htlou's picture
Upload folder using huggingface_hub
a687ba3 verified
raw
history blame
34.4 kB
{"current_steps": 5, "total_steps": 774, "loss": 1.7186, "learning_rate": 5e-07, "epoch": 0.019342359767891684, "percentage": 0.65, "elapsed_time": "0:01:09", "remaining_time": "2:57:11"}
{"current_steps": 10, "total_steps": 774, "loss": 1.5925, "learning_rate": 1e-06, "epoch": 0.03868471953578337, "percentage": 1.29, "elapsed_time": "0:02:14", "remaining_time": "2:50:58"}
{"current_steps": 15, "total_steps": 774, "loss": 1.2917, "learning_rate": 9.998943236640677e-07, "epoch": 0.058027079303675046, "percentage": 1.94, "elapsed_time": "0:03:20", "remaining_time": "2:48:41"}
{"current_steps": 20, "total_steps": 774, "loss": 1.152, "learning_rate": 9.995773393262229e-07, "epoch": 0.07736943907156674, "percentage": 2.58, "elapsed_time": "0:04:25", "remaining_time": "2:46:52"}
{"current_steps": 25, "total_steps": 774, "loss": 1.0662, "learning_rate": 9.99049180977439e-07, "epoch": 0.09671179883945841, "percentage": 3.23, "elapsed_time": "0:05:30", "remaining_time": "2:45:03"}
{"current_steps": 30, "total_steps": 774, "loss": 1.0205, "learning_rate": 9.983100718730718e-07, "epoch": 0.11605415860735009, "percentage": 3.88, "elapsed_time": "0:06:36", "remaining_time": "2:43:42"}
{"current_steps": 35, "total_steps": 774, "loss": 0.9948, "learning_rate": 9.973603244384906e-07, "epoch": 0.13539651837524178, "percentage": 4.52, "elapsed_time": "0:07:40", "remaining_time": "2:42:09"}
{"current_steps": 40, "total_steps": 774, "loss": 0.9421, "learning_rate": 9.9620034013701e-07, "epoch": 0.15473887814313347, "percentage": 5.17, "elapsed_time": "0:08:46", "remaining_time": "2:40:55"}
{"current_steps": 45, "total_steps": 774, "loss": 0.9544, "learning_rate": 9.948306093001933e-07, "epoch": 0.17408123791102514, "percentage": 5.81, "elapsed_time": "0:09:51", "remaining_time": "2:39:39"}
{"current_steps": 50, "total_steps": 774, "loss": 0.9541, "learning_rate": 9.932517109205849e-07, "epoch": 0.19342359767891681, "percentage": 6.46, "elapsed_time": "0:10:56", "remaining_time": "2:38:32"}
{"current_steps": 50, "total_steps": 774, "eval_loss": 0.9273383021354675, "epoch": 0.19342359767891681, "percentage": 6.46, "elapsed_time": "0:13:04", "remaining_time": "3:09:23"}
{"current_steps": 55, "total_steps": 774, "loss": 0.906, "learning_rate": 9.914643124069666e-07, "epoch": 0.2127659574468085, "percentage": 7.11, "elapsed_time": "0:14:09", "remaining_time": "3:05:00"}
{"current_steps": 60, "total_steps": 774, "loss": 0.9124, "learning_rate": 9.89469169302242e-07, "epoch": 0.23210831721470018, "percentage": 7.75, "elapsed_time": "0:15:14", "remaining_time": "3:01:24"}
{"current_steps": 65, "total_steps": 774, "loss": 0.9371, "learning_rate": 9.872671249640626e-07, "epoch": 0.2514506769825919, "percentage": 8.4, "elapsed_time": "0:16:19", "remaining_time": "2:58:08"}
{"current_steps": 70, "total_steps": 774, "loss": 0.9202, "learning_rate": 9.848591102083375e-07, "epoch": 0.27079303675048355, "percentage": 9.04, "elapsed_time": "0:17:24", "remaining_time": "2:55:02"}
{"current_steps": 75, "total_steps": 774, "loss": 0.9395, "learning_rate": 9.822461429157716e-07, "epoch": 0.2901353965183752, "percentage": 9.69, "elapsed_time": "0:18:29", "remaining_time": "2:52:23"}
{"current_steps": 80, "total_steps": 774, "loss": 0.9039, "learning_rate": 9.794293276016023e-07, "epoch": 0.30947775628626695, "percentage": 10.34, "elapsed_time": "0:19:34", "remaining_time": "2:49:51"}
{"current_steps": 85, "total_steps": 774, "loss": 0.8935, "learning_rate": 9.764098549487155e-07, "epoch": 0.3288201160541586, "percentage": 10.98, "elapsed_time": "0:20:40", "remaining_time": "2:47:31"}
{"current_steps": 90, "total_steps": 774, "loss": 0.8922, "learning_rate": 9.731890013043367e-07, "epoch": 0.3481624758220503, "percentage": 11.63, "elapsed_time": "0:21:44", "remaining_time": "2:45:16"}
{"current_steps": 95, "total_steps": 774, "loss": 0.8675, "learning_rate": 9.697681281405128e-07, "epoch": 0.36750483558994196, "percentage": 12.27, "elapsed_time": "0:22:50", "remaining_time": "2:43:18"}
{"current_steps": 100, "total_steps": 774, "loss": 0.8621, "learning_rate": 9.6614868147861e-07, "epoch": 0.38684719535783363, "percentage": 12.92, "elapsed_time": "0:23:55", "remaining_time": "2:41:18"}
