chchen's picture
Training in progress, step 3245
8bc6903 verified
{"current_steps": 10, "total_steps": 3245, "loss": 1.3364, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:27", "remaining_time": "7:50:09"}
{"current_steps": 20, "total_steps": 3245, "loss": 1.2705, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:54", "remaining_time": "7:48:26"}
{"current_steps": 30, "total_steps": 3245, "loss": 1.0348, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:21", "remaining_time": "7:47:13"}
{"current_steps": 40, "total_steps": 3245, "loss": 0.555, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:05:48", "remaining_time": "7:45:39"}
{"current_steps": 50, "total_steps": 3245, "loss": 0.2583, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:07:15", "remaining_time": "7:44:08"}
{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.24182522296905518, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:10:17", "remaining_time": "10:57:45"}
{"current_steps": 60, "total_steps": 3245, "loss": 0.1594, "lr": 1.8461538461538465e-05, "epoch": 0.0923432089265102, "percentage": 1.85, "elapsed_time": "0:11:59", "remaining_time": "10:36:15"}
{"current_steps": 70, "total_steps": 3245, "loss": 0.1275, "lr": 2.1538461538461542e-05, "epoch": 0.10773374374759523, "percentage": 2.16, "elapsed_time": "0:13:26", "remaining_time": "10:09:33"}
{"current_steps": 80, "total_steps": 3245, "loss": 0.1016, "lr": 2.461538461538462e-05, "epoch": 0.12312427856868026, "percentage": 2.47, "elapsed_time": "0:14:53", "remaining_time": "9:48:49"}
{"current_steps": 90, "total_steps": 3245, "loss": 0.1185, "lr": 2.7692307692307694e-05, "epoch": 0.1385148133897653, "percentage": 2.77, "elapsed_time": "0:16:19", "remaining_time": "9:32:30"}
{"current_steps": 100, "total_steps": 3245, "loss": 0.0854, "lr": 3.0769230769230774e-05, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:17:47", "remaining_time": "9:19:20"}
{"current_steps": 100, "total_steps": 3245, "eval_loss": 0.06951398402452469, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:20:48", "remaining_time": "10:54:36"}
{"current_steps": 110, "total_steps": 3245, "loss": 0.0648, "lr": 3.384615384615385e-05, "epoch": 0.16929588303193535, "percentage": 3.39, "elapsed_time": "0:22:29", "remaining_time": "10:41:11"}
{"current_steps": 120, "total_steps": 3245, "loss": 0.0724, "lr": 3.692307692307693e-05, "epoch": 0.1846864178530204, "percentage": 3.7, "elapsed_time": "0:23:56", "remaining_time": "10:23:39"}
{"current_steps": 130, "total_steps": 3245, "loss": 0.0692, "lr": 4e-05, "epoch": 0.2000769526741054, "percentage": 4.01, "elapsed_time": "0:25:23", "remaining_time": "10:08:35"}
{"current_steps": 140, "total_steps": 3245, "loss": 0.079, "lr": 4.3076923076923084e-05, "epoch": 0.21546748749519046, "percentage": 4.31, "elapsed_time": "0:26:50", "remaining_time": "9:55:28"}
{"current_steps": 150, "total_steps": 3245, "loss": 0.061, "lr": 4.615384615384616e-05, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:28:18", "remaining_time": "9:43:58"}
{"current_steps": 150, "total_steps": 3245, "eval_loss": 0.0585860013961792, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:31:19", "remaining_time": "10:46:28"}
{"current_steps": 160, "total_steps": 3245, "loss": 0.0617, "lr": 4.923076923076924e-05, "epoch": 0.24624855713736052, "percentage": 4.93, "elapsed_time": "0:32:50", "remaining_time": "10:33:19"}
{"current_steps": 170, "total_steps": 3245, "loss": 0.0615, "lr": 5.230769230769231e-05, "epoch": 0.26163909195844554, "percentage": 5.24, "elapsed_time": "0:34:17", "remaining_time": "10:20:20"}
{"current_steps": 180, "total_steps": 3245, "loss": 0.0526, "lr": 5.538461538461539e-05, "epoch": 0.2770296267795306, "percentage": 5.55, "elapsed_time": "0:35:44", "remaining_time": "10:08:37"}
{"current_steps": 190, "total_steps": 3245, "loss": 0.044, "lr": 5.846153846153847e-05, "epoch": 0.2924201616006156, "percentage": 5.86, "elapsed_time": "0:37:11", "remaining_time": "9:57:55"}
{"current_steps": 200, "total_steps": 3245, "loss": 0.0581, "lr": 6.153846153846155e-05, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:38:38", "remaining_time": "9:48:15"}
{"current_steps": 200, "total_steps": 3245, "eval_loss": 0.05444643646478653, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:41:39", "remaining_time": "10:34:21"}
{"current_steps": 210, "total_steps": 3245, "loss": 0.0558, "lr": 6.461538461538462e-05, "epoch": 0.3232012312427857, "percentage": 6.47, "elapsed_time": "0:43:20", "remaining_time": "10:26:20"}
{"current_steps": 220, "total_steps": 3245, "loss": 0.0499, "lr": 6.76923076923077e-05, "epoch": 0.3385917660638707, "percentage": 6.78, "elapsed_time": "0:44:47", "remaining_time": "10:15:50"}
{"current_steps": 230, "total_steps": 3245, "loss": 0.0384, "lr": 7.076923076923078e-05, "epoch": 0.35398230088495575, "percentage": 7.09, "elapsed_time": "0:46:14", "remaining_time": "10:06:09"}
{"current_steps": 240, "total_steps": 3245, "loss": 0.0458, "lr": 7.384615384615386e-05, "epoch": 0.3693728357060408, "percentage": 7.4, "elapsed_time": "0:47:41", "remaining_time": "9:57:09"}
{"current_steps": 250, "total_steps": 3245, "loss": 0.0443, "lr": 7.692307692307693e-05, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:49:08", "remaining_time": "9:48:44"}
{"current_steps": 250, "total_steps": 3245, "eval_loss": 0.04309243708848953, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:52:10", "remaining_time": "10:25:01"}
{"current_steps": 260, "total_steps": 3245, "loss": 0.0404, "lr": 8e-05, "epoch": 0.4001539053482108, "percentage": 8.01, "elapsed_time": "0:53:51", "remaining_time": "10:18:17"}
{"current_steps": 270, "total_steps": 3245, "loss": 0.0411, "lr": 8.307692307692309e-05, "epoch": 0.41554444016929587, "percentage": 8.32, "elapsed_time": "0:55:18", "remaining_time": "10:09:22"}
{"current_steps": 280, "total_steps": 3245, "loss": 0.0541, "lr": 8.615384615384617e-05, "epoch": 0.4309349749903809, "percentage": 8.63, "elapsed_time": "0:56:45", "remaining_time": "10:01:02"}
{"current_steps": 290, "total_steps": 3245, "loss": 0.0506, "lr": 8.923076923076924e-05, "epoch": 0.44632550981146596, "percentage": 8.94, "elapsed_time": "0:58:12", "remaining_time": "9:53:08"}
{"current_steps": 300, "total_steps": 3245, "loss": 0.0398, "lr": 9.230769230769232e-05, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:59:39", "remaining_time": "9:45:40"}
{"current_steps": 300, "total_steps": 3245, "eval_loss": 0.04688544571399689, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "1:02:41", "remaining_time": "10:15:24"}
{"current_steps": 310, "total_steps": 3245, "loss": 0.0522, "lr": 9.53846153846154e-05, "epoch": 0.477106579453636, "percentage": 9.55, "elapsed_time": "1:04:20", "remaining_time": "10:09:09"}
{"current_steps": 320, "total_steps": 3245, "loss": 0.0464, "lr": 9.846153846153848e-05, "epoch": 0.49249711427472104, "percentage": 9.86, "elapsed_time": "1:05:47", "remaining_time": "10:01:19"}
{"current_steps": 330, "total_steps": 3245, "loss": 0.048, "lr": 9.999927654251793e-05, "epoch": 0.5078876490958061, "percentage": 10.17, "elapsed_time": "1:07:14", "remaining_time": "9:53:58"}
{"current_steps": 340, "total_steps": 3245, "loss": 0.0445, "lr": 9.99934890082745e-05, "epoch": 0.5232781839168911, "percentage": 10.48, "elapsed_time": "1:08:41", "remaining_time": "9:46:55"}
{"current_steps": 350, "total_steps": 3245, "loss": 0.0431, "lr": 9.99819146097084e-05, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:10:08", "remaining_time": "9:40:09"}
{"current_steps": 350, "total_steps": 3245, "eval_loss": 0.045772019773721695, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:13:10", "remaining_time": "10:05:12"}
{"current_steps": 360, "total_steps": 3245, "loss": 0.0571, "lr": 9.996455468658355e-05, "epoch": 0.5540592535590612, "percentage": 11.09, "elapsed_time": "1:14:55", "remaining_time": "10:00:28"}
{"current_steps": 370, "total_steps": 3245, "loss": 0.0369, "lr": 9.994141124835203e-05, "epoch": 0.5694497883801463, "percentage": 11.4, "elapsed_time": "1:16:23", "remaining_time": "9:53:33"}
{"current_steps": 380, "total_steps": 3245, "loss": 0.038, "lr": 9.991248697392142e-05, "epoch": 0.5848403232012312, "percentage": 11.71, "elapsed_time": "1:17:50", "remaining_time": "9:46:50"}
{"current_steps": 390, "total_steps": 3245, "loss": 0.0351, "lr": 9.987778521134476e-05, "epoch": 0.6002308580223162, "percentage": 12.02, "elapsed_time": "1:19:17", "remaining_time": "9:40:25"}
{"current_steps": 400, "total_steps": 3245, "loss": 0.0482, "lr": 9.983730997743294e-05, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:20:44", "remaining_time": "9:34:17"}
{"current_steps": 400, "total_steps": 3245, "eval_loss": 0.04355475306510925, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:23:46", "remaining_time": "9:55:50"}
{"current_steps": 410, "total_steps": 3245, "loss": 0.042, "lr": 9.979106595728978e-05, "epoch": 0.6310119276644863, "percentage": 12.63, "elapsed_time": "1:25:24", "remaining_time": "9:50:32"}
{"current_steps": 420, "total_steps": 3245, "loss": 0.0454, "lr": 9.973905850376977e-05, "epoch": 0.6464024624855714, "percentage": 12.94, "elapsed_time": "1:26:51", "remaining_time": "9:44:14"}
