chchen's picture
Training in progress, step 3245
caedb62 verified
{"current_steps": 10, "total_steps": 3245, "loss": 1.6846, "lr": 3.0769230769230774e-06, "epoch": 0.015392015392015393, "percentage": 0.31, "elapsed_time": "0:01:26", "remaining_time": "7:46:20"}
{"current_steps": 20, "total_steps": 3245, "loss": 1.7088, "lr": 6.153846153846155e-06, "epoch": 0.030784030784030785, "percentage": 0.62, "elapsed_time": "0:02:53", "remaining_time": "7:47:16"}
{"current_steps": 30, "total_steps": 3245, "loss": 1.6361, "lr": 9.230769230769232e-06, "epoch": 0.046176046176046176, "percentage": 0.92, "elapsed_time": "0:04:21", "remaining_time": "7:47:11"}
{"current_steps": 40, "total_steps": 3245, "loss": 1.3897, "lr": 1.230769230769231e-05, "epoch": 0.06156806156806157, "percentage": 1.23, "elapsed_time": "0:05:48", "remaining_time": "7:45:59"}
{"current_steps": 50, "total_steps": 3245, "loss": 0.8796, "lr": 1.5384615384615387e-05, "epoch": 0.07696007696007696, "percentage": 1.54, "elapsed_time": "0:07:16", "remaining_time": "7:44:30"}
{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.6148930191993713, "epoch": 0.07696007696007696, "percentage": 1.54, "elapsed_time": "0:10:33", "remaining_time": "11:15:00"}
{"current_steps": 60, "total_steps": 3245, "loss": 0.6706, "lr": 1.8461538461538465e-05, "epoch": 0.09235209235209235, "percentage": 1.85, "elapsed_time": "0:12:04", "remaining_time": "10:40:38"}
{"current_steps": 70, "total_steps": 3245, "loss": 0.4537, "lr": 2.1538461538461542e-05, "epoch": 0.10774410774410774, "percentage": 2.16, "elapsed_time": "0:13:31", "remaining_time": "10:13:33"}
{"current_steps": 80, "total_steps": 3245, "loss": 0.3221, "lr": 2.461538461538462e-05, "epoch": 0.12313612313612314, "percentage": 2.47, "elapsed_time": "0:14:58", "remaining_time": "9:52:35"}
{"current_steps": 90, "total_steps": 3245, "loss": 0.1961, "lr": 2.7692307692307694e-05, "epoch": 0.13852813852813853, "percentage": 2.77, "elapsed_time": "0:16:26", "remaining_time": "9:36:24"}
{"current_steps": 100, "total_steps": 3245, "loss": 0.1225, "lr": 3.0769230769230774e-05, "epoch": 0.15392015392015393, "percentage": 3.08, "elapsed_time": "0:17:53", "remaining_time": "9:22:48"}
{"current_steps": 100, "total_steps": 3245, "eval_loss": 0.10787783563137054, "epoch": 0.15392015392015393, "percentage": 3.08, "elapsed_time": "0:21:11", "remaining_time": "11:06:18"}
{"current_steps": 110, "total_steps": 3245, "loss": 0.1266, "lr": 3.384615384615385e-05, "epoch": 0.1693121693121693, "percentage": 3.39, "elapsed_time": "0:22:42", "remaining_time": "10:46:59"}
{"current_steps": 120, "total_steps": 3245, "loss": 0.095, "lr": 3.692307692307693e-05, "epoch": 0.1847041847041847, "percentage": 3.7, "elapsed_time": "0:24:09", "remaining_time": "10:28:58"}
{"current_steps": 130, "total_steps": 3245, "loss": 0.0803, "lr": 4e-05, "epoch": 0.2000962000962001, "percentage": 4.01, "elapsed_time": "0:25:35", "remaining_time": "10:13:23"}
{"current_steps": 140, "total_steps": 3245, "loss": 0.0952, "lr": 4.3076923076923084e-05, "epoch": 0.21548821548821548, "percentage": 4.31, "elapsed_time": "0:27:03", "remaining_time": "9:59:57"}
{"current_steps": 150, "total_steps": 3245, "loss": 0.0896, "lr": 4.615384615384616e-05, "epoch": 0.23088023088023088, "percentage": 4.62, "elapsed_time": "0:28:29", "remaining_time": "9:47:57"}
{"current_steps": 150, "total_steps": 3245, "eval_loss": 0.061511509120464325, "epoch": 0.23088023088023088, "percentage": 4.62, "elapsed_time": "0:31:46", "remaining_time": "10:55:41"}
{"current_steps": 160, "total_steps": 3245, "loss": 0.0479, "lr": 4.923076923076924e-05, "epoch": 0.24627224627224628, "percentage": 4.93, "elapsed_time": "0:33:16", "remaining_time": "10:41:40"}
{"current_steps": 170, "total_steps": 3245, "loss": 0.0745, "lr": 5.230769230769231e-05, "epoch": 0.26166426166426165, "percentage": 5.24, "elapsed_time": "0:34:43", "remaining_time": "10:28:03"}
{"current_steps": 180, "total_steps": 3245, "loss": 0.062, "lr": 5.538461538461539e-05, "epoch": 0.27705627705627706, "percentage": 5.55, "elapsed_time": "0:36:10", "remaining_time": "10:15:50"}
{"current_steps": 190, "total_steps": 3245, "loss": 0.0677, "lr": 5.846153846153847e-05, "epoch": 0.29244829244829246, "percentage": 5.86, "elapsed_time": "0:37:36", "remaining_time": "10:04:42"}
{"current_steps": 200, "total_steps": 3245, "loss": 0.0656, "lr": 6.153846153846155e-05, "epoch": 0.30784030784030786, "percentage": 6.16, "elapsed_time": "0:39:03", "remaining_time": "9:54:40"}
{"current_steps": 200, "total_steps": 3245, "eval_loss": 0.05193961039185524, "epoch": 0.30784030784030786, "percentage": 6.16, "elapsed_time": "0:42:20", "remaining_time": "10:44:34"}
{"current_steps": 210, "total_steps": 3245, "loss": 0.0635, "lr": 6.461538461538462e-05, "epoch": 0.32323232323232326, "percentage": 6.47, "elapsed_time": "0:43:51", "remaining_time": "10:33:44"}
{"current_steps": 220, "total_steps": 3245, "loss": 0.0705, "lr": 6.76923076923077e-05, "epoch": 0.3386243386243386, "percentage": 6.78, "elapsed_time": "0:45:17", "remaining_time": "10:22:49"}
{"current_steps": 230, "total_steps": 3245, "loss": 0.058, "lr": 7.076923076923078e-05, "epoch": 0.354016354016354, "percentage": 7.09, "elapsed_time": "0:46:44", "remaining_time": "10:12:45"}
{"current_steps": 240, "total_steps": 3245, "loss": 0.0615, "lr": 7.384615384615386e-05, "epoch": 0.3694083694083694, "percentage": 7.4, "elapsed_time": "0:48:11", "remaining_time": "10:03:20"}
{"current_steps": 250, "total_steps": 3245, "loss": 0.0599, "lr": 7.692307692307693e-05, "epoch": 0.3848003848003848, "percentage": 7.7, "elapsed_time": "0:49:37", "remaining_time": "9:54:34"}
{"current_steps": 250, "total_steps": 3245, "eval_loss": 0.048700157552957535, "epoch": 0.3848003848003848, "percentage": 7.7, "elapsed_time": "0:52:54", "remaining_time": "10:33:47"}
{"current_steps": 260, "total_steps": 3245, "loss": 0.0589, "lr": 8e-05, "epoch": 0.4001924001924002, "percentage": 8.01, "elapsed_time": "0:54:24", "remaining_time": "10:24:34"}
{"current_steps": 270, "total_steps": 3245, "loss": 0.0543, "lr": 8.307692307692309e-05, "epoch": 0.4155844155844156, "percentage": 8.32, "elapsed_time": "0:55:50", "remaining_time": "10:15:19"}
{"current_steps": 280, "total_steps": 3245, "loss": 0.0418, "lr": 8.615384615384617e-05, "epoch": 0.43097643097643096, "percentage": 8.63, "elapsed_time": "0:57:17", "remaining_time": "10:06:38"}
{"current_steps": 290, "total_steps": 3245, "loss": 0.056, "lr": 8.923076923076924e-05, "epoch": 0.44636844636844636, "percentage": 8.94, "elapsed_time": "0:58:44", "remaining_time": "9:58:29"}
{"current_steps": 300, "total_steps": 3245, "loss": 0.0559, "lr": 9.230769230769232e-05, "epoch": 0.46176046176046176, "percentage": 9.24, "elapsed_time": "1:00:10", "remaining_time": "9:50:45"}
{"current_steps": 300, "total_steps": 3245, "eval_loss": 0.0453476682305336, "epoch": 0.46176046176046176, "percentage": 9.24, "elapsed_time": "1:03:27", "remaining_time": "10:22:55"}
{"current_steps": 310, "total_steps": 3245, "loss": 0.047, "lr": 9.53846153846154e-05, "epoch": 0.47715247715247716, "percentage": 9.55, "elapsed_time": "1:04:57", "remaining_time": "10:15:01"}
{"current_steps": 320, "total_steps": 3245, "loss": 0.048, "lr": 9.846153846153848e-05, "epoch": 0.49254449254449256, "percentage": 9.86, "elapsed_time": "1:06:24", "remaining_time": "10:06:59"}
{"current_steps": 330, "total_steps": 3245, "loss": 0.065, "lr": 9.999927654251793e-05, "epoch": 0.5079365079365079, "percentage": 10.17, "elapsed_time": "1:07:51", "remaining_time": "9:59:22"}
{"current_steps": 340, "total_steps": 3245, "loss": 0.0422, "lr": 9.99934890082745e-05, "epoch": 0.5233285233285233, "percentage": 10.48, "elapsed_time": "1:09:17", "remaining_time": "9:52:05"}
{"current_steps": 350, "total_steps": 3245, "loss": 0.047, "lr": 9.99819146097084e-05, "epoch": 0.5387205387205387, "percentage": 10.79, "elapsed_time": "1:10:44", "remaining_time": "9:45:06"}
{"current_steps": 350, "total_steps": 3245, "eval_loss": 0.04271285608410835, "epoch": 0.5387205387205387, "percentage": 10.79, "elapsed_time": "1:14:00", "remaining_time": "10:12:11"}
{"current_steps": 360, "total_steps": 3245, "loss": 0.0413, "lr": 9.996455468658355e-05, "epoch": 0.5541125541125541, "percentage": 11.09, "elapsed_time": "1:15:30", "remaining_time": "10:05:08"}
{"current_steps": 370, "total_steps": 3245, "loss": 0.0399, "lr": 9.994141124835203e-05, "epoch": 0.5695045695045695, "percentage": 11.4, "elapsed_time": "1:16:57", "remaining_time": "9:57:58"}
{"current_steps": 380, "total_steps": 3245, "loss": 0.0383, "lr": 9.991248697392142e-05, "epoch": 0.5848965848965849, "percentage": 11.71, "elapsed_time": "1:18:23", "remaining_time": "9:51:05"}
{"current_steps": 390, "total_steps": 3245, "loss": 0.0396, "lr": 9.987778521134476e-05, "epoch": 0.6002886002886003, "percentage": 12.02, "elapsed_time": "1:19:51", "remaining_time": "9:44:33"}
{"current_steps": 400, "total_steps": 3245, "loss": 0.0386, "lr": 9.983730997743294e-05, "epoch": 0.6156806156806157, "percentage": 12.33, "elapsed_time": "1:21:17", "remaining_time": "9:38:11"}
{"current_steps": 400, "total_steps": 3245, "eval_loss": 0.03978649154305458, "epoch": 0.6156806156806157, "percentage": 12.33, "elapsed_time": "1:24:33", "remaining_time": "10:01:24"}
{"current_steps": 410, "total_steps": 3245, "loss": 0.058, "lr": 9.979106595728978e-05, "epoch": 0.6310726310726311, "percentage": 12.63, "elapsed_time": "1:26:03", "remaining_time": "9:55:00"}
