mix_base_code_math_t_0_5 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 1
62557bc verified
raw
history blame
37.8 kB
{"current_steps": 1, "total_steps": 312, "loss": 1.0433, "lr": 3.125e-07, "epoch": 0.0096, "percentage": 0.32, "elapsed_time": "0:01:42", "remaining_time": "8:48:44"}
{"current_steps": 2, "total_steps": 312, "loss": 1.0077, "lr": 6.25e-07, "epoch": 0.0192, "percentage": 0.64, "elapsed_time": "0:03:18", "remaining_time": "8:32:41"}
{"current_steps": 3, "total_steps": 312, "loss": 1.0115, "lr": 9.375000000000001e-07, "epoch": 0.0288, "percentage": 0.96, "elapsed_time": "0:04:51", "remaining_time": "8:20:57"}
{"current_steps": 4, "total_steps": 312, "loss": 0.9998, "lr": 1.25e-06, "epoch": 0.0384, "percentage": 1.28, "elapsed_time": "0:06:37", "remaining_time": "8:29:35"}
{"current_steps": 5, "total_steps": 312, "loss": 1.0162, "lr": 1.5625e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:07:53", "remaining_time": "8:04:52"}
{"current_steps": 6, "total_steps": 312, "loss": 1.0018, "lr": 1.8750000000000003e-06, "epoch": 0.0576, "percentage": 1.92, "elapsed_time": "0:09:20", "remaining_time": "7:56:10"}
{"current_steps": 7, "total_steps": 312, "loss": 0.9726, "lr": 2.1875000000000002e-06, "epoch": 0.0672, "percentage": 2.24, "elapsed_time": "0:11:04", "remaining_time": "8:02:40"}
{"current_steps": 8, "total_steps": 312, "loss": 0.9681, "lr": 2.5e-06, "epoch": 0.0768, "percentage": 2.56, "elapsed_time": "0:12:32", "remaining_time": "7:56:38"}
{"current_steps": 9, "total_steps": 312, "loss": 0.9057, "lr": 2.8125e-06, "epoch": 0.0864, "percentage": 2.88, "elapsed_time": "0:14:09", "remaining_time": "7:56:33"}
{"current_steps": 10, "total_steps": 312, "loss": 0.8879, "lr": 3.125e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:15:22", "remaining_time": "7:44:10"}
{"current_steps": 11, "total_steps": 312, "loss": 0.8817, "lr": 3.4375e-06, "epoch": 0.1056, "percentage": 3.53, "elapsed_time": "0:16:57", "remaining_time": "7:44:08"}
{"current_steps": 12, "total_steps": 312, "loss": 0.9022, "lr": 3.7500000000000005e-06, "epoch": 0.1152, "percentage": 3.85, "elapsed_time": "0:18:40", "remaining_time": "7:46:47"}
{"current_steps": 13, "total_steps": 312, "loss": 0.9261, "lr": 4.0625000000000005e-06, "epoch": 0.1248, "percentage": 4.17, "elapsed_time": "0:20:09", "remaining_time": "7:43:47"}
{"current_steps": 14, "total_steps": 312, "loss": 0.8719, "lr": 4.3750000000000005e-06, "epoch": 0.1344, "percentage": 4.49, "elapsed_time": "0:21:42", "remaining_time": "7:41:54"}
{"current_steps": 15, "total_steps": 312, "loss": 0.855, "lr": 4.6875000000000004e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:23:08", "remaining_time": "7:38:08"}
{"current_steps": 16, "total_steps": 312, "loss": 0.8304, "lr": 5e-06, "epoch": 0.1536, "percentage": 5.13, "elapsed_time": "0:24:49", "remaining_time": "7:39:17"}
{"current_steps": 17, "total_steps": 312, "loss": 0.7902, "lr": 5.3125e-06, "epoch": 0.1632, "percentage": 5.45, "elapsed_time": "0:26:04", "remaining_time": "7:32:30"}
{"current_steps": 18, "total_steps": 312, "loss": 0.861, "lr": 5.625e-06, "epoch": 0.1728, "percentage": 5.77, "elapsed_time": "0:27:27", "remaining_time": "7:28:33"}
{"current_steps": 19, "total_steps": 312, "loss": 0.799, "lr": 5.9375e-06, "epoch": 0.1824, "percentage": 6.09, "elapsed_time": "0:28:58", "remaining_time": "7:26:56"}
{"current_steps": 20, "total_steps": 312, "loss": 0.7878, "lr": 6.25e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:30:17", "remaining_time": "7:22:10"}
{"current_steps": 21, "total_steps": 312, "loss": 0.7172, "lr": 6.5625e-06, "epoch": 0.2016, "percentage": 6.73, "elapsed_time": "0:31:44", "remaining_time": "7:19:50"}
{"current_steps": 22, "total_steps": 312, "loss": 0.7376, "lr": 6.875e-06, "epoch": 0.2112, "percentage": 7.05, "elapsed_time": "0:33:03", "remaining_time": "7:15:40"}
{"current_steps": 23, "total_steps": 312, "loss": 0.7649, "lr": 7.1875e-06, "epoch": 0.2208, "percentage": 7.37, "elapsed_time": "0:34:42", "remaining_time": "7:16:06"}
{"current_steps": 24, "total_steps": 312, "loss": 0.7702, "lr": 7.500000000000001e-06, "epoch": 0.2304, "percentage": 7.69, "elapsed_time": "0:36:33", "remaining_time": "7:18:44"}
{"current_steps": 25, "total_steps": 312, "loss": 0.7414, "lr": 7.8125e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:38:08", "remaining_time": "7:17:52"}
{"current_steps": 26, "total_steps": 312, "loss": 0.7156, "lr": 8.125000000000001e-06, "epoch": 0.2496, "percentage": 8.33, "elapsed_time": "0:39:25", "remaining_time": "7:13:37"}
{"current_steps": 27, "total_steps": 312, "loss": 0.7275, "lr": 8.4375e-06, "epoch": 0.2592, "percentage": 8.65, "elapsed_time": "0:41:03", "remaining_time": "7:13:25"}