{"current_steps": 100, "total_steps": 774, "eval_loss": 0.8719474077224731, "epoch": 0.38684719535783363, "percentage": 12.92, "elapsed_time": "0:26:03", "remaining_time": "2:55:39"}
{"current_steps": 105, "total_steps": 774, "loss": 0.8956, "learning_rate": 9.623321912780744e-07, "epoch": 0.40618955512572535, "percentage": 13.57, "elapsed_time": "0:27:09", "remaining_time": "2:53:01"}
{"current_steps": 110, "total_steps": 774, "loss": 0.8645, "learning_rate": 9.583202707897073e-07, "epoch": 0.425531914893617, "percentage": 14.21, "elapsed_time": "0:28:14", "remaining_time": "2:50:29"}
{"current_steps": 115, "total_steps": 774, "loss": 0.8526, "learning_rate": 9.54114615873738e-07, "epoch": 0.4448742746615087, "percentage": 14.86, "elapsed_time": "0:29:20", "remaining_time": "2:48:05"}
{"current_steps": 120, "total_steps": 774, "loss": 0.873, "learning_rate": 9.497170042829736e-07, "epoch": 0.46421663442940037, "percentage": 15.5, "elapsed_time": "0:30:25", "remaining_time": "2:45:47"}
{"current_steps": 125, "total_steps": 774, "loss": 0.8646, "learning_rate": 9.451292949113329e-07, "epoch": 0.4835589941972921, "percentage": 16.15, "elapsed_time": "0:31:31", "remaining_time": "2:43:38"}
{"current_steps": 130, "total_steps": 774, "loss": 0.8668, "learning_rate": 9.403534270080829e-07, "epoch": 0.5029013539651838, "percentage": 16.8, "elapsed_time": "0:32:35", "remaining_time": "2:41:26"}
{"current_steps": 135, "total_steps": 774, "loss": 0.8522, "learning_rate": 9.353914193581072e-07, "epoch": 0.5222437137330754, "percentage": 17.44, "elapsed_time": "0:33:40", "remaining_time": "2:39:25"}
{"current_steps": 140, "total_steps": 774, "loss": 0.8552, "learning_rate": 9.302453694285548e-07, "epoch": 0.5415860735009671, "percentage": 18.09, "elapsed_time": "0:34:45", "remaining_time": "2:37:23"}
{"current_steps": 145, "total_steps": 774, "loss": 0.8569, "learning_rate": 9.249174524822305e-07, "epoch": 0.5609284332688588, "percentage": 18.73, "elapsed_time": "0:35:50", "remaining_time": "2:35:27"}
{"current_steps": 150, "total_steps": 774, "loss": 0.8657, "learning_rate": 9.19409920658098e-07, "epoch": 0.5802707930367504, "percentage": 19.38, "elapsed_time": "0:36:55", "remaining_time": "2:33:35"}
{"current_steps": 150, "total_steps": 774, "eval_loss": 0.8459084033966064, "epoch": 0.5802707930367504, "percentage": 19.38, "elapsed_time": "0:39:02", "remaining_time": "2:42:26"}
{"current_steps": 155, "total_steps": 774, "loss": 0.8513, "learning_rate": 9.137251020192907e-07, "epoch": 0.5996131528046421, "percentage": 20.03, "elapsed_time": "0:40:07", "remaining_time": "2:40:13"}
{"current_steps": 160, "total_steps": 774, "loss": 0.8375, "learning_rate": 9.078653995690246e-07, "epoch": 0.6189555125725339, "percentage": 20.67, "elapsed_time": "0:41:11", "remaining_time": "2:38:05"}
{"current_steps": 165, "total_steps": 774, "loss": 0.8505, "learning_rate": 9.018332902348388e-07, "epoch": 0.6382978723404256, "percentage": 21.32, "elapsed_time": "0:42:16", "remaining_time": "2:36:03"}
{"current_steps": 170, "total_steps": 774, "loss": 0.8472, "learning_rate": 8.956313238215823e-07, "epoch": 0.6576402321083172, "percentage": 21.96, "elapsed_time": "0:43:22", "remaining_time": "2:34:05"}
{"current_steps": 175, "total_steps": 774, "loss": 0.8489, "learning_rate": 8.892621219336e-07, "epoch": 0.6769825918762089, "percentage": 22.61, "elapsed_time": "0:44:27", "remaining_time": "2:32:11"}
{"current_steps": 180, "total_steps": 774, "loss": 0.8463, "learning_rate": 8.827283768665648e-07, "epoch": 0.6963249516441006, "percentage": 23.26, "elapsed_time": "0:45:32", "remaining_time": "2:30:17"}
{"current_steps": 185, "total_steps": 774, "loss": 0.8303, "learning_rate": 8.760328504694317e-07, "epoch": 0.7156673114119922, "percentage": 23.9, "elapsed_time": "0:46:37", "remaining_time": "2:28:27"}
{"current_steps": 190, "total_steps": 774, "loss": 0.8285, "learning_rate": 8.691783729769873e-07, "epoch": 0.7350096711798839, "percentage": 24.55, "elapsed_time": "0:47:43", "remaining_time": "2:26:41"}
{"current_steps": 195, "total_steps": 774, "loss": 0.8267, "learning_rate": 8.621678418134963e-07, "epoch": 0.7543520309477756, "percentage": 25.19, "elapsed_time": "0:48:48", "remaining_time": "2:24:56"}
