trainer_log.jsonl

{"current_steps": 10, "total_steps": 4530, "loss": 1.6257, "reward": null, "learning_rate": 4.999939881018594e-05, "epoch": 0.01, "percentage": 0.22, "elapsed_time": "0:00:48", "remaining_time": "6:04:04"}
{"current_steps": 20, "total_steps": 4530, "loss": 1.6388, "reward": null, "learning_rate": 4.999759526965809e-05, "epoch": 0.01, "percentage": 0.44, "elapsed_time": "0:01:33", "remaining_time": "5:49:40"}
{"current_steps": 30, "total_steps": 4530, "loss": 1.5034, "reward": null, "learning_rate": 4.999458946515808e-05, "epoch": 0.02, "percentage": 0.66, "elapsed_time": "0:02:18", "remaining_time": "5:46:24"}
{"current_steps": 40, "total_steps": 4530, "loss": 1.5761, "reward": null, "learning_rate": 4.999038154125061e-05, "epoch": 0.03, "percentage": 0.88, "elapsed_time": "0:03:01", "remaining_time": "5:40:03"}
{"current_steps": 50, "total_steps": 4530, "loss": 1.5066, "reward": null, "learning_rate": 4.998497170031657e-05, "epoch": 0.03, "percentage": 1.1, "elapsed_time": "0:03:42", "remaining_time": "5:32:10"}
{"current_steps": 60, "total_steps": 4530, "loss": 1.5738, "reward": null, "learning_rate": 4.997836020254328e-05, "epoch": 0.04, "percentage": 1.32, "elapsed_time": "0:04:24", "remaining_time": "5:28:48"}
{"current_steps": 70, "total_steps": 4530, "loss": 1.4921, "reward": null, "learning_rate": 4.9970547365911925e-05, "epoch": 0.05, "percentage": 1.55, "elapsed_time": "0:05:10", "remaining_time": "5:29:44"}
{"current_steps": 80, "total_steps": 4530, "loss": 1.4508, "reward": null, "learning_rate": 4.996153356618233e-05, "epoch": 0.05, "percentage": 1.77, "elapsed_time": "0:05:55", "remaining_time": "5:29:27"}
{"current_steps": 90, "total_steps": 4530, "loss": 1.4714, "reward": null, "learning_rate": 4.995131923687488e-05, "epoch": 0.06, "percentage": 1.99, "elapsed_time": "0:06:39", "remaining_time": "5:28:16"}
{"current_steps": 100, "total_steps": 4530, "loss": 1.494, "reward": null, "learning_rate": 4.9939904869249616e-05, "epoch": 0.07, "percentage": 2.21, "elapsed_time": "0:07:23", "remaining_time": "5:27:38"}
{"current_steps": 110, "total_steps": 4530, "loss": 1.4934, "reward": null, "learning_rate": 4.992729101228267e-05, "epoch": 0.07, "percentage": 2.43, "elapsed_time": "0:08:27", "remaining_time": "5:39:45"}
{"current_steps": 120, "total_steps": 4530, "loss": 1.4789, "reward": null, "learning_rate": 4.991347827263982e-05, "epoch": 0.08, "percentage": 2.65, "elapsed_time": "0:09:09", "remaining_time": "5:36:30"}
{"current_steps": 130, "total_steps": 4530, "loss": 1.4511, "reward": null, "learning_rate": 4.9898467314647356e-05, "epoch": 0.09, "percentage": 2.87, "elapsed_time": "0:09:52", "remaining_time": "5:34:17"}
{"current_steps": 140, "total_steps": 4530, "loss": 1.4876, "reward": null, "learning_rate": 4.9882258860260065e-05, "epoch": 0.09, "percentage": 3.09, "elapsed_time": "0:10:35", "remaining_time": "5:32:00"}
{"current_steps": 150, "total_steps": 4530, "loss": 1.5124, "reward": null, "learning_rate": 4.9864853689026556e-05, "epoch": 0.1, "percentage": 3.31, "elapsed_time": "0:11:18", "remaining_time": "5:30:00"}
{"current_steps": 160, "total_steps": 4530, "loss": 1.4772, "reward": null, "learning_rate": 4.984625263805178e-05, "epoch": 0.11, "percentage": 3.53, "elapsed_time": "0:12:00", "remaining_time": "5:28:04"}
{"current_steps": 170, "total_steps": 4530, "loss": 1.436, "reward": null, "learning_rate": 4.982645660195671e-05, "epoch": 0.11, "percentage": 3.75, "elapsed_time": "0:12:44", "remaining_time": "5:26:50"}
{"current_steps": 180, "total_steps": 4530, "loss": 1.4377, "reward": null, "learning_rate": 4.9805466532835376e-05, "epoch": 0.12, "percentage": 3.97, "elapsed_time": "0:13:26", "remaining_time": "5:24:57"}
{"current_steps": 190, "total_steps": 4530, "loss": 1.438, "reward": null, "learning_rate": 4.978328344020904e-05, "epoch": 0.13, "percentage": 4.19, "elapsed_time": "0:14:10", "remaining_time": "5:23:46"}
{"current_steps": 200, "total_steps": 4530, "loss": 1.4448, "reward": null, "learning_rate": 4.975990839097764e-05, "epoch": 0.13, "percentage": 4.42, "elapsed_time": "0:14:52", "remaining_time": "5:22:08"}
{"current_steps": 210, "total_steps": 4530, "loss": 1.452, "reward": null, "learning_rate": 4.973534250936851e-05, "epoch": 0.14, "percentage": 4.64, "elapsed_time": "0:15:58", "remaining_time": "5:28:29"}
{"current_steps": 220, "total_steps": 4530, "loss": 1.4813, "reward": null, "learning_rate": 4.970958697688226e-05, "epoch": 0.15, "percentage": 4.86, "elapsed_time": "0:16:42", "remaining_time": "5:27:26"}
{"current_steps": 230, "total_steps": 4530, "loss": 1.41, "reward": null, "learning_rate": 4.9682643032235996e-05, "epoch": 0.15, "percentage": 5.08, "elapsed_time": "0:17:26", "remaining_time": "5:26:12"}
{"current_steps": 240, "total_steps": 4530, "loss": 1.428, "reward": null, "learning_rate": 4.965451197130373e-05, "epoch": 0.16, "percentage": 5.3, "elapsed_time": "0:18:12", "remaining_time": "5:25:21"}
{"current_steps": 250, "total_steps": 4530, "loss": 1.463, "reward": null, "learning_rate": 4.9625195147054034e-05, "epoch": 0.17, "percentage": 5.52, "elapsed_time": "0:18:56", "remaining_time": "5:24:16"}
{"current_steps": 260, "total_steps": 4530, "loss": 1.4821, "reward": null, "learning_rate": 4.9594693969485006e-05, "epoch": 0.17, "percentage": 5.74, "elapsed_time": "0:19:39", "remaining_time": "5:22:51"}
{"current_steps": 270, "total_steps": 4530, "loss": 1.4855, "reward": null, "learning_rate": 4.956300990555643e-05, "epoch": 0.18, "percentage": 5.96, "elapsed_time": "0:20:25", "remaining_time": "5:22:10"}
{"current_steps": 280, "total_steps": 4530, "loss": 1.4322, "reward": null, "learning_rate": 4.9530144479119215e-05, "epoch": 0.19, "percentage": 6.18, "elapsed_time": "0:21:09", "remaining_time": "5:21:15"}
{"current_steps": 290, "total_steps": 4530, "loss": 1.4397, "reward": null, "learning_rate": 4.9496099270842145e-05, "epoch": 0.19, "percentage": 6.4, "elapsed_time": "0:21:51", "remaining_time": "5:19:40"}
{"current_steps": 300, "total_steps": 4530, "loss": 1.4107, "reward": null, "learning_rate": 4.9460875918135804e-05, "epoch": 0.2, "percentage": 6.62, "elapsed_time": "0:22:35", "remaining_time": "5:18:27"}
{"current_steps": 310, "total_steps": 4530, "loss": 1.4722, "reward": null, "learning_rate": 4.942447611507386e-05, "epoch": 0.21, "percentage": 6.84, "elapsed_time": "0:23:37", "remaining_time": "5:21:34"}
{"current_steps": 320, "total_steps": 4530, "loss": 1.423, "reward": null, "learning_rate": 4.938690161231159e-05, "epoch": 0.21, "percentage": 7.06, "elapsed_time": "0:24:21", "remaining_time": "5:20:30"}
{"current_steps": 330, "total_steps": 4530, "loss": 1.4288, "reward": null, "learning_rate": 4.934815421700165e-05, "epoch": 0.22, "percentage": 7.28, "elapsed_time": "0:25:05", "remaining_time": "5:19:25"}
{"current_steps": 340, "total_steps": 4530, "loss": 1.4294, "reward": null, "learning_rate": 4.9308235792707194e-05, "epoch": 0.23, "percentage": 7.51, "elapsed_time": "0:25:51", "remaining_time": "5:18:43"}
{"current_steps": 350, "total_steps": 4530, "loss": 1.4233, "reward": null, "learning_rate": 4.9267148259312224e-05, "epoch": 0.23, "percentage": 7.73, "elapsed_time": "0:26:38", "remaining_time": "5:18:12"}
{"current_steps": 360, "total_steps": 4530, "loss": 1.4553, "reward": null, "learning_rate": 4.9224893592929275e-05, "epoch": 0.24, "percentage": 7.95, "elapsed_time": "0:27:19", "remaining_time": "5:16:36"}
{"current_steps": 370, "total_steps": 4530, "loss": 1.4206, "reward": null, "learning_rate": 4.9181473825804346e-05, "epoch": 0.24, "percentage": 8.17, "elapsed_time": "0:28:03", "remaining_time": "5:15:24"}
{"current_steps": 380, "total_steps": 4530, "loss": 1.442, "reward": null, "learning_rate": 4.913689104621917e-05, "epoch": 0.25, "percentage": 8.39, "elapsed_time": "0:28:48", "remaining_time": "5:14:32"}
{"current_steps": 390, "total_steps": 4530, "loss": 1.4668, "reward": null, "learning_rate": 4.909114739839079e-05, "epoch": 0.26, "percentage": 8.61, "elapsed_time": "0:29:33", "remaining_time": "5:13:43"}
{"current_steps": 400, "total_steps": 4530, "loss": 1.4439, "reward": null, "learning_rate": 4.9044245082368415e-05, "epoch": 0.26, "percentage": 8.83, "elapsed_time": "0:30:18", "remaining_time": "5:12:51"}
{"current_steps": 410, "total_steps": 4530, "loss": 1.4224, "reward": null, "learning_rate": 4.8996186353927606e-05, "epoch": 0.27, "percentage": 9.05, "elapsed_time": "0:31:21", "remaining_time": "5:15:01"}
{"current_steps": 420, "total_steps": 4530, "loss": 1.4084, "reward": null, "learning_rate": 4.894697352446182e-05, "epoch": 0.28, "percentage": 9.27, "elapsed_time": "0:32:11", "remaining_time": "5:14:58"}
{"current_steps": 430, "total_steps": 4530, "loss": 1.4398, "reward": null, "learning_rate": 4.889660896087119e-05, "epoch": 0.28, "percentage": 9.49, "elapsed_time": "0:32:54", "remaining_time": "5:13:50"}
{"current_steps": 440, "total_steps": 4530, "loss": 1.4268, "reward": null, "learning_rate": 4.884509508544874e-05, "epoch": 0.29, "percentage": 9.71, "elapsed_time": "0:33:38", "remaining_time": "5:12:44"}
{"current_steps": 450, "total_steps": 4530, "loss": 1.4522, "reward": null, "learning_rate": 4.879243437576383e-05, "epoch": 0.3, "percentage": 9.93, "elapsed_time": "0:34:20", "remaining_time": "5:11:24"}
{"current_steps": 460, "total_steps": 4530, "loss": 1.4222, "reward": null, "learning_rate": 4.8738629364543045e-05, "epoch": 0.3, "percentage": 10.15, "elapsed_time": "0:35:03", "remaining_time": "5:10:09"}
{"current_steps": 470, "total_steps": 4530, "loss": 1.4956, "reward": null, "learning_rate": 4.8683682639548365e-05, "epoch": 0.31, "percentage": 10.38, "elapsed_time": "0:35:45", "remaining_time": "5:08:51"}
{"current_steps": 480, "total_steps": 4530, "loss": 1.4538, "reward": null, "learning_rate": 4.862759684345269e-05, "epoch": 0.32, "percentage": 10.6, "elapsed_time": "0:36:28", "remaining_time": "5:07:48"}
{"current_steps": 490, "total_steps": 4530, "loss": 1.3748, "reward": null, "learning_rate": 4.857037467371278e-05, "epoch": 0.32, "percentage": 10.82, "elapsed_time": "0:37:11", "remaining_time": "5:06:38"}
{"current_steps": 500, "total_steps": 4530, "loss": 1.4127, "reward": null, "learning_rate": 4.8512018882439475e-05, "epoch": 0.33, "percentage": 11.04, "elapsed_time": "0:37:56", "remaining_time": "5:05:45"}
{"current_steps": 510, "total_steps": 4530, "loss": 1.3795, "reward": null, "learning_rate": 4.8452532276265364e-05, "epoch": 0.34, "percentage": 11.26, "elapsed_time": "0:39:03", "remaining_time": "5:07:49"}
{"current_steps": 520, "total_steps": 4530, "loss": 1.4414, "reward": null, "learning_rate": 4.8391917716209765e-05, "epoch": 0.34, "percentage": 11.48, "elapsed_time": "0:39:45", "remaining_time": "5:06:35"}
{"current_steps": 530, "total_steps": 4530, "loss": 1.4242, "reward": null, "learning_rate": 4.833017811754119e-05, "epoch": 0.35, "percentage": 11.7, "elapsed_time": "0:40:27", "remaining_time": "5:05:19"}
{"current_steps": 540, "total_steps": 4530, "loss": 1.4196, "reward": null, "learning_rate": 4.8267316449637054e-05, "epoch": 0.36, "percentage": 11.92, "elapsed_time": "0:41:09", "remaining_time": "5:04:08"}
{"current_steps": 550, "total_steps": 4530, "loss": 1.389, "reward": null, "learning_rate": 4.820333573584091e-05, "epoch": 0.36, "percentage": 12.14, "elapsed_time": "0:41:52", "remaining_time": "5:03:02"}
{"current_steps": 560, "total_steps": 4530, "loss": 1.4597, "reward": null, "learning_rate": 4.813823905331704e-05, "epoch": 0.37, "percentage": 12.36, "elapsed_time": "0:42:36", "remaining_time": "5:02:04"}
{"current_steps": 570, "total_steps": 4530, "loss": 1.4275, "reward": null, "learning_rate": 4.8072029532902426e-05, "epoch": 0.38, "percentage": 12.58, "elapsed_time": "0:43:22", "remaining_time": "5:01:23"}
