mix_base_code_math_t_1 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
a7b5174 verified
{"current_steps": 1, "total_steps": 312, "loss": 1.008, "lr": 3.125e-07, "epoch": 0.0096, "percentage": 0.32, "elapsed_time": "0:01:47", "remaining_time": "9:18:02"}
{"current_steps": 2, "total_steps": 312, "loss": 1.0149, "lr": 6.25e-07, "epoch": 0.0192, "percentage": 0.64, "elapsed_time": "0:03:34", "remaining_time": "9:15:14"}
{"current_steps": 3, "total_steps": 312, "loss": 1.026, "lr": 9.375000000000001e-07, "epoch": 0.0288, "percentage": 0.96, "elapsed_time": "0:05:25", "remaining_time": "9:18:14"}
{"current_steps": 4, "total_steps": 312, "loss": 1.0154, "lr": 1.25e-06, "epoch": 0.0384, "percentage": 1.28, "elapsed_time": "0:06:49", "remaining_time": "8:44:59"}
{"current_steps": 5, "total_steps": 312, "loss": 1.0091, "lr": 1.5625e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:08:11", "remaining_time": "8:23:21"}
{"current_steps": 6, "total_steps": 312, "loss": 0.9624, "lr": 1.8750000000000003e-06, "epoch": 0.0576, "percentage": 1.92, "elapsed_time": "0:09:40", "remaining_time": "8:13:00"}
{"current_steps": 7, "total_steps": 312, "loss": 0.95, "lr": 2.1875000000000002e-06, "epoch": 0.0672, "percentage": 2.24, "elapsed_time": "0:11:21", "remaining_time": "8:15:12"}
{"current_steps": 8, "total_steps": 312, "loss": 0.9617, "lr": 2.5e-06, "epoch": 0.0768, "percentage": 2.56, "elapsed_time": "0:12:51", "remaining_time": "8:08:32"}
{"current_steps": 9, "total_steps": 312, "loss": 0.921, "lr": 2.8125e-06, "epoch": 0.0864, "percentage": 2.88, "elapsed_time": "0:14:27", "remaining_time": "8:06:46"}
{"current_steps": 10, "total_steps": 312, "loss": 0.8574, "lr": 3.125e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:15:48", "remaining_time": "7:57:12"}
{"current_steps": 11, "total_steps": 312, "loss": 0.9179, "lr": 3.4375e-06, "epoch": 0.1056, "percentage": 3.53, "elapsed_time": "0:17:19", "remaining_time": "7:54:03"}
{"current_steps": 12, "total_steps": 312, "loss": 0.8742, "lr": 3.7500000000000005e-06, "epoch": 0.1152, "percentage": 3.85, "elapsed_time": "0:18:44", "remaining_time": "7:48:40"}
{"current_steps": 13, "total_steps": 312, "loss": 0.8919, "lr": 4.0625000000000005e-06, "epoch": 0.1248, "percentage": 4.17, "elapsed_time": "0:20:16", "remaining_time": "7:46:20"}
{"current_steps": 14, "total_steps": 312, "loss": 0.8858, "lr": 4.3750000000000005e-06, "epoch": 0.1344, "percentage": 4.49, "elapsed_time": "0:21:38", "remaining_time": "7:40:29"}
{"current_steps": 15, "total_steps": 312, "loss": 0.8746, "lr": 4.6875000000000004e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:22:55", "remaining_time": "7:33:53"}
{"current_steps": 16, "total_steps": 312, "loss": 0.866, "lr": 5e-06, "epoch": 0.1536, "percentage": 5.13, "elapsed_time": "0:24:32", "remaining_time": "7:33:55"}
{"current_steps": 17, "total_steps": 312, "loss": 0.8143, "lr": 5.3125e-06, "epoch": 0.1632, "percentage": 5.45, "elapsed_time": "0:25:50", "remaining_time": "7:28:33"}
{"current_steps": 18, "total_steps": 312, "loss": 0.8119, "lr": 5.625e-06, "epoch": 0.1728, "percentage": 5.77, "elapsed_time": "0:27:26", "remaining_time": "7:28:12"}
{"current_steps": 19, "total_steps": 312, "loss": 0.8001, "lr": 5.9375e-06, "epoch": 0.1824, "percentage": 6.09, "elapsed_time": "0:28:58", "remaining_time": "7:26:41"}
{"current_steps": 20, "total_steps": 312, "loss": 0.7916, "lr": 6.25e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:30:12", "remaining_time": "7:21:05"}
{"current_steps": 21, "total_steps": 312, "loss": 0.7971, "lr": 6.5625e-06, "epoch": 0.2016, "percentage": 6.73, "elapsed_time": "0:31:56", "remaining_time": "7:22:30"}
{"current_steps": 22, "total_steps": 312, "loss": 0.7607, "lr": 6.875e-06, "epoch": 0.2112, "percentage": 7.05, "elapsed_time": "0:33:43", "remaining_time": "7:24:28"}
{"current_steps": 23, "total_steps": 312, "loss": 0.7394, "lr": 7.1875e-06, "epoch": 0.2208, "percentage": 7.37, "elapsed_time": "0:35:10", "remaining_time": "7:21:58"}
{"current_steps": 24, "total_steps": 312, "loss": 0.7683, "lr": 7.500000000000001e-06, "epoch": 0.2304, "percentage": 7.69, "elapsed_time": "0:36:33", "remaining_time": "7:18:43"}
{"current_steps": 25, "total_steps": 312, "loss": 0.7456, "lr": 7.8125e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:38:11", "remaining_time": "7:18:28"}
{"current_steps": 26, "total_steps": 312, "loss": 0.7246, "lr": 8.125000000000001e-06, "epoch": 0.2496, "percentage": 8.33, "elapsed_time": "0:39:30", "remaining_time": "7:14:39"}
{"current_steps": 27, "total_steps": 312, "loss": 0.7379, "lr": 8.4375e-06, "epoch": 0.2592, "percentage": 8.65, "elapsed_time": "0:41:09", "remaining_time": "7:14:22"}
{"current_steps": 28, "total_steps": 312, "loss": 0.7172, "lr": 8.750000000000001e-06, "epoch": 0.2688, "percentage": 8.97, "elapsed_time": "0:42:45", "remaining_time": "7:13:43"}
{"current_steps": 29, "total_steps": 312, "loss": 0.7218, "lr": 9.0625e-06, "epoch": 0.2784, "percentage": 9.29, "elapsed_time": "0:44:29", "remaining_time": "7:14:12"}
{"current_steps": 30, "total_steps": 312, "loss": 0.7242, "lr": 9.375000000000001e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:46:03", "remaining_time": "7:12:58"}
{"current_steps": 31, "total_steps": 312, "loss": 0.6823, "lr": 9.6875e-06, "epoch": 0.2976, "percentage": 9.94, "elapsed_time": "0:47:39", "remaining_time": "7:11:55"}
{"current_steps": 32, "total_steps": 312, "loss": 0.7239, "lr": 1e-05, "epoch": 0.3072, "percentage": 10.26, "elapsed_time": "0:49:10", "remaining_time": "7:10:18"}
{"current_steps": 33, "total_steps": 312, "loss": 0.6874, "lr": 9.999685283773504e-06, "epoch": 0.3168, "percentage": 10.58, "elapsed_time": "0:50:43", "remaining_time": "7:08:52"}
{"current_steps": 34, "total_steps": 312, "loss": 0.7055, "lr": 9.998741174712534e-06, "epoch": 0.3264, "percentage": 10.9, "elapsed_time": "0:52:26", "remaining_time": "7:08:47"}
{"current_steps": 35, "total_steps": 312, "loss": 0.6942, "lr": 9.997167791667668e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "0:54:06", "remaining_time": "7:08:14"}
{"current_steps": 36, "total_steps": 312, "loss": 0.7124, "lr": 9.994965332706574e-06, "epoch": 0.3456, "percentage": 11.54, "elapsed_time": "0:55:40", "remaining_time": "7:06:48"}
{"current_steps": 37, "total_steps": 312, "loss": 0.7075, "lr": 9.992134075089085e-06, "epoch": 0.3552, "percentage": 11.86, "elapsed_time": "0:57:04", "remaining_time": "7:04:11"}
{"current_steps": 38, "total_steps": 312, "loss": 0.7181, "lr": 9.98867437523228e-06, "epoch": 0.3648, "percentage": 12.18, "elapsed_time": "0:58:40", "remaining_time": "7:03:01"}
{"current_steps": 39, "total_steps": 312, "loss": 0.6979, "lr": 9.984586668665641e-06, "epoch": 0.3744, "percentage": 12.5, "elapsed_time": "1:00:08", "remaining_time": "7:01:01"}
{"current_steps": 40, "total_steps": 312, "loss": 0.6876, "lr": 9.979871469976197e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "1:01:47", "remaining_time": "7:00:10"}
{"current_steps": 41, "total_steps": 312, "loss": 0.6851, "lr": 9.974529372743762e-06, "epoch": 0.3936, "percentage": 13.14, "elapsed_time": "1:03:37", "remaining_time": "7:00:31"}