{"current_steps": 200, "total_steps": 774, "loss": 0.8232, "learning_rate": 8.550042203679439e-07, "epoch": 0.7736943907156673, "percentage": 25.84, "elapsed_time": "0:49:54", "remaining_time": "2:23:13"}
{"current_steps": 200, "total_steps": 774, "eval_loss": 0.8286838531494141, "epoch": 0.7736943907156673, "percentage": 25.84, "elapsed_time": "0:52:01", "remaining_time": "2:29:19"}
{"current_steps": 205, "total_steps": 774, "loss": 0.8321, "learning_rate": 8.476905367413957e-07, "epoch": 0.793036750483559, "percentage": 26.49, "elapsed_time": "0:53:06", "remaining_time": "2:27:25"}
{"current_steps": 210, "total_steps": 774, "loss": 0.8261, "learning_rate": 8.402298824670029e-07, "epoch": 0.8123791102514507, "percentage": 27.13, "elapsed_time": "0:54:12", "remaining_time": "2:25:35"}
{"current_steps": 215, "total_steps": 774, "loss": 0.83, "learning_rate": 8.326254112031949e-07, "epoch": 0.8317214700193424, "percentage": 27.78, "elapsed_time": "0:55:18", "remaining_time": "2:23:48"}
{"current_steps": 220, "total_steps": 774, "loss": 0.8263, "learning_rate": 8.248803374006113e-07, "epoch": 0.851063829787234, "percentage": 28.42, "elapsed_time": "0:56:23", "remaining_time": "2:22:01"}
{"current_steps": 225, "total_steps": 774, "loss": 0.8233, "learning_rate": 8.169979349433358e-07, "epoch": 0.8704061895551257, "percentage": 29.07, "elapsed_time": "0:57:29", "remaining_time": "2:20:17"}
{"current_steps": 230, "total_steps": 774, "loss": 0.8224, "learning_rate": 8.089815357650089e-07, "epoch": 0.8897485493230174, "percentage": 29.72, "elapsed_time": "0:58:35", "remaining_time": "2:18:35"}
{"current_steps": 235, "total_steps": 774, "loss": 0.823, "learning_rate": 8.008345284404003e-07, "epoch": 0.9090909090909091, "percentage": 30.36, "elapsed_time": "0:59:41", "remaining_time": "2:16:53"}
{"current_steps": 240, "total_steps": 774, "loss": 0.8363, "learning_rate": 7.925603567530418e-07, "epoch": 0.9284332688588007, "percentage": 31.01, "elapsed_time": "1:00:45", "remaining_time": "2:15:12"}
{"current_steps": 245, "total_steps": 774, "loss": 0.8396, "learning_rate": 7.841625182395206e-07, "epoch": 0.9477756286266924, "percentage": 31.65, "elapsed_time": "1:01:50", "remaining_time": "2:13:31"}
{"current_steps": 250, "total_steps": 774, "loss": 0.8179, "learning_rate": 7.756445627110522e-07, "epoch": 0.9671179883945842, "percentage": 32.3, "elapsed_time": "1:02:55", "remaining_time": "2:11:53"}
{"current_steps": 250, "total_steps": 774, "eval_loss": 0.8162312507629395, "epoch": 0.9671179883945842, "percentage": 32.3, "elapsed_time": "1:05:03", "remaining_time": "2:16:21"}
{"current_steps": 255, "total_steps": 774, "loss": 0.8267, "learning_rate": 7.670100907529557e-07, "epoch": 0.9864603481624759, "percentage": 32.95, "elapsed_time": "1:06:08", "remaining_time": "2:14:37"}
{"current_steps": 260, "total_steps": 774, "loss": 0.7992, "learning_rate": 7.582627522026685e-07, "epoch": 1.0058027079303675, "percentage": 33.59, "elapsed_time": "1:07:14", "remaining_time": "2:12:55"}
{"current_steps": 265, "total_steps": 774, "loss": 0.7297, "learning_rate": 7.49406244606939e-07, "epoch": 1.0251450676982592, "percentage": 34.24, "elapsed_time": "1:08:18", "remaining_time": "2:11:12"}
{"current_steps": 270, "total_steps": 774, "loss": 0.7652, "learning_rate": 7.404443116588547e-07, "epoch": 1.0444874274661509, "percentage": 34.88, "elapsed_time": "1:09:23", "remaining_time": "2:09:32"}
{"current_steps": 275, "total_steps": 774, "loss": 0.7412, "learning_rate": 7.31380741615363e-07, "epoch": 1.0638297872340425, "percentage": 35.53, "elapsed_time": "1:10:28", "remaining_time": "2:07:53"}
{"current_steps": 280, "total_steps": 774, "loss": 0.7637, "learning_rate": 7.222193656959546e-07, "epoch": 1.0831721470019342, "percentage": 36.18, "elapsed_time": "1:11:33", "remaining_time": "2:06:15"}
{"current_steps": 285, "total_steps": 774, "loss": 0.7634, "learning_rate": 7.129640564631863e-07, "epoch": 1.1025145067698259, "percentage": 36.82, "elapsed_time": "1:12:39", "remaining_time": "2:04:39"}
{"current_steps": 290, "total_steps": 774, "loss": 0.7502, "learning_rate": 7.036187261857288e-07, "epoch": 1.1218568665377175, "percentage": 37.47, "elapsed_time": "1:13:44", "remaining_time": "2:03:05"}