{"current_steps": 28, "total_steps": 312, "loss": 0.7264, "lr": 8.750000000000001e-06, "epoch": 0.2688, "percentage": 8.97, "elapsed_time": "0:42:44", "remaining_time": "7:13:32"}
{"current_steps": 29, "total_steps": 312, "loss": 0.7222, "lr": 9.0625e-06, "epoch": 0.2784, "percentage": 9.29, "elapsed_time": "0:44:20", "remaining_time": "7:12:43"}
{"current_steps": 30, "total_steps": 312, "loss": 0.7395, "lr": 9.375000000000001e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:46:01", "remaining_time": "7:12:36"}
{"current_steps": 31, "total_steps": 312, "loss": 0.7196, "lr": 9.6875e-06, "epoch": 0.2976, "percentage": 9.94, "elapsed_time": "0:47:42", "remaining_time": "7:12:24"}
{"current_steps": 32, "total_steps": 312, "loss": 0.714, "lr": 1e-05, "epoch": 0.3072, "percentage": 10.26, "elapsed_time": "0:49:26", "remaining_time": "7:12:37"}
{"current_steps": 33, "total_steps": 312, "loss": 0.7318, "lr": 9.999685283773504e-06, "epoch": 0.3168, "percentage": 10.58, "elapsed_time": "0:50:55", "remaining_time": "7:10:32"}
{"current_steps": 34, "total_steps": 312, "loss": 0.6992, "lr": 9.998741174712534e-06, "epoch": 0.3264, "percentage": 10.9, "elapsed_time": "0:52:40", "remaining_time": "7:10:38"}
{"current_steps": 35, "total_steps": 312, "loss": 0.6659, "lr": 9.997167791667668e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "0:54:02", "remaining_time": "7:07:44"}
{"current_steps": 36, "total_steps": 312, "loss": 0.6875, "lr": 9.994965332706574e-06, "epoch": 0.3456, "percentage": 11.54, "elapsed_time": "0:55:42", "remaining_time": "7:07:08"}
{"current_steps": 37, "total_steps": 312, "loss": 0.698, "lr": 9.992134075089085e-06, "epoch": 0.3552, "percentage": 11.86, "elapsed_time": "0:57:21", "remaining_time": "7:06:15"}
{"current_steps": 38, "total_steps": 312, "loss": 0.6955, "lr": 9.98867437523228e-06, "epoch": 0.3648, "percentage": 12.18, "elapsed_time": "0:59:03", "remaining_time": "7:05:53"}
{"current_steps": 39, "total_steps": 312, "loss": 0.6812, "lr": 9.984586668665641e-06, "epoch": 0.3744, "percentage": 12.5, "elapsed_time": "1:00:58", "remaining_time": "7:06:46"}
{"current_steps": 40, "total_steps": 312, "loss": 0.702, "lr": 9.979871469976197e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "1:02:30", "remaining_time": "7:05:06"}
{"current_steps": 41, "total_steps": 312, "loss": 0.7173, "lr": 9.974529372743762e-06, "epoch": 0.3936, "percentage": 13.14, "elapsed_time": "1:04:12", "remaining_time": "7:04:27"}
{"current_steps": 42, "total_steps": 312, "loss": 0.6812, "lr": 9.968561049466214e-06, "epoch": 0.4032, "percentage": 13.46, "elapsed_time": "1:05:43", "remaining_time": "7:02:29"}
{"current_steps": 43, "total_steps": 312, "loss": 0.687, "lr": 9.961967251474823e-06, "epoch": 0.4128, "percentage": 13.78, "elapsed_time": "1:07:27", "remaining_time": "7:01:59"}
{"current_steps": 44, "total_steps": 312, "loss": 0.6998, "lr": 9.954748808839675e-06, "epoch": 0.4224, "percentage": 14.1, "elapsed_time": "1:09:01", "remaining_time": "7:00:26"}
{"current_steps": 45, "total_steps": 312, "loss": 0.6714, "lr": 9.946906630265184e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "1:10:17", "remaining_time": "6:57:06"}
{"current_steps": 46, "total_steps": 312, "loss": 0.6751, "lr": 9.938441702975689e-06, "epoch": 0.4416, "percentage": 14.74, "elapsed_time": "1:11:50", "remaining_time": "6:55:25"}
{"current_steps": 47, "total_steps": 312, "loss": 0.6631, "lr": 9.92935509259118e-06, "epoch": 0.4512, "percentage": 15.06, "elapsed_time": "1:13:31", "remaining_time": "6:54:32"}
{"current_steps": 48, "total_steps": 312, "loss": 0.6804, "lr": 9.91964794299315e-06, "epoch": 0.4608, "percentage": 15.38, "elapsed_time": "1:14:56", "remaining_time": "6:52:10"}
{"current_steps": 49, "total_steps": 312, "loss": 0.69, "lr": 9.909321476180594e-06, "epoch": 0.4704, "percentage": 15.71, "elapsed_time": "1:16:21", "remaining_time": "6:49:49"}
{"current_steps": 50, "total_steps": 312, "loss": 0.6906, "lr": 9.898376992116179e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "1:18:01", "remaining_time": "6:48:52"}
{"current_steps": 51, "total_steps": 312, "loss": 0.6733, "lr": 9.886815868562596e-06, "epoch": 0.4896, "percentage": 16.35, "elapsed_time": "1:19:46", "remaining_time": "6:48:16"}
{"current_steps": 52, "total_steps": 312, "loss": 0.6967, "lr": 9.874639560909118e-06, "epoch": 0.4992, "percentage": 16.67, "elapsed_time": "1:21:15", "remaining_time": "6:46:15"}
{"current_steps": 53, "total_steps": 312, "loss": 0.6443, "lr": 9.861849601988384e-06, "epoch": 0.5088, "percentage": 16.99, "elapsed_time": "1:22:31", "remaining_time": "6:43:18"}
{"current_steps": 54, "total_steps": 312, "loss": 0.6859, "lr": 9.848447601883436e-06, "epoch": 0.5184, "percentage": 17.31, "elapsed_time": "1:24:16", "remaining_time": "6:42:40"}
