Jinwu01's picture
Upload folder using huggingface_hub
c3dc34b verified
{"current_steps": 10, "total_steps": 5000, "loss": 1.5623, "lr": 1.0000000000000002e-06, "epoch": 0.002, "percentage": 0.2, "elapsed_time": "0:00:02", "remaining_time": "0:19:52"}
{"current_steps": 20, "total_steps": 5000, "loss": 1.6985, "lr": 2.0000000000000003e-06, "epoch": 0.004, "percentage": 0.4, "elapsed_time": "0:00:03", "remaining_time": "0:16:30"}
{"current_steps": 30, "total_steps": 5000, "loss": 2.4223, "lr": 3e-06, "epoch": 0.006, "percentage": 0.6, "elapsed_time": "0:00:05", "remaining_time": "0:14:38"}
{"current_steps": 40, "total_steps": 5000, "loss": 1.5449, "lr": 4.000000000000001e-06, "epoch": 0.008, "percentage": 0.8, "elapsed_time": "0:00:07", "remaining_time": "0:14:39"}
{"current_steps": 50, "total_steps": 5000, "loss": 4.1625, "lr": 5e-06, "epoch": 0.01, "percentage": 1.0, "elapsed_time": "0:00:08", "remaining_time": "0:14:33"}
{"current_steps": 60, "total_steps": 5000, "loss": 2.6362, "lr": 6e-06, "epoch": 0.012, "percentage": 1.2, "elapsed_time": "0:00:11", "remaining_time": "0:15:18"}
{"current_steps": 70, "total_steps": 5000, "loss": 2.5902, "lr": 7.000000000000001e-06, "epoch": 0.014, "percentage": 1.4, "elapsed_time": "0:00:13", "remaining_time": "0:16:18"}
{"current_steps": 80, "total_steps": 5000, "loss": 1.5789, "lr": 8.000000000000001e-06, "epoch": 0.016, "percentage": 1.6, "elapsed_time": "0:00:16", "remaining_time": "0:16:50"}
{"current_steps": 90, "total_steps": 5000, "loss": 2.3014, "lr": 9e-06, "epoch": 0.018, "percentage": 1.8, "elapsed_time": "0:00:19", "remaining_time": "0:17:18"}
{"current_steps": 100, "total_steps": 5000, "loss": 1.8938, "lr": 1e-05, "epoch": 0.02, "percentage": 2.0, "elapsed_time": "0:00:22", "remaining_time": "0:17:59"}
{"current_steps": 110, "total_steps": 5000, "loss": 1.8176, "lr": 1.1000000000000001e-05, "epoch": 0.022, "percentage": 2.2, "elapsed_time": "0:00:23", "remaining_time": "0:17:38"}
{"current_steps": 120, "total_steps": 5000, "loss": 1.471, "lr": 1.2e-05, "epoch": 0.024, "percentage": 2.4, "elapsed_time": "0:00:26", "remaining_time": "0:17:39"}
{"current_steps": 130, "total_steps": 5000, "loss": 3.5099, "lr": 1.3000000000000001e-05, "epoch": 0.026, "percentage": 2.6, "elapsed_time": "0:00:28", "remaining_time": "0:17:30"}
{"current_steps": 140, "total_steps": 5000, "loss": 1.9727, "lr": 1.4000000000000001e-05, "epoch": 0.028, "percentage": 2.8, "elapsed_time": "0:00:30", "remaining_time": "0:17:25"}
{"current_steps": 150, "total_steps": 5000, "loss": 1.4055, "lr": 1.5e-05, "epoch": 0.03, "percentage": 3.0, "elapsed_time": "0:00:31", "remaining_time": "0:17:07"}
{"current_steps": 160, "total_steps": 5000, "loss": 1.0116, "lr": 1.6000000000000003e-05, "epoch": 0.032, "percentage": 3.2, "elapsed_time": "0:00:33", "remaining_time": "0:17:03"}
{"current_steps": 170, "total_steps": 5000, "loss": 3.2501, "lr": 1.7000000000000003e-05, "epoch": 0.034, "percentage": 3.4, "elapsed_time": "0:00:36", "remaining_time": "0:17:08"}
{"current_steps": 180, "total_steps": 5000, "loss": 1.2368, "lr": 1.8e-05, "epoch": 0.036, "percentage": 3.6, "elapsed_time": "0:00:38", "remaining_time": "0:17:05"}
{"current_steps": 190, "total_steps": 5000, "loss": 1.1736, "lr": 1.9e-05, "epoch": 0.038, "percentage": 3.8, "elapsed_time": "0:00:39", "remaining_time": "0:16:44"}
{"current_steps": 200, "total_steps": 5000, "loss": 1.8787, "lr": 2e-05, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:41", "remaining_time": "0:16:28"}
{"current_steps": 210, "total_steps": 5000, "loss": 1.136, "lr": 2.1e-05, "epoch": 0.042, "percentage": 4.2, "elapsed_time": "0:00:42", "remaining_time": "0:16:08"}