{"current_steps": 580, "total_steps": 4530, "loss": 1.4364, "reward": null, "learning_rate": 4.800471035895624e-05, "epoch": 0.38, "percentage": 12.8, "elapsed_time": "0:44:08", "remaining_time": "5:00:38"}
{"current_steps": 590, "total_steps": 4530, "loss": 1.4366, "reward": null, "learning_rate": 4.7936284769206584e-05, "epoch": 0.39, "percentage": 13.02, "elapsed_time": "0:44:49", "remaining_time": "4:59:23"}
{"current_steps": 600, "total_steps": 4530, "loss": 1.5086, "reward": null, "learning_rate": 4.786675605459487e-05, "epoch": 0.4, "percentage": 13.25, "elapsed_time": "0:45:33", "remaining_time": "4:58:27"}
{"current_steps": 610, "total_steps": 4530, "loss": 1.4309, "reward": null, "learning_rate": 4.779612755911752e-05, "epoch": 0.4, "percentage": 13.47, "elapsed_time": "0:46:38", "remaining_time": "4:59:43"}
{"current_steps": 620, "total_steps": 4530, "loss": 1.4102, "reward": null, "learning_rate": 4.772440267966508e-05, "epoch": 0.41, "percentage": 13.69, "elapsed_time": "0:47:21", "remaining_time": "4:58:40"}
{"current_steps": 630, "total_steps": 4530, "loss": 1.4035, "reward": null, "learning_rate": 4.76515848658589e-05, "epoch": 0.42, "percentage": 13.91, "elapsed_time": "0:48:05", "remaining_time": "4:57:42"}
{"current_steps": 640, "total_steps": 4530, "loss": 1.4478, "reward": null, "learning_rate": 4.7577677619885234e-05, "epoch": 0.42, "percentage": 14.13, "elapsed_time": "0:48:45", "remaining_time": "4:56:24"}
{"current_steps": 650, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 4.7502684496326746e-05, "epoch": 0.43, "percentage": 14.35, "elapsed_time": "0:49:28", "remaining_time": "4:55:21"}
{"current_steps": 660, "total_steps": 4530, "loss": 1.4042, "reward": null, "learning_rate": 4.7426609101991605e-05, "epoch": 0.44, "percentage": 14.57, "elapsed_time": "0:50:13", "remaining_time": "4:54:30"}
{"current_steps": 670, "total_steps": 4530, "loss": 1.4216, "reward": null, "learning_rate": 4.734945509573997e-05, "epoch": 0.44, "percentage": 14.79, "elapsed_time": "0:50:55", "remaining_time": "4:53:21"}
{"current_steps": 680, "total_steps": 4530, "loss": 1.4786, "reward": null, "learning_rate": 4.727122618830808e-05, "epoch": 0.45, "percentage": 15.01, "elapsed_time": "0:51:41", "remaining_time": "4:52:40"}
{"current_steps": 690, "total_steps": 4530, "loss": 1.4414, "reward": null, "learning_rate": 4.719192614212969e-05, "epoch": 0.46, "percentage": 15.23, "elapsed_time": "0:52:24", "remaining_time": "4:51:40"}
{"current_steps": 700, "total_steps": 4530, "loss": 1.493, "reward": null, "learning_rate": 4.711155877115523e-05, "epoch": 0.46, "percentage": 15.45, "elapsed_time": "0:53:05", "remaining_time": "4:50:29"}
{"current_steps": 710, "total_steps": 4530, "loss": 1.4078, "reward": null, "learning_rate": 4.703012794066827e-05, "epoch": 0.47, "percentage": 15.67, "elapsed_time": "0:54:12", "remaining_time": "4:51:37"}
{"current_steps": 720, "total_steps": 4530, "loss": 1.4539, "reward": null, "learning_rate": 4.694763756709967e-05, "epoch": 0.48, "percentage": 15.89, "elapsed_time": "0:54:58", "remaining_time": "4:50:53"}
{"current_steps": 730, "total_steps": 4530, "loss": 1.4458, "reward": null, "learning_rate": 4.6864091617839235e-05, "epoch": 0.48, "percentage": 16.11, "elapsed_time": "0:55:42", "remaining_time": "4:49:59"}
{"current_steps": 740, "total_steps": 4530, "loss": 1.4001, "reward": null, "learning_rate": 4.677949411104485e-05, "epoch": 0.49, "percentage": 16.34, "elapsed_time": "0:56:25", "remaining_time": "4:49:01"}
{"current_steps": 750, "total_steps": 4530, "loss": 1.433, "reward": null, "learning_rate": 4.669384911544927e-05, "epoch": 0.5, "percentage": 16.56, "elapsed_time": "0:57:09", "remaining_time": "4:48:06"}
{"current_steps": 760, "total_steps": 4530, "loss": 1.4323, "reward": null, "learning_rate": 4.660716075016442e-05, "epoch": 0.5, "percentage": 16.78, "elapsed_time": "0:57:56", "remaining_time": "4:47:24"}
{"current_steps": 770, "total_steps": 4530, "loss": 1.4052, "reward": null, "learning_rate": 4.6519433184483245e-05, "epoch": 0.51, "percentage": 17.0, "elapsed_time": "0:58:42", "remaining_time": "4:46:39"}
{"current_steps": 780, "total_steps": 4530, "loss": 1.4021, "reward": null, "learning_rate": 4.6430670637679295e-05, "epoch": 0.52, "percentage": 17.22, "elapsed_time": "0:59:27", "remaining_time": "4:45:52"}
{"current_steps": 790, "total_steps": 4530, "loss": 1.4049, "reward": null, "learning_rate": 4.634087737880367e-05, "epoch": 0.52, "percentage": 17.44, "elapsed_time": "1:00:12", "remaining_time": "4:45:03"}
{"current_steps": 800, "total_steps": 4530, "loss": 1.3701, "reward": null, "learning_rate": 4.625005772647979e-05, "epoch": 0.53, "percentage": 17.66, "elapsed_time": "1:00:57", "remaining_time": "4:44:14"}
{"current_steps": 810, "total_steps": 4530, "loss": 1.4209, "reward": null, "learning_rate": 4.615821604869564e-05, "epoch": 0.54, "percentage": 17.88, "elapsed_time": "1:02:00", "remaining_time": "4:44:45"}
{"current_steps": 820, "total_steps": 4530, "loss": 1.4373, "reward": null, "learning_rate": 4.606535676259372e-05, "epoch": 0.54, "percentage": 18.1, "elapsed_time": "1:02:43", "remaining_time": "4:43:47"}
{"current_steps": 830, "total_steps": 4530, "loss": 1.4913, "reward": null, "learning_rate": 4.597148433425857e-05, "epoch": 0.55, "percentage": 18.32, "elapsed_time": "1:03:26", "remaining_time": "4:42:48"}
{"current_steps": 840, "total_steps": 4530, "loss": 1.434, "reward": null, "learning_rate": 4.587660327850203e-05, "epoch": 0.56, "percentage": 18.54, "elapsed_time": "1:04:13", "remaining_time": "4:42:06"}
{"current_steps": 850, "total_steps": 4530, "loss": 1.3932, "reward": null, "learning_rate": 4.578071815864602e-05, "epoch": 0.56, "percentage": 18.76, "elapsed_time": "1:04:58", "remaining_time": "4:41:18"}
{"current_steps": 860, "total_steps": 4530, "loss": 1.4232, "reward": null, "learning_rate": 4.5683833586303157e-05, "epoch": 0.57, "percentage": 18.98, "elapsed_time": "1:05:41", "remaining_time": "4:40:19"}
{"current_steps": 870, "total_steps": 4530, "loss": 1.3651, "reward": null, "learning_rate": 4.5585954221154856e-05, "epoch": 0.58, "percentage": 19.21, "elapsed_time": "1:06:24", "remaining_time": "4:39:23"}
{"current_steps": 880, "total_steps": 4530, "loss": 1.4009, "reward": null, "learning_rate": 4.548708477072733e-05, "epoch": 0.58, "percentage": 19.43, "elapsed_time": "1:07:10", "remaining_time": "4:38:38"}
{"current_steps": 890, "total_steps": 4530, "loss": 1.428, "reward": null, "learning_rate": 4.5387229990165073e-05, "epoch": 0.59, "percentage": 19.65, "elapsed_time": "1:07:55", "remaining_time": "4:37:49"}
{"current_steps": 900, "total_steps": 4530, "loss": 1.413, "reward": null, "learning_rate": 4.528639468200226e-05, "epoch": 0.6, "percentage": 19.87, "elapsed_time": "1:08:40", "remaining_time": "4:36:57"}
{"current_steps": 910, "total_steps": 4530, "loss": 1.4328, "reward": null, "learning_rate": 4.51845836959317e-05, "epoch": 0.6, "percentage": 20.09, "elapsed_time": "1:09:42", "remaining_time": "4:37:19"}
{"current_steps": 920, "total_steps": 4530, "loss": 1.4262, "reward": null, "learning_rate": 4.508180192857162e-05, "epoch": 0.61, "percentage": 20.31, "elapsed_time": "1:10:27", "remaining_time": "4:36:28"}
{"current_steps": 930, "total_steps": 4530, "loss": 1.3677, "reward": null, "learning_rate": 4.497805432323015e-05, "epoch": 0.62, "percentage": 20.53, "elapsed_time": "1:11:12", "remaining_time": "4:35:39"}
{"current_steps": 940, "total_steps": 4530, "loss": 1.4546, "reward": null, "learning_rate": 4.487334586966756e-05, "epoch": 0.62, "percentage": 20.75, "elapsed_time": "1:11:54", "remaining_time": "4:34:37"}
{"current_steps": 950, "total_steps": 4530, "loss": 1.4011, "reward": null, "learning_rate": 4.476768160385632e-05, "epoch": 0.63, "percentage": 20.97, "elapsed_time": "1:12:39", "remaining_time": "4:33:49"}
{"current_steps": 960, "total_steps": 4530, "loss": 1.441, "reward": null, "learning_rate": 4.466106660773885e-05, "epoch": 0.64, "percentage": 21.19, "elapsed_time": "1:13:22", "remaining_time": "4:32:50"}
{"current_steps": 970, "total_steps": 4530, "loss": 1.3946, "reward": null, "learning_rate": 4.4553506008983126e-05, "epoch": 0.64, "percentage": 21.41, "elapsed_time": "1:14:06", "remaining_time": "4:31:57"}
{"current_steps": 980, "total_steps": 4530, "loss": 1.4478, "reward": null, "learning_rate": 4.4445004980736064e-05, "epoch": 0.65, "percentage": 21.63, "elapsed_time": "1:14:47", "remaining_time": "4:30:55"}
{"current_steps": 990, "total_steps": 4530, "loss": 1.4093, "reward": null, "learning_rate": 4.43355687413747e-05, "epoch": 0.66, "percentage": 21.85, "elapsed_time": "1:15:30", "remaining_time": "4:29:58"}
{"current_steps": 1000, "total_steps": 4530, "loss": 1.4285, "reward": null, "learning_rate": 4.4225202554255227e-05, "epoch": 0.66, "percentage": 22.08, "elapsed_time": "1:16:14", "remaining_time": "4:29:06"}
{"current_steps": 1010, "total_steps": 4530, "loss": 1.3971, "reward": null, "learning_rate": 4.411391172745984e-05, "epoch": 0.67, "percentage": 22.3, "elapsed_time": "1:17:17", "remaining_time": "4:29:20"}
{"current_steps": 1020, "total_steps": 4530, "loss": 1.4024, "reward": null, "learning_rate": 4.4001701613541456e-05, "epoch": 0.68, "percentage": 22.52, "elapsed_time": "1:18:00", "remaining_time": "4:28:26"}
{"current_steps": 1030, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 4.388857760926629e-05, "epoch": 0.68, "percentage": 22.74, "elapsed_time": "1:18:45", "remaining_time": "4:27:37"}
{"current_steps": 1040, "total_steps": 4530, "loss": 1.3943, "reward": null, "learning_rate": 4.3774545155354254e-05, "epoch": 0.69, "percentage": 22.96, "elapsed_time": "1:19:31", "remaining_time": "4:26:53"}
{"current_steps": 1050, "total_steps": 4530, "loss": 1.4586, "reward": null, "learning_rate": 4.3659609736217344e-05, "epoch": 0.7, "percentage": 23.18, "elapsed_time": "1:20:18", "remaining_time": "4:26:09"}
{"current_steps": 1060, "total_steps": 4530, "loss": 1.4178, "reward": null, "learning_rate": 4.354377687969581e-05, "epoch": 0.7, "percentage": 23.4, "elapsed_time": "1:21:00", "remaining_time": "4:25:10"}
{"current_steps": 1070, "total_steps": 4530, "loss": 1.4454, "reward": null, "learning_rate": 4.342705215679232e-05, "epoch": 0.71, "percentage": 23.62, "elapsed_time": "1:21:44", "remaining_time": "4:24:18"}
{"current_steps": 1080, "total_steps": 4530, "loss": 1.3769, "reward": null, "learning_rate": 4.330944118140407e-05, "epoch": 0.72, "percentage": 23.84, "elapsed_time": "1:22:33", "remaining_time": "4:23:44"}
{"current_steps": 1090, "total_steps": 4530, "loss": 1.3912, "reward": null, "learning_rate": 4.3190949610052645e-05, "epoch": 0.72, "percentage": 24.06, "elapsed_time": "1:23:18", "remaining_time": "4:22:53"}
{"current_steps": 1100, "total_steps": 4530, "loss": 1.4116, "reward": null, "learning_rate": 4.3071583141612135e-05, "epoch": 0.73, "percentage": 24.28, "elapsed_time": "1:24:01", "remaining_time": "4:21:58"}
{"current_steps": 1110, "total_steps": 4530, "loss": 1.4019, "reward": null, "learning_rate": 4.295134751703493e-05, "epoch": 0.73, "percentage": 24.5, "elapsed_time": "1:25:01", "remaining_time": "4:21:59"}
{"current_steps": 1120, "total_steps": 4530, "loss": 1.378, "reward": null, "learning_rate": 4.283024851907565e-05, "epoch": 0.74, "percentage": 24.72, "elapsed_time": "1:25:46", "remaining_time": "4:21:09"}
{"current_steps": 1130, "total_steps": 4530, "loss": 1.432, "reward": null, "learning_rate": 4.2708291972013026e-05, "epoch": 0.75, "percentage": 24.94, "elapsed_time": "1:26:31", "remaining_time": "4:20:19"}
{"current_steps": 1140, "total_steps": 4530, "loss": 1.4531, "reward": null, "learning_rate": 4.2585483741369755e-05, "epoch": 0.75, "percentage": 25.17, "elapsed_time": "1:27:13", "remaining_time": "4:19:24"}
