d1_code_mc_llm_10k / trainer_log.jsonl
ryanmarten's picture
Training in progress, epoch 3
df436c5 verified
raw
history blame
57.6 kB
{"current_steps": 1, "total_steps": 390, "loss": 1.0271, "lr": 1.0256410256410257e-06, "epoch": 0.0128, "percentage": 0.26, "elapsed_time": "0:02:33", "remaining_time": "16:35:07"}
{"current_steps": 2, "total_steps": 390, "loss": 1.0566, "lr": 2.0512820512820513e-06, "epoch": 0.0256, "percentage": 0.51, "elapsed_time": "0:05:11", "remaining_time": "16:48:22"}
{"current_steps": 3, "total_steps": 390, "loss": 1.0331, "lr": 3.0769230769230774e-06, "epoch": 0.0384, "percentage": 0.77, "elapsed_time": "0:07:56", "remaining_time": "17:03:30"}
{"current_steps": 4, "total_steps": 390, "loss": 1.0292, "lr": 4.102564102564103e-06, "epoch": 0.0512, "percentage": 1.03, "elapsed_time": "0:10:44", "remaining_time": "17:16:21"}
{"current_steps": 5, "total_steps": 390, "loss": 0.9753, "lr": 5.128205128205128e-06, "epoch": 0.064, "percentage": 1.28, "elapsed_time": "0:13:19", "remaining_time": "17:06:04"}
{"current_steps": 6, "total_steps": 390, "loss": 0.9494, "lr": 6.153846153846155e-06, "epoch": 0.0768, "percentage": 1.54, "elapsed_time": "0:16:15", "remaining_time": "17:20:31"}
{"current_steps": 7, "total_steps": 390, "loss": 0.9385, "lr": 7.17948717948718e-06, "epoch": 0.0896, "percentage": 1.79, "elapsed_time": "0:18:54", "remaining_time": "17:14:59"}
{"current_steps": 8, "total_steps": 390, "loss": 0.9709, "lr": 8.205128205128205e-06, "epoch": 0.1024, "percentage": 2.05, "elapsed_time": "0:21:41", "remaining_time": "17:15:23"}
{"current_steps": 9, "total_steps": 390, "loss": 0.9521, "lr": 9.230769230769232e-06, "epoch": 0.1152, "percentage": 2.31, "elapsed_time": "0:24:22", "remaining_time": "17:12:10"}
{"current_steps": 10, "total_steps": 390, "loss": 0.9232, "lr": 1.0256410256410256e-05, "epoch": 0.128, "percentage": 2.56, "elapsed_time": "0:27:18", "remaining_time": "17:17:42"}
{"current_steps": 11, "total_steps": 390, "loss": 0.9022, "lr": 1.1282051282051283e-05, "epoch": 0.1408, "percentage": 2.82, "elapsed_time": "0:30:04", "remaining_time": "17:16:16"}
{"current_steps": 12, "total_steps": 390, "loss": 0.8721, "lr": 1.230769230769231e-05, "epoch": 0.1536, "percentage": 3.08, "elapsed_time": "0:32:47", "remaining_time": "17:12:57"}
{"current_steps": 13, "total_steps": 390, "loss": 0.8443, "lr": 1.3333333333333333e-05, "epoch": 0.1664, "percentage": 3.33, "elapsed_time": "0:35:31", "remaining_time": "17:10:14"}
{"current_steps": 14, "total_steps": 390, "loss": 0.8302, "lr": 1.435897435897436e-05, "epoch": 0.1792, "percentage": 3.59, "elapsed_time": "0:37:59", "remaining_time": "17:00:27"}
{"current_steps": 15, "total_steps": 390, "loss": 0.8349, "lr": 1.5384615384615387e-05, "epoch": 0.192, "percentage": 3.85, "elapsed_time": "0:40:43", "remaining_time": "16:58:03"}
{"current_steps": 16, "total_steps": 390, "loss": 0.8084, "lr": 1.641025641025641e-05, "epoch": 0.2048, "percentage": 4.1, "elapsed_time": "0:43:32", "remaining_time": "16:57:36"}
{"current_steps": 17, "total_steps": 390, "loss": 0.7774, "lr": 1.7435897435897438e-05, "epoch": 0.2176, "percentage": 4.36, "elapsed_time": "0:46:16", "remaining_time": "16:55:23"}
{"current_steps": 18, "total_steps": 390, "loss": 0.7788, "lr": 1.8461538461538465e-05, "epoch": 0.2304, "percentage": 4.62, "elapsed_time": "0:49:01", "remaining_time": "16:53:20"}
{"current_steps": 19, "total_steps": 390, "loss": 0.7528, "lr": 1.9487179487179488e-05, "epoch": 0.2432, "percentage": 4.87, "elapsed_time": "0:51:49", "remaining_time": "16:52:00"}
{"current_steps": 20, "total_steps": 390, "loss": 0.747, "lr": 2.0512820512820512e-05, "epoch": 0.256, "percentage": 5.13, "elapsed_time": "0:54:39", "remaining_time": "16:51:18"}
{"current_steps": 21, "total_steps": 390, "loss": 0.7414, "lr": 2.153846153846154e-05, "epoch": 0.2688, "percentage": 5.38, "elapsed_time": "0:57:19", "remaining_time": "16:47:19"}
{"current_steps": 22, "total_steps": 390, "loss": 0.7493, "lr": 2.2564102564102566e-05, "epoch": 0.2816, "percentage": 5.64, "elapsed_time": "1:00:12", "remaining_time": "16:47:13"}
{"current_steps": 23, "total_steps": 390, "loss": 0.7551, "lr": 2.3589743589743593e-05, "epoch": 0.2944, "percentage": 5.9, "elapsed_time": "1:02:51", "remaining_time": "16:42:58"}
{"current_steps": 24, "total_steps": 390, "loss": 0.7216, "lr": 2.461538461538462e-05, "epoch": 0.3072, "percentage": 6.15, "elapsed_time": "1:05:23", "remaining_time": "16:37:19"}
{"current_steps": 25, "total_steps": 390, "loss": 0.7421, "lr": 2.5641025641025646e-05, "epoch": 0.32, "percentage": 6.41, "elapsed_time": "1:07:54", "remaining_time": "16:31:26"}
{"current_steps": 26, "total_steps": 390, "loss": 0.7436, "lr": 2.6666666666666667e-05, "epoch": 0.3328, "percentage": 6.67, "elapsed_time": "1:10:42", "remaining_time": "16:29:53"}
{"current_steps": 27, "total_steps": 390, "loss": 0.7175, "lr": 2.7692307692307694e-05, "epoch": 0.3456, "percentage": 6.92, "elapsed_time": "1:13:26", "remaining_time": "16:27:27"}
{"current_steps": 28, "total_steps": 390, "loss": 0.7104, "lr": 2.871794871794872e-05, "epoch": 0.3584, "percentage": 7.18, "elapsed_time": "1:16:08", "remaining_time": "16:24:29"}
{"current_steps": 29, "total_steps": 390, "loss": 0.7047, "lr": 2.9743589743589747e-05, "epoch": 0.3712, "percentage": 7.44, "elapsed_time": "1:18:55", "remaining_time": "16:22:27"}
{"current_steps": 30, "total_steps": 390, "loss": 0.6993, "lr": 3.0769230769230774e-05, "epoch": 0.384, "percentage": 7.69, "elapsed_time": "1:21:35", "remaining_time": "16:19:08"}
{"current_steps": 31, "total_steps": 390, "loss": 0.6966, "lr": 3.1794871794871795e-05, "epoch": 0.3968, "percentage": 7.95, "elapsed_time": "1:24:13", "remaining_time": "16:15:22"}
{"current_steps": 32, "total_steps": 390, "loss": 0.7064, "lr": 3.282051282051282e-05, "epoch": 0.4096, "percentage": 8.21, "elapsed_time": "1:26:48", "remaining_time": "16:11:05"}
{"current_steps": 33, "total_steps": 390, "loss": 0.691, "lr": 3.384615384615385e-05, "epoch": 0.4224, "percentage": 8.46, "elapsed_time": "1:29:25", "remaining_time": "16:07:27"}
{"current_steps": 34, "total_steps": 390, "loss": 0.7074, "lr": 3.4871794871794875e-05, "epoch": 0.4352, "percentage": 8.72, "elapsed_time": "1:32:08", "remaining_time": "16:04:44"}
