chchen's picture
Training in progress, step 70
eb80002 verified
{"current_steps": 1, "total_steps": 125, "loss": 0.1451, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:45", "remaining_time": "1:34:24"}
{"current_steps": 2, "total_steps": 125, "loss": 0.1334, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:31", "remaining_time": "1:34:09"}
{"current_steps": 3, "total_steps": 125, "loss": 0.1497, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:02:16", "remaining_time": "1:32:15"}
{"current_steps": 4, "total_steps": 125, "loss": 0.1521, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:02:50", "remaining_time": "1:25:46"}
{"current_steps": 5, "total_steps": 125, "loss": 0.1371, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:03:35", "remaining_time": "1:26:21"}
{"current_steps": 6, "total_steps": 125, "loss": 0.1411, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:04:17", "remaining_time": "1:25:06"}
{"current_steps": 7, "total_steps": 125, "loss": 0.1363, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:05:00", "remaining_time": "1:24:23"}
{"current_steps": 8, "total_steps": 125, "loss": 0.0971, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:05:42", "remaining_time": "1:23:24"}
{"current_steps": 9, "total_steps": 125, "loss": 0.087, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:06:28", "remaining_time": "1:23:31"}
{"current_steps": 10, "total_steps": 125, "loss": 0.0866, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:07:04", "remaining_time": "1:21:25"}
{"current_steps": 10, "total_steps": 125, "eval_loss": 0.06995195150375366, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:07:39", "remaining_time": "1:28:05"}
{"current_steps": 11, "total_steps": 125, "loss": 0.0744, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:08:24", "remaining_time": "1:27:03"}
{"current_steps": 12, "total_steps": 125, "loss": 0.0677, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:08:58", "remaining_time": "1:24:34"}
{"current_steps": 13, "total_steps": 125, "loss": 0.0534, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:09:56", "remaining_time": "1:25:42"}
{"current_steps": 14, "total_steps": 125, "loss": 0.0487, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:10:41", "remaining_time": "1:24:45"}
{"current_steps": 15, "total_steps": 125, "loss": 0.0454, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:11:22", "remaining_time": "1:23:27"}
{"current_steps": 16, "total_steps": 125, "loss": 0.0351, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:12:05", "remaining_time": "1:22:19"}
{"current_steps": 17, "total_steps": 125, "loss": 0.0329, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:13:07", "remaining_time": "1:23:25"}
{"current_steps": 18, "total_steps": 125, "loss": 0.0275, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:14:09", "remaining_time": "1:24:11"}
{"current_steps": 19, "total_steps": 125, "loss": 0.0273, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:14:52", "remaining_time": "1:22:59"}
{"current_steps": 20, "total_steps": 125, "loss": 0.0303, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:15:48", "remaining_time": "1:23:00"}
{"current_steps": 20, "total_steps": 125, "eval_loss": 0.027827324345707893, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:16:22", "remaining_time": "1:25:58"}
{"current_steps": 21, "total_steps": 125, "loss": 0.0256, "lr": 9.874639560909117e-05, "epoch": 0.8296296296296296, "percentage": 16.8, "elapsed_time": "0:17:15", "remaining_time": "1:25:27"}
{"current_steps": 22, "total_steps": 125, "loss": 0.0303, "lr": 9.841517610611309e-05, "epoch": 0.8691358024691358, "percentage": 17.6, "elapsed_time": "0:17:49", "remaining_time": "1:23:28"}
{"current_steps": 23, "total_steps": 125, "loss": 0.0208, "lr": 9.804586609725499e-05, "epoch": 0.908641975308642, "percentage": 18.4, "elapsed_time": "0:18:52", "remaining_time": "1:23:43"}
{"current_steps": 24, "total_steps": 125, "loss": 0.0285, "lr": 9.763875613614482e-05, "epoch": 0.9481481481481482, "percentage": 19.2, "elapsed_time": "0:19:49", "remaining_time": "1:23:24"}
{"current_steps": 25, "total_steps": 125, "loss": 0.0204, "lr": 9.719416651541839e-05, "epoch": 0.9876543209876543, "percentage": 20.0, "elapsed_time": "0:20:40", "remaining_time": "1:22:41"}