{"current_steps": 430, "total_steps": 3245, "loss": 0.0437, "lr": 9.968129363685833e-05, "epoch": 0.6617929973066564, "percentage": 13.25, "elapsed_time": "1:28:18", "remaining_time": "9:38:06"}
{"current_steps": 440, "total_steps": 3245, "loss": 0.0581, "lr": 9.961777804297514e-05, "epoch": 0.6771835321277414, "percentage": 13.56, "elapsed_time": "1:29:45", "remaining_time": "9:32:14"}
{"current_steps": 450, "total_steps": 3245, "loss": 0.029, "lr": 9.954851907420009e-05, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:31:12", "remaining_time": "9:26:32"}
{"current_steps": 450, "total_steps": 3245, "eval_loss": 0.038769323378801346, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:34:14", "remaining_time": "9:45:21"}
{"current_steps": 460, "total_steps": 3245, "loss": 0.0351, "lr": 9.947352474742222e-05, "epoch": 0.7079646017699115, "percentage": 14.18, "elapsed_time": "1:35:57", "remaining_time": "9:40:58"}
{"current_steps": 470, "total_steps": 3245, "loss": 0.0308, "lr": 9.93928037434118e-05, "epoch": 0.7233551365909965, "percentage": 14.48, "elapsed_time": "1:37:24", "remaining_time": "9:35:08"}
{"current_steps": 480, "total_steps": 3245, "loss": 0.0427, "lr": 9.930636540581556e-05, "epoch": 0.7387456714120816, "percentage": 14.79, "elapsed_time": "1:38:51", "remaining_time": "9:29:30"}
{"current_steps": 490, "total_steps": 3245, "loss": 0.0453, "lr": 9.921421974007506e-05, "epoch": 0.7541362062331666, "percentage": 15.1, "elapsed_time": "1:40:19", "remaining_time": "9:24:04"}
{"current_steps": 500, "total_steps": 3245, "loss": 0.0294, "lr": 9.911637741226849e-05, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:41:46", "remaining_time": "9:18:45"}
{"current_steps": 500, "total_steps": 3245, "eval_loss": 0.03677697852253914, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:44:48", "remaining_time": "9:35:23"}
{"current_steps": 510, "total_steps": 3245, "loss": 0.0299, "lr": 9.90128497478762e-05, "epoch": 0.7849172758753367, "percentage": 15.72, "elapsed_time": "1:46:36", "remaining_time": "9:31:43"}
{"current_steps": 520, "total_steps": 3245, "loss": 0.0423, "lr": 9.890364873046965e-05, "epoch": 0.8003078106964217, "percentage": 16.02, "elapsed_time": "1:48:03", "remaining_time": "9:26:16"}
{"current_steps": 530, "total_steps": 3245, "loss": 0.0525, "lr": 9.878878700032427e-05, "epoch": 0.8156983455175068, "percentage": 16.33, "elapsed_time": "1:49:30", "remaining_time": "9:21:00"}
{"current_steps": 540, "total_steps": 3245, "loss": 0.0413, "lr": 9.866827785295638e-05, "epoch": 0.8310888803385917, "percentage": 16.64, "elapsed_time": "1:50:58", "remaining_time": "9:15:51"}
{"current_steps": 550, "total_steps": 3245, "loss": 0.0415, "lr": 9.854213523758413e-05, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:52:25", "remaining_time": "9:10:51"}
{"current_steps": 550, "total_steps": 3245, "eval_loss": 0.034638144075870514, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:55:26", "remaining_time": "9:25:41"}
{"current_steps": 560, "total_steps": 3245, "loss": 0.0355, "lr": 9.841037375551294e-05, "epoch": 0.8618699499807618, "percentage": 17.26, "elapsed_time": "1:56:59", "remaining_time": "9:20:57"}
{"current_steps": 570, "total_steps": 3245, "loss": 0.0259, "lr": 9.827300865844527e-05, "epoch": 0.8772604848018468, "percentage": 17.57, "elapsed_time": "1:58:27", "remaining_time": "9:15:53"}
{"current_steps": 580, "total_steps": 3245, "loss": 0.0346, "lr": 9.813005584671522e-05, "epoch": 0.8926510196229319, "percentage": 17.87, "elapsed_time": "1:59:54", "remaining_time": "9:10:56"}
{"current_steps": 590, "total_steps": 3245, "loss": 0.0499, "lr": 9.79815318674481e-05, "epoch": 0.9080415544440169, "percentage": 18.18, "elapsed_time": "2:01:21", "remaining_time": "9:06:06"}
{"current_steps": 600, "total_steps": 3245, "loss": 0.0341, "lr": 9.782745391264498e-05, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:02:48", "remaining_time": "9:01:22"}
{"current_steps": 600, "total_steps": 3245, "eval_loss": 0.034780871123075485, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:05:50", "remaining_time": "9:14:43"}
{"current_steps": 610, "total_steps": 3245, "loss": 0.0313, "lr": 9.76678398171927e-05, "epoch": 0.938822624086187, "percentage": 18.8, "elapsed_time": "2:07:31", "remaining_time": "9:10:50"}
{"current_steps": 620, "total_steps": 3245, "loss": 0.0435, "lr": 9.750270805679945e-05, "epoch": 0.954213158907272, "percentage": 19.11, "elapsed_time": "2:08:58", "remaining_time": "9:06:02"}
{"current_steps": 630, "total_steps": 3245, "loss": 0.0427, "lr": 9.733207774585618e-05, "epoch": 0.9696036937283571, "percentage": 19.41, "elapsed_time": "2:10:25", "remaining_time": "9:01:20"}
{"current_steps": 640, "total_steps": 3245, "loss": 0.0327, "lr": 9.715596863522398e-05, "epoch": 0.9849942285494421, "percentage": 19.72, "elapsed_time": "2:11:52", "remaining_time": "8:56:44"}
{"current_steps": 650, "total_steps": 3245, "loss": 0.0303, "lr": 9.697440110994801e-05, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:13:19", "remaining_time": "8:52:15"}
{"current_steps": 650, "total_steps": 3245, "eval_loss": 0.03528154641389847, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:16:21", "remaining_time": "9:04:21"}
{"current_steps": 660, "total_steps": 3245, "loss": 0.0339, "lr": 9.678739618689775e-05, "epoch": 1.0157752981916122, "percentage": 20.34, "elapsed_time": "2:17:53", "remaining_time": "9:00:05"}
{"current_steps": 670, "total_steps": 3245, "loss": 0.0311, "lr": 9.659497551233431e-05, "epoch": 1.0311658330126972, "percentage": 20.65, "elapsed_time": "2:19:20", "remaining_time": "8:55:32"}
{"current_steps": 680, "total_steps": 3245, "loss": 0.033, "lr": 9.639716135940485e-05, "epoch": 1.0465563678337821, "percentage": 20.96, "elapsed_time": "2:20:47", "remaining_time": "8:51:05"}
{"current_steps": 690, "total_steps": 3245, "loss": 0.0442, "lr": 9.619397662556435e-05, "epoch": 1.0619469026548674, "percentage": 21.26, "elapsed_time": "2:22:15", "remaining_time": "8:46:44"}
{"current_steps": 700, "total_steps": 3245, "loss": 0.0353, "lr": 9.598544482992517e-05, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:23:42", "remaining_time": "8:42:28"}
{"current_steps": 700, "total_steps": 3245, "eval_loss": 0.037871893495321274, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:26:44", "remaining_time": "8:53:29"}
{"current_steps": 710, "total_steps": 3245, "loss": 0.0325, "lr": 9.57715901105348e-05, "epoch": 1.0927279722970373, "percentage": 21.88, "elapsed_time": "2:28:16", "remaining_time": "8:49:22"}
{"current_steps": 720, "total_steps": 3245, "loss": 0.0287, "lr": 9.555243722158158e-05, "epoch": 1.1081185071181223, "percentage": 22.19, "elapsed_time": "2:29:42", "remaining_time": "8:45:02"}
{"current_steps": 730, "total_steps": 3245, "loss": 0.029, "lr": 9.532801153052958e-05, "epoch": 1.1235090419392073, "percentage": 22.5, "elapsed_time": "2:31:09", "remaining_time": "8:40:47"}
{"current_steps": 740, "total_steps": 3245, "loss": 0.0361, "lr": 9.509833901518209e-05, "epoch": 1.1388995767602923, "percentage": 22.8, "elapsed_time": "2:32:36", "remaining_time": "8:36:37"}
{"current_steps": 750, "total_steps": 3245, "loss": 0.026, "lr": 9.486344626067475e-05, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:34:04", "remaining_time": "8:32:32"}
{"current_steps": 750, "total_steps": 3245, "eval_loss": 0.03458985313773155, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:37:06", "remaining_time": "8:42:37"}
{"current_steps": 760, "total_steps": 3245, "loss": 0.033, "lr": 9.462336045639815e-05, "epoch": 1.1696806464024625, "percentage": 23.42, "elapsed_time": "2:38:47", "remaining_time": "8:39:10"}
{"current_steps": 770, "total_steps": 3245, "loss": 0.0344, "lr": 9.437810939285068e-05, "epoch": 1.1850711812235475, "percentage": 23.73, "elapsed_time": "2:40:14", "remaining_time": "8:35:03"}
{"current_steps": 780, "total_steps": 3245, "loss": 0.0347, "lr": 9.412772145842165e-05, "epoch": 1.2004617160446325, "percentage": 24.04, "elapsed_time": "2:41:41", "remaining_time": "8:30:58"}
{"current_steps": 790, "total_steps": 3245, "loss": 0.0346, "lr": 9.387222563610535e-05, "epoch": 1.2158522508657175, "percentage": 24.35, "elapsed_time": "2:43:08", "remaining_time": "8:26:58"}
{"current_steps": 800, "total_steps": 3245, "loss": 0.0289, "lr": 9.361165150014606e-05, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:44:35", "remaining_time": "8:23:02"}
{"current_steps": 800, "total_steps": 3245, "eval_loss": 0.0333932600915432, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:47:37", "remaining_time": "8:32:18"}
{"current_steps": 810, "total_steps": 3245, "loss": 0.0287, "lr": 9.334602921261492e-05, "epoch": 1.2466333205078877, "percentage": 24.96, "elapsed_time": "2:49:09", "remaining_time": "8:28:29"}
{"current_steps": 820, "total_steps": 3245, "loss": 0.0286, "lr": 9.307538951991852e-05, "epoch": 1.2620238553289727, "percentage": 25.27, "elapsed_time": "2:50:36", "remaining_time": "8:24:31"}
{"current_steps": 830, "total_steps": 3245, "loss": 0.0341, "lr": 9.279976374923988e-05, "epoch": 1.2774143901500576, "percentage": 25.58, "elapsed_time": "2:52:03", "remaining_time": "8:20:36"}