{"current_steps": 42, "total_steps": 312, "loss": 0.6735, "lr": 9.968561049466214e-06, "epoch": 0.4032, "percentage": 13.46, "elapsed_time": "1:05:05", "remaining_time": "6:58:26"}
{"current_steps": 43, "total_steps": 312, "loss": 0.6874, "lr": 9.961967251474823e-06, "epoch": 0.4128, "percentage": 13.78, "elapsed_time": "1:06:27", "remaining_time": "6:55:46"}
{"current_steps": 44, "total_steps": 312, "loss": 0.6558, "lr": 9.954748808839675e-06, "epoch": 0.4224, "percentage": 14.1, "elapsed_time": "1:08:01", "remaining_time": "6:54:17"}
{"current_steps": 45, "total_steps": 312, "loss": 0.6932, "lr": 9.946906630265184e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "1:09:39", "remaining_time": "6:53:18"}
{"current_steps": 46, "total_steps": 312, "loss": 0.6569, "lr": 9.938441702975689e-06, "epoch": 0.4416, "percentage": 14.74, "elapsed_time": "1:11:06", "remaining_time": "6:51:13"}
{"current_steps": 47, "total_steps": 312, "loss": 0.6916, "lr": 9.92935509259118e-06, "epoch": 0.4512, "percentage": 15.06, "elapsed_time": "1:13:04", "remaining_time": "6:52:03"}
{"current_steps": 48, "total_steps": 312, "loss": 0.6927, "lr": 9.91964794299315e-06, "epoch": 0.4608, "percentage": 15.38, "elapsed_time": "1:14:44", "remaining_time": "6:51:04"}
{"current_steps": 49, "total_steps": 312, "loss": 0.6418, "lr": 9.909321476180594e-06, "epoch": 0.4704, "percentage": 15.71, "elapsed_time": "1:16:28", "remaining_time": "6:50:29"}
{"current_steps": 50, "total_steps": 312, "loss": 0.6697, "lr": 9.898376992116179e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "1:18:15", "remaining_time": "6:50:01"}
{"current_steps": 51, "total_steps": 312, "loss": 0.6535, "lr": 9.886815868562596e-06, "epoch": 0.4896, "percentage": 16.35, "elapsed_time": "1:19:44", "remaining_time": "6:48:07"}
{"current_steps": 52, "total_steps": 312, "loss": 0.6738, "lr": 9.874639560909118e-06, "epoch": 0.4992, "percentage": 16.67, "elapsed_time": "1:21:25", "remaining_time": "6:47:07"}
{"current_steps": 53, "total_steps": 312, "loss": 0.6844, "lr": 9.861849601988384e-06, "epoch": 0.5088, "percentage": 16.99, "elapsed_time": "1:22:43", "remaining_time": "6:44:15"}
{"current_steps": 54, "total_steps": 312, "loss": 0.6897, "lr": 9.848447601883436e-06, "epoch": 0.5184, "percentage": 17.31, "elapsed_time": "1:24:15", "remaining_time": "6:42:35"}
{"current_steps": 55, "total_steps": 312, "loss": 0.6598, "lr": 9.834435247725032e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "1:25:57", "remaining_time": "6:41:38"}
{"current_steps": 56, "total_steps": 312, "loss": 0.6383, "lr": 9.819814303479268e-06, "epoch": 0.5376, "percentage": 17.95, "elapsed_time": "1:27:24", "remaining_time": "6:39:36"}
{"current_steps": 57, "total_steps": 312, "loss": 0.6667, "lr": 9.804586609725499e-06, "epoch": 0.5472, "percentage": 18.27, "elapsed_time": "1:28:56", "remaining_time": "6:37:53"}
{"current_steps": 58, "total_steps": 312, "loss": 0.6504, "lr": 9.788754083424654e-06, "epoch": 0.5568, "percentage": 18.59, "elapsed_time": "1:30:22", "remaining_time": "6:35:44"}
{"current_steps": 59, "total_steps": 312, "loss": 0.6343, "lr": 9.772318717677905e-06, "epoch": 0.5664, "percentage": 18.91, "elapsed_time": "1:31:51", "remaining_time": "6:33:52"}
{"current_steps": 60, "total_steps": 312, "loss": 0.6418, "lr": 9.755282581475769e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "1:33:32", "remaining_time": "6:32:50"}
{"current_steps": 61, "total_steps": 312, "loss": 0.644, "lr": 9.737647819437645e-06, "epoch": 0.5856, "percentage": 19.55, "elapsed_time": "1:35:13", "remaining_time": "6:31:50"}
{"current_steps": 62, "total_steps": 312, "loss": 0.6532, "lr": 9.719416651541839e-06, "epoch": 0.5952, "percentage": 19.87, "elapsed_time": "1:36:44", "remaining_time": "6:30:05"}
{"current_steps": 63, "total_steps": 312, "loss": 0.6262, "lr": 9.700591372846096e-06, "epoch": 0.6048, "percentage": 20.19, "elapsed_time": "1:38:18", "remaining_time": "6:28:31"}
{"current_steps": 64, "total_steps": 312, "loss": 0.6576, "lr": 9.681174353198687e-06, "epoch": 0.6144, "percentage": 20.51, "elapsed_time": "1:39:43", "remaining_time": "6:26:25"}
{"current_steps": 65, "total_steps": 312, "loss": 0.6518, "lr": 9.661168036940071e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "1:41:20", "remaining_time": "6:25:06"}
{"current_steps": 66, "total_steps": 312, "loss": 0.6315, "lr": 9.640574942595195e-06, "epoch": 0.6336, "percentage": 21.15, "elapsed_time": "1:42:45", "remaining_time": "6:23:00"}
{"current_steps": 67, "total_steps": 312, "loss": 0.6615, "lr": 9.619397662556434e-06, "epoch": 0.6432, "percentage": 21.47, "elapsed_time": "1:44:22", "remaining_time": "6:21:39"}
{"current_steps": 68, "total_steps": 312, "loss": 0.6511, "lr": 9.597638862757255e-06, "epoch": 0.6528, "percentage": 21.79, "elapsed_time": "1:45:55", "remaining_time": "6:20:05"}
{"current_steps": 69, "total_steps": 312, "loss": 0.6523, "lr": 9.5753012823366e-06, "epoch": 0.6624, "percentage": 22.12, "elapsed_time": "1:47:12", "remaining_time": "6:17:33"}
{"current_steps": 70, "total_steps": 312, "loss": 0.6317, "lr": 9.552387733294081e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "1:49:00", "remaining_time": "6:16:52"}
{"current_steps": 71, "total_steps": 312, "loss": 0.6424, "lr": 9.528901100135971e-06, "epoch": 0.6816, "percentage": 22.76, "elapsed_time": "1:50:49", "remaining_time": "6:16:10"}
{"current_steps": 72, "total_steps": 312, "loss": 0.6868, "lr": 9.504844339512096e-06, "epoch": 0.6912, "percentage": 23.08, "elapsed_time": "1:52:32", "remaining_time": "6:15:09"}
{"current_steps": 73, "total_steps": 312, "loss": 0.6638, "lr": 9.480220479843627e-06, "epoch": 0.7008, "percentage": 23.4, "elapsed_time": "1:54:10", "remaining_time": "6:13:47"}
{"current_steps": 74, "total_steps": 312, "loss": 0.6381, "lr": 9.45503262094184e-06, "epoch": 0.7104, "percentage": 23.72, "elapsed_time": "1:55:43", "remaining_time": "6:12:10"}
{"current_steps": 75, "total_steps": 312, "loss": 0.627, "lr": 9.4292839336179e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "1:57:25", "remaining_time": "6:11:04"}
{"current_steps": 76, "total_steps": 312, "loss": 0.6597, "lr": 9.40297765928369e-06, "epoch": 0.7296, "percentage": 24.36, "elapsed_time": "1:58:57", "remaining_time": "6:09:23"}
{"current_steps": 77, "total_steps": 312, "loss": 0.6607, "lr": 9.376117109543769e-06, "epoch": 0.7392, "percentage": 24.68, "elapsed_time": "2:00:29", "remaining_time": "6:07:42"}
{"current_steps": 78, "total_steps": 312, "loss": 0.6459, "lr": 9.348705665778479e-06, "epoch": 0.7488, "percentage": 25.0, "elapsed_time": "2:02:11", "remaining_time": "6:06:34"}
{"current_steps": 79, "total_steps": 312, "loss": 0.6418, "lr": 9.320746778718274e-06, "epoch": 0.7584, "percentage": 25.32, "elapsed_time": "2:03:52", "remaining_time": "6:05:21"}
{"current_steps": 80, "total_steps": 312, "loss": 0.6269, "lr": 9.292243968009332e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "2:05:14", "remaining_time": "6:03:12"}