{"current_steps": 220, "total_steps": 5000, "loss": 1.4965, "lr": 2.2000000000000003e-05, "epoch": 0.044, "percentage": 4.4, "elapsed_time": "0:00:44", "remaining_time": "0:15:56"}
{"current_steps": 230, "total_steps": 5000, "loss": 1.0649, "lr": 2.3000000000000003e-05, "epoch": 0.046, "percentage": 4.6, "elapsed_time": "0:00:45", "remaining_time": "0:15:47"}
{"current_steps": 240, "total_steps": 5000, "loss": 2.5735, "lr": 2.4e-05, "epoch": 0.048, "percentage": 4.8, "elapsed_time": "0:00:47", "remaining_time": "0:15:37"}
{"current_steps": 250, "total_steps": 5000, "loss": 1.7272, "lr": 2.5e-05, "epoch": 0.05, "percentage": 5.0, "elapsed_time": "0:00:48", "remaining_time": "0:15:28"}
{"current_steps": 260, "total_steps": 5000, "loss": 0.8727, "lr": 2.6000000000000002e-05, "epoch": 0.052, "percentage": 5.2, "elapsed_time": "0:00:50", "remaining_time": "0:15:17"}
{"current_steps": 270, "total_steps": 5000, "loss": 0.6941, "lr": 2.7000000000000002e-05, "epoch": 0.054, "percentage": 5.4, "elapsed_time": "0:00:51", "remaining_time": "0:15:09"}
{"current_steps": 280, "total_steps": 5000, "loss": 0.9007, "lr": 2.8000000000000003e-05, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:00:53", "remaining_time": "0:15:00"}
{"current_steps": 290, "total_steps": 5000, "loss": 0.8201, "lr": 2.9e-05, "epoch": 0.058, "percentage": 5.8, "elapsed_time": "0:00:54", "remaining_time": "0:14:52"}
{"current_steps": 300, "total_steps": 5000, "loss": 0.7618, "lr": 3e-05, "epoch": 0.06, "percentage": 6.0, "elapsed_time": "0:00:56", "remaining_time": "0:14:48"}
{"current_steps": 310, "total_steps": 5000, "loss": 1.1848, "lr": 3.1e-05, "epoch": 0.062, "percentage": 6.2, "elapsed_time": "0:00:58", "remaining_time": "0:14:42"}
{"current_steps": 320, "total_steps": 5000, "loss": 0.2964, "lr": 3.2000000000000005e-05, "epoch": 0.064, "percentage": 6.4, "elapsed_time": "0:00:59", "remaining_time": "0:14:29"}
{"current_steps": 330, "total_steps": 5000, "loss": 0.9551, "lr": 3.3e-05, "epoch": 0.066, "percentage": 6.6, "elapsed_time": "0:01:01", "remaining_time": "0:14:24"}
{"current_steps": 340, "total_steps": 5000, "loss": 0.7661, "lr": 3.4000000000000007e-05, "epoch": 0.068, "percentage": 6.8, "elapsed_time": "0:01:02", "remaining_time": "0:14:14"}
{"current_steps": 350, "total_steps": 5000, "loss": 0.7432, "lr": 3.5e-05, "epoch": 0.07, "percentage": 7.0, "elapsed_time": "0:01:03", "remaining_time": "0:14:06"}
{"current_steps": 360, "total_steps": 5000, "loss": 0.4258, "lr": 3.6e-05, "epoch": 0.072, "percentage": 7.2, "elapsed_time": "0:01:04", "remaining_time": "0:13:57"}
{"current_steps": 370, "total_steps": 5000, "loss": 0.6312, "lr": 3.7e-05, "epoch": 0.074, "percentage": 7.4, "elapsed_time": "0:01:06", "remaining_time": "0:13:51"}
{"current_steps": 380, "total_steps": 5000, "loss": 0.8, "lr": 3.8e-05, "epoch": 0.076, "percentage": 7.6, "elapsed_time": "0:01:07", "remaining_time": "0:13:44"}
{"current_steps": 390, "total_steps": 5000, "loss": 1.5303, "lr": 3.9000000000000006e-05, "epoch": 0.078, "percentage": 7.8, "elapsed_time": "0:01:09", "remaining_time": "0:13:37"}
{"current_steps": 400, "total_steps": 5000, "loss": 0.743, "lr": 4e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:01:10", "remaining_time": "0:13:32"}
{"current_steps": 410, "total_steps": 5000, "loss": 0.7327, "lr": 4.1e-05, "epoch": 0.082, "percentage": 8.2, "elapsed_time": "0:01:11", "remaining_time": "0:13:24"}
{"current_steps": 420, "total_steps": 5000, "loss": 0.4283, "lr": 4.2e-05, "epoch": 0.084, "percentage": 8.4, "elapsed_time": "0:01:13", "remaining_time": "0:13:18"}