{"current_steps": 1150, "total_steps": 4530, "loss": 1.4455, "reward": null, "learning_rate": 4.2461829733630435e-05, "epoch": 0.76, "percentage": 25.39, "elapsed_time": "1:27:58", "remaining_time": "4:18:34"}
{"current_steps": 1160, "total_steps": 4530, "loss": 1.4081, "reward": null, "learning_rate": 4.233733589595746e-05, "epoch": 0.77, "percentage": 25.61, "elapsed_time": "1:28:40", "remaining_time": "4:17:38"}
{"current_steps": 1170, "total_steps": 4530, "loss": 1.4344, "reward": null, "learning_rate": 4.2212008215905e-05, "epoch": 0.77, "percentage": 25.83, "elapsed_time": "1:29:22", "remaining_time": "4:16:38"}
{"current_steps": 1180, "total_steps": 4530, "loss": 1.3935, "reward": null, "learning_rate": 4.208585272113102e-05, "epoch": 0.78, "percentage": 26.05, "elapsed_time": "1:30:04", "remaining_time": "4:15:43"}
{"current_steps": 1190, "total_steps": 4530, "loss": 1.4161, "reward": null, "learning_rate": 4.195887547910741e-05, "epoch": 0.79, "percentage": 26.27, "elapsed_time": "1:30:49", "remaining_time": "4:14:54"}
{"current_steps": 1200, "total_steps": 4530, "loss": 1.4185, "reward": null, "learning_rate": 4.1831082596828106e-05, "epoch": 0.79, "percentage": 26.49, "elapsed_time": "1:31:31", "remaining_time": "4:13:59"}
{"current_steps": 1210, "total_steps": 4530, "loss": 1.3714, "reward": null, "learning_rate": 4.1702480220515475e-05, "epoch": 0.8, "percentage": 26.71, "elapsed_time": "1:32:38", "remaining_time": "4:14:10"}
{"current_steps": 1220, "total_steps": 4530, "loss": 1.4062, "reward": null, "learning_rate": 4.157307453532457e-05, "epoch": 0.81, "percentage": 26.93, "elapsed_time": "1:33:23", "remaining_time": "4:13:23"}
{"current_steps": 1230, "total_steps": 4530, "loss": 1.4007, "reward": null, "learning_rate": 4.144287176504582e-05, "epoch": 0.81, "percentage": 27.15, "elapsed_time": "1:34:06", "remaining_time": "4:12:29"}
{"current_steps": 1240, "total_steps": 4530, "loss": 1.4153, "reward": null, "learning_rate": 4.131187817180554e-05, "epoch": 0.82, "percentage": 27.37, "elapsed_time": "1:34:51", "remaining_time": "4:11:41"}
{"current_steps": 1250, "total_steps": 4530, "loss": 1.3619, "reward": null, "learning_rate": 4.118010005576485e-05, "epoch": 0.83, "percentage": 27.59, "elapsed_time": "1:35:34", "remaining_time": "4:10:48"}
{"current_steps": 1260, "total_steps": 4530, "loss": 1.507, "reward": null, "learning_rate": 4.104754375481664e-05, "epoch": 0.83, "percentage": 27.81, "elapsed_time": "1:36:17", "remaining_time": "4:09:53"}
{"current_steps": 1270, "total_steps": 4530, "loss": 1.4487, "reward": null, "learning_rate": 4.0914215644280754e-05, "epoch": 0.84, "percentage": 28.04, "elapsed_time": "1:36:58", "remaining_time": "4:08:55"}
{"current_steps": 1280, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 4.0780122136597323e-05, "epoch": 0.85, "percentage": 28.26, "elapsed_time": "1:37:42", "remaining_time": "4:08:04"}
{"current_steps": 1290, "total_steps": 4530, "loss": 1.3994, "reward": null, "learning_rate": 4.064526968101844e-05, "epoch": 0.85, "percentage": 28.48, "elapsed_time": "1:38:23", "remaining_time": "4:07:07"}
{"current_steps": 1300, "total_steps": 4530, "loss": 1.4285, "reward": null, "learning_rate": 4.050966476329793e-05, "epoch": 0.86, "percentage": 28.7, "elapsed_time": "1:39:06", "remaining_time": "4:06:14"}
{"current_steps": 1310, "total_steps": 4530, "loss": 1.4562, "reward": null, "learning_rate": 4.037331390537939e-05, "epoch": 0.87, "percentage": 28.92, "elapsed_time": "1:40:10", "remaining_time": "4:06:13"}
{"current_steps": 1320, "total_steps": 4530, "loss": 1.4202, "reward": null, "learning_rate": 4.023622366508261e-05, "epoch": 0.87, "percentage": 29.14, "elapsed_time": "1:40:53", "remaining_time": "4:05:22"}
{"current_steps": 1330, "total_steps": 4530, "loss": 1.381, "reward": null, "learning_rate": 4.0098400635788035e-05, "epoch": 0.88, "percentage": 29.36, "elapsed_time": "1:41:37", "remaining_time": "4:04:30"}
{"current_steps": 1340, "total_steps": 4530, "loss": 1.4656, "reward": null, "learning_rate": 3.99598514461198e-05, "epoch": 0.89, "percentage": 29.58, "elapsed_time": "1:42:16", "remaining_time": "4:03:27"}
{"current_steps": 1350, "total_steps": 4530, "loss": 1.4094, "reward": null, "learning_rate": 3.9820582759626825e-05, "epoch": 0.89, "percentage": 29.8, "elapsed_time": "1:43:03", "remaining_time": "4:02:45"}
{"current_steps": 1360, "total_steps": 4530, "loss": 1.4183, "reward": null, "learning_rate": 3.968060127446236e-05, "epoch": 0.9, "percentage": 30.02, "elapsed_time": "1:43:46", "remaining_time": "4:01:53"}
{"current_steps": 1370, "total_steps": 4530, "loss": 1.411, "reward": null, "learning_rate": 3.953991372306186e-05, "epoch": 0.91, "percentage": 30.24, "elapsed_time": "1:44:29", "remaining_time": "4:01:00"}
{"current_steps": 1380, "total_steps": 4530, "loss": 1.418, "reward": null, "learning_rate": 3.9398526871819154e-05, "epoch": 0.91, "percentage": 30.46, "elapsed_time": "1:45:13", "remaining_time": "4:00:10"}
{"current_steps": 1390, "total_steps": 4530, "loss": 1.4751, "reward": null, "learning_rate": 3.925644752076101e-05, "epoch": 0.92, "percentage": 30.68, "elapsed_time": "1:45:55", "remaining_time": "3:59:17"}
{"current_steps": 1400, "total_steps": 4530, "loss": 1.4246, "reward": null, "learning_rate": 3.911368250322014e-05, "epoch": 0.93, "percentage": 30.91, "elapsed_time": "1:46:39", "remaining_time": "3:58:27"}
{"current_steps": 1410, "total_steps": 4530, "loss": 1.4102, "reward": null, "learning_rate": 3.897023868550649e-05, "epoch": 0.93, "percentage": 31.13, "elapsed_time": "1:47:40", "remaining_time": "3:58:15"}
{"current_steps": 1420, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 3.882612296657701e-05, "epoch": 0.94, "percentage": 31.35, "elapsed_time": "1:48:23", "remaining_time": "3:57:24"}
{"current_steps": 1430, "total_steps": 4530, "loss": 1.4156, "reward": null, "learning_rate": 3.8681342277703906e-05, "epoch": 0.95, "percentage": 31.57, "elapsed_time": "1:49:06", "remaining_time": "3:56:32"}
{"current_steps": 1440, "total_steps": 4530, "loss": 1.433, "reward": null, "learning_rate": 3.853590358214119e-05, "epoch": 0.95, "percentage": 31.79, "elapsed_time": "1:49:49", "remaining_time": "3:55:40"}
{"current_steps": 1450, "total_steps": 4530, "loss": 1.4372, "reward": null, "learning_rate": 3.8389813874789856e-05, "epoch": 0.96, "percentage": 32.01, "elapsed_time": "1:50:31", "remaining_time": "3:54:46"}
{"current_steps": 1460, "total_steps": 4530, "loss": 1.3978, "reward": null, "learning_rate": 3.8243080181861435e-05, "epoch": 0.97, "percentage": 32.23, "elapsed_time": "1:51:13", "remaining_time": "3:53:52"}
{"current_steps": 1470, "total_steps": 4530, "loss": 1.3964, "reward": null, "learning_rate": 3.809570956054004e-05, "epoch": 0.97, "percentage": 32.45, "elapsed_time": "1:51:54", "remaining_time": "3:52:56"}
{"current_steps": 1480, "total_steps": 4530, "loss": 1.4332, "reward": null, "learning_rate": 3.794770909864298e-05, "epoch": 0.98, "percentage": 32.67, "elapsed_time": "1:52:35", "remaining_time": "3:52:02"}
{"current_steps": 1490, "total_steps": 4530, "loss": 1.4044, "reward": null, "learning_rate": 3.779908591427988e-05, "epoch": 0.99, "percentage": 32.89, "elapsed_time": "1:53:20", "remaining_time": "3:51:14"}
{"current_steps": 1500, "total_steps": 4530, "loss": 1.4301, "reward": null, "learning_rate": 3.764984715551032e-05, "epoch": 0.99, "percentage": 33.11, "elapsed_time": "1:54:00", "remaining_time": "3:50:18"}
{"current_steps": 1510, "total_steps": 4530, "loss": 1.4721, "reward": null, "learning_rate": 3.7500000000000003e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:55:04", "remaining_time": "3:50:08"}
{"current_steps": 1520, "total_steps": 4530, "loss": 1.3905, "reward": null, "learning_rate": 3.734955165467563e-05, "epoch": 1.01, "percentage": 33.55, "elapsed_time": "1:55:47", "remaining_time": "3:49:17"}
{"current_steps": 1530, "total_steps": 4530, "loss": 1.423, "reward": null, "learning_rate": 3.719850935537821e-05, "epoch": 1.01, "percentage": 33.77, "elapsed_time": "1:56:29", "remaining_time": "3:48:24"}
{"current_steps": 1540, "total_steps": 4530, "loss": 1.404, "reward": null, "learning_rate": 3.70468803665151e-05, "epoch": 1.02, "percentage": 34.0, "elapsed_time": "1:57:10", "remaining_time": "3:47:30"}
{"current_steps": 1550, "total_steps": 4530, "loss": 1.4042, "reward": null, "learning_rate": 3.6894671980710574e-05, "epoch": 1.03, "percentage": 34.22, "elapsed_time": "1:57:54", "remaining_time": "3:46:42"}
{"current_steps": 1560, "total_steps": 4530, "loss": 1.4158, "reward": null, "learning_rate": 3.674189151845515e-05, "epoch": 1.03, "percentage": 34.44, "elapsed_time": "1:58:40", "remaining_time": "3:45:55"}
{"current_steps": 1570, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 3.6588546327753425e-05, "epoch": 1.04, "percentage": 34.66, "elapsed_time": "1:59:21", "remaining_time": "3:45:01"}
{"current_steps": 1580, "total_steps": 4530, "loss": 1.3764, "reward": null, "learning_rate": 3.6434643783770736e-05, "epoch": 1.05, "percentage": 34.88, "elapsed_time": "2:00:04", "remaining_time": "3:44:11"}
{"current_steps": 1590, "total_steps": 4530, "loss": 1.4021, "reward": null, "learning_rate": 3.6280191288478436e-05, "epoch": 1.05, "percentage": 35.1, "elapsed_time": "2:00:47", "remaining_time": "3:43:20"}
{"current_steps": 1600, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 3.612519627029787e-05, "epoch": 1.06, "percentage": 35.32, "elapsed_time": "2:01:26", "remaining_time": "3:42:22"}
{"current_steps": 1610, "total_steps": 4530, "loss": 1.3985, "reward": null, "learning_rate": 3.596966618374313e-05, "epoch": 1.07, "percentage": 35.54, "elapsed_time": "2:02:32", "remaining_time": "3:42:14"}
{"current_steps": 1620, "total_steps": 4530, "loss": 1.3444, "reward": null, "learning_rate": 3.5813608509062526e-05, "epoch": 1.07, "percentage": 35.76, "elapsed_time": "2:03:19", "remaining_time": "3:41:31"}
{"current_steps": 1630, "total_steps": 4530, "loss": 1.4207, "reward": null, "learning_rate": 3.5657030751878814e-05, "epoch": 1.08, "percentage": 35.98, "elapsed_time": "2:04:00", "remaining_time": "3:40:38"}
{"current_steps": 1640, "total_steps": 4530, "loss": 1.4304, "reward": null, "learning_rate": 3.5499940442828206e-05, "epoch": 1.09, "percentage": 36.2, "elapsed_time": "2:04:42", "remaining_time": "3:39:46"}
{"current_steps": 1650, "total_steps": 4530, "loss": 1.3924, "reward": null, "learning_rate": 3.534234513719821e-05, "epoch": 1.09, "percentage": 36.42, "elapsed_time": "2:05:25", "remaining_time": "3:38:54"}
{"current_steps": 1660, "total_steps": 4530, "loss": 1.3686, "reward": null, "learning_rate": 3.51842524145642e-05, "epoch": 1.1, "percentage": 36.64, "elapsed_time": "2:06:11", "remaining_time": "3:38:09"}
{"current_steps": 1670, "total_steps": 4530, "loss": 1.4248, "reward": null, "learning_rate": 3.502566987842496e-05, "epoch": 1.11, "percentage": 36.87, "elapsed_time": "2:06:53", "remaining_time": "3:37:18"}
{"current_steps": 1680, "total_steps": 4530, "loss": 1.3906, "reward": null, "learning_rate": 3.4866605155836915e-05, "epoch": 1.11, "percentage": 37.09, "elapsed_time": "2:07:34", "remaining_time": "3:36:25"}
{"current_steps": 1690, "total_steps": 4530, "loss": 1.444, "reward": null, "learning_rate": 3.470706589704734e-05, "epoch": 1.12, "percentage": 37.31, "elapsed_time": "2:08:19", "remaining_time": "3:35:37"}
{"current_steps": 1700, "total_steps": 4530, "loss": 1.3589, "reward": null, "learning_rate": 3.4547059775126445e-05, "epoch": 1.13, "percentage": 37.53, "elapsed_time": "2:09:04", "remaining_time": "3:34:52"}