{"current_steps": 420, "total_steps": 3245, "loss": 0.0347, "lr": 9.973905850376977e-05, "epoch": 0.6464646464646465, "percentage": 12.94, "elapsed_time": "1:27:30", "remaining_time": "9:48:34"}
{"current_steps": 430, "total_steps": 3245, "loss": 0.0443, "lr": 9.968129363685833e-05, "epoch": 0.6618566618566618, "percentage": 13.25, "elapsed_time": "1:28:56", "remaining_time": "9:42:18"}
{"current_steps": 440, "total_steps": 3245, "loss": 0.0424, "lr": 9.961777804297514e-05, "epoch": 0.6772486772486772, "percentage": 13.56, "elapsed_time": "1:30:23", "remaining_time": "9:36:15"}
{"current_steps": 450, "total_steps": 3245, "loss": 0.0402, "lr": 9.954851907420009e-05, "epoch": 0.6926406926406926, "percentage": 13.87, "elapsed_time": "1:31:50", "remaining_time": "9:30:24"}
{"current_steps": 450, "total_steps": 3245, "eval_loss": 0.04286464676260948, "epoch": 0.6926406926406926, "percentage": 13.87, "elapsed_time": "1:35:05", "remaining_time": "9:50:38"}
{"current_steps": 460, "total_steps": 3245, "loss": 0.0444, "lr": 9.947352474742222e-05, "epoch": 0.708032708032708, "percentage": 14.18, "elapsed_time": "1:36:35", "remaining_time": "9:44:48"}
{"current_steps": 470, "total_steps": 3245, "loss": 0.0529, "lr": 9.93928037434118e-05, "epoch": 0.7234247234247234, "percentage": 14.48, "elapsed_time": "1:38:01", "remaining_time": "9:38:47"}
{"current_steps": 480, "total_steps": 3245, "loss": 0.0435, "lr": 9.930636540581556e-05, "epoch": 0.7388167388167388, "percentage": 14.79, "elapsed_time": "1:39:28", "remaining_time": "9:33:02"}
{"current_steps": 490, "total_steps": 3245, "loss": 0.0393, "lr": 9.921421974007506e-05, "epoch": 0.7542087542087542, "percentage": 15.1, "elapsed_time": "1:40:55", "remaining_time": "9:27:25"}
{"current_steps": 500, "total_steps": 3245, "loss": 0.0525, "lr": 9.911637741226849e-05, "epoch": 0.7696007696007696, "percentage": 15.41, "elapsed_time": "1:42:21", "remaining_time": "9:21:56"}
{"current_steps": 500, "total_steps": 3245, "eval_loss": 0.03837933763861656, "epoch": 0.7696007696007696, "percentage": 15.41, "elapsed_time": "1:45:37", "remaining_time": "9:39:50"}
{"current_steps": 510, "total_steps": 3245, "loss": 0.0455, "lr": 9.90128497478762e-05, "epoch": 0.784992784992785, "percentage": 15.72, "elapsed_time": "1:47:06", "remaining_time": "9:34:23"}
{"current_steps": 520, "total_steps": 3245, "loss": 0.0424, "lr": 9.890364873046965e-05, "epoch": 0.8003848003848004, "percentage": 16.02, "elapsed_time": "1:48:32", "remaining_time": "9:28:49"}
{"current_steps": 530, "total_steps": 3245, "loss": 0.0289, "lr": 9.878878700032427e-05, "epoch": 0.8157768157768158, "percentage": 16.33, "elapsed_time": "1:49:59", "remaining_time": "9:23:24"}
{"current_steps": 540, "total_steps": 3245, "loss": 0.0429, "lr": 9.866827785295638e-05, "epoch": 0.8311688311688312, "percentage": 16.64, "elapsed_time": "1:51:25", "remaining_time": "9:18:09"}
{"current_steps": 550, "total_steps": 3245, "loss": 0.0374, "lr": 9.854213523758413e-05, "epoch": 0.8465608465608465, "percentage": 16.95, "elapsed_time": "1:52:52", "remaining_time": "9:13:03"}
{"current_steps": 550, "total_steps": 3245, "eval_loss": 0.03806205838918686, "epoch": 0.8465608465608465, "percentage": 16.95, "elapsed_time": "1:56:07", "remaining_time": "9:29:02"}
{"current_steps": 560, "total_steps": 3245, "loss": 0.0427, "lr": 9.841037375551294e-05, "epoch": 0.8619528619528619, "percentage": 17.26, "elapsed_time": "1:57:37", "remaining_time": "9:23:56"}
{"current_steps": 570, "total_steps": 3245, "loss": 0.0427, "lr": 9.827300865844527e-05, "epoch": 0.8773448773448773, "percentage": 17.57, "elapsed_time": "1:59:03", "remaining_time": "9:18:45"}
{"current_steps": 580, "total_steps": 3245, "loss": 0.0344, "lr": 9.813005584671522e-05, "epoch": 0.8927368927368927, "percentage": 17.87, "elapsed_time": "2:00:29", "remaining_time": "9:13:39"}
{"current_steps": 590, "total_steps": 3245, "loss": 0.0356, "lr": 9.79815318674481e-05, "epoch": 0.9081289081289081, "percentage": 18.18, "elapsed_time": "2:01:55", "remaining_time": "9:08:40"}
{"current_steps": 600, "total_steps": 3245, "loss": 0.0479, "lr": 9.782745391264498e-05, "epoch": 0.9235209235209235, "percentage": 18.49, "elapsed_time": "2:03:22", "remaining_time": "9:03:53"}
{"current_steps": 600, "total_steps": 3245, "eval_loss": 0.03358432278037071, "epoch": 0.9235209235209235, "percentage": 18.49, "elapsed_time": "2:06:38", "remaining_time": "9:18:16"}
{"current_steps": 610, "total_steps": 3245, "loss": 0.0414, "lr": 9.76678398171927e-05, "epoch": 0.9389129389129389, "percentage": 18.8, "elapsed_time": "2:08:07", "remaining_time": "9:13:29"}
{"current_steps": 620, "total_steps": 3245, "loss": 0.0283, "lr": 9.750270805679945e-05, "epoch": 0.9543049543049543, "percentage": 19.11, "elapsed_time": "2:09:34", "remaining_time": "9:08:34"}
{"current_steps": 630, "total_steps": 3245, "loss": 0.0494, "lr": 9.733207774585618e-05, "epoch": 0.9696969696969697, "percentage": 19.41, "elapsed_time": "2:11:00", "remaining_time": "9:03:47"}
{"current_steps": 640, "total_steps": 3245, "loss": 0.0339, "lr": 9.715596863522398e-05, "epoch": 0.9850889850889851, "percentage": 19.72, "elapsed_time": "2:12:26", "remaining_time": "8:59:04"}
{"current_steps": 650, "total_steps": 3245, "loss": 0.0464, "lr": 9.697440110994801e-05, "epoch": 1.0004810004810005, "percentage": 20.03, "elapsed_time": "2:13:52", "remaining_time": "8:54:29"}
{"current_steps": 650, "total_steps": 3245, "eval_loss": 0.03368612006306648, "epoch": 1.0004810004810005, "percentage": 20.03, "elapsed_time": "2:17:08", "remaining_time": "9:07:30"}
{"current_steps": 660, "total_steps": 3245, "loss": 0.0321, "lr": 9.678739618689775e-05, "epoch": 1.0158730158730158, "percentage": 20.34, "elapsed_time": "2:18:37", "remaining_time": "9:02:58"}
{"current_steps": 670, "total_steps": 3245, "loss": 0.0293, "lr": 9.659497551233431e-05, "epoch": 1.0312650312650313, "percentage": 20.65, "elapsed_time": "2:20:04", "remaining_time": "8:58:19"}
{"current_steps": 680, "total_steps": 3245, "loss": 0.028, "lr": 9.639716135940485e-05, "epoch": 1.0466570466570466, "percentage": 20.96, "elapsed_time": "2:21:30", "remaining_time": "8:53:46"}
{"current_steps": 690, "total_steps": 3245, "loss": 0.0309, "lr": 9.619397662556435e-05, "epoch": 1.0620490620490621, "percentage": 21.26, "elapsed_time": "2:22:56", "remaining_time": "8:49:17"}
{"current_steps": 700, "total_steps": 3245, "loss": 0.0291, "lr": 9.598544482992517e-05, "epoch": 1.0774410774410774, "percentage": 21.57, "elapsed_time": "2:24:23", "remaining_time": "8:44:56"}
{"current_steps": 700, "total_steps": 3245, "eval_loss": 0.0350741408765316, "epoch": 1.0774410774410774, "percentage": 21.57, "elapsed_time": "2:27:38", "remaining_time": "8:56:47"}
{"current_steps": 710, "total_steps": 3245, "loss": 0.0317, "lr": 9.57715901105348e-05, "epoch": 1.092833092833093, "percentage": 21.88, "elapsed_time": "2:29:07", "remaining_time": "8:52:27"}
{"current_steps": 720, "total_steps": 3245, "loss": 0.0328, "lr": 9.555243722158158e-05, "epoch": 1.1082251082251082, "percentage": 22.19, "elapsed_time": "2:30:33", "remaining_time": "8:48:00"}
{"current_steps": 730, "total_steps": 3245, "loss": 0.038, "lr": 9.532801153052958e-05, "epoch": 1.1236171236171235, "percentage": 22.5, "elapsed_time": "2:31:59", "remaining_time": "8:43:39"}
{"current_steps": 740, "total_steps": 3245, "loss": 0.0345, "lr": 9.509833901518209e-05, "epoch": 1.139009139009139, "percentage": 22.8, "elapsed_time": "2:33:26", "remaining_time": "8:39:23"}
{"current_steps": 750, "total_steps": 3245, "loss": 0.0266, "lr": 9.486344626067475e-05, "epoch": 1.1544011544011543, "percentage": 23.11, "elapsed_time": "2:34:52", "remaining_time": "8:35:11"}
{"current_steps": 750, "total_steps": 3245, "eval_loss": 0.033587317913770676, "epoch": 1.1544011544011543, "percentage": 23.11, "elapsed_time": "2:38:07", "remaining_time": "8:46:01"}
{"current_steps": 760, "total_steps": 3245, "loss": 0.0333, "lr": 9.462336045639815e-05, "epoch": 1.1697931697931698, "percentage": 23.42, "elapsed_time": "2:39:36", "remaining_time": "8:41:52"}
{"current_steps": 770, "total_steps": 3245, "loss": 0.0222, "lr": 9.437810939285068e-05, "epoch": 1.1851851851851851, "percentage": 23.73, "elapsed_time": "2:41:02", "remaining_time": "8:37:37"}
{"current_steps": 780, "total_steps": 3245, "loss": 0.0255, "lr": 9.412772145842165e-05, "epoch": 1.2005772005772006, "percentage": 24.04, "elapsed_time": "2:42:28", "remaining_time": "8:33:27"}
{"current_steps": 790, "total_steps": 3245, "loss": 0.0319, "lr": 9.387222563610535e-05, "epoch": 1.215969215969216, "percentage": 24.35, "elapsed_time": "2:43:54", "remaining_time": "8:29:22"}
{"current_steps": 800, "total_steps": 3245, "loss": 0.0268, "lr": 9.361165150014606e-05, "epoch": 1.2313612313612314, "percentage": 24.65, "elapsed_time": "2:45:21", "remaining_time": "8:25:22"}
{"current_steps": 800, "total_steps": 3245, "eval_loss": 0.03231462836265564, "epoch": 1.2313612313612314, "percentage": 24.65, "elapsed_time": "2:48:36", "remaining_time": "8:35:18"}
{"current_steps": 810, "total_steps": 3245, "loss": 0.0383, "lr": 9.334602921261492e-05, "epoch": 1.2467532467532467, "percentage": 24.96, "elapsed_time": "2:50:05", "remaining_time": "8:31:20"}
