chchen's picture
Training in progress, step 550
7749115 verified
raw
history blame
12.7 kB
{"current_steps": 10, "total_steps": 3245, "loss": 1.9976, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:22", "remaining_time": "7:27:21"}
{"current_steps": 20, "total_steps": 3245, "loss": 1.9289, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:43", "remaining_time": "7:19:48"}
{"current_steps": 30, "total_steps": 3245, "loss": 1.7183, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:04", "remaining_time": "7:17:29"}
{"current_steps": 40, "total_steps": 3245, "loss": 1.3793, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:05:25", "remaining_time": "7:14:57"}
{"current_steps": 50, "total_steps": 3245, "loss": 0.8724, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:06:46", "remaining_time": "7:13:01"}
{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.6930168867111206, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:09:20", "remaining_time": "9:56:52"}
{"current_steps": 60, "total_steps": 3245, "loss": 0.5891, "lr": 1.8461538461538465e-05, "epoch": 0.0923432089265102, "percentage": 1.85, "elapsed_time": "0:10:45", "remaining_time": "9:30:56"}
{"current_steps": 70, "total_steps": 3245, "loss": 0.407, "lr": 2.1538461538461542e-05, "epoch": 0.10773374374759523, "percentage": 2.16, "elapsed_time": "0:12:05", "remaining_time": "9:08:42"}
{"current_steps": 80, "total_steps": 3245, "loss": 0.2129, "lr": 2.461538461538462e-05, "epoch": 0.12312427856868026, "percentage": 2.47, "elapsed_time": "0:13:26", "remaining_time": "8:52:00"}
{"current_steps": 90, "total_steps": 3245, "loss": 0.218, "lr": 2.7692307692307694e-05, "epoch": 0.1385148133897653, "percentage": 2.77, "elapsed_time": "0:14:47", "remaining_time": "8:38:38"}
{"current_steps": 100, "total_steps": 3245, "loss": 0.1565, "lr": 3.0769230769230774e-05, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:16:08", "remaining_time": "8:27:47"}
{"current_steps": 100, "total_steps": 3245, "eval_loss": 0.10799121856689453, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:18:42", "remaining_time": "9:48:28"}
{"current_steps": 110, "total_steps": 3245, "loss": 0.1103, "lr": 3.384615384615385e-05, "epoch": 0.16929588303193535, "percentage": 3.39, "elapsed_time": "0:20:08", "remaining_time": "9:34:13"}
{"current_steps": 120, "total_steps": 3245, "loss": 0.1095, "lr": 3.692307692307693e-05, "epoch": 0.1846864178530204, "percentage": 3.7, "elapsed_time": "0:21:30", "remaining_time": "9:19:56"}
{"current_steps": 130, "total_steps": 3245, "loss": 0.0785, "lr": 4e-05, "epoch": 0.2000769526741054, "percentage": 4.01, "elapsed_time": "0:22:50", "remaining_time": "9:07:29"}
{"current_steps": 140, "total_steps": 3245, "loss": 0.0838, "lr": 4.3076923076923084e-05, "epoch": 0.21546748749519046, "percentage": 4.31, "elapsed_time": "0:24:12", "remaining_time": "8:56:44"}
{"current_steps": 150, "total_steps": 3245, "loss": 0.0877, "lr": 4.615384615384616e-05, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:25:32", "remaining_time": "8:47:04"}
{"current_steps": 150, "total_steps": 3245, "eval_loss": 0.07301879674196243, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:28:06", "remaining_time": "9:39:57"}
{"current_steps": 160, "total_steps": 3245, "loss": 0.0826, "lr": 4.923076923076924e-05, "epoch": 0.24624855713736052, "percentage": 4.93, "elapsed_time": "0:29:32", "remaining_time": "9:29:26"}
{"current_steps": 170, "total_steps": 3245, "loss": 0.0755, "lr": 5.230769230769231e-05, "epoch": 0.26163909195844554, "percentage": 5.24, "elapsed_time": "0:30:53", "remaining_time": "9:18:39"}
{"current_steps": 180, "total_steps": 3245, "loss": 0.0598, "lr": 5.538461538461539e-05, "epoch": 0.2770296267795306, "percentage": 5.55, "elapsed_time": "0:32:13", "remaining_time": "9:08:42"}
{"current_steps": 190, "total_steps": 3245, "loss": 0.0519, "lr": 5.846153846153847e-05, "epoch": 0.2924201616006156, "percentage": 5.86, "elapsed_time": "0:33:34", "remaining_time": "8:59:47"}