{"current_steps": 26, "total_steps": 125, "loss": 0.021, "lr": 9.671244701472999e-05, "epoch": 1.0271604938271606, "percentage": 20.8, "elapsed_time": "0:21:44", "remaining_time": "1:22:48"}
{"current_steps": 27, "total_steps": 125, "loss": 0.025, "lr": 9.619397662556435e-05, "epoch": 1.0666666666666667, "percentage": 21.6, "elapsed_time": "0:22:28", "remaining_time": "1:21:36"}
{"current_steps": 28, "total_steps": 125, "loss": 0.0171, "lr": 9.563916325306594e-05, "epoch": 1.106172839506173, "percentage": 22.4, "elapsed_time": "0:23:18", "remaining_time": "1:20:45"}
{"current_steps": 29, "total_steps": 125, "loss": 0.0208, "lr": 9.504844339512095e-05, "epoch": 1.145679012345679, "percentage": 23.2, "elapsed_time": "0:23:58", "remaining_time": "1:19:20"}
{"current_steps": 30, "total_steps": 125, "loss": 0.0158, "lr": 9.442228179894362e-05, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:24:43", "remaining_time": "1:18:17"}
{"current_steps": 30, "total_steps": 125, "eval_loss": 0.019997378811240196, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:25:17", "remaining_time": "1:20:04"}
{"current_steps": 31, "total_steps": 125, "loss": 0.0202, "lr": 9.376117109543769e-05, "epoch": 1.2246913580246914, "percentage": 24.8, "elapsed_time": "0:26:14", "remaining_time": "1:19:33"}
{"current_steps": 32, "total_steps": 125, "loss": 0.0207, "lr": 9.306563141162046e-05, "epoch": 1.2641975308641975, "percentage": 25.6, "elapsed_time": "0:26:59", "remaining_time": "1:18:26"}
{"current_steps": 33, "total_steps": 125, "loss": 0.0183, "lr": 9.233620996141421e-05, "epoch": 1.3037037037037038, "percentage": 26.4, "elapsed_time": "0:27:36", "remaining_time": "1:16:59"}
{"current_steps": 34, "total_steps": 125, "loss": 0.0184, "lr": 9.157348061512727e-05, "epoch": 1.34320987654321, "percentage": 27.2, "elapsed_time": "0:28:31", "remaining_time": "1:16:19"}
{"current_steps": 35, "total_steps": 125, "loss": 0.0157, "lr": 9.077804344796302e-05, "epoch": 1.382716049382716, "percentage": 28.0, "elapsed_time": "0:29:09", "remaining_time": "1:14:57"}
{"current_steps": 36, "total_steps": 125, "loss": 0.0161, "lr": 8.995052426791247e-05, "epoch": 1.4222222222222223, "percentage": 28.8, "elapsed_time": "0:29:55", "remaining_time": "1:13:58"}
{"current_steps": 37, "total_steps": 125, "loss": 0.0214, "lr": 8.90915741234015e-05, "epoch": 1.4617283950617284, "percentage": 29.6, "elapsed_time": "0:30:46", "remaining_time": "1:13:12"}
{"current_steps": 38, "total_steps": 125, "loss": 0.0194, "lr": 8.820186879108038e-05, "epoch": 1.5012345679012347, "percentage": 30.4, "elapsed_time": "0:31:33", "remaining_time": "1:12:14"}
{"current_steps": 39, "total_steps": 125, "loss": 0.0154, "lr": 8.728210824415827e-05, "epoch": 1.5407407407407407, "percentage": 31.2, "elapsed_time": "0:32:15", "remaining_time": "1:11:08"}
{"current_steps": 40, "total_steps": 125, "loss": 0.017, "lr": 8.633301610170135e-05, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:32:55", "remaining_time": "1:09:58"}
{"current_steps": 40, "total_steps": 125, "eval_loss": 0.017982618883252144, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:33:29", "remaining_time": "1:11:10"}
{"current_steps": 41, "total_steps": 125, "loss": 0.0185, "lr": 8.535533905932738e-05, "epoch": 1.6197530864197531, "percentage": 32.8, "elapsed_time": "0:34:17", "remaining_time": "1:10:14"}
{"current_steps": 42, "total_steps": 125, "loss": 0.0166, "lr": 8.434984630174509e-05, "epoch": 1.6592592592592592, "percentage": 33.6, "elapsed_time": "0:34:57", "remaining_time": "1:09:04"}
{"current_steps": 43, "total_steps": 125, "loss": 0.0176, "lr": 8.33173288976002e-05, "epoch": 1.6987654320987655, "percentage": 34.4, "elapsed_time": "0:35:37", "remaining_time": "1:07:55"}
{"current_steps": 44, "total_steps": 125, "loss": 0.015, "lr": 8.225859917710439e-05, "epoch": 1.7382716049382716, "percentage": 35.2, "elapsed_time": "0:36:23", "remaining_time": "1:06:59"}
{"current_steps": 45, "total_steps": 125, "loss": 0.0165, "lr": 8.117449009293668e-05, "epoch": 1.7777777777777777, "percentage": 36.0, "elapsed_time": "0:37:10", "remaining_time": "1:06:05"}