{"current_steps": 295, "total_steps": 774, "loss": 0.7737, "learning_rate": 6.941873251846293e-07, "epoch": 1.1411992263056092, "percentage": 38.11, "elapsed_time": "1:14:50", "remaining_time": "2:01:31"}
{"current_steps": 300, "total_steps": 774, "loss": 0.7558, "learning_rate": 6.846738401634898e-07, "epoch": 1.1605415860735009, "percentage": 38.76, "elapsed_time": "1:15:55", "remaining_time": "1:59:58"}
{"current_steps": 300, "total_steps": 774, "eval_loss": 0.8122316598892212, "epoch": 1.1605415860735009, "percentage": 38.76, "elapsed_time": "1:18:03", "remaining_time": "2:03:20"}
{"current_steps": 305, "total_steps": 774, "loss": 0.7701, "learning_rate": 6.750822925232663e-07, "epoch": 1.1798839458413926, "percentage": 39.41, "elapsed_time": "1:19:08", "remaining_time": "2:01:41"}
{"current_steps": 310, "total_steps": 774, "loss": 0.7641, "learning_rate": 6.654167366624008e-07, "epoch": 1.1992263056092844, "percentage": 40.05, "elapsed_time": "1:20:13", "remaining_time": "2:00:05"}
{"current_steps": 315, "total_steps": 774, "loss": 0.7481, "learning_rate": 6.556812582630059e-07, "epoch": 1.218568665377176, "percentage": 40.7, "elapsed_time": "1:21:18", "remaining_time": "1:58:29"}
{"current_steps": 320, "total_steps": 774, "loss": 0.7494, "learning_rate": 6.458799725638248e-07, "epoch": 1.2379110251450678, "percentage": 41.34, "elapsed_time": "1:22:23", "remaining_time": "1:56:53"}
{"current_steps": 325, "total_steps": 774, "loss": 0.7291, "learning_rate": 6.36017022620698e-07, "epoch": 1.2572533849129595, "percentage": 41.99, "elapsed_time": "1:23:29", "remaining_time": "1:55:20"}
{"current_steps": 330, "total_steps": 774, "loss": 0.7643, "learning_rate": 6.260965775552713e-07, "epoch": 1.2765957446808511, "percentage": 42.64, "elapsed_time": "1:24:35", "remaining_time": "1:53:48"}
{"current_steps": 335, "total_steps": 774, "loss": 0.7374, "learning_rate": 6.161228307926858e-07, "epoch": 1.2959381044487428, "percentage": 43.28, "elapsed_time": "1:25:39", "remaining_time": "1:52:15"}
{"current_steps": 340, "total_steps": 774, "loss": 0.7568, "learning_rate": 6.060999982889954e-07, "epoch": 1.3152804642166345, "percentage": 43.93, "elapsed_time": "1:26:45", "remaining_time": "1:50:44"}
{"current_steps": 345, "total_steps": 774, "loss": 0.7453, "learning_rate": 5.960323167490588e-07, "epoch": 1.3346228239845261, "percentage": 44.57, "elapsed_time": "1:27:50", "remaining_time": "1:49:13"}
{"current_steps": 350, "total_steps": 774, "loss": 0.7602, "learning_rate": 5.859240418356614e-07, "epoch": 1.3539651837524178, "percentage": 45.22, "elapsed_time": "1:28:55", "remaining_time": "1:47:43"}
{"current_steps": 350, "total_steps": 774, "eval_loss": 0.8059322834014893, "epoch": 1.3539651837524178, "percentage": 45.22, "elapsed_time": "1:31:03", "remaining_time": "1:50:18"}
{"current_steps": 355, "total_steps": 774, "loss": 0.7523, "learning_rate": 5.757794463706253e-07, "epoch": 1.3733075435203095, "percentage": 45.87, "elapsed_time": "1:32:09", "remaining_time": "1:48:45"}
{"current_steps": 360, "total_steps": 774, "loss": 0.7496, "learning_rate": 5.656028185286637e-07, "epoch": 1.3926499032882012, "percentage": 46.51, "elapsed_time": "1:33:14", "remaining_time": "1:47:13"}
{"current_steps": 365, "total_steps": 774, "loss": 0.7647, "learning_rate": 5.553984600247463e-07, "epoch": 1.4119922630560928, "percentage": 47.16, "elapsed_time": "1:34:19", "remaining_time": "1:45:41"}
{"current_steps": 370, "total_steps": 774, "loss": 0.718, "learning_rate": 5.451706842957421e-07, "epoch": 1.4313346228239845, "percentage": 47.8, "elapsed_time": "1:35:24", "remaining_time": "1:44:10"}
{"current_steps": 375, "total_steps": 774, "loss": 0.7583, "learning_rate": 5.349238146771061e-07, "epoch": 1.4506769825918762, "percentage": 48.45, "elapsed_time": "1:36:30", "remaining_time": "1:42:40"}
{"current_steps": 380, "total_steps": 774, "loss": 0.7435, "learning_rate": 5.246621825753827e-07, "epoch": 1.4700193423597678, "percentage": 49.1, "elapsed_time": "1:37:35", "remaining_time": "1:41:11"}
{"current_steps": 385, "total_steps": 774, "loss": 0.7397, "learning_rate": 5.143901256372967e-07, "epoch": 1.4893617021276595, "percentage": 49.74, "elapsed_time": "1:38:41", "remaining_time": "1:39:42"}
{"current_steps": 390, "total_steps": 774, "loss": 0.7295, "learning_rate": 5.041119859162068e-07, "epoch": 1.5087040618955512, "percentage": 50.39, "elapsed_time": "1:39:46", "remaining_time": "1:38:13"}
