mix_base_code_math_t_0_75 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 0
8bd0509 verified
raw
history blame
18.7 kB
{"current_steps": 1, "total_steps": 312, "loss": 1.0265, "lr": 3.125e-07, "epoch": 0.0096, "percentage": 0.32, "elapsed_time": "0:01:31", "remaining_time": "7:52:49"}
{"current_steps": 2, "total_steps": 312, "loss": 1.0057, "lr": 6.25e-07, "epoch": 0.0192, "percentage": 0.64, "elapsed_time": "0:03:06", "remaining_time": "8:01:18"}
{"current_steps": 3, "total_steps": 312, "loss": 1.0008, "lr": 9.375000000000001e-07, "epoch": 0.0288, "percentage": 0.96, "elapsed_time": "0:04:46", "remaining_time": "8:11:21"}
{"current_steps": 4, "total_steps": 312, "loss": 0.9984, "lr": 1.25e-06, "epoch": 0.0384, "percentage": 1.28, "elapsed_time": "0:06:19", "remaining_time": "8:06:44"}
{"current_steps": 5, "total_steps": 312, "loss": 0.9975, "lr": 1.5625e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:07:43", "remaining_time": "7:54:25"}
{"current_steps": 6, "total_steps": 312, "loss": 0.9607, "lr": 1.8750000000000003e-06, "epoch": 0.0576, "percentage": 1.92, "elapsed_time": "0:09:16", "remaining_time": "7:53:03"}
{"current_steps": 7, "total_steps": 312, "loss": 0.9757, "lr": 2.1875000000000002e-06, "epoch": 0.0672, "percentage": 2.24, "elapsed_time": "0:10:51", "remaining_time": "7:53:14"}
{"current_steps": 8, "total_steps": 312, "loss": 0.9083, "lr": 2.5e-06, "epoch": 0.0768, "percentage": 2.56, "elapsed_time": "0:12:24", "remaining_time": "7:51:38"}
{"current_steps": 9, "total_steps": 312, "loss": 0.9022, "lr": 2.8125e-06, "epoch": 0.0864, "percentage": 2.88, "elapsed_time": "0:14:12", "remaining_time": "7:58:05"}
{"current_steps": 10, "total_steps": 312, "loss": 0.9135, "lr": 3.125e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:15:44", "remaining_time": "7:55:26"}
{"current_steps": 11, "total_steps": 312, "loss": 0.8983, "lr": 3.4375e-06, "epoch": 0.1056, "percentage": 3.53, "elapsed_time": "0:17:29", "remaining_time": "7:58:48"}
{"current_steps": 12, "total_steps": 312, "loss": 0.8729, "lr": 3.7500000000000005e-06, "epoch": 0.1152, "percentage": 3.85, "elapsed_time": "0:18:57", "remaining_time": "7:53:56"}
{"current_steps": 13, "total_steps": 312, "loss": 0.9055, "lr": 4.0625000000000005e-06, "epoch": 0.1248, "percentage": 4.17, "elapsed_time": "0:20:49", "remaining_time": "7:59:09"}
{"current_steps": 14, "total_steps": 312, "loss": 0.8707, "lr": 4.3750000000000005e-06, "epoch": 0.1344, "percentage": 4.49, "elapsed_time": "0:22:12", "remaining_time": "7:52:33"}
{"current_steps": 15, "total_steps": 312, "loss": 0.8631, "lr": 4.6875000000000004e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:23:44", "remaining_time": "7:50:01"}
{"current_steps": 16, "total_steps": 312, "loss": 0.8467, "lr": 5e-06, "epoch": 0.1536, "percentage": 5.13, "elapsed_time": "0:25:31", "remaining_time": "7:52:04"}
{"current_steps": 17, "total_steps": 312, "loss": 0.8559, "lr": 5.3125e-06, "epoch": 0.1632, "percentage": 5.45, "elapsed_time": "0:26:58", "remaining_time": "7:48:05"}
