chchen's picture
Training in progress, step 2050
d2db092 verified
raw
history blame
47.5 kB
{"current_steps": 10, "total_steps": 3245, "loss": 1.3358, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:26", "remaining_time": "7:45:10"}
{"current_steps": 20, "total_steps": 3245, "loss": 1.2715, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:51", "remaining_time": "7:41:32"}
{"current_steps": 30, "total_steps": 3245, "loss": 1.0351, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:17", "remaining_time": "7:40:11"}
{"current_steps": 40, "total_steps": 3245, "loss": 0.5541, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:05:43", "remaining_time": "7:39:06"}
{"current_steps": 50, "total_steps": 3245, "loss": 0.258, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:07:10", "remaining_time": "7:37:57"}
{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.24170933663845062, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:10:10", "remaining_time": "10:50:31"}
{"current_steps": 60, "total_steps": 3245, "loss": 0.1593, "lr": 1.8461538461538465e-05, "epoch": 0.0923432089265102, "percentage": 1.85, "elapsed_time": "0:11:41", "remaining_time": "10:20:52"}
{"current_steps": 70, "total_steps": 3245, "loss": 0.1273, "lr": 2.1538461538461542e-05, "epoch": 0.10773374374759523, "percentage": 2.16, "elapsed_time": "0:13:08", "remaining_time": "9:55:49"}
{"current_steps": 80, "total_steps": 3245, "loss": 0.1017, "lr": 2.461538461538462e-05, "epoch": 0.12312427856868026, "percentage": 2.47, "elapsed_time": "0:14:33", "remaining_time": "9:36:13"}
{"current_steps": 90, "total_steps": 3245, "loss": 0.1181, "lr": 2.7692307692307694e-05, "epoch": 0.1385148133897653, "percentage": 2.77, "elapsed_time": "0:15:59", "remaining_time": "9:20:43"}
{"current_steps": 100, "total_steps": 3245, "loss": 0.0852, "lr": 3.0769230769230774e-05, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:17:25", "remaining_time": "9:08:14"}
{"current_steps": 100, "total_steps": 3245, "eval_loss": 0.06961193680763245, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:20:26", "remaining_time": "10:42:57"}
{"current_steps": 110, "total_steps": 3245, "loss": 0.065, "lr": 3.384615384615385e-05, "epoch": 0.16929588303193535, "percentage": 3.39, "elapsed_time": "0:21:57", "remaining_time": "10:25:45"}
{"current_steps": 120, "total_steps": 3245, "loss": 0.0724, "lr": 3.692307692307693e-05, "epoch": 0.1846864178530204, "percentage": 3.7, "elapsed_time": "0:23:23", "remaining_time": "10:09:10"}
{"current_steps": 130, "total_steps": 3245, "loss": 0.069, "lr": 4e-05, "epoch": 0.2000769526741054, "percentage": 4.01, "elapsed_time": "0:24:49", "remaining_time": "9:54:54"}
{"current_steps": 140, "total_steps": 3245, "loss": 0.0791, "lr": 4.3076923076923084e-05, "epoch": 0.21546748749519046, "percentage": 4.31, "elapsed_time": "0:26:15", "remaining_time": "9:42:28"}
{"current_steps": 150, "total_steps": 3245, "loss": 0.0613, "lr": 4.615384615384616e-05, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:27:42", "remaining_time": "9:31:33"}
{"current_steps": 150, "total_steps": 3245, "eval_loss": 0.0586475245654583, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:30:43", "remaining_time": "10:33:57"}
{"current_steps": 160, "total_steps": 3245, "loss": 0.0615, "lr": 4.923076923076924e-05, "epoch": 0.24624855713736052, "percentage": 4.93, "elapsed_time": "0:32:14", "remaining_time": "10:21:37"}
{"current_steps": 170, "total_steps": 3245, "loss": 0.0612, "lr": 5.230769230769231e-05, "epoch": 0.26163909195844554, "percentage": 5.24, "elapsed_time": "0:33:40", "remaining_time": "10:09:10"}
{"current_steps": 180, "total_steps": 3245, "loss": 0.0528, "lr": 5.538461538461539e-05, "epoch": 0.2770296267795306, "percentage": 5.55, "elapsed_time": "0:35:06", "remaining_time": "9:57:55"}
{"current_steps": 190, "total_steps": 3245, "loss": 0.0447, "lr": 5.846153846153847e-05, "epoch": 0.2924201616006156, "percentage": 5.86, "elapsed_time": "0:36:32", "remaining_time": "9:47:38"}
{"current_steps": 200, "total_steps": 3245, "loss": 0.0575, "lr": 6.153846153846155e-05, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:37:59", "remaining_time": "9:38:22"}
{"current_steps": 200, "total_steps": 3245, "eval_loss": 0.0534023754298687, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:41:01", "remaining_time": "10:24:29"}
{"current_steps": 210, "total_steps": 3245, "loss": 0.0549, "lr": 6.461538461538462e-05, "epoch": 0.3232012312427857, "percentage": 6.47, "elapsed_time": "0:42:32", "remaining_time": "10:14:44"}
{"current_steps": 220, "total_steps": 3245, "loss": 0.0499, "lr": 6.76923076923077e-05, "epoch": 0.3385917660638707, "percentage": 6.78, "elapsed_time": "0:43:58", "remaining_time": "10:04:39"}
{"current_steps": 230, "total_steps": 3245, "loss": 0.0382, "lr": 7.076923076923078e-05, "epoch": 0.35398230088495575, "percentage": 7.09, "elapsed_time": "0:45:24", "remaining_time": "9:55:20"}
{"current_steps": 240, "total_steps": 3245, "loss": 0.0461, "lr": 7.384615384615386e-05, "epoch": 0.3693728357060408, "percentage": 7.4, "elapsed_time": "0:46:51", "remaining_time": "9:46:43"}
{"current_steps": 250, "total_steps": 3245, "loss": 0.0438, "lr": 7.692307692307693e-05, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:48:18", "remaining_time": "9:38:40"}
{"current_steps": 250, "total_steps": 3245, "eval_loss": 0.04324482008814812, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:51:19", "remaining_time": "10:14:57"}
{"current_steps": 260, "total_steps": 3245, "loss": 0.0396, "lr": 8e-05, "epoch": 0.4001539053482108, "percentage": 8.01, "elapsed_time": "0:52:52", "remaining_time": "10:06:59"}
{"current_steps": 270, "total_steps": 3245, "loss": 0.0417, "lr": 8.307692307692309e-05, "epoch": 0.41554444016929587, "percentage": 8.32, "elapsed_time": "0:54:18", "remaining_time": "9:58:26"}