{"current_steps": 35, "total_steps": 390, "loss": 0.7076, "lr": 3.58974358974359e-05, "epoch": 0.448, "percentage": 8.97, "elapsed_time": "1:34:47", "remaining_time": "16:01:31"}
{"current_steps": 36, "total_steps": 390, "loss": 0.7041, "lr": 3.692307692307693e-05, "epoch": 0.4608, "percentage": 9.23, "elapsed_time": "1:37:29", "remaining_time": "15:58:39"}
{"current_steps": 37, "total_steps": 390, "loss": 0.6936, "lr": 3.794871794871795e-05, "epoch": 0.4736, "percentage": 9.49, "elapsed_time": "1:40:18", "remaining_time": "15:56:58"}
{"current_steps": 38, "total_steps": 390, "loss": 0.6956, "lr": 3.8974358974358976e-05, "epoch": 0.4864, "percentage": 9.74, "elapsed_time": "1:43:02", "remaining_time": "15:54:32"}
{"current_steps": 39, "total_steps": 390, "loss": 0.6904, "lr": 4e-05, "epoch": 0.4992, "percentage": 10.0, "elapsed_time": "1:45:42", "remaining_time": "15:51:20"}
{"current_steps": 40, "total_steps": 390, "loss": 0.6966, "lr": 3.9999198907597046e-05, "epoch": 0.512, "percentage": 10.26, "elapsed_time": "1:48:18", "remaining_time": "15:47:44"}
{"current_steps": 41, "total_steps": 390, "loss": 0.6851, "lr": 3.9996795694563096e-05, "epoch": 0.5248, "percentage": 10.51, "elapsed_time": "1:51:08", "remaining_time": "15:46:05"}
{"current_steps": 42, "total_steps": 390, "loss": 0.69, "lr": 3.999279055341771e-05, "epoch": 0.5376, "percentage": 10.77, "elapsed_time": "1:53:52", "remaining_time": "15:43:33"}
{"current_steps": 43, "total_steps": 390, "loss": 0.6757, "lr": 3.998718380500971e-05, "epoch": 0.5504, "percentage": 11.03, "elapsed_time": "1:56:29", "remaining_time": "15:40:04"}
{"current_steps": 44, "total_steps": 390, "loss": 0.6808, "lr": 3.997997589849145e-05, "epoch": 0.5632, "percentage": 11.28, "elapsed_time": "1:59:06", "remaining_time": "15:36:39"}
{"current_steps": 45, "total_steps": 390, "loss": 0.6719, "lr": 3.9971167411282835e-05, "epoch": 0.576, "percentage": 11.54, "elapsed_time": "2:01:40", "remaining_time": "15:32:46"}
{"current_steps": 46, "total_steps": 390, "loss": 0.6879, "lr": 3.99607590490251e-05, "epoch": 0.5888, "percentage": 11.79, "elapsed_time": "2:04:21", "remaining_time": "15:29:56"}
{"current_steps": 47, "total_steps": 390, "loss": 0.6715, "lr": 3.9948751645524235e-05, "epoch": 0.6016, "percentage": 12.05, "elapsed_time": "2:07:09", "remaining_time": "15:27:56"}
{"current_steps": 48, "total_steps": 390, "loss": 0.6844, "lr": 3.9935146162684206e-05, "epoch": 0.6144, "percentage": 12.31, "elapsed_time": "2:09:49", "remaining_time": "15:25:02"}
{"current_steps": 49, "total_steps": 390, "loss": 0.6801, "lr": 3.9919943690429906e-05, "epoch": 0.6272, "percentage": 12.56, "elapsed_time": "2:12:25", "remaining_time": "15:21:36"}
{"current_steps": 50, "total_steps": 390, "loss": 0.667, "lr": 3.9903145446619837e-05, "epoch": 0.64, "percentage": 12.82, "elapsed_time": "2:14:57", "remaining_time": "15:17:42"}
{"current_steps": 51, "total_steps": 390, "loss": 0.679, "lr": 3.9884752776948564e-05, "epoch": 0.6528, "percentage": 13.08, "elapsed_time": "2:17:47", "remaining_time": "15:15:57"}
{"current_steps": 52, "total_steps": 390, "loss": 0.6727, "lr": 3.9864767154838864e-05, "epoch": 0.6656, "percentage": 13.33, "elapsed_time": "2:20:38", "remaining_time": "15:14:08"}
{"current_steps": 53, "total_steps": 390, "loss": 0.6695, "lr": 3.9843190181323744e-05, "epoch": 0.6784, "percentage": 13.59, "elapsed_time": "2:23:19", "remaining_time": "15:11:22"}
{"current_steps": 54, "total_steps": 390, "loss": 0.6736, "lr": 3.982002358491817e-05, "epoch": 0.6912, "percentage": 13.85, "elapsed_time": "2:26:11", "remaining_time": "15:09:37"}
{"current_steps": 55, "total_steps": 390, "loss": 0.6783, "lr": 3.979526922148058e-05, "epoch": 0.704, "percentage": 14.1, "elapsed_time": "2:29:06", "remaining_time": "15:08:14"}
{"current_steps": 56, "total_steps": 390, "loss": 0.6768, "lr": 3.9768929074064206e-05, "epoch": 0.7168, "percentage": 14.36, "elapsed_time": "2:31:44", "remaining_time": "15:05:00"}
{"current_steps": 57, "total_steps": 390, "loss": 0.6601, "lr": 3.9741005252758255e-05, "epoch": 0.7296, "percentage": 14.62, "elapsed_time": "2:34:21", "remaining_time": "15:01:48"}
{"current_steps": 58, "total_steps": 390, "loss": 0.6605, "lr": 3.971149999451886e-05, "epoch": 0.7424, "percentage": 14.87, "elapsed_time": "2:37:03", "remaining_time": "14:58:58"}
{"current_steps": 59, "total_steps": 390, "loss": 0.6612, "lr": 3.9680415662989806e-05, "epoch": 0.7552, "percentage": 15.13, "elapsed_time": "2:39:55", "remaining_time": "14:57:11"}
{"current_steps": 60, "total_steps": 390, "loss": 0.6583, "lr": 3.9647754748313294e-05, "epoch": 0.768, "percentage": 15.38, "elapsed_time": "2:42:33", "remaining_time": "14:54:06"}
{"current_steps": 61, "total_steps": 390, "loss": 0.6718, "lr": 3.96135198669304e-05, "epoch": 0.7808, "percentage": 15.64, "elapsed_time": "2:45:21", "remaining_time": "14:51:51"}
{"current_steps": 62, "total_steps": 390, "loss": 0.6525, "lr": 3.957771376137144e-05, "epoch": 0.7936, "percentage": 15.9, "elapsed_time": "2:48:18", "remaining_time": "14:50:24"}
{"current_steps": 63, "total_steps": 390, "loss": 0.6604, "lr": 3.954033930003634e-05, "epoch": 0.8064, "percentage": 16.15, "elapsed_time": "2:50:55", "remaining_time": "14:47:09"}
{"current_steps": 64, "total_steps": 390, "loss": 0.6551, "lr": 3.9501399476964806e-05, "epoch": 0.8192, "percentage": 16.41, "elapsed_time": "2:53:42", "remaining_time": "14:44:47"}
{"current_steps": 65, "total_steps": 390, "loss": 0.6571, "lr": 3.946089741159648e-05, "epoch": 0.832, "percentage": 16.67, "elapsed_time": "2:56:29", "remaining_time": "14:42:27"}
{"current_steps": 66, "total_steps": 390, "loss": 0.6603, "lr": 3.9418836348521045e-05, "epoch": 0.8448, "percentage": 16.92, "elapsed_time": "2:59:04", "remaining_time": "14:39:03"}
{"current_steps": 67, "total_steps": 390, "loss": 0.6597, "lr": 3.937521965721831e-05, "epoch": 0.8576, "percentage": 17.18, "elapsed_time": "3:01:36", "remaining_time": "14:35:28"}
{"current_steps": 68, "total_steps": 390, "loss": 0.658, "lr": 3.933005083178828e-05, "epoch": 0.8704, "percentage": 17.44, "elapsed_time": "3:04:24", "remaining_time": "14:33:12"}