{"current_steps": 18, "total_steps": 312, "loss": 0.826, "lr": 5.625e-06, "epoch": 0.1728, "percentage": 5.77, "elapsed_time": "0:28:35", "remaining_time": "7:46:52"}
{"current_steps": 19, "total_steps": 312, "loss": 0.7943, "lr": 5.9375e-06, "epoch": 0.1824, "percentage": 6.09, "elapsed_time": "0:30:20", "remaining_time": "7:47:53"}
{"current_steps": 20, "total_steps": 312, "loss": 0.7867, "lr": 6.25e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:31:52", "remaining_time": "7:45:18"}
{"current_steps": 21, "total_steps": 312, "loss": 0.7834, "lr": 6.5625e-06, "epoch": 0.2016, "percentage": 6.73, "elapsed_time": "0:33:19", "remaining_time": "7:41:42"}
{"current_steps": 22, "total_steps": 312, "loss": 0.7868, "lr": 6.875e-06, "epoch": 0.2112, "percentage": 7.05, "elapsed_time": "0:34:44", "remaining_time": "7:37:52"}
{"current_steps": 23, "total_steps": 312, "loss": 0.7418, "lr": 7.1875e-06, "epoch": 0.2208, "percentage": 7.37, "elapsed_time": "0:36:15", "remaining_time": "7:35:31"}
{"current_steps": 24, "total_steps": 312, "loss": 0.7465, "lr": 7.500000000000001e-06, "epoch": 0.2304, "percentage": 7.69, "elapsed_time": "0:37:35", "remaining_time": "7:31:09"}
{"current_steps": 25, "total_steps": 312, "loss": 0.7539, "lr": 7.8125e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:39:06", "remaining_time": "7:28:55"}
{"current_steps": 26, "total_steps": 312, "loss": 0.745, "lr": 8.125000000000001e-06, "epoch": 0.2496, "percentage": 8.33, "elapsed_time": "0:40:28", "remaining_time": "7:25:18"}
{"current_steps": 27, "total_steps": 312, "loss": 0.7436, "lr": 8.4375e-06, "epoch": 0.2592, "percentage": 8.65, "elapsed_time": "0:41:56", "remaining_time": "7:22:45"}
{"current_steps": 28, "total_steps": 312, "loss": 0.7235, "lr": 8.750000000000001e-06, "epoch": 0.2688, "percentage": 8.97, "elapsed_time": "0:43:30", "remaining_time": "7:21:15"}
{"current_steps": 29, "total_steps": 312, "loss": 0.7152, "lr": 9.0625e-06, "epoch": 0.2784, "percentage": 9.29, "elapsed_time": "0:45:09", "remaining_time": "7:20:45"}
{"current_steps": 30, "total_steps": 312, "loss": 0.7189, "lr": 9.375000000000001e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:46:34", "remaining_time": "7:17:44"}
{"current_steps": 31, "total_steps": 312, "loss": 0.6841, "lr": 9.6875e-06, "epoch": 0.2976, "percentage": 9.94, "elapsed_time": "0:47:53", "remaining_time": "7:14:10"}
{"current_steps": 32, "total_steps": 312, "loss": 0.7011, "lr": 1e-05, "epoch": 0.3072, "percentage": 10.26, "elapsed_time": "0:49:32", "remaining_time": "7:13:27"}
{"current_steps": 33, "total_steps": 312, "loss": 0.7023, "lr": 9.999685283773504e-06, "epoch": 0.3168, "percentage": 10.58, "elapsed_time": "0:51:16", "remaining_time": "7:13:34"}
{"current_steps": 34, "total_steps": 312, "loss": 0.6653, "lr": 9.998741174712534e-06, "epoch": 0.3264, "percentage": 10.9, "elapsed_time": "0:52:53", "remaining_time": "7:12:27"}
{"current_steps": 35, "total_steps": 312, "loss": 0.685, "lr": 9.997167791667668e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "0:54:22", "remaining_time": "7:10:18"}
