976} {"current_steps": 30130, "total_steps": 40000, "loss": 0.2004, "lr": 7.144137115150909e-06, "epoch": 24.65656979124028, "percentage": 75.33, "elapsed_time": "3:27:48", "remaining_time": "1:08:04", "throughput": 787.37, "total_tokens": 9817704} {"current_steps": 30135, "total_steps": 40000, "loss": 0.2327, "lr": 7.1372671764938725e-06, "epoch": 24.660663119115842, "percentage": 75.34, "elapsed_time": "3:27:50", "remaining_time": "1:08:02", "throughput": 787.39, "total_tokens": 9819288} {"current_steps": 30140, "total_steps": 40000, "loss": 0.2034, "lr": 7.130399992494705e-06, "epoch": 24.664756446991404, "percentage": 75.35, "elapsed_time": "3:27:52", "remaining_time": "1:08:00", "throughput": 787.42, "total_tokens": 9820952} {"current_steps": 30145, "total_steps": 40000, "loss": 0.2985, "lr": 7.123535564212419e-06, "epoch": 24.668849774866967, "percentage": 75.36, "elapsed_time": "3:27:54", "remaining_time": "1:07:58", "throughput": 787.44, "total_tokens": 9822616} {"current_steps": 30150, "total_steps": 40000, "loss": 0.2249, "lr": 7.116673892705611e-06, "epoch": 24.67294310274253, "percentage": 75.38, "elapsed_time": "3:27:55", "remaining_time": "1:07:55", "throughput": 787.46, "total_tokens": 9824184} {"current_steps": 30155, "total_steps": 40000, "loss": 0.1064, "lr": 7.109814979032415e-06, "epoch": 24.67703643061809, "percentage": 75.39, "elapsed_time": "3:27:57", "remaining_time": "1:07:53", "throughput": 787.48, "total_tokens": 9825768} {"current_steps": 30160, "total_steps": 40000, "loss": 0.1733, "lr": 7.102958824250577e-06, "epoch": 24.681129758493654, "percentage": 75.4, "elapsed_time": "3:27:59", "remaining_time": "1:07:51", "throughput": 787.5, "total_tokens": 9827416} {"current_steps": 30165, "total_steps": 40000, "loss": 0.1494, "lr": 7.096105429417393e-06, "epoch": 24.68522308636922, "percentage": 75.41, "elapsed_time": "3:28:00", "remaining_time": "1:07:49", "throughput": 787.52, "total_tokens": 9829016} {"current_steps": 30170, "total_steps": 40000, "loss": 0.2186, "lr": 7.0892547955897506e-06, "epoch": 24.689316414244782, "percentage": 75.42, "elapsed_time": "3:28:02", "remaining_time": "1:07:47", "throughput": 787.55, "total_tokens": 9830792} {"current_steps": 30175, "total_steps": 40000, "loss": 0.1623, "lr": 7.0824069238241e-06, "epoch": 24.693409742120345, "percentage": 75.44, "elapsed_time": "3:28:04", "remaining_time": "1:07:44", "throughput": 787.58, "total_tokens": 9832424} {"current_steps": 30180, "total_steps": 40000, "loss": 0.1953, "lr": 7.075561815176462e-06, "epoch": 24.697503069995907, "percentage": 75.45, "elapsed_time": "3:28:06", "remaining_time": "1:07:42", "throughput": 787.59, "total_tokens": 9833992} {"current_steps": 30185, "total_steps": 40000, "loss": 0.2105, "lr": 7.068719470702445e-06, "epoch": 24.70159639787147, "percentage": 75.46, "elapsed_time": "3:28:07", "remaining_time": "1:07:40", "throughput": 787.62, "total_tokens": 9835672} {"current_steps": 30190, "total_steps": 40000, "loss": 0.1444, "lr": 7.061879891457229e-06, "epoch": 24.705689725747032, "percentage": 75.48, "elapsed_time": "3:28:09", "remaining_time": "1:07:38", "throughput": 787.65, "total_tokens": 9837368} {"current_steps": 30195, "total_steps": 40000, "loss": 0.1487, "lr": 7.0550430784955515e-06, "epoch": 24.709783053622594, "percentage": 75.49, "elapsed_time": "3:28:11", "remaining_time": "1:07:36", "throughput": 787.67, "total_tokens": 9838968} {"current_steps": 30200, "total_steps": 40000, "loss": 0.1052, "lr": 7.048209032871752e-06, "epoch": 24.713876381498157, "percentage": 75.5, "elapsed_time": "3:28:12", "remaining_time": "1:07:34", "throughput": 787.69, "total_tokens": 9840600} {"current_steps": 30200, "total_steps": 40000, "eval_loss": 0.21590875089168549, "epoch": 24.713876381498157, "percentage": 75.5, "elapsed_time": "3:28:25", "remaining_time": "1:07:38", "throughput": 786.9, "total_tokens": 9840600} {"current_steps": 30205, "total_steps": 40000, "loss": 0.1804, "lr": 7.0413777556397055e-06, "epoch": 24.717969709373723, "percentage": 75.51, "elapsed_time": "3:28:28", "remaining_time": "1:07:36", "throughput": 786.83, "total_tokens": 9842200} {"current_steps": 30210, "total_steps": 40000, "loss": 0.2136, "lr": 7.0345492478528925e-06, "epoch": 24.722063037249285, "percentage": 75.52, "elapsed_time": "3:28:30", "remaining_time": "1:07:34", "throughput": 786.85, "total_tokens": 9843832} {"current_steps": 30215, "total_steps": 40000, "loss": 0.1702, "lr": 7.02772351056436e-06, "epoch": 24.726156365124847, "percentage": 75.54, "elapsed_time": "3:28:32", "remaining_time": "1:07:32", "throughput": 786.87, "total_tokens": 9845496} {"current_steps": 30220, "total_steps": 40000, "loss": 0.2446, "lr": 7.020900544826709e-06, "epoch": 24.73024969300041, "percentage": 75.55, "elapsed_time": "3:28:33", "remaining_time": "1:07:29", "throughput": 786.9, "total_tokens": 9847144} {"current_steps": 30225, "total_steps": 40000, "loss": 0.1587, "lr": 7.014080351692134e-06, "epoch": 24.734343020875972, "percentage": 75.56, "elapsed_time": "3:28:35", "remaining_time": "1:07:27", "throughput": 786.92, "total_tokens": 9848728} {"current_steps": 30230, "total_steps": 40000, "loss": 0.1281, "lr": 7.0072629322124024e-06, "epoch": 24.738436348751534, "percentage": 75.58, "elapsed_time": "3:28:37", "remaining_time": "1:07:25", "throughput": 786.94, "total_tokens": 9850408} {"current_steps": 30235, "total_steps": 40000, "loss": 0.2617, "lr": 7.000448287438827e-06, "epoch": 24.742529676627097, "percentage": 75.59, "elapsed_time": "3:28:39", "remaining_time": "1:07:23", "throughput": 786.96, "total_tokens": 9852008} {"current_steps": 30240, "total_steps": 40000, "loss": 0.2786, "lr": 6.993636418422331e-06, "epoch": 24.74662300450266, "percentage": 75.6, "elapsed_time": "3:28:40", "remaining_time": "1:07:21", "throughput": 786.98, "total_tokens": 9853608} {"current_steps": 30245, "total_steps": 40000, "loss": 0.1124, "lr": 6.986827326213383e-06, "epoch": 24.750716332378225, "percentage": 75.61, "elapsed_time": "3:28:42", "remaining_time": "1:07:18", "throughput": 787.01, "total_tokens": 9855304} {"current_steps": 30250, "total_steps": 40000, "loss": 0.1196, "lr": 6.9800210118620205e-06, "epoch": 24.754809660253787, "percentage": 75.62, "elapsed_time": "3:28:44", "remaining_time": "1:07:16", "throughput": 787.03, "total_tokens": 9856920} {"current_steps": 30255, "total_steps": 40000, "loss": 0.1807, "lr": 6.973217476417876e-06, "epoch": 24.75890298812935, "percentage": 75.64, "elapsed_time": "3:28:45", "remaining_time": "1:07:14", "throughput": 787.05, "total_tokens": 9858520} {"current_steps": 30260, "total_steps": 40000, "loss": 0.2165, "lr": 6.96641672093013e-06, "epoch": 24.762996316004912, "percentage": 75.65, "elapsed_time": "3:28:47", "remaining_time": "1:07:12", "throughput": 787.07, "total_tokens": 9860104} {"current_steps": 30265, "total_steps": 40000, "loss": 0.1917, "lr": 6.95961874644755e-06, "epoch": 24.767089643880475, "percentage": 75.66, "elapsed_time": "3:28:49", "remaining_time": "1:07:10", "throughput": 787.09, "total_tokens": 9861704} {"current_steps": 30270, "total_steps": 40000, "loss": 0.1091, "lr": 6.952823554018476e-06, "epoch": 24.771182971756037, "percentage": 75.67, "elapsed_time": "3:28:51", "remaining_time": "1:07:07", "throughput": 787.11, "total_tokens": 9863336} {"current_steps": 30275, "total_steps": 40000, "loss": 0.107, "lr": 6.946031144690798e-06, "epoch": 24.7752762996316, "percentage": 75.69, "elapsed_time": "3:28:52", "remaining_time": "1:07:05", "throughput": 787.13, "total_tokens": 9864936} {"current_steps": 30280, "total_steps": 40000, "loss": 0.1562, "lr": 6.939241519512005e-06, "epoch": 24.77936962750716, "percentage": 75.7, "elapsed_time": "3:28:54", "remaining_time": "1:07:03", "throughput": 787.15, "total_tokens": 9866568} {"current_steps": 30285, "total_steps": 40000, "loss": 0.2202, "lr": 6.932454679529129e-06, "epoch": 24.783462955382728, "percentage": 75.71, "elapsed_time": "3:28:56", "remaining_time": "1:07:01", "throughput": 787.17, "total_tokens": 9868120} {"current_steps": 30290, "total_steps": 40000, "loss": 0.0957, "lr": 6.925670625788791e-06, "epoch": 24.78755628325829, "percentage": 75.72, "elapsed_time": "3:28:57", "remaining_time": "1:06:59", "throughput": 787.19, "total_tokens": 9869752} {"current_steps": 30295, "total_steps": 40000, "loss": 0.1961, "lr": 6.918889359337186e-06, "epoch": 24.791649611133852, "percentage": 75.74, "elapsed_time": "3:28:59", "remaining_time": "1:06:57", "throughput": 787.21, "total_tokens": 9871368} {"current_steps": 30300, "total_steps": 40000, "loss": 0.1688, "lr": 6.912110881220058e-06, "epoch": 24.795742939009415, "percentage": 75.75, "elapsed_time": "3:29:01", "remaining_time": "1:06:54", "throughput": 787.23, "total_tokens": 9872936} {"current_steps": 30305, "total_steps": 40000, "loss": 0.184, "lr": 6.905335192482735e-06, "epoch": 24.799836266884977, "percentage": 75.76, "elapsed_time": "3:29:03", "remaining_time": "1:06:52", "throughput": 787.25, "total_tokens": 9874568} {"current_steps": 30310, "total_steps": 40000, "loss": 0.1495, "lr": 6.8985622941701275e-06, "epoch": 24.80392959476054, "percentage": 75.78, "elapsed_time": "3:29:04", "remaining_time": "1:06:50", "throughput": 787.27, "total_tokens": 9876152} {"current_steps": 30315, "total_steps": 40000, "loss": 0.1588, "lr": 6.89179218732669e-06, "epoch": 24.808022922636102, "percentage": 75.79, "elapsed_time": "3:29:06", "remaining_time": "1:06:48", "throughput": 787.28, "total_tokens": 9877720} {"current_steps": 30320, "total_steps": 40000, "loss": 0.1325, "lr": 6.8850248729964595e-06, "epoch": 24.812116250511664, "percentage": 75.8, "elapsed_time": "3:29:08", "remaining_time": "1:06:46", "throughput": 787.31, "total_tokens": 9879368} {"current_steps": 30325, "total_steps": 40000, "loss": 0.1401, "lr": 6.8782603522230314e-06, "epoch": 24.81620957838723, "percentage": 75.81, "elapsed_time": "3:29:10", "remaining_time": "1:06:44", "throughput": 787.33, "total_tokens": 9881000} {"current_steps": 30330, "total_steps": 40000, "loss": 0.1485, "lr": 6.871498626049591e-06, "epoch": 24.820302906262793, "percentage": 75.83, "elapsed_time": "3:29:11", "remaining_time": "1:06:41", "throughput": 787.35, "total_tokens": 9882616} {"current_steps": 30335, "total_steps": 40000, "loss": 0.1677, "lr": 6.8647396955188875e-06, "epoch": 24.824396234138355, "percentage": 75.84, "elapsed_time": "3:29:13", "remaining_time": "1:06:39", "throughput": 787.37, "total_tokens": 9884280} {"current_steps": 30340, "total_steps": 40000, "loss": 0.1883, "lr": 6.857983561673218e-06, "epoch": 24.828489562013917, "percentage": 75.85, "elapsed_time": "3:29:15", "remaining_time": "1:06:37", "throughput": 787.39, "total_tokens": 9885880} {"current_steps": 30345, "total_steps": 40000, "loss": 0.1457, "lr": 6.851230225554467e-06, "epoch": 24.83258288988948, "percentage": 75.86, "elapsed_time": "3:29:16", "remaining_time": "1:06:35", "throughput": 787.41, "total_tokens": 9887464} {"current_steps": 30350, "total_steps": 40000, "loss": 0.1829, "lr": 6.8444796882040946e-06, "epoch": 24.836676217765042, "percentage": 75.88, "elapsed_time": "3:29:18", "remaining_time": "1:06:33", "throughput": 787.44, "total_tokens": 9889128} {"current_steps": 30355, "total_steps": 40000, "loss": 0.1833, "lr": 6.837731950663106e-06, "epoch": 24.840769545640605, "percentage": 75.89, "elapsed_time": "3:29:20", "remaining_time": "1:06:30", "throughput": 787.46, "total_tokens": 9890712} {"current_steps": 30360, "total_steps": 40000, "loss": 0.1541, "lr": 6.830987013972098e-06, "epoch": 24.844862873516167, "percentage": 75.9, "elapsed_time": "3:29:22", "remaining_time": "1:06:28", "throughput": 787.48, "total_tokens": 9892344} {"current_steps": 30365, "total_steps": 40000, "loss": 0.1644, "lr": 6.82424487917121e-06, "epoch": 24.848956201391733, "percentage": 75.91, "elapsed_time": "3:29:23", "remaining_time": "1:06:26", "throughput": 787.5, "total_tokens": 9893992} {"current_steps": 30370, "total_steps": 40000, "loss": 0.1627, "lr": 6.8175055473001735e-06, "epoch": 24.853049529267295, "percentage": 75.92, "elapsed_time": "3:29:25", "remaining_time": "1:06:24", "throughput": 787.52, "total_tokens": 9895560} {"current_steps": 30375, "total_steps": 40000, "loss": 0.2414, "lr": 6.8107690193982855e-06, "epoch": 24.857142857142858, "percentage": 75.94, "elapsed_time": "3:29:27", "remaining_time": "1:06:22", "throughput": 787.53, "total_tokens": 9897112} {"current_steps": 30380, "total_steps": 40000, "loss": 0.1989, "lr": 6.804035296504385e-06, "epoch": 24.86123618501842, "percentage": 75.95, "elapsed_time": "3:29:28", "remaining_time": "1:06:20", "throughput": 787.55, "total_tokens": 9898712} {"current_steps": 30385, "total_steps": 40000, "loss": 0.1562, "lr": 6.797304379656916e-06, "epoch": 24.865329512893982, "percentage": 75.96, "elapsed_time": "3:29:30", "remaining_time": "1:06:17", "throughput": 787.58, "total_tokens": 9900360} {"current_steps": 30390, "total_steps": 40000, "loss": 0.1036, "lr": 6.790576269893861e-06, "epoch": 24.869422840769545, "percentage": 75.98, "elapsed_time": "3:29:32", "remaining_time": "1:06:15", "throughput": 787.6, "total_tokens": 9902056} {"current_steps": 30395, "total_steps": 40000, "loss": 0.1551, "lr": 6.783850968252772e-06, "epoch": 24.873516168645107, "percentage": 75.99, "elapsed_time": "3:29:34", "remaining_time": "1:06:13", "throughput": 787.63, "total_tokens": 9903704} {"current_steps": 30400, "total_steps": 40000, "loss": 0.126, "lr": 6.777128475770789e-06, "epoch": 24.87760949652067, "percentage": 76.0, "elapsed_time": "3:29:35", "remaining_time": "1:06:11", "throughput": 787.65, "total_tokens": 9905368} {"current_steps": 30400, "total_steps": 40000, "eval_loss": 0.21341003477573395, "epoch": 24.87760949652067, "percentage": 76.0, "elapsed_time": "3:29:48", "remaining_time": "1:06:15", "throughput": 786.87, "total_tokens": 9905368} {"current_steps": 30405, "total_steps": 40000, "loss": 0.183, "lr": 6.77040879348459e-06, "epoch": 24.881702824396235, "percentage": 76.01, "elapsed_time": "3:29:51", "remaining_time": "1:06:13", "throughput": 786.77, "total_tokens": 9906984} {"current_steps": 30410, "total_steps": 40000, "loss": 0.1585, "lr": 6.763691922430443e-06, "epoch": 24.885796152271798, "percentage": 76.02, "elapsed_time": "3:29:53", "remaining_time": "1:06:11", "throughput": 786.79, "total_tokens": 9908568} {"current_steps": 30415, "total_steps": 40000, "loss": 0.2041, "lr": 6.756977863644178e-06, "epoch": 24.88988948014736, "percentage": 76.04, "elapsed_time": "3:29:55", "remaining_time": "1:06:09", "throughput": 786.81, "total_tokens": 9910200} {"current_steps": 30420, "total_steps": 40000, "loss": 0.217, "lr": 6.7502666181611804e-06, "epoch": 24.893982808022923, "percentage": 76.05, "elapsed_time": "3:29:57", "remaining_time": "1:06:07", "throughput": 786.83, "total_tokens": 9911816} {"current_steps": 30425, "total_steps": 40000, "loss": 0.1643, "lr": 6.743558187016405e-06, "epoch": 24.898076135898485, "percentage": 76.06, "elapsed_time": "3:29:58", "remaining_time": "1:06:04", "throughput": 786.86, "total_tokens": 9913496} {"current_steps": 30430, "total_steps": 40000, "loss": 0.1969, "lr": 6.7368525712443925e-06, "epoch": 24.902169463774047, "percentage": 76.08, "elapsed_time": "3:30:00", "remaining_time": "1:06:02", "throughput": 786.88, "total_tokens": 9915160} {"current_steps": 30435, "total_steps": 40000, "loss": 0.235, "lr": 6.7301497718792155e-06, "epoch": 24.90626279164961, "percentage": 76.09, "elapsed_time": "3:30:02", "remaining_time": "1:06:00", "throughput": 786.91, "total_tokens": 9916872} {"current_steps": 30440, "total_steps": 40000, "loss": 0.178, "lr": 6.723449789954544e-06, "epoch": 24.910356119525176, "percentage": 76.1, "elapsed_time": "3:30:04", "remaining_time": "1:05:58", "throughput": 786.93, "total_tokens": 9918472} {"current_steps": 30445, "total_steps": 40000, "loss": 0.2047, "lr": 6.716752626503586e-06, "epoch": 24.914449447400738, "percentage": 76.11, "elapsed_time": "3:30:05", "remaining_time": "1:05:56", "throughput": 786.95, "total_tokens": 9920136} {"current_steps": 30450, "total_steps": 40000, "loss": 0.1453, "lr": 6.710058282559131e-06, "epoch": 24.9185427752763, "percentage": 76.12, "elapsed_time": "3:30:07", "remaining_time": "1:05:54", "throughput": 786.97, "total_tokens": 9921656} {"current_steps": 30455, "total_steps": 40000, "loss": 0.1349, "lr": 6.703366759153545e-06, "epoch": 24.922636103151863, "percentage": 76.14, "elapsed_time": "3:30:09", "remaining_time": "1:05:51", "throughput": 786.99, "total_tokens": 9923240} {"current_steps": 30460, "total_steps": 40000, "loss": 0.1611, "lr": 6.6966780573187335e-06, "epoch": 24.926729431027425, "percentage": 76.15, "elapsed_time": "3:30:10", "remaining_time": "1:05:49", "throughput": 787.01, "total_tokens": 9924872} {"current_steps": 30465, "total_steps": 40000, "loss": 0.1685, "lr": 6.689992178086174e-06, "epoch": 24.930822758902988, "percentage": 76.16, "elapsed_time": "3:30:12", "remaining_time": "1:05:47", "throughput": 787.03, "total_tokens": 9926456} {"current_steps": 30470, "total_steps": 40000, "loss": 0.1483, "lr": 6.683309122486925e-06, "epoch": 24.93491608677855, "percentage": 76.17, "elapsed_time": "3:30:14", "remaining_time": "1:05:45", "throughput": 787.05, "total_tokens": 9928152} {"current_steps": 30475, "total_steps": 40000, "loss": 0.123, "lr": 6.676628891551584e-06, "epoch": 24.939009414654112, "percentage": 76.19, "elapsed_time": "3:30:16", "remaining_time": "1:05:43", "throughput": 787.08, "total_tokens": 9929784} {"current_steps": 30480, "total_steps": 40000, "loss": 0.2531, "lr": 6.6699514863103385e-06, "epoch": 24.94310274252968, "percentage": 76.2, "elapsed_time": "3:30:17", "remaining_time": "1:05:40", "throughput": 787.1, "total_tokens": 9931400} {"current_steps": 30485, "total_steps": 40000, "loss": 0.2575, "lr": 6.663276907792921e-06, "epoch": 24.94719607040524, "percentage": 76.21, "elapsed_time": "3:30:19", "remaining_time": "1:05:38", "throughput": 787.12, "total_tokens": 9933064} {"current_steps": 30490, "total_steps": 40000, "loss": 0.1333, "lr": 6.656605157028634e-06, "epoch": 24.951289398280803, "percentage": 76.22, "elapsed_time": "3:30:21", "remaining_time": "1:05:36", "throughput": 787.14, "total_tokens": 9934712} {"current_steps": 30495, "total_steps": 40000, "loss": 0.1351, "lr": 6.649936235046358e-06, "epoch": 24.955382726156365, "percentage": 76.24, "elapsed_time": "3:30:22", "remaining_time": "1:05:34", "throughput": 787.16, "total_tokens": 9936328} {"current_steps": 30500, "total_steps": 40000, "loss": 0.1691, "lr": 6.643270142874508e-06, "epoch": 24.959476054031928, "percentage": 76.25, "elapsed_time": "3:30:24", "remaining_time": "1:05:32", "throughput": 787.18, "total_tokens": 9937928} {"current_steps": 30505, "total_steps": 40000, "loss": 0.24, "lr": 6.636606881541094e-06, "epoch": 24.96356938190749, "percentage": 76.26, "elapsed_time": "3:30:26", "remaining_time": "1:05:30", "throughput": 787.2, "total_tokens": 9939528} {"current_steps": 30510, "total_steps": 40000, "loss": 0.2227, "lr": 6.629946452073662e-06, "epoch": 24.967662709783053, "percentage": 76.28, "elapsed_time": "3:30:28", "remaining_time": "1:05:27", "throughput": 787.22, "total_tokens": 9941128} {"current_steps": 30515, "total_steps": 40000, "loss": 0.2031, "lr": 6.6232888554993375e-06, "epoch": 24.971756037658615, "percentage": 76.29, "elapsed_time": "3:30:29", "remaining_time": "1:05:25", "throughput": 787.25, "total_tokens": 9942776} {"current_steps": 30520, "total_steps": 40000, "loss": 0.2096, "lr": 6.616634092844817e-06, "epoch": 24.97584936553418, "percentage": 76.3, "elapsed_time": "3:30:31", "remaining_time": "1:05:23", "throughput": 787.27, "total_tokens": 9944456} {"current_steps": 30525, "total_steps": 40000, "loss": 0.1996, "lr": 6.609982165136331e-06, "epoch": 24.979942693409743, "percentage": 76.31, "elapsed_time": "3:30:33", "remaining_time": "1:05:21", "throughput": 787.29, "total_tokens": 9946024} {"current_steps": 30530, "total_steps": 40000, "loss": 0.1989, "lr": 6.603333073399706e-06, "epoch": 24.984036021285306, "percentage": 76.33, "elapsed_time": "3:30:34", "remaining_time": "1:05:19", "throughput": 787.31, "total_tokens": 9947640} {"current_steps": 30535, "total_steps": 40000, "loss": 0.1613, "lr": 6.596686818660308e-06, "epoch": 24.988129349160868, "percentage": 76.34, "elapsed_time": "3:30:36", "remaining_time": "1:05:17", "throughput": 787.34, "total_tokens": 9949336} {"current_steps": 30540, "total_steps": 40000, "loss": 0.1402, "lr": 6.590043401943066e-06, "epoch": 24.99222267703643, "percentage": 76.35, "elapsed_time": "3:30:38", "remaining_time": "1:05:14", "throughput": 787.36, "total_tokens": 9951016} {"current_steps": 30545, "total_steps": 40000, "loss": 0.1616, "lr": 6.583402824272494e-06, "epoch": 24.996316004911993, "percentage": 76.36, "elapsed_time": "3:30:40", "remaining_time": "1:05:12", "throughput": 787.39, "total_tokens": 9952680} {"current_steps": 30550, "total_steps": 40000, "loss": 0.1791, "lr": 6.576765086672634e-06, "epoch": 25.0, "percentage": 76.38, "elapsed_time": "3:30:41", "remaining_time": "1:05:10", "throughput": 787.4, "total_tokens": 9954096} {"current_steps": 30555, "total_steps": 40000, "loss": 0.2701, "lr": 6.57013019016712e-06, "epoch": 25.004093327875562, "percentage": 76.39, "elapsed_time": "3:30:43", "remaining_time": "1:05:08", "throughput": 787.4, "total_tokens": 9955728} {"current_steps": 30560, "total_steps": 40000, "loss": 0.1843, "lr": 6.563498135779142e-06, "epoch": 25.008186655751125, "percentage": 76.4, "elapsed_time": "3:30:45", "remaining_time": "1:05:06", "throughput": 787.42, "total_tokens": 9957328} {"current_steps": 30565, "total_steps": 40000, "loss": 0.1994, "lr": 6.556868924531431e-06, "epoch": 25.012279983626687, "percentage": 76.41, "elapsed_time": "3:30:47", "remaining_time": "1:05:04", "throughput": 787.45, "total_tokens": 9958976} {"current_steps": 30570, "total_steps": 40000, "loss": 0.2123, "lr": 6.550242557446304e-06, "epoch": 25.016373311502253, "percentage": 76.42, "elapsed_time": "3:30:48", "remaining_time": "1:05:01", "throughput": 787.46, "total_tokens": 9960560} {"current_steps": 30575, "total_steps": 40000, "loss": 0.1365, "lr": 6.543619035545634e-06, "epoch": 25.020466639377815, "percentage": 76.44, "elapsed_time": "3:30:50", "remaining_time": "1:04:59", "throughput": 787.48, "total_tokens": 9962160} {"current_steps": 30580, "total_steps": 40000, "loss": 0.1772, "lr": 6.53699835985084e-06, "epoch": 25.024559967253378, "percentage": 76.45, "elapsed_time": "3:30:52", "remaining_time": "1:04:57", "throughput": 787.5, "total_tokens": 9963744} {"current_steps": 30585, "total_steps": 40000, "loss": 0.1116, "lr": 6.530380531382927e-06, "epoch": 25.02865329512894, "percentage": 76.46, "elapsed_time": "3:30:54", "remaining_time": "1:04:55", "throughput": 787.53, "total_tokens": 9965392} {"current_steps": 30590, "total_steps": 40000, "loss": 0.2586, "lr": 6.523765551162433e-06, "epoch": 25.032746623004503, "percentage": 76.48, "elapsed_time": "3:30:55", "remaining_time": "1:04:53", "throughput": 787.55, "total_tokens": 9967008} {"current_steps": 30595, "total_steps": 40000, "loss": 0.1382, "lr": 6.517153420209476e-06, "epoch": 25.036839950880065, "percentage": 76.49, "elapsed_time": "3:30:57", "remaining_time": "1:04:50", "throughput": 787.56, "total_tokens": 9968560} {"current_steps": 30600, "total_steps": 40000, "loss": 0.2103, "lr": 6.510544139543739e-06, "epoch": 25.040933278755627, "percentage": 76.5, "elapsed_time": "3:30:59", "remaining_time": "1:04:48", "throughput": 787.58, "total_tokens": 9970160} {"current_steps": 30600, "total_steps": 40000, "eval_loss": 0.21526062488555908, "epoch": 25.040933278755627, "percentage": 76.5, "elapsed_time": "3:31:11", "remaining_time": "1:04:52", "throughput": 786.81, "total_tokens": 9970160} {"current_steps": 30605, "total_steps": 40000, "loss": 0.195, "lr": 6.503937710184452e-06, "epoch": 25.04502660663119, "percentage": 76.51, "elapsed_time": "3:31:14", "remaining_time": "1:04:50", "throughput": 786.73, "total_tokens": 9971808} {"current_steps": 30610, "total_steps": 40000, "loss": 0.2885, "lr": 6.4973341331503954e-06, "epoch": 25.049119934506756, "percentage": 76.53, "elapsed_time": "3:31:16", "remaining_time": "1:04:48", "throughput": 786.75, "total_tokens": 9973408} {"current_steps": 30615, "total_steps": 40000, "loss": 0.14, "lr": 6.490733409459942e-06, "epoch": 25.053213262382318, "percentage": 76.54, "elapsed_time": "3:31:18", "remaining_time": "1:04:46", "throughput": 786.77, "total_tokens": 9975088} {"current_steps": 30620, "total_steps": 40000, "loss": 0.1376, "lr": 6.484135540130995e-06, "epoch": 25.05730659025788, "percentage": 76.55, "elapsed_time": "3:31:20", "remaining_time": "1:04:44", "throughput": 786.79, "total_tokens": 9976704} {"current_steps": 30625, "total_steps": 40000, "loss": 0.2381, "lr": 6.4775405261810364e-06, "epoch": 25.061399918133443, "percentage": 76.56, "elapsed_time": "3:31:21", "remaining_time": "1:04:42", "throughput": 786.81, "total_tokens": 9978304} {"current_steps": 30630, "total_steps": 40000, "loss": 0.1821, "lr": 6.470948368627092e-06, "epoch": 25.065493246009005, "percentage": 76.58, "elapsed_time": "3:31:23", "remaining_time": "1:04:40", "throughput": 786.83, "total_tokens": 9979904} {"current_steps": 30635, "total_steps": 40000, "loss": 0.1549, "lr": 6.464359068485756e-06, "epoch": 25.069586573884568, "percentage": 76.59, "elapsed_time": "3:31:25", "remaining_time": "1:04:37", "throughput": 786.85, "total_tokens": 9981536} {"current_steps": 30640, "total_steps": 40000, "loss": 0.2367, "lr": 6.457772626773195e-06, "epoch": 25.07367990176013, "percentage": 76.6, "elapsed_time": "3:31:27", "remaining_time": "1:04:35", "throughput": 786.88, "total_tokens": 9983184} {"current_steps": 30645, "total_steps": 40000, "loss": 0.17, "lr": 6.451189044505104e-06, "epoch": 25.077773229635692, "percentage": 76.61, "elapsed_time": "3:31:28", "remaining_time": "1:04:33", "throughput": 786.9, "total_tokens": 9984800} {"current_steps": 30650, "total_steps": 40000, "loss": 0.1386, "lr": 6.44460832269676e-06, "epoch": 25.08186655751126, "percentage": 76.62, "elapsed_time": "3:31:30", "remaining_time": "1:04:31", "throughput": 786.91, "total_tokens": 9986384} {"current_steps": 30655, "total_steps": 40000, "loss": 0.1952, "lr": 6.438030462363001e-06, "epoch": 25.08595988538682, "percentage": 76.64, "elapsed_time": "3:31:32", "remaining_time": "1:04:29", "throughput": 786.93, "total_tokens": 9987968} {"current_steps": 30660, "total_steps": 40000, "loss": 0.2082, "lr": 6.431455464518205e-06, "epoch": 25.090053213262383, "percentage": 76.65, "elapsed_time": "3:31:33", "remaining_time": "1:04:26", "throughput": 786.96, "total_tokens": 9989696} {"current_steps": 30665, "total_steps": 40000, "loss": 0.232, "lr": 6.424883330176326e-06, "epoch": 25.094146541137945, "percentage": 76.66, "elapsed_time": "3:31:35", "remaining_time": "1:04:24", "throughput": 786.99, "total_tokens": 9991344} {"current_steps": 30670, "total_steps": 40000, "loss": 0.1719, "lr": 6.418314060350864e-06, "epoch": 25.098239869013508, "percentage": 76.68, "elapsed_time": "3:31:37", "remaining_time": "1:04:22", "throughput": 787.01, "total_tokens": 9992960} {"current_steps": 30675, "total_steps": 40000, "loss": 0.1268, "lr": 6.4117476560548895e-06, "epoch": 25.10233319688907, "percentage": 76.69, "elapsed_time": "3:31:39", "remaining_time": "1:04:20", "throughput": 787.03, "total_tokens": 9994624} {"current_steps": 30680, "total_steps": 40000, "loss": 0.0934, "lr": 6.405184118301016e-06, "epoch": 25.106426524764633, "percentage": 76.7, "elapsed_time": "3:31:40", "remaining_time": "1:04:18", "throughput": 787.05, "total_tokens": 9996192} {"current_steps": 30685, "total_steps": 40000, "loss": 0.1937, "lr": 6.398623448101434e-06, "epoch": 25.110519852640195, "percentage": 76.71, "elapsed_time": "3:31:42", "remaining_time": "1:04:16", "throughput": 787.07, "total_tokens": 9997808} {"current_steps": 30690, "total_steps": 40000, "loss": 0.1531, "lr": 6.392065646467871e-06, "epoch": 25.11461318051576, "percentage": 76.72, "elapsed_time": "3:31:44", "remaining_time": "1:04:13", "throughput": 787.09, "total_tokens": 9999440} {"current_steps": 30695, "total_steps": 40000, "loss": 0.1586, "lr": 6.385510714411632e-06, "epoch": 25.118706508391323, "percentage": 76.74, "elapsed_time": "3:31:46", "remaining_time": "1:04:11", "throughput": 787.11, "total_tokens": 10001040} {"current_steps": 30700, "total_steps": 40000, "loss": 0.2112, "lr": 6.378958652943559e-06, "epoch": 25.122799836266886, "percentage": 76.75, "elapsed_time": "3:31:47", "remaining_time": "1:04:09", "throughput": 787.13, "total_tokens": 10002640} {"current_steps": 30705, "total_steps": 40000, "loss": 0.2016, "lr": 6.3724094630740776e-06, "epoch": 25.126893164142448, "percentage": 76.76, "elapsed_time": "3:31:49", "remaining_time": "1:04:07", "throughput": 787.14, "total_tokens": 10004176} {"current_steps": 30710, "total_steps": 40000, "loss": 0.1716, "lr": 6.365863145813136e-06, "epoch": 25.13098649201801, "percentage": 76.78, "elapsed_time": "3:31:51", "remaining_time": "1:04:05", "throughput": 787.16, "total_tokens": 10005808} {"current_steps": 30715, "total_steps": 40000, "loss": 0.0985, "lr": 6.359319702170269e-06, "epoch": 25.135079819893573, "percentage": 76.79, "elapsed_time": "3:31:52", "remaining_time": "1:04:03", "throughput": 787.19, "total_tokens": 10007472} {"current_steps": 30720, "total_steps": 40000, "loss": 0.1873, "lr": 6.352779133154566e-06, "epoch": 25.139173147769135, "percentage": 76.8, "elapsed_time": "3:31:54", "remaining_time": "1:04:00", "throughput": 787.21, "total_tokens": 10009152} {"current_steps": 30725, "total_steps": 40000, "loss": 0.1468, "lr": 6.346241439774648e-06, "epoch": 25.143266475644698, "percentage": 76.81, "elapsed_time": "3:31:56", "remaining_time": "1:03:58", "throughput": 787.23, "total_tokens": 10010704} {"current_steps": 30730, "total_steps": 40000, "loss": 0.1574, "lr": 6.339706623038716e-06, "epoch": 25.147359803520263, "percentage": 76.83, "elapsed_time": "3:31:58", "remaining_time": "1:03:56", "throughput": 787.26, "total_tokens": 10012384} {"current_steps": 30735, "total_steps": 40000, "loss": 0.1374, "lr": 6.333174683954532e-06, "epoch": 25.151453131395826, "percentage": 76.84, "elapsed_time": "3:31:59", "remaining_time": "1:03:54", "throughput": 787.28, "total_tokens": 10014032} {"current_steps": 30740, "total_steps": 40000, "loss": 0.2038, "lr": 6.326645623529387e-06, "epoch": 25.155546459271388, "percentage": 76.85, "elapsed_time": "3:32:01", "remaining_time": "1:03:52", "throughput": 787.3, "total_tokens": 10015648} {"current_steps": 30745, "total_steps": 40000, "loss": 0.1126, "lr": 6.320119442770156e-06, "epoch": 25.15963978714695, "percentage": 76.86, "elapsed_time": "3:32:03", "remaining_time": "1:03:50", "throughput": 787.31, "total_tokens": 10017184} {"current_steps": 30750, "total_steps": 40000, "loss": 0.2339, "lr": 6.313596142683254e-06, "epoch": 25.163733115022513, "percentage": 76.88, "elapsed_time": "3:32:04", "remaining_time": "1:03:47", "throughput": 787.33, "total_tokens": 10018800} {"current_steps": 30755, "total_steps": 40000, "loss": 0.1644, "lr": 6.307075724274647e-06, "epoch": 25.167826442898075, "percentage": 76.89, "elapsed_time": "3:32:06", "remaining_time": "1:03:45", "throughput": 787.35, "total_tokens": 10020416} {"current_steps": 30760, "total_steps": 40000, "loss": 0.218, "lr": 6.300558188549882e-06, "epoch": 25.171919770773638, "percentage": 76.9, "elapsed_time": "3:32:08", "remaining_time": "1:03:43", "throughput": 787.38, "total_tokens": 10022032} {"current_steps": 30765, "total_steps": 40000, "loss": 0.2731, "lr": 6.29404353651403e-06, "epoch": 25.1760130986492, "percentage": 76.91, "elapsed_time": "3:32:10", "remaining_time": "1:03:41", "throughput": 787.39, "total_tokens": 10023616} {"current_steps": 30770, "total_steps": 40000, "loss": 0.1364, "lr": 6.287531769171737e-06, "epoch": 25.180106426524766, "percentage": 76.92, "elapsed_time": "3:32:11", "remaining_time": "1:03:39", "throughput": 787.42, "total_tokens": 10025264} {"current_steps": 30775, "total_steps": 40000, "loss": 0.2181, "lr": 6.2810228875272045e-06, "epoch": 25.18419975440033, "percentage": 76.94, "elapsed_time": "3:32:13", "remaining_time": "1:03:36", "throughput": 787.44, "total_tokens": 10026864} {"current_steps": 30780, "total_steps": 40000, "loss": 0.1196, "lr": 6.274516892584179e-06, "epoch": 25.18829308227589, "percentage": 76.95, "elapsed_time": "3:32:15", "remaining_time": "1:03:34", "throughput": 787.47, "total_tokens": 10028592} {"current_steps": 30785, "total_steps": 40000, "loss": 0.1606, "lr": 6.268013785345969e-06, "epoch": 25.192386410151453, "percentage": 76.96, "elapsed_time": "3:32:17", "remaining_time": "1:03:32", "throughput": 787.49, "total_tokens": 10030304} {"current_steps": 30790, "total_steps": 40000, "loss": 0.1641, "lr": 6.26151356681543e-06, "epoch": 25.196479738027016, "percentage": 76.98, "elapsed_time": "3:32:18", "remaining_time": "1:03:30", "throughput": 787.52, "total_tokens": 10031936} {"current_steps": 30795, "total_steps": 40000, "loss": 0.2638, "lr": 6.255016237994981e-06, "epoch": 25.200573065902578, "percentage": 76.99, "elapsed_time": "3:32:20", "remaining_time": "1:03:28", "throughput": 787.54, "total_tokens": 10033568} {"current_steps": 30800, "total_steps": 40000, "loss": 0.149, "lr": 6.248521799886603e-06, "epoch": 25.20466639377814, "percentage": 77.0, "elapsed_time": "3:32:22", "remaining_time": "1:03:26", "throughput": 787.56, "total_tokens": 10035200} {"current_steps": 30800, "total_steps": 40000, "eval_loss": 0.21306739747524261, "epoch": 25.20466639377814, "percentage": 77.0, "elapsed_time": "3:32:34", "remaining_time": "1:03:29", "throughput": 786.79, "total_tokens": 10035200} {"current_steps": 30805, "total_steps": 40000, "loss": 0.2178, "lr": 6.242030253491798e-06, "epoch": 25.208759721653703, "percentage": 77.01, "elapsed_time": "3:32:37", "remaining_time": "1:03:28", "throughput": 786.72, "total_tokens": 10036832} {"current_steps": 30810, "total_steps": 40000, "loss": 0.1525, "lr": 6.235541599811656e-06, "epoch": 25.21285304952927, "percentage": 77.03, "elapsed_time": "3:32:39", "remaining_time": "1:03:25", "throughput": 786.74, "total_tokens": 10038416} {"current_steps": 30815, "total_steps": 40000, "loss": 0.1595, "lr": 6.229055839846814e-06, "epoch": 25.21694637740483, "percentage": 77.04, "elapsed_time": "3:32:41", "remaining_time": "1:03:23", "throughput": 786.76, "total_tokens": 10040112} {"current_steps": 30820, "total_steps": 40000, "loss": 0.2013, "lr": 6.222572974597455e-06, "epoch": 25.221039705280393, "percentage": 77.05, "elapsed_time": "3:32:43", "remaining_time": "1:03:21", "throughput": 786.78, "total_tokens": 10041696} {"current_steps": 30825, "total_steps": 40000, "loss": 0.2351, "lr": 6.216093005063306e-06, "epoch": 25.225133033155956, "percentage": 77.06, "elapsed_time": "3:32:44", "remaining_time": "1:03:19", "throughput": 786.8, "total_tokens": 10043344} {"current_steps": 30830, "total_steps": 40000, "loss": 0.1869, "lr": 6.209615932243678e-06, "epoch": 25.229226361031518, "percentage": 77.08, "elapsed_time": "3:32:46", "remaining_time": "1:03:17", "throughput": 786.82, "total_tokens": 10044944} {"current_steps": 30835, "total_steps": 40000, "loss": 0.2357, "lr": 6.203141757137399e-06, "epoch": 25.23331968890708, "percentage": 77.09, "elapsed_time": "3:32:48", "remaining_time": "1:03:15", "throughput": 786.85, "total_tokens": 10046592} {"current_steps": 30840, "total_steps": 40000, "loss": 0.1893, "lr": 6.196670480742886e-06, "epoch": 25.237413016782643, "percentage": 77.1, "elapsed_time": "3:32:49", "remaining_time": "1:03:12", "throughput": 786.87, "total_tokens": 10048304} {"current_steps": 30845, "total_steps": 40000, "loss": 0.2585, "lr": 6.190202104058074e-06, "epoch": 25.24150634465821, "percentage": 77.11, "elapsed_time": "3:32:51", "remaining_time": "1:03:10", "throughput": 786.89, "total_tokens": 10049888} {"current_steps": 30850, "total_steps": 40000, "loss": 0.1291, "lr": 6.183736628080475e-06, "epoch": 25.24559967253377, "percentage": 77.12, "elapsed_time": "3:32:53", "remaining_time": "1:03:08", "throughput": 786.91, "total_tokens": 10051520} {"current_steps": 30855, "total_steps": 40000, "loss": 0.1518, "lr": 6.177274053807155e-06, "epoch": 25.249693000409334, "percentage": 77.14, "elapsed_time": "3:32:55", "remaining_time": "1:03:06", "throughput": 786.94, "total_tokens": 10053184} {"current_steps": 30860, "total_steps": 40000, "loss": 0.1623, "lr": 6.170814382234713e-06, "epoch": 25.253786328284896, "percentage": 77.15, "elapsed_time": "3:32:56", "remaining_time": "1:03:04", "throughput": 786.96, "total_tokens": 10054816} {"current_steps": 30865, "total_steps": 40000, "loss": 0.159, "lr": 6.16435761435932e-06, "epoch": 25.25787965616046, "percentage": 77.16, "elapsed_time": "3:32:58", "remaining_time": "1:03:02", "throughput": 786.98, "total_tokens": 10056464} {"current_steps": 30870, "total_steps": 40000, "loss": 0.135, "lr": 6.157903751176681e-06, "epoch": 25.26197298403602, "percentage": 77.18, "elapsed_time": "3:33:00", "remaining_time": "1:02:59", "throughput": 787.0, "total_tokens": 10058096} {"current_steps": 30875, "total_steps": 40000, "loss": 0.0994, "lr": 6.151452793682066e-06, "epoch": 25.266066311911583, "percentage": 77.19, "elapsed_time": "3:33:01", "remaining_time": "1:02:57", "throughput": 787.03, "total_tokens": 10059760} {"current_steps": 30880, "total_steps": 40000, "loss": 0.1527, "lr": 6.145004742870305e-06, "epoch": 25.270159639787146, "percentage": 77.2, "elapsed_time": "3:33:03", "remaining_time": "1:02:55", "throughput": 787.05, "total_tokens": 10061344} {"current_steps": 30885, "total_steps": 40000, "loss": 0.1167, "lr": 6.138559599735752e-06, "epoch": 25.27425296766271, "percentage": 77.21, "elapsed_time": "3:33:05", "remaining_time": "1:02:53", "throughput": 787.06, "total_tokens": 10062912} {"current_steps": 30890, "total_steps": 40000, "loss": 0.1087, "lr": 6.132117365272344e-06, "epoch": 25.278346295538274, "percentage": 77.22, "elapsed_time": "3:33:07", "remaining_time": "1:02:51", "throughput": 787.08, "total_tokens": 10064528} {"current_steps": 30895, "total_steps": 40000, "loss": 0.2461, "lr": 6.125678040473545e-06, "epoch": 25.282439623413836, "percentage": 77.24, "elapsed_time": "3:33:08", "remaining_time": "1:02:48", "throughput": 787.11, "total_tokens": 10066192} {"current_steps": 30900, "total_steps": 40000, "loss": 0.1076, "lr": 6.1192416263323755e-06, "epoch": 25.2865329512894, "percentage": 77.25, "elapsed_time": "3:33:10", "remaining_time": "1:02:46", "throughput": 787.13, "total_tokens": 10067776} {"current_steps": 30905, "total_steps": 40000, "loss": 0.1765, "lr": 6.112808123841424e-06, "epoch": 25.29062627916496, "percentage": 77.26, "elapsed_time": "3:33:12", "remaining_time": "1:02:44", "throughput": 787.15, "total_tokens": 10069424} {"current_steps": 30910, "total_steps": 40000, "loss": 0.1893, "lr": 6.106377533992805e-06, "epoch": 25.294719607040523, "percentage": 77.28, "elapsed_time": "3:33:13", "remaining_time": "1:02:42", "throughput": 787.18, "total_tokens": 10071104} {"current_steps": 30915, "total_steps": 40000, "loss": 0.3395, "lr": 6.099949857778204e-06, "epoch": 25.298812934916086, "percentage": 77.29, "elapsed_time": "3:33:15", "remaining_time": "1:02:40", "throughput": 787.2, "total_tokens": 10072816} {"current_steps": 30920, "total_steps": 40000, "loss": 0.1028, "lr": 6.093525096188852e-06, "epoch": 25.302906262791648, "percentage": 77.3, "elapsed_time": "3:33:17", "remaining_time": "1:02:38", "throughput": 787.23, "total_tokens": 10074496} {"current_steps": 30925, "total_steps": 40000, "loss": 0.2108, "lr": 6.087103250215518e-06, "epoch": 25.306999590667214, "percentage": 77.31, "elapsed_time": "3:33:19", "remaining_time": "1:02:35", "throughput": 787.25, "total_tokens": 10076128} {"current_steps": 30930, "total_steps": 40000, "loss": 0.1896, "lr": 6.080684320848537e-06, "epoch": 25.311092918542776, "percentage": 77.33, "elapsed_time": "3:33:20", "remaining_time": "1:02:33", "throughput": 787.27, "total_tokens": 10077712} {"current_steps": 30935, "total_steps": 40000, "loss": 0.1458, "lr": 6.074268309077794e-06, "epoch": 25.31518624641834, "percentage": 77.34, "elapsed_time": "3:33:22", "remaining_time": "1:02:31", "throughput": 787.29, "total_tokens": 10079344} {"current_steps": 30940, "total_steps": 40000, "loss": 0.1848, "lr": 6.067855215892709e-06, "epoch": 25.3192795742939, "percentage": 77.35, "elapsed_time": "3:33:24", "remaining_time": "1:02:29", "throughput": 787.31, "total_tokens": 10080928} {"current_steps": 30945, "total_steps": 40000, "loss": 0.1528, "lr": 6.061445042282271e-06, "epoch": 25.323372902169464, "percentage": 77.36, "elapsed_time": "3:33:26", "remaining_time": "1:02:27", "throughput": 787.33, "total_tokens": 10082512} {"current_steps": 30950, "total_steps": 40000, "loss": 0.1262, "lr": 6.055037789234999e-06, "epoch": 25.327466230045026, "percentage": 77.38, "elapsed_time": "3:33:27", "remaining_time": "1:02:25", "throughput": 787.35, "total_tokens": 10084160} {"current_steps": 30955, "total_steps": 40000, "loss": 0.1568, "lr": 6.048633457738975e-06, "epoch": 25.33155955792059, "percentage": 77.39, "elapsed_time": "3:33:29", "remaining_time": "1:02:22", "throughput": 787.37, "total_tokens": 10085792} {"current_steps": 30960, "total_steps": 40000, "loss": 0.1019, "lr": 6.042232048781837e-06, "epoch": 25.33565288579615, "percentage": 77.4, "elapsed_time": "3:33:31", "remaining_time": "1:02:20", "throughput": 787.39, "total_tokens": 10087424} {"current_steps": 30965, "total_steps": 40000, "loss": 0.1198, "lr": 6.035833563350757e-06, "epoch": 25.339746213671717, "percentage": 77.41, "elapsed_time": "3:33:32", "remaining_time": "1:02:18", "throughput": 787.41, "total_tokens": 10088992} {"current_steps": 30970, "total_steps": 40000, "loss": 0.1491, "lr": 6.0294380024324525e-06, "epoch": 25.34383954154728, "percentage": 77.42, "elapsed_time": "3:33:34", "remaining_time": "1:02:16", "throughput": 787.43, "total_tokens": 10090544} {"current_steps": 30975, "total_steps": 40000, "loss": 0.1458, "lr": 6.023045367013213e-06, "epoch": 25.34793286942284, "percentage": 77.44, "elapsed_time": "3:33:36", "remaining_time": "1:02:14", "throughput": 787.45, "total_tokens": 10092192} {"current_steps": 30980, "total_steps": 40000, "loss": 0.1441, "lr": 6.016655658078851e-06, "epoch": 25.352026197298404, "percentage": 77.45, "elapsed_time": "3:33:38", "remaining_time": "1:02:12", "throughput": 787.47, "total_tokens": 10093840} {"current_steps": 30985, "total_steps": 40000, "loss": 0.2467, "lr": 6.010268876614753e-06, "epoch": 25.356119525173966, "percentage": 77.46, "elapsed_time": "3:33:39", "remaining_time": "1:02:09", "throughput": 787.5, "total_tokens": 10095504} {"current_steps": 30990, "total_steps": 40000, "loss": 0.152, "lr": 6.0038850236058266e-06, "epoch": 25.36021285304953, "percentage": 77.48, "elapsed_time": "3:33:41", "remaining_time": "1:02:07", "throughput": 787.52, "total_tokens": 10097136} {"current_steps": 30995, "total_steps": 40000, "loss": 0.1242, "lr": 5.997504100036549e-06, "epoch": 25.36430618092509, "percentage": 77.49, "elapsed_time": "3:33:43", "remaining_time": "1:02:05", "throughput": 787.54, "total_tokens": 10098752} {"current_steps": 31000, "total_steps": 40000, "loss": 0.171, "lr": 5.991126106890949e-06, "epoch": 25.368399508800653, "percentage": 77.5, "elapsed_time": "3:33:44", "remaining_time": "1:02:03", "throughput": 787.56, "total_tokens": 10100368} {"current_steps": 31000, "total_steps": 40000, "eval_loss": 0.21748274564743042, "epoch": 25.368399508800653, "percentage": 77.5, "elapsed_time": "3:33:57", "remaining_time": "1:02:06", "throughput": 786.79, "total_tokens": 10100368} {"current_steps": 31005, "total_steps": 40000, "loss": 0.2239, "lr": 5.984751045152576e-06, "epoch": 25.37249283667622, "percentage": 77.51, "elapsed_time": "3:34:00", "remaining_time": "1:02:05", "throughput": 786.72, "total_tokens": 10102000} {"current_steps": 31010, "total_steps": 40000, "loss": 0.2654, "lr": 5.978378915804553e-06, "epoch": 25.37658616455178, "percentage": 77.53, "elapsed_time": "3:34:02", "remaining_time": "1:02:03", "throughput": 786.74, "total_tokens": 10103616} {"current_steps": 31015, "total_steps": 40000, "loss": 0.1549, "lr": 5.972009719829547e-06, "epoch": 25.380679492427344, "percentage": 77.54, "elapsed_time": "3:34:04", "remaining_time": "1:02:00", "throughput": 786.76, "total_tokens": 10105232} {"current_steps": 31020, "total_steps": 40000, "loss": 0.1897, "lr": 5.965643458209755e-06, "epoch": 25.384772820302906, "percentage": 77.55, "elapsed_time": "3:34:05", "remaining_time": "1:01:58", "throughput": 786.77, "total_tokens": 10106800} {"current_steps": 31025, "total_steps": 40000, "loss": 0.1396, "lr": 5.95928013192695e-06, "epoch": 25.38886614817847, "percentage": 77.56, "elapsed_time": "3:34:07", "remaining_time": "1:01:56", "throughput": 786.79, "total_tokens": 10108400} {"current_steps": 31030, "total_steps": 40000, "loss": 0.1743, "lr": 5.952919741962423e-06, "epoch": 25.39295947605403, "percentage": 77.58, "elapsed_time": "3:34:09", "remaining_time": "1:01:54", "throughput": 786.81, "total_tokens": 10110000} {"current_steps": 31035, "total_steps": 40000, "loss": 0.2189, "lr": 5.946562289297042e-06, "epoch": 25.397052803929594, "percentage": 77.59, "elapsed_time": "3:34:11", "remaining_time": "1:01:52", "throughput": 786.83, "total_tokens": 10111616} {"current_steps": 31040, "total_steps": 40000, "loss": 0.1954, "lr": 5.9402077749111855e-06, "epoch": 25.401146131805156, "percentage": 77.6, "elapsed_time": "3:34:12", "remaining_time": "1:01:50", "throughput": 786.86, "total_tokens": 10113312} {"current_steps": 31045, "total_steps": 40000, "loss": 0.1606, "lr": 5.933856199784821e-06, "epoch": 25.405239459680722, "percentage": 77.61, "elapsed_time": "3:34:14", "remaining_time": "1:01:47", "throughput": 786.88, "total_tokens": 10114944} {"current_steps": 31050, "total_steps": 40000, "loss": 0.2403, "lr": 5.927507564897419e-06, "epoch": 25.409332787556284, "percentage": 77.62, "elapsed_time": "3:34:16", "remaining_time": "1:01:45", "throughput": 786.91, "total_tokens": 10116640} {"current_steps": 31055, "total_steps": 40000, "loss": 0.133, "lr": 5.9211618712280395e-06, "epoch": 25.413426115431847, "percentage": 77.64, "elapsed_time": "3:34:17", "remaining_time": "1:01:43", "throughput": 786.94, "total_tokens": 10118400} {"current_steps": 31060, "total_steps": 40000, "loss": 0.1676, "lr": 5.914819119755255e-06, "epoch": 25.41751944330741, "percentage": 77.65, "elapsed_time": "3:34:19", "remaining_time": "1:01:41", "throughput": 786.97, "total_tokens": 10120128} {"current_steps": 31065, "total_steps": 40000, "loss": 0.2307, "lr": 5.908479311457205e-06, "epoch": 25.42161277118297, "percentage": 77.66, "elapsed_time": "3:34:21", "remaining_time": "1:01:39", "throughput": 786.99, "total_tokens": 10121712} {"current_steps": 31070, "total_steps": 40000, "loss": 0.1509, "lr": 5.902142447311559e-06, "epoch": 25.425706099058534, "percentage": 77.68, "elapsed_time": "3:34:23", "remaining_time": "1:01:37", "throughput": 787.0, "total_tokens": 10123264} {"current_steps": 31075, "total_steps": 40000, "loss": 0.1291, "lr": 5.895808528295546e-06, "epoch": 25.429799426934096, "percentage": 77.69, "elapsed_time": "3:34:24", "remaining_time": "1:01:34", "throughput": 787.03, "total_tokens": 10124944} {"current_steps": 31080, "total_steps": 40000, "loss": 0.2075, "lr": 5.889477555385941e-06, "epoch": 25.433892754809662, "percentage": 77.7, "elapsed_time": "3:34:26", "remaining_time": "1:01:32", "throughput": 787.05, "total_tokens": 10126544} {"current_steps": 31085, "total_steps": 40000, "loss": 0.1741, "lr": 5.883149529559051e-06, "epoch": 25.437986082685224, "percentage": 77.71, "elapsed_time": "3:34:28", "remaining_time": "1:01:30", "throughput": 787.07, "total_tokens": 10128128} {"current_steps": 31090, "total_steps": 40000, "loss": 0.1519, "lr": 5.876824451790738e-06, "epoch": 25.442079410560787, "percentage": 77.72, "elapsed_time": "3:34:29", "remaining_time": "1:01:28", "throughput": 787.09, "total_tokens": 10129776} {"current_steps": 31095, "total_steps": 40000, "loss": 0.1625, "lr": 5.87050232305642e-06, "epoch": 25.44617273843635, "percentage": 77.74, "elapsed_time": "3:34:31", "remaining_time": "1:01:26", "throughput": 787.11, "total_tokens": 10131392} {"current_steps": 31100, "total_steps": 40000, "loss": 0.206, "lr": 5.864183144331034e-06, "epoch": 25.45026606631191, "percentage": 77.75, "elapsed_time": "3:34:33", "remaining_time": "1:01:24", "throughput": 787.13, "total_tokens": 10133024} {"current_steps": 31105, "total_steps": 40000, "loss": 0.1839, "lr": 5.857866916589089e-06, "epoch": 25.454359394187474, "percentage": 77.76, "elapsed_time": "3:34:35", "remaining_time": "1:01:21", "throughput": 787.15, "total_tokens": 10134640} {"current_steps": 31110, "total_steps": 40000, "loss": 0.1453, "lr": 5.8515536408046216e-06, "epoch": 25.458452722063036, "percentage": 77.78, "elapsed_time": "3:34:36", "remaining_time": "1:01:19", "throughput": 787.18, "total_tokens": 10136336} {"current_steps": 31115, "total_steps": 40000, "loss": 0.1224, "lr": 5.845243317951208e-06, "epoch": 25.4625460499386, "percentage": 77.79, "elapsed_time": "3:34:38", "remaining_time": "1:01:17", "throughput": 787.2, "total_tokens": 10137952} {"current_steps": 31120, "total_steps": 40000, "loss": 0.1561, "lr": 5.838935949001997e-06, "epoch": 25.466639377814165, "percentage": 77.8, "elapsed_time": "3:34:40", "remaining_time": "1:01:15", "throughput": 787.22, "total_tokens": 10139584} {"current_steps": 31125, "total_steps": 40000, "loss": 0.1505, "lr": 5.8326315349296476e-06, "epoch": 25.470732705689727, "percentage": 77.81, "elapsed_time": "3:34:41", "remaining_time": "1:01:13", "throughput": 787.24, "total_tokens": 10141184} {"current_steps": 31130, "total_steps": 40000, "loss": 0.183, "lr": 5.826330076706396e-06, "epoch": 25.47482603356529, "percentage": 77.83, "elapsed_time": "3:34:43", "remaining_time": "1:01:10", "throughput": 787.26, "total_tokens": 10142816} {"current_steps": 31135, "total_steps": 40000, "loss": 0.1398, "lr": 5.820031575303988e-06, "epoch": 25.478919361440852, "percentage": 77.84, "elapsed_time": "3:34:45", "remaining_time": "1:01:08", "throughput": 787.28, "total_tokens": 10144432} {"current_steps": 31140, "total_steps": 40000, "loss": 0.1991, "lr": 5.813736031693745e-06, "epoch": 25.483012689316414, "percentage": 77.85, "elapsed_time": "3:34:47", "remaining_time": "1:01:06", "throughput": 787.3, "total_tokens": 10146048} {"current_steps": 31145, "total_steps": 40000, "loss": 0.1285, "lr": 5.807443446846522e-06, "epoch": 25.487106017191977, "percentage": 77.86, "elapsed_time": "3:34:48", "remaining_time": "1:01:04", "throughput": 787.32, "total_tokens": 10147680} {"current_steps": 31150, "total_steps": 40000, "loss": 0.1302, "lr": 5.801153821732699e-06, "epoch": 25.49119934506754, "percentage": 77.88, "elapsed_time": "3:34:50", "remaining_time": "1:01:02", "throughput": 787.34, "total_tokens": 10149264} {"current_steps": 31155, "total_steps": 40000, "loss": 0.1781, "lr": 5.794867157322229e-06, "epoch": 25.4952926729431, "percentage": 77.89, "elapsed_time": "3:34:52", "remaining_time": "1:01:00", "throughput": 787.36, "total_tokens": 10150880} {"current_steps": 31160, "total_steps": 40000, "loss": 0.178, "lr": 5.788583454584593e-06, "epoch": 25.499386000818667, "percentage": 77.9, "elapsed_time": "3:34:53", "remaining_time": "1:00:57", "throughput": 787.38, "total_tokens": 10152480} {"current_steps": 31165, "total_steps": 40000, "loss": 0.2178, "lr": 5.7823027144888075e-06, "epoch": 25.50347932869423, "percentage": 77.91, "elapsed_time": "3:34:55", "remaining_time": "1:00:55", "throughput": 787.4, "total_tokens": 10154128} {"current_steps": 31170, "total_steps": 40000, "loss": 0.193, "lr": 5.776024938003455e-06, "epoch": 25.507572656569792, "percentage": 77.92, "elapsed_time": "3:34:57", "remaining_time": "1:00:53", "throughput": 787.43, "total_tokens": 10155792} {"current_steps": 31175, "total_steps": 40000, "loss": 0.2062, "lr": 5.7697501260966345e-06, "epoch": 25.511665984445354, "percentage": 77.94, "elapsed_time": "3:34:59", "remaining_time": "1:00:51", "throughput": 787.45, "total_tokens": 10157408} {"current_steps": 31180, "total_steps": 40000, "loss": 0.2406, "lr": 5.7634782797360145e-06, "epoch": 25.515759312320917, "percentage": 77.95, "elapsed_time": "3:35:00", "remaining_time": "1:00:49", "throughput": 787.47, "total_tokens": 10159024} {"current_steps": 31185, "total_steps": 40000, "loss": 0.2157, "lr": 5.757209399888777e-06, "epoch": 25.51985264019648, "percentage": 77.96, "elapsed_time": "3:35:02", "remaining_time": "1:00:47", "throughput": 787.49, "total_tokens": 10160656} {"current_steps": 31190, "total_steps": 40000, "loss": 0.1216, "lr": 5.750943487521679e-06, "epoch": 25.52394596807204, "percentage": 77.98, "elapsed_time": "3:35:04", "remaining_time": "1:00:44", "throughput": 787.51, "total_tokens": 10162320} {"current_steps": 31195, "total_steps": 40000, "loss": 0.1625, "lr": 5.744680543600986e-06, "epoch": 25.528039295947604, "percentage": 77.99, "elapsed_time": "3:35:06", "remaining_time": "1:00:42", "throughput": 787.53, "total_tokens": 10163920} {"current_steps": 31200, "total_steps": 40000, "loss": 0.1219, "lr": 5.738420569092537e-06, "epoch": 25.53213262382317, "percentage": 78.0, "elapsed_time": "3:35:07", "remaining_time": "1:00:40", "throughput": 787.56, "total_tokens": 10165552} {"current_steps": 31200, "total_steps": 40000, "eval_loss": 0.21487021446228027, "epoch": 25.53213262382317, "percentage": 78.0, "elapsed_time": "3:35:20", "remaining_time": "1:00:44", "throughput": 786.8, "total_tokens": 10165552} {"current_steps": 31205, "total_steps": 40000, "loss": 0.094, "lr": 5.732163564961684e-06, "epoch": 25.536225951698732, "percentage": 78.01, "elapsed_time": "3:35:23", "remaining_time": "1:00:42", "throughput": 786.73, "total_tokens": 10167232} {"current_steps": 31210, "total_steps": 40000, "loss": 0.1307, "lr": 5.725909532173354e-06, "epoch": 25.540319279574295, "percentage": 78.03, "elapsed_time": "3:35:25", "remaining_time": "1:00:40", "throughput": 786.74, "total_tokens": 10168816} {"current_steps": 31215, "total_steps": 40000, "loss": 0.1981, "lr": 5.719658471691977e-06, "epoch": 25.544412607449857, "percentage": 78.04, "elapsed_time": "3:35:26", "remaining_time": "1:00:38", "throughput": 786.76, "total_tokens": 10170400} {"current_steps": 31220, "total_steps": 40000, "loss": 0.1152, "lr": 5.71341038448156e-06, "epoch": 25.54850593532542, "percentage": 78.05, "elapsed_time": "3:35:28", "remaining_time": "1:00:35", "throughput": 786.78, "total_tokens": 10172032} {"current_steps": 31225, "total_steps": 40000, "loss": 0.1684, "lr": 5.707165271505635e-06, "epoch": 25.55259926320098, "percentage": 78.06, "elapsed_time": "3:35:30", "remaining_time": "1:00:33", "throughput": 786.8, "total_tokens": 10173632} {"current_steps": 31230, "total_steps": 40000, "loss": 0.2265, "lr": 5.700923133727271e-06, "epoch": 25.556692591076544, "percentage": 78.08, "elapsed_time": "3:35:32", "remaining_time": "1:00:31", "throughput": 786.82, "total_tokens": 10175200} {"current_steps": 31235, "total_steps": 40000, "loss": 0.2094, "lr": 5.694683972109083e-06, "epoch": 25.560785918952106, "percentage": 78.09, "elapsed_time": "3:35:33", "remaining_time": "1:00:29", "throughput": 786.84, "total_tokens": 10176816} {"current_steps": 31240, "total_steps": 40000, "loss": 0.2674, "lr": 5.688447787613241e-06, "epoch": 25.564879246827672, "percentage": 78.1, "elapsed_time": "3:35:35", "remaining_time": "1:00:27", "throughput": 786.86, "total_tokens": 10178400} {"current_steps": 31245, "total_steps": 40000, "loss": 0.1585, "lr": 5.6822145812014285e-06, "epoch": 25.568972574703235, "percentage": 78.11, "elapsed_time": "3:35:37", "remaining_time": "1:00:25", "throughput": 786.87, "total_tokens": 10180000} {"current_steps": 31250, "total_steps": 40000, "loss": 0.1373, "lr": 5.675984353834896e-06, "epoch": 25.573065902578797, "percentage": 78.12, "elapsed_time": "3:35:38", "remaining_time": "1:00:22", "throughput": 786.89, "total_tokens": 10181568} {"current_steps": 31255, "total_steps": 40000, "loss": 0.1758, "lr": 5.66975710647441e-06, "epoch": 25.57715923045436, "percentage": 78.14, "elapsed_time": "3:35:40", "remaining_time": "1:00:20", "throughput": 786.91, "total_tokens": 10183200} {"current_steps": 31260, "total_steps": 40000, "loss": 0.179, "lr": 5.663532840080304e-06, "epoch": 25.581252558329922, "percentage": 78.15, "elapsed_time": "3:35:42", "remaining_time": "1:00:18", "throughput": 786.94, "total_tokens": 10184880} {"current_steps": 31265, "total_steps": 40000, "loss": 0.1139, "lr": 5.6573115556124325e-06, "epoch": 25.585345886205484, "percentage": 78.16, "elapsed_time": "3:35:44", "remaining_time": "1:00:16", "throughput": 786.95, "total_tokens": 10186448} {"current_steps": 31270, "total_steps": 40000, "loss": 0.1626, "lr": 5.651093254030185e-06, "epoch": 25.589439214081047, "percentage": 78.17, "elapsed_time": "3:35:45", "remaining_time": "1:00:14", "throughput": 786.98, "total_tokens": 10188096} {"current_steps": 31275, "total_steps": 40000, "loss": 0.1494, "lr": 5.644877936292514e-06, "epoch": 25.59353254195661, "percentage": 78.19, "elapsed_time": "3:35:47", "remaining_time": "1:00:12", "throughput": 787.0, "total_tokens": 10189744} {"current_steps": 31280, "total_steps": 40000, "loss": 0.1866, "lr": 5.638665603357901e-06, "epoch": 25.597625869832175, "percentage": 78.2, "elapsed_time": "3:35:49", "remaining_time": "1:00:09", "throughput": 787.02, "total_tokens": 10191360} {"current_steps": 31285, "total_steps": 40000, "loss": 0.1942, "lr": 5.632456256184357e-06, "epoch": 25.601719197707737, "percentage": 78.21, "elapsed_time": "3:35:51", "remaining_time": "1:00:07", "throughput": 787.04, "total_tokens": 10193040} {"current_steps": 31290, "total_steps": 40000, "loss": 0.1139, "lr": 5.626249895729452e-06, "epoch": 25.6058125255833, "percentage": 78.22, "elapsed_time": "3:35:52", "remaining_time": "1:00:05", "throughput": 787.07, "total_tokens": 10194736} {"current_steps": 31295, "total_steps": 40000, "loss": 0.1486, "lr": 5.620046522950273e-06, "epoch": 25.609905853458862, "percentage": 78.24, "elapsed_time": "3:35:54", "remaining_time": "1:00:03", "throughput": 787.09, "total_tokens": 10196384} {"current_steps": 31300, "total_steps": 40000, "loss": 0.1598, "lr": 5.613846138803464e-06, "epoch": 25.613999181334425, "percentage": 78.25, "elapsed_time": "3:35:56", "remaining_time": "1:00:01", "throughput": 787.11, "total_tokens": 10198000} {"current_steps": 31305, "total_steps": 40000, "loss": 0.1692, "lr": 5.607648744245206e-06, "epoch": 25.618092509209987, "percentage": 78.26, "elapsed_time": "3:35:57", "remaining_time": "0:59:59", "throughput": 787.13, "total_tokens": 10199632} {"current_steps": 31310, "total_steps": 40000, "loss": 0.2157, "lr": 5.601454340231207e-06, "epoch": 25.62218583708555, "percentage": 78.27, "elapsed_time": "3:35:59", "remaining_time": "0:59:56", "throughput": 787.16, "total_tokens": 10201296} {"current_steps": 31315, "total_steps": 40000, "loss": 0.1927, "lr": 5.595262927716724e-06, "epoch": 25.62627916496111, "percentage": 78.29, "elapsed_time": "3:36:01", "remaining_time": "0:59:54", "throughput": 787.18, "total_tokens": 10202912} {"current_steps": 31320, "total_steps": 40000, "loss": 0.2071, "lr": 5.589074507656561e-06, "epoch": 25.630372492836678, "percentage": 78.3, "elapsed_time": "3:36:03", "remaining_time": "0:59:52", "throughput": 787.2, "total_tokens": 10204544} {"current_steps": 31325, "total_steps": 40000, "loss": 0.1026, "lr": 5.582889081005044e-06, "epoch": 25.63446582071224, "percentage": 78.31, "elapsed_time": "3:36:04", "remaining_time": "0:59:50", "throughput": 787.22, "total_tokens": 10206144} {"current_steps": 31330, "total_steps": 40000, "loss": 0.1562, "lr": 5.5767066487160316e-06, "epoch": 25.638559148587802, "percentage": 78.33, "elapsed_time": "3:36:06", "remaining_time": "0:59:48", "throughput": 787.22, "total_tokens": 10207808} {"current_steps": 31335, "total_steps": 40000, "loss": 0.2373, "lr": 5.570527211742949e-06, "epoch": 25.642652476463365, "percentage": 78.34, "elapsed_time": "3:36:08", "remaining_time": "0:59:46", "throughput": 787.25, "total_tokens": 10209472} {"current_steps": 31340, "total_steps": 40000, "loss": 0.2374, "lr": 5.564350771038731e-06, "epoch": 25.646745804338927, "percentage": 78.35, "elapsed_time": "3:36:10", "remaining_time": "0:59:43", "throughput": 787.28, "total_tokens": 10211168} {"current_steps": 31345, "total_steps": 40000, "loss": 0.2297, "lr": 5.558177327555875e-06, "epoch": 25.65083913221449, "percentage": 78.36, "elapsed_time": "3:36:11", "remaining_time": "0:59:41", "throughput": 787.3, "total_tokens": 10212848} {"current_steps": 31350, "total_steps": 40000, "loss": 0.0937, "lr": 5.552006882246388e-06, "epoch": 25.654932460090052, "percentage": 78.38, "elapsed_time": "3:36:13", "remaining_time": "0:59:39", "throughput": 787.32, "total_tokens": 10214464} {"current_steps": 31355, "total_steps": 40000, "loss": 0.252, "lr": 5.545839436061839e-06, "epoch": 25.659025787965618, "percentage": 78.39, "elapsed_time": "3:36:15", "remaining_time": "0:59:37", "throughput": 787.34, "total_tokens": 10216128} {"current_steps": 31360, "total_steps": 40000, "loss": 0.1557, "lr": 5.539674989953331e-06, "epoch": 25.66311911584118, "percentage": 78.4, "elapsed_time": "3:36:17", "remaining_time": "0:59:35", "throughput": 787.37, "total_tokens": 10217760} {"current_steps": 31365, "total_steps": 40000, "loss": 0.2235, "lr": 5.533513544871488e-06, "epoch": 25.667212443716743, "percentage": 78.41, "elapsed_time": "3:36:18", "remaining_time": "0:59:33", "throughput": 