chchen's picture
Training in progress, step 750
b09e123 verified
raw
history blame
18.1 kB
{"current_steps": 10, "total_steps": 3245, "loss": 2.0, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:25", "remaining_time": "7:40:22"}
{"current_steps": 20, "total_steps": 3245, "loss": 1.9308, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:50", "remaining_time": "7:37:30"}
{"current_steps": 30, "total_steps": 3245, "loss": 1.7153, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:15", "remaining_time": "7:36:51"}
{"current_steps": 40, "total_steps": 3245, "loss": 1.3784, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:05:40", "remaining_time": "7:35:03"}
{"current_steps": 50, "total_steps": 3245, "loss": 0.8721, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:07:05", "remaining_time": "7:33:30"}
{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.6930733919143677, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:09:47", "remaining_time": "10:26:00"}
{"current_steps": 60, "total_steps": 3245, "loss": 0.5895, "lr": 1.8461538461538465e-05, "epoch": 0.0923432089265102, "percentage": 1.85, "elapsed_time": "0:11:16", "remaining_time": "9:58:51"}
{"current_steps": 70, "total_steps": 3245, "loss": 0.4074, "lr": 2.1538461538461542e-05, "epoch": 0.10773374374759523, "percentage": 2.16, "elapsed_time": "0:12:41", "remaining_time": "9:35:42"}
{"current_steps": 80, "total_steps": 3245, "loss": 0.2138, "lr": 2.461538461538462e-05, "epoch": 0.12312427856868026, "percentage": 2.47, "elapsed_time": "0:14:06", "remaining_time": "9:18:22"}
{"current_steps": 90, "total_steps": 3245, "loss": 0.2181, "lr": 2.7692307692307694e-05, "epoch": 0.1385148133897653, "percentage": 2.77, "elapsed_time": "0:15:31", "remaining_time": "9:04:26"}
{"current_steps": 100, "total_steps": 3245, "loss": 0.1563, "lr": 3.0769230769230774e-05, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:16:57", "remaining_time": "8:53:06"}
{"current_steps": 100, "total_steps": 3245, "eval_loss": 0.10821972787380219, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:19:38", "remaining_time": "10:17:56"}
{"current_steps": 110, "total_steps": 3245, "loss": 0.1099, "lr": 3.384615384615385e-05, "epoch": 0.16929588303193535, "percentage": 3.39, "elapsed_time": "0:21:08", "remaining_time": "10:02:23"}
{"current_steps": 120, "total_steps": 3245, "loss": 0.1087, "lr": 3.692307692307693e-05, "epoch": 0.1846864178530204, "percentage": 3.7, "elapsed_time": "0:22:33", "remaining_time": "9:47:28"}
{"current_steps": 130, "total_steps": 3245, "loss": 0.0778, "lr": 4e-05, "epoch": 0.2000769526741054, "percentage": 4.01, "elapsed_time": "0:23:58", "remaining_time": "9:34:30"}
{"current_steps": 140, "total_steps": 3245, "loss": 0.0835, "lr": 4.3076923076923084e-05, "epoch": 0.21546748749519046, "percentage": 4.31, "elapsed_time": "0:25:23", "remaining_time": "9:23:16"}
{"current_steps": 150, "total_steps": 3245, "loss": 0.0879, "lr": 4.615384615384616e-05, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:26:48", "remaining_time": "9:13:11"}
{"current_steps": 150, "total_steps": 3245, "eval_loss": 0.07276571542024612, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:29:30", "remaining_time": "10:08:50"}
{"current_steps": 160, "total_steps": 3245, "loss": 0.0827, "lr": 4.923076923076924e-05, "epoch": 0.24624855713736052, "percentage": 4.93, "elapsed_time": "0:30:59", "remaining_time": "9:57:41"}