{"current_steps": 69, "total_steps": 390, "loss": 0.6431, "lr": 3.928333349067125e-05, "epoch": 0.8832, "percentage": 17.69, "elapsed_time": "3:07:10", "remaining_time": "14:30:44"}
{"current_steps": 70, "total_steps": 390, "loss": 0.6416, "lr": 3.923507137635792e-05, "epoch": 0.896, "percentage": 17.95, "elapsed_time": "3:09:48", "remaining_time": "14:27:41"}
{"current_steps": 71, "total_steps": 390, "loss": 0.6492, "lr": 3.9185268355089606e-05, "epoch": 0.9088, "percentage": 18.21, "elapsed_time": "3:12:36", "remaining_time": "14:25:24"}
{"current_steps": 72, "total_steps": 390, "loss": 0.6525, "lr": 3.913392841654851e-05, "epoch": 0.9216, "percentage": 18.46, "elapsed_time": "3:15:06", "remaining_time": "14:21:42"}
{"current_steps": 73, "total_steps": 390, "loss": 0.6478, "lr": 3.9081055673538093e-05, "epoch": 0.9344, "percentage": 18.72, "elapsed_time": "3:17:52", "remaining_time": "14:19:17"}
{"current_steps": 74, "total_steps": 390, "loss": 0.6476, "lr": 3.902665436165364e-05, "epoch": 0.9472, "percentage": 18.97, "elapsed_time": "3:20:42", "remaining_time": "14:17:05"}
{"current_steps": 75, "total_steps": 390, "loss": 0.659, "lr": 3.897072883894291e-05, "epoch": 0.96, "percentage": 19.23, "elapsed_time": "3:23:20", "remaining_time": "14:14:01"}
{"current_steps": 76, "total_steps": 390, "loss": 0.6322, "lr": 3.8913283585557054e-05, "epoch": 0.9728, "percentage": 19.49, "elapsed_time": "3:26:13", "remaining_time": "14:12:04"}
{"current_steps": 77, "total_steps": 390, "loss": 0.6385, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "3:28:50", "remaining_time": "14:08:56"}
{"current_steps": 78, "total_steps": 390, "loss": 0.6446, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "3:31:16", "remaining_time": "14:05:06"}
{"current_steps": 79, "total_steps": 390, "loss": 0.6037, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "3:34:49", "remaining_time": "14:05:42"}
{"current_steps": 80, "total_steps": 390, "loss": 0.587, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "3:37:43", "remaining_time": "14:03:41"}
{"current_steps": 81, "total_steps": 390, "loss": 0.5928, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:40:33", "remaining_time": "14:01:22"}
{"current_steps": 82, "total_steps": 390, "loss": 0.5948, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:43:18", "remaining_time": "13:58:47"}
{"current_steps": 83, "total_steps": 390, "loss": 0.6015, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:46:04", "remaining_time": "13:56:11"}
{"current_steps": 84, "total_steps": 390, "loss": 0.5881, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:48:44", "remaining_time": "13:53:15"}
{"current_steps": 85, "total_steps": 390, "loss": 0.5908, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:51:29", "remaining_time": "13:50:38"}
{"current_steps": 86, "total_steps": 390, "loss": 0.5954, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:54:20", "remaining_time": "13:48:22"}
{"current_steps": 87, "total_steps": 390, "loss": 0.5999, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:57:02", "remaining_time": "13:45:34"}
{"current_steps": 88, "total_steps": 390, "loss": 0.5967, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:59:39", "remaining_time": "13:42:27"}
{"current_steps": 89, "total_steps": 390, "loss": 0.6134, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "4:02:20", "remaining_time": "13:39:37"}
{"current_steps": 90, "total_steps": 390, "loss": 0.6097, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "4:05:06", "remaining_time": "13:37:03"}
{"current_steps": 91, "total_steps": 390, "loss": 0.5706, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "4:07:38", "remaining_time": "13:33:41"}
{"current_steps": 92, "total_steps": 390, "loss": 0.5831, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "4:10:10", "remaining_time": "13:30:20"}
{"current_steps": 93, "total_steps": 390, "loss": 0.582, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "4:12:56", "remaining_time": "13:27:46"}
{"current_steps": 94, "total_steps": 390, "loss": 0.5902, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "4:15:42", "remaining_time": "13:25:12"}
{"current_steps": 95, "total_steps": 390, "loss": 0.604, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "4:18:27", "remaining_time": "13:22:35"}
{"current_steps": 96, "total_steps": 390, "loss": 0.5949, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "4:21:01", "remaining_time": "13:19:23"}
{"current_steps": 97, "total_steps": 390, "loss": 0.5933, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "4:23:35", "remaining_time": "13:16:13"}
{"current_steps": 98, "total_steps": 390, "loss": 0.5898, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "4:26:19", "remaining_time": "13:13:31"}
{"current_steps": 99, "total_steps": 390, "loss": 0.5781, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "4:28:55", "remaining_time": "13:10:29"}
{"current_steps": 100, "total_steps": 390, "loss": 0.5956, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "4:31:31", "remaining_time": "13:07:25"}
{"current_steps": 101, "total_steps": 390, "loss": 0.5873, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "4:34:16", "remaining_time": "13:04:47"}
{"current_steps": 102, "total_steps": 390, "loss": 0.5888, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "4:37:01", "remaining_time": "13:02:12"}
{"current_steps": 103, "total_steps": 390, "loss": 0.5853, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "4:39:47", "remaining_time": "12:59:37"}
{"current_steps": 104, "total_steps": 390, "loss": 0.59, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "4:42:32", "remaining_time": "12:56:58"}
{"current_steps": 105, "total_steps": 390, "loss": 0.6016, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "4:45:20", "remaining_time": "12:54:29"}
{"current_steps": 106, "total_steps": 390, "loss": 0.5634, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "4:48:08", "remaining_time": "12:52:00"}
{"current_steps": 107, "total_steps": 390, "loss": 0.5662, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "4:50:53", "remaining_time": "12:49:22"}