{"current_steps": 81, "total_steps": 312, "loss": 0.63, "lr": 9.263200821770462e-06, "epoch": 0.7776, "percentage": 25.96, "elapsed_time": "2:07:01", "remaining_time": "6:02:15"}
{"current_steps": 82, "total_steps": 312, "loss": 0.6605, "lr": 9.233620996141421e-06, "epoch": 0.7872, "percentage": 26.28, "elapsed_time": "2:08:36", "remaining_time": "6:00:42"}
{"current_steps": 83, "total_steps": 312, "loss": 0.6678, "lr": 9.203508214822652e-06, "epoch": 0.7968, "percentage": 26.6, "elapsed_time": "2:10:05", "remaining_time": "5:58:55"}
{"current_steps": 84, "total_steps": 312, "loss": 0.663, "lr": 9.172866268606514e-06, "epoch": 0.8064, "percentage": 26.92, "elapsed_time": "2:11:32", "remaining_time": "5:57:03"}
{"current_steps": 85, "total_steps": 312, "loss": 0.6427, "lr": 9.141699014900084e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "2:13:01", "remaining_time": "5:55:16"}
{"current_steps": 86, "total_steps": 312, "loss": 0.6407, "lr": 9.110010377239552e-06, "epoch": 0.8256, "percentage": 27.56, "elapsed_time": "2:14:33", "remaining_time": "5:53:35"}
{"current_steps": 87, "total_steps": 312, "loss": 0.634, "lr": 9.077804344796302e-06, "epoch": 0.8352, "percentage": 27.88, "elapsed_time": "2:16:14", "remaining_time": "5:52:21"}
{"current_steps": 88, "total_steps": 312, "loss": 0.6503, "lr": 9.045084971874738e-06, "epoch": 0.8448, "percentage": 28.21, "elapsed_time": "2:18:02", "remaining_time": "5:51:21"}
{"current_steps": 89, "total_steps": 312, "loss": 0.6418, "lr": 9.011856377401891e-06, "epoch": 0.8544, "percentage": 28.53, "elapsed_time": "2:19:51", "remaining_time": "5:50:24"}
{"current_steps": 90, "total_steps": 312, "loss": 0.6438, "lr": 8.978122744408905e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "2:21:08", "remaining_time": "5:48:07"}
{"current_steps": 91, "total_steps": 312, "loss": 0.6566, "lr": 8.943888319504456e-06, "epoch": 0.8736, "percentage": 29.17, "elapsed_time": "2:22:56", "remaining_time": "5:47:07"}
{"current_steps": 92, "total_steps": 312, "loss": 0.6361, "lr": 8.90915741234015e-06, "epoch": 0.8832, "percentage": 29.49, "elapsed_time": "2:24:37", "remaining_time": "5:45:49"}
{"current_steps": 93, "total_steps": 312, "loss": 0.6652, "lr": 8.873934395068006e-06, "epoch": 0.8928, "percentage": 29.81, "elapsed_time": "2:25:53", "remaining_time": "5:43:32"}
{"current_steps": 94, "total_steps": 312, "loss": 0.6216, "lr": 8.838223701790057e-06, "epoch": 0.9024, "percentage": 30.13, "elapsed_time": "2:27:29", "remaining_time": "5:42:02"}
{"current_steps": 95, "total_steps": 312, "loss": 0.6123, "lr": 8.802029828000157e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "2:28:51", "remaining_time": "5:40:00"}
{"current_steps": 96, "total_steps": 312, "loss": 0.6392, "lr": 8.765357330018056e-06, "epoch": 0.9216, "percentage": 30.77, "elapsed_time": "2:30:28", "remaining_time": "5:38:34"}
{"current_steps": 97, "total_steps": 312, "loss": 0.6051, "lr": 8.728210824415829e-06, "epoch": 0.9312, "percentage": 31.09, "elapsed_time": "2:32:10", "remaining_time": "5:37:17"}
{"current_steps": 98, "total_steps": 312, "loss": 0.6084, "lr": 8.690594987436705e-06, "epoch": 0.9408, "percentage": 31.41, "elapsed_time": "2:33:35", "remaining_time": "5:35:23"}
{"current_steps": 99, "total_steps": 312, "loss": 0.6335, "lr": 8.652514554406388e-06, "epoch": 0.9504, "percentage": 31.73, "elapsed_time": "2:35:02", "remaining_time": "5:33:34"}
{"current_steps": 100, "total_steps": 312, "loss": 0.6244, "lr": 8.613974319136959e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "2:36:32", "remaining_time": "5:31:52"}
{"current_steps": 101, "total_steps": 312, "loss": 0.6363, "lr": 8.574979133323378e-06, "epoch": 0.9696, "percentage": 32.37, "elapsed_time": "2:38:18", "remaining_time": "5:30:43"}
{"current_steps": 102, "total_steps": 312, "loss": 0.6407, "lr": 8.535533905932739e-06, "epoch": 0.9792, "percentage": 32.69, "elapsed_time": "2:39:51", "remaining_time": "5:29:07"}
{"current_steps": 103, "total_steps": 312, "loss": 0.6485, "lr": 8.495643602586287e-06, "epoch": 0.9888, "percentage": 33.01, "elapsed_time": "2:41:14", "remaining_time": "5:27:10"}
{"current_steps": 104, "total_steps": 312, "loss": 0.6727, "lr": 8.455313244934324e-06, "epoch": 0.9984, "percentage": 33.33, "elapsed_time": "2:42:54", "remaining_time": "5:25:48"}
{"current_steps": 105, "total_steps": 312, "loss": 1.0788, "lr": 8.414547910024035e-06, "epoch": 1.008, "percentage": 33.65, "elapsed_time": "2:45:20", "remaining_time": "5:25:57"}
{"current_steps": 106, "total_steps": 312, "loss": 0.5632, "lr": 8.373352729660373e-06, "epoch": 1.0176, "percentage": 33.97, "elapsed_time": "2:46:53", "remaining_time": "5:24:20"}
{"current_steps": 107, "total_steps": 312, "loss": 0.5904, "lr": 8.331732889760021e-06, "epoch": 1.0272, "percentage": 34.29, "elapsed_time": "2:48:29", "remaining_time": "5:22:49"}
{"current_steps": 108, "total_steps": 312, "loss": 0.5909, "lr": 8.289693629698564e-06, "epoch": 1.0368, "percentage": 34.62, "elapsed_time": "2:49:53", "remaining_time": "5:20:55"}
{"current_steps": 109, "total_steps": 312, "loss": 0.6101, "lr": 8.247240241650918e-06, "epoch": 1.0464, "percentage": 34.94, "elapsed_time": "2:51:31", "remaining_time": "5:19:27"}
{"current_steps": 110, "total_steps": 312, "loss": 0.6091, "lr": 8.204378069925121e-06, "epoch": 1.056, "percentage": 35.26, "elapsed_time": "2:53:18", "remaining_time": "5:18:16"}
{"current_steps": 111, "total_steps": 312, "loss": 0.5899, "lr": 8.16111251028955e-06, "epoch": 1.0656, "percentage": 35.58, "elapsed_time": "2:54:57", "remaining_time": "5:16:48"}
{"current_steps": 112, "total_steps": 312, "loss": 0.5446, "lr": 8.117449009293668e-06, "epoch": 1.0752, "percentage": 35.9, "elapsed_time": "2:56:14", "remaining_time": "5:14:43"}
{"current_steps": 113, "total_steps": 312, "loss": 0.5883, "lr": 8.073393063582386e-06, "epoch": 1.0848, "percentage": 36.22, "elapsed_time": "2:57:57", "remaining_time": "5:13:24"}
{"current_steps": 114, "total_steps": 312, "loss": 0.5656, "lr": 8.0289502192041e-06, "epoch": 1.0944, "percentage": 36.54, "elapsed_time": "2:59:38", "remaining_time": "5:12:00"}
{"current_steps": 115, "total_steps": 312, "loss": 0.6299, "lr": 7.984126070912519e-06, "epoch": 1.104, "percentage": 36.86, "elapsed_time": "3:01:32", "remaining_time": "5:10:59"}
{"current_steps": 116, "total_steps": 312, "loss": 0.5624, "lr": 7.938926261462366e-06, "epoch": 1.1136, "percentage": 37.18, "elapsed_time": "3:03:10", "remaining_time": "5:09:30"}
{"current_steps": 117, "total_steps": 312, "loss": 0.6331, "lr": 7.89335648089903e-06, "epoch": 1.1232, "percentage": 37.5, "elapsed_time": "3:04:58", "remaining_time": "5:08:17"}
{"current_steps": 118, "total_steps": 312, "loss": 0.5773, "lr": 7.84742246584226e-06, "epoch": 1.1328, "percentage": 37.82, "elapsed_time": "3:06:24", "remaining_time": "5:06:27"}
{"current_steps": 119, "total_steps": 312, "loss": 0.5535, "lr": 7.801129998764014e-06, "epoch": 1.1424, "percentage": 38.14, "elapsed_time": "3:07:44", "remaining_time": "5:04:29"}
{"current_steps": 120, "total_steps": 312, "loss": 0.6113, "lr": 7.754484907260513e-06, "epoch": 1.152, "percentage": 38.46, "elapsed_time": "3:09:24", "remaining_time": "5:03:03"}