{"current_steps": 840, "total_steps": 3245, "loss": 0.0269, "lr": 9.251918380491238e-05, "epoch": 1.2928049249711426, "percentage": 25.89, "elapsed_time": "2:53:30", "remaining_time": "8:16:45"}
{"current_steps": 850, "total_steps": 3245, "loss": 0.0274, "lr": 9.223368216472668e-05, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "2:54:57", "remaining_time": "8:12:58"}
{"current_steps": 850, "total_steps": 3245, "eval_loss": 0.03453436121344566, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "2:57:59", "remaining_time": "8:21:30"}
{"current_steps": 860, "total_steps": 3245, "loss": 0.0265, "lr": 9.194329187617127e-05, "epoch": 1.3235859946133128, "percentage": 26.5, "elapsed_time": "2:59:30", "remaining_time": "8:17:49"}
{"current_steps": 870, "total_steps": 3245, "loss": 0.0266, "lr": 9.164804655260735e-05, "epoch": 1.3389765294343978, "percentage": 26.81, "elapsed_time": "3:00:57", "remaining_time": "8:13:58"}
{"current_steps": 880, "total_steps": 3245, "loss": 0.0288, "lr": 9.134798036937778e-05, "epoch": 1.3543670642554828, "percentage": 27.12, "elapsed_time": "3:02:24", "remaining_time": "8:10:12"}
{"current_steps": 890, "total_steps": 3245, "loss": 0.0383, "lr": 9.104312805985134e-05, "epoch": 1.3697575990765678, "percentage": 27.43, "elapsed_time": "3:03:51", "remaining_time": "8:06:30"}
{"current_steps": 900, "total_steps": 3245, "loss": 0.0206, "lr": 9.073352491140221e-05, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:05:18", "remaining_time": "8:02:50"}
{"current_steps": 900, "total_steps": 3245, "eval_loss": 0.032716140151023865, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:08:20", "remaining_time": "8:10:43"}
{"current_steps": 910, "total_steps": 3245, "loss": 0.0294, "lr": 9.041920676132543e-05, "epoch": 1.400538668718738, "percentage": 28.04, "elapsed_time": "3:10:02", "remaining_time": "8:07:38"}
{"current_steps": 920, "total_steps": 3245, "loss": 0.0312, "lr": 9.010020999268854e-05, "epoch": 1.415929203539823, "percentage": 28.35, "elapsed_time": "3:11:29", "remaining_time": "8:03:56"}
{"current_steps": 930, "total_steps": 3245, "loss": 0.0266, "lr": 8.977657153012027e-05, "epoch": 1.431319738360908, "percentage": 28.66, "elapsed_time": "3:12:56", "remaining_time": "8:00:17"}
{"current_steps": 940, "total_steps": 3245, "loss": 0.0283, "lr": 8.944832883553633e-05, "epoch": 1.446710273181993, "percentage": 28.97, "elapsed_time": "3:14:23", "remaining_time": "7:56:41"}
{"current_steps": 950, "total_steps": 3245, "loss": 0.0362, "lr": 8.91155199038032e-05, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:15:51", "remaining_time": "7:53:08"}
{"current_steps": 950, "total_steps": 3245, "eval_loss": 0.0331537090241909, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:18:53", "remaining_time": "8:00:27"}
{"current_steps": 960, "total_steps": 3245, "loss": 0.0283, "lr": 8.877818325834006e-05, "epoch": 1.4774913428241632, "percentage": 29.58, "elapsed_time": "3:20:24", "remaining_time": "7:57:00"}
{"current_steps": 970, "total_steps": 3245, "loss": 0.0229, "lr": 8.843635794665961e-05, "epoch": 1.4928818776452482, "percentage": 29.89, "elapsed_time": "3:21:51", "remaining_time": "7:53:25"}
{"current_steps": 980, "total_steps": 3245, "loss": 0.0295, "lr": 8.809008353584829e-05, "epoch": 1.5082724124663334, "percentage": 30.2, "elapsed_time": "3:23:18", "remaining_time": "7:49:53"}
{"current_steps": 990, "total_steps": 3245, "loss": 0.0295, "lr": 8.773940010798627e-05, "epoch": 1.5236629472874181, "percentage": 30.51, "elapsed_time": "3:24:46", "remaining_time": "7:46:24"}
{"current_steps": 1000, "total_steps": 3245, "loss": 0.0305, "lr": 8.738434825550785e-05, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:26:13", "remaining_time": "7:42:57"}
{"current_steps": 1000, "total_steps": 3245, "eval_loss": 0.035451073199510574, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:29:15", "remaining_time": "7:49:46"}
{"current_steps": 1010, "total_steps": 3245, "loss": 0.0346, "lr": 8.702496907650274e-05, "epoch": 1.5544440169295883, "percentage": 31.12, "elapsed_time": "3:30:55", "remaining_time": "7:46:45"}
{"current_steps": 1020, "total_steps": 3245, "loss": 0.0316, "lr": 8.666130416995897e-05, "epoch": 1.5698345517506733, "percentage": 31.43, "elapsed_time": "3:32:22", "remaining_time": "7:43:16"}
{"current_steps": 1030, "total_steps": 3245, "loss": 0.0297, "lr": 8.629339563094758e-05, "epoch": 1.5852250865717585, "percentage": 31.74, "elapsed_time": "3:33:50", "remaining_time": "7:39:51"}
{"current_steps": 1040, "total_steps": 3245, "loss": 0.0274, "lr": 8.592128604575014e-05, "epoch": 1.6006156213928433, "percentage": 32.05, "elapsed_time": "3:35:17", "remaining_time": "7:36:27"}
{"current_steps": 1050, "total_steps": 3245, "loss": 0.033, "lr": 8.554501848692921e-05, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:36:44", "remaining_time": "7:33:06"}
{"current_steps": 1050, "total_steps": 3245, "eval_loss": 0.03250161185860634, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:39:46", "remaining_time": "7:39:26"}
{"current_steps": 1060, "total_steps": 3245, "loss": 0.0226, "lr": 8.51646365083426e-05, "epoch": 1.6313966910350135, "percentage": 32.67, "elapsed_time": "3:41:27", "remaining_time": "7:36:30"}
{"current_steps": 1070, "total_steps": 3245, "loss": 0.0258, "lr": 8.478018414010191e-05, "epoch": 1.6467872258560985, "percentage": 32.97, "elapsed_time": "3:42:54", "remaining_time": "7:33:06"}
{"current_steps": 1080, "total_steps": 3245, "loss": 0.0231, "lr": 8.439170588347598e-05, "epoch": 1.6621777606771835, "percentage": 33.28, "elapsed_time": "3:44:21", "remaining_time": "7:29:45"}
{"current_steps": 1090, "total_steps": 3245, "loss": 0.0287, "lr": 8.399924670573969e-05, "epoch": 1.6775682954982685, "percentage": 33.59, "elapsed_time": "3:45:48", "remaining_time": "7:26:25"}
{"current_steps": 1100, "total_steps": 3245, "loss": 0.035, "lr": 8.360285203496894e-05, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:47:15", "remaining_time": "7:23:10"}
{"current_steps": 1100, "total_steps": 3245, "eval_loss": 0.03675594925880432, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:50:17", "remaining_time": "7:29:04"}
{"current_steps": 1110, "total_steps": 3245, "loss": 0.0307, "lr": 8.320256775478228e-05, "epoch": 1.7083493651404387, "percentage": 34.21, "elapsed_time": "3:51:58", "remaining_time": "7:26:11"}
{"current_steps": 1120, "total_steps": 3245, "loss": 0.0241, "lr": 8.279844019902968e-05, "epoch": 1.7237398999615237, "percentage": 34.51, "elapsed_time": "3:53:26", "remaining_time": "7:22:54"}
{"current_steps": 1130, "total_steps": 3245, "loss": 0.0338, "lr": 8.239051614642934e-05, "epoch": 1.7391304347826086, "percentage": 34.82, "elapsed_time": "3:54:53", "remaining_time": "7:19:37"}
{"current_steps": 1140, "total_steps": 3245, "loss": 0.0391, "lr": 8.197884281515292e-05, "epoch": 1.7545209696036936, "percentage": 35.13, "elapsed_time": "3:56:20", "remaining_time": "7:16:23"}
{"current_steps": 1150, "total_steps": 3245, "loss": 0.0219, "lr": 8.156346785735997e-05, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "3:57:47", "remaining_time": "7:13:11"}
{"current_steps": 1150, "total_steps": 3245, "eval_loss": 0.03331456333398819, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "4:00:49", "remaining_time": "7:18:42"}
{"current_steps": 1160, "total_steps": 3245, "loss": 0.0336, "lr": 8.114443935368198e-05, "epoch": 1.7853020392458638, "percentage": 35.75, "elapsed_time": "4:02:29", "remaining_time": "7:15:51"}
{"current_steps": 1170, "total_steps": 3245, "loss": 0.0242, "lr": 8.072180580765709e-05, "epoch": 1.8006925740669488, "percentage": 36.06, "elapsed_time": "4:03:56", "remaining_time": "7:12:38"}
{"current_steps": 1180, "total_steps": 3245, "loss": 0.0259, "lr": 8.02956161401155e-05, "epoch": 1.8160831088880338, "percentage": 36.36, "elapsed_time": "4:05:24", "remaining_time": "7:09:28"}
{"current_steps": 1190, "total_steps": 3245, "loss": 0.0299, "lr": 7.98659196835169e-05, "epoch": 1.8314736437091188, "percentage": 36.67, "elapsed_time": "4:06:51", "remaining_time": "7:06:18"}
{"current_steps": 1200, "total_steps": 3245, "loss": 0.0199, "lr": 7.943276617624014e-05, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:08:19", "remaining_time": "7:03:10"}
{"current_steps": 1200, "total_steps": 3245, "eval_loss": 0.037526000291109085, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:11:20", "remaining_time": "7:08:20"}
{"current_steps": 1210, "total_steps": 3245, "loss": 0.0295, "lr": 7.899620575682578e-05, "epoch": 1.862254713351289, "percentage": 37.29, "elapsed_time": "4:12:52", "remaining_time": "7:05:17"}
{"current_steps": 1220, "total_steps": 3245, "loss": 0.0233, "lr": 7.85562889581725e-05, "epoch": 1.877645248172374, "percentage": 37.6, "elapsed_time": "4:14:19", "remaining_time": "7:02:08"}
{"current_steps": 1230, "total_steps": 3245, "loss": 0.0276, "lr": 7.811306670168788e-05, "epoch": 1.893035782993459, "percentage": 37.9, "elapsed_time": "4:15:46", "remaining_time": "6:59:01"}
{"current_steps": 1240, "total_steps": 3245, "loss": 0.0347, "lr": 7.766659029139393e-05, "epoch": 1.908426317814544, "percentage": 38.21, "elapsed_time": "4:17:13", "remaining_time": "6:55:55"}