{"current_steps": 280, "total_steps": 3245, "loss": 0.0532, "lr": 8.615384615384617e-05, "epoch": 0.4309349749903809, "percentage": 8.63, "elapsed_time": "0:55:45", "remaining_time": "9:50:24"}
{"current_steps": 290, "total_steps": 3245, "loss": 0.0516, "lr": 8.923076923076924e-05, "epoch": 0.44632550981146596, "percentage": 8.94, "elapsed_time": "0:57:11", "remaining_time": "9:42:49"}
{"current_steps": 300, "total_steps": 3245, "loss": 0.0403, "lr": 9.230769230769232e-05, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:58:38", "remaining_time": "9:35:40"}
{"current_steps": 300, "total_steps": 3245, "eval_loss": 0.046436503529548645, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "1:01:40", "remaining_time": "10:05:24"}
{"current_steps": 310, "total_steps": 3245, "loss": 0.0515, "lr": 9.53846153846154e-05, "epoch": 0.477106579453636, "percentage": 9.55, "elapsed_time": "1:03:12", "remaining_time": "9:58:23"}
{"current_steps": 320, "total_steps": 3245, "loss": 0.048, "lr": 9.846153846153848e-05, "epoch": 0.49249711427472104, "percentage": 9.86, "elapsed_time": "1:04:38", "remaining_time": "9:50:51"}
{"current_steps": 330, "total_steps": 3245, "loss": 0.0476, "lr": 9.999927654251793e-05, "epoch": 0.5078876490958061, "percentage": 10.17, "elapsed_time": "1:06:05", "remaining_time": "9:43:48"}
{"current_steps": 340, "total_steps": 3245, "loss": 0.0447, "lr": 9.99934890082745e-05, "epoch": 0.5232781839168911, "percentage": 10.48, "elapsed_time": "1:07:32", "remaining_time": "9:37:02"}
{"current_steps": 350, "total_steps": 3245, "loss": 0.0439, "lr": 9.99819146097084e-05, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:08:58", "remaining_time": "9:30:32"}
{"current_steps": 350, "total_steps": 3245, "eval_loss": 0.04594171419739723, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:12:00", "remaining_time": "9:55:37"}
{"current_steps": 360, "total_steps": 3245, "loss": 0.0575, "lr": 9.996455468658355e-05, "epoch": 0.5540592535590612, "percentage": 11.09, "elapsed_time": "1:13:31", "remaining_time": "9:49:11"}
{"current_steps": 370, "total_steps": 3245, "loss": 0.0377, "lr": 9.994141124835203e-05, "epoch": 0.5694497883801463, "percentage": 11.4, "elapsed_time": "1:14:58", "remaining_time": "9:42:33"}
{"current_steps": 380, "total_steps": 3245, "loss": 0.0389, "lr": 9.991248697392142e-05, "epoch": 0.5848403232012312, "percentage": 11.71, "elapsed_time": "1:16:24", "remaining_time": "9:36:07"}
{"current_steps": 390, "total_steps": 3245, "loss": 0.0344, "lr": 9.987778521134476e-05, "epoch": 0.6002308580223162, "percentage": 12.02, "elapsed_time": "1:17:51", "remaining_time": "9:29:57"}
{"current_steps": 400, "total_steps": 3245, "loss": 0.0497, "lr": 9.983730997743294e-05, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:19:18", "remaining_time": "9:24:04"}
{"current_steps": 400, "total_steps": 3245, "eval_loss": 0.04411020502448082, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:22:20", "remaining_time": "9:45:38"}
{"current_steps": 410, "total_steps": 3245, "loss": 0.0411, "lr": 9.979106595728978e-05, "epoch": 0.6310119276644863, "percentage": 12.63, "elapsed_time": "1:23:51", "remaining_time": "9:39:53"}
{"current_steps": 420, "total_steps": 3245, "loss": 0.0461, "lr": 9.973905850376977e-05, "epoch": 0.6464024624855714, "percentage": 12.94, "elapsed_time": "1:25:18", "remaining_time": "9:33:49"}
{"current_steps": 430, "total_steps": 3245, "loss": 0.0431, "lr": 9.968129363685833e-05, "epoch": 0.6617929973066564, "percentage": 13.25, "elapsed_time": "1:26:45", "remaining_time": "9:27:56"}
{"current_steps": 440, "total_steps": 3245, "loss": 0.0597, "lr": 9.961777804297514e-05, "epoch": 0.6771835321277414, "percentage": 13.56, "elapsed_time": "1:28:12", "remaining_time": "9:22:17"}
{"current_steps": 450, "total_steps": 3245, "loss": 0.0294, "lr": 9.954851907420009e-05, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:29:38", "remaining_time": "9:16:47"}
{"current_steps": 450, "total_steps": 3245, "eval_loss": 0.038757991045713425, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:32:40", "remaining_time": "9:35:36"}
{"current_steps": 460, "total_steps": 3245, "loss": 0.0343, "lr": 9.947352474742222e-05, "epoch": 0.7079646017699115, "percentage": 14.18, "elapsed_time": "1:34:11", "remaining_time": "9:30:16"}
{"current_steps": 470, "total_steps": 3245, "loss": 0.0316, "lr": 9.93928037434118e-05, "epoch": 0.7233551365909965, "percentage": 14.48, "elapsed_time": "1:35:38", "remaining_time": "9:24:39"}
{"current_steps": 480, "total_steps": 3245, "loss": 0.0419, "lr": 9.930636540581556e-05, "epoch": 0.7387456714120816, "percentage": 14.79, "elapsed_time": "1:37:05", "remaining_time": "9:19:15"}
{"current_steps": 490, "total_steps": 3245, "loss": 0.0453, "lr": 9.921421974007506e-05, "epoch": 0.7541362062331666, "percentage": 15.1, "elapsed_time": "1:38:32", "remaining_time": "9:14:02"}
{"current_steps": 500, "total_steps": 3245, "loss": 0.0296, "lr": 9.911637741226849e-05, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:39:59", "remaining_time": "9:08:55"}
{"current_steps": 500, "total_steps": 3245, "eval_loss": 0.03969333693385124, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:43:00", "remaining_time": "9:25:33"}
{"current_steps": 510, "total_steps": 3245, "loss": 0.0311, "lr": 9.90128497478762e-05, "epoch": 0.7849172758753367, "percentage": 15.72, "elapsed_time": "1:44:32", "remaining_time": "9:20:36"}
{"current_steps": 520, "total_steps": 3245, "loss": 0.0446, "lr": 9.890364873046965e-05, "epoch": 0.8003078106964217, "percentage": 16.02, "elapsed_time": "1:45:59", "remaining_time": "9:15:24"}