{"current_steps": 1710, "total_steps": 4530, "loss": 1.319, "reward": null, "learning_rate": 3.438659448559825e-05, "epoch": 1.13, "percentage": 37.75, "elapsed_time": "2:10:07", "remaining_time": "3:34:34"}
{"current_steps": 1720, "total_steps": 4530, "loss": 1.406, "reward": null, "learning_rate": 3.422567774607058e-05, "epoch": 1.14, "percentage": 37.97, "elapsed_time": "2:10:50", "remaining_time": "3:33:44"}
{"current_steps": 1730, "total_steps": 4530, "loss": 1.4114, "reward": null, "learning_rate": 3.406431729586382e-05, "epoch": 1.15, "percentage": 38.19, "elapsed_time": "2:11:33", "remaining_time": "3:32:55"}
{"current_steps": 1740, "total_steps": 4530, "loss": 1.3722, "reward": null, "learning_rate": 3.390252089563867e-05, "epoch": 1.15, "percentage": 38.41, "elapsed_time": "2:12:16", "remaining_time": "3:32:05"}
{"current_steps": 1750, "total_steps": 4530, "loss": 1.3528, "reward": null, "learning_rate": 3.3740296327022984e-05, "epoch": 1.16, "percentage": 38.63, "elapsed_time": "2:13:01", "remaining_time": "3:31:19"}
{"current_steps": 1760, "total_steps": 4530, "loss": 1.4274, "reward": null, "learning_rate": 3.35776513922374e-05, "epoch": 1.17, "percentage": 38.85, "elapsed_time": "2:13:45", "remaining_time": "3:30:31"}
{"current_steps": 1770, "total_steps": 4530, "loss": 1.4324, "reward": null, "learning_rate": 3.341459391372016e-05, "epoch": 1.17, "percentage": 39.07, "elapsed_time": "2:14:29", "remaining_time": "3:29:43"}
{"current_steps": 1780, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 3.32511317337509e-05, "epoch": 1.18, "percentage": 39.29, "elapsed_time": "2:15:10", "remaining_time": "3:28:50"}
{"current_steps": 1790, "total_steps": 4530, "loss": 1.3464, "reward": null, "learning_rate": 3.30872727140734e-05, "epoch": 1.19, "percentage": 39.51, "elapsed_time": "2:15:55", "remaining_time": "3:28:04"}
{"current_steps": 1800, "total_steps": 4530, "loss": 1.4144, "reward": null, "learning_rate": 3.292302473551757e-05, "epoch": 1.19, "percentage": 39.74, "elapsed_time": "2:16:40", "remaining_time": "3:27:16"}
{"current_steps": 1810, "total_steps": 4530, "loss": 1.4139, "reward": null, "learning_rate": 3.2758395697620334e-05, "epoch": 1.2, "percentage": 39.96, "elapsed_time": "2:17:41", "remaining_time": "3:26:55"}
{"current_steps": 1820, "total_steps": 4530, "loss": 1.4247, "reward": null, "learning_rate": 3.259339351824575e-05, "epoch": 1.2, "percentage": 40.18, "elapsed_time": "2:18:25", "remaining_time": "3:26:06"}
{"current_steps": 1830, "total_steps": 4530, "loss": 1.4241, "reward": null, "learning_rate": 3.2428026133204184e-05, "epoch": 1.21, "percentage": 40.4, "elapsed_time": "2:19:09", "remaining_time": "3:25:18"}
{"current_steps": 1840, "total_steps": 4530, "loss": 1.3941, "reward": null, "learning_rate": 3.226230149587063e-05, "epoch": 1.22, "percentage": 40.62, "elapsed_time": "2:19:53", "remaining_time": "3:24:31"}
{"current_steps": 1850, "total_steps": 4530, "loss": 1.4238, "reward": null, "learning_rate": 3.20962275768022e-05, "epoch": 1.22, "percentage": 40.84, "elapsed_time": "2:20:36", "remaining_time": "3:23:41"}
{"current_steps": 1860, "total_steps": 4530, "loss": 1.382, "reward": null, "learning_rate": 3.1929812363354766e-05, "epoch": 1.23, "percentage": 41.06, "elapsed_time": "2:21:17", "remaining_time": "3:22:49"}
{"current_steps": 1870, "total_steps": 4530, "loss": 1.4124, "reward": null, "learning_rate": 3.1763063859298845e-05, "epoch": 1.24, "percentage": 41.28, "elapsed_time": "2:22:00", "remaining_time": "3:22:00"}
{"current_steps": 1880, "total_steps": 4530, "loss": 1.3963, "reward": null, "learning_rate": 3.159599008443459e-05, "epoch": 1.24, "percentage": 41.5, "elapsed_time": "2:22:44", "remaining_time": "3:21:12"}
{"current_steps": 1890, "total_steps": 4530, "loss": 1.3542, "reward": null, "learning_rate": 3.142859907420615e-05, "epoch": 1.25, "percentage": 41.72, "elapsed_time": "2:23:27", "remaining_time": "3:20:23"}
{"current_steps": 1900, "total_steps": 4530, "loss": 1.3852, "reward": null, "learning_rate": 3.126089887931515e-05, "epoch": 1.26, "percentage": 41.94, "elapsed_time": "2:24:09", "remaining_time": "3:19:32"}
{"current_steps": 1910, "total_steps": 4530, "loss": 1.3972, "reward": null, "learning_rate": 3.109289756533349e-05, "epoch": 1.26, "percentage": 42.16, "elapsed_time": "2:25:13", "remaining_time": "3:19:13"}
{"current_steps": 1920, "total_steps": 4530, "loss": 1.3783, "reward": null, "learning_rate": 3.092460321231547e-05, "epoch": 1.27, "percentage": 42.38, "elapsed_time": "2:25:55", "remaining_time": "3:18:21"}
{"current_steps": 1930, "total_steps": 4530, "loss": 1.4122, "reward": null, "learning_rate": 3.075602391440918e-05, "epoch": 1.28, "percentage": 42.6, "elapsed_time": "2:26:40", "remaining_time": "3:17:35"}
{"current_steps": 1940, "total_steps": 4530, "loss": 1.4105, "reward": null, "learning_rate": 3.058716777946713e-05, "epoch": 1.28, "percentage": 42.83, "elapsed_time": "2:27:26", "remaining_time": "3:16:50"}
{"current_steps": 1950, "total_steps": 4530, "loss": 1.4091, "reward": null, "learning_rate": 3.0418042928656414e-05, "epoch": 1.29, "percentage": 43.05, "elapsed_time": "2:28:10", "remaining_time": "3:16:03"}
{"current_steps": 1960, "total_steps": 4530, "loss": 1.4067, "reward": null, "learning_rate": 3.0248657496068027e-05, "epoch": 1.3, "percentage": 43.27, "elapsed_time": "2:28:55", "remaining_time": "3:15:16"}
{"current_steps": 1970, "total_steps": 4530, "loss": 1.4172, "reward": null, "learning_rate": 3.0079019628325706e-05, "epoch": 1.3, "percentage": 43.49, "elapsed_time": "2:29:36", "remaining_time": "3:14:24"}
{"current_steps": 1980, "total_steps": 4530, "loss": 1.3803, "reward": null, "learning_rate": 2.990913748419411e-05, "epoch": 1.31, "percentage": 43.71, "elapsed_time": "2:30:19", "remaining_time": "3:13:36"}
{"current_steps": 1990, "total_steps": 4530, "loss": 1.4096, "reward": null, "learning_rate": 2.97390192341864e-05, "epoch": 1.32, "percentage": 43.93, "elapsed_time": "2:31:03", "remaining_time": "3:12:48"}
{"current_steps": 2000, "total_steps": 4530, "loss": 1.3774, "reward": null, "learning_rate": 2.9568673060171326e-05, "epoch": 1.32, "percentage": 44.15, "elapsed_time": "2:31:46", "remaining_time": "3:11:59"}
{"current_steps": 2010, "total_steps": 4530, "loss": 1.3729, "reward": null, "learning_rate": 2.9398107154979638e-05, "epoch": 1.33, "percentage": 44.37, "elapsed_time": "2:32:51", "remaining_time": "3:11:38"}
{"current_steps": 2020, "total_steps": 4530, "loss": 1.3687, "reward": null, "learning_rate": 2.922732972201014e-05, "epoch": 1.34, "percentage": 44.59, "elapsed_time": "2:33:33", "remaining_time": "3:10:49"}
{"current_steps": 2030, "total_steps": 4530, "loss": 1.3946, "reward": null, "learning_rate": 2.9056348974835067e-05, "epoch": 1.34, "percentage": 44.81, "elapsed_time": "2:34:17", "remaining_time": "3:10:01"}
{"current_steps": 2040, "total_steps": 4530, "loss": 1.3922, "reward": null, "learning_rate": 2.8885173136805127e-05, "epoch": 1.35, "percentage": 45.03, "elapsed_time": "2:35:01", "remaining_time": "3:09:12"}
{"current_steps": 2050, "total_steps": 4530, "loss": 1.3631, "reward": null, "learning_rate": 2.8713810440653926e-05, "epoch": 1.36, "percentage": 45.25, "elapsed_time": "2:35:45", "remaining_time": "3:08:25"}
{"current_steps": 2060, "total_steps": 4530, "loss": 1.4193, "reward": null, "learning_rate": 2.8542269128102063e-05, "epoch": 1.36, "percentage": 45.47, "elapsed_time": "2:36:29", "remaining_time": "3:07:37"}
{"current_steps": 2070, "total_steps": 4530, "loss": 1.3776, "reward": null, "learning_rate": 2.837055744946072e-05, "epoch": 1.37, "percentage": 45.7, "elapsed_time": "2:37:14", "remaining_time": "3:06:51"}
{"current_steps": 2080, "total_steps": 4530, "loss": 1.4099, "reward": null, "learning_rate": 2.819868366323488e-05, "epoch": 1.38, "percentage": 45.92, "elapsed_time": "2:37:56", "remaining_time": "3:06:02"}
{"current_steps": 2090, "total_steps": 4530, "loss": 1.41, "reward": null, "learning_rate": 2.8026656035726095e-05, "epoch": 1.38, "percentage": 46.14, "elapsed_time": "2:38:40", "remaining_time": "3:05:14"}
{"current_steps": 2100, "total_steps": 4530, "loss": 1.4604, "reward": null, "learning_rate": 2.7854482840634965e-05, "epoch": 1.39, "percentage": 46.36, "elapsed_time": "2:39:21", "remaining_time": "3:04:24"}
{"current_steps": 2110, "total_steps": 4530, "loss": 1.4485, "reward": null, "learning_rate": 2.7682172358663173e-05, "epoch": 1.4, "percentage": 46.58, "elapsed_time": "2:40:23", "remaining_time": "3:03:57"}
{"current_steps": 2120, "total_steps": 4530, "loss": 1.4445, "reward": null, "learning_rate": 2.7509732877115257e-05, "epoch": 1.4, "percentage": 46.8, "elapsed_time": "2:41:06", "remaining_time": "3:03:08"}
{"current_steps": 2130, "total_steps": 4530, "loss": 1.3889, "reward": null, "learning_rate": 2.73371726895e-05, "epoch": 1.41, "percentage": 47.02, "elapsed_time": "2:41:49", "remaining_time": "3:02:20"}
{"current_steps": 2140, "total_steps": 4530, "loss": 1.4167, "reward": null, "learning_rate": 2.716450009513158e-05, "epoch": 1.42, "percentage": 47.24, "elapsed_time": "2:42:32", "remaining_time": "3:01:31"}
{"current_steps": 2150, "total_steps": 4530, "loss": 1.3388, "reward": null, "learning_rate": 2.6991723398730383e-05, "epoch": 1.42, "percentage": 47.46, "elapsed_time": "2:43:16", "remaining_time": "3:00:44"}
{"current_steps": 2160, "total_steps": 4530, "loss": 1.4379, "reward": null, "learning_rate": 2.68188509100236e-05, "epoch": 1.43, "percentage": 47.68, "elapsed_time": "2:44:01", "remaining_time": "2:59:57"}
{"current_steps": 2170, "total_steps": 4530, "loss": 1.4119, "reward": null, "learning_rate": 2.6645890943345585e-05, "epoch": 1.44, "percentage": 47.9, "elapsed_time": "2:44:44", "remaining_time": "2:59:09"}
{"current_steps": 2180, "total_steps": 4530, "loss": 1.3961, "reward": null, "learning_rate": 2.6472851817237948e-05, "epoch": 1.44, "percentage": 48.12, "elapsed_time": "2:45:29", "remaining_time": "2:58:23"}
{"current_steps": 2190, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 2.6299741854049508e-05, "epoch": 1.45, "percentage": 48.34, "elapsed_time": "2:46:10", "remaining_time": "2:57:33"}
{"current_steps": 2200, "total_steps": 4530, "loss": 1.3739, "reward": null, "learning_rate": 2.6126569379535985e-05, "epoch": 1.46, "percentage": 48.57, "elapsed_time": "2:46:53", "remaining_time": "2:56:45"}
{"current_steps": 2210, "total_steps": 4530, "loss": 1.4256, "reward": null, "learning_rate": 2.5953342722459594e-05, "epoch": 1.46, "percentage": 48.79, "elapsed_time": "2:47:53", "remaining_time": "2:56:14"}
{"current_steps": 2220, "total_steps": 4530, "loss": 1.4615, "reward": null, "learning_rate": 2.5780070214188478e-05, "epoch": 1.47, "percentage": 49.01, "elapsed_time": "2:48:38", "remaining_time": "2:55:28"}
{"current_steps": 2230, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 2.5606760188296004e-05, "epoch": 1.48, "percentage": 49.23, "elapsed_time": "2:49:20", "remaining_time": "2:54:38"}
{"current_steps": 2240, "total_steps": 4530, "loss": 1.3752, "reward": null, "learning_rate": 2.5433420980159944e-05, "epoch": 1.48, "percentage": 49.45, "elapsed_time": "2:50:03", "remaining_time": "2:53:50"}
{"current_steps": 2250, "total_steps": 4530, "loss": 1.4084, "reward": null, "learning_rate": 2.526006092656161e-05, "epoch": 1.49, "percentage": 49.67, "elapsed_time": "2:50:45", "remaining_time": "2:53:01"}
{"current_steps": 2260, "total_steps": 4530, "loss": 1.3921, "reward": null, "learning_rate": 2.508668836528486e-05, "epoch": 1.5, "percentage": 49.89, "elapsed_time": "2:51:29", "remaining_time": "2:52:14"}
{"current_steps": 2270, "total_steps": 4530, "loss": 1.4104, "reward": null, "learning_rate": 2.491331163471514e-05, "epoch": 1.5, "percentage": 50.11, "elapsed_time": "2:52:13", "remaining_time": "2:51:28"}