787.39, "total_tokens": 10219408} {"current_steps": 31370, "total_steps": 40000, "loss": 0.2465, "lr": 5.527355101766493e-06, "epoch": 25.671305771592305, "percentage": 78.42, "elapsed_time": "3:36:20", "remaining_time": "0:59:31", "throughput": 787.41, "total_tokens": 10221024} {"current_steps": 31375, "total_steps": 40000, "loss": 0.163, "lr": 5.521199661588044e-06, "epoch": 25.675399099467867, "percentage": 78.44, "elapsed_time": "3:36:22", "remaining_time": "0:59:28", "throughput": 787.44, "total_tokens": 10222736} {"current_steps": 31380, "total_steps": 40000, "loss": 0.2179, "lr": 5.5150472252853944e-06, "epoch": 25.67949242734343, "percentage": 78.45, "elapsed_time": "3:36:24", "remaining_time": "0:59:26", "throughput": 787.46, "total_tokens": 10224400} {"current_steps": 31385, "total_steps": 40000, "loss": 0.1511, "lr": 5.50889779380733e-06, "epoch": 25.683585755218992, "percentage": 78.46, "elapsed_time": "3:36:25", "remaining_time": "0:59:24", "throughput": 787.48, "total_tokens": 10226032} {"current_steps": 31390, "total_steps": 40000, "loss": 0.1736, "lr": 5.5027513681021605e-06, "epoch": 25.687679083094554, "percentage": 78.47, "elapsed_time": "3:36:27", "remaining_time": "0:59:22", "throughput": 787.51, "total_tokens": 10227680} {"current_steps": 31395, "total_steps": 40000, "loss": 0.1947, "lr": 5.4966079491177545e-06, "epoch": 25.691772410970117, "percentage": 78.49, "elapsed_time": "3:36:29", "remaining_time": "0:59:20", "throughput": 787.53, "total_tokens": 10229360} {"current_steps": 31400, "total_steps": 40000, "loss": 0.113, "lr": 5.490467537801491e-06, "epoch": 25.695865738845683, "percentage": 78.5, "elapsed_time": "3:36:30", "remaining_time": "0:59:18", "throughput": 787.55, "total_tokens": 10230992} {"current_steps": 31400, "total_steps": 40000, "eval_loss": 0.21407254040241241, "epoch": 25.695865738845683, "percentage": 78.5, "elapsed_time": "3:36:43", "remaining_time": "0:59:21", "throughput": 786.8, "total_tokens": 10230992} {"current_steps": 31405, "total_steps": 40000, "loss": 0.1585, "lr": 5.484330135100313e-06, "epoch": 25.699959066721245, "percentage": 78.51, "elapsed_time": "3:36:46", "remaining_time": "0:59:19", "throughput": 786.73, "total_tokens": 10232608} {"current_steps": 31410, "total_steps": 40000, "loss": 0.1521, "lr": 5.4781957419606785e-06, "epoch": 25.704052394596808, "percentage": 78.53, "elapsed_time": "3:36:48", "remaining_time": "0:59:17", "throughput": 786.75, "total_tokens": 10234256} {"current_steps": 31415, "total_steps": 40000, "loss": 0.2583, "lr": 5.472064359328577e-06, "epoch": 25.70814572247237, "percentage": 78.54, "elapsed_time": "3:36:49", "remaining_time": "0:59:15", "throughput": 786.77, "total_tokens": 10235856} {"current_steps": 31420, "total_steps": 40000, "loss": 0.1881, "lr": 5.4659359881495565e-06, "epoch": 25.712239050347932, "percentage": 78.55, "elapsed_time": "3:36:51", "remaining_time": "0:59:13", "throughput": 786.8, "total_tokens": 10237536} {"current_steps": 31425, "total_steps": 40000, "loss": 0.1353, "lr": 5.4598106293686916e-06, "epoch": 25.716332378223495, "percentage": 78.56, "elapsed_time": "3:36:53", "remaining_time": "0:59:10", "throughput": 786.81, "total_tokens": 10239088} {"current_steps": 31430, "total_steps": 40000, "loss": 0.1214, "lr": 5.45368828393058e-06, "epoch": 25.720425706099057, "percentage": 78.57, "elapsed_time": "3:36:55", "remaining_time": "0:59:08", "throughput": 786.83, "total_tokens": 10240672} {"current_steps": 31435, "total_steps": 40000, "loss": 0.1089, "lr": 5.44756895277937e-06, "epoch": 25.724519033974623, "percentage": 78.59, "elapsed_time": "3:36:56", "remaining_time": "0:59:06", "throughput": 786.85, "total_tokens": 10242272} {"current_steps": 31440, "total_steps": 40000, "loss": 0.1479, "lr": 5.441452636858746e-06, "epoch": 25.728612361850185, "percentage": 78.6, "elapsed_time": "3:36:58", "remaining_time": "0:59:04", "throughput": 786.87, "total_tokens": 10243968} {"current_steps": 31445, "total_steps": 40000, "loss": 0.3145, "lr": 5.435339337111905e-06, "epoch": 25.732705689725748, "percentage": 78.61, "elapsed_time": "3:37:00", "remaining_time": "0:59:02", "throughput": 786.9, "total_tokens": 10245616} {"current_steps": 31450, "total_steps": 40000, "loss": 0.1059, "lr": 5.42922905448161e-06, "epoch": 25.73679901760131, "percentage": 78.62, "elapsed_time": "3:37:01", "remaining_time": "0:59:00", "throughput": 786.92, "total_tokens": 10247248} {"current_steps": 31455, "total_steps": 40000, "loss": 0.1973, "lr": 5.423121789910129e-06, "epoch": 25.740892345476873, "percentage": 78.64, "elapsed_time": "3:37:03", "remaining_time": "0:58:57", "throughput": 786.95, "total_tokens": 10248960} {"current_steps": 31460, "total_steps": 40000, "loss": 0.1482, "lr": 5.417017544339287e-06, "epoch": 25.744985673352435, "percentage": 78.65, "elapsed_time": "3:37:05", "remaining_time": "0:58:55", "throughput": 786.97, "total_tokens": 10250592} {"current_steps": 31465, "total_steps": 40000, "loss": 0.1929, "lr": 5.410916318710443e-06, "epoch": 25.749079001227997, "percentage": 78.66, "elapsed_time": "3:37:07", "remaining_time": "0:58:53", "throughput": 786.98, "total_tokens": 10252144} {"current_steps": 31470, "total_steps": 40000, "loss": 0.2516, "lr": 5.404818113964466e-06, "epoch": 25.75317232910356, "percentage": 78.67, "elapsed_time": "3:37:08", "remaining_time": "0:58:51", "throughput": 787.0, "total_tokens": 10253744} {"current_steps": 31475, "total_steps": 40000, "loss": 0.1161, "lr": 5.398722931041792e-06, "epoch": 25.757265656979126, "percentage": 78.69, "elapsed_time": "3:37:10", "remaining_time": "0:58:49", "throughput": 787.02, "total_tokens": 10255392} {"current_steps": 31480, "total_steps": 40000, "loss": 0.1877, "lr": 5.392630770882367e-06, "epoch": 25.761358984854688, "percentage": 78.7, "elapsed_time": "3:37:12", "remaining_time": "0:58:47", "throughput": 787.04, "total_tokens": 10256992} {"current_steps": 31485, "total_steps": 40000, "loss": 0.1463, "lr": 5.3865416344256705e-06, "epoch": 25.76545231273025, "percentage": 78.71, "elapsed_time": "3:37:14", "remaining_time": "0:58:45", "throughput": 787.07, "total_tokens": 10258624} {"current_steps": 31490, "total_steps": 40000, "loss": 0.1282, "lr": 5.380455522610742e-06, "epoch": 25.769545640605813, "percentage": 78.72, "elapsed_time": "3:37:15", "remaining_time": "0:58:42", "throughput": 787.08, "total_tokens": 10260208} {"current_steps": 31495, "total_steps": 40000, "loss": 0.1998, "lr": 5.374372436376116e-06, "epoch": 25.773638968481375, "percentage": 78.74, "elapsed_time": "3:37:17", "remaining_time": "0:58:40", "throughput": 787.11, "total_tokens": 10261872} {"current_steps": 31500, "total_steps": 40000, "loss": 0.1349, "lr": 5.368292376659895e-06, "epoch": 25.777732296356938, "percentage": 78.75, "elapsed_time": "3:37:19", "remaining_time": "0:58:38", "throughput": 787.13, "total_tokens": 10263472} {"current_steps": 31505, "total_steps": 40000, "loss": 0.2529, "lr": 5.362215344399701e-06, "epoch": 25.7818256242325, "percentage": 78.76, "elapsed_time": "3:37:20", "remaining_time": "0:58:36", "throughput": 787.14, "total_tokens": 10265024} {"current_steps": 31510, "total_steps": 40000, "loss": 0.1892, "lr": 5.356141340532678e-06, "epoch": 25.785918952108062, "percentage": 78.77, "elapsed_time": "3:37:22", "remaining_time": "0:58:34", "throughput": 787.16, "total_tokens": 10266624} {"current_steps": 31515, "total_steps": 40000, "loss": 0.2469, "lr": 5.350070365995522e-06, "epoch": 25.790012279983628, "percentage": 78.79, "elapsed_time": "3:37:24", "remaining_time": "0:58:32", "throughput": 787.18, "total_tokens": 10268224} {"current_steps": 31520, "total_steps": 40000, "loss": 0.1424, "lr": 5.344002421724459e-06, "epoch": 25.79410560785919, "percentage": 78.8, "elapsed_time": "3:37:26", "remaining_time": "0:58:29", "throughput": 787.2, "total_tokens": 10269824} {"current_steps": 31525, "total_steps": 40000, "loss": 0.1286, "lr": 5.337937508655228e-06, "epoch": 25.798198935734753, "percentage": 78.81, "elapsed_time": "3:37:27", "remaining_time": "0:58:27", "throughput": 787.22, "total_tokens": 10271440} {"current_steps": 31530, "total_steps": 40000, "loss": 0.1363, "lr": 5.331875627723126e-06, "epoch": 25.802292263610315, "percentage": 78.83, "elapsed_time": "3:37:29", "remaining_time": "0:58:25", "throughput": 787.23, "total_tokens": 10272976} {"current_steps": 31535, "total_steps": 40000, "loss": 0.1791, "lr": 5.325816779862963e-06, "epoch": 25.806385591485878, "percentage": 78.84, "elapsed_time": "3:37:31", "remaining_time": "0:58:23", "throughput": 787.25, "total_tokens": 10274640} {"current_steps": 31540, "total_steps": 40000, "loss": 0.1586, "lr": 5.319760966009102e-06, "epoch": 25.81047891936144, "percentage": 78.85, "elapsed_time": "3:37:33", "remaining_time": "0:58:21", "throughput": 787.27, "total_tokens": 10276272} {"current_steps": 31545, "total_steps": 40000, "loss": 0.1317, "lr": 5.3137081870954096e-06, "epoch": 25.814572247237003, "percentage": 78.86, "elapsed_time": "3:37:34", "remaining_time": "0:58:19", "throughput": 787.29, "total_tokens": 10277840} {"current_steps": 31550, "total_steps": 40000, "loss": 0.1024, "lr": 5.307658444055313e-06, "epoch": 25.818665575112565, "percentage": 78.88, "elapsed_time": "3:37:36", "remaining_time": "0:58:16", "throughput": 787.3, "total_tokens": 10279440} {"current_steps": 31555, "total_steps": 40000, "loss": 0.2816, "lr": 5.301611737821749e-06, "epoch": 25.82275890298813, "percentage": 78.89, "elapsed_time": "3:37:38", "remaining_time": "0:58:14", "throughput": 787.32, "total_tokens": 10281056} {"current_steps": 31560, "total_steps": 40000, "loss": 0.1149, "lr": 5.295568069327206e-06, "epoch": 25.826852230863693, "percentage": 78.9, "elapsed_time": "3:37:39", "remaining_time": "0:58:12", "throughput": 787.35, "total_tokens": 10282720} {"current_steps": 31565, "total_steps": 40000, "loss": 0.2042, "lr": 5.289527439503683e-06, "epoch": 25.830945558739256, "percentage": 78.91, "elapsed_time": "3:37:41", "remaining_time": "0:58:10", "throughput": 787.36, "total_tokens": 10284304} {"current_steps": 31570, "total_steps": 40000, "loss": 0.1656, "lr": 5.28348984928273e-06, "epoch": 25.835038886614818, "percentage": 78.92, "elapsed_time": "3:37:43", "remaining_time": "0:58:08", "throughput": 787.38, "total_tokens": 10285936} {"current_steps": 31575, "total_steps": 40000, "loss": 0.1795, "lr": 5.27745529959541e-06, "epoch": 25.83913221449038, "percentage": 78.94, "elapsed_time": "3:37:45", "remaining_time": "0:58:06", "throughput": 787.41, "total_tokens": 10287584} {"current_steps": 31580, "total_steps": 40000, "loss": 0.179, "lr": 5.271423791372335e-06, "epoch": 25.843225542365943, "percentage": 78.95, "elapsed_time": "3:37:46", "remaining_time": "0:58:03", "throughput": 787.42, "total_tokens": 10289216} {"current_steps": 31585, "total_steps": 40000, "loss": 0.248, "lr": 5.26539532554364e-06, "epoch": 25.847318870241505, "percentage": 78.96, "elapsed_time": "3:37:48", "remaining_time": "0:58:01", "throughput": 787.46, "total_tokens": 10291024} {"current_steps": 31590, "total_steps": 40000, "loss": 0.174, "lr": 5.25936990303898e-06, "epoch": 25.851412198117067, "percentage": 78.97, "elapsed_time": "3:37:50", "remaining_time": "0:57:59", "throughput": 787.48, "total_tokens": 10292672} {"current_steps": 31595, "total_steps": 40000, "loss": 0.13, "lr": 5.253347524787555e-06, "epoch": 25.855505525992633, "percentage": 78.99, "elapsed_time": "3:37:52", "remaining_time": "0:57:57", "throughput": 787.5, "total_tokens": 10294256} {"current_steps": 31600, "total_steps": 40000, "loss": 0.1668, "lr": 5.2473281917181035e-06, "epoch": 25.859598853868196, "percentage": 79.0, "elapsed_time": "3:37:53", "remaining_time": "0:57:55", "throughput": 787.51, "total_tokens": 10295840} {"current_steps": 31600, "total_steps": 40000, "eval_loss": 0.21353588998317719, "epoch": 25.859598853868196, "percentage": 79.0, "elapsed_time": "3:38:06", "remaining_time": "0:57:58", "throughput": 786.77, "total_tokens": 10295840} {"current_steps": 31605, "total_steps": 40000, "loss": 0.2121, "lr": 5.241311904758864e-06, "epoch": 25.863692181743758, "percentage": 79.01, "elapsed_time": "3:38:09", "remaining_time": "0:57:56", "throughput": 786.69, "total_tokens": 10297488} {"current_steps": 31610, "total_steps": 40000, "loss": 0.2887, "lr": 5.23529866483764e-06, "epoch": 25.86778550961932, "percentage": 79.03, "elapsed_time": "3:38:11", "remaining_time": "0:57:54", "throughput": 786.72, "total_tokens": 10299200} {"current_steps": 31615, "total_steps": 40000, "loss": 0.1053, "lr": 5.229288472881732e-06, "epoch": 25.871878837494883, "percentage": 79.04, "elapsed_time": "3:38:13", "remaining_time": "0:57:52", "throughput": 786.74, "total_tokens": 10300864} {"current_steps": 31620, "total_steps": 40000, "loss": 0.2104, "lr": 5.2232813298180025e-06, "epoch": 25.875972165370445, "percentage": 79.05, "elapsed_time": "3:38:14", "remaining_time": "0:57:50", "throughput": 786.76, "total_tokens": 10302464} {"current_steps": 31625, "total_steps": 40000, "loss": 0.1874, "lr": 5.217277236572824e-06, "epoch": 25.880065493246008, "percentage": 79.06, "elapsed_time": "3:38:16", "remaining_time": "0:57:48", "throughput": 786.78, "total_tokens": 10304064} {"current_steps": 31630, "total_steps": 40000, "loss": 0.1115, "lr": 5.211276194072093e-06, "epoch": 25.884158821121574, "percentage": 79.07, "elapsed_time": "3:38:18", "remaining_time": "0:57:46", "throughput": 786.79, "total_tokens": 10305664} {"current_steps": 31635, "total_steps": 40000, "loss": 0.241, "lr": 5.205278203241254e-06, "epoch": 25.888252148997136, "percentage": 79.09, "elapsed_time": "3:38:20", "remaining_time": "0:57:43", "throughput": 786.82, "total_tokens": 10307328} {"current_steps": 31640, "total_steps": 40000, "loss": 0.2005, "lr": 5.199283265005278e-06, "epoch": 25.8923454768727, "percentage": 79.1, "elapsed_time": "3:38:21", "remaining_time": "0:57:41", "throughput": 786.83, "total_tokens": 10308880} {"current_steps": 31645, "total_steps": 40000, "loss": 0.2254, "lr": 5.193291380288648e-06, "epoch": 25.89643880474826, "percentage": 79.11, "elapsed_time": "3:38:23", "remaining_time": "0:57:39", "throughput": 786.85, "total_tokens": 10310496} {"current_steps": 31650, "total_steps": 40000, "loss": 0.1813, "lr": 5.1873025500153995e-06, "epoch": 25.900532132623823, "percentage": 79.12, "elapsed_time": "3:38:25", "remaining_time": "0:57:37", "throughput": 786.87, "total_tokens": 10312144} {"current_steps": 31655, "total_steps": 40000, "loss": 0.138, "lr": 5.181316775109071e-06, "epoch": 25.904625460499386, "percentage": 79.14, "elapsed_time": "3:38:27", "remaining_time": "0:57:35", "throughput": 786.89, "total_tokens": 10313824} {"current_steps": 31660, "total_steps": 40000, "loss": 0.1555, "lr": 5.1753340564927564e-06, "epoch": 25.908718788374948, "percentage": 79.15, "elapsed_time": "3:38:28", "remaining_time": "0:57:33", "throughput": 786.92, "total_tokens": 10315472} {"current_steps": 31665, "total_steps": 40000, "loss": 0.1852, "lr": 5.169354395089068e-06, "epoch": 25.91281211625051, "percentage": 79.16, "elapsed_time": "3:38:30", "remaining_time": "0:57:31", "throughput": 786.94, "total_tokens": 10317120} {"current_steps": 31670, "total_steps": 40000, "loss": 0.1982, "lr": 5.1633777918201346e-06, "epoch": 25.916905444126076, "percentage": 79.17, "elapsed_time": "3:38:32", "remaining_time": "0:57:28", "throughput": 786.95, "total_tokens": 10318720} {"current_steps": 31675, "total_steps": 40000, "loss": 0.1527, "lr": 5.157404247607625e-06, "epoch": 25.92099877200164, "percentage": 79.19, "elapsed_time": "3:38:33", "remaining_time": "0:57:26", "throughput": 786.97, "total_tokens": 10320304} {"current_steps": 31680, "total_steps": 40000, "loss": 0.1324, "lr": 5.1514337633727454e-06, "epoch": 25.9250920998772, "percentage": 79.2, "elapsed_time": "3:38:35", "remaining_time": "0:57:24", "throughput": 786.99, "total_tokens": 10321968} {"current_steps": 31685, "total_steps": 40000, "loss": 0.133, "lr": 5.145466340036206e-06, "epoch": 25.929185427752763, "percentage": 79.21, "elapsed_time": "3:38:37", "remaining_time": "0:57:22", "throughput": 787.02, "total_tokens": 10323648} {"current_steps": 31690, "total_steps": 40000, "loss": 0.2376, "lr": 5.139501978518274e-06, "epoch": 25.933278755628326, "percentage": 79.22, "elapsed_time": "3:38:39", "remaining_time": "0:57:20", "throughput": 787.04, "total_tokens": 10325264} {"current_steps": 31695, "total_steps": 40000, "loss": 0.1244, "lr": 5.133540679738716e-06, "epoch": 25.937372083503888, "percentage": 79.24, "elapsed_time": "3:38:40", "remaining_time": "0:57:18", "throughput": 787.06, "total_tokens": 10326912} {"current_steps": 31700, "total_steps": 40000, "loss": 0.1552, "lr": 5.127582444616838e-06, "epoch": 25.94146541137945, "percentage": 79.25, "elapsed_time": "3:38:42", "remaining_time": "0:57:15", "throughput": 787.08, "total_tokens": 10328560} {"current_steps": 31705, "total_steps": 40000, "loss": 0.1793, "lr": 5.121627274071486e-06, "epoch": 25.945558739255013, "percentage": 79.26, "elapsed_time": "3:38:44", "remaining_time": "0:57:13", "throughput": 787.1, "total_tokens": 10330208} {"current_steps": 31710, "total_steps": 40000, "loss": 0.1996, "lr": 5.115675169021009e-06, "epoch": 25.94965206713058, "percentage": 79.27, "elapsed_time": "3:38:46", "remaining_time": "0:57:11", "throughput": 787.12, "total_tokens": 10331792} {"current_steps": 31715, "total_steps": 40000, "loss": 0.3196, "lr": 5.1097261303832994e-06, "epoch": 25.95374539500614, "percentage": 79.29, "elapsed_time": "3:38:47", "remaining_time": "0:57:09", "throughput": 787.13, "total_tokens": 10333408} {"current_steps": 31720, "total_steps": 40000, "loss": 0.179, "lr": 5.103780159075788e-06, "epoch": 25.957838722881704, "percentage": 79.3, "elapsed_time": "3:38:49", "remaining_time": "0:57:07", "throughput": 787.16, "total_tokens": 10335056} {"current_steps": 31725, "total_steps": 40000, "loss": 0.1592, "lr": 5.0978372560154e-06, "epoch": 25.961932050757266, "percentage": 79.31, "elapsed_time": "3:38:51", "remaining_time": "0:57:05", "throughput": 787.18, "total_tokens": 10336672} {"current_steps": 31730, "total_steps": 40000, "loss": 0.1451, "lr": 5.091897422118619e-06, "epoch": 25.96602537863283, "percentage": 79.33, "elapsed_time": "3:38:53", "remaining_time": "0:57:02", "throughput": 787.2, "total_tokens": 10338400} {"current_steps": 31735, "total_steps": 40000, "loss": 0.1918, "lr": 5.0859606583014305e-06, "epoch": 25.97011870650839, "percentage": 79.34, "elapsed_time": "3:38:54", "remaining_time": "0:57:00", "throughput": 787.22, "total_tokens": 10340048} {"current_steps": 31740, "total_steps": 40000, "loss": 0.1679, "lr": 5.080026965479365e-06, "epoch": 25.974212034383953, "percentage": 79.35, "elapsed_time": "3:38:56", "remaining_time": "0:56:58", "throughput": 787.24, "total_tokens": 10341648} {"current_steps": 31745, "total_steps": 40000, "loss": 0.2005, "lr": 5.074096344567475e-06, "epoch": 25.978305362259515, "percentage": 79.36, "elapsed_time": "3:38:58", "remaining_time": "0:56:56", "throughput": 787.26, "total_tokens": 10343264} {"current_steps": 31750, "total_steps": 40000, "loss": 0.1913, "lr": 5.0681687964803294e-06, "epoch": 25.98239869013508, "percentage": 79.38, "elapsed_time": "3:39:00", "remaining_time": "0:56:54", "throughput": 787.28, "total_tokens": 10344928} {"current_steps": 31755, "total_steps": 40000, "loss": 0.1611, "lr": 5.06224432213204e-06, "epoch": 25.986492018010644, "percentage": 79.39, "elapsed_time": "3:39:01", "remaining_time": "0:56:52", "throughput": 787.31, "total_tokens": 10346592} {"current_steps": 31760, "total_steps": 40000, "loss": 0.1072, "lr": 5.056322922436224e-06, "epoch": 25.990585345886206, "percentage": 79.4, "elapsed_time": "3:39:03", "remaining_time": "0:56:50", "throughput": 787.32, "total_tokens": 10348176} {"current_steps": 31765, "total_steps": 40000, "loss": 0.1606, "lr": 5.0504045983060465e-06, "epoch": 25.99467867376177, "percentage": 79.41, "elapsed_time": "3:39:05", "remaining_time": "0:56:47", "throughput": 787.34, "total_tokens": 10349824} {"current_steps": 31770, "total_steps": 40000, "loss": 0.138, "lr": 5.044489350654183e-06, "epoch": 25.99877200163733, "percentage": 79.42, "elapsed_time": "3:39:06", "remaining_time": "0:56:45", "throughput": 787.36, "total_tokens": 10351392} {"current_steps": 31775, "total_steps": 40000, "loss": 0.1283, "lr": 5.038577180392831e-06, "epoch": 26.002455996725338, "percentage": 79.44, "elapsed_time": "3:39:08", "remaining_time": "0:56:43", "throughput": 787.35, "total_tokens": 10352760} {"current_steps": 31780, "total_steps": 40000, "loss": 0.0876, "lr": 5.032668088433729e-06, "epoch": 26.0065493246009, "percentage": 79.45, "elapsed_time": "3:39:10", "remaining_time": "0:56:41", "throughput": 787.37, "total_tokens": 10354392} {"current_steps": 31785, "total_steps": 40000, "loss": 0.1968, "lr": 5.02676207568814e-06, "epoch": 26.010642652476463, "percentage": 79.46, "elapsed_time": "3:39:12", "remaining_time": "0:56:39", "throughput": 787.39, "total_tokens": 10356008} {"current_steps": 31790, "total_steps": 40000, "loss": 0.1524, "lr": 5.02085914306683e-06, "epoch": 26.014735980352025, "percentage": 79.47, "elapsed_time": "3:39:14", "remaining_time": "0:56:37", "throughput": 787.4, "total_tokens": 10357608} {"current_steps": 31795, "total_steps": 40000, "loss": 0.1772, "lr": 5.014959291480123e-06, "epoch": 26.018829308227588, "percentage": 79.49, "elapsed_time": "3:39:15", "remaining_time": "0:56:34", "throughput": 787.42, "total_tokens": 10359256} {"current_steps": 31800, "total_steps": 40000, "loss": 0.1436, "lr": 5.009062521837835e-06, "epoch": 26.022922636103154, "percentage": 79.5, "elapsed_time": "3:39:17", "remaining_time": "0:56:32", "throughput": 787.45, "total_tokens": 10360952} {"current_steps": 31800, "total_steps": 40000, "eval_loss": 0.21186962723731995, "epoch": 26.022922636103154, "percentage": 79.5, "elapsed_time": "3:39:30", "remaining_time": "0:56:36", "throughput": 786.7, "total_tokens": 10360952} {"current_steps": 31805, "total_steps": 40000, "loss": 0.2188, "lr": 5.003168835049324e-06, "epoch": 26.027015963978716, "percentage": 79.51, "elapsed_time": "3:39:33", "remaining_time": "0:56:34", "throughput": 786.63, "total_tokens": 10362568} {"current_steps": 31810, "total_steps": 40000, "loss": 0.1582, "lr": 4.997278232023483e-06, "epoch": 26.03110929185428, "percentage": 79.53, "elapsed_time": "3:39:35", "remaining_time": "0:56:32", "throughput": 786.65, "total_tokens": 10364216} {"current_steps": 31815, "total_steps": 40000, "loss": 0.2326, "lr": 4.9913907136687036e-06, "epoch": 26.03520261972984, "percentage": 79.54, "elapsed_time": "3:39:36", "remaining_time": "0:56:30", "throughput": 786.67, "total_tokens": 10365816} {"current_steps": 31820, "total_steps": 40000, "loss": 0.2005, "lr": 4.985506280892918e-06, "epoch": 26.039295947605403, "percentage": 79.55, "elapsed_time": "3:39:38", "remaining_time": "0:56:27", "throughput": 786.68, "total_tokens": 10367368} {"current_steps": 31825, "total_steps": 40000, "loss": 0.2255, "lr": 4.979624934603589e-06, "epoch": 26.043389275480965, "percentage": 79.56, "elapsed_time": "3:39:40", "remaining_time": "0:56:25", "throughput": 786.7, "total_tokens": 10368968} {"current_steps": 31830, "total_steps": 40000, "loss": 0.1232, "lr": 4.97374667570768e-06, "epoch": 26.047482603356528, "percentage": 79.57, "elapsed_time": "3:39:42", "remaining_time": "0:56:23", "throughput": 786.72, "total_tokens": 10370648} {"current_steps": 31835, "total_steps": 40000, "loss": 0.2329, "lr": 4.967871505111704e-06, "epoch": 26.05157593123209, "percentage": 79.59, "elapsed_time": "3:39:43", "remaining_time": "0:56:21", "throughput": 786.74, "total_tokens": 10372264} {"current_steps": 31840, "total_steps": 40000, "loss": 0.1194, "lr": 4.961999423721686e-06, "epoch": 26.055669259107656, "percentage": 79.6, "elapsed_time": "3:39:45", "remaining_time": "0:56:19", "throughput": 786.75, "total_tokens": 10373816} {"current_steps": 31845, "total_steps": 40000, "loss": 0.1425, "lr": 4.956130432443159e-06, "epoch": 26.05976258698322, "percentage": 79.61, "elapsed_time": "3:39:47", "remaining_time": "0:56:17", "throughput": 786.77, "total_tokens": 10375416} {"current_steps": 31850, "total_steps": 40000, "loss": 0.1456, "lr": 4.950264532181215e-06, "epoch": 26.06385591485878, "percentage": 79.62, "elapsed_time": "3:39:49", "remaining_time": "0:56:14", "throughput": 786.78, "total_tokens": 10376952} {"current_steps": 31855, "total_steps": 40000, "loss": 0.1893, "lr": 4.944401723840433e-06, "epoch": 26.067949242734343, "percentage": 79.64, "elapsed_time": "3:39:50", "remaining_time": "0:56:12", "throughput": 786.8, "total_tokens": 10378568} {"current_steps": 31860, "total_steps": 40000, "loss": 0.1088, "lr": 4.938542008324942e-06, "epoch": 26.072042570609906, "percentage": 79.65, "elapsed_time": "3:39:52", "remaining_time": "0:56:10", "throughput": 786.83, "total_tokens": 10380312} {"current_steps": 31865, "total_steps": 40000, "loss": 0.1878, "lr": 4.9326853865383855e-06, "epoch": 26.076135898485468, "percentage": 79.66, "elapsed_time": "3:39:54", "remaining_time": "0:56:08", "throughput": 786.85, "total_tokens": 10381928} {"current_steps": 31870, "total_steps": 40000, "loss": 0.2476, "lr": 4.926831859383918e-06, "epoch": 26.08022922636103, "percentage": 79.67, "elapsed_time": "3:39:56", "remaining_time": "0:56:06", "throughput": 786.87, "total_tokens": 10383560} {"current_steps": 31875, "total_steps": 40000, "loss": 0.1449, "lr": 4.92098142776424e-06, "epoch": 26.084322554236593, "percentage": 79.69, "elapsed_time": "3:39:57", "remaining_time": "0:56:04", "throughput": 786.89, "total_tokens": 10385144} {"current_steps": 31880, "total_steps": 40000, "loss": 0.1426, "lr": 4.91513409258155e-06, "epoch": 26.08841588211216, "percentage": 79.7, "elapsed_time": "3:39:59", "remaining_time": "0:56:01", "throughput": 786.91, "total_tokens": 10386792} {"current_steps": 31885, "total_steps": 40000, "loss": 0.1741, "lr": 4.909289854737581e-06, "epoch": 26.09250920998772, "percentage": 79.71, "elapsed_time": "3:40:01", "remaining_time": "0:55:59", "throughput": 786.93, "total_tokens": 10388440} {"current_steps": 31890, "total_steps": 40000, "loss": 0.1966, "lr": 4.903448715133602e-06, "epoch": 26.096602537863284, "percentage": 79.72, "elapsed_time": "3:40:02", "remaining_time": "0:55:57", "throughput": 786.95, "total_tokens": 10390104} {"current_steps": 31895, "total_steps": 40000, "loss": 0.1463, "lr": 4.897610674670372e-06, "epoch": 26.100695865738846, "percentage": 79.74, "elapsed_time": "3:40:04", "remaining_time": "0:55:55", "throughput": 786.97, "total_tokens": 10391768} {"current_steps": 31900, "total_steps": 40000, "loss": 0.1588, "lr": 4.8917757342482e-06, "epoch": 26.10478919361441, "percentage": 79.75, "elapsed_time": "3:40:06", "remaining_time": "0:55:53", "throughput": 787.0, "total_tokens": 10393432} {"current_steps": 31905, "total_steps": 40000, "loss": 0.1433, "lr": 4.885943894766909e-06, "epoch": 26.10888252148997, "percentage": 79.76, "elapsed_time": "3:40:08", "remaining_time": "0:55:51", "throughput": 787.01, "total_tokens": 10395016} {"current_steps": 31910, "total_steps": 40000, "loss": 0.2395, "lr": 4.880115157125842e-06, "epoch": 26.112975849365533, "percentage": 79.77, "elapsed_time": "3:40:09", "remaining_time": "0:55:49", "throughput": 787.04, "total_tokens": 10396696} {"current_steps": 31915, "total_steps": 40000, "loss": 0.1846, "lr": 4.874289522223857e-06, "epoch": 26.117069177241095, "percentage": 79.79, "elapsed_time": "3:40:11", "remaining_time": "0:55:46", "throughput": 787.06, "total_tokens": 10398360} {"current_steps": 31920, "total_steps": 40000, "loss": 0.2724, "lr": 4.868466990959339e-06, "epoch": 26.12116250511666, "percentage": 79.8, "elapsed_time": "3:40:13", "remaining_time": "0:55:44", "throughput": 787.08, "total_tokens": 10399992} {"current_steps": 31925, "total_steps": 40000, "loss": 0.2173, "lr": 4.8626475642301964e-06, "epoch": 26.125255832992224, "percentage": 79.81, "elapsed_time": "3:40:15", "remaining_time": "0:55:42", "throughput": 787.1, "total_tokens": 10401640} {"current_steps": 31930, "total_steps": 40000, "loss": 0.2179, "lr": 4.856831242933871e-06, "epoch": 26.129349160867786, "percentage": 79.83, "elapsed_time": "3:40:16", "remaining_time": "0:55:40", "throughput": 787.11, "total_tokens": 10403224} {"current_steps": 31935, "total_steps": 40000, "loss": 0.1073, "lr": 4.851018027967294e-06, "epoch": 26.13344248874335, "percentage": 79.84, "elapsed_time": "3:40:18", "remaining_time": "0:55:38", "throughput": 787.14, "total_tokens": 10404872} {"current_steps": 31940, "total_steps": 40000, "loss": 0.1137, "lr": 4.845207920226946e-06, "epoch": 26.13753581661891, "percentage": 79.85, "elapsed_time": "3:40:20", "remaining_time": "0:55:36", "throughput": 787.15, "total_tokens": 10406456} {"current_steps": 31945, "total_steps": 40000, "loss": 0.1231, "lr": 4.839400920608825e-06, "epoch": 26.141629144494473, "percentage": 79.86, "elapsed_time": "3:40:22", "remaining_time": "0:55:33", "throughput": 787.17, "total_tokens": 10408056} {"current_steps": 31950, "total_steps": 40000, "loss": 0.1754, "lr": 4.83359703000843e-06, "epoch": 26.145722472370036, "percentage": 79.88, "elapsed_time": "3:40:23", "remaining_time": "0:55:31", "throughput": 787.19, "total_tokens": 10409704} {"current_steps": 31955, "total_steps": 40000, "loss": 0.174, "lr": 4.827796249320804e-06, "epoch": 26.149815800245598, "percentage": 79.89, "elapsed_time": "3:40:25", "remaining_time": "0:55:29", "throughput": 787.21, "total_tokens": 10411256} {"current_steps": 31960, "total_steps": 40000, "loss": 0.1137, "lr": 4.82199857944049e-06, "epoch": 26.153909128121164, "percentage": 79.9, "elapsed_time": "3:40:27", "remaining_time": "0:55:27", "throughput": 787.22, "total_tokens": 10412856} {"current_steps": 31965, "total_steps": 40000, "loss": 0.1793, "lr": 4.8162040212615695e-06, "epoch": 26.158002455996726, "percentage": 79.91, "elapsed_time": "3:40:29", "remaining_time": "0:55:25", "throughput": 787.24, "total_tokens": 10414472} {"current_steps": 31970, "total_steps": 40000, "loss": 0.161, "lr": 4.810412575677639e-06, "epoch": 26.16209578387229, "percentage": 79.92, "elapsed_time": "3:40:30", "remaining_time": "0:55:23", "throughput": 787.26, "total_tokens": 10416104} {"current_steps": 31975, "total_steps": 40000, "loss": 0.0744, "lr": 4.804624243581801e-06, "epoch": 26.16618911174785, "percentage": 79.94, "elapsed_time": "3:40:32", "remaining_time": "0:55:21", "throughput": 787.28, "total_tokens": 10417720} {"current_steps": 31980, "total_steps": 40000, "loss": 0.2002, "lr": 4.798839025866703e-06, "epoch": 26.170282439623413, "percentage": 79.95, "elapsed_time": "3:40:34", "remaining_time": "0:55:18", "throughput": 787.3, "total_tokens": 10419352} {"current_steps": 31985, "total_steps": 40000, "loss": 0.1783, "lr": 4.793056923424491e-06, "epoch": 26.174375767498976, "percentage": 79.96, "elapsed_time": "3:40:36", "remaining_time": "0:55:16", "throughput": 787.32, "total_tokens": 10420968} {"current_steps": 31990, "total_steps": 40000, "loss": 0.131, "lr": 4.78727793714683e-06, "epoch": 26.17846909537454, "percentage": 79.97, "elapsed_time": "3:40:37", "remaining_time": "0:55:14", "throughput": 787.34, "total_tokens": 10422584} {"current_steps": 31995, "total_steps": 40000, "loss": 0.1943, "lr": 4.7815020679249285e-06, "epoch": 26.1825624232501, "percentage": 79.99, "elapsed_time": "3:40:39", "remaining_time": "0:55:12", "throughput": 787.36, "total_tokens": 10424200} {"current_steps": 32000, "total_steps": 40000, "loss": 0.1337, "lr": 4.775729316649483e-06, "epoch": 26.186655751125667, "percentage": 80.0, "elapsed_time": "3:40:41", "remaining_time": "0:55:10", "throughput": 787.38, "total_tokens": 10425832} {"current_steps": 32000, "total_steps": 40000, "eval_loss": 0.21385759115219116, "epoch": 26.186655751125667, "percentage": 80.0, "elapsed_time": "3:40:53", "remaining_time": "0:55:13", "throughput": 786.64, "total_tokens": 10425832} {"current_steps": 32005, "total_steps": 40000, "loss": 0.113, "lr": 4.769959684210728e-06, "epoch": 26.19074907900123, "percentage": 80.01, "elapsed_time": "3:40:57", "remaining_time": "0:55:11", "throughput": 786.56, "total_tokens": 10427400} {"current_steps": 32010, "total_steps": 40000, "loss": 0.1022, "lr": 4.764193171498426e-06, "epoch": 26.19484240687679, "percentage": 80.03, "elapsed_time": "3:40:58", "remaining_time": "0:55:09", "throughput": 786.57, "total_tokens": 10429000} {"current_steps": 32015, "total_steps": 40000, "loss": 0.2379, "lr": 4.75842977940183e-06, "epoch": 26.198935734752354, "percentage": 80.04, "elapsed_time": "3:41:00", "remaining_time": "0:55:07", "throughput": 786.59, "total_tokens": 10430632} {"current_steps": 32020, "total_steps": 40000, "loss": 0.1634, "lr": 4.752669508809729e-06, "epoch": 26.203029062627916, "percentage": 80.05, "elapsed_time": "3:41:02", "remaining_time": "0:55:05", "throughput": 786.61, "total_tokens": 10432216} {"current_steps": 32025, "total_steps": 40000, "loss": 0.1271, "lr": 4.746912360610445e-06, "epoch": 26.20712239050348, "percentage": 80.06, "elapsed_time": "3:41:03", "remaining_time": "0:55:03", "throughput": 786.63, "total_tokens": 10433864} {"current_steps": 32030, "total_steps": 40000, "loss": 0.2011, "lr": 4.741158335691781e-06, "epoch": 26.21121571837904, "percentage": 80.08, "elapsed_time": "3:41:05", "remaining_time": "0:55:00", "throughput": 786.65, "total_tokens": 10435464} {"current_steps": 32035, "total_steps": 40000, "loss": 0.139, "lr": 4.7354074349410994e-06, "epoch": 26.215309046254603, "percentage": 80.09, "elapsed_time": "3:41:07", "remaining_time": "0:54:58", "throughput": 786.67, "total_tokens": 10437080} {"current_steps": 32040, "total_steps": 40000, "loss": 0.1518, "lr": 4.729659659245245e-06, "epoch": 26.21940237413017, "percentage": 80.1, "elapsed_time": "3:41:09", "remaining_time": "0:54:56", "throughput": 786.69, "total_tokens": 10438696} {"current_steps": 32045, "total_steps": 40000, "loss": 0.1475, "lr": 4.723915009490601e-06, "epoch": 26.22349570200573, "percentage": 80.11, "elapsed_time": "3:41:10", "remaining_time": "0:54:54", "throughput": 786.71, "total_tokens": 10440312} {"current_steps": 32050, "total_steps": 40000, "loss": 0.1381, "lr": 4.718173486563077e-06, "epoch": 26.227589029881294, "percentage": 80.12, "elapsed_time": "3:41:12", "remaining_time": "0:54:52", "throughput": 786.73, "total_tokens": 10441944} {"current_steps": 32055, "total_steps": 40000, "loss": 0.1602, "lr": 4.71243509134808e-06, "epoch": 26.231682357756856, "percentage": 80.14, "elapsed_time": "3:41:14", "remaining_time": "0:54:50", "throughput": 786.75, "total_tokens": 10443576} {"current_steps": 32060, "total_steps": 40000, "loss": 0.1303, "lr": 4.706699824730532e-06, "epoch": 26.23577568563242, "percentage": 80.15, "elapsed_time": "3:41:16", "remaining_time": "0:54:47", "throughput": 786.77, "total_tokens": 10445256} {"current_steps": 32065, "total_steps": 40000, "loss": 0.1146, "lr": 4.700967687594901e-06, "epoch": 26.23986901350798, "percentage": 80.16, "elapsed_time": "3:41:17", "remaining_time": "0:54:45", "throughput": 786.79, "total_tokens": 10446904} {"current_steps": 32070, "total_steps": 40000, "loss": 0.1149, "lr": 4.69523868082514e-06, "epoch": 26.243962341383543, "percentage": 80.17, "elapsed_time": "3:41:19", "remaining_time": "0:54:43", "throughput": 786.81, "total_tokens": 10448552} {"current_steps": 32075, "total_steps": 40000, "loss": 0.1267, "lr": 4.689512805304747e-06, "epoch": 26.24805566925911, "percentage": 80.19, "elapsed_time": "3:41:21", "remaining_time": "0:54:41", "throughput": 786.83, "total_tokens": 10450184} {"current_steps": 32080, "total_steps": 40000, "loss": 0.199, "lr": 4.683790061916707e-06, "epoch": 26.25214899713467, "percentage": 80.2, "elapsed_time": "3:41:23", "remaining_time": "0:54:39", "throughput": 786.85, "total_tokens": 10451784} {"current_steps": 32085, "total_steps": 40000, "loss": 0.2075, "lr": 4.678070451543551e-06, "epoch": 26.256242325010234, "percentage": 80.21, "elapsed_time": "3:41:24", "remaining_time": "0:54:37", "throughput": 786.87, "total_tokens": 10453400} {"current_steps": 32090, "total_steps": 40000, "loss": 0.1336, "lr": 4.6723539750673204e-06, "epoch": 26.260335652885797, "percentage": 80.23, "elapsed_time": "3:41:26", "remaining_time": "0:54:35", "throughput": 786.88, "total_tokens": 10455000} {"current_steps": 32095, "total_steps": 40000, "loss": 0.1332, "lr": 4.666640633369551e-06, "epoch": 26.26442898076136, "percentage": 80.24, "elapsed_time": "3:41:28", "remaining_time": "0:54:32", "throughput": 786.91, "total_tokens": 10456648} {"current_steps": 32100, "total_steps": 40000, "loss": 0.2206, "lr": 4.660930427331323e-06, "epoch": 26.26852230863692, "percentage": 80.25, "elapsed_time": "3:41:30", "remaining_time": "0:54:30", "throughput": 786.93, "total_tokens": 10458296} {"current_steps": 32105, "total_steps": 40000, "loss": 0.1547, "lr": 4.6552233578332244e-06, "epoch": 26.272615636512484, "percentage": 80.26, "elapsed_time": "3:41:31", "remaining_time": "0:54:28", "throughput": 786.95, "total_tokens": 10459944} {"current_steps": 32110, "total_steps": 40000, "loss": 0.1159, "lr": 4.649519425755347e-06, "epoch": 26.276708964388046, "percentage": 80.27, "elapsed_time": "3:41:33", "remaining_time": "0:54:26", "throughput": 786.97, "total_tokens": 10461576} {"current_steps": 32115, "total_steps": 40000, "loss": 0.2007, "lr": 4.64381863197732e-06, "epoch": 26.280802292263612, "percentage": 80.29, "elapsed_time": "3:41:35", "remaining_time": "0:54:24", "throughput": 786.98, "total_tokens": 10463160} {"current_steps": 32120, "total_steps": 40000, "loss": 0.3723, "lr": 4.638120977378269e-06, "epoch": 26.284895620139174, "percentage": 80.3, "elapsed_time": "3:41:36", "remaining_time": "0:54:22", "throughput": 787.01, "total_tokens": 10464824} {"current_steps": 32125, "total_steps": 40000, "loss": 0.1975, "lr": 4.632426462836848e-06, "epoch": 26.288988948014737, "percentage": 80.31, "elapsed_time": "3:41:38", "remaining_time": "0:54:19", "throughput": 787.03, "total_tokens": 10466440} {"current_steps": 32130, "total_steps": 40000, "loss": 0.1762, "lr": 4.626735089231224e-06, "epoch": 26.2930822758903, "percentage": 80.33, "elapsed_time": "3:41:40", "remaining_time": "0:54:17", "throughput": 787.05, "total_tokens": 10468104} {"current_steps": 32135, "total_steps": 40000, "loss": 0.203, "lr": 4.621046857439068e-06, "epoch": 26.29717560376586, "percentage": 80.34, "elapsed_time": "3:41:42", "remaining_time": "0:54:15", "throughput": 787.07, "total_tokens": 10469704} {"current_steps": 32140, "total_steps": 40000, "loss": 0.2061, "lr": 4.615361768337587e-06, "epoch": 26.301268931641424, "percentage": 80.35, "elapsed_time": "3:41:43", "remaining_time": "0:54:13", "throughput": 787.09, "total_tokens": 10471336} {"current_steps": 32145, "total_steps": 40000, "loss": 0.2107, "lr": 4.6096798228034946e-06, "epoch": 26.305362259516986, "percentage": 80.36, "elapsed_time": "3:41:45", "remaining_time": "0:54:11", "throughput": 787.11, "total_tokens": 10473000} {"current_steps": 32150, "total_steps": 40000, "loss": 0.1467, "lr": 4.604001021713008e-06, "epoch": 26.30945558739255, "percentage": 80.38, "elapsed_time": "3:41:47", "remaining_time": "0:54:09", "throughput": 787.13, "total_tokens": 10474712} {"current_steps": 32155, "total_steps": 40000, "loss": 0.1339, "lr": 4.598325365941883e-06, "epoch": 26.313548915268115, "percentage": 80.39, "elapsed_time": "3:41:49", "remaining_time": "0:54:07", "throughput": 787.16, "total_tokens": 10476408} {"current_steps": 32160, "total_steps": 40000, "loss": 0.1546, "lr": 4.5926528563653645e-06, "epoch": 26.317642243143677, "percentage": 80.4, "elapsed_time": "3:41:50", "remaining_time": "0:54:04", "throughput": 787.18, "total_tokens": 10478088} {"current_steps": 32165, "total_steps": 40000, "loss": 0.2246, "lr": 4.5869834938582295e-06, "epoch": 26.32173557101924, "percentage": 80.41, "elapsed_time": "3:41:52", "remaining_time": "0:54:02", "throughput": 787.2, "total_tokens": 10479688} {"current_steps": 32170, "total_steps": 40000, "loss": 0.1964, "lr": 4.581317279294772e-06, "epoch": 26.3258288988948, "percentage": 80.42, "elapsed_time": "3:41:54", "remaining_time": "0:54:00", "throughput": 787.21, "total_tokens": 10481256} {"current_steps": 32175, "total_steps": 40000, "loss": 0.2385, "lr": 4.57565421354878e-06, "epoch": 26.329922226770364, "percentage": 80.44, "elapsed_time": "3:41:56", "remaining_time": "0:53:58", "throughput": 787.23, "total_tokens": 10482824} {"current_steps": 32180, "total_steps": 40000, "loss": 0.1935, "lr": 4.569994297493579e-06, "epoch": 26.334015554645926, "percentage": 80.45, "elapsed_time": "3:41:57", "remaining_time": "0:53:56", "throughput": 787.25, "total_tokens": 10484504} {"current_steps": 32185, "total_steps": 40000, "loss": 0.2658, "lr": 4.564337532002002e-06, "epoch": 26.33810888252149, "percentage": 80.46, "elapsed_time": "3:41:59", "remaining_time": "0:53:54", "throughput": 787.27, "total_tokens": 10486136} {"current_steps": 32190, "total_steps": 40000, "loss": 0.2229, "lr": 4.55868391794638e-06, "epoch": 26.34220221039705, "percentage": 80.47, "elapsed_time": "3:42:01", "remaining_time": "0:53:52", "throughput": 787.28, "total_tokens": 10487688} {"current_steps": 32195, "total_steps": 40000, "loss": 0.1384, "lr": 4.553033456198588e-06, "epoch": 26.346295538272617, "percentage": 80.49, "elapsed_time": "3:42:03", "remaining_time": "0:53:49", "throughput": 787.3, "total_tokens": 10489288} {"current_steps": 32200, "total_steps": 40000, "loss": 0.2203, "lr": 4.54738614762999e-06, "epoch": 26.35038886614818, "percentage": 80.5, "elapsed_time": "3:42:04", "remaining_time": "0:53:47", "throughput": 787.32, "total_tokens": 10490904} {"current_steps": 32200, "total_steps": 40000, "eval_loss": 0.2135670930147171, "epoch": 26.35038886614818, "percentage": 80.5, "elapsed_time": "3:42:17", "remaining_time": "0:53:50", "throughput": 786.59, "total_tokens": 10490904} {"current_steps": 32205, "total_steps": 40000, "loss": 0.1031, "lr": 4.541741993111465e-06, "epoch": 26.354482194023742, "percentage": 80.51, "elapsed_time": "3:42:20", "remaining_time": "0:53:49", "throughput": 786.51, "total_tokens": 10492552} {"current_steps": 32210, "total_steps": 40000, "loss": 0.1985, "lr": 4.536100993513423e-06, "epoch": 26.358575521899304, "percentage": 80.53, "elapsed_time": "3:42:22", "remaining_time": "0:53:46", "throughput": 786.53, "total_tokens": 10494136} {"current_steps": 32215, "total_steps": 40000, "loss": 0.1642, "lr": 4.530463149705768e-06, "epoch": 26.362668849774867, "percentage": 80.54, "elapsed_time": "3:42:24", "remaining_time": "0:53:44", "throughput": 786.55, "total_tokens": 10495800} {"current_steps": 32220, "total_steps": 40000, "loss": 0.1709, "lr": 4.524828462557934e-06, "epoch": 26.36676217765043, "percentage": 80.55, "elapsed_time": "3:42:25", "remaining_time": "0:53:42", "throughput": 786.57, "total_tokens": 10497480} {"current_steps": 32225, "total_steps": 40000, "loss": 0.204, "lr": 4.5191969329388625e-06, "epoch": 26.37085550552599, "percentage": 80.56, "elapsed_time": "3:42:27", "remaining_time": "0:53:40", "throughput": 786.6, "total_tokens": 10499144} {"current_steps": 32230, "total_steps": 40000, "loss": 0.2689, "lr": 4.5135685617169965e-06, "epoch": 26.374948833401554, "percentage": 80.58, "elapsed_time": "3:42:29", "remaining_time": "0:53:38", "throughput": 786.61, "total_tokens": 10500696} {"current_steps": 32235, "total_steps": 40000, "loss": 0.2431, "lr": 4.507943349760313e-06, "epoch": 26.37904216127712, "percentage": 80.59, "elapsed_time": "3:42:31", "remaining_time": "0:53:36", "throughput": 786.63, "total_tokens": 10502376} {"current_steps": 32240, "total_steps": 40000, "loss": 0.2172, "lr": 4.502321297936277e-06, "epoch": 26.383135489152682, "percentage": 80.6, "elapsed_time": "3:42:32", "remaining_time": "0:53:33", "throughput": 786.65, "total_tokens": 10504008} {"current_steps": 32245, "total_steps": 40000, "loss": 0.1687, "lr": 4.496702407111888e-06, "epoch": 26.387228817028245, "percentage": 80.61, "elapsed_time": "3:42:34", "remaining_time": "0:53:31", "throughput": 786.67, "total_tokens": 10505592} {"current_steps": 32250, "total_steps": 40000, "loss": 0.159, "lr": 4.491086678153653e-06, "epoch": 26.391322144903807, "percentage": 80.62, "elapsed_time": "3:42:36", "remaining_time": "0:53:29", "throughput": 786.68, "total_tokens": 10507160} {"current_steps": 32255, "total_steps": 40000, "loss": 0.1934, "lr": 4.485474111927579e-06, "epoch": 26.39541547277937, "percentage": 80.64, "elapsed_time": "3:42:38", "remaining_time": "0:53:27", "throughput": 786.7, "total_tokens": 10508712} {"current_steps": 32260, "total_steps": 40000, "loss": 0.1539, "lr": 4.479864709299197e-06, "epoch": 26.39950880065493, "percentage": 80.65, "elapsed_time": "3:42:39", "remaining_time": "0:53:25", "throughput": 786.71, "total_tokens": 10510296} {"current_steps": 32265, "total_steps": 40000, "loss": 0.1291, "lr": 4.474258471133555e-06, "epoch": 26.403602128530494, "percentage": 80.66, "elapsed_time": "3:42:41", "remaining_time": "0:53:23", "throughput": 786.73, "total_tokens": 10511944} {"current_steps": 32270, "total_steps": 40000, "loss": 0.1291, "lr": 4.4686553982952014e-06, "epoch": 26.407695456406056, "percentage": 80.67, "elapsed_time": "3:42:43", "remaining_time": "0:53:21", "throughput": 786.76, "total_tokens": 10513608} {"current_steps": 32275, "total_steps": 40000, "loss": 0.2042, "lr": 4.463055491648191e-06, "epoch": 26.411788784281622, "percentage": 80.69, "elapsed_time": "3:42:44", "remaining_time": "0:53:18", "throughput": 786.78, "total_tokens": 10515272} {"current_steps": 32280, "total_steps": 40000, "loss": 0.1363, "lr": 4.457458752056112e-06, "epoch": 26.415882112157185, "percentage": 80.7, "elapsed_time": "3:42:46", "remaining_time": "0:53:16", "throughput": 786.8, "total_tokens": 10516936} {"current_steps": 32285, "total_steps": 40000, "loss": 0.1802, "lr": 4.451865180382042e-06, "epoch": 26.419975440032747, "percentage": 80.71, "elapsed_time": "3:42:48", "remaining_time": "0:53:14", "throughput": 786.82, "total_tokens": 10518584} {"current_steps": 32290, "total_steps": 40000, "loss": 0.0872, "lr": 4.4462747774885936e-06, "epoch": 26.42406876790831, "percentage": 80.73, "elapsed_time": "3:42:50", "remaining_time": "0:53:12", "throughput": 786.84, "total_tokens": 10520232} {"current_steps": 32295, "total_steps": 40000, "loss": 0.1147, "lr": 4.440687544237859e-06, "epoch": 26.428162095783872, "percentage": 80.74, "elapsed_time": "3:42:51", "remaining_time": "0:53:10", "throughput": 786.86, "total_tokens": 10521848} {"current_steps": 32300, "total_steps": 40000, "loss": 0.1203, "lr": 4.435103481491471e-06, "epoch": 26.432255423659434, "percentage": 80.75, "elapsed_time": "3:42:53", "remaining_time": "0:53:08", "throughput": 786.88, "total_tokens": 10523448} {"current_steps": 32305, "total_steps": 40000, "loss": 0.2147, "lr": 4.429522590110569e-06, "epoch": 26.436348751534997, "percentage": 80.76, "elapsed_time": "3:42:55", "remaining_time": "0:53:05", "throughput": 786.91, "total_tokens": 10525176} {"current_steps": 32310, "total_steps": 40000, "loss": 0.138, "lr": 4.423944870955779e-06, "epoch": 26.44044207941056, "percentage": 80.77, "elapsed_time": "3:42:57", "remaining_time": "0:53:03", "throughput": 786.92, "total_tokens": 10526728} {"current_steps": 32315, "total_steps": 40000, "loss": 0.1569, "lr": 4.418370324887272e-06, "epoch": 26.444535407286125, "percentage": 80.79, "elapsed_time": "3:42:58", "remaining_time": "0:53:01", "throughput": 786.94, "total_tokens": 10528408} {"current_steps": 32320, "total_steps": 40000, "loss": 0.1823, "lr": 4.412798952764699e-06, "epoch": 26.448628735161687, "percentage": 80.8, "elapsed_time": "3:43:00", "remaining_time": "0:52:59", "throughput": 786.96, "total_tokens": 10530024} {"current_steps": 32325, "total_steps": 40000, "loss": 0.155, "lr": 4.407230755447245e-06, "epoch": 26.45272206303725, "percentage": 80.81, "elapsed_time": "3:43:02", "remaining_time": "0:52:57", "throughput": 786.98, "total_tokens": 10531656} {"current_steps": 32330, "total_steps": 40000, "loss": 0.2591, "lr": 4.401665733793598e-06, "epoch": 26.456815390912812, "percentage": 80.83, "elapsed_time": "3:43:04", "remaining_time": "0:52:55", "throughput": 787.0, "total_tokens": 10533304} {"current_steps": 32335, "total_steps": 40000, "loss": 0.1486, "lr": 4.3961038886619425e-06, "epoch": 26.460908718788374, "percentage": 80.84, "elapsed_time": "3:43:05", "remaining_time": "0:52:53", "throughput": 787.02, "total_tokens": 10534936} {"current_steps": 32340, "total_steps": 40000, "loss": 0.1563, "lr": 4.39054522091e-06, "epoch": 26.465002046663937, "percentage": 80.85, "elapsed_time": "3:43:07", "remaining_time": "0:52:50", "throughput": 787.04, "total_tokens": 10536520} {"current_steps": 32345, "total_steps": 40000, "loss": 0.1251, "lr": 4.384989731394979e-06, "epoch": 26.4690953745395, "percentage": 80.86, "elapsed_time": "3:43:09", "remaining_time": "0:52:48", "throughput": 787.06, "total_tokens": 10538184} {"current_steps": 32350, "total_steps": 40000, "loss": 0.1897, "lr": 4.379437420973598e-06, "epoch": 26.473188702415065, "percentage": 80.88, "elapsed_time": "3:43:11", "remaining_time": "0:52:46", "throughput": 787.08, "total_tokens": 10539816} {"current_steps": 32355, "total_steps": 40000, "loss": 0.2319, "lr": 4.373888290502107e-06, "epoch": 26.477282030290628, "percentage": 80.89, "elapsed_time": "3:43:12", "remaining_time": "0:52:44", "throughput": 787.1, "total_tokens": 10541416} {"current_steps": 32360, "total_steps": 40000, "loss": 0.2007, "lr": 4.36834234083624e-06, "epoch": 26.48137535816619, "percentage": 80.9, "elapsed_time": "3:43:14", "remaining_time": "0:52:42", "throughput": 787.12, "total_tokens": 10543064} {"current_steps": 32365, "total_steps": 40000, "loss": 0.1826, "lr": 4.362799572831258e-06, "epoch": 26.485468686041752, "percentage": 80.91, "elapsed_time": "3:43:16", "remaining_time": "0:52:40", "throughput": 787.14, "total_tokens": 10544712} {"current_steps": 32370, "total_steps": 40000, "loss": 0.2284, "lr": 4.35725998734193e-06, "epoch": 26.489562013917315, "percentage": 80.92, "elapsed_time": "3:43:17", "remaining_time": "0:52:38", "throughput": 787.16, "total_tokens": 10546296} {"current_steps": 32375, "total_steps": 40000, "loss": 0.3182, "lr": 4.3517235852225195e-06, "epoch": 26.493655341792877, "percentage": 80.94, "elapsed_time": "3:43:19", "remaining_time": "0:52:35", "throughput": 787.17, "total_tokens": 10547928} {"current_steps": 32380, "total_steps": 40000, "loss": 0.0934, "lr": 4.346190367326822e-06, "epoch": 26.49774866966844, "percentage": 80.95, "elapsed_time": "3:43:21", "remaining_time": "0:52:33", "throughput": 787.19, "total_tokens": 10549544} {"current_steps": 32385, "total_steps": 40000, "loss": 0.2386, "lr": 4.340660334508115e-06, "epoch": 26.501841997544002, "percentage": 80.96, "elapsed_time": "3:43:23", "remaining_time": "0:52:31", "throughput": 787.21, "total_tokens": 10551208} {"current_steps": 32390, "total_steps": 40000, "loss": 0.1525, "lr": 4.335133487619206e-06, "epoch": 26.505935325419568, "percentage": 80.97, "elapsed_time": "3:43:24", "remaining_time": "0:52:29", "throughput": 787.23, "total_tokens": 10552792} {"current_steps": 32395, "total_steps": 40000, "loss": 0.2637, "lr": 4.329609827512409e-06, "epoch": 26.51002865329513, "percentage": 80.99, "elapsed_time": "3:43:26", "remaining_time": "0:52:27", "throughput": 787.25, "total_tokens": 10554424} {"current_steps": 32400, "total_steps": 40000, "loss": 0.1747, "lr": 4.324089355039531e-06, "epoch": 26.514121981170693, "percentage": 81.0, "elapsed_time": "3:43:28", "remaining_time": "0:52:25", "throughput": 787.27, "total_tokens": 10556056} {"current_steps": 32400, "total_steps": 40000, "eval_loss": 0.21609848737716675, "epoch": 26.514121981170693, "percentage": 81.0, "elapsed_time": "3:43:40", "remaining_time": "0:52:28", "throughput": 786.54, "total_tokens": 10556056} {"current_steps": 32405, "total_steps": 40000, "loss": 0.1635, "lr": 4.3185720710519075e-06, "epoch": 26.518215309046255, "percentage": 81.01, "elapsed_time": "3:43:44", "remaining_time": "0:52:26", "throughput": 786.47, "total_tokens": 10557720} {"current_steps": 32410, "total_steps": 40000, "loss": 0.1568, "lr": 4.3130579764003724e-06, "epoch": 26.522308636921817, "percentage": 81.03, "elapsed_time": "3:43:45", "remaining_time": "0:52:24", "throughput": 786.49, "total_tokens": 10559320} {"current_steps": 32415, "total_steps": 40000, "loss": 0.185, "lr": 4.307547071935267e-06, "epoch": 26.52640196479738, "percentage": 81.04, "elapsed_time": "3:43:47", "remaining_time": "0:52:22", "throughput": 786.51, "total_tokens": 10560936} {"current_steps": 32420, "total_steps": 40000, "loss": 0.1506, "lr": 4.302039358506435e-06, "epoch": 26.530495292672942, "percentage": 81.05, "elapsed_time": "3:43:49", "remaining_time": "0:52:19", "throughput": 786.52, "total_tokens": 10562472} {"current_steps": 32425, "total_steps": 40000, "loss": 0.284, "lr": 4.296534836963245e-06, "epoch": 26.534588620548504, "percentage": 81.06, "elapsed_time": "3:43:51", "remaining_time": "0:52:17", "throughput": 786.54, "total_tokens": 10564072} {"current_steps": 32430, "total_steps": 40000, "loss": 0.1419, "lr": 4.291033508154555e-06, "epoch": 26.53868194842407, "percentage": 81.08, "elapsed_time": "3:43:52", "remaining_time": "0:52:15", "throughput": 786.56, "total_tokens": 10565720} {"current_steps": 32435, "total_steps": 40000, "loss": 0.1075, "lr": 4.285535372928748e-06, "epoch": 26.542775276299633, "percentage": 81.09, "elapsed_time": "3:43:54", "remaining_time": "0:52:13", "throughput": 786.58, "total_tokens": 10567320} {"current_steps": 32440, "total_steps": 40000, "loss": 0.1123, "lr": 4.280040432133695e-06, "epoch": 26.546868604175195, "percentage": 81.1, "elapsed_time": "3:43:56", "remaining_time": "0:52:11", "throughput": 786.59, "total_tokens": 10568936} {"current_steps": 32445, "total_steps": 40000, "loss": 0.1772, "lr": 4.274548686616789e-06, "epoch": 26.550961932050757, "percentage": 81.11, "elapsed_time": "3:43:58", "remaining_time": "0:52:09", "throughput": 786.62, "total_tokens": 10570600} {"current_steps": 32450, "total_steps": 40000, "loss": 0.2, "lr": 4.2690601372249364e-06, "epoch": 26.55505525992632, "percentage": 81.12, "elapsed_time": "3:43:59", "remaining_time": "0:52:06", "throughput": 786.64, "total_tokens": 10572200} {"current_steps": 32455, "total_steps": 40000, "loss": 0.1251, "lr": 4.263574784804525e-06, "epoch": 26.559148587801882, "percentage": 81.14, "elapsed_time": "3:44:01", "remaining_time": "0:52:04", "throughput": 786.66, "total_tokens": 10573864} {"current_steps": 32460, "total_steps": 40000, "loss": 0.1728, "lr": 4.258092630201479e-06, "epoch": 26.563241915677445, "percentage": 81.15, "elapsed_time": "3:44:03", "remaining_time": "0:52:02", "throughput": 786.68, "total_tokens": 10575608} {"current_steps": 32465, "total_steps": 40000, "loss": 0.1426, "lr": 4.252613674261202e-06, "epoch": 26.567335243553007, "percentage": 81.16, "elapsed_time": "3:44:05", "remaining_time": "0:52:00", "throughput": 786.7, "total_tokens": 10577240} {"current_steps": 32470, "total_steps": 40000, "loss": 0.2328, "lr": 4.2471379178286224e-06, "epoch": 26.571428571428573, "percentage": 81.17, "elapsed_time": "3:44:06", "remaining_time": "0:51:58", "throughput": 786.73, "total_tokens": 10578904} {"current_steps": 32475, "total_steps": 40000, "loss": 0.1547, "lr": 4.241665361748181e-06, "epoch": 26.575521899304135, "percentage": 81.19, "elapsed_time": "3:44:08", "remaining_time": "0:51:56", "throughput": 786.75, "total_tokens": 10580584} {"current_steps": 32480, "total_steps": 40000, "loss": 0.1747, "lr": 4.2361960068637994e-06, "epoch": 26.579615227179698, "percentage": 81.2, "elapsed_time": "3:44:10", "remaining_time": "0:51:54", "throughput": 786.78, "total_tokens": 10582280} {"current_steps": 32485, "total_steps": 40000, "loss": 0.1532, "lr": 4.230729854018933e-06, "epoch": 26.58370855505526, "percentage": 81.21, "elapsed_time": "3:44:11", "remaining_time": "0:51:51", "throughput": 786.79, "total_tokens": 10583880} {"current_steps": 32490, "total_steps": 40000, "loss": 0.2649, "lr": 4.225266904056521e-06, "epoch": 26.587801882930822, "percentage": 81.23, "elapsed_time": "3:44:13", "remaining_time": "0:51:49", "throughput": 786.81, "total_tokens": 10585528} {"current_steps": 32495, "total_steps": 40000, "loss": 0.1825, "lr": 4.21980715781903e-06, "epoch": 26.591895210806385, "percentage": 81.24, "elapsed_time": "3:44:15", "remaining_time": "0:51:47", "throughput": 786.84, "total_tokens": 10587256} {"current_steps": 32500, "total_steps": 40000, "loss": 0.1746, "lr": 4.214350616148416e-06, "epoch": 26.595988538681947, "percentage": 81.25, "elapsed_time": "3:44:17", "remaining_time": "0:51:45", "throughput": 786.86, "total_tokens": 10588904} {"current_steps": 32505, "total_steps": 40000, "loss": 0.1144, "lr": 4.20889727988614e-06, "epoch": 26.60008186655751, "percentage": 81.26, "elapsed_time": "3:44:18", "remaining_time": "0:51:43", "throughput": 786.88, "total_tokens": 10590520} {"current_steps": 32510, "total_steps": 40000, "loss": 0.1493, "lr": 4.20344714987318e-06, "epoch": 26.604175194433076, "percentage": 81.27, "elapsed_time": "3:44:20", "remaining_time": "0:51:41", "throughput": 786.9, "total_tokens": 10592120} {"current_steps": 32515, "total_steps": 40000, "loss": 0.1667, "lr": 4.198000226950022e-06, "epoch": 26.608268522308638, "percentage": 81.29, "elapsed_time": "3:44:22", "remaining_time": "0:51:39", "throughput": 786.92, "total_tokens": 10593752} {"current_steps": 32520, "total_steps": 40000, "loss": 0.1619, "lr": 4.192556511956635e-06, "epoch": 26.6123618501842, "percentage": 81.3, "elapsed_time": "3:44:24", "remaining_time": "0:51:36", "throughput": 786.93, "total_tokens": 10595336} {"current_steps": 32525, "total_steps": 40000, "loss": 0.146, "lr": 4.18711600573252e-06, "epoch": 26.616455178059763, "percentage": 81.31, "elapsed_time": "3:44:25", "remaining_time": "0:51:34", "throughput": 786.95, "total_tokens": 10596952} {"current_steps": 32530, "total_steps": 40000, "loss": 0.2467, "lr": 4.181678709116671e-06, "epoch": 26.620548505935325, "percentage": 81.33, "elapsed_time": "3:44:27", "remaining_time": "0:51:32", "throughput": 786.97, "total_tokens": 10598552} {"current_steps": 32535, "total_steps": 40000, "loss": 0.2532, "lr": 4.1762446229475785e-06, "epoch": 26.624641833810887, "percentage": 81.34, "elapsed_time": "3:44:29", "remaining_time": "0:51:30", "throughput": 786.99, "total_tokens": 10600184} {"current_steps": 32540, "total_steps": 40000, "loss": 0.1034, "lr": 4.17081374806326e-06, "epoch": 26.62873516168645, "percentage": 81.35, "elapsed_time": "3:44:31", "remaining_time": "0:51:28", "throughput": 787.01, "total_tokens": 10601800} {"current_steps": 32545, "total_steps": 40000, "loss": 0.2087, "lr": 4.165386085301212e-06, "epoch": 26.632828489562012, "percentage": 81.36, "elapsed_time": "3:44:32", "remaining_time": "0:51:26", "throughput": 787.02, "total_tokens": 10603432} {"current_steps": 32550, "total_steps": 40000, "loss": 0.1593, "lr": 4.1599616354984525e-06, "epoch": 26.636921817437578, "percentage": 81.38, "elapsed_time": "3:44:34", "remaining_time": "0:51:24", "throughput": 787.04, "total_tokens": 10605048} {"current_steps": 32555, "total_steps": 40000, "loss": 0.1776, "lr": 4.154540399491508e-06, "epoch": 26.64101514531314, "percentage": 81.39, "elapsed_time": "3:44:36", "remaining_time": "0:51:21", "throughput": 787.06, "total_tokens": 10606664} {"current_steps": 32560, "total_steps": 40000, "loss": 0.0945, "lr": 4.149122378116394e-06, "epoch": 26.645108473188703, "percentage": 81.4, "elapsed_time": "3:44:38", "remaining_time": "0:51:19", "throughput": 787.08, "total_tokens": 10608296} {"current_steps": 32565, "total_steps": 40000, "loss": 0.2046, "lr": 4.14370757220863e-06, "epoch": 26.649201801064265, "percentage": 81.41, "elapsed_time": "3:44:39", "remaining_time": "0:51:17", "throughput": 787.1, "total_tokens": 10609912} {"current_steps": 32570, "total_steps": 40000, "loss": 0.2174, "lr": 4.138295982603263e-06, "epoch": 26.653295128939828, "percentage": 81.42, "elapsed_time": "3:44:41", "remaining_time": "0:51:15", "throughput": 787.13, "total_tokens": 10611624} {"current_steps": 32575, "total_steps": 40000, "loss": 0.1912, "lr": 4.132887610134814e-06, "epoch": 26.65738845681539, "percentage": 81.44, "elapsed_time": "3:44:43", "remaining_time": "0:51:13", "throughput": 787.14, "total_tokens": 10613256} {"current_steps": 32580, "total_steps": 40000, "loss": 0.1832, "lr": 4.127482455637335e-06, "epoch": 26.661481784690952, "percentage": 81.45, "elapsed_time": "3:44:44", "remaining_time": "0:51:11", "throughput": 787.17, "total_tokens": 10614920} {"current_steps": 32585, "total_steps": 40000, "loss": 0.1234, "lr": 4.1220805199443545e-06, "epoch": 26.665575112566515, "percentage": 81.46, "elapsed_time": "3:44:46", "remaining_time": "0:51:09", "throughput": 787.18, "total_tokens": 10616504} {"current_steps": 32590, "total_steps": 40000, "loss": 0.2754, "lr": 4.116681803888925e-06, "epoch": 26.66966844044208, "percentage": 81.47, "elapsed_time": "3:44:48", "remaining_time": "0:51:06", "throughput": 787.21, "total_tokens": 10618200} {"current_steps": 32595, "total_steps": 40000, "loss": 0.1536, "lr": 4.111286308303605e-06, "epoch": 26.673761768317643, "percentage": 81.49, "elapsed_time": "3:44:50", "remaining_time": "0:51:04", "throughput": 787.23, "total_tokens": 10619848} {"current_steps": 32600, "total_steps": 40000, "loss": 0.1391, "lr": 4.105894034020433e-06, "epoch": 26.677855096193205, "percentage": 81.5, "elapsed_time": "3:44:51", "remaining_time": "0:51:02", "throughput": 787.24, "total_tokens": 10621432} {"current_steps": 32600, "total_steps": 