{"current_steps": 395, "total_steps": 774, "loss": 0.7484, "learning_rate": 4.938321080366968e-07, "epoch": 1.528046421663443, "percentage": 51.03, "elapsed_time": "1:40:51", "remaining_time": "1:36:46"}
{"current_steps": 400, "total_steps": 774, "loss": 0.771, "learning_rate": 4.835548373580792e-07, "epoch": 1.5473887814313345, "percentage": 51.68, "elapsed_time": "1:41:57", "remaining_time": "1:35:19"}
{"current_steps": 400, "total_steps": 774, "eval_loss": 0.7998485565185547, "epoch": 1.5473887814313345, "percentage": 51.68, "elapsed_time": "1:44:05", "remaining_time": "1:37:19"}
{"current_steps": 405, "total_steps": 774, "loss": 0.7472, "learning_rate": 4.73284518137589e-07, "epoch": 1.5667311411992264, "percentage": 52.33, "elapsed_time": "1:45:10", "remaining_time": "1:35:49"}
{"current_steps": 410, "total_steps": 774, "loss": 0.7349, "learning_rate": 4.630254916940423e-07, "epoch": 1.5860735009671179, "percentage": 52.97, "elapsed_time": "1:46:15", "remaining_time": "1:34:20"}
{"current_steps": 415, "total_steps": 774, "loss": 0.7539, "learning_rate": 4.5278209457273825e-07, "epoch": 1.6054158607350097, "percentage": 53.62, "elapsed_time": "1:47:20", "remaining_time": "1:32:51"}
{"current_steps": 420, "total_steps": 774, "loss": 0.7561, "learning_rate": 4.425586567123779e-07, "epoch": 1.6247582205029012, "percentage": 54.26, "elapsed_time": "1:48:25", "remaining_time": "1:31:23"}
{"current_steps": 425, "total_steps": 774, "loss": 0.7456, "learning_rate": 4.3235949961477627e-07, "epoch": 1.644100580270793, "percentage": 54.91, "elapsed_time": "1:49:30", "remaining_time": "1:29:55"}
{"current_steps": 430, "total_steps": 774, "loss": 0.7458, "learning_rate": 4.2218893451814e-07, "epoch": 1.6634429400386848, "percentage": 55.56, "elapsed_time": "1:50:35", "remaining_time": "1:28:28"}
{"current_steps": 435, "total_steps": 774, "loss": 0.7394, "learning_rate": 4.120512605746842e-07, "epoch": 1.6827852998065764, "percentage": 56.2, "elapsed_time": "1:51:40", "remaining_time": "1:27:02"}
{"current_steps": 440, "total_steps": 774, "loss": 0.7365, "learning_rate": 4.019507630333577e-07, "epoch": 1.702127659574468, "percentage": 56.85, "elapsed_time": "1:52:46", "remaining_time": "1:25:36"}
{"current_steps": 445, "total_steps": 774, "loss": 0.7559, "learning_rate": 3.9189171142844553e-07, "epoch": 1.7214700193423598, "percentage": 57.49, "elapsed_time": "1:53:52", "remaining_time": "1:24:11"}
{"current_steps": 450, "total_steps": 774, "loss": 0.753, "learning_rate": 3.8187835777481375e-07, "epoch": 1.7408123791102514, "percentage": 58.14, "elapsed_time": "1:54:56", "remaining_time": "1:22:45"}
{"current_steps": 450, "total_steps": 774, "eval_loss": 0.7954617738723755, "epoch": 1.7408123791102514, "percentage": 58.14, "elapsed_time": "1:57:04", "remaining_time": "1:24:17"}
{"current_steps": 455, "total_steps": 774, "loss": 0.7416, "learning_rate": 3.7191493477056086e-07, "epoch": 1.760154738878143, "percentage": 58.79, "elapsed_time": "1:58:09", "remaining_time": "1:22:50"}
{"current_steps": 460, "total_steps": 774, "loss": 0.7465, "learning_rate": 3.620056540078323e-07, "epoch": 1.7794970986460348, "percentage": 59.43, "elapsed_time": "1:59:15", "remaining_time": "1:21:24"}
{"current_steps": 465, "total_steps": 774, "loss": 0.7381, "learning_rate": 3.5215470419255897e-07, "epoch": 1.7988394584139265, "percentage": 60.08, "elapsed_time": "2:00:20", "remaining_time": "1:19:58"}
{"current_steps": 470, "total_steps": 774, "loss": 0.7393, "learning_rate": 3.423662493738687e-07, "epoch": 1.8181818181818183, "percentage": 60.72, "elapsed_time": "2:01:24", "remaining_time": "1:18:31"}
{"current_steps": 475, "total_steps": 774, "loss": 0.7361, "learning_rate": 3.3264442718392014e-07, "epoch": 1.8375241779497098, "percentage": 61.37, "elapsed_time": "2:02:30", "remaining_time": "1:17:06"}
{"current_steps": 480, "total_steps": 774, "loss": 0.743, "learning_rate": 3.229933470889038e-07, "epoch": 1.8568665377176017, "percentage": 62.02, "elapsed_time": "2:03:36", "remaining_time": "1:15:42"}
{"current_steps": 485, "total_steps": 774, "loss": 0.722, "learning_rate": 3.134170886519486e-07, "epoch": 1.8762088974854931, "percentage": 62.66, "elapsed_time": "2:04:41", "remaining_time": "1:14:17"}