{"current_steps": 55, "total_steps": 312, "loss": 0.666, "lr": 9.834435247725032e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "1:26:03", "remaining_time": "6:42:08"}
{"current_steps": 56, "total_steps": 312, "loss": 0.6793, "lr": 9.819814303479268e-06, "epoch": 0.5376, "percentage": 17.95, "elapsed_time": "1:27:40", "remaining_time": "6:40:48"}
{"current_steps": 57, "total_steps": 312, "loss": 0.6658, "lr": 9.804586609725499e-06, "epoch": 0.5472, "percentage": 18.27, "elapsed_time": "1:29:29", "remaining_time": "6:40:21"}
{"current_steps": 58, "total_steps": 312, "loss": 0.6394, "lr": 9.788754083424654e-06, "epoch": 0.5568, "percentage": 18.59, "elapsed_time": "1:31:07", "remaining_time": "6:39:05"}
{"current_steps": 59, "total_steps": 312, "loss": 0.6516, "lr": 9.772318717677905e-06, "epoch": 0.5664, "percentage": 18.91, "elapsed_time": "1:32:45", "remaining_time": "6:37:46"}
{"current_steps": 60, "total_steps": 312, "loss": 0.6525, "lr": 9.755282581475769e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "1:34:32", "remaining_time": "6:37:03"}
{"current_steps": 61, "total_steps": 312, "loss": 0.6514, "lr": 9.737647819437645e-06, "epoch": 0.5856, "percentage": 19.55, "elapsed_time": "1:36:08", "remaining_time": "6:35:34"}
{"current_steps": 62, "total_steps": 312, "loss": 0.6435, "lr": 9.719416651541839e-06, "epoch": 0.5952, "percentage": 19.87, "elapsed_time": "1:37:45", "remaining_time": "6:34:09"}
{"current_steps": 63, "total_steps": 312, "loss": 0.6284, "lr": 9.700591372846096e-06, "epoch": 0.6048, "percentage": 20.19, "elapsed_time": "1:39:07", "remaining_time": "6:31:47"}
{"current_steps": 64, "total_steps": 312, "loss": 0.6461, "lr": 9.681174353198687e-06, "epoch": 0.6144, "percentage": 20.51, "elapsed_time": "1:40:57", "remaining_time": "6:31:11"}
{"current_steps": 65, "total_steps": 312, "loss": 0.6377, "lr": 9.661168036940071e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "1:42:41", "remaining_time": "6:30:14"}
{"current_steps": 66, "total_steps": 312, "loss": 0.671, "lr": 9.640574942595195e-06, "epoch": 0.6336, "percentage": 21.15, "elapsed_time": "1:44:02", "remaining_time": "6:27:49"}
{"current_steps": 67, "total_steps": 312, "loss": 0.6321, "lr": 9.619397662556434e-06, "epoch": 0.6432, "percentage": 21.47, "elapsed_time": "1:45:32", "remaining_time": "6:25:55"}
{"current_steps": 68, "total_steps": 312, "loss": 0.6631, "lr": 9.597638862757255e-06, "epoch": 0.6528, "percentage": 21.79, "elapsed_time": "1:46:51", "remaining_time": "6:23:25"}
{"current_steps": 69, "total_steps": 312, "loss": 0.6322, "lr": 9.5753012823366e-06, "epoch": 0.6624, "percentage": 22.12, "elapsed_time": "1:48:22", "remaining_time": "6:21:39"}
{"current_steps": 70, "total_steps": 312, "loss": 0.6306, "lr": 9.552387733294081e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "1:49:57", "remaining_time": "6:20:09"}
{"current_steps": 71, "total_steps": 312, "loss": 0.6515, "lr": 9.528901100135971e-06, "epoch": 0.6816, "percentage": 22.76, "elapsed_time": "1:51:30", "remaining_time": "6:18:31"}
{"current_steps": 72, "total_steps": 312, "loss": 0.6523, "lr": 9.504844339512096e-06, "epoch": 0.6912, "percentage": 23.08, "elapsed_time": "1:53:05", "remaining_time": "6:16:58"}
{"current_steps": 73, "total_steps": 312, "loss": 0.6377, "lr": 9.480220479843627e-06, "epoch": 0.7008, "percentage": 23.4, "elapsed_time": "1:54:36", "remaining_time": "6:15:12"}
{"current_steps": 74, "total_steps": 312, "loss": 0.6265, "lr": 9.45503262094184e-06, "epoch": 0.7104, "percentage": 23.72, "elapsed_time": "1:56:02", "remaining_time": "6:13:12"}
{"current_steps": 75, "total_steps": 312, "loss": 0.6339, "lr": 9.4292839336179e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "1:57:39", "remaining_time": "6:11:47"}
{"current_steps": 76, "total_steps": 312, "loss": 0.633, "lr": 9.40297765928369e-06, "epoch": 0.7296, "percentage": 24.36, "elapsed_time": "1:58:59", "remaining_time": "6:09:29"}
{"current_steps": 77, "total_steps": 312, "loss": 0.653, "lr": 9.376117109543769e-06, "epoch": 0.7392, "percentage": 24.68, "elapsed_time": "2:00:30", "remaining_time": "6:07:48"}
{"current_steps": 78, "total_steps": 312, "loss": 0.6315, "lr": 9.348705665778479e-06, "epoch": 0.7488, "percentage": 25.0, "elapsed_time": "2:01:55", "remaining_time": "6:05:45"}
{"current_steps": 79, "total_steps": 312, "loss": 0.6411, "lr": 9.320746778718274e-06, "epoch": 0.7584, "percentage": 25.32, "elapsed_time": "2:03:29", "remaining_time": "6:04:13"}
{"current_steps": 80, "total_steps": 312, "loss": 0.6365, "lr": 9.292243968009332e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "2:04:47", "remaining_time": "6:01:55"}