{"current_steps": 820, "total_steps": 3245, "loss": 0.0323, "lr": 9.307538951991852e-05, "epoch": 1.2621452621452622, "percentage": 25.27, "elapsed_time": "2:51:31", "remaining_time": "8:27:16"}
{"current_steps": 830, "total_steps": 3245, "loss": 0.0307, "lr": 9.279976374923988e-05, "epoch": 1.2775372775372775, "percentage": 25.58, "elapsed_time": "2:52:58", "remaining_time": "8:23:16"}
{"current_steps": 840, "total_steps": 3245, "loss": 0.0239, "lr": 9.251918380491238e-05, "epoch": 1.2929292929292928, "percentage": 25.89, "elapsed_time": "2:54:24", "remaining_time": "8:19:20"}
{"current_steps": 850, "total_steps": 3245, "loss": 0.0257, "lr": 9.223368216472668e-05, "epoch": 1.3083213083213083, "percentage": 26.19, "elapsed_time": "2:55:50", "remaining_time": "8:15:28"}
{"current_steps": 850, "total_steps": 3245, "eval_loss": 0.03252238407731056, "epoch": 1.3083213083213083, "percentage": 26.19, "elapsed_time": "2:59:05", "remaining_time": "8:24:36"}
{"current_steps": 860, "total_steps": 3245, "loss": 0.0215, "lr": 9.194329187617127e-05, "epoch": 1.3237133237133238, "percentage": 26.5, "elapsed_time": "3:00:34", "remaining_time": "8:20:47"}
{"current_steps": 870, "total_steps": 3245, "loss": 0.0348, "lr": 9.164804655260735e-05, "epoch": 1.3391053391053391, "percentage": 26.81, "elapsed_time": "3:02:00", "remaining_time": "8:16:52"}
{"current_steps": 880, "total_steps": 3245, "loss": 0.03, "lr": 9.134798036937778e-05, "epoch": 1.3544973544973544, "percentage": 27.12, "elapsed_time": "3:03:27", "remaining_time": "8:13:01"}
{"current_steps": 890, "total_steps": 3245, "loss": 0.0289, "lr": 9.104312805985134e-05, "epoch": 1.36988936988937, "percentage": 27.43, "elapsed_time": "3:04:53", "remaining_time": "8:09:13"}
{"current_steps": 900, "total_steps": 3245, "loss": 0.0311, "lr": 9.073352491140221e-05, "epoch": 1.3852813852813852, "percentage": 27.73, "elapsed_time": "3:06:18", "remaining_time": "8:05:27"}
{"current_steps": 900, "total_steps": 3245, "eval_loss": 0.03226852789521217, "epoch": 1.3852813852813852, "percentage": 27.73, "elapsed_time": "3:09:33", "remaining_time": "8:13:54"}
{"current_steps": 910, "total_steps": 3245, "loss": 0.0384, "lr": 9.041920676132543e-05, "epoch": 1.4006734006734007, "percentage": 28.04, "elapsed_time": "3:11:03", "remaining_time": "8:10:13"}
{"current_steps": 920, "total_steps": 3245, "loss": 0.0322, "lr": 9.010020999268854e-05, "epoch": 1.416065416065416, "percentage": 28.35, "elapsed_time": "3:12:29", "remaining_time": "8:06:27"}
{"current_steps": 930, "total_steps": 3245, "loss": 0.0288, "lr": 8.977657153012027e-05, "epoch": 1.4314574314574315, "percentage": 28.66, "elapsed_time": "3:13:55", "remaining_time": "8:02:43"}
{"current_steps": 940, "total_steps": 3245, "loss": 0.036, "lr": 8.944832883553633e-05, "epoch": 1.4468494468494468, "percentage": 28.97, "elapsed_time": "3:15:21", "remaining_time": "7:59:03"}
{"current_steps": 950, "total_steps": 3245, "loss": 0.0345, "lr": 8.91155199038032e-05, "epoch": 1.4622414622414621, "percentage": 29.28, "elapsed_time": "3:16:47", "remaining_time": "7:55:24"}
{"current_steps": 950, "total_steps": 3245, "eval_loss": 0.03173607587814331, "epoch": 1.4622414622414621, "percentage": 29.28, "elapsed_time": "3:20:02", "remaining_time": "8:03:14"}
{"current_steps": 960, "total_steps": 3245, "loss": 0.0295, "lr": 8.877818325834006e-05, "epoch": 1.4776334776334776, "percentage": 29.58, "elapsed_time": "3:21:31", "remaining_time": "7:59:39"}
{"current_steps": 970, "total_steps": 3245, "loss": 0.038, "lr": 8.843635794665961e-05, "epoch": 1.4930254930254931, "percentage": 29.89, "elapsed_time": "3:22:57", "remaining_time": "7:56:01"}
{"current_steps": 980, "total_steps": 3245, "loss": 0.0352, "lr": 8.809008353584829e-05, "epoch": 1.5084175084175084, "percentage": 30.2, "elapsed_time": "3:24:23", "remaining_time": "7:52:24"}
{"current_steps": 990, "total_steps": 3245, "loss": 0.0236, "lr": 8.773940010798627e-05, "epoch": 1.5238095238095237, "percentage": 30.51, "elapsed_time": "3:25:49", "remaining_time": "7:48:49"}
{"current_steps": 1000, "total_steps": 3245, "loss": 0.0287, "lr": 8.738434825550785e-05, "epoch": 1.5392015392015392, "percentage": 30.82, "elapsed_time": "3:27:15", "remaining_time": "7:45:16"}
{"current_steps": 1000, "total_steps": 3245, "eval_loss": 0.03453391045331955, "epoch": 1.5392015392015392, "percentage": 30.82, "elapsed_time": "3:30:29", "remaining_time": "7:52:34"}
{"current_steps": 1010, "total_steps": 3245, "loss": 0.0312, "lr": 8.702496907650274e-05, "epoch": 1.5545935545935547, "percentage": 31.12, "elapsed_time": "3:31:59", "remaining_time": "7:49:05"}
{"current_steps": 1020, "total_steps": 3245, "loss": 0.0232, "lr": 8.666130416995897e-05, "epoch": 1.56998556998557, "percentage": 31.43, "elapsed_time": "3:33:24", "remaining_time": "7:45:32"}
{"current_steps": 1030, "total_steps": 3245, "loss": 0.0228, "lr": 8.629339563094758e-05, "epoch": 1.5853775853775853, "percentage": 31.74, "elapsed_time": "3:34:50", "remaining_time": "7:42:00"}
{"current_steps": 1040, "total_steps": 3245, "loss": 0.0338, "lr": 8.592128604575014e-05, "epoch": 1.6007696007696008, "percentage": 32.05, "elapsed_time": "3:36:16", "remaining_time": "7:38:31"}
{"current_steps": 1050, "total_steps": 3245, "loss": 0.0333, "lr": 8.554501848692921e-05, "epoch": 1.6161616161616161, "percentage": 32.36, "elapsed_time": "3:37:39", "remaining_time": "7:35:01"}
{"current_steps": 1050, "total_steps": 3245, "eval_loss": 0.03127632290124893, "epoch": 1.6161616161616161, "percentage": 32.36, "elapsed_time": "3:40:55", "remaining_time": "7:41:51"}
{"current_steps": 1060, "total_steps": 3245, "loss": 0.0344, "lr": 8.51646365083426e-05, "epoch": 1.6315536315536314, "percentage": 32.67, "elapsed_time": "3:42:26", "remaining_time": "7:38:31"}
{"current_steps": 1070, "total_steps": 3245, "loss": 0.039, "lr": 8.478018414010191e-05, "epoch": 1.646945646945647, "percentage": 32.97, "elapsed_time": "3:43:53", "remaining_time": "7:35:06"}
{"current_steps": 1080, "total_steps": 3245, "loss": 0.0311, "lr": 8.439170588347598e-05, "epoch": 1.6623376623376624, "percentage": 33.28, "elapsed_time": "3:45:18", "remaining_time": "7:31:39"}
{"current_steps": 1090, "total_steps": 3245, "loss": 0.0208, "lr": 8.399924670573969e-05, "epoch": 1.6777296777296777, "percentage": 33.59, "elapsed_time": "3:46:45", "remaining_time": "7:28:18"}
{"current_steps": 1100, "total_steps": 3245, "loss": 0.0278, "lr": 8.360285203496894e-05, "epoch": 1.693121693121693, "percentage": 33.9, "elapsed_time": "3:48:13", "remaining_time": "7:25:01"}
{"current_steps": 1100, "total_steps": 3245, "eval_loss": 0.03136962652206421, "epoch": 1.693121693121693, "percentage": 33.9, "elapsed_time": "3:51:32", "remaining_time": "7:31:30"}
{"current_steps": 1110, "total_steps": 3245, "loss": 0.0368, "lr": 8.320256775478228e-05, "epoch": 1.7085137085137085, "percentage": 34.21, "elapsed_time": "3:53:00", "remaining_time": "7:28:09"}
{"current_steps": 1120, "total_steps": 3245, "loss": 0.0223, "lr": 8.279844019902968e-05, "epoch": 1.723905723905724, "percentage": 34.51, "elapsed_time": "3:54:26", "remaining_time": "7:24:49"}
{"current_steps": 1130, "total_steps": 3245, "loss": 0.0227, "lr": 8.239051614642934e-05, "epoch": 1.7392977392977393, "percentage": 34.82, "elapsed_time": "3:55:54", "remaining_time": "7:21:32"}
{"current_steps": 1140, "total_steps": 3245, "loss": 0.0297, "lr": 8.197884281515292e-05, "epoch": 1.7546897546897546, "percentage": 35.13, "elapsed_time": "3:57:23", "remaining_time": "7:18:19"}
{"current_steps": 1150, "total_steps": 3245, "loss": 0.0239, "lr": 8.156346785735997e-05, "epoch": 1.7700817700817701, "percentage": 35.44, "elapsed_time": "3:58:49", "remaining_time": "7:15:05"}
{"current_steps": 1150, "total_steps": 3245, "eval_loss": 0.030629225075244904, "epoch": 1.7700817700817701, "percentage": 35.44, "elapsed_time": "4:02:07", "remaining_time": "7:21:05"}
{"current_steps": 1160, "total_steps": 3245, "loss": 0.0294, "lr": 8.114443935368198e-05, "epoch": 1.7854737854737854, "percentage": 35.75, "elapsed_time": "4:03:38", "remaining_time": "7:17:56"}
{"current_steps": 1170, "total_steps": 3245, "loss": 0.0263, "lr": 8.072180580765709e-05, "epoch": 1.8008658008658007, "percentage": 36.06, "elapsed_time": "4:05:06", "remaining_time": "7:14:42"}
{"current_steps": 1180, "total_steps": 3245, "loss": 0.0292, "lr": 8.02956161401155e-05, "epoch": 1.8162578162578162, "percentage": 36.36, "elapsed_time": "4:06:33", "remaining_time": "7:11:27"}
{"current_steps": 1190, "total_steps": 3245, "loss": 0.03, "lr": 7.98659196835169e-05, "epoch": 1.8316498316498318, "percentage": 36.67, "elapsed_time": "4:08:00", "remaining_time": "7:08:17"}
{"current_steps": 1200, "total_steps": 3245, "loss": 0.0346, "lr": 7.943276617624014e-05, "epoch": 1.847041847041847, "percentage": 36.98, "elapsed_time": "4:09:29", "remaining_time": "7:05:09"}
{"current_steps": 1200, "total_steps": 3245, "eval_loss": 0.031223421916365623, "epoch": 1.847041847041847, "percentage": 36.98, "elapsed_time": "4:12:45", "remaining_time": "7:10:44"}
{"current_steps": 1210, "total_steps": 3245, "loss": 0.0241, "lr": 7.899620575682578e-05, "epoch": 1.8624338624338623, "percentage": 37.29, "elapsed_time": "4:14:09", "remaining_time": "7:07:26"}
{"current_steps": 1220, "total_steps": 3245, "loss": 0.0288, "lr": 7.85562889581725e-05, "epoch": 1.8778258778258778, "percentage": 37.6, "elapsed_time": "4:15:28", "remaining_time": "7:04:03"}
