d1_math_all_10k / trainer_log.jsonl
ryanmarten's picture
Training in progress, epoch 4
726f1ac verified
{"current_steps": 1, "total_steps": 390, "loss": 0.8147, "lr": 1.0256410256410257e-06, "epoch": 0.0128, "percentage": 0.26, "elapsed_time": "0:02:30", "remaining_time": "16:13:21"}
{"current_steps": 2, "total_steps": 390, "loss": 0.8026, "lr": 2.0512820512820513e-06, "epoch": 0.0256, "percentage": 0.51, "elapsed_time": "0:05:21", "remaining_time": "17:20:23"}
{"current_steps": 3, "total_steps": 390, "loss": 0.8253, "lr": 3.0769230769230774e-06, "epoch": 0.0384, "percentage": 0.77, "elapsed_time": "0:08:01", "remaining_time": "17:16:12"}
{"current_steps": 4, "total_steps": 390, "loss": 0.7983, "lr": 4.102564102564103e-06, "epoch": 0.0512, "percentage": 1.03, "elapsed_time": "0:10:36", "remaining_time": "17:03:30"}
{"current_steps": 5, "total_steps": 390, "loss": 0.7638, "lr": 5.128205128205128e-06, "epoch": 0.064, "percentage": 1.28, "elapsed_time": "0:13:11", "remaining_time": "16:55:09"}
{"current_steps": 6, "total_steps": 390, "loss": 0.7242, "lr": 6.153846153846155e-06, "epoch": 0.0768, "percentage": 1.54, "elapsed_time": "0:15:49", "remaining_time": "16:52:53"}
{"current_steps": 7, "total_steps": 390, "loss": 0.7065, "lr": 7.17948717948718e-06, "epoch": 0.0896, "percentage": 1.79, "elapsed_time": "0:18:24", "remaining_time": "16:47:20"}
{"current_steps": 8, "total_steps": 390, "loss": 0.7417, "lr": 8.205128205128205e-06, "epoch": 0.1024, "percentage": 2.05, "elapsed_time": "0:21:08", "remaining_time": "16:49:32"}
{"current_steps": 9, "total_steps": 390, "loss": 0.7359, "lr": 9.230769230769232e-06, "epoch": 0.1152, "percentage": 2.31, "elapsed_time": "0:23:38", "remaining_time": "16:40:55"}
{"current_steps": 10, "total_steps": 390, "loss": 0.684, "lr": 1.0256410256410256e-05, "epoch": 0.128, "percentage": 2.56, "elapsed_time": "0:26:10", "remaining_time": "16:34:41"}
{"current_steps": 11, "total_steps": 390, "loss": 0.6851, "lr": 1.1282051282051283e-05, "epoch": 0.1408, "percentage": 2.82, "elapsed_time": "0:28:37", "remaining_time": "16:26:24"}
{"current_steps": 12, "total_steps": 390, "loss": 0.6562, "lr": 1.230769230769231e-05, "epoch": 0.1536, "percentage": 3.08, "elapsed_time": "0:31:13", "remaining_time": "16:23:47"}
{"current_steps": 13, "total_steps": 390, "loss": 0.6468, "lr": 1.3333333333333333e-05, "epoch": 0.1664, "percentage": 3.33, "elapsed_time": "0:33:45", "remaining_time": "16:18:57"}
{"current_steps": 14, "total_steps": 390, "loss": 0.6221, "lr": 1.435897435897436e-05, "epoch": 0.1792, "percentage": 3.59, "elapsed_time": "0:36:31", "remaining_time": "16:20:48"}
{"current_steps": 15, "total_steps": 390, "loss": 0.6111, "lr": 1.5384615384615387e-05, "epoch": 0.192, "percentage": 3.85, "elapsed_time": "0:39:03", "remaining_time": "16:16:30"}
{"current_steps": 16, "total_steps": 390, "loss": 0.6177, "lr": 1.641025641025641e-05, "epoch": 0.2048, "percentage": 4.1, "elapsed_time": "0:41:43", "remaining_time": "16:15:27"}
{"current_steps": 17, "total_steps": 390, "loss": 0.5846, "lr": 1.7435897435897438e-05, "epoch": 0.2176, "percentage": 4.36, "elapsed_time": "0:44:14", "remaining_time": "16:10:41"}
{"current_steps": 18, "total_steps": 390, "loss": 0.5833, "lr": 1.8461538461538465e-05, "epoch": 0.2304, "percentage": 4.62, "elapsed_time": "0:46:48", "remaining_time": "16:07:23"}
{"current_steps": 19, "total_steps": 390, "loss": 0.5769, "lr": 1.9487179487179488e-05, "epoch": 0.2432, "percentage": 4.87, "elapsed_time": "0:49:12", "remaining_time": "16:00:56"}
{"current_steps": 20, "total_steps": 390, "loss": 0.5658, "lr": 2.0512820512820512e-05, "epoch": 0.256, "percentage": 5.13, "elapsed_time": "0:51:49", "remaining_time": "15:58:52"}
{"current_steps": 21, "total_steps": 390, "loss": 0.5334, "lr": 2.153846153846154e-05, "epoch": 0.2688, "percentage": 5.38, "elapsed_time": "0:54:13", "remaining_time": "15:52:55"}
{"current_steps": 22, "total_steps": 390, "loss": 0.5505, "lr": 2.2564102564102566e-05, "epoch": 0.2816, "percentage": 5.64, "elapsed_time": "0:56:51", "remaining_time": "15:51:07"}
{"current_steps": 23, "total_steps": 390, "loss": 0.5475, "lr": 2.3589743589743593e-05, "epoch": 0.2944, "percentage": 5.9, "elapsed_time": "0:59:34", "remaining_time": "15:50:42"}
{"current_steps": 24, "total_steps": 390, "loss": 0.5328, "lr": 2.461538461538462e-05, "epoch": 0.3072, "percentage": 6.15, "elapsed_time": "1:02:17", "remaining_time": "15:50:03"}
{"current_steps": 25, "total_steps": 390, "loss": 0.5313, "lr": 2.5641025641025646e-05, "epoch": 0.32, "percentage": 6.41, "elapsed_time": "1:04:58", "remaining_time": "15:48:34"}
{"current_steps": 26, "total_steps": 390, "loss": 0.5443, "lr": 2.6666666666666667e-05, "epoch": 0.3328, "percentage": 6.67, "elapsed_time": "1:07:33", "remaining_time": "15:45:48"}
{"current_steps": 27, "total_steps": 390, "loss": 0.5271, "lr": 2.7692307692307694e-05, "epoch": 0.3456, "percentage": 6.92, "elapsed_time": "1:10:12", "remaining_time": "15:43:48"}
{"current_steps": 28, "total_steps": 390, "loss": 0.5243, "lr": 2.871794871794872e-05, "epoch": 0.3584, "percentage": 7.18, "elapsed_time": "1:12:43", "remaining_time": "15:40:15"}
{"current_steps": 29, "total_steps": 390, "loss": 0.5439, "lr": 2.9743589743589747e-05, "epoch": 0.3712, "percentage": 7.44, "elapsed_time": "1:15:16", "remaining_time": "15:37:03"}
{"current_steps": 30, "total_steps": 390, "loss": 0.5174, "lr": 3.0769230769230774e-05, "epoch": 0.384, "percentage": 7.69, "elapsed_time": "1:17:46", "remaining_time": "15:33:17"}
{"current_steps": 31, "total_steps": 390, "loss": 0.5247, "lr": 3.1794871794871795e-05, "epoch": 0.3968, "percentage": 7.95, "elapsed_time": "1:20:12", "remaining_time": "15:28:55"}
{"current_steps": 32, "total_steps": 390, "loss": 0.5226, "lr": 3.282051282051282e-05, "epoch": 0.4096, "percentage": 8.21, "elapsed_time": "1:22:49", "remaining_time": "15:26:33"}
{"current_steps": 33, "total_steps": 390, "loss": 0.5135, "lr": 3.384615384615385e-05, "epoch": 0.4224, "percentage": 8.46, "elapsed_time": "1:25:12", "remaining_time": "15:21:47"}
{"current_steps": 34, "total_steps": 390, "loss": 0.5186, "lr": 3.4871794871794875e-05, "epoch": 0.4352, "percentage": 8.72, "elapsed_time": "1:27:58", "remaining_time": "15:21:12"}
{"current_steps": 35, "total_steps": 390, "loss": 0.5132, "lr": 3.58974358974359e-05, "epoch": 0.448, "percentage": 8.97, "elapsed_time": "1:30:25", "remaining_time": "15:17:11"}
{"current_steps": 36, "total_steps": 390, "loss": 0.5345, "lr": 3.692307692307693e-05, "epoch": 0.4608, "percentage": 9.23, "elapsed_time": "1:33:01", "remaining_time": "15:14:40"}
{"current_steps": 37, "total_steps": 390, "loss": 0.498, "lr": 3.794871794871795e-05, "epoch": 0.4736, "percentage": 9.49, "elapsed_time": "1:35:39", "remaining_time": "15:12:38"}
{"current_steps": 38, "total_steps": 390, "loss": 0.4986, "lr": 3.8974358974358976e-05, "epoch": 0.4864, "percentage": 9.74, "elapsed_time": "1:38:28", "remaining_time": "15:12:06"}
{"current_steps": 39, "total_steps": 390, "loss": 0.5038, "lr": 4e-05, "epoch": 0.4992, "percentage": 10.0, "elapsed_time": "1:40:56", "remaining_time": "15:08:30"}
{"current_steps": 40, "total_steps": 390, "loss": 0.4991, "lr": 3.9999198907597046e-05, "epoch": 0.512, "percentage": 10.26, "elapsed_time": "1:43:29", "remaining_time": "15:05:31"}
{"current_steps": 41, "total_steps": 390, "loss": 0.498, "lr": 3.9996795694563096e-05, "epoch": 0.5248, "percentage": 10.51, "elapsed_time": "1:46:08", "remaining_time": "15:03:27"}
{"current_steps": 42, "total_steps": 390, "loss": 0.5124, "lr": 3.999279055341771e-05, "epoch": 0.5376, "percentage": 10.77, "elapsed_time": "1:48:42", "remaining_time": "15:00:44"}