{"current_steps": 46, "total_steps": 125, "loss": 0.0167, "lr": 8.006585456492029e-05, "epoch": 1.817283950617284, "percentage": 36.8, "elapsed_time": "0:38:12", "remaining_time": "1:05:37"}
{"current_steps": 47, "total_steps": 125, "loss": 0.0139, "lr": 7.89335648089903e-05, "epoch": 1.8567901234567903, "percentage": 37.6, "elapsed_time": "0:39:02", "remaining_time": "1:04:47"}
{"current_steps": 48, "total_steps": 125, "loss": 0.0154, "lr": 7.777851165098012e-05, "epoch": 1.8962962962962964, "percentage": 38.4, "elapsed_time": "0:39:59", "remaining_time": "1:04:08"}
{"current_steps": 49, "total_steps": 125, "loss": 0.0141, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:40:43", "remaining_time": "1:03:09"}
{"current_steps": 50, "total_steps": 125, "loss": 0.0132, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:41:19", "remaining_time": "1:01:58"}
{"current_steps": 50, "total_steps": 125, "eval_loss": 0.01624014787375927, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:41:52", "remaining_time": "1:02:49"}
{"current_steps": 51, "total_steps": 125, "loss": 0.0114, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:42:46", "remaining_time": "1:02:04"}
{"current_steps": 52, "total_steps": 125, "loss": 0.0125, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:43:35", "remaining_time": "1:01:11"}
{"current_steps": 53, "total_steps": 125, "loss": 0.0122, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:44:29", "remaining_time": "1:00:26"}
{"current_steps": 54, "total_steps": 125, "loss": 0.0145, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:45:06", "remaining_time": "0:59:18"}
{"current_steps": 55, "total_steps": 125, "loss": 0.0129, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:45:53", "remaining_time": "0:58:24"}
{"current_steps": 56, "total_steps": 125, "loss": 0.0129, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:46:51", "remaining_time": "0:57:44"}
{"current_steps": 57, "total_steps": 125, "loss": 0.012, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:47:52", "remaining_time": "0:57:06"}
{"current_steps": 58, "total_steps": 125, "loss": 0.0116, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:48:46", "remaining_time": "0:56:21"}
{"current_steps": 59, "total_steps": 125, "loss": 0.0122, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:49:22", "remaining_time": "0:55:14"}
{"current_steps": 60, "total_steps": 125, "loss": 0.01, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:50:12", "remaining_time": "0:54:23"}
{"current_steps": 60, "total_steps": 125, "eval_loss": 0.015550716780126095, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:50:46", "remaining_time": "0:55:00"}
{"current_steps": 61, "total_steps": 125, "loss": 0.0108, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:51:33", "remaining_time": "0:54:06"}
{"current_steps": 62, "total_steps": 125, "loss": 0.0094, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:52:09", "remaining_time": "0:52:59"}
{"current_steps": 63, "total_steps": 125, "loss": 0.0113, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:52:50", "remaining_time": "0:51:59"}
{"current_steps": 64, "total_steps": 125, "loss": 0.012, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:53:33", "remaining_time": "0:51:02"}
{"current_steps": 65, "total_steps": 125, "loss": 0.0134, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:54:19", "remaining_time": "0:50:08"}
{"current_steps": 66, "total_steps": 125, "loss": 0.0107, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:55:01", "remaining_time": "0:49:11"}
{"current_steps": 67, "total_steps": 125, "loss": 0.0131, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:55:49", "remaining_time": "0:48:19"}
{"current_steps": 68, "total_steps": 125, "loss": 0.0123, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:56:45", "remaining_time": "0:47:34"}
{"current_steps": 69, "total_steps": 125, "loss": 0.0119, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:57:31", "remaining_time": "0:46:41"}
{"current_steps": 70, "total_steps": 125, "loss": 0.0147, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:58:12", "remaining_time": "0:45:43"}
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.015393273904919624, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:58:46", "remaining_time": "0:46:10"}