{"current_steps": 430, "total_steps": 5000, "loss": 0.5758, "lr": 4.3e-05, "epoch": 0.086, "percentage": 8.6, "elapsed_time": "0:01:14", "remaining_time": "0:13:12"}
{"current_steps": 440, "total_steps": 5000, "loss": 0.8512, "lr": 4.4000000000000006e-05, "epoch": 0.088, "percentage": 8.8, "elapsed_time": "0:01:16", "remaining_time": "0:13:09"}
{"current_steps": 450, "total_steps": 5000, "loss": 0.5049, "lr": 4.5e-05, "epoch": 0.09, "percentage": 9.0, "elapsed_time": "0:01:17", "remaining_time": "0:13:04"}
{"current_steps": 460, "total_steps": 5000, "loss": 1.1472, "lr": 4.600000000000001e-05, "epoch": 0.092, "percentage": 9.2, "elapsed_time": "0:01:19", "remaining_time": "0:12:59"}
{"current_steps": 470, "total_steps": 5000, "loss": 0.2267, "lr": 4.7e-05, "epoch": 0.094, "percentage": 9.4, "elapsed_time": "0:01:19", "remaining_time": "0:12:50"}
{"current_steps": 480, "total_steps": 5000, "loss": 0.7747, "lr": 4.8e-05, "epoch": 0.096, "percentage": 9.6, "elapsed_time": "0:01:21", "remaining_time": "0:12:45"}
{"current_steps": 490, "total_steps": 5000, "loss": 1.5527, "lr": 4.9e-05, "epoch": 0.098, "percentage": 9.8, "elapsed_time": "0:01:22", "remaining_time": "0:12:42"}
{"current_steps": 500, "total_steps": 5000, "loss": 0.8587, "lr": 5e-05, "epoch": 0.1, "percentage": 10.0, "elapsed_time": "0:01:24", "remaining_time": "0:12:40"}
{"current_steps": 510, "total_steps": 5000, "loss": 1.3302, "lr": 4.999939076763487e-05, "epoch": 0.102, "percentage": 10.2, "elapsed_time": "0:01:25", "remaining_time": "0:12:36"}
{"current_steps": 520, "total_steps": 5000, "loss": 1.2599, "lr": 4.999756310023261e-05, "epoch": 0.104, "percentage": 10.4, "elapsed_time": "0:01:27", "remaining_time": "0:12:34"}
{"current_steps": 530, "total_steps": 5000, "loss": 1.2629, "lr": 4.999451708687114e-05, "epoch": 0.106, "percentage": 10.6, "elapsed_time": "0:01:28", "remaining_time": "0:12:30"}
{"current_steps": 540, "total_steps": 5000, "loss": 0.5081, "lr": 4.999025287600886e-05, "epoch": 0.108, "percentage": 10.8, "elapsed_time": "0:01:30", "remaining_time": "0:12:28"}
{"current_steps": 550, "total_steps": 5000, "loss": 0.3987, "lr": 4.99847706754774e-05, "epoch": 0.11, "percentage": 11.0, "elapsed_time": "0:01:31", "remaining_time": "0:12:23"}
{"current_steps": 560, "total_steps": 5000, "loss": 0.8476, "lr": 4.997807075247146e-05, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:01:33", "remaining_time": "0:12:21"}
{"current_steps": 570, "total_steps": 5000, "loss": 0.3636, "lr": 4.997015343353585e-05, "epoch": 0.114, "percentage": 11.4, "elapsed_time": "0:01:34", "remaining_time": "0:12:17"}
{"current_steps": 580, "total_steps": 5000, "loss": 0.5166, "lr": 4.996101910454953e-05, "epoch": 0.116, "percentage": 11.6, "elapsed_time": "0:01:36", "remaining_time": "0:12:14"}
{"current_steps": 590, "total_steps": 5000, "loss": 0.8616, "lr": 4.995066821070679e-05, "epoch": 0.118, "percentage": 11.8, "elapsed_time": "0:01:37", "remaining_time": "0:12:10"}
{"current_steps": 600, "total_steps": 5000, "loss": 1.1722, "lr": 4.993910125649561e-05, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:01:39", "remaining_time": "0:12:08"}
{"current_steps": 610, "total_steps": 5000, "loss": 0.8744, "lr": 4.992631880567301e-05, "epoch": 0.122, "percentage": 12.2, "elapsed_time": "0:01:40", "remaining_time": "0:12:05"}
{"current_steps": 620, "total_steps": 5000, "loss": 0.6318, "lr": 4.991232148123761e-05, "epoch": 0.124, "percentage": 12.4, "elapsed_time": "0:01:41", "remaining_time": "0:11:58"}