{"current_steps": 2280, "total_steps": 4530, "loss": 1.4053, "reward": null, "learning_rate": 2.4739939073438397e-05, "epoch": 1.51, "percentage": 50.33, "elapsed_time": "2:52:59", "remaining_time": "2:50:42"}
{"current_steps": 2290, "total_steps": 4530, "loss": 1.381, "reward": null, "learning_rate": 2.456657901984006e-05, "epoch": 1.52, "percentage": 50.55, "elapsed_time": "2:53:45", "remaining_time": "2:49:57"}
{"current_steps": 2300, "total_steps": 4530, "loss": 1.3752, "reward": null, "learning_rate": 2.4393239811704e-05, "epoch": 1.52, "percentage": 50.77, "elapsed_time": "2:54:29", "remaining_time": "2:49:10"}
{"current_steps": 2310, "total_steps": 4530, "loss": 1.4023, "reward": null, "learning_rate": 2.4219929785811518e-05, "epoch": 1.53, "percentage": 50.99, "elapsed_time": "2:55:31", "remaining_time": "2:48:41"}
{"current_steps": 2320, "total_steps": 4530, "loss": 1.3642, "reward": null, "learning_rate": 2.4046657277540412e-05, "epoch": 1.54, "percentage": 51.21, "elapsed_time": "2:56:16", "remaining_time": "2:47:55"}
{"current_steps": 2330, "total_steps": 4530, "loss": 1.3977, "reward": null, "learning_rate": 2.3873430620464024e-05, "epoch": 1.54, "percentage": 51.43, "elapsed_time": "2:57:01", "remaining_time": "2:47:09"}
{"current_steps": 2340, "total_steps": 4530, "loss": 1.3905, "reward": null, "learning_rate": 2.3700258145950495e-05, "epoch": 1.55, "percentage": 51.66, "elapsed_time": "2:57:45", "remaining_time": "2:46:22"}
{"current_steps": 2350, "total_steps": 4530, "loss": 1.4022, "reward": null, "learning_rate": 2.3527148182762054e-05, "epoch": 1.56, "percentage": 51.88, "elapsed_time": "2:58:29", "remaining_time": "2:45:34"}
{"current_steps": 2360, "total_steps": 4530, "loss": 1.4162, "reward": null, "learning_rate": 2.335410905665442e-05, "epoch": 1.56, "percentage": 52.1, "elapsed_time": "2:59:10", "remaining_time": "2:44:45"}
{"current_steps": 2370, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 2.3181149089976405e-05, "epoch": 1.57, "percentage": 52.32, "elapsed_time": "2:59:55", "remaining_time": "2:43:58"}
{"current_steps": 2380, "total_steps": 4530, "loss": 1.3704, "reward": null, "learning_rate": 2.3008276601269623e-05, "epoch": 1.58, "percentage": 52.54, "elapsed_time": "3:00:41", "remaining_time": "2:43:14"}
{"current_steps": 2390, "total_steps": 4530, "loss": 1.3725, "reward": null, "learning_rate": 2.283549990486842e-05, "epoch": 1.58, "percentage": 52.76, "elapsed_time": "3:01:26", "remaining_time": "2:42:28"}
{"current_steps": 2400, "total_steps": 4530, "loss": 1.4232, "reward": null, "learning_rate": 2.2662827310499995e-05, "epoch": 1.59, "percentage": 52.98, "elapsed_time": "3:02:10", "remaining_time": "2:41:41"}
{"current_steps": 2410, "total_steps": 4530, "loss": 1.3916, "reward": null, "learning_rate": 2.249026712288474e-05, "epoch": 1.6, "percentage": 53.2, "elapsed_time": "3:03:15", "remaining_time": "2:41:12"}
{"current_steps": 2420, "total_steps": 4530, "loss": 1.384, "reward": null, "learning_rate": 2.2317827641336833e-05, "epoch": 1.6, "percentage": 53.42, "elapsed_time": "3:03:59", "remaining_time": "2:40:25"}
{"current_steps": 2430, "total_steps": 4530, "loss": 1.3969, "reward": null, "learning_rate": 2.2145517159365044e-05, "epoch": 1.61, "percentage": 53.64, "elapsed_time": "3:04:44", "remaining_time": "2:39:39"}
{"current_steps": 2440, "total_steps": 4530, "loss": 1.3742, "reward": null, "learning_rate": 2.197334396427391e-05, "epoch": 1.62, "percentage": 53.86, "elapsed_time": "3:05:26", "remaining_time": "2:38:50"}
{"current_steps": 2450, "total_steps": 4530, "loss": 1.3901, "reward": null, "learning_rate": 2.1801316336765126e-05, "epoch": 1.62, "percentage": 54.08, "elapsed_time": "3:06:08", "remaining_time": "2:38:02"}
{"current_steps": 2460, "total_steps": 4530, "loss": 1.3853, "reward": null, "learning_rate": 2.162944255053928e-05, "epoch": 1.63, "percentage": 54.3, "elapsed_time": "3:06:52", "remaining_time": "2:37:14"}
{"current_steps": 2470, "total_steps": 4530, "loss": 1.3709, "reward": null, "learning_rate": 2.145773087189794e-05, "epoch": 1.64, "percentage": 54.53, "elapsed_time": "3:07:36", "remaining_time": "2:36:27"}
{"current_steps": 2480, "total_steps": 4530, "loss": 1.3758, "reward": null, "learning_rate": 2.128618955934608e-05, "epoch": 1.64, "percentage": 54.75, "elapsed_time": "3:08:19", "remaining_time": "2:35:40"}
{"current_steps": 2490, "total_steps": 4530, "loss": 1.3561, "reward": null, "learning_rate": 2.1114826863194882e-05, "epoch": 1.65, "percentage": 54.97, "elapsed_time": "3:09:04", "remaining_time": "2:34:54"}
{"current_steps": 2500, "total_steps": 4530, "loss": 1.3774, "reward": null, "learning_rate": 2.0943651025164932e-05, "epoch": 1.66, "percentage": 55.19, "elapsed_time": "3:09:48", "remaining_time": "2:34:07"}
{"current_steps": 2510, "total_steps": 4530, "loss": 1.3961, "reward": null, "learning_rate": 2.0772670277989864e-05, "epoch": 1.66, "percentage": 55.41, "elapsed_time": "3:10:52", "remaining_time": "2:33:36"}
{"current_steps": 2520, "total_steps": 4530, "loss": 1.3794, "reward": null, "learning_rate": 2.060189284502037e-05, "epoch": 1.67, "percentage": 55.63, "elapsed_time": "3:11:35", "remaining_time": "2:32:49"}
{"current_steps": 2530, "total_steps": 4530, "loss": 1.4147, "reward": null, "learning_rate": 2.0431326939828686e-05, "epoch": 1.68, "percentage": 55.85, "elapsed_time": "3:12:17", "remaining_time": "2:32:00"}
{"current_steps": 2540, "total_steps": 4530, "loss": 1.4336, "reward": null, "learning_rate": 2.0260980765813604e-05, "epoch": 1.68, "percentage": 56.07, "elapsed_time": "3:13:00", "remaining_time": "2:31:13"}
{"current_steps": 2550, "total_steps": 4530, "loss": 1.4228, "reward": null, "learning_rate": 2.0090862515805898e-05, "epoch": 1.69, "percentage": 56.29, "elapsed_time": "3:13:45", "remaining_time": "2:30:26"}
{"current_steps": 2560, "total_steps": 4530, "loss": 1.4188, "reward": null, "learning_rate": 1.99209803716743e-05, "epoch": 1.69, "percentage": 56.51, "elapsed_time": "3:14:26", "remaining_time": "2:29:37"}
{"current_steps": 2570, "total_steps": 4530, "loss": 1.4492, "reward": null, "learning_rate": 1.975134250393198e-05, "epoch": 1.7, "percentage": 56.73, "elapsed_time": "3:15:10", "remaining_time": "2:28:50"}
{"current_steps": 2580, "total_steps": 4530, "loss": 1.4492, "reward": null, "learning_rate": 1.9581957071343592e-05, "epoch": 1.71, "percentage": 56.95, "elapsed_time": "3:15:51", "remaining_time": "2:28:02"}
{"current_steps": 2590, "total_steps": 4530, "loss": 1.4261, "reward": null, "learning_rate": 1.9412832220532867e-05, "epoch": 1.71, "percentage": 57.17, "elapsed_time": "3:16:32", "remaining_time": "2:27:13"}
{"current_steps": 2600, "total_steps": 4530, "loss": 1.412, "reward": null, "learning_rate": 1.9243976085590824e-05, "epoch": 1.72, "percentage": 57.4, "elapsed_time": "3:17:14", "remaining_time": "2:26:25"}
{"current_steps": 2610, "total_steps": 4530, "loss": 1.3858, "reward": null, "learning_rate": 1.9075396787684533e-05, "epoch": 1.73, "percentage": 57.62, "elapsed_time": "3:18:17", "remaining_time": "2:25:51"}
{"current_steps": 2620, "total_steps": 4530, "loss": 1.3648, "reward": null, "learning_rate": 1.8907102434666523e-05, "epoch": 1.73, "percentage": 57.84, "elapsed_time": "3:19:00", "remaining_time": "2:25:04"}
{"current_steps": 2630, "total_steps": 4530, "loss": 1.4267, "reward": null, "learning_rate": 1.8739101120684866e-05, "epoch": 1.74, "percentage": 58.06, "elapsed_time": "3:19:40", "remaining_time": "2:24:15"}
{"current_steps": 2640, "total_steps": 4530, "loss": 1.4115, "reward": null, "learning_rate": 1.8571400925793855e-05, "epoch": 1.75, "percentage": 58.28, "elapsed_time": "3:20:23", "remaining_time": "2:23:27"}
{"current_steps": 2650, "total_steps": 4530, "loss": 1.3767, "reward": null, "learning_rate": 1.840400991556541e-05, "epoch": 1.75, "percentage": 58.5, "elapsed_time": "3:21:07", "remaining_time": "2:22:41"}
{"current_steps": 2660, "total_steps": 4530, "loss": 1.3934, "reward": null, "learning_rate": 1.8236936140701165e-05, "epoch": 1.76, "percentage": 58.72, "elapsed_time": "3:21:53", "remaining_time": "2:21:56"}
{"current_steps": 2670, "total_steps": 4530, "loss": 1.368, "reward": null, "learning_rate": 1.807018763664524e-05, "epoch": 1.77, "percentage": 58.94, "elapsed_time": "3:22:39", "remaining_time": "2:21:10"}
{"current_steps": 2680, "total_steps": 4530, "loss": 1.3925, "reward": null, "learning_rate": 1.7903772423197806e-05, "epoch": 1.77, "percentage": 59.16, "elapsed_time": "3:23:20", "remaining_time": "2:20:22"}
{"current_steps": 2690, "total_steps": 4530, "loss": 1.3786, "reward": null, "learning_rate": 1.773769850412937e-05, "epoch": 1.78, "percentage": 59.38, "elapsed_time": "3:24:04", "remaining_time": "2:19:35"}
{"current_steps": 2700, "total_steps": 4530, "loss": 1.4204, "reward": null, "learning_rate": 1.7571973866795815e-05, "epoch": 1.79, "percentage": 59.6, "elapsed_time": "3:24:46", "remaining_time": "2:18:47"}
{"current_steps": 2710, "total_steps": 4530, "loss": 1.3907, "reward": null, "learning_rate": 1.7406606481754258e-05, "epoch": 1.79, "percentage": 59.82, "elapsed_time": "3:25:52", "remaining_time": "2:18:15"}
{"current_steps": 2720, "total_steps": 4530, "loss": 1.3598, "reward": null, "learning_rate": 1.724160430237967e-05, "epoch": 1.8, "percentage": 60.04, "elapsed_time": "3:26:39", "remaining_time": "2:17:31"}
{"current_steps": 2730, "total_steps": 4530, "loss": 1.4157, "reward": null, "learning_rate": 1.7076975264482434e-05, "epoch": 1.81, "percentage": 60.26, "elapsed_time": "3:27:20", "remaining_time": "2:16:42"}
{"current_steps": 2740, "total_steps": 4530, "loss": 1.3922, "reward": null, "learning_rate": 1.6912727285926605e-05, "epoch": 1.81, "percentage": 60.49, "elapsed_time": "3:28:04", "remaining_time": "2:15:55"}
{"current_steps": 2750, "total_steps": 4530, "loss": 1.4413, "reward": null, "learning_rate": 1.6748868266249114e-05, "epoch": 1.82, "percentage": 60.71, "elapsed_time": "3:28:47", "remaining_time": "2:15:08"}
{"current_steps": 2760, "total_steps": 4530, "loss": 1.4219, "reward": null, "learning_rate": 1.658540608627985e-05, "epoch": 1.83, "percentage": 60.93, "elapsed_time": "3:29:30", "remaining_time": "2:14:21"}
{"current_steps": 2770, "total_steps": 4530, "loss": 1.3447, "reward": null, "learning_rate": 1.642234860776261e-05, "epoch": 1.83, "percentage": 61.15, "elapsed_time": "3:30:13", "remaining_time": "2:13:34"}
{"current_steps": 2780, "total_steps": 4530, "loss": 1.4383, "reward": null, "learning_rate": 1.6259703672977022e-05, "epoch": 1.84, "percentage": 61.37, "elapsed_time": "3:30:55", "remaining_time": "2:12:46"}
{"current_steps": 2790, "total_steps": 4530, "loss": 1.3562, "reward": null, "learning_rate": 1.6097479104361326e-05, "epoch": 1.85, "percentage": 61.59, "elapsed_time": "3:31:39", "remaining_time": "2:12:00"}
{"current_steps": 2800, "total_steps": 4530, "loss": 1.3865, "reward": null, "learning_rate": 1.5935682704136183e-05, "epoch": 1.85, "percentage": 61.81, "elapsed_time": "3:32:23", "remaining_time": "2:11:13"}
{"current_steps": 2810, "total_steps": 4530, "loss": 1.3875, "reward": null, "learning_rate": 1.5774322253929425e-05, "epoch": 1.86, "percentage": 62.03, "elapsed_time": "3:33:27", "remaining_time": "2:10:39"}
{"current_steps": 2820, "total_steps": 4530, "loss": 1.4282, "reward": null, "learning_rate": 1.561340551440176e-05, "epoch": 1.87, "percentage": 62.25, "elapsed_time": "3:34:09", "remaining_time": "2:09:51"}
{"current_steps": 2830, "total_steps": 4530, "loss": 1.401, "reward": null, "learning_rate": 1.5452940224873568e-05, "epoch": 1.87, "percentage": 62.47, "elapsed_time": "3:34:51", "remaining_time": "2:09:04"}