{"current_steps": 530, "total_steps": 3245, "loss": 0.0547, "lr": 9.878878700032427e-05, "epoch": 0.8156983455175068, "percentage": 16.33, "elapsed_time": "1:47:26", "remaining_time": "9:10:21"}
{"current_steps": 540, "total_steps": 3245, "loss": 0.0408, "lr": 9.866827785295638e-05, "epoch": 0.8310888803385917, "percentage": 16.64, "elapsed_time": "1:48:53", "remaining_time": "9:05:25"}
{"current_steps": 550, "total_steps": 3245, "loss": 0.0424, "lr": 9.854213523758413e-05, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:50:20", "remaining_time": "9:00:38"}
{"current_steps": 550, "total_steps": 3245, "eval_loss": 0.03501049801707268, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:53:22", "remaining_time": "9:15:30"}
{"current_steps": 560, "total_steps": 3245, "loss": 0.0349, "lr": 9.841037375551294e-05, "epoch": 0.8618699499807618, "percentage": 17.26, "elapsed_time": "1:54:54", "remaining_time": "9:10:55"}
{"current_steps": 570, "total_steps": 3245, "loss": 0.0255, "lr": 9.827300865844527e-05, "epoch": 0.8772604848018468, "percentage": 17.57, "elapsed_time": "1:56:21", "remaining_time": "9:06:01"}
{"current_steps": 580, "total_steps": 3245, "loss": 0.0348, "lr": 9.813005584671522e-05, "epoch": 0.8926510196229319, "percentage": 17.87, "elapsed_time": "1:57:48", "remaining_time": "9:01:16"}
{"current_steps": 590, "total_steps": 3245, "loss": 0.0513, "lr": 9.79815318674481e-05, "epoch": 0.9080415544440169, "percentage": 18.18, "elapsed_time": "1:59:14", "remaining_time": "8:56:36"}
{"current_steps": 600, "total_steps": 3245, "loss": 0.0346, "lr": 9.782745391264498e-05, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:00:41", "remaining_time": "8:52:03"}
{"current_steps": 600, "total_steps": 3245, "eval_loss": 0.03482295945286751, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:03:43", "remaining_time": "9:05:25"}
{"current_steps": 610, "total_steps": 3245, "loss": 0.0306, "lr": 9.76678398171927e-05, "epoch": 0.938822624086187, "percentage": 18.8, "elapsed_time": "2:05:15", "remaining_time": "9:01:04"}
{"current_steps": 620, "total_steps": 3245, "loss": 0.0445, "lr": 9.750270805679945e-05, "epoch": 0.954213158907272, "percentage": 19.11, "elapsed_time": "2:06:42", "remaining_time": "8:56:25"}
{"current_steps": 630, "total_steps": 3245, "loss": 0.043, "lr": 9.733207774585618e-05, "epoch": 0.9696036937283571, "percentage": 19.41, "elapsed_time": "2:08:08", "remaining_time": "8:51:52"}
{"current_steps": 640, "total_steps": 3245, "loss": 0.0334, "lr": 9.715596863522398e-05, "epoch": 0.9849942285494421, "percentage": 19.72, "elapsed_time": "2:09:34", "remaining_time": "8:47:26"}
{"current_steps": 650, "total_steps": 3245, "loss": 0.0303, "lr": 9.697440110994801e-05, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:11:01", "remaining_time": "8:43:06"}
{"current_steps": 650, "total_steps": 3245, "eval_loss": 0.035778697580099106, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:14:03", "remaining_time": "8:55:12"}
{"current_steps": 660, "total_steps": 3245, "loss": 0.0347, "lr": 9.678739618689775e-05, "epoch": 1.0157752981916122, "percentage": 20.34, "elapsed_time": "2:15:34", "remaining_time": "8:51:00"}
{"current_steps": 670, "total_steps": 3245, "loss": 0.0307, "lr": 9.659497551233431e-05, "epoch": 1.0311658330126972, "percentage": 20.65, "elapsed_time": "2:17:01", "remaining_time": "8:46:36"}
{"current_steps": 680, "total_steps": 3245, "loss": 0.033, "lr": 9.639716135940485e-05, "epoch": 1.0465563678337821, "percentage": 20.96, "elapsed_time": "2:18:27", "remaining_time": "8:42:18"}
{"current_steps": 690, "total_steps": 3245, "loss": 0.0442, "lr": 9.619397662556435e-05, "epoch": 1.0619469026548674, "percentage": 21.26, "elapsed_time": "2:19:54", "remaining_time": "8:38:05"}
{"current_steps": 700, "total_steps": 3245, "loss": 0.0331, "lr": 9.598544482992517e-05, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:21:21", "remaining_time": "8:33:56"}
{"current_steps": 700, "total_steps": 3245, "eval_loss": 0.03669578209519386, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:24:23", "remaining_time": "8:44:58"}
{"current_steps": 710, "total_steps": 3245, "loss": 0.0314, "lr": 9.57715901105348e-05, "epoch": 1.0927279722970373, "percentage": 21.88, "elapsed_time": "2:25:55", "remaining_time": "8:41:01"}
{"current_steps": 720, "total_steps": 3245, "loss": 0.0297, "lr": 9.555243722158158e-05, "epoch": 1.1081185071181223, "percentage": 22.19, "elapsed_time": "2:27:22", "remaining_time": "8:36:48"}
{"current_steps": 730, "total_steps": 3245, "loss": 0.0281, "lr": 9.532801153052958e-05, "epoch": 1.1235090419392073, "percentage": 22.5, "elapsed_time": "2:28:48", "remaining_time": "8:32:41"}
{"current_steps": 740, "total_steps": 3245, "loss": 0.0367, "lr": 9.509833901518209e-05, "epoch": 1.1388995767602923, "percentage": 22.8, "elapsed_time": "2:30:15", "remaining_time": "8:28:38"}
{"current_steps": 750, "total_steps": 3245, "loss": 0.0261, "lr": 9.486344626067475e-05, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:31:42", "remaining_time": "8:24:40"}
{"current_steps": 750, "total_steps": 3245, "eval_loss": 0.03604958578944206, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:34:44", "remaining_time": "8:34:45"}
{"current_steps": 760, "total_steps": 3245, "loss": 0.0346, "lr": 9.462336045639815e-05, "epoch": 1.1696806464024625, "percentage": 23.42, "elapsed_time": "2:36:15", "remaining_time": "8:30:56"}
{"current_steps": 770, "total_steps": 3245, "loss": 0.0362, "lr": 9.437810939285068e-05, "epoch": 1.1850711812235475, "percentage": 23.73, "elapsed_time": "2:37:42", "remaining_time": "8:26:55"}
{"current_steps": 780, "total_steps": 3245, "loss": 0.035, "lr": 9.412772145842165e-05, "epoch": 1.2004617160446325, "percentage": 24.04, "elapsed_time": "2:39:09", "remaining_time": "8:22:58"}