{"current_steps": 170, "total_steps": 3245, "loss": 0.0748, "lr": 5.230769230769231e-05, "epoch": 0.26163909195844554, "percentage": 5.24, "elapsed_time": "0:32:25", "remaining_time": "9:46:25"}
{"current_steps": 180, "total_steps": 3245, "loss": 0.0593, "lr": 5.538461538461539e-05, "epoch": 0.2770296267795306, "percentage": 5.55, "elapsed_time": "0:33:49", "remaining_time": "9:36:02"}
{"current_steps": 190, "total_steps": 3245, "loss": 0.0522, "lr": 5.846153846153847e-05, "epoch": 0.2924201616006156, "percentage": 5.86, "elapsed_time": "0:35:14", "remaining_time": "9:26:45"}
{"current_steps": 200, "total_steps": 3245, "loss": 0.0734, "lr": 6.153846153846155e-05, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:36:40", "remaining_time": "9:18:19"}
{"current_steps": 200, "total_steps": 3245, "eval_loss": 0.05593929439783096, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:39:22", "remaining_time": "9:59:25"}
{"current_steps": 210, "total_steps": 3245, "loss": 0.0646, "lr": 6.461538461538462e-05, "epoch": 0.3232012312427857, "percentage": 6.47, "elapsed_time": "0:40:51", "remaining_time": "9:50:24"}
{"current_steps": 220, "total_steps": 3245, "loss": 0.0611, "lr": 6.76923076923077e-05, "epoch": 0.3385917660638707, "percentage": 6.78, "elapsed_time": "0:42:15", "remaining_time": "9:41:04"}
{"current_steps": 230, "total_steps": 3245, "loss": 0.0462, "lr": 7.076923076923078e-05, "epoch": 0.35398230088495575, "percentage": 7.09, "elapsed_time": "0:43:40", "remaining_time": "9:32:32"}
{"current_steps": 240, "total_steps": 3245, "loss": 0.0588, "lr": 7.384615384615386e-05, "epoch": 0.3693728357060408, "percentage": 7.4, "elapsed_time": "0:45:05", "remaining_time": "9:24:36"}
{"current_steps": 250, "total_steps": 3245, "loss": 0.0548, "lr": 7.692307692307693e-05, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:46:31", "remaining_time": "9:17:16"}
{"current_steps": 250, "total_steps": 3245, "eval_loss": 0.05322062969207764, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:49:12", "remaining_time": "9:49:35"}
{"current_steps": 260, "total_steps": 3245, "loss": 0.0524, "lr": 8e-05, "epoch": 0.4001539053482108, "percentage": 8.01, "elapsed_time": "0:50:42", "remaining_time": "9:42:10"}
{"current_steps": 270, "total_steps": 3245, "loss": 0.052, "lr": 8.307692307692309e-05, "epoch": 0.41554444016929587, "percentage": 8.32, "elapsed_time": "0:52:07", "remaining_time": "9:34:19"}
{"current_steps": 280, "total_steps": 3245, "loss": 0.0584, "lr": 8.615384615384617e-05, "epoch": 0.4309349749903809, "percentage": 8.63, "elapsed_time": "0:53:32", "remaining_time": "9:26:58"}
{"current_steps": 290, "total_steps": 3245, "loss": 0.0617, "lr": 8.923076923076924e-05, "epoch": 0.44632550981146596, "percentage": 8.94, "elapsed_time": "0:54:57", "remaining_time": "9:20:01"}
{"current_steps": 300, "total_steps": 3245, "loss": 0.0519, "lr": 9.230769230769232e-05, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:56:23", "remaining_time": "9:13:30"}
{"current_steps": 300, "total_steps": 3245, "eval_loss": 0.049991585314273834, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "0:59:04", "remaining_time": "9:39:58"}
{"current_steps": 310, "total_steps": 3245, "loss": 0.0575, "lr": 9.53846153846154e-05, "epoch": 0.477106579453636, "percentage": 9.55, "elapsed_time": "1:00:43", "remaining_time": "9:34:54"}
{"current_steps": 320, "total_steps": 3245, "loss": 0.0621, "lr": 9.846153846153848e-05, "epoch": 0.49249711427472104, "percentage": 9.86, "elapsed_time": "1:02:08", "remaining_time": "9:27:58"}