{"current_steps": 2840, "total_steps": 4530, "loss": 1.3645, "reward": null, "learning_rate": 1.529293410295266e-05, "epoch": 1.88, "percentage": 62.69, "elapsed_time": "3:35:37", "remaining_time": "2:08:18"}
{"current_steps": 2850, "total_steps": 4530, "loss": 1.3877, "reward": null, "learning_rate": 1.5133394844163093e-05, "epoch": 1.89, "percentage": 62.91, "elapsed_time": "3:36:19", "remaining_time": "2:07:30"}
{"current_steps": 2860, "total_steps": 4530, "loss": 1.4026, "reward": null, "learning_rate": 1.4974330121575048e-05, "epoch": 1.89, "percentage": 63.13, "elapsed_time": "3:37:03", "remaining_time": "2:06:44"}
{"current_steps": 2870, "total_steps": 4530, "loss": 1.4235, "reward": null, "learning_rate": 1.4815747585435801e-05, "epoch": 1.9, "percentage": 63.36, "elapsed_time": "3:37:42", "remaining_time": "2:05:55"}
{"current_steps": 2880, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 1.4657654862801798e-05, "epoch": 1.91, "percentage": 63.58, "elapsed_time": "3:38:23", "remaining_time": "2:05:07"}
{"current_steps": 2890, "total_steps": 4530, "loss": 1.3823, "reward": null, "learning_rate": 1.4500059557171791e-05, "epoch": 1.91, "percentage": 63.8, "elapsed_time": "3:39:07", "remaining_time": "2:04:20"}
{"current_steps": 2900, "total_steps": 4530, "loss": 1.3717, "reward": null, "learning_rate": 1.4342969248121185e-05, "epoch": 1.92, "percentage": 64.02, "elapsed_time": "3:39:51", "remaining_time": "2:03:34"}
{"current_steps": 2910, "total_steps": 4530, "loss": 1.434, "reward": null, "learning_rate": 1.4186391490937481e-05, "epoch": 1.93, "percentage": 64.24, "elapsed_time": "3:40:52", "remaining_time": "2:02:57"}
{"current_steps": 2920, "total_steps": 4530, "loss": 1.3688, "reward": null, "learning_rate": 1.403033381625688e-05, "epoch": 1.93, "percentage": 64.46, "elapsed_time": "3:41:34", "remaining_time": "2:02:10"}
{"current_steps": 2930, "total_steps": 4530, "loss": 1.3404, "reward": null, "learning_rate": 1.3874803729702141e-05, "epoch": 1.94, "percentage": 64.68, "elapsed_time": "3:42:21", "remaining_time": "2:01:25"}
{"current_steps": 2940, "total_steps": 4530, "loss": 1.3956, "reward": null, "learning_rate": 1.3719808711521573e-05, "epoch": 1.95, "percentage": 64.9, "elapsed_time": "3:43:04", "remaining_time": "2:00:38"}
{"current_steps": 2950, "total_steps": 4530, "loss": 1.366, "reward": null, "learning_rate": 1.3565356216229268e-05, "epoch": 1.95, "percentage": 65.12, "elapsed_time": "3:43:50", "remaining_time": "1:59:53"}
{"current_steps": 2960, "total_steps": 4530, "loss": 1.4425, "reward": null, "learning_rate": 1.341145367224657e-05, "epoch": 1.96, "percentage": 65.34, "elapsed_time": "3:44:32", "remaining_time": "1:59:06"}
{"current_steps": 2970, "total_steps": 4530, "loss": 1.3728, "reward": null, "learning_rate": 1.3258108481544849e-05, "epoch": 1.97, "percentage": 65.56, "elapsed_time": "3:45:17", "remaining_time": "1:58:20"}
{"current_steps": 2980, "total_steps": 4530, "loss": 1.4581, "reward": null, "learning_rate": 1.310532801928942e-05, "epoch": 1.97, "percentage": 65.78, "elapsed_time": "3:45:59", "remaining_time": "1:57:32"}
{"current_steps": 2990, "total_steps": 4530, "loss": 1.3678, "reward": null, "learning_rate": 1.2953119633484903e-05, "epoch": 1.98, "percentage": 66.0, "elapsed_time": "3:46:42", "remaining_time": "1:56:46"}
{"current_steps": 3000, "total_steps": 4530, "loss": 1.4091, "reward": null, "learning_rate": 1.2801490644621789e-05, "epoch": 1.99, "percentage": 66.23, "elapsed_time": "3:47:26", "remaining_time": "1:55:59"}
{"current_steps": 3010, "total_steps": 4530, "loss": 1.3642, "reward": null, "learning_rate": 1.2650448345324384e-05, "epoch": 1.99, "percentage": 66.45, "elapsed_time": "3:48:27", "remaining_time": "1:55:21"}
{"current_steps": 3020, "total_steps": 4530, "loss": 1.3949, "reward": null, "learning_rate": 1.2500000000000006e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:49:12", "remaining_time": "1:54:36"}
{"current_steps": 3030, "total_steps": 4530, "loss": 1.3507, "reward": null, "learning_rate": 1.235015284448969e-05, "epoch": 2.01, "percentage": 66.89, "elapsed_time": "3:49:55", "remaining_time": "1:53:49"}
{"current_steps": 3040, "total_steps": 4530, "loss": 1.3553, "reward": null, "learning_rate": 1.2200914085720119e-05, "epoch": 2.01, "percentage": 67.11, "elapsed_time": "3:50:39", "remaining_time": "1:53:03"}
{"current_steps": 3050, "total_steps": 4530, "loss": 1.4108, "reward": null, "learning_rate": 1.2052290901357025e-05, "epoch": 2.02, "percentage": 67.33, "elapsed_time": "3:51:21", "remaining_time": "1:52:16"}
{"current_steps": 3060, "total_steps": 4530, "loss": 1.3549, "reward": null, "learning_rate": 1.1904290439459973e-05, "epoch": 2.03, "percentage": 67.55, "elapsed_time": "3:52:05", "remaining_time": "1:51:29"}
{"current_steps": 3070, "total_steps": 4530, "loss": 1.3371, "reward": null, "learning_rate": 1.175691981813858e-05, "epoch": 2.03, "percentage": 67.77, "elapsed_time": "3:52:51", "remaining_time": "1:50:44"}
{"current_steps": 3080, "total_steps": 4530, "loss": 1.3775, "reward": null, "learning_rate": 1.1610186125210151e-05, "epoch": 2.04, "percentage": 67.99, "elapsed_time": "3:53:33", "remaining_time": "1:49:57"}
{"current_steps": 3090, "total_steps": 4530, "loss": 1.3884, "reward": null, "learning_rate": 1.1464096417858822e-05, "epoch": 2.05, "percentage": 68.21, "elapsed_time": "3:54:18", "remaining_time": "1:49:11"}
{"current_steps": 3100, "total_steps": 4530, "loss": 1.3516, "reward": null, "learning_rate": 1.1318657722296097e-05, "epoch": 2.05, "percentage": 68.43, "elapsed_time": "3:54:59", "remaining_time": "1:48:24"}
{"current_steps": 3110, "total_steps": 4530, "loss": 1.405, "reward": null, "learning_rate": 1.1173877033422994e-05, "epoch": 2.06, "percentage": 68.65, "elapsed_time": "3:56:02", "remaining_time": "1:47:46"}
{"current_steps": 3120, "total_steps": 4530, "loss": 1.3909, "reward": null, "learning_rate": 1.102976131449352e-05, "epoch": 2.07, "percentage": 68.87, "elapsed_time": "3:56:44", "remaining_time": "1:46:59"}
{"current_steps": 3130, "total_steps": 4530, "loss": 1.4057, "reward": null, "learning_rate": 1.0886317496779863e-05, "epoch": 2.07, "percentage": 69.09, "elapsed_time": "3:57:27", "remaining_time": "1:46:12"}
{"current_steps": 3140, "total_steps": 4530, "loss": 1.3807, "reward": null, "learning_rate": 1.0743552479238994e-05, "epoch": 2.08, "percentage": 69.32, "elapsed_time": "3:58:11", "remaining_time": "1:45:26"}
{"current_steps": 3150, "total_steps": 4530, "loss": 1.3804, "reward": null, "learning_rate": 1.0601473128180855e-05, "epoch": 2.09, "percentage": 69.54, "elapsed_time": "3:58:55", "remaining_time": "1:44:40"}
{"current_steps": 3160, "total_steps": 4530, "loss": 1.3368, "reward": null, "learning_rate": 1.0460086276938144e-05, "epoch": 2.09, "percentage": 69.76, "elapsed_time": "3:59:38", "remaining_time": "1:43:53"}
{"current_steps": 3170, "total_steps": 4530, "loss": 1.3465, "reward": null, "learning_rate": 1.0319398725537644e-05, "epoch": 2.1, "percentage": 69.98, "elapsed_time": "4:00:22", "remaining_time": "1:43:07"}
{"current_steps": 3180, "total_steps": 4530, "loss": 1.3716, "reward": null, "learning_rate": 1.0179417240373183e-05, "epoch": 2.11, "percentage": 70.2, "elapsed_time": "4:01:04", "remaining_time": "1:42:20"}
{"current_steps": 3190, "total_steps": 4530, "loss": 1.3833, "reward": null, "learning_rate": 1.0040148553880205e-05, "epoch": 2.11, "percentage": 70.42, "elapsed_time": "4:01:47", "remaining_time": "1:41:33"}
{"current_steps": 3200, "total_steps": 4530, "loss": 1.3893, "reward": null, "learning_rate": 9.90159936421197e-06, "epoch": 2.12, "percentage": 70.64, "elapsed_time": "4:02:29", "remaining_time": "1:40:47"}
{"current_steps": 3210, "total_steps": 4530, "loss": 1.4088, "reward": null, "learning_rate": 9.763776334917399e-06, "epoch": 2.13, "percentage": 70.86, "elapsed_time": "4:03:32", "remaining_time": "1:40:08"}
{"current_steps": 3220, "total_steps": 4530, "loss": 1.402, "reward": null, "learning_rate": 9.626686094620608e-06, "epoch": 2.13, "percentage": 71.08, "elapsed_time": "4:04:14", "remaining_time": "1:39:21"}
{"current_steps": 3230, "total_steps": 4530, "loss": 1.3151, "reward": null, "learning_rate": 9.490335236702075e-06, "epoch": 2.14, "percentage": 71.3, "elapsed_time": "4:04:57", "remaining_time": "1:38:35"}
{"current_steps": 3240, "total_steps": 4530, "loss": 1.4126, "reward": null, "learning_rate": 9.354730318981562e-06, "epoch": 2.15, "percentage": 71.52, "elapsed_time": "4:05:40", "remaining_time": "1:37:48"}
{"current_steps": 3250, "total_steps": 4530, "loss": 1.431, "reward": null, "learning_rate": 9.219877863402682e-06, "epoch": 2.15, "percentage": 71.74, "elapsed_time": "4:06:23", "remaining_time": "1:37:02"}
{"current_steps": 3260, "total_steps": 4530, "loss": 1.3843, "reward": null, "learning_rate": 9.085784355719257e-06, "epoch": 2.16, "percentage": 71.96, "elapsed_time": "4:07:06", "remaining_time": "1:36:15"}
{"current_steps": 3270, "total_steps": 4530, "loss": 1.3513, "reward": null, "learning_rate": 8.95245624518336e-06, "epoch": 2.17, "percentage": 72.19, "elapsed_time": "4:07:51", "remaining_time": "1:35:30"}
{"current_steps": 3280, "total_steps": 4530, "loss": 1.362, "reward": null, "learning_rate": 8.819899944235152e-06, "epoch": 2.17, "percentage": 72.41, "elapsed_time": "4:08:35", "remaining_time": "1:34:44"}
{"current_steps": 3290, "total_steps": 4530, "loss": 1.3979, "reward": null, "learning_rate": 8.688121828194462e-06, "epoch": 2.18, "percentage": 72.63, "elapsed_time": "4:09:17", "remaining_time": "1:33:57"}
{"current_steps": 3300, "total_steps": 4530, "loss": 1.3949, "reward": null, "learning_rate": 8.55712823495419e-06, "epoch": 2.18, "percentage": 72.85, "elapsed_time": "4:10:01", "remaining_time": "1:33:11"}
{"current_steps": 3310, "total_steps": 4530, "loss": 1.3912, "reward": null, "learning_rate": 8.426925464675433e-06, "epoch": 2.19, "percentage": 73.07, "elapsed_time": "4:11:04", "remaining_time": "1:32:32"}
{"current_steps": 3320, "total_steps": 4530, "loss": 1.35, "reward": null, "learning_rate": 8.297519779484541e-06, "epoch": 2.2, "percentage": 73.29, "elapsed_time": "4:11:47", "remaining_time": "1:31:45"}
{"current_steps": 3330, "total_steps": 4530, "loss": 1.3528, "reward": null, "learning_rate": 8.168917403171891e-06, "epoch": 2.2, "percentage": 73.51, "elapsed_time": "4:12:33", "remaining_time": "1:31:00"}
{"current_steps": 3340, "total_steps": 4530, "loss": 1.3743, "reward": null, "learning_rate": 8.041124520892598e-06, "epoch": 2.21, "percentage": 73.73, "elapsed_time": "4:13:19", "remaining_time": "1:30:15"}
{"current_steps": 3350, "total_steps": 4530, "loss": 1.3708, "reward": null, "learning_rate": 7.91414727886898e-06, "epoch": 2.22, "percentage": 73.95, "elapsed_time": "4:14:05", "remaining_time": "1:29:30"}
{"current_steps": 3360, "total_steps": 4530, "loss": 1.4525, "reward": null, "learning_rate": 7.787991784095e-06, "epoch": 2.22, "percentage": 74.17, "elapsed_time": "4:14:46", "remaining_time": "1:28:43"}
{"current_steps": 3370, "total_steps": 4530, "loss": 1.3708, "reward": null, "learning_rate": 7.662664104042538e-06, "epoch": 2.23, "percentage": 74.39, "elapsed_time": "4:15:29", "remaining_time": "1:27:56"}
{"current_steps": 3380, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 7.538170266369563e-06, "epoch": 2.24, "percentage": 74.61, "elapsed_time": "4:16:13", "remaining_time": "1:27:10"}
{"current_steps": 3390, "total_steps": 4530, "loss": 1.3853, "reward": null, "learning_rate": 7.414516258630244e-06, "epoch": 2.24, "percentage": 74.83, "elapsed_time": "4:16:55", "remaining_time": "1:26:24"}
{"current_steps": 3400, "total_steps": 4530, "loss": 1.3861, "reward": null, "learning_rate": 7.291708027986988e-06, "epoch": 2.25, "percentage": 75.06, "elapsed_time": "4:17:38", "remaining_time": "1:25:37"}