{"current_steps": 81, "total_steps": 312, "loss": 0.6323, "lr": 9.263200821770462e-06, "epoch": 0.7776, "percentage": 25.96, "elapsed_time": "2:06:32", "remaining_time": "6:00:51"}
{"current_steps": 82, "total_steps": 312, "loss": 0.6308, "lr": 9.233620996141421e-06, "epoch": 0.7872, "percentage": 26.28, "elapsed_time": "2:07:56", "remaining_time": "5:58:51"}
{"current_steps": 83, "total_steps": 312, "loss": 0.6506, "lr": 9.203508214822652e-06, "epoch": 0.7968, "percentage": 26.6, "elapsed_time": "2:09:34", "remaining_time": "5:57:29"}
{"current_steps": 84, "total_steps": 312, "loss": 0.637, "lr": 9.172866268606514e-06, "epoch": 0.8064, "percentage": 26.92, "elapsed_time": "2:11:08", "remaining_time": "5:55:56"}
{"current_steps": 85, "total_steps": 312, "loss": 0.6459, "lr": 9.141699014900084e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "2:12:45", "remaining_time": "5:54:32"}
{"current_steps": 86, "total_steps": 312, "loss": 0.6292, "lr": 9.110010377239552e-06, "epoch": 0.8256, "percentage": 27.56, "elapsed_time": "2:14:16", "remaining_time": "5:52:52"}
{"current_steps": 87, "total_steps": 312, "loss": 0.6732, "lr": 9.077804344796302e-06, "epoch": 0.8352, "percentage": 27.88, "elapsed_time": "2:15:55", "remaining_time": "5:51:31"}
{"current_steps": 88, "total_steps": 312, "loss": 0.6458, "lr": 9.045084971874738e-06, "epoch": 0.8448, "percentage": 28.21, "elapsed_time": "2:17:38", "remaining_time": "5:50:21"}
{"current_steps": 89, "total_steps": 312, "loss": 0.6382, "lr": 9.011856377401891e-06, "epoch": 0.8544, "percentage": 28.53, "elapsed_time": "2:19:16", "remaining_time": "5:48:57"}
{"current_steps": 90, "total_steps": 312, "loss": 0.6416, "lr": 8.978122744408905e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "2:21:08", "remaining_time": "5:48:08"}
{"current_steps": 91, "total_steps": 312, "loss": 0.6572, "lr": 8.943888319504456e-06, "epoch": 0.8736, "percentage": 29.17, "elapsed_time": "2:23:00", "remaining_time": "5:47:19"}
{"current_steps": 92, "total_steps": 312, "loss": 0.652, "lr": 8.90915741234015e-06, "epoch": 0.8832, "percentage": 29.49, "elapsed_time": "2:24:36", "remaining_time": "5:45:47"}
{"current_steps": 93, "total_steps": 312, "loss": 0.6423, "lr": 8.873934395068006e-06, "epoch": 0.8928, "percentage": 29.81, "elapsed_time": "2:26:08", "remaining_time": "5:44:07"}
{"current_steps": 94, "total_steps": 312, "loss": 0.6345, "lr": 8.838223701790057e-06, "epoch": 0.9024, "percentage": 30.13, "elapsed_time": "2:27:40", "remaining_time": "5:42:28"}
{"current_steps": 95, "total_steps": 312, "loss": 0.6438, "lr": 8.802029828000157e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "2:29:07", "remaining_time": "5:40:37"}
{"current_steps": 96, "total_steps": 312, "loss": 0.618, "lr": 8.765357330018056e-06, "epoch": 0.9216, "percentage": 30.77, "elapsed_time": "2:30:37", "remaining_time": "5:38:54"}
{"current_steps": 97, "total_steps": 312, "loss": 0.6686, "lr": 8.728210824415829e-06, "epoch": 0.9312, "percentage": 31.09, "elapsed_time": "2:32:19", "remaining_time": "5:37:36"}
{"current_steps": 98, "total_steps": 312, "loss": 0.6275, "lr": 8.690594987436705e-06, "epoch": 0.9408, "percentage": 31.41, "elapsed_time": "2:33:48", "remaining_time": "5:35:51"}
{"current_steps": 99, "total_steps": 312, "loss": 0.6106, "lr": 8.652514554406388e-06, "epoch": 0.9504, "percentage": 31.73, "elapsed_time": "2:35:22", "remaining_time": "5:34:17"}
{"current_steps": 100, "total_steps": 312, "loss": 0.6525, "lr": 8.613974319136959e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "2:37:07", "remaining_time": "5:33:05"}
{"current_steps": 101, "total_steps": 312, "loss": 0.6289, "lr": 8.574979133323378e-06, "epoch": 0.9696, "percentage": 32.37, "elapsed_time": "2:38:54", "remaining_time": "5:31:59"}
{"current_steps": 102, "total_steps": 312, "loss": 0.6406, "lr": 8.535533905932739e-06, "epoch": 0.9792, "percentage": 32.69, "elapsed_time": "2:40:51", "remaining_time": "5:31:09"}
{"current_steps": 103, "total_steps": 312, "loss": 0.6076, "lr": 8.495643602586287e-06, "epoch": 0.9888, "percentage": 33.01, "elapsed_time": "2:42:22", "remaining_time": "5:29:29"}
{"current_steps": 104, "total_steps": 312, "loss": 0.6568, "lr": 8.455313244934324e-06, "epoch": 0.9984, "percentage": 33.33, "elapsed_time": "2:44:07", "remaining_time": "5:28:14"}
{"current_steps": 105, "total_steps": 312, "loss": 1.1839, "lr": 8.414547910024035e-06, "epoch": 1.008, "percentage": 33.65, "elapsed_time": "2:46:49", "remaining_time": "5:28:52"}
{"current_steps": 106, "total_steps": 312, "loss": 0.5265, "lr": 8.373352729660373e-06, "epoch": 1.0176, "percentage": 33.97, "elapsed_time": "2:48:18", "remaining_time": "5:27:06"}