{"current_steps": 200, "total_steps": 3245, "loss": 0.0732, "lr": 6.153846153846155e-05, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:34:55", "remaining_time": "8:51:44"}
{"current_steps": 200, "total_steps": 3245, "eval_loss": 0.05595707520842552, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:37:29", "remaining_time": "9:30:42"}
{"current_steps": 210, "total_steps": 3245, "loss": 0.0653, "lr": 6.461538461538462e-05, "epoch": 0.3232012312427857, "percentage": 6.47, "elapsed_time": "0:38:54", "remaining_time": "9:22:22"}
{"current_steps": 220, "total_steps": 3245, "loss": 0.0615, "lr": 6.76923076923077e-05, "epoch": 0.3385917660638707, "percentage": 6.78, "elapsed_time": "0:40:15", "remaining_time": "9:13:28"}
{"current_steps": 230, "total_steps": 3245, "loss": 0.0462, "lr": 7.076923076923078e-05, "epoch": 0.35398230088495575, "percentage": 7.09, "elapsed_time": "0:41:35", "remaining_time": "9:05:18"}
{"current_steps": 240, "total_steps": 3245, "loss": 0.0586, "lr": 7.384615384615386e-05, "epoch": 0.3693728357060408, "percentage": 7.4, "elapsed_time": "0:42:56", "remaining_time": "8:57:43"}
{"current_steps": 250, "total_steps": 3245, "loss": 0.0544, "lr": 7.692307692307693e-05, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:44:18", "remaining_time": "8:50:44"}
{"current_steps": 250, "total_steps": 3245, "eval_loss": 0.05310456082224846, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:46:51", "remaining_time": "9:21:23"}
{"current_steps": 260, "total_steps": 3245, "loss": 0.0524, "lr": 8e-05, "epoch": 0.4001539053482108, "percentage": 8.01, "elapsed_time": "0:48:17", "remaining_time": "9:14:22"}
{"current_steps": 270, "total_steps": 3245, "loss": 0.0522, "lr": 8.307692307692309e-05, "epoch": 0.41554444016929587, "percentage": 8.32, "elapsed_time": "0:49:38", "remaining_time": "9:06:53"}
{"current_steps": 280, "total_steps": 3245, "loss": 0.0585, "lr": 8.615384615384617e-05, "epoch": 0.4309349749903809, "percentage": 8.63, "elapsed_time": "0:50:59", "remaining_time": "8:59:52"}
{"current_steps": 290, "total_steps": 3245, "loss": 0.0623, "lr": 8.923076923076924e-05, "epoch": 0.44632550981146596, "percentage": 8.94, "elapsed_time": "0:52:19", "remaining_time": "8:53:14"}
{"current_steps": 300, "total_steps": 3245, "loss": 0.0517, "lr": 9.230769230769232e-05, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:53:41", "remaining_time": "8:47:01"}
{"current_steps": 300, "total_steps": 3245, "eval_loss": 0.04978759214282036, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:56:14", "remaining_time": "9:12:09"}
{"current_steps": 310, "total_steps": 3245, "loss": 0.0583, "lr": 9.53846153846154e-05, "epoch": 0.477106579453636, "percentage": 9.55, "elapsed_time": "0:57:50", "remaining_time": "9:07:40"}
{"current_steps": 320, "total_steps": 3245, "loss": 0.063, "lr": 9.846153846153848e-05, "epoch": 0.49249711427472104, "percentage": 9.86, "elapsed_time": "0:59:11", "remaining_time": "9:01:02"}
{"current_steps": 330, "total_steps": 3245, "loss": 0.0562, "lr": 9.999927654251793e-05, "epoch": 0.5078876490958061, "percentage": 10.17, "elapsed_time": "1:00:32", "remaining_time": "8:54:45"}
{"current_steps": 340, "total_steps": 3245, "loss": 0.053, "lr": 9.99934890082745e-05, "epoch": 0.5232781839168911, "percentage": 10.48, "elapsed_time": "1:01:53", "remaining_time": "8:48:47"}
{"current_steps": 350, "total_steps": 3245, "loss": 0.0468, "lr": 9.99819146097084e-05, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:03:13", "remaining_time": "8:43:00"}
{"current_steps": 350, "total_steps": 3245, "eval_loss": 0.04682430624961853, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:05:47", "remaining_time": "9:04:12"}
{"current_steps": 360, "total_steps": 3245, "loss": 0.0587, "lr": 9.996455468658355e-05, "epoch": 0.5540592535590612, "percentage": 11.09, "elapsed_time": "1:07:12", "remaining_time": "8:58:39"}
{"current_steps": 370, "total_steps": 3245, "loss": 0.0445, "lr": 9.994141124835203e-05, "epoch": 0.5694497883801463, "percentage": 11.4, "elapsed_time": "1:08:33", "remaining_time": "8:52:43"}