{"current_steps": 330, "total_steps": 3245, "loss": 0.0563, "lr": 9.999927654251793e-05, "epoch": 0.5078876490958061, "percentage": 10.17, "elapsed_time": "1:03:33", "remaining_time": "9:21:23"}
{"current_steps": 340, "total_steps": 3245, "loss": 0.0521, "lr": 9.99934890082745e-05, "epoch": 0.5232781839168911, "percentage": 10.48, "elapsed_time": "1:04:58", "remaining_time": "9:15:08"}
{"current_steps": 350, "total_steps": 3245, "loss": 0.0463, "lr": 9.99819146097084e-05, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:06:23", "remaining_time": "9:09:05"}
{"current_steps": 350, "total_steps": 3245, "eval_loss": 0.0476096011698246, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:09:04", "remaining_time": "9:31:24"}
{"current_steps": 360, "total_steps": 3245, "loss": 0.0585, "lr": 9.996455468658355e-05, "epoch": 0.5540592535590612, "percentage": 11.09, "elapsed_time": "1:10:33", "remaining_time": "9:25:28"}
{"current_steps": 370, "total_steps": 3245, "loss": 0.0449, "lr": 9.994141124835203e-05, "epoch": 0.5694497883801463, "percentage": 11.4, "elapsed_time": "1:11:58", "remaining_time": "9:19:14"}
{"current_steps": 380, "total_steps": 3245, "loss": 0.0452, "lr": 9.991248697392142e-05, "epoch": 0.5848403232012312, "percentage": 11.71, "elapsed_time": "1:13:23", "remaining_time": "9:13:21"}
{"current_steps": 390, "total_steps": 3245, "loss": 0.0429, "lr": 9.987778521134476e-05, "epoch": 0.6002308580223162, "percentage": 12.02, "elapsed_time": "1:14:48", "remaining_time": "9:07:39"}
{"current_steps": 400, "total_steps": 3245, "loss": 0.0622, "lr": 9.983730997743294e-05, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:16:13", "remaining_time": "9:02:12"}
{"current_steps": 400, "total_steps": 3245, "eval_loss": 0.0440874807536602, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:18:55", "remaining_time": "9:21:23"}
{"current_steps": 410, "total_steps": 3245, "loss": 0.0421, "lr": 9.979106595728978e-05, "epoch": 0.6310119276644863, "percentage": 12.63, "elapsed_time": "1:20:34", "remaining_time": "9:17:06"}
{"current_steps": 420, "total_steps": 3245, "loss": 0.0543, "lr": 9.973905850376977e-05, "epoch": 0.6464024624855714, "percentage": 12.94, "elapsed_time": "1:21:59", "remaining_time": "9:11:28"}
{"current_steps": 430, "total_steps": 3245, "loss": 0.0477, "lr": 9.968129363685833e-05, "epoch": 0.6617929973066564, "percentage": 13.25, "elapsed_time": "1:23:24", "remaining_time": "9:06:01"}
{"current_steps": 440, "total_steps": 3245, "loss": 0.0614, "lr": 9.961777804297514e-05, "epoch": 0.6771835321277414, "percentage": 13.56, "elapsed_time": "1:24:49", "remaining_time": "9:00:44"}
{"current_steps": 450, "total_steps": 3245, "loss": 0.0345, "lr": 9.954851907420009e-05, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:26:15", "remaining_time": "8:55:43"}
{"current_steps": 450, "total_steps": 3245, "eval_loss": 0.04345938190817833, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:28:56", "remaining_time": "9:12:28"}
{"current_steps": 460, "total_steps": 3245, "loss": 0.0356, "lr": 9.947352474742222e-05, "epoch": 0.7079646017699115, "percentage": 14.18, "elapsed_time": "1:30:38", "remaining_time": "9:08:48"}
{"current_steps": 470, "total_steps": 3245, "loss": 0.0297, "lr": 9.93928037434118e-05, "epoch": 0.7233551365909965, "percentage": 14.48, "elapsed_time": "1:32:03", "remaining_time": "9:03:34"}
{"current_steps": 480, "total_steps": 3245, "loss": 0.0356, "lr": 9.930636540581556e-05, "epoch": 0.7387456714120816, "percentage": 14.79, "elapsed_time": "1:33:28", "remaining_time": "8:58:29"}