{"current_steps": 107, "total_steps": 312, "loss": 0.6195, "lr": 8.331732889760021e-06, "epoch": 1.0272, "percentage": 34.29, "elapsed_time": "2:49:45", "remaining_time": "5:25:13"}
{"current_steps": 108, "total_steps": 312, "loss": 0.5916, "lr": 8.289693629698564e-06, "epoch": 1.0368, "percentage": 34.62, "elapsed_time": "2:51:33", "remaining_time": "5:24:03"}
{"current_steps": 109, "total_steps": 312, "loss": 0.6107, "lr": 8.247240241650918e-06, "epoch": 1.0464, "percentage": 34.94, "elapsed_time": "2:53:13", "remaining_time": "5:22:36"}
{"current_steps": 110, "total_steps": 312, "loss": 0.574, "lr": 8.204378069925121e-06, "epoch": 1.056, "percentage": 35.26, "elapsed_time": "2:54:52", "remaining_time": "5:21:07"}
{"current_steps": 111, "total_steps": 312, "loss": 0.5733, "lr": 8.16111251028955e-06, "epoch": 1.0656, "percentage": 35.58, "elapsed_time": "2:56:19", "remaining_time": "5:19:17"}
{"current_steps": 112, "total_steps": 312, "loss": 0.5392, "lr": 8.117449009293668e-06, "epoch": 1.0752, "percentage": 35.9, "elapsed_time": "2:57:54", "remaining_time": "5:17:42"}
{"current_steps": 113, "total_steps": 312, "loss": 0.6129, "lr": 8.073393063582386e-06, "epoch": 1.0848, "percentage": 36.22, "elapsed_time": "2:59:30", "remaining_time": "5:16:06"}
{"current_steps": 114, "total_steps": 312, "loss": 0.5385, "lr": 8.0289502192041e-06, "epoch": 1.0944, "percentage": 36.54, "elapsed_time": "3:00:54", "remaining_time": "5:14:13"}
{"current_steps": 115, "total_steps": 312, "loss": 0.5992, "lr": 7.984126070912519e-06, "epoch": 1.104, "percentage": 36.86, "elapsed_time": "3:02:19", "remaining_time": "5:12:19"}
{"current_steps": 116, "total_steps": 312, "loss": 0.5639, "lr": 7.938926261462366e-06, "epoch": 1.1136, "percentage": 37.18, "elapsed_time": "3:03:54", "remaining_time": "5:10:44"}
{"current_steps": 117, "total_steps": 312, "loss": 0.5616, "lr": 7.89335648089903e-06, "epoch": 1.1232, "percentage": 37.5, "elapsed_time": "3:05:35", "remaining_time": "5:09:19"}
{"current_steps": 118, "total_steps": 312, "loss": 0.6215, "lr": 7.84742246584226e-06, "epoch": 1.1328, "percentage": 37.82, "elapsed_time": "3:07:09", "remaining_time": "5:07:42"}
{"current_steps": 119, "total_steps": 312, "loss": 0.5937, "lr": 7.801129998764014e-06, "epoch": 1.1424, "percentage": 38.14, "elapsed_time": "3:08:27", "remaining_time": "5:05:38"}
{"current_steps": 120, "total_steps": 312, "loss": 0.5782, "lr": 7.754484907260513e-06, "epoch": 1.152, "percentage": 38.46, "elapsed_time": "3:10:10", "remaining_time": "5:04:16"}
{"current_steps": 121, "total_steps": 312, "loss": 0.5605, "lr": 7.70749306331863e-06, "epoch": 1.1616, "percentage": 38.78, "elapsed_time": "3:11:55", "remaining_time": "5:02:57"}
{"current_steps": 122, "total_steps": 312, "loss": 0.6192, "lr": 7.660160382576683e-06, "epoch": 1.1712, "percentage": 39.1, "elapsed_time": "3:13:55", "remaining_time": "5:02:00"}
{"current_steps": 123, "total_steps": 312, "loss": 0.572, "lr": 7.612492823579744e-06, "epoch": 1.1808, "percentage": 39.42, "elapsed_time": "3:15:36", "remaining_time": "5:00:34"}
{"current_steps": 124, "total_steps": 312, "loss": 0.6344, "lr": 7.564496387029532e-06, "epoch": 1.1904, "percentage": 39.74, "elapsed_time": "3:16:57", "remaining_time": "4:58:36"}
{"current_steps": 125, "total_steps": 312, "loss": 0.5583, "lr": 7.516177115029002e-06, "epoch": 1.2, "percentage": 40.06, "elapsed_time": "3:18:47", "remaining_time": "4:57:22"}
{"current_steps": 126, "total_steps": 312, "loss": 0.6031, "lr": 7.467541090321735e-06, "epoch": 1.2096, "percentage": 40.38, "elapsed_time": "3:20:28", "remaining_time": "4:55:56"}
{"current_steps": 127, "total_steps": 312, "loss": 0.5596, "lr": 7.4185944355261996e-06, "epoch": 1.2192, "percentage": 40.71, "elapsed_time": "3:22:03", "remaining_time": "4:54:20"}
{"current_steps": 128, "total_steps": 312, "loss": 0.5966, "lr": 7.369343312364994e-06, "epoch": 1.2288000000000001, "percentage": 41.03, "elapsed_time": "3:23:36", "remaining_time": "4:52:40"}
{"current_steps": 129, "total_steps": 312, "loss": 0.5785, "lr": 7.319793920889171e-06, "epoch": 1.2384, "percentage": 41.35, "elapsed_time": "3:24:58", "remaining_time": "4:50:46"}
{"current_steps": 130, "total_steps": 312, "loss": 0.6048, "lr": 7.269952498697734e-06, "epoch": 1.248, "percentage": 41.67, "elapsed_time": "3:26:25", "remaining_time": "4:48:59"}
{"current_steps": 131, "total_steps": 312, "loss": 0.6424, "lr": 7.219825320152411e-06, "epoch": 1.2576, "percentage": 41.99, "elapsed_time": "3:28:15", "remaining_time": "4:47:44"}
{"current_steps": 132, "total_steps": 312, "loss": 0.4882, "lr": 7.169418695587791e-06, "epoch": 1.2671999999999999, "percentage": 42.31, "elapsed_time": "3:29:31", "remaining_time": "4:45:43"}