{"current_steps": 108, "total_steps": 390, "loss": 0.5909, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "4:53:37", "remaining_time": "12:46:40"}
{"current_steps": 109, "total_steps": 390, "loss": 0.5737, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "4:56:24", "remaining_time": "12:44:07"}
{"current_steps": 110, "total_steps": 390, "loss": 0.5863, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:59:07", "remaining_time": "12:41:25"}
{"current_steps": 111, "total_steps": 390, "loss": 0.5741, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "5:02:04", "remaining_time": "12:39:15"}
{"current_steps": 112, "total_steps": 390, "loss": 0.6046, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "5:04:48", "remaining_time": "12:36:35"}
{"current_steps": 113, "total_steps": 390, "loss": 0.5681, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "5:07:31", "remaining_time": "12:33:50"}
{"current_steps": 114, "total_steps": 390, "loss": 0.5862, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "5:10:25", "remaining_time": "12:31:33"}
{"current_steps": 115, "total_steps": 390, "loss": 0.5817, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "5:12:56", "remaining_time": "12:28:19"}
{"current_steps": 116, "total_steps": 390, "loss": 0.5845, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "5:15:36", "remaining_time": "12:25:29"}
{"current_steps": 117, "total_steps": 390, "loss": 0.5822, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "5:18:08", "remaining_time": "12:22:20"}
{"current_steps": 118, "total_steps": 390, "loss": 0.5928, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "5:21:00", "remaining_time": "12:19:56"}
{"current_steps": 119, "total_steps": 390, "loss": 0.5728, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "5:23:35", "remaining_time": "12:16:55"}
{"current_steps": 120, "total_steps": 390, "loss": 0.5843, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "5:26:16", "remaining_time": "12:14:07"}
{"current_steps": 121, "total_steps": 390, "loss": 0.5734, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "5:29:15", "remaining_time": "12:11:59"}
{"current_steps": 122, "total_steps": 390, "loss": 0.59, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "5:32:01", "remaining_time": "12:09:21"}
{"current_steps": 123, "total_steps": 390, "loss": 0.5812, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "5:34:56", "remaining_time": "12:07:04"}
{"current_steps": 124, "total_steps": 390, "loss": 0.5884, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "5:37:27", "remaining_time": "12:03:54"}
{"current_steps": 125, "total_steps": 390, "loss": 0.5771, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "5:40:13", "remaining_time": "12:01:17"}
{"current_steps": 126, "total_steps": 390, "loss": 0.5776, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "5:42:56", "remaining_time": "11:58:31"}
{"current_steps": 127, "total_steps": 390, "loss": 0.5841, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "5:45:42", "remaining_time": "11:55:53"}
{"current_steps": 128, "total_steps": 390, "loss": 0.5871, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "5:48:20", "remaining_time": "11:53:01"}
{"current_steps": 129, "total_steps": 390, "loss": 0.5723, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "5:51:09", "remaining_time": "11:50:29"}
{"current_steps": 130, "total_steps": 390, "loss": 0.583, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "5:53:47", "remaining_time": "11:47:34"}
{"current_steps": 131, "total_steps": 390, "loss": 0.585, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "5:56:26", "remaining_time": "11:44:42"}
{"current_steps": 132, "total_steps": 390, "loss": 0.5816, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "5:59:09", "remaining_time": "11:41:59"}
{"current_steps": 133, "total_steps": 390, "loss": 0.5832, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "6:01:46", "remaining_time": "11:39:05"}
{"current_steps": 134, "total_steps": 390, "loss": 0.5716, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "6:04:33", "remaining_time": "11:36:29"}
{"current_steps": 135, "total_steps": 390, "loss": 0.5762, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "6:07:26", "remaining_time": "11:34:03"}
{"current_steps": 136, "total_steps": 390, "loss": 0.5799, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "6:10:15", "remaining_time": "11:31:30"}
{"current_steps": 137, "total_steps": 390, "loss": 0.575, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "6:13:00", "remaining_time": "11:28:49"}
{"current_steps": 138, "total_steps": 390, "loss": 0.583, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "6:15:47", "remaining_time": "11:26:12"}
{"current_steps": 139, "total_steps": 390, "loss": 0.5696, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "6:18:26", "remaining_time": "11:23:23"}
{"current_steps": 140, "total_steps": 390, "loss": 0.5772, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "6:21:12", "remaining_time": "11:20:43"}
{"current_steps": 141, "total_steps": 390, "loss": 0.5798, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "6:23:40", "remaining_time": "11:17:32"}
{"current_steps": 142, "total_steps": 390, "loss": 0.5821, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "6:26:27", "remaining_time": "11:14:56"}
{"current_steps": 143, "total_steps": 390, "loss": 0.5699, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "6:29:03", "remaining_time": "11:12:00"}
{"current_steps": 144, "total_steps": 390, "loss": 0.5632, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "6:31:38", "remaining_time": "11:09:03"}
{"current_steps": 145, "total_steps": 390, "loss": 0.5684, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "6:34:24", "remaining_time": "11:06:24"}
{"current_steps": 146, "total_steps": 390, "loss": 0.5769, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "6:37:20", "remaining_time": "11:04:03"}
{"current_steps": 147, "total_steps": 390, "loss": 0.5713, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "6:40:06", "remaining_time": "11:01:24"}
{"current_steps": 148, "total_steps": 390, "loss": 0.5811, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "6:42:43", "remaining_time": "10:58:31"}