40000, "eval_loss": 0.21451368927955627, "epoch": 26.677855096193205, "percentage": 81.5, "elapsed_time": "3:45:04", "remaining_time": "0:51:05", "throughput": 786.52, "total_tokens": 10621432} {"current_steps": 32605, "total_steps": 40000, "loss": 0.1495, "lr": 4.100504981870975e-06, "epoch": 26.681948424068768, "percentage": 81.51, "elapsed_time": "3:45:07", "remaining_time": "0:51:03", "throughput": 786.44, "total_tokens": 10623064} {"current_steps": 32610, "total_steps": 40000, "loss": 0.1719, "lr": 4.0951191526862915e-06, "epoch": 26.68604175194433, "percentage": 81.53, "elapsed_time": "3:45:09", "remaining_time": "0:51:01", "throughput": 786.46, "total_tokens": 10624728} {"current_steps": 32615, "total_steps": 40000, "loss": 0.2164, "lr": 4.089736547296938e-06, "epoch": 26.690135079819893, "percentage": 81.54, "elapsed_time": "3:45:11", "remaining_time": "0:50:59", "throughput": 786.48, "total_tokens": 10626376} {"current_steps": 32620, "total_steps": 40000, "loss": 0.1775, "lr": 4.08435716653299e-06, "epoch": 26.694228407695455, "percentage": 81.55, "elapsed_time": "3:45:13", "remaining_time": "0:50:57", "throughput": 786.5, "total_tokens": 10627976} {"current_steps": 32625, "total_steps": 40000, "loss": 0.1353, "lr": 4.0789810112240005e-06, "epoch": 26.69832173557102, "percentage": 81.56, "elapsed_time": "3:45:14", "remaining_time": "0:50:55", "throughput": 786.52, "total_tokens": 10629592} {"current_steps": 32630, "total_steps": 40000, "loss": 0.2213, "lr": 4.073608082199057e-06, "epoch": 26.702415063446583, "percentage": 81.58, "elapsed_time": "3:45:16", "remaining_time": "0:50:52", "throughput": 786.54, "total_tokens": 10631256} {"current_steps": 32635, "total_steps": 40000, "loss": 0.164, "lr": 4.068238380286718e-06, "epoch": 26.706508391322146, "percentage": 81.59, "elapsed_time": "3:45:18", "remaining_time": "0:50:50", "throughput": 786.56, "total_tokens": 10632936} {"current_steps": 32640, "total_steps": 40000, "loss": 0.1881, "lr": 4.062871906315072e-06, "epoch": 26.710601719197708, "percentage": 81.6, "elapsed_time": "3:45:19", "remaining_time": "0:50:48", "throughput": 786.59, "total_tokens": 10634616} {"current_steps": 32645, "total_steps": 40000, "loss": 0.1266, "lr": 4.057508661111686e-06, "epoch": 26.71469504707327, "percentage": 81.61, "elapsed_time": "3:45:21", "remaining_time": "0:50:46", "throughput": 786.6, "total_tokens": 10636232} {"current_steps": 32650, "total_steps": 40000, "loss": 0.1346, "lr": 4.052148645503648e-06, "epoch": 26.718788374948833, "percentage": 81.62, "elapsed_time": "3:45:23", "remaining_time": "0:50:44", "throughput": 786.62, "total_tokens": 10637864} {"current_steps": 32655, "total_steps": 40000, "loss": 0.1376, "lr": 4.046791860317531e-06, "epoch": 26.722881702824395, "percentage": 81.64, "elapsed_time": "3:45:25", "remaining_time": "0:50:42", "throughput": 786.64, "total_tokens": 10639464} {"current_steps": 32660, "total_steps": 40000, "loss": 0.2057, "lr": 4.041438306379431e-06, "epoch": 26.726975030699958, "percentage": 81.65, "elapsed_time": "3:45:26", "remaining_time": "0:50:40", "throughput": 786.65, "total_tokens": 10641000} {"current_steps": 32665, "total_steps": 40000, "loss": 0.1552, "lr": 4.036087984514916e-06, "epoch": 26.731068358575524, "percentage": 81.66, "elapsed_time": "3:45:28", "remaining_time": "0:50:37", "throughput": 786.67, "total_tokens": 10642616} {"current_steps": 32670, "total_steps": 40000, "loss": 0.1346, "lr": 4.030740895549084e-06, "epoch": 26.735161686451086, "percentage": 81.67, "elapsed_time": "3:45:30", "remaining_time": "0:50:35", "throughput": 786.7, "total_tokens": 10644296} {"current_steps": 32675, "total_steps": 40000, "loss": 0.2402, "lr": 4.025397040306531e-06, "epoch": 26.73925501432665, "percentage": 81.69, "elapsed_time": "3:45:32", "remaining_time": "0:50:33", "throughput": 786.71, "total_tokens": 10645896} {"current_steps": 32680, "total_steps": 40000, "loss": 0.1567, "lr": 4.0200564196113285e-06, "epoch": 26.74334834220221, "percentage": 81.7, "elapsed_time": "3:45:33", "remaining_time": "0:50:31", "throughput": 786.73, "total_tokens": 10647544} {"current_steps": 32685, "total_steps": 40000, "loss": 0.1785, "lr": 4.014719034287079e-06, "epoch": 26.747441670077773, "percentage": 81.71, "elapsed_time": "3:45:35", "remaining_time": "0:50:29", "throughput": 786.75, "total_tokens": 10649192} {"current_steps": 32690, "total_steps": 40000, "loss": 0.1842, "lr": 4.0093848851568775e-06, "epoch": 26.751534997953335, "percentage": 81.73, "elapsed_time": "3:45:37", "remaining_time": "0:50:27", "throughput": 786.77, "total_tokens": 10650792} {"current_steps": 32695, "total_steps": 40000, "loss": 0.2003, "lr": 4.004053973043304e-06, "epoch": 26.755628325828898, "percentage": 81.74, "elapsed_time": "3:45:39", "remaining_time": "0:50:25", "throughput": 786.79, "total_tokens": 10652440} {"current_steps": 32700, "total_steps": 40000, "loss": 0.1839, "lr": 3.998726298768465e-06, "epoch": 26.75972165370446, "percentage": 81.75, "elapsed_time": "3:45:40", "remaining_time": "0:50:22", "throughput": 786.81, "total_tokens": 10654024} {"current_steps": 32705, "total_steps": 40000, "loss": 0.158, "lr": 3.99340186315395e-06, "epoch": 26.763814981580026, "percentage": 81.76, "elapsed_time": "3:45:42", "remaining_time": "0:50:20", "throughput": 786.83, "total_tokens": 10655640} {"current_steps": 32710, "total_steps": 40000, "loss": 0.2566, "lr": 3.988080667020849e-06, "epoch": 26.76790830945559, "percentage": 81.77, "elapsed_time": "3:45:44", "remaining_time": "0:50:18", "throughput": 786.84, "total_tokens": 10657256} {"current_steps": 32715, "total_steps": 40000, "loss": 0.2055, "lr": 3.982762711189766e-06, "epoch": 26.77200163733115, "percentage": 81.79, "elapsed_time": "3:45:46", "remaining_time": "0:50:16", "throughput": 786.86, "total_tokens": 10658872} {"current_steps": 32720, "total_steps": 40000, "loss": 0.1266, "lr": 3.977447996480785e-06, "epoch": 26.776094965206713, "percentage": 81.8, "elapsed_time": "3:45:47", "remaining_time": "0:50:14", "throughput": 786.88, "total_tokens": 10660488} {"current_steps": 32725, "total_steps": 40000, "loss": 0.1789, "lr": 3.97213652371351e-06, "epoch": 26.780188293082276, "percentage": 81.81, "elapsed_time": "3:45:49", "remaining_time": "0:50:12", "throughput": 786.9, "total_tokens": 10662104} {"current_steps": 32730, "total_steps": 40000, "loss": 0.1838, "lr": 3.966828293707042e-06, "epoch": 26.784281620957838, "percentage": 81.83, "elapsed_time": "3:45:51", "remaining_time": "0:50:10", "throughput": 786.92, "total_tokens": 10663848} {"current_steps": 32735, "total_steps": 40000, "loss": 0.2119, "lr": 3.961523307279963e-06, "epoch": 26.7883749488334, "percentage": 81.84, "elapsed_time": "3:45:53", "remaining_time": "0:50:07", "throughput": 786.95, "total_tokens": 10665512} {"current_steps": 32740, "total_steps": 40000, "loss": 0.2095, "lr": 3.956221565250382e-06, "epoch": 26.792468276708963, "percentage": 81.85, "elapsed_time": "3:45:54", "remaining_time": "0:50:05", "throughput": 786.97, "total_tokens": 10667112} {"current_steps": 32745, "total_steps": 40000, "loss": 0.1457, "lr": 3.950923068435883e-06, "epoch": 26.79656160458453, "percentage": 81.86, "elapsed_time": "3:45:56", "remaining_time": "0:50:03", "throughput": 786.99, "total_tokens": 10668760} {"current_steps": 32750, "total_steps": 40000, "loss": 0.1009, "lr": 3.945627817653566e-06, "epoch": 26.80065493246009, "percentage": 81.88, "elapsed_time": "3:45:58", "remaining_time": "0:50:01", "throughput": 787.0, "total_tokens": 10670360} {"current_steps": 32755, "total_steps": 40000, "loss": 0.2345, "lr": 3.9403358137200335e-06, "epoch": 26.804748260335653, "percentage": 81.89, "elapsed_time": "3:46:00", "remaining_time": "0:49:59", "throughput": 787.02, "total_tokens": 10672008} {"current_steps": 32760, "total_steps": 40000, "loss": 0.1686, "lr": 3.9350470574513605e-06, "epoch": 26.808841588211216, "percentage": 81.9, "elapsed_time": "3:46:01", "remaining_time": "0:49:57", "throughput": 787.04, "total_tokens": 10673688} {"current_steps": 32765, "total_steps": 40000, "loss": 0.1347, "lr": 3.9297615496631525e-06, "epoch": 26.81293491608678, "percentage": 81.91, "elapsed_time": "3:46:03", "remaining_time": "0:49:55", "throughput": 787.06, "total_tokens": 10675304} {"current_steps": 32770, "total_steps": 40000, "loss": 0.2112, "lr": 3.924479291170505e-06, "epoch": 26.81702824396234, "percentage": 81.92, "elapsed_time": "3:46:05", "remaining_time": "0:49:52", "throughput": 787.08, "total_tokens": 10676936} {"current_steps": 32775, "total_steps": 40000, "loss": 0.2076, "lr": 3.919200282788002e-06, "epoch": 26.821121571837903, "percentage": 81.94, "elapsed_time": "3:46:06", "remaining_time": "0:49:50", "throughput": 787.11, "total_tokens": 10678600} {"current_steps": 32780, "total_steps": 40000, "loss": 0.1239, "lr": 3.913924525329726e-06, "epoch": 26.825214899713465, "percentage": 81.95, "elapsed_time": "3:46:08", "remaining_time": "0:49:48", "throughput": 787.12, "total_tokens": 10680216} {"current_steps": 32785, "total_steps": 40000, "loss": 0.154, "lr": 3.908652019609279e-06, "epoch": 26.82930822758903, "percentage": 81.96, "elapsed_time": "3:46:10", "remaining_time": "0:49:46", "throughput": 787.14, "total_tokens": 10681848} {"current_steps": 32790, "total_steps": 40000, "loss": 0.1626, "lr": 3.9033827664397364e-06, "epoch": 26.833401555464594, "percentage": 81.97, "elapsed_time": "3:46:12", "remaining_time": "0:49:44", "throughput": 787.16, "total_tokens": 10683496} {"current_steps": 32795, "total_steps": 40000, "loss": 0.1662, "lr": 3.898116766633694e-06, "epoch": 26.837494883340156, "percentage": 81.99, "elapsed_time": "3:46:13", "remaining_time": "0:49:42", "throughput": 787.18, "total_tokens": 10685160} {"current_steps": 32800, "total_steps": 40000, "loss": 0.2583, "lr": 3.8928540210032225e-06, "epoch": 26.84158821121572, "percentage": 82.0, "elapsed_time": "3:46:15", "remaining_time": "0:49:40", "throughput": 787.2, "total_tokens": 10686808} {"current_steps": 32800, "total_steps": 40000, "eval_loss": 0.21344970166683197, "epoch": 26.84158821121572, "percentage": 82.0, "elapsed_time": "3:46:28", "remaining_time": "0:49:42", "throughput": 786.48, "total_tokens": 10686808} {"current_steps": 32805, "total_steps": 40000, "loss": 0.1075, "lr": 3.887594530359909e-06, "epoch": 26.84568153909128, "percentage": 82.01, "elapsed_time": "3:46:31", "remaining_time": "0:49:40", "throughput": 786.41, "total_tokens": 10688376} {"current_steps": 32810, "total_steps": 40000, "loss": 0.1541, "lr": 3.88233829551484e-06, "epoch": 26.849774866966843, "percentage": 82.03, "elapsed_time": "3:46:33", "remaining_time": "0:49:38", "throughput": 786.42, "total_tokens": 10689944} {"current_steps": 32815, "total_steps": 40000, "loss": 0.1225, "lr": 3.877085317278581e-06, "epoch": 26.853868194842406, "percentage": 82.04, "elapsed_time": "3:46:34", "remaining_time": "0:49:36", "throughput": 786.44, "total_tokens": 10691560} {"current_steps": 32820, "total_steps": 40000, "loss": 0.1799, "lr": 3.87183559646122e-06, "epoch": 26.857961522717968, "percentage": 82.05, "elapsed_time": "3:46:36", "remaining_time": "0:49:34", "throughput": 786.46, "total_tokens": 10693160} {"current_steps": 32825, "total_steps": 40000, "loss": 0.1648, "lr": 3.866589133872317e-06, "epoch": 26.862054850593534, "percentage": 82.06, "elapsed_time": "3:46:38", "remaining_time": "0:49:32", "throughput": 786.48, "total_tokens": 10694776} {"current_steps": 32830, "total_steps": 40000, "loss": 0.1803, "lr": 3.861345930320948e-06, "epoch": 26.866148178469096, "percentage": 82.08, "elapsed_time": "3:46:40", "remaining_time": "0:49:30", "throughput": 786.5, "total_tokens": 10696456} {"current_steps": 32835, "total_steps": 40000, "loss": 0.1346, "lr": 3.856105986615688e-06, "epoch": 26.87024150634466, "percentage": 82.09, "elapsed_time": "3:46:41", "remaining_time": "0:49:28", "throughput": 786.52, "total_tokens": 10698088} {"current_steps": 32840, "total_steps": 40000, "loss": 0.11, "lr": 3.850869303564589e-06, "epoch": 26.87433483422022, "percentage": 82.1, "elapsed_time": "3:46:43", "remaining_time": "0:49:25", "throughput": 786.54, "total_tokens": 10699672} {"current_steps": 32845, "total_steps": 40000, "loss": 0.1471, "lr": 3.845635881975226e-06, "epoch": 26.878428162095783, "percentage": 82.11, "elapsed_time": "3:46:45", "remaining_time": "0:49:23", "throughput": 786.56, "total_tokens": 10701304} {"current_steps": 32850, "total_steps": 40000, "loss": 0.1671, "lr": 3.840405722654647e-06, "epoch": 26.882521489971346, "percentage": 82.12, "elapsed_time": "3:46:46", "remaining_time": "0:49:21", "throughput": 786.57, "total_tokens": 10702904} {"current_steps": 32855, "total_steps": 40000, "loss": 0.2065, "lr": 3.835178826409419e-06, "epoch": 26.886614817846908, "percentage": 82.14, "elapsed_time": "3:46:48", "remaining_time": "0:49:19", "throughput": 786.59, "total_tokens": 10704536} {"current_steps": 32860, "total_steps": 40000, "loss": 0.1156, "lr": 3.8299551940455895e-06, "epoch": 26.89070814572247, "percentage": 82.15, "elapsed_time": "3:46:50", "remaining_time": "0:49:17", "throughput": 786.62, "total_tokens": 10706184} {"current_steps": 32865, "total_steps": 40000, "loss": 0.2051, "lr": 3.824734826368703e-06, "epoch": 26.894801473598037, "percentage": 82.16, "elapsed_time": "3:46:52", "remaining_time": "0:49:15", "throughput": 786.64, "total_tokens": 10707832} {"current_steps": 32870, "total_steps": 40000, "loss": 0.1675, "lr": 3.819517724183813e-06, "epoch": 26.8988948014736, "percentage": 82.17, "elapsed_time": "3:46:53", "remaining_time": "0:49:13", "throughput": 786.66, "total_tokens": 10709480} {"current_steps": 32875, "total_steps": 40000, "loss": 0.2528, "lr": 3.8143038882954648e-06, "epoch": 26.90298812934916, "percentage": 82.19, "elapsed_time": "3:46:55", "remaining_time": "0:49:10", "throughput": 786.67, "total_tokens": 10711128} {"current_steps": 32880, "total_steps": 40000, "loss": 0.2264, "lr": 3.8090933195076867e-06, "epoch": 26.907081457224724, "percentage": 82.2, "elapsed_time": "3:46:57", "remaining_time": "0:49:08", "throughput": 786.69, "total_tokens": 10712760} {"current_steps": 32885, "total_steps": 40000, "loss": 0.1243, "lr": 3.8038860186240198e-06, "epoch": 26.911174785100286, "percentage": 82.21, "elapsed_time": "3:46:59", "remaining_time": "0:49:06", "throughput": 786.71, "total_tokens": 10714376} {"current_steps": 32890, "total_steps": 40000, "loss": 0.2226, "lr": 3.7986819864475026e-06, "epoch": 26.91526811297585, "percentage": 82.23, "elapsed_time": "3:47:00", "remaining_time": "0:49:04", "throughput": 786.74, "total_tokens": 10716040} {"current_steps": 32895, "total_steps": 40000, "loss": 0.15, "lr": 3.793481223780651e-06, "epoch": 26.91936144085141, "percentage": 82.24, "elapsed_time": "3:47:02", "remaining_time": "0:49:02", "throughput": 786.76, "total_tokens": 10717672} {"current_steps": 32900, "total_steps": 40000, "loss": 0.1669, "lr": 3.788283731425496e-06, "epoch": 26.923454768726977, "percentage": 82.25, "elapsed_time": "3:47:04", "remaining_time": "0:49:00", "throughput": 786.78, "total_tokens": 10719368} {"current_steps": 32905, "total_steps": 40000, "loss": 0.1678, "lr": 3.7830895101835488e-06, "epoch": 26.92754809660254, "percentage": 82.26, "elapsed_time": "3:47:06", "remaining_time": "0:48:58", "throughput": 786.8, "total_tokens": 10720952} {"current_steps": 32910, "total_steps": 40000, "loss": 0.1971, "lr": 3.7778985608558274e-06, "epoch": 26.9316414244781, "percentage": 82.27, "elapsed_time": "3:47:07", "remaining_time": "0:48:55", "throughput": 786.82, "total_tokens": 10722632} {"current_steps": 32915, "total_steps": 40000, "loss": 0.2144, "lr": 3.7727108842428443e-06, "epoch": 26.935734752353664, "percentage": 82.29, "elapsed_time": "3:47:09", "remaining_time": "0:48:53", "throughput": 786.84, "total_tokens": 10724312} {"current_steps": 32920, "total_steps": 40000, "loss": 0.2569, "lr": 3.7675264811446065e-06, "epoch": 26.939828080229226, "percentage": 82.3, "elapsed_time": "3:47:11", "remaining_time": "0:48:51", "throughput": 786.86, "total_tokens": 10725912} {"current_steps": 32925, "total_steps": 40000, "loss": 0.1249, "lr": 3.7623453523605994e-06, "epoch": 26.94392140810479, "percentage": 82.31, "elapsed_time": "3:47:13", "remaining_time": "0:48:49", "throughput": 786.88, "total_tokens": 10727624} {"current_steps": 32930, "total_steps": 40000, "loss": 0.1788, "lr": 3.757167498689834e-06, "epoch": 26.94801473598035, "percentage": 82.33, "elapsed_time": "3:47:14", "remaining_time": "0:48:47", "throughput": 786.9, "total_tokens": 10729256} {"current_steps": 32935, "total_steps": 40000, "loss": 0.237, "lr": 3.7519929209307914e-06, "epoch": 26.952108063855913, "percentage": 82.34, "elapsed_time": "3:47:16", "remaining_time": "0:48:45", "throughput": 786.9, "total_tokens": 10730856} {"current_steps": 32940, "total_steps": 40000, "loss": 0.1378, "lr": 3.746821619881463e-06, "epoch": 26.95620139173148, "percentage": 82.35, "elapsed_time": "3:47:18", "remaining_time": "0:48:43", "throughput": 786.92, "total_tokens": 10732456} {"current_steps": 32945, "total_steps": 40000, "loss": 0.1398, "lr": 3.74165359633932e-06, "epoch": 26.96029471960704, "percentage": 82.36, "elapsed_time": "3:47:20", "remaining_time": "0:48:40", "throughput": 786.95, "total_tokens": 10734120} {"current_steps": 32950, "total_steps": 40000, "loss": 0.2106, "lr": 3.736488851101341e-06, "epoch": 26.964388047482604, "percentage": 82.38, "elapsed_time": "3:47:21", "remaining_time": "0:48:38", "throughput": 786.97, "total_tokens": 10735784} {"current_steps": 32955, "total_steps": 40000, "loss": 0.1651, "lr": 3.7313273849640035e-06, "epoch": 26.968481375358166, "percentage": 82.39, "elapsed_time": "3:47:23", "remaining_time": "0:48:36", "throughput": 786.99, "total_tokens": 10737496} {"current_steps": 32960, "total_steps": 40000, "loss": 0.2151, "lr": 3.7261691987232533e-06, "epoch": 26.97257470323373, "percentage": 82.4, "elapsed_time": "3:47:25", "remaining_time": "0:48:34", "throughput": 787.01, "total_tokens": 10739128} {"current_steps": 32965, "total_steps": 40000, "loss": 0.1353, "lr": 3.7210142931745575e-06, "epoch": 26.97666803110929, "percentage": 82.41, "elapsed_time": "3:47:27", "remaining_time": "0:48:32", "throughput": 787.03, "total_tokens": 10740728} {"current_steps": 32970, "total_steps": 40000, "loss": 0.1606, "lr": 3.7158626691128712e-06, "epoch": 26.980761358984854, "percentage": 82.42, "elapsed_time": "3:47:28", "remaining_time": "0:48:30", "throughput": 787.04, "total_tokens": 10742328} {"current_steps": 32975, "total_steps": 40000, "loss": 0.145, "lr": 3.710714327332629e-06, "epoch": 26.984854686860416, "percentage": 82.44, "elapsed_time": "3:47:30", "remaining_time": "0:48:28", "throughput": 787.06, "total_tokens": 10743960} {"current_steps": 32980, "total_steps": 40000, "loss": 0.1487, "lr": 3.7055692686277815e-06, "epoch": 26.988948014735982, "percentage": 82.45, "elapsed_time": "3:47:32", "remaining_time": "0:48:26", "throughput": 787.08, "total_tokens": 10745560} {"current_steps": 32985, "total_steps": 40000, "loss": 0.1897, "lr": 3.70042749379175e-06, "epoch": 26.993041342611544, "percentage": 82.46, "elapsed_time": "3:47:34", "remaining_time": "0:48:23", "throughput": 787.1, "total_tokens": 10747176} {"current_steps": 32990, "total_steps": 40000, "loss": 0.1742, "lr": 3.6952890036174693e-06, "epoch": 26.997134670487107, "percentage": 82.47, "elapsed_time": "3:47:35", "remaining_time": "0:48:21", "throughput": 787.13, "total_tokens": 10748856} {"current_steps": 32995, "total_steps": 40000, "loss": 0.1305, "lr": 3.690153798897353e-06, "epoch": 27.000818665575114, "percentage": 82.49, "elapsed_time": "3:47:37", "remaining_time": "0:48:19", "throughput": 787.12, "total_tokens": 10750280} {"current_steps": 33000, "total_steps": 40000, "loss": 0.1223, "lr": 3.6850218804233225e-06, "epoch": 27.004911993450676, "percentage": 82.5, "elapsed_time": "3:47:39", "remaining_time": "0:48:17", "throughput": 787.14, "total_tokens": 10751912} {"current_steps": 33000, "total_steps": 40000, "eval_loss": 0.21115587651729584, "epoch": 27.004911993450676, "percentage": 82.5, "elapsed_time": "3:47:51", "remaining_time": "0:48:20", "throughput": 786.42, "total_tokens": 10751912} {"current_steps": 33005, "total_steps": 40000, "loss": 0.1136, "lr": 3.679893248986779e-06, "epoch": 27.00900532132624, "percentage": 82.51, "elapsed_time": "3:47:55", "remaining_time": "0:48:18", "throughput": 786.35, "total_tokens": 10753624} {"current_steps": 33010, "total_steps": 40000, "loss": 0.0965, "lr": 3.6747679053786147e-06, "epoch": 27.0130986492018, "percentage": 82.53, "elapsed_time": "3:47:57", "remaining_time": "0:48:16", "throughput": 786.37, "total_tokens": 10755272} {"current_steps": 33015, "total_steps": 40000, "loss": 0.1546, "lr": 3.669645850389228e-06, "epoch": 27.017191977077363, "percentage": 82.54, "elapsed_time": "3:47:58", "remaining_time": "0:48:14", "throughput": 786.4, "total_tokens": 10756968} {"current_steps": 33020, "total_steps": 40000, "loss": 0.1055, "lr": 3.664527084808514e-06, "epoch": 27.021285304952926, "percentage": 82.55, "elapsed_time": "3:48:00", "remaining_time": "0:48:11", "throughput": 786.41, "total_tokens": 10758568} {"current_steps": 33025, "total_steps": 40000, "loss": 0.1865, "lr": 3.6594116094258337e-06, "epoch": 27.025378632828488, "percentage": 82.56, "elapsed_time": "3:48:02", "remaining_time": "0:48:09", "throughput": 786.43, "total_tokens": 10760184} {"current_steps": 33030, "total_steps": 40000, "loss": 0.1342, "lr": 3.6542994250300665e-06, "epoch": 27.029471960704054, "percentage": 82.58, "elapsed_time": "3:48:03", "remaining_time": "0:48:07", "throughput": 786.45, "total_tokens": 10761800} {"current_steps": 33035, "total_steps": 40000, "loss": 0.1918, "lr": 3.6491905324095825e-06, "epoch": 27.033565288579616, "percentage": 82.59, "elapsed_time": "3:48:05", "remaining_time": "0:48:05", "throughput": 786.48, "total_tokens": 10763496} {"current_steps": 33040, "total_steps": 40000, "loss": 0.1903, "lr": 3.644084932352221e-06, "epoch": 27.03765861645518, "percentage": 82.6, "elapsed_time": "3:48:07", "remaining_time": "0:48:03", "throughput": 786.5, "total_tokens": 10765144} {"current_steps": 33045, "total_steps": 40000, "loss": 0.1442, "lr": 3.6389826256453457e-06, "epoch": 27.04175194433074, "percentage": 82.61, "elapsed_time": "3:48:09", "remaining_time": "0:48:01", "throughput": 786.52, "total_tokens": 10766808} {"current_steps": 33050, "total_steps": 40000, "loss": 0.2489, "lr": 3.633883613075781e-06, "epoch": 27.045845272206304, "percentage": 82.62, "elapsed_time": "3:48:10", "remaining_time": "0:47:59", "throughput": 786.53, "total_tokens": 10768360} {"current_steps": 33055, "total_steps": 40000, "loss": 0.2177, "lr": 3.6287878954298693e-06, "epoch": 27.049938600081866, "percentage": 82.64, "elapsed_time": "3:48:12", "remaining_time": "0:47:56", "throughput": 786.55, "total_tokens": 10770040} {"current_steps": 33060, "total_steps": 40000, "loss": 0.1554, "lr": 3.6236954734934354e-06, "epoch": 27.05403192795743, "percentage": 82.65, "elapsed_time": "3:48:14", "remaining_time": "0:47:54", "throughput": 786.57, "total_tokens": 10771688} {"current_steps": 33065, "total_steps": 40000, "loss": 0.2115, "lr": 3.618606348051784e-06, "epoch": 27.05812525583299, "percentage": 82.66, "elapsed_time": "3:48:16", "remaining_time": "0:47:52", "throughput": 786.59, "total_tokens": 10773368} {"current_steps": 33070, "total_steps": 40000, "loss": 0.2513, "lr": 3.6135205198897376e-06, "epoch": 27.062218583708557, "percentage": 82.67, "elapsed_time": "3:48:17", "remaining_time": "0:47:50", "throughput": 786.61, "total_tokens": 10774968} {"current_steps": 33075, "total_steps": 40000, "loss": 0.1761, "lr": 3.6084379897915854e-06, "epoch": 27.06631191158412, "percentage": 82.69, "elapsed_time": "3:48:19", "remaining_time": "0:47:48", "throughput": 786.64, "total_tokens": 10776664} {"current_steps": 33080, "total_steps": 40000, "loss": 0.2166, "lr": 3.6033587585411115e-06, "epoch": 27.07040523945968, "percentage": 82.7, "elapsed_time": "3:48:21", "remaining_time": "0:47:46", "throughput": 786.65, "total_tokens": 10778248} {"current_steps": 33085, "total_steps": 40000, "loss": 0.2136, "lr": 3.5982828269216117e-06, "epoch": 27.074498567335244, "percentage": 82.71, "elapsed_time": "3:48:23", "remaining_time": "0:47:44", "throughput": 786.67, "total_tokens": 10779848} {"current_steps": 33090, "total_steps": 40000, "loss": 0.144, "lr": 3.593210195715843e-06, "epoch": 27.078591895210806, "percentage": 82.73, "elapsed_time": "3:48:24", "remaining_time": "0:47:41", "throughput": 786.69, "total_tokens": 10781480} {"current_steps": 33095, "total_steps": 40000, "loss": 0.1821, "lr": 3.5881408657060773e-06, "epoch": 27.08268522308637, "percentage": 82.74, "elapsed_time": "3:48:26", "remaining_time": "0:47:39", "throughput": 786.72, "total_tokens": 10783192} {"current_steps": 33100, "total_steps": 40000, "loss": 0.1293, "lr": 3.583074837674075e-06, "epoch": 27.08677855096193, "percentage": 82.75, "elapsed_time": "3:48:28", "remaining_time": "0:47:37", "throughput": 786.73, "total_tokens": 10784792} {"current_steps": 33105, "total_steps": 40000, "loss": 0.0855, "lr": 3.578012112401069e-06, "epoch": 27.090871878837493, "percentage": 82.76, "elapsed_time": "3:48:30", "remaining_time": "0:47:35", "throughput": 786.76, "total_tokens": 10786472} {"current_steps": 33110, "total_steps": 40000, "loss": 0.2146, "lr": 3.5729526906677996e-06, "epoch": 27.09496520671306, "percentage": 82.78, "elapsed_time": "3:48:31", "remaining_time": "0:47:33", "throughput": 786.77, "total_tokens": 10788056} {"current_steps": 33115, "total_steps": 40000, "loss": 0.139, "lr": 3.5678965732545007e-06, "epoch": 27.09905853458862, "percentage": 82.79, "elapsed_time": "3:48:33", "remaining_time": "0:47:31", "throughput": 786.79, "total_tokens": 10789640} {"current_steps": 33120, "total_steps": 40000, "loss": 0.1631, "lr": 3.562843760940876e-06, "epoch": 27.103151862464184, "percentage": 82.8, "elapsed_time": "3:48:35", "remaining_time": "0:47:29", "throughput": 786.8, "total_tokens": 10791256} {"current_steps": 33125, "total_steps": 40000, "loss": 0.1527, "lr": 3.5577942545061473e-06, "epoch": 27.107245190339746, "percentage": 82.81, "elapsed_time": "3:48:37", "remaining_time": "0:47:26", "throughput": 786.82, "total_tokens": 10792904} {"current_steps": 33130, "total_steps": 40000, "loss": 0.1635, "lr": 3.5527480547289967e-06, "epoch": 27.11133851821531, "percentage": 82.83, "elapsed_time": "3:48:38", "remaining_time": "0:47:24", "throughput": 786.84, "total_tokens": 10794488} {"current_steps": 33135, "total_steps": 40000, "loss": 0.2051, "lr": 3.547705162387624e-06, "epoch": 27.11543184609087, "percentage": 82.84, "elapsed_time": "3:48:40", "remaining_time": "0:47:22", "throughput": 786.86, "total_tokens": 10796168} {"current_steps": 33140, "total_steps": 40000, "loss": 0.2587, "lr": 3.542665578259699e-06, "epoch": 27.119525173966434, "percentage": 82.85, "elapsed_time": "3:48:42", "remaining_time": "0:47:20", "throughput": 786.88, "total_tokens": 10797752} {"current_steps": 33145, "total_steps": 40000, "loss": 0.149, "lr": 3.5376293031223945e-06, "epoch": 27.123618501841996, "percentage": 82.86, "elapsed_time": "3:48:43", "remaining_time": "0:47:18", "throughput": 786.91, "total_tokens": 10799432} {"current_steps": 33150, "total_steps": 40000, "loss": 0.2149, "lr": 3.5325963377523614e-06, "epoch": 27.127711829717562, "percentage": 82.88, "elapsed_time": "3:48:45", "remaining_time": "0:47:16", "throughput": 786.93, "total_tokens": 10801064} {"current_steps": 33155, "total_steps": 40000, "loss": 0.2091, "lr": 3.5275666829257536e-06, "epoch": 27.131805157593124, "percentage": 82.89, "elapsed_time": "3:48:47", "remaining_time": "0:47:14", "throughput": 786.94, "total_tokens": 10802664} {"current_steps": 33160, "total_steps": 40000, "loss": 0.129, "lr": 3.5225403394181955e-06, "epoch": 27.135898485468687, "percentage": 82.9, "elapsed_time": "3:48:49", "remaining_time": "0:47:11", "throughput": 786.96, "total_tokens": 10804280} {"current_steps": 33165, "total_steps": 40000, "loss": 0.1372, "lr": 3.517517308004828e-06, "epoch": 27.13999181334425, "percentage": 82.91, "elapsed_time": "3:48:50", "remaining_time": "0:47:09", "throughput": 786.98, "total_tokens": 10805928} {"current_steps": 33170, "total_steps": 40000, "loss": 0.3312, "lr": 3.512497589460251e-06, "epoch": 27.14408514121981, "percentage": 82.93, "elapsed_time": "3:48:52", "remaining_time": "0:47:07", "throughput": 786.99, "total_tokens": 10807448} {"current_steps": 33175, "total_steps": 40000, "loss": 0.1291, "lr": 3.5074811845585727e-06, "epoch": 27.148178469095374, "percentage": 82.94, "elapsed_time": "3:48:54", "remaining_time": "0:47:05", "throughput": 787.01, "total_tokens": 10809176} {"current_steps": 33180, "total_steps": 40000, "loss": 0.1479, "lr": 3.5024680940733937e-06, "epoch": 27.152271796970936, "percentage": 82.95, "elapsed_time": "3:48:56", "remaining_time": "0:47:03", "throughput": 787.03, "total_tokens": 10810840} {"current_steps": 33185, "total_steps": 40000, "loss": 0.2787, "lr": 3.4974583187777852e-06, "epoch": 27.1563651248465, "percentage": 82.96, "elapsed_time": "3:48:57", "remaining_time": "0:47:01", "throughput": 787.05, "total_tokens": 10812424} {"current_steps": 33190, "total_steps": 40000, "loss": 0.1758, "lr": 3.4924518594443204e-06, "epoch": 27.160458452722064, "percentage": 82.97, "elapsed_time": "3:48:59", "remaining_time": "0:46:59", "throughput": 787.07, "total_tokens": 10814008} {"current_steps": 33195, "total_steps": 40000, "loss": 0.215, "lr": 3.4874487168450682e-06, "epoch": 27.164551780597627, "percentage": 82.99, "elapsed_time": "3:49:01", "remaining_time": "0:46:56", "throughput": 787.09, "total_tokens": 10815640} {"current_steps": 33200, "total_steps": 40000, "loss": 0.139, "lr": 3.482448891751558e-06, "epoch": 27.16864510847319, "percentage": 83.0, "elapsed_time": "3:49:03", "remaining_time": "0:46:54", "throughput": 787.11, "total_tokens": 10817272} {"current_steps": 33200, "total_steps": 40000, "eval_loss": 0.21212419867515564, "epoch": 27.16864510847319, "percentage": 83.0, "elapsed_time": "3:49:15", "remaining_time": "0:46:57", "throughput": 786.4, "total_tokens": 10817272} {"current_steps": 33205, "total_steps": 40000, "loss": 0.2133, "lr": 3.477452384934843e-06, "epoch": 27.17273843634875, "percentage": 83.01, "elapsed_time": "3:49:19", "remaining_time": "0:46:55", "throughput": 786.31, "total_tokens": 10818888} {"current_steps": 33210, "total_steps": 40000, "loss": 0.1456, "lr": 3.472459197165434e-06, "epoch": 27.176831764224314, "percentage": 83.03, "elapsed_time": "3:49:20", "remaining_time": "0:46:53", "throughput": 786.33, "total_tokens": 10820536} {"current_steps": 33215, "total_steps": 40000, "loss": 0.1437, "lr": 3.4674693292133518e-06, "epoch": 27.180925092099876, "percentage": 83.04, "elapsed_time": "3:49:22", "remaining_time": "0:46:51", "throughput": 786.35, "total_tokens": 10822168} {"current_steps": 33220, "total_steps": 40000, "loss": 0.1257, "lr": 3.4624827818480977e-06, "epoch": 27.18501841997544, "percentage": 83.05, "elapsed_time": "3:49:24", "remaining_time": "0:46:49", "throughput": 786.37, "total_tokens": 10823800} {"current_steps": 33225, "total_steps": 40000, "loss": 0.1679, "lr": 3.4574995558386474e-06, "epoch": 27.189111747851, "percentage": 83.06, "elapsed_time": "3:49:26", "remaining_time": "0:46:47", "throughput": 786.38, "total_tokens": 10825368} {"current_steps": 33230, "total_steps": 40000, "loss": 0.1848, "lr": 3.452519651953487e-06, "epoch": 27.193205075726567, "percentage": 83.08, "elapsed_time": "3:49:27", "remaining_time": "0:46:44", "throughput": 786.4, "total_tokens": 10827016} {"current_steps": 33235, "total_steps": 40000, "loss": 0.1684, "lr": 3.447543070960585e-06, "epoch": 27.19729840360213, "percentage": 83.09, "elapsed_time": "3:49:29", "remaining_time": "0:46:42", "throughput": 786.42, "total_tokens": 10828632} {"current_steps": 33240, "total_steps": 40000, "loss": 0.1681, "lr": 3.4425698136273778e-06, "epoch": 27.201391731477692, "percentage": 83.1, "elapsed_time": "3:49:31", "remaining_time": "0:46:40", "throughput": 786.44, "total_tokens": 10830248} {"current_steps": 33245, "total_steps": 40000, "loss": 0.1485, "lr": 3.437599880720821e-06, "epoch": 27.205485059353254, "percentage": 83.11, "elapsed_time": "3:49:33", "remaining_time": "0:46:38", "throughput": 786.45, "total_tokens": 10831832} {"current_steps": 33250, "total_steps": 40000, "loss": 0.1084, "lr": 3.4326332730073267e-06, "epoch": 27.209578387228817, "percentage": 83.12, "elapsed_time": "3:49:34", "remaining_time": "0:46:36", "throughput": 786.47, "total_tokens": 10833464} {"current_steps": 33255, "total_steps": 40000, "loss": 0.1327, "lr": 3.427669991252813e-06, "epoch": 27.21367171510438, "percentage": 83.14, "elapsed_time": "3:49:36", "remaining_time": "0:46:34", "throughput": 786.5, "total_tokens": 10835128} {"current_steps": 33260, "total_steps": 40000, "loss": 0.1271, "lr": 3.42271003622269e-06, "epoch": 27.21776504297994, "percentage": 83.15, "elapsed_time": "3:49:38", "remaining_time": "0:46:32", "throughput": 786.52, "total_tokens": 10836760} {"current_steps": 33265, "total_steps": 40000, "loss": 0.188, "lr": 3.4177534086818286e-06, "epoch": 27.221858370855507, "percentage": 83.16, "elapsed_time": "3:49:39", "remaining_time": "0:46:29", "throughput": 786.54, "total_tokens": 10838376} {"current_steps": 33270, "total_steps": 40000, "loss": 0.2008, "lr": 3.412800109394612e-06, "epoch": 27.22595169873107, "percentage": 83.17, "elapsed_time": "3:49:41", "remaining_time": "0:46:27", "throughput": 786.56, "total_tokens": 10840088} {"current_steps": 33275, "total_steps": 40000, "loss": 0.1782, "lr": 3.4078501391249044e-06, "epoch": 27.230045026606632, "percentage": 83.19, "elapsed_time": "3:49:43", "remaining_time": "0:46:25", "throughput": 786.58, "total_tokens": 10841736} {"current_steps": 33280, "total_steps": 40000, "loss": 0.1102, "lr": 3.4029034986360453e-06, "epoch": 27.234138354482194, "percentage": 83.2, "elapsed_time": "3:49:45", "remaining_time": "0:46:23", "throughput": 786.6, "total_tokens": 10843384} {"current_steps": 33285, "total_steps": 40000, "loss": 0.1567, "lr": 3.397960188690877e-06, "epoch": 27.238231682357757, "percentage": 83.21, "elapsed_time": "3:49:46", "remaining_time": "0:46:21", "throughput": 786.61, "total_tokens": 10844936} {"current_steps": 33290, "total_steps": 40000, "loss": 0.2247, "lr": 3.393020210051717e-06, "epoch": 27.24232501023332, "percentage": 83.23, "elapsed_time": "3:49:48", "remaining_time": "0:46:19", "throughput": 786.63, "total_tokens": 10846520} {"current_steps": 33295, "total_steps": 40000, "loss": 0.1345, "lr": 3.3880835634803655e-06, "epoch": 27.24641833810888, "percentage": 83.24, "elapsed_time": "3:49:50", "remaining_time": "0:46:17", "throughput": 786.65, "total_tokens": 10848152} {"current_steps": 33300, "total_steps": 40000, "loss": 0.1703, "lr": 3.383150249738126e-06, "epoch": 27.250511665984444, "percentage": 83.25, "elapsed_time": "3:49:52", "remaining_time": "0:46:14", "throughput": 786.66, "total_tokens": 10849768} {"current_steps": 33305, "total_steps": 40000, "loss": 0.217, "lr": 3.3782202695857663e-06, "epoch": 27.25460499386001, "percentage": 83.26, "elapsed_time": "3:49:53", "remaining_time": "0:46:12", "throughput": 786.69, "total_tokens": 10851464} {"current_steps": 33310, "total_steps": 40000, "loss": 0.1432, "lr": 3.373293623783558e-06, "epoch": 27.258698321735572, "percentage": 83.28, "elapsed_time": "3:49:55", "remaining_time": "0:46:10", "throughput": 786.71, "total_tokens": 10853096} {"current_steps": 33315, "total_steps": 40000, "loss": 0.1224, "lr": 3.368370313091257e-06, "epoch": 27.262791649611135, "percentage": 83.29, "elapsed_time": "3:49:57", "remaining_time": "0:46:08", "throughput": 786.73, "total_tokens": 10854760} {"current_steps": 33320, "total_steps": 40000, "loss": 0.1255, "lr": 3.363450338268087e-06, "epoch": 27.266884977486697, "percentage": 83.3, "elapsed_time": "3:49:59", "remaining_time": "0:46:06", "throughput": 786.75, "total_tokens": 10856392} {"current_steps": 33325, "total_steps": 40000, "loss": 0.2006, "lr": 3.358533700072783e-06, "epoch": 27.27097830536226, "percentage": 83.31, "elapsed_time": "3:50:00", "remaining_time": "0:46:04", "throughput": 786.77, "total_tokens": 10857960} {"current_steps": 33330, "total_steps": 40000, "loss": 0.1535, "lr": 3.3536203992635377e-06, "epoch": 27.275071633237822, "percentage": 83.33, "elapsed_time": "3:50:02", "remaining_time": "0:46:02", "throughput": 786.78, "total_tokens": 10859576} {"current_steps": 33335, "total_steps": 40000, "loss": 0.1233, "lr": 3.348710436598057e-06, "epoch": 27.279164961113384, "percentage": 83.34, "elapsed_time": "3:50:04", "remaining_time": "0:46:00", "throughput": 786.81, "total_tokens": 10861272} {"current_steps": 33340, "total_steps": 40000, "loss": 0.1463, "lr": 3.3438038128335155e-06, "epoch": 27.283258288988947, "percentage": 83.35, "elapsed_time": "3:50:05", "remaining_time": "0:45:57", "throughput": 786.83, "total_tokens": 10862904} {"current_steps": 33345, "total_steps": 40000, "loss": 0.1946, "lr": 3.338900528726571e-06, "epoch": 27.287351616864512, "percentage": 83.36, "elapsed_time": "3:50:07", "remaining_time": "0:45:55", "throughput": 786.85, "total_tokens": 10864536} {"current_steps": 33350, "total_steps": 40000, "loss": 0.2109, "lr": 3.3340005850333812e-06, "epoch": 27.291444944740075, "percentage": 83.38, "elapsed_time": "3:50:09", "remaining_time": "0:45:53", "throughput": 786.86, "total_tokens": 10866152} {"current_steps": 33355, "total_steps": 40000, "loss": 0.1517, "lr": 3.329103982509568e-06, "epoch": 27.295538272615637, "percentage": 83.39, "elapsed_time": "3:50:11", "remaining_time": "0:45:51", "throughput": 786.88, "total_tokens": 10867752} {"current_steps": 33360, "total_steps": 40000, "loss": 0.1543, "lr": 3.324210721910259e-06, "epoch": 27.2996316004912, "percentage": 83.4, "elapsed_time": "3:50:12", "remaining_time": "0:45:49", "throughput": 786.9, "total_tokens": 10869384} {"current_steps": 33365, "total_steps": 40000, "loss": 0.1285, "lr": 3.319320803990053e-06, "epoch": 27.303724928366762, "percentage": 83.41, "elapsed_time": "3:50:14", "remaining_time": "0:45:47", "throughput": 786.91, "total_tokens": 10871000} {"current_steps": 33370, "total_steps": 40000, "loss": 0.1844, "lr": 3.3144342295030274e-06, "epoch": 27.307818256242324, "percentage": 83.43, "elapsed_time": "3:50:16", "remaining_time": "0:45:45", "throughput": 786.93, "total_tokens": 10872664} {"current_steps": 33375, "total_steps": 40000, "loss": 0.1762, "lr": 3.309550999202765e-06, "epoch": 27.311911584117887, "percentage": 83.44, "elapsed_time": "3:50:18", "remaining_time": "0:45:42", "throughput": 786.95, "total_tokens": 10874280} {"current_steps": 33380, "total_steps": 40000, "loss": 0.1718, "lr": 3.3046711138423197e-06, "epoch": 27.31600491199345, "percentage": 83.45, "elapsed_time": "3:50:19", "remaining_time": "0:45:40", "throughput": 786.97, "total_tokens": 10875912} {"current_steps": 33385, "total_steps": 40000, "loss": 0.2012, "lr": 3.2997945741742255e-06, "epoch": 27.320098239869015, "percentage": 83.46, "elapsed_time": "3:50:21", "remaining_time": "0:45:38", "throughput": 786.99, "total_tokens": 10877544} {"current_steps": 33390, "total_steps": 40000, "loss": 0.1466, "lr": 3.2949213809505082e-06, "epoch": 27.324191567744577, "percentage": 83.47, "elapsed_time": "3:50:23", "remaining_time": "0:45:36", "throughput": 787.02, "total_tokens": 10879288} {"current_steps": 33395, "total_steps": 40000, "loss": 0.1206, "lr": 3.2900515349226834e-06, "epoch": 27.32828489562014, "percentage": 83.49, "elapsed_time": "3:50:25", "remaining_time": "0:45:34", "throughput": 787.04, "total_tokens": 10880904} {"current_steps": 33400, "total_steps": 40000, "loss": 0.168, "lr": 3.285185036841731e-06, "epoch": 27.332378223495702, "percentage": 83.5, "elapsed_time": "3:50:26", "remaining_time": "0:45:32", "throughput": 787.07, "total_tokens": 10882568} {"current_steps": 33400, "total_steps": 40000, "eval_loss": 0.21927355229854584, "epoch": 27.332378223495702, "percentage": 83.5, "elapsed_time": "3:50:39", "remaining_time": "0:45:34", "throughput": 786.36, "total_tokens": 10882568} {"current_steps": 33405, "total_steps": 40000, "loss": 0.2303, "lr": 3.2803218874581377e-06, "epoch": 27.336471551371265, "percentage": 83.51, "elapsed_time": "3:50:42", "remaining_time": "0:45:32", "throughput": 786.29, "total_tokens": 10884216} {"current_steps": 33410, "total_steps": 40000, "loss": 0.1254, "lr": 3.2754620875218494e-06, "epoch": 27.340564879246827, "percentage": 83.53, "elapsed_time": "3:50:44", "remaining_time": "0:45:30", "throughput": 786.31, "total_tokens": 10885832} {"current_steps": 33415, "total_steps": 40000, "loss": 0.1174, "lr": 3.2706056377823146e-06, "epoch": 27.34465820712239, "percentage": 83.54, "elapsed_time": "3:50:46", "remaining_time": "0:45:28", "throughput": 786.33, "total_tokens": 10887480} {"current_steps": 33420, "total_steps": 40000, "loss": 0.213, "lr": 3.2657525389884647e-06, "epoch": 27.34875153499795, "percentage": 83.55, "elapsed_time": "3:50:47", "remaining_time": "0:45:26", "throughput": 786.34, "total_tokens": 10889128} {"current_steps": 33425, "total_steps": 40000, "loss": 0.22, "lr": 3.260902791888698e-06, "epoch": 27.352844862873518, "percentage": 83.56, "elapsed_time": "3:50:49", "remaining_time": "0:45:24", "throughput": 786.37, "total_tokens": 10890792} {"current_steps": 33430, "total_steps": 40000, "loss": 0.1557, "lr": 3.2560563972309166e-06, "epoch": 27.35693819074908, "percentage": 83.58, "elapsed_time": "3:50:51", "remaining_time": "0:45:22", "throughput": 786.38, "total_tokens": 10892392} {"current_steps": 33435, "total_steps": 40000, "loss": 0.1551, "lr": 3.251213355762489e-06, "epoch": 27.361031518624642, "percentage": 83.59, "elapsed_time": "3:50:53", "remaining_time": "0:45:20", "throughput": 786.4, "total_tokens": 10894024} {"current_steps": 33440, "total_steps": 40000, "loss": 0.2914, "lr": 3.2463736682302707e-06, "epoch": 27.365124846500205, "percentage": 83.6, "elapsed_time": "3:50:54", "remaining_time": "0:45:17", "throughput": 786.42, "total_tokens": 10895672} {"current_steps": 33445, "total_steps": 40000, "loss": 0.1952, "lr": 3.2415373353806124e-06, "epoch": 27.369218174375767, "percentage": 83.61, "elapsed_time": "3:50:56", "remaining_time": "0:45:15", "throughput": 786.44, "total_tokens": 10897304} {"current_steps": 33450, "total_steps": 40000, "loss": 0.129, "lr": 3.236704357959322e-06, "epoch": 27.37331150225133, "percentage": 83.62, "elapsed_time": "3:50:58", "remaining_time": "0:45:13", "throughput": 786.46, "total_tokens": 10898920} {"current_steps": 33455, "total_steps": 40000, "loss": 0.1155, "lr": 3.2318747367117154e-06, "epoch": 27.377404830126892, "percentage": 83.64, "elapsed_time": "3:51:00", "remaining_time": "0:45:11", "throughput": 786.47, "total_tokens": 10900504} {"current_steps": 33460, "total_steps": 40000, "loss": 0.1069, "lr": 3.227048472382585e-06, "epoch": 27.381498158002454, "percentage": 83.65, "elapsed_time": "3:51:01", "remaining_time": "0:45:09", "throughput": 786.49, "total_tokens": 10902120} {"current_steps": 33465, "total_steps": 40000, "loss": 0.2274, "lr": 3.2222255657161915e-06, "epoch": 27.38559148587802, "percentage": 83.66, "elapsed_time": "3:51:03", "remaining_time": "0:45:07", "throughput": 786.51, "total_tokens": 10903720} {"current_steps": 33470, "total_steps": 40000, "loss": 0.2295, "lr": 3.2174060174562924e-06, "epoch": 27.389684813753583, "percentage": 83.67, "elapsed_time": "3:51:05", "remaining_time": "0:45:05", "throughput": 786.52, "total_tokens": 10905272} {"current_steps": 33475, "total_steps": 40000, "loss": 0.1644, "lr": 3.2125898283461298e-06, "epoch": 27.393778141629145, "percentage": 83.69, "elapsed_time": "3:51:06", "remaining_time": "0:45:02", "throughput": 786.54, "total_tokens": 10906840} {"current_steps": 33480, "total_steps": 40000, "loss": 0.186, "lr": 3.207776999128406e-06, "epoch": 27.397871469504707, "percentage": 83.7, "elapsed_time": "3:51:08", "remaining_time": "0:45:00", "throughput": 786.56, "total_tokens": 10908472} {"current_steps": 33485, "total_steps": 40000, "loss": 0.1675, "lr": 3.202967530545331e-06, "epoch": 27.40196479738027, "percentage": 83.71, "elapsed_time": "3:51:10", "remaining_time": "0:44:58", "throughput": 786.58, "total_tokens": 10910088} {"current_steps": 33490, "total_steps": 40000, "loss": 0.2537, "lr": 3.1981614233385778e-06, "epoch": 27.406058125255832, "percentage": 83.73, "elapsed_time": "3:51:12", "remaining_time": "0:44:56", "throughput": 786.6, "total_tokens": 10911736} {"current_steps": 33495, "total_steps": 40000, "loss": 0.2157, "lr": 3.1933586782493115e-06, "epoch": 27.410151453131395, "percentage": 83.74, "elapsed_time": "3:51:13", "remaining_time": "0:44:54", "throughput": 786.61, "total_tokens": 10913320} {"current_steps": 33500, "total_steps": 40000, "loss": 0.1245, "lr": 3.188559296018184e-06, "epoch": 27.414244781006957, "percentage": 83.75, "elapsed_time": "3:51:15", "remaining_time": "0:44:52", "throughput": 786.63, "total_tokens": 10914920} {"current_steps": 33505, "total_steps": 40000, "loss": 0.147, "lr": 3.1837632773853098e-06, "epoch": 27.418338108882523, "percentage": 83.76, "elapsed_time": "3:51:17", "remaining_time": "0:44:50", "throughput": 786.64, "total_tokens": 10916568} {"current_steps": 33510, "total_steps": 40000, "loss": 0.225, "lr": 3.178970623090294e-06, "epoch": 27.422431436758085, "percentage": 83.78, "elapsed_time": "3:51:19", "remaining_time": "0:44:48", "throughput": 786.66, "total_tokens": 10918152} {"current_steps": 33515, "total_steps": 40000, "loss": 0.2047, "lr": 3.174181333872234e-06, "epoch": 27.426524764633648, "percentage": 83.79, "elapsed_time": "3:51:20", "remaining_time": "0:44:45", "throughput": 786.67, "total_tokens": 10919720} {"current_steps": 33520, "total_steps": 40000, "loss": 0.1285, "lr": 3.169395410469686e-06, "epoch": 27.43061809250921, "percentage": 83.8, "elapsed_time": "3:51:22", "remaining_time": "0:44:43", "throughput": 786.69, "total_tokens": 10921336} {"current_steps": 33525, "total_steps": 40000, "loss": 0.1731, "lr": 3.164612853620713e-06, "epoch": 27.434711420384772, "percentage": 83.81, "elapsed_time": "3:51:24", "remaining_time": "0:44:41", "throughput": 786.71, "total_tokens": 10922936} {"current_steps": 33530, "total_steps": 40000, "loss": 0.2179, "lr": 3.1598336640628333e-06, "epoch": 27.438804748260335, "percentage": 83.83, "elapsed_time": "3:51:26", "remaining_time": "0:44:39", "throughput": 786.73, "total_tokens": 10924584} {"current_steps": 33535, "total_steps": 40000, "loss": 0.1657, "lr": 3.155057842533063e-06, "epoch": 27.442898076135897, "percentage": 83.84, "elapsed_time": "3:51:27", "remaining_time": "0:44:37", "throughput": 786.75, "total_tokens": 10926264} {"current_steps": 33540, "total_steps": 40000, "loss": 0.1256, "lr": 3.1502853897678984e-06, "epoch": 27.446991404011463, "percentage": 83.85, "elapsed_time": "3:51:29", "remaining_time": "0:44:35", "throughput": 786.77, "total_tokens": 10927928} {"current_steps": 33545, "total_steps": 40000, "loss": 0.1748, "lr": 3.1455163065033017e-06, "epoch": 27.451084731887025, "percentage": 83.86, "elapsed_time": "3:51:31", "remaining_time": "0:44:33", "throughput": 786.79, "total_tokens": 10929528} {"current_steps": 33550, "total_steps": 40000, "loss": 0.1684, "lr": 3.140750593474734e-06, "epoch": 27.455178059762588, "percentage": 83.88, "elapsed_time": "3:51:33", "remaining_time": "0:44:30", "throughput": 786.81, "total_tokens": 10931224} {"current_steps": 33555, "total_steps": 40000, "loss": 0.2133, "lr": 3.1359882514171294e-06, "epoch": 27.45927138763815, "percentage": 83.89, "elapsed_time": "3:51:34", "remaining_time": "0:44:28", "throughput": 786.83, "total_tokens": 10932840} {"current_steps": 33560, "total_steps": 40000, "loss": 0.1366, "lr": 3.1312292810648903e-06, "epoch": 27.463364715513713, "percentage": 83.9, "elapsed_time": "3:51:36", "remaining_time": "0:44:26", "throughput": 786.85, "total_tokens": 10934456} {"current_steps": 33565, "total_steps": 40000, "loss": 0.1685, "lr": 3.1264736831519204e-06, "epoch": 27.467458043389275, "percentage": 83.91, "elapsed_time": "3:51:38", "remaining_time": "0:44:24", "throughput": 786.87, "total_tokens": 10936072} {"current_steps": 33570, "total_steps": 40000, "loss": 0.1651, "lr": 3.1217214584115863e-06, "epoch": 27.471551371264837, "percentage": 83.93, "elapsed_time": "3:51:39", "remaining_time": "0:44:22", "throughput": 786.89, "total_tokens": 10937688} {"current_steps": 33575, "total_steps": 40000, "loss": 0.1353, "lr": 3.116972607576746e-06, "epoch": 27.4756446991404, "percentage": 83.94, "elapsed_time": "3:51:41", "remaining_time": "0:44:20", "throughput": 786.91, "total_tokens": 10939320} {"current_steps": 33580, "total_steps": 40000, "loss": 0.1933, "lr": 3.1122271313797303e-06, "epoch": 27.479738027015966, "percentage": 83.95, "elapsed_time": "3:51:43", "remaining_time": "0:44:18", "throughput": 786.92, "total_tokens": 10940904} {"current_steps": 33585, "total_steps": 40000, "loss": 0.2216, "lr": 3.107485030552343e-06, "epoch": 27.483831354891528, "percentage": 83.96, "elapsed_time": "3:51:45", "remaining_time": "0:44:16", "throughput": 786.94, "total_tokens": 10942536} {"current_steps": 33590, "total_steps": 40000, "loss": 0.1503, "lr": 3.1027463058258848e-06, "epoch": 27.48792468276709, "percentage": 83.97, "elapsed_time": "3:51:46", "remaining_time": "0:44:13", "throughput": 786.96, "total_tokens": 10944216} {"current_steps": 33595, "total_steps": 40000, "loss": 0.1562, "lr": 3.0980109579311273e-06, "epoch": 27.492018010642653, "percentage": 83.99, "elapsed_time": "3:51:48", "remaining_time": "0:44:11", "throughput": 786.97, "total_tokens": 10945800} {"current_steps": 33600, "total_steps": 40000, "loss": 0.2141, "lr": 3.093278987598314e-06, "epoch": 27.496111338518215, "percentage": 84.0, "elapsed_time": "3:51:50", "remaining_time": "0:44:09", "throughput": 786.99, "total_tokens": 10947368} {"current_steps": 33600, "total_steps": 40000, "eval_loss": 0.21614989638328552, "epoch": 27.496111338518215, "percentage": 84.0, "elapsed_time": "3:52:02", "remaining_time": "0:44:11", "throughput": 786.28, "total_tokens": 10947368} {"current_steps": 33605, "total_steps": 40000, "loss": 0.2306, "lr": 3.0885503955571826e-06, "epoch": 27.500204666393778, "percentage": 84.01, "elapsed_time": "3:52:06", "remaining_time": "0:44:10", "throughput": 786.21, "total_tokens": 10948984} {"current_steps": 33610, "total_steps": 40000, "loss": 0.2657, "lr": 3.0838251825369313e-06, "epoch": 27.50429799426934, "percentage": 84.03, "elapsed_time": "3:52:07", "remaining_time": "0:44:08", "throughput": 786.23, "total_tokens": 10950552} {"current_steps": 33615, "total_steps": 40000, "loss": 0.1457, "lr": 3.0791033492662517e-06, "epoch": 27.508391322144902, "percentage": 84.04, "elapsed_time": "3:52:09", "remaining_time": "0:44:05", "throughput": 786.25, "total_tokens": 10952232} {"current_steps": 33620, "total_steps": 40000, "loss": 0.2488, "lr": 3.0743848964733203e-06, "epoch": 27.51248465002047, "percentage": 84.05, "elapsed_time": "3:52:11", "remaining_time": "0:44:03", "throughput": 786.27, "total_tokens": 10953864} {"current_steps": 33625, "total_steps": 40000, "loss": 0.1379, "lr": 3.0696698248857625e-06, "epoch": 27.51657797789603, "percentage": 84.06, "elapsed_time": "3:52:13", "remaining_time": "0:44:01", "throughput": 786.29, "total_tokens": 10955544} {"current_steps": 33630, "total_steps": 40000, "loss": 0.2125, "lr": 3.0649581352307192e-06, "epoch": 27.520671305771593, "percentage": 84.08, "elapsed_time": "3:52:14", "remaining_time": "0:43:59", "throughput": 786.31, "total_tokens": 10957128} {"current_steps": 33635, "total_steps": 40000, "loss": 0.1986, "lr": 3.060249828234776e-06, "epoch": 27.524764633647155, "percentage": 84.09, "elapsed_time": "3:52:16", "remaining_time": "0:43:57", "throughput": 786.33, "total_tokens": 10958808} {"current_steps": 33640, "total_steps": 40000, "loss": 0.2085, "lr": 3.055544904624025e-06, "epoch": 27.528857961522718, "percentage": 84.1, "elapsed_time": "3:52:18", "remaining_time": "0:43:55", "throughput": 786.35, "total_tokens": 10960440} {"current_steps": 33645, "total_steps": 40000, "loss": 0.149, "lr": 3.050843365124026e-06, "epoch": 27.53295128939828, "percentage": 84.11, "elapsed_time": "3:52:20", "remaining_time": "0:43:53", "throughput": 786.37, "total_tokens": 10962056} {"current_steps": 33650, "total_steps": 40000, "loss": 0.2175, "lr": 3.0461452104598083e-06, "epoch": 27.537044617273843, "percentage": 84.12, "elapsed_time": "3:52:21", "remaining_time": "0:43:50", "throughput": 786.39, "total_tokens": 10963608} {"current_steps": 33655, "total_steps": 40000, "loss": 0.0987, "lr": 3.0414504413558836e-06, "epoch": 27.541137945149405, "percentage": 84.14, "elapsed_time": "3:52:23", "remaining_time": "0:43:48", "throughput": 786.4, "total_tokens": 10965224} {"current_steps": 33660, "total_steps": 40000, "loss": 0.2093, "lr": 3.0367590585362564e-06, "epoch": 27.54523127302497, "percentage": 84.15, "elapsed_time": "3:52:25", "remaining_time": "0:43:46", "throughput": 786.42, "total_tokens": 10966856} {"current_steps": 33665, "total_steps": 40000, "loss": 0.166, "lr": 3.0320710627243813e-06, "epoch": 27.549324600900533, "percentage": 84.16, "elapsed_time": "3:52:27", "remaining_time": "0:43:44", "throughput": 786.44, "total_tokens": 10968440} {"current_steps": 33670, "total_steps": 40000, "loss": 0.1997, "lr": 3.027386454643222e-06, "epoch": 27.553417928776096, "percentage": 84.17, "elapsed_time": "3:52:28", "remaining_time": "0:43:42", "throughput": 786.45, "total_tokens": 10970024} {"current_steps": 33675, "total_steps": 40000, "loss": 0.2133, "lr": 3.0227052350151914e-06, "epoch": 27.557511256651658, "percentage": 84.19, "elapsed_time": "3:52:30", "remaining_time": "0:43:40", "throughput": 786.47, "total_tokens": 10971736} {"current_steps": 33680, "total_steps": 40000, "loss": 0.2121, "lr": 3.0180274045621957e-06, "epoch": 27.56160458452722, "percentage": 84.2, "elapsed_time": "3:52:32", "remaining_time": "0:43:38", "throughput": 786.49, "total_tokens": 10973320} {"current_steps": 33685, "total_steps": 40000, "loss": 0.2115, "lr": 3.013352964005625e-06, "epoch": 27.565697912402783, "percentage": 84.21, "elapsed_time": "3:52:34", "remaining_time": "0:43:35", "throughput": 786.51, "total_tokens": 10974984} {"current_steps": 33690, "total_steps": 40000, "loss": 0.1186, "lr": 3.0086819140663218e-06, "epoch": 27.569791240278345, "percentage": 84.23, "elapsed_time": "3:52:35", "remaining_time": "0:43:33", "throughput": 786.53, "total_tokens": 10976600} {"current_steps": 33695, "total_steps": 40000, "loss": 0.287, "lr": 3.0040142554646265e-06, "epoch": 27.573884568153908, "percentage": 84.24, "elapsed_time": "3:52:37", "remaining_time": "0:43:31", "throughput": 786.55, "total_tokens": 10978248} {"current_steps": 33700, "total_steps": 40000, "loss": 0.1686, "lr": 2.999349988920361e-06, "epoch": 27.577977896029473, "percentage": 84.25, "elapsed_time": "3:52:39", "remaining_time": "0:43:29", "throughput": 786.57, "total_tokens": 10979928} {"current_steps": 33705, "total_steps": 40000, "loss": 0.212, "lr": 2.994689115152796e-06, "epoch": 27.582071223905036, "percentage": 84.26, "elapsed_time": "3:52:41", "remaining_time": "0:43:27", "throughput": 786.59, "total_tokens": 10981560} {"current_steps": 33710, "total_steps": 40000, "loss": 0.1944, "lr": 2.9900316348807105e-06, "epoch": 27.5861645517806, "percentage": 84.28, "elapsed_time": "3:52:42", "remaining_time": "0:43:25", "throughput": 786.61, "total_tokens": 10983224} {"current_steps": 33715, "total_steps": 40000, "loss": 0.1803, "lr": 2.985377548822338e-06, "epoch": 27.59025787965616, "percentage": 84.29, "elapsed_time": "3:52:44", "remaining_time": "0:43:23", "throughput": 786.63, "total_tokens": 10984792} {"current_steps": 33720, "total_steps": 40000, "loss": 0.173, "lr": 2.980726857695404e-06, "epoch": 27.594351207531723, "percentage": 84.3, "elapsed_time": "3:52:46", "remaining_time": "0:43:21", "throughput": 786.64, "total_tokens": 10986344} {"current_steps": 33725, "total_steps": 40000, "loss": 0.2662, "lr": 2.9760795622171017e-06, "epoch": 27.598444535407285, "percentage": 84.31, "elapsed_time": "3:52:47", "remaining_time": "0:43:18", "throughput": 786.66, "total_tokens": 10987928} {"current_steps": 33730, "total_steps": 40000, "loss": 0.1166, "lr": 2.971435663104094e-06, "epoch": 27.602537863282848, "percentage": 84.33, "elapsed_time": "3:52:49", "remaining_time": "0:43:16", "throughput": 786.68, "total_tokens": 10989592} {"current_steps": 33735, "total_steps": 40000, "loss": 0.1594, "lr": 2.9667951610725385e-06, "epoch": 27.60663119115841, "percentage": 84.34, "elapsed_time": "3:52:51", "remaining_time": "0:43:14", "throughput": 786.7, "total_tokens": 10991240} {"current_steps": 33740, "total_steps": 40000, "loss": 0.1283, "lr": 2.9621580568380575e-06, "epoch": 27.610724519033976, "percentage": 84.35, "elapsed_time": "3:52:53", "remaining_time": "0:43:12", "throughput": 786.72, "total_tokens": 10992888} {"current_steps": 33745, "total_steps": 40000, "loss": 0.1174, "lr": 2.9575243511157453e-06, "epoch": 27.61481784690954, "percentage": 84.36, "elapsed_time": "3:52:54", "remaining_time": "0:43:10", "throughput": 786.74, "total_tokens": 10994520} {"current_steps": 33750, "total_steps": 40000, "loss": 0.1283, "lr": 2.952894044620186e-06, "epoch": 27.6189111747851, "percentage": 84.38, "elapsed_time": "3:52:56", "remaining_time": "0:43:08", "throughput": 786.76, "total_tokens": 10996136} {"current_steps": 33755, "total_steps": 40000, "loss": 0.1494, "lr": 2.948267138065419e-06, "epoch": 27.623004502660663, "percentage": 84.39, "elapsed_time": "3:52:58", "remaining_time": "0:43:06", "throughput": 786.77, "total_tokens": 10997752} {"current_steps": 33760, "total_steps": 40000, "loss": 0.179, "lr": 2.943643632164983e-06, "epoch": 27.627097830536226, "percentage": 84.4, "elapsed_time": "3:53:00", "remaining_time": "0:43:03", "throughput": 786.79, "total_tokens": 10999352} {"current_steps": 33765, "total_steps": 40000, "loss": 0.1311, "lr": 2.939023527631879e-06, "epoch": 27.631191158411788, "percentage": 84.41, "elapsed_time": "3:53:01", "remaining_time": "0:43:01", "throughput": 786.81, "total_tokens": 11001016} {"current_steps": 33770, "total_steps": 40000, "loss": 0.0879, "lr": 2.934406825178576e-06, "epoch": 27.63528448628735, "percentage": 84.42, "elapsed_time": "3:53:03", "remaining_time": "0:42:59", "throughput": 786.83, "total_tokens": 11002664} {"current_steps": 33775, "total_steps": 40000, "loss": 0.1267, "lr": 2.9297935255170357e-06, "epoch": 27.639377814162913, "percentage": 84.44, "elapsed_time": "3:53:05", "remaining_time": "0:42:57", "throughput": 786.85, "total_tokens": 11004280} {"current_steps": 33780, "total_steps": 40000, "loss": 0.2097, "lr": 2.925183629358691e-06, "epoch": 27.64347114203848, "percentage": 84.45, "elapsed_time": "3:53:07", "remaining_time": "0:42:55", "throughput": 786.87, "total_tokens": 11006008} {"current_steps": 33785, "total_steps": 40000, "loss": 0.1215, "lr": 2.9205771374144346e-06, "epoch": 27.64756446991404, "percentage": 84.46, "elapsed_time": "3:53:08", "remaining_time": "0:42:53", "throughput": 786.89, "total_tokens": 11007624} {"current_steps": 33790, "total_steps": 40000, "loss": 0.1316, "lr": 2.915974050394657e-06, "epoch": 27.651657797789603, "percentage": 84.47, "elapsed_time": "3:53:10", "remaining_time": "0:42:51", "throughput": 786.91, "total_tokens": 11009336} {"current_steps": 33795, "total_steps": 40000, "loss": 0.1487, "lr": 2.9113743690092067e-06, "epoch": 27.655751125665166, "percentage": 84.49, "elapsed_time": "3:53:12", "remaining_time": "0:42:49", "throughput": 786.93, "total_tokens": 11010920} {"current_steps": 33800, "total_steps": 40000, "loss": 0.2343, "lr": 2.906778093967402e-06, "epoch": 27.659844453540728, "percentage": 84.5, "elapsed_time": "3:53:14", "remaining_time": "0:42:46", "throughput": 786.94, "total_tokens": 11012568} {"current_steps": 33800, "total_steps": 40000, "eval_loss": 0.2125473916530609, "epoch": 27.659844453540728, "percentage": 84.5, "elapsed_time": "3:53:26", "remaining_time": "0:42:49", "throughput": 786.25, "total_tokens": 11012568} {"current_steps": 33805, "total_steps": 40000, "loss": 0.1588, "lr": 2.9021852259780656e-06, "epoch": 27.66393778141629, "percentage": 84.51, "elapsed_time": "3:53:29", "remaining_time": "0:42:47", "throughput": 786.19, "total_tokens": 11014360} {"current_steps": 33810, "total_steps": 40000, "loss": 0.2662, "lr": 2.8975957657494583e-06, "epoch": 27.668031109291853, "percentage": 84.52, "elapsed_time": "3:53:31", "remaining_time": "0:42:45", "throughput": 786.21, "total_tokens": 11015992} {"current_steps": 33815, "total_steps": 40000, "loss": 0.1289, "lr": 2.8930097139893417e-06, "epoch": 27.67212443716742, "percentage": 84.54, "elapsed_time": "3:53:33", "remaining_time": "0:42:43", "throughput": 786.22, "total_tokens": 11017560} {"current_steps": 33820, "total_steps": 40000, "loss": 0.2637, "lr": 2.888427071404945e-06, "epoch": 27.67621776504298, "percentage": 84.55, "elapsed_time": "3:53:34", "remaining_time": "0:42:40", "throughput": 786.24, "total_tokens": 11019144} {"current_steps": 33825, "total_steps": 40000, "loss": 0.1779, "lr": 2.8838478387029606e-06, "epoch": 27.680311092918544, "percentage": 84.56, "elapsed_time": "3:53:36", "remaining_time": "0:42:38", "throughput": 786.26, "total_tokens": 11020824} {"current_steps": 33830, "total_steps": 40000, "loss": 0.1967, "lr": 2.8792720165895737e-06, "epoch": 27.684404420794106, "percentage": 84.58, "elapsed_time": "3:53:38", "remaining_time": "0:42:36", "throughput": 786.29, "total_tokens": 11022504} {"current_steps": 33835, "total_steps": 40000, "loss": 