{"current_steps": 121, "total_steps": 312, "loss": 0.5759, "lr": 7.70749306331863e-06, "epoch": 1.1616, "percentage": 38.78, "elapsed_time": "3:11:00", "remaining_time": "5:01:30"}
{"current_steps": 122, "total_steps": 312, "loss": 0.6, "lr": 7.660160382576683e-06, "epoch": 1.1712, "percentage": 39.1, "elapsed_time": "3:12:34", "remaining_time": "4:59:54"}
{"current_steps": 123, "total_steps": 312, "loss": 0.6019, "lr": 7.612492823579744e-06, "epoch": 1.1808, "percentage": 39.42, "elapsed_time": "3:14:21", "remaining_time": "4:58:39"}
{"current_steps": 124, "total_steps": 312, "loss": 0.6021, "lr": 7.564496387029532e-06, "epoch": 1.1904, "percentage": 39.74, "elapsed_time": "3:15:55", "remaining_time": "4:57:02"}
{"current_steps": 125, "total_steps": 312, "loss": 0.5664, "lr": 7.516177115029002e-06, "epoch": 1.2, "percentage": 40.06, "elapsed_time": "3:17:31", "remaining_time": "4:55:30"}
{"current_steps": 126, "total_steps": 312, "loss": 0.5799, "lr": 7.467541090321735e-06, "epoch": 1.2096, "percentage": 40.38, "elapsed_time": "3:19:09", "remaining_time": "4:54:00"}
{"current_steps": 127, "total_steps": 312, "loss": 0.5393, "lr": 7.4185944355261996e-06, "epoch": 1.2192, "percentage": 40.71, "elapsed_time": "3:20:30", "remaining_time": "4:52:04"}
{"current_steps": 128, "total_steps": 312, "loss": 0.6331, "lr": 7.369343312364994e-06, "epoch": 1.2288000000000001, "percentage": 41.03, "elapsed_time": "3:22:06", "remaining_time": "4:50:32"}
{"current_steps": 129, "total_steps": 312, "loss": 0.5094, "lr": 7.319793920889171e-06, "epoch": 1.2384, "percentage": 41.35, "elapsed_time": "3:23:52", "remaining_time": "4:49:12"}
{"current_steps": 130, "total_steps": 312, "loss": 0.5987, "lr": 7.269952498697734e-06, "epoch": 1.248, "percentage": 41.67, "elapsed_time": "3:25:29", "remaining_time": "4:47:41"}
{"current_steps": 131, "total_steps": 312, "loss": 0.6032, "lr": 7.219825320152411e-06, "epoch": 1.2576, "percentage": 41.99, "elapsed_time": "3:27:00", "remaining_time": "4:46:00"}
{"current_steps": 132, "total_steps": 312, "loss": 0.488, "lr": 7.169418695587791e-06, "epoch": 1.2671999999999999, "percentage": 42.31, "elapsed_time": "3:28:13", "remaining_time": "4:43:57"}
{"current_steps": 133, "total_steps": 312, "loss": 0.6191, "lr": 7.118738970516944e-06, "epoch": 1.2768, "percentage": 42.63, "elapsed_time": "3:29:52", "remaining_time": "4:42:28"}
{"current_steps": 134, "total_steps": 312, "loss": 0.5268, "lr": 7.067792524832604e-06, "epoch": 1.2864, "percentage": 42.95, "elapsed_time": "3:31:07", "remaining_time": "4:40:27"}
{"current_steps": 135, "total_steps": 312, "loss": 0.6349, "lr": 7.016585772004026e-06, "epoch": 1.296, "percentage": 43.27, "elapsed_time": "3:32:36", "remaining_time": "4:38:45"}
{"current_steps": 136, "total_steps": 312, "loss": 0.6108, "lr": 6.965125158269619e-06, "epoch": 1.3056, "percentage": 43.59, "elapsed_time": "3:34:18", "remaining_time": "4:37:19"}
{"current_steps": 137, "total_steps": 312, "loss": 0.579, "lr": 6.913417161825449e-06, "epoch": 1.3152, "percentage": 43.91, "elapsed_time": "3:35:37", "remaining_time": "4:35:25"}
{"current_steps": 138, "total_steps": 312, "loss": 0.5309, "lr": 6.8614682920097265e-06, "epoch": 1.3248, "percentage": 44.23, "elapsed_time": "3:36:55", "remaining_time": "4:33:31"}
{"current_steps": 139, "total_steps": 312, "loss": 0.6401, "lr": 6.809285088483361e-06, "epoch": 1.3344, "percentage": 44.55, "elapsed_time": "3:38:48", "remaining_time": "4:32:19"}
{"current_steps": 140, "total_steps": 312, "loss": 0.5554, "lr": 6.7568741204067145e-06, "epoch": 1.3439999999999999, "percentage": 44.87, "elapsed_time": "3:40:18", "remaining_time": "4:30:40"}
{"current_steps": 141, "total_steps": 312, "loss": 0.5849, "lr": 6.704241985612625e-06, "epoch": 1.3536000000000001, "percentage": 45.19, "elapsed_time": "3:41:59", "remaining_time": "4:29:13"}
{"current_steps": 142, "total_steps": 312, "loss": 0.5626, "lr": 6.651395309775837e-06, "epoch": 1.3632, "percentage": 45.51, "elapsed_time": "3:43:38", "remaining_time": "4:27:44"}
{"current_steps": 143, "total_steps": 312, "loss": 0.6218, "lr": 6.598340745578908e-06, "epoch": 1.3728, "percentage": 45.83, "elapsed_time": "3:45:19", "remaining_time": "4:26:17"}
{"current_steps": 144, "total_steps": 312, "loss": 0.5982, "lr": 6.545084971874738e-06, "epoch": 1.3824, "percentage": 46.15, "elapsed_time": "3:46:47", "remaining_time": "4:24:34"}
{"current_steps": 145, "total_steps": 312, "loss": 0.5755, "lr": 6.491634692845781e-06, "epoch": 1.392, "percentage": 46.47, "elapsed_time": "3:48:20", "remaining_time": "4:22:59"}
{"current_steps": 146, "total_steps": 312, "loss": 0.5432, "lr": 6.437996637160086e-06, "epoch": 1.4016, "percentage": 46.79, "elapsed_time": "3:50:16", "remaining_time": "4:21:49"}
{"current_steps": 147, "total_steps": 312, "loss": 0.6209, "lr": 6.384177557124247e-06, "epoch": 1.4112, "percentage": 47.12, "elapsed_time": "3:52:04", "remaining_time": "4:20:29"}
{"current_steps": 148, "total_steps": 312, "loss": 0.553, "lr": 6.330184227833376e-06, "epoch": 1.4208, "percentage": 47.44, "elapsed_time": "3:53:30", "remaining_time": "4:18:45"}
{"current_steps": 149, "total_steps": 312, "loss": 0.5674, "lr": 6.276023446318214e-06, "epoch": 1.4304000000000001, "percentage": 47.76, "elapsed_time": "3:55:05", "remaining_time": "4:17:11"}
{"current_steps": 150, "total_steps": 312, "loss": 0.5947, "lr": 6.2217020306894705e-06, "epoch": 1.44, "percentage": 48.08, "elapsed_time": "3:56:32", "remaining_time": "4:15:28"}
{"current_steps": 151, "total_steps": 312, "loss": 0.5382, "lr": 6.1672268192795285e-06, "epoch": 1.4496, "percentage": 48.4, "elapsed_time": "3:57:48", "remaining_time": "4:13:33"}
{"current_steps": 152, "total_steps": 312, "loss": 0.5702, "lr": 6.112604669781572e-06, "epoch": 1.4592, "percentage": 48.72, "elapsed_time": "3:59:04", "remaining_time": "4:11:39"}
{"current_steps": 153, "total_steps": 312, "loss": 0.6564, "lr": 6.057842458386315e-06, "epoch": 1.4687999999999999, "percentage": 49.04, "elapsed_time": "4:00:27", "remaining_time": "4:09:53"}
{"current_steps": 154, "total_steps": 312, "loss": 0.5484, "lr": 6.002947078916365e-06, "epoch": 1.4784, "percentage": 49.36, "elapsed_time": "4:01:54", "remaining_time": "4:08:11"}
{"current_steps": 155, "total_steps": 312, "loss": 0.5918, "lr": 5.947925441958393e-06, "epoch": 1.488, "percentage": 49.68, "elapsed_time": "4:03:26", "remaining_time": "4:06:34"}
{"current_steps": 156, "total_steps": 312, "loss": 0.5526, "lr": 5.892784473993184e-06, "epoch": 1.4976, "percentage": 50.0, "elapsed_time": "4:05:05", "remaining_time": "4:05:05"}
{"current_steps": 157, "total_steps": 312, "loss": 0.6385, "lr": 5.837531116523683e-06, "epoch": 1.5072, "percentage": 50.32, "elapsed_time": "4:06:49", "remaining_time": "4:03:40"}
{"current_steps": 158, "total_steps": 312, "loss": 0.5744, "lr": 5.782172325201155e-06, "epoch": 1.5168, "percentage": 50.64, "elapsed_time": "4:08:29", "remaining_time": "4:02:11"}