{"current_steps": 149, "total_steps": 390, "loss": 0.5864, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "6:45:33", "remaining_time": "10:55:58"}
{"current_steps": 150, "total_steps": 390, "loss": 0.5721, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "6:48:15", "remaining_time": "10:53:12"}
{"current_steps": 151, "total_steps": 390, "loss": 0.5824, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "6:50:58", "remaining_time": "10:50:29"}
{"current_steps": 152, "total_steps": 390, "loss": 0.5724, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "6:53:32", "remaining_time": "10:47:30"}
{"current_steps": 153, "total_steps": 390, "loss": 0.5625, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "6:56:03", "remaining_time": "10:44:29"}
{"current_steps": 154, "total_steps": 390, "loss": 0.5689, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "6:58:47", "remaining_time": "10:41:47"}
{"current_steps": 155, "total_steps": 390, "loss": 0.5637, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "7:01:20", "remaining_time": "10:38:47"}
{"current_steps": 156, "total_steps": 390, "loss": 0.5754, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "7:03:57", "remaining_time": "10:35:56"}
{"current_steps": 157, "total_steps": 390, "loss": 0.5323, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "7:07:19", "remaining_time": "10:34:10"}
{"current_steps": 158, "total_steps": 390, "loss": 0.4942, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "7:10:09", "remaining_time": "10:31:37"}
{"current_steps": 159, "total_steps": 390, "loss": 0.5174, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "7:12:42", "remaining_time": "10:28:38"}
{"current_steps": 160, "total_steps": 390, "loss": 0.5189, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "7:15:37", "remaining_time": "10:26:12"}
{"current_steps": 161, "total_steps": 390, "loss": 0.5006, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "7:18:25", "remaining_time": "10:23:35"}
{"current_steps": 162, "total_steps": 390, "loss": 0.5017, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "7:21:14", "remaining_time": "10:21:00"}
{"current_steps": 163, "total_steps": 390, "loss": 0.5056, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "7:24:03", "remaining_time": "10:18:24"}
{"current_steps": 164, "total_steps": 390, "loss": 0.4892, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "7:26:51", "remaining_time": "10:15:48"}
{"current_steps": 165, "total_steps": 390, "loss": 0.4972, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "7:29:31", "remaining_time": "10:12:59"}
{"current_steps": 166, "total_steps": 390, "loss": 0.4821, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "7:32:16", "remaining_time": "10:10:18"}
{"current_steps": 167, "total_steps": 390, "loss": 0.4918, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "7:34:58", "remaining_time": "10:07:31"}
{"current_steps": 168, "total_steps": 390, "loss": 0.4862, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "7:37:51", "remaining_time": "10:05:01"}
{"current_steps": 169, "total_steps": 390, "loss": 0.4931, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "7:40:23", "remaining_time": "10:02:03"}
{"current_steps": 170, "total_steps": 390, "loss": 0.4955, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "7:43:15", "remaining_time": "9:59:30"}
{"current_steps": 171, "total_steps": 390, "loss": 0.4861, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "7:46:01", "remaining_time": "9:56:49"}
{"current_steps": 172, "total_steps": 390, "loss": 0.5052, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "7:48:41", "remaining_time": "9:54:02"}
{"current_steps": 173, "total_steps": 390, "loss": 0.4911, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "7:51:21", "remaining_time": "9:51:15"}
{"current_steps": 174, "total_steps": 390, "loss": 0.4889, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "7:53:58", "remaining_time": "9:48:22"}
{"current_steps": 175, "total_steps": 390, "loss": 0.5002, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "7:56:59", "remaining_time": "9:46:00"}
{"current_steps": 176, "total_steps": 390, "loss": 0.494, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "7:59:43", "remaining_time": "9:43:18"}
{"current_steps": 177, "total_steps": 390, "loss": 0.4997, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "8:02:23", "remaining_time": "9:40:29"}
{"current_steps": 178, "total_steps": 390, "loss": 0.5026, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "8:05:17", "remaining_time": "9:37:58"}
{"current_steps": 179, "total_steps": 390, "loss": 0.5009, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "8:08:01", "remaining_time": "9:35:15"}
{"current_steps": 180, "total_steps": 390, "loss": 0.4984, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "8:10:41", "remaining_time": "9:32:28"}
{"current_steps": 181, "total_steps": 390, "loss": 0.4976, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "8:13:29", "remaining_time": "9:29:49"}
{"current_steps": 182, "total_steps": 390, "loss": 0.492, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "8:16:02", "remaining_time": "9:26:54"}
{"current_steps": 183, "total_steps": 390, "loss": 0.4925, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "8:18:42", "remaining_time": "9:24:06"}
{"current_steps": 184, "total_steps": 390, "loss": 0.5095, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "8:21:36", "remaining_time": "9:21:34"}
{"current_steps": 185, "total_steps": 390, "loss": 0.4972, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "8:24:12", "remaining_time": "9:18:42"}
{"current_steps": 186, "total_steps": 390, "loss": 0.5092, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "8:26:44", "remaining_time": "9:15:46"}
{"current_steps": 187, "total_steps": 390, "loss": 0.4982, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "8:29:26", "remaining_time": "9:13:01"}
{"current_steps": 188, "total_steps": 390, "loss": 0.4817, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "8:32:05", "remaining_time": "9:10:14"}
{"current_steps": 189, "total_steps": 390, "loss": 0.5008, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "8:34:46", "remaining_time": "9:07:27"}