0.1973, "lr": 2.874699605770423e-06, "epoch": 27.68849774866967, "percentage": 84.59, "elapsed_time": "3:53:40", "remaining_time": "0:42:34", "throughput": 786.3, "total_tokens": 11024072} {"current_steps": 33840, "total_steps": 40000, "loss": 0.1547, "lr": 2.8701306069506383e-06, "epoch": 27.69259107654523, "percentage": 84.6, "elapsed_time": "3:53:41", "remaining_time": "0:42:32", "throughput": 786.33, "total_tokens": 11025768} {"current_steps": 33845, "total_steps": 40000, "loss": 0.2619, "lr": 2.8655650208348178e-06, "epoch": 27.696684404420793, "percentage": 84.61, "elapsed_time": "3:53:43", "remaining_time": "0:42:30", "throughput": 786.35, "total_tokens": 11027416} {"current_steps": 33850, "total_steps": 40000, "loss": 0.1395, "lr": 2.8610028481270257e-06, "epoch": 27.700777732296356, "percentage": 84.62, "elapsed_time": "3:53:45", "remaining_time": "0:42:28", "throughput": 786.37, "total_tokens": 11029048} {"current_steps": 33855, "total_steps": 40000, "loss": 0.1466, "lr": 2.856444089530813e-06, "epoch": 27.70487106017192, "percentage": 84.64, "elapsed_time": "3:53:47", "remaining_time": "0:42:26", "throughput": 786.38, "total_tokens": 11030616} {"current_steps": 33860, "total_steps": 40000, "loss": 0.199, "lr": 2.8518887457491955e-06, "epoch": 27.708964388047484, "percentage": 84.65, "elapsed_time": "3:53:48", "remaining_time": "0:42:23", "throughput": 786.4, "total_tokens": 11032248} {"current_steps": 33865, "total_steps": 40000, "loss": 0.1353, "lr": 2.8473368174846666e-06, "epoch": 27.713057715923046, "percentage": 84.66, "elapsed_time": "3:53:50", "remaining_time": "0:42:21", "throughput": 786.42, "total_tokens": 11033816} {"current_steps": 33870, "total_steps": 40000, "loss": 0.178, "lr": 2.842788305439184e-06, "epoch": 27.71715104379861, "percentage": 84.67, "elapsed_time": "3:53:52", "remaining_time": "0:42:19", "throughput": 786.43, "total_tokens": 11035416} {"current_steps": 33875, "total_steps": 40000, "loss": 0.1222, "lr": 2.8382432103141925e-06, "epoch": 27.72124437167417, "percentage": 84.69, "elapsed_time": "3:53:54", "remaining_time": "0:42:17", "throughput": 786.45, "total_tokens": 11037080} {"current_steps": 33880, "total_steps": 40000, "loss": 0.1282, "lr": 2.833701532810598e-06, "epoch": 27.725337699549733, "percentage": 84.7, "elapsed_time": "3:53:55", "remaining_time": "0:42:15", "throughput": 786.47, "total_tokens": 11038664} {"current_steps": 33885, "total_steps": 40000, "loss": 0.2234, "lr": 2.8291632736287877e-06, "epoch": 27.729431027425296, "percentage": 84.71, "elapsed_time": "3:53:57", "remaining_time": "0:42:13", "throughput": 786.48, "total_tokens": 11040296} {"current_steps": 33890, "total_steps": 40000, "loss": 0.1551, "lr": 2.824628433468615e-06, "epoch": 27.733524355300858, "percentage": 84.72, "elapsed_time": "3:53:59", "remaining_time": "0:42:11", "throughput": 786.5, "total_tokens": 11041928} {"current_steps": 33895, "total_steps": 40000, "loss": 0.1849, "lr": 2.8200970130294073e-06, "epoch": 27.737617683176424, "percentage": 84.74, "elapsed_time": "3:54:01", "remaining_time": "0:42:09", "throughput": 786.52, "total_tokens": 11043560} {"current_steps": 33900, "total_steps": 40000, "loss": 0.201, "lr": 2.8155690130099775e-06, "epoch": 27.741711011051986, "percentage": 84.75, "elapsed_time": "3:54:02", "remaining_time": "0:42:06", "throughput": 786.54, "total_tokens": 11045240} {"current_steps": 33905, "total_steps": 40000, "loss": 0.2669, "lr": 2.8110444341085895e-06, "epoch": 27.74580433892755, "percentage": 84.76, "elapsed_time": "3:54:04", "remaining_time": "0:42:04", "throughput": 786.56, "total_tokens": 11046872} {"current_steps": 33910, "total_steps": 40000, "loss": 0.2164, "lr": 2.806523277022996e-06, "epoch": 27.74989766680311, "percentage": 84.78, "elapsed_time": "3:54:06", "remaining_time": "0:42:02", "throughput": 786.58, "total_tokens": 11048488} {"current_steps": 33915, "total_steps": 40000, "loss": 0.1725, "lr": 2.802005542450409e-06, "epoch": 27.753990994678674, "percentage": 84.79, "elapsed_time": "3:54:08", "remaining_time": "0:42:00", "throughput": 786.59, "total_tokens": 11050104} {"current_steps": 33920, "total_steps": 40000, "loss": 0.1118, "lr": 2.797491231087526e-06, "epoch": 27.758084322554236, "percentage": 84.8, "elapsed_time": "3:54:09", "remaining_time": "0:41:58", "throughput": 786.61, "total_tokens": 11051736} {"current_steps": 33925, "total_steps": 40000, "loss": 0.3672, "lr": 2.7929803436305137e-06, "epoch": 27.7621776504298, "percentage": 84.81, "elapsed_time": "3:54:11", "remaining_time": "0:41:56", "throughput": 786.64, "total_tokens": 11053432} {"current_steps": 33930, "total_steps": 40000, "loss": 0.1894, "lr": 2.788472880774998e-06, "epoch": 27.76627097830536, "percentage": 84.82, "elapsed_time": "3:54:13", "remaining_time": "0:41:54", "throughput": 786.66, "total_tokens": 11055048} {"current_steps": 33935, "total_steps": 40000, "loss": 0.122, "lr": 2.7839688432160977e-06, "epoch": 27.770364306180927, "percentage": 84.84, "elapsed_time": "3:54:14", "remaining_time": "0:41:51", "throughput": 786.67, "total_tokens": 11056648} {"current_steps": 33940, "total_steps": 40000, "loss": 0.1723, "lr": 2.779468231648383e-06, "epoch": 27.77445763405649, "percentage": 84.85, "elapsed_time": "3:54:16", "remaining_time": "0:41:49", "throughput": 786.69, "total_tokens": 11058232} {"current_steps": 33945, "total_steps": 40000, "loss": 0.1514, "lr": 2.774971046765906e-06, "epoch": 27.77855096193205, "percentage": 84.86, "elapsed_time": "3:54:18", "remaining_time": "0:41:47", "throughput": 786.71, "total_tokens": 11059896} {"current_steps": 33950, "total_steps": 40000, "loss": 0.1332, "lr": 2.770477289262194e-06, "epoch": 27.782644289807614, "percentage": 84.88, "elapsed_time": "3:54:20", "remaining_time": "0:41:45", "throughput": 786.73, "total_tokens": 11061560} {"current_steps": 33955, "total_steps": 40000, "loss": 0.1765, "lr": 2.765986959830233e-06, "epoch": 27.786737617683176, "percentage": 84.89, "elapsed_time": "3:54:21", "remaining_time": "0:41:43", "throughput": 786.75, "total_tokens": 11063176} {"current_steps": 33960, "total_steps": 40000, "loss": 0.1833, "lr": 2.761500059162492e-06, "epoch": 27.79083094555874, "percentage": 84.9, "elapsed_time": "3:54:23", "remaining_time": "0:41:41", "throughput": 786.78, "total_tokens": 11064888} {"current_steps": 33965, "total_steps": 40000, "loss": 0.1775, "lr": 2.757016587950914e-06, "epoch": 27.7949242734343, "percentage": 84.91, "elapsed_time": "3:54:25", "remaining_time": "0:41:39", "throughput": 786.8, "total_tokens": 11066520} {"current_steps": 33970, "total_steps": 40000, "loss": 0.0953, "lr": 2.752536546886897e-06, "epoch": 27.799017601309863, "percentage": 84.92, "elapsed_time": "3:54:27", "remaining_time": "0:41:37", "throughput": 786.82, "total_tokens": 11068136} {"current_steps": 33975, "total_steps": 40000, "loss": 0.2371, "lr": 2.7480599366613234e-06, "epoch": 27.80311092918543, "percentage": 84.94, "elapsed_time": "3:54:28", "remaining_time": "0:41:34", "throughput": 786.84, "total_tokens": 11069784} {"current_steps": 33980, "total_steps": 40000, "loss": 0.1416, "lr": 2.7435867579645473e-06, "epoch": 27.80720425706099, "percentage": 84.95, "elapsed_time": "3:54:30", "remaining_time": "0:41:32", "throughput": 786.85, "total_tokens": 11071400} {"current_steps": 33985, "total_steps": 40000, "loss": 0.2104, "lr": 2.739117011486378e-06, "epoch": 27.811297584936554, "percentage": 84.96, "elapsed_time": "3:54:32", "remaining_time": "0:41:30", "throughput": 786.87, "total_tokens": 11073048} {"current_steps": 33990, "total_steps": 40000, "loss": 0.1163, "lr": 2.7346506979161216e-06, "epoch": 27.815390912812116, "percentage": 84.97, "elapsed_time": "3:54:33", "remaining_time": "0:41:28", "throughput": 786.9, "total_tokens": 11074744} {"current_steps": 33995, "total_steps": 40000, "loss": 0.1158, "lr": 2.7301878179425227e-06, "epoch": 27.81948424068768, "percentage": 84.99, "elapsed_time": "3:54:35", "remaining_time": "0:41:26", "throughput": 786.91, "total_tokens": 11076376} {"current_steps": 34000, "total_steps": 40000, "loss": 0.2322, "lr": 2.7257283722538244e-06, "epoch": 27.82357756856324, "percentage": 85.0, "elapsed_time": "3:54:37", "remaining_time": "0:41:24", "throughput": 786.94, "total_tokens": 11078056} {"current_steps": 34000, "total_steps": 40000, "eval_loss": 0.21317695081233978, "epoch": 27.82357756856324, "percentage": 85.0, "elapsed_time": "3:54:49", "remaining_time": "0:41:26", "throughput": 786.24, "total_tokens": 11078056} {"current_steps": 34005, "total_steps": 40000, "loss": 0.1559, "lr": 2.7212723615377326e-06, "epoch": 27.827670896438804, "percentage": 85.01, "elapsed_time": "3:54:53", "remaining_time": "0:41:24", "throughput": 786.17, "total_tokens": 11079688} {"current_steps": 34010, "total_steps": 40000, "loss": 0.2116, "lr": 2.7168197864814145e-06, "epoch": 27.831764224314366, "percentage": 85.02, "elapsed_time": "3:54:55", "remaining_time": "0:41:22", "throughput": 786.19, "total_tokens": 11081304} {"current_steps": 34015, "total_steps": 40000, "loss": 0.2386, "lr": 2.712370647771509e-06, "epoch": 27.835857552189932, "percentage": 85.04, "elapsed_time": "3:54:56", "remaining_time": "0:41:20", "throughput": 786.21, "total_tokens": 11082968} {"current_steps": 34020, "total_steps": 40000, "loss": 0.1779, "lr": 2.707924946094137e-06, "epoch": 27.839950880065494, "percentage": 85.05, "elapsed_time": "3:54:58", "remaining_time": "0:41:18", "throughput": 786.22, "total_tokens": 11084536} {"current_steps": 34025, "total_steps": 40000, "loss": 0.1683, "lr": 2.7034826821348723e-06, "epoch": 27.844044207941057, "percentage": 85.06, "elapsed_time": "3:55:00", "remaining_time": "0:41:16", "throughput": 786.24, "total_tokens": 11086136} {"current_steps": 34030, "total_steps": 40000, "loss": 0.308, "lr": 2.6990438565787786e-06, "epoch": 27.84813753581662, "percentage": 85.08, "elapsed_time": "3:55:02", "remaining_time": "0:41:13", "throughput": 786.25, "total_tokens": 11087752} {"current_steps": 34035, "total_steps": 40000, "loss": 0.1154, "lr": 2.6946084701103714e-06, "epoch": 27.85223086369218, "percentage": 85.09, "elapsed_time": "3:55:03", "remaining_time": "0:41:11", "throughput": 786.27, "total_tokens": 11089352} {"current_steps": 34040, "total_steps": 40000, "loss": 0.187, "lr": 2.6901765234136428e-06, "epoch": 27.856324191567744, "percentage": 85.1, "elapsed_time": "3:55:05", "remaining_time": "0:41:09", "throughput": 786.29, "total_tokens": 11091016} {"current_steps": 34045, "total_steps": 40000, "loss": 0.1169, "lr": 2.685748017172063e-06, "epoch": 27.860417519443306, "percentage": 85.11, "elapsed_time": "3:55:07", "remaining_time": "0:41:07", "throughput": 786.31, "total_tokens": 11092664} {"current_steps": 34050, "total_steps": 40000, "loss": 0.1916, "lr": 2.681322952068549e-06, "epoch": 27.86451084731887, "percentage": 85.12, "elapsed_time": "3:55:09", "remaining_time": "0:41:05", "throughput": 786.32, "total_tokens": 11094280} {"current_steps": 34055, "total_steps": 40000, "loss": 0.1202, "lr": 2.6769013287855137e-06, "epoch": 27.868604175194434, "percentage": 85.14, "elapsed_time": "3:55:10", "remaining_time": "0:41:03", "throughput": 786.34, "total_tokens": 11095864} {"current_steps": 34060, "total_steps": 40000, "loss": 0.1637, "lr": 2.6724831480048286e-06, "epoch": 27.872697503069997, "percentage": 85.15, "elapsed_time": "3:55:12", "remaining_time": "0:41:01", "throughput": 786.36, "total_tokens": 11097528} {"current_steps": 34065, "total_steps": 40000, "loss": 0.1118, "lr": 2.66806841040782e-06, "epoch": 27.87679083094556, "percentage": 85.16, "elapsed_time": "3:55:14", "remaining_time": "0:40:59", "throughput": 786.38, "total_tokens": 11099160} {"current_steps": 34070, "total_steps": 40000, "loss": 0.1285, "lr": 2.6636571166753083e-06, "epoch": 27.88088415882112, "percentage": 85.17, "elapsed_time": "3:55:15", "remaining_time": "0:40:56", "throughput": 786.4, "total_tokens": 11100760} {"current_steps": 34075, "total_steps": 40000, "loss": 0.2057, "lr": 2.6592492674875598e-06, "epoch": 27.884977486696684, "percentage": 85.19, "elapsed_time": "3:55:17", "remaining_time": "0:40:54", "throughput": 786.42, "total_tokens": 11102344} {"current_steps": 34080, "total_steps": 40000, "loss": 0.216, "lr": 2.6548448635243305e-06, "epoch": 27.889070814572246, "percentage": 85.2, "elapsed_time": "3:55:19", "remaining_time": "0:40:52", "throughput": 786.43, "total_tokens": 11103944} {"current_steps": 34085, "total_steps": 40000, "loss": 0.1146, "lr": 2.650443905464828e-06, "epoch": 27.89316414244781, "percentage": 85.21, "elapsed_time": "3:55:21", "remaining_time": "0:40:50", "throughput": 786.46, "total_tokens": 11105624} {"current_steps": 34090, "total_steps": 40000, "loss": 0.1591, "lr": 2.646046393987739e-06, "epoch": 27.897257470323375, "percentage": 85.22, "elapsed_time": "3:55:22", "remaining_time": "0:40:48", "throughput": 786.48, "total_tokens": 11107240} {"current_steps": 34095, "total_steps": 40000, "loss": 0.1478, "lr": 2.64165232977121e-06, "epoch": 27.901350798198937, "percentage": 85.24, "elapsed_time": "3:55:24", "remaining_time": "0:40:46", "throughput": 786.5, "total_tokens": 11108872} {"current_steps": 34100, "total_steps": 40000, "loss": 0.2417, "lr": 2.6372617134928695e-06, "epoch": 27.9054441260745, "percentage": 85.25, "elapsed_time": "3:55:26", "remaining_time": "0:40:44", "throughput": 786.52, "total_tokens": 11110568} {"current_steps": 34105, "total_steps": 40000, "loss": 0.178, "lr": 2.6328745458297943e-06, "epoch": 27.909537453950062, "percentage": 85.26, "elapsed_time": "3:55:27", "remaining_time": "0:40:41", "throughput": 786.55, "total_tokens": 11112328} {"current_steps": 34110, "total_steps": 40000, "loss": 0.1618, "lr": 2.6284908274585546e-06, "epoch": 27.913630781825624, "percentage": 85.28, "elapsed_time": "3:55:29", "remaining_time": "0:40:39", "throughput": 786.57, "total_tokens": 11113960} {"current_steps": 34115, "total_steps": 40000, "loss": 0.1348, "lr": 2.6241105590551595e-06, "epoch": 27.917724109701187, "percentage": 85.29, "elapsed_time": "3:55:31", "remaining_time": "0:40:37", "throughput": 786.59, "total_tokens": 11115656} {"current_steps": 34120, "total_steps": 40000, "loss": 0.1225, "lr": 2.6197337412951105e-06, "epoch": 27.92181743757675, "percentage": 85.3, "elapsed_time": "3:55:33", "remaining_time": "0:40:35", "throughput": 786.61, "total_tokens": 11117240} {"current_steps": 34125, "total_steps": 40000, "loss": 0.2092, "lr": 2.6153603748533705e-06, "epoch": 27.92591076545231, "percentage": 85.31, "elapsed_time": "3:55:34", "remaining_time": "0:40:33", "throughput": 786.62, "total_tokens": 11118824} {"current_steps": 34130, "total_steps": 40000, "loss": 0.1568, "lr": 2.6109904604043585e-06, "epoch": 27.930004093327877, "percentage": 85.32, "elapsed_time": "3:55:36", "remaining_time": "0:40:31", "throughput": 786.64, "total_tokens": 11120488} {"current_steps": 34135, "total_steps": 40000, "loss": 0.1705, "lr": 2.6066239986219765e-06, "epoch": 27.93409742120344, "percentage": 85.34, "elapsed_time": "3:55:38", "remaining_time": "0:40:29", "throughput": 786.66, "total_tokens": 11122104} {"current_steps": 34140, "total_steps": 40000, "loss": 0.1416, "lr": 2.602260990179592e-06, "epoch": 27.938190749079002, "percentage": 85.35, "elapsed_time": "3:55:40", "remaining_time": "0:40:27", "throughput": 786.68, "total_tokens": 11123800} {"current_steps": 34145, "total_steps": 40000, "loss": 0.1405, "lr": 2.5979014357500248e-06, "epoch": 27.942284076954564, "percentage": 85.36, "elapsed_time": "3:55:41", "remaining_time": "0:40:24", "throughput": 786.69, "total_tokens": 11125368} {"current_steps": 34150, "total_steps": 40000, "loss": 0.1529, "lr": 2.5935453360055844e-06, "epoch": 27.946377404830127, "percentage": 85.38, "elapsed_time": "3:55:43", "remaining_time": "0:40:22", "throughput": 786.72, "total_tokens": 11127048} {"current_steps": 34155, "total_steps": 40000, "loss": 0.1603, "lr": 2.5891926916180283e-06, "epoch": 27.95047073270569, "percentage": 85.39, "elapsed_time": "3:55:45", "remaining_time": "0:40:20", "throughput": 786.73, "total_tokens": 11128664} {"current_steps": 34160, "total_steps": 40000, "loss": 0.1457, "lr": 2.5848435032585883e-06, "epoch": 27.95456406058125, "percentage": 85.4, "elapsed_time": "3:55:47", "remaining_time": "0:40:18", "throughput": 786.75, "total_tokens": 11130248} {"current_steps": 34165, "total_steps": 40000, "loss": 0.1507, "lr": 2.58049777159797e-06, "epoch": 27.958657388456814, "percentage": 85.41, "elapsed_time": "3:55:48", "remaining_time": "0:40:16", "throughput": 786.76, "total_tokens": 11131896} {"current_steps": 34170, "total_steps": 40000, "loss": 0.2759, "lr": 2.576155497306332e-06, "epoch": 27.96275071633238, "percentage": 85.42, "elapsed_time": "3:55:50", "remaining_time": "0:40:14", "throughput": 786.78, "total_tokens": 11133528} {"current_steps": 34175, "total_steps": 40000, "loss": 0.1413, "lr": 2.57181668105331e-06, "epoch": 27.966844044207942, "percentage": 85.44, "elapsed_time": "3:55:52", "remaining_time": "0:40:12", "throughput": 786.8, "total_tokens": 11135128} {"current_steps": 34180, "total_steps": 40000, "loss": 0.1825, "lr": 2.567481323508014e-06, "epoch": 27.970937372083505, "percentage": 85.45, "elapsed_time": "3:55:54", "remaining_time": "0:40:10", "throughput": 786.81, "total_tokens": 11136728} {"current_steps": 34185, "total_steps": 40000, "loss": 0.1877, "lr": 2.5631494253389954e-06, "epoch": 27.975030699959067, "percentage": 85.46, "elapsed_time": "3:55:55", "remaining_time": "0:40:07", "throughput": 786.83, "total_tokens": 11138360} {"current_steps": 34190, "total_steps": 40000, "loss": 0.1555, "lr": 2.5588209872142997e-06, "epoch": 27.97912402783463, "percentage": 85.47, "elapsed_time": "3:55:57", "remaining_time": "0:40:05", "throughput": 786.85, "total_tokens": 11139976} {"current_steps": 34195, "total_steps": 40000, "loss": 0.219, "lr": 2.5544960098014186e-06, "epoch": 27.98321735571019, "percentage": 85.49, "elapsed_time": "3:55:59", "remaining_time": "0:40:03", "throughput": 786.87, "total_tokens": 11141640} {"current_steps": 34200, "total_steps": 40000, "loss": 0.2502, "lr": 2.550174493767318e-06, "epoch": 27.987310683585754, "percentage": 85.5, "elapsed_time": "3:56:01", "remaining_time": "0:40:01", "throughput": 786.89, "total_tokens": 11143272} {"current_steps": 34200, "total_steps": 40000, "eval_loss": 0.21364924311637878, "epoch": 27.987310683585754, "percentage": 85.5, "elapsed_time": "3:56:13", "remaining_time": "0:40:03", "throughput": 786.2, "total_tokens": 11143272} {"current_steps": 34205, "total_steps": 40000, "loss": 0.2113, "lr": 2.545856439778438e-06, "epoch": 27.991404011461317, "percentage": 85.51, "elapsed_time": "3:56:16", "remaining_time": "0:40:01", "throughput": 786.13, "total_tokens": 11144888} {"current_steps": 34210, "total_steps": 40000, "loss": 0.1975, "lr": 2.541541848500667e-06, "epoch": 27.995497339336882, "percentage": 85.52, "elapsed_time": "3:56:18", "remaining_time": "0:39:59", "throughput": 786.15, "total_tokens": 11146472} {"current_steps": 34215, "total_steps": 40000, "loss": 0.108, "lr": 2.5372307205993733e-06, "epoch": 27.999590667212445, "percentage": 85.54, "elapsed_time": "3:56:20", "remaining_time": "0:39:57", "throughput": 786.17, "total_tokens": 11148184} {"current_steps": 34220, "total_steps": 40000, "loss": 0.1185, "lr": 2.5329230567393917e-06, "epoch": 28.003274662300452, "percentage": 85.55, "elapsed_time": "3:56:22", "remaining_time": "0:39:55", "throughput": 786.16, "total_tokens": 11149520} {"current_steps": 34225, "total_steps": 40000, "loss": 0.1167, "lr": 2.5286188575850164e-06, "epoch": 28.007367990176014, "percentage": 85.56, "elapsed_time": "3:56:23", "remaining_time": "0:39:53", "throughput": 786.18, "total_tokens": 11151104} {"current_steps": 34230, "total_steps": 40000, "loss": 0.1435, "lr": 2.5243181237999984e-06, "epoch": 28.011461318051577, "percentage": 85.58, "elapsed_time": "3:56:25", "remaining_time": "0:39:51", "throughput": 786.2, "total_tokens": 11152736} {"current_steps": 34235, "total_steps": 40000, "loss": 0.1391, "lr": 2.520020856047578e-06, "epoch": 28.01555464592714, "percentage": 85.59, "elapsed_time": "3:56:27", "remaining_time": "0:39:49", "throughput": 786.22, "total_tokens": 11154416} {"current_steps": 34240, "total_steps": 40000, "loss": 0.1067, "lr": 2.515727054990438e-06, "epoch": 28.0196479738027, "percentage": 85.6, "elapsed_time": "3:56:29", "remaining_time": "0:39:46", "throughput": 786.24, "total_tokens": 11156064} {"current_steps": 34245, "total_steps": 40000, "loss": 0.2677, "lr": 2.511436721290747e-06, "epoch": 28.023741301678264, "percentage": 85.61, "elapsed_time": "3:56:30", "remaining_time": "0:39:44", "throughput": 786.26, "total_tokens": 11157728} {"current_steps": 34250, "total_steps": 40000, "loss": 0.2363, "lr": 2.5071498556101164e-06, "epoch": 28.027834629553826, "percentage": 85.62, "elapsed_time": "3:56:32", "remaining_time": "0:39:42", "throughput": 786.29, "total_tokens": 11159392} {"current_steps": 34255, "total_steps": 40000, "loss": 0.0947, "lr": 2.5028664586096485e-06, "epoch": 28.03192795742939, "percentage": 85.64, "elapsed_time": "3:56:34", "remaining_time": "0:39:40", "throughput": 786.3, "total_tokens": 11161024} {"current_steps": 34260, "total_steps": 40000, "loss": 0.1825, "lr": 2.498586530949881e-06, "epoch": 28.036021285304955, "percentage": 85.65, "elapsed_time": "3:56:35", "remaining_time": "0:39:38", "throughput": 786.33, "total_tokens": 11162672} {"current_steps": 34265, "total_steps": 40000, "loss": 0.1692, "lr": 2.4943100732908427e-06, "epoch": 28.040114613180517, "percentage": 85.66, "elapsed_time": "3:56:37", "remaining_time": "0:39:36", "throughput": 786.34, "total_tokens": 11164240} {"current_steps": 34270, "total_steps": 40000, "loss": 0.1756, "lr": 2.4900370862920188e-06, "epoch": 28.04420794105608, "percentage": 85.67, "elapsed_time": "3:56:39", "remaining_time": "0:39:34", "throughput": 786.36, "total_tokens": 11165888} {"current_steps": 34275, "total_steps": 40000, "loss": 0.1362, "lr": 2.4857675706123518e-06, "epoch": 28.04830126893164, "percentage": 85.69, "elapsed_time": "3:56:41", "remaining_time": "0:39:32", "throughput": 786.38, "total_tokens": 11167472} {"current_steps": 34280, "total_steps": 40000, "loss": 0.1863, "lr": 2.4815015269102543e-06, "epoch": 28.052394596807204, "percentage": 85.7, "elapsed_time": "3:56:42", "remaining_time": "0:39:29", "throughput": 786.39, "total_tokens": 11169024} {"current_steps": 34285, "total_steps": 40000, "loss": 0.1442, "lr": 2.477238955843611e-06, "epoch": 28.056487924682767, "percentage": 85.71, "elapsed_time": "3:56:44", "remaining_time": "0:39:27", "throughput": 786.41, "total_tokens": 11170720} {"current_steps": 34290, "total_steps": 40000, "loss": 0.1741, "lr": 2.4729798580697573e-06, "epoch": 28.06058125255833, "percentage": 85.72, "elapsed_time": "3:56:46", "remaining_time": "0:39:25", "throughput": 786.43, "total_tokens": 11172352} {"current_steps": 34295, "total_steps": 40000, "loss": 0.1417, "lr": 2.4687242342455034e-06, "epoch": 28.06467458043389, "percentage": 85.74, "elapsed_time": "3:56:48", "remaining_time": "0:39:23", "throughput": 786.45, "total_tokens": 11173984} {"current_steps": 34300, "total_steps": 40000, "loss": 0.1256, "lr": 2.4644720850271196e-06, "epoch": 28.068767908309457, "percentage": 85.75, "elapsed_time": "3:56:49", "remaining_time": "0:39:21", "throughput": 786.47, "total_tokens": 11175664} {"current_steps": 34305, "total_steps": 40000, "loss": 0.0931, "lr": 2.4602234110703364e-06, "epoch": 28.07286123618502, "percentage": 85.76, "elapsed_time": "3:56:51", "remaining_time": "0:39:19", "throughput": 786.49, "total_tokens": 11177344} {"current_steps": 34310, "total_steps": 40000, "loss": 0.1718, "lr": 2.4559782130303576e-06, "epoch": 28.076954564060582, "percentage": 85.78, "elapsed_time": "3:56:53", "remaining_time": "0:39:17", "throughput": 786.51, "total_tokens": 11178992} {"current_steps": 34315, "total_steps": 40000, "loss": 0.1462, "lr": 2.451736491561843e-06, "epoch": 28.081047891936144, "percentage": 85.79, "elapsed_time": "3:56:55", "remaining_time": "0:39:15", "throughput": 786.53, "total_tokens": 11180672} {"current_steps": 34320, "total_steps": 40000, "loss": 0.1806, "lr": 2.4474982473189163e-06, "epoch": 28.085141219811707, "percentage": 85.8, "elapsed_time": "3:56:56", "remaining_time": "0:39:12", "throughput": 786.55, "total_tokens": 11182288} {"current_steps": 34325, "total_steps": 40000, "loss": 0.1575, "lr": 2.4432634809551796e-06, "epoch": 28.08923454768727, "percentage": 85.81, "elapsed_time": "3:56:58", "remaining_time": "0:39:10", "throughput": 786.56, "total_tokens": 11183856} {"current_steps": 34330, "total_steps": 40000, "loss": 0.1785, "lr": 2.439032193123675e-06, "epoch": 28.09332787556283, "percentage": 85.82, "elapsed_time": "3:57:00", "remaining_time": "0:39:08", "throughput": 786.58, "total_tokens": 11185488} {"current_steps": 34335, "total_steps": 40000, "loss": 0.2032, "lr": 2.4348043844769297e-06, "epoch": 28.097421203438394, "percentage": 85.84, "elapsed_time": "3:57:02", "remaining_time": "0:39:06", "throughput": 786.59, "total_tokens": 11187104} {"current_steps": 34340, "total_steps": 40000, "loss": 0.1558, "lr": 2.4305800556669146e-06, "epoch": 28.10151453131396, "percentage": 85.85, "elapsed_time": "3:57:03", "remaining_time": "0:39:04", "throughput": 786.61, "total_tokens": 11188720} {"current_steps": 34345, "total_steps": 40000, "loss": 0.2009, "lr": 2.426359207345083e-06, "epoch": 28.105607859189522, "percentage": 85.86, "elapsed_time": "3:57:05", "remaining_time": "0:39:02", "throughput": 786.62, "total_tokens": 11190288} {"current_steps": 34350, "total_steps": 40000, "loss": 0.1862, "lr": 2.4221418401623396e-06, "epoch": 28.109701187065085, "percentage": 85.88, "elapsed_time": "3:57:07", "remaining_time": "0:39:00", "throughput": 786.64, "total_tokens": 11191904} {"current_steps": 34355, "total_steps": 40000, "loss": 0.136, "lr": 2.4179279547690557e-06, "epoch": 28.113794514940647, "percentage": 85.89, "elapsed_time": "3:57:09", "remaining_time": "0:38:58", "throughput": 786.65, "total_tokens": 11193504} {"current_steps": 34360, "total_steps": 40000, "loss": 0.1961, "lr": 2.413717551815062e-06, "epoch": 28.11788784281621, "percentage": 85.9, "elapsed_time": "3:57:11", "remaining_time": "0:38:55", "throughput": 786.67, "total_tokens": 11195056} {"current_steps": 34365, "total_steps": 40000, "loss": 0.1468, "lr": 2.409510631949666e-06, "epoch": 28.12198117069177, "percentage": 85.91, "elapsed_time": "3:57:12", "remaining_time": "0:38:53", "throughput": 786.68, "total_tokens": 11196672} {"current_steps": 34370, "total_steps": 40000, "loss": 0.1991, "lr": 2.405307195821618e-06, "epoch": 28.126074498567334, "percentage": 85.92, "elapsed_time": "3:57:14", "remaining_time": "0:38:51", "throughput": 786.71, "total_tokens": 11198352} {"current_steps": 34375, "total_steps": 40000, "loss": 0.161, "lr": 2.4011072440791372e-06, "epoch": 28.130167826442896, "percentage": 85.94, "elapsed_time": "3:57:16", "remaining_time": "0:38:49", "throughput": 786.72, "total_tokens": 11199968} {"current_steps": 34380, "total_steps": 40000, "loss": 0.1224, "lr": 2.3969107773699233e-06, "epoch": 28.134261154318462, "percentage": 85.95, "elapsed_time": "3:57:17", "remaining_time": "0:38:47", "throughput": 786.74, "total_tokens": 11201616} {"current_steps": 34385, "total_steps": 40000, "loss": 0.1024, "lr": 2.3927177963411096e-06, "epoch": 28.138354482194025, "percentage": 85.96, "elapsed_time": "3:57:19", "remaining_time": "0:38:45", "throughput": 786.76, "total_tokens": 11203232} {"current_steps": 34390, "total_steps": 40000, "loss": 0.1536, "lr": 2.3885283016393144e-06, "epoch": 28.142447810069587, "percentage": 85.97, "elapsed_time": "3:57:21", "remaining_time": "0:38:43", "throughput": 786.78, "total_tokens": 11204896} {"current_steps": 34395, "total_steps": 40000, "loss": 0.1651, "lr": 2.3843422939106076e-06, "epoch": 28.14654113794515, "percentage": 85.99, "elapsed_time": "3:57:23", "remaining_time": "0:38:41", "throughput": 786.81, "total_tokens": 11206560} {"current_steps": 34400, "total_steps": 40000, "loss": 0.145, "lr": 2.380159773800525e-06, "epoch": 28.150634465820712, "percentage": 86.0, "elapsed_time": "3:57:24", "remaining_time": "0:38:38", "throughput": 786.82, "total_tokens": 11208128} {"current_steps": 34400, "total_steps": 40000, "eval_loss": 0.2145642638206482, "epoch": 28.150634465820712, "percentage": 86.0, "elapsed_time": "3:57:37", "remaining_time": "0:38:40", "throughput": 786.13, "total_tokens": 11208128} {"current_steps": 34405, "total_steps": 40000, "loss": 0.1694, "lr": 2.3759807419540675e-06, "epoch": 28.154727793696274, "percentage": 86.01, "elapsed_time": "3:57:40", "remaining_time": "0:38:39", "throughput": 786.07, "total_tokens": 11209744} {"current_steps": 34410, "total_steps": 40000, "loss": 0.2395, "lr": 2.3718051990156835e-06, "epoch": 28.158821121571837, "percentage": 86.02, "elapsed_time": "3:57:42", "remaining_time": "0:38:36", "throughput": 786.08, "total_tokens": 11211344} {"current_steps": 34415, "total_steps": 40000, "loss": 0.1213, "lr": 2.367633145629311e-06, "epoch": 28.1629144494474, "percentage": 86.04, "elapsed_time": "3:57:44", "remaining_time": "0:38:34", "throughput": 786.11, "total_tokens": 11213024} {"current_steps": 34420, "total_steps": 40000, "loss": 0.1514, "lr": 2.363464582438316e-06, "epoch": 28.167007777322965, "percentage": 86.05, "elapsed_time": "3:57:45", "remaining_time": "0:38:32", "throughput": 786.13, "total_tokens": 11214672} {"current_steps": 34425, "total_steps": 40000, "loss": 0.1635, "lr": 2.3592995100855526e-06, "epoch": 28.171101105198527, "percentage": 86.06, "elapsed_time": "3:57:47", "remaining_time": "0:38:30", "throughput": 786.15, "total_tokens": 11216336} {"current_steps": 34430, "total_steps": 40000, "loss": 0.2447, "lr": 2.3551379292133273e-06, "epoch": 28.17519443307409, "percentage": 86.08, "elapsed_time": "3:57:49", "remaining_time": "0:38:28", "throughput": 786.16, "total_tokens": 11217888} {"current_steps": 34435, "total_steps": 40000, "loss": 0.2031, "lr": 2.3509798404634047e-06, "epoch": 28.179287760949652, "percentage": 86.09, "elapsed_time": "3:57:50", "remaining_time": "0:38:26", "throughput": 786.18, "total_tokens": 11219536} {"current_steps": 34440, "total_steps": 40000, "loss": 0.1866, "lr": 2.346825244477019e-06, "epoch": 28.183381088825215, "percentage": 86.1, "elapsed_time": "3:57:52", "remaining_time": "0:38:24", "throughput": 786.21, "total_tokens": 11221264} {"current_steps": 34445, "total_steps": 40000, "loss": 0.1659, "lr": 2.3426741418948545e-06, "epoch": 28.187474416700777, "percentage": 86.11, "elapsed_time": "3:57:54", "remaining_time": "0:38:22", "throughput": 786.23, "total_tokens": 11222912} {"current_steps": 34450, "total_steps": 40000, "loss": 0.1815, "lr": 2.3385265333570715e-06, "epoch": 28.19156774457634, "percentage": 86.12, "elapsed_time": "3:57:56", "remaining_time": "0:38:19", "throughput": 786.25, "total_tokens": 11224528} {"current_steps": 34455, "total_steps": 40000, "loss": 0.1404, "lr": 2.334382419503278e-06, "epoch": 28.1956610724519, "percentage": 86.14, "elapsed_time": "3:57:57", "remaining_time": "0:38:17", "throughput": 786.27, "total_tokens": 11226208} {"current_steps": 34460, "total_steps": 40000, "loss": 0.2572, "lr": 2.3302418009725465e-06, "epoch": 28.199754400327468, "percentage": 86.15, "elapsed_time": "3:57:59", "remaining_time": "0:38:15", "throughput": 786.29, "total_tokens": 11227840} {"current_steps": 34465, "total_steps": 40000, "loss": 0.1331, "lr": 2.326104678403415e-06, "epoch": 28.20384772820303, "percentage": 86.16, "elapsed_time": "3:58:01", "remaining_time": "0:38:13", "throughput": 786.31, "total_tokens": 11229424} {"current_steps": 34470, "total_steps": 40000, "loss": 0.157, "lr": 2.321971052433883e-06, "epoch": 28.207941056078592, "percentage": 86.17, "elapsed_time": "3:58:02", "remaining_time": "0:38:11", "throughput": 786.33, "total_tokens": 11231120} {"current_steps": 34475, "total_steps": 40000, "loss": 0.1709, "lr": 2.3178409237014004e-06, "epoch": 28.212034383954155, "percentage": 86.19, "elapsed_time": "3:58:04", "remaining_time": "0:38:09", "throughput": 786.35, "total_tokens": 11232752} {"current_steps": 34480, "total_steps": 40000, "loss": 0.1885, "lr": 2.313714292842889e-06, "epoch": 28.216127711829717, "percentage": 86.2, "elapsed_time": "3:58:06", "remaining_time": "0:38:07", "throughput": 786.36, "total_tokens": 11234368} {"current_steps": 34485, "total_steps": 40000, "loss": 0.1446, "lr": 2.309591160494734e-06, "epoch": 28.22022103970528, "percentage": 86.21, "elapsed_time": "3:58:08", "remaining_time": "0:38:05", "throughput": 786.39, "total_tokens": 11236096} {"current_steps": 34490, "total_steps": 40000, "loss": 0.1311, "lr": 2.305471527292763e-06, "epoch": 28.224314367580842, "percentage": 86.22, "elapsed_time": "3:58:09", "remaining_time": "0:38:02", "throughput": 786.41, "total_tokens": 11237728} {"current_steps": 34495, "total_steps": 40000, "loss": 0.195, "lr": 2.3013553938722817e-06, "epoch": 28.228407695456404, "percentage": 86.24, "elapsed_time": "3:58:11", "remaining_time": "0:38:00", "throughput": 786.42, "total_tokens": 11239312} {"current_steps": 34500, "total_steps": 40000, "loss": 0.1526, "lr": 2.297242760868043e-06, "epoch": 28.23250102333197, "percentage": 86.25, "elapsed_time": "3:58:13", "remaining_time": "0:37:58", "throughput": 786.44, "total_tokens": 11240912} {"current_steps": 34505, "total_steps": 40000, "loss": 0.1367, "lr": 2.2931336289142735e-06, "epoch": 28.236594351207533, "percentage": 86.26, "elapsed_time": "3:58:15", "remaining_time": "0:37:56", "throughput": 786.45, "total_tokens": 11242512} {"current_steps": 34510, "total_steps": 40000, "loss": 0.2122, "lr": 2.289027998644655e-06, "epoch": 28.240687679083095, "percentage": 86.28, "elapsed_time": "3:58:17", "remaining_time": "0:37:54", "throughput": 786.46, "total_tokens": 11244096} {"current_steps": 34515, "total_steps": 40000, "loss": 0.1329, "lr": 2.2849258706923228e-06, "epoch": 28.244781006958657, "percentage": 86.29, "elapsed_time": "3:58:18", "remaining_time": "0:37:52", "throughput": 786.48, "total_tokens": 11245712} {"current_steps": 34520, "total_steps": 40000, "loss": 0.1888, "lr": 2.2808272456898705e-06, "epoch": 28.24887433483422, "percentage": 86.3, "elapsed_time": "3:58:20", "remaining_time": "0:37:50", "throughput": 786.5, "total_tokens": 11247312} {"current_steps": 34525, "total_steps": 40000, "loss": 0.1462, "lr": 2.2767321242693707e-06, "epoch": 28.252967662709782, "percentage": 86.31, "elapsed_time": "3:58:22", "remaining_time": "0:37:48", "throughput": 786.52, "total_tokens": 11248976} {"current_steps": 34530, "total_steps": 40000, "loss": 0.1315, "lr": 2.272640507062329e-06, "epoch": 28.257060990585344, "percentage": 86.33, "elapsed_time": "3:58:24", "remaining_time": "0:37:45", "throughput": 786.53, "total_tokens": 11250624} {"current_steps": 34535, "total_steps": 40000, "loss": 0.1519, "lr": 2.2685523946997382e-06, "epoch": 28.26115431846091, "percentage": 86.34, "elapsed_time": "3:58:25", "remaining_time": "0:37:43", "throughput": 786.55, "total_tokens": 11252256} {"current_steps": 34540, "total_steps": 40000, "loss": 0.2221, "lr": 2.2644677878120245e-06, "epoch": 28.265247646336473, "percentage": 86.35, "elapsed_time": "3:58:27", "remaining_time": "0:37:41", "throughput": 786.57, "total_tokens": 11253872} {"current_steps": 34545, "total_steps": 40000, "loss": 0.2713, "lr": 2.2603866870290897e-06, "epoch": 28.269340974212035, "percentage": 86.36, "elapsed_time": "3:58:29", "remaining_time": "0:37:39", "throughput": 786.59, "total_tokens": 11255568} {"current_steps": 34550, "total_steps": 40000, "loss": 0.2334, "lr": 2.256309092980294e-06, "epoch": 28.273434302087598, "percentage": 86.38, "elapsed_time": "3:58:31", "remaining_time": "0:37:37", "throughput": 786.6, "total_tokens": 11257152} {"current_steps": 34555, "total_steps": 40000, "loss": 0.1533, "lr": 2.252235006294448e-06, "epoch": 28.27752762996316, "percentage": 86.39, "elapsed_time": "3:58:32", "remaining_time": "0:37:35", "throughput": 786.62, "total_tokens": 11258768} {"current_steps": 34560, "total_steps": 40000, "loss": 0.2297, "lr": 2.2481644275998333e-06, "epoch": 28.281620957838722, "percentage": 86.4, "elapsed_time": "3:58:34", "remaining_time": "0:37:33", "throughput": 786.63, "total_tokens": 11260352} {"current_steps": 34565, "total_steps": 40000, "loss": 0.1806, "lr": 2.2440973575241832e-06, "epoch": 28.285714285714285, "percentage": 86.41, "elapsed_time": "3:58:36", "remaining_time": "0:37:31", "throughput": 786.65, "total_tokens": 11261952} {"current_steps": 34570, "total_steps": 40000, "loss": 0.1636, "lr": 2.240033796694685e-06, "epoch": 28.289807613589847, "percentage": 86.42, "elapsed_time": "3:58:38", "remaining_time": "0:37:28", "throughput": 786.67, "total_tokens": 11263552} {"current_steps": 34575, "total_steps": 40000, "loss": 0.1915, "lr": 2.235973745737999e-06, "epoch": 28.293900941465413, "percentage": 86.44, "elapsed_time": "3:58:39", "remaining_time": "0:37:26", "throughput": 786.68, "total_tokens": 11265152} {"current_steps": 34580, "total_steps": 40000, "loss": 0.2262, "lr": 2.2319172052802263e-06, "epoch": 28.297994269340975, "percentage": 86.45, "elapsed_time": "3:58:41", "remaining_time": "0:37:24", "throughput": 786.68, "total_tokens": 11266704} {"current_steps": 34585, "total_steps": 40000, "loss": 0.1556, "lr": 2.2278641759469477e-06, "epoch": 28.302087597216538, "percentage": 86.46, "elapsed_time": "3:58:43", "remaining_time": "0:37:22", "throughput": 786.7, "total_tokens": 11268352} {"current_steps": 34590, "total_steps": 40000, "loss": 0.2191, "lr": 2.2238146583631825e-06, "epoch": 28.3061809250921, "percentage": 86.48, "elapsed_time": "3:58:45", "remaining_time": "0:37:20", "throughput": 786.72, "total_tokens": 11270016} {"current_steps": 34595, "total_steps": 40000, "loss": 0.1699, "lr": 2.2197686531534256e-06, "epoch": 28.310274252967663, "percentage": 86.49, "elapsed_time": "3:58:47", "remaining_time": "0:37:18", "throughput": 786.75, "total_tokens": 11271744} {"current_steps": 34600, "total_steps": 40000, "loss": 0.1127, "lr": 2.2157261609416087e-06, "epoch": 28.314367580843225, "percentage": 86.5, "elapsed_time": "3:58:48", "remaining_time": "0:37:16", "throughput": 786.77, "total_tokens": 11273344} {"current_steps": 34600, "total_steps": 40000, "eval_loss": 0.21529437601566315, "epoch": 28.314367580843225, "percentage": 86.5, "elapsed_time": "3:59:01", "remaining_time": "0:37:18", "throughput": 786.08, "total_tokens": 11273344} {"current_steps": 34605, "total_steps": 40000, "loss": 0.1896, "lr": 2.211687182351149e-06, "epoch": 28.318460908718787, "percentage": 86.51, "elapsed_time": "3:59:04", "remaining_time": "0:37:16", "throughput": 786.02, "total_tokens": 11275056} {"current_steps": 34610, "total_steps": 40000, "loss": 0.2362, "lr": 2.2076517180048993e-06, "epoch": 28.32255423659435, "percentage": 86.52, "elapsed_time": "3:59:06", "remaining_time": "0:37:14", "throughput": 786.04, "total_tokens": 11276704} {"current_steps": 34615, "total_steps": 40000, "loss": 0.1458, "lr": 2.2036197685251834e-06, "epoch": 28.326647564469916, "percentage": 86.54, "elapsed_time": "3:59:07", "remaining_time": "0:37:12", "throughput": 786.06, "total_tokens": 11278272} {"current_steps": 34620, "total_steps": 40000, "loss": 0.2, "lr": 2.199591334533771e-06, "epoch": 28.330740892345478, "percentage": 86.55, "elapsed_time": "3:59:09", "remaining_time": "0:37:09", "throughput": 786.08, "total_tokens": 11279856} {"current_steps": 34625, "total_steps": 40000, "loss": 0.1253, "lr": 2.1955664166519036e-06, "epoch": 28.33483422022104, "percentage": 86.56, "elapsed_time": "3:59:11", "remaining_time": "0:37:07", "throughput": 786.1, "total_tokens": 11281472} {"current_steps": 34630, "total_steps": 40000, "loss": 0.2426, "lr": 2.1915450155002793e-06, "epoch": 28.338927548096603, "percentage": 86.58, "elapsed_time": "3:59:12", "remaining_time": "0:37:05", "throughput": 786.11, "total_tokens": 11283072} {"current_steps": 34635, "total_steps": 40000, "loss": 0.1234, "lr": 2.187527131699038e-06, "epoch": 28.343020875972165, "percentage": 86.59, "elapsed_time": "3:59:14", "remaining_time": "0:37:03", "throughput": 786.14, "total_tokens": 11284800} {"current_steps": 34640, "total_steps": 40000, "loss": 0.18, "lr": 2.18351276586779e-06, "epoch": 28.347114203847728, "percentage": 86.6, "elapsed_time": "3:59:16", "remaining_time": "0:37:01", "throughput": 786.15, "total_tokens": 11286384} {"current_steps": 34645, "total_steps": 40000, "loss": 0.11, "lr": 2.1795019186256092e-06, "epoch": 28.35120753172329, "percentage": 86.61, "elapsed_time": "3:59:18", "remaining_time": "0:36:59", "throughput": 786.17, "total_tokens": 11288000} {"current_steps": 34650, "total_steps": 40000, "loss": 0.2333, "lr": 2.1754945905910094e-06, "epoch": 28.355300859598852, "percentage": 86.62, "elapsed_time": "3:59:19", "remaining_time": "0:36:57", "throughput": 786.19, "total_tokens": 11289584} {"current_steps": 34655, "total_steps": 40000, "loss": 0.3675, "lr": 2.171490782381977e-06, "epoch": 28.359394187474418, "percentage": 86.64, "elapsed_time": "3:59:21", "remaining_time": "0:36:55", "throughput": 786.21, "total_tokens": 11291232} {"current_steps": 34660, "total_steps": 40000, "loss": 0.1748, "lr": 2.1674904946159425e-06, "epoch": 28.36348751534998, "percentage": 86.65, "elapsed_time": "3:59:23", "remaining_time": "0:36:52", "throughput": 786.23, "total_tokens": 11292832} {"current_steps": 34665, "total_steps": 40000, "loss": 0.1804, "lr": 2.16349372790981e-06, "epoch": 28.367580843225543, "percentage": 86.66, "elapsed_time": "3:59:25", "remaining_time": "0:36:50", "throughput": 786.25, "total_tokens": 11294480} {"current_steps": 34670, "total_steps": 40000, "loss": 0.091, "lr": 2.159500482879928e-06, "epoch": 28.371674171101105, "percentage": 86.67, "elapsed_time": "3:59:26", "remaining_time": "0:36:48", "throughput": 786.27, "total_tokens": 11296160} {"current_steps": 34675, "total_steps": 40000, "loss": 0.123, "lr": 2.155510760142096e-06, "epoch": 28.375767498976668, "percentage": 86.69, "elapsed_time": "3:59:28", "remaining_time": "0:36:46", "throughput": 786.29, "total_tokens": 11297760} {"current_steps": 34680, "total_steps": 40000, "loss": 0.1967, "lr": 2.151524560311588e-06, "epoch": 28.37986082685223, "percentage": 86.7, "elapsed_time": "3:59:30", "remaining_time": "0:36:44", "throughput": 786.31, "total_tokens": 11299424} {"current_steps": 34685, "total_steps": 40000, "loss": 0.1679, "lr": 2.147541884003129e-06, "epoch": 28.383954154727792, "percentage": 86.71, "elapsed_time": "3:59:31", "remaining_time": "0:36:42", "throughput": 786.33, "total_tokens": 11301040} {"current_steps": 34690, "total_steps": 40000, "loss": 0.1864, "lr": 2.1435627318308895e-06, "epoch": 28.388047482603355, "percentage": 86.72, "elapsed_time": "3:59:33", "remaining_time": "0:36:40", "throughput": 786.34, "total_tokens": 11302592} {"current_steps": 34695, "total_steps": 40000, "loss": 0.1457, "lr": 2.139587104408511e-06, "epoch": 28.39214081047892, "percentage": 86.74, "elapsed_time": "3:59:35", "remaining_time": "0:36:38", "throughput": 786.36, "total_tokens": 11304208} {"current_steps": 34700, "total_steps": 40000, "loss": 0.109, "lr": 2.1356150023490783e-06, "epoch": 28.396234138354483, "percentage": 86.75, "elapsed_time": "3:59:37", "remaining_time": "0:36:35", "throughput": 786.38, "total_tokens": 11305856} {"current_steps": 34705, "total_steps": 40000, "loss": 0.1474, "lr": 2.1316464262651464e-06, "epoch": 28.400327466230046, "percentage": 86.76, "elapsed_time": "3:59:38", "remaining_time": "0:36:33", "throughput": 786.4, "total_tokens": 11307488} {"current_steps": 34710, "total_steps": 40000, "loss": 0.1522, "lr": 2.1276813767687224e-06, "epoch": 28.404420794105608, "percentage": 86.78, "elapsed_time": "3:59:40", "remaining_time": "0:36:31", "throughput": 786.42, "total_tokens": 11309072} {"current_steps": 34715, "total_steps": 40000, "loss": 0.2188, "lr": 2.123719854471254e-06, "epoch": 28.40851412198117, "percentage": 86.79, "elapsed_time": "3:59:42", "remaining_time": "0:36:29", "throughput": 786.43, "total_tokens": 11310720} {"current_steps": 34720, "total_steps": 40000, "loss": 0.177, "lr": 2.119761859983668e-06, "epoch": 28.412607449856733, "percentage": 86.8, "elapsed_time": "3:59:44", "remaining_time": "0:36:27", "throughput": 786.46, "total_tokens": 11312400} {"current_steps": 34725, "total_steps": 40000, "loss": 0.1836, "lr": 2.1158073939163386e-06, "epoch": 28.416700777732295, "percentage": 86.81, "elapsed_time": "3:59:45", "remaining_time": "0:36:25", "throughput": 786.48, "total_tokens": 11314080} {"current_steps": 34730, "total_steps": 40000, "loss": 0.2828, "lr": 2.111856456879088e-06, "epoch": 28.420794105607857, "percentage": 86.83, "elapsed_time": "3:59:47", "remaining_time": "0:36:23", "throughput": 786.49, "total_tokens": 11315696} {"current_steps": 34735, "total_steps": 40000, "loss": 0.1663, "lr": 2.1079090494811993e-06, "epoch": 28.424887433483423, "percentage": 86.84, "elapsed_time": "3:59:49", "remaining_time": "0:36:21", "throughput": 786.52, "total_tokens": 11317440} {"current_steps": 34740, "total_steps": 40000, "loss": 0.1335, "lr": 2.103965172331418e-06, "epoch": 28.428980761358986, "percentage": 86.85, "elapsed_time": "3:59:51", "remaining_time": "0:36:18", "throughput": 786.53, "total_tokens": 11319040} {"current_steps": 34745, "total_steps": 40000, "loss": 0.2121, "lr": 2.100024826037933e-06, "epoch": 28.433074089234548, "percentage": 86.86, "elapsed_time": "3:59:52", "remaining_time": "0:36:16", "throughput": 786.55, "total_tokens": 11320656} {"current_steps": 34750, "total_steps": 40000, "loss": 0.2099, "lr": 2.0960880112084027e-06, "epoch": 28.43716741711011, "percentage": 86.88, "elapsed_time": "3:59:54", "remaining_time": "0:36:14", "throughput": 786.57, "total_tokens": 11322304} {"current_steps": 34755, "total_steps": 40000, "loss": 0.1681, "lr": 2.092154728449927e-06, "epoch": 28.441260744985673, "percentage": 86.89, "elapsed_time": "3:59:56", "remaining_time": "0:36:12", "throughput": 786.59, "total_tokens": 11323952} {"current_steps": 34760, "total_steps": 40000, "loss": 0.2376, "lr": 2.0882249783690687e-06, "epoch": 28.445354072861235, "percentage": 86.9, "elapsed_time": "3:59:58", "remaining_time": "0:36:10", "throughput": 786.6, "total_tokens": 11325568} {"current_steps": 34765, "total_steps": 40000, "loss": 0.1686, "lr": 2.084298761571851e-06, "epoch": 28.449447400736798, "percentage": 86.91, "elapsed_time": "3:59:59", "remaining_time": "0:36:08", "throughput": 786.62, "total_tokens": 11327200} {"current_steps": 34770, "total_steps": 40000, "loss": 0.1743, "lr": 2.080376078663737e-06, "epoch": 28.45354072861236, "percentage": 86.92, "elapsed_time": "4:00:01", "remaining_time": "0:36:06", "throughput": 786.64, "total_tokens": 11328880} {"current_steps": 34775, "total_steps": 40000, "loss": 0.1203, "lr": 2.0764569302496593e-06, "epoch": 28.457634056487926, "percentage": 86.94, "elapsed_time": "4:00:03", "remaining_time": "0:36:04", "throughput": 786.66, "total_tokens": 11330496} {"current_steps": 34780, "total_steps": 40000, "loss": 0.1639, "lr": 2.0725413169339957e-06, "epoch": 28.46172738436349, "percentage": 86.95, "elapsed_time": "4:00:05", "remaining_time": "0:36:02", "throughput": 786.67, "total_tokens": 11332064} {"current_steps": 34785, "total_steps": 40000, "loss": 0.2092, "lr": 2.068629239320588e-06, "epoch": 28.46582071223905, "percentage": 86.96, "elapsed_time": "4:00:06", "remaining_time": "0:35:59", "throughput": 786.69, "total_tokens": 11333664} {"current_steps": 34790, "total_steps": 40000, "loss": 0.1271, "lr": 2.064720698012726e-06, "epoch": 28.469914040114613, "percentage": 86.98, "elapsed_time": "4:00:08", "remaining_time": "0:35:57", "throughput": 786.71, "total_tokens": 11335424} {"current_steps": 34795, "total_steps": 40000, "loss": 0.1429, "lr": 2.0608156936131522e-06, "epoch": 28.474007367990176, "percentage": 86.99, "elapsed_time": "4:00:10", "remaining_time": "0:35:55", "throughput": 786.74, "total_tokens": 11337120} {"current_steps": 34800, "total_steps": 40000, "loss": 0.105, "lr": 2.056914226724074e-06, "epoch": 28.478100695865738, "percentage": 87.0, "elapsed_time": "4:00:12", "remaining_time": "0:35:53", "throughput": 786.75, "total_tokens": 11338704} {"current_steps": 34800, "total_steps": 40000, "eval_loss": 0.21390025317668915, "epoch": 28.478100695865738, "percentage": 87.0, "elapsed_time": "4:00:24", "remaining_time": "0:35:55", "throughput": 786.07, "total_tokens": 11338704} {"current_steps": 34805, "total_steps": 40000, "loss": 0.1578, "lr": 2.0530162979471385e-06, "epoch": 28.4821940237413, "percentage": 87.01, "elapsed_time": "4:00:27", "remaining_time": "0:35:53", "throughput": 786.0, "total_tokens": 11340304} {"current_steps": 34810, "total_steps": 40000, "loss": 0.2051, "lr": 2.0491219078834667e-06, "epoch": 28.486287351616866, "percentage": 87.02, "elapsed_time": "4:00:29", "remaining_time": "0:35:51", "throughput": 786.02, "total_tokens": 11341936} {"current_steps": 34815, "total_steps": 40000, "loss": 0.2067, "lr": 2.045231057133612e-06, "epoch": 28.49038067949243, "percentage": 87.04, "elapsed_time": "4:00:31", "remaining_time": "0:35:49", "throughput": 786.03, "total_tokens": 11343552} {"current_steps": 34820, "total_steps": 40000, "loss": 0.1554, "lr": 2.0413437462975944e-06, "epoch": 28.49447400736799, "percentage": 87.05, "elapsed_time": "4:00:33", "remaining_time": "0:35:47", "throughput": 786.05, "total_tokens": 11345152} {"current_steps": 34825, "total_steps": 40000, "loss": 0.1538, "lr": 2.0374599759748843e-06, "epoch": 28.498567335243553, "percentage": 87.06, "elapsed_time": "4:00:34", "remaining_time": "0:35:45", "throughput": 786.07, "total_tokens": 11346768} {"current_steps": 34830, "total_steps": 40000, "loss": 0.193, "lr": 2.033579746764419e-06, "epoch": 28.502660663119116, "percentage": 87.08, "elapsed_time": "4:00:36", "remaining_time": "0:35:42", "throughput": 786.08, "total_tokens": 11348432} {"current_steps": 34835, "total_steps": 40000, "loss": 0.1462, "lr": 2.029703059264565e-06, "epoch": 28.506753990994678, "percentage": 87.09, "elapsed_time": "4:00:38", "remaining_time": "0:35:40", "throughput": 786.1, "total_tokens": 11350032} {"current_steps": 34840, "total_steps": 40000, "loss": 0.1815, "lr": 2.02582991407316e-06, "epoch": 28.51084731887024, "percentage": 87.1, "elapsed_time": "4:00:40", "remaining_time": "0:35:38", "throughput": 786.12, "total_tokens": 11351680} {"current_steps": 34845, "total_steps": 40000, "loss": 0.0733, "lr": 2.0219603117874992e-06, "epoch": 28.514940646745803, "percentage": 87.11, "elapsed_time": "4:00:41", "remaining_time": "0:35:36", "throughput": 786.14, "total_tokens": 11353408} {"current_steps": 34850, "total_steps": 40000, "loss": 0.1166, "lr": 2.0180942530043156e-06, "epoch": 28.51903397462137, "percentage": 87.12, "elapsed_time": "4:00:43", "remaining_time": "0:35:34", "throughput": 786.16, "total_tokens": 11354992} {"current_steps": 34855, "total_steps": 40000, "loss": 0.1946, "lr": 2.0142317383198107e-06, "epoch": 28.52312730249693, "percentage": 87.14, "elapsed_time": "4:00:45", "remaining_time": "0:35:32", "throughput": 786.18, "total_tokens": 11356704} {"current_steps": 34860, "total_steps": 40000, "loss": 0.1487, "lr": 2.0103727683296243e-06, "epoch": 28.527220630372494, "percentage": 87.15, "elapsed_time": "4:00:47", "remaining_time": "0:35:30", "throughput": 786.2, "total_tokens": 11358336} {"current_steps": 34865, "total_steps": 40000, "loss": 0.1889, "lr": 2.0065173436288636e-06, "epoch": 28.531313958248056, "percentage": 87.16, "elapsed_time": "4:00:48", "remaining_time": "0:35:28", "throughput": 786.22, "total_tokens": 11359952} {"current_steps": 34870, "total_steps": 40000, "loss": 0.1262, "lr": 2.002665464812087e-06, "epoch": 28.53540728612362, "percentage": 87.17, "elapsed_time": "4:00:50", "remaining_time": "0:35:25", "throughput": 786.24, "total_tokens": 11361584} {"current_steps": 34875, "total_steps": 40000, "loss": 0.0902, "lr": 1.998817132473291e-06, "epoch": 28.53950061399918, "percentage": 87.19, "elapsed_time": "4:00:52", "remaining_time": "0:35:23", "throughput": 786.26, "total_tokens": 11363216} {"current_steps": 34880, "total_steps": 40000, "loss": 0.1154, "lr": 1.9949723472059507e-06, "epoch": 28.543593941874743, "percentage": 87.2, "elapsed_time": "4:00:53", "remaining_time": "0:35:21", "throughput": 786.28, "total_tokens": 11364848} {"current_steps": 34885, "total_steps": 40000, "loss": 0.1899, "lr": 1.9911311096029726e-06, "epoch": 28.547687269750305, "percentage": 87.21, "elapsed_time": "4:00:55", "remaining_time": "0:35:19", "throughput": 786.3, "total_tokens": 11366576} {"current_steps": 34890, "total_steps": 40000, "loss": 0.1406, "lr": 1.9872934202567224e-06, "epoch": 28.55178059762587, "percentage": 87.22, "elapsed_time": "4:00:57", "remaining_time": "0:35:17", "throughput": 786.33, "total_tokens": 11368288} {"current_steps": 34895, "total_steps": 40000, "loss": 0.255, "lr": 1.9834592797590257e-06, "epoch": 28.555873925501434, "percentage": 87.24, "elapsed_time": "4:00:59", "remaining_time": "0:35:15", "throughput": 786.35, "total_tokens": 11369920} {"current_steps": 34900, "total_steps": 40000, "loss": 0.1618, "lr": 1.979628688701149e-06, "epoch": 28.559967253376996, "percentage": 87.25, "elapsed_time": "4:01:00", "remaining_time": "0:35:13", "throughput": 786.36, "total_tokens": 11371520} {"current_steps": 34905, "total_steps": 40000, "loss": 0.1247, "lr": 1.9758016476738193e-06, "epoch": 28.56406058125256, "percentage": 87.26, "elapsed_time": "4:01:02", "remaining_time": "0:35:11", "throughput": 786.38, "total_tokens": 11373136} {"current_steps": 34910, "total_steps": 40000, "loss": 0.2031, "lr": 1.971978157267221e-06, "epoch": 28.56815390912812, "percentage": 87.28, "elapsed_time": "4:01:04", "remaining_time": "0:35:08", "throughput": 786.4, "total_tokens": 11374752} {"current_steps": 34915, "total_steps": 40000, "loss": 0.2333, "lr": 1.968158218070973e-06, "epoch": 28.572247237003683, "percentage": 87.29, "elapsed_time": "4:01:06", "remaining_time": "0:35:06", "throughput": 786.42, "total_tokens": 11376304} {"current_steps": 34920, "total_steps": 40000, "loss": 0.2214, "lr": 1.9643418306741682e-06, "epoch": 28.576340564879246, "percentage": 87.3, "elapsed_time": "4:01:07", "remaining_time": "0:35:04", "throughput": 786.43, "total_tokens": 11377872} {"current_steps": 34925, "total_steps": 40000, "loss": 0.1404, "lr": 1.9605289956653337e-06, "epoch": 28.580433892754808, "percentage": 87.31, "elapsed_time": "4:01:09", "remaining_time": "0:35:02", "throughput": 786.45, "total_tokens": 11379504} {"current_steps": 34930, "total_steps": 40000, "loss": 0.2063, "lr": 1.9567197136324626e-06, "epoch": 28.584527220630374, "percentage": 87.33, "elapsed_time": "4:01:11", "remaining_time": "0:35:00", "throughput": 786.47, "total_tokens": 11381104} {"current_steps": 34935, "total_steps": 40000, "loss": 0.1647, "lr": 1.9529139851629935e-06, "epoch": 28.588620548505936, "percentage": 87.34, "elapsed_time": "4:01:12", "remaining_time": "0:34:58", "throughput": 786.49, "total_tokens": 11382720} {"current_steps": 34940, "total_steps": 40000, "loss": 0.1865, "lr": 1.949111810843812e-06, "epoch": 28.5927138763815, "percentage": 87.35, "elapsed_time": "4:01:14", "remaining_time": "0:34:56", "throughput": 786.51, "total_tokens": 11384400} {"current_steps": 34945, "total_steps": 40000, "loss": 0.297, "lr": 1.9453131912612694e-06, "epoch": 28.59680720425706, "percentage": 87.36, "elapsed_time": "4:01:16", "remaining_time": "0:34:54", "throughput": 786.53, "total_tokens": 11386064} {"current_steps": 34950, "total_steps": 40000, "loss": 0.1476, "lr": 1.941518127001149e-06, "epoch": 28.600900532132624, "percentage": 87.38, "elapsed_time": "4:01:18", "remaining_time": "0:34:51", "throughput": 786.55, "total_tokens": 11387744} {"current_steps": 34955, "total_steps": 40000, "loss": 0.332, "lr": 1.9377266186487107e-06, "epoch": 28.604993860008186, "percentage": 87.39, "elapsed_time": "4:01:19", "remaining_time": "0:34:49", "throughput": 786.57, "total_tokens": 11389424} {"current_steps": 34960, "total_steps": 40000, "loss": 0.1383, "lr": 1.9339386667886483e-06, "epoch": 28.60908718788375, "percentage": 87.4, "elapsed_time": "4:01:21", "remaining_time": "0:34:47", "throughput": 786.6, "total_tokens": 11391072} {"current_steps": 34965, "total_steps": 40000, "loss": 0.2282, "lr": 1.9301542720051024e-06, "epoch": 28.61318051575931, "percentage": 87.41, "elapsed_time": "4:01:23", "remaining_time": "0:34:45", "throughput": 786.61, "total_tokens": 11392672} {"current_steps": 34970, "total_steps": 40000, "loss": 0.1909, "lr": 1.926373434881684e-06, "epoch": 28.617273843634877, "percentage": 87.42, "elapsed_time": "4:01:24", "remaining_time": "0:34:43", "throughput": 786.64, "total_tokens": 11394352} {"current_steps": 34975, "total_steps": 40000, "loss": 0.1035, "lr": 1.9225961560014468e-06, "epoch": 28.62136717151044, "percentage": 87.44, "elapsed_time": "4:01:26", "remaining_time": "0:34:41", "throughput": 786.65, "total_tokens": 11395968} {"current_steps": 34980, "total_steps": 40000, "loss": 0.1412, "lr": 1.918822435946885e-06, "epoch": 28.625460499386, "percentage": 87.45, "elapsed_time": "4:01:28", "remaining_time": "0:34:39", "throughput": 786.68, "total_tokens": 11397680} {"current_steps": 34985, "total_steps": 40000, "loss": 0.1767, "lr": 1.915052275299961e-06, "epoch": 28.629553827261564, "percentage": 87.46, "elapsed_time": "4:01:30", "remaining_time": "0:34:37", "throughput": 786.7, "total_tokens": 11399344} {"current_steps": 34990, "total_steps": 40000, "loss": 0.2286, "lr": 1.9112856746420854e-06, "epoch": 28.633647155137126, "percentage": 87.48, "elapsed_time": "4:01:31", "remaining_time": "0:34:34", "throughput": 786.72, "total_tokens": 11401008} {"current_steps": 34995, "total_steps": 40000, "loss": 0.1782, "lr": 1.907522634554104e-06, "epoch": 28.63774048301269, "percentage": 87.49, "elapsed_time": "4:01:33", "remaining_time": "0:34:32", "throughput": 786.74, "total_tokens": 11402640} {"current_steps": 35000, "total_steps": 40000, "loss": 0.1332, "lr": 1.9037631556163337e-06, "epoch": 28.64183381088825, "percentage": 87.5, "elapsed_time": "4:01:35", "remaining_time": "0:34:30", "throughput": 786.76, "total_tokens": 11404240} {"current_steps": 35000, "total_steps": 40000, "eval_loss": 0.215963676571846, "epoch": 28.64183381088825, "percentage": 87.5, "elapsed_time": "4:01:47", "remaining_time": "0:34:32", "throughput": 786.08, "total_tokens": 11404240} {"current_steps": 35005, "total_steps": 40000, "loss": 0.1424, "lr": 1.9000072384085272e-06, "epoch": 28.645927138763817, "percentage": 87.51, "elapsed_time": "4:01:50", "remaining_time": "0:34:30", "throughput": 786.02, "total_tokens": 11405904} {"current_steps": 35010, "total_steps": 40000, "loss": 0.1108, "lr": 1.8962548835098987e-06, "epoch": 28.65002046663938, "percentage": 87.52, "elapsed_time": "4:01:52", "remaining_time": "0:34:28", "throughput": 786.04, "total_tokens": 11407520} {"current_steps": 35015, "total_steps": 40000, "loss": 0.185, "lr": 1.8925060914991077e-06, "epoch": 28.65411379451494, "percentage": 87.54, "elapsed_time": "4:01:54", "remaining_time": "0:34:26", "throughput": 786.05, "total_tokens": 11409104} {"current_steps": 35020, "total_steps": 40000, "loss": 0.1605, "lr": 1.888760862954264e-06, "epoch": 28.658207122390504, "percentage": 87.55, "elapsed_time": "4:01:56", "remaining_time": "0:34:24", "throughput": 786.07, "total_tokens": 11410688} {"current_steps": 35025, "total_steps": 40000, "loss": 0.2326, "lr": 1.8850191984529309e-06, "epoch": 28.662300450266066, "percentage": 87.56, "elapsed_time": "4:01:57", "remaining_time": "0:34:22", "throughput": 786.08, "total_tokens": 11412272} {"current_steps": 35030, "total_steps": 40000, "loss": 0.1668, "lr": 1.8812810985721186e-06, "epoch": 28.66639377814163, "percentage": 87.58, "elapsed_time": "4:01:59", "remaining_time": "0:34:20", "throughput": 786.1, "total_tokens": 11413888} {"current_steps": 35035, "total_steps": 40000, "loss": 0.2094, "lr": 1.8775465638882856e-06, "epoch": 28.67048710601719, "percentage": 87.59, "elapsed_time": "4:02:01", "remaining_time": "0:34:17", "throughput": 786.11, "total_tokens": 11415472} {"current_steps": 35040, "total_steps": 40000, "loss": 0.1696, "lr": 1.8738155949773517e-06, "epoch": 28.674580433892753, "percentage": 87.6, "elapsed_time": "4:02:03", "remaining_time": "0:34:15", "throughput": 786.13, "total_tokens": 11417072} {"current_steps": 35045, "total_steps": 40000, "loss": 0.2155, "lr": 1.8700881924146707e-06, "epoch": 28.678673761768316, "percentage": 87.61, "elapsed_time": "4:02:04", "remaining_time": "0:34:13", "throughput": 786.14, "total_tokens": 11418656} {"current_steps": 35050, "total_steps": 40000, "loss": 0.2235, "lr": 1.8663643567750577e-06, "epoch": 28.68276708964388, "percentage": 87.62, "elapsed_time": "4:02:06", "remaining_time": "0:34:11", "throughput": 786.16, "total_tokens": 11420368} {"current_steps": 35055, "total_steps": 40000, "loss": 0.1787, "lr": 1.8626440886327813e-06, "epoch": 28.686860417519444, "percentage": 87.64, "elapsed_time": "4:02:08", "remaining_time": "0:34:09", "throughput": 786.18, "total_tokens": 11421952} {"current_steps": 35060, "total_steps": 40000, "loss": 0.2921, "lr": 1.8589273885615432e-06, "epoch": 28.690953745395007, "percentage": 87.65, "elapsed_time": "4:02:10", "remaining_time": "0:34:07", "throughput": 786.19, "total_tokens": 11423584} {"current_steps": 35065, "total_steps": 40000, "loss": 0.2821, "lr": 1.8552142571345133e-06, "epoch": 28.69504707327057, "percentage": 87.66, "elapsed_time": "4:02:11", "remaining_time": "0:34:05", "throughput": 786.21, "total_tokens": 11425168} {"current_steps": 