{"current_steps": 159, "total_steps": 312, "loss": 0.5168, "lr": 5.726715068949564e-06, "epoch": 1.5264, "percentage": 50.96, "elapsed_time": "4:10:01", "remaining_time": "4:00:35"}
{"current_steps": 160, "total_steps": 312, "loss": 0.6515, "lr": 5.671166329088278e-06, "epoch": 1.536, "percentage": 51.28, "elapsed_time": "4:11:33", "remaining_time": "3:58:58"}
{"current_steps": 161, "total_steps": 312, "loss": 0.5704, "lr": 5.615533098453215e-06, "epoch": 1.5455999999999999, "percentage": 51.6, "elapsed_time": "4:13:01", "remaining_time": "3:57:18"}
{"current_steps": 162, "total_steps": 312, "loss": 0.5753, "lr": 5.559822380516539e-06, "epoch": 1.5552000000000001, "percentage": 51.92, "elapsed_time": "4:14:37", "remaining_time": "3:55:46"}
{"current_steps": 163, "total_steps": 312, "loss": 0.5911, "lr": 5.504041188505022e-06, "epoch": 1.5648, "percentage": 52.24, "elapsed_time": "4:16:09", "remaining_time": "3:54:09"}
{"current_steps": 164, "total_steps": 312, "loss": 0.5771, "lr": 5.448196544517168e-06, "epoch": 1.5744, "percentage": 52.56, "elapsed_time": "4:17:53", "remaining_time": "3:52:44"}
{"current_steps": 165, "total_steps": 312, "loss": 0.5714, "lr": 5.392295478639226e-06, "epoch": 1.584, "percentage": 52.88, "elapsed_time": "4:19:16", "remaining_time": "3:50:59"}
{"current_steps": 166, "total_steps": 312, "loss": 0.5873, "lr": 5.336345028060199e-06, "epoch": 1.5936, "percentage": 53.21, "elapsed_time": "4:21:00", "remaining_time": "3:49:33"}
{"current_steps": 167, "total_steps": 312, "loss": 0.5667, "lr": 5.2803522361859596e-06, "epoch": 1.6032, "percentage": 53.53, "elapsed_time": "4:22:27", "remaining_time": "3:47:52"}
{"current_steps": 168, "total_steps": 312, "loss": 0.5715, "lr": 5.224324151752575e-06, "epoch": 1.6128, "percentage": 53.85, "elapsed_time": "4:23:58", "remaining_time": "3:46:15"}
{"current_steps": 169, "total_steps": 312, "loss": 0.5353, "lr": 5.168267827938971e-06, "epoch": 1.6223999999999998, "percentage": 54.17, "elapsed_time": "4:25:34", "remaining_time": "3:44:42"}
{"current_steps": 170, "total_steps": 312, "loss": 0.582, "lr": 5.112190321479026e-06, "epoch": 1.6320000000000001, "percentage": 54.49, "elapsed_time": "4:27:14", "remaining_time": "3:43:13"}
{"current_steps": 171, "total_steps": 312, "loss": 0.6188, "lr": 5.05609869177323e-06, "epoch": 1.6416, "percentage": 54.81, "elapsed_time": "4:28:43", "remaining_time": "3:41:34"}
{"current_steps": 172, "total_steps": 312, "loss": 0.4733, "lr": 5e-06, "epoch": 1.6512, "percentage": 55.13, "elapsed_time": "4:30:03", "remaining_time": "3:39:49"}
{"current_steps": 173, "total_steps": 312, "loss": 0.6487, "lr": 4.943901308226771e-06, "epoch": 1.6608, "percentage": 55.45, "elapsed_time": "4:31:24", "remaining_time": "3:38:04"}
{"current_steps": 174, "total_steps": 312, "loss": 0.5334, "lr": 4.887809678520976e-06, "epoch": 1.6703999999999999, "percentage": 55.77, "elapsed_time": "4:32:47", "remaining_time": "3:36:21"}
{"current_steps": 175, "total_steps": 312, "loss": 0.5959, "lr": 4.831732172061032e-06, "epoch": 1.6800000000000002, "percentage": 56.09, "elapsed_time": "4:34:32", "remaining_time": "3:34:55"}
{"current_steps": 176, "total_steps": 312, "loss": 0.6187, "lr": 4.775675848247427e-06, "epoch": 1.6896, "percentage": 56.41, "elapsed_time": "4:36:14", "remaining_time": "3:33:27"}
{"current_steps": 177, "total_steps": 312, "loss": 0.5754, "lr": 4.719647763814041e-06, "epoch": 1.6992, "percentage": 56.73, "elapsed_time": "4:37:55", "remaining_time": "3:31:58"}
{"current_steps": 178, "total_steps": 312, "loss": 0.6058, "lr": 4.663654971939802e-06, "epoch": 1.7088, "percentage": 57.05, "elapsed_time": "4:39:34", "remaining_time": "3:30:27"}
{"current_steps": 179, "total_steps": 312, "loss": 0.5671, "lr": 4.6077045213607765e-06, "epoch": 1.7184, "percentage": 57.37, "elapsed_time": "4:41:08", "remaining_time": "3:28:53"}
{"current_steps": 180, "total_steps": 312, "loss": 0.5921, "lr": 4.551803455482833e-06, "epoch": 1.728, "percentage": 57.69, "elapsed_time": "4:42:41", "remaining_time": "3:27:18"}
{"current_steps": 181, "total_steps": 312, "loss": 0.6229, "lr": 4.4959588114949785e-06, "epoch": 1.7376, "percentage": 58.01, "elapsed_time": "4:44:30", "remaining_time": "3:25:54"}
{"current_steps": 182, "total_steps": 312, "loss": 0.5371, "lr": 4.4401776194834615e-06, "epoch": 1.7471999999999999, "percentage": 58.33, "elapsed_time": "4:46:10", "remaining_time": "3:24:24"}
{"current_steps": 183, "total_steps": 312, "loss": 0.6257, "lr": 4.384466901546786e-06, "epoch": 1.7568000000000001, "percentage": 58.65, "elapsed_time": "4:47:53", "remaining_time": "3:22:56"}
{"current_steps": 184, "total_steps": 312, "loss": 0.558, "lr": 4.3288336709117246e-06, "epoch": 1.7664, "percentage": 58.97, "elapsed_time": "4:49:37", "remaining_time": "3:21:28"}
{"current_steps": 185, "total_steps": 312, "loss": 0.5644, "lr": 4.273284931050438e-06, "epoch": 1.776, "percentage": 59.29, "elapsed_time": "4:51:18", "remaining_time": "3:19:58"}
{"current_steps": 186, "total_steps": 312, "loss": 0.583, "lr": 4.217827674798845e-06, "epoch": 1.7856, "percentage": 59.62, "elapsed_time": "4:53:02", "remaining_time": "3:18:30"}
{"current_steps": 187, "total_steps": 312, "loss": 0.6316, "lr": 4.162468883476319e-06, "epoch": 1.7952, "percentage": 59.94, "elapsed_time": "4:54:48", "remaining_time": "3:17:03"}
{"current_steps": 188, "total_steps": 312, "loss": 0.5279, "lr": 4.107215526006818e-06, "epoch": 1.8048, "percentage": 60.26, "elapsed_time": "4:56:15", "remaining_time": "3:15:24"}
{"current_steps": 189, "total_steps": 312, "loss": 0.5368, "lr": 4.052074558041608e-06, "epoch": 1.8144, "percentage": 60.58, "elapsed_time": "4:57:57", "remaining_time": "3:13:54"}
{"current_steps": 190, "total_steps": 312, "loss": 0.6028, "lr": 3.997052921083637e-06, "epoch": 1.8239999999999998, "percentage": 60.9, "elapsed_time": "4:59:34", "remaining_time": "3:12:21"}
{"current_steps": 191, "total_steps": 312, "loss": 0.5955, "lr": 3.9421575416136866e-06, "epoch": 1.8336000000000001, "percentage": 61.22, "elapsed_time": "5:01:15", "remaining_time": "3:10:50"}
{"current_steps": 192, "total_steps": 312, "loss": 0.5063, "lr": 3.887395330218429e-06, "epoch": 1.8432, "percentage": 61.54, "elapsed_time": "5:02:36", "remaining_time": "3:09:07"}
{"current_steps": 193, "total_steps": 312, "loss": 0.6493, "lr": 3.832773180720475e-06, "epoch": 1.8528, "percentage": 61.86, "elapsed_time": "5:04:26", "remaining_time": "3:07:42"}
{"current_steps": 194, "total_steps": 312, "loss": 0.5779, "lr": 3.778297969310529e-06, "epoch": 1.8624, "percentage": 62.18, "elapsed_time": "5:06:04", "remaining_time": "3:06:09"}
{"current_steps": 195, "total_steps": 312, "loss": 0.5444, "lr": 3.723976553681787e-06, "epoch": 1.8719999999999999, "percentage": 62.5, "elapsed_time": "5:07:25", "remaining_time": "3:04:27"}
{"current_steps": 196, "total_steps": 312, "loss": 0.5834, "lr": 3.669815772166625e-06, "epoch": 1.8816000000000002, "percentage": 62.82, "elapsed_time": "5:09:05", "remaining_time": "3:02:55"}
{"current_steps": 197, "total_steps": 312, "loss": 0.5167, "lr": 3.6158224428757538e-06, "epoch": 1.8912, "percentage": 63.14, "elapsed_time": "5:10:27", "remaining_time": "3:01:14"}