{"current_steps": 190, "total_steps": 390, "loss": 0.5043, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "8:37:28", "remaining_time": "9:04:42"}
{"current_steps": 191, "total_steps": 390, "loss": 0.5056, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "8:40:13", "remaining_time": "9:02:00"}
{"current_steps": 192, "total_steps": 390, "loss": 0.5097, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "8:42:52", "remaining_time": "8:59:13"}
{"current_steps": 193, "total_steps": 390, "loss": 0.4935, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "8:45:31", "remaining_time": "8:56:24"}
{"current_steps": 194, "total_steps": 390, "loss": 0.487, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "8:48:14", "remaining_time": "8:53:40"}
{"current_steps": 195, "total_steps": 390, "loss": 0.5035, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "8:50:57", "remaining_time": "8:50:57"}
{"current_steps": 196, "total_steps": 390, "loss": 0.5008, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "8:53:37", "remaining_time": "8:48:10"}
{"current_steps": 197, "total_steps": 390, "loss": 0.4767, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "8:56:13", "remaining_time": "8:45:19"}
{"current_steps": 198, "total_steps": 390, "loss": 0.4889, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "8:59:05", "remaining_time": "8:42:45"}
{"current_steps": 199, "total_steps": 390, "loss": 0.5001, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "9:01:57", "remaining_time": "8:40:09"}
{"current_steps": 200, "total_steps": 390, "loss": 0.4938, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "9:04:43", "remaining_time": "8:37:29"}
{"current_steps": 201, "total_steps": 390, "loss": 0.5084, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "9:07:22", "remaining_time": "8:34:41"}
{"current_steps": 202, "total_steps": 390, "loss": 0.4862, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "9:09:58", "remaining_time": "8:31:51"}
{"current_steps": 203, "total_steps": 390, "loss": 0.4912, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "9:12:48", "remaining_time": "8:29:13"}
{"current_steps": 204, "total_steps": 390, "loss": 0.4962, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "9:15:34", "remaining_time": "8:26:32"}
{"current_steps": 205, "total_steps": 390, "loss": 0.5071, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "9:18:13", "remaining_time": "8:23:46"}
{"current_steps": 206, "total_steps": 390, "loss": 0.4994, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "9:20:54", "remaining_time": "8:21:00"}
{"current_steps": 207, "total_steps": 390, "loss": 0.4927, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "9:23:35", "remaining_time": "8:18:15"}
{"current_steps": 208, "total_steps": 390, "loss": 0.498, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "9:26:23", "remaining_time": "8:15:35"}
{"current_steps": 209, "total_steps": 390, "loss": 0.5075, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "9:29:13", "remaining_time": "8:12:57"}
{"current_steps": 210, "total_steps": 390, "loss": 0.5161, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "9:31:52", "remaining_time": "8:10:10"}
{"current_steps": 211, "total_steps": 390, "loss": 0.4865, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "9:34:37", "remaining_time": "8:07:28"}
{"current_steps": 212, "total_steps": 390, "loss": 0.4951, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "9:37:23", "remaining_time": "8:04:47"}
{"current_steps": 213, "total_steps": 390, "loss": 0.503, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "9:40:12", "remaining_time": "8:02:08"}
{"current_steps": 214, "total_steps": 390, "loss": 0.4958, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "9:42:57", "remaining_time": "7:59:26"}
{"current_steps": 215, "total_steps": 390, "loss": 0.498, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "9:45:30", "remaining_time": "7:56:34"}
{"current_steps": 216, "total_steps": 390, "loss": 0.4875, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "9:48:14", "remaining_time": "7:53:51"}
{"current_steps": 217, "total_steps": 390, "loss": 0.4963, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "9:50:58", "remaining_time": "7:51:09"}
{"current_steps": 218, "total_steps": 390, "loss": 0.4861, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "9:53:43", "remaining_time": "7:48:26"}
{"current_steps": 219, "total_steps": 390, "loss": 0.5046, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "9:56:35", "remaining_time": "7:45:49"}
{"current_steps": 220, "total_steps": 390, "loss": 0.4939, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "9:59:26", "remaining_time": "7:43:12"}
{"current_steps": 221, "total_steps": 390, "loss": 0.5042, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "10:02:07", "remaining_time": "7:40:26"}
{"current_steps": 222, "total_steps": 390, "loss": 0.5127, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "10:04:54", "remaining_time": "7:37:45"}
{"current_steps": 223, "total_steps": 390, "loss": 0.5017, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "10:07:35", "remaining_time": "7:35:01"}
{"current_steps": 224, "total_steps": 390, "loss": 0.4958, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "10:10:21", "remaining_time": "7:32:19"}
{"current_steps": 225, "total_steps": 390, "loss": 0.4842, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "10:12:53", "remaining_time": "7:29:27"}
{"current_steps": 226, "total_steps": 390, "loss": 0.5083, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "10:15:45", "remaining_time": "7:26:50"}
{"current_steps": 227, "total_steps": 390, "loss": 0.4986, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "10:18:20", "remaining_time": "7:24:00"}
{"current_steps": 228, "total_steps": 390, "loss": 0.4967, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "10:21:00", "remaining_time": "7:21:14"}
{"current_steps": 229, "total_steps": 390, "loss": 0.4957, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "10:23:46", "remaining_time": "7:18:32"}
{"current_steps": 230, "total_steps": 390, "loss": 0.4802, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "10:26:39", "remaining_time": "7:15:56"}
{"current_steps": 231, "total_steps": 390, "loss": 0.4943, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "10:29:19", "remaining_time": "7:13:10"}