35070, "total_steps": 40000, "loss": 0.144, "lr": 1.8515046949243025e-06, "epoch": 28.69914040114613, "percentage": 87.67, "elapsed_time": "4:02:13", "remaining_time": "0:34:03", "throughput": 786.23, "total_tokens": 11426816} {"current_steps": 35075, "total_steps": 40000, "loss": 0.1533, "lr": 1.8477987025029674e-06, "epoch": 28.703233729021694, "percentage": 87.69, "elapsed_time": "4:02:15", "remaining_time": "0:34:00", "throughput": 786.25, "total_tokens": 11428496} {"current_steps": 35080, "total_steps": 40000, "loss": 0.1379, "lr": 1.8440962804420232e-06, "epoch": 28.707327056897256, "percentage": 87.7, "elapsed_time": "4:02:17", "remaining_time": "0:33:58", "throughput": 786.27, "total_tokens": 11430160} {"current_steps": 35085, "total_steps": 40000, "loss": 0.1466, "lr": 1.8403974293124265e-06, "epoch": 28.711420384772822, "percentage": 87.71, "elapsed_time": "4:02:18", "remaining_time": "0:33:56", "throughput": 786.28, "total_tokens": 11431760} {"current_steps": 35090, "total_steps": 40000, "loss": 0.1607, "lr": 1.8367021496845854e-06, "epoch": 28.715513712648384, "percentage": 87.72, "elapsed_time": "4:02:20", "remaining_time": "0:33:54", "throughput": 786.3, "total_tokens": 11433376} {"current_steps": 35095, "total_steps": 40000, "loss": 0.1694, "lr": 1.8330104421283662e-06, "epoch": 28.719607040523947, "percentage": 87.74, "elapsed_time": "4:02:22", "remaining_time": "0:33:52", "throughput": 786.32, "total_tokens": 11435008} {"current_steps": 35100, "total_steps": 40000, "loss": 0.2012, "lr": 1.8293223072130717e-06, "epoch": 28.72370036839951, "percentage": 87.75, "elapsed_time": "4:02:24", "remaining_time": "0:33:50", "throughput": 786.33, "total_tokens": 11436656} {"current_steps": 35105, "total_steps": 40000, "loss": 0.1996, "lr": 1.8256377455074525e-06, "epoch": 28.72779369627507, "percentage": 87.76, "elapsed_time": "4:02:26", "remaining_time": "0:33:48", "throughput": 786.35, "total_tokens": 11438272} {"current_steps": 35110, "total_steps": 40000, "loss": 0.192, "lr": 1.8219567575797263e-06, "epoch": 28.731887024150634, "percentage": 87.78, "elapsed_time": "4:02:27", "remaining_time": "0:33:46", "throughput": 786.37, "total_tokens": 11439888} {"current_steps": 35115, "total_steps": 40000, "loss": 0.1762, "lr": 1.8182793439975365e-06, "epoch": 28.735980352026196, "percentage": 87.79, "elapsed_time": "4:02:29", "remaining_time": "0:33:44", "throughput": 786.38, "total_tokens": 11441488} {"current_steps": 35120, "total_steps": 40000, "loss": 0.1203, "lr": 1.8146055053279958e-06, "epoch": 28.74007367990176, "percentage": 87.8, "elapsed_time": "4:02:31", "remaining_time": "0:33:41", "throughput": 786.4, "total_tokens": 11443184} {"current_steps": 35125, "total_steps": 40000, "loss": 0.2097, "lr": 1.8109352421376486e-06, "epoch": 28.744167007777325, "percentage": 87.81, "elapsed_time": "4:02:33", "remaining_time": "0:33:39", "throughput": 786.42, "total_tokens": 11444768} {"current_steps": 35130, "total_steps": 40000, "loss": 0.1479, "lr": 1.8072685549924972e-06, "epoch": 28.748260335652887, "percentage": 87.83, "elapsed_time": "4:02:34", "remaining_time": "0:33:37", "throughput": 786.43, "total_tokens": 11446368} {"current_steps": 35135, "total_steps": 40000, "loss": 0.2034, "lr": 1.8036054444579982e-06, "epoch": 28.75235366352845, "percentage": 87.84, "elapsed_time": "4:02:36", "remaining_time": "0:33:35", "throughput": 786.45, "total_tokens": 11447984} {"current_steps": 35140, "total_steps": 40000, "loss": 0.1643, "lr": 1.7999459110990407e-06, "epoch": 28.75644699140401, "percentage": 87.85, "elapsed_time": "4:02:38", "remaining_time": "0:33:33", "throughput": 786.47, "total_tokens": 11449648} {"current_steps": 35145, "total_steps": 40000, "loss": 0.1508, "lr": 1.7962899554799712e-06, "epoch": 28.760540319279574, "percentage": 87.86, "elapsed_time": "4:02:40", "remaining_time": "0:33:31", "throughput": 786.49, "total_tokens": 11451312} {"current_steps": 35150, "total_steps": 40000, "loss": 0.2138, "lr": 1.7926375781645937e-06, "epoch": 28.764633647155136, "percentage": 87.88, "elapsed_time": "4:02:41", "remaining_time": "0:33:29", "throughput": 786.5, "total_tokens": 11452864} {"current_steps": 35155, "total_steps": 40000, "loss": 0.132, "lr": 1.7889887797161359e-06, "epoch": 28.7687269750307, "percentage": 87.89, "elapsed_time": "4:02:43", "remaining_time": "0:33:27", "throughput": 786.51, "total_tokens": 11454464} {"current_steps": 35160, "total_steps": 40000, "loss": 0.1041, "lr": 1.7853435606973028e-06, "epoch": 28.77282030290626, "percentage": 87.9, "elapsed_time": "4:02:45", "remaining_time": "0:33:25", "throughput": 786.53, "total_tokens": 11456096} {"current_steps": 35165, "total_steps": 40000, "loss": 0.2113, "lr": 1.781701921670223e-06, "epoch": 28.776913630781827, "percentage": 87.91, "elapsed_time": "4:02:47", "remaining_time": "0:33:22", "throughput": 786.55, "total_tokens": 11457696} {"current_steps": 35170, "total_steps": 40000, "loss": 0.1383, "lr": 1.7780638631964886e-06, "epoch": 28.78100695865739, "percentage": 87.92, "elapsed_time": "4:02:48", "remaining_time": "0:33:20", "throughput": 786.56, "total_tokens": 11459328} {"current_steps": 35175, "total_steps": 40000, "loss": 0.165, "lr": 1.7744293858371314e-06, "epoch": 28.785100286532952, "percentage": 87.94, "elapsed_time": "4:02:50", "remaining_time": "0:33:18", "throughput": 786.58, "total_tokens": 11460944} {"current_steps": 35180, "total_steps": 40000, "loss": 0.1757, "lr": 1.770798490152631e-06, "epoch": 28.789193614408514, "percentage": 87.95, "elapsed_time": "4:02:52", "remaining_time": "0:33:16", "throughput": 786.6, "total_tokens": 11462576} {"current_steps": 35185, "total_steps": 40000, "loss": 0.1479, "lr": 1.767171176702917e-06, "epoch": 28.793286942284077, "percentage": 87.96, "elapsed_time": "4:02:54", "remaining_time": "0:33:14", "throughput": 786.62, "total_tokens": 11464224} {"current_steps": 35190, "total_steps": 40000, "loss": 0.1516, "lr": 1.7635474460473755e-06, "epoch": 28.79738027015964, "percentage": 87.98, "elapsed_time": "4:02:55", "remaining_time": "0:33:12", "throughput": 786.63, "total_tokens": 11465840} {"current_steps": 35195, "total_steps": 40000, "loss": 0.1996, "lr": 1.7599272987448206e-06, "epoch": 28.8014735980352, "percentage": 87.99, "elapsed_time": "4:02:57", "remaining_time": "0:33:10", "throughput": 786.65, "total_tokens": 11467456} {"current_steps": 35200, "total_steps": 40000, "loss": 0.12, "lr": 1.7563107353535362e-06, "epoch": 28.805566925910764, "percentage": 88.0, "elapsed_time": "4:02:59", "remaining_time": "0:33:08", "throughput": 786.66, "total_tokens": 11469056} {"current_steps": 35200, "total_steps": 40000, "eval_loss": 0.21415743231773376, "epoch": 28.805566925910764, "percentage": 88.0, "elapsed_time": "4:03:11", "remaining_time": "0:33:09", "throughput": 785.99, "total_tokens": 11469056} {"current_steps": 35205, "total_steps": 40000, "loss": 0.1513, "lr": 1.7526977564312263e-06, "epoch": 28.80966025378633, "percentage": 88.01, "elapsed_time": "4:03:15", "remaining_time": "0:33:07", "throughput": 785.92, "total_tokens": 11470672} {"current_steps": 35210, "total_steps": 40000, "loss": 0.1261, "lr": 1.7490883625350701e-06, "epoch": 28.813753581661892, "percentage": 88.02, "elapsed_time": "4:03:16", "remaining_time": "0:33:05", "throughput": 785.94, "total_tokens": 11472304} {"current_steps": 35215, "total_steps": 40000, "loss": 0.1429, "lr": 1.7454825542216807e-06, "epoch": 28.817846909537455, "percentage": 88.04, "elapsed_time": "4:03:18", "remaining_time": "0:33:03", "throughput": 785.96, "total_tokens": 11473952} {"current_steps": 35220, "total_steps": 40000, "loss": 0.1628, "lr": 1.7418803320471105e-06, "epoch": 28.821940237413017, "percentage": 88.05, "elapsed_time": "4:03:20", "remaining_time": "0:33:01", "throughput": 785.98, "total_tokens": 11475568} {"current_steps": 35225, "total_steps": 40000, "loss": 0.1079, "lr": 1.7382816965668737e-06, "epoch": 28.82603356528858, "percentage": 88.06, "elapsed_time": "4:03:22", "remaining_time": "0:32:59", "throughput": 786.0, "total_tokens": 11477168} {"current_steps": 35230, "total_steps": 40000, "loss": 0.1948, "lr": 1.7346866483359285e-06, "epoch": 28.83012689316414, "percentage": 88.08, "elapsed_time": "4:03:23", "remaining_time": "0:32:57", "throughput": 786.01, "total_tokens": 11478736} {"current_steps": 35235, "total_steps": 40000, "loss": 0.1568, "lr": 1.7310951879086657e-06, "epoch": 28.834220221039704, "percentage": 88.09, "elapsed_time": "4:03:25", "remaining_time": "0:32:55", "throughput": 786.03, "total_tokens": 11480384} {"current_steps": 35240, "total_steps": 40000, "loss": 0.1334, "lr": 1.7275073158389471e-06, "epoch": 28.838313548915266, "percentage": 88.1, "elapsed_time": "4:03:27", "remaining_time": "0:32:53", "throughput": 786.05, "total_tokens": 11482000} {"current_steps": 35245, "total_steps": 40000, "loss": 0.2082, "lr": 1.723923032680061e-06, "epoch": 28.842406876790832, "percentage": 88.11, "elapsed_time": "4:03:28", "remaining_time": "0:32:50", "throughput": 786.07, "total_tokens": 11483616} {"current_steps": 35250, "total_steps": 40000, "loss": 0.142, "lr": 1.7203423389847428e-06, "epoch": 28.846500204666395, "percentage": 88.12, "elapsed_time": "4:03:30", "remaining_time": "0:32:48", "throughput": 786.09, "total_tokens": 11485248} {"current_steps": 35255, "total_steps": 40000, "loss": 0.2036, "lr": 1.7167652353051928e-06, "epoch": 28.850593532541957, "percentage": 88.14, "elapsed_time": "4:03:32", "remaining_time": "0:32:46", "throughput": 786.11, "total_tokens": 11486880} {"current_steps": 35260, "total_steps": 40000, "loss": 0.2188, "lr": 1.7131917221930333e-06, "epoch": 28.85468686041752, "percentage": 88.15, "elapsed_time": "4:03:34", "remaining_time": "0:32:44", "throughput": 786.12, "total_tokens": 11488480} {"current_steps": 35265, "total_steps": 40000, "loss": 0.2584, "lr": 1.7096218001993513e-06, "epoch": 28.858780188293082, "percentage": 88.16, "elapsed_time": "4:03:35", "remaining_time": "0:32:42", "throughput": 786.14, "total_tokens": 11490112} {"current_steps": 35270, "total_steps": 40000, "loss": 0.1812, "lr": 1.706055469874676e-06, "epoch": 28.862873516168644, "percentage": 88.17, "elapsed_time": "4:03:37", "remaining_time": "0:32:40", "throughput": 786.16, "total_tokens": 11491664} {"current_steps": 35275, "total_steps": 40000, "loss": 0.1524, "lr": 1.702492731768976e-06, "epoch": 28.866966844044207, "percentage": 88.19, "elapsed_time": "4:03:39", "remaining_time": "0:32:38", "throughput": 786.17, "total_tokens": 11493200} {"current_steps": 35280, "total_steps": 40000, "loss": 0.2398, "lr": 1.6989335864316724e-06, "epoch": 28.871060171919773, "percentage": 88.2, "elapsed_time": "4:03:40", "remaining_time": "0:32:36", "throughput": 786.19, "total_tokens": 11494832} {"current_steps": 35285, "total_steps": 40000, "loss": 0.196, "lr": 1.6953780344116265e-06, "epoch": 28.875153499795335, "percentage": 88.21, "elapsed_time": "4:03:42", "remaining_time": "0:32:33", "throughput": 786.2, "total_tokens": 11496432} {"current_steps": 35290, "total_steps": 40000, "loss": 0.0875, "lr": 1.6918260762571497e-06, "epoch": 28.879246827670897, "percentage": 88.22, "elapsed_time": "4:03:44", "remaining_time": "0:32:31", "throughput": 786.23, "total_tokens": 11498128} {"current_steps": 35295, "total_steps": 40000, "loss": 0.1578, "lr": 1.6882777125160093e-06, "epoch": 28.88334015554646, "percentage": 88.24, "elapsed_time": "4:03:46", "remaining_time": "0:32:29", "throughput": 786.25, "total_tokens": 11499744} {"current_steps": 35300, "total_steps": 40000, "loss": 0.1596, "lr": 1.6847329437353899e-06, "epoch": 28.887433483422022, "percentage": 88.25, "elapsed_time": "4:03:47", "remaining_time": "0:32:27", "throughput": 786.27, "total_tokens": 11501504} {"current_steps": 35305, "total_steps": 40000, "loss": 0.1488, "lr": 1.6811917704619511e-06, "epoch": 28.891526811297584, "percentage": 88.26, "elapsed_time": "4:03:49", "remaining_time": "0:32:25", "throughput": 786.29, "total_tokens": 11503152} {"current_steps": 35310, "total_steps": 40000, "loss": 0.2073, "lr": 1.67765419324179e-06, "epoch": 28.895620139173147, "percentage": 88.28, "elapsed_time": "4:03:51", "remaining_time": "0:32:23", "throughput": 786.32, "total_tokens": 11504832} {"current_steps": 35315, "total_steps": 40000, "loss": 0.2834, "lr": 1.6741202126204364e-06, "epoch": 28.89971346704871, "percentage": 88.29, "elapsed_time": "4:03:53", "remaining_time": "0:32:21", "throughput": 786.33, "total_tokens": 11506464} {"current_steps": 35320, "total_steps": 40000, "loss": 0.1923, "lr": 1.6705898291428767e-06, "epoch": 28.90380679492427, "percentage": 88.3, "elapsed_time": "4:03:54", "remaining_time": "0:32:19", "throughput": 786.36, "total_tokens": 11508128} {"current_steps": 35325, "total_steps": 40000, "loss": 0.1346, "lr": 1.6670630433535395e-06, "epoch": 28.907900122799838, "percentage": 88.31, "elapsed_time": "4:03:56", "remaining_time": "0:32:17", "throughput": 786.38, "total_tokens": 11509840} {"current_steps": 35330, "total_steps": 40000, "loss": 0.1662, "lr": 1.6635398557962979e-06, "epoch": 28.9119934506754, "percentage": 88.33, "elapsed_time": "4:03:58", "remaining_time": "0:32:14", "throughput": 786.4, "total_tokens": 11511520} {"current_steps": 35335, "total_steps": 40000, "loss": 0.2361, "lr": 1.660020267014481e-06, "epoch": 28.916086778550962, "percentage": 88.34, "elapsed_time": "4:03:59", "remaining_time": "0:32:12", "throughput": 786.43, "total_tokens": 11513200} {"current_steps": 35340, "total_steps": 40000, "loss": 0.22, "lr": 1.6565042775508438e-06, "epoch": 28.920180106426525, "percentage": 88.35, "elapsed_time": "4:04:01", "remaining_time": "0:32:10", "throughput": 786.44, "total_tokens": 11514816} {"current_steps": 35345, "total_steps": 40000, "loss": 0.1618, "lr": 1.6529918879475997e-06, "epoch": 28.924273434302087, "percentage": 88.36, "elapsed_time": "4:04:03", "remaining_time": "0:32:08", "throughput": 786.46, "total_tokens": 11516432} {"current_steps": 35350, "total_steps": 40000, "loss": 0.1767, "lr": 1.6494830987464043e-06, "epoch": 28.92836676217765, "percentage": 88.38, "elapsed_time": "4:04:05", "remaining_time": "0:32:06", "throughput": 786.48, "total_tokens": 11518064} {"current_steps": 35355, "total_steps": 40000, "loss": 0.1615, "lr": 1.6459779104883555e-06, "epoch": 28.932460090053212, "percentage": 88.39, "elapsed_time": "4:04:06", "remaining_time": "0:32:04", "throughput": 786.5, "total_tokens": 11519664} {"current_steps": 35360, "total_steps": 40000, "loss": 0.1689, "lr": 1.6424763237140013e-06, "epoch": 28.936553417928778, "percentage": 88.4, "elapsed_time": "4:04:08", "remaining_time": "0:32:02", "throughput": 786.51, "total_tokens": 11521280} {"current_steps": 35365, "total_steps": 40000, "loss": 0.2069, "lr": 1.6389783389633207e-06, "epoch": 28.94064674580434, "percentage": 88.41, "elapsed_time": "4:04:10", "remaining_time": "0:32:00", "throughput": 786.53, "total_tokens": 11522896} {"current_steps": 35370, "total_steps": 40000, "loss": 0.1495, "lr": 1.6354839567757546e-06, "epoch": 28.944740073679903, "percentage": 88.42, "elapsed_time": "4:04:11", "remaining_time": "0:31:57", "throughput": 786.55, "total_tokens": 11524480} {"current_steps": 35375, "total_steps": 40000, "loss": 0.1099, "lr": 1.6319931776901831e-06, "epoch": 28.948833401555465, "percentage": 88.44, "elapsed_time": "4:04:13", "remaining_time": "0:31:55", "throughput": 786.57, "total_tokens": 11526160} {"current_steps": 35380, "total_steps": 40000, "loss": 0.1747, "lr": 1.6285060022449229e-06, "epoch": 28.952926729431027, "percentage": 88.45, "elapsed_time": "4:04:15", "remaining_time": "0:31:53", "throughput": 786.59, "total_tokens": 11527744} {"current_steps": 35385, "total_steps": 40000, "loss": 0.1921, "lr": 1.6250224309777434e-06, "epoch": 28.95702005730659, "percentage": 88.46, "elapsed_time": "4:04:17", "remaining_time": "0:31:51", "throughput": 786.61, "total_tokens": 11529408} {"current_steps": 35390, "total_steps": 40000, "loss": 0.1676, "lr": 1.6215424644258515e-06, "epoch": 28.961113385182152, "percentage": 88.48, "elapsed_time": "4:04:18", "remaining_time": "0:31:49", "throughput": 786.62, "total_tokens": 11530960} {"current_steps": 35395, "total_steps": 40000, "loss": 0.1498, "lr": 1.6180661031259036e-06, "epoch": 28.965206713057714, "percentage": 88.49, "elapsed_time": "4:04:20", "remaining_time": "0:31:47", "throughput": 786.64, "total_tokens": 11532624} {"current_steps": 35400, "total_steps": 40000, "loss": 0.1864, "lr": 1.614593347613999e-06, "epoch": 28.96930004093328, "percentage": 88.5, "elapsed_time": "4:04:22", "remaining_time": "0:31:45", "throughput": 786.66, "total_tokens": 11534288} {"current_steps": 35400, "total_steps": 40000, "eval_loss": 0.21412159502506256, "epoch": 28.96930004093328, "percentage": 88.5, "elapsed_time": "4:04:34", "remaining_time": "0:31:46", "throughput": 786.0, "total_tokens": 11534288} {"current_steps": 35405, "total_steps": 40000, "loss": 0.2211, "lr": 1.6111241984256758e-06, "epoch": 28.973393368808843, "percentage": 88.51, "elapsed_time": "4:04:38", "remaining_time": "0:31:44", "throughput": 785.93, "total_tokens": 11535904} {"current_steps": 35410, "total_steps": 40000, "loss": 0.1409, "lr": 1.6076586560959257e-06, "epoch": 28.977486696684405, "percentage": 88.52, "elapsed_time": "4:04:39", "remaining_time": "0:31:42", "throughput": 785.94, "total_tokens": 11537456} {"current_steps": 35415, "total_steps": 40000, "loss": 0.0829, "lr": 1.604196721159182e-06, "epoch": 28.981580024559968, "percentage": 88.54, "elapsed_time": "4:04:41", "remaining_time": "0:31:40", "throughput": 785.96, "total_tokens": 11539040} {"current_steps": 35420, "total_steps": 40000, "loss": 0.1312, "lr": 1.6007383941493092e-06, "epoch": 28.98567335243553, "percentage": 88.55, "elapsed_time": "4:04:43", "remaining_time": "0:31:38", "throughput": 785.98, "total_tokens": 11540704} {"current_steps": 35425, "total_steps": 40000, "loss": 0.2067, "lr": 1.5972836755996285e-06, "epoch": 28.989766680311092, "percentage": 88.56, "elapsed_time": "4:04:44", "remaining_time": "0:31:36", "throughput": 786.0, "total_tokens": 11542336} {"current_steps": 35430, "total_steps": 40000, "loss": 0.1789, "lr": 1.5938325660429076e-06, "epoch": 28.993860008186655, "percentage": 88.58, "elapsed_time": "4:04:46", "remaining_time": "0:31:34", "throughput": 786.02, "total_tokens": 11544000} {"current_steps": 35435, "total_steps": 40000, "loss": 0.2648, "lr": 1.5903850660113378e-06, "epoch": 28.997953336062217, "percentage": 88.59, "elapsed_time": "4:04:48", "remaining_time": "0:31:32", "throughput": 786.04, "total_tokens": 11545664} {"current_steps": 35440, "total_steps": 40000, "loss": 0.1806, "lr": 1.5869411760365826e-06, "epoch": 29.001637331150224, "percentage": 88.6, "elapsed_time": "4:04:50", "remaining_time": "0:31:30", "throughput": 786.04, "total_tokens": 11547104} {"current_steps": 35445, "total_steps": 40000, "loss": 0.1071, "lr": 1.58350089664972e-06, "epoch": 29.005730659025787, "percentage": 88.61, "elapsed_time": "4:04:51", "remaining_time": "0:31:28", "throughput": 786.06, "total_tokens": 11548704} {"current_steps": 35450, "total_steps": 40000, "loss": 0.2086, "lr": 1.5800642283812865e-06, "epoch": 29.009823986901353, "percentage": 88.62, "elapsed_time": "4:04:53", "remaining_time": "0:31:25", "throughput": 786.07, "total_tokens": 11550320} {"current_steps": 35455, "total_steps": 40000, "loss": 0.076, "lr": 1.5766311717612698e-06, "epoch": 29.013917314776915, "percentage": 88.64, "elapsed_time": "4:04:55", "remaining_time": "0:31:23", "throughput": 786.09, "total_tokens": 11551936} {"current_steps": 35460, "total_steps": 40000, "loss": 0.2125, "lr": 1.5732017273190818e-06, "epoch": 29.018010642652477, "percentage": 88.65, "elapsed_time": "4:04:57", "remaining_time": "0:31:21", "throughput": 786.11, "total_tokens": 11553488} {"current_steps": 35465, "total_steps": 40000, "loss": 0.1797, "lr": 1.5697758955835806e-06, "epoch": 29.02210397052804, "percentage": 88.66, "elapsed_time": "4:04:58", "remaining_time": "0:31:19", "throughput": 786.13, "total_tokens": 11555120} {"current_steps": 35470, "total_steps": 40000, "loss": 0.1458, "lr": 1.566353677083085e-06, "epoch": 29.026197298403602, "percentage": 88.67, "elapsed_time": "4:05:00", "remaining_time": "0:31:17", "throughput": 786.14, "total_tokens": 11556752} {"current_steps": 35475, "total_steps": 40000, "loss": 0.1987, "lr": 1.562935072345334e-06, "epoch": 29.030290626279164, "percentage": 88.69, "elapsed_time": "4:05:02", "remaining_time": "0:31:15", "throughput": 786.16, "total_tokens": 11558352} {"current_steps": 35480, "total_steps": 40000, "loss": 0.1178, "lr": 1.5595200818975281e-06, "epoch": 29.034383954154727, "percentage": 88.7, "elapsed_time": "4:05:04", "remaining_time": "0:31:13", "throughput": 786.17, "total_tokens": 11559952} {"current_steps": 35485, "total_steps": 40000, "loss": 0.198, "lr": 1.5561087062662905e-06, "epoch": 29.03847728203029, "percentage": 88.71, "elapsed_time": "4:05:05", "remaining_time": "0:31:11", "throughput": 786.19, "total_tokens": 11561648} {"current_steps": 35490, "total_steps": 40000, "loss": 0.113, "lr": 1.5527009459777087e-06, "epoch": 29.042570609905855, "percentage": 88.72, "elapsed_time": "4:05:07", "remaining_time": "0:31:09", "throughput": 786.21, "total_tokens": 11563248} {"current_steps": 35495, "total_steps": 40000, "loss": 0.1571, "lr": 1.5492968015572984e-06, "epoch": 29.046663937781418, "percentage": 88.74, "elapsed_time": "4:05:09", "remaining_time": "0:31:06", "throughput": 786.23, "total_tokens": 11564912} {"current_steps": 35500, "total_steps": 40000, "loss": 0.1542, "lr": 1.5458962735300203e-06, "epoch": 29.05075726565698, "percentage": 88.75, "elapsed_time": "4:05:11", "remaining_time": "0:31:04", "throughput": 786.24, "total_tokens": 11566512} {"current_steps": 35505, "total_steps": 40000, "loss": 0.1817, "lr": 1.54249936242028e-06, "epoch": 29.054850593532542, "percentage": 88.76, "elapsed_time": "4:05:12", "remaining_time": "0:31:02", "throughput": 786.26, "total_tokens": 11568144} {"current_steps": 35510, "total_steps": 40000, "loss": 0.2362, "lr": 1.5391060687519222e-06, "epoch": 29.058943921408105, "percentage": 88.78, "elapsed_time": "4:05:14", "remaining_time": "0:31:00", "throughput": 786.28, "total_tokens": 11569840} {"current_steps": 35515, "total_steps": 40000, "loss": 0.1009, "lr": 1.5357163930482367e-06, "epoch": 29.063037249283667, "percentage": 88.79, "elapsed_time": "4:05:16", "remaining_time": "0:30:58", "throughput": 786.3, "total_tokens": 11571552} {"current_steps": 35520, "total_steps": 40000, "loss": 0.2301, "lr": 1.532330335831955e-06, "epoch": 29.06713057715923, "percentage": 88.8, "elapsed_time": "4:05:18", "remaining_time": "0:30:56", "throughput": 786.32, "total_tokens": 11573120} {"current_steps": 35525, "total_steps": 40000, "loss": 0.1482, "lr": 1.5289478976252491e-06, "epoch": 29.071223905034792, "percentage": 88.81, "elapsed_time": "4:05:19", "remaining_time": "0:30:54", "throughput": 786.33, "total_tokens": 11574736} {"current_steps": 35530, "total_steps": 40000, "loss": 0.0863, "lr": 1.5255690789497345e-06, "epoch": 29.075317232910358, "percentage": 88.83, "elapsed_time": "4:05:21", "remaining_time": "0:30:52", "throughput": 786.35, "total_tokens": 11576320} {"current_steps": 35535, "total_steps": 40000, "loss": 0.1504, "lr": 1.5221938803264641e-06, "epoch": 29.07941056078592, "percentage": 88.84, "elapsed_time": "4:05:23", "remaining_time": "0:30:50", "throughput": 786.36, "total_tokens": 11577936} {"current_steps": 35540, "total_steps": 40000, "loss": 0.1097, "lr": 1.518822302275938e-06, "epoch": 29.083503888661483, "percentage": 88.85, "elapsed_time": "4:05:25", "remaining_time": "0:30:47", "throughput": 786.38, "total_tokens": 11579520} {"current_steps": 35545, "total_steps": 40000, "loss": 0.196, "lr": 1.5154543453180958e-06, "epoch": 29.087597216537045, "percentage": 88.86, "elapsed_time": "4:05:26", "remaining_time": "0:30:45", "throughput": 786.4, "total_tokens": 11581200} {"current_steps": 35550, "total_steps": 40000, "loss": 0.2277, "lr": 1.5120900099723167e-06, "epoch": 29.091690544412607, "percentage": 88.88, "elapsed_time": "4:05:28", "remaining_time": "0:30:43", "throughput": 786.41, "total_tokens": 11582832} {"current_steps": 35555, "total_steps": 40000, "loss": 0.1339, "lr": 1.5087292967574273e-06, "epoch": 29.09578387228817, "percentage": 88.89, "elapsed_time": "4:05:30", "remaining_time": "0:30:41", "throughput": 786.43, "total_tokens": 11584448} {"current_steps": 35560, "total_steps": 40000, "loss": 0.2008, "lr": 1.5053722061916908e-06, "epoch": 29.099877200163732, "percentage": 88.9, "elapsed_time": "4:05:32", "remaining_time": "0:30:39", "throughput": 786.45, "total_tokens": 11586112} {"current_steps": 35565, "total_steps": 40000, "loss": 0.1284, "lr": 1.5020187387928124e-06, "epoch": 29.103970528039294, "percentage": 88.91, "elapsed_time": "4:05:33", "remaining_time": "0:30:37", "throughput": 786.46, "total_tokens": 11587728} {"current_steps": 35570, "total_steps": 40000, "loss": 0.2561, "lr": 1.4986688950779343e-06, "epoch": 29.10806385591486, "percentage": 88.92, "elapsed_time": "4:05:35", "remaining_time": "0:30:35", "throughput": 786.48, "total_tokens": 11589360} {"current_steps": 35575, "total_steps": 40000, "loss": 0.2504, "lr": 1.495322675563654e-06, "epoch": 29.112157183790423, "percentage": 88.94, "elapsed_time": "4:05:37", "remaining_time": "0:30:33", "throughput": 786.5, "total_tokens": 11590976} {"current_steps": 35580, "total_steps": 40000, "loss": 0.151, "lr": 1.4919800807659922e-06, "epoch": 29.116250511665985, "percentage": 88.95, "elapsed_time": "4:05:39", "remaining_time": "0:30:31", "throughput": 786.52, "total_tokens": 11592640} {"current_steps": 35585, "total_steps": 40000, "loss": 0.2113, "lr": 1.4886411112004255e-06, "epoch": 29.120343839541547, "percentage": 88.96, "elapsed_time": "4:05:40", "remaining_time": "0:30:28", "throughput": 786.53, "total_tokens": 11594272} {"current_steps": 35590, "total_steps": 40000, "loss": 0.2969, "lr": 1.4853057673818588e-06, "epoch": 29.12443716741711, "percentage": 88.98, "elapsed_time": "4:05:42", "remaining_time": "0:30:26", "throughput": 786.55, "total_tokens": 11595888} {"current_steps": 35595, "total_steps": 40000, "loss": 0.2756, "lr": 1.481974049824647e-06, "epoch": 29.128530495292672, "percentage": 88.99, "elapsed_time": "4:05:44", "remaining_time": "0:30:24", "throughput": 786.57, "total_tokens": 11597568} {"current_steps": 35600, "total_steps": 40000, "loss": 0.1407, "lr": 1.4786459590425849e-06, "epoch": 29.132623823168235, "percentage": 89.0, "elapsed_time": "4:05:46", "remaining_time": "0:30:22", "throughput": 786.59, "total_tokens": 11599248} {"current_steps": 35600, "total_steps": 40000, "eval_loss": 0.2156042605638504, "epoch": 29.132623823168235, "percentage": 89.0, "elapsed_time": "4:05:58", "remaining_time": "0:30:24", "throughput": 785.93, "total_tokens": 11599248} {"current_steps": 35605, "total_steps": 40000, "loss": 0.2111, "lr": 1.4753214955489036e-06, "epoch": 29.136717151043797, "percentage": 89.01, "elapsed_time": "4:06:02", "remaining_time": "0:30:22", "throughput": 785.86, "total_tokens": 11600864} {"current_steps": 35610, "total_steps": 40000, "loss": 0.1679, "lr": 1.4720006598562737e-06, "epoch": 29.140810478919363, "percentage": 89.03, "elapsed_time": "4:06:03", "remaining_time": "0:30:20", "throughput": 785.87, "total_tokens": 11602448} {"current_steps": 35615, "total_steps": 40000, "loss": 0.1863, "lr": 1.4686834524768185e-06, "epoch": 29.144903806794925, "percentage": 89.04, "elapsed_time": "4:06:05", "remaining_time": "0:30:17", "throughput": 785.89, "total_tokens": 11604096} {"current_steps": 35620, "total_steps": 40000, "loss": 0.1723, "lr": 1.4653698739220844e-06, "epoch": 29.148997134670488, "percentage": 89.05, "elapsed_time": "4:06:07", "remaining_time": "0:30:15", "throughput": 785.91, "total_tokens": 11605744} {"current_steps": 35625, "total_steps": 40000, "loss": 0.2278, "lr": 1.4620599247030715e-06, "epoch": 29.15309046254605, "percentage": 89.06, "elapsed_time": "4:06:09", "remaining_time": "0:30:13", "throughput": 785.93, "total_tokens": 11607360} {"current_steps": 35630, "total_steps": 40000, "loss": 0.1051, "lr": 1.4587536053302125e-06, "epoch": 29.157183790421612, "percentage": 89.08, "elapsed_time": "4:06:10", "remaining_time": "0:30:11", "throughput": 785.94, "total_tokens": 11608928} {"current_steps": 35635, "total_steps": 40000, "loss": 0.1302, "lr": 1.4554509163133862e-06, "epoch": 29.161277118297175, "percentage": 89.09, "elapsed_time": "4:06:12", "remaining_time": "0:30:09", "throughput": 785.96, "total_tokens": 11610544} {"current_steps": 35640, "total_steps": 40000, "loss": 0.1913, "lr": 1.4521518581619098e-06, "epoch": 29.165370446172737, "percentage": 89.1, "elapsed_time": "4:06:14", "remaining_time": "0:30:07", "throughput": 785.98, "total_tokens": 11612224} {"current_steps": 35645, "total_steps": 40000, "loss": 0.1458, "lr": 1.4488564313845348e-06, "epoch": 29.1694637740483, "percentage": 89.11, "elapsed_time": "4:06:16", "remaining_time": "0:30:05", "throughput": 785.99, "total_tokens": 11613872} {"current_steps": 35650, "total_steps": 40000, "loss": 0.1541, "lr": 1.4455646364894603e-06, "epoch": 29.173557101923866, "percentage": 89.12, "elapsed_time": "4:06:17", "remaining_time": "0:30:03", "throughput": 786.01, "total_tokens": 11615472} {"current_steps": 35655, "total_steps": 40000, "loss": 0.1321, "lr": 1.4422764739843247e-06, "epoch": 29.177650429799428, "percentage": 89.14, "elapsed_time": "4:06:19", "remaining_time": "0:30:01", "throughput": 786.03, "total_tokens": 11617232} {"current_steps": 35660, "total_steps": 40000, "loss": 0.1597, "lr": 1.4389919443762e-06, "epoch": 29.18174375767499, "percentage": 89.15, "elapsed_time": "4:06:21", "remaining_time": "0:29:58", "throughput": 786.05, "total_tokens": 11618864} {"current_steps": 35665, "total_steps": 40000, "loss": 0.2102, "lr": 1.4357110481716063e-06, "epoch": 29.185837085550553, "percentage": 89.16, "elapsed_time": "4:06:23", "remaining_time": "0:29:56", "throughput": 786.07, "total_tokens": 11620544} {"current_steps": 35670, "total_steps": 40000, "loss": 0.1474, "lr": 1.4324337858764941e-06, "epoch": 29.189930413426115, "percentage": 89.18, "elapsed_time": "4:06:24", "remaining_time": "0:29:54", "throughput": 786.09, "total_tokens": 11622128} {"current_steps": 35675, "total_steps": 40000, "loss": 0.1263, "lr": 1.4291601579962622e-06, "epoch": 29.194023741301677, "percentage": 89.19, "elapsed_time": "4:06:26", "remaining_time": "0:29:52", "throughput": 786.1, "total_tokens": 11623712} {"current_steps": 35680, "total_steps": 40000, "loss": 0.2195, "lr": 1.42589016503574e-06, "epoch": 29.19811706917724, "percentage": 89.2, "elapsed_time": "4:06:28", "remaining_time": "0:29:50", "throughput": 786.12, "total_tokens": 11625360} {"current_steps": 35685, "total_steps": 40000, "loss": 0.1379, "lr": 1.4226238074992099e-06, "epoch": 29.202210397052802, "percentage": 89.21, "elapsed_time": "4:06:30", "remaining_time": "0:29:48", "throughput": 786.14, "total_tokens": 11627040} {"current_steps": 35690, "total_steps": 40000, "loss": 0.2867, "lr": 1.4193610858903778e-06, "epoch": 29.206303724928368, "percentage": 89.22, "elapsed_time": "4:06:31", "remaining_time": "0:29:46", "throughput": 786.16, "total_tokens": 11628688} {"current_steps": 35695, "total_steps": 40000, "loss": 0.1007, "lr": 1.416102000712402e-06, "epoch": 29.21039705280393, "percentage": 89.24, "elapsed_time": "4:06:33", "remaining_time": "0:29:44", "throughput": 786.17, "total_tokens": 11630256} {"current_steps": 35700, "total_steps": 40000, "loss": 0.1905, "lr": 1.4128465524678668e-06, "epoch": 29.214490380679493, "percentage": 89.25, "elapsed_time": "4:06:35", "remaining_time": "0:29:42", "throughput": 786.18, "total_tokens": 11631856} {"current_steps": 35705, "total_steps": 40000, "loss": 0.2023, "lr": 1.4095947416588124e-06, "epoch": 29.218583708555055, "percentage": 89.26, "elapsed_time": "4:06:37", "remaining_time": "0:29:39", "throughput": 786.2, "total_tokens": 11633520} {"current_steps": 35710, "total_steps": 40000, "loss": 0.1703, "lr": 1.4063465687866983e-06, "epoch": 29.222677036430618, "percentage": 89.28, "elapsed_time": "4:06:38", "remaining_time": "0:29:37", "throughput": 786.22, "total_tokens": 11635152} {"current_steps": 35715, "total_steps": 40000, "loss": 0.2888, "lr": 1.4031020343524438e-06, "epoch": 29.22677036430618, "percentage": 89.29, "elapsed_time": "4:06:40", "remaining_time": "0:29:35", "throughput": 786.24, "total_tokens": 11636784} {"current_steps": 35720, "total_steps": 40000, "loss": 0.1922, "lr": 1.3998611388563926e-06, "epoch": 29.230863692181742, "percentage": 89.3, "elapsed_time": "4:06:42", "remaining_time": "0:29:33", "throughput": 786.26, "total_tokens": 11638432} {"current_steps": 35725, "total_steps": 40000, "loss": 0.197, "lr": 1.3966238827983314e-06, "epoch": 29.23495702005731, "percentage": 89.31, "elapsed_time": "4:06:44", "remaining_time": "0:29:31", "throughput": 786.27, "total_tokens": 11640000} {"current_steps": 35730, "total_steps": 40000, "loss": 0.2161, "lr": 1.393390266677483e-06, "epoch": 29.23905034793287, "percentage": 89.33, "elapsed_time": "4:06:45", "remaining_time": "0:29:29", "throughput": 786.29, "total_tokens": 11641648} {"current_steps": 35735, "total_steps": 40000, "loss": 0.2884, "lr": 1.3901602909925204e-06, "epoch": 29.243143675808433, "percentage": 89.34, "elapsed_time": "4:06:47", "remaining_time": "0:29:27", "throughput": 786.3, "total_tokens": 11643232} {"current_steps": 35740, "total_steps": 40000, "loss": 0.1308, "lr": 1.3869339562415373e-06, "epoch": 29.247237003683995, "percentage": 89.35, "elapsed_time": "4:06:49", "remaining_time": "0:29:25", "throughput": 786.31, "total_tokens": 11644784} {"current_steps": 35745, "total_steps": 40000, "loss": 0.2295, "lr": 1.38371126292208e-06, "epoch": 29.251330331559558, "percentage": 89.36, "elapsed_time": "4:06:51", "remaining_time": "0:29:23", "throughput": 786.33, "total_tokens": 11646416} {"current_steps": 35750, "total_steps": 40000, "loss": 0.1632, "lr": 1.3804922115311286e-06, "epoch": 29.25542365943512, "percentage": 89.38, "elapsed_time": "4:06:52", "remaining_time": "0:29:20", "throughput": 786.35, "total_tokens": 11648112} {"current_steps": 35755, "total_steps": 40000, "loss": 0.1614, "lr": 1.3772768025650945e-06, "epoch": 29.259516987310683, "percentage": 89.39, "elapsed_time": "4:06:54", "remaining_time": "0:29:18", "throughput": 786.36, "total_tokens": 11649712} {"current_steps": 35760, "total_steps": 40000, "loss": 0.1241, "lr": 1.3740650365198448e-06, "epoch": 29.263610315186245, "percentage": 89.4, "elapsed_time": "4:06:56", "remaining_time": "0:29:16", "throughput": 786.38, "total_tokens": 11651344} {"current_steps": 35765, "total_steps": 40000, "loss": 0.2239, "lr": 1.3708569138906612e-06, "epoch": 29.26770364306181, "percentage": 89.41, "elapsed_time": "4:06:58", "remaining_time": "0:29:14", "throughput": 786.4, "total_tokens": 11653008} {"current_steps": 35770, "total_steps": 40000, "loss": 0.103, "lr": 1.367652435172287e-06, "epoch": 29.271796970937373, "percentage": 89.42, "elapsed_time": "4:06:59", "remaining_time": "0:29:12", "throughput": 786.42, "total_tokens": 11654672} {"current_steps": 35775, "total_steps": 40000, "loss": 0.159, "lr": 1.364451600858893e-06, "epoch": 29.275890298812936, "percentage": 89.44, "elapsed_time": "4:07:01", "remaining_time": "0:29:10", "throughput": 786.43, "total_tokens": 11656256} {"current_steps": 35780, "total_steps": 40000, "loss": 0.211, "lr": 1.3612544114440823e-06, "epoch": 29.279983626688498, "percentage": 89.45, "elapsed_time": "4:07:03", "remaining_time": "0:29:08", "throughput": 786.45, "total_tokens": 11657920} {"current_steps": 35785, "total_steps": 40000, "loss": 0.1318, "lr": 1.3580608674209072e-06, "epoch": 29.28407695456406, "percentage": 89.46, "elapsed_time": "4:07:05", "remaining_time": "0:29:06", "throughput": 786.47, "total_tokens": 11659568} {"current_steps": 35790, "total_steps": 40000, "loss": 0.166, "lr": 1.3548709692818434e-06, "epoch": 29.288170282439623, "percentage": 89.48, "elapsed_time": "4:07:06", "remaining_time": "0:29:04", "throughput": 786.49, "total_tokens": 11661200} {"current_steps": 35795, "total_steps": 40000, "loss": 0.1467, "lr": 1.3516847175188223e-06, "epoch": 29.292263610315185, "percentage": 89.49, "elapsed_time": "4:07:08", "remaining_time": "0:29:01", "throughput": 786.51, "total_tokens": 11662880} {"current_steps": 35800, "total_steps": 40000, "loss": 0.2872, "lr": 1.348502112623204e-06, "epoch": 29.296356938190748, "percentage": 89.5, "elapsed_time": "4:07:10", "remaining_time": "0:28:59", "throughput": 786.53, "total_tokens": 11664528} {"current_steps": 35800, "total_steps": 40000, "eval_loss": 0.2146545648574829, "epoch": 29.296356938190748, "percentage": 89.5, "elapsed_time": "4:07:22", "remaining_time": "0:29:01", "throughput": 785.87, "total_tokens": 11664528} {"current_steps": 35805, "total_steps": 40000, "loss": 0.1721, "lr": 1.3453231550857787e-06, "epoch": 29.300450266066314, "percentage": 89.51, "elapsed_time": "4:07:26", "remaining_time": "0:28:59", "throughput": 785.8, "total_tokens": 11666176} {"current_steps": 35810, "total_steps": 40000, "loss": 0.2285, "lr": 1.3421478453967878e-06, "epoch": 29.304543593941876, "percentage": 89.53, "elapsed_time": "4:07:27", "remaining_time": "0:28:57", "throughput": 785.82, "total_tokens": 11667824} {"current_steps": 35815, "total_steps": 40000, "loss": 0.3126, "lr": 1.3389761840459065e-06, "epoch": 29.30863692181744, "percentage": 89.54, "elapsed_time": "4:07:29", "remaining_time": "0:28:55", "throughput": 785.84, "total_tokens": 11669408} {"current_steps": 35820, "total_steps": 40000, "loss": 0.1485, "lr": 1.3358081715222376e-06, "epoch": 29.312730249693, "percentage": 89.55, "elapsed_time": "4:07:31", "remaining_time": "0:28:53", "throughput": 785.86, "total_tokens": 11671008} {"current_steps": 35825, "total_steps": 40000, "loss": 0.292, "lr": 1.3326438083143295e-06, "epoch": 29.316823577568563, "percentage": 89.56, "elapsed_time": "4:07:33", "remaining_time": "0:28:50", "throughput": 785.88, "total_tokens": 11672672} {"current_steps": 35830, "total_steps": 40000, "loss": 0.1639, "lr": 1.3294830949101723e-06, "epoch": 29.320916905444125, "percentage": 89.58, "elapsed_time": "4:07:34", "remaining_time": "0:28:48", "throughput": 785.89, "total_tokens": 11674272} {"current_steps": 35835, "total_steps": 40000, "loss": 0.1694, "lr": 1.3263260317971815e-06, "epoch": 29.325010233319688, "percentage": 89.59, "elapsed_time": "4:07:36", "remaining_time": "0:28:46", "throughput": 785.92, "total_tokens": 11675952} {"current_steps": 35840, "total_steps": 40000, "loss": 0.1632, "lr": 1.3231726194622208e-06, "epoch": 29.32910356119525, "percentage": 89.6, "elapsed_time": "4:07:38", "remaining_time": "0:28:44", "throughput": 785.93, "total_tokens": 11677568} {"current_steps": 35845, "total_steps": 40000, "loss": 0.1993, "lr": 1.3200228583915814e-06, "epoch": 29.333196889070816, "percentage": 89.61, "elapsed_time": "4:07:39", "remaining_time": "0:28:42", "throughput": 785.96, "total_tokens": 11679280} {"current_steps": 35850, "total_steps": 40000, "loss": 0.1648, "lr": 1.3168767490709971e-06, "epoch": 29.33729021694638, "percentage": 89.62, "elapsed_time": "4:07:41", "remaining_time": "0:28:40", "throughput": 785.97, "total_tokens": 11680848} {"current_steps": 35855, "total_steps": 40000, "loss": 0.1817, "lr": 1.3137342919856437e-06, "epoch": 29.34138354482194, "percentage": 89.64, "elapsed_time": "4:07:43", "remaining_time": "0:28:38", "throughput": 785.99, "total_tokens": 11682448} {"current_steps": 35860, "total_steps": 40000, "loss": 0.1305, "lr": 1.310595487620117e-06, "epoch": 29.345476872697503, "percentage": 89.65, "elapsed_time": "4:07:45", "remaining_time": "0:28:36", "throughput": 786.01, "total_tokens": 11684080} {"current_steps": 35865, "total_steps": 40000, "loss": 0.1673, "lr": 1.3074603364584715e-06, "epoch": 29.349570200573066, "percentage": 89.66, "elapsed_time": "4:07:46", "remaining_time": "0:28:34", "throughput": 786.03, "total_tokens": 11685760} {"current_steps": 35870, "total_steps": 40000, "loss": 0.1182, "lr": 1.3043288389841758e-06, "epoch": 29.353663528448628, "percentage": 89.68, "elapsed_time": "4:07:48", "remaining_time": "0:28:31", "throughput": 786.05, "total_tokens": 11687456} {"current_steps": 35875, "total_steps": 40000, "loss": 0.1243, "lr": 1.3012009956801546e-06, "epoch": 29.35775685632419, "percentage": 89.69, "elapsed_time": "4:07:50", "remaining_time": "0:28:29", "throughput": 786.07, "total_tokens": 11689072} {"current_steps": 35880, "total_steps": 40000, "loss": 0.1232, "lr": 1.2980768070287586e-06, "epoch": 29.361850184199753, "percentage": 89.7, "elapsed_time": "4:07:52", "remaining_time": "0:28:27", "throughput": 786.09, "total_tokens": 11690672} {"current_steps": 35885, "total_steps": 40000, "loss": 0.1261, "lr": 1.2949562735117716e-06, "epoch": 29.36594351207532, "percentage": 89.71, "elapsed_time": "4:07:53", "remaining_time": "0:28:25", "throughput": 786.1, "total_tokens": 11692304} {"current_steps": 35890, "total_steps": 40000, "loss": 0.1827, "lr": 1.291839395610428e-06, "epoch": 29.37003683995088, "percentage": 89.72, "elapsed_time": "4:07:55", "remaining_time": "0:28:23", "throughput": 786.12, "total_tokens": 11693952} {"current_steps": 35895, "total_steps": 40000, "loss": 0.1991, "lr": 1.2887261738053852e-06, "epoch": 29.374130167826443, "percentage": 89.74, "elapsed_time": "4:07:57", "remaining_time": "0:28:21", "throughput": 786.14, "total_tokens": 11695552} {"current_steps": 35900, "total_steps": 40000, "loss": 0.1277, "lr": 1.2856166085767396e-06, "epoch": 29.378223495702006, "percentage": 89.75, "elapsed_time": "4:07:58", "remaining_time": "0:28:19", "throughput": 786.16, "total_tokens": 11697216} {"current_steps": 35905, "total_steps": 40000, "loss": 0.169, "lr": 1.2825107004040272e-06, "epoch": 29.38231682357757, "percentage": 89.76, "elapsed_time": "4:08:00", "remaining_time": "0:28:17", "throughput": 786.18, "total_tokens": 11698832} {"current_steps": 35910, "total_steps": 40000, "loss": 0.1628, "lr": 1.2794084497662146e-06, "epoch": 29.38641015145313, "percentage": 89.78, "elapsed_time": "4:08:02", "remaining_time": "0:28:15", "throughput": 786.2, "total_tokens": 11700432} {"current_steps": 35915, "total_steps": 40000, "loss": 0.125, "lr": 1.276309857141711e-06, "epoch": 29.390503479328693, "percentage": 89.79, "elapsed_time": "4:08:04", "remaining_time": "0:28:12", "throughput": 786.22, "total_tokens": 11702080} {"current_steps": 35920, "total_steps": 40000, "loss": 0.1231, "lr": 1.273214923008359e-06, "epoch": 29.394596807204255, "percentage": 89.8, "elapsed_time": "4:08:05", "remaining_time": "0:28:10", "throughput": 786.23, "total_tokens": 11703712} {"current_steps": 35925, "total_steps": 40000, "loss": 0.155, "lr": 1.2701236478434352e-06, "epoch": 29.39869013507982, "percentage": 89.81, "elapsed_time": "4:08:07", "remaining_time": "0:28:08", "throughput": 786.25, "total_tokens": 11705280} {"current_steps": 35930, "total_steps": 40000, "loss": 0.1586, "lr": 1.2670360321236502e-06, "epoch": 29.402783462955384, "percentage": 89.83, "elapsed_time": "4:08:09", "remaining_time": "0:28:06", "throughput": 786.27, "total_tokens": 11706944} {"current_steps": 35935, "total_steps": 40000, "loss": 0.1178, "lr": 1.2639520763251617e-06, "epoch": 29.406876790830946, "percentage": 89.84, "elapsed_time": "4:08:10", "remaining_time": "0:28:04", "throughput": 786.29, "total_tokens": 11708528} {"current_steps": 35940, "total_steps": 40000, "loss": 0.1485, "lr": 1.2608717809235448e-06, "epoch": 29.41097011870651, "percentage": 89.85, "elapsed_time": "4:08:12", "remaining_time": "0:28:02", "throughput": 786.31, "total_tokens": 11710176} {"current_steps": 35945, "total_steps": 40000, "loss": 0.1463, "lr": 1.2577951463938282e-06, "epoch": 29.41506344658207, "percentage": 89.86, "elapsed_time": "4:08:14", "remaining_time": "0:28:00", "throughput": 786.33, "total_tokens": 11711856} {"current_steps": 35950, "total_steps": 40000, "loss": 0.1355, "lr": 1.2547221732104569e-06, "epoch": 29.419156774457633, "percentage": 89.88, "elapsed_time": "4:08:16", "remaining_time": "0:27:58", "throughput": 786.34, "total_tokens": 11713424} {"current_steps": 35955, "total_steps": 40000, "loss": 0.169, "lr": 1.25165286184733e-06, "epoch": 29.423250102333196, "percentage": 89.89, "elapsed_time": "4:08:17", "remaining_time": "0:27:56", "throughput": 786.36, "total_tokens": 11715008} {"current_steps": 35960, "total_steps": 40000, "loss": 0.2092, "lr": 1.248587212777777e-06, "epoch": 29.427343430208758, "percentage": 89.9, "elapsed_time": "4:08:19", "remaining_time": "0:27:53", "throughput": 786.38, "total_tokens": 11716704} {"current_steps": 35965, "total_steps": 40000, "loss": 0.1202, "lr": 1.2455252264745532e-06, "epoch": 29.431436758084324, "percentage": 89.91, "elapsed_time": "4:08:21", "remaining_time": "0:27:51", "throughput": 786.41, "total_tokens": 11718480} {"current_steps": 35970, "total_steps": 40000, "loss": 0.1781, "lr": 1.2424669034098528e-06, "epoch": 29.435530085959886, "percentage": 89.92, "elapsed_time": "4:08:22", "remaining_time": "0:27:49", "throughput": 786.43, "total_tokens": 11720192} {"current_steps": 35975, "total_steps": 40000, "loss": 0.1719, "lr": 1.2394122440553185e-06, "epoch": 29.43962341383545, "percentage": 89.94, "elapsed_time": "4:08:24", "remaining_time": "0:27:47", "throughput": 786.46, "total_tokens": 11721920} {"current_steps": 35980, "total_steps": 40000, "loss": 0.2345, "lr": 1.2363612488820037e-06, "epoch": 29.44371674171101, "percentage": 89.95, "elapsed_time": "4:08:26", "remaining_time": "0:27:45", "throughput": 786.47, "total_tokens": 11723504} {"current_steps": 35985, "total_steps": 40000, "loss": 0.2785, "lr": 1.2333139183604208e-06, "epoch": 29.447810069586573, "percentage": 89.96, "elapsed_time": "4:08:28", "remaining_time": "0:27:43", "throughput": 786.49, "total_tokens": 11725088} {"current_steps": 35990, "total_steps": 40000, "loss": 0.1602, "lr": 1.2302702529604998e-06, "epoch": 29.451903397462136, "percentage": 89.98, "elapsed_time": "4:08:29", "remaining_time": "0:27:41", "throughput": 786.51, "total_tokens": 11726768} {"current_steps": 35995, "total_steps": 40000, "loss": 0.1911, "lr": 1.227230253151615e-06, "epoch": 29.455996725337698, "percentage": 89.99, "elapsed_time": "4:08:31", "remaining_time": "0:27:39", "throughput": 786.52, "total_tokens": 11728320} {"current_steps": 36000, "total_steps": 40000, "loss": 0.1861, "lr": 1.2241939194025748e-06, "epoch": 29.460090053213264, "percentage": 90.0, "elapsed_time": "4:08:33", "remaining_time": "0:27:37", "throughput": 786.54, "total_tokens": 11729904} {"current_steps": 36000, "total_steps": 40000, "eval_loss": 0.21293938159942627, "epoch": 29.460090053213264, "percentage": 90.0, "elapsed_time": "4:08:45", "remaining_time": "0:27:38", "throughput": 785.88, "total_tokens": 11729904} {"current_steps": 36005, "total_steps": 40000, "loss": 0.1808, "lr": 1.2211612521816156e-06, "epoch": 29.464183381088827, "percentage": 90.01, "elapsed_time": "4:08:49", "remaining_time": "0:27:36", "throughput": 785.81, "total_tokens": 11731520} {"current_steps": 36010, "total_steps": 40000, "loss": 0.1677, "lr": 1.2181322519564137e-06, "epoch": 29.46827670896439, "percentage": 90.03, "elapsed_time": "4:08:50", "remaining_time": "0:27:34", "throughput": 785.84, "total_tokens": 11733216} {"current_steps": 36015, "total_steps": 40000, "loss": 0.1354, "lr": 1.2151069191940839e-06, "epoch": 29.47237003683995, "percentage": 90.04, "elapsed_time": "4:08:52", "remaining_time": "0:27:32", "throughput": 785.86, "total_tokens": 11734912} {"current_steps": 36020, "total_steps": 40000, "loss": 0.2383, "lr": 1.2120852543611644e-06, "epoch": 29.476463364715514, "percentage": 90.05, "elapsed_time": "4:08:54", "remaining_time": "0:27:30", "throughput": 785.88, "total_tokens": 11736512} {"current_steps": 36025, "total_steps": 40000, "loss": 0.1348, "lr": 1.2090672579236379e-06, "epoch": 29.480556692591076, "percentage": 90.06, "elapsed_time": "4:08:56", "remaining_time": "0:27:28", "throughput": 785.89, "total_tokens": 11738128} {"current_steps": 36030, "total_steps": 40000, "loss": 0.1512, "lr": 1.2060529303469126e-06, "epoch": 29.48465002046664, "percentage": 90.08, "elapsed_time": "4:08:57", "remaining_time": "0:27:25", "throughput": 785.91, "total_tokens": 11739728} {"current_steps": 36035, "total_steps": 40000, "loss": 0.1825, "lr": 1.2030422720958445e-06, "epoch": 29.4887433483422, "percentage": 90.09, "elapsed_time": "4:08:59", "remaining_time": "0:27:23", "throughput": 785.93, "total_tokens": 11741424} {"current_steps": 36040, "total_steps": 40000, "loss": 0.2115, "lr": 1.200035283634704e-06, "epoch": 29.492836676217767, "percentage": 90.1, "elapsed_time": "4:09:01", "remaining_time": "0:27:21", "throughput": 785.95, "total_tokens": 11743040} {"current_steps": 36045, "total_steps": 40000, "loss": 0.1526, "lr": 1.1970319654272144e-06, "epoch": 29.49693000409333, "percentage": 90.11, "elapsed_time": "4:09:02", "remaining_time": "0:27:19", "throughput": 785.97, "total_tokens": 11744640} {"current_steps": 36050, "total_steps": 40000, "loss": 0.1576, "lr": 1.1940323179365192e-06, "epoch": 29.50102333196889, "percentage": 90.12, "elapsed_time": "4:09:04", "remaining_time": "0:27:17", "throughput": 785.99, "total_tokens": 11746304} {"current_steps": 36055, "total_steps": 40000, "loss": 0.1152, "lr": 1.1910363416252095e-06, "epoch": 29.505116659844454, "percentage": 90.14, "elapsed_time": "4:09:06", "remaining_time": "0:27:15", "throughput": 786.0, "total_tokens": 11747888} {"current_steps": 36060, "total_steps": 40000, "loss": 0.1668, "lr": 1.1880440369552964e-06, "epoch": 29.509209987720016, "percentage": 90.15, "elapsed_time": "4:09:08", "remaining_time": "0:27:13", "throughput": 786.02, "total_tokens": 11749472} {"current_steps": 36065, "total_steps": 40000, "loss": 0.2127, "lr": 1.1850554043882328e-06, "epoch": 29.51330331559558, "percentage": 90.16, "elapsed_time": "4:09:09", "remaining_time": "0:27:11", "throughput": 786.04, "total_tokens": 11751072} {"current_steps": 36070, "total_steps": 40000, "loss": 0.1309, "lr": 1.1820704443849028e-06, "epoch": 29.51739664347114, "percentage": 90.18, "elapsed_time": "4:09:11", "remaining_time": "0:27:09", "throughput": 786.06, "total_tokens": 11752704} {"current_steps": 36075, "total_steps": 40000, "loss": 0.1839, "lr": 1.1790891574056219e-06, "epoch": 29.521489971346703, "percentage": 90.19, "elapsed_time": "4:09:13", "remaining_time": "0:27:06", "throughput": 786.07, "total_tokens": 11754336} {"current_steps": 36080, "total_steps": 40000, "loss": 0.1146, "lr": 1.1761115439101523e-06, "epoch": 29.52558329922227, "percentage": 90.2, "elapsed_time": "4:09:14", "remaining_time": "0:27:04", "throughput": 786.09, "total_tokens": 11755856} {"current_steps": 36085, "total_steps": 40000, "loss": 0.2343, "lr": 1.1731376043576659e-06, "epoch": 29.52967662709783, "percentage": 90.21, "elapsed_time": "4:09:16", "remaining_time": "0:27:02", "throughput": 786.1, "total_tokens": 11757472} {"current_steps": 36090, "total_steps": 40000, "loss": 0.1305, "lr": 1.1701673392067875e-06, "epoch": 29.533769954973394, "percentage": 90.22, "elapsed_time": "4:09:18", "remaining_time": "0:27:00", "throughput": 786.12, "total_tokens": 11759120} {"current_steps": 36095, "total_steps": 40000, "loss": 0.2002, "lr": 1.1672007489155757e-06, "epoch": 29.537863282848956, "percentage": 90.24, "elapsed_time": "4:09:20", "remaining_time": "0:26:58", "throughput": 786.14, "total_tokens": 11760752} {"current_steps": 36100, "total_steps": 40000, "loss": 0.1441, "lr": 1.164237833941506e-06, "epoch": 29.54195661072452, "percentage": 90.25, "elapsed_time": "4:09:21", "remaining_time": "0:26:56", "throughput": 786.16, "total_tokens": 11762400} {"current_steps": 36105, "total_steps": 40000, "loss": 0.2101, "lr": 1.1612785947415022e-06, "epoch": 29.54604993860008, "percentage": 90.26, "elapsed_time": "4:09:23", "remaining_time": "0:26:54", "throughput": 786.18, "total_tokens": 11764080} {"current_steps": 36110, "total_steps": 40000, "loss": 0.1686, "lr": 1.1583230317719185e-06, "epoch": 29.550143266475644, "percentage": 90.28, "elapsed_time": "4:09:25", "remaining_time": "0:26:52", "throughput": 786.2, "total_tokens": 11765728} {"current_steps": 36115, "total_steps": 40000, "loss": 0.1428, "lr": 1.1553711454885318e-06, "epoch": 29.554236594351206, "percentage": 90.29, "elapsed_time": "4:09:26", "remaining_time": "0:26:50", "throughput": 786.22, "total_tokens": 11767344} {"current_steps": 36120, "total_steps": 40000, "loss": 0.2177, "lr": 1.152422936346567e-06, "epoch": 29.558329922226772, "percentage": 90.3, "elapsed_time": "4:09:28", "remaining_time": "0:26:47", "throughput": 786.24, "total_tokens": 11769008} {"current_steps": 36125, "total_steps": 40000, "loss": 0.1246, "lr": 1.1494784048006718e-06, "epoch": 29.562423250102334, "percentage": 90.31, "elapsed_time": "4:09:30", "remaining_time": "0:26:45", "throughput": 786.25, "total_tokens": 11770640} {"current_steps": 36130, "total_steps": 40000, "loss": 0.1194, "lr": 1.1465375513049326e-06, "epoch": 29.566516577977897, "percentage": 90.33, "elapsed_time": "4:09:32", "remaining_time": "0:26:43", "throughput": 786.26, "total_tokens": 11772224} {"current_steps": 36135, "total_steps": 40000, "loss": 0.1234, "lr": 1.1436003763128616e-06, "epoch": 29.57060990585346, "percentage": 90.34, "elapsed_time": "4:09:34", "remaining_time": "0:26:41", "throughput": 786.28, "total_tokens": 11773856} {"current_steps": 36140, "total_steps": 40000, "loss": 0.1126, "lr": 1.1406668802774106e-06, "epoch": 29.57470323372902, "percentage": 90.35, "elapsed_time": "4:09:35", "remaining_time": "0:26:39", "throughput": 786.3, "total_tokens": 11775472} {"current_steps": 36145, "total_steps": 40000, "loss": 0.1766, "lr": 1.137737063650965e-06, "epoch": 29.578796561604584, "percentage": 90.36, "elapsed_time": "4:09:37", "remaining_time": "0:26:37", "throughput": 786.31, "total_tokens": 11777024} {"current_steps": 36150, "total_steps": 40000, "loss": 0.1176, "lr": 1.1348109268853323e-06, "epoch": 29.582889889480146, "percentage": 90.38, "elapsed_time": "4:09:39", "remaining_time": "0:26:35", "throughput": 786.33, "total_tokens": 11778624} {"current_steps": 36155, "total_steps": 40000, "loss": 0.1162, "lr": 1.1318884704317634e-06, "epoch": 29.58698321735571, "percentage": 90.39, "elapsed_time": "4:09:40", "remaining_time": "0:26:33", "throughput": 786.35, "total_tokens": 11780256} {"current_steps": 36160, "total_steps": 40000, "loss": 0.1731, "lr": 1.1289696947409417e-06, "epoch": 29.591076545231275, "percentage": 90.4, "elapsed_time": "4:09:42", "remaining_time": "0:26:31", "throughput": 786.36, "total_tokens": 11781856} {"current_steps": 36165, "total_steps": 40000, "loss": 0.1122, "lr": 1.126054600262974e-06, "epoch": 29.595169873106837, "percentage": 90.41, "elapsed_time": "4:09:44", "remaining_time": "0:26:28", "throughput": 786.38, "total_tokens": 11783504} {"current_steps": 36170, "total_steps": 40000, "loss": 0.3071, "lr": 1.1231431874474064e-06, "epoch": 29.5992632009824, "percentage": 90.42, "elapsed_time": "4:09:46", "remaining_time": "0:26:26", "throughput": 786.4, "total_tokens": 11785120} {"current_steps": 36175, "total_steps": 40000, "loss": 0.1601, "lr": 1.12023545674321e-06, "epoch": 29.60335652885796, "percentage": 90.44, "elapsed_time": "4:09:47", "remaining_time": "0:26:24", "throughput": 786.42, "total_tokens": 11786736} {"current_steps": 36180, "total_steps": 40000, "loss": 0.0992, "lr": 1.117331408598804e-06, "epoch": 29.607449856733524, "percentage": 90.45, "elapsed_time": "4:09:49", "remaining_time": "0:26:22", "throughput": 786.44, "total_tokens": 11788464} {"current_steps": 36185, "total_steps": 40000, "loss": 0.1378, "lr": 1.1144310434620191e-06, "epoch": 29.611543184609086, "percentage": 90.46, "elapsed_time": "4:09:51", "remaining_time": "0:26:20", "throughput": 786.46, "total_tokens": 11790064} {"current_steps": 36190, "total_steps": 40000, "loss": 0.0828, "lr": 1.1115343617801365e-06, "epoch": 29.61563651248465, "percentage": 90.48, "elapsed_time": "4:09:52", "remaining_time": "0:26:18", "throughput": 786.48, "total_tokens": 11791696} {"current_steps": 36195, "total_steps": 40000, "loss": 0.1615, "lr": 1.1086413639998515e-06, "epoch": 29.61972984036021, "percentage": 90.49, "elapsed_time": "4:09:54", "remaining_time": "0:26:16", "throughput": 786.5, "total_tokens": 11793312} {"current_steps": 36200, "total_steps": 40000, "loss": 0.1767, "lr": 1.1057520505673103e-06, "epoch": 29.623823168235777, "percentage": 90.5, "elapsed_time": "4:09:56", "remaining_time": "0:26:14", "throughput": 786.52, "total_tokens": 11794928} {"current_steps": 36200, "total_steps": 40000, "eval_loss": 0.21402399241924286, "epoch": 29.623823168235777, "percentage": 90.5, "elapsed_time": "4:10:08", "remaining_time": "0:26:15", "throughput": 785.86, "total_tokens": 11794928} {"current_steps": 36205, "total_steps": 40000, "loss": 0.1163, "lr": 1.1028664219280727e-06, "epoch": 29.62791649611134, "percentage": 90.51, "elapsed_time": "4:10:12", "remaining_time": "0:26:13", "throughput": 785.8, "total_tokens": 11796592} {"current_steps": 36210, "total_steps": 40000, "loss": 0.182, "lr": 1.0999844785271468e-06, "epoch": 29.632009823986902, "percentage": 90.53, "elapsed_time": "4:10:13", "remaining_time": "0:26:11", "throughput": 785.82, "total_tokens": 11798208} {"current_steps": 36215, "total_steps": 40000, "loss": 0.1633, "lr": 1.097106220808955e-06, "epoch": 29.636103151862464, "percentage": 90.54, "elapsed_time": "4:10:15", "remaining_time": "0:26:09", "throughput": 785.84, "total_tokens": 11799808} {"current_steps": 36220, "total_steps": 40000, "loss": 0.2817, "lr": 1.0942316492173698e-06, "epoch": 29.640196479738027, "percentage": 90.55, "elapsed_time": "4:10:17", "remaining_time": "0:26:07", "throughput": 785.85, "total_tokens": 11801424} {"current_steps": 36225, "total_steps": 40000, "loss": 0.3351, "lr": 1.0913607641956841e-06, "epoch": 29.64428980761359, "percentage": 90.56, "elapsed_time": "4:10:19", "remaining_time": "0:26:05", "throughput": 785.87, "total_tokens": 11803008} {"current_steps": 36230, "total_steps": 40000, "loss": 0.174, "lr": 1.0884935661866213e-06, "epoch": 29.64838313548915, "percentage": 90.58, "elapsed_time": "4:10:20", "remaining_time": "0:26:03", "throughput": 785.89, "total_tokens": 11804592} {"current_steps": 36235, "total_steps": 40000, "loss": 0.1859, "lr": 1.0856300556323418e-06, "epoch": 29.652476463364714, "percentage": 90.59, "elapsed_time": "4:10:22", "remaining_time": "0:26:00", "throughput": 785.91, "total_tokens": 11806272} {"current_steps": 36240, "total_steps": 40000, "loss": 0.1192, "lr": 1.0827702329744365e-06, "epoch": 29.65656979124028, "percentage": 90.6, "elapsed_time": "4:10:24", "remaining_time": "0:25:58", "throughput": 785.93, "total_tokens": 11807888} {"current_steps": 36245, "total_steps": 40000, "loss": 0.1854, "lr": 1.0799140986539197e-06, "epoch": 29.660663119115842, "percentage": 90.61, "elapsed_time": "4:10:25", "remaining_time": "0:25:56", "throughput": 785.95, "total_tokens": 11809536} {"current_steps": 36250, "total_steps": 40000, "loss": 0.136, "lr": 1.0770616531112526e-06, "epoch": 29.664756446991404, "percentage": 90.62, "elapsed_time": "4:10:27", "remaining_time": "0:25:54", "throughput": 785.96, "total_tokens": 11811152} {"current_steps": 36255, "total_steps": 40000, "loss": 0.2336, "lr": 1.0742128967863085e-06, "epoch": 29.668849774866967, "percentage": 90.64, "elapsed_time": "4:10:29", "remaining_time": "0:25:52", "throughput": 785.98, "total_tokens": 11812800} {"current_steps": 36260, "total_steps": 40000, "loss": 0.1572, "lr": 1.071367830118411e-06, "epoch": 29.67294310274253, "percentage": 90.65, "elapsed_time": "4:10:31", "remaining_time": "0:25:50", "throughput": 786.0, "total_tokens": 11814432} {"current_steps": 36265, "total_steps": 40000, "loss": 0.1327, "lr": 1.068526453546298e-06, "epoch": 29.67703643061809, "percentage": 90.66, "elapsed_time": "4:10:32", "remaining_time": "0:25:48", "throughput": 786.02, "total_tokens": 11816128} {"current_steps": 36270, "total_steps": 40000, "loss": 0.1697, "lr": 1.0656887675081467e-06, "epoch": 29.681129758493654, "percentage": 90.67, "elapsed_time": "4:10:34", "remaining_time": "0:25:46", "throughput": 786.04, "total_tokens": 11817760} {"current_steps": 36275, "total_steps": 40000, "loss": 0.1891, "lr": 1.0628547724415628e-06, "epoch": 29.68522308636922, "percentage": 90.69, "elapsed_time": "4:10:36", "remaining_time": "0:25:44", "throughput": 786.07, "total_tokens": 11819440} {"current_steps": 36280, "total_steps": 40000, "loss": 0.174, "lr": 1.0600244687835881e-06, "epoch": 29.689316414244782, "percentage": 90.7, "elapsed_time": "4:10:37", "remaining_time": "0:25:41", "throughput": 786.08, "total_tokens": 11821056} {"current_steps": 36285, "total_steps": 40000, "loss": 0.1862, "lr": 1.0571978569706876e-06, "epoch": 29.693409742120345, "percentage": 90.71, "elapsed_time": "4:10:39", "remaining_time": "0:25:39", "throughput": 786.11, "total_tokens": 11822752} {"current_steps": 36290, "total_steps": 40000, "loss": 0.1166, "lr": 1.0543749374387652e-06, "epoch": 29.697503069995907, "percentage": 90.72, "elapsed_time": "4:10:41", "remaining_time": "0:25:37", "throughput": 786.12, "total_tokens": 11824352} {"current_steps": 36295, "total_steps": 40000, "loss": 0.1768, "lr": 1.051555710623142e-06, "epoch": 29.70159639787147, "percentage": 90.74, "elapsed_time": "4:10:43", "remaining_time": "0:25:35", "throughput": 786.15, "total_tokens": 11826080} {"current_steps": 36300, "total_steps": 40000, "loss": 0.1671, "lr": 1.0487401769585847e-06, "epoch": 29.705689725747032, "percentage": 90.75, "elapsed_time": "4:10:44", "remaining_time": "0:25:33", "throughput": 