chchen's picture
Training in progress, step 80
c3fb193 verified
raw
history blame
16.7 kB
{"current_steps": 1, "total_steps": 125, "loss": 0.3801, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:35", "remaining_time": "1:13:35"}
{"current_steps": 2, "total_steps": 125, "loss": 0.3998, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:10", "remaining_time": "1:12:30"}
{"current_steps": 3, "total_steps": 125, "loss": 0.3922, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:42", "remaining_time": "1:09:41"}
{"current_steps": 4, "total_steps": 125, "loss": 0.3526, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:02:26", "remaining_time": "1:13:54"}
{"current_steps": 5, "total_steps": 125, "loss": 0.4106, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:02:58", "remaining_time": "1:11:35"}
{"current_steps": 6, "total_steps": 125, "loss": 0.3415, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:03:44", "remaining_time": "1:14:03"}
{"current_steps": 7, "total_steps": 125, "loss": 0.3451, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:04:20", "remaining_time": "1:13:15"}
{"current_steps": 8, "total_steps": 125, "loss": 0.3091, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:04:56", "remaining_time": "1:12:09"}
{"current_steps": 9, "total_steps": 125, "loss": 0.3165, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:05:27", "remaining_time": "1:10:22"}
{"current_steps": 10, "total_steps": 125, "loss": 0.2596, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:06:03", "remaining_time": "1:09:36"}
{"current_steps": 10, "total_steps": 125, "eval_loss": 0.2647669315338135, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:06:30", "remaining_time": "1:14:45"}
{"current_steps": 11, "total_steps": 125, "loss": 0.2365, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:07:12", "remaining_time": "1:14:43"}
{"current_steps": 12, "total_steps": 125, "loss": 0.2335, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:07:49", "remaining_time": "1:13:41"}
{"current_steps": 13, "total_steps": 125, "loss": 0.2001, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:08:29", "remaining_time": "1:13:07"}
{"current_steps": 14, "total_steps": 125, "loss": 0.1965, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:09:03", "remaining_time": "1:11:49"}
{"current_steps": 15, "total_steps": 125, "loss": 0.2116, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:09:34", "remaining_time": "1:10:14"}
{"current_steps": 16, "total_steps": 125, "loss": 0.1727, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:10:07", "remaining_time": "1:08:57"}
{"current_steps": 17, "total_steps": 125, "loss": 0.1671, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:10:43", "remaining_time": "1:08:10"}
{"current_steps": 18, "total_steps": 125, "loss": 0.1546, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:11:17", "remaining_time": "1:07:08"}
{"current_steps": 19, "total_steps": 125, "loss": 0.1469, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:11:50", "remaining_time": "1:06:04"}
{"current_steps": 20, "total_steps": 125, "loss": 0.1329, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:12:25", "remaining_time": "1:05:13"}
{"current_steps": 20, "total_steps": 125, "eval_loss": 0.1412116140127182, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:12:52", "remaining_time": "1:07:33"}
{"current_steps": 21, "total_steps": 125, "loss": 0.1555, "lr": 9.874639560909117e-05, "epoch": 0.8296296296296296, "percentage": 16.8, "elapsed_time": "0:13:34", "remaining_time": "1:07:11"}
{"current_steps": 22, "total_steps": 125, "loss": 0.1543, "lr": 9.841517610611309e-05, "epoch": 0.8691358024691358, "percentage": 17.6, "elapsed_time": "0:14:05", "remaining_time": "1:06:00"}