{"current_steps": 232, "total_steps": 390, "loss": 0.4964, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "10:31:57", "remaining_time": "7:10:23"}
{"current_steps": 233, "total_steps": 390, "loss": 0.4911, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:34:40", "remaining_time": "7:07:39"}
{"current_steps": 234, "total_steps": 390, "loss": 0.4965, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:37:27", "remaining_time": "7:04:58"}
{"current_steps": 235, "total_steps": 390, "loss": 0.4581, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:41:08", "remaining_time": "7:02:52"}
{"current_steps": 236, "total_steps": 390, "loss": 0.4304, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:43:46", "remaining_time": "7:00:05"}
{"current_steps": 237, "total_steps": 390, "loss": 0.4246, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:46:21", "remaining_time": "6:57:16"}
{"current_steps": 238, "total_steps": 390, "loss": 0.4262, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:49:01", "remaining_time": "6:54:30"}
{"current_steps": 239, "total_steps": 390, "loss": 0.4242, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:51:47", "remaining_time": "6:51:48"}
{"current_steps": 240, "total_steps": 390, "loss": 0.4189, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:54:14", "remaining_time": "6:48:54"}
{"current_steps": 241, "total_steps": 390, "loss": 0.4189, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:56:51", "remaining_time": "6:46:06"}
{"current_steps": 242, "total_steps": 390, "loss": 0.4336, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:59:26", "remaining_time": "6:43:17"}
{"current_steps": 243, "total_steps": 390, "loss": 0.4151, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "11:02:11", "remaining_time": "6:40:35"}
{"current_steps": 244, "total_steps": 390, "loss": 0.4336, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:05:01", "remaining_time": "6:37:55"}
{"current_steps": 245, "total_steps": 390, "loss": 0.4183, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:07:41", "remaining_time": "6:35:09"}
{"current_steps": 246, "total_steps": 390, "loss": 0.4332, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:10:17", "remaining_time": "6:32:22"}
{"current_steps": 247, "total_steps": 390, "loss": 0.4303, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:13:02", "remaining_time": "6:29:39"}
{"current_steps": 248, "total_steps": 390, "loss": 0.419, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:15:26", "remaining_time": "6:26:44"}
{"current_steps": 249, "total_steps": 390, "loss": 0.4321, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:18:23", "remaining_time": "6:24:09"}
{"current_steps": 250, "total_steps": 390, "loss": 0.4159, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:21:04", "remaining_time": "6:21:23"}
{"current_steps": 251, "total_steps": 390, "loss": 0.4287, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:23:47", "remaining_time": "6:18:40"}
{"current_steps": 252, "total_steps": 390, "loss": 0.4336, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:26:31", "remaining_time": "6:15:57"}
{"current_steps": 253, "total_steps": 390, "loss": 0.4266, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:29:16", "remaining_time": "6:13:14"}
{"current_steps": 254, "total_steps": 390, "loss": 0.4239, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:32:01", "remaining_time": "6:10:31"}
{"current_steps": 255, "total_steps": 390, "loss": 0.422, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:34:45", "remaining_time": "6:07:49"}
{"current_steps": 256, "total_steps": 390, "loss": 0.4232, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:37:38", "remaining_time": "6:05:10"}
{"current_steps": 257, "total_steps": 390, "loss": 0.4281, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:40:24", "remaining_time": "6:02:28"}
{"current_steps": 258, "total_steps": 390, "loss": 0.4366, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:43:17", "remaining_time": "5:59:49"}
{"current_steps": 259, "total_steps": 390, "loss": 0.4235, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:46:12", "remaining_time": "5:57:11"}
{"current_steps": 260, "total_steps": 390, "loss": 0.4243, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:49:01", "remaining_time": "5:54:30"}
{"current_steps": 261, "total_steps": 390, "loss": 0.4204, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:51:43", "remaining_time": "5:51:46"}
{"current_steps": 262, "total_steps": 390, "loss": 0.4162, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:54:31", "remaining_time": "5:49:04"}
{"current_steps": 263, "total_steps": 390, "loss": 0.4247, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:57:10", "remaining_time": "5:46:18"}
{"current_steps": 264, "total_steps": 390, "loss": 0.4078, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:59:46", "remaining_time": "5:43:31"}
{"current_steps": 265, "total_steps": 390, "loss": 0.4261, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "12:02:39", "remaining_time": "5:40:52"}
{"current_steps": 266, "total_steps": 390, "loss": 0.4328, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "12:05:25", "remaining_time": "5:38:10"}
{"current_steps": 267, "total_steps": 390, "loss": 0.4083, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:08:00", "remaining_time": "5:35:22"}
{"current_steps": 268, "total_steps": 390, "loss": 0.4207, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:10:35", "remaining_time": "5:32:34"}
{"current_steps": 269, "total_steps": 390, "loss": 0.424, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:13:12", "remaining_time": "5:29:48"}
{"current_steps": 270, "total_steps": 390, "loss": 0.4162, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:15:57", "remaining_time": "5:27:05"}
{"current_steps": 271, "total_steps": 390, "loss": 0.4178, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:18:45", "remaining_time": "5:24:23"}
{"current_steps": 272, "total_steps": 390, "loss": 0.406, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:21:17", "remaining_time": "5:21:35"}