786.17, "total_tokens": 11827744} {"current_steps": 36305, "total_steps": 40000, "loss": 0.1504, "lr": 1.0459283368792845e-06, "epoch": 29.709783053622594, "percentage": 90.76, "elapsed_time": "4:10:46", "remaining_time": "0:25:31", "throughput": 786.19, "total_tokens": 11829456} {"current_steps": 36310, "total_steps": 40000, "loss": 0.1847, "lr": 1.043120190818858e-06, "epoch": 29.713876381498157, "percentage": 90.77, "elapsed_time": "4:10:48", "remaining_time": "0:25:29", "throughput": 786.21, "total_tokens": 11831104} {"current_steps": 36315, "total_steps": 40000, "loss": 0.1453, "lr": 1.0403157392103596e-06, "epoch": 29.717969709373723, "percentage": 90.79, "elapsed_time": "4:10:49", "remaining_time": "0:25:27", "throughput": 786.23, "total_tokens": 11832720} {"current_steps": 36320, "total_steps": 40000, "loss": 0.2062, "lr": 1.0375149824862735e-06, "epoch": 29.722063037249285, "percentage": 90.8, "elapsed_time": "4:10:51", "remaining_time": "0:25:25", "throughput": 786.24, "total_tokens": 11834336} {"current_steps": 36325, "total_steps": 40000, "loss": 0.1819, "lr": 1.034717921078507e-06, "epoch": 29.726156365124847, "percentage": 90.81, "elapsed_time": "4:10:53", "remaining_time": "0:25:22", "throughput": 786.26, "total_tokens": 11836000} {"current_steps": 36330, "total_steps": 40000, "loss": 0.118, "lr": 1.0319245554184009e-06, "epoch": 29.73024969300041, "percentage": 90.83, "elapsed_time": "4:10:55", "remaining_time": "0:25:20", "throughput": 786.28, "total_tokens": 11837632} {"current_steps": 36335, "total_steps": 40000, "loss": 0.1483, "lr": 1.0291348859367361e-06, "epoch": 29.734343020875972, "percentage": 90.84, "elapsed_time": "4:10:56", "remaining_time": "0:25:18", "throughput": 786.3, "total_tokens": 11839232} {"current_steps": 36340, "total_steps": 40000, "loss": 0.1455, "lr": 1.0263489130637016e-06, "epoch": 29.738436348751534, "percentage": 90.85, "elapsed_time": "4:10:58", "remaining_time": "0:25:16", "throughput": 786.31, "total_tokens": 11840832} {"current_steps": 36345, "total_steps": 40000, "loss": 0.1625, "lr": 1.0235666372289427e-06, "epoch": 29.742529676627097, "percentage": 90.86, "elapsed_time": "4:11:00", "remaining_time": "0:25:14", "throughput": 786.33, "total_tokens": 11842496} {"current_steps": 36350, "total_steps": 40000, "loss": 0.1631, "lr": 1.0207880588615076e-06, "epoch": 29.74662300450266, "percentage": 90.88, "elapsed_time": "4:11:02", "remaining_time": "0:25:12", "throughput": 786.34, "total_tokens": 11844048} {"current_steps": 36355, "total_steps": 40000, "loss": 0.2294, "lr": 1.0180131783898984e-06, "epoch": 29.750716332378225, "percentage": 90.89, "elapsed_time": "4:11:03", "remaining_time": "0:25:10", "throughput": 786.36, "total_tokens": 11845712} {"current_steps": 36360, "total_steps": 40000, "loss": 0.1681, "lr": 1.0152419962420362e-06, "epoch": 29.754809660253787, "percentage": 90.9, "elapsed_time": "4:11:05", "remaining_time": "0:25:08", "throughput": 786.38, "total_tokens": 11847360} {"current_steps": 36365, "total_steps": 40000, "loss": 0.1948, "lr": 1.0124745128452685e-06, "epoch": 29.75890298812935, "percentage": 90.91, "elapsed_time": "4:11:07", "remaining_time": "0:25:06", "throughput": 786.39, "total_tokens": 11848960} {"current_steps": 36370, "total_steps": 40000, "loss": 0.1536, "lr": 1.0097107286263758e-06, "epoch": 29.762996316004912, "percentage": 90.92, "elapsed_time": "4:11:09", "remaining_time": "0:25:04", "throughput": 786.41, "total_tokens": 11850592} {"current_steps": 36375, "total_steps": 40000, "loss": 0.2468, "lr": 1.00695064401157e-06, "epoch": 29.767089643880475, "percentage": 90.94, "elapsed_time": "4:11:10", "remaining_time": "0:25:01", "throughput": 786.42, "total_tokens": 11852192} {"current_steps": 36380, "total_steps": 40000, "loss": 0.2808, "lr": 1.0041942594264886e-06, "epoch": 29.771182971756037, "percentage": 90.95, "elapsed_time": "4:11:12", "remaining_time": "0:24:59", "throughput": 786.44, "total_tokens": 11853840} {"current_steps": 36385, "total_steps": 40000, "loss": 0.2229, "lr": 1.001441575296208e-06, "epoch": 29.7752762996316, "percentage": 90.96, "elapsed_time": "4:11:14", "remaining_time": "0:24:57", "throughput": 786.46, "total_tokens": 11855456} {"current_steps": 36390, "total_steps": 40000, "loss": 0.1254, "lr": 9.986925920452139e-07, "epoch": 29.77936962750716, "percentage": 90.97, "elapsed_time": "4:11:16", "remaining_time": "0:24:55", "throughput": 786.47, "total_tokens": 11857104} {"current_steps": 36395, "total_steps": 40000, "loss": 0.1243, "lr": 9.959473100974475e-07, "epoch": 29.783462955382728, "percentage": 90.99, "elapsed_time": "4:11:18", "remaining_time": "0:24:53", "throughput": 786.49, "total_tokens": 11858752} {"current_steps": 36400, "total_steps": 40000, "loss": 0.1488, "lr": 9.932057298762564e-07, "epoch": 29.78755628325829, "percentage": 91.0, "elapsed_time": "4:11:19", "remaining_time": "0:24:51", "throughput": 786.51, "total_tokens": 11860400} {"current_steps": 36400, "total_steps": 40000, "eval_loss": 0.21232014894485474, "epoch": 29.78755628325829, "percentage": 91.0, "elapsed_time": "4:11:32", "remaining_time": "0:24:52", "throughput": 785.86, "total_tokens": 11860400} {"current_steps": 36405, "total_steps": 40000, "loss": 0.1923, "lr": 9.90467851804433e-07, "epoch": 29.791649611133852, "percentage": 91.01, "elapsed_time": "4:11:35", "remaining_time": "0:24:50", "throughput": 785.79, "total_tokens": 11862048} {"current_steps": 36410, "total_steps": 40000, "loss": 0.2733, "lr": 9.877336763041895e-07, "epoch": 29.795742939009415, "percentage": 91.03, "elapsed_time": "4:11:37", "remaining_time": "0:24:48", "throughput": 785.8, "total_tokens": 11863632} {"current_steps": 36415, "total_steps": 40000, "loss": 0.2181, "lr": 9.850032037971662e-07, "epoch": 29.799836266884977, "percentage": 91.04, "elapsed_time": "4:11:39", "remaining_time": "0:24:46", "throughput": 785.82, "total_tokens": 11865248} {"current_steps": 36420, "total_steps": 40000, "loss": 0.2003, "lr": 9.822764347044406e-07, "epoch": 29.80392959476054, "percentage": 91.05, "elapsed_time": "4:11:40", "remaining_time": "0:24:44", "throughput": 785.84, "total_tokens": 11866928} {"current_steps": 36425, "total_steps": 40000, "loss": 0.1609, "lr": 9.795533694465175e-07, "epoch": 29.808022922636102, "percentage": 91.06, "elapsed_time": "4:11:42", "remaining_time": "0:24:42", "throughput": 785.85, "total_tokens": 11868544} {"current_steps": 36430, "total_steps": 40000, "loss": 0.2483, "lr": 9.768340084433197e-07, "epoch": 29.812116250511664, "percentage": 91.07, "elapsed_time": "4:11:44", "remaining_time": "0:24:40", "throughput": 785.87, "total_tokens": 11870128} {"current_steps": 36435, "total_steps": 40000, "loss": 0.1918, "lr": 9.741183521142143e-07, "epoch": 29.81620957838723, "percentage": 91.09, "elapsed_time": "4:11:46", "remaining_time": "0:24:38", "throughput": 785.88, "total_tokens": 11871760} {"current_steps": 36440, "total_steps": 40000, "loss": 0.1991, "lr": 9.714064008779889e-07, "epoch": 29.820302906262793, "percentage": 91.1, "elapsed_time": "4:11:48", "remaining_time": "0:24:35", "throughput": 785.9, "total_tokens": 11873360} {"current_steps": 36445, "total_steps": 40000, "loss": 0.1757, "lr": 9.686981551528584e-07, "epoch": 29.824396234138355, "percentage": 91.11, "elapsed_time": "4:11:49", "remaining_time": "0:24:33", "throughput": 785.91, "total_tokens": 11874960} {"current_steps": 36450, "total_steps": 40000, "loss": 0.0917, "lr": 9.65993615356467e-07, "epoch": 29.828489562013917, "percentage": 91.12, "elapsed_time": "4:11:51", "remaining_time": "0:24:31", "throughput": 785.93, "total_tokens": 11876576} {"current_steps": 36455, "total_steps": 40000, "loss": 0.0905, "lr": 9.632927819058917e-07, "epoch": 29.83258288988948, "percentage": 91.14, "elapsed_time": "4:11:53", "remaining_time": "0:24:29", "throughput": 785.94, "total_tokens": 11878160} {"current_steps": 36460, "total_steps": 40000, "loss": 0.281, "lr": 9.605956552176305e-07, "epoch": 29.836676217765042, "percentage": 91.15, "elapsed_time": "4:11:55", "remaining_time": "0:24:27", "throughput": 785.96, "total_tokens": 11879808} {"current_steps": 36465, "total_steps": 40000, "loss": 0.1902, "lr": 9.579022357076223e-07, "epoch": 29.840769545640605, "percentage": 91.16, "elapsed_time": "4:11:56", "remaining_time": "0:24:25", "throughput": 785.98, "total_tokens": 11881424} {"current_steps": 36470, "total_steps": 40000, "loss": 0.2206, "lr": 9.552125237912158e-07, "epoch": 29.844862873516167, "percentage": 91.17, "elapsed_time": "4:11:58", "remaining_time": "0:24:23", "throughput": 785.99, "total_tokens": 11883008} {"current_steps": 36475, "total_steps": 40000, "loss": 0.1437, "lr": 9.525265198832096e-07, "epoch": 29.848956201391733, "percentage": 91.19, "elapsed_time": "4:12:00", "remaining_time": "0:24:21", "throughput": 786.0, "total_tokens": 11884576} {"current_steps": 36480, "total_steps": 40000, "loss": 0.1945, "lr": 9.498442243978112e-07, "epoch": 29.853049529267295, "percentage": 91.2, "elapsed_time": "4:12:02", "remaining_time": "0:24:19", "throughput": 786.02, "total_tokens": 11886224} {"current_steps": 36485, "total_steps": 40000, "loss": 0.1123, "lr": 9.471656377486649e-07, "epoch": 29.857142857142858, "percentage": 91.21, "elapsed_time": "4:12:03", "remaining_time": "0:24:17", "throughput": 786.03, "total_tokens": 11887824} {"current_steps": 36490, "total_steps": 40000, "loss": 0.1633, "lr": 9.444907603488456e-07, "epoch": 29.86123618501842, "percentage": 91.22, "elapsed_time": "4:12:05", "remaining_time": "0:24:14", "throughput": 786.05, "total_tokens": 11889440} {"current_steps": 36495, "total_steps": 40000, "loss": 0.1817, "lr": 9.418195926108514e-07, "epoch": 29.865329512893982, "percentage": 91.24, "elapsed_time": "4:12:07", "remaining_time": "0:24:12", "throughput": 786.06, "total_tokens": 11891024} {"current_steps": 36500, "total_steps": 40000, "loss": 0.153, "lr": 9.391521349466053e-07, "epoch": 29.869422840769545, "percentage": 91.25, "elapsed_time": "4:12:09", "remaining_time": "0:24:10", "throughput": 786.09, "total_tokens": 11892736} {"current_steps": 36505, "total_steps": 40000, "loss": 0.1777, "lr": 9.364883877674758e-07, "epoch": 29.873516168645107, "percentage": 91.26, "elapsed_time": "4:12:10", "remaining_time": "0:24:08", "throughput": 786.1, "total_tokens": 11894384} {"current_steps": 36510, "total_steps": 40000, "loss": 0.2092, "lr": 9.33828351484231e-07, "epoch": 29.87760949652067, "percentage": 91.27, "elapsed_time": "4:12:12", "remaining_time": "0:24:06", "throughput": 786.12, "total_tokens": 11896016} {"current_steps": 36515, "total_steps": 40000, "loss": 0.1851, "lr": 9.311720265070906e-07, "epoch": 29.881702824396235, "percentage": 91.29, "elapsed_time": "4:12:14", "remaining_time": "0:24:04", "throughput": 786.14, "total_tokens": 11897680} {"current_steps": 36520, "total_steps": 40000, "loss": 0.2077, "lr": 9.285194132456931e-07, "epoch": 29.885796152271798, "percentage": 91.3, "elapsed_time": "4:12:16", "remaining_time": "0:24:02", "throughput": 786.15, "total_tokens": 11899280} {"current_steps": 36525, "total_steps": 40000, "loss": 0.154, "lr": 9.258705121091032e-07, "epoch": 29.88988948014736, "percentage": 91.31, "elapsed_time": "4:12:17", "remaining_time": "0:24:00", "throughput": 786.18, "total_tokens": 11901008} {"current_steps": 36530, "total_steps": 40000, "loss": 0.1637, "lr": 9.232253235058136e-07, "epoch": 29.893982808022923, "percentage": 91.33, "elapsed_time": "4:12:19", "remaining_time": "0:23:58", "throughput": 786.19, "total_tokens": 11902576} {"current_steps": 36535, "total_steps": 40000, "loss": 0.2, "lr": 9.205838478437478e-07, "epoch": 29.898076135898485, "percentage": 91.34, "elapsed_time": "4:12:21", "remaining_time": "0:23:56", "throughput": 786.2, "total_tokens": 11904192} {"current_steps": 36540, "total_steps": 40000, "loss": 0.1911, "lr": 9.179460855302524e-07, "epoch": 29.902169463774047, "percentage": 91.35, "elapsed_time": "4:12:23", "remaining_time": "0:23:53", "throughput": 786.22, "total_tokens": 11905824} {"current_steps": 36545, "total_steps": 40000, "loss": 0.2259, "lr": 9.153120369721046e-07, "epoch": 29.90626279164961, "percentage": 91.36, "elapsed_time": "4:12:24", "remaining_time": "0:23:51", "throughput": 786.24, "total_tokens": 11907504} {"current_steps": 36550, "total_steps": 40000, "loss": 0.1999, "lr": 9.126817025755103e-07, "epoch": 29.910356119525176, "percentage": 91.38, "elapsed_time": "4:12:26", "remaining_time": "0:23:49", "throughput": 786.26, "total_tokens": 11909184} {"current_steps": 36555, "total_steps": 40000, "loss": 0.1401, "lr": 9.100550827460947e-07, "epoch": 29.914449447400738, "percentage": 91.39, "elapsed_time": "4:12:28", "remaining_time": "0:23:47", "throughput": 786.28, "total_tokens": 11910832} {"current_steps": 36560, "total_steps": 40000, "loss": 0.124, "lr": 9.0743217788892e-07, "epoch": 29.9185427752763, "percentage": 91.4, "elapsed_time": "4:12:30", "remaining_time": "0:23:45", "throughput": 786.3, "total_tokens": 11912496} {"current_steps": 36565, "total_steps": 40000, "loss": 0.1674, "lr": 9.048129884084683e-07, "epoch": 29.922636103151863, "percentage": 91.41, "elapsed_time": "4:12:31", "remaining_time": "0:23:43", "throughput": 786.31, "total_tokens": 11914096} {"current_steps": 36570, "total_steps": 40000, "loss": 0.1698, "lr": 9.021975147086553e-07, "epoch": 29.926729431027425, "percentage": 91.42, "elapsed_time": "4:12:33", "remaining_time": "0:23:41", "throughput": 786.32, "total_tokens": 11915664} {"current_steps": 36575, "total_steps": 40000, "loss": 0.1808, "lr": 8.995857571928141e-07, "epoch": 29.930822758902988, "percentage": 91.44, "elapsed_time": "4:12:35", "remaining_time": "0:23:39", "throughput": 786.34, "total_tokens": 11917312} {"current_steps": 36580, "total_steps": 40000, "loss": 0.1646, "lr": 8.969777162637139e-07, "epoch": 29.93491608677855, "percentage": 91.45, "elapsed_time": "4:12:37", "remaining_time": "0:23:37", "throughput": 786.35, "total_tokens": 11918832} {"current_steps": 36585, "total_steps": 40000, "loss": 0.1227, "lr": 8.943733923235525e-07, "epoch": 29.939009414654112, "percentage": 91.46, "elapsed_time": "4:12:38", "remaining_time": "0:23:34", "throughput": 786.37, "total_tokens": 11920480} {"current_steps": 36590, "total_steps": 40000, "loss": 0.1384, "lr": 8.917727857739394e-07, "epoch": 29.94310274252968, "percentage": 91.47, "elapsed_time": "4:12:40", "remaining_time": "0:23:32", "throughput": 786.38, "total_tokens": 11922080} {"current_steps": 36595, "total_steps": 40000, "loss": 0.2033, "lr": 8.891758970159258e-07, "epoch": 29.94719607040524, "percentage": 91.49, "elapsed_time": "4:12:42", "remaining_time": "0:23:30", "throughput": 786.4, "total_tokens": 11923712} {"current_steps": 36600, "total_steps": 40000, "loss": 0.1311, "lr": 8.86582726449986e-07, "epoch": 29.951289398280803, "percentage": 91.5, "elapsed_time": "4:12:44", "remaining_time": "0:23:28", "throughput": 786.42, "total_tokens": 11925328} {"current_steps": 36600, "total_steps": 40000, "eval_loss": 0.2131337821483612, "epoch": 29.951289398280803, "percentage": 91.5, "elapsed_time": "4:12:56", "remaining_time": "0:23:29", "throughput": 785.77, "total_tokens": 11925328} {"current_steps": 36605, "total_steps": 40000, "loss": 0.2042, "lr": 8.839932744760165e-07, "epoch": 29.955382726156365, "percentage": 91.51, "elapsed_time": "4:12:59", "remaining_time": "0:23:27", "throughput": 785.7, "total_tokens": 11926960} {"current_steps": 36610, "total_steps": 40000, "loss": 0.1191, "lr": 8.814075414933482e-07, "epoch": 29.959476054031928, "percentage": 91.53, "elapsed_time": "4:13:01", "remaining_time": "0:23:25", "throughput": 785.72, "total_tokens": 11928608} {"current_steps": 36615, "total_steps": 40000, "loss": 0.1668, "lr": 8.788255279007257e-07, "epoch": 29.96356938190749, "percentage": 91.54, "elapsed_time": "4:13:03", "remaining_time": "0:23:23", "throughput": 785.74, "total_tokens": 11930256} {"current_steps": 36620, "total_steps": 40000, "loss": 0.1362, "lr": 8.762472340963362e-07, "epoch": 29.967662709783053, "percentage": 91.55, "elapsed_time": "4:13:05", "remaining_time": "0:23:21", "throughput": 785.75, "total_tokens": 11931840} {"current_steps": 36625, "total_steps": 40000, "loss": 0.1535, "lr": 8.736726604777811e-07, "epoch": 29.971756037658615, "percentage": 91.56, "elapsed_time": "4:13:06", "remaining_time": "0:23:19", "throughput": 785.77, "total_tokens": 11933456} {"current_steps": 36630, "total_steps": 40000, "loss": 0.1419, "lr": 8.711018074420901e-07, "epoch": 29.97584936553418, "percentage": 91.57, "elapsed_time": "4:13:08", "remaining_time": "0:23:17", "throughput": 785.78, "total_tokens": 11935056} {"current_steps": 36635, "total_steps": 40000, "loss": 0.1659, "lr": 8.685346753857209e-07, "epoch": 29.979942693409743, "percentage": 91.59, "elapsed_time": "4:13:10", "remaining_time": "0:23:15", "throughput": 785.8, "total_tokens": 11936624} {"current_steps": 36640, "total_steps": 40000, "loss": 0.1429, "lr": 8.659712647045654e-07, "epoch": 29.984036021285306, "percentage": 91.6, "elapsed_time": "4:13:12", "remaining_time": "0:23:13", "throughput": 785.81, "total_tokens": 11938208} {"current_steps": 36645, "total_steps": 40000, "loss": 0.1586, "lr": 8.634115757939209e-07, "epoch": 29.988129349160868, "percentage": 91.61, "elapsed_time": "4:13:14", "remaining_time": "0:23:11", "throughput": 785.83, "total_tokens": 11939856} {"current_steps": 36650, "total_steps": 40000, "loss": 0.1248, "lr": 8.608556090485387e-07, "epoch": 29.99222267703643, "percentage": 91.62, "elapsed_time": "4:13:15", "remaining_time": "0:23:08", "throughput": 785.84, "total_tokens": 11941488} {"current_steps": 36655, "total_steps": 40000, "loss": 0.1501, "lr": 8.583033648625671e-07, "epoch": 29.996316004911993, "percentage": 91.64, "elapsed_time": "4:13:17", "remaining_time": "0:23:06", "throughput": 785.86, "total_tokens": 11943088} {"current_steps": 36660, "total_steps": 40000, "loss": 0.2795, "lr": 8.557548436295998e-07, "epoch": 30.0, "percentage": 91.65, "elapsed_time": "4:13:19", "remaining_time": "0:23:04", "throughput": 785.86, "total_tokens": 11944472} {"current_steps": 36665, "total_steps": 40000, "loss": 0.1595, "lr": 8.532100457426556e-07, "epoch": 30.004093327875562, "percentage": 91.66, "elapsed_time": "4:13:21", "remaining_time": "0:23:02", "throughput": 785.87, "total_tokens": 11946152} {"current_steps": 36670, "total_steps": 40000, "loss": 0.1552, "lr": 8.506689715941679e-07, "epoch": 30.008186655751125, "percentage": 91.67, "elapsed_time": "4:13:22", "remaining_time": "0:23:00", "throughput": 785.89, "total_tokens": 11947784} {"current_steps": 36675, "total_steps": 40000, "loss": 0.2048, "lr": 8.481316215760011e-07, "epoch": 30.012279983626687, "percentage": 91.69, "elapsed_time": "4:13:24", "remaining_time": "0:22:58", "throughput": 785.9, "total_tokens": 11949400} {"current_steps": 36680, "total_steps": 40000, "loss": 0.1445, "lr": 8.455979960794558e-07, "epoch": 30.016373311502253, "percentage": 91.7, "elapsed_time": "4:13:26", "remaining_time": "0:22:56", "throughput": 785.92, "total_tokens": 11951016} {"current_steps": 36685, "total_steps": 40000, "loss": 0.3057, "lr": 8.430680954952364e-07, "epoch": 30.020466639377815, "percentage": 91.71, "elapsed_time": "4:13:28", "remaining_time": "0:22:54", "throughput": 785.94, "total_tokens": 11952680} {"current_steps": 36690, "total_steps": 40000, "loss": 0.1122, "lr": 8.405419202134974e-07, "epoch": 30.024559967253378, "percentage": 91.72, "elapsed_time": "4:13:29", "remaining_time": "0:22:52", "throughput": 785.95, "total_tokens": 11954248} {"current_steps": 36695, "total_steps": 40000, "loss": 0.1194, "lr": 8.380194706237993e-07, "epoch": 30.02865329512894, "percentage": 91.74, "elapsed_time": "4:13:31", "remaining_time": "0:22:50", "throughput": 785.96, "total_tokens": 11955848} {"current_steps": 36700, "total_steps": 40000, "loss": 0.1623, "lr": 8.355007471151366e-07, "epoch": 30.032746623004503, "percentage": 91.75, "elapsed_time": "4:13:33", "remaining_time": "0:22:47", "throughput": 785.98, "total_tokens": 11957528} {"current_steps": 36705, "total_steps": 40000, "loss": 0.1673, "lr": 8.329857500759292e-07, "epoch": 30.036839950880065, "percentage": 91.76, "elapsed_time": "4:13:35", "remaining_time": "0:22:45", "throughput": 786.0, "total_tokens": 11959176} {"current_steps": 36710, "total_steps": 40000, "loss": 0.149, "lr": 8.304744798940194e-07, "epoch": 30.040933278755627, "percentage": 91.77, "elapsed_time": "4:13:37", "remaining_time": "0:22:43", "throughput": 786.01, "total_tokens": 11960776} {"current_steps": 36715, "total_steps": 40000, "loss": 0.1709, "lr": 8.279669369566756e-07, "epoch": 30.04502660663119, "percentage": 91.79, "elapsed_time": "4:13:38", "remaining_time": "0:22:41", "throughput": 786.03, "total_tokens": 11962408} {"current_steps": 36720, "total_steps": 40000, "loss": 0.1296, "lr": 8.254631216505993e-07, "epoch": 30.049119934506756, "percentage": 91.8, "elapsed_time": "4:13:40", "remaining_time": "0:22:39", "throughput": 786.04, "total_tokens": 11963992} {"current_steps": 36725, "total_steps": 40000, "loss": 0.1812, "lr": 8.229630343619038e-07, "epoch": 30.053213262382318, "percentage": 91.81, "elapsed_time": "4:13:42", "remaining_time": "0:22:37", "throughput": 786.06, "total_tokens": 11965576} {"current_steps": 36730, "total_steps": 40000, "loss": 0.091, "lr": 8.204666754761392e-07, "epoch": 30.05730659025788, "percentage": 91.83, "elapsed_time": "4:13:44", "remaining_time": "0:22:35", "throughput": 786.07, "total_tokens": 11967176} {"current_steps": 36735, "total_steps": 40000, "loss": 0.1324, "lr": 8.179740453782669e-07, "epoch": 30.061399918133443, "percentage": 91.84, "elapsed_time": "4:13:45", "remaining_time": "0:22:33", "throughput": 786.09, "total_tokens": 11968776} {"current_steps": 36740, "total_steps": 40000, "loss": 0.167, "lr": 8.154851444526907e-07, "epoch": 30.065493246009005, "percentage": 91.85, "elapsed_time": "4:13:47", "remaining_time": "0:22:31", "throughput": 786.1, "total_tokens": 11970408} {"current_steps": 36745, "total_steps": 40000, "loss": 0.1457, "lr": 8.129999730832283e-07, "epoch": 30.069586573884568, "percentage": 91.86, "elapsed_time": "4:13:49", "remaining_time": "0:22:29", "throughput": 786.11, "total_tokens": 11971976} {"current_steps": 36750, "total_steps": 40000, "loss": 0.1913, "lr": 8.105185316531178e-07, "epoch": 30.07367990176013, "percentage": 91.88, "elapsed_time": "4:13:51", "remaining_time": "0:22:26", "throughput": 786.13, "total_tokens": 11973576} {"current_steps": 36755, "total_steps": 40000, "loss": 0.2727, "lr": 8.08040820545039e-07, "epoch": 30.077773229635692, "percentage": 91.89, "elapsed_time": "4:13:52", "remaining_time": "0:22:24", "throughput": 786.14, "total_tokens": 11975176} {"current_steps": 36760, "total_steps": 40000, "loss": 0.1674, "lr": 8.055668401410782e-07, "epoch": 30.08186655751126, "percentage": 91.9, "elapsed_time": "4:13:54", "remaining_time": "0:22:22", "throughput": 786.16, "total_tokens": 11976840} {"current_steps": 36765, "total_steps": 40000, "loss": 0.2185, "lr": 8.030965908227578e-07, "epoch": 30.08595988538682, "percentage": 91.91, "elapsed_time": "4:13:56", "remaining_time": "0:22:20", "throughput": 786.18, "total_tokens": 11978504} {"current_steps": 36770, "total_steps": 40000, "loss": 0.1189, "lr": 8.006300729710203e-07, "epoch": 30.090053213262383, "percentage": 91.92, "elapsed_time": "4:13:58", "remaining_time": "0:22:18", "throughput": 786.19, "total_tokens": 11980104} {"current_steps": 36775, "total_steps": 40000, "loss": 0.1386, "lr": 7.981672869662337e-07, "epoch": 30.094146541137945, "percentage": 91.94, "elapsed_time": "4:13:59", "remaining_time": "0:22:16", "throughput": 786.21, "total_tokens": 11981736} {"current_steps": 36780, "total_steps": 40000, "loss": 0.1311, "lr": 7.957082331881888e-07, "epoch": 30.098239869013508, "percentage": 91.95, "elapsed_time": "4:14:01", "remaining_time": "0:22:14", "throughput": 786.23, "total_tokens": 11983352} {"current_steps": 36785, "total_steps": 40000, "loss": 0.1027, "lr": 7.932529120161069e-07, "epoch": 30.10233319688907, "percentage": 91.96, "elapsed_time": "4:14:03", "remaining_time": "0:22:12", "throughput": 786.24, "total_tokens": 11985000} {"current_steps": 36790, "total_steps": 40000, "loss": 0.1769, "lr": 7.908013238286243e-07, "epoch": 30.106426524764633, "percentage": 91.97, "elapsed_time": "4:14:05", "remaining_time": "0:22:10", "throughput": 786.26, "total_tokens": 11986632} {"current_steps": 36795, "total_steps": 40000, "loss": 0.1546, "lr": 7.883534690038136e-07, "epoch": 30.110519852640195, "percentage": 91.99, "elapsed_time": "4:14:06", "remaining_time": "0:22:08", "throughput": 786.28, "total_tokens": 11988344} {"current_steps": 36800, "total_steps": 40000, "loss": 0.1531, "lr": 7.859093479191559e-07, "epoch": 30.11461318051576, "percentage": 92.0, "elapsed_time": "4:14:08", "remaining_time": "0:22:05", "throughput": 786.3, "total_tokens": 11989944} {"current_steps": 36800, "total_steps": 40000, "eval_loss": 0.21279332041740417, "epoch": 30.11461318051576, "percentage": 92.0, "elapsed_time": "4:14:21", "remaining_time": "0:22:07", "throughput": 785.65, "total_tokens": 11989944} {"current_steps": 36805, "total_steps": 40000, "loss": 0.103, "lr": 7.834689609515722e-07, "epoch": 30.118706508391323, "percentage": 92.01, "elapsed_time": "4:14:24", "remaining_time": "0:22:05", "throughput": 785.59, "total_tokens": 11991592} {"current_steps": 36810, "total_steps": 40000, "loss": 0.2667, "lr": 7.810323084774002e-07, "epoch": 30.122799836266886, "percentage": 92.03, "elapsed_time": "4:14:26", "remaining_time": "0:22:02", "throughput": 785.61, "total_tokens": 11993240} {"current_steps": 36815, "total_steps": 40000, "loss": 0.1774, "lr": 7.785993908723976e-07, "epoch": 30.126893164142448, "percentage": 92.04, "elapsed_time": "4:14:27", "remaining_time": "0:22:00", "throughput": 785.63, "total_tokens": 11994872} {"current_steps": 36820, "total_steps": 40000, "loss": 0.1643, "lr": 7.761702085117534e-07, "epoch": 30.13098649201801, "percentage": 92.05, "elapsed_time": "4:14:29", "remaining_time": "0:21:58", "throughput": 785.64, "total_tokens": 11996520} {"current_steps": 36825, "total_steps": 40000, "loss": 0.1764, "lr": 7.737447617700844e-07, "epoch": 30.135079819893573, "percentage": 92.06, "elapsed_time": "4:14:31", "remaining_time": "0:21:56", "throughput": 785.66, "total_tokens": 11998152} {"current_steps": 36830, "total_steps": 40000, "loss": 0.1167, "lr": 7.713230510214136e-07, "epoch": 30.139173147769135, "percentage": 92.07, "elapsed_time": "4:14:33", "remaining_time": "0:21:54", "throughput": 785.68, "total_tokens": 11999848} {"current_steps": 36835, "total_steps": 40000, "loss": 0.3014, "lr": 7.689050766392092e-07, "epoch": 30.143266475644698, "percentage": 92.09, "elapsed_time": "4:14:34", "remaining_time": "0:21:52", "throughput": 785.7, "total_tokens": 12001528} {"current_steps": 36840, "total_steps": 40000, "loss": 0.1402, "lr": 7.664908389963477e-07, "epoch": 30.147359803520263, "percentage": 92.1, "elapsed_time": "4:14:36", "remaining_time": "0:21:50", "throughput": 785.72, "total_tokens": 12003144} {"current_steps": 36845, "total_steps": 40000, "loss": 0.1538, "lr": 7.64080338465134e-07, "epoch": 30.151453131395826, "percentage": 92.11, "elapsed_time": "4:14:38", "remaining_time": "0:21:48", "throughput": 785.73, "total_tokens": 12004760} {"current_steps": 36850, "total_steps": 40000, "loss": 0.1843, "lr": 7.616735754173043e-07, "epoch": 30.155546459271388, "percentage": 92.12, "elapsed_time": "4:14:40", "remaining_time": "0:21:46", "throughput": 785.75, "total_tokens": 12006408} {"current_steps": 36855, "total_steps": 40000, "loss": 0.2356, "lr": 7.592705502240005e-07, "epoch": 30.15963978714695, "percentage": 92.14, "elapsed_time": "4:14:41", "remaining_time": "0:21:44", "throughput": 785.76, "total_tokens": 12008008} {"current_steps": 36860, "total_steps": 40000, "loss": 0.1092, "lr": 7.568712632558095e-07, "epoch": 30.163733115022513, "percentage": 92.15, "elapsed_time": "4:14:43", "remaining_time": "0:21:41", "throughput": 785.78, "total_tokens": 12009608} {"current_steps": 36865, "total_steps": 40000, "loss": 0.1556, "lr": 7.544757148827297e-07, "epoch": 30.167826442898075, "percentage": 92.16, "elapsed_time": "4:14:45", "remaining_time": "0:21:39", "throughput": 785.8, "total_tokens": 12011272} {"current_steps": 36870, "total_steps": 40000, "loss": 0.2067, "lr": 7.520839054741797e-07, "epoch": 30.171919770773638, "percentage": 92.17, "elapsed_time": "4:14:47", "remaining_time": "0:21:37", "throughput": 785.81, "total_tokens": 12012920} {"current_steps": 36875, "total_steps": 40000, "loss": 0.2056, "lr": 7.496958353990113e-07, "epoch": 30.1760130986492, "percentage": 92.19, "elapsed_time": "4:14:48", "remaining_time": "0:21:35", "throughput": 785.83, "total_tokens": 12014552} {"current_steps": 36880, "total_steps": 40000, "loss": 0.1887, "lr": 7.473115050254941e-07, "epoch": 30.180106426524766, "percentage": 92.2, "elapsed_time": "4:14:50", "remaining_time": "0:21:33", "throughput": 785.85, "total_tokens": 12016168} {"current_steps": 36885, "total_steps": 40000, "loss": 0.1984, "lr": 7.449309147213173e-07, "epoch": 30.18419975440033, "percentage": 92.21, "elapsed_time": "4:14:52", "remaining_time": "0:21:31", "throughput": 785.86, "total_tokens": 12017768} {"current_steps": 36890, "total_steps": 40000, "loss": 0.2402, "lr": 7.425540648536067e-07, "epoch": 30.18829308227589, "percentage": 92.22, "elapsed_time": "4:14:54", "remaining_time": "0:21:29", "throughput": 785.88, "total_tokens": 12019416} {"current_steps": 36895, "total_steps": 40000, "loss": 0.1244, "lr": 7.40180955788894e-07, "epoch": 30.192386410151453, "percentage": 92.24, "elapsed_time": "4:14:56", "remaining_time": "0:21:27", "throughput": 785.89, "total_tokens": 12021032} {"current_steps": 36900, "total_steps": 40000, "loss": 0.1609, "lr": 7.378115878931474e-07, "epoch": 30.196479738027016, "percentage": 92.25, "elapsed_time": "4:14:57", "remaining_time": "0:21:25", "throughput": 785.91, "total_tokens": 12022664} {"current_steps": 36905, "total_steps": 40000, "loss": 0.1511, "lr": 7.354459615317527e-07, "epoch": 30.200573065902578, "percentage": 92.26, "elapsed_time": "4:14:59", "remaining_time": "0:21:23", "throughput": 785.92, "total_tokens": 12024200} {"current_steps": 36910, "total_steps": 40000, "loss": 0.2059, "lr": 7.33084077069518e-07, "epoch": 30.20466639377814, "percentage": 92.27, "elapsed_time": "4:15:01", "remaining_time": "0:21:20", "throughput": 785.94, "total_tokens": 12025880} {"current_steps": 36915, "total_steps": 40000, "loss": 0.0684, "lr": 7.307259348706768e-07, "epoch": 30.208759721653703, "percentage": 92.29, "elapsed_time": "4:15:03", "remaining_time": "0:21:18", "throughput": 785.95, "total_tokens": 12027432} {"current_steps": 36920, "total_steps": 40000, "loss": 0.2314, "lr": 7.283715352988801e-07, "epoch": 30.21285304952927, "percentage": 92.3, "elapsed_time": "4:15:04", "remaining_time": "0:21:16", "throughput": 785.96, "total_tokens": 12029032} {"current_steps": 36925, "total_steps": 40000, "loss": 0.1378, "lr": 7.260208787172068e-07, "epoch": 30.21694637740483, "percentage": 92.31, "elapsed_time": "4:15:06", "remaining_time": "0:21:14", "throughput": 785.99, "total_tokens": 12030728} {"current_steps": 36930, "total_steps": 40000, "loss": 0.2239, "lr": 7.23673965488167e-07, "epoch": 30.221039705280393, "percentage": 92.33, "elapsed_time": "4:15:08", "remaining_time": "0:21:12", "throughput": 786.0, "total_tokens": 12032312} {"current_steps": 36935, "total_steps": 40000, "loss": 0.1192, "lr": 7.213307959736709e-07, "epoch": 30.225133033155956, "percentage": 92.34, "elapsed_time": "4:15:10", "remaining_time": "0:21:10", "throughput": 786.02, "total_tokens": 12033976} {"current_steps": 36940, "total_steps": 40000, "loss": 0.113, "lr": 7.189913705350715e-07, "epoch": 30.229226361031518, "percentage": 92.35, "elapsed_time": "4:15:11", "remaining_time": "0:21:08", "throughput": 786.03, "total_tokens": 12035576} {"current_steps": 36945, "total_steps": 40000, "loss": 0.1731, "lr": 7.166556895331411e-07, "epoch": 30.23331968890708, "percentage": 92.36, "elapsed_time": "4:15:13", "remaining_time": "0:21:06", "throughput": 786.05, "total_tokens": 12037192} {"current_steps": 36950, "total_steps": 40000, "loss": 0.1315, "lr": 7.143237533280639e-07, "epoch": 30.237413016782643, "percentage": 92.38, "elapsed_time": "4:15:15", "remaining_time": "0:21:04", "throughput": 786.06, "total_tokens": 12038760} {"current_steps": 36955, "total_steps": 40000, "loss": 0.1666, "lr": 7.119955622794578e-07, "epoch": 30.24150634465821, "percentage": 92.39, "elapsed_time": "4:15:17", "remaining_time": "0:21:02", "throughput": 786.08, "total_tokens": 12040376} {"current_steps": 36960, "total_steps": 40000, "loss": 0.1325, "lr": 7.096711167463577e-07, "epoch": 30.24559967253377, "percentage": 92.4, "elapsed_time": "4:15:18", "remaining_time": "0:20:59", "throughput": 786.09, "total_tokens": 12042008} {"current_steps": 36965, "total_steps": 40000, "loss": 0.0931, "lr": 7.073504170872213e-07, "epoch": 30.249693000409334, "percentage": 92.41, "elapsed_time": "4:15:20", "remaining_time": "0:20:57", "throughput": 786.11, "total_tokens": 12043656} {"current_steps": 36970, "total_steps": 40000, "loss": 0.1718, "lr": 7.05033463659932e-07, "epoch": 30.253786328284896, "percentage": 92.42, "elapsed_time": "4:15:22", "remaining_time": "0:20:55", "throughput": 786.13, "total_tokens": 12045304} {"current_steps": 36975, "total_steps": 40000, "loss": 0.1752, "lr": 7.027202568217928e-07, "epoch": 30.25787965616046, "percentage": 92.44, "elapsed_time": "4:15:24", "remaining_time": "0:20:53", "throughput": 786.14, "total_tokens": 12046888} {"current_steps": 36980, "total_steps": 40000, "loss": 0.1511, "lr": 7.004107969295293e-07, "epoch": 30.26197298403602, "percentage": 92.45, "elapsed_time": "4:15:25", "remaining_time": "0:20:51", "throughput": 786.16, "total_tokens": 12048552} {"current_steps": 36985, "total_steps": 40000, "loss": 0.1922, "lr": 6.9810508433929e-07, "epoch": 30.266066311911583, "percentage": 92.46, "elapsed_time": "4:15:27", "remaining_time": "0:20:49", "throughput": 786.17, "total_tokens": 12050136} {"current_steps": 36990, "total_steps": 40000, "loss": 0.156, "lr": 6.958031194066406e-07, "epoch": 30.270159639787146, "percentage": 92.47, "elapsed_time": "4:15:29", "remaining_time": "0:20:47", "throughput": 786.19, "total_tokens": 12051784} {"current_steps": 36995, "total_steps": 40000, "loss": 0.1907, "lr": 6.935049024865776e-07, "epoch": 30.27425296766271, "percentage": 92.49, "elapsed_time": "4:15:31", "remaining_time": "0:20:45", "throughput": 786.2, "total_tokens": 12053336} {"current_steps": 37000, "total_steps": 40000, "loss": 0.1226, "lr": 6.912104339335118e-07, "epoch": 30.278346295538274, "percentage": 92.5, "elapsed_time": "4:15:32", "remaining_time": "0:20:43", "throughput": 786.22, "total_tokens": 12054968} {"current_steps": 37000, "total_steps": 40000, "eval_loss": 0.21528886258602142, "epoch": 30.278346295538274, "percentage": 92.5, "elapsed_time": "4:15:45", "remaining_time": "0:20:44", "throughput": 785.58, "total_tokens": 12054968} {"current_steps": 37005, "total_steps": 40000, "loss": 0.1647, "lr": 6.889197141012799e-07, "epoch": 30.282439623413836, "percentage": 92.51, "elapsed_time": "4:15:48", "remaining_time": "0:20:42", "throughput": 785.51, "total_tokens": 12056568} {"current_steps": 37010, "total_steps": 40000, "loss": 0.1998, "lr": 6.866327433431435e-07, "epoch": 30.2865329512894, "percentage": 92.53, "elapsed_time": "4:15:50", "remaining_time": "0:20:40", "throughput": 785.53, "total_tokens": 12058184} {"current_steps": 37015, "total_steps": 40000, "loss": 0.0819, "lr": 6.843495220117735e-07, "epoch": 30.29062627916496, "percentage": 92.54, "elapsed_time": "4:15:52", "remaining_time": "0:20:38", "throughput": 785.54, "total_tokens": 12059816} {"current_steps": 37020, "total_steps": 40000, "loss": 0.132, "lr": 6.820700504592798e-07, "epoch": 30.294719607040523, "percentage": 92.55, "elapsed_time": "4:15:53", "remaining_time": "0:20:35", "throughput": 785.56, "total_tokens": 12061480} {"current_steps": 37025, "total_steps": 40000, "loss": 0.2279, "lr": 6.797943290371839e-07, "epoch": 30.298812934916086, "percentage": 92.56, "elapsed_time": "4:15:55", "remaining_time": "0:20:33", "throughput": 785.58, "total_tokens": 12063112} {"current_steps": 37030, "total_steps": 40000, "loss": 0.1196, "lr": 6.775223580964274e-07, "epoch": 30.302906262791648, "percentage": 92.58, "elapsed_time": "4:15:57", "remaining_time": "0:20:31", "throughput": 785.6, "total_tokens": 12064744} {"current_steps": 37035, "total_steps": 40000, "loss": 0.1601, "lr": 6.7525413798738e-07, "epoch": 30.306999590667214, "percentage": 92.59, "elapsed_time": "4:15:59", "remaining_time": "0:20:29", "throughput": 785.61, "total_tokens": 12066376} {"current_steps": 37040, "total_steps": 40000, "loss": 0.1101, "lr": 6.729896690598259e-07, "epoch": 30.311092918542776, "percentage": 92.6, "elapsed_time": "4:16:00", "remaining_time": "0:20:27", "throughput": 785.63, "total_tokens": 12067992} {"current_steps": 37045, "total_steps": 40000, "loss": 0.1783, "lr": 6.707289516629772e-07, "epoch": 30.31518624641834, "percentage": 92.61, "elapsed_time": "4:16:02", "remaining_time": "0:20:25", "throughput": 785.64, "total_tokens": 12069560} {"current_steps": 37050, "total_steps": 40000, "loss": 0.301, "lr": 6.684719861454692e-07, "epoch": 30.3192795742939, "percentage": 92.62, "elapsed_time": "4:16:04", "remaining_time": "0:20:23", "throughput": 785.66, "total_tokens": 12071272} {"current_steps": 37055, "total_steps": 40000, "loss": 0.2431, "lr": 6.662187728553481e-07, "epoch": 30.323372902169464, "percentage": 92.64, "elapsed_time": "4:16:06", "remaining_time": "0:20:21", "throughput": 785.68, "total_tokens": 12072904} {"current_steps": 37060, "total_steps": 40000, "loss": 0.1729, "lr": 6.639693121400892e-07, "epoch": 30.327466230045026, "percentage": 92.65, "elapsed_time": "4:16:07", "remaining_time": "0:20:19", "throughput": 785.69, "total_tokens": 12074504} {"current_steps": 37065, "total_steps": 40000, "loss": 0.2959, "lr": 6.617236043465868e-07, "epoch": 30.33155955792059, "percentage": 92.66, "elapsed_time": "4:16:09", "remaining_time": "0:20:17", "throughput": 785.71, "total_tokens": 12076136} {"current_steps": 37070, "total_steps": 40000, "loss": 0.1902, "lr": 6.594816498211587e-07, "epoch": 30.33565288579615, "percentage": 92.67, "elapsed_time": "4:16:11", "remaining_time": "0:20:14", "throughput": 785.73, "total_tokens": 12077848} {"current_steps": 37075, "total_steps": 40000, "loss": 0.1207, "lr": 6.572434489095447e-07, "epoch": 30.339746213671717, "percentage": 92.69, "elapsed_time": "4:16:13", "remaining_time": "0:20:12", "throughput": 785.75, "total_tokens": 12079480} {"current_steps": 37080, "total_steps": 40000, "loss": 0.162, "lr": 6.550090019568994e-07, "epoch": 30.34383954154728, "percentage": 92.7, "elapsed_time": "4:16:15", "remaining_time": "0:20:10", "throughput": 785.76, "total_tokens": 12081096} {"current_steps": 37085, "total_steps": 40000, "loss": 0.2055, "lr": 6.527783093078027e-07, "epoch": 30.34793286942284, "percentage": 92.71, "elapsed_time": "4:16:16", "remaining_time": "0:20:08", "throughput": 785.78, "total_tokens": 12082696} {"current_steps": 37090, "total_steps": 40000, "loss": 0.1584, "lr": 6.5055137130626e-07, "epoch": 30.352026197298404, "percentage": 92.73, "elapsed_time": "4:16:18", "remaining_time": "0:20:06", "throughput": 785.79, "total_tokens": 12084376} {"current_steps": 37095, "total_steps": 40000, "loss": 0.3132, "lr": 6.483281882956854e-07, "epoch": 30.356119525173966, "percentage": 92.74, "elapsed_time": "4:16:20", "remaining_time": "0:20:04", "throughput": 785.81, "total_tokens": 12086024} {"current_steps": 37100, "total_steps": 40000, "loss": 0.1678, "lr": 6.461087606189298e-07, "epoch": 30.36021285304953, "percentage": 92.75, "elapsed_time": "4:16:22", "remaining_time": "0:20:02", "throughput": 785.83, "total_tokens": 12087672} {"current_steps": 37105, "total_steps": 40000, "loss": 0.1399, "lr": 6.438930886182554e-07, "epoch": 30.36430618092509, "percentage": 92.76, "elapsed_time": "4:16:23", "remaining_time": "0:20:00", "throughput": 785.85, "total_tokens": 12089304} {"current_steps": 37110, "total_steps": 40000, "loss": 0.1675, "lr": 6.416811726353417e-07, "epoch": 30.368399508800653, "percentage": 92.77, "elapsed_time": "4:16:25", "remaining_time": "0:19:58", "throughput": 785.86, "total_tokens": 12090952} {"current_steps": 37115, "total_steps": 40000, "loss": 0.2596, "lr": 6.394730130112991e-07, "epoch": 30.37249283667622, "percentage": 92.79, "elapsed_time": "4:16:27", "remaining_time": "0:19:56", "throughput": 785.88, "total_tokens": 12092536} {"current_steps": 37120, "total_steps": 40000, "loss": 0.2253, "lr": 6.372686100866471e-07, "epoch": 30.37658616455178, "percentage": 92.8, "elapsed_time": "4:16:29", "remaining_time": "0:19:53", "throughput": 785.89, "total_tokens": 12094120} {"current_steps": 37125, "total_steps": 40000, "loss": 0.1723, "lr": 6.350679642013413e-07, "epoch": 30.380679492427344, "percentage": 92.81, "elapsed_time": "4:16:30", "remaining_time": "0:19:51", "throughput": 785.9, "total_tokens": 12095704} {"current_steps": 37130, "total_steps": 40000, "loss": 0.0968, "lr": 6.328710756947437e-07, "epoch": 30.384772820302906, "percentage": 92.83, "elapsed_time": "4:16:32", "remaining_time": "0:19:49", "throughput": 785.92, "total_tokens": 12097320} {"current_steps": 37135, "total_steps": 40000, "loss": 0.2627, "lr": 6.306779449056416e-07, "epoch": 30.38886614817847, "percentage": 92.84, "elapsed_time": "4:16:34", "remaining_time": "0:19:47", "throughput": 785.94, "total_tokens": 12098984} {"current_steps": 37140, "total_steps": 40000, "loss": 0.1673, "lr": 6.284885721722422e-07, "epoch": 30.39295947605403, "percentage": 92.85, "elapsed_time": "4:16:36", "remaining_time": "0:19:45", "throughput": 785.95, "total_tokens": 12100616} {"current_steps": 37145, "total_steps": 40000, "loss": 0.1541, "lr": 6.26302957832181e-07, "epoch": 30.397052803929594, "percentage": 92.86, "elapsed_time": "4:16:37", "remaining_time": "0:19:43", "throughput": 785.97, "total_tokens": 12102280} {"current_steps": 37150, "total_steps": 40000, "loss": 0.2363, "lr": 6.241211022224997e-07, "epoch": 30.401146131805156, "percentage": 92.88, "elapsed_time": "4:16:39", "remaining_time": "0:19:41", "throughput": 785.99, "total_tokens": 12103944} {"current_steps": 37155, "total_steps": 40000, "loss": 0.1915, "lr": 6.219430056796732e-07, "epoch": 30.405239459680722, "percentage": 92.89, "elapsed_time": "4:16:41", "remaining_time": "0:19:39", "throughput": 786.0, "total_tokens": 12105512} {"current_steps": 37160, "total_steps": 40000, "loss": 0.1233, "lr": 6.19768668539586e-07, "epoch": 30.409332787556284, "percentage": 92.9, "elapsed_time": "4:16:43", "remaining_time": "0:19:37", "throughput": 786.02, "total_tokens": 12107176} {"current_steps": 37165, "total_steps": 40000, "loss": 0.2024, "lr": 6.175980911375528e-07, "epoch": 30.413426115431847, "percentage": 92.91, "elapsed_time": "4:16:44", "remaining_time": "0:19:35", "throughput": 786.03, "total_tokens": 12108776} {"current_steps": 37170, "total_steps": 40000, "loss": 0.1346, "lr": 6.154312738083034e-07, "epoch": 30.41751944330741, "percentage": 92.92, "elapsed_time": "4:16:46", "remaining_time": "0:19:33", "throughput": 786.05, "total_tokens": 12110408} {"current_steps": 37175, "total_steps": 40000, "loss": 0.0943, "lr": 6.132682168859843e-07, "epoch": 30.42161277118297, "percentage": 92.94, "elapsed_time": "4:16:48", "remaining_time": "0:19:30", "throughput": 786.07, "total_tokens": 12112040} {"current_steps": 37180, "total_steps": 40000, "loss": 0.1179, "lr": 6.111089207041704e-07, "epoch": 30.425706099058534, "percentage": 92.95, "elapsed_time": "4:16:50", "remaining_time": "0:19:28", "throughput": 786.08, "total_tokens": 12113688} {"current_steps": 37185, "total_steps": 40000, "loss": 0.1607, "lr": 6.089533855958507e-07, "epoch": 30.429799426934096, "percentage": 92.96, "elapsed_time": "4:16:51", "remaining_time": "0:19:26", "throughput": 786.1, "total_tokens": 12115288} {"current_steps": 37190, "total_steps": 40000, "loss": 0.1547, "lr": 6.068016118934372e-07, "epoch": 30.433892754809662, "percentage": 92.97, "elapsed_time": "4:16:53", "remaining_time": "0:19:24", "throughput": 786.12, "total_tokens": 12116952} {"current_steps": 37195, "total_steps": 40000, "loss": 0.1383, "lr": 6.04653599928759e-07, "epoch": 30.437986082685224, "percentage": 92.99, "elapsed_time": "4:16:55", "remaining_time": "0:19:22", "throughput": 786.13, "total_tokens": 12118600} {"current_steps": 37200, "total_steps": 40000, "loss": 0.1902, "lr": 6.025093500330675e-07, "epoch": 30.442079410560787, "percentage": 93.0, "elapsed_time": "4:16:57", "remaining_time": "0:19:20", "throughput": 786.15, "total_tokens": 12120184} {"current_steps": 37200, "total_steps": 40000, "eval_loss": 0.21375319361686707, "epoch": 30.442079410560787, "percentage": 93.0, "elapsed_time": "4:17:09", "remaining_time": "0:19:21", "throughput": 785.51, "total_tokens": 12120184} {"current_steps": 37205, "total_steps": 40000, "loss": 0.147, "lr": 6.003688625370291e-07, "epoch": 30.44617273843635, "percentage": 93.01, "elapsed_time": "4:17:12", "remaining_time": "0:19:19", "throughput": 785.45, "total_tokens": 12121848} {"current_steps": 37210, "total_steps": 40000, "loss": 0.1187, "lr": 5.982321377707406e-07, "epoch": 30.45026606631191, "percentage": 93.03, "elapsed_time": "4:17:14", "remaining_time": "0:19:17", "throughput": 785.47, "total_tokens": 12123448} {"current_steps": 37215, "total_steps": 40000, "loss": 0.1035, "lr": 5.96099176063708e-07, "epoch": 30.454359394187474, "percentage": 93.04, "elapsed_time": "4:17:16", "remaining_time": "0:19:15", "throughput": 785.48, "total_tokens": 12125064} {"current_steps": 37220, "total_steps": 40000, "loss": 0.129, "lr": 5.93969977744857e-07, "epoch": 30.458452722063036, "percentage": 93.05, "elapsed_time": "4:17:18", "remaining_time": "0:19:13", "throughput": 785.5, "total_tokens": 12126728} {"current_steps": 37225, "total_steps": 40000, "loss": 0.1025, "lr": 5.918445431425445e-07, "epoch": 30.4625460499386, "percentage": 93.06, "elapsed_time": "4:17:20", "remaining_time": "0:19:11", "throughput": 785.51, "total_tokens": 12128312} {"current_steps": 37230, "total_steps": 40000, "loss": 0.1144, "lr": 5.897228725845333e-07, "epoch": 30.466639377814165, "percentage": 93.08, "elapsed_time": "4:17:21", "remaining_time": "0:19:08", "throughput": 785.53, "total_tokens": 12130024} {"current_steps": 37235, "total_steps": 40000, "loss": 0.1353, "lr": 5.876049663980171e-07, "epoch": 30.470732705689727, "percentage": 93.09, "elapsed_time": "4:17:23", "remaining_time": "0:19:06", "throughput": 785.55, "total_tokens": 12131704} {"current_steps": 37240, "total_steps": 40000, "loss": 0.2477, "lr": 5.854908249095959e-07, "epoch": 30.47482603356529, "percentage": 93.1, "elapsed_time": "4:17:25", "remaining_time": "0:19:04", "throughput": 785.57, "total_tokens": 12133320} {"current_steps": 37245, "total_steps": 40000, "loss": 0.2087, "lr": 5.833804484453031e-07, "epoch": 30.478919361440852, "percentage": 93.11, "elapsed_time": "4:17:27", "remaining_time": "0:19:02", "throughput": 785.59, "total_tokens": 12135032} {"current_steps": 37250, "total_steps": 40000, "loss": 0.2052, "lr": 5.81273837330587e-07, "epoch": 30.483012689316414, "percentage": 93.12, "elapsed_time": "4:17:28", "remaining_time": "0:19:00", "throughput": 785.61, "total_tokens": 12136680} {"current_steps": 37255, "total_steps": 40000, "loss": 0.1517, "lr": 5.791709918903071e-07, "epoch": 30.487106017191977, "percentage": 93.14, "elapsed_time": "4:17:30", "remaining_time": "0:18:58", "throughput": 785.62, "total_tokens": 12138280} {"current_steps": 37260, "total_steps": 40000, "loss": 0.1237, "lr": 5.770719124487483e-07, "epoch": 30.49119934506754, "percentage": 93.15, "elapsed_time": "4:17:32", "remaining_time": "0:18:56", "throughput": 785.64, "total_tokens": 12139976} {"current_steps": 37265, "total_steps": 40000, "loss": 0.1953, "lr": 5.749765993296241e-07, "epoch": 30.4952926729431, "percentage": 93.16, "elapsed_time": "4:17:34", "remaining_time": "0:18:54", "throughput": 785.66, "total_tokens": 12141592} {"current_steps": 37270, "total_steps": 40000, "loss": 0.1582, "lr": 5.728850528560509e-07, "epoch": 30.499386000818667, "percentage": 93.17, "elapsed_time": "4:17:35", "remaining_time": "0:18:52", "throughput": 785.67, "total_tokens": 12143192} {"current_steps": 37275, "total_steps": 40000, "loss": 0.201, "lr": 5.707972733505707e-07, "epoch": 30.50347932869423, "percentage": 93.19, "elapsed_time": "4:17:37", "remaining_time": "0:18:50", "throughput": 785.68, "total_tokens": 12144776} {"current_steps": 37280, "total_steps": 40000, "loss": 0.1189, "lr": 5.687132611351509e-07, "epoch": 30.507572656569792, "percentage": 93.2, "elapsed_time": "4:17:39", "remaining_time": "0:18:47", "throughput": 785.7, "total_tokens": 12146392} {"current_steps": 37285, "total_steps": 40000, "loss": 0.2261, "lr": 5.666330165311651e-07, "epoch": 30.511665984445354, "percentage": 93.21, "elapsed_time": "4:17:41", "remaining_time": "0:18:45", "throughput": 785.72, "total_tokens": 12148040} {"current_steps": 37290, "total_steps": 40000, "loss": 0.2117, "lr": 5.645565398594204e-07, "epoch": 30.515759312320917, "percentage": 93.23, "elapsed_time": "4:17:42", "remaining_time": "0:18:43", "throughput": 785.73, "total_tokens": 12149624} {"current_steps": 37295, "total_steps": 40000, "loss": 0.1375, "lr": 5.624838314401304e-07, "epoch": 30.51985264019648, "percentage": 93.24, "elapsed_time": "4:17:44", "remaining_time": "0:18:41", "throughput": 785.75, "total_tokens": 12151320} {"current_steps": 37300, "total_steps": 40000, "loss": 0.1537, "lr": 5.604148915929336e-07, "epoch": 30.52394596807204, "percentage": 93.25, "elapsed_time": "4:17:46", "remaining_time": "0:18:39", "throughput": 785.76, "total_tokens": 12152920} {"current_steps": 37305, "total_steps": 40000, "loss": 0.165, "lr": 5.583497206368887e-07, "epoch": 30.528039295947604, "percentage": 93.26, "elapsed_time": "4:17:48", "remaining_time": "0:18:37", "throughput": 785.78, "total_tokens": 12154616} {"current_steps": 37310, "total_steps": 40000, "loss": 0.1912, "lr": 5.562883188904688e-07, "epoch": 30.53213262382317, "percentage": 93.27, "elapsed_time": "4:17:49", "remaining_time": "0:18:35", "throughput": 785.8, "total_tokens": 12156216} {"current_steps": 37315, "total_steps": 40000, "loss": 0.2817, "lr": 5.542306866715724e-07, "epoch": 30.536225951698732, "percentage": 93.29, "elapsed_time": "4:17:51", "remaining_time": "0:18:33", "throughput": 785.82, "total_tokens": 12157880} {"current_steps": 37320, "total_steps": 40000, "loss": 0.1412, "lr": 5.52176824297504e-07, "epoch": 30.540319279574295, "percentage": 93.3, "elapsed_time": "4:17:53", "remaining_time": "0:18:31", "throughput": 785.84, "total_tokens": 12159560} {"current_steps": 37325, "total_steps": 40000, "loss": 0.2282, "lr": 5.501267320850018e-07, "epoch": 30.544412607449857, "percentage": 93.31, "elapsed_time": "4:17:55", "remaining_time": "0:18:29", "throughput": 785.85, "total_tokens": 12161192} {"current_steps": 37330, "total_steps": 40000, "loss": 0.1159, "lr": 5.480804103502157e-07, "epoch": 30.54850593532542, "percentage": 93.33, "elapsed_time": "4:17:56", "remaining_time": "0:18:26", "throughput": 785.87, "total_tokens": 12162808} {"current_steps": 37335, "total_steps": 40000, "loss": 0.1137, "lr": 5.460378594087101e-07, "epoch": 30.55259926320098, "percentage": 93.34, "elapsed_time": "4:17:58", "remaining_time": "0:18:24", "throughput": 785.88, "total_tokens": 12164440} {"current_steps": 37340, "total_steps": 40000, "loss": 0.1272, "lr": 5.439990795754773e-07, "epoch": 30.556692591076544, "percentage": 93.35, "elapsed_time": "4:18:00", "remaining_time": "0:18:22", "throughput": 785.9, "total_tokens": 12166136} {"current_steps": 37345, "total_steps": 40000, "loss": 0.1434, "lr": 5.419640711649188e-07, "epoch": 30.560785918952106, "percentage": 93.36, "elapsed_time": "4:18:02", "remaining_time": "0:18:20", "throughput": 785.92, "total_tokens": 12167752} {"current_steps": 37350, "total_steps": 40000, "loss": 0.1318, "lr": 5.399328344908583e-07, "epoch": 30.564879246827672, "percentage": 93.38, "elapsed_time": "4:18:03", "remaining_time": "0:18:18", "throughput": 785.94, "total_tokens": 12169400} {"current_steps": 37355, "total_steps": 40000, "loss": 0.1911, "lr": 5.379053698665399e-07, "epoch": 30.568972574703235, "percentage": 93.39, "elapsed_time": "4:18:05", "remaining_time": "0:18:16", "throughput": 785.96, "total_tokens": 12171080} {"current_steps": 37360, "total_steps": 40000, "loss": 0.207, "lr": 5.358816776046216e-07, "epoch": 30.573065902578797, "percentage": 93.4, "elapsed_time": "4:18:07", "remaining_time": "0:18:14", "throughput": 785.97, "total_tokens": 12172664} {"current_steps": 37365, "total_steps": 40000, "loss": 0.2225, "lr": 5.338617580171817e-07, "epoch": 30.57715923045436, "percentage": 93.41, "elapsed_time": "4:18:09", "remaining_time": "0:18:12", "throughput": 785.98, "total_tokens": 12174296} {"current_steps": 37370, "total_steps": 40000, "loss": 0.1436, "lr": 5.318456114157239e-07, "epoch": 30.581252558329922, "percentage": 93.42, "elapsed_time": "4:18:10", "remaining_time": "0:18:10", "throughput": 786.0, "total_tokens": 12175896} {"current_steps": 37375, "total_steps": 40000, "loss": 0.2053, "lr": 5.298332381111576e-07, "epoch": 30.585345886205484, "percentage": 93.44, "elapsed_time": "4:18:12", "remaining_time": "0:18:08", "throughput": 786.01, "total_tokens": 12177512} {"current_steps": 37380, "total_steps": 40000, "loss": 0.2114, "lr": 5.27824638413818e-07, "epoch": 30.589439214081047, "percentage": 93.45, "elapsed_time": "4:18:14", "remaining_time": "0:18:06", "throughput": 786.03, "total_tokens": 12179160} {"current_steps": 37385, "total_steps": 40000, "loss": 0.2605, "lr": 5.258198126334546e-07, "epoch": 30.59353254195661, "percentage": 93.46, "elapsed_time": "4:18:16", "remaining_time": "0:18:03", "throughput": 786.05, "total_tokens": 12180872} {"current_steps": 37390, "total_steps": 40000, "loss": 0.2009, "lr": 5.238187610792367e-07, "epoch": 30.597625869832175, "percentage": 93.47, "elapsed_time": "4:18:17", "remaining_time": "0:18:01", "throughput": 786.07, "total_tokens": 12182504} {"current_steps": 37395, "total_steps": 40000, "loss": 0.1743, "lr": 5.218214840597563e-07, "epoch": 30.601719197707737, "percentage": 93.49, "elapsed_time": "4:18:19", "remaining_time": "0:17:59", "throughput": 786.09, "total_tokens": 12184136} {"current_steps": 37400, "total_steps": 40000, "loss": 0.1804, "lr": 5.198279818830115e-07, "epoch": 30.6058125255833, "percentage": 93.5, "elapsed_time": "4:18:21", "remaining_time": "0:17:57", "throughput": 786.11, "total_tokens": 12185832} {"current_steps": 37400, "total_steps": 40000, "eval_loss": 0.21414321660995483, "epoch": 30.6058125255833, "percentage": 93.5, "elapsed_time": "4:18:33", "remaining_time": "0:17:58", "throughput": 785.48, "total_tokens": 12185832} {"current_steps": 37405, "total_steps": 40000, "loss": 0.1256, "lr": 5.178382548564287e-07, "epoch": 30.609905853458862, "percentage": 93.51, "elapsed_time": "4:18:37", "remaining_time": "0:17:56", "throughput": 785.42, "total_tokens": 12187544} {"current_steps": 37410, "total_steps": 40000, "loss": 0.1804, "lr": 5.15852303286854e-07, "epoch": 30.613999181334425, "percentage": 93.53, "elapsed_time": "4:18:39", "remaining_time": "0:17:54", "throughput": 785.43, "total_tokens": 12189128} {"current_steps": 37415, "total_steps": 40000, "loss": 0.166, "lr": 5.138701274805396e-07, "epoch": 30.618092509209987, "percentage": 93.54, "elapsed_time": "4:18:40", "remaining_time": "0:17:52", "throughput": 785.44, "total_tokens": 12190712} {"current_steps": 37420, "total_steps": 40000, "loss": 0.1732, "lr": 5.118917277431606e-07, "epoch": 30.62218583708555, "percentage": 93.55, "elapsed_time": "4:18:42", "remaining_time": "0:17:50", "throughput": 785.46, "total_tokens": 12192280} {"current_steps": 37425, "total_steps": 40000, "loss": 0.0643, "lr": 5.099171043798145e-07, "epoch": 30.62627916496111, "percentage": 93.56, "elapsed_time": "4:18:44", "remaining_time": "0:17:48", "throughput": 785.48, "total_tokens": 12193912} {"current_steps": 37430, "total_steps": 40000, "loss": 0.2506, "lr": 5.079462576950133e-07, "epoch": 30.630372492836678, "percentage": 93.58, "elapsed_time": "4:18:45", "remaining_time": "0:17:46", "throughput": 785.49, "total_tokens": 12195512} {"current_steps": 37435, "total_steps": 40000, "loss": 0.1508, "lr": 5.059791879926862e-07, "epoch": 30.63446582071224, "percentage": 93.59, "elapsed_time": "4:18:47", "remaining_time": "0:17:43", "throughput": 785.51, "total_tokens": 12197144} {"current_steps": 37440, "total_steps": 40000, "loss": 0.1672, "lr": 5.040158955761793e-07, "epoch": 30.638559148587802, "percentage": 93.6, "elapsed_time": "4:18:49", "remaining_time": "0:17:41", "throughput": 785.53, "total_tokens": 12198760} {"current_steps": 37445, "total_steps": 40000, "loss": 0.1792, "lr": 5.020563807482559e-07, "epoch": 30.642652476463365, "percentage": 93.61, "elapsed_time": "4:18:51", "remaining_time": "0:17:39", "throughput": 785.55, "total_tokens": 12200440} {"current_steps": 37450, "total_steps": 40000, "loss": 0.1857, "lr": 5.001006438110995e-07, "epoch": 30.646745804338927, "percentage": 93.62, "elapsed_time": "4:18:52", "remaining_time": "0:17:37", "throughput": 785.57, "total_tokens": 12202104} {"current_steps": 37455, "total_steps": 40000, "loss": 0.1875, "lr": 4.981486850663075e-07, "epoch": 30.65083913221449, "percentage": 93.64, "elapsed_time": "4:18:54", "remaining_time": "0:17:35", "throughput": 785.59, "total_tokens": 12203736} {"current_steps": 37460, "total_steps": 40000, "loss": 0.1938, "lr": 4.962005048149005e-07, "epoch": 30.654932460090052, "percentage": 93.65, "elapsed_time": "4:18:56", "remaining_time": "0:17:33", "throughput": 785.61, "total_tokens": 12205400} {"current_steps": 37465, "total_steps": 40000, "loss": 0.1401, "lr": 4.942561033573073e-07, "epoch": 30.659025787965618, "percentage": 93.66, "elapsed_time": "4:18:57", "remaining_time": "0:17:31", "throughput": 785.62, "total_tokens": 12207016} {"current_steps": 37470, "total_steps": 40000, "loss": 0.2486, "lr": 4.923154809933827e-07, "epoch": 30.66311911584118, "percentage": 93.67, "elapsed_time": "4:18:59", "remaining_time": "0:17:29", "throughput": 785.64, "total_tokens": 12208632} {"current_steps": 37475, "total_steps": 40000, "loss": 0.1578, "lr": 4.903786380223957e-07, "epoch": 30.667212443716743, "percentage": 93.69, "elapsed_time": "4:19:01", "remaining_time": "0:17:27", "throughput": 785.66, "total_tokens": 12210296} {"current_steps": 37480, "total_steps": 40000, "loss": 0.1713, "lr": 4.884455747430266e-07, "epoch": 30.671305771592305, "percentage": 93.7, "elapsed_time": "4:19:03", "remaining_time": "0:17:25", "throughput": 785.68, "total_tokens": 12211944} {"current_steps": 37485, "total_steps": 40000, "loss": 0.2782, "lr": 4.865162914533816e-07, "epoch": 30.675399099467867, "percentage": 93.71, "elapsed_time": "4:19:04", "remaining_time": "0:17:22", "throughput": 785.69, "total_tokens": 12213512} {"current_steps": 37490, "total_steps": 40000, "loss": 0.2325, "lr": 4.845907884509809e-07, "epoch": 30.67949242734343, "percentage": 93.73, "elapsed_time": "4:19:06", "remaining_time": "0:17:20", "throughput": 785.71, "total_tokens": 12215176} {"current_steps": 37495, "total_steps": 40000, "loss": 0.1271, "lr": 4.82669066032762e-07, "epoch": 30.683585755218992, "percentage": 93.74, "elapsed_time": "4:19:08", "remaining_time": "0:17:18", "throughput": 785.73, "total_tokens": 12216792} {"current_steps": 37500, "total_steps": 40000, "loss": 0.1146, "lr": 4.807511244950768e-07, "epoch": 30.687679083094554, "percentage": 93.75, "elapsed_time": "4:19:10", "remaining_time": "0:17:16", "throughput": 785.75, "total_tokens": 12218392} {"current_steps": 37505, "total_steps": 40000, "loss": 0.111, "lr": 4.788369641336943e-07, "epoch": 30.691772410970117, "percentage": 93.76, "elapsed_time": "4:19:11", "remaining_time": "0:17:14", "throughput": 785.77, "total_tokens": 12220104} {"current_steps": 37510, "total_steps": 40000, "loss": 0.1158, "lr": 4.769265852438032e-07, "epoch": 30.695865738845683, "percentage": 93.77, "elapsed_time": "4:19:13", "remaining_time": "0:17:12", "throughput": 785.79, "total_tokens": 12221784} {"current_steps": 37515, "total_steps": 40000, "loss": 0.2285, "lr": 4.750199881200124e-07, "epoch": 30.699959066721245, "percentage": 93.79, "elapsed_time": "4:19:15", "remaining_time": "0:17:10", "throughput": 785.81, "total_tokens": 12223384} {"current_steps": 37520, "total_steps": 40000, "loss": 0.1875, "lr": 4.7311717305633664e-07, "epoch": 30.704052394596808, "percentage": 93.8, "elapsed_time": "4:19:16", "remaining_time": "0:17:08", "throughput": 785.83, "total_tokens": 12225048} {"current_steps": 37525, "total_steps": 40000, "loss": 0.1609, "lr": 4.7121814034621623e-07, "epoch": 30.70814572247237, "percentage": 93.81, "elapsed_time": "4:19:18", "remaining_time": "0:17:06", "throughput": 785.84, "total_tokens": 12226664} {"current_steps": 37530, "total_steps": 40000, "loss": 0.2655, "lr": 4.693228902825114e-07, "epoch": 30.712239050347932, "percentage": 93.83, "elapsed_time": "4:19:20", "remaining_time": "0:17:04", "throughput": 785.86, "total_tokens": 12228248} {"current_steps": 37535, "total_steps": 40000, "loss": 0.0826, "lr": 4.6743142315748277e-07, "epoch": 30.716332378223495, "percentage": 93.84, "elapsed_time": "4:19:22", "remaining_time": "0:17:01", "throughput": 785.87, "total_tokens": 12229832} {"current_steps": 37540, "total_steps": 40000, "loss": 