{"current_steps": 43, "total_steps": 390, "loss": 0.498, "lr": 3.998718380500971e-05, "epoch": 0.5504, "percentage": 11.03, "elapsed_time": "1:51:12", "remaining_time": "14:57:25"}
{"current_steps": 44, "total_steps": 390, "loss": 0.4982, "lr": 3.997997589849145e-05, "epoch": 0.5632, "percentage": 11.28, "elapsed_time": "1:53:53", "remaining_time": "14:55:34"}
{"current_steps": 45, "total_steps": 390, "loss": 0.5059, "lr": 3.9971167411282835e-05, "epoch": 0.576, "percentage": 11.54, "elapsed_time": "1:56:26", "remaining_time": "14:52:43"}
{"current_steps": 46, "total_steps": 390, "loss": 0.4946, "lr": 3.99607590490251e-05, "epoch": 0.5888, "percentage": 11.79, "elapsed_time": "1:59:05", "remaining_time": "14:50:34"}
{"current_steps": 47, "total_steps": 390, "loss": 0.4627, "lr": 3.9948751645524235e-05, "epoch": 0.6016, "percentage": 12.05, "elapsed_time": "2:01:48", "remaining_time": "14:48:55"}
{"current_steps": 48, "total_steps": 390, "loss": 0.4707, "lr": 3.9935146162684206e-05, "epoch": 0.6144, "percentage": 12.31, "elapsed_time": "2:04:30", "remaining_time": "14:47:06"}
{"current_steps": 49, "total_steps": 390, "loss": 0.4913, "lr": 3.9919943690429906e-05, "epoch": 0.6272, "percentage": 12.56, "elapsed_time": "2:07:08", "remaining_time": "14:44:50"}
{"current_steps": 50, "total_steps": 390, "loss": 0.4858, "lr": 3.9903145446619837e-05, "epoch": 0.64, "percentage": 12.82, "elapsed_time": "2:09:45", "remaining_time": "14:42:19"}
{"current_steps": 51, "total_steps": 390, "loss": 0.4779, "lr": 3.9884752776948564e-05, "epoch": 0.6528, "percentage": 13.08, "elapsed_time": "2:12:28", "remaining_time": "14:40:34"}
{"current_steps": 52, "total_steps": 390, "loss": 0.4893, "lr": 3.9864767154838864e-05, "epoch": 0.6656, "percentage": 13.33, "elapsed_time": "2:15:01", "remaining_time": "14:37:42"}
{"current_steps": 53, "total_steps": 390, "loss": 0.4722, "lr": 3.9843190181323744e-05, "epoch": 0.6784, "percentage": 13.59, "elapsed_time": "2:17:44", "remaining_time": "14:35:50"}
{"current_steps": 54, "total_steps": 390, "loss": 0.4854, "lr": 3.982002358491817e-05, "epoch": 0.6912, "percentage": 13.85, "elapsed_time": "2:20:25", "remaining_time": "14:33:47"}
{"current_steps": 55, "total_steps": 390, "loss": 0.4759, "lr": 3.979526922148058e-05, "epoch": 0.704, "percentage": 14.1, "elapsed_time": "2:23:02", "remaining_time": "14:31:15"}
{"current_steps": 56, "total_steps": 390, "loss": 0.4665, "lr": 3.9768929074064206e-05, "epoch": 0.7168, "percentage": 14.36, "elapsed_time": "2:25:28", "remaining_time": "14:27:36"}
{"current_steps": 57, "total_steps": 390, "loss": 0.4816, "lr": 3.9741005252758255e-05, "epoch": 0.7296, "percentage": 14.62, "elapsed_time": "2:28:13", "remaining_time": "14:25:56"}
{"current_steps": 58, "total_steps": 390, "loss": 0.4836, "lr": 3.971149999451886e-05, "epoch": 0.7424, "percentage": 14.87, "elapsed_time": "2:30:53", "remaining_time": "14:23:41"}
{"current_steps": 59, "total_steps": 390, "loss": 0.4754, "lr": 3.9680415662989806e-05, "epoch": 0.7552, "percentage": 15.13, "elapsed_time": "2:33:24", "remaining_time": "14:20:38"}
{"current_steps": 60, "total_steps": 390, "loss": 0.4822, "lr": 3.9647754748313294e-05, "epoch": 0.768, "percentage": 15.38, "elapsed_time": "2:36:03", "remaining_time": "14:18:21"}
{"current_steps": 61, "total_steps": 390, "loss": 0.4621, "lr": 3.96135198669304e-05, "epoch": 0.7808, "percentage": 15.64, "elapsed_time": "2:38:49", "remaining_time": "14:16:34"}
{"current_steps": 62, "total_steps": 390, "loss": 0.4736, "lr": 3.957771376137144e-05, "epoch": 0.7936, "percentage": 15.9, "elapsed_time": "2:41:44", "remaining_time": "14:15:38"}
{"current_steps": 63, "total_steps": 390, "loss": 0.4855, "lr": 3.954033930003634e-05, "epoch": 0.8064, "percentage": 16.15, "elapsed_time": "2:44:24", "remaining_time": "14:13:19"}
{"current_steps": 64, "total_steps": 390, "loss": 0.4652, "lr": 3.9501399476964806e-05, "epoch": 0.8192, "percentage": 16.41, "elapsed_time": "2:46:56", "remaining_time": "14:10:19"}
{"current_steps": 65, "total_steps": 390, "loss": 0.4645, "lr": 3.946089741159648e-05, "epoch": 0.832, "percentage": 16.67, "elapsed_time": "2:49:26", "remaining_time": "14:07:14"}
{"current_steps": 66, "total_steps": 390, "loss": 0.4703, "lr": 3.9418836348521045e-05, "epoch": 0.8448, "percentage": 16.92, "elapsed_time": "2:51:50", "remaining_time": "14:03:33"}
{"current_steps": 67, "total_steps": 390, "loss": 0.4649, "lr": 3.937521965721831e-05, "epoch": 0.8576, "percentage": 17.18, "elapsed_time": "2:54:27", "remaining_time": "14:01:02"}
{"current_steps": 68, "total_steps": 390, "loss": 0.4705, "lr": 3.933005083178828e-05, "epoch": 0.8704, "percentage": 17.44, "elapsed_time": "2:56:53", "remaining_time": "13:57:39"}
{"current_steps": 69, "total_steps": 390, "loss": 0.466, "lr": 3.928333349067125e-05, "epoch": 0.8832, "percentage": 17.69, "elapsed_time": "2:59:30", "remaining_time": "13:55:05"}
{"current_steps": 70, "total_steps": 390, "loss": 0.4713, "lr": 3.923507137635792e-05, "epoch": 0.896, "percentage": 17.95, "elapsed_time": "3:02:02", "remaining_time": "13:52:11"}
{"current_steps": 71, "total_steps": 390, "loss": 0.4589, "lr": 3.9185268355089606e-05, "epoch": 0.9088, "percentage": 18.21, "elapsed_time": "3:04:39", "remaining_time": "13:49:39"}
{"current_steps": 72, "total_steps": 390, "loss": 0.467, "lr": 3.913392841654851e-05, "epoch": 0.9216, "percentage": 18.46, "elapsed_time": "3:07:22", "remaining_time": "13:47:32"}
{"current_steps": 73, "total_steps": 390, "loss": 0.4588, "lr": 3.9081055673538093e-05, "epoch": 0.9344, "percentage": 18.72, "elapsed_time": "3:09:52", "remaining_time": "13:44:33"}
{"current_steps": 74, "total_steps": 390, "loss": 0.4736, "lr": 3.902665436165364e-05, "epoch": 0.9472, "percentage": 18.97, "elapsed_time": "3:12:23", "remaining_time": "13:41:33"}
{"current_steps": 75, "total_steps": 390, "loss": 0.4549, "lr": 3.897072883894291e-05, "epoch": 0.96, "percentage": 19.23, "elapsed_time": "3:14:51", "remaining_time": "13:38:25"}
{"current_steps": 76, "total_steps": 390, "loss": 0.4443, "lr": 3.8913283585557054e-05, "epoch": 0.9728, "percentage": 19.49, "elapsed_time": "3:17:32", "remaining_time": "13:36:10"}
{"current_steps": 77, "total_steps": 390, "loss": 0.4469, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:20:09", "remaining_time": "13:33:35"}
{"current_steps": 78, "total_steps": 390, "loss": 0.4737, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:22:41", "remaining_time": "13:30:44"}
{"current_steps": 79, "total_steps": 390, "loss": 0.4336, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:26:06", "remaining_time": "13:31:23"}
{"current_steps": 80, "total_steps": 390, "loss": 0.4229, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:28:48", "remaining_time": "13:29:08"}
{"current_steps": 81, "total_steps": 390, "loss": 0.4258, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:31:31", "remaining_time": "13:26:54"}
{"current_steps": 82, "total_steps": 390, "loss": 0.4277, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:34:19", "remaining_time": "13:25:00"}
{"current_steps": 83, "total_steps": 390, "loss": 0.4213, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:36:53", "remaining_time": "13:22:13"}
{"current_steps": 84, "total_steps": 390, "loss": 0.4209, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:39:34", "remaining_time": "13:19:54"}
{"current_steps": 85, "total_steps": 390, "loss": 0.4385, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:42:20", "remaining_time": "13:17:50"}