{"current_steps": 36, "total_steps": 312, "loss": 0.6926, "lr": 9.994965332706574e-06, "epoch": 0.3456, "percentage": 11.54, "elapsed_time": "0:56:06", "remaining_time": "7:10:08"}
{"current_steps": 37, "total_steps": 312, "loss": 0.7199, "lr": 9.992134075089085e-06, "epoch": 0.3552, "percentage": 11.86, "elapsed_time": "0:57:51", "remaining_time": "7:10:02"}
{"current_steps": 38, "total_steps": 312, "loss": 0.7199, "lr": 9.98867437523228e-06, "epoch": 0.3648, "percentage": 12.18, "elapsed_time": "0:59:30", "remaining_time": "7:09:06"}
{"current_steps": 39, "total_steps": 312, "loss": 0.6906, "lr": 9.984586668665641e-06, "epoch": 0.3744, "percentage": 12.5, "elapsed_time": "1:01:00", "remaining_time": "7:07:02"}
{"current_steps": 40, "total_steps": 312, "loss": 0.6521, "lr": 9.979871469976197e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "1:02:33", "remaining_time": "7:05:25"}
{"current_steps": 41, "total_steps": 312, "loss": 0.6861, "lr": 9.974529372743762e-06, "epoch": 0.3936, "percentage": 13.14, "elapsed_time": "1:04:24", "remaining_time": "7:05:41"}
{"current_steps": 42, "total_steps": 312, "loss": 0.6681, "lr": 9.968561049466214e-06, "epoch": 0.4032, "percentage": 13.46, "elapsed_time": "1:05:58", "remaining_time": "7:04:06"}
{"current_steps": 43, "total_steps": 312, "loss": 0.676, "lr": 9.961967251474823e-06, "epoch": 0.4128, "percentage": 13.78, "elapsed_time": "1:07:24", "remaining_time": "7:01:39"}
{"current_steps": 44, "total_steps": 312, "loss": 0.6803, "lr": 9.954748808839675e-06, "epoch": 0.4224, "percentage": 14.1, "elapsed_time": "1:08:50", "remaining_time": "6:59:17"}
{"current_steps": 45, "total_steps": 312, "loss": 0.6705, "lr": 9.946906630265184e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "1:10:21", "remaining_time": "6:57:25"}
{"current_steps": 46, "total_steps": 312, "loss": 0.7002, "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": 0.6463, "lr": 9.92935509259118e-06, "epoch": 0.4512, "percentage": 15.06, "elapsed_time": "1:13:25", "remaining_time": "6:53:56"}
{"current_steps": 48, "total_steps": 312, "loss": 0.6628, "lr": 9.91964794299315e-06, "epoch": 0.4608, "percentage": 15.38, "elapsed_time": "1:14:45", "remaining_time": "6:51:11"}
{"current_steps": 49, "total_steps": 312, "loss": 0.6417, "lr": 9.909321476180594e-06, "epoch": 0.4704, "percentage": 15.71, "elapsed_time": "1:16:20", "remaining_time": "6:49:46"}
{"current_steps": 50, "total_steps": 312, "loss": 0.6774, "lr": 9.898376992116179e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "1:17:51", "remaining_time": "6:47:58"}
{"current_steps": 51, "total_steps": 312, "loss": 0.6737, "lr": 9.886815868562596e-06, "epoch": 0.4896, "percentage": 16.35, "elapsed_time": "1:19:31", "remaining_time": "6:46:58"}
{"current_steps": 52, "total_steps": 312, "loss": 0.682, "lr": 9.874639560909118e-06, "epoch": 0.4992, "percentage": 16.67, "elapsed_time": "1:21:15", "remaining_time": "6:46:16"}
{"current_steps": 53, "total_steps": 312, "loss": 0.6683, "lr": 9.861849601988384e-06, "epoch": 0.5088, "percentage": 16.99, "elapsed_time": "1:22:50", "remaining_time": "6:44:47"}