{"current_steps": 1250, "total_steps": 3245, "loss": 0.0279, "lr": 7.72169114079887e-05, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:18:40", "remaining_time": "6:52:51"}
{"current_steps": 1250, "total_steps": 3245, "eval_loss": 0.032986849546432495, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:21:42", "remaining_time": "6:57:41"}
{"current_steps": 1260, "total_steps": 3245, "loss": 0.0302, "lr": 7.676408210286407e-05, "epoch": 1.9392073874567142, "percentage": 38.83, "elapsed_time": "4:23:14", "remaining_time": "6:54:42"}
{"current_steps": 1270, "total_steps": 3245, "loss": 0.0309, "lr": 7.630815479208066e-05, "epoch": 1.9545979222777992, "percentage": 39.14, "elapsed_time": "4:24:41", "remaining_time": "6:51:37"}
{"current_steps": 1280, "total_steps": 3245, "loss": 0.0225, "lr": 7.584918225030053e-05, "epoch": 1.9699884570988841, "percentage": 39.45, "elapsed_time": "4:26:08", "remaining_time": "6:48:34"}
{"current_steps": 1290, "total_steps": 3245, "loss": 0.0315, "lr": 7.538721760467845e-05, "epoch": 1.9853789919199691, "percentage": 39.75, "elapsed_time": "4:27:35", "remaining_time": "6:45:32"}
{"current_steps": 1300, "total_steps": 3245, "loss": 0.0226, "lr": 7.49223143287122e-05, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:29:02", "remaining_time": "6:42:31"}
{"current_steps": 1300, "total_steps": 3245, "eval_loss": 0.03224512189626694, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:32:04", "remaining_time": "6:47:03"}
{"current_steps": 1310, "total_steps": 3245, "loss": 0.0176, "lr": 7.445452623605307e-05, "epoch": 2.016160061562139, "percentage": 40.37, "elapsed_time": "4:33:40", "remaining_time": "6:44:14"}
{"current_steps": 1320, "total_steps": 3245, "loss": 0.018, "lr": 7.398390747427662e-05, "epoch": 2.0315505963832243, "percentage": 40.68, "elapsed_time": "4:35:07", "remaining_time": "6:41:13"}
{"current_steps": 1330, "total_steps": 3245, "loss": 0.0192, "lr": 7.351051251861501e-05, "epoch": 2.0469411312043095, "percentage": 40.99, "elapsed_time": "4:36:35", "remaining_time": "6:38:14"}
{"current_steps": 1340, "total_steps": 3245, "loss": 0.0213, "lr": 7.303439616565146e-05, "epoch": 2.0623316660253943, "percentage": 41.29, "elapsed_time": "4:38:02", "remaining_time": "6:35:16"}
{"current_steps": 1350, "total_steps": 3245, "loss": 0.0178, "lr": 7.255561352697732e-05, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:39:29", "remaining_time": "6:32:19"}
{"current_steps": 1350, "total_steps": 3245, "eval_loss": 0.03181542828679085, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:42:30", "remaining_time": "6:36:34"}
{"current_steps": 1360, "total_steps": 3245, "loss": 0.0185, "lr": 7.207422002281281e-05, "epoch": 2.0931127356675643, "percentage": 41.91, "elapsed_time": "4:44:11", "remaining_time": "6:33:53"}
{"current_steps": 1370, "total_steps": 3245, "loss": 0.0164, "lr": 7.159027137559197e-05, "epoch": 2.1085032704886495, "percentage": 42.22, "elapsed_time": "4:45:38", "remaining_time": "6:30:56"}
{"current_steps": 1380, "total_steps": 3245, "loss": 0.0134, "lr": 7.110382360351267e-05, "epoch": 2.1238938053097347, "percentage": 42.53, "elapsed_time": "4:47:05", "remaining_time": "6:27:59"}
{"current_steps": 1390, "total_steps": 3245, "loss": 0.0142, "lr": 7.061493301405244e-05, "epoch": 2.1392843401308195, "percentage": 42.84, "elapsed_time": "4:48:32", "remaining_time": "6:25:04"}
{"current_steps": 1400, "total_steps": 3245, "loss": 0.022, "lr": 7.012365619745064e-05, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:50:00", "remaining_time": "6:22:10"}
{"current_steps": 1400, "total_steps": 3245, "eval_loss": 0.03445231914520264, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:53:01", "remaining_time": "6:26:10"}
{"current_steps": 1410, "total_steps": 3245, "loss": 0.0168, "lr": 6.963005002015808e-05, "epoch": 2.1700654097729895, "percentage": 43.45, "elapsed_time": "4:54:42", "remaining_time": "6:23:32"}
{"current_steps": 1420, "total_steps": 3245, "loss": 0.0219, "lr": 6.91341716182545e-05, "epoch": 2.1854559445940747, "percentage": 43.76, "elapsed_time": "4:56:09", "remaining_time": "6:20:38"}
{"current_steps": 1430, "total_steps": 3245, "loss": 0.0111, "lr": 6.863607839083507e-05, "epoch": 2.20084647941516, "percentage": 44.07, "elapsed_time": "4:57:37", "remaining_time": "6:17:44"}
{"current_steps": 1440, "total_steps": 3245, "loss": 0.021, "lr": 6.813582799336624e-05, "epoch": 2.2162370142362446, "percentage": 44.38, "elapsed_time": "4:59:04", "remaining_time": "6:14:52"}
{"current_steps": 1450, "total_steps": 3245, "loss": 0.0098, "lr": 6.763347833101192e-05, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "5:00:31", "remaining_time": "6:12:02"}
{"current_steps": 1450, "total_steps": 3245, "eval_loss": 0.03824140876531601, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "5:03:33", "remaining_time": "6:15:47"}
{"current_steps": 1460, "total_steps": 3245, "loss": 0.0188, "lr": 6.712908755193094e-05, "epoch": 2.2470180838784146, "percentage": 44.99, "elapsed_time": "5:05:05", "remaining_time": "6:13:00"}
{"current_steps": 1470, "total_steps": 3245, "loss": 0.0211, "lr": 6.662271404054621e-05, "epoch": 2.2624086186995, "percentage": 45.3, "elapsed_time": "5:06:32", "remaining_time": "6:10:08"}
{"current_steps": 1480, "total_steps": 3245, "loss": 0.0186, "lr": 6.611441641078657e-05, "epoch": 2.2777991535205846, "percentage": 45.61, "elapsed_time": "5:07:59", "remaining_time": "6:07:17"}
{"current_steps": 1490, "total_steps": 3245, "loss": 0.0204, "lr": 6.560425349930208e-05, "epoch": 2.29318968834167, "percentage": 45.92, "elapsed_time": "5:09:25", "remaining_time": "6:04:27"}
{"current_steps": 1500, "total_steps": 3245, "loss": 0.0209, "lr": 6.509228435865357e-05, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:10:52", "remaining_time": "6:01:39"}
{"current_steps": 1500, "total_steps": 3245, "eval_loss": 0.03401584550738335, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:13:54", "remaining_time": "6:05:10"}
{"current_steps": 1510, "total_steps": 3245, "loss": 0.0216, "lr": 6.45785682504772e-05, "epoch": 2.32397075798384, "percentage": 46.53, "elapsed_time": "5:15:26", "remaining_time": "6:02:26"}
{"current_steps": 1520, "total_steps": 3245, "loss": 0.0219, "lr": 6.406316463862467e-05, "epoch": 2.339361292804925, "percentage": 46.84, "elapsed_time": "5:16:53", "remaining_time": "5:59:37"}
{"current_steps": 1530, "total_steps": 3245, "loss": 0.0145, "lr": 6.35461331822803e-05, "epoch": 2.3547518276260098, "percentage": 47.15, "elapsed_time": "5:18:20", "remaining_time": "5:56:50"}
{"current_steps": 1540, "total_steps": 3245, "loss": 0.0184, "lr": 6.302753372905515e-05, "epoch": 2.370142362447095, "percentage": 47.46, "elapsed_time": "5:19:47", "remaining_time": "5:54:03"}
{"current_steps": 1550, "total_steps": 3245, "loss": 0.015, "lr": 6.250742630805971e-05, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:21:14", "remaining_time": "5:51:18"}
{"current_steps": 1550, "total_steps": 3245, "eval_loss": 0.0370011031627655, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:24:16", "remaining_time": "5:54:36"}
{"current_steps": 1560, "total_steps": 3245, "loss": 0.0137, "lr": 6.198587112295526e-05, "epoch": 2.400923432089265, "percentage": 48.07, "elapsed_time": "5:25:48", "remaining_time": "5:51:55"}
{"current_steps": 1570, "total_steps": 3245, "loss": 0.0177, "lr": 6.14629285449852e-05, "epoch": 2.41631396691035, "percentage": 48.38, "elapsed_time": "5:27:16", "remaining_time": "5:49:09"}
{"current_steps": 1580, "total_steps": 3245, "loss": 0.0177, "lr": 6.093865910598688e-05, "epoch": 2.431704501731435, "percentage": 48.69, "elapsed_time": "5:28:43", "remaining_time": "5:46:24"}
{"current_steps": 1590, "total_steps": 3245, "loss": 0.018, "lr": 6.0413123491385025e-05, "epoch": 2.44709503655252, "percentage": 49.0, "elapsed_time": "5:30:10", "remaining_time": "5:43:40"}
{"current_steps": 1600, "total_steps": 3245, "loss": 0.0139, "lr": 5.988638253316713e-05, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:31:37", "remaining_time": "5:40:56"}
{"current_steps": 1600, "total_steps": 3245, "eval_loss": 0.036044903099536896, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:34:39", "remaining_time": "5:44:03"}
{"current_steps": 1610, "total_steps": 3245, "loss": 0.0166, "lr": 5.935849720284206e-05, "epoch": 2.47787610619469, "percentage": 49.61, "elapsed_time": "5:36:10", "remaining_time": "5:41:23"}
{"current_steps": 1620, "total_steps": 3245, "loss": 0.0211, "lr": 5.8829528604382436e-05, "epoch": 2.4932666410157753, "percentage": 49.92, "elapsed_time": "5:37:37", "remaining_time": "5:38:39"}
{"current_steps": 1630, "total_steps": 3245, "loss": 0.0168, "lr": 5.829953796715176e-05, "epoch": 2.50865717583686, "percentage": 50.23, "elapsed_time": "5:39:04", "remaining_time": "5:35:57"}
{"current_steps": 1640, "total_steps": 3245, "loss": 0.0213, "lr": 5.7768586638816924e-05, "epoch": 2.5240477106579453, "percentage": 50.54, "elapsed_time": "5:40:30", "remaining_time": "5:33:14"}
{"current_steps": 1650, "total_steps": 3245, "loss": 0.0196, "lr": 5.723673607824705e-05, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:41:58", "remaining_time": "5:30:34"}