{"current_steps": 133, "total_steps": 312, "loss": 0.6386, "lr": 7.118738970516944e-06, "epoch": 1.2768, "percentage": 42.63, "elapsed_time": "3:31:08", "remaining_time": "4:44:10"}
{"current_steps": 134, "total_steps": 312, "loss": 0.55, "lr": 7.067792524832604e-06, "epoch": 1.2864, "percentage": 42.95, "elapsed_time": "3:32:31", "remaining_time": "4:42:18"}
{"current_steps": 135, "total_steps": 312, "loss": 0.5872, "lr": 7.016585772004026e-06, "epoch": 1.296, "percentage": 43.27, "elapsed_time": "3:33:42", "remaining_time": "4:40:12"}
{"current_steps": 136, "total_steps": 312, "loss": 0.5644, "lr": 6.965125158269619e-06, "epoch": 1.3056, "percentage": 43.59, "elapsed_time": "3:35:28", "remaining_time": "4:38:51"}
{"current_steps": 137, "total_steps": 312, "loss": 0.5939, "lr": 6.913417161825449e-06, "epoch": 1.3152, "percentage": 43.91, "elapsed_time": "3:37:07", "remaining_time": "4:37:20"}
{"current_steps": 138, "total_steps": 312, "loss": 0.5159, "lr": 6.8614682920097265e-06, "epoch": 1.3248, "percentage": 44.23, "elapsed_time": "3:38:28", "remaining_time": "4:35:27"}
{"current_steps": 139, "total_steps": 312, "loss": 0.6378, "lr": 6.809285088483361e-06, "epoch": 1.3344, "percentage": 44.55, "elapsed_time": "3:40:08", "remaining_time": "4:33:59"}
{"current_steps": 140, "total_steps": 312, "loss": 0.5809, "lr": 6.7568741204067145e-06, "epoch": 1.3439999999999999, "percentage": 44.87, "elapsed_time": "3:41:57", "remaining_time": "4:32:41"}
{"current_steps": 141, "total_steps": 312, "loss": 0.5644, "lr": 6.704241985612625e-06, "epoch": 1.3536000000000001, "percentage": 45.19, "elapsed_time": "3:43:44", "remaining_time": "4:31:21"}
{"current_steps": 142, "total_steps": 312, "loss": 0.5674, "lr": 6.651395309775837e-06, "epoch": 1.3632, "percentage": 45.51, "elapsed_time": "3:45:38", "remaining_time": "4:30:07"}
{"current_steps": 143, "total_steps": 312, "loss": 0.5975, "lr": 6.598340745578908e-06, "epoch": 1.3728, "percentage": 45.83, "elapsed_time": "3:47:33", "remaining_time": "4:28:56"}
{"current_steps": 144, "total_steps": 312, "loss": 0.5691, "lr": 6.545084971874738e-06, "epoch": 1.3824, "percentage": 46.15, "elapsed_time": "3:49:11", "remaining_time": "4:27:23"}
{"current_steps": 145, "total_steps": 312, "loss": 0.5846, "lr": 6.491634692845781e-06, "epoch": 1.392, "percentage": 46.47, "elapsed_time": "3:50:44", "remaining_time": "4:25:45"}
{"current_steps": 146, "total_steps": 312, "loss": 0.5742, "lr": 6.437996637160086e-06, "epoch": 1.4016, "percentage": 46.79, "elapsed_time": "3:52:22", "remaining_time": "4:24:12"}
{"current_steps": 147, "total_steps": 312, "loss": 0.6475, "lr": 6.384177557124247e-06, "epoch": 1.4112, "percentage": 47.12, "elapsed_time": "3:54:01", "remaining_time": "4:22:40"}
{"current_steps": 148, "total_steps": 312, "loss": 0.5551, "lr": 6.330184227833376e-06, "epoch": 1.4208, "percentage": 47.44, "elapsed_time": "3:55:40", "remaining_time": "4:21:09"}
{"current_steps": 149, "total_steps": 312, "loss": 0.5611, "lr": 6.276023446318214e-06, "epoch": 1.4304000000000001, "percentage": 47.76, "elapsed_time": "3:57:10", "remaining_time": "4:19:28"}
{"current_steps": 150, "total_steps": 312, "loss": 0.6391, "lr": 6.2217020306894705e-06, "epoch": 1.44, "percentage": 48.08, "elapsed_time": "3:58:28", "remaining_time": "4:17:33"}
{"current_steps": 151, "total_steps": 312, "loss": 0.5015, "lr": 6.1672268192795285e-06, "epoch": 1.4496, "percentage": 48.4, "elapsed_time": "3:59:53", "remaining_time": "4:15:46"}
{"current_steps": 152, "total_steps": 312, "loss": 0.5833, "lr": 6.112604669781572e-06, "epoch": 1.4592, "percentage": 48.72, "elapsed_time": "4:01:23", "remaining_time": "4:14:05"}
{"current_steps": 153, "total_steps": 312, "loss": 0.6352, "lr": 6.057842458386315e-06, "epoch": 1.4687999999999999, "percentage": 49.04, "elapsed_time": "4:03:02", "remaining_time": "4:12:34"}
{"current_steps": 154, "total_steps": 312, "loss": 0.5687, "lr": 6.002947078916365e-06, "epoch": 1.4784, "percentage": 49.36, "elapsed_time": "4:04:18", "remaining_time": "4:10:39"}
{"current_steps": 155, "total_steps": 312, "loss": 0.5447, "lr": 5.947925441958393e-06, "epoch": 1.488, "percentage": 49.68, "elapsed_time": "4:05:42", "remaining_time": "4:08:52"}
{"current_steps": 156, "total_steps": 312, "loss": 0.5974, "lr": 5.892784473993184e-06, "epoch": 1.4976, "percentage": 50.0, "elapsed_time": "4:07:10", "remaining_time": "4:07:10"}
{"current_steps": 157, "total_steps": 312, "loss": 0.6202, "lr": 5.837531116523683e-06, "epoch": 1.5072, "percentage": 50.32, "elapsed_time": "4:08:47", "remaining_time": "4:05:37"}
{"current_steps": 158, "total_steps": 312, "loss": 0.5773, "lr": 5.782172325201155e-06, "epoch": 1.5168, "percentage": 50.64, "elapsed_time": "4:10:07", "remaining_time": "4:03:47"}