{"current_steps": 490, "total_steps": 3245, "loss": 0.041, "lr": 9.921421974007506e-05, "epoch": 0.7541362062331666, "percentage": 15.1, "elapsed_time": "1:34:54", "remaining_time": "8:53:35"}
{"current_steps": 500, "total_steps": 3245, "loss": 0.0317, "lr": 9.911637741226849e-05, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:36:19", "remaining_time": "8:48:51"}
{"current_steps": 500, "total_steps": 3245, "eval_loss": 0.04137541353702545, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:39:01", "remaining_time": "9:03:39"}
{"current_steps": 510, "total_steps": 3245, "loss": 0.0336, "lr": 9.90128497478762e-05, "epoch": 0.7849172758753367, "percentage": 15.72, "elapsed_time": "1:40:31", "remaining_time": "8:59:06"}
{"current_steps": 520, "total_steps": 3245, "loss": 0.0495, "lr": 9.890364873046965e-05, "epoch": 0.8003078106964217, "percentage": 16.02, "elapsed_time": "1:41:56", "remaining_time": "8:54:13"}
{"current_steps": 530, "total_steps": 3245, "loss": 0.0648, "lr": 9.878878700032427e-05, "epoch": 0.8156983455175068, "percentage": 16.33, "elapsed_time": "1:43:21", "remaining_time": "8:49:28"}
{"current_steps": 540, "total_steps": 3245, "loss": 0.0418, "lr": 9.866827785295638e-05, "epoch": 0.8310888803385917, "percentage": 16.64, "elapsed_time": "1:44:46", "remaining_time": "8:44:49"}
{"current_steps": 550, "total_steps": 3245, "loss": 0.048, "lr": 9.854213523758413e-05, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:46:11", "remaining_time": "8:40:19"}
{"current_steps": 550, "total_steps": 3245, "eval_loss": 0.03805786743760109, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:48:53", "remaining_time": "8:53:33"}
{"current_steps": 560, "total_steps": 3245, "loss": 0.0322, "lr": 9.841037375551294e-05, "epoch": 0.8618699499807618, "percentage": 17.26, "elapsed_time": "1:50:22", "remaining_time": "8:49:12"}
{"current_steps": 570, "total_steps": 3245, "loss": 0.0322, "lr": 9.827300865844527e-05, "epoch": 0.8772604848018468, "percentage": 17.57, "elapsed_time": "1:51:47", "remaining_time": "8:44:39"}
{"current_steps": 580, "total_steps": 3245, "loss": 0.0391, "lr": 9.813005584671522e-05, "epoch": 0.8926510196229319, "percentage": 17.87, "elapsed_time": "1:53:12", "remaining_time": "8:40:12"}
{"current_steps": 590, "total_steps": 3245, "loss": 0.0549, "lr": 9.79815318674481e-05, "epoch": 0.9080415544440169, "percentage": 18.18, "elapsed_time": "1:54:38", "remaining_time": "8:35:51"}
{"current_steps": 600, "total_steps": 3245, "loss": 0.0373, "lr": 9.782745391264498e-05, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "1:56:03", "remaining_time": "8:31:37"}
{"current_steps": 600, "total_steps": 3245, "eval_loss": 0.037635400891304016, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "1:58:45", "remaining_time": "8:43:30"}
{"current_steps": 610, "total_steps": 3245, "loss": 0.0368, "lr": 9.76678398171927e-05, "epoch": 0.938822624086187, "percentage": 18.8, "elapsed_time": "2:00:13", "remaining_time": "8:39:21"}
{"current_steps": 620, "total_steps": 3245, "loss": 0.0393, "lr": 9.750270805679945e-05, "epoch": 0.954213158907272, "percentage": 19.11, "elapsed_time": "2:01:38", "remaining_time": "8:35:02"}
{"current_steps": 630, "total_steps": 3245, "loss": 0.0442, "lr": 9.733207774585618e-05, "epoch": 0.9696036937283571, "percentage": 19.41, "elapsed_time": "2:03:03", "remaining_time": "8:30:48"}