{"current_steps": 273, "total_steps": 390, "loss": 0.4357, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:23:59", "remaining_time": "5:18:51"}
{"current_steps": 274, "total_steps": 390, "loss": 0.4262, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:26:50", "remaining_time": "5:16:10"}
{"current_steps": 275, "total_steps": 390, "loss": 0.4253, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:29:45", "remaining_time": "5:13:31"}
{"current_steps": 276, "total_steps": 390, "loss": 0.4173, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:32:19", "remaining_time": "5:10:44"}
{"current_steps": 277, "total_steps": 390, "loss": 0.4266, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:35:00", "remaining_time": "5:07:59"}
{"current_steps": 278, "total_steps": 390, "loss": 0.417, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:37:42", "remaining_time": "5:05:15"}
{"current_steps": 279, "total_steps": 390, "loss": 0.4246, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:40:25", "remaining_time": "5:02:32"}
{"current_steps": 280, "total_steps": 390, "loss": 0.4198, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:43:00", "remaining_time": "4:59:45"}
{"current_steps": 281, "total_steps": 390, "loss": 0.4365, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:45:41", "remaining_time": "4:57:00"}
{"current_steps": 282, "total_steps": 390, "loss": 0.4373, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:48:38", "remaining_time": "4:54:22"}
{"current_steps": 283, "total_steps": 390, "loss": 0.4205, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:51:22", "remaining_time": "4:51:38"}
{"current_steps": 284, "total_steps": 390, "loss": 0.4258, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:54:00", "remaining_time": "4:48:53"}
{"current_steps": 285, "total_steps": 390, "loss": 0.4303, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:56:54", "remaining_time": "4:46:13"}
{"current_steps": 286, "total_steps": 390, "loss": 0.4331, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:59:34", "remaining_time": "4:43:29"}
{"current_steps": 287, "total_steps": 390, "loss": 0.4066, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "13:02:14", "remaining_time": "4:40:44"}
{"current_steps": 288, "total_steps": 390, "loss": 0.4158, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "13:04:58", "remaining_time": "4:38:00"}
{"current_steps": 289, "total_steps": 390, "loss": 0.4184, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:07:39", "remaining_time": "4:35:16"}
{"current_steps": 290, "total_steps": 390, "loss": 0.424, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:10:30", "remaining_time": "4:32:35"}
{"current_steps": 291, "total_steps": 390, "loss": 0.4218, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:13:11", "remaining_time": "4:29:50"}
{"current_steps": 292, "total_steps": 390, "loss": 0.4243, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:15:51", "remaining_time": "4:27:06"}
{"current_steps": 293, "total_steps": 390, "loss": 0.4346, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:18:38", "remaining_time": "4:24:23"}
{"current_steps": 294, "total_steps": 390, "loss": 0.4214, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:21:26", "remaining_time": "4:21:41"}
{"current_steps": 295, "total_steps": 390, "loss": 0.4325, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:24:05", "remaining_time": "4:18:56"}
{"current_steps": 296, "total_steps": 390, "loss": 0.4148, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:26:43", "remaining_time": "4:16:11"}
{"current_steps": 297, "total_steps": 390, "loss": 0.423, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:29:19", "remaining_time": "4:13:25"}
{"current_steps": 298, "total_steps": 390, "loss": 0.4168, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:32:01", "remaining_time": "4:10:41"}
{"current_steps": 299, "total_steps": 390, "loss": 0.4266, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:34:39", "remaining_time": "4:07:56"}
{"current_steps": 300, "total_steps": 390, "loss": 0.4316, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:37:20", "remaining_time": "4:05:12"}
{"current_steps": 301, "total_steps": 390, "loss": 0.4249, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:40:00", "remaining_time": "4:02:27"}
{"current_steps": 302, "total_steps": 390, "loss": 0.4198, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:42:44", "remaining_time": "3:59:44"}
{"current_steps": 303, "total_steps": 390, "loss": 0.433, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:45:25", "remaining_time": "3:57:00"}
{"current_steps": 304, "total_steps": 390, "loss": 0.4226, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:48:18", "remaining_time": "3:54:19"}
{"current_steps": 305, "total_steps": 390, "loss": 0.4237, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:51:01", "remaining_time": "3:51:35"}
{"current_steps": 306, "total_steps": 390, "loss": 0.4305, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:53:45", "remaining_time": "3:48:52"}
{"current_steps": 307, "total_steps": 390, "loss": 0.4376, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:56:24", "remaining_time": "3:46:07"}
{"current_steps": 308, "total_steps": 390, "loss": 0.4164, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:59:07", "remaining_time": "3:43:24"}
{"current_steps": 309, "total_steps": 390, "loss": 0.4235, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "14:01:45", "remaining_time": "3:40:39"}
{"current_steps": 310, "total_steps": 390, "loss": 0.4207, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "14:04:23", "remaining_time": "3:37:54"}
{"current_steps": 311, "total_steps": 390, "loss": 0.4223, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:07:01", "remaining_time": "3:35:09"}
{"current_steps": 312, "total_steps": 390, "loss": 0.4352, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:38", "remaining_time": "3:32:24"}
{"current_steps": 313, "total_steps": 390, "loss": 0.401, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:14", "remaining_time": "3:29:54"}
{"current_steps": 314, "total_steps": 390, "loss": 0.3838, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:42", "remaining_time": "3:27:06"}