{"current_steps": 159, "total_steps": 312, "loss": 0.5287, "lr": 5.726715068949564e-06, "epoch": 1.5264, "percentage": 50.96, "elapsed_time": "4:11:36", "remaining_time": "4:02:06"}
{"current_steps": 160, "total_steps": 312, "loss": 0.5825, "lr": 5.671166329088278e-06, "epoch": 1.536, "percentage": 51.28, "elapsed_time": "4:13:09", "remaining_time": "4:00:29"}
{"current_steps": 161, "total_steps": 312, "loss": 0.5705, "lr": 5.615533098453215e-06, "epoch": 1.5455999999999999, "percentage": 51.6, "elapsed_time": "4:14:45", "remaining_time": "3:58:56"}
{"current_steps": 162, "total_steps": 312, "loss": 0.5636, "lr": 5.559822380516539e-06, "epoch": 1.5552000000000001, "percentage": 51.92, "elapsed_time": "4:16:14", "remaining_time": "3:57:15"}
{"current_steps": 163, "total_steps": 312, "loss": 0.6215, "lr": 5.504041188505022e-06, "epoch": 1.5648, "percentage": 52.24, "elapsed_time": "4:17:56", "remaining_time": "3:55:47"}
{"current_steps": 164, "total_steps": 312, "loss": 0.5536, "lr": 5.448196544517168e-06, "epoch": 1.5744, "percentage": 52.56, "elapsed_time": "4:19:37", "remaining_time": "3:54:17"}
{"current_steps": 165, "total_steps": 312, "loss": 0.5631, "lr": 5.392295478639226e-06, "epoch": 1.584, "percentage": 52.88, "elapsed_time": "4:21:11", "remaining_time": "3:52:42"}
{"current_steps": 166, "total_steps": 312, "loss": 0.6346, "lr": 5.336345028060199e-06, "epoch": 1.5936, "percentage": 53.21, "elapsed_time": "4:22:38", "remaining_time": "3:51:00"}
{"current_steps": 167, "total_steps": 312, "loss": 0.5556, "lr": 5.2803522361859596e-06, "epoch": 1.6032, "percentage": 53.53, "elapsed_time": "4:24:07", "remaining_time": "3:49:19"}
{"current_steps": 168, "total_steps": 312, "loss": 0.5818, "lr": 5.224324151752575e-06, "epoch": 1.6128, "percentage": 53.85, "elapsed_time": "4:25:48", "remaining_time": "3:47:49"}
{"current_steps": 169, "total_steps": 312, "loss": 0.525, "lr": 5.168267827938971e-06, "epoch": 1.6223999999999998, "percentage": 54.17, "elapsed_time": "4:27:18", "remaining_time": "3:46:10"}
{"current_steps": 170, "total_steps": 312, "loss": 0.5892, "lr": 5.112190321479026e-06, "epoch": 1.6320000000000001, "percentage": 54.49, "elapsed_time": "4:29:13", "remaining_time": "3:44:52"}
{"current_steps": 171, "total_steps": 312, "loss": 0.5804, "lr": 5.05609869177323e-06, "epoch": 1.6416, "percentage": 54.81, "elapsed_time": "4:30:41", "remaining_time": "3:43:11"}
{"current_steps": 172, "total_steps": 312, "loss": 0.5514, "lr": 5e-06, "epoch": 1.6512, "percentage": 55.13, "elapsed_time": "4:31:58", "remaining_time": "3:41:22"}
{"current_steps": 173, "total_steps": 312, "loss": 0.5864, "lr": 4.943901308226771e-06, "epoch": 1.6608, "percentage": 55.45, "elapsed_time": "4:33:57", "remaining_time": "3:40:07"}
{"current_steps": 174, "total_steps": 312, "loss": 0.5485, "lr": 4.887809678520976e-06, "epoch": 1.6703999999999999, "percentage": 55.77, "elapsed_time": "4:35:22", "remaining_time": "3:38:24"}
{"current_steps": 175, "total_steps": 312, "loss": 0.6079, "lr": 4.831732172061032e-06, "epoch": 1.6800000000000002, "percentage": 56.09, "elapsed_time": "4:36:40", "remaining_time": "3:36:35"}
{"current_steps": 176, "total_steps": 312, "loss": 0.5801, "lr": 4.775675848247427e-06, "epoch": 1.6896, "percentage": 56.41, "elapsed_time": "4:37:50", "remaining_time": "3:34:41"}
{"current_steps": 177, "total_steps": 312, "loss": 0.6149, "lr": 4.719647763814041e-06, "epoch": 1.6992, "percentage": 56.73, "elapsed_time": "4:39:30", "remaining_time": "3:33:10"}
{"current_steps": 178, "total_steps": 312, "loss": 0.5747, "lr": 4.663654971939802e-06, "epoch": 1.7088, "percentage": 57.05, "elapsed_time": "4:40:56", "remaining_time": "3:31:29"}
{"current_steps": 179, "total_steps": 312, "loss": 0.5494, "lr": 4.6077045213607765e-06, "epoch": 1.7184, "percentage": 57.37, "elapsed_time": "4:42:11", "remaining_time": "3:29:40"}
{"current_steps": 180, "total_steps": 312, "loss": 0.6107, "lr": 4.551803455482833e-06, "epoch": 1.728, "percentage": 57.69, "elapsed_time": "4:43:43", "remaining_time": "3:28:04"}
{"current_steps": 181, "total_steps": 312, "loss": 0.6397, "lr": 4.4959588114949785e-06, "epoch": 1.7376, "percentage": 58.01, "elapsed_time": "4:45:45", "remaining_time": "3:26:49"}
{"current_steps": 182, "total_steps": 312, "loss": 0.5693, "lr": 4.4401776194834615e-06, "epoch": 1.7471999999999999, "percentage": 58.33, "elapsed_time": "4:47:19", "remaining_time": "3:25:13"}
{"current_steps": 183, "total_steps": 312, "loss": 0.5641, "lr": 4.384466901546786e-06, "epoch": 1.7568000000000001, "percentage": 58.65, "elapsed_time": "4:49:04", "remaining_time": "3:23:46"}