{"current_steps": 790, "total_steps": 3245, "loss": 0.0341, "lr": 9.387222563610535e-05, "epoch": 1.2158522508657175, "percentage": 24.35, "elapsed_time": "2:40:36", "remaining_time": "8:19:05"}
{"current_steps": 800, "total_steps": 3245, "loss": 0.0273, "lr": 9.361165150014606e-05, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:42:03", "remaining_time": "8:15:16"}
{"current_steps": 800, "total_steps": 3245, "eval_loss": 0.03427645564079285, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:45:04", "remaining_time": "8:24:31"}
{"current_steps": 810, "total_steps": 3245, "loss": 0.0295, "lr": 9.334602921261492e-05, "epoch": 1.2466333205078877, "percentage": 24.96, "elapsed_time": "2:46:36", "remaining_time": "8:20:50"}
{"current_steps": 820, "total_steps": 3245, "loss": 0.0275, "lr": 9.307538951991852e-05, "epoch": 1.2620238553289727, "percentage": 25.27, "elapsed_time": "2:48:02", "remaining_time": "8:16:58"}
{"current_steps": 830, "total_steps": 3245, "loss": 0.032, "lr": 9.279976374923988e-05, "epoch": 1.2774143901500576, "percentage": 25.58, "elapsed_time": "2:49:29", "remaining_time": "8:13:09"}
{"current_steps": 840, "total_steps": 3245, "loss": 0.0271, "lr": 9.251918380491238e-05, "epoch": 1.2928049249711426, "percentage": 25.89, "elapsed_time": "2:50:56", "remaining_time": "8:09:25"}
{"current_steps": 850, "total_steps": 3245, "loss": 0.0277, "lr": 9.223368216472668e-05, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "2:52:23", "remaining_time": "8:05:43"}
{"current_steps": 850, "total_steps": 3245, "eval_loss": 0.034582581371068954, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "2:55:25", "remaining_time": "8:14:16"}
{"current_steps": 860, "total_steps": 3245, "loss": 0.0262, "lr": 9.194329187617127e-05, "epoch": 1.3235859946133128, "percentage": 26.5, "elapsed_time": "2:56:56", "remaining_time": "8:10:42"}
{"current_steps": 870, "total_steps": 3245, "loss": 0.0263, "lr": 9.164804655260735e-05, "epoch": 1.3389765294343978, "percentage": 26.81, "elapsed_time": "2:58:22", "remaining_time": "8:06:57"}
{"current_steps": 880, "total_steps": 3245, "loss": 0.03, "lr": 9.134798036937778e-05, "epoch": 1.3543670642554828, "percentage": 27.12, "elapsed_time": "2:59:49", "remaining_time": "8:03:16"}
{"current_steps": 890, "total_steps": 3245, "loss": 0.0358, "lr": 9.104312805985134e-05, "epoch": 1.3697575990765678, "percentage": 27.43, "elapsed_time": "3:01:16", "remaining_time": "7:59:40"}
{"current_steps": 900, "total_steps": 3245, "loss": 0.0213, "lr": 9.073352491140221e-05, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:02:43", "remaining_time": "7:56:05"}
{"current_steps": 900, "total_steps": 3245, "eval_loss": 0.03390317037701607, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:05:45", "remaining_time": "8:03:59"}
{"current_steps": 910, "total_steps": 3245, "loss": 0.0303, "lr": 9.041920676132543e-05, "epoch": 1.400538668718738, "percentage": 28.04, "elapsed_time": "3:07:17", "remaining_time": "8:00:34"}
{"current_steps": 920, "total_steps": 3245, "loss": 0.0316, "lr": 9.010020999268854e-05, "epoch": 1.415929203539823, "percentage": 28.35, "elapsed_time": "3:08:44", "remaining_time": "7:56:58"}
{"current_steps": 930, "total_steps": 3245, "loss": 0.0289, "lr": 8.977657153012027e-05, "epoch": 1.431319738360908, "percentage": 28.66, "elapsed_time": "3:10:10", "remaining_time": "7:53:24"}
{"current_steps": 940, "total_steps": 3245, "loss": 0.029, "lr": 8.944832883553633e-05, "epoch": 1.446710273181993, "percentage": 28.97, "elapsed_time": "3:11:37", "remaining_time": "7:49:53"}
{"current_steps": 950, "total_steps": 3245, "loss": 0.036, "lr": 8.91155199038032e-05, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:13:04", "remaining_time": "7:46:25"}
{"current_steps": 950, "total_steps": 3245, "eval_loss": 0.034716229885816574, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:16:06", "remaining_time": "7:53:44"}
{"current_steps": 960, "total_steps": 3245, "loss": 0.0284, "lr": 8.877818325834006e-05, "epoch": 1.4774913428241632, "percentage": 29.58, "elapsed_time": "3:17:37", "remaining_time": "7:50:23"}
{"current_steps": 970, "total_steps": 3245, "loss": 0.0238, "lr": 8.843635794665961e-05, "epoch": 1.4928818776452482, "percentage": 29.89, "elapsed_time": "3:19:04", "remaining_time": "7:46:54"}
{"current_steps": 980, "total_steps": 3245, "loss": 0.0302, "lr": 8.809008353584829e-05, "epoch": 1.5082724124663334, "percentage": 30.2, "elapsed_time": "3:20:31", "remaining_time": "7:43:27"}
{"current_steps": 990, "total_steps": 3245, "loss": 0.0304, "lr": 8.773940010798627e-05, "epoch": 1.5236629472874181, "percentage": 30.51, "elapsed_time": "3:21:58", "remaining_time": "7:40:02"}
{"current_steps": 1000, "total_steps": 3245, "loss": 0.0333, "lr": 8.738434825550785e-05, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:23:25", "remaining_time": "7:36:40"}
{"current_steps": 1000, "total_steps": 3245, "eval_loss": 0.03497457504272461, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:26:27", "remaining_time": "7:43:29"}
{"current_steps": 1010, "total_steps": 3245, "loss": 0.0324, "lr": 8.702496907650274e-05, "epoch": 1.5544440169295883, "percentage": 31.12, "elapsed_time": "3:27:58", "remaining_time": "7:40:13"}
{"current_steps": 1020, "total_steps": 3245, "loss": 0.0308, "lr": 8.666130416995897e-05, "epoch": 1.5698345517506733, "percentage": 31.43, "elapsed_time": "3:29:25", "remaining_time": "7:36:49"}
{"current_steps": 1030, "total_steps": 3245, "loss": 0.0283, "lr": 8.629339563094758e-05, "epoch": 1.5852250865717585, "percentage": 31.74, "elapsed_time": "3:30:52", "remaining_time": "7:33:29"}
{"current_steps": 1040, "total_steps": 3245, "loss": 0.0264, "lr": 8.592128604575014e-05, "epoch": 1.6006156213928433, "percentage": 32.05, "elapsed_time": "3:32:19", "remaining_time": "7:30:11"}