{"current_steps": 54, "total_steps": 312, "loss": 0.636, "lr": 9.848447601883436e-06, "epoch": 0.5184, "percentage": 17.31, "elapsed_time": "1:24:27", "remaining_time": "6:43:29"}
{"current_steps": 55, "total_steps": 312, "loss": 0.6805, "lr": 9.834435247725032e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "1:26:12", "remaining_time": "6:42:49"}
{"current_steps": 56, "total_steps": 312, "loss": 0.6687, "lr": 9.819814303479268e-06, "epoch": 0.5376, "percentage": 17.95, "elapsed_time": "1:27:44", "remaining_time": "6:41:07"}
{"current_steps": 57, "total_steps": 312, "loss": 0.6715, "lr": 9.804586609725499e-06, "epoch": 0.5472, "percentage": 18.27, "elapsed_time": "1:29:13", "remaining_time": "6:39:11"}
{"current_steps": 58, "total_steps": 312, "loss": 0.6472, "lr": 9.788754083424654e-06, "epoch": 0.5568, "percentage": 18.59, "elapsed_time": "1:30:56", "remaining_time": "6:38:15"}
{"current_steps": 59, "total_steps": 312, "loss": 0.6436, "lr": 9.772318717677905e-06, "epoch": 0.5664, "percentage": 18.91, "elapsed_time": "1:32:27", "remaining_time": "6:36:29"}
{"current_steps": 60, "total_steps": 312, "loss": 0.6464, "lr": 9.755282581475769e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "1:33:58", "remaining_time": "6:34:40"}
{"current_steps": 61, "total_steps": 312, "loss": 0.6675, "lr": 9.737647819437645e-06, "epoch": 0.5856, "percentage": 19.55, "elapsed_time": "1:35:50", "remaining_time": "6:34:21"}
{"current_steps": 62, "total_steps": 312, "loss": 0.6503, "lr": 9.719416651541839e-06, "epoch": 0.5952, "percentage": 19.87, "elapsed_time": "1:37:34", "remaining_time": "6:33:28"}
{"current_steps": 63, "total_steps": 312, "loss": 0.6445, "lr": 9.700591372846096e-06, "epoch": 0.6048, "percentage": 20.19, "elapsed_time": "1:39:08", "remaining_time": "6:31:50"}
{"current_steps": 64, "total_steps": 312, "loss": 0.6297, "lr": 9.681174353198687e-06, "epoch": 0.6144, "percentage": 20.51, "elapsed_time": "1:40:38", "remaining_time": "6:29:58"}
{"current_steps": 65, "total_steps": 312, "loss": 0.6752, "lr": 9.661168036940071e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "1:42:00", "remaining_time": "6:27:39"}
{"current_steps": 66, "total_steps": 312, "loss": 0.6437, "lr": 9.640574942595195e-06, "epoch": 0.6336, "percentage": 21.15, "elapsed_time": "1:43:18", "remaining_time": "6:25:02"}
{"current_steps": 67, "total_steps": 312, "loss": 0.6894, "lr": 9.619397662556434e-06, "epoch": 0.6432, "percentage": 21.47, "elapsed_time": "1:44:54", "remaining_time": "6:23:36"}
{"current_steps": 68, "total_steps": 312, "loss": 0.6406, "lr": 9.597638862757255e-06, "epoch": 0.6528, "percentage": 21.79, "elapsed_time": "1:46:07", "remaining_time": "6:20:47"}
{"current_steps": 69, "total_steps": 312, "loss": 0.6221, "lr": 9.5753012823366e-06, "epoch": 0.6624, "percentage": 22.12, "elapsed_time": "1:47:26", "remaining_time": "6:18:23"}
{"current_steps": 70, "total_steps": 312, "loss": 0.6503, "lr": 9.552387733294081e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "1:49:11", "remaining_time": "6:17:29"}
{"current_steps": 71, "total_steps": 312, "loss": 0.6564, "lr": 9.528901100135971e-06, "epoch": 0.6816, "percentage": 22.76, "elapsed_time": "1:50:54", "remaining_time": "6:16:27"}