{"current_steps": 198, "total_steps": 312, "loss": 0.576, "lr": 3.562003362839914e-06, "epoch": 1.9008, "percentage": 63.46, "elapsed_time": "5:11:50", "remaining_time": "2:59:32"}
{"current_steps": 199, "total_steps": 312, "loss": 0.5696, "lr": 3.50836530715422e-06, "epoch": 1.9104, "percentage": 63.78, "elapsed_time": "5:13:27", "remaining_time": "2:57:59"}
{"current_steps": 200, "total_steps": 312, "loss": 0.6113, "lr": 3.4549150281252635e-06, "epoch": 1.92, "percentage": 64.1, "elapsed_time": "5:14:49", "remaining_time": "2:56:18"}
{"current_steps": 201, "total_steps": 312, "loss": 0.5417, "lr": 3.4016592544210937e-06, "epoch": 1.9296, "percentage": 64.42, "elapsed_time": "5:16:06", "remaining_time": "2:54:33"}
{"current_steps": 202, "total_steps": 312, "loss": 0.5776, "lr": 3.3486046902241663e-06, "epoch": 1.9392, "percentage": 64.74, "elapsed_time": "5:17:31", "remaining_time": "2:52:54"}
{"current_steps": 203, "total_steps": 312, "loss": 0.5334, "lr": 3.295758014387375e-06, "epoch": 1.9487999999999999, "percentage": 65.06, "elapsed_time": "5:18:52", "remaining_time": "2:51:13"}
{"current_steps": 204, "total_steps": 312, "loss": 0.5946, "lr": 3.2431258795932863e-06, "epoch": 1.9584000000000001, "percentage": 65.38, "elapsed_time": "5:20:35", "remaining_time": "2:49:43"}
{"current_steps": 205, "total_steps": 312, "loss": 0.5666, "lr": 3.1907149115166403e-06, "epoch": 1.968, "percentage": 65.71, "elapsed_time": "5:22:07", "remaining_time": "2:48:08"}
{"current_steps": 206, "total_steps": 312, "loss": 0.597, "lr": 3.1385317079902743e-06, "epoch": 1.9776, "percentage": 66.03, "elapsed_time": "5:23:52", "remaining_time": "2:46:39"}
{"current_steps": 207, "total_steps": 312, "loss": 0.538, "lr": 3.0865828381745515e-06, "epoch": 1.9872, "percentage": 66.35, "elapsed_time": "5:25:11", "remaining_time": "2:44:57"}
{"current_steps": 208, "total_steps": 312, "loss": 0.5785, "lr": 3.0348748417303826e-06, "epoch": 1.9968, "percentage": 66.67, "elapsed_time": "5:26:51", "remaining_time": "2:43:25"}
{"current_steps": 209, "total_steps": 312, "loss": 1.0245, "lr": 2.9834142279959754e-06, "epoch": 2.0064, "percentage": 66.99, "elapsed_time": "5:29:19", "remaining_time": "2:42:18"}
{"current_steps": 210, "total_steps": 312, "loss": 0.4894, "lr": 2.932207475167398e-06, "epoch": 2.016, "percentage": 67.31, "elapsed_time": "5:30:53", "remaining_time": "2:40:43"}
{"current_steps": 211, "total_steps": 312, "loss": 0.5657, "lr": 2.8812610294830568e-06, "epoch": 2.0256, "percentage": 67.63, "elapsed_time": "5:32:49", "remaining_time": "2:39:18"}
{"current_steps": 212, "total_steps": 312, "loss": 0.4564, "lr": 2.83058130441221e-06, "epoch": 2.0352, "percentage": 67.95, "elapsed_time": "5:34:08", "remaining_time": "2:37:37"}
{"current_steps": 213, "total_steps": 312, "loss": 0.5775, "lr": 2.7801746798475905e-06, "epoch": 2.0448, "percentage": 68.27, "elapsed_time": "5:36:00", "remaining_time": "2:36:10"}
{"current_steps": 214, "total_steps": 312, "loss": 0.5677, "lr": 2.7300475013022666e-06, "epoch": 2.0544, "percentage": 68.59, "elapsed_time": "5:37:40", "remaining_time": "2:34:38"}
{"current_steps": 215, "total_steps": 312, "loss": 0.5207, "lr": 2.6802060791108304e-06, "epoch": 2.064, "percentage": 68.91, "elapsed_time": "5:38:52", "remaining_time": "2:32:53"}
{"current_steps": 216, "total_steps": 312, "loss": 0.4673, "lr": 2.6306566876350072e-06, "epoch": 2.0736, "percentage": 69.23, "elapsed_time": "5:40:21", "remaining_time": "2:31:16"}
{"current_steps": 217, "total_steps": 312, "loss": 0.5457, "lr": 2.5814055644738013e-06, "epoch": 2.0832, "percentage": 69.55, "elapsed_time": "5:42:08", "remaining_time": "2:29:46"}
{"current_steps": 218, "total_steps": 312, "loss": 0.5164, "lr": 2.532458909678266e-06, "epoch": 2.0928, "percentage": 69.87, "elapsed_time": "5:43:53", "remaining_time": "2:28:16"}
{"current_steps": 219, "total_steps": 312, "loss": 0.557, "lr": 2.483822884971e-06, "epoch": 2.1024, "percentage": 70.19, "elapsed_time": "5:45:31", "remaining_time": "2:26:43"}
{"current_steps": 220, "total_steps": 312, "loss": 0.4987, "lr": 2.43550361297047e-06, "epoch": 2.112, "percentage": 70.51, "elapsed_time": "5:46:46", "remaining_time": "2:25:01"}
{"current_steps": 221, "total_steps": 312, "loss": 0.5607, "lr": 2.387507176420256e-06, "epoch": 2.1216, "percentage": 70.83, "elapsed_time": "5:48:36", "remaining_time": "2:23:32"}
{"current_steps": 222, "total_steps": 312, "loss": 0.5208, "lr": 2.339839617423318e-06, "epoch": 2.1312, "percentage": 71.15, "elapsed_time": "5:50:21", "remaining_time": "2:22:02"}
{"current_steps": 223, "total_steps": 312, "loss": 0.5426, "lr": 2.2925069366813718e-06, "epoch": 2.1408, "percentage": 71.47, "elapsed_time": "5:52:04", "remaining_time": "2:20:30"}
{"current_steps": 224, "total_steps": 312, "loss": 0.5239, "lr": 2.245515092739488e-06, "epoch": 2.1504, "percentage": 71.79, "elapsed_time": "5:53:40", "remaining_time": "2:18:56"}
{"current_steps": 225, "total_steps": 312, "loss": 0.5492, "lr": 2.1988700012359865e-06, "epoch": 2.16, "percentage": 72.12, "elapsed_time": "5:55:16", "remaining_time": "2:17:22"}
{"current_steps": 226, "total_steps": 312, "loss": 0.4777, "lr": 2.1525775341577404e-06, "epoch": 2.1696, "percentage": 72.44, "elapsed_time": "5:56:52", "remaining_time": "2:15:47"}
{"current_steps": 227, "total_steps": 312, "loss": 0.6065, "lr": 2.1066435191009717e-06, "epoch": 2.1792, "percentage": 72.76, "elapsed_time": "5:58:41", "remaining_time": "2:14:18"}
{"current_steps": 228, "total_steps": 312, "loss": 0.4807, "lr": 2.061073738537635e-06, "epoch": 2.1888, "percentage": 73.08, "elapsed_time": "6:00:21", "remaining_time": "2:12:45"}
{"current_steps": 229, "total_steps": 312, "loss": 0.5807, "lr": 2.0158739290874822e-06, "epoch": 2.1984, "percentage": 73.4, "elapsed_time": "6:02:13", "remaining_time": "2:11:17"}
{"current_steps": 230, "total_steps": 312, "loss": 0.5519, "lr": 1.971049780795901e-06, "epoch": 2.208, "percentage": 73.72, "elapsed_time": "6:03:39", "remaining_time": "2:09:38"}
{"current_steps": 231, "total_steps": 312, "loss": 0.5069, "lr": 1.9266069364176144e-06, "epoch": 2.2176, "percentage": 74.04, "elapsed_time": "6:05:03", "remaining_time": "2:08:00"}
{"current_steps": 232, "total_steps": 312, "loss": 0.5327, "lr": 1.8825509907063328e-06, "epoch": 2.2272, "percentage": 74.36, "elapsed_time": "6:06:36", "remaining_time": "2:06:25"}
{"current_steps": 233, "total_steps": 312, "loss": 0.5435, "lr": 1.838887489710452e-06, "epoch": 2.2368, "percentage": 74.68, "elapsed_time": "6:08:02", "remaining_time": "2:04:47"}
{"current_steps": 234, "total_steps": 312, "loss": 0.4793, "lr": 1.7956219300748796e-06, "epoch": 2.2464, "percentage": 75.0, "elapsed_time": "6:09:26", "remaining_time": "2:03:08"}
{"current_steps": 235, "total_steps": 312, "loss": 0.5631, "lr": 1.7527597583490825e-06, "epoch": 2.2560000000000002, "percentage": 75.32, "elapsed_time": "6:11:07", "remaining_time": "2:01:36"}