{"current_steps": 1050, "total_steps": 3245, "loss": 0.0312, "lr": 8.554501848692921e-05, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:33:46", "remaining_time": "7:26:54"}
{"current_steps": 1050, "total_steps": 3245, "eval_loss": 0.032106366008520126, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:36:48", "remaining_time": "7:33:14"}
{"current_steps": 1060, "total_steps": 3245, "loss": 0.0214, "lr": 8.51646365083426e-05, "epoch": 1.6313966910350135, "percentage": 32.67, "elapsed_time": "3:38:20", "remaining_time": "7:30:03"}
{"current_steps": 1070, "total_steps": 3245, "loss": 0.0279, "lr": 8.478018414010191e-05, "epoch": 1.6467872258560985, "percentage": 32.97, "elapsed_time": "3:39:46", "remaining_time": "7:26:44"}
{"current_steps": 1080, "total_steps": 3245, "loss": 0.0236, "lr": 8.439170588347598e-05, "epoch": 1.6621777606771835, "percentage": 33.28, "elapsed_time": "3:41:13", "remaining_time": "7:23:28"}
{"current_steps": 1090, "total_steps": 3245, "loss": 0.0269, "lr": 8.399924670573969e-05, "epoch": 1.6775682954982685, "percentage": 33.59, "elapsed_time": "3:42:39", "remaining_time": "7:20:13"}
{"current_steps": 1100, "total_steps": 3245, "loss": 0.0331, "lr": 8.360285203496894e-05, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:44:07", "remaining_time": "7:17:02"}
{"current_steps": 1100, "total_steps": 3245, "eval_loss": 0.035727474838495255, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:47:09", "remaining_time": "7:22:56"}
{"current_steps": 1110, "total_steps": 3245, "loss": 0.0318, "lr": 8.320256775478228e-05, "epoch": 1.7083493651404387, "percentage": 34.21, "elapsed_time": "3:48:40", "remaining_time": "7:19:51"}
{"current_steps": 1120, "total_steps": 3245, "loss": 0.0232, "lr": 8.279844019902968e-05, "epoch": 1.7237398999615237, "percentage": 34.51, "elapsed_time": "3:50:07", "remaining_time": "7:16:37"}
{"current_steps": 1130, "total_steps": 3245, "loss": 0.0345, "lr": 8.239051614642934e-05, "epoch": 1.7391304347826086, "percentage": 34.82, "elapsed_time": "3:51:34", "remaining_time": "7:13:25"}
{"current_steps": 1140, "total_steps": 3245, "loss": 0.0395, "lr": 8.197884281515292e-05, "epoch": 1.7545209696036936, "percentage": 35.13, "elapsed_time": "3:53:01", "remaining_time": "7:10:15"}
{"current_steps": 1150, "total_steps": 3245, "loss": 0.024, "lr": 8.156346785735997e-05, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "3:54:27", "remaining_time": "7:07:07"}
{"current_steps": 1150, "total_steps": 3245, "eval_loss": 0.03280346468091011, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "3:57:29", "remaining_time": "7:12:38"}
{"current_steps": 1160, "total_steps": 3245, "loss": 0.0331, "lr": 8.114443935368198e-05, "epoch": 1.7853020392458638, "percentage": 35.75, "elapsed_time": "3:59:00", "remaining_time": "7:09:35"}
{"current_steps": 1170, "total_steps": 3245, "loss": 0.0243, "lr": 8.072180580765709e-05, "epoch": 1.8006925740669488, "percentage": 36.06, "elapsed_time": "4:00:27", "remaining_time": "7:06:27"}
{"current_steps": 1180, "total_steps": 3245, "loss": 0.0248, "lr": 8.02956161401155e-05, "epoch": 1.8160831088880338, "percentage": 36.36, "elapsed_time": "4:01:54", "remaining_time": "7:03:21"}
{"current_steps": 1190, "total_steps": 3245, "loss": 0.0294, "lr": 7.98659196835169e-05, "epoch": 1.8314736437091188, "percentage": 36.67, "elapsed_time": "4:03:22", "remaining_time": "7:00:16"}
{"current_steps": 1200, "total_steps": 3245, "loss": 0.021, "lr": 7.943276617624014e-05, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:04:48", "remaining_time": "6:57:12"}
{"current_steps": 1200, "total_steps": 3245, "eval_loss": 0.037004999816417694, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:07:50", "remaining_time": "7:02:22"}
{"current_steps": 1210, "total_steps": 3245, "loss": 0.029, "lr": 7.899620575682578e-05, "epoch": 1.862254713351289, "percentage": 37.29, "elapsed_time": "4:09:22", "remaining_time": "6:59:24"}
{"current_steps": 1220, "total_steps": 3245, "loss": 0.0231, "lr": 7.85562889581725e-05, "epoch": 1.877645248172374, "percentage": 37.6, "elapsed_time": "4:10:49", "remaining_time": "6:56:19"}
{"current_steps": 1230, "total_steps": 3245, "loss": 0.0269, "lr": 7.811306670168788e-05, "epoch": 1.893035782993459, "percentage": 37.9, "elapsed_time": "4:12:16", "remaining_time": "6:53:16"}
{"current_steps": 1240, "total_steps": 3245, "loss": 0.0341, "lr": 7.766659029139393e-05, "epoch": 1.908426317814544, "percentage": 38.21, "elapsed_time": "4:13:42", "remaining_time": "6:50:14"}
{"current_steps": 1250, "total_steps": 3245, "loss": 0.028, "lr": 7.72169114079887e-05, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:15:09", "remaining_time": "6:47:14"}
{"current_steps": 1250, "total_steps": 3245, "eval_loss": 0.03357686474919319, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:18:11", "remaining_time": "6:52:04"}
{"current_steps": 1260, "total_steps": 3245, "loss": 0.0314, "lr": 7.676408210286407e-05, "epoch": 1.9392073874567142, "percentage": 38.83, "elapsed_time": "4:19:43", "remaining_time": "6:49:10"}
{"current_steps": 1270, "total_steps": 3245, "loss": 0.031, "lr": 7.630815479208066e-05, "epoch": 1.9545979222777992, "percentage": 39.14, "elapsed_time": "4:21:09", "remaining_time": "6:46:08"}
{"current_steps": 1280, "total_steps": 3245, "loss": 0.023, "lr": 7.584918225030053e-05, "epoch": 1.9699884570988841, "percentage": 39.45, "elapsed_time": "4:22:36", "remaining_time": "6:43:09"}
{"current_steps": 1290, "total_steps": 3245, "loss": 0.0326, "lr": 7.538721760467845e-05, "epoch": 1.9853789919199691, "percentage": 39.75, "elapsed_time": "4:24:03", "remaining_time": "6:40:10"}