{"current_steps": 1230, "total_steps": 3245, "loss": 0.0253, "lr": 7.811306670168788e-05, "epoch": 1.8932178932178934, "percentage": 37.9, "elapsed_time": "4:16:47", "remaining_time": "7:00:41"}
{"current_steps": 1240, "total_steps": 3245, "loss": 0.0317, "lr": 7.766659029139393e-05, "epoch": 1.9086099086099086, "percentage": 38.21, "elapsed_time": "4:18:06", "remaining_time": "6:57:20"}
{"current_steps": 1250, "total_steps": 3245, "loss": 0.0289, "lr": 7.72169114079887e-05, "epoch": 1.924001924001924, "percentage": 38.52, "elapsed_time": "4:19:25", "remaining_time": "6:54:02"}
{"current_steps": 1250, "total_steps": 3245, "eval_loss": 0.030128151178359985, "epoch": 1.924001924001924, "percentage": 38.52, "elapsed_time": "4:22:22", "remaining_time": "6:58:45"}
{"current_steps": 1260, "total_steps": 3245, "loss": 0.0265, "lr": 7.676408210286407e-05, "epoch": 1.9393939393939394, "percentage": 38.83, "elapsed_time": "4:23:45", "remaining_time": "6:55:31"}
{"current_steps": 1270, "total_steps": 3245, "loss": 0.0236, "lr": 7.630815479208066e-05, "epoch": 1.9547859547859547, "percentage": 39.14, "elapsed_time": "4:25:04", "remaining_time": "6:52:12"}
{"current_steps": 1280, "total_steps": 3245, "loss": 0.0224, "lr": 7.584918225030053e-05, "epoch": 1.97017797017797, "percentage": 39.45, "elapsed_time": "4:26:22", "remaining_time": "6:48:55"}
{"current_steps": 1290, "total_steps": 3245, "loss": 0.0348, "lr": 7.538721760467845e-05, "epoch": 1.9855699855699855, "percentage": 39.75, "elapsed_time": "4:27:41", "remaining_time": "6:45:40"}
{"current_steps": 1300, "total_steps": 3245, "loss": 0.0308, "lr": 7.49223143287122e-05, "epoch": 2.000962000962001, "percentage": 40.06, "elapsed_time": "4:29:00", "remaining_time": "6:42:28"}
{"current_steps": 1300, "total_steps": 3245, "eval_loss": 0.03185825049877167, "epoch": 2.000962000962001, "percentage": 40.06, "elapsed_time": "4:31:57", "remaining_time": "6:46:53"}
{"current_steps": 1310, "total_steps": 3245, "loss": 0.025, "lr": 7.445452623605307e-05, "epoch": 2.0163540163540166, "percentage": 40.37, "elapsed_time": "4:33:19", "remaining_time": "6:43:44"}
{"current_steps": 1320, "total_steps": 3245, "loss": 0.0192, "lr": 7.398390747427662e-05, "epoch": 2.0317460317460316, "percentage": 40.68, "elapsed_time": "4:34:38", "remaining_time": "6:40:31"}
{"current_steps": 1330, "total_steps": 3245, "loss": 0.0199, "lr": 7.351051251861501e-05, "epoch": 2.047138047138047, "percentage": 40.99, "elapsed_time": "4:35:57", "remaining_time": "6:37:20"}
{"current_steps": 1340, "total_steps": 3245, "loss": 0.0159, "lr": 7.303439616565146e-05, "epoch": 2.0625300625300627, "percentage": 41.29, "elapsed_time": "4:37:16", "remaining_time": "6:34:10"}
{"current_steps": 1350, "total_steps": 3245, "loss": 0.0176, "lr": 7.255561352697732e-05, "epoch": 2.0779220779220777, "percentage": 41.6, "elapsed_time": "4:38:34", "remaining_time": "6:31:02"}
{"current_steps": 1350, "total_steps": 3245, "eval_loss": 0.03141428157687187, "epoch": 2.0779220779220777, "percentage": 41.6, "elapsed_time": "4:41:32", "remaining_time": "6:35:11"}
{"current_steps": 1360, "total_steps": 3245, "loss": 0.0146, "lr": 7.207422002281281e-05, "epoch": 2.0933140933140932, "percentage": 41.91, "elapsed_time": "4:42:54", "remaining_time": "6:32:07"}
{"current_steps": 1370, "total_steps": 3245, "loss": 0.0174, "lr": 7.159027137559197e-05, "epoch": 2.1087061087061088, "percentage": 42.22, "elapsed_time": "4:44:13", "remaining_time": "6:28:59"}
{"current_steps": 1380, "total_steps": 3245, "loss": 0.019, "lr": 7.110382360351267e-05, "epoch": 2.1240981240981243, "percentage": 42.53, "elapsed_time": "4:45:32", "remaining_time": "6:25:53"}
{"current_steps": 1390, "total_steps": 3245, "loss": 0.0144, "lr": 7.061493301405244e-05, "epoch": 2.1394901394901393, "percentage": 42.84, "elapsed_time": "4:46:50", "remaining_time": "6:22:48"}
{"current_steps": 1400, "total_steps": 3245, "loss": 0.0192, "lr": 7.012365619745064e-05, "epoch": 2.154882154882155, "percentage": 43.14, "elapsed_time": "4:48:09", "remaining_time": "6:19:45"}
{"current_steps": 1400, "total_steps": 3245, "eval_loss": 0.03115396946668625, "epoch": 2.154882154882155, "percentage": 43.14, "elapsed_time": "4:51:07", "remaining_time": "6:23:39"}
{"current_steps": 1410, "total_steps": 3245, "loss": 0.0212, "lr": 6.963005002015808e-05, "epoch": 2.1702741702741704, "percentage": 43.45, "elapsed_time": "4:52:30", "remaining_time": "6:20:40"}
{"current_steps": 1420, "total_steps": 3245, "loss": 0.0153, "lr": 6.91341716182545e-05, "epoch": 2.185666185666186, "percentage": 43.76, "elapsed_time": "4:53:49", "remaining_time": "6:17:37"}
{"current_steps": 1430, "total_steps": 3245, "loss": 0.0241, "lr": 6.863607839083507e-05, "epoch": 2.201058201058201, "percentage": 44.07, "elapsed_time": "4:55:08", "remaining_time": "6:14:35"}
{"current_steps": 1440, "total_steps": 3245, "loss": 0.0163, "lr": 6.813582799336624e-05, "epoch": 2.2164502164502164, "percentage": 44.38, "elapsed_time": "4:56:26", "remaining_time": "6:11:35"}
{"current_steps": 1450, "total_steps": 3245, "loss": 0.0157, "lr": 6.763347833101192e-05, "epoch": 2.231842231842232, "percentage": 44.68, "elapsed_time": "4:57:45", "remaining_time": "6:08:36"}
{"current_steps": 1450, "total_steps": 3245, "eval_loss": 0.031504761427640915, "epoch": 2.231842231842232, "percentage": 44.68, "elapsed_time": "5:00:43", "remaining_time": "6:12:16"}
{"current_steps": 1460, "total_steps": 3245, "loss": 0.0213, "lr": 6.712908755193094e-05, "epoch": 2.247234247234247, "percentage": 44.99, "elapsed_time": "5:02:05", "remaining_time": "6:09:20"}
{"current_steps": 1470, "total_steps": 3245, "loss": 0.0171, "lr": 6.662271404054621e-05, "epoch": 2.2626262626262625, "percentage": 45.3, "elapsed_time": "5:03:24", "remaining_time": "6:06:21"}
{"current_steps": 1480, "total_steps": 3245, "loss": 0.0177, "lr": 6.611441641078657e-05, "epoch": 2.278018278018278, "percentage": 45.61, "elapsed_time": "5:04:43", "remaining_time": "6:03:24"}
{"current_steps": 1490, "total_steps": 3245, "loss": 0.0211, "lr": 6.560425349930208e-05, "epoch": 2.2934102934102936, "percentage": 45.92, "elapsed_time": "5:06:02", "remaining_time": "6:00:27"}
{"current_steps": 1500, "total_steps": 3245, "loss": 0.0227, "lr": 6.509228435865357e-05, "epoch": 2.3088023088023086, "percentage": 46.22, "elapsed_time": "5:07:21", "remaining_time": "5:57:33"}
{"current_steps": 1500, "total_steps": 3245, "eval_loss": 0.030094966292381287, "epoch": 2.3088023088023086, "percentage": 46.22, "elapsed_time": "5:10:18", "remaining_time": "6:00:59"}
{"current_steps": 1510, "total_steps": 3245, "loss": 0.0237, "lr": 6.45785682504772e-05, "epoch": 2.324194324194324, "percentage": 46.53, "elapsed_time": "5:11:41", "remaining_time": "5:58:07"}
{"current_steps": 1520, "total_steps": 3245, "loss": 0.0156, "lr": 6.406316463862467e-05, "epoch": 2.3395863395863397, "percentage": 46.84, "elapsed_time": "5:13:00", "remaining_time": "5:55:13"}
{"current_steps": 1530, "total_steps": 3245, "loss": 0.0224, "lr": 6.35461331822803e-05, "epoch": 2.354978354978355, "percentage": 47.15, "elapsed_time": "5:14:19", "remaining_time": "5:52:19"}
{"current_steps": 1540, "total_steps": 3245, "loss": 0.0272, "lr": 6.302753372905515e-05, "epoch": 2.3703703703703702, "percentage": 47.46, "elapsed_time": "5:15:38", "remaining_time": "5:49:27"}
{"current_steps": 1550, "total_steps": 3245, "loss": 0.0211, "lr": 6.250742630805971e-05, "epoch": 2.3857623857623858, "percentage": 47.77, "elapsed_time": "5:16:57", "remaining_time": "5:46:36"}
{"current_steps": 1550, "total_steps": 3245, "eval_loss": 0.030527736991643906, "epoch": 2.3857623857623858, "percentage": 47.77, "elapsed_time": "5:19:55", "remaining_time": "5:49:51"}
{"current_steps": 1560, "total_steps": 3245, "loss": 0.0226, "lr": 6.198587112295526e-05, "epoch": 2.4011544011544013, "percentage": 48.07, "elapsed_time": "5:21:18", "remaining_time": "5:47:03"}
{"current_steps": 1570, "total_steps": 3245, "loss": 0.0184, "lr": 6.14629285449852e-05, "epoch": 2.4165464165464163, "percentage": 48.38, "elapsed_time": "5:22:38", "remaining_time": "5:44:12"}
{"current_steps": 1580, "total_steps": 3245, "loss": 0.0164, "lr": 6.093865910598688e-05, "epoch": 2.431938431938432, "percentage": 48.69, "elapsed_time": "5:23:56", "remaining_time": "5:41:22"}
{"current_steps": 1590, "total_steps": 3245, "loss": 0.017, "lr": 6.0413123491385025e-05, "epoch": 2.4473304473304474, "percentage": 49.0, "elapsed_time": "5:25:15", "remaining_time": "5:38:33"}
{"current_steps": 1600, "total_steps": 3245, "loss": 0.0192, "lr": 5.988638253316713e-05, "epoch": 2.462722462722463, "percentage": 49.31, "elapsed_time": "5:26:34", "remaining_time": "5:35:45"}
{"current_steps": 1600, "total_steps": 3245, "eval_loss": 0.03266085684299469, "epoch": 2.462722462722463, "percentage": 49.31, "elapsed_time": "5:29:32", "remaining_time": "5:38:48"}
{"current_steps": 1610, "total_steps": 3245, "loss": 0.0165, "lr": 5.935849720284206e-05, "epoch": 2.478114478114478, "percentage": 49.61, "elapsed_time": "5:30:54", "remaining_time": "5:36:02"}
{"current_steps": 1620, "total_steps": 3245, "loss": 0.0229, "lr": 5.8829528604382436e-05, "epoch": 2.4935064935064934, "percentage": 49.92, "elapsed_time": "5:32:13", "remaining_time": "5:33:14"}
{"current_steps": 1630, "total_steps": 3245, "loss": 0.0246, "lr": 5.829953796715176e-05, "epoch": 2.508898508898509, "percentage": 50.23, "elapsed_time": "5:33:31", "remaining_time": "5:30:27"}