{"current_steps": 72, "total_steps": 312, "loss": 0.6607, "lr": 9.504844339512096e-06, "epoch": 0.6912, "percentage": 23.08, "elapsed_time": "1:52:37", "remaining_time": "6:15:23"}
{"current_steps": 73, "total_steps": 312, "loss": 0.6542, "lr": 9.480220479843627e-06, "epoch": 0.7008, "percentage": 23.4, "elapsed_time": "1:53:59", "remaining_time": "6:13:11"}
{"current_steps": 74, "total_steps": 312, "loss": 0.6654, "lr": 9.45503262094184e-06, "epoch": 0.7104, "percentage": 23.72, "elapsed_time": "1:55:38", "remaining_time": "6:11:54"}
{"current_steps": 75, "total_steps": 312, "loss": 0.6524, "lr": 9.4292839336179e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "1:57:18", "remaining_time": "6:10:40"}
{"current_steps": 76, "total_steps": 312, "loss": 0.6422, "lr": 9.40297765928369e-06, "epoch": 0.7296, "percentage": 24.36, "elapsed_time": "1:58:31", "remaining_time": "6:08:04"}
{"current_steps": 77, "total_steps": 312, "loss": 0.6439, "lr": 9.376117109543769e-06, "epoch": 0.7392, "percentage": 24.68, "elapsed_time": "2:00:11", "remaining_time": "6:06:49"}
{"current_steps": 78, "total_steps": 312, "loss": 0.6406, "lr": 9.348705665778479e-06, "epoch": 0.7488, "percentage": 25.0, "elapsed_time": "2:01:50", "remaining_time": "6:05:31"}
{"current_steps": 79, "total_steps": 312, "loss": 0.6251, "lr": 9.320746778718274e-06, "epoch": 0.7584, "percentage": 25.32, "elapsed_time": "2:03:33", "remaining_time": "6:04:24"}
{"current_steps": 80, "total_steps": 312, "loss": 0.6287, "lr": 9.292243968009332e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "2:05:01", "remaining_time": "6:02:33"}
{"current_steps": 81, "total_steps": 312, "loss": 0.632, "lr": 9.263200821770462e-06, "epoch": 0.7776, "percentage": 25.96, "elapsed_time": "2:06:41", "remaining_time": "6:01:19"}
{"current_steps": 82, "total_steps": 312, "loss": 0.6545, "lr": 9.233620996141421e-06, "epoch": 0.7872, "percentage": 26.28, "elapsed_time": "2:08:25", "remaining_time": "6:00:12"}
{"current_steps": 83, "total_steps": 312, "loss": 0.6306, "lr": 9.203508214822652e-06, "epoch": 0.7968, "percentage": 26.6, "elapsed_time": "2:10:10", "remaining_time": "5:59:08"}
{"current_steps": 84, "total_steps": 312, "loss": 0.6223, "lr": 9.172866268606514e-06, "epoch": 0.8064, "percentage": 26.92, "elapsed_time": "2:11:47", "remaining_time": "5:57:42"}
{"current_steps": 85, "total_steps": 312, "loss": 0.6647, "lr": 9.141699014900084e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "2:13:36", "remaining_time": "5:56:48"}
{"current_steps": 86, "total_steps": 312, "loss": 0.6681, "lr": 9.110010377239552e-06, "epoch": 0.8256, "percentage": 27.56, "elapsed_time": "2:15:19", "remaining_time": "5:55:36"}
{"current_steps": 87, "total_steps": 312, "loss": 0.6452, "lr": 9.077804344796302e-06, "epoch": 0.8352, "percentage": 27.88, "elapsed_time": "2:16:55", "remaining_time": "5:54:06"}
{"current_steps": 88, "total_steps": 312, "loss": 0.6397, "lr": 9.045084971874738e-06, "epoch": 0.8448, "percentage": 28.21, "elapsed_time": "2:18:36", "remaining_time": "5:52:49"}