{"current_steps": 1300, "total_steps": 3245, "loss": 0.0222, "lr": 7.49223143287122e-05, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:25:30", "remaining_time": "6:37:14"}
{"current_steps": 1300, "total_steps": 3245, "eval_loss": 0.031579531729221344, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:28:32", "remaining_time": "6:41:46"}
{"current_steps": 1310, "total_steps": 3245, "loss": 0.0169, "lr": 7.445452623605307e-05, "epoch": 2.016160061562139, "percentage": 40.37, "elapsed_time": "4:30:03", "remaining_time": "6:38:54"}
{"current_steps": 1320, "total_steps": 3245, "loss": 0.019, "lr": 7.398390747427662e-05, "epoch": 2.0315505963832243, "percentage": 40.68, "elapsed_time": "4:31:30", "remaining_time": "6:35:56"}
{"current_steps": 1330, "total_steps": 3245, "loss": 0.0186, "lr": 7.351051251861501e-05, "epoch": 2.0469411312043095, "percentage": 40.99, "elapsed_time": "4:32:57", "remaining_time": "6:33:01"}
{"current_steps": 1340, "total_steps": 3245, "loss": 0.0215, "lr": 7.303439616565146e-05, "epoch": 2.0623316660253943, "percentage": 41.29, "elapsed_time": "4:34:24", "remaining_time": "6:30:06"}
{"current_steps": 1350, "total_steps": 3245, "loss": 0.018, "lr": 7.255561352697732e-05, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:35:51", "remaining_time": "6:27:12"}
{"current_steps": 1350, "total_steps": 3245, "eval_loss": 0.03076998144388199, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:38:53", "remaining_time": "6:31:28"}
{"current_steps": 1360, "total_steps": 3245, "loss": 0.0181, "lr": 7.207422002281281e-05, "epoch": 2.0931127356675643, "percentage": 41.91, "elapsed_time": "4:40:24", "remaining_time": "6:28:39"}
{"current_steps": 1370, "total_steps": 3245, "loss": 0.0168, "lr": 7.159027137559197e-05, "epoch": 2.1085032704886495, "percentage": 42.22, "elapsed_time": "4:41:51", "remaining_time": "6:25:45"}
{"current_steps": 1380, "total_steps": 3245, "loss": 0.0133, "lr": 7.110382360351267e-05, "epoch": 2.1238938053097347, "percentage": 42.53, "elapsed_time": "4:43:18", "remaining_time": "6:22:53"}
{"current_steps": 1390, "total_steps": 3245, "loss": 0.0142, "lr": 7.061493301405244e-05, "epoch": 2.1392843401308195, "percentage": 42.84, "elapsed_time": "4:44:45", "remaining_time": "6:20:01"}
{"current_steps": 1400, "total_steps": 3245, "loss": 0.0213, "lr": 7.012365619745064e-05, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:46:12", "remaining_time": "6:17:11"}
{"current_steps": 1400, "total_steps": 3245, "eval_loss": 0.033796727657318115, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:49:14", "remaining_time": "6:21:10"}
{"current_steps": 1410, "total_steps": 3245, "loss": 0.0157, "lr": 6.963005002015808e-05, "epoch": 2.1700654097729895, "percentage": 43.45, "elapsed_time": "4:50:45", "remaining_time": "6:18:24"}
{"current_steps": 1420, "total_steps": 3245, "loss": 0.0226, "lr": 6.91341716182545e-05, "epoch": 2.1854559445940747, "percentage": 43.76, "elapsed_time": "4:52:12", "remaining_time": "6:15:33"}
{"current_steps": 1430, "total_steps": 3245, "loss": 0.012, "lr": 6.863607839083507e-05, "epoch": 2.20084647941516, "percentage": 44.07, "elapsed_time": "4:53:40", "remaining_time": "6:12:43"}
{"current_steps": 1440, "total_steps": 3245, "loss": 0.0189, "lr": 6.813582799336624e-05, "epoch": 2.2162370142362446, "percentage": 44.38, "elapsed_time": "4:55:07", "remaining_time": "6:09:55"}
{"current_steps": 1450, "total_steps": 3245, "loss": 0.0094, "lr": 6.763347833101192e-05, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "4:56:34", "remaining_time": "6:07:08"}
{"current_steps": 1450, "total_steps": 3245, "eval_loss": 0.03715962916612625, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "4:59:36", "remaining_time": "6:10:53"}
{"current_steps": 1460, "total_steps": 3245, "loss": 0.0174, "lr": 6.712908755193094e-05, "epoch": 2.2470180838784146, "percentage": 44.99, "elapsed_time": "5:01:08", "remaining_time": "6:08:10"}
{"current_steps": 1470, "total_steps": 3245, "loss": 0.0228, "lr": 6.662271404054621e-05, "epoch": 2.2624086186995, "percentage": 45.3, "elapsed_time": "5:02:35", "remaining_time": "6:05:21"}
{"current_steps": 1480, "total_steps": 3245, "loss": 0.0189, "lr": 6.611441641078657e-05, "epoch": 2.2777991535205846, "percentage": 45.61, "elapsed_time": "5:04:01", "remaining_time": "6:02:34"}
{"current_steps": 1490, "total_steps": 3245, "loss": 0.0204, "lr": 6.560425349930208e-05, "epoch": 2.29318968834167, "percentage": 45.92, "elapsed_time": "5:05:28", "remaining_time": "5:59:48"}
{"current_steps": 1500, "total_steps": 3245, "loss": 0.0197, "lr": 6.509228435865357e-05, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:06:55", "remaining_time": "5:57:03"}
{"current_steps": 1500, "total_steps": 3245, "eval_loss": 0.0334332212805748, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:09:57", "remaining_time": "6:00:35"}
{"current_steps": 1510, "total_steps": 3245, "loss": 0.0215, "lr": 6.45785682504772e-05, "epoch": 2.32397075798384, "percentage": 46.53, "elapsed_time": "5:11:28", "remaining_time": "5:57:53"}
{"current_steps": 1520, "total_steps": 3245, "loss": 0.0193, "lr": 6.406316463862467e-05, "epoch": 2.339361292804925, "percentage": 46.84, "elapsed_time": "5:12:55", "remaining_time": "5:55:08"}
{"current_steps": 1530, "total_steps": 3245, "loss": 0.0135, "lr": 6.35461331822803e-05, "epoch": 2.3547518276260098, "percentage": 47.15, "elapsed_time": "5:14:22", "remaining_time": "5:52:23"}
{"current_steps": 1540, "total_steps": 3245, "loss": 0.0175, "lr": 6.302753372905515e-05, "epoch": 2.370142362447095, "percentage": 47.46, "elapsed_time": "5:15:49", "remaining_time": "5:49:40"}
{"current_steps": 1550, "total_steps": 3245, "loss": 0.0156, "lr": 6.250742630805971e-05, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:17:16", "remaining_time": "5:46:57"}