{"current_steps": 86, "total_steps": 390, "loss": 0.4193, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:45:01", "remaining_time": "13:15:25"}
{"current_steps": 87, "total_steps": 390, "loss": 0.4032, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:47:26", "remaining_time": "13:12:07"}
{"current_steps": 88, "total_steps": 390, "loss": 0.4365, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:49:54", "remaining_time": "13:09:01"}
{"current_steps": 89, "total_steps": 390, "loss": 0.434, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:52:41", "remaining_time": "13:06:58"}
{"current_steps": 90, "total_steps": 390, "loss": 0.4155, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:55:15", "remaining_time": "13:04:11"}
{"current_steps": 91, "total_steps": 390, "loss": 0.4168, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:57:47", "remaining_time": "13:01:19"}
{"current_steps": 92, "total_steps": 390, "loss": 0.417, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "4:00:11", "remaining_time": "12:58:00"}
{"current_steps": 93, "total_steps": 390, "loss": 0.4015, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:02:44", "remaining_time": "12:55:14"}
{"current_steps": 94, "total_steps": 390, "loss": 0.4255, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:05:16", "remaining_time": "12:52:21"}
{"current_steps": 95, "total_steps": 390, "loss": 0.4118, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:07:44", "remaining_time": "12:49:18"}
{"current_steps": 96, "total_steps": 390, "loss": 0.413, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:10:13", "remaining_time": "12:46:20"}
{"current_steps": 97, "total_steps": 390, "loss": 0.4214, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:12:51", "remaining_time": "12:43:48"}
{"current_steps": 98, "total_steps": 390, "loss": 0.4005, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:15:40", "remaining_time": "12:41:46"}
{"current_steps": 99, "total_steps": 390, "loss": 0.4144, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:18:13", "remaining_time": "12:39:00"}
{"current_steps": 100, "total_steps": 390, "loss": 0.4152, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:21:05", "remaining_time": "12:37:08"}
{"current_steps": 101, "total_steps": 390, "loss": 0.4032, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:23:53", "remaining_time": "12:35:05"}
{"current_steps": 102, "total_steps": 390, "loss": 0.4072, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:26:34", "remaining_time": "12:32:39"}
{"current_steps": 103, "total_steps": 390, "loss": 0.4128, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:29:05", "remaining_time": "12:29:47"}
{"current_steps": 104, "total_steps": 390, "loss": 0.4284, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:31:29", "remaining_time": "12:26:35"}
{"current_steps": 105, "total_steps": 390, "loss": 0.4255, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:34:13", "remaining_time": "12:24:20"}
{"current_steps": 106, "total_steps": 390, "loss": 0.4107, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:36:59", "remaining_time": "12:22:07"}
{"current_steps": 107, "total_steps": 390, "loss": 0.4034, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:39:25", "remaining_time": "12:19:02"}
{"current_steps": 108, "total_steps": 390, "loss": 0.4207, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:42:10", "remaining_time": "12:16:46"}
{"current_steps": 109, "total_steps": 390, "loss": 0.4123, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:44:41", "remaining_time": "12:13:55"}
{"current_steps": 110, "total_steps": 390, "loss": 0.417, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:47:14", "remaining_time": "12:11:10"}
{"current_steps": 111, "total_steps": 390, "loss": 0.4186, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "4:49:55", "remaining_time": "12:08:43"}
{"current_steps": 112, "total_steps": 390, "loss": 0.426, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "4:52:34", "remaining_time": "12:06:13"}
{"current_steps": 113, "total_steps": 390, "loss": 0.4139, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "4:55:26", "remaining_time": "12:04:12"}
{"current_steps": 114, "total_steps": 390, "loss": 0.4127, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "4:57:59", "remaining_time": "12:01:26"}
{"current_steps": 115, "total_steps": 390, "loss": 0.4152, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "5:00:50", "remaining_time": "11:59:23"}
{"current_steps": 116, "total_steps": 390, "loss": 0.4058, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "5:03:29", "remaining_time": "11:56:51"}
{"current_steps": 117, "total_steps": 390, "loss": 0.4031, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "5:06:05", "remaining_time": "11:54:12"}
{"current_steps": 118, "total_steps": 390, "loss": 0.4164, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:08:39", "remaining_time": "11:51:28"}
{"current_steps": 119, "total_steps": 390, "loss": 0.4167, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:11:24", "remaining_time": "11:49:10"}
{"current_steps": 120, "total_steps": 390, "loss": 0.4082, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:13:58", "remaining_time": "11:46:26"}
{"current_steps": 121, "total_steps": 390, "loss": 0.4113, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:16:21", "remaining_time": "11:43:19"}
{"current_steps": 122, "total_steps": 390, "loss": 0.4107, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:18:59", "remaining_time": "11:40:44"}
{"current_steps": 123, "total_steps": 390, "loss": 0.408, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:21:34", "remaining_time": "11:38:02"}
{"current_steps": 124, "total_steps": 390, "loss": 0.4109, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:24:06", "remaining_time": "11:35:16"}
{"current_steps": 125, "total_steps": 390, "loss": 0.4262, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:26:49", "remaining_time": "11:32:51"}
{"current_steps": 126, "total_steps": 390, "loss": 0.4112, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:29:13", "remaining_time": "11:29:48"}
{"current_steps": 127, "total_steps": 390, "loss": 0.4131, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:31:42", "remaining_time": "11:26:56"}
{"current_steps": 128, "total_steps": 390, "loss": 0.4134, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:34:04", "remaining_time": "11:23:47"}
{"current_steps": 129, "total_steps": 390, "loss": 0.4201, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:36:39", "remaining_time": "11:21:08"}
{"current_steps": 130, "total_steps": 390, "loss": 0.4116, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:39:03", "remaining_time": "11:18:07"}
{"current_steps": 131, "total_steps": 390, "loss": 0.403, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:41:37", "remaining_time": "11:15:25"}
{"current_steps": 132, "total_steps": 390, "loss": 0.4199, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:44:24", "remaining_time": "11:13:09"}
{"current_steps": 133, "total_steps": 390, "loss": 0.4008, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "5:46:53", "remaining_time": "11:10:18"}
{"current_steps": 134, "total_steps": 390, "loss": 0.392, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "5:49:24", "remaining_time": "11:07:31"}
{"current_steps": 135, "total_steps": 390, "loss": 0.4118, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "5:52:05", "remaining_time": "11:05:04"}
{"current_steps": 136, "total_steps": 390, "loss": 0.4141, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "5:54:39", "remaining_time": "11:02:22"}