{"current_steps": 1640, "total_steps": 3245, "loss": 0.0227, "lr": 5.7768586638816924e-05, "epoch": 2.5242905242905245, "percentage": 50.54, "elapsed_time": "5:34:50", "remaining_time": "5:27:41"}
{"current_steps": 1650, "total_steps": 3245, "loss": 0.0215, "lr": 5.723673607824705e-05, "epoch": 2.5396825396825395, "percentage": 50.85, "elapsed_time": "5:36:09", "remaining_time": "5:24:56"}
{"current_steps": 1650, "total_steps": 3245, "eval_loss": 0.031051570549607277, "epoch": 2.5396825396825395, "percentage": 50.85, "elapsed_time": "5:39:06", "remaining_time": "5:27:48"}
{"current_steps": 1660, "total_steps": 3245, "loss": 0.0289, "lr": 5.670404784839953e-05, "epoch": 2.555074555074555, "percentage": 51.16, "elapsed_time": "5:40:29", "remaining_time": "5:25:06"}
{"current_steps": 1670, "total_steps": 3245, "loss": 0.0243, "lr": 5.6170583609193984e-05, "epoch": 2.5704665704665706, "percentage": 51.46, "elapsed_time": "5:41:48", "remaining_time": "5:22:21"}
{"current_steps": 1680, "total_steps": 3245, "loss": 0.0215, "lr": 5.56364051103749e-05, "epoch": 2.5858585858585856, "percentage": 51.77, "elapsed_time": "5:43:07", "remaining_time": "5:19:38"}
{"current_steps": 1690, "total_steps": 3245, "loss": 0.0175, "lr": 5.5101574184364056e-05, "epoch": 2.601250601250601, "percentage": 52.08, "elapsed_time": "5:44:26", "remaining_time": "5:16:55"}
{"current_steps": 1700, "total_steps": 3245, "loss": 0.0235, "lr": 5.4566152739103116e-05, "epoch": 2.6166426166426167, "percentage": 52.39, "elapsed_time": "5:45:45", "remaining_time": "5:14:13"}
{"current_steps": 1700, "total_steps": 3245, "eval_loss": 0.029672790318727493, "epoch": 2.6166426166426167, "percentage": 52.39, "elapsed_time": "5:48:43", "remaining_time": "5:16:55"}
{"current_steps": 1710, "total_steps": 3245, "loss": 0.0175, "lr": 5.403020275088786e-05, "epoch": 2.632034632034632, "percentage": 52.7, "elapsed_time": "5:50:05", "remaining_time": "5:14:15"}
{"current_steps": 1720, "total_steps": 3245, "loss": 0.0215, "lr": 5.349378625719408e-05, "epoch": 2.6474266474266477, "percentage": 53.0, "elapsed_time": "5:51:24", "remaining_time": "5:11:33"}
{"current_steps": 1730, "total_steps": 3245, "loss": 0.0198, "lr": 5.2956965349496743e-05, "epoch": 2.6628186628186628, "percentage": 53.31, "elapsed_time": "5:52:42", "remaining_time": "5:08:52"}
{"current_steps": 1740, "total_steps": 3245, "loss": 0.0173, "lr": 5.241980216608261e-05, "epoch": 2.6782106782106783, "percentage": 53.62, "elapsed_time": "5:54:02", "remaining_time": "5:06:13"}
{"current_steps": 1750, "total_steps": 3245, "loss": 0.0149, "lr": 5.188235888485773e-05, "epoch": 2.6936026936026938, "percentage": 53.93, "elapsed_time": "5:55:21", "remaining_time": "5:03:34"}
{"current_steps": 1750, "total_steps": 3245, "eval_loss": 0.031217539682984352, "epoch": 2.6936026936026938, "percentage": 53.93, "elapsed_time": "5:58:19", "remaining_time": "5:06:06"}
{"current_steps": 1760, "total_steps": 3245, "loss": 0.0163, "lr": 5.13446977161501e-05, "epoch": 2.708994708994709, "percentage": 54.24, "elapsed_time": "5:59:42", "remaining_time": "5:03:29"}
{"current_steps": 1770, "total_steps": 3245, "loss": 0.0211, "lr": 5.0806880895508766e-05, "epoch": 2.7243867243867244, "percentage": 54.55, "elapsed_time": "6:01:01", "remaining_time": "5:00:50"}
{"current_steps": 1780, "total_steps": 3245, "loss": 0.0232, "lr": 5.026897067649976e-05, "epoch": 2.73977873977874, "percentage": 54.85, "elapsed_time": "6:02:19", "remaining_time": "4:58:12"}
{"current_steps": 1790, "total_steps": 3245, "loss": 0.0149, "lr": 4.973102932350026e-05, "epoch": 2.755170755170755, "percentage": 55.16, "elapsed_time": "6:03:38", "remaining_time": "4:55:35"}
{"current_steps": 1800, "total_steps": 3245, "loss": 0.0206, "lr": 4.9193119104491245e-05, "epoch": 2.7705627705627704, "percentage": 55.47, "elapsed_time": "6:04:57", "remaining_time": "4:52:59"}
{"current_steps": 1800, "total_steps": 3245, "eval_loss": 0.02991563268005848, "epoch": 2.7705627705627704, "percentage": 55.47, "elapsed_time": "6:07:56", "remaining_time": "4:55:22"}
{"current_steps": 1810, "total_steps": 3245, "loss": 0.0211, "lr": 4.86553022838499e-05, "epoch": 2.785954785954786, "percentage": 55.78, "elapsed_time": "6:09:19", "remaining_time": "4:52:48"}
{"current_steps": 1820, "total_steps": 3245, "loss": 0.0185, "lr": 4.8117641115142285e-05, "epoch": 2.8013468013468015, "percentage": 56.09, "elapsed_time": "6:10:38", "remaining_time": "4:50:12"}
{"current_steps": 1830, "total_steps": 3245, "loss": 0.0231, "lr": 4.758019783391741e-05, "epoch": 2.816738816738817, "percentage": 56.39, "elapsed_time": "6:11:57", "remaining_time": "4:47:36"}
{"current_steps": 1840, "total_steps": 3245, "loss": 0.0209, "lr": 4.704303465050327e-05, "epoch": 2.832130832130832, "percentage": 56.7, "elapsed_time": "6:13:17", "remaining_time": "4:45:02"}
{"current_steps": 1850, "total_steps": 3245, "loss": 0.0154, "lr": 4.6506213742805924e-05, "epoch": 2.8475228475228476, "percentage": 57.01, "elapsed_time": "6:14:35", "remaining_time": "4:42:28"}
{"current_steps": 1850, "total_steps": 3245, "eval_loss": 0.03181726485490799, "epoch": 2.8475228475228476, "percentage": 57.01, "elapsed_time": "6:17:34", "remaining_time": "4:44:42"}
{"current_steps": 1860, "total_steps": 3245, "loss": 0.0161, "lr": 4.5969797249112146e-05, "epoch": 2.862914862914863, "percentage": 57.32, "elapsed_time": "6:18:56", "remaining_time": "4:42:10"}
{"current_steps": 1870, "total_steps": 3245, "loss": 0.0216, "lr": 4.54338472608969e-05, "epoch": 2.878306878306878, "percentage": 57.63, "elapsed_time": "6:20:15", "remaining_time": "4:39:36"}
{"current_steps": 1880, "total_steps": 3245, "loss": 0.015, "lr": 4.489842581563597e-05, "epoch": 2.8936988936988937, "percentage": 57.94, "elapsed_time": "6:21:35", "remaining_time": "4:37:03"}
{"current_steps": 1890, "total_steps": 3245, "loss": 0.0143, "lr": 4.436359488962511e-05, "epoch": 2.909090909090909, "percentage": 58.24, "elapsed_time": "6:22:54", "remaining_time": "4:34:30"}
{"current_steps": 1900, "total_steps": 3245, "loss": 0.0188, "lr": 4.382941639080602e-05, "epoch": 2.9244829244829242, "percentage": 58.55, "elapsed_time": "6:24:13", "remaining_time": "4:31:59"}
{"current_steps": 1900, "total_steps": 3245, "eval_loss": 0.03009277582168579, "epoch": 2.9244829244829242, "percentage": 58.55, "elapsed_time": "6:27:11", "remaining_time": "4:34:05"}
{"current_steps": 1910, "total_steps": 3245, "loss": 0.0166, "lr": 4.3295952151600475e-05, "epoch": 2.9398749398749398, "percentage": 58.86, "elapsed_time": "6:28:33", "remaining_time": "4:31:35"}
{"current_steps": 1920, "total_steps": 3245, "loss": 0.0178, "lr": 4.276326392175296e-05, "epoch": 2.9552669552669553, "percentage": 59.17, "elapsed_time": "6:29:53", "remaining_time": "4:29:03"}
{"current_steps": 1930, "total_steps": 3245, "loss": 0.0227, "lr": 4.2231413361183095e-05, "epoch": 2.9706589706589708, "percentage": 59.48, "elapsed_time": "6:31:12", "remaining_time": "4:26:32"}
{"current_steps": 1940, "total_steps": 3245, "loss": 0.0212, "lr": 4.1700462032848244e-05, "epoch": 2.9860509860509863, "percentage": 59.78, "elapsed_time": "6:32:30", "remaining_time": "4:24:02"}
{"current_steps": 1950, "total_steps": 3245, "loss": 0.0198, "lr": 4.117047139561758e-05, "epoch": 3.0014430014430014, "percentage": 60.09, "elapsed_time": "6:33:49", "remaining_time": "4:21:32"}
{"current_steps": 1950, "total_steps": 3245, "eval_loss": 0.029989564791321754, "epoch": 3.0014430014430014, "percentage": 60.09, "elapsed_time": "6:36:47", "remaining_time": "4:23:30"}
{"current_steps": 1960, "total_steps": 3245, "loss": 0.0158, "lr": 4.0641502797157966e-05, "epoch": 3.016835016835017, "percentage": 60.4, "elapsed_time": "6:38:10", "remaining_time": "4:21:03"}
{"current_steps": 1970, "total_steps": 3245, "loss": 0.0102, "lr": 4.011361746683288e-05, "epoch": 3.0322270322270324, "percentage": 60.71, "elapsed_time": "6:39:30", "remaining_time": "4:18:33"}
{"current_steps": 1980, "total_steps": 3245, "loss": 0.0103, "lr": 3.958687650861499e-05, "epoch": 3.0476190476190474, "percentage": 61.02, "elapsed_time": "6:40:49", "remaining_time": "4:16:04"}
{"current_steps": 1990, "total_steps": 3245, "loss": 0.0111, "lr": 3.906134089401313e-05, "epoch": 3.063011063011063, "percentage": 61.33, "elapsed_time": "6:42:07", "remaining_time": "4:13:36"}
{"current_steps": 2000, "total_steps": 3245, "loss": 0.0117, "lr": 3.853707145501482e-05, "epoch": 3.0784030784030785, "percentage": 61.63, "elapsed_time": "6:43:26", "remaining_time": "4:11:08"}
{"current_steps": 2000, "total_steps": 3245, "eval_loss": 0.03222152963280678, "epoch": 3.0784030784030785, "percentage": 61.63, "elapsed_time": "6:46:25", "remaining_time": "4:12:59"}
{"current_steps": 2010, "total_steps": 3245, "loss": 0.0086, "lr": 3.801412887704475e-05, "epoch": 3.093795093795094, "percentage": 61.94, "elapsed_time": "6:47:47", "remaining_time": "4:10:33"}
{"current_steps": 2020, "total_steps": 3245, "loss": 0.0127, "lr": 3.749257369194029e-05, "epoch": 3.109187109187109, "percentage": 62.25, "elapsed_time": "6:49:06", "remaining_time": "4:08:06"}
{"current_steps": 2030, "total_steps": 3245, "loss": 0.0103, "lr": 3.697246627094487e-05, "epoch": 3.1245791245791246, "percentage": 62.56, "elapsed_time": "6:50:25", "remaining_time": "4:05:39"}