{"current_steps": 1550, "total_steps": 3245, "eval_loss": 0.03909274563193321, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:20:18", "remaining_time": "5:50:16"}
{"current_steps": 1560, "total_steps": 3245, "loss": 0.0134, "lr": 6.198587112295526e-05, "epoch": 2.400923432089265, "percentage": 48.07, "elapsed_time": "5:21:51", "remaining_time": "5:47:38"}
{"current_steps": 1570, "total_steps": 3245, "loss": 0.0171, "lr": 6.14629285449852e-05, "epoch": 2.41631396691035, "percentage": 48.38, "elapsed_time": "5:23:18", "remaining_time": "5:44:56"}
{"current_steps": 1580, "total_steps": 3245, "loss": 0.0179, "lr": 6.093865910598688e-05, "epoch": 2.431704501731435, "percentage": 48.69, "elapsed_time": "5:24:46", "remaining_time": "5:42:14"}
{"current_steps": 1590, "total_steps": 3245, "loss": 0.0173, "lr": 6.0413123491385025e-05, "epoch": 2.44709503655252, "percentage": 49.0, "elapsed_time": "5:26:12", "remaining_time": "5:39:32"}
{"current_steps": 1600, "total_steps": 3245, "loss": 0.0129, "lr": 5.988638253316713e-05, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:27:39", "remaining_time": "5:36:52"}
{"current_steps": 1600, "total_steps": 3245, "eval_loss": 0.03702254593372345, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:30:41", "remaining_time": "5:39:59"}
{"current_steps": 1610, "total_steps": 3245, "loss": 0.0151, "lr": 5.935849720284206e-05, "epoch": 2.47787610619469, "percentage": 49.61, "elapsed_time": "5:32:12", "remaining_time": "5:37:22"}
{"current_steps": 1620, "total_steps": 3245, "loss": 0.0205, "lr": 5.8829528604382436e-05, "epoch": 2.4932666410157753, "percentage": 49.92, "elapsed_time": "5:33:39", "remaining_time": "5:34:40"}
{"current_steps": 1630, "total_steps": 3245, "loss": 0.0149, "lr": 5.829953796715176e-05, "epoch": 2.50865717583686, "percentage": 50.23, "elapsed_time": "5:35:05", "remaining_time": "5:32:00"}
{"current_steps": 1640, "total_steps": 3245, "loss": 0.0204, "lr": 5.7768586638816924e-05, "epoch": 2.5240477106579453, "percentage": 50.54, "elapsed_time": "5:36:32", "remaining_time": "5:29:21"}
{"current_steps": 1650, "total_steps": 3245, "loss": 0.0193, "lr": 5.723673607824705e-05, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:37:59", "remaining_time": "5:26:43"}
{"current_steps": 1650, "total_steps": 3245, "eval_loss": 0.033449891954660416, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:41:01", "remaining_time": "5:29:39"}
{"current_steps": 1660, "total_steps": 3245, "loss": 0.0139, "lr": 5.670404784839953e-05, "epoch": 2.5548287803001153, "percentage": 51.16, "elapsed_time": "5:42:33", "remaining_time": "5:27:04"}
{"current_steps": 1670, "total_steps": 3245, "loss": 0.0184, "lr": 5.6170583609193984e-05, "epoch": 2.5702193151212005, "percentage": 51.46, "elapsed_time": "5:43:59", "remaining_time": "5:24:25"}
{"current_steps": 1680, "total_steps": 3245, "loss": 0.0197, "lr": 5.56364051103749e-05, "epoch": 2.5856098499422853, "percentage": 51.77, "elapsed_time": "5:45:26", "remaining_time": "5:21:48"}
{"current_steps": 1690, "total_steps": 3245, "loss": 0.0192, "lr": 5.5101574184364056e-05, "epoch": 2.6010003847633705, "percentage": 52.08, "elapsed_time": "5:46:53", "remaining_time": "5:19:10"}
{"current_steps": 1700, "total_steps": 3245, "loss": 0.0209, "lr": 5.4566152739103116e-05, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "5:48:20", "remaining_time": "5:16:34"}
{"current_steps": 1700, "total_steps": 3245, "eval_loss": 0.03561204671859741, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "5:51:22", "remaining_time": "5:19:19"}
{"current_steps": 1710, "total_steps": 3245, "loss": 0.0179, "lr": 5.403020275088786e-05, "epoch": 2.6317814544055405, "percentage": 52.7, "elapsed_time": "5:52:53", "remaining_time": "5:16:46"}
{"current_steps": 1720, "total_steps": 3245, "loss": 0.0261, "lr": 5.349378625719408e-05, "epoch": 2.6471719892266257, "percentage": 53.0, "elapsed_time": "5:54:20", "remaining_time": "5:14:09"}
{"current_steps": 1730, "total_steps": 3245, "loss": 0.0196, "lr": 5.2956965349496743e-05, "epoch": 2.6625625240477104, "percentage": 53.31, "elapsed_time": "5:55:47", "remaining_time": "5:11:34"}
{"current_steps": 1740, "total_steps": 3245, "loss": 0.0159, "lr": 5.241980216608261e-05, "epoch": 2.6779530588687956, "percentage": 53.62, "elapsed_time": "5:57:13", "remaining_time": "5:08:59"}
{"current_steps": 1750, "total_steps": 3245, "loss": 0.0227, "lr": 5.188235888485773e-05, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "5:58:40", "remaining_time": "5:06:24"}
{"current_steps": 1750, "total_steps": 3245, "eval_loss": 0.03291955217719078, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "6:01:42", "remaining_time": "5:09:00"}
{"current_steps": 1760, "total_steps": 3245, "loss": 0.0133, "lr": 5.13446977161501e-05, "epoch": 2.7087341285109656, "percentage": 54.24, "elapsed_time": "6:03:14", "remaining_time": "5:06:29"}
{"current_steps": 1770, "total_steps": 3245, "loss": 0.017, "lr": 5.0806880895508766e-05, "epoch": 2.724124663332051, "percentage": 54.55, "elapsed_time": "6:04:41", "remaining_time": "5:03:54"}
{"current_steps": 1780, "total_steps": 3245, "loss": 0.0227, "lr": 5.026897067649976e-05, "epoch": 2.7395151981531356, "percentage": 54.85, "elapsed_time": "6:06:08", "remaining_time": "5:01:21"}
{"current_steps": 1790, "total_steps": 3245, "loss": 0.0181, "lr": 4.973102932350026e-05, "epoch": 2.754905732974221, "percentage": 55.16, "elapsed_time": "6:07:35", "remaining_time": "4:58:47"}
{"current_steps": 1800, "total_steps": 3245, "loss": 0.0207, "lr": 4.9193119104491245e-05, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:09:02", "remaining_time": "4:56:15"}