{"current_steps": 137, "total_steps": 390, "loss": 0.4091, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "5:57:24", "remaining_time": "11:00:02"}
{"current_steps": 138, "total_steps": 390, "loss": 0.4058, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "6:00:00", "remaining_time": "10:57:25"}
{"current_steps": 139, "total_steps": 390, "loss": 0.4045, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "6:02:39", "remaining_time": "10:54:52"}
{"current_steps": 140, "total_steps": 390, "loss": 0.3928, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "6:05:07", "remaining_time": "10:52:00"}
{"current_steps": 141, "total_steps": 390, "loss": 0.4109, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "6:07:50", "remaining_time": "10:49:34"}
{"current_steps": 142, "total_steps": 390, "loss": 0.4097, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:10:25", "remaining_time": "10:46:56"}
{"current_steps": 143, "total_steps": 390, "loss": 0.4214, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:12:45", "remaining_time": "10:43:50"}
{"current_steps": 144, "total_steps": 390, "loss": 0.4098, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:15:17", "remaining_time": "10:41:06"}
{"current_steps": 145, "total_steps": 390, "loss": 0.4041, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:18:01", "remaining_time": "10:38:43"}
{"current_steps": 146, "total_steps": 390, "loss": 0.4104, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:20:44", "remaining_time": "10:36:18"}
{"current_steps": 147, "total_steps": 390, "loss": 0.4157, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:23:35", "remaining_time": "10:34:05"}
{"current_steps": 148, "total_steps": 390, "loss": 0.4094, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:26:14", "remaining_time": "10:31:34"}
{"current_steps": 149, "total_steps": 390, "loss": 0.4162, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:28:57", "remaining_time": "10:29:07"}
{"current_steps": 150, "total_steps": 390, "loss": 0.4064, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:31:32", "remaining_time": "10:26:28"}
{"current_steps": 151, "total_steps": 390, "loss": 0.4164, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:34:21", "remaining_time": "10:24:11"}
{"current_steps": 152, "total_steps": 390, "loss": 0.4225, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:36:50", "remaining_time": "10:21:21"}
{"current_steps": 153, "total_steps": 390, "loss": 0.4254, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:39:09", "remaining_time": "10:18:18"}
{"current_steps": 154, "total_steps": 390, "loss": 0.4077, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:41:35", "remaining_time": "10:15:25"}
{"current_steps": 155, "total_steps": 390, "loss": 0.4039, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "6:44:09", "remaining_time": "10:12:45"}
{"current_steps": 156, "total_steps": 390, "loss": 0.4166, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "6:46:51", "remaining_time": "10:10:17"}
{"current_steps": 157, "total_steps": 390, "loss": 0.3617, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "6:50:13", "remaining_time": "10:08:48"}
{"current_steps": 158, "total_steps": 390, "loss": 0.3407, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "6:52:47", "remaining_time": "10:06:07"}
{"current_steps": 159, "total_steps": 390, "loss": 0.3578, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "6:55:12", "remaining_time": "10:03:14"}
{"current_steps": 160, "total_steps": 390, "loss": 0.3512, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "6:57:47", "remaining_time": "10:00:34"}
{"current_steps": 161, "total_steps": 390, "loss": 0.3478, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "7:00:34", "remaining_time": "9:58:12"}
{"current_steps": 162, "total_steps": 390, "loss": 0.3581, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "7:03:05", "remaining_time": "9:55:27"}
{"current_steps": 163, "total_steps": 390, "loss": 0.3494, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "7:05:48", "remaining_time": "9:52:59"}
{"current_steps": 164, "total_steps": 390, "loss": 0.3476, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "7:08:37", "remaining_time": "9:50:40"}
{"current_steps": 165, "total_steps": 390, "loss": 0.3498, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "7:11:16", "remaining_time": "9:48:05"}
{"current_steps": 166, "total_steps": 390, "loss": 0.3538, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:13:49", "remaining_time": "9:45:23"}
{"current_steps": 167, "total_steps": 390, "loss": 0.3476, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:16:22", "remaining_time": "9:42:42"}
{"current_steps": 168, "total_steps": 390, "loss": 0.3483, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:18:50", "remaining_time": "9:39:54"}
{"current_steps": 169, "total_steps": 390, "loss": 0.3562, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:21:34", "remaining_time": "9:37:26"}
{"current_steps": 170, "total_steps": 390, "loss": 0.3431, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:24:03", "remaining_time": "9:34:40"}
{"current_steps": 171, "total_steps": 390, "loss": 0.3471, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:26:36", "remaining_time": "9:31:57"}
{"current_steps": 172, "total_steps": 390, "loss": 0.3549, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:29:16", "remaining_time": "9:29:25"}
{"current_steps": 173, "total_steps": 390, "loss": 0.3508, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:31:56", "remaining_time": "9:26:52"}
{"current_steps": 174, "total_steps": 390, "loss": 0.3347, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:34:28", "remaining_time": "9:24:11"}
{"current_steps": 175, "total_steps": 390, "loss": 0.3393, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:36:57", "remaining_time": "9:21:24"}
{"current_steps": 176, "total_steps": 390, "loss": 0.3463, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:39:42", "remaining_time": "9:18:57"}
{"current_steps": 177, "total_steps": 390, "loss": 0.3442, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "7:42:35", "remaining_time": "9:16:40"}
{"current_steps": 178, "total_steps": 390, "loss": 0.3447, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "7:45:21", "remaining_time": "9:14:14"}
{"current_steps": 179, "total_steps": 390, "loss": 0.3414, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "7:48:00", "remaining_time": "9:11:40"}
{"current_steps": 180, "total_steps": 390, "loss": 0.3534, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "7:50:26", "remaining_time": "9:08:51"}
{"current_steps": 181, "total_steps": 390, "loss": 0.3406, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "7:52:59", "remaining_time": "9:06:10"}
{"current_steps": 182, "total_steps": 390, "loss": 0.3427, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "7:55:20", "remaining_time": "9:03:14"}
{"current_steps": 183, "total_steps": 390, "loss": 0.3549, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "7:57:57", "remaining_time": "9:00:38"}
{"current_steps": 184, "total_steps": 390, "loss": 0.3468, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "8:00:24", "remaining_time": "8:57:50"}
{"current_steps": 185, "total_steps": 390, "loss": 0.3466, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "8:02:55", "remaining_time": "8:55:08"}
{"current_steps": 186, "total_steps": 390, "loss": 0.3439, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "8:05:37", "remaining_time": "8:52:36"}
{"current_steps": 187, "total_steps": 390, "loss": 0.3422, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "8:08:24", "remaining_time": "8:50:12"}