{"current_steps": 2040, "total_steps": 3245, "loss": 0.0097, "lr": 3.6453866817719726e-05, "epoch": 3.13997113997114, "percentage": 62.87, "elapsed_time": "6:51:44", "remaining_time": "4:03:12"}
{"current_steps": 2050, "total_steps": 3245, "loss": 0.0103, "lr": 3.593683536137533e-05, "epoch": 3.1553631553631556, "percentage": 63.17, "elapsed_time": "6:53:03", "remaining_time": "4:00:47"}
{"current_steps": 2050, "total_steps": 3245, "eval_loss": 0.03335327282547951, "epoch": 3.1553631553631556, "percentage": 63.17, "elapsed_time": "6:56:01", "remaining_time": "4:02:31"}
{"current_steps": 2060, "total_steps": 3245, "loss": 0.0095, "lr": 3.542143174952282e-05, "epoch": 3.1707551707551707, "percentage": 63.48, "elapsed_time": "6:57:25", "remaining_time": "4:00:07"}
{"current_steps": 2070, "total_steps": 3245, "loss": 0.0101, "lr": 3.490771564134643e-05, "epoch": 3.186147186147186, "percentage": 63.79, "elapsed_time": "6:58:44", "remaining_time": "3:57:41"}
{"current_steps": 2080, "total_steps": 3245, "loss": 0.0135, "lr": 3.4395746500697925e-05, "epoch": 3.2015392015392017, "percentage": 64.1, "elapsed_time": "7:00:03", "remaining_time": "3:55:16"}
{"current_steps": 2090, "total_steps": 3245, "loss": 0.0124, "lr": 3.388558358921343e-05, "epoch": 3.2169312169312168, "percentage": 64.41, "elapsed_time": "7:01:22", "remaining_time": "3:52:51"}
{"current_steps": 2100, "total_steps": 3245, "loss": 0.0158, "lr": 3.337728595945378e-05, "epoch": 3.2323232323232323, "percentage": 64.71, "elapsed_time": "7:02:41", "remaining_time": "3:50:27"}
{"current_steps": 2100, "total_steps": 3245, "eval_loss": 0.034329500049352646, "epoch": 3.2323232323232323, "percentage": 64.71, "elapsed_time": "7:05:39", "remaining_time": "3:52:05"}
{"current_steps": 2110, "total_steps": 3245, "loss": 0.0074, "lr": 3.287091244806907e-05, "epoch": 3.2477152477152478, "percentage": 65.02, "elapsed_time": "7:07:02", "remaining_time": "3:49:42"}
{"current_steps": 2120, "total_steps": 3245, "loss": 0.0177, "lr": 3.2366521668988106e-05, "epoch": 3.2631072631072633, "percentage": 65.33, "elapsed_time": "7:08:21", "remaining_time": "3:47:19"}
{"current_steps": 2130, "total_steps": 3245, "loss": 0.0126, "lr": 3.186417200663379e-05, "epoch": 3.2784992784992784, "percentage": 65.64, "elapsed_time": "7:09:41", "remaining_time": "3:44:55"}
{"current_steps": 2140, "total_steps": 3245, "loss": 0.0112, "lr": 3.136392160916495e-05, "epoch": 3.293891293891294, "percentage": 65.95, "elapsed_time": "7:10:59", "remaining_time": "3:42:32"}
{"current_steps": 2150, "total_steps": 3245, "loss": 0.0116, "lr": 3.086582838174551e-05, "epoch": 3.3092833092833094, "percentage": 66.26, "elapsed_time": "7:12:19", "remaining_time": "3:40:10"}
{"current_steps": 2150, "total_steps": 3245, "eval_loss": 0.03303411602973938, "epoch": 3.3092833092833094, "percentage": 66.26, "elapsed_time": "7:15:17", "remaining_time": "3:41:41"}
{"current_steps": 2160, "total_steps": 3245, "loss": 0.0097, "lr": 3.036994997984194e-05, "epoch": 3.324675324675325, "percentage": 66.56, "elapsed_time": "7:16:40", "remaining_time": "3:39:20"}
{"current_steps": 2170, "total_steps": 3245, "loss": 0.0077, "lr": 2.9876343802549357e-05, "epoch": 3.34006734006734, "percentage": 66.87, "elapsed_time": "7:17:59", "remaining_time": "3:36:58"}
{"current_steps": 2180, "total_steps": 3245, "loss": 0.0119, "lr": 2.938506698594755e-05, "epoch": 3.3554593554593555, "percentage": 67.18, "elapsed_time": "7:19:18", "remaining_time": "3:34:37"}
{"current_steps": 2190, "total_steps": 3245, "loss": 0.0101, "lr": 2.8896176396487334e-05, "epoch": 3.370851370851371, "percentage": 67.49, "elapsed_time": "7:20:38", "remaining_time": "3:32:16"}
{"current_steps": 2200, "total_steps": 3245, "loss": 0.0117, "lr": 2.8409728624408067e-05, "epoch": 3.386243386243386, "percentage": 67.8, "elapsed_time": "7:21:56", "remaining_time": "3:29:55"}
{"current_steps": 2200, "total_steps": 3245, "eval_loss": 0.034219466149806976, "epoch": 3.386243386243386, "percentage": 67.8, "elapsed_time": "7:24:55", "remaining_time": "3:31:20"}
{"current_steps": 2210, "total_steps": 3245, "loss": 0.0088, "lr": 2.7925779977187215e-05, "epoch": 3.4016354016354016, "percentage": 68.1, "elapsed_time": "7:26:19", "remaining_time": "3:29:01"}
{"current_steps": 2220, "total_steps": 3245, "loss": 0.0131, "lr": 2.7444386473022686e-05, "epoch": 3.417027417027417, "percentage": 68.41, "elapsed_time": "7:27:38", "remaining_time": "3:26:40"}
{"current_steps": 2230, "total_steps": 3245, "loss": 0.0104, "lr": 2.696560383434854e-05, "epoch": 3.4324194324194326, "percentage": 68.72, "elapsed_time": "7:28:57", "remaining_time": "3:24:20"}
{"current_steps": 2240, "total_steps": 3245, "loss": 0.0074, "lr": 2.6489487481384988e-05, "epoch": 3.4478114478114477, "percentage": 69.03, "elapsed_time": "7:30:16", "remaining_time": "3:22:01"}
{"current_steps": 2250, "total_steps": 3245, "loss": 0.01, "lr": 2.601609252572339e-05, "epoch": 3.463203463203463, "percentage": 69.34, "elapsed_time": "7:31:36", "remaining_time": "3:19:42"}
{"current_steps": 2250, "total_steps": 3245, "eval_loss": 0.03453659638762474, "epoch": 3.463203463203463, "percentage": 69.34, "elapsed_time": "7:34:34", "remaining_time": "3:21:01"}
{"current_steps": 2260, "total_steps": 3245, "loss": 0.0135, "lr": 2.554547376394692e-05, "epoch": 3.4785954785954787, "percentage": 69.65, "elapsed_time": "7:35:57", "remaining_time": "3:18:43"}
{"current_steps": 2270, "total_steps": 3245, "loss": 0.0104, "lr": 2.5077685671287808e-05, "epoch": 3.493987493987494, "percentage": 69.95, "elapsed_time": "7:37:16", "remaining_time": "3:16:24"}
{"current_steps": 2280, "total_steps": 3245, "loss": 0.0114, "lr": 2.4612782395321593e-05, "epoch": 3.5093795093795093, "percentage": 70.26, "elapsed_time": "7:38:35", "remaining_time": "3:14:05"}
{"current_steps": 2290, "total_steps": 3245, "loss": 0.0084, "lr": 2.4150817749699496e-05, "epoch": 3.5247715247715248, "percentage": 70.57, "elapsed_time": "7:39:54", "remaining_time": "3:11:47"}
{"current_steps": 2300, "total_steps": 3245, "loss": 0.0113, "lr": 2.3691845207919357e-05, "epoch": 3.5401635401635403, "percentage": 70.88, "elapsed_time": "7:41:12", "remaining_time": "3:09:29"}
{"current_steps": 2300, "total_steps": 3245, "eval_loss": 0.03454257547855377, "epoch": 3.5401635401635403, "percentage": 70.88, "elapsed_time": "7:44:11", "remaining_time": "3:10:43"}
{"current_steps": 2310, "total_steps": 3245, "loss": 0.0084, "lr": 2.3235917897135934e-05, "epoch": 3.5555555555555554, "percentage": 71.19, "elapsed_time": "7:45:34", "remaining_time": "3:08:27"}
{"current_steps": 2320, "total_steps": 3245, "loss": 0.0125, "lr": 2.2783088592011303e-05, "epoch": 3.570947570947571, "percentage": 71.49, "elapsed_time": "7:46:54", "remaining_time": "3:06:09"}
{"current_steps": 2330, "total_steps": 3245, "loss": 0.0129, "lr": 2.233340970860608e-05, "epoch": 3.5863395863395864, "percentage": 71.8, "elapsed_time": "7:48:13", "remaining_time": "3:03:52"}
{"current_steps": 2340, "total_steps": 3245, "loss": 0.01, "lr": 2.1886933298312125e-05, "epoch": 3.601731601731602, "percentage": 72.11, "elapsed_time": "7:49:32", "remaining_time": "3:01:35"}
{"current_steps": 2350, "total_steps": 3245, "loss": 0.0111, "lr": 2.1443711041827503e-05, "epoch": 3.617123617123617, "percentage": 72.42, "elapsed_time": "7:50:51", "remaining_time": "2:59:19"}
{"current_steps": 2350, "total_steps": 3245, "eval_loss": 0.03422347456216812, "epoch": 3.617123617123617, "percentage": 72.42, "elapsed_time": "7:53:49", "remaining_time": "3:00:27"}
{"current_steps": 2360, "total_steps": 3245, "loss": 0.007, "lr": 2.1003794243174252e-05, "epoch": 3.6325156325156325, "percentage": 72.73, "elapsed_time": "7:55:12", "remaining_time": "2:58:12"}
{"current_steps": 2370, "total_steps": 3245, "loss": 0.0079, "lr": 2.0567233823759886e-05, "epoch": 3.647907647907648, "percentage": 73.04, "elapsed_time": "7:56:31", "remaining_time": "2:55:56"}
{"current_steps": 2380, "total_steps": 3245, "loss": 0.0079, "lr": 2.0134080316483113e-05, "epoch": 3.6632996632996635, "percentage": 73.34, "elapsed_time": "7:57:50", "remaining_time": "2:53:40"}
{"current_steps": 2390, "total_steps": 3245, "loss": 0.0082, "lr": 1.970438385988452e-05, "epoch": 3.6786916786916786, "percentage": 73.65, "elapsed_time": "7:59:09", "remaining_time": "2:51:25"}
{"current_steps": 2400, "total_steps": 3245, "loss": 0.0105, "lr": 1.927819419234292e-05, "epoch": 3.694083694083694, "percentage": 73.96, "elapsed_time": "8:00:29", "remaining_time": "2:49:10"}
{"current_steps": 2400, "total_steps": 3245, "eval_loss": 0.03513110429048538, "epoch": 3.694083694083694, "percentage": 73.96, "elapsed_time": "8:03:27", "remaining_time": "2:50:13"}
{"current_steps": 2410, "total_steps": 3245, "loss": 0.0146, "lr": 1.885556064631801e-05, "epoch": 3.7094757094757096, "percentage": 74.27, "elapsed_time": "8:04:50", "remaining_time": "2:47:59"}
{"current_steps": 2420, "total_steps": 3245, "loss": 0.0081, "lr": 1.843653214264003e-05, "epoch": 3.7248677248677247, "percentage": 74.58, "elapsed_time": "8:06:10", "remaining_time": "2:45:44"}
{"current_steps": 2430, "total_steps": 3245, "loss": 0.0106, "lr": 1.8021157184847087e-05, "epoch": 3.74025974025974, "percentage": 74.88, "elapsed_time": "8:07:29", "remaining_time": "2:43:30"}
{"current_steps": 2440, "total_steps": 3245, "loss": 0.0117, "lr": 1.7609483853570668e-05, "epoch": 3.7556517556517557, "percentage": 75.19, "elapsed_time": "8:08:48", "remaining_time": "2:41:15"}