0.2742, "lr": 4.655437392628276e-07, "epoch": 30.720425706099057, "percentage": 93.85, "elapsed_time": "4:19:23", "remaining_time": "0:16:59", "throughput": 785.89, "total_tokens": 12231368} {"current_steps": 37545, "total_steps": 40000, "loss": 0.1659, "lr": 4.636598388896463e-07, "epoch": 30.724519033974623, "percentage": 93.86, "elapsed_time": "4:19:25", "remaining_time": "0:16:57", "throughput": 785.9, "total_tokens": 12232952} {"current_steps": 37550, "total_steps": 40000, "loss": 0.2146, "lr": 4.6177972232845925e-07, "epoch": 30.728612361850185, "percentage": 93.88, "elapsed_time": "4:19:27", "remaining_time": "0:16:55", "throughput": 785.92, "total_tokens": 12234552} {"current_steps": 37555, "total_steps": 40000, "loss": 0.1373, "lr": 4.5990338986920953e-07, "epoch": 30.732705689725748, "percentage": 93.89, "elapsed_time": "4:19:28", "remaining_time": "0:16:53", "throughput": 785.93, "total_tokens": 12236152} {"current_steps": 37560, "total_steps": 40000, "loss": 0.1925, "lr": 4.5803084180124633e-07, "epoch": 30.73679901760131, "percentage": 93.9, "elapsed_time": "4:19:30", "remaining_time": "0:16:51", "throughput": 785.95, "total_tokens": 12237736} {"current_steps": 37565, "total_steps": 40000, "loss": 0.1516, "lr": 4.561620784133386e-07, "epoch": 30.740892345476873, "percentage": 93.91, "elapsed_time": "4:19:32", "remaining_time": "0:16:49", "throughput": 785.97, "total_tokens": 12239368} {"current_steps": 37570, "total_steps": 40000, "loss": 0.1764, "lr": 4.5429709999367796e-07, "epoch": 30.744985673352435, "percentage": 93.92, "elapsed_time": "4:19:34", "remaining_time": "0:16:47", "throughput": 785.98, "total_tokens": 12240984} {"current_steps": 37575, "total_steps": 40000, "loss": 0.1767, "lr": 4.5243590682986223e-07, "epoch": 30.749079001227997, "percentage": 93.94, "elapsed_time": "4:19:35", "remaining_time": "0:16:45", "throughput": 785.99, "total_tokens": 12242520} {"current_steps": 37580, "total_steps": 40000, "loss": 0.2055, "lr": 4.5057849920891735e-07, "epoch": 30.75317232910356, "percentage": 93.95, "elapsed_time": "4:19:37", "remaining_time": "0:16:43", "throughput": 786.01, "total_tokens": 12244168} {"current_steps": 37585, "total_steps": 40000, "loss": 0.29, "lr": 4.487248774172698e-07, "epoch": 30.757265656979126, "percentage": 93.96, "elapsed_time": "4:19:39", "remaining_time": "0:16:41", "throughput": 786.03, "total_tokens": 12245800} {"current_steps": 37590, "total_steps": 40000, "loss": 0.2588, "lr": 4.4687504174077965e-07, "epoch": 30.761358984854688, "percentage": 93.97, "elapsed_time": "4:19:40", "remaining_time": "0:16:38", "throughput": 786.05, "total_tokens": 12247432} {"current_steps": 37595, "total_steps": 40000, "loss": 0.1257, "lr": 4.450289924647133e-07, "epoch": 30.76545231273025, "percentage": 93.99, "elapsed_time": "4:19:42", "remaining_time": "0:16:36", "throughput": 786.07, "total_tokens": 12249016} {"current_steps": 37600, "total_steps": 40000, "loss": 0.1548, "lr": 4.431867298737513e-07, "epoch": 30.769545640605813, "percentage": 94.0, "elapsed_time": "4:19:44", "remaining_time": "0:16:34", "throughput": 786.09, "total_tokens": 12250664} {"current_steps": 37600, "total_steps": 40000, "eval_loss": 0.21478280425071716, "epoch": 30.769545640605813, "percentage": 94.0, "elapsed_time": "4:19:56", "remaining_time": "0:16:35", "throughput": 785.46, "total_tokens": 12250664} {"current_steps": 37605, "total_steps": 40000, "loss": 0.1676, "lr": 4.41348254251997e-07, "epoch": 30.773638968481375, "percentage": 94.01, "elapsed_time": "4:20:00", "remaining_time": "0:16:33", "throughput": 785.39, "total_tokens": 12252248} {"current_steps": 37610, "total_steps": 40000, "loss": 0.1463, "lr": 4.395135658829652e-07, "epoch": 30.777732296356938, "percentage": 94.03, "elapsed_time": "4:20:01", "remaining_time": "0:16:31", "throughput": 785.41, "total_tokens": 12253848} {"current_steps": 37615, "total_steps": 40000, "loss": 0.1222, "lr": 4.376826650495852e-07, "epoch": 30.7818256242325, "percentage": 94.04, "elapsed_time": "4:20:03", "remaining_time": "0:16:29", "throughput": 785.42, "total_tokens": 12255432} {"current_steps": 37620, "total_steps": 40000, "loss": 0.1924, "lr": 4.358555520342117e-07, "epoch": 30.785918952108062, "percentage": 94.05, "elapsed_time": "4:20:05", "remaining_time": "0:16:27", "throughput": 785.43, "total_tokens": 12256968} {"current_steps": 37625, "total_steps": 40000, "loss": 0.2372, "lr": 4.3403222711860257e-07, "epoch": 30.790012279983628, "percentage": 94.06, "elapsed_time": "4:20:07", "remaining_time": "0:16:25", "throughput": 785.45, "total_tokens": 12258568} {"current_steps": 37630, "total_steps": 40000, "loss": 0.2181, "lr": 4.3221269058394133e-07, "epoch": 30.79410560785919, "percentage": 94.08, "elapsed_time": "4:20:08", "remaining_time": "0:16:23", "throughput": 785.46, "total_tokens": 12260120} {"current_steps": 37635, "total_steps": 40000, "loss": 0.151, "lr": 4.303969427108173e-07, "epoch": 30.798198935734753, "percentage": 94.09, "elapsed_time": "4:20:10", "remaining_time": "0:16:20", "throughput": 785.48, "total_tokens": 12261800} {"current_steps": 37640, "total_steps": 40000, "loss": 0.1426, "lr": 4.2858498377924825e-07, "epoch": 30.802292263610315, "percentage": 94.1, "elapsed_time": "4:20:12", "remaining_time": "0:16:18", "throughput": 785.5, "total_tokens": 12263400} {"current_steps": 37645, "total_steps": 40000, "loss": 0.2085, "lr": 4.267768140686579e-07, "epoch": 30.806385591485878, "percentage": 94.11, "elapsed_time": "4:20:13", "remaining_time": "0:16:16", "throughput": 785.52, "total_tokens": 12265000} {"current_steps": 37650, "total_steps": 40000, "loss": 0.1681, "lr": 4.2497243385788975e-07, "epoch": 30.81047891936144, "percentage": 94.12, "elapsed_time": "4:20:15", "remaining_time": "0:16:14", "throughput": 785.53, "total_tokens": 12266632} {"current_steps": 37655, "total_steps": 40000, "loss": 0.1202, "lr": 4.231718434251991e-07, "epoch": 30.814572247237003, "percentage": 94.14, "elapsed_time": "4:20:17", "remaining_time": "0:16:12", "throughput": 785.55, "total_tokens": 12268232} {"current_steps": 37660, "total_steps": 40000, "loss": 0.2253, "lr": 4.213750430482666e-07, "epoch": 30.818665575112565, "percentage": 94.15, "elapsed_time": "4:20:19", "remaining_time": "0:16:10", "throughput": 785.57, "total_tokens": 12269832} {"current_steps": 37665, "total_steps": 40000, "loss": 0.1534, "lr": 4.1958203300417054e-07, "epoch": 30.82275890298813, "percentage": 94.16, "elapsed_time": "4:20:20", "remaining_time": "0:16:08", "throughput": 785.59, "total_tokens": 12271496} {"current_steps": 37670, "total_steps": 40000, "loss": 0.142, "lr": 4.177928135694259e-07, "epoch": 30.826852230863693, "percentage": 94.17, "elapsed_time": "4:20:22", "remaining_time": "0:16:06", "throughput": 785.6, "total_tokens": 12273112} {"current_steps": 37675, "total_steps": 40000, "loss": 0.1783, "lr": 4.1600738501994807e-07, "epoch": 30.830945558739256, "percentage": 94.19, "elapsed_time": "4:20:24", "remaining_time": "0:16:04", "throughput": 785.62, "total_tokens": 12274728} {"current_steps": 37680, "total_steps": 40000, "loss": 0.1589, "lr": 4.1422574763107237e-07, "epoch": 30.835038886614818, "percentage": 94.2, "elapsed_time": "4:20:25", "remaining_time": "0:16:02", "throughput": 785.64, "total_tokens": 12276376} {"current_steps": 37685, "total_steps": 40000, "loss": 0.1854, "lr": 4.124479016775512e-07, "epoch": 30.83913221449038, "percentage": 94.21, "elapsed_time": "4:20:27", "remaining_time": "0:16:00", "throughput": 785.66, "total_tokens": 12278040} {"current_steps": 37690, "total_steps": 40000, "loss": 0.1809, "lr": 4.106738474335514e-07, "epoch": 30.843225542365943, "percentage": 94.23, "elapsed_time": "4:20:29", "remaining_time": "0:15:57", "throughput": 785.68, "total_tokens": 12279704} {"current_steps": 37695, "total_steps": 40000, "loss": 0.2562, "lr": 4.089035851726486e-07, "epoch": 30.847318870241505, "percentage": 94.24, "elapsed_time": "4:20:31", "remaining_time": "0:15:55", "throughput": 785.69, "total_tokens": 12281320} {"current_steps": 37700, "total_steps": 40000, "loss": 0.1178, "lr": 4.0713711516784937e-07, "epoch": 30.851412198117067, "percentage": 94.25, "elapsed_time": "4:20:32", "remaining_time": "0:15:53", "throughput": 785.71, "total_tokens": 12282984} {"current_steps": 37705, "total_steps": 40000, "loss": 0.1491, "lr": 4.05374437691558e-07, "epoch": 30.855505525992633, "percentage": 94.26, "elapsed_time": "4:20:34", "remaining_time": "0:15:51", "throughput": 785.73, "total_tokens": 12284584} {"current_steps": 37710, "total_steps": 40000, "loss": 0.1917, "lr": 4.036155530156044e-07, "epoch": 30.859598853868196, "percentage": 94.27, "elapsed_time": "4:20:36", "remaining_time": "0:15:49", "throughput": 785.75, "total_tokens": 12286232} {"current_steps": 37715, "total_steps": 40000, "loss": 0.1626, "lr": 4.018604614112298e-07, "epoch": 30.863692181743758, "percentage": 94.29, "elapsed_time": "4:20:38", "remaining_time": "0:15:47", "throughput": 785.78, "total_tokens": 12287992} {"current_steps": 37720, "total_steps": 40000, "loss": 0.2347, "lr": 4.0010916314908996e-07, "epoch": 30.86778550961932, "percentage": 94.3, "elapsed_time": "4:20:39", "remaining_time": "0:15:45", "throughput": 785.79, "total_tokens": 12289624} {"current_steps": 37725, "total_steps": 40000, "loss": 0.2464, "lr": 3.983616584992578e-07, "epoch": 30.871878837494883, "percentage": 94.31, "elapsed_time": "4:20:41", "remaining_time": "0:15:43", "throughput": 785.81, "total_tokens": 12291224} {"current_steps": 37730, "total_steps": 40000, "loss": 0.2752, "lr": 3.9661794773122595e-07, "epoch": 30.875972165370445, "percentage": 94.33, "elapsed_time": "4:20:43", "remaining_time": "0:15:41", "throughput": 785.83, "total_tokens": 12292840} {"current_steps": 37735, "total_steps": 40000, "loss": 0.1444, "lr": 3.9487803111388777e-07, "epoch": 30.880065493246008, "percentage": 94.34, "elapsed_time": "4:20:44", "remaining_time": "0:15:39", "throughput": 785.85, "total_tokens": 12294536} {"current_steps": 37740, "total_steps": 40000, "loss": 0.1608, "lr": 3.9314190891556747e-07, "epoch": 30.884158821121574, "percentage": 94.35, "elapsed_time": "4:20:46", "remaining_time": "0:15:36", "throughput": 785.86, "total_tokens": 12296136} {"current_steps": 37745, "total_steps": 40000, "loss": 0.1901, "lr": 3.914095814039925e-07, "epoch": 30.888252148997136, "percentage": 94.36, "elapsed_time": "4:20:48", "remaining_time": "0:15:34", "throughput": 785.88, "total_tokens": 12297736} {"current_steps": 37750, "total_steps": 40000, "loss": 0.1316, "lr": 3.896810488463104e-07, "epoch": 30.8923454768727, "percentage": 94.38, "elapsed_time": "4:20:50", "remaining_time": "0:15:32", "throughput": 785.9, "total_tokens": 12299336} {"current_steps": 37755, "total_steps": 40000, "loss": 0.1304, "lr": 3.8795631150908565e-07, "epoch": 30.89643880474826, "percentage": 94.39, "elapsed_time": "4:20:51", "remaining_time": "0:15:30", "throughput": 785.91, "total_tokens": 12300968} {"current_steps": 37760, "total_steps": 40000, "loss": 0.2169, "lr": 3.862353696582888e-07, "epoch": 30.900532132623823, "percentage": 94.4, "elapsed_time": "4:20:53", "remaining_time": "0:15:28", "throughput": 785.93, "total_tokens": 12302552} {"current_steps": 37765, "total_steps": 40000, "loss": 0.198, "lr": 3.8451822355931313e-07, "epoch": 30.904625460499386, "percentage": 94.41, "elapsed_time": "4:20:55", "remaining_time": "0:15:26", "throughput": 785.95, "total_tokens": 12304168} {"current_steps": 37770, "total_steps": 40000, "loss": 0.1414, "lr": 3.82804873476969e-07, "epoch": 30.908718788374948, "percentage": 94.42, "elapsed_time": "4:20:56", "remaining_time": "0:15:24", "throughput": 785.97, "total_tokens": 12305832} {"current_steps": 37775, "total_steps": 40000, "loss": 0.1543, "lr": 3.810953196754702e-07, "epoch": 30.91281211625051, "percentage": 94.44, "elapsed_time": "4:20:58", "remaining_time": "0:15:22", "throughput": 785.99, "total_tokens": 12307464} {"current_steps": 37780, "total_steps": 40000, "loss": 0.1443, "lr": 3.793895624184529e-07, "epoch": 30.916905444126076, "percentage": 94.45, "elapsed_time": "4:21:00", "remaining_time": "0:15:20", "throughput": 786.0, "total_tokens": 12309016} {"current_steps": 37785, "total_steps": 40000, "loss": 0.1807, "lr": 3.776876019689679e-07, "epoch": 30.92099877200164, "percentage": 94.46, "elapsed_time": "4:21:02", "remaining_time": "0:15:18", "throughput": 786.01, "total_tokens": 12310632} {"current_steps": 37790, "total_steps": 40000, "loss": 0.1473, "lr": 3.7598943858947743e-07, "epoch": 30.9250920998772, "percentage": 94.47, "elapsed_time": "4:21:04", "remaining_time": "0:15:16", "throughput": 786.02, "total_tokens": 12312312} {"current_steps": 37795, "total_steps": 40000, "loss": 0.2251, "lr": 3.742950725418637e-07, "epoch": 30.929185427752763, "percentage": 94.49, "elapsed_time": "4:21:05", "remaining_time": "0:15:13", "throughput": 786.05, "total_tokens": 12314040} {"current_steps": 37800, "total_steps": 40000, "loss": 0.105, "lr": 3.726045040874093e-07, "epoch": 30.933278755628326, "percentage": 94.5, "elapsed_time": "4:21:07", "remaining_time": "0:15:11", "throughput": 786.07, "total_tokens": 12315704} {"current_steps": 37800, "total_steps": 40000, "eval_loss": 0.21417438983917236, "epoch": 30.933278755628326, "percentage": 94.5, "elapsed_time": "4:21:19", "remaining_time": "0:15:12", "throughput": 785.44, "total_tokens": 12315704} {"current_steps": 37805, "total_steps": 40000, "loss": 0.2459, "lr": 3.709177334868308e-07, "epoch": 30.937372083503888, "percentage": 94.51, "elapsed_time": "4:21:23", "remaining_time": "0:15:10", "throughput": 785.38, "total_tokens": 12317368} {"current_steps": 37810, "total_steps": 40000, "loss": 0.2652, "lr": 3.692347610002478e-07, "epoch": 30.94146541137945, "percentage": 94.53, "elapsed_time": "4:21:24", "remaining_time": "0:15:08", "throughput": 785.4, "total_tokens": 12319016} {"current_steps": 37815, "total_steps": 40000, "loss": 0.0804, "lr": 3.675555868871916e-07, "epoch": 30.945558739255013, "percentage": 94.54, "elapsed_time": "4:21:26", "remaining_time": "0:15:06", "throughput": 785.42, "total_tokens": 12320680} {"current_steps": 37820, "total_steps": 40000, "loss": 0.1335, "lr": 3.658802114066162e-07, "epoch": 30.94965206713058, "percentage": 94.55, "elapsed_time": "4:21:28", "remaining_time": "0:15:04", "throughput": 785.44, "total_tokens": 12322296} {"current_steps": 37825, "total_steps": 40000, "loss": 0.138, "lr": 3.6420863481688437e-07, "epoch": 30.95374539500614, "percentage": 94.56, "elapsed_time": "4:21:30", "remaining_time": "0:15:02", "throughput": 785.46, "total_tokens": 12323960} {"current_steps": 37830, "total_steps": 40000, "loss": 0.171, "lr": 3.625408573757705e-07, "epoch": 30.957838722881704, "percentage": 94.58, "elapsed_time": "4:21:31", "remaining_time": "0:15:00", "throughput": 785.48, "total_tokens": 12325640} {"current_steps": 37835, "total_steps": 40000, "loss": 0.147, "lr": 3.608768793404743e-07, "epoch": 30.961932050757266, "percentage": 94.59, "elapsed_time": "4:21:33", "remaining_time": "0:14:58", "throughput": 785.5, "total_tokens": 12327240} {"current_steps": 37840, "total_steps": 40000, "loss": 0.1672, "lr": 3.592167009675934e-07, "epoch": 30.96602537863283, "percentage": 94.6, "elapsed_time": "4:21:35", "remaining_time": "0:14:55", "throughput": 785.51, "total_tokens": 12328840} {"current_steps": 37845, "total_steps": 40000, "loss": 0.2075, "lr": 3.575603225131563e-07, "epoch": 30.97011870650839, "percentage": 94.61, "elapsed_time": "4:21:36", "remaining_time": "0:14:53", "throughput": 785.53, "total_tokens": 12330520} {"current_steps": 37850, "total_steps": 40000, "loss": 0.2296, "lr": 3.55907744232592e-07, "epoch": 30.974212034383953, "percentage": 94.62, "elapsed_time": "4:21:38", "remaining_time": "0:14:51", "throughput": 785.55, "total_tokens": 12332104} {"current_steps": 37855, "total_steps": 40000, "loss": 0.2125, "lr": 3.5425896638075217e-07, "epoch": 30.978305362259515, "percentage": 94.64, "elapsed_time": "4:21:40", "remaining_time": "0:14:49", "throughput": 785.57, "total_tokens": 12333768} {"current_steps": 37860, "total_steps": 40000, "loss": 0.2165, "lr": 3.5261398921189736e-07, "epoch": 30.98239869013508, "percentage": 94.65, "elapsed_time": "4:21:42", "remaining_time": "0:14:47", "throughput": 785.59, "total_tokens": 12335416} {"current_steps": 37865, "total_steps": 40000, "loss": 0.1145, "lr": 3.509728129797024e-07, "epoch": 30.986492018010644, "percentage": 94.66, "elapsed_time": "4:21:43", "remaining_time": "0:14:45", "throughput": 785.6, "total_tokens": 12337032} {"current_steps": 37870, "total_steps": 40000, "loss": 0.1513, "lr": 3.4933543793725656e-07, "epoch": 30.990585345886206, "percentage": 94.67, "elapsed_time": "4:21:45", "remaining_time": "0:14:43", "throughput": 785.62, "total_tokens": 12338696} {"current_steps": 37875, "total_steps": 40000, "loss": 0.2484, "lr": 3.4770186433707163e-07, "epoch": 30.99467867376177, "percentage": 94.69, "elapsed_time": "4:21:47", "remaining_time": "0:14:41", "throughput": 785.64, "total_tokens": 12340328} {"current_steps": 37880, "total_steps": 40000, "loss": 0.162, "lr": 3.4607209243105453e-07, "epoch": 30.99877200163733, "percentage": 94.7, "elapsed_time": "4:21:49", "remaining_time": "0:14:39", "throughput": 785.66, "total_tokens": 12341944} {"current_steps": 37885, "total_steps": 40000, "loss": 0.2325, "lr": 3.444461224705431e-07, "epoch": 31.002455996725338, "percentage": 94.71, "elapsed_time": "4:21:50", "remaining_time": "0:14:37", "throughput": 785.65, "total_tokens": 12343288} {"current_steps": 37890, "total_steps": 40000, "loss": 0.1713, "lr": 3.4282395470628116e-07, "epoch": 31.0065493246009, "percentage": 94.73, "elapsed_time": "4:21:52", "remaining_time": "0:14:34", "throughput": 785.67, "total_tokens": 12344888} {"current_steps": 37895, "total_steps": 40000, "loss": 0.1617, "lr": 3.4120558938842417e-07, "epoch": 31.010642652476463, "percentage": 94.74, "elapsed_time": "4:21:54", "remaining_time": "0:14:32", "throughput": 785.68, "total_tokens": 12346520} {"current_steps": 37900, "total_steps": 40000, "loss": 0.1546, "lr": 3.395910267665503e-07, "epoch": 31.014735980352025, "percentage": 94.75, "elapsed_time": "4:21:56", "remaining_time": "0:14:30", "throughput": 785.7, "total_tokens": 12348152} {"current_steps": 37905, "total_steps": 40000, "loss": 0.1706, "lr": 3.3798026708964094e-07, "epoch": 31.018829308227588, "percentage": 94.76, "elapsed_time": "4:21:57", "remaining_time": "0:14:28", "throughput": 785.72, "total_tokens": 12349832} {"current_steps": 37910, "total_steps": 40000, "loss": 0.1567, "lr": 3.3637331060609456e-07, "epoch": 31.022922636103154, "percentage": 94.77, "elapsed_time": "4:21:59", "remaining_time": "0:14:26", "throughput": 785.74, "total_tokens": 12351400} {"current_steps": 37915, "total_steps": 40000, "loss": 0.1835, "lr": 3.3477015756372966e-07, "epoch": 31.027015963978716, "percentage": 94.79, "elapsed_time": "4:22:01", "remaining_time": "0:14:24", "throughput": 785.75, "total_tokens": 12353032} {"current_steps": 37920, "total_steps": 40000, "loss": 0.1302, "lr": 3.3317080820976785e-07, "epoch": 31.03110929185428, "percentage": 94.8, "elapsed_time": "4:22:02", "remaining_time": "0:14:22", "throughput": 785.77, "total_tokens": 12354696} {"current_steps": 37925, "total_steps": 40000, "loss": 0.2714, "lr": 3.315752627908508e-07, "epoch": 31.03520261972984, "percentage": 94.81, "elapsed_time": "4:22:04", "remaining_time": "0:14:20", "throughput": 785.78, "total_tokens": 12356232} {"current_steps": 37930, "total_steps": 40000, "loss": 0.1244, "lr": 3.299835215530317e-07, "epoch": 31.039295947605403, "percentage": 94.83, "elapsed_time": "4:22:06", "remaining_time": "0:14:18", "throughput": 785.8, "total_tokens": 12357832} {"current_steps": 37935, "total_steps": 40000, "loss": 0.2334, "lr": 3.2839558474177245e-07, "epoch": 31.043389275480965, "percentage": 94.84, "elapsed_time": "4:22:08", "remaining_time": "0:14:16", "throughput": 785.82, "total_tokens": 12359448} {"current_steps": 37940, "total_steps": 40000, "loss": 0.1487, "lr": 3.2681145260196056e-07, "epoch": 31.047482603356528, "percentage": 94.85, "elapsed_time": "4:22:09", "remaining_time": "0:14:14", "throughput": 785.84, "total_tokens": 12361160} {"current_steps": 37945, "total_steps": 40000, "loss": 0.1893, "lr": 3.252311253778839e-07, "epoch": 31.05157593123209, "percentage": 94.86, "elapsed_time": "4:22:11", "remaining_time": "0:14:11", "throughput": 785.86, "total_tokens": 12362808} {"current_steps": 37950, "total_steps": 40000, "loss": 0.2398, "lr": 3.2365460331325034e-07, "epoch": 31.055669259107656, "percentage": 94.88, "elapsed_time": "4:22:13", "remaining_time": "0:14:09", "throughput": 785.88, "total_tokens": 12364488} {"current_steps": 37955, "total_steps": 40000, "loss": 0.1159, "lr": 3.2208188665117934e-07, "epoch": 31.05976258698322, "percentage": 94.89, "elapsed_time": "4:22:15", "remaining_time": "0:14:07", "throughput": 785.9, "total_tokens": 12366136} {"current_steps": 37960, "total_steps": 40000, "loss": 0.216, "lr": 3.205129756342018e-07, "epoch": 31.06385591485878, "percentage": 94.9, "elapsed_time": "4:22:16", "remaining_time": "0:14:05", "throughput": 785.91, "total_tokens": 12367704} {"current_steps": 37965, "total_steps": 40000, "loss": 0.1078, "lr": 3.189478705042659e-07, "epoch": 31.067949242734343, "percentage": 94.91, "elapsed_time": "4:22:18", "remaining_time": "0:14:03", "throughput": 785.93, "total_tokens": 12369288} {"current_steps": 37970, "total_steps": 40000, "loss": 0.1375, "lr": 3.173865715027341e-07, "epoch": 31.072042570609906, "percentage": 94.92, "elapsed_time": "4:22:20", "remaining_time": "0:14:01", "throughput": 785.94, "total_tokens": 12370904} {"current_steps": 37975, "total_steps": 40000, "loss": 0.1266, "lr": 3.158290788703694e-07, "epoch": 31.076135898485468, "percentage": 94.94, "elapsed_time": "4:22:21", "remaining_time": "0:13:59", "throughput": 785.96, "total_tokens": 12372520} {"current_steps": 37980, "total_steps": 40000, "loss": 0.2134, "lr": 3.1427539284736297e-07, "epoch": 31.08022922636103, "percentage": 94.95, "elapsed_time": "4:22:23", "remaining_time": "0:13:57", "throughput": 785.98, "total_tokens": 12374136} {"current_steps": 37985, "total_steps": 40000, "loss": 0.1796, "lr": 3.127255136733093e-07, "epoch": 31.084322554236593, "percentage": 94.96, "elapsed_time": "4:22:25", "remaining_time": "0:13:55", "throughput": 786.0, "total_tokens": 12375800} {"current_steps": 37990, "total_steps": 40000, "loss": 0.1817, "lr": 3.1117944158722544e-07, "epoch": 31.08841588211216, "percentage": 94.97, "elapsed_time": "4:22:27", "remaining_time": "0:13:53", "throughput": 786.02, "total_tokens": 12377480} {"current_steps": 37995, "total_steps": 40000, "loss": 0.1181, "lr": 3.0963717682752635e-07, "epoch": 31.09250920998772, "percentage": 94.99, "elapsed_time": "4:22:28", "remaining_time": "0:13:51", "throughput": 786.04, "total_tokens": 12379128} {"current_steps": 38000, "total_steps": 40000, "loss": 0.23, "lr": 3.080987196320578e-07, "epoch": 31.096602537863284, "percentage": 95.0, "elapsed_time": "4:22:30", "remaining_time": "0:13:48", "throughput": 786.06, "total_tokens": 12380824} {"current_steps": 38000, "total_steps": 40000, "eval_loss": 0.2123337835073471, "epoch": 31.096602537863284, "percentage": 95.0, "elapsed_time": "4:22:42", "remaining_time": "0:13:49", "throughput": 785.44, "total_tokens": 12380824} {"current_steps": 38005, "total_steps": 40000, "loss": 0.1287, "lr": 3.065640702380607e-07, "epoch": 31.100695865738846, "percentage": 95.01, "elapsed_time": "4:22:46", "remaining_time": "0:13:47", "throughput": 785.38, "total_tokens": 12382488} {"current_steps": 38010, "total_steps": 40000, "loss": 0.1307, "lr": 3.050332288822011e-07, "epoch": 31.10478919361441, "percentage": 95.03, "elapsed_time": "4:22:47", "remaining_time": "0:13:45", "throughput": 785.4, "total_tokens": 12384120} {"current_steps": 38015, "total_steps": 40000, "loss": 0.1721, "lr": 3.035061958005542e-07, "epoch": 31.10888252148997, "percentage": 95.04, "elapsed_time": "4:22:49", "remaining_time": "0:13:43", "throughput": 785.41, "total_tokens": 12385704} {"current_steps": 38020, "total_steps": 40000, "loss": 0.1719, "lr": 3.019829712286093e-07, "epoch": 31.112975849365533, "percentage": 95.05, "elapsed_time": "4:22:51", "remaining_time": "0:13:41", "throughput": 785.44, "total_tokens": 12387512} {"current_steps": 38025, "total_steps": 40000, "loss": 0.2113, "lr": 3.004635554012647e-07, "epoch": 31.117069177241095, "percentage": 95.06, "elapsed_time": "4:22:53", "remaining_time": "0:13:39", "throughput": 785.46, "total_tokens": 12389176} {"current_steps": 38030, "total_steps": 40000, "loss": 0.1892, "lr": 2.9894794855283017e-07, "epoch": 31.12116250511666, "percentage": 95.08, "elapsed_time": "4:22:54", "remaining_time": "0:13:37", "throughput": 785.48, "total_tokens": 12390728} {"current_steps": 38035, "total_steps": 40000, "loss": 0.1357, "lr": 2.9743615091703816e-07, "epoch": 31.125255832992224, "percentage": 95.09, "elapsed_time": "4:22:56", "remaining_time": "0:13:35", "throughput": 785.49, "total_tokens": 12392344} {"current_steps": 38040, "total_steps": 40000, "loss": 0.1717, "lr": 2.959281627270216e-07, "epoch": 31.129349160867786, "percentage": 95.1, "elapsed_time": "4:22:58", "remaining_time": "0:13:32", "throughput": 785.51, "total_tokens": 12393912} {"current_steps": 38045, "total_steps": 40000, "loss": 0.0907, "lr": 2.944239842153362e-07, "epoch": 31.13344248874335, "percentage": 95.11, "elapsed_time": "4:22:59", "remaining_time": "0:13:30", "throughput": 785.53, "total_tokens": 12395544} {"current_steps": 38050, "total_steps": 40000, "loss": 0.1267, "lr": 2.929236156139381e-07, "epoch": 31.13753581661891, "percentage": 95.12, "elapsed_time": "4:23:01", "remaining_time": "0:13:28", "throughput": 785.55, "total_tokens": 12397208} {"current_steps": 38055, "total_steps": 40000, "loss": 0.1529, "lr": 2.9142705715420883e-07, "epoch": 31.141629144494473, "percentage": 95.14, "elapsed_time": "4:23:03", "remaining_time": "0:13:26", "throughput": 785.56, "total_tokens": 12398808} {"current_steps": 38060, "total_steps": 40000, "loss": 0.1252, "lr": 2.8993430906693595e-07, "epoch": 31.145722472370036, "percentage": 95.15, "elapsed_time": "4:23:05", "remaining_time": "0:13:24", "throughput": 785.58, "total_tokens": 12400456} {"current_steps": 38065, "total_steps": 40000, "loss": 0.123, "lr": 2.88445371582316e-07, "epoch": 31.149815800245598, "percentage": 95.16, "elapsed_time": "4:23:06", "remaining_time": "0:13:22", "throughput": 785.6, "total_tokens": 12402088} {"current_steps": 38070, "total_steps": 40000, "loss": 0.1104, "lr": 2.8696024492996796e-07, "epoch": 31.153909128121164, "percentage": 95.17, "elapsed_time": "4:23:08", "remaining_time": "0:13:20", "throughput": 785.62, "total_tokens": 12403736} {"current_steps": 38075, "total_steps": 40000, "loss": 0.1391, "lr": 2.854789293389115e-07, "epoch": 31.158002455996726, "percentage": 95.19, "elapsed_time": "4:23:10", "remaining_time": "0:13:18", "throughput": 785.63, "total_tokens": 12405368} {"current_steps": 38080, "total_steps": 40000, "loss": 0.1463, "lr": 2.8400142503758606e-07, "epoch": 31.16209578387229, "percentage": 95.2, "elapsed_time": "4:23:11", "remaining_time": "0:13:16", "throughput": 785.65, "total_tokens": 12407032} {"current_steps": 38085, "total_steps": 40000, "loss": 0.2181, "lr": 2.8252773225384276e-07, "epoch": 31.16618911174785, "percentage": 95.21, "elapsed_time": "4:23:13", "remaining_time": "0:13:14", "throughput": 785.67, "total_tokens": 12408696} {"current_steps": 38090, "total_steps": 40000, "loss": 0.1441, "lr": 2.8105785121494143e-07, "epoch": 31.170282439623413, "percentage": 95.23, "elapsed_time": "4:23:15", "remaining_time": "0:13:12", "throughput": 785.69, "total_tokens": 12410344} {"current_steps": 38095, "total_steps": 40000, "loss": 0.1884, "lr": 2.795917821475563e-07, "epoch": 31.174375767498976, "percentage": 95.24, "elapsed_time": "4:23:17", "remaining_time": "0:13:09", "throughput": 785.72, "total_tokens": 12412056} {"current_steps": 38100, "total_steps": 40000, "loss": 0.1277, "lr": 2.78129525277776e-07, "epoch": 31.17846909537454, "percentage": 95.25, "elapsed_time": "4:23:18", "remaining_time": "0:13:07", "throughput": 785.73, "total_tokens": 12413656} {"current_steps": 38105, "total_steps": 40000, "loss": 0.2053, "lr": 2.766710808310952e-07, "epoch": 31.1825624232501, "percentage": 95.26, "elapsed_time": "4:23:20", "remaining_time": "0:13:05", "throughput": 785.75, "total_tokens": 12415240} {"current_steps": 38110, "total_steps": 40000, "loss": 0.1708, "lr": 2.7521644903242827e-07, "epoch": 31.186655751125667, "percentage": 95.28, "elapsed_time": "4:23:22", "remaining_time": "0:13:03", "throughput": 785.76, "total_tokens": 12416872} {"current_steps": 38115, "total_steps": 40000, "loss": 0.1893, "lr": 2.7376563010609593e-07, "epoch": 31.19074907900123, "percentage": 95.29, "elapsed_time": "4:23:23", "remaining_time": "0:13:01", "throughput": 785.78, "total_tokens": 12418536} {"current_steps": 38120, "total_steps": 40000, "loss": 0.1755, "lr": 2.72318624275833e-07, "epoch": 31.19484240687679, "percentage": 95.3, "elapsed_time": "4:23:25", "remaining_time": "0:12:59", "throughput": 785.8, "total_tokens": 12420184} {"current_steps": 38125, "total_steps": 40000, "loss": 0.1625, "lr": 2.7087543176478324e-07, "epoch": 31.198935734752354, "percentage": 95.31, "elapsed_time": "4:23:27", "remaining_time": "0:12:57", "throughput": 785.82, "total_tokens": 12421720} {"current_steps": 38130, "total_steps": 40000, "loss": 0.1395, "lr": 2.694360527955103e-07, "epoch": 31.203029062627916, "percentage": 95.33, "elapsed_time": "4:23:29", "remaining_time": "0:12:55", "throughput": 785.83, "total_tokens": 12423368} {"current_steps": 38135, "total_steps": 40000, "loss": 0.1208, "lr": 2.680004875899811e-07, "epoch": 31.20712239050348, "percentage": 95.34, "elapsed_time": "4:23:30", "remaining_time": "0:12:53", "throughput": 785.85, "total_tokens": 12425032} {"current_steps": 38140, "total_steps": 40000, "loss": 0.1747, "lr": 2.665687363695768e-07, "epoch": 31.21121571837904, "percentage": 95.35, "elapsed_time": "4:23:32", "remaining_time": "0:12:51", "throughput": 785.87, "total_tokens": 12426680} {"current_steps": 38145, "total_steps": 40000, "loss": 0.2585, "lr": 2.6514079935509584e-07, "epoch": 31.215309046254603, "percentage": 95.36, "elapsed_time": "4:23:34", "remaining_time": "0:12:49", "throughput": 785.89, "total_tokens": 12428296} {"current_steps": 38150, "total_steps": 40000, "loss": 0.18, "lr": 2.6371667676673983e-07, "epoch": 31.21940237413017, "percentage": 95.38, "elapsed_time": "4:23:36", "remaining_time": "0:12:46", "throughput": 785.91, "total_tokens": 12429960} {"current_steps": 38155, "total_steps": 40000, "loss": 0.1704, "lr": 2.6229636882412755e-07, "epoch": 31.22349570200573, "percentage": 95.39, "elapsed_time": "4:23:37", "remaining_time": "0:12:44", "throughput": 785.92, "total_tokens": 12431544} {"current_steps": 38160, "total_steps": 40000, "loss": 0.1753, "lr": 2.6087987574628935e-07, "epoch": 31.227589029881294, "percentage": 95.4, "elapsed_time": "4:23:39", "remaining_time": "0:12:42", "throughput": 785.95, "total_tokens": 12433288} {"current_steps": 38165, "total_steps": 40000, "loss": 0.1915, "lr": 2.5946719775166437e-07, "epoch": 31.231682357756856, "percentage": 95.41, "elapsed_time": "4:23:41", "remaining_time": "0:12:40", "throughput": 785.97, "total_tokens": 12434936} {"current_steps": 38170, "total_steps": 40000, "loss": 0.228, "lr": 2.5805833505810616e-07, "epoch": 31.23577568563242, "percentage": 95.43, "elapsed_time": "4:23:42", "remaining_time": "0:12:38", "throughput": 785.99, "total_tokens": 12436552} {"current_steps": 38175, "total_steps": 40000, "loss": 0.2039, "lr": 2.566532878828798e-07, "epoch": 31.23986901350798, "percentage": 95.44, "elapsed_time": "4:23:44", "remaining_time": "0:12:36", "throughput": 786.01, "total_tokens": 12438264} {"current_steps": 38180, "total_steps": 40000, "loss": 0.1013, "lr": 2.552520564426619e-07, "epoch": 31.243962341383543, "percentage": 95.45, "elapsed_time": "4:23:46", "remaining_time": "0:12:34", "throughput": 786.03, "total_tokens": 12439880} {"current_steps": 38185, "total_steps": 40000, "loss": 0.1612, "lr": 2.5385464095353803e-07, "epoch": 31.24805566925911, "percentage": 95.46, "elapsed_time": "4:23:48", "remaining_time": "0:12:32", "throughput": 786.05, "total_tokens": 12441592} {"current_steps": 38190, "total_steps": 40000, "loss": 0.0671, "lr": 2.5246104163100804e-07, "epoch": 31.25214899713467, "percentage": 95.47, "elapsed_time": "4:23:49", "remaining_time": "0:12:30", "throughput": 786.07, "total_tokens": 12443208} {"current_steps": 38195, "total_steps": 40000, "loss": 0.1966, "lr": 2.510712586899833e-07, "epoch": 31.256242325010234, "percentage": 95.49, "elapsed_time": "4:23:51", "remaining_time": "0:12:28", "throughput": 786.08, "total_tokens": 12444808} {"current_steps": 38200, "total_steps": 40000, "loss": 0.1433, "lr": 2.4968529234478124e-07, "epoch": 31.260335652885797, "percentage": 95.5, "elapsed_time": "4:23:53", "remaining_time": "0:12:26", "throughput": 786.1, "total_tokens": 12446424} {"current_steps": 38200, "total_steps": 40000, "eval_loss": 0.21315647661685944, "epoch": 31.260335652885797, "percentage": 95.5, "elapsed_time": "4:24:05", "remaining_time": "0:12:26", "throughput": 785.48, "total_tokens": 12446424} {"current_steps": 38205, "total_steps": 40000, "loss": 0.1376, "lr": 2.483031428091448e-07, "epoch": 31.26442898076136, "percentage": 95.51, "elapsed_time": "4:24:08", "remaining_time": "0:12:24", "throughput": 785.42, "total_tokens": 12448040} {"current_steps": 38210, "total_steps": 40000, "loss": 0.1567, "lr": 2.469248102962091e-07, "epoch": 31.26852230863692, "percentage": 95.53, "elapsed_time": "4:24:10", "remaining_time": "0:12:22", "throughput": 785.45, "total_tokens": 12449848} {"current_steps": 38215, "total_steps": 40000, "loss": 0.1323, "lr": 2.4555029501853455e-07, "epoch": 31.272615636512484, "percentage": 95.54, "elapsed_time": "4:24:12", "remaining_time": "0:12:20", "throughput": 785.46, "total_tokens": 12451432} {"current_steps": 38220, "total_steps": 40000, "loss": 0.2034, "lr": 2.441795971880906e-07, "epoch": 31.276708964388046, "percentage": 95.55, "elapsed_time": "4:24:14", "remaining_time": "0:12:18", "throughput": 785.48, "total_tokens": 12453048} {"current_steps": 38225, "total_steps": 40000, "loss": 0.1736, "lr": 2.4281271701625255e-07, "epoch": 31.280802292263612, "percentage": 95.56, "elapsed_time": "4:24:15", "remaining_time": "0:12:16", "throughput": 785.49, "total_tokens": 12454664} {"current_steps": 38230, "total_steps": 40000, "loss": 0.1782, "lr": 2.4144965471381007e-07, "epoch": 31.284895620139174, "percentage": 95.58, "elapsed_time": "4:24:17", "remaining_time": "0:12:14", "throughput": 785.51, "total_tokens": 12456296} {"current_steps": 38235, "total_steps": 40000, "loss": 0.1078, "lr": 2.400904104909674e-07, "epoch": 31.288988948014737, "percentage": 95.59, "elapsed_time": "4:24:19", "remaining_time": "0:12:12", "throughput": 785.53, "total_tokens": 12457928} {"current_steps": 38240, "total_steps": 40000, "loss": 0.2562, "lr": 2.3873498455733725e-07, "epoch": 31.2930822758903, "percentage": 95.6, "elapsed_time": "4:24:20", "remaining_time": "0:12:10", "throughput": 785.55, "total_tokens": 12459560} {"current_steps": 38245, "total_steps": 40000, "loss": 0.1633, "lr": 2.3738337712194137e-07, "epoch": 31.29717560376586, "percentage": 95.61, "elapsed_time": "4:24:22", "remaining_time": "0:12:07", "throughput": 785.56, "total_tokens": 12461192} {"current_steps": 38250, "total_steps": 40000, "loss": 0.0914, "lr": 2.3603558839321305e-07, "epoch": 31.301268931641424, "percentage": 95.62, "elapsed_time": "4:24:24", "remaining_time": "0:12:05", "throughput": 785.58, "total_tokens": 12462824} {"current_steps": 38255, "total_steps": 40000, "loss": 0.2155, "lr": 2.3469161857900267e-07, "epoch": 31.305362259516986, "percentage": 95.64, "elapsed_time": "4:24:26", "remaining_time": "0:12:03", "throughput": 785.6, "total_tokens": 12464504} {"current_steps": 38260, "total_steps": 40000, "loss": 0.1383, "lr": 2.3335146788656393e-07, "epoch": 31.30945558739255, "percentage": 95.65, "elapsed_time": "4:24:27", "remaining_time": "0:12:01", "throughput": 785.62, "total_tokens": 12466104} {"current_steps": 38265, "total_steps": 40000, "loss": 0.1875, "lr": 2.3201513652256757e-07, "epoch": 31.313548915268115, "percentage": 95.66, "elapsed_time": "4:24:29", "remaining_time": "0:11:59", "throughput": 785.64, "total_tokens": 12467736} {"current_steps": 38270, "total_steps": 40000, "loss": 0.2045, "lr": 2.3068262469308766e-07, "epoch": 31.317642243143677, "percentage": 95.67, "elapsed_time": "4:24:31", "remaining_time": "0:11:57", "throughput": 785.66, "total_tokens": 12469432} {"current_steps": 38275, "total_steps": 40000, "loss": 0.2552, "lr": 2.2935393260362093e-07, "epoch": 31.32173557101924, "percentage": 95.69, "elapsed_time": "4:24:33", "remaining_time": "0:11:55", "throughput": 785.68, "total_tokens": 12471048} {"current_steps": 38280, "total_steps": 40000, "loss": 0.1494, "lr": 2.2802906045906458e-07, "epoch": 31.3258288988948, "percentage": 95.7, "elapsed_time": "4:24:34", "remaining_time": "0:11:53", "throughput": 785.69, "total_tokens": 12472696} {"current_steps": 38285, "total_steps": 40000, "loss": 0.1195, "lr": 2.2670800846373018e-07, "epoch": 31.329922226770364, "percentage": 95.71, "elapsed_time": "4:24:36", "remaining_time": "0:11:51", "throughput": 785.71, "total_tokens": 12474344} {"current_steps": 38290, "total_steps": 40000, "loss": 0.2012, "lr": 2.2539077682134367e-07, "epoch": 31.334015554645926, "percentage": 95.73, "elapsed_time": "4:24:38", "remaining_time": "0:11:49", "throughput": 785.73, "total_tokens": 12476040} {"current_steps": 38295, "total_steps": 40000, "loss": 0.126, "lr": 2.2407736573503423e-07, "epoch": 31.33810888252149, "percentage": 95.74, "elapsed_time": "4:24:39", "remaining_time": "0:11:47", "throughput": 785.75, "total_tokens": 12477640} {"current_steps": 38300, "total_steps": 40000, "loss": 0.2077, "lr": 2.2276777540735093e-07, "epoch": 31.34220221039705, "percentage": 95.75, "elapsed_time": "4:24:41", "remaining_time": "0:11:44", "throughput": 785.77, "total_tokens": 12479336} {"current_steps": 38305, "total_steps": 40000, "loss": 0.1895, "lr": 2.2146200604024613e-07, "epoch": 31.346295538272617, "percentage": 95.76, "elapsed_time": "4:24:43", "remaining_time": "0:11:42", "throughput": 785.79, "total_tokens": 12480968} {"current_steps": 38310, "total_steps": 40000, "loss": 0.1599, "lr": 2.2016005783508375e-07, "epoch": 31.35038886614818, "percentage": 95.78, "elapsed_time": "4:24:45", "remaining_time": "0:11:40", "throughput": 785.81, "total_tokens": 12482584} {"current_steps": 38315, "total_steps": 40000, "loss": 0.1984, "lr": 2.1886193099264763e-07, "epoch": 31.354482194023742, "percentage": 95.79, "elapsed_time": "4:24:46", "remaining_time": "0:11:38", "throughput": 785.82, "total_tokens": 12484232} {"current_steps": 38320, "total_steps": 40000, "loss": 0.1493, "lr": 2.175676257131165e-07, "epoch": 31.358575521899304, "percentage": 95.8, "elapsed_time": "4:24:48", "remaining_time": "0:11:36", "throughput": 785.84, "total_tokens": 12485912} {"current_steps": 38325, "total_steps": 40000, "loss": 0.2262, "lr": 2.162771421960974e-07, "epoch": 31.362668849774867, "percentage": 95.81, "elapsed_time": "4:24:50", "remaining_time": "0:11:34", "throughput": 785.86, "total_tokens": 12487480} {"current_steps": 38330, "total_steps": 40000, "loss": 0.1726, "lr": 2.1499048064059224e-07, "epoch": 31.36676217765043, "percentage": 95.83, "elapsed_time": "4:24:51", "remaining_time": "0:11:32", "throughput": 785.88, "total_tokens": 12489144} {"current_steps": 38335, "total_steps": 40000, "loss": 0.1106, "lr": 2.1370764124502285e-07, "epoch": 31.37085550552599, "percentage": 95.84, "elapsed_time": "4:24:53", "remaining_time": "0:11:30", "throughput": 785.9, "total_tokens": 12490808} {"current_steps": 38340, "total_steps": 40000, "loss": 0.1414, "lr": 2.1242862420721988e-07, "epoch": 31.374948833401554, "percentage": 95.85, "elapsed_time": "4:24:55", "remaining_time": "0:11:28", "throughput": 785.92, "total_tokens": 12492456} {"current_steps": 38345, "total_steps": 40000, "loss": 0.1407, "lr": 2.1115342972442276e-07, "epoch": 31.37904216127712, "percentage": 95.86, "elapsed_time": "4:24:57", "remaining_time": "0:11:26", "throughput": 785.94, "total_tokens": 12494104} {"current_steps": 38350, "total_steps": 40000, "loss": 0.0778, "lr": 2.0988205799328252e-07, "epoch": 31.383135489152682, "percentage": 95.88, "elapsed_time": "4:24:58", "remaining_time": "0:11:24", "throughput": 785.95, "total_tokens": 12495688} {"current_steps": 38355, "total_steps": 40000, "loss": 0.1361, "lr": 2.0861450920986182e-07, "epoch": 31.387228817028245, "percentage": 95.89, "elapsed_time": "4:25:00", "remaining_time": "0:11:21", "throughput": 785.96, "total_tokens": 12497272} {"current_steps": 38360, "total_steps": 40000, "loss": 0.1655, "lr": 2.07350783569632e-07, "epoch": 31.391322144903807, "percentage": 95.9, "elapsed_time": "4:25:02", "remaining_time": "0:11:19", "throughput": 785.98, "total_tokens": 12498872} {"current_steps": 38365, "total_steps": 40000, "loss": 0.2065, "lr": 2.060908812674761e-07, "epoch": 31.39541547277937, "percentage": 95.91, "elapsed_time": "4:25:04", "remaining_time": "0:11:17", "throughput": 786.0, "total_tokens": 12500488} {"current_steps": 38370, "total_steps": 40000, "loss": 0.156, "lr": 2.0483480249768317e-07, "epoch": 31.39950880065493, "percentage": 95.93, "elapsed_time": "4:25:05", "remaining_time": "0:11:15", "throughput": 786.01, "total_tokens": 12502136} {"current_steps": 38375, "total_steps": 40000, "loss": 0.1252, "lr": 2.035825474539621e-07, "epoch": 31.403602128530494, "percentage": 95.94, "elapsed_time": "4:25:07", "remaining_time": "0:11:13", "throughput": 786.03, "total_tokens": 12503752} {"current_steps": 38380, "total_steps": 40000, "loss": 0.1764, "lr": 2.0233411632942235e-07, "epoch": 31.407695456406056, "percentage": 95.95, "elapsed_time": "4:25:09", "remaining_time": "0:11:11", "throughput": 786.05, "total_tokens": 12505352} {"current_steps": 38385, "total_steps": 40000, "loss": 0.1474, "lr": 2.0108950931658764e-07, "epoch": 31.411788784281622, "percentage": 95.96, "elapsed_time": "4:25:10", "remaining_time": "0:11:09", "throughput": 786.06, "total_tokens": 12506952} {"current_steps": 38390, "total_steps": 40000, "loss": 0.1085, "lr": 1.998487266073934e-07, "epoch": 31.415882112157185, "percentage": 95.97, "elapsed_time": "4:25:12", "remaining_time": "0:11:07", "throughput": 786.08, "total_tokens": 12508568} {"current_steps": 38395, "total_steps": 40000, "loss": 0.1705, "lr": 1.986117683931865e-07, "epoch": 31.419975440032747, "percentage": 95.99, "elapsed_time": "4:25:14", "remaining_time": "0:11:05", "throughput": 786.1, "total_tokens": 12510200} {"current_steps": 38400, "total_steps": 40000, "loss": 0.2038, "lr": 1.9737863486471442e-07, "epoch": 31.42406876790831, "percentage": 96.0, "elapsed_time": "4:25:16", "remaining_time": "0:11:03", "throughput": 786.11, "total_tokens": 12511800} {"current_steps": 38400, "total_steps": 40000, "eval_loss": 0.21295985579490662, "epoch": 31.42406876790831, "percentage": 96.0, "elapsed_time": "4:25:28", "remaining_time": "0:11:03", "throughput": 785.5, "total_tokens": 12511800} {"current_steps": 38405, "total_steps": 40000, "loss": 0.177, "lr": 1.9614932621215e-07, "epoch": 31.428162095783872, "percentage": 96.01, "elapsed_time": "4:25:31", "remaining_time": "0:11:01", "throughput": 785.43, "total_tokens": 12513448} {"current_steps": 38410, "total_steps": 40000, "loss": 0.2296, "lr": 1.9492384262506102e-07, "epoch": 31.432255423659434, "percentage": 96.03, "elapsed_time": "4:25:33", "remaining_time": "0:10:59", "throughput": 785.45, "total_tokens": 12515064} {"current_steps": 38415, "total_steps": 40000, "loss": 0.2084, "lr": 1.9370218429243524e-07, "epoch": 31.436348751534997, "percentage": 96.04, "elapsed_time": "4:25:35", "remaining_time": "0:10:57", "throughput": 785.47, "total_tokens": 12516664} {"current_steps": 38420, "total_steps": 40000, "loss": 0.1304, "lr": 1.9248435140267197e-07, "epoch": 31.44044207941056, "percentage": 96.05, "elapsed_time": "4:25:37", "remaining_time": "0:10:55", "throughput": 785.48, "total_tokens": 12518296} {"current_steps": 38425, "total_steps": 40000, "loss": 0.1856, "lr": 1.9127034414356814e-07, "epoch": 31.444535407286125, "percentage": 96.06, "elapsed_time": "4:25:38", "remaining_time": "0:10:53", "throughput": 785.5, "total_tokens": 12519880} {"current_steps": 38430, "total_steps": 40000, "loss": 0.171, "lr": 1.9006016270234627e-07, "epoch": 31.448628735161687, "percentage": 96.08, "elapsed_time": "4:25:40", "remaining_time": "0:10:51", "throughput": 785.51, "total_tokens": 12521432} {"current_steps": 38435, "total_steps": 40000, "loss": 0.2079, "lr": 1.888538072656293e-07, "epoch": 31.45272206303725, "percentage": 96.09, "elapsed_time": "4:25:42", "remaining_time": "0:10:49", "throughput": 785.53, "total_tokens": 12523096} {"current_steps": 38440, "total_steps": 40000, "loss": 0.2206, "lr": 1.8765127801944893e-07, "epoch": 31.456815390912812, "percentage": 96.1, "elapsed_time": "4:25:43", "remaining_time": "0:10:47", "throughput": 785.55, "total_tokens": 12524744} {"current_steps": 38445, "total_steps": 40000, "loss": 0.1645, "lr": 1.8645257514925406e-07, "epoch": 31.460908718788374, "percentage": 96.11, "elapsed_time": "4:25:45", "remaining_time": "0:10:44", "throughput": 785.57, "total_tokens": 12526360} {"current_steps": 38450, "total_steps": 40000, "loss": 0.1229, "lr": 1.8525769883989685e-07, "epoch": 31.465002046663937, "percentage": 96.12, "elapsed_time": "4:25:47", "remaining_time": "0:10:42", "throughput": 785.58, "total_tokens": 12527960} {"current_steps": 38455, "total_steps": 40000, "loss": 0.1816, "lr": 1.8406664927564654e-07, "epoch": 31.4690953745395, "percentage": 96.14, "elapsed_time": "4:25:49", "remaining_time": "0:10:40", "throughput": 785.6, "total_tokens": 12529624} {"current_steps": 38460, "total_steps": 40000, "loss": 0.2161, "lr": 1.8287942664017566e-07, "epoch": 31.473188702415065, "percentage": 96.15, "elapsed_time": "4:25:50", "remaining_time": "0:10:38", "throughput": 785.62, "total_tokens": 12531240} {"current_steps": 38465, "total_steps": 40000, "loss": 0.1096, "lr": 1.8169603111656552e-07, "epoch": 31.477282030290628, "percentage": 96.16, "elapsed_time": "4:25:52", "remaining_time": "0:10:36", "throughput": 785.64, "total_tokens": 12532856} {"current_steps": 38470, "total_steps": 40000, "loss": 0.1684, "lr": 1.805164628873146e-07, "epoch": 31.48137535816619, "percentage": 96.17, "elapsed_time": "4:25:54", "remaining_time": "0:10:34", "throughput": 785.65, "total_tokens": 12534472} {"current_steps": 38475, "total_steps": 40000, "loss": 0.0912, "lr": 1.793407221343274e-07, "epoch": 31.485468686041752, "percentage": 96.19, "elapsed_time": "4:25:55", "remaining_time": "0:10:32", "throughput": 785.67, "total_tokens": 12536088} {"current_steps": 38480, "total_steps": 40000, "loss": 0.227, "lr": 1.781688090389172e-07, "epoch": 31.489562013917315, "percentage": 96.2, "elapsed_time": "4:25:57", "remaining_time": "0:10:30", "throughput": 785.69, "total_tokens": 12537736} {"current_steps": 38485, "total_steps": 40000, "loss": 0.1652, "lr": 1.770007237818061e-07, "epoch": 31.493655341792877, "percentage": 96.21, "elapsed_time": "4:25:59", "remaining_time": "0:10:28", "throughput": 785.7, "total_tokens": 12539336} {"current_steps": 38490, "total_steps": 40000, "loss": 0.1573, "lr": 1.7583646654313059e-07, "epoch": 31.49774866966844, "percentage": 96.23, "elapsed_time": "4:26:01", "remaining_time": "0:10:26", "throughput": 785.72, "total_tokens": 12541000} {"current_steps": 38495, "total_steps": 40000, "loss": 0.1014, "lr": 1.7467603750242757e-07, "epoch": 31.501841997544002, "percentage": 96.24, "elapsed_time": "4:26:02", "remaining_time": "0:10:24", "throughput": 785.75, "total_tokens": 12542712} {"current_steps": 38500, "total_steps": 40000, "loss": 0.1903, "lr": 1.7351943683865944e-07, "epoch": 31.505935325419568, "percentage": 96.25, "elapsed_time": "4:26:04", "remaining_time": "0:10:21", "throughput": 785.77, "total_tokens": 12544456} {"current_steps": 38505, "total_steps": 40000, "loss": 0.167, "lr": 1.723666647301808e-07, "epoch": 31.51002865329513, "percentage": 96.26, "elapsed_time": "4:26:06", "remaining_time": "0:10:19", "throughput": 785.79, "total_tokens": 12546120} {"current_steps": 38510, "total_steps": 40000, "loss": 0.2412, "lr": 1.712177213547661e-07, "epoch": 31.514121981170693, "percentage": 96.28, "elapsed_time": "4:26:07", "remaining_time": "0:10:17", "throughput": 785.81, "total_tokens": 12547736} {"current_steps": 38515, "total_steps": 40000, "loss": 0.1516, "lr": 1.7007260688959581e-07, "epoch": 31.518215309046255, "percentage": 96.29, "elapsed_time": "4:26:09", "remaining_time": "0:10:15", "throughput": 785.82, "total_tokens": 12549352} {"current_steps": 38520, "total_steps": 40000, "loss": 0.2141, "lr": 1.68931321511262e-07, "epoch": 31.522308636921817, "percentage": 96.3, "elapsed_time": "4:26:11", "remaining_time": "0:10:13", "throughput": 785.84, "total_tokens": 12550952} {"current_steps": 38525, "total_steps": 40000, "loss": 0.1631, "lr": 1.6779386539576835e-07, "epoch": 31.52640196479738, "percentage": 96.31, "elapsed_time": "4:26:13", "remaining_time": "0:10:11", "throughput": 785.86, "total_tokens": 12552584} {"current_steps": 38530, "total_steps": 40000, "loss": 0.1247, "lr": 1.666602387185162e-07, "epoch": 31.530495292672942, "percentage": 96.33, "elapsed_time": "4:26:14", "remaining_time": "0:10:09", "throughput": 785.87, "total_tokens": 12554200} {"current_steps": 38535, "total_steps": 40000, "loss": 0.1996, "lr": 1.655304416543352e-07, "epoch": 31.534588620548504, "percentage": 96.34, "elapsed_time": "4:26:16", "remaining_time": "0:10:07", "throughput": 785.89, "total_tokens": 12555768} {"current_steps": 38540, "total_steps": 40000, "loss": 0.2121, "lr": 1.6440447437744698e-07, "epoch": 31.53868194842407, "percentage": 96.35, "elapsed_time": "4:26:18", "remaining_time": "0:10:05", "throughput": 785.9, "total_tokens": 12557336} {"current_steps": 38545, "total_steps": 40000, "loss": 0.1506, "lr": 1.6328233706149332e-07, "epoch": 31.542775276299633, "percentage": 96.36, "elapsed_time": "4:26:19", "remaining_time": "0:10:03", "throughput": 785.92, "total_tokens": 12559016} {"current_steps": 38550, "total_steps": 40000, "loss": 0.1867, "lr": 1.6216402987951906e-07, "epoch": 31.546868604175195, "percentage": 96.38, "elapsed_time": "4:26:21", "remaining_time": "0:10:01", "throughput": 785.94, "total_tokens": 12560648} {"current_steps": 38555, "total_steps": 40000, "loss": 0.1843, "lr": 1.6104955300398627e-07, "epoch": 31.550961932050757, "percentage": 96.39, "elapsed_time": "4:26:23", "remaining_time": "0:09:59", "throughput": 785.96, "total_tokens": 12562328} {"current_steps": 38560, "total_steps": 40000, "loss": 0.1162, "lr": 1.5993890660675748e-07, "epoch": 31.55505525992632, "percentage": 96.4, "elapsed_time": "4:26:25", "remaining_time": "0:09:56", "throughput": 785.98, "total_tokens": 12563928} {"current_steps": 38565, "total_steps": 40000, "loss": 0.0858, "lr": 1.5883209085910678e-07, "epoch": 31.559148587801882, "percentage": 96.41, "elapsed_time": "4:26:26", "remaining_time": "0:09:54", "throughput": 785.99, "total_tokens": 12565544} {"current_steps": 38570, "total_steps": 40000, "loss": 0.1323, "lr": 1.5772910593172264e-07, "epoch": 31.563241915677445, "percentage": 96.43, "elapsed_time": "4:26:28", "remaining_time": "0:09:52", "throughput": 786.01, "total_tokens": 12567176} {"current_steps": 38575, "total_steps": 40000, "loss": 0.198, "lr": 1.5662995199469954e-07, "epoch": 31.567335243553007, "percentage": 96.44, "elapsed_time": "4:26:30", "remaining_time": "0:09:50", "throughput": 786.03, "total_tokens": 12568824} {"current_steps": 38580, "total_steps": 40000, "loss": 0.2136, "lr": 1.5553462921753802e-07, "epoch": 31.571428571428573, "percentage": 96.45, "elapsed_time": "4:26:32", "remaining_time": "0:09:48", "throughput": 786.05, "total_tokens": 12570472} {"current_steps": 38585, "total_steps": 40000, "loss": 0.2138, "lr": 1.544431377691502e-07, "epoch": 31.575521899304135, "percentage": 96.46, "elapsed_time": "4:26:33", "remaining_time": "0:09:46", "throughput": 786.06, "total_tokens": 12572056} {"current_steps": 38590, "total_steps": 40000, "loss": 0.1679, "lr": 1.5335547781785975e-07, "epoch": 31.579615227179698, "percentage": 96.47, "elapsed_time": "4:26:35", "remaining_time": "0:09:44", "throughput": 786.08, "total_tokens": 12573672} {"current_steps": 38595, "total_steps": 40000, "loss": 0.1815, "lr": 1.5227164953139917e-07, "epoch": 31.58370855505526, "percentage": 96.49, "elapsed_time": "4:26:37", "remaining_time": "0:09:42", "throughput": 786.09, "total_tokens": 12575288} {"current_steps": 38600, "total_steps": 40000, "loss": 0.2055, "lr": 1.511916530769042e-07, "epoch": 31.587801882930822, "percentage": 96.5, "elapsed_time": "4:26:38", "remaining_time": "0:09:40", "throughput": 786.11, "total_tokens": 12576920} {"current_steps": 38600, "total_steps": 40000, "eval_loss": 0.21360130608081818, "epoch": 31.587801882930822, "percentage": 96.5, "elapsed_time": "4:26:51", "remaining_time": "0:09:40", "throughput": 785.5, "total_tokens": 12576920} {"current_steps": 38605, "total_steps": 40000, "loss": 0.2321, "lr": 1.5011548862092773e-07, "epoch": 31.591895210806385, "percentage": 96.51, "elapsed_time": "4:26:54", "remaining_time": "0:09:38", "throughput": 785.44, "total_tokens": 12578568} {"current_steps": 38610, "total_steps": 40000, "loss": 0.1644, "lr": 1.490431563294231e-07, "epoch": 31.595988538681947, "percentage": 96.53, "elapsed_time": "4:26:56", "remaining_time": "0:09:36", "throughput": 785.45, "total_tokens": 12580120} {"current_steps": 38615, "total_steps": 40000, "loss": 0.2386, "lr": 1.4797465636776365e-07, "epoch": 31.60008186655751, "percentage": 96.54, "elapsed_time": "4:26:58", "remaining_time": "0:09:34", "throughput": 785.47, "total_tokens": 12581672} {"current_steps": 38620, "total_steps": 40000, "loss": 0.2334, "lr": 1.4690998890072027e-07, "epoch": 31.604175194433076, "percentage": 96.55, "elapsed_time": "4:26:59", "remaining_time": "0:09:32", "throughput": 785.48, "total_tokens": 12583272} {"current_steps": 38625, "total_steps": 40000, "loss": 0.2175, "lr": 1.4584915409248112e-07, "epoch": 31.608268522308638, "percentage": 96.56, "elapsed_time": "4:27:01", "remaining_time": "0:09:30", "throughput": 785.5, "total_tokens": 12584872} {"current_steps": 38630, "total_steps": 40000, "loss": 0.1535, "lr": 1.4479215210663754e-07, "epoch": 31.6123618501842, "percentage": 96.58, "elapsed_time": "4:27:03", "remaining_time": "0:09:28", "throughput": 785.51, "total_tokens": 12586488} {"current_steps": 38635, "total_steps": 40000, "loss": 0.2717, "lr": 1.4373898310619528e-07, "epoch": 31.616455178059763, "percentage": 96.59, "elapsed_time": "4:27:04", "remaining_time": "0:09:26", "throughput": 785.53, "total_tokens": 12588088} {"current_steps": 38640, "total_steps": 40000, "loss": 0.1693, "lr": 1.4268964725356604e-07, "epoch": 31.620548505935325, "percentage": 96.6, "elapsed_time": "4:27:06", "remaining_time": "0:09:24", "throughput": 785.55, "total_tokens": 12589688} {"current_steps": 38645, "total_steps": 40000, "loss": 0.2237, "lr": 1.4164414471056764e-07, "epoch": 31.624641833810887, "percentage": 96.61, "elapsed_time": "4:27:08", "remaining_time": "0:09:21", "throughput": 785.56, "total_tokens": 12591224} {"current_steps": 38650, "total_steps": 40000, "loss": 0.1123, "lr": 1.4060247563843497e-07, "epoch": 31.62873516168645, "percentage": 96.62, "elapsed_time": "4:27:10", "remaining_time": "0:09:19", "throughput": 785.57, "total_tokens": 12592808} {"current_steps": 38655, "total_steps": 40000, "loss": 0.1796, "lr": 1.3956464019780068e-07, "epoch": 31.632828489562012, "percentage": 96.64, "elapsed_time": "4:27:11", "remaining_time": "0:09:17", "throughput": 785.59, "total_tokens": 12594472} {"current_steps": 38660, "total_steps": 40000, "loss": 0.1546, "lr": 1.385306385487145e-07, "epoch": 31.636921817437578, "percentage": 96.65, "elapsed_time": "4:27:13", "remaining_time": "0:09:15", "throughput": 785.61, "total_tokens": 12596104} {"current_steps": 38665, "total_steps": 40000, "loss": 0.1647, "lr": 1.3750047085063222e-07, "epoch": 31.64101514531314, "percentage": 96.66, "elapsed_time": "4:27:15", "remaining_time": "0:09:13", "throughput": 785.62, "total_tokens": 12597704} {"current_steps": 38670, "total_steps": 40000, "loss": 0.1349, "lr": 1.3647413726242119e-07, "epoch": 31.645108473188703, "percentage": 96.67, "elapsed_time": "4:27:17", "remaining_time": "0:09:11", "throughput": 785.64, "total_tokens": 12599368} {"current_steps": 38675, "total_steps": 40000, "loss": 0.2302, "lr": 1.3545163794235205e-07, "epoch": 31.649201801064265, "percentage": 96.69, "elapsed_time": "4:27:18", "remaining_time": "0:09:09", "throughput": 785.66, "total_tokens": 12601000} {"current_steps": 38680, "total_steps": 40000, "loss": 0.1114, "lr": 1.3443297304810698e-07, "epoch": 31.653295128939828, "percentage": 96.7, "elapsed_time": "4:27:20", "remaining_time": "0:09:07", "throughput": 785.68, "total_tokens": 12602600} {"current_steps": 38685, "total_steps": 40000, "loss": 0.2222, "lr": 1.3341814273677977e-07, "epoch": 31.65738845681539, "percentage": 96.71, "elapsed_time": "4:27:22", "remaining_time": "0:09:05", "throughput": 785.69, "total_tokens": 12604232} {"current_steps": 38690, "total_steps": 40000, "loss": 0.2271, "lr": 1.324071471648647e-07, "epoch": 31.661481784690952, "percentage": 96.73, "elapsed_time": "4:27:23", "remaining_time": "0:09:03", "throughput": 785.72, "total_tokens": 12605960} {"current_steps": 38695, "total_steps": 40000, "loss": 0.1983, "lr": 1.3139998648827312e-07, "epoch": 31.665575112566515, "percentage": 96.74, "elapsed_time": "4:27:25", "remaining_time": "0:09:01", "throughput": 785.74, "total_tokens": 12607624} {"current_steps": 38700, "total_steps": 40000, "loss": 0.2328, "lr": 1.3039666086232526e-07, "epoch": 31.66966844044208, "percentage": 96.75, "elapsed_time": "4:27:27", "remaining_time": "0:08:59", "throughput": 785.76, "total_tokens": 12609288} {"current_steps": 38705, "total_steps": 40000, "loss": 0.1486, "lr": 1.2939717044174183e-07, "epoch": 31.673761768317643, "percentage": 96.76, "elapsed_time": "4:27:29", "remaining_time": "0:08:56", "throughput": 785.77, "total_tokens": 12610856} {"current_steps": 38710, "total_steps": 40000, "loss": 0.1427, "lr": 1.284015153806578e-07, "epoch": 31.677855096193205, "percentage": 96.78, "elapsed_time": "4:27:30", "remaining_time": "0:08:54", "throughput": 785.79, "total_tokens": 12612504} {"current_steps": 38715, "total_steps": 40000, "loss": 0.1604, "lr": 1.274096958326171e-07, "epoch": 31.681948424068768, "percentage": 96.79, "elapsed_time": "4:27:32", "remaining_time": "0:08:52", "throughput": 785.81, "total_tokens": 12614152} {"current_steps": 38720, "total_steps": 40000, "loss": 0.1655, "lr": 1.2642171195056952e-07, "epoch": 31.68604175194433, "percentage": 96.8, "elapsed_time": "4:27:34", "remaining_time": "0:08:50", "throughput": 785.82, "total_tokens": 12615768} {"current_steps": 38725, "total_steps": 40000, "loss": 0.2368, "lr": 1.2543756388687377e-07, "epoch": 31.690135079819893, "percentage": 96.81, "elapsed_time": "4:27:35", "remaining_time": "0:08:48", "throughput": 785.84, "total_tokens": 12617368} {"current_steps": 38730, "total_steps": 40000, "loss": 0.1785, "lr": 1.2445725179330014e-07, "epoch": 31.694228407695455, "percentage": 96.83, "elapsed_time": "4:27:37", "remaining_time": "0:08:46", "throughput": 785.86, "total_tokens": 12619000} {"current_steps": 38735, "total_steps": 40000, "loss": 0.2184, "lr": 1.2348077582102212e-07, "epoch": 31.69832173557102, "percentage": 96.84, "elapsed_time": "4:27:39", "remaining_time": "0:08:44", "throughput": 785.88, "total_tokens": 12620648} {"current_steps": 38740, "total_steps": 40000, "loss": 0.1251, "lr": 1.2250813612062762e-07, "epoch": 31.702415063446583, "percentage": 96.85, "elapsed_time": "4:27:41", "remaining_time": "0:08:42", "throughput": 785.89, "total_tokens": 12622248} {"current_steps": 38745, "total_steps": 40000, "loss": 0.1646, "lr": 1.215393328421105e-07, "epoch": 31.706508391322146, "percentage": 96.86, "elapsed_time": "4:27:42", "remaining_time": "0:08:40", "throughput": 785.91, "total_tokens": 12623848} {"current_steps": 38750, "total_steps": 40000, "loss": 0.1255, "lr": 1.2057436613486796e-07, "epoch": 31.710601719197708, "percentage": 96.88, "elapsed_time": "4:27:44", "remaining_time": "0:08:38", "throughput": 785.92, "total_tokens": 12625448} {"current_steps": 38755, "total_steps": 40000, "loss": 0.179, "lr": 1.1961323614771424e-07, "epoch": 31.71469504707327, "percentage": 96.89, "elapsed_time": "4:27:46", "remaining_time": "0:08:36", "throughput": 785.94, "total_tokens": 12627096} {"current_steps": 38760, "total_steps": 40000, "loss": 0.2315, "lr": 1.1865594302886418e-07, "epoch": 31.718788374948833, "percentage": 96.9, "elapsed_time": "4:27:47", "remaining_time": "0:08:34", "throughput": 785.95, "total_tokens": 12628664} {"current_steps": 38765, "total_steps": 40000, "loss": 0.2338, "lr": 1.1770248692594687e-07, "epoch": 31.722881702824395, "percentage": 96.91, "elapsed_time": "4:27:49", "remaining_time": "0:08:31", "throughput": 785.97, "total_tokens": 12630280} {"current_steps": 38770, "total_steps": 40000, "loss": 0.259, "lr": 1.167528679859975e-07, "epoch": 31.726975030699958, "percentage": 96.92, "elapsed_time": "4:27:51", "remaining_time": "0:08:29", "throughput": 785.99, "total_tokens": 12631960} {"current_steps": 