{"current_steps": 23, "total_steps": 125, "loss": 0.1194, "lr": 9.804586609725499e-05, "epoch": 0.908641975308642, "percentage": 18.4, "elapsed_time": "0:14:39", "remaining_time": "1:05:00"}
{"current_steps": 24, "total_steps": 125, "loss": 0.1116, "lr": 9.763875613614482e-05, "epoch": 0.9481481481481482, "percentage": 19.2, "elapsed_time": "0:15:08", "remaining_time": "1:03:42"}
{"current_steps": 25, "total_steps": 125, "loss": 0.109, "lr": 9.719416651541839e-05, "epoch": 0.9876543209876543, "percentage": 20.0, "elapsed_time": "0:15:44", "remaining_time": "1:02:56"}
{"current_steps": 26, "total_steps": 125, "loss": 0.2163, "lr": 9.671244701472999e-05, "epoch": 1.0271604938271606, "percentage": 20.8, "elapsed_time": "0:16:23", "remaining_time": "1:02:24"}
{"current_steps": 27, "total_steps": 125, "loss": 0.0916, "lr": 9.619397662556435e-05, "epoch": 1.0666666666666667, "percentage": 21.6, "elapsed_time": "0:16:57", "remaining_time": "1:01:33"}
{"current_steps": 28, "total_steps": 125, "loss": 0.1117, "lr": 9.563916325306594e-05, "epoch": 1.106172839506173, "percentage": 22.4, "elapsed_time": "0:17:39", "remaining_time": "1:01:09"}
{"current_steps": 29, "total_steps": 125, "loss": 0.1135, "lr": 9.504844339512095e-05, "epoch": 1.145679012345679, "percentage": 23.2, "elapsed_time": "0:18:21", "remaining_time": "1:00:46"}
{"current_steps": 30, "total_steps": 125, "loss": 0.1064, "lr": 9.442228179894362e-05, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:18:55", "remaining_time": "0:59:55"}
{"current_steps": 30, "total_steps": 125, "eval_loss": 0.10077542066574097, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:19:22", "remaining_time": "1:01:20"}
{"current_steps": 31, "total_steps": 125, "loss": 0.0736, "lr": 9.376117109543769e-05, "epoch": 1.2246913580246914, "percentage": 24.8, "elapsed_time": "0:19:54", "remaining_time": "1:00:21"}
{"current_steps": 32, "total_steps": 125, "loss": 0.1029, "lr": 9.306563141162046e-05, "epoch": 1.2641975308641975, "percentage": 25.6, "elapsed_time": "0:20:32", "remaining_time": "0:59:43"}
{"current_steps": 33, "total_steps": 125, "loss": 0.1009, "lr": 9.233620996141421e-05, "epoch": 1.3037037037037038, "percentage": 26.4, "elapsed_time": "0:21:08", "remaining_time": "0:58:56"}
{"current_steps": 34, "total_steps": 125, "loss": 0.0811, "lr": 9.157348061512727e-05, "epoch": 1.34320987654321, "percentage": 27.2, "elapsed_time": "0:21:40", "remaining_time": "0:58:01"}
{"current_steps": 35, "total_steps": 125, "loss": 0.0929, "lr": 9.077804344796302e-05, "epoch": 1.382716049382716, "percentage": 28.0, "elapsed_time": "0:22:14", "remaining_time": "0:57:10"}
{"current_steps": 36, "total_steps": 125, "loss": 0.0924, "lr": 8.995052426791247e-05, "epoch": 1.4222222222222223, "percentage": 28.8, "elapsed_time": "0:22:54", "remaining_time": "0:56:38"}
{"current_steps": 37, "total_steps": 125, "loss": 0.0908, "lr": 8.90915741234015e-05, "epoch": 1.4617283950617284, "percentage": 29.6, "elapsed_time": "0:23:30", "remaining_time": "0:55:54"}
{"current_steps": 38, "total_steps": 125, "loss": 0.0701, "lr": 8.820186879108038e-05, "epoch": 1.5012345679012347, "percentage": 30.4, "elapsed_time": "0:24:01", "remaining_time": "0:55:00"}
{"current_steps": 39, "total_steps": 125, "loss": 0.0792, "lr": 8.728210824415827e-05, "epoch": 1.5407407407407407, "percentage": 31.2, "elapsed_time": "0:24:37", "remaining_time": "0:54:18"}
{"current_steps": 40, "total_steps": 125, "loss": 0.0896, "lr": 8.633301610170135e-05, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:25:19", "remaining_time": "0:53:49"}