{"current_steps": 1650, "total_steps": 3245, "eval_loss": 0.0336180217564106, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:45:00", "remaining_time": "5:33:30"}
{"current_steps": 1660, "total_steps": 3245, "loss": 0.0111, "lr": 5.670404784839953e-05, "epoch": 2.5548287803001153, "percentage": 51.16, "elapsed_time": "5:46:31", "remaining_time": "5:30:52"}
{"current_steps": 1670, "total_steps": 3245, "loss": 0.0175, "lr": 5.6170583609193984e-05, "epoch": 2.5702193151212005, "percentage": 51.46, "elapsed_time": "5:47:58", "remaining_time": "5:28:10"}
{"current_steps": 1680, "total_steps": 3245, "loss": 0.0195, "lr": 5.56364051103749e-05, "epoch": 2.5856098499422853, "percentage": 51.77, "elapsed_time": "5:49:25", "remaining_time": "5:25:30"}
{"current_steps": 1690, "total_steps": 3245, "loss": 0.021, "lr": 5.5101574184364056e-05, "epoch": 2.6010003847633705, "percentage": 52.08, "elapsed_time": "5:50:52", "remaining_time": "5:22:50"}
{"current_steps": 1700, "total_steps": 3245, "loss": 0.0205, "lr": 5.4566152739103116e-05, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "5:52:19", "remaining_time": "5:20:12"}
{"current_steps": 1700, "total_steps": 3245, "eval_loss": 0.03435565531253815, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "5:55:21", "remaining_time": "5:22:57"}
{"current_steps": 1710, "total_steps": 3245, "loss": 0.0192, "lr": 5.403020275088786e-05, "epoch": 2.6317814544055405, "percentage": 52.7, "elapsed_time": "5:56:53", "remaining_time": "5:20:21"}
{"current_steps": 1720, "total_steps": 3245, "loss": 0.0268, "lr": 5.349378625719408e-05, "epoch": 2.6471719892266257, "percentage": 53.0, "elapsed_time": "5:58:20", "remaining_time": "5:17:42"}
{"current_steps": 1730, "total_steps": 3245, "loss": 0.0201, "lr": 5.2956965349496743e-05, "epoch": 2.6625625240477104, "percentage": 53.31, "elapsed_time": "5:59:47", "remaining_time": "5:15:04"}
{"current_steps": 1740, "total_steps": 3245, "loss": 0.0152, "lr": 5.241980216608261e-05, "epoch": 2.6779530588687956, "percentage": 53.62, "elapsed_time": "6:01:14", "remaining_time": "5:12:27"}
{"current_steps": 1750, "total_steps": 3245, "loss": 0.0229, "lr": 5.188235888485773e-05, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "6:02:41", "remaining_time": "5:09:50"}
{"current_steps": 1750, "total_steps": 3245, "eval_loss": 0.032898351550102234, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "6:05:43", "remaining_time": "5:12:25"}
{"current_steps": 1760, "total_steps": 3245, "loss": 0.0129, "lr": 5.13446977161501e-05, "epoch": 2.7087341285109656, "percentage": 54.24, "elapsed_time": "6:07:15", "remaining_time": "5:09:52"}
{"current_steps": 1770, "total_steps": 3245, "loss": 0.0173, "lr": 5.0806880895508766e-05, "epoch": 2.724124663332051, "percentage": 54.55, "elapsed_time": "6:08:42", "remaining_time": "5:07:15"}
{"current_steps": 1780, "total_steps": 3245, "loss": 0.0221, "lr": 5.026897067649976e-05, "epoch": 2.7395151981531356, "percentage": 54.85, "elapsed_time": "6:10:10", "remaining_time": "5:04:39"}
{"current_steps": 1790, "total_steps": 3245, "loss": 0.0175, "lr": 4.973102932350026e-05, "epoch": 2.754905732974221, "percentage": 55.16, "elapsed_time": "6:11:37", "remaining_time": "5:02:04"}
{"current_steps": 1800, "total_steps": 3245, "loss": 0.0184, "lr": 4.9193119104491245e-05, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:13:04", "remaining_time": "4:59:29"}
{"current_steps": 1800, "total_steps": 3245, "eval_loss": 0.03297585994005203, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:16:06", "remaining_time": "5:01:55"}
{"current_steps": 1810, "total_steps": 3245, "loss": 0.0186, "lr": 4.86553022838499e-05, "epoch": 2.785686802616391, "percentage": 55.78, "elapsed_time": "6:17:41", "remaining_time": "4:59:26"}
{"current_steps": 1820, "total_steps": 3245, "loss": 0.0217, "lr": 4.8117641115142285e-05, "epoch": 2.801077337437476, "percentage": 56.09, "elapsed_time": "6:19:09", "remaining_time": "4:56:51"}
{"current_steps": 1830, "total_steps": 3245, "loss": 0.0205, "lr": 4.758019783391741e-05, "epoch": 2.8164678722585608, "percentage": 56.39, "elapsed_time": "6:20:36", "remaining_time": "4:54:17"}
{"current_steps": 1840, "total_steps": 3245, "loss": 0.0204, "lr": 4.704303465050327e-05, "epoch": 2.831858407079646, "percentage": 56.7, "elapsed_time": "6:22:03", "remaining_time": "4:51:43"}
{"current_steps": 1850, "total_steps": 3245, "loss": 0.0192, "lr": 4.6506213742805924e-05, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:23:30", "remaining_time": "4:49:11"}
{"current_steps": 1850, "total_steps": 3245, "eval_loss": 0.03292803466320038, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:26:32", "remaining_time": "4:51:28"}
{"current_steps": 1860, "total_steps": 3245, "loss": 0.0146, "lr": 4.5969797249112146e-05, "epoch": 2.862639476721816, "percentage": 57.32, "elapsed_time": "6:28:04", "remaining_time": "4:48:58"}
{"current_steps": 1870, "total_steps": 3245, "loss": 0.0245, "lr": 4.54338472608969e-05, "epoch": 2.878030011542901, "percentage": 57.63, "elapsed_time": "6:29:32", "remaining_time": "4:46:25"}
{"current_steps": 1880, "total_steps": 3245, "loss": 0.0137, "lr": 4.489842581563597e-05, "epoch": 2.893420546363986, "percentage": 57.94, "elapsed_time": "6:30:59", "remaining_time": "4:43:52"}
{"current_steps": 1890, "total_steps": 3245, "loss": 0.0169, "lr": 4.436359488962511e-05, "epoch": 2.908811081185071, "percentage": 58.24, "elapsed_time": "6:32:26", "remaining_time": "4:41:21"}
{"current_steps": 1900, "total_steps": 3245, "loss": 0.0176, "lr": 4.382941639080602e-05, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:33:53", "remaining_time": "4:38:49"}
{"current_steps": 1900, "total_steps": 3245, "eval_loss": 0.03322253003716469, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:36:55", "remaining_time": "4:40:58"}
{"current_steps": 1910, "total_steps": 3245, "loss": 0.023, "lr": 4.3295952151600475e-05, "epoch": 2.939592150827241, "percentage": 58.86, "elapsed_time": "6:38:27", "remaining_time": "4:38:30"}
{"current_steps": 1920, "total_steps": 3245, "loss": 0.0187, "lr": 4.276326392175296e-05, "epoch": 2.9549826856483263, "percentage": 59.17, "elapsed_time": "6:39:54", "remaining_time": "4:35:58"}
{"current_steps": 1930, "total_steps": 3245, "loss": 0.0155, "lr": 4.2231413361183095e-05, "epoch": 2.970373220469411, "percentage": 59.48, "elapsed_time": "6:41:21", "remaining_time": "4:33:27"}
{"current_steps": 1940, "total_steps": 3245, "loss": 0.0134, "lr": 4.1700462032848244e-05, "epoch": 2.9857637552904963, "percentage": 59.78, "elapsed_time": "6:42:48", "remaining_time": "4:30:57"}
{"current_steps": 1950, "total_steps": 3245, "loss": 0.0235, "lr": 4.117047139561758e-05, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:44:15", "remaining_time": "4:28:28"}
{"current_steps": 1950, "total_steps": 3245, "eval_loss": 0.034495554864406586, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:47:17", "remaining_time": "4:30:29"}
{"current_steps": 1960, "total_steps": 3245, "loss": 0.0068, "lr": 4.0641502797157966e-05, "epoch": 3.0165448249326663, "percentage": 60.4, "elapsed_time": "6:48:49", "remaining_time": "4:28:01"}
{"current_steps": 1970, "total_steps": 3245, "loss": 0.0107, "lr": 4.011361746683288e-05, "epoch": 3.0319353597537515, "percentage": 60.71, "elapsed_time": "6:50:15", "remaining_time": "4:25:31"}
{"current_steps": 1980, "total_steps": 3245, "loss": 0.0084, "lr": 3.958687650861499e-05, "epoch": 3.0473258945748363, "percentage": 61.02, "elapsed_time": "6:51:42", "remaining_time": "4:23:02"}
{"current_steps": 1990, "total_steps": 3245, "loss": 0.0061, "lr": 3.906134089401313e-05, "epoch": 3.0627164293959215, "percentage": 61.33, "elapsed_time": "6:53:09", "remaining_time": "4:20:33"}
{"current_steps": 2000, "total_steps": 3245, "loss": 0.0092, "lr": 3.853707145501482e-05, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "6:54:37", "remaining_time": "4:18:05"}
{"current_steps": 2000, "total_steps": 3245, "eval_loss": 0.03834828734397888, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "6:57:39", "remaining_time": "4:19:59"}
{"current_steps": 2010, "total_steps": 3245, "loss": 0.0046, "lr": 3.801412887704475e-05, "epoch": 3.0934974990380915, "percentage": 61.94, "elapsed_time": "6:59:11", "remaining_time": "4:17:33"}
{"current_steps": 2020, "total_steps": 3245, "loss": 0.0095, "lr": 3.749257369194029e-05, "epoch": 3.1088880338591767, "percentage": 62.25, "elapsed_time": "7:00:38", "remaining_time": "4:15:05"}
{"current_steps": 2030, "total_steps": 3245, "loss": 0.0094, "lr": 3.697246627094487e-05, "epoch": 3.1242785686802614, "percentage": 62.56, "elapsed_time": "7:02:05", "remaining_time": "4:12:37"}
{"current_steps": 2040, "total_steps": 3245, "loss": 0.009, "lr": 3.6453866817719726e-05, "epoch": 3.1396691035013466, "percentage": 62.87, "elapsed_time": "7:03:32", "remaining_time": "4:10:10"}
{"current_steps": 2050, "total_steps": 3245, "loss": 0.012, "lr": 3.593683536137533e-05, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:04:59", "remaining_time": "4:07:44"}
{"current_steps": 2050, "total_steps": 3245, "eval_loss": 0.041652098298072815, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:08:01", "remaining_time": "4:09:30"}