{"current_steps": 2450, "total_steps": 3245, "loss": 0.0094, "lr": 1.720155980097034e-05, "epoch": 3.771043771043771, "percentage": 75.5, "elapsed_time": "8:10:07", "remaining_time": "2:39:02"}
{"current_steps": 2450, "total_steps": 3245, "eval_loss": 0.03652167692780495, "epoch": 3.771043771043771, "percentage": 75.5, "elapsed_time": "8:13:06", "remaining_time": "2:40:00"}
{"current_steps": 2460, "total_steps": 3245, "loss": 0.0093, "lr": 1.6797432245217736e-05, "epoch": 3.7864357864357867, "percentage": 75.81, "elapsed_time": "8:14:29", "remaining_time": "2:37:47"}
{"current_steps": 2470, "total_steps": 3245, "loss": 0.011, "lr": 1.6397147965031072e-05, "epoch": 3.801827801827802, "percentage": 76.12, "elapsed_time": "8:15:48", "remaining_time": "2:35:33"}
{"current_steps": 2480, "total_steps": 3245, "loss": 0.0112, "lr": 1.600075329426033e-05, "epoch": 3.8172198172198173, "percentage": 76.43, "elapsed_time": "8:17:07", "remaining_time": "2:33:20"}
{"current_steps": 2490, "total_steps": 3245, "loss": 0.0097, "lr": 1.560829411652403e-05, "epoch": 3.832611832611833, "percentage": 76.73, "elapsed_time": "8:18:26", "remaining_time": "2:31:08"}
{"current_steps": 2500, "total_steps": 3245, "loss": 0.0144, "lr": 1.521981585989809e-05, "epoch": 3.848003848003848, "percentage": 77.04, "elapsed_time": "8:19:45", "remaining_time": "2:28:55"}
{"current_steps": 2500, "total_steps": 3245, "eval_loss": 0.03374967724084854, "epoch": 3.848003848003848, "percentage": 77.04, "elapsed_time": "8:22:44", "remaining_time": "2:29:48"}
{"current_steps": 2510, "total_steps": 3245, "loss": 0.0159, "lr": 1.4835363491657412e-05, "epoch": 3.8633958633958634, "percentage": 77.35, "elapsed_time": "8:24:07", "remaining_time": "2:27:37"}
{"current_steps": 2520, "total_steps": 3245, "loss": 0.0119, "lr": 1.4454981513070791e-05, "epoch": 3.878787878787879, "percentage": 77.66, "elapsed_time": "8:25:26", "remaining_time": "2:25:24"}
{"current_steps": 2530, "total_steps": 3245, "loss": 0.0073, "lr": 1.4078713954249873e-05, "epoch": 3.894179894179894, "percentage": 77.97, "elapsed_time": "8:26:45", "remaining_time": "2:23:12"}
{"current_steps": 2540, "total_steps": 3245, "loss": 0.0075, "lr": 1.3706604369052434e-05, "epoch": 3.9095719095719095, "percentage": 78.27, "elapsed_time": "8:28:04", "remaining_time": "2:21:01"}
{"current_steps": 2550, "total_steps": 3245, "loss": 0.0071, "lr": 1.3338695830041047e-05, "epoch": 3.924963924963925, "percentage": 78.58, "elapsed_time": "8:29:23", "remaining_time": "2:18:50"}
{"current_steps": 2550, "total_steps": 3245, "eval_loss": 0.034059759229421616, "epoch": 3.924963924963925, "percentage": 78.58, "elapsed_time": "8:32:22", "remaining_time": "2:19:38"}
{"current_steps": 2560, "total_steps": 3245, "loss": 0.0088, "lr": 1.2975030923497262e-05, "epoch": 3.9403559403559405, "percentage": 78.89, "elapsed_time": "8:33:45", "remaining_time": "2:17:28"}
{"current_steps": 2570, "total_steps": 3245, "loss": 0.0097, "lr": 1.2615651744492151e-05, "epoch": 3.955747955747956, "percentage": 79.2, "elapsed_time": "8:35:04", "remaining_time": "2:15:16"}
{"current_steps": 2580, "total_steps": 3245, "loss": 0.0084, "lr": 1.2260599892013719e-05, "epoch": 3.971139971139971, "percentage": 79.51, "elapsed_time": "8:36:23", "remaining_time": "2:13:06"}
{"current_steps": 2590, "total_steps": 3245, "loss": 0.0099, "lr": 1.1909916464151715e-05, "epoch": 3.9865319865319866, "percentage": 79.82, "elapsed_time": "8:37:42", "remaining_time": "2:10:55"}
{"current_steps": 2600, "total_steps": 3245, "loss": 0.0081, "lr": 1.1563642053340406e-05, "epoch": 4.001924001924002, "percentage": 80.12, "elapsed_time": "8:39:01", "remaining_time": "2:08:45"}
{"current_steps": 2600, "total_steps": 3245, "eval_loss": 0.03393612429499626, "epoch": 4.001924001924002, "percentage": 80.12, "elapsed_time": "8:42:00", "remaining_time": "2:09:29"}
{"current_steps": 2610, "total_steps": 3245, "loss": 0.0062, "lr": 1.1221816741659964e-05, "epoch": 4.017316017316017, "percentage": 80.43, "elapsed_time": "8:43:23", "remaining_time": "2:07:20"}
{"current_steps": 2620, "total_steps": 3245, "loss": 0.0062, "lr": 1.0884480096196803e-05, "epoch": 4.032708032708033, "percentage": 80.74, "elapsed_time": "8:44:43", "remaining_time": "2:05:10"}
{"current_steps": 2630, "total_steps": 3245, "loss": 0.0061, "lr": 1.0551671164463666e-05, "epoch": 4.048100048100048, "percentage": 81.05, "elapsed_time": "8:46:02", "remaining_time": "2:03:00"}
{"current_steps": 2640, "total_steps": 3245, "loss": 0.0051, "lr": 1.0223428469879736e-05, "epoch": 4.063492063492063, "percentage": 81.36, "elapsed_time": "8:47:22", "remaining_time": "2:00:51"}
{"current_steps": 2650, "total_steps": 3245, "loss": 0.0051, "lr": 9.899790007311455e-06, "epoch": 4.078884078884079, "percentage": 81.66, "elapsed_time": "8:48:40", "remaining_time": "1:58:42"}
{"current_steps": 2650, "total_steps": 3245, "eval_loss": 0.0355365127325058, "epoch": 4.078884078884079, "percentage": 81.66, "elapsed_time": "8:51:39", "remaining_time": "1:59:22"}
{"current_steps": 2660, "total_steps": 3245, "loss": 0.0035, "lr": 9.580793238674573e-06, "epoch": 4.094276094276094, "percentage": 81.97, "elapsed_time": "8:53:02", "remaining_time": "1:57:13"}
{"current_steps": 2670, "total_steps": 3245, "loss": 0.0045, "lr": 9.266475088597781e-06, "epoch": 4.109668109668109, "percentage": 82.28, "elapsed_time": "8:54:21", "remaining_time": "1:55:04"}
{"current_steps": 2680, "total_steps": 3245, "loss": 0.0076, "lr": 8.956871940148681e-06, "epoch": 4.125060125060125, "percentage": 82.59, "elapsed_time": "8:55:40", "remaining_time": "1:52:55"}
{"current_steps": 2690, "total_steps": 3245, "loss": 0.0053, "lr": 8.65201963062225e-06, "epoch": 4.14045214045214, "percentage": 82.9, "elapsed_time": "8:56:59", "remaining_time": "1:50:47"}
{"current_steps": 2700, "total_steps": 3245, "loss": 0.0081, "lr": 8.351953447392674e-06, "epoch": 4.1558441558441555, "percentage": 83.2, "elapsed_time": "8:58:18", "remaining_time": "1:48:39"}
{"current_steps": 2700, "total_steps": 3245, "eval_loss": 0.03636639565229416, "epoch": 4.1558441558441555, "percentage": 83.2, "elapsed_time": "9:01:16", "remaining_time": "1:49:15"}
{"current_steps": 2710, "total_steps": 3245, "loss": 0.0042, "lr": 8.056708123828738e-06, "epoch": 4.171236171236171, "percentage": 83.51, "elapsed_time": "9:02:39", "remaining_time": "1:47:07"}
{"current_steps": 2720, "total_steps": 3245, "loss": 0.0038, "lr": 7.76631783527334e-06, "epoch": 4.1866281866281865, "percentage": 83.82, "elapsed_time": "9:03:58", "remaining_time": "1:44:59"}
{"current_steps": 2730, "total_steps": 3245, "loss": 0.0086, "lr": 7.4808161950876145e-06, "epoch": 4.202020202020202, "percentage": 84.13, "elapsed_time": "9:05:18", "remaining_time": "1:42:52"}
{"current_steps": 2740, "total_steps": 3245, "loss": 0.0053, "lr": 7.200236250760111e-06, "epoch": 4.2174122174122175, "percentage": 84.44, "elapsed_time": "9:06:37", "remaining_time": "1:40:44"}
{"current_steps": 2750, "total_steps": 3245, "loss": 0.0068, "lr": 6.924610480081478e-06, "epoch": 4.232804232804233, "percentage": 84.75, "elapsed_time": "9:07:56", "remaining_time": "1:38:37"}
{"current_steps": 2750, "total_steps": 3245, "eval_loss": 0.03818191587924957, "epoch": 4.232804232804233, "percentage": 84.75, "elapsed_time": "9:10:55", "remaining_time": "1:39:09"}
{"current_steps": 2760, "total_steps": 3245, "loss": 0.006, "lr": 6.6539707873850774e-06, "epoch": 4.2481962481962485, "percentage": 85.05, "elapsed_time": "9:12:17", "remaining_time": "1:37:03"}
{"current_steps": 2770, "total_steps": 3245, "loss": 0.0081, "lr": 6.3883484998539525e-06, "epoch": 4.263588263588264, "percentage": 85.36, "elapsed_time": "9:13:36", "remaining_time": "1:34:56"}
{"current_steps": 2780, "total_steps": 3245, "loss": 0.0032, "lr": 6.127774363894667e-06, "epoch": 4.278980278980279, "percentage": 85.67, "elapsed_time": "9:14:56", "remaining_time": "1:32:49"}
{"current_steps": 2790, "total_steps": 3245, "loss": 0.0042, "lr": 5.872278541578352e-06, "epoch": 4.294372294372295, "percentage": 85.98, "elapsed_time": "9:16:15", "remaining_time": "1:30:42"}
{"current_steps": 2800, "total_steps": 3245, "loss": 0.0055, "lr": 5.6218906071493275e-06, "epoch": 4.30976430976431, "percentage": 86.29, "elapsed_time": "9:17:34", "remaining_time": "1:28:36"}
{"current_steps": 2800, "total_steps": 3245, "eval_loss": 0.03888539969921112, "epoch": 4.30976430976431, "percentage": 86.29, "elapsed_time": "9:20:32", "remaining_time": "1:29:05"}
{"current_steps": 2810, "total_steps": 3245, "loss": 0.0039, "lr": 5.376639543601858e-06, "epoch": 4.325156325156325, "percentage": 86.59, "elapsed_time": "9:21:55", "remaining_time": "1:26:59"}
{"current_steps": 2820, "total_steps": 3245, "loss": 0.004, "lr": 5.136553739325256e-06, "epoch": 4.340548340548341, "percentage": 86.9, "elapsed_time": "9:23:15", "remaining_time": "1:24:53"}
{"current_steps": 2830, "total_steps": 3245, "loss": 0.0046, "lr": 4.901660984817908e-06, "epoch": 4.355940355940356, "percentage": 87.21, "elapsed_time": "9:24:34", "remaining_time": "1:22:47"}
{"current_steps": 2840, "total_steps": 3245, "loss": 0.0051, "lr": 4.671988469470434e-06, "epoch": 4.371332371332372, "percentage": 87.52, "elapsed_time": "9:25:53", "remaining_time": "1:20:41"}