{"current_steps": 640, "total_steps": 3245, "loss": 0.0367, "lr": 9.715596863522398e-05, "epoch": 0.9849942285494421, "percentage": 19.72, "elapsed_time": "2:04:28", "remaining_time": "8:26:38"}
{"current_steps": 650, "total_steps": 3245, "loss": 0.0312, "lr": 9.697440110994801e-05, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:05:53", "remaining_time": "8:22:35"}
{"current_steps": 650, "total_steps": 3245, "eval_loss": 0.036002594977617264, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:08:35", "remaining_time": "8:33:21"}
{"current_steps": 660, "total_steps": 3245, "loss": 0.0382, "lr": 9.678739618689775e-05, "epoch": 1.0157752981916122, "percentage": 20.34, "elapsed_time": "2:10:05", "remaining_time": "8:29:29"}
{"current_steps": 670, "total_steps": 3245, "loss": 0.0369, "lr": 9.659497551233431e-05, "epoch": 1.0311658330126972, "percentage": 20.65, "elapsed_time": "2:11:30", "remaining_time": "8:25:26"}
{"current_steps": 680, "total_steps": 3245, "loss": 0.0325, "lr": 9.639716135940485e-05, "epoch": 1.0465563678337821, "percentage": 20.96, "elapsed_time": "2:12:55", "remaining_time": "8:21:23"}
{"current_steps": 690, "total_steps": 3245, "loss": 0.0474, "lr": 9.619397662556435e-05, "epoch": 1.0619469026548674, "percentage": 21.26, "elapsed_time": "2:14:19", "remaining_time": "8:17:25"}
{"current_steps": 700, "total_steps": 3245, "loss": 0.0362, "lr": 9.598544482992517e-05, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:15:45", "remaining_time": "8:13:33"}
{"current_steps": 700, "total_steps": 3245, "eval_loss": 0.03780118748545647, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:18:27", "remaining_time": "8:23:22"}
{"current_steps": 710, "total_steps": 3245, "loss": 0.0312, "lr": 9.57715901105348e-05, "epoch": 1.0927279722970373, "percentage": 21.88, "elapsed_time": "2:19:56", "remaining_time": "8:19:38"}
{"current_steps": 720, "total_steps": 3245, "loss": 0.0267, "lr": 9.555243722158158e-05, "epoch": 1.1081185071181223, "percentage": 22.19, "elapsed_time": "2:21:21", "remaining_time": "8:15:44"}
{"current_steps": 730, "total_steps": 3245, "loss": 0.0321, "lr": 9.532801153052958e-05, "epoch": 1.1235090419392073, "percentage": 22.5, "elapsed_time": "2:22:46", "remaining_time": "8:11:55"}
{"current_steps": 740, "total_steps": 3245, "loss": 0.0376, "lr": 9.509833901518209e-05, "epoch": 1.1388995767602923, "percentage": 22.8, "elapsed_time": "2:24:12", "remaining_time": "8:08:09"}
{"current_steps": 750, "total_steps": 3245, "loss": 0.03, "lr": 9.486344626067475e-05, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:25:37", "remaining_time": "8:04:25"}
{"current_steps": 750, "total_steps": 3245, "eval_loss": 0.03487715125083923, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:28:19", "remaining_time": "8:13:24"}
{"current_steps": 760, "total_steps": 3245, "loss": 0.0377, "lr": 9.462336045639815e-05, "epoch": 1.1696806464024625, "percentage": 23.42, "elapsed_time": "2:29:48", "remaining_time": "8:09:48"}
{"current_steps": 770, "total_steps": 3245, "loss": 0.0407, "lr": 9.437810939285068e-05, "epoch": 1.1850711812235475, "percentage": 23.73, "elapsed_time": "2:31:13", "remaining_time": "8:06:04"}
{"current_steps": 780, "total_steps": 3245, "loss": 0.0325, "lr": 9.412772145842165e-05, "epoch": 1.2004617160446325, "percentage": 24.04, "elapsed_time": "2:32:38", "remaining_time": "8:02:23"}
{"current_steps": 790, "total_steps": 3245, "loss": 0.0342, "lr": 9.387222563610535e-05, "epoch": 1.2158522508657175, "percentage": 24.35, "elapsed_time": "2:34:03", "remaining_time": "7:58:45"}