{"current_steps": 2060, "total_steps": 3245, "loss": 0.0061, "lr": 3.542143174952282e-05, "epoch": 3.1704501731435166, "percentage": 63.48, "elapsed_time": "7:09:33", "remaining_time": "4:07:06"}
{"current_steps": 2070, "total_steps": 3245, "loss": 0.0071, "lr": 3.490771564134643e-05, "epoch": 3.185840707964602, "percentage": 63.79, "elapsed_time": "7:11:00", "remaining_time": "4:04:39"}
{"current_steps": 2080, "total_steps": 3245, "loss": 0.0089, "lr": 3.4395746500697925e-05, "epoch": 3.2012312427856866, "percentage": 64.1, "elapsed_time": "7:12:28", "remaining_time": "4:02:13"}
{"current_steps": 2090, "total_steps": 3245, "loss": 0.0102, "lr": 3.388558358921343e-05, "epoch": 3.216621777606772, "percentage": 64.41, "elapsed_time": "7:13:55", "remaining_time": "3:59:47"}
{"current_steps": 2100, "total_steps": 3245, "loss": 0.0077, "lr": 3.337728595945378e-05, "epoch": 3.232012312427857, "percentage": 64.71, "elapsed_time": "7:15:22", "remaining_time": "3:57:22"}
{"current_steps": 2100, "total_steps": 3245, "eval_loss": 0.03836505860090256, "epoch": 3.232012312427857, "percentage": 64.71, "elapsed_time": "7:18:24", "remaining_time": "3:59:02"}
{"current_steps": 2110, "total_steps": 3245, "loss": 0.0082, "lr": 3.287091244806907e-05, "epoch": 3.247402847248942, "percentage": 65.02, "elapsed_time": "7:19:56", "remaining_time": "3:56:38"}
{"current_steps": 2120, "total_steps": 3245, "loss": 0.0089, "lr": 3.2366521668988106e-05, "epoch": 3.262793382070027, "percentage": 65.33, "elapsed_time": "7:21:23", "remaining_time": "3:54:13"}
{"current_steps": 2130, "total_steps": 3245, "loss": 0.0086, "lr": 3.186417200663379e-05, "epoch": 3.2781839168911118, "percentage": 65.64, "elapsed_time": "7:22:50", "remaining_time": "3:51:48"}
{"current_steps": 2140, "total_steps": 3245, "loss": 0.0065, "lr": 3.136392160916495e-05, "epoch": 3.293574451712197, "percentage": 65.95, "elapsed_time": "7:24:17", "remaining_time": "3:49:24"}
{"current_steps": 2150, "total_steps": 3245, "loss": 0.0068, "lr": 3.086582838174551e-05, "epoch": 3.308964986533282, "percentage": 66.26, "elapsed_time": "7:25:44", "remaining_time": "3:47:01"}
{"current_steps": 2150, "total_steps": 3245, "eval_loss": 0.039253655821084976, "epoch": 3.308964986533282, "percentage": 66.26, "elapsed_time": "7:28:46", "remaining_time": "3:48:33"}
{"current_steps": 2160, "total_steps": 3245, "loss": 0.0079, "lr": 3.036994997984194e-05, "epoch": 3.324355521354367, "percentage": 66.56, "elapsed_time": "7:30:18", "remaining_time": "3:46:11"}
{"current_steps": 2170, "total_steps": 3245, "loss": 0.0108, "lr": 2.9876343802549357e-05, "epoch": 3.339746056175452, "percentage": 66.87, "elapsed_time": "7:31:46", "remaining_time": "3:43:48"}
{"current_steps": 2180, "total_steps": 3245, "loss": 0.0091, "lr": 2.938506698594755e-05, "epoch": 3.355136590996537, "percentage": 67.18, "elapsed_time": "7:33:13", "remaining_time": "3:41:24"}
{"current_steps": 2190, "total_steps": 3245, "loss": 0.006, "lr": 2.8896176396487334e-05, "epoch": 3.370527125817622, "percentage": 67.49, "elapsed_time": "7:34:40", "remaining_time": "3:39:02"}
{"current_steps": 2200, "total_steps": 3245, "loss": 0.0121, "lr": 2.8409728624408067e-05, "epoch": 3.3859176606387074, "percentage": 67.8, "elapsed_time": "7:36:08", "remaining_time": "3:36:39"}
{"current_steps": 2200, "total_steps": 3245, "eval_loss": 0.03834627568721771, "epoch": 3.3859176606387074, "percentage": 67.8, "elapsed_time": "7:39:10", "remaining_time": "3:38:06"}
{"current_steps": 2210, "total_steps": 3245, "loss": 0.0096, "lr": 2.7925779977187215e-05, "epoch": 3.401308195459792, "percentage": 68.1, "elapsed_time": "7:40:41", "remaining_time": "3:35:45"}
{"current_steps": 2220, "total_steps": 3245, "loss": 0.0064, "lr": 2.7444386473022686e-05, "epoch": 3.4166987302808773, "percentage": 68.41, "elapsed_time": "7:42:09", "remaining_time": "3:33:23"}
{"current_steps": 2230, "total_steps": 3245, "loss": 0.0107, "lr": 2.696560383434854e-05, "epoch": 3.432089265101962, "percentage": 68.72, "elapsed_time": "7:43:36", "remaining_time": "3:31:00"}
{"current_steps": 2240, "total_steps": 3245, "loss": 0.011, "lr": 2.6489487481384988e-05, "epoch": 3.4474797999230473, "percentage": 69.03, "elapsed_time": "7:45:03", "remaining_time": "3:28:39"}
{"current_steps": 2250, "total_steps": 3245, "loss": 0.0077, "lr": 2.601609252572339e-05, "epoch": 3.4628703347441325, "percentage": 69.34, "elapsed_time": "7:46:30", "remaining_time": "3:26:18"}
{"current_steps": 2250, "total_steps": 3245, "eval_loss": 0.03682588040828705, "epoch": 3.4628703347441325, "percentage": 69.34, "elapsed_time": "7:49:32", "remaining_time": "3:27:38"}
{"current_steps": 2260, "total_steps": 3245, "loss": 0.0072, "lr": 2.554547376394692e-05, "epoch": 3.4782608695652173, "percentage": 69.65, "elapsed_time": "7:51:04", "remaining_time": "3:25:18"}
{"current_steps": 2270, "total_steps": 3245, "loss": 0.0052, "lr": 2.5077685671287808e-05, "epoch": 3.4936514043863025, "percentage": 69.95, "elapsed_time": "7:52:31", "remaining_time": "3:22:57"}
{"current_steps": 2280, "total_steps": 3245, "loss": 0.0076, "lr": 2.4612782395321593e-05, "epoch": 3.5090419392073873, "percentage": 70.26, "elapsed_time": "7:53:58", "remaining_time": "3:20:36"}
{"current_steps": 2290, "total_steps": 3245, "loss": 0.0056, "lr": 2.4150817749699496e-05, "epoch": 3.5244324740284725, "percentage": 70.57, "elapsed_time": "7:55:25", "remaining_time": "3:18:15"}
{"current_steps": 2300, "total_steps": 3245, "loss": 0.0115, "lr": 2.3691845207919357e-05, "epoch": 3.5398230088495577, "percentage": 70.88, "elapsed_time": "7:56:52", "remaining_time": "3:15:55"}
{"current_steps": 2300, "total_steps": 3245, "eval_loss": 0.03893190994858742, "epoch": 3.5398230088495577, "percentage": 70.88, "elapsed_time": "7:59:55", "remaining_time": "3:17:11"}
{"current_steps": 2310, "total_steps": 3245, "loss": 0.0097, "lr": 2.3235917897135934e-05, "epoch": 3.5552135436706425, "percentage": 71.19, "elapsed_time": "8:01:27", "remaining_time": "3:14:52"}
{"current_steps": 2320, "total_steps": 3245, "loss": 0.0093, "lr": 2.2783088592011303e-05, "epoch": 3.5706040784917277, "percentage": 71.49, "elapsed_time": "8:02:54", "remaining_time": "3:12:32"}
{"current_steps": 2330, "total_steps": 3245, "loss": 0.0074, "lr": 2.233340970860608e-05, "epoch": 3.5859946133128124, "percentage": 71.8, "elapsed_time": "8:04:21", "remaining_time": "3:10:12"}
{"current_steps": 2340, "total_steps": 3245, "loss": 0.0134, "lr": 2.1886933298312125e-05, "epoch": 3.6013851481338977, "percentage": 72.11, "elapsed_time": "8:05:49", "remaining_time": "3:07:53"}
{"current_steps": 2350, "total_steps": 3245, "loss": 0.0061, "lr": 2.1443711041827503e-05, "epoch": 3.616775682954983, "percentage": 72.42, "elapsed_time": "8:07:16", "remaining_time": "3:05:34"}
{"current_steps": 2350, "total_steps": 3245, "eval_loss": 0.03987393528223038, "epoch": 3.616775682954983, "percentage": 72.42, "elapsed_time": "8:10:18", "remaining_time": "3:06:44"}
{"current_steps": 2360, "total_steps": 3245, "loss": 0.0145, "lr": 2.1003794243174252e-05, "epoch": 3.6321662177760676, "percentage": 72.73, "elapsed_time": "8:11:50", "remaining_time": "3:04:26"}
{"current_steps": 2370, "total_steps": 3245, "loss": 0.0088, "lr": 2.0567233823759886e-05, "epoch": 3.647556752597153, "percentage": 73.04, "elapsed_time": "8:13:18", "remaining_time": "3:02:07"}
{"current_steps": 2380, "total_steps": 3245, "loss": 0.0095, "lr": 2.0134080316483113e-05, "epoch": 3.6629472874182376, "percentage": 73.34, "elapsed_time": "8:14:45", "remaining_time": "2:59:48"}
{"current_steps": 2390, "total_steps": 3245, "loss": 0.0118, "lr": 1.970438385988452e-05, "epoch": 3.678337822239323, "percentage": 73.65, "elapsed_time": "8:16:12", "remaining_time": "2:57:30"}
{"current_steps": 2400, "total_steps": 3245, "loss": 0.0132, "lr": 1.927819419234292e-05, "epoch": 3.693728357060408, "percentage": 73.96, "elapsed_time": "8:17:39", "remaining_time": "2:55:13"}
{"current_steps": 2400, "total_steps": 3245, "eval_loss": 0.036747824400663376, "epoch": 3.693728357060408, "percentage": 73.96, "elapsed_time": "8:20:42", "remaining_time": "2:56:17"}
{"current_steps": 2410, "total_steps": 3245, "loss": 0.0083, "lr": 1.885556064631801e-05, "epoch": 3.709118891881493, "percentage": 74.27, "elapsed_time": "8:22:16", "remaining_time": "2:54:01"}
{"current_steps": 2420, "total_steps": 3245, "loss": 0.0068, "lr": 1.843653214264003e-05, "epoch": 3.724509426702578, "percentage": 74.58, "elapsed_time": "8:23:42", "remaining_time": "2:51:43"}
{"current_steps": 2430, "total_steps": 3245, "loss": 0.0097, "lr": 1.8021157184847087e-05, "epoch": 3.7398999615236628, "percentage": 74.88, "elapsed_time": "8:25:10", "remaining_time": "2:49:25"}
{"current_steps": 2440, "total_steps": 3245, "loss": 0.006, "lr": 1.7609483853570668e-05, "epoch": 3.755290496344748, "percentage": 75.19, "elapsed_time": "8:26:37", "remaining_time": "2:47:08"}
{"current_steps": 2450, "total_steps": 3245, "loss": 0.0066, "lr": 1.720155980097034e-05, "epoch": 3.770681031165833, "percentage": 75.5, "elapsed_time": "8:28:04", "remaining_time": "2:44:51"}
{"current_steps": 2450, "total_steps": 3245, "eval_loss": 0.03801007568836212, "epoch": 3.770681031165833, "percentage": 75.5, "elapsed_time": "8:31:06", "remaining_time": "2:45:51"}