{"current_steps": 490, "total_steps": 774, "loss": 0.7292, "learning_rate": 3.039196998086687e-07, "epoch": 1.895551257253385, "percentage": 63.31, "elapsed_time": "2:05:46", "remaining_time": "1:12:53"}
{"current_steps": 495, "total_steps": 774, "loss": 0.7402, "learning_rate": 2.9450519515607963e-07, "epoch": 1.9148936170212765, "percentage": 63.95, "elapsed_time": "2:06:52", "remaining_time": "1:11:30"}
{"current_steps": 500, "total_steps": 774, "loss": 0.7479, "learning_rate": 2.8517755425560663e-07, "epoch": 1.9342359767891684, "percentage": 64.6, "elapsed_time": "2:07:57", "remaining_time": "1:10:07"}
{"current_steps": 500, "total_steps": 774, "eval_loss": 0.7919633984565735, "epoch": 1.9342359767891684, "percentage": 64.6, "elapsed_time": "2:10:05", "remaining_time": "1:11:17"}
{"current_steps": 505, "total_steps": 774, "loss": 0.7414, "learning_rate": 2.7594071995090283e-07, "epoch": 1.9535783365570598, "percentage": 65.25, "elapsed_time": "2:11:10", "remaining_time": "1:09:52"}
{"current_steps": 510, "total_steps": 774, "loss": 0.7442, "learning_rate": 2.667985967011878e-07, "epoch": 1.9729206963249517, "percentage": 65.89, "elapsed_time": "2:12:15", "remaining_time": "1:08:27"}
{"current_steps": 515, "total_steps": 774, "loss": 0.7445, "learning_rate": 2.577550489308123e-07, "epoch": 1.9922630560928434, "percentage": 66.54, "elapsed_time": "2:13:21", "remaining_time": "1:07:04"}
{"current_steps": 520, "total_steps": 774, "loss": 0.7238, "learning_rate": 2.488138993957452e-07, "epoch": 2.011605415860735, "percentage": 67.18, "elapsed_time": "2:14:26", "remaining_time": "1:05:40"}
{"current_steps": 525, "total_steps": 774, "loss": 0.7148, "learning_rate": 2.3997892756767394e-07, "epoch": 2.0309477756286265, "percentage": 67.83, "elapsed_time": "2:15:31", "remaining_time": "1:04:16"}
{"current_steps": 530, "total_steps": 774, "loss": 0.6955, "learning_rate": 2.3125386803640183e-07, "epoch": 2.0502901353965184, "percentage": 68.48, "elapsed_time": "2:16:36", "remaining_time": "1:02:53"}
{"current_steps": 535, "total_steps": 774, "loss": 0.7016, "learning_rate": 2.226424089312174e-07, "epoch": 2.0696324951644103, "percentage": 69.12, "elapsed_time": "2:17:41", "remaining_time": "1:01:30"}
{"current_steps": 540, "total_steps": 774, "loss": 0.7054, "learning_rate": 2.1414819036190157e-07, "epoch": 2.0889748549323017, "percentage": 69.77, "elapsed_time": "2:18:47", "remaining_time": "1:00:08"}
{"current_steps": 545, "total_steps": 774, "loss": 0.6801, "learning_rate": 2.057748028800344e-07, "epoch": 2.1083172147001936, "percentage": 70.41, "elapsed_time": "2:19:52", "remaining_time": "0:58:46"}
{"current_steps": 550, "total_steps": 774, "loss": 0.6735, "learning_rate": 1.9752578596124952e-07, "epoch": 2.127659574468085, "percentage": 71.06, "elapsed_time": "2:20:57", "remaining_time": "0:57:24"}
{"current_steps": 550, "total_steps": 774, "eval_loss": 0.7972328066825867, "epoch": 2.127659574468085, "percentage": 71.06, "elapsed_time": "2:23:05", "remaining_time": "0:58:16"}
{"current_steps": 555, "total_steps": 774, "loss": 0.6887, "learning_rate": 1.8940462650907912e-07, "epoch": 2.147001934235977, "percentage": 71.71, "elapsed_time": "2:24:10", "remaining_time": "0:56:53"}
{"current_steps": 560, "total_steps": 774, "loss": 0.6829, "learning_rate": 1.8141475738102086e-07, "epoch": 2.1663442940038684, "percentage": 72.35, "elapsed_time": "2:25:15", "remaining_time": "0:55:30"}
{"current_steps": 565, "total_steps": 774, "loss": 0.701, "learning_rate": 1.735595559374508e-07, "epoch": 2.1856866537717603, "percentage": 73.0, "elapsed_time": "2:26:20", "remaining_time": "0:54:08"}
{"current_steps": 570, "total_steps": 774, "loss": 0.6962, "learning_rate": 1.6584234261399532e-07, "epoch": 2.2050290135396517, "percentage": 73.64, "elapsed_time": "2:27:27", "remaining_time": "0:52:46"}
{"current_steps": 575, "total_steps": 774, "loss": 0.704, "learning_rate": 1.5826637951796474e-07, "epoch": 2.2243713733075436, "percentage": 74.29, "elapsed_time": "2:28:32", "remaining_time": "0:51:24"}
{"current_steps": 580, "total_steps": 774, "loss": 0.6866, "learning_rate": 1.5083486904944387e-07, "epoch": 2.243713733075435, "percentage": 74.94, "elapsed_time": "2:29:37", "remaining_time": "0:50:02"}