{"current_steps": 89, "total_steps": 312, "loss": 0.6696, "lr": 9.011856377401891e-06, "epoch": 0.8544, "percentage": 28.53, "elapsed_time": "2:20:23", "remaining_time": "5:51:47"}
{"current_steps": 90, "total_steps": 312, "loss": 0.6499, "lr": 8.978122744408905e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "2:21:59", "remaining_time": "5:50:14"}
{"current_steps": 91, "total_steps": 312, "loss": 0.6374, "lr": 8.943888319504456e-06, "epoch": 0.8736, "percentage": 29.17, "elapsed_time": "2:23:50", "remaining_time": "5:49:20"}
{"current_steps": 92, "total_steps": 312, "loss": 0.6274, "lr": 8.90915741234015e-06, "epoch": 0.8832, "percentage": 29.49, "elapsed_time": "2:25:15", "remaining_time": "5:47:20"}
{"current_steps": 93, "total_steps": 312, "loss": 0.6345, "lr": 8.873934395068006e-06, "epoch": 0.8928, "percentage": 29.81, "elapsed_time": "2:26:38", "remaining_time": "5:45:18"}
{"current_steps": 94, "total_steps": 312, "loss": 0.6189, "lr": 8.838223701790057e-06, "epoch": 0.9024, "percentage": 30.13, "elapsed_time": "2:28:20", "remaining_time": "5:44:02"}
{"current_steps": 95, "total_steps": 312, "loss": 0.6121, "lr": 8.802029828000157e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "2:29:48", "remaining_time": "5:42:12"}
{"current_steps": 96, "total_steps": 312, "loss": 0.6638, "lr": 8.765357330018056e-06, "epoch": 0.9216, "percentage": 30.77, "elapsed_time": "2:31:11", "remaining_time": "5:40:11"}
{"current_steps": 97, "total_steps": 312, "loss": 0.6404, "lr": 8.728210824415829e-06, "epoch": 0.9312, "percentage": 31.09, "elapsed_time": "2:32:43", "remaining_time": "5:38:30"}
{"current_steps": 98, "total_steps": 312, "loss": 0.6537, "lr": 8.690594987436705e-06, "epoch": 0.9408, "percentage": 31.41, "elapsed_time": "2:34:07", "remaining_time": "5:36:33"}
{"current_steps": 99, "total_steps": 312, "loss": 0.655, "lr": 8.652514554406388e-06, "epoch": 0.9504, "percentage": 31.73, "elapsed_time": "2:35:27", "remaining_time": "5:34:28"}
{"current_steps": 100, "total_steps": 312, "loss": 0.6456, "lr": 8.613974319136959e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "2:37:13", "remaining_time": "5:33:19"}
{"current_steps": 101, "total_steps": 312, "loss": 0.6164, "lr": 8.574979133323378e-06, "epoch": 0.9696, "percentage": 32.37, "elapsed_time": "2:38:46", "remaining_time": "5:31:42"}
{"current_steps": 102, "total_steps": 312, "loss": 0.6365, "lr": 8.535533905932739e-06, "epoch": 0.9792, "percentage": 32.69, "elapsed_time": "2:40:14", "remaining_time": "5:29:53"}
{"current_steps": 103, "total_steps": 312, "loss": 0.6633, "lr": 8.495643602586287e-06, "epoch": 0.9888, "percentage": 33.01, "elapsed_time": "2:41:20", "remaining_time": "5:27:22"}
{"current_steps": 104, "total_steps": 312, "loss": 0.6223, "lr": 8.455313244934324e-06, "epoch": 0.9984, "percentage": 33.33, "elapsed_time": "2:42:53", "remaining_time": "5:25:46"}
{"current_steps": 105, "total_steps": 312, "loss": 1.0996, "lr": 8.414547910024035e-06, "epoch": 1.008, "percentage": 33.65, "elapsed_time": "2:45:17", "remaining_time": "5:25:52"}