{"current_steps": 380, "total_steps": 3245, "loss": 0.0453, "lr": 9.991248697392142e-05, "epoch": 0.5848403232012312, "percentage": 11.71, "elapsed_time": "1:09:54", "remaining_time": "8:47:05"}
{"current_steps": 390, "total_steps": 3245, "loss": 0.0418, "lr": 9.987778521134476e-05, "epoch": 0.6002308580223162, "percentage": 12.02, "elapsed_time": "1:11:15", "remaining_time": "8:41:38"}
{"current_steps": 400, "total_steps": 3245, "loss": 0.065, "lr": 9.983730997743294e-05, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:12:36", "remaining_time": "8:36:25"}
{"current_steps": 400, "total_steps": 3245, "eval_loss": 0.045511145144701004, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:15:10", "remaining_time": "8:54:38"}
{"current_steps": 410, "total_steps": 3245, "loss": 0.0439, "lr": 9.979106595728978e-05, "epoch": 0.6310119276644863, "percentage": 12.63, "elapsed_time": "1:16:45", "remaining_time": "8:50:48"}
{"current_steps": 420, "total_steps": 3245, "loss": 0.0534, "lr": 9.973905850376977e-05, "epoch": 0.6464024624855714, "percentage": 12.94, "elapsed_time": "1:18:06", "remaining_time": "8:45:25"}
{"current_steps": 430, "total_steps": 3245, "loss": 0.0475, "lr": 9.968129363685833e-05, "epoch": 0.6617929973066564, "percentage": 13.25, "elapsed_time": "1:19:27", "remaining_time": "8:40:13"}
{"current_steps": 440, "total_steps": 3245, "loss": 0.0605, "lr": 9.961777804297514e-05, "epoch": 0.6771835321277414, "percentage": 13.56, "elapsed_time": "1:20:48", "remaining_time": "8:35:10"}
{"current_steps": 450, "total_steps": 3245, "loss": 0.0349, "lr": 9.954851907420009e-05, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:22:10", "remaining_time": "8:30:22"}
{"current_steps": 450, "total_steps": 3245, "eval_loss": 0.043942831456661224, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:24:43", "remaining_time": "8:46:16"}
{"current_steps": 460, "total_steps": 3245, "loss": 0.0363, "lr": 9.947352474742222e-05, "epoch": 0.7079646017699115, "percentage": 14.18, "elapsed_time": "1:26:09", "remaining_time": "8:41:37"}
{"current_steps": 470, "total_steps": 3245, "loss": 0.0303, "lr": 9.93928037434118e-05, "epoch": 0.7233551365909965, "percentage": 14.48, "elapsed_time": "1:27:30", "remaining_time": "8:36:39"}
{"current_steps": 480, "total_steps": 3245, "loss": 0.0352, "lr": 9.930636540581556e-05, "epoch": 0.7387456714120816, "percentage": 14.79, "elapsed_time": "1:28:51", "remaining_time": "8:31:49"}
{"current_steps": 490, "total_steps": 3245, "loss": 0.0393, "lr": 9.921421974007506e-05, "epoch": 0.7541362062331666, "percentage": 15.1, "elapsed_time": "1:30:12", "remaining_time": "8:27:09"}
{"current_steps": 500, "total_steps": 3245, "loss": 0.0292, "lr": 9.911637741226849e-05, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:31:33", "remaining_time": "8:22:39"}
{"current_steps": 500, "total_steps": 3245, "eval_loss": 0.040697645395994186, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:34:07", "remaining_time": "8:36:42"}
{"current_steps": 510, "total_steps": 3245, "loss": 0.0326, "lr": 9.90128497478762e-05, "epoch": 0.7849172758753367, "percentage": 15.72, "elapsed_time": "1:35:32", "remaining_time": "8:32:24"}
{"current_steps": 520, "total_steps": 3245, "loss": 0.0497, "lr": 9.890364873046965e-05, "epoch": 0.8003078106964217, "percentage": 16.02, "elapsed_time": "1:36:53", "remaining_time": "8:27:45"}
{"current_steps": 530, "total_steps": 3245, "loss": 0.0629, "lr": 9.878878700032427e-05, "epoch": 0.8156983455175068, "percentage": 16.33, "elapsed_time": "1:38:14", "remaining_time": "8:23:14"}
{"current_steps": 540, "total_steps": 3245, "loss": 0.0417, "lr": 9.866827785295638e-05, "epoch": 0.8310888803385917, "percentage": 16.64, "elapsed_time": "1:39:34", "remaining_time": "8:18:49"}
{"current_steps": 550, "total_steps": 3245, "loss": 0.0477, "lr": 9.854213523758413e-05, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:40:55", "remaining_time": "8:14:32"}
{"current_steps": 550, "total_steps": 3245, "eval_loss": 0.03853714093565941, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:43:29", "remaining_time": "8:27:05"}