{"current_steps": 585, "total_steps": 774, "loss": 0.6921, "learning_rate": 1.4355095254761974e-07, "epoch": 2.263056092843327, "percentage": 75.58, "elapsed_time": "2:30:42", "remaining_time": "0:48:41"}
{"current_steps": 590, "total_steps": 774, "loss": 0.6813, "learning_rate": 1.3641770896292082e-07, "epoch": 2.2823984526112184, "percentage": 76.23, "elapsed_time": "2:31:48", "remaining_time": "0:47:20"}
{"current_steps": 595, "total_steps": 774, "loss": 0.6928, "learning_rate": 1.2943815355552851e-07, "epoch": 2.3017408123791103, "percentage": 76.87, "elapsed_time": "2:32:52", "remaining_time": "0:45:59"}
{"current_steps": 600, "total_steps": 774, "loss": 0.7116, "learning_rate": 1.226152366208104e-07, "epoch": 2.3210831721470018, "percentage": 77.52, "elapsed_time": "2:33:58", "remaining_time": "0:44:39"}
{"current_steps": 600, "total_steps": 774, "eval_loss": 0.7951865196228027, "epoch": 2.3210831721470018, "percentage": 77.52, "elapsed_time": "2:36:06", "remaining_time": "0:45:16"}
{"current_steps": 605, "total_steps": 774, "loss": 0.692, "learning_rate": 1.1595184224221466e-07, "epoch": 2.3404255319148937, "percentage": 78.17, "elapsed_time": "2:37:11", "remaining_time": "0:43:54"}
{"current_steps": 610, "total_steps": 774, "loss": 0.6865, "learning_rate": 1.0945078707215221e-07, "epoch": 2.359767891682785, "percentage": 78.81, "elapsed_time": "2:38:17", "remaining_time": "0:42:33"}
{"current_steps": 615, "total_steps": 774, "loss": 0.6985, "learning_rate": 1.0311481914138371e-07, "epoch": 2.379110251450677, "percentage": 79.46, "elapsed_time": "2:39:22", "remaining_time": "0:41:12"}
{"current_steps": 620, "total_steps": 774, "loss": 0.6968, "learning_rate": 9.6946616697411e-08, "epoch": 2.398452611218569, "percentage": 80.1, "elapsed_time": "2:40:27", "remaining_time": "0:39:51"}
{"current_steps": 625, "total_steps": 774, "loss": 0.7002, "learning_rate": 9.094878707236841e-08, "epoch": 2.4177949709864603, "percentage": 80.75, "elapsed_time": "2:41:33", "remaining_time": "0:38:30"}
{"current_steps": 630, "total_steps": 774, "loss": 0.7018, "learning_rate": 8.512386558088919e-08, "epoch": 2.437137330754352, "percentage": 81.4, "elapsed_time": "2:42:38", "remaining_time": "0:37:10"}
{"current_steps": 635, "total_steps": 774, "loss": 0.6953, "learning_rate": 7.947431444841452e-08, "epoch": 2.4564796905222437, "percentage": 82.04, "elapsed_time": "2:43:43", "remaining_time": "0:35:50"}
{"current_steps": 640, "total_steps": 774, "loss": 0.7023, "learning_rate": 7.400252177039784e-08, "epoch": 2.4758220502901356, "percentage": 82.69, "elapsed_time": "2:44:48", "remaining_time": "0:34:30"}
{"current_steps": 645, "total_steps": 774, "loss": 0.6822, "learning_rate": 6.871080050284394e-08, "epoch": 2.495164410058027, "percentage": 83.33, "elapsed_time": "2:45:53", "remaining_time": "0:33:10"}
{"current_steps": 650, "total_steps": 774, "loss": 0.6822, "learning_rate": 6.360138748461013e-08, "epoch": 2.514506769825919, "percentage": 83.98, "elapsed_time": "2:46:58", "remaining_time": "0:31:51"}
{"current_steps": 650, "total_steps": 774, "eval_loss": 0.794310986995697, "epoch": 2.514506769825919, "percentage": 83.98, "elapsed_time": "2:49:06", "remaining_time": "0:32:15"}
{"current_steps": 655, "total_steps": 774, "loss": 0.6991, "learning_rate": 5.867644249188247e-08, "epoch": 2.5338491295938104, "percentage": 84.63, "elapsed_time": "2:50:12", "remaining_time": "0:30:55"}
{"current_steps": 660, "total_steps": 774, "loss": 0.6986, "learning_rate": 5.3938047325226944e-08, "epoch": 2.5531914893617023, "percentage": 85.27, "elapsed_time": "2:51:18", "remaining_time": "0:29:35"}
{"current_steps": 665, "total_steps": 774, "loss": 0.6854, "learning_rate": 4.9388204929601326e-08, "epoch": 2.5725338491295937, "percentage": 85.92, "elapsed_time": "2:52:23", "remaining_time": "0:28:15"}
{"current_steps": 670, "total_steps": 774, "loss": 0.6924, "learning_rate": 4.5028838547699346e-08, "epoch": 2.5918762088974856, "percentage": 86.56, "elapsed_time": "2:53:28", "remaining_time": "0:26:55"}
{"current_steps": 675, "total_steps": 774, "loss": 0.6888, "learning_rate": 4.0861790906985884e-08, "epoch": 2.611218568665377, "percentage": 87.21, "elapsed_time": "2:54:34", "remaining_time": "0:25:36"}