{"current_steps": 40, "total_steps": 125, "eval_loss": 0.07914844900369644, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:25:46", "remaining_time": "0:54:45"}
{"current_steps": 41, "total_steps": 125, "loss": 0.0726, "lr": 8.535533905932738e-05, "epoch": 1.6197530864197531, "percentage": 32.8, "elapsed_time": "0:26:23", "remaining_time": "0:54:03"}
{"current_steps": 42, "total_steps": 125, "loss": 0.0742, "lr": 8.434984630174509e-05, "epoch": 1.6592592592592592, "percentage": 33.6, "elapsed_time": "0:26:52", "remaining_time": "0:53:06"}
{"current_steps": 43, "total_steps": 125, "loss": 0.0859, "lr": 8.33173288976002e-05, "epoch": 1.6987654320987655, "percentage": 34.4, "elapsed_time": "0:27:30", "remaining_time": "0:52:26"}
{"current_steps": 44, "total_steps": 125, "loss": 0.0838, "lr": 8.225859917710439e-05, "epoch": 1.7382716049382716, "percentage": 35.2, "elapsed_time": "0:28:04", "remaining_time": "0:51:40"}
{"current_steps": 45, "total_steps": 125, "loss": 0.0729, "lr": 8.117449009293668e-05, "epoch": 1.7777777777777777, "percentage": 36.0, "elapsed_time": "0:28:39", "remaining_time": "0:50:57"}
{"current_steps": 46, "total_steps": 125, "loss": 0.0748, "lr": 8.006585456492029e-05, "epoch": 1.817283950617284, "percentage": 36.8, "elapsed_time": "0:29:10", "remaining_time": "0:50:06"}
{"current_steps": 47, "total_steps": 125, "loss": 0.0801, "lr": 7.89335648089903e-05, "epoch": 1.8567901234567903, "percentage": 37.6, "elapsed_time": "0:29:45", "remaining_time": "0:49:23"}
{"current_steps": 48, "total_steps": 125, "loss": 0.0697, "lr": 7.777851165098012e-05, "epoch": 1.8962962962962964, "percentage": 38.4, "elapsed_time": "0:30:20", "remaining_time": "0:48:39"}
{"current_steps": 49, "total_steps": 125, "loss": 0.0601, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:30:54", "remaining_time": "0:47:55"}
{"current_steps": 50, "total_steps": 125, "loss": 0.0653, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:31:30", "remaining_time": "0:47:15"}
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.06871605664491653, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:31:56", "remaining_time": "0:47:55"}
{"current_steps": 51, "total_steps": 125, "loss": 0.1005, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:32:33", "remaining_time": "0:47:13"}
{"current_steps": 52, "total_steps": 125, "loss": 0.0587, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:33:07", "remaining_time": "0:46:29"}
{"current_steps": 53, "total_steps": 125, "loss": 0.055, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:33:42", "remaining_time": "0:45:47"}
{"current_steps": 54, "total_steps": 125, "loss": 0.0703, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:34:22", "remaining_time": "0:45:11"}
{"current_steps": 55, "total_steps": 125, "loss": 0.0628, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:34:55", "remaining_time": "0:44:27"}
{"current_steps": 56, "total_steps": 125, "loss": 0.0606, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:35:32", "remaining_time": "0:43:47"}
{"current_steps": 57, "total_steps": 125, "loss": 0.0842, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:36:20", "remaining_time": "0:43:21"}
{"current_steps": 58, "total_steps": 125, "loss": 0.0496, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:36:54", "remaining_time": "0:42:38"}
{"current_steps": 59, "total_steps": 125, "loss": 0.0566, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:37:25", "remaining_time": "0:41:51"}
{"current_steps": 60, "total_steps": 125, "loss": 0.0631, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:37:58", "remaining_time": "0:41:07"}
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.06542201340198517, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:38:24", "remaining_time": "0:41:36"}