{"current_steps": 236, "total_steps": 312, "loss": 0.563, "lr": 1.7103063703014372e-06, "epoch": 2.2656, "percentage": 75.64, "elapsed_time": "6:13:00", "remaining_time": "2:00:07"}
{"current_steps": 237, "total_steps": 312, "loss": 0.5599, "lr": 1.6682671102399806e-06, "epoch": 2.2752, "percentage": 75.96, "elapsed_time": "6:14:43", "remaining_time": "1:58:35"}
{"current_steps": 238, "total_steps": 312, "loss": 0.5192, "lr": 1.6266472703396286e-06, "epoch": 2.2848, "percentage": 76.28, "elapsed_time": "6:16:10", "remaining_time": "1:56:57"}
{"current_steps": 239, "total_steps": 312, "loss": 0.5279, "lr": 1.5854520899759656e-06, "epoch": 2.2944, "percentage": 76.6, "elapsed_time": "6:17:37", "remaining_time": "1:55:20"}
{"current_steps": 240, "total_steps": 312, "loss": 0.4906, "lr": 1.544686755065677e-06, "epoch": 2.304, "percentage": 76.92, "elapsed_time": "6:18:46", "remaining_time": "1:53:37"}
{"current_steps": 241, "total_steps": 312, "loss": 0.5485, "lr": 1.5043563974137132e-06, "epoch": 2.3136, "percentage": 77.24, "elapsed_time": "6:20:30", "remaining_time": "1:52:06"}
{"current_steps": 242, "total_steps": 312, "loss": 0.5269, "lr": 1.4644660940672628e-06, "epoch": 2.3232, "percentage": 77.56, "elapsed_time": "6:21:49", "remaining_time": "1:50:26"}
{"current_steps": 243, "total_steps": 312, "loss": 0.5483, "lr": 1.4250208666766235e-06, "epoch": 2.3327999999999998, "percentage": 77.88, "elapsed_time": "6:23:23", "remaining_time": "1:48:51"}
{"current_steps": 244, "total_steps": 312, "loss": 0.5018, "lr": 1.3860256808630429e-06, "epoch": 2.3424, "percentage": 78.21, "elapsed_time": "6:24:47", "remaining_time": "1:47:14"}
{"current_steps": 245, "total_steps": 312, "loss": 0.5486, "lr": 1.3474854455936126e-06, "epoch": 2.352, "percentage": 78.53, "elapsed_time": "6:26:17", "remaining_time": "1:45:38"}
{"current_steps": 246, "total_steps": 312, "loss": 0.5573, "lr": 1.3094050125632973e-06, "epoch": 2.3616, "percentage": 78.85, "elapsed_time": "6:27:41", "remaining_time": "1:44:00"}
{"current_steps": 247, "total_steps": 312, "loss": 0.506, "lr": 1.2717891755841722e-06, "epoch": 2.3712, "percentage": 79.17, "elapsed_time": "6:29:07", "remaining_time": "1:42:23"}
{"current_steps": 248, "total_steps": 312, "loss": 0.5406, "lr": 1.234642669981946e-06, "epoch": 2.3808, "percentage": 79.49, "elapsed_time": "6:31:02", "remaining_time": "1:40:54"}
{"current_steps": 249, "total_steps": 312, "loss": 0.545, "lr": 1.1979701719998454e-06, "epoch": 2.3904, "percentage": 79.81, "elapsed_time": "6:32:52", "remaining_time": "1:39:24"}
{"current_steps": 250, "total_steps": 312, "loss": 0.5294, "lr": 1.1617762982099446e-06, "epoch": 2.4, "percentage": 80.13, "elapsed_time": "6:34:24", "remaining_time": "1:37:48"}
{"current_steps": 251, "total_steps": 312, "loss": 0.5246, "lr": 1.1260656049319957e-06, "epoch": 2.4096, "percentage": 80.45, "elapsed_time": "6:35:58", "remaining_time": "1:36:13"}
{"current_steps": 252, "total_steps": 312, "loss": 0.5649, "lr": 1.0908425876598512e-06, "epoch": 2.4192, "percentage": 80.77, "elapsed_time": "6:37:38", "remaining_time": "1:34:40"}
{"current_steps": 253, "total_steps": 312, "loss": 0.537, "lr": 1.0561116804955451e-06, "epoch": 2.4288, "percentage": 81.09, "elapsed_time": "6:39:10", "remaining_time": "1:33:05"}
{"current_steps": 254, "total_steps": 312, "loss": 0.5036, "lr": 1.0218772555910955e-06, "epoch": 2.4384, "percentage": 81.41, "elapsed_time": "6:40:41", "remaining_time": "1:31:29"}
{"current_steps": 255, "total_steps": 312, "loss": 0.5812, "lr": 9.881436225981107e-07, "epoch": 2.448, "percentage": 81.73, "elapsed_time": "6:42:16", "remaining_time": "1:29:55"}
{"current_steps": 256, "total_steps": 312, "loss": 0.4417, "lr": 9.549150281252633e-07, "epoch": 2.4576000000000002, "percentage": 82.05, "elapsed_time": "6:43:33", "remaining_time": "1:28:16"}
{"current_steps": 257, "total_steps": 312, "loss": 0.5798, "lr": 9.221956552036992e-07, "epoch": 2.4672, "percentage": 82.37, "elapsed_time": "6:45:45", "remaining_time": "1:26:50"}
{"current_steps": 258, "total_steps": 312, "loss": 0.502, "lr": 8.899896227604509e-07, "epoch": 2.4768, "percentage": 82.69, "elapsed_time": "6:47:24", "remaining_time": "1:25:16"}
{"current_steps": 259, "total_steps": 312, "loss": 0.5429, "lr": 8.58300985099918e-07, "epoch": 2.4864, "percentage": 83.01, "elapsed_time": "6:48:43", "remaining_time": "1:23:38"}
{"current_steps": 260, "total_steps": 312, "loss": 0.5403, "lr": 8.271337313934869e-07, "epoch": 2.496, "percentage": 83.33, "elapsed_time": "6:50:16", "remaining_time": "1:22:03"}
{"current_steps": 261, "total_steps": 312, "loss": 0.5212, "lr": 7.964917851773496e-07, "epoch": 2.5056000000000003, "percentage": 83.65, "elapsed_time": "6:51:52", "remaining_time": "1:20:28"}
{"current_steps": 262, "total_steps": 312, "loss": 0.5227, "lr": 7.663790038585794e-07, "epoch": 2.5152, "percentage": 83.97, "elapsed_time": "6:53:27", "remaining_time": "1:18:54"}
{"current_steps": 263, "total_steps": 312, "loss": 0.4788, "lr": 7.367991782295392e-07, "epoch": 2.5248, "percentage": 84.29, "elapsed_time": "6:54:37", "remaining_time": "1:17:15"}
{"current_steps": 264, "total_steps": 312, "loss": 0.5376, "lr": 7.077560319906696e-07, "epoch": 2.5343999999999998, "percentage": 84.62, "elapsed_time": "6:56:14", "remaining_time": "1:15:40"}
{"current_steps": 265, "total_steps": 312, "loss": 0.4766, "lr": 6.792532212817271e-07, "epoch": 2.544, "percentage": 84.94, "elapsed_time": "6:57:41", "remaining_time": "1:14:04"}
{"current_steps": 266, "total_steps": 312, "loss": 0.57, "lr": 6.512943342215234e-07, "epoch": 2.5536, "percentage": 85.26, "elapsed_time": "6:59:23", "remaining_time": "1:12:31"}
{"current_steps": 267, "total_steps": 312, "loss": 0.4631, "lr": 6.238828904562316e-07, "epoch": 2.5632, "percentage": 85.58, "elapsed_time": "7:00:47", "remaining_time": "1:10:55"}
{"current_steps": 268, "total_steps": 312, "loss": 0.549, "lr": 5.9702234071631e-07, "epoch": 2.5728, "percentage": 85.9, "elapsed_time": "7:02:02", "remaining_time": "1:09:17"}
{"current_steps": 269, "total_steps": 312, "loss": 0.5225, "lr": 5.707160663821009e-07, "epoch": 2.5824, "percentage": 86.22, "elapsed_time": "7:03:21", "remaining_time": "1:07:40"}
{"current_steps": 270, "total_steps": 312, "loss": 0.5731, "lr": 5.449673790581611e-07, "epoch": 2.592, "percentage": 86.54, "elapsed_time": "7:05:05", "remaining_time": "1:06:07"}
{"current_steps": 271, "total_steps": 312, "loss": 0.4647, "lr": 5.197795201563744e-07, "epoch": 2.6016, "percentage": 86.86, "elapsed_time": "7:06:42", "remaining_time": "1:04:33"}
{"current_steps": 272, "total_steps": 312, "loss": 0.6043, "lr": 4.951556604879049e-07, "epoch": 2.6112, "percentage": 87.18, "elapsed_time": "7:08:24", "remaining_time": "1:03:00"}
{"current_steps": 273, "total_steps": 312, "loss": 0.5218, "lr": 4.710988998640298e-07, "epoch": 2.6208, "percentage": 87.5, "elapsed_time": "7:09:58", "remaining_time": "1:01:25"}
{"current_steps": 274, "total_steps": 312, "loss": 0.5365, "lr": 4.4761226670592074e-07, "epoch": 2.6304, "percentage": 87.82, "elapsed_time": "7:11:44", "remaining_time": "0:59:52"}