{"current_steps": 680, "total_steps": 774, "loss": 0.6914, "learning_rate": 3.6888823440766214e-08, "epoch": 2.630560928433269, "percentage": 87.86, "elapsed_time": "2:55:39", "remaining_time": "0:24:16"}
{"current_steps": 685, "total_steps": 774, "loss": 0.6773, "learning_rate": 3.311161554361874e-08, "epoch": 2.6499032882011604, "percentage": 88.5, "elapsed_time": "2:56:44", "remaining_time": "0:22:57"}
{"current_steps": 690, "total_steps": 774, "loss": 0.6908, "learning_rate": 2.9531763861505964e-08, "epoch": 2.6692456479690523, "percentage": 89.15, "elapsed_time": "2:57:49", "remaining_time": "0:21:38"}
{"current_steps": 695, "total_steps": 774, "loss": 0.6638, "learning_rate": 2.6150781616863794e-08, "epoch": 2.6885880077369437, "percentage": 89.79, "elapsed_time": "2:58:55", "remaining_time": "0:20:20"}
{"current_steps": 700, "total_steps": 774, "loss": 0.6861, "learning_rate": 2.2970097968953994e-08, "epoch": 2.7079303675048356, "percentage": 90.44, "elapsed_time": "3:00:00", "remaining_time": "0:19:01"}
{"current_steps": 700, "total_steps": 774, "eval_loss": 0.7937687635421753, "epoch": 2.7079303675048356, "percentage": 90.44, "elapsed_time": "3:02:08", "remaining_time": "0:19:15"}
{"current_steps": 705, "total_steps": 774, "loss": 0.6911, "learning_rate": 1.9991057409751267e-08, "epoch": 2.7272727272727275, "percentage": 91.09, "elapsed_time": "3:03:14", "remaining_time": "0:17:56"}
{"current_steps": 710, "total_steps": 774, "loss": 0.6909, "learning_rate": 1.7214919195619125e-08, "epoch": 2.746615087040619, "percentage": 91.73, "elapsed_time": "3:04:19", "remaining_time": "0:16:36"}
{"current_steps": 715, "total_steps": 774, "loss": 0.6999, "learning_rate": 1.4642856815015758e-08, "epoch": 2.7659574468085104, "percentage": 92.38, "elapsed_time": "3:05:24", "remaining_time": "0:15:17"}
{"current_steps": 720, "total_steps": 774, "loss": 0.6933, "learning_rate": 1.2275957492453692e-08, "epoch": 2.7852998065764023, "percentage": 93.02, "elapsed_time": "3:06:30", "remaining_time": "0:13:59"}
{"current_steps": 725, "total_steps": 774, "loss": 0.6775, "learning_rate": 1.0115221728924706e-08, "epoch": 2.804642166344294, "percentage": 93.67, "elapsed_time": "3:07:35", "remaining_time": "0:12:40"}
{"current_steps": 730, "total_steps": 774, "loss": 0.6748, "learning_rate": 8.161562878982398e-09, "epoch": 2.8239845261121856, "percentage": 94.32, "elapsed_time": "3:08:40", "remaining_time": "0:11:22"}
{"current_steps": 735, "total_steps": 774, "loss": 0.6759, "learning_rate": 6.415806764662524e-09, "epoch": 2.843326885880077, "percentage": 94.96, "elapsed_time": "3:09:46", "remaining_time": "0:10:04"}
{"current_steps": 740, "total_steps": 774, "loss": 0.698, "learning_rate": 4.8786913264033945e-09, "epoch": 2.862669245647969, "percentage": 95.61, "elapsed_time": "3:10:51", "remaining_time": "0:08:46"}
{"current_steps": 745, "total_steps": 774, "loss": 0.6856, "learning_rate": 3.5508663111147306e-09, "epoch": 2.882011605415861, "percentage": 96.25, "elapsed_time": "3:11:56", "remaining_time": "0:07:28"}
{"current_steps": 750, "total_steps": 774, "loss": 0.6989, "learning_rate": 2.432892997526026e-09, "epoch": 2.9013539651837523, "percentage": 96.9, "elapsed_time": "3:13:02", "remaining_time": "0:06:10"}
{"current_steps": 750, "total_steps": 774, "eval_loss": 0.7935436367988586, "epoch": 2.9013539651837523, "percentage": 96.9, "elapsed_time": "3:15:09", "remaining_time": "0:06:14"}
{"current_steps": 755, "total_steps": 774, "loss": 0.6929, "learning_rate": 1.5252439589311107e-09, "epoch": 2.920696324951644, "percentage": 97.55, "elapsed_time": "3:16:15", "remaining_time": "0:04:56"}
{"current_steps": 760, "total_steps": 774, "loss": 0.6963, "learning_rate": 8.283028634287203e-10, "epoch": 2.9400386847195357, "percentage": 98.19, "elapsed_time": "3:17:21", "remaining_time": "0:03:38"}
{"current_steps": 765, "total_steps": 774, "loss": 0.683, "learning_rate": 3.4236431174428094e-10, "epoch": 2.9593810444874276, "percentage": 98.84, "elapsed_time": "3:18:26", "remaining_time": "0:02:20"}
{"current_steps": 770, "total_steps": 774, "loss": 0.684, "learning_rate": 6.763371270035457e-11, "epoch": 2.978723404255319, "percentage": 99.48, "elapsed_time": "3:19:31", "remaining_time": "0:01:02"}
{"current_steps": 774, "total_steps": 774, "epoch": 2.9941972920696323, "percentage": 100.0, "elapsed_time": "3:20:56", "remaining_time": "0:00:00"}