{"current_steps": 2850, "total_steps": 3245, "loss": 0.0045, "lr": 4.447562778418435e-06, "epoch": 4.386724386724387, "percentage": 87.83, "elapsed_time": "9:27:12", "remaining_time": "1:18:36"}
{"current_steps": 2850, "total_steps": 3245, "eval_loss": 0.038550637662410736, "epoch": 4.386724386724387, "percentage": 87.83, "elapsed_time": "9:30:11", "remaining_time": "1:19:01"}
{"current_steps": 2860, "total_steps": 3245, "loss": 0.0039, "lr": 4.228409889465218e-06, "epoch": 4.402116402116402, "percentage": 88.14, "elapsed_time": "9:31:34", "remaining_time": "1:16:56"}
{"current_steps": 2870, "total_steps": 3245, "loss": 0.0053, "lr": 4.014555170074824e-06, "epoch": 4.417508417508418, "percentage": 88.44, "elapsed_time": "9:32:54", "remaining_time": "1:14:51"}
{"current_steps": 2880, "total_steps": 3245, "loss": 0.0036, "lr": 3.8060233744356633e-06, "epoch": 4.432900432900433, "percentage": 88.75, "elapsed_time": "9:34:13", "remaining_time": "1:12:46"}
{"current_steps": 2890, "total_steps": 3245, "loss": 0.005, "lr": 3.602838640595152e-06, "epoch": 4.448292448292448, "percentage": 89.06, "elapsed_time": "9:35:32", "remaining_time": "1:10:41"}
{"current_steps": 2900, "total_steps": 3245, "loss": 0.0033, "lr": 3.4050244876656866e-06, "epoch": 4.463684463684464, "percentage": 89.37, "elapsed_time": "9:36:51", "remaining_time": "1:08:37"}
{"current_steps": 2900, "total_steps": 3245, "eval_loss": 0.038627784699201584, "epoch": 4.463684463684464, "percentage": 89.37, "elapsed_time": "9:39:49", "remaining_time": "1:08:58"}
{"current_steps": 2910, "total_steps": 3245, "loss": 0.0038, "lr": 3.2126038131022552e-06, "epoch": 4.479076479076479, "percentage": 89.68, "elapsed_time": "9:41:13", "remaining_time": "1:06:54"}
{"current_steps": 2920, "total_steps": 3245, "loss": 0.0038, "lr": 3.025598890051995e-06, "epoch": 4.494468494468494, "percentage": 89.98, "elapsed_time": "9:42:32", "remaining_time": "1:04:50"}
{"current_steps": 2930, "total_steps": 3245, "loss": 0.0057, "lr": 2.8440313647760288e-06, "epoch": 4.50986050986051, "percentage": 90.29, "elapsed_time": "9:43:51", "remaining_time": "1:02:46"}
{"current_steps": 2940, "total_steps": 3245, "loss": 0.0038, "lr": 2.6679222541438397e-06, "epoch": 4.525252525252525, "percentage": 90.6, "elapsed_time": "9:45:10", "remaining_time": "1:00:42"}
{"current_steps": 2950, "total_steps": 3245, "loss": 0.0031, "lr": 2.4972919432005582e-06, "epoch": 4.540644540644541, "percentage": 90.91, "elapsed_time": "9:46:29", "remaining_time": "0:58:38"}
{"current_steps": 2950, "total_steps": 3245, "eval_loss": 0.03910013660788536, "epoch": 4.540644540644541, "percentage": 90.91, "elapsed_time": "9:49:28", "remaining_time": "0:58:56"}
{"current_steps": 2960, "total_steps": 3245, "loss": 0.0052, "lr": 2.3321601828073135e-06, "epoch": 4.556036556036556, "percentage": 91.22, "elapsed_time": "9:50:50", "remaining_time": "0:56:53"}
{"current_steps": 2970, "total_steps": 3245, "loss": 0.0032, "lr": 2.1725460873550317e-06, "epoch": 4.571428571428571, "percentage": 91.53, "elapsed_time": "9:52:10", "remaining_time": "0:54:49"}
{"current_steps": 2980, "total_steps": 3245, "loss": 0.0072, "lr": 2.0184681325519096e-06, "epoch": 4.586820586820587, "percentage": 91.83, "elapsed_time": "9:53:28", "remaining_time": "0:52:46"}
{"current_steps": 2990, "total_steps": 3245, "loss": 0.0031, "lr": 1.869944153284786e-06, "epoch": 4.602212602212602, "percentage": 92.14, "elapsed_time": "9:54:48", "remaining_time": "0:50:43"}
{"current_steps": 3000, "total_steps": 3245, "loss": 0.0055, "lr": 1.7269913415547456e-06, "epoch": 4.617604617604617, "percentage": 92.45, "elapsed_time": "9:56:07", "remaining_time": "0:48:41"}
{"current_steps": 3000, "total_steps": 3245, "eval_loss": 0.03934362530708313, "epoch": 4.617604617604617, "percentage": 92.45, "elapsed_time": "9:59:06", "remaining_time": "0:48:55"}
{"current_steps": 3010, "total_steps": 3245, "loss": 0.0056, "lr": 1.589626244487069e-06, "epoch": 4.632996632996633, "percentage": 92.76, "elapsed_time": "10:00:29", "remaining_time": "0:46:52"}
{"current_steps": 3020, "total_steps": 3245, "loss": 0.0058, "lr": 1.4578647624158726e-06, "epoch": 4.648388648388648, "percentage": 93.07, "elapsed_time": "10:01:48", "remaining_time": "0:44:50"}
{"current_steps": 3030, "total_steps": 3245, "loss": 0.0051, "lr": 1.3317221470436293e-06, "epoch": 4.663780663780663, "percentage": 93.37, "elapsed_time": "10:03:07", "remaining_time": "0:42:47"}
{"current_steps": 3040, "total_steps": 3245, "loss": 0.0049, "lr": 1.2112129996757315e-06, "epoch": 4.679172679172679, "percentage": 93.68, "elapsed_time": "10:04:26", "remaining_time": "0:40:45"}
{"current_steps": 3050, "total_steps": 3245, "loss": 0.0081, "lr": 1.0963512695303546e-06, "epoch": 4.694564694564694, "percentage": 93.99, "elapsed_time": "10:05:46", "remaining_time": "0:38:43"}
{"current_steps": 3050, "total_steps": 3245, "eval_loss": 0.03952018544077873, "epoch": 4.694564694564694, "percentage": 93.99, "elapsed_time": "10:08:44", "remaining_time": "0:38:55"}
{"current_steps": 3060, "total_steps": 3245, "loss": 0.0042, "lr": 9.871502521237975e-07, "epoch": 4.70995670995671, "percentage": 94.3, "elapsed_time": "10:10:07", "remaining_time": "0:36:53"}
{"current_steps": 3070, "total_steps": 3245, "loss": 0.0027, "lr": 8.83622587731514e-07, "epoch": 4.725348725348725, "percentage": 94.61, "elapsed_time": "10:11:26", "remaining_time": "0:34:51"}
{"current_steps": 3080, "total_steps": 3245, "loss": 0.004, "lr": 7.857802599249564e-07, "epoch": 4.7407407407407405, "percentage": 94.92, "elapsed_time": "10:12:46", "remaining_time": "0:32:49"}
{"current_steps": 3090, "total_steps": 3245, "loss": 0.0068, "lr": 6.936345941844335e-07, "epoch": 4.756132756132756, "percentage": 95.22, "elapsed_time": "10:14:05", "remaining_time": "0:30:48"}
{"current_steps": 3100, "total_steps": 3245, "loss": 0.0034, "lr": 6.071962565881939e-07, "epoch": 4.7715247715247715, "percentage": 95.53, "elapsed_time": "10:15:24", "remaining_time": "0:28:47"}
{"current_steps": 3100, "total_steps": 3245, "eval_loss": 0.03963901102542877, "epoch": 4.7715247715247715, "percentage": 95.53, "elapsed_time": "10:18:22", "remaining_time": "0:28:55"}
{"current_steps": 3110, "total_steps": 3245, "loss": 0.0029, "lr": 5.264752525777961e-07, "epoch": 4.786916786916787, "percentage": 95.84, "elapsed_time": "10:19:46", "remaining_time": "0:26:54"}
{"current_steps": 3120, "total_steps": 3245, "loss": 0.0061, "lr": 4.5148092579991863e-07, "epoch": 4.8023088023088025, "percentage": 96.15, "elapsed_time": "10:21:05", "remaining_time": "0:24:53"}
{"current_steps": 3130, "total_steps": 3245, "loss": 0.0052, "lr": 3.822219570248531e-07, "epoch": 4.817700817700818, "percentage": 96.46, "elapsed_time": "10:22:24", "remaining_time": "0:22:52"}
{"current_steps": 3140, "total_steps": 3245, "loss": 0.0066, "lr": 3.187063631416742e-07, "epoch": 4.833092833092833, "percentage": 96.76, "elapsed_time": "10:23:43", "remaining_time": "0:20:51"}
{"current_steps": 3150, "total_steps": 3245, "loss": 0.0073, "lr": 2.6094149623024365e-07, "epoch": 4.848484848484849, "percentage": 97.07, "elapsed_time": "10:25:02", "remaining_time": "0:18:51"}
{"current_steps": 3150, "total_steps": 3245, "eval_loss": 0.03955617547035217, "epoch": 4.848484848484849, "percentage": 97.07, "elapsed_time": "10:28:01", "remaining_time": "0:18:56"}
{"current_steps": 3160, "total_steps": 3245, "loss": 0.0035, "lr": 2.0893404271022376e-07, "epoch": 4.863876863876864, "percentage": 97.38, "elapsed_time": "10:29:24", "remaining_time": "0:16:55"}
{"current_steps": 3170, "total_steps": 3245, "loss": 0.0041, "lr": 1.626900225670691e-07, "epoch": 4.87926887926888, "percentage": 97.69, "elapsed_time": "10:30:43", "remaining_time": "0:14:55"}
{"current_steps": 3180, "total_steps": 3245, "loss": 0.0039, "lr": 1.2221478865524493e-07, "epoch": 4.894660894660895, "percentage": 98.0, "elapsed_time": "10:32:02", "remaining_time": "0:12:55"}
{"current_steps": 3190, "total_steps": 3245, "loss": 0.005, "lr": 8.751302607857836e-08, "epoch": 4.91005291005291, "percentage": 98.31, "elapsed_time": "10:33:21", "remaining_time": "0:10:55"}
{"current_steps": 3200, "total_steps": 3245, "loss": 0.0043, "lr": 5.8588751647975506e-08, "epoch": 4.925444925444926, "percentage": 98.61, "elapsed_time": "10:34:41", "remaining_time": "0:08:55"}
{"current_steps": 3200, "total_steps": 3245, "eval_loss": 0.039594002068042755, "epoch": 4.925444925444926, "percentage": 98.61, "elapsed_time": "10:37:40", "remaining_time": "0:08:58"}
{"current_steps": 3210, "total_steps": 3245, "loss": 0.0098, "lr": 3.544531341646007e-08, "epoch": 4.940836940836941, "percentage": 98.92, "elapsed_time": "10:39:03", "remaining_time": "0:06:58"}
{"current_steps": 3220, "total_steps": 3245, "loss": 0.0052, "lr": 1.808539029161116e-08, "epoch": 4.956228956228956, "percentage": 99.23, "elapsed_time": "10:40:22", "remaining_time": "0:04:58"}
{"current_steps": 3230, "total_steps": 3245, "loss": 0.0058, "lr": 6.510991725500182e-09, "epoch": 4.971620971620972, "percentage": 99.54, "elapsed_time": "10:41:41", "remaining_time": "0:02:58"}
{"current_steps": 3240, "total_steps": 3245, "loss": 0.0062, "lr": 7.234574820769169e-10, "epoch": 4.987012987012987, "percentage": 99.85, "elapsed_time": "10:43:01", "remaining_time": "0:00:59"}
{"current_steps": 3245, "total_steps": 3245, "epoch": 4.994708994708994, "percentage": 100.0, "elapsed_time": "10:43:44", "remaining_time": "0:00:00"}