{"current_steps": 275, "total_steps": 312, "loss": 0.5295, "lr": 4.2469871766340096e-07, "epoch": 2.64, "percentage": 88.14, "elapsed_time": "7:13:19", "remaining_time": "0:58:18"}
{"current_steps": 276, "total_steps": 312, "loss": 0.544, "lr": 4.0236113724274716e-07, "epoch": 2.6496, "percentage": 88.46, "elapsed_time": "7:14:52", "remaining_time": "0:56:43"}
{"current_steps": 277, "total_steps": 312, "loss": 0.5751, "lr": 3.8060233744356634e-07, "epoch": 2.6592000000000002, "percentage": 88.78, "elapsed_time": "7:16:18", "remaining_time": "0:55:07"}
{"current_steps": 278, "total_steps": 312, "loss": 0.483, "lr": 3.5942505740480583e-07, "epoch": 2.6688, "percentage": 89.1, "elapsed_time": "7:17:42", "remaining_time": "0:53:31"}
{"current_steps": 279, "total_steps": 312, "loss": 0.5429, "lr": 3.3883196305992906e-07, "epoch": 2.6784, "percentage": 89.42, "elapsed_time": "7:19:13", "remaining_time": "0:51:57"}
{"current_steps": 280, "total_steps": 312, "loss": 0.5176, "lr": 3.18825646801314e-07, "epoch": 2.6879999999999997, "percentage": 89.74, "elapsed_time": "7:20:40", "remaining_time": "0:50:21"}
{"current_steps": 281, "total_steps": 312, "loss": 0.5182, "lr": 2.9940862715390483e-07, "epoch": 2.6976, "percentage": 90.06, "elapsed_time": "7:22:11", "remaining_time": "0:48:46"}
{"current_steps": 282, "total_steps": 312, "loss": 0.4759, "lr": 2.8058334845816214e-07, "epoch": 2.7072000000000003, "percentage": 90.38, "elapsed_time": "7:23:31", "remaining_time": "0:47:11"}
{"current_steps": 283, "total_steps": 312, "loss": 0.5925, "lr": 2.6235218056235633e-07, "epoch": 2.7168, "percentage": 90.71, "elapsed_time": "7:25:08", "remaining_time": "0:45:36"}
{"current_steps": 284, "total_steps": 312, "loss": 0.5799, "lr": 2.447174185242324e-07, "epoch": 2.7264, "percentage": 91.03, "elapsed_time": "7:26:50", "remaining_time": "0:44:03"}
{"current_steps": 285, "total_steps": 312, "loss": 0.4825, "lr": 2.276812823220964e-07, "epoch": 2.7359999999999998, "percentage": 91.35, "elapsed_time": "7:28:10", "remaining_time": "0:42:27"}
{"current_steps": 286, "total_steps": 312, "loss": 0.5338, "lr": 2.1124591657534776e-07, "epoch": 2.7456, "percentage": 91.67, "elapsed_time": "7:29:34", "remaining_time": "0:40:52"}
{"current_steps": 287, "total_steps": 312, "loss": 0.5208, "lr": 1.9541339027450256e-07, "epoch": 2.7552, "percentage": 91.99, "elapsed_time": "7:31:04", "remaining_time": "0:39:17"}
{"current_steps": 288, "total_steps": 312, "loss": 0.5941, "lr": 1.801856965207338e-07, "epoch": 2.7648, "percentage": 92.31, "elapsed_time": "7:32:55", "remaining_time": "0:37:44"}
{"current_steps": 289, "total_steps": 312, "loss": 0.4631, "lr": 1.6556475227496816e-07, "epoch": 2.7744, "percentage": 92.63, "elapsed_time": "7:34:24", "remaining_time": "0:36:09"}
{"current_steps": 290, "total_steps": 312, "loss": 0.5773, "lr": 1.5155239811656562e-07, "epoch": 2.784, "percentage": 92.95, "elapsed_time": "7:36:18", "remaining_time": "0:34:36"}
{"current_steps": 291, "total_steps": 312, "loss": 0.553, "lr": 1.3815039801161723e-07, "epoch": 2.7936, "percentage": 93.27, "elapsed_time": "7:37:59", "remaining_time": "0:33:03"}
{"current_steps": 292, "total_steps": 312, "loss": 0.5055, "lr": 1.253604390908819e-07, "epoch": 2.8032, "percentage": 93.59, "elapsed_time": "7:39:07", "remaining_time": "0:31:26"}
{"current_steps": 293, "total_steps": 312, "loss": 0.5562, "lr": 1.1318413143740436e-07, "epoch": 2.8128, "percentage": 93.91, "elapsed_time": "7:40:41", "remaining_time": "0:29:52"}
{"current_steps": 294, "total_steps": 312, "loss": 0.5532, "lr": 1.0162300788382263e-07, "epoch": 2.8224, "percentage": 94.23, "elapsed_time": "7:42:19", "remaining_time": "0:28:18"}
{"current_steps": 295, "total_steps": 312, "loss": 0.4918, "lr": 9.0678523819408e-08, "epoch": 2.832, "percentage": 94.55, "elapsed_time": "7:43:45", "remaining_time": "0:26:43"}
{"current_steps": 296, "total_steps": 312, "loss": 0.5126, "lr": 8.035205700685167e-08, "epoch": 2.8416, "percentage": 94.87, "elapsed_time": "7:45:10", "remaining_time": "0:25:08"}
{"current_steps": 297, "total_steps": 312, "loss": 0.5539, "lr": 7.064490740882057e-08, "epoch": 2.8512, "percentage": 95.19, "elapsed_time": "7:46:46", "remaining_time": "0:23:34"}
{"current_steps": 298, "total_steps": 312, "loss": 0.5242, "lr": 6.15582970243117e-08, "epoch": 2.8608000000000002, "percentage": 95.51, "elapsed_time": "7:48:13", "remaining_time": "0:21:59"}
{"current_steps": 299, "total_steps": 312, "loss": 0.5205, "lr": 5.3093369734816824e-08, "epoch": 2.8704, "percentage": 95.83, "elapsed_time": "7:49:47", "remaining_time": "0:20:25"}
{"current_steps": 300, "total_steps": 312, "loss": 0.5625, "lr": 4.52511911603265e-08, "epoch": 2.88, "percentage": 96.15, "elapsed_time": "7:51:24", "remaining_time": "0:18:51"}
{"current_steps": 301, "total_steps": 312, "loss": 0.4993, "lr": 3.8032748525179684e-08, "epoch": 2.8895999999999997, "percentage": 96.47, "elapsed_time": "7:52:58", "remaining_time": "0:17:17"}
{"current_steps": 302, "total_steps": 312, "loss": 0.5518, "lr": 3.143895053378698e-08, "epoch": 2.8992, "percentage": 96.79, "elapsed_time": "7:54:38", "remaining_time": "0:15:42"}
{"current_steps": 303, "total_steps": 312, "loss": 0.6037, "lr": 2.547062725623828e-08, "epoch": 2.9088000000000003, "percentage": 97.12, "elapsed_time": "7:55:57", "remaining_time": "0:14:08"}
{"current_steps": 304, "total_steps": 312, "loss": 0.4652, "lr": 2.012853002380466e-08, "epoch": 2.9184, "percentage": 97.44, "elapsed_time": "7:57:28", "remaining_time": "0:12:33"}
{"current_steps": 305, "total_steps": 312, "loss": 0.5442, "lr": 1.541333133436018e-08, "epoch": 2.928, "percentage": 97.76, "elapsed_time": "7:59:08", "remaining_time": "0:10:59"}
{"current_steps": 306, "total_steps": 312, "loss": 0.5293, "lr": 1.132562476771959e-08, "epoch": 2.9375999999999998, "percentage": 98.08, "elapsed_time": "8:00:40", "remaining_time": "0:09:25"}
{"current_steps": 307, "total_steps": 312, "loss": 0.554, "lr": 7.865924910916977e-09, "epoch": 2.9472, "percentage": 98.4, "elapsed_time": "8:02:24", "remaining_time": "0:07:51"}
{"current_steps": 308, "total_steps": 312, "loss": 0.5274, "lr": 5.034667293427053e-09, "epoch": 2.9568, "percentage": 98.72, "elapsed_time": "8:03:53", "remaining_time": "0:06:17"}
{"current_steps": 309, "total_steps": 312, "loss": 0.5124, "lr": 2.8322083323334417e-09, "epoch": 2.9664, "percentage": 99.04, "elapsed_time": "8:05:18", "remaining_time": "0:04:42"}
{"current_steps": 310, "total_steps": 312, "loss": 0.5876, "lr": 1.2588252874673469e-09, "epoch": 2.976, "percentage": 99.36, "elapsed_time": "8:06:54", "remaining_time": "0:03:08"}
{"current_steps": 311, "total_steps": 312, "loss": 0.5288, "lr": 3.147162264971471e-10, "epoch": 2.9856, "percentage": 99.68, "elapsed_time": "8:08:19", "remaining_time": "0:01:34"}
{"current_steps": 312, "total_steps": 312, "loss": 0.5648, "lr": 0.0, "epoch": 2.9952, "percentage": 100.0, "elapsed_time": "8:10:02", "remaining_time": "0:00:00"}
{"current_steps": 312, "total_steps": 312, "epoch": 2.9952, "percentage": 100.0, "elapsed_time": "8:12:09", "remaining_time": "0:00:00"}