{"current_steps": 1800, "total_steps": 3245, "eval_loss": 0.03256721794605255, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:12:04", "remaining_time": "4:58:41"}
{"current_steps": 1810, "total_steps": 3245, "loss": 0.019, "lr": 4.86553022838499e-05, "epoch": 2.785686802616391, "percentage": 55.78, "elapsed_time": "6:13:36", "remaining_time": "4:56:11"}
{"current_steps": 1820, "total_steps": 3245, "loss": 0.0221, "lr": 4.8117641115142285e-05, "epoch": 2.801077337437476, "percentage": 56.09, "elapsed_time": "6:15:03", "remaining_time": "4:53:39"}
{"current_steps": 1830, "total_steps": 3245, "loss": 0.0187, "lr": 4.758019783391741e-05, "epoch": 2.8164678722585608, "percentage": 56.39, "elapsed_time": "6:16:30", "remaining_time": "4:51:07"}
{"current_steps": 1840, "total_steps": 3245, "loss": 0.018, "lr": 4.704303465050327e-05, "epoch": 2.831858407079646, "percentage": 56.7, "elapsed_time": "6:17:56", "remaining_time": "4:48:35"}
{"current_steps": 1850, "total_steps": 3245, "loss": 0.0204, "lr": 4.6506213742805924e-05, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:19:23", "remaining_time": "4:46:05"}
{"current_steps": 1850, "total_steps": 3245, "eval_loss": 0.03224136680364609, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:22:25", "remaining_time": "4:48:22"}
{"current_steps": 1860, "total_steps": 3245, "loss": 0.014, "lr": 4.5969797249112146e-05, "epoch": 2.862639476721816, "percentage": 57.32, "elapsed_time": "6:23:56", "remaining_time": "4:45:53"}
{"current_steps": 1870, "total_steps": 3245, "loss": 0.0243, "lr": 4.54338472608969e-05, "epoch": 2.878030011542901, "percentage": 57.63, "elapsed_time": "6:25:23", "remaining_time": "4:43:22"}
{"current_steps": 1880, "total_steps": 3245, "loss": 0.0158, "lr": 4.489842581563597e-05, "epoch": 2.893420546363986, "percentage": 57.94, "elapsed_time": "6:26:50", "remaining_time": "4:40:52"}
{"current_steps": 1890, "total_steps": 3245, "loss": 0.0162, "lr": 4.436359488962511e-05, "epoch": 2.908811081185071, "percentage": 58.24, "elapsed_time": "6:28:17", "remaining_time": "4:38:22"}
{"current_steps": 1900, "total_steps": 3245, "loss": 0.0172, "lr": 4.382941639080602e-05, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:29:44", "remaining_time": "4:35:53"}
{"current_steps": 1900, "total_steps": 3245, "eval_loss": 0.0330594927072525, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:32:46", "remaining_time": "4:38:02"}
{"current_steps": 1910, "total_steps": 3245, "loss": 0.0223, "lr": 4.3295952151600475e-05, "epoch": 2.939592150827241, "percentage": 58.86, "elapsed_time": "6:34:18", "remaining_time": "4:35:36"}
{"current_steps": 1920, "total_steps": 3245, "loss": 0.018, "lr": 4.276326392175296e-05, "epoch": 2.9549826856483263, "percentage": 59.17, "elapsed_time": "6:35:45", "remaining_time": "4:33:06"}
{"current_steps": 1930, "total_steps": 3245, "loss": 0.0151, "lr": 4.2231413361183095e-05, "epoch": 2.970373220469411, "percentage": 59.48, "elapsed_time": "6:37:12", "remaining_time": "4:30:37"}
{"current_steps": 1940, "total_steps": 3245, "loss": 0.0146, "lr": 4.1700462032848244e-05, "epoch": 2.9857637552904963, "percentage": 59.78, "elapsed_time": "6:38:39", "remaining_time": "4:28:09"}
{"current_steps": 1950, "total_steps": 3245, "loss": 0.0239, "lr": 4.117047139561758e-05, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:40:06", "remaining_time": "4:25:42"}
{"current_steps": 1950, "total_steps": 3245, "eval_loss": 0.03445501625537872, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:43:07", "remaining_time": "4:27:43"}
{"current_steps": 1960, "total_steps": 3245, "loss": 0.0076, "lr": 4.0641502797157966e-05, "epoch": 3.0165448249326663, "percentage": 60.4, "elapsed_time": "6:44:39", "remaining_time": "4:25:17"}
{"current_steps": 1970, "total_steps": 3245, "loss": 0.01, "lr": 4.011361746683288e-05, "epoch": 3.0319353597537515, "percentage": 60.71, "elapsed_time": "6:46:05", "remaining_time": "4:22:49"}
{"current_steps": 1980, "total_steps": 3245, "loss": 0.0086, "lr": 3.958687650861499e-05, "epoch": 3.0473258945748363, "percentage": 61.02, "elapsed_time": "6:47:32", "remaining_time": "4:20:22"}
{"current_steps": 1990, "total_steps": 3245, "loss": 0.0065, "lr": 3.906134089401313e-05, "epoch": 3.0627164293959215, "percentage": 61.33, "elapsed_time": "6:48:59", "remaining_time": "4:17:56"}
{"current_steps": 2000, "total_steps": 3245, "loss": 0.0089, "lr": 3.853707145501482e-05, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "6:50:26", "remaining_time": "4:15:30"}
{"current_steps": 2000, "total_steps": 3245, "eval_loss": 0.03778772056102753, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "6:53:28", "remaining_time": "4:17:23"}
{"current_steps": 2010, "total_steps": 3245, "loss": 0.0047, "lr": 3.801412887704475e-05, "epoch": 3.0934974990380915, "percentage": 61.94, "elapsed_time": "6:55:00", "remaining_time": "4:14:59"}
{"current_steps": 2020, "total_steps": 3245, "loss": 0.0089, "lr": 3.749257369194029e-05, "epoch": 3.1088880338591767, "percentage": 62.25, "elapsed_time": "6:56:27", "remaining_time": "4:12:33"}
{"current_steps": 2030, "total_steps": 3245, "loss": 0.0087, "lr": 3.697246627094487e-05, "epoch": 3.1242785686802614, "percentage": 62.56, "elapsed_time": "6:57:54", "remaining_time": "4:10:07"}
{"current_steps": 2040, "total_steps": 3245, "loss": 0.0077, "lr": 3.6453866817719726e-05, "epoch": 3.1396691035013466, "percentage": 62.87, "elapsed_time": "6:59:21", "remaining_time": "4:07:42"}
{"current_steps": 2050, "total_steps": 3245, "loss": 0.0119, "lr": 3.593683536137533e-05, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:00:48", "remaining_time": "4:05:17"}
{"current_steps": 2050, "total_steps": 3245, "eval_loss": 0.04142413288354874, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:03:50", "remaining_time": "4:07:03"}