{"current_steps": 188, "total_steps": 390, "loss": 0.3453, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "8:10:50", "remaining_time": "8:47:23"}
{"current_steps": 189, "total_steps": 390, "loss": 0.3548, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "8:13:16", "remaining_time": "8:44:36"}
{"current_steps": 190, "total_steps": 390, "loss": 0.3362, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "8:15:47", "remaining_time": "8:41:52"}
{"current_steps": 191, "total_steps": 390, "loss": 0.3499, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:18:25", "remaining_time": "8:39:17"}
{"current_steps": 192, "total_steps": 390, "loss": 0.3491, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:20:53", "remaining_time": "8:36:32"}
{"current_steps": 193, "total_steps": 390, "loss": 0.3489, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:23:26", "remaining_time": "8:33:52"}
{"current_steps": 194, "total_steps": 390, "loss": 0.3573, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:26:12", "remaining_time": "8:31:25"}
{"current_steps": 195, "total_steps": 390, "loss": 0.3484, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:28:49", "remaining_time": "8:28:49"}
{"current_steps": 196, "total_steps": 390, "loss": 0.3395, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:31:19", "remaining_time": "8:26:06"}
{"current_steps": 197, "total_steps": 390, "loss": 0.3415, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:33:56", "remaining_time": "8:23:30"}
{"current_steps": 198, "total_steps": 390, "loss": 0.3481, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:36:41", "remaining_time": "8:21:01"}
{"current_steps": 199, "total_steps": 390, "loss": 0.3506, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "8:39:21", "remaining_time": "8:18:29"}
{"current_steps": 200, "total_steps": 390, "loss": 0.3469, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "8:42:02", "remaining_time": "8:15:56"}
{"current_steps": 201, "total_steps": 390, "loss": 0.3505, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "8:44:42", "remaining_time": "8:13:22"}
{"current_steps": 202, "total_steps": 390, "loss": 0.3478, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "8:47:10", "remaining_time": "8:10:37"}
{"current_steps": 203, "total_steps": 390, "loss": 0.3406, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "8:49:53", "remaining_time": "8:08:07"}
{"current_steps": 204, "total_steps": 390, "loss": 0.349, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "8:52:37", "remaining_time": "8:05:37"}
{"current_steps": 205, "total_steps": 390, "loss": 0.3387, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "8:55:23", "remaining_time": "8:03:09"}
{"current_steps": 206, "total_steps": 390, "loss": 0.3375, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "8:57:52", "remaining_time": "8:00:26"}
{"current_steps": 207, "total_steps": 390, "loss": 0.3458, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "9:00:23", "remaining_time": "7:57:44"}
{"current_steps": 208, "total_steps": 390, "loss": 0.3474, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "9:02:52", "remaining_time": "7:55:00"}
{"current_steps": 209, "total_steps": 390, "loss": 0.3407, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "9:05:27", "remaining_time": "7:52:22"}
{"current_steps": 210, "total_steps": 390, "loss": 0.3459, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "9:08:04", "remaining_time": "7:49:46"}
{"current_steps": 211, "total_steps": 390, "loss": 0.3483, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "9:10:43", "remaining_time": "7:47:12"}
{"current_steps": 212, "total_steps": 390, "loss": 0.3466, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "9:13:26", "remaining_time": "7:44:40"}
{"current_steps": 213, "total_steps": 390, "loss": 0.3468, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "9:16:02", "remaining_time": "7:42:04"}
{"current_steps": 214, "total_steps": 390, "loss": 0.3426, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "9:18:43", "remaining_time": "7:39:31"}
{"current_steps": 215, "total_steps": 390, "loss": 0.35, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:21:12", "remaining_time": "7:36:48"}
{"current_steps": 216, "total_steps": 390, "loss": 0.344, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:23:50", "remaining_time": "7:34:12"}
{"current_steps": 217, "total_steps": 390, "loss": 0.3481, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:26:22", "remaining_time": "7:31:31"}
{"current_steps": 218, "total_steps": 390, "loss": 0.345, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:28:57", "remaining_time": "7:28:54"}
{"current_steps": 219, "total_steps": 390, "loss": 0.356, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:31:35", "remaining_time": "7:26:19"}
{"current_steps": 220, "total_steps": 390, "loss": 0.359, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:34:15", "remaining_time": "7:23:44"}
{"current_steps": 221, "total_steps": 390, "loss": 0.3439, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "9:36:49", "remaining_time": "7:21:05"}
{"current_steps": 222, "total_steps": 390, "loss": 0.338, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "9:39:28", "remaining_time": "7:18:31"}
{"current_steps": 223, "total_steps": 390, "loss": 0.357, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "9:42:07", "remaining_time": "7:15:56"}
{"current_steps": 224, "total_steps": 390, "loss": 0.3445, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "9:44:40", "remaining_time": "7:13:17"}
{"current_steps": 225, "total_steps": 390, "loss": 0.3473, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "9:47:28", "remaining_time": "7:10:49"}
{"current_steps": 226, "total_steps": 390, "loss": 0.3559, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "9:50:01", "remaining_time": "7:08:09"}
{"current_steps": 227, "total_steps": 390, "loss": 0.3525, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "9:52:43", "remaining_time": "7:05:36"}
{"current_steps": 228, "total_steps": 390, "loss": 0.3494, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "9:55:24", "remaining_time": "7:03:03"}
{"current_steps": 229, "total_steps": 390, "loss": 0.345, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "9:58:15", "remaining_time": "7:00:36"}
{"current_steps": 230, "total_steps": 390, "loss": 0.3509, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "10:00:51", "remaining_time": "6:57:59"}
{"current_steps": 231, "total_steps": 390, "loss": 0.3441, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "10:03:25", "remaining_time": "6:55:20"}
{"current_steps": 232, "total_steps": 390, "loss": 0.3457, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "10:06:09", "remaining_time": "6:52:48"}
{"current_steps": 233, "total_steps": 390, "loss": 0.3418, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:08:44", "remaining_time": "6:50:11"}
{"current_steps": 234, "total_steps": 390, "loss": 0.3414, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:11:22", "remaining_time": "6:47:35"}
{"current_steps": 235, "total_steps": 390, "loss": 0.3281, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:14:57", "remaining_time": "6:45:36"}
{"current_steps": 236, "total_steps": 390, "loss": 0.2922, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:17:39", "remaining_time": "6:43:02"}
{"current_steps": 237, "total_steps": 390, "loss": 0.2993, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:20:03", "remaining_time": "6:40:17"}
{"current_steps": 238, "total_steps": 390, "loss": 0.2923, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:22:43", "remaining_time": "6:37:42"}