{"current_steps": 2460, "total_steps": 3245, "loss": 0.0075, "lr": 1.6797432245217736e-05, "epoch": 3.786071565986918, "percentage": 75.81, "elapsed_time": "8:32:38", "remaining_time": "2:43:35"}
{"current_steps": 2470, "total_steps": 3245, "loss": 0.0051, "lr": 1.6397147965031072e-05, "epoch": 3.801462100808003, "percentage": 76.12, "elapsed_time": "8:34:05", "remaining_time": "2:41:18"}
{"current_steps": 2480, "total_steps": 3245, "loss": 0.0117, "lr": 1.600075329426033e-05, "epoch": 3.816852635629088, "percentage": 76.43, "elapsed_time": "8:35:33", "remaining_time": "2:39:01"}
{"current_steps": 2490, "total_steps": 3245, "loss": 0.0092, "lr": 1.560829411652403e-05, "epoch": 3.832243170450173, "percentage": 76.73, "elapsed_time": "8:37:00", "remaining_time": "2:36:45"}
{"current_steps": 2500, "total_steps": 3245, "loss": 0.0076, "lr": 1.521981585989809e-05, "epoch": 3.8476337052712584, "percentage": 77.04, "elapsed_time": "8:38:27", "remaining_time": "2:34:29"}
{"current_steps": 2500, "total_steps": 3245, "eval_loss": 0.03867095336318016, "epoch": 3.8476337052712584, "percentage": 77.04, "elapsed_time": "8:41:29", "remaining_time": "2:35:24"}
{"current_steps": 2510, "total_steps": 3245, "loss": 0.0104, "lr": 1.4835363491657412e-05, "epoch": 3.863024240092343, "percentage": 77.35, "elapsed_time": "8:43:02", "remaining_time": "2:33:09"}
{"current_steps": 2520, "total_steps": 3245, "loss": 0.0043, "lr": 1.4454981513070791e-05, "epoch": 3.8784147749134283, "percentage": 77.66, "elapsed_time": "8:44:29", "remaining_time": "2:30:53"}
{"current_steps": 2530, "total_steps": 3245, "loss": 0.0057, "lr": 1.4078713954249873e-05, "epoch": 3.893805309734513, "percentage": 77.97, "elapsed_time": "8:45:56", "remaining_time": "2:28:38"}
{"current_steps": 2540, "total_steps": 3245, "loss": 0.0039, "lr": 1.3706604369052434e-05, "epoch": 3.9091958445555983, "percentage": 78.27, "elapsed_time": "8:47:24", "remaining_time": "2:26:23"}
{"current_steps": 2550, "total_steps": 3245, "loss": 0.0087, "lr": 1.3338695830041047e-05, "epoch": 3.9245863793766835, "percentage": 78.58, "elapsed_time": "8:48:51", "remaining_time": "2:24:08"}
{"current_steps": 2550, "total_steps": 3245, "eval_loss": 0.0398300401866436, "epoch": 3.9245863793766835, "percentage": 78.58, "elapsed_time": "8:51:54", "remaining_time": "2:24:58"}
{"current_steps": 2560, "total_steps": 3245, "loss": 0.0072, "lr": 1.2975030923497262e-05, "epoch": 3.9399769141977683, "percentage": 78.89, "elapsed_time": "8:53:26", "remaining_time": "2:22:44"}
{"current_steps": 2570, "total_steps": 3245, "loss": 0.0065, "lr": 1.2615651744492151e-05, "epoch": 3.9553674490188535, "percentage": 79.2, "elapsed_time": "8:54:53", "remaining_time": "2:20:29"}
{"current_steps": 2580, "total_steps": 3245, "loss": 0.0118, "lr": 1.2260599892013719e-05, "epoch": 3.9707579838399383, "percentage": 79.51, "elapsed_time": "8:56:20", "remaining_time": "2:18:14"}
{"current_steps": 2590, "total_steps": 3245, "loss": 0.0082, "lr": 1.1909916464151715e-05, "epoch": 3.9861485186610235, "percentage": 79.82, "elapsed_time": "8:57:48", "remaining_time": "2:16:00"}
{"current_steps": 2600, "total_steps": 3245, "loss": 0.0094, "lr": 1.1563642053340406e-05, "epoch": 4.001539053482109, "percentage": 80.12, "elapsed_time": "8:59:15", "remaining_time": "2:13:46"}
{"current_steps": 2600, "total_steps": 3245, "eval_loss": 0.03990135341882706, "epoch": 4.001539053482109, "percentage": 80.12, "elapsed_time": "9:02:17", "remaining_time": "2:14:31"}
{"current_steps": 2610, "total_steps": 3245, "loss": 0.0036, "lr": 1.1221816741659964e-05, "epoch": 4.016929588303194, "percentage": 80.43, "elapsed_time": "9:03:50", "remaining_time": "2:12:18"}
{"current_steps": 2620, "total_steps": 3245, "loss": 0.0024, "lr": 1.0884480096196803e-05, "epoch": 4.032320123124278, "percentage": 80.74, "elapsed_time": "9:05:17", "remaining_time": "2:10:04"}
{"current_steps": 2630, "total_steps": 3245, "loss": 0.002, "lr": 1.0551671164463666e-05, "epoch": 4.047710657945363, "percentage": 81.05, "elapsed_time": "9:06:44", "remaining_time": "2:07:51"}
{"current_steps": 2640, "total_steps": 3245, "loss": 0.0054, "lr": 1.0223428469879736e-05, "epoch": 4.063101192766449, "percentage": 81.36, "elapsed_time": "9:08:11", "remaining_time": "2:05:37"}
{"current_steps": 2650, "total_steps": 3245, "loss": 0.0024, "lr": 9.899790007311455e-06, "epoch": 4.078491727587534, "percentage": 81.66, "elapsed_time": "9:09:38", "remaining_time": "2:03:24"}
{"current_steps": 2650, "total_steps": 3245, "eval_loss": 0.041614893823862076, "epoch": 4.078491727587534, "percentage": 81.66, "elapsed_time": "9:12:41", "remaining_time": "2:04:05"}
{"current_steps": 2660, "total_steps": 3245, "loss": 0.0051, "lr": 9.580793238674573e-06, "epoch": 4.093882262408619, "percentage": 81.97, "elapsed_time": "9:14:12", "remaining_time": "2:01:53"}
{"current_steps": 2670, "total_steps": 3245, "loss": 0.0024, "lr": 9.266475088597781e-06, "epoch": 4.109272797229703, "percentage": 82.28, "elapsed_time": "9:15:40", "remaining_time": "1:59:40"}
{"current_steps": 2680, "total_steps": 3245, "loss": 0.0029, "lr": 8.956871940148681e-06, "epoch": 4.124663332050789, "percentage": 82.59, "elapsed_time": "9:17:07", "remaining_time": "1:57:27"}
{"current_steps": 2690, "total_steps": 3245, "loss": 0.0051, "lr": 8.65201963062225e-06, "epoch": 4.140053866871874, "percentage": 82.9, "elapsed_time": "9:18:33", "remaining_time": "1:55:14"}
{"current_steps": 2700, "total_steps": 3245, "loss": 0.0077, "lr": 8.351953447392674e-06, "epoch": 4.155444401692959, "percentage": 83.2, "elapsed_time": "9:20:00", "remaining_time": "1:53:02"}
{"current_steps": 2700, "total_steps": 3245, "eval_loss": 0.04621283337473869, "epoch": 4.155444401692959, "percentage": 83.2, "elapsed_time": "9:23:03", "remaining_time": "1:53:39"}
{"current_steps": 2710, "total_steps": 3245, "loss": 0.0037, "lr": 8.056708123828738e-06, "epoch": 4.170834936514044, "percentage": 83.51, "elapsed_time": "9:24:35", "remaining_time": "1:51:27"}
{"current_steps": 2720, "total_steps": 3245, "loss": 0.008, "lr": 7.76631783527334e-06, "epoch": 4.186225471335129, "percentage": 83.82, "elapsed_time": "9:26:02", "remaining_time": "1:49:15"}
{"current_steps": 2730, "total_steps": 3245, "loss": 0.0039, "lr": 7.4808161950876145e-06, "epoch": 4.201616006156214, "percentage": 84.13, "elapsed_time": "9:27:29", "remaining_time": "1:47:03"}
{"current_steps": 2740, "total_steps": 3245, "loss": 0.004, "lr": 7.200236250760111e-06, "epoch": 4.217006540977299, "percentage": 84.44, "elapsed_time": "9:28:57", "remaining_time": "1:44:51"}
{"current_steps": 2750, "total_steps": 3245, "loss": 0.0018, "lr": 6.924610480081478e-06, "epoch": 4.232397075798384, "percentage": 84.75, "elapsed_time": "9:30:24", "remaining_time": "1:42:40"}
{"current_steps": 2750, "total_steps": 3245, "eval_loss": 0.04548865929245949, "epoch": 4.232397075798384, "percentage": 84.75, "elapsed_time": "9:33:27", "remaining_time": "1:43:13"}
{"current_steps": 2760, "total_steps": 3245, "loss": 0.0019, "lr": 6.6539707873850774e-06, "epoch": 4.247787610619469, "percentage": 85.05, "elapsed_time": "9:34:59", "remaining_time": "1:41:02"}
{"current_steps": 2770, "total_steps": 3245, "loss": 0.0021, "lr": 6.3883484998539525e-06, "epoch": 4.263178145440554, "percentage": 85.36, "elapsed_time": "9:36:26", "remaining_time": "1:38:50"}
{"current_steps": 2780, "total_steps": 3245, "loss": 0.0027, "lr": 6.127774363894667e-06, "epoch": 4.278568680261639, "percentage": 85.67, "elapsed_time": "9:37:53", "remaining_time": "1:36:39"}
{"current_steps": 2790, "total_steps": 3245, "loss": 0.0034, "lr": 5.872278541578352e-06, "epoch": 4.293959215082724, "percentage": 85.98, "elapsed_time": "9:39:20", "remaining_time": "1:34:28"}
{"current_steps": 2800, "total_steps": 3245, "loss": 0.0021, "lr": 5.6218906071493275e-06, "epoch": 4.309349749903809, "percentage": 86.29, "elapsed_time": "9:40:47", "remaining_time": "1:32:18"}
{"current_steps": 2800, "total_steps": 3245, "eval_loss": 0.04689283296465874, "epoch": 4.309349749903809, "percentage": 86.29, "elapsed_time": "9:43:50", "remaining_time": "1:32:47"}
{"current_steps": 2810, "total_steps": 3245, "loss": 0.0029, "lr": 5.376639543601858e-06, "epoch": 4.324740284724895, "percentage": 86.59, "elapsed_time": "9:45:22", "remaining_time": "1:30:37"}
{"current_steps": 2820, "total_steps": 3245, "loss": 0.0015, "lr": 5.136553739325256e-06, "epoch": 4.340130819545979, "percentage": 86.9, "elapsed_time": "9:46:49", "remaining_time": "1:28:26"}
{"current_steps": 2830, "total_steps": 3245, "loss": 0.0021, "lr": 4.901660984817908e-06, "epoch": 4.355521354367064, "percentage": 87.21, "elapsed_time": "9:48:16", "remaining_time": "1:26:16"}
{"current_steps": 2840, "total_steps": 3245, "loss": 0.0024, "lr": 4.671988469470434e-06, "epoch": 4.370911889188149, "percentage": 87.52, "elapsed_time": "9:49:44", "remaining_time": "1:24:05"}
{"current_steps": 2850, "total_steps": 3245, "loss": 0.0026, "lr": 4.447562778418435e-06, "epoch": 4.3863024240092345, "percentage": 87.83, "elapsed_time": "9:51:11", "remaining_time": "1:21:56"}