38775, "total_steps": 40000, "loss": 0.1981, "lr": 1.1580708635545446e-07, "epoch": 31.731068358575524, "percentage": 96.94, "elapsed_time": "4:27:53", "remaining_time": "0:08:27", "throughput": 786.01, "total_tokens": 12633576} {"current_steps": 38780, "total_steps": 40000, "loss": 0.1543, "lr": 1.1486514218017885e-07, "epoch": 31.735161686451086, "percentage": 96.95, "elapsed_time": "4:27:54", "remaining_time": "0:08:25", "throughput": 786.03, "total_tokens": 12635256} {"current_steps": 38785, "total_steps": 40000, "loss": 0.1872, "lr": 1.1392703560542117e-07, "epoch": 31.73925501432665, "percentage": 96.96, "elapsed_time": "4:27:56", "remaining_time": "0:08:23", "throughput": 786.04, "total_tokens": 12636856} {"current_steps": 38790, "total_steps": 40000, "loss": 0.1839, "lr": 1.129927667758518e-07, "epoch": 31.74334834220221, "percentage": 96.97, "elapsed_time": "4:27:58", "remaining_time": "0:08:21", "throughput": 786.07, "total_tokens": 12638616} {"current_steps": 38795, "total_steps": 40000, "loss": 0.1402, "lr": 1.1206233583554992e-07, "epoch": 31.747441670077773, "percentage": 96.99, "elapsed_time": "4:27:59", "remaining_time": "0:08:19", "throughput": 786.09, "total_tokens": 12640248} {"current_steps": 38800, "total_steps": 40000, "loss": 0.2024, "lr": 1.1113574292799523e-07, "epoch": 31.751534997953335, "percentage": 97.0, "elapsed_time": "4:28:01", "remaining_time": "0:08:17", "throughput": 786.11, "total_tokens": 12641896} {"current_steps": 38800, "total_steps": 40000, "eval_loss": 0.21606408059597015, "epoch": 31.751534997953335, "percentage": 97.0, "elapsed_time": "4:28:14", "remaining_time": "0:08:17", "throughput": 785.5, "total_tokens": 12641896} {"current_steps": 38805, "total_steps": 40000, "loss": 0.1767, "lr": 1.1021298819608449e-07, "epoch": 31.755628325828898, "percentage": 97.01, "elapsed_time": "4:28:17", "remaining_time": "0:08:15", "throughput": 785.43, "total_tokens": 12643496} {"current_steps": 38810, "total_steps": 40000, "loss": 0.1627, "lr": 1.0929407178211226e-07, "epoch": 31.75972165370446, "percentage": 97.02, "elapsed_time": "4:28:19", "remaining_time": "0:08:13", "throughput": 785.45, "total_tokens": 12645032} {"current_steps": 38815, "total_steps": 40000, "loss": 0.0775, "lr": 1.0837899382779293e-07, "epoch": 31.763814981580026, "percentage": 97.04, "elapsed_time": "4:28:20", "remaining_time": "0:08:11", "throughput": 785.46, "total_tokens": 12646664} {"current_steps": 38820, "total_steps": 40000, "loss": 0.1992, "lr": 1.0746775447423862e-07, "epoch": 31.76790830945559, "percentage": 97.05, "elapsed_time": "4:28:22", "remaining_time": "0:08:09", "throughput": 785.48, "total_tokens": 12648280} {"current_steps": 38825, "total_steps": 40000, "loss": 0.1587, "lr": 1.0656035386197583e-07, "epoch": 31.77200163733115, "percentage": 97.06, "elapsed_time": "4:28:24", "remaining_time": "0:08:07", "throughput": 785.5, "total_tokens": 12649912} {"current_steps": 38830, "total_steps": 40000, "loss": 0.1591, "lr": 1.0565679213093982e-07, "epoch": 31.776094965206713, "percentage": 97.08, "elapsed_time": "4:28:26", "remaining_time": "0:08:05", "throughput": 785.52, "total_tokens": 12651576} {"current_steps": 38835, "total_steps": 40000, "loss": 0.1613, "lr": 1.0475706942046638e-07, "epoch": 31.780188293082276, "percentage": 97.09, "elapsed_time": "4:28:27", "remaining_time": "0:08:03", "throughput": 785.53, "total_tokens": 12653128} {"current_steps": 38840, "total_steps": 40000, "loss": 0.267, "lr": 1.0386118586930282e-07, "epoch": 31.784281620957838, "percentage": 97.1, "elapsed_time": "4:28:29", "remaining_time": "0:08:01", "throughput": 785.55, "total_tokens": 12654712} {"current_steps": 38845, "total_steps": 40000, "loss": 0.195, "lr": 1.0296914161561367e-07, "epoch": 31.7883749488334, "percentage": 97.11, "elapsed_time": "4:28:31", "remaining_time": "0:07:59", "throughput": 785.56, "total_tokens": 12656328} {"current_steps": 38850, "total_steps": 40000, "loss": 0.2457, "lr": 1.0208093679695552e-07, "epoch": 31.792468276708963, "percentage": 97.12, "elapsed_time": "4:28:32", "remaining_time": "0:07:56", "throughput": 785.57, "total_tokens": 12657848} {"current_steps": 38855, "total_steps": 40000, "loss": 0.1776, "lr": 1.0119657155030493e-07, "epoch": 31.79656160458453, "percentage": 97.14, "elapsed_time": "4:28:34", "remaining_time": "0:07:54", "throughput": 785.59, "total_tokens": 12659464} {"current_steps": 38860, "total_steps": 40000, "loss": 0.193, "lr": 1.003160460120417e-07, "epoch": 31.80065493246009, "percentage": 97.15, "elapsed_time": "4:28:36", "remaining_time": "0:07:52", "throughput": 785.61, "total_tokens": 12661096} {"current_steps": 38865, "total_steps": 40000, "loss": 0.247, "lr": 9.943936031795165e-08, "epoch": 31.804748260335653, "percentage": 97.16, "elapsed_time": "4:28:38", "remaining_time": "0:07:50", "throughput": 785.63, "total_tokens": 12662760} {"current_steps": 38870, "total_steps": 40000, "loss": 0.133, "lr": 9.856651460323219e-08, "epoch": 31.808841588211216, "percentage": 97.17, "elapsed_time": "4:28:39", "remaining_time": "0:07:48", "throughput": 785.64, "total_tokens": 12664328} {"current_steps": 38875, "total_steps": 40000, "loss": 0.1506, "lr": 9.769750900248953e-08, "epoch": 31.81293491608678, "percentage": 97.19, "elapsed_time": "4:28:41", "remaining_time": "0:07:46", "throughput": 785.66, "total_tokens": 12666008} {"current_steps": 38880, "total_steps": 40000, "loss": 0.1068, "lr": 9.683234364973038e-08, "epoch": 31.81702824396234, "percentage": 97.2, "elapsed_time": "4:28:43", "remaining_time": "0:07:44", "throughput": 785.68, "total_tokens": 12667624} {"current_steps": 38885, "total_steps": 40000, "loss": 0.3288, "lr": 9.597101867837854e-08, "epoch": 31.821121571837903, "percentage": 97.21, "elapsed_time": "4:28:44", "remaining_time": "0:07:42", "throughput": 785.69, "total_tokens": 12669272} {"current_steps": 38890, "total_steps": 40000, "loss": 0.2635, "lr": 9.511353422125835e-08, "epoch": 31.825214899713465, "percentage": 97.22, "elapsed_time": "4:28:46", "remaining_time": "0:07:40", "throughput": 785.71, "total_tokens": 12670872} {"current_steps": 38895, "total_steps": 40000, "loss": 0.1592, "lr": 9.42598904106029e-08, "epoch": 31.82930822758903, "percentage": 97.24, "elapsed_time": "4:28:48", "remaining_time": "0:07:38", "throughput": 785.73, "total_tokens": 12672472} {"current_steps": 38900, "total_steps": 40000, "loss": 0.2243, "lr": 9.341008737806245e-08, "epoch": 31.833401555464594, "percentage": 97.25, "elapsed_time": "4:28:50", "remaining_time": "0:07:36", "throughput": 785.75, "total_tokens": 12674168} {"current_steps": 38905, "total_steps": 40000, "loss": 0.1398, "lr": 9.256412525467661e-08, "epoch": 31.837494883340156, "percentage": 97.26, "elapsed_time": "4:28:51", "remaining_time": "0:07:34", "throughput": 785.76, "total_tokens": 12675752} {"current_steps": 38910, "total_steps": 40000, "loss": 0.2072, "lr": 9.172200417091326e-08, "epoch": 31.84158821121572, "percentage": 97.28, "elapsed_time": "4:28:53", "remaining_time": "0:07:31", "throughput": 785.77, "total_tokens": 12677304} {"current_steps": 38915, "total_steps": 40000, "loss": 0.1735, "lr": 9.088372425663239e-08, "epoch": 31.84568153909128, "percentage": 97.29, "elapsed_time": "4:28:55", "remaining_time": "0:07:29", "throughput": 785.79, "total_tokens": 12678872} {"current_steps": 38920, "total_steps": 40000, "loss": 0.1863, "lr": 9.004928564110837e-08, "epoch": 31.849774866966843, "percentage": 97.3, "elapsed_time": "4:28:56", "remaining_time": "0:07:27", "throughput": 785.81, "total_tokens": 12680520} {"current_steps": 38925, "total_steps": 40000, "loss": 0.2116, "lr": 8.92186884530244e-08, "epoch": 31.853868194842406, "percentage": 97.31, "elapsed_time": "4:28:58", "remaining_time": "0:07:25", "throughput": 785.82, "total_tokens": 12682136} {"current_steps": 38930, "total_steps": 40000, "loss": 0.1216, "lr": 8.83919328204641e-08, "epoch": 31.857961522717968, "percentage": 97.32, "elapsed_time": "4:29:00", "remaining_time": "0:07:23", "throughput": 785.84, "total_tokens": 12683768} {"current_steps": 38935, "total_steps": 40000, "loss": 0.1611, "lr": 8.756901887093105e-08, "epoch": 31.862054850593534, "percentage": 97.34, "elapsed_time": "4:29:02", "remaining_time": "0:07:21", "throughput": 785.85, "total_tokens": 12685352} {"current_steps": 38940, "total_steps": 40000, "loss": 0.1236, "lr": 8.674994673132098e-08, "epoch": 31.866148178469096, "percentage": 97.35, "elapsed_time": "4:29:03", "remaining_time": "0:07:19", "throughput": 785.87, "total_tokens": 12686968} {"current_steps": 38945, "total_steps": 40000, "loss": 0.1206, "lr": 8.593471652794949e-08, "epoch": 31.87024150634466, "percentage": 97.36, "elapsed_time": "4:29:05", "remaining_time": "0:07:17", "throughput": 785.89, "total_tokens": 12688568} {"current_steps": 38950, "total_steps": 40000, "loss": 0.1446, "lr": 8.512332838653548e-08, "epoch": 31.87433483422022, "percentage": 97.38, "elapsed_time": "4:29:07", "remaining_time": "0:07:15", "throughput": 785.9, "total_tokens": 12690168} {"current_steps": 38955, "total_steps": 40000, "loss": 0.1905, "lr": 8.431578243220106e-08, "epoch": 31.878428162095783, "percentage": 97.39, "elapsed_time": "4:29:09", "remaining_time": "0:07:13", "throughput": 785.92, "total_tokens": 12691784} {"current_steps": 38960, "total_steps": 40000, "loss": 0.2024, "lr": 8.351207878948552e-08, "epoch": 31.882521489971346, "percentage": 97.4, "elapsed_time": "4:29:10", "remaining_time": "0:07:11", "throughput": 785.93, "total_tokens": 12693400} {"current_steps": 38965, "total_steps": 40000, "loss": 0.238, "lr": 8.271221758232583e-08, "epoch": 31.886614817846908, "percentage": 97.41, "elapsed_time": "4:29:12", "remaining_time": "0:07:09", "throughput": 785.95, "total_tokens": 12695080} {"current_steps": 38970, "total_steps": 40000, "loss": 0.1485, "lr": 8.191619893407332e-08, "epoch": 31.89070814572247, "percentage": 97.42, "elapsed_time": "4:29:14", "remaining_time": "0:07:06", "throughput": 785.97, "total_tokens": 12696712} {"current_steps": 38975, "total_steps": 40000, "loss": 0.1987, "lr": 8.112402296748534e-08, "epoch": 31.894801473598037, "percentage": 97.44, "elapsed_time": "4:29:15", "remaining_time": "0:07:04", "throughput": 785.99, "total_tokens": 12698344} {"current_steps": 38980, "total_steps": 40000, "loss": 0.1345, "lr": 8.033568980471973e-08, "epoch": 31.8988948014736, "percentage": 97.45, "elapsed_time": "4:29:17", "remaining_time": "0:07:02", "throughput": 786.0, "total_tokens": 12699912} {"current_steps": 38985, "total_steps": 40000, "loss": 0.1764, "lr": 7.955119956735146e-08, "epoch": 31.90298812934916, "percentage": 97.46, "elapsed_time": "4:29:19", "remaining_time": "0:07:00", "throughput": 786.02, "total_tokens": 12701576} {"current_steps": 38990, "total_steps": 40000, "loss": 0.1915, "lr": 7.877055237636155e-08, "epoch": 31.907081457224724, "percentage": 97.47, "elapsed_time": "4:29:21", "remaining_time": "0:06:58", "throughput": 786.04, "total_tokens": 12703176} {"current_steps": 38995, "total_steps": 40000, "loss": 0.1728, "lr": 7.79937483521287e-08, "epoch": 31.911174785100286, "percentage": 97.49, "elapsed_time": "4:29:22", "remaining_time": "0:06:56", "throughput": 786.06, "total_tokens": 12704856} {"current_steps": 39000, "total_steps": 40000, "loss": 0.1504, "lr": 7.722078761444873e-08, "epoch": 31.91526811297585, "percentage": 97.5, "elapsed_time": "4:29:24", "remaining_time": "0:06:54", "throughput": 786.08, "total_tokens": 12706504} {"current_steps": 39000, "total_steps": 40000, "eval_loss": 0.21511177718639374, "epoch": 31.91526811297585, "percentage": 97.5, "elapsed_time": "4:29:36", "remaining_time": "0:06:54", "throughput": 785.47, "total_tokens": 12706504} {"current_steps": 39005, "total_steps": 40000, "loss": 0.1291, "lr": 7.645167028252631e-08, "epoch": 31.91936144085141, "percentage": 97.51, "elapsed_time": "4:29:40", "remaining_time": "0:06:52", "throughput": 785.41, "total_tokens": 12708120} {"current_steps": 39010, "total_steps": 40000, "loss": 0.1635, "lr": 7.568639647496379e-08, "epoch": 31.923454768726977, "percentage": 97.52, "elapsed_time": "4:29:41", "remaining_time": "0:06:50", "throughput": 785.43, "total_tokens": 12709800} {"current_steps": 39015, "total_steps": 40000, "loss": 0.3091, "lr": 7.492496630977508e-08, "epoch": 31.92754809660254, "percentage": 97.54, "elapsed_time": "4:29:43", "remaining_time": "0:06:48", "throughput": 785.45, "total_tokens": 12711400} {"current_steps": 39020, "total_steps": 40000, "loss": 0.2, "lr": 7.416737990438571e-08, "epoch": 31.9316414244781, "percentage": 97.55, "elapsed_time": "4:29:45", "remaining_time": "0:06:46", "throughput": 785.46, "total_tokens": 12713032} {"current_steps": 39025, "total_steps": 40000, "loss": 0.1581, "lr": 7.341363737562445e-08, "epoch": 31.935734752353664, "percentage": 97.56, "elapsed_time": "4:29:47", "remaining_time": "0:06:44", "throughput": 785.48, "total_tokens": 12714568} {"current_steps": 39030, "total_steps": 40000, "loss": 0.1181, "lr": 7.266373883972887e-08, "epoch": 31.939828080229226, "percentage": 97.58, "elapsed_time": "4:29:48", "remaining_time": "0:06:42", "throughput": 785.49, "total_tokens": 12716216} {"current_steps": 39035, "total_steps": 40000, "loss": 0.1315, "lr": 7.191768441233981e-08, "epoch": 31.94392140810479, "percentage": 97.59, "elapsed_time": "4:29:50", "remaining_time": "0:06:40", "throughput": 785.51, "total_tokens": 12717848} {"current_steps": 39040, "total_steps": 40000, "loss": 0.1489, "lr": 7.11754742085069e-08, "epoch": 31.94801473598035, "percentage": 97.6, "elapsed_time": "4:29:52", "remaining_time": "0:06:38", "throughput": 785.53, "total_tokens": 12719544} {"current_steps": 39045, "total_steps": 40000, "loss": 0.216, "lr": 7.043710834269413e-08, "epoch": 31.952108063855913, "percentage": 97.61, "elapsed_time": "4:29:53", "remaining_time": "0:06:36", "throughput": 785.55, "total_tokens": 12721160} {"current_steps": 39050, "total_steps": 40000, "loss": 0.1645, "lr": 6.970258692876319e-08, "epoch": 31.95620139173148, "percentage": 97.62, "elapsed_time": "4:29:55", "remaining_time": "0:06:34", "throughput": 785.57, "total_tokens": 12722808} {"current_steps": 39055, "total_steps": 40000, "loss": 0.1809, "lr": 6.897191007998738e-08, "epoch": 31.96029471960704, "percentage": 97.64, "elapsed_time": "4:29:57", "remaining_time": "0:06:31", "throughput": 785.58, "total_tokens": 12724424} {"current_steps": 39060, "total_steps": 40000, "loss": 0.1352, "lr": 6.824507790904599e-08, "epoch": 31.964388047482604, "percentage": 97.65, "elapsed_time": "4:29:59", "remaining_time": "0:06:29", "throughput": 785.6, "total_tokens": 12726008} {"current_steps": 39065, "total_steps": 40000, "loss": 0.1591, "lr": 6.752209052802439e-08, "epoch": 31.968481375358166, "percentage": 97.66, "elapsed_time": "4:30:00", "remaining_time": "0:06:27", "throughput": 785.61, "total_tokens": 12727624} {"current_steps": 39070, "total_steps": 40000, "loss": 0.1346, "lr": 6.680294804841946e-08, "epoch": 31.97257470323373, "percentage": 97.67, "elapsed_time": "4:30:02", "remaining_time": "0:06:25", "throughput": 785.63, "total_tokens": 12729224} {"current_steps": 39075, "total_steps": 40000, "loss": 0.1772, "lr": 6.608765058112865e-08, "epoch": 31.97666803110929, "percentage": 97.69, "elapsed_time": "4:30:04", "remaining_time": "0:06:23", "throughput": 785.65, "total_tokens": 12730840} {"current_steps": 39080, "total_steps": 40000, "loss": 0.1638, "lr": 6.537619823646368e-08, "epoch": 31.980761358984854, "percentage": 97.7, "elapsed_time": "4:30:05", "remaining_time": "0:06:21", "throughput": 785.66, "total_tokens": 12732456} {"current_steps": 39085, "total_steps": 40000, "loss": 0.2212, "lr": 6.466859112413404e-08, "epoch": 31.984854686860416, "percentage": 97.71, "elapsed_time": "4:30:07", "remaining_time": "0:06:19", "throughput": 785.68, "total_tokens": 12734056} {"current_steps": 39090, "total_steps": 40000, "loss": 0.1767, "lr": 6.39648293532663e-08, "epoch": 31.988948014735982, "percentage": 97.72, "elapsed_time": "4:30:09", "remaining_time": "0:06:17", "throughput": 785.7, "total_tokens": 12735704} {"current_steps": 39095, "total_steps": 40000, "loss": 0.1781, "lr": 6.32649130323848e-08, "epoch": 31.993041342611544, "percentage": 97.74, "elapsed_time": "4:30:11", "remaining_time": "0:06:15", "throughput": 785.71, "total_tokens": 12737304} {"current_steps": 39100, "total_steps": 40000, "loss": 0.1976, "lr": 6.256884226943094e-08, "epoch": 31.997134670487107, "percentage": 97.75, "elapsed_time": "4:30:12", "remaining_time": "0:06:13", "throughput": 785.73, "total_tokens": 12738968} {"current_steps": 39105, "total_steps": 40000, "loss": 0.1088, "lr": 6.187661717174386e-08, "epoch": 32.00081866557511, "percentage": 97.76, "elapsed_time": "4:30:14", "remaining_time": "0:06:11", "throughput": 785.73, "total_tokens": 12740408} {"current_steps": 39110, "total_steps": 40000, "loss": 0.1395, "lr": 6.118823784607708e-08, "epoch": 32.004911993450676, "percentage": 97.78, "elapsed_time": "4:30:16", "remaining_time": "0:06:09", "throughput": 785.75, "total_tokens": 12742152} {"current_steps": 39115, "total_steps": 40000, "loss": 0.1591, "lr": 6.050370439858178e-08, "epoch": 32.009005321326235, "percentage": 97.79, "elapsed_time": "4:30:18", "remaining_time": "0:06:06", "throughput": 785.77, "total_tokens": 12743720} {"current_steps": 39120, "total_steps": 40000, "loss": 0.1315, "lr": 5.98230169348235e-08, "epoch": 32.0130986492018, "percentage": 97.8, "elapsed_time": "4:30:19", "remaining_time": "0:06:04", "throughput": 785.78, "total_tokens": 12745368} {"current_steps": 39125, "total_steps": 40000, "loss": 0.2314, "lr": 5.914617555977664e-08, "epoch": 32.01719197707737, "percentage": 97.81, "elapsed_time": "4:30:21", "remaining_time": "0:06:02", "throughput": 785.8, "total_tokens": 12747016} {"current_steps": 39130, "total_steps": 40000, "loss": 0.185, "lr": 5.8473180377816017e-08, "epoch": 32.021285304952926, "percentage": 97.82, "elapsed_time": "4:30:23", "remaining_time": "0:06:00", "throughput": 785.82, "total_tokens": 12748664} {"current_steps": 39135, "total_steps": 40000, "loss": 0.1655, "lr": 5.780403149272251e-08, "epoch": 32.02537863282849, "percentage": 97.84, "elapsed_time": "4:30:25", "remaining_time": "0:05:58", "throughput": 785.84, "total_tokens": 12750232} {"current_steps": 39140, "total_steps": 40000, "loss": 0.21, "lr": 5.7138729007694126e-08, "epoch": 32.02947196070405, "percentage": 97.85, "elapsed_time": "4:30:26", "remaining_time": "0:05:56", "throughput": 785.85, "total_tokens": 12751848} {"current_steps": 39145, "total_steps": 40000, "loss": 0.1745, "lr": 5.64772730253238e-08, "epoch": 32.03356528857962, "percentage": 97.86, "elapsed_time": "4:30:28", "remaining_time": "0:05:54", "throughput": 785.87, "total_tokens": 12753416} {"current_steps": 39150, "total_steps": 40000, "loss": 0.1499, "lr": 5.5819663647618814e-08, "epoch": 32.037658616455175, "percentage": 97.88, "elapsed_time": "4:30:30", "remaining_time": "0:05:52", "throughput": 785.88, "total_tokens": 12755016} {"current_steps": 39155, "total_steps": 40000, "loss": 0.1528, "lr": 5.5165900975989723e-08, "epoch": 32.04175194433074, "percentage": 97.89, "elapsed_time": "4:30:31", "remaining_time": "0:05:50", "throughput": 785.9, "total_tokens": 12756664} {"current_steps": 39160, "total_steps": 40000, "loss": 0.2458, "lr": 5.451598511125311e-08, "epoch": 32.04584527220631, "percentage": 97.9, "elapsed_time": "4:30:33", "remaining_time": "0:05:48", "throughput": 785.92, "total_tokens": 12758376} {"current_steps": 39165, "total_steps": 40000, "loss": 0.139, "lr": 5.3869916153637124e-08, "epoch": 32.049938600081866, "percentage": 97.91, "elapsed_time": "4:30:35", "remaining_time": "0:05:46", "throughput": 785.94, "total_tokens": 12759992} {"current_steps": 39170, "total_steps": 40000, "loss": 0.1489, "lr": 5.322769420277318e-08, "epoch": 32.05403192795743, "percentage": 97.92, "elapsed_time": "4:30:37", "remaining_time": "0:05:44", "throughput": 785.95, "total_tokens": 12761592} {"current_steps": 39175, "total_steps": 40000, "loss": 0.1201, "lr": 5.258931935769873e-08, "epoch": 32.05812525583299, "percentage": 97.94, "elapsed_time": "4:30:38", "remaining_time": "0:05:41", "throughput": 785.97, "total_tokens": 12763192} {"current_steps": 39180, "total_steps": 40000, "loss": 0.1663, "lr": 5.19547917168628e-08, "epoch": 32.06221858370856, "percentage": 97.95, "elapsed_time": "4:30:40", "remaining_time": "0:05:39", "throughput": 785.98, "total_tokens": 12764792} {"current_steps": 39185, "total_steps": 40000, "loss": 0.2569, "lr": 5.13241113781121e-08, "epoch": 32.066311911584116, "percentage": 97.96, "elapsed_time": "4:30:42", "remaining_time": "0:05:37", "throughput": 786.0, "total_tokens": 12766392} {"current_steps": 39190, "total_steps": 40000, "loss": 0.1665, "lr": 5.0697278438707755e-08, "epoch": 32.07040523945968, "percentage": 97.97, "elapsed_time": "4:30:43", "remaining_time": "0:05:35", "throughput": 786.02, "total_tokens": 12768072} {"current_steps": 39195, "total_steps": 40000, "loss": 0.1991, "lr": 5.0074292995316854e-08, "epoch": 32.07449856733524, "percentage": 97.99, "elapsed_time": "4:30:45", "remaining_time": "0:05:33", "throughput": 786.03, "total_tokens": 12769656} {"current_steps": 39200, "total_steps": 40000, "loss": 0.1118, "lr": 4.945515514400978e-08, "epoch": 32.078591895210806, "percentage": 98.0, "elapsed_time": "4:30:47", "remaining_time": "0:05:31", "throughput": 786.04, "total_tokens": 12771208} {"current_steps": 39200, "total_steps": 40000, "eval_loss": 0.21310102939605713, "epoch": 32.078591895210806, "percentage": 98.0, "elapsed_time": "4:30:59", "remaining_time": "0:05:31", "throughput": 785.44, "total_tokens": 12771208} {"current_steps": 39205, "total_steps": 40000, "loss": 0.1318, "lr": 4.883986498026571e-08, "epoch": 32.08268522308637, "percentage": 98.01, "elapsed_time": "4:31:03", "remaining_time": "0:05:29", "throughput": 785.38, "total_tokens": 12772856} {"current_steps": 39210, "total_steps": 40000, "loss": 0.1988, "lr": 4.822842259896987e-08, "epoch": 32.08677855096193, "percentage": 98.02, "elapsed_time": "4:31:04", "remaining_time": "0:05:27", "throughput": 785.4, "total_tokens": 12774472} {"current_steps": 39215, "total_steps": 40000, "loss": 0.229, "lr": 4.762082809441626e-08, "epoch": 32.0908718788375, "percentage": 98.04, "elapsed_time": "4:31:06", "remaining_time": "0:05:25", "throughput": 785.42, "total_tokens": 12776104} {"current_steps": 39220, "total_steps": 40000, "loss": 0.202, "lr": 4.7017081560302156e-08, "epoch": 32.094965206713056, "percentage": 98.05, "elapsed_time": "4:31:08", "remaining_time": "0:05:23", "throughput": 785.43, "total_tokens": 12777688} {"current_steps": 39225, "total_steps": 40000, "loss": 0.2148, "lr": 4.6417183089730866e-08, "epoch": 32.09905853458862, "percentage": 98.06, "elapsed_time": "4:31:10", "remaining_time": "0:05:21", "throughput": 785.44, "total_tokens": 12779272} {"current_steps": 39230, "total_steps": 40000, "loss": 0.2018, "lr": 4.5821132775217265e-08, "epoch": 32.10315186246418, "percentage": 98.08, "elapsed_time": "4:31:11", "remaining_time": "0:05:19", "throughput": 785.46, "total_tokens": 12780888} {"current_steps": 39235, "total_steps": 40000, "loss": 0.1227, "lr": 4.5228930708679504e-08, "epoch": 32.107245190339746, "percentage": 98.09, "elapsed_time": "4:31:13", "remaining_time": "0:05:17", "throughput": 785.48, "total_tokens": 12782632} {"current_steps": 39240, "total_steps": 40000, "loss": 0.1237, "lr": 4.464057698144175e-08, "epoch": 32.11133851821531, "percentage": 98.1, "elapsed_time": "4:31:15", "remaining_time": "0:05:15", "throughput": 785.5, "total_tokens": 12784280} {"current_steps": 39245, "total_steps": 40000, "loss": 0.2059, "lr": 4.4056071684236974e-08, "epoch": 32.11543184609087, "percentage": 98.11, "elapsed_time": "4:31:17", "remaining_time": "0:05:13", "throughput": 785.52, "total_tokens": 12785896} {"current_steps": 39250, "total_steps": 40000, "loss": 0.2191, "lr": 4.347541490719864e-08, "epoch": 32.11952517396644, "percentage": 98.12, "elapsed_time": "4:31:18", "remaining_time": "0:05:11", "throughput": 785.54, "total_tokens": 12787560} {"current_steps": 39255, "total_steps": 40000, "loss": 0.1343, "lr": 4.2898606739877336e-08, "epoch": 32.123618501841996, "percentage": 98.14, "elapsed_time": "4:31:20", "remaining_time": "0:05:08", "throughput": 785.55, "total_tokens": 12789128} {"current_steps": 39260, "total_steps": 40000, "loss": 0.234, "lr": 4.232564727122135e-08, "epoch": 32.12771182971756, "percentage": 98.15, "elapsed_time": "4:31:22", "remaining_time": "0:05:06", "throughput": 785.57, "total_tokens": 12790856} {"current_steps": 39265, "total_steps": 40000, "loss": 0.1833, "lr": 4.1756536589585004e-08, "epoch": 32.13180515759312, "percentage": 98.16, "elapsed_time": "4:31:23", "remaining_time": "0:05:04", "throughput": 785.59, "total_tokens": 12792472} {"current_steps": 39270, "total_steps": 40000, "loss": 0.2333, "lr": 4.119127478273976e-08, "epoch": 32.13589848546869, "percentage": 98.17, "elapsed_time": "4:31:25", "remaining_time": "0:05:02", "throughput": 785.61, "total_tokens": 12794152} {"current_steps": 39275, "total_steps": 40000, "loss": 0.136, "lr": 4.062986193784923e-08, "epoch": 32.139991813344245, "percentage": 98.19, "elapsed_time": "4:31:27", "remaining_time": "0:05:00", "throughput": 785.63, "total_tokens": 12795800} {"current_steps": 39280, "total_steps": 40000, "loss": 0.208, "lr": 4.007229814149416e-08, "epoch": 32.14408514121981, "percentage": 98.2, "elapsed_time": "4:31:29", "remaining_time": "0:04:58", "throughput": 785.64, "total_tokens": 12797400} {"current_steps": 39285, "total_steps": 40000, "loss": 0.1296, "lr": 3.951858347965576e-08, "epoch": 32.14817846909538, "percentage": 98.21, "elapsed_time": "4:31:30", "remaining_time": "0:04:56", "throughput": 785.66, "total_tokens": 12799032} {"current_steps": 39290, "total_steps": 40000, "loss": 0.191, "lr": 3.896871803772684e-08, "epoch": 32.152271796970936, "percentage": 98.22, "elapsed_time": "4:31:32", "remaining_time": "0:04:54", "throughput": 785.68, "total_tokens": 12800664} {"current_steps": 39295, "total_steps": 40000, "loss": 0.1976, "lr": 3.842270190050068e-08, "epoch": 32.1563651248465, "percentage": 98.24, "elapsed_time": "4:31:34", "remaining_time": "0:04:52", "throughput": 785.69, "total_tokens": 12802280} {"current_steps": 39300, "total_steps": 40000, "loss": 0.2501, "lr": 3.7880535152179376e-08, "epoch": 32.16045845272206, "percentage": 98.25, "elapsed_time": "4:31:35", "remaining_time": "0:04:50", "throughput": 785.71, "total_tokens": 12803880} {"current_steps": 39305, "total_steps": 40000, "loss": 0.151, "lr": 3.734221787637382e-08, "epoch": 32.16455178059763, "percentage": 98.26, "elapsed_time": "4:31:37", "remaining_time": "0:04:48", "throughput": 785.73, "total_tokens": 12805544} {"current_steps": 39310, "total_steps": 40000, "loss": 0.2185, "lr": 3.680775015609817e-08, "epoch": 32.168645108473186, "percentage": 98.28, "elapsed_time": "4:31:39", "remaining_time": "0:04:46", "throughput": 785.75, "total_tokens": 12807176} {"current_steps": 39315, "total_steps": 40000, "loss": 0.243, "lr": 3.627713207377537e-08, "epoch": 32.17273843634875, "percentage": 98.29, "elapsed_time": "4:31:41", "remaining_time": "0:04:44", "throughput": 785.76, "total_tokens": 12808776} {"current_steps": 39320, "total_steps": 40000, "loss": 0.2757, "lr": 3.575036371123164e-08, "epoch": 32.17683176422432, "percentage": 98.3, "elapsed_time": "4:31:42", "remaining_time": "0:04:41", "throughput": 785.78, "total_tokens": 12810472} {"current_steps": 39325, "total_steps": 40000, "loss": 0.1397, "lr": 3.5227445149704776e-08, "epoch": 32.180925092099876, "percentage": 98.31, "elapsed_time": "4:31:44", "remaining_time": "0:04:39", "throughput": 785.8, "total_tokens": 12812104} {"current_steps": 39330, "total_steps": 40000, "loss": 0.1734, "lr": 3.470837646983027e-08, "epoch": 32.18501841997544, "percentage": 98.32, "elapsed_time": "4:31:46", "remaining_time": "0:04:37", "throughput": 785.81, "total_tokens": 12813688} {"current_steps": 39335, "total_steps": 40000, "loss": 0.221, "lr": 3.419315775165799e-08, "epoch": 32.189111747851, "percentage": 98.34, "elapsed_time": "4:31:47", "remaining_time": "0:04:35", "throughput": 785.83, "total_tokens": 12815304} {"current_steps": 39340, "total_steps": 40000, "loss": 0.2253, "lr": 3.368178907464103e-08, "epoch": 32.19320507572657, "percentage": 98.35, "elapsed_time": "4:31:49", "remaining_time": "0:04:33", "throughput": 785.85, "total_tokens": 12817032} {"current_steps": 39345, "total_steps": 40000, "loss": 0.119, "lr": 3.317427051763855e-08, "epoch": 32.197298403602126, "percentage": 98.36, "elapsed_time": "4:31:51", "remaining_time": "0:04:31", "throughput": 785.87, "total_tokens": 12818632} {"current_steps": 39350, "total_steps": 40000, "loss": 0.1619, "lr": 3.267060215891571e-08, "epoch": 32.20139173147769, "percentage": 98.38, "elapsed_time": "4:31:53", "remaining_time": "0:04:29", "throughput": 785.89, "total_tokens": 12820248} {"current_steps": 39355, "total_steps": 40000, "loss": 0.1035, "lr": 3.217078407614649e-08, "epoch": 32.20548505935325, "percentage": 98.39, "elapsed_time": "4:31:54", "remaining_time": "0:04:27", "throughput": 785.91, "total_tokens": 12821928} {"current_steps": 39360, "total_steps": 40000, "loss": 0.1707, "lr": 3.1674816346405345e-08, "epoch": 32.20957838722882, "percentage": 98.4, "elapsed_time": "4:31:56", "remaining_time": "0:04:25", "throughput": 785.92, "total_tokens": 12823528} {"current_steps": 39365, "total_steps": 40000, "loss": 0.1319, "lr": 3.11826990461811e-08, "epoch": 32.21367171510438, "percentage": 98.41, "elapsed_time": "4:31:58", "remaining_time": "0:04:23", "throughput": 785.94, "total_tokens": 12825192} {"current_steps": 39370, "total_steps": 40000, "loss": 0.1441, "lr": 3.069443225136304e-08, "epoch": 32.21776504297994, "percentage": 98.42, "elapsed_time": "4:31:59", "remaining_time": "0:04:21", "throughput": 785.96, "total_tokens": 12826872} {"current_steps": 39375, "total_steps": 40000, "loss": 0.1479, "lr": 3.021001603724372e-08, "epoch": 32.22185837085551, "percentage": 98.44, "elapsed_time": "4:32:01", "remaining_time": "0:04:19", "throughput": 785.98, "total_tokens": 12828536} {"current_steps": 39380, "total_steps": 40000, "loss": 0.2174, "lr": 2.9729450478532818e-08, "epoch": 32.225951698731066, "percentage": 98.45, "elapsed_time": "4:32:03", "remaining_time": "0:04:16", "throughput": 786.0, "total_tokens": 12830248} {"current_steps": 39385, "total_steps": 40000, "loss": 0.1899, "lr": 2.9252735649337726e-08, "epoch": 32.23004502660663, "percentage": 98.46, "elapsed_time": "4:32:05", "remaining_time": "0:04:14", "throughput": 786.02, "total_tokens": 12831864} {"current_steps": 39390, "total_steps": 40000, "loss": 0.0871, "lr": 2.8779871623171863e-08, "epoch": 32.23413835448219, "percentage": 98.47, "elapsed_time": "4:32:06", "remaining_time": "0:04:12", "throughput": 786.04, "total_tokens": 12833512} {"current_steps": 39395, "total_steps": 40000, "loss": 0.1451, "lr": 2.8310858472957448e-08, "epoch": 32.23823168235776, "percentage": 98.49, "elapsed_time": "4:32:08", "remaining_time": "0:04:10", "throughput": 786.05, "total_tokens": 12835128} {"current_steps": 39400, "total_steps": 40000, "loss": 0.1624, "lr": 2.784569627101996e-08, "epoch": 32.24232501023332, "percentage": 98.5, "elapsed_time": "4:32:10", "remaining_time": "0:04:08", "throughput": 786.07, "total_tokens": 12836760} {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.2150798738002777, "epoch": 32.24232501023332, "percentage": 98.5, "elapsed_time": "4:32:22", "remaining_time": "0:04:08", "throughput": 785.47, "total_tokens": 12836760} {"current_steps": 39405, "total_steps": 40000, "loss": 0.1203, "lr": 2.738438508909924e-08, "epoch": 32.24641833810888, "percentage": 98.51, "elapsed_time": "4:32:26", "remaining_time": "0:04:06", "throughput": 785.41, "total_tokens": 12838408} {"current_steps": 39410, "total_steps": 40000, "loss": 0.1557, "lr": 2.692692499833005e-08, "epoch": 32.25051166598445, "percentage": 98.52, "elapsed_time": "4:32:27", "remaining_time": "0:04:04", "throughput": 785.43, "total_tokens": 12840072} {"current_steps": 39415, "total_steps": 40000, "loss": 0.1523, "lr": 2.647331606926151e-08, "epoch": 32.254604993860006, "percentage": 98.54, "elapsed_time": "4:32:29", "remaining_time": "0:04:02", "throughput": 785.45, "total_tokens": 12841720} {"current_steps": 39420, "total_steps": 40000, "loss": 0.1451, "lr": 2.6023558371843225e-08, "epoch": 32.25869832173557, "percentage": 98.55, "elapsed_time": "4:32:31", "remaining_time": "0:04:00", "throughput": 785.46, "total_tokens": 12843288} {"current_steps": 39425, "total_steps": 40000, "loss": 0.2626, "lr": 2.557765197543638e-08, "epoch": 32.26279164961113, "percentage": 98.56, "elapsed_time": "4:32:33", "remaining_time": "0:03:58", "throughput": 785.48, "total_tokens": 12844904} {"current_steps": 39430, "total_steps": 40000, "loss": 0.1711, "lr": 2.513559694880263e-08, "epoch": 32.2668849774867, "percentage": 98.58, "elapsed_time": "4:32:34", "remaining_time": "0:03:56", "throughput": 785.49, "total_tokens": 12846520} {"current_steps": 39435, "total_steps": 40000, "loss": 0.1145, "lr": 2.469739336011523e-08, "epoch": 32.27097830536226, "percentage": 98.59, "elapsed_time": "4:32:36", "remaining_time": "0:03:54", "throughput": 785.51, "total_tokens": 12848168} {"current_steps": 39440, "total_steps": 40000, "loss": 0.1731, "lr": 2.4263041276947894e-08, "epoch": 32.27507163323782, "percentage": 98.6, "elapsed_time": "4:32:38", "remaining_time": "0:03:52", "throughput": 785.52, "total_tokens": 12849752} {"current_steps": 39445, "total_steps": 40000, "loss": 0.1486, "lr": 2.3832540766283164e-08, "epoch": 32.27916496111339, "percentage": 98.61, "elapsed_time": "4:32:39", "remaining_time": "0:03:50", "throughput": 785.55, "total_tokens": 12851448} {"current_steps": 39450, "total_steps": 40000, "loss": 0.1477, "lr": 2.3405891894512366e-08, "epoch": 32.28325828898895, "percentage": 98.62, "elapsed_time": "4:32:41", "remaining_time": "0:03:48", "throughput": 785.57, "total_tokens": 12853144} {"current_steps": 39455, "total_steps": 40000, "loss": 0.1729, "lr": 2.29830947274301e-08, "epoch": 32.28735161686451, "percentage": 98.64, "elapsed_time": "4:32:43", "remaining_time": "0:03:46", "throughput": 785.58, "total_tokens": 12854792} {"current_steps": 39460, "total_steps": 40000, "loss": 0.2274, "lr": 2.2564149330231432e-08, "epoch": 32.29144494474007, "percentage": 98.65, "elapsed_time": "4:32:45", "remaining_time": "0:03:43", "throughput": 785.6, "total_tokens": 12856472} {"current_steps": 39465, "total_steps": 40000, "loss": 0.16, "lr": 2.2149055767528572e-08, "epoch": 32.29553827261564, "percentage": 98.66, "elapsed_time": "4:32:47", "remaining_time": "0:03:41", "throughput": 785.61, "total_tokens": 12858088} {"current_steps": 39470, "total_steps": 40000, "loss": 0.172, "lr": 2.1737814103334197e-08, "epoch": 32.299631600491196, "percentage": 98.67, "elapsed_time": "4:32:48", "remaining_time": "0:03:39", "throughput": 785.63, "total_tokens": 12859784} {"current_steps": 39475, "total_steps": 40000, "loss": 0.2647, "lr": 2.1330424401064253e-08, "epoch": 32.30372492836676, "percentage": 98.69, "elapsed_time": "4:32:50", "remaining_time": "0:03:37", "throughput": 785.65, "total_tokens": 12861416} {"current_steps": 39480, "total_steps": 40000, "loss": 0.2096, "lr": 2.092688672354348e-08, "epoch": 32.30781825624233, "percentage": 98.7, "elapsed_time": "4:32:52", "remaining_time": "0:03:35", "throughput": 785.66, "total_tokens": 12863048} {"current_steps": 39485, "total_steps": 40000, "loss": 0.1262, "lr": 2.0527201133005435e-08, "epoch": 32.31191158411789, "percentage": 98.71, "elapsed_time": "4:32:53", "remaining_time": "0:03:33", "throughput": 785.68, "total_tokens": 12864680} {"current_steps": 39490, "total_steps": 40000, "loss": 0.1102, "lr": 2.0131367691084148e-08, "epoch": 32.31600491199345, "percentage": 98.72, "elapsed_time": "4:32:55", "remaining_time": "0:03:31", "throughput": 785.7, "total_tokens": 12866296} {"current_steps": 39495, "total_steps": 40000, "loss": 0.1321, "lr": 1.9739386458819675e-08, "epoch": 32.32009823986901, "percentage": 98.74, "elapsed_time": "4:32:57", "remaining_time": "0:03:29", "throughput": 785.71, "total_tokens": 12867848} {"current_steps": 39500, "total_steps": 40000, "loss": 0.1348, "lr": 1.9351257496666442e-08, "epoch": 32.32419156774458, "percentage": 98.75, "elapsed_time": "4:32:59", "remaining_time": "0:03:27", "throughput": 785.73, "total_tokens": 12869448} {"current_steps": 39505, "total_steps": 40000, "loss": 0.1166, "lr": 1.896698086447657e-08, "epoch": 32.328284895620136, "percentage": 98.76, "elapsed_time": "4:33:00", "remaining_time": "0:03:25", "throughput": 785.74, "total_tokens": 12871096} {"current_steps": 39510, "total_steps": 40000, "loss": 0.0842, "lr": 1.8586556621505436e-08, "epoch": 32.3323782234957, "percentage": 98.78, "elapsed_time": "4:33:02", "remaining_time": "0:03:23", "throughput": 785.76, "total_tokens": 12872696} {"current_steps": 39515, "total_steps": 40000, "loss": 0.2146, "lr": 1.820998482642833e-08, "epoch": 32.33647155137127, "percentage": 98.79, "elapsed_time": "4:33:04", "remaining_time": "0:03:21", "throughput": 785.78, "total_tokens": 12874328} {"current_steps": 39520, "total_steps": 40000, "loss": 0.2077, "lr": 1.7837265537309912e-08, "epoch": 32.34056487924683, "percentage": 98.8, "elapsed_time": "4:33:05", "remaining_time": "0:03:19", "throughput": 785.79, "total_tokens": 12875912} {"current_steps": 39525, "total_steps": 40000, "loss": 0.0991, "lr": 1.7468398811629206e-08, "epoch": 32.34465820712239, "percentage": 98.81, "elapsed_time": "4:33:07", "remaining_time": "0:03:16", "throughput": 785.8, "total_tokens": 12877496} {"current_steps": 39530, "total_steps": 40000, "loss": 0.2227, "lr": 1.710338470627404e-08, "epoch": 32.34875153499795, "percentage": 98.83, "elapsed_time": "4:33:09", "remaining_time": "0:03:14", "throughput": 785.82, "total_tokens": 12879112} {"current_steps": 39535, "total_steps": 40000, "loss": 0.1387, "lr": 1.6742223277529945e-08, "epoch": 32.35284486287352, "percentage": 98.84, "elapsed_time": "4:33:11", "remaining_time": "0:03:12", "throughput": 785.84, "total_tokens": 12880760} {"current_steps": 39540, "total_steps": 40000, "loss": 0.1824, "lr": 1.6384914581094036e-08, "epoch": 32.35693819074908, "percentage": 98.85, "elapsed_time": "4:33:12", "remaining_time": "0:03:10", "throughput": 785.86, "total_tokens": 12882440} {"current_steps": 39545, "total_steps": 40000, "loss": 0.256, "lr": 1.6031458672069455e-08, "epoch": 32.36103151862464, "percentage": 98.86, "elapsed_time": "4:33:14", "remaining_time": "0:03:08", "throughput": 785.87, "total_tokens": 12884024} {"current_steps": 39550, "total_steps": 40000, "loss": 0.1344, "lr": 1.5681855604962602e-08, "epoch": 32.3651248465002, "percentage": 98.88, "elapsed_time": "4:33:16", "remaining_time": "0:03:06", "throughput": 785.89, "total_tokens": 12885624} {"current_steps": 39555, "total_steps": 40000, "loss": 0.2139, "lr": 1.5336105433683135e-08, "epoch": 32.36921817437577, "percentage": 98.89, "elapsed_time": "4:33:18", "remaining_time": "0:03:04", "throughput": 785.9, "total_tokens": 12887256} {"current_steps": 39560, "total_steps": 40000, "loss": 0.1517, "lr": 1.499420821155506e-08, "epoch": 32.37331150225133, "percentage": 98.9, "elapsed_time": "4:33:19", "remaining_time": "0:03:02", "throughput": 785.92, "total_tokens": 12888904} {"current_steps": 39565, "total_steps": 40000, "loss": 0.1549, "lr": 1.4656163991302874e-08, "epoch": 32.37740483012689, "percentage": 98.91, "elapsed_time": "4:33:21", "remaining_time": "0:03:00", "throughput": 785.94, "total_tokens": 12890536} {"current_steps": 39570, "total_steps": 40000, "loss": 0.13, "lr": 1.4321972825051544e-08, "epoch": 32.38149815800246, "percentage": 98.92, "elapsed_time": "4:33:23", "remaining_time": "0:02:58", "throughput": 785.95, "total_tokens": 12892136} {"current_steps": 39575, "total_steps": 40000, "loss": 0.2462, "lr": 1.3991634764345951e-08, "epoch": 32.38559148587802, "percentage": 98.94, "elapsed_time": "4:33:24", "remaining_time": "0:02:56", "throughput": 785.97, "total_tokens": 12893800} {"current_steps": 39580, "total_steps": 40000, "loss": 0.1445, "lr": 1.3665149860120352e-08, "epoch": 32.38968481375358, "percentage": 98.95, "elapsed_time": "4:33:26", "remaining_time": "0:02:54", "throughput": 785.99, "total_tokens": 12895384} {"current_steps": 39585, "total_steps": 40000, "loss": 0.2756, "lr": 1.3342518162728912e-08, "epoch": 32.39377814162914, "percentage": 98.96, "elapsed_time": "4:33:28", "remaining_time": "0:02:52", "throughput": 786.0, "total_tokens": 12896936} {"current_steps": 39590, "total_steps": 40000, "loss": 0.1409, "lr": 1.30237397219235e-08, "epoch": 32.39787146950471, "percentage": 98.98, "elapsed_time": "4:33:30", "remaining_time": "0:02:49", "throughput": 786.02, "total_tokens": 12898584} {"current_steps": 39595, "total_steps": 40000, "loss": 0.1006, "lr": 1.2708814586862016e-08, "epoch": 32.40196479738027, "percentage": 98.99, "elapsed_time": "4:33:31", "remaining_time": "0:02:47", "throughput": 786.04, "total_tokens": 12900216} {"current_steps": 39600, "total_steps": 40000, "loss": 0.1188, "lr": 1.2397742806111168e-08, "epoch": 32.40605812525583, "percentage": 99.0, "elapsed_time": "4:33:33", "remaining_time": "0:02:45", "throughput": 786.06, "total_tokens": 12901944} {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.2150798738002777, "epoch": 32.40605812525583, "percentage": 99.0, "elapsed_time": "4:33:45", "remaining_time": "0:02:45", "throughput": 785.46, "total_tokens": 12901944} {"current_steps": 39605, "total_steps": 40000, "loss": 0.1603, "lr": 1.209052442764369e-08, "epoch": 32.4101514531314, "percentage": 99.01, "elapsed_time": "4:33:49", "remaining_time": "0:02:43", "throughput": 785.4, "total_tokens": 12903544} {"current_steps": 39610, "total_steps": 40000, "loss": 0.1509, "lr": 1.17871594988328e-08, "epoch": 32.41424478100696, "percentage": 99.02, "elapsed_time": "4:33:50", "remaining_time": "0:02:41", "throughput": 785.42, "total_tokens": 12905192} {"current_steps": 39615, "total_steps": 40000, "loss": 0.1756, "lr": 1.1487648066466072e-08, "epoch": 32.41833810888252, "percentage": 99.04, "elapsed_time": "4:33:52", "remaining_time": "0:02:39", "throughput": 785.44, "total_tokens": 12906840} {"current_steps": 39620, "total_steps": 40000, "loss": 0.3255, "lr": 1.1191990176728784e-08, "epoch": 32.42243143675808, "percentage": 99.05, "elapsed_time": "4:33:54", "remaining_time": "0:02:37", "throughput": 785.46, "total_tokens": 12908504} {"current_steps": 39625, "total_steps": 40000, "loss": 0.2258, "lr": 1.0900185875215018e-08, "epoch": 32.42652476463365, "percentage": 99.06, "elapsed_time": "4:33:56", "remaining_time": "0:02:35", "throughput": 785.48, "total_tokens": 12910152} {"current_steps": 39630, "total_steps": 40000, "loss": 0.1531, "lr": 1.0612235206924891e-08, "epoch": 32.43061809250921, "percentage": 99.08, "elapsed_time": "4:33:57", "remaining_time": "0:02:33", "throughput": 785.49, "total_tokens": 12911784} {"current_steps": 39635, "total_steps": 40000, "loss": 0.1457, "lr": 1.0328138216264549e-08, "epoch": 32.43471142038477, "percentage": 99.09, "elapsed_time": "4:33:59", "remaining_time": "0:02:31", "throughput": 785.51, "total_tokens": 12913384} {"current_steps": 39640, "total_steps": 40000, "loss": 0.1536, "lr": 1.004789494704339e-08, "epoch": 32.43880474826034, "percentage": 99.1, "elapsed_time": "4:34:01", "remaining_time": "0:02:29", "throughput": 785.52, "total_tokens": 12914984} {"current_steps": 39645, "total_steps": 40000, "loss": 0.158, "lr": 9.771505442482397e-09, "epoch": 32.4428980761359, "percentage": 99.11, "elapsed_time": "4:34:02", "remaining_time": "0:02:27", "throughput": 785.54, "total_tokens": 12916584} {"current_steps": 39650, "total_steps": 40000, "loss": 0.1592, "lr": 9.498969745200259e-09, "epoch": 32.44699140401146, "percentage": 99.12, "elapsed_time": "4:34:04", "remaining_time": "0:02:25", "throughput": 785.55, "total_tokens": 12918168} {"current_steps": 39655, "total_steps": 40000, "loss": 0.2479, "lr": 9.230287897230017e-09, "epoch": 32.45108473188702, "percentage": 99.14, "elapsed_time": "4:34:06", "remaining_time": "0:02:23", "throughput": 785.57, "total_tokens": 12919848} {"current_steps": 39660, "total_steps": 40000, "loss": 0.168, "lr": 8.965459940002419e-09, "epoch": 32.45517805976259, "percentage": 99.15, "elapsed_time": "4:34:08", "remaining_time": "0:02:21", "throughput": 785.59, "total_tokens": 12921400} {"current_steps": 39665, "total_steps": 40000, "loss": 0.1196, "lr": 8.704485914357019e-09, "epoch": 32.45927138763815, "percentage": 99.16, "elapsed_time": "4:34:09", "remaining_time": "0:02:18", "throughput": 785.61, "total_tokens": 12923128} {"current_steps": 39670, "total_steps": 40000, "loss": 0.3109, "lr": 8.447365860539402e-09, "epoch": 32.46336471551371, "percentage": 99.17, "elapsed_time": "4:34:11", "remaining_time": "0:02:16", "throughput": 785.62, "total_tokens": 12924744} {"current_steps": 39675, "total_steps": 40000, "loss": 0.0939, "lr": 8.194099818201184e-09, "epoch": 32.46745804338928, "percentage": 99.19, "elapsed_time": "4:34:13", "remaining_time": "0:02:14", "throughput": 785.64, "total_tokens": 12926344} {"current_steps": 39680, "total_steps": 40000, "loss": 0.1582, "lr": 7.944687826400011e-09, "epoch": 32.47155137126484, "percentage": 99.2, "elapsed_time": "4:34:15", "remaining_time": "0:02:12", "throughput": 785.66, "total_tokens": 12927976} {"current_steps": 39685, "total_steps": 40000, "loss": 0.1499, "lr": 7.699129923599557e-09, "epoch": 32.4756446991404, "percentage": 99.21, "elapsed_time": "4:34:16", "remaining_time": "0:02:10", "throughput": 785.67, "total_tokens": 12929560} {"current_steps": 39690, "total_steps": 40000, "loss": 0.1303, "lr": 7.457426147663982e-09, "epoch": 32.47973802701596, "percentage": 99.22, "elapsed_time": "4:34:18", "remaining_time": "0:02:08", "throughput": 785.69, "total_tokens": 12931208} {"current_steps": 39695, "total_steps": 40000, "loss": 0.227, "lr": 7.219576535871797e-09, "epoch": 32.48383135489153, "percentage": 99.24, "elapsed_time": "4:34:20", "remaining_time": "0:02:06", "throughput": 785.71, "total_tokens": 12932840} {"current_steps": 39700, "total_steps": 40000, "loss": 0.1956, "lr": 6.985581124896445e-09, "epoch": 32.48792468276709, "percentage": 99.25, "elapsed_time": "4:34:21", "remaining_time": "0:02:04", "throughput": 785.72, "total_tokens": 12934456} {"current_steps": 39705, "total_steps": 40000, "loss": 0.1631, "lr": 6.755439950828501e-09, "epoch": 32.49201801064265, "percentage": 99.26, "elapsed_time": "4:34:23", "remaining_time": "0:02:02", "throughput": 785.74, "total_tokens": 12936056} {"current_steps": 39710, "total_steps": 40000, "loss": 0.1171, "lr": 6.5291530491562444e-09, "epoch": 32.49611133851822, "percentage": 99.28, "elapsed_time": "4:34:25", "remaining_time": "0:02:00", "throughput": 785.75, "total_tokens": 12937688} {"current_steps": 39715, "total_steps": 40000, "loss": 0.0883, "lr": 6.3067204547739845e-09, "epoch": 32.50020466639378, "percentage": 99.29, "elapsed_time": "4:34:27", "remaining_time": "0:01:58", "throughput": 785.77, "total_tokens": 12939224} {"current_steps": 39720, "total_steps": 40000, "loss": 0.2707, "lr": 6.088142201987612e-09, "epoch": 32.50429799426934, "percentage": 99.3, "elapsed_time": "4:34:28", "remaining_time": "0:01:56", "throughput": 785.79, "total_tokens": 12940904} {"current_steps": 39725, "total_steps": 40000, "loss": 0.1176, "lr": 5.873418324503499e-09, "epoch": 32.5083913221449, "percentage": 99.31, "elapsed_time": "4:34:30", "remaining_time": "0:01:54", "throughput": 785.8, "total_tokens": 12942536} {"current_steps": 39730, "total_steps": 40000, "loss": 0.1704, "lr": 5.6625488554340465e-09, "epoch": 32.51248465002047, "percentage": 99.33, "elapsed_time": "4:34:32", "remaining_time": "0:01:51", "throughput": 785.82, "total_tokens": 12944152} {"current_steps": 39735, "total_steps": 40000, "loss": 0.2208, "lr": 5.455533827297688e-09, "epoch": 32.51657797789603, "percentage": 99.34, "elapsed_time": "4:34:33", "remaining_time": "0:01:49", "throughput": 785.83, "total_tokens": 12945768} {"current_steps": 39740, "total_steps": 40000, "loss": 0.1496, "lr": 5.252373272018885e-09, "epoch": 32.52067130577159, "percentage": 99.35, "elapsed_time": "4:34:35", "remaining_time": "0:01:47", "throughput": 785.85, "total_tokens": 12947384} {"current_steps": 39745, "total_steps": 40000, "loss": 0.1959, "lr": 5.053067220925356e-09, "epoch": 32.52476463364715, "percentage": 99.36, "elapsed_time": "4:34:37", "remaining_time": "0:01:45", "throughput": 785.87, "total_tokens": 12949080} {"current_steps": 39750, "total_steps": 40000, "loss": 0.2623, "lr": 4.857615704759177e-09, "epoch": 32.52885796152272, "percentage": 99.38, "elapsed_time": "4:34:39", "remaining_time": "0:01:43", "throughput": 785.89, "total_tokens": 12950712} {"current_steps": 39755, "total_steps": 40000, "loss": 0.153, "lr": 4.666018753654577e-09, "epoch": 32.532951289398284, "percentage": 99.39, "elapsed_time": "4:34:40", "remaining_time": "0:01:41", "throughput": 785.91, "total_tokens": 12952344} {"current_steps": 39760, "total_steps": 40000, "loss": 0.2393, "lr": 4.478276397162917e-09, "epoch": 32.53704461727384, "percentage": 99.4, "elapsed_time": "4:34:42", "remaining_time": "0:01:39", "throughput": 785.92, "total_tokens": 12953944} {"current_steps": 39765, "total_steps": 40000, "loss": 0.218, "lr": 4.294388664233262e-09, "epoch": 32.54113794514941, "percentage": 99.41, "elapsed_time": "4:34:44", "remaining_time": "0:01:37", "throughput": 785.94, "total_tokens": 12955560} {"current_steps": 39770, "total_steps": 40000, "loss": 0.1899, "lr": 4.114355583223484e-09, "epoch": 32.54523127302497, "percentage": 99.42, "elapsed_time": "4:34:45", "remaining_time": "0:01:35", "throughput": 785.96, "total_tokens": 12957256} {"current_steps": 39775, "total_steps": 40000, "loss": 0.2193, "lr": 3.9381771818974845e-09, "epoch": 32.54932460090053, "percentage": 99.44, "elapsed_time": "4:34:47", "remaining_time": "0:01:33", "throughput": 785.98, "total_tokens": 12958904} {"current_steps": 39780, "total_steps": 40000, "loss": 0.2258, "lr": 3.765853487427973e-09, "epoch": 32.55341792877609, "percentage": 99.45, "elapsed_time": "4:34:49", "remaining_time": "0:01:31", "throughput": 785.99, "total_tokens": 12960552} {"current_steps": 39785, "total_steps": 40000, "loss": 0.1585, "lr": 3.5973845263825857e-09, "epoch": 32.55751125665166, "percentage": 99.46, "elapsed_time": "4:34:51", "remaining_time": "0:01:29", "throughput": 786.01, "total_tokens": 12962168} {"current_steps": 39790, "total_steps": 40000, "loss": 0.1954, "lr": 3.4327703247488684e-09, "epoch": 32.561604584527224, "percentage": 99.48, "elapsed_time": "4:34:52", "remaining_time": "0:01:27", "throughput": 786.02, "total_tokens": 12963752} {"current_steps": 39795, "total_steps": 40000, "loss": 0.1941, "lr": 3.2720109079037443e-09, "epoch": 32.56569791240278, "percentage": 99.49, "elapsed_time": "4:34:54", "remaining_time": "0:01:24", "throughput": 786.04, "total_tokens": 12965368} {"current_steps": 39800, "total_steps": 40000, "loss": 0.1194, "lr": 3.1151063006468193e-09, "epoch": 32.56979124027835, "percentage": 99.5, "elapsed_time": "4:34:56", "remaining_time": "0:01:22", "throughput": 786.06, "total_tokens": 12967000} {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.2150798738002777, "epoch": 32.56979124027835, "percentage": 99.5, "elapsed_time": "4:35:08", "remaining_time": "0:01:22", "throughput": 785.47, "total_tokens": 12967000} {"current_steps": 39805, "total_steps": 40000, "loss": 0.154, "lr": 2.962056527169854e-09, "epoch": 32.57388456815391, "percentage": 99.51, "elapsed_time": "4:35:12", "remaining_time": "0:01:20", "throughput": 785.4, "total_tokens": 12968648} {"current_steps": 39810, "total_steps": 40000, "loss": 0.1899, "lr": 2.8128616110761898e-09, "epoch": 32.57797789602947, "percentage": 99.52, "elapsed_time": "4:35:13", "remaining_time": "0:01:18", "throughput": 785.43, "total_tokens": 12970408} {"current_steps": 39815, "total_steps": 40000, "loss": 0.0849, "lr": 2.6675215753724223e-09, "epoch": 32.58207122390503, "percentage": 99.54, "elapsed_time": "4:35:15", "remaining_time": "0:01:16", "throughput": 785.44, "total_tokens": 12972008} {"current_steps": 39820, "total_steps": 40000, "loss": 0.1691, "lr": 2.5260364424739557e-09, "epoch": 32.5861645517806, "percentage": 99.55, "elapsed_time": "4:35:17", "remaining_time": "0:01:14", "throughput": 785.46, "total_tokens": 12973640} {"current_steps": 39825, "total_steps": 40000, "loss": 0.134, "lr": 2.3884062341994475e-09, "epoch": 32.59025787965616, "percentage": 99.56, "elapsed_time": "4:35:18", "remaining_time": "0:01:12", "throughput": 785.48, "total_tokens": 12975256} {"current_steps": 39830, "total_steps": 40000, "loss": 0.132, "lr": 2.25463097177081e-09, "epoch": 32.59435120753172, "percentage": 99.58, "elapsed_time": "4:35:20", "remaining_time": "0:01:10", "throughput": 785.5, "total_tokens": 12976920} {"current_steps": 39835, "total_steps": 40000, "loss": 0.1588, "lr": 2.1247106758215397e-09, "epoch": 32.59844453540729, "percentage": 99.59, "elapsed_time": "4:35:22", "remaining_time": "0:01:08", "throughput": 785.52, "total_tokens": 12978600} {"current_steps": 39840, "total_steps": 40000, "loss": 0.2047, "lr": 1.998645366382834e-09, "epoch": 32.60253786328285, "percentage": 99.6, "elapsed_time": "4:35:24", "remaining_time": "0:01:06", "throughput": 785.53, "total_tokens": 12980264} {"current_steps": 39845, "total_steps": 40000, "loss": 0.1774, "lr": 1.876435062897475e-09, "epoch": 32.606631191158414, "percentage": 99.61, "elapsed_time": "4:35:25", "remaining_time": "0:01:04", "throughput": 785.55, "total_tokens": 12981928} {"current_steps": 39850, "total_steps": 40000, "loss": 0.2028, "lr": 1.758079784211497e-09, "epoch": 32.61072451903397, "percentage": 99.62, "elapsed_time": "4:35:27", "remaining_time": "0:01:02", "throughput": 785.57, "total_tokens": 12983496} {"current_steps": 39855, "total_steps": 40000, "loss": 0.162, "lr": 1.6435795485797434e-09, "epoch": 32.61481784690954, "percentage": 99.64, "elapsed_time": "4:35:29", "remaining_time": "0:01:00", "throughput": 785.58, "total_tokens": 12985128} {"current_steps": 39860, "total_steps": 40000, "loss": 0.1563, "lr": 1.5329343736547596e-09, "epoch": 32.6189111747851, "percentage": 99.65, "elapsed_time": "4:35:31", "remaining_time": "0:00:58", "throughput": 785.6, "total_tokens": 12986744} {"current_steps": 39865, "total_steps": 40000, "loss": 0.1846, "lr": 1.4261442765006739e-09, "epoch": 32.62300450266066, "percentage": 99.66, "elapsed_time": "4:35:32", "remaining_time": "0:00:55", "throughput": 785.62, "total_tokens": 12988392} {"current_steps": 39870, "total_steps": 40000, "loss": 0.2113, "lr": 1.3232092735876445e-09, "epoch": 32.62709783053623, "percentage": 99.67, "elapsed_time": "4:35:34", "remaining_time": "0:00:53", "throughput": 785.63, "total_tokens": 12990008} {"current_steps": 39875, "total_steps": 40000, "loss": 0.2081, "lr": 1.2241293807918607e-09, "epoch": 32.63119115841179, "percentage": 99.69, "elapsed_time": "4:35:36", "remaining_time": "0:00:51", "throughput": 785.65, "total_tokens": 12991624} {"current_steps": 39880, "total_steps": 40000, "loss": 0.2393, "lr": 1.128904613387216e-09, "epoch": 32.635284486287354, "percentage": 99.7, "elapsed_time": "4:35:37", "remaining_time": "0:00:49", "throughput": 785.67, "total_tokens": 12993240} {"current_steps": 39885, "total_steps": 40000, "loss": 0.13, "lr": 1.0375349860591853e-09, "epoch": 32.63937781416291, "percentage": 99.71, "elapsed_time": "4:35:39", "remaining_time": "0:00:47", "throughput": 785.68, "total_tokens": 12994840} {"current_steps": 39890, "total_steps": 40000, "loss": 0.1616, "lr": 9.5002051290205e-10, "epoch": 32.64347114203848, "percentage": 99.72, "elapsed_time": "4:35:41", "remaining_time": "0:00:45", "throughput": 785.7, "total_tokens": 12996488} {"current_steps": 39895, "total_steps": 40000, "loss": 0.1642, "lr": 8.663612074077954e-10, "epoch": 32.64756446991404, "percentage": 99.74, "elapsed_time": "4:35:43", "remaining_time": "0:00:43", "throughput": 785.71, "total_tokens": 12998040} {"current_steps": 39900, "total_steps": 40000, "loss": 0.1757, "lr": 7.865570824799884e-10, "epoch": 32.6516577977896, "percentage": 99.75, "elapsed_time": "4:35:44", "remaining_time": "0:00:41", "throughput": 785.72, "total_tokens": 12999624} {"current_steps": 39905, "total_steps": 40000, "loss": 0.1977, "lr": 7.106081504254514e-10, "epoch": 32.65575112566516, "percentage": 99.76, "elapsed_time": "4:35:46", "remaining_time": "0:00:39", "throughput": 785.74, "total_tokens": 13001224} {"current_steps": 39910, "total_steps": 40000, "loss": 0.1909, "lr": 6.385144229570372e-10, "epoch": 32.65984445354073, "percentage": 99.78, "elapsed_time": "4:35:48", "remaining_time": "0:00:37", "throughput": 785.76, "total_tokens": 13002840} {"current_steps": 39915, "total_steps": 40000, "loss": 0.2365, "lr": 5.70275911190854e-10, "epoch": 32.663937781416294, "percentage": 99.79, "elapsed_time": "4:35:49", "remaining_time": "0:00:35", "throughput": 785.77, "total_tokens": 13004488} {"current_steps": 39920, "total_steps": 40000, "loss": 0.1423, "lr": 5.058926256490403e-10, "epoch": 32.66803110929185, "percentage": 99.8, "elapsed_time": "4:35:51", "remaining_time": "0:00:33", "throughput": 785.79, "total_tokens": 13006184} {"current_steps": 39925, "total_steps": 40000, "loss": 0.2071, "lr": 4.4536457626254134e-10, "epoch": 32.67212443716742, "percentage": 99.81, "elapsed_time": "4:35:53", "remaining_time": "0:00:31", "throughput": 785.81, "total_tokens": 13007848} {"current_steps": 39930, "total_steps": 40000, "loss": 0.1281, "lr": 3.88691772365557e-10, "epoch": 32.67621776504298, "percentage": 99.83, "elapsed_time": "4:35:55", "remaining_time": "0:00:29", "throughput": 785.83, "total_tokens": 13009496} {"current_steps": 39935, "total_steps": 40000, "loss": 0.1102, "lr": 3.358742226955425e-10, "epoch": 32.680311092918544, "percentage": 99.84, "elapsed_time": "4:35:56", "remaining_time": "0:00:26", "throughput": 785.85, "total_tokens": 13011080} {"current_steps": 39940, "total_steps": 40000, "loss": 0.1419, "lr": 2.8691193539875925e-10, "epoch": 32.6844044207941, "percentage": 99.85, "elapsed_time": "4:35:58", "remaining_time": "0:00:24", "throughput": 785.86, "total_tokens": 13012728} {"current_steps": 39945, "total_steps": 40000, "loss": 0.2107, "lr": 2.418049180274995e-10, "epoch": 32.68849774866967, "percentage": 99.86, "elapsed_time": "4:36:00", "remaining_time": "0:00:22", "throughput": 785.88, "total_tokens": 13014344} {"current_steps": 39950, "total_steps": 40000, "loss": 0.1458, "lr": 2.005531775373104e-10, "epoch": 32.692591076545234, "percentage": 99.88, "elapsed_time": "4:36:01", "remaining_time": "0:00:20", "throughput": 785.89, "total_tokens": 13015928} {"current_steps": 39955, "total_steps": 40000, "loss": 0.1568, "lr": 1.6315672028699435e-10, "epoch": 32.69668440442079, "percentage": 99.89, "elapsed_time": "4:36:03", "remaining_time": "0:00:18", "throughput": 785.91, "total_tokens": 13017528} {"current_steps": 39960, "total_steps": 40000, "loss": 0.1437, "lr": 1.2961555204693555e-10, "epoch": 32.70077773229636, "percentage": 99.9, "elapsed_time": "4:36:05", "remaining_time": "0:00:16", "throughput": 785.92, "total_tokens": 13019160} {"current_steps": 39965, "total_steps": 40000, "loss": 0.1441, "lr": 9.992967798799768e-11, "epoch": 32.70487106017192, "percentage": 99.91, "elapsed_time": "4:36:07", "remaining_time": "0:00:14", "throughput": 785.94, "total_tokens": 13020776} {"current_steps": 39970, "total_steps": 40000, "loss": 0.0982, "lr": 7.409910268707521e-11, "epoch": 32.708964388047484, "percentage": 99.92, "elapsed_time": "4:36:08", "remaining_time": "0:00:12", "throughput": 785.96, "total_tokens": 13022392} {"current_steps": 39975, "total_steps": 40000, "loss": 0.1015, "lr": 5.212383012986877e-11, "epoch": 32.71305771592304, "percentage": 99.94, "elapsed_time": "4:36:10", "remaining_time": "0:00:10", "throughput": 785.97, "total_tokens": 13023976} {"current_steps": 39980, "total_steps": 40000, "loss": 0.161, "lr": 3.400386370533415e-11, "epoch": 32.71715104379861, "percentage": 99.95, "elapsed_time": "4:36:12", "remaining_time": "0:00:08", "throughput": 785.98, "total_tokens": 13025544} {"current_steps": 39985, "total_steps": 40000, "loss": 0.1379, "lr": 1.9739206205682258e-11, "epoch": 32.721244371674175, "percentage": 99.96, "elapsed_time": "4:36:14", "remaining_time": "0:00:06", "throughput": 786.0, "total_tokens": 13027176} {"current_steps": 39990, "total_steps": 40000, "loss": 0.1276, "lr": 9.329859829154685e-12, "epoch": 32.72533769954973, "percentage": 99.98, "elapsed_time": "4:36:15", "remaining_time": "0:00:04", "throughput": 786.02, "total_tokens": 13028792} {"current_steps": 39995, "total_steps": 40000, "loss": 0.2259, "lr": 2.7758261855748148e-12, "epoch": 32.7294310274253, "percentage": 99.99, "elapsed_time": "4:36:17", "remaining_time": "0:00:02", "throughput": 786.03, "total_tokens": 13030344} {"current_steps": 40000, "total_steps": 40000, "loss": 0.1335, "lr": 7.710628524559838e-14, "epoch": 32.73352435530086, "percentage": 100.0, "elapsed_time": "4:36:19", "remaining_time": "0:00:00", "throughput": 786.04, "total_tokens": 13031928} {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.2150798738002777, "epoch": 32.73352435530086, "percentage": 100.0, "elapsed_time": "4:36:31", "remaining_time": "0:00:00", "throughput": 785.45, "total_tokens": 13031928} {"current_steps": 40000, "total_steps": 40000, "epoch": 32.73352435530086, "percentage": 100.0, "elapsed_time": "4:36:33", "remaining_time": "0:00:00", "throughput": 785.36, "total_tokens": 13031928}