{"current_steps": 239, "total_steps": 390, "loss": 0.2896, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:25:14", "remaining_time": "6:35:01"}
{"current_steps": 240, "total_steps": 390, "loss": 0.2841, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:27:50", "remaining_time": "6:32:24"}
{"current_steps": 241, "total_steps": 390, "loss": 0.2981, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:30:28", "remaining_time": "6:29:47"}
{"current_steps": 242, "total_steps": 390, "loss": 0.2852, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:32:54", "remaining_time": "6:27:04"}
{"current_steps": 243, "total_steps": 390, "loss": 0.2926, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:35:27", "remaining_time": "6:24:24"}
{"current_steps": 244, "total_steps": 390, "loss": 0.3012, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:38:08", "remaining_time": "6:21:50"}
{"current_steps": 245, "total_steps": 390, "loss": 0.2896, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:40:47", "remaining_time": "6:19:14"}
{"current_steps": 246, "total_steps": 390, "loss": 0.2893, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:43:26", "remaining_time": "6:16:38"}
{"current_steps": 247, "total_steps": 390, "loss": 0.2894, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:46:03", "remaining_time": "6:14:02"}
{"current_steps": 248, "total_steps": 390, "loss": 0.2845, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "10:48:38", "remaining_time": "6:11:24"}
{"current_steps": 249, "total_steps": 390, "loss": 0.3048, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "10:51:18", "remaining_time": "6:08:48"}
{"current_steps": 250, "total_steps": 390, "loss": 0.2865, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "10:54:15", "remaining_time": "6:06:23"}
{"current_steps": 251, "total_steps": 390, "loss": 0.2876, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "10:56:55", "remaining_time": "6:03:47"}
{"current_steps": 252, "total_steps": 390, "loss": 0.2894, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "10:59:30", "remaining_time": "6:01:09"}
{"current_steps": 253, "total_steps": 390, "loss": 0.2924, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:02:09", "remaining_time": "5:58:33"}
{"current_steps": 254, "total_steps": 390, "loss": 0.2805, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:04:49", "remaining_time": "5:55:58"}
{"current_steps": 255, "total_steps": 390, "loss": 0.2829, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:07:27", "remaining_time": "5:53:21"}
{"current_steps": 256, "total_steps": 390, "loss": 0.2962, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:10:12", "remaining_time": "5:50:48"}
{"current_steps": 257, "total_steps": 390, "loss": 0.2803, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:12:47", "remaining_time": "5:48:10"}
{"current_steps": 258, "total_steps": 390, "loss": 0.293, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:15:30", "remaining_time": "5:45:36"}
{"current_steps": 259, "total_steps": 390, "loss": 0.2968, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:18:16", "remaining_time": "5:43:04"}
{"current_steps": 260, "total_steps": 390, "loss": 0.2872, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:20:56", "remaining_time": "5:40:28"}
{"current_steps": 261, "total_steps": 390, "loss": 0.2938, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:23:33", "remaining_time": "5:37:51"}
{"current_steps": 262, "total_steps": 390, "loss": 0.2816, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:26:25", "remaining_time": "5:35:20"}
{"current_steps": 263, "total_steps": 390, "loss": 0.286, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:29:06", "remaining_time": "5:32:46"}
{"current_steps": 264, "total_steps": 390, "loss": 0.2848, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:31:45", "remaining_time": "5:30:09"}
{"current_steps": 265, "total_steps": 390, "loss": 0.2877, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:34:18", "remaining_time": "5:27:30"}
{"current_steps": 266, "total_steps": 390, "loss": 0.2844, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:36:48", "remaining_time": "5:24:49"}
{"current_steps": 267, "total_steps": 390, "loss": 0.2826, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:39:13", "remaining_time": "5:22:07"}
{"current_steps": 268, "total_steps": 390, "loss": 0.2752, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:41:45", "remaining_time": "5:19:27"}
{"current_steps": 269, "total_steps": 390, "loss": 0.2817, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:44:05", "remaining_time": "5:16:42"}
{"current_steps": 270, "total_steps": 390, "loss": 0.2839, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "11:46:32", "remaining_time": "5:14:01"}
{"current_steps": 271, "total_steps": 390, "loss": 0.2929, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "11:49:07", "remaining_time": "5:11:23"}
{"current_steps": 272, "total_steps": 390, "loss": 0.3, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "11:51:46", "remaining_time": "5:08:47"}
{"current_steps": 273, "total_steps": 390, "loss": 0.2844, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "11:54:19", "remaining_time": "5:06:08"}
{"current_steps": 274, "total_steps": 390, "loss": 0.2819, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "11:57:07", "remaining_time": "5:03:36"}
{"current_steps": 275, "total_steps": 390, "loss": 0.2877, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "11:59:39", "remaining_time": "5:00:56"}
{"current_steps": 276, "total_steps": 390, "loss": 0.2796, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:02:11", "remaining_time": "4:58:17"}
{"current_steps": 277, "total_steps": 390, "loss": 0.3047, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:04:38", "remaining_time": "4:55:36"}
{"current_steps": 278, "total_steps": 390, "loss": 0.2884, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:07:21", "remaining_time": "4:53:02"}
{"current_steps": 279, "total_steps": 390, "loss": 0.289, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:09:59", "remaining_time": "4:50:25"}
{"current_steps": 280, "total_steps": 390, "loss": 0.2893, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:12:38", "remaining_time": "4:47:49"}
{"current_steps": 281, "total_steps": 390, "loss": 0.2976, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:15:07", "remaining_time": "4:45:09"}
{"current_steps": 282, "total_steps": 390, "loss": 0.2829, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:17:40", "remaining_time": "4:42:30"}
{"current_steps": 283, "total_steps": 390, "loss": 0.2913, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:20:12", "remaining_time": "4:39:51"}
{"current_steps": 284, "total_steps": 390, "loss": 0.2807, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:22:42", "remaining_time": "4:37:12"}
{"current_steps": 285, "total_steps": 390, "loss": 0.2899, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:25:15", "remaining_time": "4:34:34"}
{"current_steps": 286, "total_steps": 390, "loss": 0.2767, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:27:53", "remaining_time": "4:31:57"}
{"current_steps": 287, "total_steps": 390, "loss": 0.2864, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:30:23", "remaining_time": "4:29:18"}
{"current_steps": 288, "total_steps": 390, "loss": 0.2897, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:32:55", "remaining_time": "4:26:39"}
{"current_steps": 289, "total_steps": 390, "loss": 0.2821, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:35:28", "remaining_time": "4:24:01"}