{"current_steps": 184, "total_steps": 312, "loss": 0.5919, "lr": 4.3288336709117246e-06, "epoch": 1.7664, "percentage": 58.97, "elapsed_time": "4:50:46", "remaining_time": "3:22:16"}
{"current_steps": 185, "total_steps": 312, "loss": 0.5703, "lr": 4.273284931050438e-06, "epoch": 1.776, "percentage": 59.29, "elapsed_time": "4:52:28", "remaining_time": "3:20:46"}
{"current_steps": 186, "total_steps": 312, "loss": 0.5699, "lr": 4.217827674798845e-06, "epoch": 1.7856, "percentage": 59.62, "elapsed_time": "4:54:15", "remaining_time": "3:19:19"}
{"current_steps": 187, "total_steps": 312, "loss": 0.6142, "lr": 4.162468883476319e-06, "epoch": 1.7952, "percentage": 59.94, "elapsed_time": "4:56:10", "remaining_time": "3:17:58"}
{"current_steps": 188, "total_steps": 312, "loss": 0.5429, "lr": 4.107215526006818e-06, "epoch": 1.8048, "percentage": 60.26, "elapsed_time": "4:58:05", "remaining_time": "3:16:36"}
{"current_steps": 189, "total_steps": 312, "loss": 0.5619, "lr": 4.052074558041608e-06, "epoch": 1.8144, "percentage": 60.58, "elapsed_time": "4:59:37", "remaining_time": "3:14:59"}
{"current_steps": 190, "total_steps": 312, "loss": 0.5374, "lr": 3.997052921083637e-06, "epoch": 1.8239999999999998, "percentage": 60.9, "elapsed_time": "5:01:13", "remaining_time": "3:13:25"}
{"current_steps": 191, "total_steps": 312, "loss": 0.602, "lr": 3.9421575416136866e-06, "epoch": 1.8336000000000001, "percentage": 61.22, "elapsed_time": "5:02:58", "remaining_time": "3:11:56"}
{"current_steps": 192, "total_steps": 312, "loss": 0.5084, "lr": 3.887395330218429e-06, "epoch": 1.8432, "percentage": 61.54, "elapsed_time": "5:04:27", "remaining_time": "3:10:16"}
{"current_steps": 193, "total_steps": 312, "loss": 0.6236, "lr": 3.832773180720475e-06, "epoch": 1.8528, "percentage": 61.86, "elapsed_time": "5:06:03", "remaining_time": "3:08:42"}
{"current_steps": 194, "total_steps": 312, "loss": 0.5434, "lr": 3.778297969310529e-06, "epoch": 1.8624, "percentage": 62.18, "elapsed_time": "5:07:26", "remaining_time": "3:07:00"}
{"current_steps": 195, "total_steps": 312, "loss": 0.5635, "lr": 3.723976553681787e-06, "epoch": 1.8719999999999999, "percentage": 62.5, "elapsed_time": "5:08:54", "remaining_time": "3:05:20"}
{"current_steps": 196, "total_steps": 312, "loss": 0.6102, "lr": 3.669815772166625e-06, "epoch": 1.8816000000000002, "percentage": 62.82, "elapsed_time": "5:10:29", "remaining_time": "3:03:45"}
{"current_steps": 197, "total_steps": 312, "loss": 0.5521, "lr": 3.6158224428757538e-06, "epoch": 1.8912, "percentage": 63.14, "elapsed_time": "5:12:07", "remaining_time": "3:02:12"}
{"current_steps": 198, "total_steps": 312, "loss": 0.5657, "lr": 3.562003362839914e-06, "epoch": 1.9008, "percentage": 63.46, "elapsed_time": "5:13:34", "remaining_time": "3:00:32"}
{"current_steps": 199, "total_steps": 312, "loss": 0.6052, "lr": 3.50836530715422e-06, "epoch": 1.9104, "percentage": 63.78, "elapsed_time": "5:14:54", "remaining_time": "2:58:49"}
{"current_steps": 200, "total_steps": 312, "loss": 0.5717, "lr": 3.4549150281252635e-06, "epoch": 1.92, "percentage": 64.1, "elapsed_time": "5:16:23", "remaining_time": "2:57:10"}
{"current_steps": 201, "total_steps": 312, "loss": 0.5916, "lr": 3.4016592544210937e-06, "epoch": 1.9296, "percentage": 64.42, "elapsed_time": "5:17:55", "remaining_time": "2:55:34"}
{"current_steps": 202, "total_steps": 312, "loss": 0.575, "lr": 3.3486046902241663e-06, "epoch": 1.9392, "percentage": 64.74, "elapsed_time": "5:19:14", "remaining_time": "2:53:50"}
{"current_steps": 203, "total_steps": 312, "loss": 0.5483, "lr": 3.295758014387375e-06, "epoch": 1.9487999999999999, "percentage": 65.06, "elapsed_time": "5:20:43", "remaining_time": "2:52:12"}
{"current_steps": 204, "total_steps": 312, "loss": 0.5633, "lr": 3.2431258795932863e-06, "epoch": 1.9584000000000001, "percentage": 65.38, "elapsed_time": "5:22:18", "remaining_time": "2:50:37"}
{"current_steps": 205, "total_steps": 312, "loss": 0.6315, "lr": 3.1907149115166403e-06, "epoch": 1.968, "percentage": 65.71, "elapsed_time": "5:24:03", "remaining_time": "2:49:08"}
{"current_steps": 206, "total_steps": 312, "loss": 0.5895, "lr": 3.1385317079902743e-06, "epoch": 1.9776, "percentage": 66.03, "elapsed_time": "5:25:46", "remaining_time": "2:47:37"}
{"current_steps": 207, "total_steps": 312, "loss": 0.5481, "lr": 3.0865828381745515e-06, "epoch": 1.9872, "percentage": 66.35, "elapsed_time": "5:27:30", "remaining_time": "2:46:07"}
{"current_steps": 208, "total_steps": 312, "loss": 0.5961, "lr": 3.0348748417303826e-06, "epoch": 1.9968, "percentage": 66.67, "elapsed_time": "5:29:09", "remaining_time": "2:44:34"}
{"current_steps": 209, "total_steps": 312, "loss": 1.0621, "lr": 2.9834142279959754e-06, "epoch": 2.0064, "percentage": 66.99, "elapsed_time": "5:31:49", "remaining_time": "2:43:32"}