{"current_steps": 3410, "total_steps": 4530, "loss": 1.3738, "reward": null, "learning_rate": 7.169751480924361e-06, "epoch": 2.26, "percentage": 75.28, "elapsed_time": "4:18:41", "remaining_time": "1:24:58"}
{"current_steps": 3420, "total_steps": 4530, "loss": 1.3908, "reward": null, "learning_rate": 7.048652482965079e-06, "epoch": 2.26, "percentage": 75.5, "elapsed_time": "4:19:23", "remaining_time": "1:24:11"}
{"current_steps": 3430, "total_steps": 4530, "loss": 1.3652, "reward": null, "learning_rate": 6.928416858387874e-06, "epoch": 2.27, "percentage": 75.72, "elapsed_time": "4:20:09", "remaining_time": "1:23:26"}
{"current_steps": 3440, "total_steps": 4530, "loss": 1.3673, "reward": null, "learning_rate": 6.809050389947363e-06, "epoch": 2.28, "percentage": 75.94, "elapsed_time": "4:20:54", "remaining_time": "1:22:40"}
{"current_steps": 3450, "total_steps": 4530, "loss": 1.395, "reward": null, "learning_rate": 6.690558818595943e-06, "epoch": 2.28, "percentage": 76.16, "elapsed_time": "4:21:39", "remaining_time": "1:21:54"}
{"current_steps": 3460, "total_steps": 4530, "loss": 1.3734, "reward": null, "learning_rate": 6.5729478432076775e-06, "epoch": 2.29, "percentage": 76.38, "elapsed_time": "4:22:23", "remaining_time": "1:21:08"}
{"current_steps": 3470, "total_steps": 4530, "loss": 1.4366, "reward": null, "learning_rate": 6.456223120304192e-06, "epoch": 2.3, "percentage": 76.6, "elapsed_time": "4:23:02", "remaining_time": "1:20:21"}
{"current_steps": 3480, "total_steps": 4530, "loss": 1.4222, "reward": null, "learning_rate": 6.340390263782655e-06, "epoch": 2.3, "percentage": 76.82, "elapsed_time": "4:23:43", "remaining_time": "1:19:34"}
{"current_steps": 3490, "total_steps": 4530, "loss": 1.3545, "reward": null, "learning_rate": 6.22545484464574e-06, "epoch": 2.31, "percentage": 77.04, "elapsed_time": "4:24:29", "remaining_time": "1:18:49"}
{"current_steps": 3500, "total_steps": 4530, "loss": 1.3581, "reward": null, "learning_rate": 6.111422390733715e-06, "epoch": 2.32, "percentage": 77.26, "elapsed_time": "4:25:13", "remaining_time": "1:18:02"}
{"current_steps": 3510, "total_steps": 4530, "loss": 1.4052, "reward": null, "learning_rate": 5.998298386458545e-06, "epoch": 2.32, "percentage": 77.48, "elapsed_time": "4:26:17", "remaining_time": "1:17:23"}
{"current_steps": 3520, "total_steps": 4530, "loss": 1.3886, "reward": null, "learning_rate": 5.8860882725401665e-06, "epoch": 2.33, "percentage": 77.7, "elapsed_time": "4:27:02", "remaining_time": "1:16:37"}
{"current_steps": 3530, "total_steps": 4530, "loss": 1.3818, "reward": null, "learning_rate": 5.774797445744781e-06, "epoch": 2.34, "percentage": 77.92, "elapsed_time": "4:27:45", "remaining_time": "1:15:51"}
{"current_steps": 3540, "total_steps": 4530, "loss": 1.3817, "reward": null, "learning_rate": 5.664431258625305e-06, "epoch": 2.34, "percentage": 78.15, "elapsed_time": "4:28:25", "remaining_time": "1:15:04"}
{"current_steps": 3550, "total_steps": 4530, "loss": 1.3617, "reward": null, "learning_rate": 5.55499501926394e-06, "epoch": 2.35, "percentage": 78.37, "elapsed_time": "4:29:09", "remaining_time": "1:14:18"}
{"current_steps": 3560, "total_steps": 4530, "loss": 1.3768, "reward": null, "learning_rate": 5.446493991016879e-06, "epoch": 2.36, "percentage": 78.59, "elapsed_time": "4:29:50", "remaining_time": "1:13:31"}
{"current_steps": 3570, "total_steps": 4530, "loss": 1.3755, "reward": null, "learning_rate": 5.338933392261159e-06, "epoch": 2.36, "percentage": 78.81, "elapsed_time": "4:30:35", "remaining_time": "1:12:45"}
{"current_steps": 3580, "total_steps": 4530, "loss": 1.3823, "reward": null, "learning_rate": 5.23231839614369e-06, "epoch": 2.37, "percentage": 79.03, "elapsed_time": "4:31:20", "remaining_time": "1:12:00"}
{"current_steps": 3590, "total_steps": 4530, "loss": 1.3883, "reward": null, "learning_rate": 5.126654130332451e-06, "epoch": 2.38, "percentage": 79.25, "elapsed_time": "4:32:02", "remaining_time": "1:11:13"}
{"current_steps": 3600, "total_steps": 4530, "loss": 1.3988, "reward": null, "learning_rate": 5.02194567676986e-06, "epoch": 2.38, "percentage": 79.47, "elapsed_time": "4:32:44", "remaining_time": "1:10:27"}
{"current_steps": 3610, "total_steps": 4530, "loss": 1.3838, "reward": null, "learning_rate": 4.918198071428382e-06, "epoch": 2.39, "percentage": 79.69, "elapsed_time": "4:33:48", "remaining_time": "1:09:46"}
{"current_steps": 3620, "total_steps": 4530, "loss": 1.4422, "reward": null, "learning_rate": 4.815416304068298e-06, "epoch": 2.4, "percentage": 79.91, "elapsed_time": "4:34:36", "remaining_time": "1:09:01"}
{"current_steps": 3630, "total_steps": 4530, "loss": 1.3834, "reward": null, "learning_rate": 4.713605317997741e-06, "epoch": 2.4, "percentage": 80.13, "elapsed_time": "4:35:20", "remaining_time": "1:08:15"}
{"current_steps": 3640, "total_steps": 4530, "loss": 1.3743, "reward": null, "learning_rate": 4.61277000983493e-06, "epoch": 2.41, "percentage": 80.35, "elapsed_time": "4:36:00", "remaining_time": "1:07:29"}
{"current_steps": 3650, "total_steps": 4530, "loss": 1.451, "reward": null, "learning_rate": 4.51291522927268e-06, "epoch": 2.42, "percentage": 80.57, "elapsed_time": "4:36:40", "remaining_time": "1:06:42"}
{"current_steps": 3660, "total_steps": 4530, "loss": 1.3644, "reward": null, "learning_rate": 4.414045778845144e-06, "epoch": 2.42, "percentage": 80.79, "elapsed_time": "4:37:22", "remaining_time": "1:05:56"}
{"current_steps": 3670, "total_steps": 4530, "loss": 1.3944, "reward": null, "learning_rate": 4.316166413696851e-06, "epoch": 2.43, "percentage": 81.02, "elapsed_time": "4:38:05", "remaining_time": "1:05:09"}
{"current_steps": 3680, "total_steps": 4530, "loss": 1.3514, "reward": null, "learning_rate": 4.219281841353981e-06, "epoch": 2.44, "percentage": 81.24, "elapsed_time": "4:38:47", "remaining_time": "1:04:23"}
{"current_steps": 3690, "total_steps": 4530, "loss": 1.3389, "reward": null, "learning_rate": 4.123396721497977e-06, "epoch": 2.44, "percentage": 81.46, "elapsed_time": "4:39:30", "remaining_time": "1:03:37"}
{"current_steps": 3700, "total_steps": 4530, "loss": 1.3792, "reward": null, "learning_rate": 4.028515665741439e-06, "epoch": 2.45, "percentage": 81.68, "elapsed_time": "4:40:13", "remaining_time": "1:02:51"}
{"current_steps": 3710, "total_steps": 4530, "loss": 1.3686, "reward": null, "learning_rate": 3.934643237406291e-06, "epoch": 2.46, "percentage": 81.9, "elapsed_time": "4:41:18", "remaining_time": "1:02:10"}
{"current_steps": 3720, "total_steps": 4530, "loss": 1.3424, "reward": null, "learning_rate": 3.8417839513043645e-06, "epoch": 2.46, "percentage": 82.12, "elapsed_time": "4:42:03", "remaining_time": "1:01:25"}
{"current_steps": 3730, "total_steps": 4530, "loss": 1.3684, "reward": null, "learning_rate": 3.7499422735202127e-06, "epoch": 2.47, "percentage": 82.34, "elapsed_time": "4:42:45", "remaining_time": "1:00:38"}
{"current_steps": 3740, "total_steps": 4530, "loss": 1.3868, "reward": null, "learning_rate": 3.6591226211963287e-06, "epoch": 2.48, "percentage": 82.56, "elapsed_time": "4:43:28", "remaining_time": "0:59:52"}
{"current_steps": 3750, "total_steps": 4530, "loss": 1.368, "reward": null, "learning_rate": 3.5693293623207086e-06, "epoch": 2.48, "percentage": 82.78, "elapsed_time": "4:44:12", "remaining_time": "0:59:06"}
{"current_steps": 3760, "total_steps": 4530, "loss": 1.3027, "reward": null, "learning_rate": 3.480566815516756e-06, "epoch": 2.49, "percentage": 83.0, "elapsed_time": "4:44:59", "remaining_time": "0:58:21"}
{"current_steps": 3770, "total_steps": 4530, "loss": 1.4223, "reward": null, "learning_rate": 3.3928392498355916e-06, "epoch": 2.5, "percentage": 83.22, "elapsed_time": "4:45:40", "remaining_time": "0:57:35"}
{"current_steps": 3780, "total_steps": 4530, "loss": 1.3674, "reward": null, "learning_rate": 3.3061508845507323e-06, "epoch": 2.5, "percentage": 83.44, "elapsed_time": "4:46:26", "remaining_time": "0:56:49"}
{"current_steps": 3790, "total_steps": 4530, "loss": 1.3848, "reward": null, "learning_rate": 3.22050588895515e-06, "epoch": 2.51, "percentage": 83.66, "elapsed_time": "4:47:11", "remaining_time": "0:56:04"}
{"current_steps": 3800, "total_steps": 4530, "loss": 1.4191, "reward": null, "learning_rate": 3.135908382160771e-06, "epoch": 2.52, "percentage": 83.89, "elapsed_time": "4:47:54", "remaining_time": "0:55:18"}
{"current_steps": 3810, "total_steps": 4530, "loss": 1.3796, "reward": null, "learning_rate": 3.0523624329003324e-06, "epoch": 2.52, "percentage": 84.11, "elapsed_time": "4:49:00", "remaining_time": "0:54:37"}
{"current_steps": 3820, "total_steps": 4530, "loss": 1.4101, "reward": null, "learning_rate": 2.969872059331738e-06, "epoch": 2.53, "percentage": 84.33, "elapsed_time": "4:49:44", "remaining_time": "0:53:51"}
{"current_steps": 3830, "total_steps": 4530, "loss": 1.379, "reward": null, "learning_rate": 2.8884412288447737e-06, "epoch": 2.54, "percentage": 84.55, "elapsed_time": "4:50:27", "remaining_time": "0:53:05"}
{"current_steps": 3840, "total_steps": 4530, "loss": 1.3881, "reward": null, "learning_rate": 2.8080738578703054e-06, "epoch": 2.54, "percentage": 84.77, "elapsed_time": "4:51:09", "remaining_time": "0:52:19"}
{"current_steps": 3850, "total_steps": 4530, "loss": 1.3464, "reward": null, "learning_rate": 2.728773811691923e-06, "epoch": 2.55, "percentage": 84.99, "elapsed_time": "4:51:54", "remaining_time": "0:51:33"}
{"current_steps": 3860, "total_steps": 4530, "loss": 1.367, "reward": null, "learning_rate": 2.6505449042600244e-06, "epoch": 2.56, "percentage": 85.21, "elapsed_time": "4:52:39", "remaining_time": "0:50:47"}
{"current_steps": 3870, "total_steps": 4530, "loss": 1.3498, "reward": null, "learning_rate": 2.5733908980083988e-06, "epoch": 2.56, "percentage": 85.43, "elapsed_time": "4:53:24", "remaining_time": "0:50:02"}
{"current_steps": 3880, "total_steps": 4530, "loss": 1.3895, "reward": null, "learning_rate": 2.4973155036732534e-06, "epoch": 2.57, "percentage": 85.65, "elapsed_time": "4:54:06", "remaining_time": "0:49:16"}
{"current_steps": 3890, "total_steps": 4530, "loss": 1.4072, "reward": null, "learning_rate": 2.422322380114772e-06, "epoch": 2.58, "percentage": 85.87, "elapsed_time": "4:54:47", "remaining_time": "0:48:30"}
{"current_steps": 3900, "total_steps": 4530, "loss": 1.347, "reward": null, "learning_rate": 2.348415134141102e-06, "epoch": 2.58, "percentage": 86.09, "elapsed_time": "4:55:33", "remaining_time": "0:47:44"}
{"current_steps": 3910, "total_steps": 4530, "loss": 1.3605, "reward": null, "learning_rate": 2.2755973203349294e-06, "epoch": 2.59, "percentage": 86.31, "elapsed_time": "4:56:36", "remaining_time": "0:47:02"}
{"current_steps": 3920, "total_steps": 4530, "loss": 1.3105, "reward": null, "learning_rate": 2.2038724408824844e-06, "epoch": 2.6, "percentage": 86.53, "elapsed_time": "4:57:21", "remaining_time": "0:46:16"}
{"current_steps": 3930, "total_steps": 4530, "loss": 1.3718, "reward": null, "learning_rate": 2.133243945405128e-06, "epoch": 2.6, "percentage": 86.75, "elapsed_time": "4:58:06", "remaining_time": "0:45:30"}
{"current_steps": 3940, "total_steps": 4530, "loss": 1.3293, "reward": null, "learning_rate": 2.0637152307934228e-06, "epoch": 2.61, "percentage": 86.98, "elapsed_time": "4:58:53", "remaining_time": "0:44:45"}
{"current_steps": 3950, "total_steps": 4530, "loss": 1.3677, "reward": null, "learning_rate": 1.995289641043768e-06, "epoch": 2.62, "percentage": 87.2, "elapsed_time": "4:59:35", "remaining_time": "0:43:59"}
{"current_steps": 3960, "total_steps": 4530, "loss": 1.409, "reward": null, "learning_rate": 1.927970467097573e-06, "epoch": 2.62, "percentage": 87.42, "elapsed_time": "5:00:16", "remaining_time": "0:43:13"}