{"current_steps": 290, "total_steps": 390, "loss": 0.2877, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:38:05", "remaining_time": "4:21:24"}
{"current_steps": 291, "total_steps": 390, "loss": 0.2803, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "12:40:34", "remaining_time": "4:18:45"}
{"current_steps": 292, "total_steps": 390, "loss": 0.2919, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "12:43:05", "remaining_time": "4:16:06"}
{"current_steps": 293, "total_steps": 390, "loss": 0.283, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "12:45:34", "remaining_time": "4:13:27"}
{"current_steps": 294, "total_steps": 390, "loss": 0.2979, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "12:48:04", "remaining_time": "4:10:48"}
{"current_steps": 295, "total_steps": 390, "loss": 0.2842, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "12:50:38", "remaining_time": "4:08:10"}
{"current_steps": 296, "total_steps": 390, "loss": 0.2868, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "12:53:15", "remaining_time": "4:05:33"}
{"current_steps": 297, "total_steps": 390, "loss": 0.2898, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "12:55:58", "remaining_time": "4:02:58"}
{"current_steps": 298, "total_steps": 390, "loss": 0.2882, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "12:58:32", "remaining_time": "4:00:21"}
{"current_steps": 299, "total_steps": 390, "loss": 0.2807, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:01:08", "remaining_time": "3:57:44"}
{"current_steps": 300, "total_steps": 390, "loss": 0.2854, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:03:52", "remaining_time": "3:55:09"}
{"current_steps": 301, "total_steps": 390, "loss": 0.2921, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:06:28", "remaining_time": "3:52:32"}
{"current_steps": 302, "total_steps": 390, "loss": 0.2771, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:08:57", "remaining_time": "3:49:53"}
{"current_steps": 303, "total_steps": 390, "loss": 0.2876, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:11:33", "remaining_time": "3:47:16"}
{"current_steps": 304, "total_steps": 390, "loss": 0.2879, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:14:13", "remaining_time": "3:44:41"}
{"current_steps": 305, "total_steps": 390, "loss": 0.2792, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:16:50", "remaining_time": "3:42:04"}
{"current_steps": 306, "total_steps": 390, "loss": 0.3027, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:19:30", "remaining_time": "3:39:28"}
{"current_steps": 307, "total_steps": 390, "loss": 0.2851, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:22:06", "remaining_time": "3:36:51"}
{"current_steps": 308, "total_steps": 390, "loss": 0.2931, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:24:38", "remaining_time": "3:34:13"}
{"current_steps": 309, "total_steps": 390, "loss": 0.2933, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:27:24", "remaining_time": "3:31:39"}
{"current_steps": 310, "total_steps": 390, "loss": 0.2871, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:29:55", "remaining_time": "3:29:00"}
{"current_steps": 311, "total_steps": 390, "loss": 0.2883, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:32:29", "remaining_time": "3:26:23"}
{"current_steps": 312, "total_steps": 390, "loss": 0.2863, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:34:56", "remaining_time": "3:23:44"}
{"current_steps": 313, "total_steps": 390, "loss": 0.2854, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:38:20", "remaining_time": "3:21:18"}
{"current_steps": 314, "total_steps": 390, "loss": 0.2554, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:40:44", "remaining_time": "3:18:38"}
{"current_steps": 315, "total_steps": 390, "loss": 0.2509, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:43:23", "remaining_time": "3:16:02"}
{"current_steps": 316, "total_steps": 390, "loss": 0.2483, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:45:54", "remaining_time": "3:13:24"}
{"current_steps": 317, "total_steps": 390, "loss": 0.254, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:48:25", "remaining_time": "3:10:46"}
{"current_steps": 318, "total_steps": 390, "loss": 0.2508, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:50:53", "remaining_time": "3:08:07"}
{"current_steps": 319, "total_steps": 390, "loss": 0.245, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:53:40", "remaining_time": "3:05:33"}
{"current_steps": 320, "total_steps": 390, "loss": 0.2526, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:56:23", "remaining_time": "3:02:57"}
{"current_steps": 321, "total_steps": 390, "loss": 0.2508, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "13:59:09", "remaining_time": "3:00:22"}
{"current_steps": 322, "total_steps": 390, "loss": 0.2562, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:01:53", "remaining_time": "2:57:47"}
{"current_steps": 323, "total_steps": 390, "loss": 0.256, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:04:36", "remaining_time": "2:55:11"}
{"current_steps": 324, "total_steps": 390, "loss": 0.2447, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:07:12", "remaining_time": "2:52:34"}
{"current_steps": 325, "total_steps": 390, "loss": 0.2614, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:09:54", "remaining_time": "2:49:58"}
{"current_steps": 326, "total_steps": 390, "loss": 0.2397, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:12:25", "remaining_time": "2:47:20"}
{"current_steps": 327, "total_steps": 390, "loss": 0.241, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:14:51", "remaining_time": "2:44:41"}
{"current_steps": 328, "total_steps": 390, "loss": 0.2484, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:17:29", "remaining_time": "2:42:05"}
{"current_steps": 329, "total_steps": 390, "loss": 0.2443, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:20:03", "remaining_time": "2:39:27"}
{"current_steps": 330, "total_steps": 390, "loss": 0.2535, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:22:34", "remaining_time": "2:36:49"}
{"current_steps": 331, "total_steps": 390, "loss": 0.2459, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:25:13", "remaining_time": "2:34:13"}
{"current_steps": 332, "total_steps": 390, "loss": 0.2462, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:27:51", "remaining_time": "2:31:36"}
{"current_steps": 333, "total_steps": 390, "loss": 0.2583, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "14:30:24", "remaining_time": "2:28:59"}
{"current_steps": 334, "total_steps": 390, "loss": 0.2541, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "14:32:59", "remaining_time": "2:26:22"}
{"current_steps": 335, "total_steps": 390, "loss": 0.2568, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:35:36", "remaining_time": "2:23:45"}
{"current_steps": 336, "total_steps": 390, "loss": 0.244, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:38:09", "remaining_time": "2:21:07"}
{"current_steps": 337, "total_steps": 390, "loss": 0.2548, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "14:40:42", "remaining_time": "2:18:30"}
{"current_steps": 338, "total_steps": 390, "loss": 0.2498, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "14:43:25", "remaining_time": "2:15:54"}
{"current_steps": 339, "total_steps": 390, "loss": 0.253, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:45:59", "remaining_time": "2:13:17"}
{"current_steps": 340, "total_steps": 390, "loss": 0.2547, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "14:48:35", "remaining_time": "2:10:40"}