{"current_steps": 2850, "total_steps": 3245, "eval_loss": 0.048040326684713364, "epoch": 4.3863024240092345, "percentage": 87.83, "elapsed_time": "9:54:13", "remaining_time": "1:22:21"}
{"current_steps": 2860, "total_steps": 3245, "loss": 0.0022, "lr": 4.228409889465218e-06, "epoch": 4.40169295883032, "percentage": 88.14, "elapsed_time": "9:55:45", "remaining_time": "1:20:11"}
{"current_steps": 2870, "total_steps": 3245, "loss": 0.0013, "lr": 4.014555170074824e-06, "epoch": 4.417083493651404, "percentage": 88.44, "elapsed_time": "9:57:12", "remaining_time": "1:18:02"}
{"current_steps": 2880, "total_steps": 3245, "loss": 0.0074, "lr": 3.8060233744356633e-06, "epoch": 4.432474028472489, "percentage": 88.75, "elapsed_time": "9:58:40", "remaining_time": "1:15:52"}
{"current_steps": 2890, "total_steps": 3245, "loss": 0.0039, "lr": 3.602838640595152e-06, "epoch": 4.4478645632935745, "percentage": 89.06, "elapsed_time": "10:00:07", "remaining_time": "1:13:43"}
{"current_steps": 2900, "total_steps": 3245, "loss": 0.0043, "lr": 3.4050244876656866e-06, "epoch": 4.46325509811466, "percentage": 89.37, "elapsed_time": "10:01:34", "remaining_time": "1:11:33"}
{"current_steps": 2900, "total_steps": 3245, "eval_loss": 0.04885905236005783, "epoch": 4.46325509811466, "percentage": 89.37, "elapsed_time": "10:04:36", "remaining_time": "1:11:55"}
{"current_steps": 2910, "total_steps": 3245, "loss": 0.0073, "lr": 3.2126038131022552e-06, "epoch": 4.478645632935745, "percentage": 89.68, "elapsed_time": "10:06:08", "remaining_time": "1:09:46"}
{"current_steps": 2920, "total_steps": 3245, "loss": 0.0041, "lr": 3.025598890051995e-06, "epoch": 4.494036167756829, "percentage": 89.98, "elapsed_time": "10:07:36", "remaining_time": "1:07:37"}
{"current_steps": 2930, "total_steps": 3245, "loss": 0.0033, "lr": 2.8440313647760288e-06, "epoch": 4.5094267025779144, "percentage": 90.29, "elapsed_time": "10:09:03", "remaining_time": "1:05:28"}
{"current_steps": 2940, "total_steps": 3245, "loss": 0.0058, "lr": 2.6679222541438397e-06, "epoch": 4.524817237399, "percentage": 90.6, "elapsed_time": "10:10:30", "remaining_time": "1:03:20"}
{"current_steps": 2950, "total_steps": 3245, "loss": 0.0018, "lr": 2.4972919432005582e-06, "epoch": 4.540207772220085, "percentage": 90.91, "elapsed_time": "10:11:57", "remaining_time": "1:01:11"}
{"current_steps": 2950, "total_steps": 3245, "eval_loss": 0.047888416796922684, "epoch": 4.540207772220085, "percentage": 90.91, "elapsed_time": "10:15:00", "remaining_time": "1:01:30"}
{"current_steps": 2960, "total_steps": 3245, "loss": 0.0011, "lr": 2.3321601828073135e-06, "epoch": 4.555598307041169, "percentage": 91.22, "elapsed_time": "10:16:31", "remaining_time": "0:59:21"}
{"current_steps": 2970, "total_steps": 3245, "loss": 0.0072, "lr": 2.1725460873550317e-06, "epoch": 4.570988841862254, "percentage": 91.53, "elapsed_time": "10:17:58", "remaining_time": "0:57:13"}
{"current_steps": 2980, "total_steps": 3245, "loss": 0.0023, "lr": 2.0184681325519096e-06, "epoch": 4.58637937668334, "percentage": 91.83, "elapsed_time": "10:19:25", "remaining_time": "0:55:05"}
{"current_steps": 2990, "total_steps": 3245, "loss": 0.0043, "lr": 1.869944153284786e-06, "epoch": 4.601769911504425, "percentage": 92.14, "elapsed_time": "10:20:52", "remaining_time": "0:52:57"}
{"current_steps": 3000, "total_steps": 3245, "loss": 0.0034, "lr": 1.7269913415547456e-06, "epoch": 4.61716044632551, "percentage": 92.45, "elapsed_time": "10:22:20", "remaining_time": "0:50:49"}
{"current_steps": 3000, "total_steps": 3245, "eval_loss": 0.04794705659151077, "epoch": 4.61716044632551, "percentage": 92.45, "elapsed_time": "10:25:22", "remaining_time": "0:51:04"}
{"current_steps": 3010, "total_steps": 3245, "loss": 0.0026, "lr": 1.589626244487069e-06, "epoch": 4.632550981146595, "percentage": 92.76, "elapsed_time": "10:26:54", "remaining_time": "0:48:56"}
{"current_steps": 3020, "total_steps": 3245, "loss": 0.0031, "lr": 1.4578647624158726e-06, "epoch": 4.64794151596768, "percentage": 93.07, "elapsed_time": "10:28:21", "remaining_time": "0:46:48"}
{"current_steps": 3030, "total_steps": 3245, "loss": 0.0051, "lr": 1.3317221470436293e-06, "epoch": 4.663332050788765, "percentage": 93.37, "elapsed_time": "10:29:48", "remaining_time": "0:44:41"}
{"current_steps": 3040, "total_steps": 3245, "loss": 0.0036, "lr": 1.2112129996757315e-06, "epoch": 4.67872258560985, "percentage": 93.68, "elapsed_time": "10:31:16", "remaining_time": "0:42:34"}
{"current_steps": 3050, "total_steps": 3245, "loss": 0.0037, "lr": 1.0963512695303546e-06, "epoch": 4.694113120430935, "percentage": 93.99, "elapsed_time": "10:32:43", "remaining_time": "0:40:27"}
{"current_steps": 3050, "total_steps": 3245, "eval_loss": 0.048097576946020126, "epoch": 4.694113120430935, "percentage": 93.99, "elapsed_time": "10:35:46", "remaining_time": "0:40:38"}
{"current_steps": 3060, "total_steps": 3245, "loss": 0.0021, "lr": 9.871502521237975e-07, "epoch": 4.7095036552520195, "percentage": 94.3, "elapsed_time": "10:37:17", "remaining_time": "0:38:31"}
{"current_steps": 3070, "total_steps": 3245, "loss": 0.0031, "lr": 8.83622587731514e-07, "epoch": 4.724894190073105, "percentage": 94.61, "elapsed_time": "10:38:45", "remaining_time": "0:36:24"}
{"current_steps": 3080, "total_steps": 3245, "loss": 0.0078, "lr": 7.857802599249564e-07, "epoch": 4.74028472489419, "percentage": 94.92, "elapsed_time": "10:40:12", "remaining_time": "0:34:17"}
{"current_steps": 3090, "total_steps": 3245, "loss": 0.0028, "lr": 6.936345941844335e-07, "epoch": 4.755675259715275, "percentage": 95.22, "elapsed_time": "10:41:38", "remaining_time": "0:32:11"}
{"current_steps": 3100, "total_steps": 3245, "loss": 0.0037, "lr": 6.071962565881939e-07, "epoch": 4.77106579453636, "percentage": 95.53, "elapsed_time": "10:43:06", "remaining_time": "0:30:04"}
{"current_steps": 3100, "total_steps": 3245, "eval_loss": 0.048036374151706696, "epoch": 4.77106579453636, "percentage": 95.53, "elapsed_time": "10:46:08", "remaining_time": "0:30:13"}
{"current_steps": 3110, "total_steps": 3245, "loss": 0.0073, "lr": 5.264752525777961e-07, "epoch": 4.786456329357446, "percentage": 95.84, "elapsed_time": "10:47:41", "remaining_time": "0:28:06"}
{"current_steps": 3120, "total_steps": 3245, "loss": 0.0039, "lr": 4.5148092579991863e-07, "epoch": 4.80184686417853, "percentage": 96.15, "elapsed_time": "10:49:07", "remaining_time": "0:26:00"}
{"current_steps": 3130, "total_steps": 3245, "loss": 0.006, "lr": 3.822219570248531e-07, "epoch": 4.817237398999615, "percentage": 96.46, "elapsed_time": "10:50:34", "remaining_time": "0:23:54"}
{"current_steps": 3140, "total_steps": 3245, "loss": 0.002, "lr": 3.187063631416742e-07, "epoch": 4.8326279338207, "percentage": 96.76, "elapsed_time": "10:52:00", "remaining_time": "0:21:48"}
{"current_steps": 3150, "total_steps": 3245, "loss": 0.0036, "lr": 2.6094149623024365e-07, "epoch": 4.8480184686417855, "percentage": 97.07, "elapsed_time": "10:53:26", "remaining_time": "0:19:42"}
{"current_steps": 3150, "total_steps": 3245, "eval_loss": 0.04801381751894951, "epoch": 4.8480184686417855, "percentage": 97.07, "elapsed_time": "10:56:27", "remaining_time": "0:19:47"}
{"current_steps": 3160, "total_steps": 3245, "loss": 0.003, "lr": 2.0893404271022376e-07, "epoch": 4.86340900346287, "percentage": 97.38, "elapsed_time": "10:57:58", "remaining_time": "0:17:41"}
{"current_steps": 3170, "total_steps": 3245, "loss": 0.003, "lr": 1.626900225670691e-07, "epoch": 4.878799538283955, "percentage": 97.69, "elapsed_time": "10:59:24", "remaining_time": "0:15:36"}
{"current_steps": 3180, "total_steps": 3245, "loss": 0.0026, "lr": 1.2221478865524493e-07, "epoch": 4.89419007310504, "percentage": 98.0, "elapsed_time": "11:00:50", "remaining_time": "0:13:30"}
{"current_steps": 3190, "total_steps": 3245, "loss": 0.0045, "lr": 8.751302607857836e-08, "epoch": 4.9095806079261255, "percentage": 98.31, "elapsed_time": "11:02:16", "remaining_time": "0:11:25"}
{"current_steps": 3200, "total_steps": 3245, "loss": 0.0027, "lr": 5.8588751647975506e-08, "epoch": 4.924971142747211, "percentage": 98.61, "elapsed_time": "11:03:42", "remaining_time": "0:09:19"}
{"current_steps": 3200, "total_steps": 3245, "eval_loss": 0.04795505106449127, "epoch": 4.924971142747211, "percentage": 98.61, "elapsed_time": "11:06:42", "remaining_time": "0:09:22"}
{"current_steps": 3210, "total_steps": 3245, "loss": 0.0031, "lr": 3.544531341646007e-08, "epoch": 4.940361677568296, "percentage": 98.92, "elapsed_time": "11:08:15", "remaining_time": "0:07:17"}
{"current_steps": 3220, "total_steps": 3245, "loss": 0.0019, "lr": 1.808539029161116e-08, "epoch": 4.95575221238938, "percentage": 99.23, "elapsed_time": "11:09:42", "remaining_time": "0:05:11"}
{"current_steps": 3230, "total_steps": 3245, "loss": 0.0055, "lr": 6.510991725500182e-09, "epoch": 4.9711427472104655, "percentage": 99.54, "elapsed_time": "11:11:09", "remaining_time": "0:03:07"}
{"current_steps": 3240, "total_steps": 3245, "loss": 0.0017, "lr": 7.234574820769169e-10, "epoch": 4.986533282031551, "percentage": 99.85, "elapsed_time": "11:12:36", "remaining_time": "0:01:02"}
{"current_steps": 3245, "total_steps": 3245, "epoch": 4.994228549442093, "percentage": 100.0, "elapsed_time": "11:13:25", "remaining_time": "0:00:00"}