{"current_steps": 3970, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 1.8617609466829666e-06, "epoch": 2.63, "percentage": 87.64, "elapsed_time": "5:01:01", "remaining_time": "0:42:27"}
{"current_steps": 3980, "total_steps": 4530, "loss": 1.3991, "reward": null, "learning_rate": 1.7966642641590925e-06, "epoch": 2.64, "percentage": 87.86, "elapsed_time": "5:01:43", "remaining_time": "0:41:41"}
{"current_steps": 3990, "total_steps": 4530, "loss": 1.3662, "reward": null, "learning_rate": 1.732683550362954e-06, "epoch": 2.64, "percentage": 88.08, "elapsed_time": "5:02:25", "remaining_time": "0:40:55"}
{"current_steps": 4000, "total_steps": 4530, "loss": 1.3871, "reward": null, "learning_rate": 1.6698218824588164e-06, "epoch": 2.65, "percentage": 88.3, "elapsed_time": "5:03:09", "remaining_time": "0:40:10"}
{"current_steps": 4010, "total_steps": 4530, "loss": 1.4072, "reward": null, "learning_rate": 1.6080822837902382e-06, "epoch": 2.65, "percentage": 88.52, "elapsed_time": "5:04:12", "remaining_time": "0:39:26"}
{"current_steps": 4020, "total_steps": 4530, "loss": 1.3841, "reward": null, "learning_rate": 1.5474677237346468e-06, "epoch": 2.66, "percentage": 88.74, "elapsed_time": "5:04:57", "remaining_time": "0:38:41"}
{"current_steps": 4030, "total_steps": 4530, "loss": 1.3729, "reward": null, "learning_rate": 1.4879811175605302e-06, "epoch": 2.67, "percentage": 88.96, "elapsed_time": "5:05:42", "remaining_time": "0:37:55"}
{"current_steps": 4040, "total_steps": 4530, "loss": 1.3648, "reward": null, "learning_rate": 1.4296253262872234e-06, "epoch": 2.67, "percentage": 89.18, "elapsed_time": "5:06:24", "remaining_time": "0:37:09"}
{"current_steps": 4050, "total_steps": 4530, "loss": 1.4043, "reward": null, "learning_rate": 1.3724031565473112e-06, "epoch": 2.68, "percentage": 89.4, "elapsed_time": "5:07:06", "remaining_time": "0:36:23"}
{"current_steps": 4060, "total_steps": 4530, "loss": 1.4135, "reward": null, "learning_rate": 1.316317360451641e-06, "epoch": 2.69, "percentage": 89.62, "elapsed_time": "5:07:50", "remaining_time": "0:35:38"}
{"current_steps": 4070, "total_steps": 4530, "loss": 1.399, "reward": null, "learning_rate": 1.2613706354569571e-06, "epoch": 2.69, "percentage": 89.85, "elapsed_time": "5:08:34", "remaining_time": "0:34:52"}
{"current_steps": 4080, "total_steps": 4530, "loss": 1.4024, "reward": null, "learning_rate": 1.2075656242361732e-06, "epoch": 2.7, "percentage": 90.07, "elapsed_time": "5:09:18", "remaining_time": "0:34:06"}
{"current_steps": 4090, "total_steps": 4530, "loss": 1.3668, "reward": null, "learning_rate": 1.1549049145512636e-06, "epoch": 2.71, "percentage": 90.29, "elapsed_time": "5:10:02", "remaining_time": "0:33:21"}
{"current_steps": 4100, "total_steps": 4530, "loss": 1.3692, "reward": null, "learning_rate": 1.1033910391288065e-06, "epoch": 2.71, "percentage": 90.51, "elapsed_time": "5:10:48", "remaining_time": "0:32:35"}
{"current_steps": 4110, "total_steps": 4530, "loss": 1.3908, "reward": null, "learning_rate": 1.0530264755381824e-06, "epoch": 2.72, "percentage": 90.73, "elapsed_time": "5:11:50", "remaining_time": "0:31:52"}
{"current_steps": 4120, "total_steps": 4530, "loss": 1.3999, "reward": null, "learning_rate": 1.0038136460723963e-06, "epoch": 2.73, "percentage": 90.95, "elapsed_time": "5:12:34", "remaining_time": "0:31:06"}
{"current_steps": 4130, "total_steps": 4530, "loss": 1.4098, "reward": null, "learning_rate": 9.557549176315934e-07, "epoch": 2.73, "percentage": 91.17, "elapsed_time": "5:13:16", "remaining_time": "0:30:20"}
{"current_steps": 4140, "total_steps": 4530, "loss": 1.3973, "reward": null, "learning_rate": 9.088526016092142e-07, "epoch": 2.74, "percentage": 91.39, "elapsed_time": "5:13:59", "remaining_time": "0:29:34"}
{"current_steps": 4150, "total_steps": 4530, "loss": 1.3758, "reward": null, "learning_rate": 8.631089537808307e-07, "epoch": 2.75, "percentage": 91.61, "elapsed_time": "5:14:41", "remaining_time": "0:28:48"}
{"current_steps": 4160, "total_steps": 4530, "loss": 1.3197, "reward": null, "learning_rate": 8.185261741956551e-07, "epoch": 2.75, "percentage": 91.83, "elapsed_time": "5:15:24", "remaining_time": "0:28:03"}
{"current_steps": 4170, "total_steps": 4530, "loss": 1.3794, "reward": null, "learning_rate": 7.751064070707248e-07, "epoch": 2.76, "percentage": 92.05, "elapsed_time": "5:16:10", "remaining_time": "0:27:17"}
{"current_steps": 4180, "total_steps": 4530, "loss": 1.3764, "reward": null, "learning_rate": 7.328517406877761e-07, "epoch": 2.77, "percentage": 92.27, "elapsed_time": "5:16:57", "remaining_time": "0:26:32"}
{"current_steps": 4190, "total_steps": 4530, "loss": 1.4063, "reward": null, "learning_rate": 6.917642072928137e-07, "epoch": 2.77, "percentage": 92.49, "elapsed_time": "5:17:38", "remaining_time": "0:25:46"}
{"current_steps": 4200, "total_steps": 4530, "loss": 1.3959, "reward": null, "learning_rate": 6.51845782998356e-07, "epoch": 2.78, "percentage": 92.72, "elapsed_time": "5:18:19", "remaining_time": "0:25:00"}
{"current_steps": 4210, "total_steps": 4530, "loss": 1.3767, "reward": null, "learning_rate": 6.130983876884155e-07, "epoch": 2.79, "percentage": 92.94, "elapsed_time": "5:19:24", "remaining_time": "0:24:16"}
{"current_steps": 4220, "total_steps": 4530, "loss": 1.3619, "reward": null, "learning_rate": 5.755238849261407e-07, "epoch": 2.79, "percentage": 93.16, "elapsed_time": "5:20:07", "remaining_time": "0:23:30"}
{"current_steps": 4230, "total_steps": 4530, "loss": 1.3723, "reward": null, "learning_rate": 5.391240818642007e-07, "epoch": 2.8, "percentage": 93.38, "elapsed_time": "5:20:48", "remaining_time": "0:22:45"}
{"current_steps": 4240, "total_steps": 4530, "loss": 1.4262, "reward": null, "learning_rate": 5.039007291578579e-07, "epoch": 2.81, "percentage": 93.6, "elapsed_time": "5:21:33", "remaining_time": "0:21:59"}
{"current_steps": 4250, "total_steps": 4530, "loss": 1.3775, "reward": null, "learning_rate": 4.698555208807853e-07, "epoch": 2.81, "percentage": 93.82, "elapsed_time": "5:22:16", "remaining_time": "0:21:13"}
{"current_steps": 4260, "total_steps": 4530, "loss": 1.4159, "reward": null, "learning_rate": 4.3699009444357344e-07, "epoch": 2.82, "percentage": 94.04, "elapsed_time": "5:22:58", "remaining_time": "0:20:28"}
{"current_steps": 4270, "total_steps": 4530, "loss": 1.4007, "reward": null, "learning_rate": 4.0530603051499584e-07, "epoch": 2.83, "percentage": 94.26, "elapsed_time": "5:23:38", "remaining_time": "0:19:42"}
{"current_steps": 4280, "total_steps": 4530, "loss": 1.3898, "reward": null, "learning_rate": 3.7480485294596747e-07, "epoch": 2.83, "percentage": 94.48, "elapsed_time": "5:24:23", "remaining_time": "0:18:56"}
{"current_steps": 4290, "total_steps": 4530, "loss": 1.4173, "reward": null, "learning_rate": 3.454880286962781e-07, "epoch": 2.84, "percentage": 94.7, "elapsed_time": "5:25:05", "remaining_time": "0:18:11"}
{"current_steps": 4300, "total_steps": 4530, "loss": 1.3539, "reward": null, "learning_rate": 3.1735696776400703e-07, "epoch": 2.85, "percentage": 94.92, "elapsed_time": "5:25:51", "remaining_time": "0:17:25"}
{"current_steps": 4310, "total_steps": 4530, "loss": 1.3803, "reward": null, "learning_rate": 2.9041302311774433e-07, "epoch": 2.85, "percentage": 95.14, "elapsed_time": "5:26:52", "remaining_time": "0:16:41"}
{"current_steps": 4320, "total_steps": 4530, "loss": 1.4141, "reward": null, "learning_rate": 2.646574906314925e-07, "epoch": 2.86, "percentage": 95.36, "elapsed_time": "5:27:35", "remaining_time": "0:15:55"}
{"current_steps": 4330, "total_steps": 4530, "loss": 1.3444, "reward": null, "learning_rate": 2.4009160902235816e-07, "epoch": 2.87, "percentage": 95.58, "elapsed_time": "5:28:18", "remaining_time": "0:15:09"}
{"current_steps": 4340, "total_steps": 4530, "loss": 1.3669, "reward": null, "learning_rate": 2.1671655979096094e-07, "epoch": 2.87, "percentage": 95.81, "elapsed_time": "5:29:03", "remaining_time": "0:14:24"}
{"current_steps": 4350, "total_steps": 4530, "loss": 1.3776, "reward": null, "learning_rate": 1.9453346716462317e-07, "epoch": 2.88, "percentage": 96.03, "elapsed_time": "5:29:46", "remaining_time": "0:13:38"}
{"current_steps": 4360, "total_steps": 4530, "loss": 1.4048, "reward": null, "learning_rate": 1.73543398043291e-07, "epoch": 2.89, "percentage": 96.25, "elapsed_time": "5:30:28", "remaining_time": "0:12:53"}
{"current_steps": 4370, "total_steps": 4530, "loss": 1.3623, "reward": null, "learning_rate": 1.537473619482227e-07, "epoch": 2.89, "percentage": 96.47, "elapsed_time": "5:31:09", "remaining_time": "0:12:07"}
{"current_steps": 4380, "total_steps": 4530, "loss": 1.3861, "reward": null, "learning_rate": 1.351463109734441e-07, "epoch": 2.9, "percentage": 96.69, "elapsed_time": "5:31:48", "remaining_time": "0:11:21"}
{"current_steps": 4390, "total_steps": 4530, "loss": 1.3323, "reward": null, "learning_rate": 1.1774113973994083e-07, "epoch": 2.91, "percentage": 96.91, "elapsed_time": "5:32:32", "remaining_time": "0:10:36"}
{"current_steps": 4400, "total_steps": 4530, "loss": 1.3646, "reward": null, "learning_rate": 1.0153268535264827e-07, "epoch": 2.91, "percentage": 97.13, "elapsed_time": "5:33:15", "remaining_time": "0:09:50"}
{"current_steps": 4410, "total_steps": 4530, "loss": 1.3963, "reward": null, "learning_rate": 8.652172736017816e-08, "epoch": 2.92, "percentage": 97.35, "elapsed_time": "5:34:18", "remaining_time": "0:09:05"}
{"current_steps": 4420, "total_steps": 4530, "loss": 1.3812, "reward": null, "learning_rate": 7.270898771733481e-08, "epoch": 2.93, "percentage": 97.57, "elapsed_time": "5:35:04", "remaining_time": "0:08:20"}
{"current_steps": 4430, "total_steps": 4530, "loss": 1.375, "reward": null, "learning_rate": 6.00951307503872e-08, "epoch": 2.93, "percentage": 97.79, "elapsed_time": "5:35:47", "remaining_time": "0:07:34"}
{"current_steps": 4440, "total_steps": 4530, "loss": 1.4015, "reward": null, "learning_rate": 4.868076312512515e-08, "epoch": 2.94, "percentage": 98.01, "elapsed_time": "5:36:30", "remaining_time": "0:06:49"}
{"current_steps": 4450, "total_steps": 4530, "loss": 1.3795, "reward": null, "learning_rate": 3.846643381766879e-08, "epoch": 2.95, "percentage": 98.23, "elapsed_time": "5:37:12", "remaining_time": "0:06:03"}
{"current_steps": 4460, "total_steps": 4530, "loss": 1.4244, "reward": null, "learning_rate": 2.94526340880813e-08, "epoch": 2.95, "percentage": 98.45, "elapsed_time": "5:37:53", "remaining_time": "0:05:18"}
{"current_steps": 4470, "total_steps": 4530, "loss": 1.3731, "reward": null, "learning_rate": 2.1639797456723952e-08, "epoch": 2.96, "percentage": 98.68, "elapsed_time": "5:38:37", "remaining_time": "0:04:32"}
{"current_steps": 4480, "total_steps": 4530, "loss": 1.4061, "reward": null, "learning_rate": 1.5028299683425562e-08, "epoch": 2.97, "percentage": 98.9, "elapsed_time": "5:39:21", "remaining_time": "0:03:47"}
{"current_steps": 4490, "total_steps": 4530, "loss": 1.3842, "reward": null, "learning_rate": 9.618458749391379e-09, "epoch": 2.97, "percentage": 99.12, "elapsed_time": "5:40:04", "remaining_time": "0:03:01"}
{"current_steps": 4500, "total_steps": 4530, "loss": 1.3693, "reward": null, "learning_rate": 5.41053484192644e-09, "epoch": 2.98, "percentage": 99.34, "elapsed_time": "5:40:45", "remaining_time": "0:02:16"}
{"current_steps": 4510, "total_steps": 4530, "loss": 1.3439, "reward": null, "learning_rate": 2.4047303419094667e-09, "epoch": 2.99, "percentage": 99.56, "elapsed_time": "5:41:51", "remaining_time": "0:01:30"}
{"current_steps": 4520, "total_steps": 4530, "loss": 1.3848, "reward": null, "learning_rate": 6.011898140617645e-10, "epoch": 2.99, "percentage": 99.78, "elapsed_time": "5:42:37", "remaining_time": "0:00:45"}
{"current_steps": 4530, "total_steps": 4530, "loss": 1.3852, "reward": null, "learning_rate": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:43:21", "remaining_time": "0:00:00"}