{"current_steps": 341, "total_steps": 390, "loss": 0.242, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:51:13", "remaining_time": "2:08:03"}
{"current_steps": 342, "total_steps": 390, "loss": 0.2534, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:53:43", "remaining_time": "2:05:26"}
{"current_steps": 343, "total_steps": 390, "loss": 0.2534, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:56:14", "remaining_time": "2:02:48"}
{"current_steps": 344, "total_steps": 390, "loss": 0.2475, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:58:54", "remaining_time": "2:00:12"}
{"current_steps": 345, "total_steps": 390, "loss": 0.2451, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:01:29", "remaining_time": "1:57:35"}
{"current_steps": 346, "total_steps": 390, "loss": 0.2476, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:04:05", "remaining_time": "1:54:58"}
{"current_steps": 347, "total_steps": 390, "loss": 0.2583, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:06:47", "remaining_time": "1:52:22"}
{"current_steps": 348, "total_steps": 390, "loss": 0.2466, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:09:23", "remaining_time": "1:49:45"}
{"current_steps": 349, "total_steps": 390, "loss": 0.2462, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:12:04", "remaining_time": "1:47:08"}
{"current_steps": 350, "total_steps": 390, "loss": 0.2486, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:14:40", "remaining_time": "1:44:32"}
{"current_steps": 351, "total_steps": 390, "loss": 0.2535, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:17:24", "remaining_time": "1:41:56"}
{"current_steps": 352, "total_steps": 390, "loss": 0.2466, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:20:10", "remaining_time": "1:39:20"}
{"current_steps": 353, "total_steps": 390, "loss": 0.2508, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:22:38", "remaining_time": "1:36:42"}
{"current_steps": 354, "total_steps": 390, "loss": 0.2569, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:25:14", "remaining_time": "1:34:05"}
{"current_steps": 355, "total_steps": 390, "loss": 0.2497, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "15:27:47", "remaining_time": "1:31:28"}
{"current_steps": 356, "total_steps": 390, "loss": 0.2541, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "15:30:22", "remaining_time": "1:28:51"}
{"current_steps": 357, "total_steps": 390, "loss": 0.2431, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "15:33:01", "remaining_time": "1:26:14"}
{"current_steps": 358, "total_steps": 390, "loss": 0.2549, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "15:35:41", "remaining_time": "1:23:38"}
{"current_steps": 359, "total_steps": 390, "loss": 0.2426, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "15:38:15", "remaining_time": "1:21:01"}
{"current_steps": 360, "total_steps": 390, "loss": 0.2401, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "15:40:49", "remaining_time": "1:18:24"}
{"current_steps": 361, "total_steps": 390, "loss": 0.2578, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "15:43:22", "remaining_time": "1:15:47"}
{"current_steps": 362, "total_steps": 390, "loss": 0.248, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "15:45:59", "remaining_time": "1:13:10"}
{"current_steps": 363, "total_steps": 390, "loss": 0.2481, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "15:48:28", "remaining_time": "1:10:32"}
{"current_steps": 364, "total_steps": 390, "loss": 0.2549, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "15:51:07", "remaining_time": "1:07:56"}
{"current_steps": 365, "total_steps": 390, "loss": 0.2474, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "15:53:53", "remaining_time": "1:05:20"}
{"current_steps": 366, "total_steps": 390, "loss": 0.2493, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:56:21", "remaining_time": "1:02:42"}
{"current_steps": 367, "total_steps": 390, "loss": 0.2604, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:59:06", "remaining_time": "1:00:06"}
{"current_steps": 368, "total_steps": 390, "loss": 0.2421, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:01:43", "remaining_time": "0:57:29"}
{"current_steps": 369, "total_steps": 390, "loss": 0.2526, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:04:21", "remaining_time": "0:54:52"}
{"current_steps": 370, "total_steps": 390, "loss": 0.2544, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:07:04", "remaining_time": "0:52:16"}
{"current_steps": 371, "total_steps": 390, "loss": 0.246, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:09:46", "remaining_time": "0:49:39"}
{"current_steps": 372, "total_steps": 390, "loss": 0.2516, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:12:27", "remaining_time": "0:47:03"}
{"current_steps": 373, "total_steps": 390, "loss": 0.2588, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:15:06", "remaining_time": "0:44:26"}
{"current_steps": 374, "total_steps": 390, "loss": 0.2453, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:17:50", "remaining_time": "0:41:49"}
{"current_steps": 375, "total_steps": 390, "loss": 0.252, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:20:32", "remaining_time": "0:39:13"}
{"current_steps": 376, "total_steps": 390, "loss": 0.251, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "16:23:14", "remaining_time": "0:36:36"}
{"current_steps": 377, "total_steps": 390, "loss": 0.2536, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "16:25:50", "remaining_time": "0:33:59"}
{"current_steps": 378, "total_steps": 390, "loss": 0.2507, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "16:28:33", "remaining_time": "0:31:22"}
{"current_steps": 379, "total_steps": 390, "loss": 0.2472, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "16:31:01", "remaining_time": "0:28:45"}
{"current_steps": 380, "total_steps": 390, "loss": 0.2479, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "16:33:32", "remaining_time": "0:26:08"}
{"current_steps": 381, "total_steps": 390, "loss": 0.2477, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "16:36:02", "remaining_time": "0:23:31"}
{"current_steps": 382, "total_steps": 390, "loss": 0.2458, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "16:38:32", "remaining_time": "0:20:54"}
{"current_steps": 383, "total_steps": 390, "loss": 0.2483, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "16:41:09", "remaining_time": "0:18:17"}
{"current_steps": 384, "total_steps": 390, "loss": 0.2472, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "16:43:37", "remaining_time": "0:15:40"}
{"current_steps": 385, "total_steps": 390, "loss": 0.2567, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "16:46:14", "remaining_time": "0:13:04"}
{"current_steps": 386, "total_steps": 390, "loss": 0.2526, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "16:48:40", "remaining_time": "0:10:27"}
{"current_steps": 387, "total_steps": 390, "loss": 0.2519, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "16:51:15", "remaining_time": "0:07:50"}
{"current_steps": 388, "total_steps": 390, "loss": 0.2554, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "16:53:58", "remaining_time": "0:05:13"}
{"current_steps": 389, "total_steps": 390, "loss": 0.2485, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "16:56:25", "remaining_time": "0:02:36"}
{"current_steps": 390, "total_steps": 390, "loss": 0.2562, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:59:00", "remaining_time": "0:00:00"}
{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:00:44", "remaining_time": "0:00:00"}