{"current_steps": 61, "total_steps": 125, "loss": 0.0592, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:39:02", "remaining_time": "0:40:58"}
{"current_steps": 62, "total_steps": 125, "loss": 0.0577, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:39:35", "remaining_time": "0:40:13"}
{"current_steps": 63, "total_steps": 125, "loss": 0.0478, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:40:04", "remaining_time": "0:39:26"}
{"current_steps": 64, "total_steps": 125, "loss": 0.0541, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:40:36", "remaining_time": "0:38:42"}
{"current_steps": 65, "total_steps": 125, "loss": 0.0706, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:41:16", "remaining_time": "0:38:06"}
{"current_steps": 66, "total_steps": 125, "loss": 0.0446, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:41:50", "remaining_time": "0:37:24"}
{"current_steps": 67, "total_steps": 125, "loss": 0.0582, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:42:30", "remaining_time": "0:36:47"}
{"current_steps": 68, "total_steps": 125, "loss": 0.047, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:43:07", "remaining_time": "0:36:08"}
{"current_steps": 69, "total_steps": 125, "loss": 0.0549, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:43:44", "remaining_time": "0:35:30"}
{"current_steps": 70, "total_steps": 125, "loss": 0.0644, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:44:21", "remaining_time": "0:34:51"}
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.06151283532381058, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:44:48", "remaining_time": "0:35:12"}
{"current_steps": 71, "total_steps": 125, "loss": 0.0511, "lr": 4.7196477638140404e-05, "epoch": 2.8049382716049385, "percentage": 56.8, "elapsed_time": "0:45:26", "remaining_time": "0:34:33"}
{"current_steps": 72, "total_steps": 125, "loss": 0.0618, "lr": 4.579747375353763e-05, "epoch": 2.8444444444444446, "percentage": 57.6, "elapsed_time": "0:46:01", "remaining_time": "0:33:52"}
{"current_steps": 73, "total_steps": 125, "loss": 0.0473, "lr": 4.4401776194834613e-05, "epoch": 2.8839506172839506, "percentage": 58.4, "elapsed_time": "0:46:35", "remaining_time": "0:33:11"}
{"current_steps": 74, "total_steps": 125, "loss": 0.0543, "lr": 4.3010483023225045e-05, "epoch": 2.9234567901234567, "percentage": 59.2, "elapsed_time": "0:47:13", "remaining_time": "0:32:32"}
{"current_steps": 75, "total_steps": 125, "loss": 0.0493, "lr": 4.162468883476319e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "0:47:46", "remaining_time": "0:31:50"}
{"current_steps": 76, "total_steps": 125, "loss": 0.0864, "lr": 4.0245483899193595e-05, "epoch": 3.0024691358024693, "percentage": 60.8, "elapsed_time": "0:48:14", "remaining_time": "0:31:06"}
{"current_steps": 77, "total_steps": 125, "loss": 0.0469, "lr": 3.887395330218429e-05, "epoch": 3.0419753086419754, "percentage": 61.6, "elapsed_time": "0:48:46", "remaining_time": "0:30:24"}
{"current_steps": 78, "total_steps": 125, "loss": 0.055, "lr": 3.7511176091638653e-05, "epoch": 3.0814814814814815, "percentage": 62.4, "elapsed_time": "0:49:32", "remaining_time": "0:29:50"}
{"current_steps": 79, "total_steps": 125, "loss": 0.0541, "lr": 3.6158224428757535e-05, "epoch": 3.1209876543209876, "percentage": 63.2, "elapsed_time": "0:50:04", "remaining_time": "0:29:09"}
{"current_steps": 80, "total_steps": 125, "loss": 0.053, "lr": 3.4816162744519263e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:50:37", "remaining_time": "0:28:28"}
{"current_steps": 80, "total_steps": 125, "eval_loss": 0.0588352307677269, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:51:04", "remaining_time": "0:28:43"}