{"current_steps": 630, "total_steps": 5000, "loss": 0.5133, "lr": 4.989710996539926e-05, "epoch": 0.126, "percentage": 12.6, "elapsed_time": "0:01:43", "remaining_time": "0:11:55"}
{"current_steps": 640, "total_steps": 5000, "loss": 0.9733, "lr": 4.988068499954578e-05, "epoch": 0.128, "percentage": 12.8, "elapsed_time": "0:01:44", "remaining_time": "0:11:52"}
{"current_steps": 650, "total_steps": 5000, "loss": 0.4055, "lr": 4.9863047384206835e-05, "epoch": 0.13, "percentage": 13.0, "elapsed_time": "0:01:46", "remaining_time": "0:11:51"}
{"current_steps": 660, "total_steps": 5000, "loss": 0.2974, "lr": 4.984419797901491e-05, "epoch": 0.132, "percentage": 13.2, "elapsed_time": "0:01:47", "remaining_time": "0:11:46"}
{"current_steps": 670, "total_steps": 5000, "loss": 1.2051, "lr": 4.982413770266342e-05, "epoch": 0.134, "percentage": 13.4, "elapsed_time": "0:01:48", "remaining_time": "0:11:44"}
{"current_steps": 680, "total_steps": 5000, "loss": 0.9672, "lr": 4.980286753286195e-05, "epoch": 0.136, "percentage": 13.6, "elapsed_time": "0:01:50", "remaining_time": "0:11:41"}
{"current_steps": 690, "total_steps": 5000, "loss": 0.8584, "lr": 4.978038850628854e-05, "epoch": 0.138, "percentage": 13.8, "elapsed_time": "0:01:52", "remaining_time": "0:11:39"}
{"current_steps": 700, "total_steps": 5000, "loss": 0.7926, "lr": 4.975670171853926e-05, "epoch": 0.14, "percentage": 14.0, "elapsed_time": "0:01:53", "remaining_time": "0:11:35"}
{"current_steps": 710, "total_steps": 5000, "loss": 0.8325, "lr": 4.9731808324074717e-05, "epoch": 0.142, "percentage": 14.2, "elapsed_time": "0:01:54", "remaining_time": "0:11:32"}
{"current_steps": 720, "total_steps": 5000, "loss": 1.4764, "lr": 4.9705709536163824e-05, "epoch": 0.144, "percentage": 14.4, "elapsed_time": "0:01:56", "remaining_time": "0:11:30"}
{"current_steps": 730, "total_steps": 5000, "loss": 0.383, "lr": 4.96784066268247e-05, "epoch": 0.146, "percentage": 14.6, "elapsed_time": "0:01:57", "remaining_time": "0:11:29"}
{"current_steps": 740, "total_steps": 5000, "loss": 0.9716, "lr": 4.964990092676263e-05, "epoch": 0.148, "percentage": 14.8, "elapsed_time": "0:01:59", "remaining_time": "0:11:26"}
{"current_steps": 750, "total_steps": 5000, "loss": 0.8388, "lr": 4.962019382530521e-05, "epoch": 0.15, "percentage": 15.0, "elapsed_time": "0:02:00", "remaining_time": "0:11:22"}
{"current_steps": 760, "total_steps": 5000, "loss": 0.4702, "lr": 4.9589286770334654e-05, "epoch": 0.152, "percentage": 15.2, "elapsed_time": "0:02:01", "remaining_time": "0:11:19"}
{"current_steps": 770, "total_steps": 5000, "loss": 0.4621, "lr": 4.9557181268217227e-05, "epoch": 0.154, "percentage": 15.4, "elapsed_time": "0:02:03", "remaining_time": "0:11:16"}
{"current_steps": 780, "total_steps": 5000, "loss": 1.2844, "lr": 4.952387888372979e-05, "epoch": 0.156, "percentage": 15.6, "elapsed_time": "0:02:04", "remaining_time": "0:11:13"}
{"current_steps": 790, "total_steps": 5000, "loss": 0.7515, "lr": 4.94893812399836e-05, "epoch": 0.158, "percentage": 15.8, "elapsed_time": "0:02:05", "remaining_time": "0:11:11"}
{"current_steps": 800, "total_steps": 5000, "loss": 1.2068, "lr": 4.9453690018345144e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:02:07", "remaining_time": "0:11:08"}
{"current_steps": 810, "total_steps": 5000, "loss": 0.7996, "lr": 4.94168069583542e-05, "epoch": 0.162, "percentage": 16.2, "elapsed_time": "0:02:08", "remaining_time": "0:11:06"}
{"current_steps": 820, "total_steps": 5000, "loss": 0.4823, "lr": 4.937873385763908e-05, "epoch": 0.164, "percentage": 16.4, "elapsed_time": "0:02:10", "remaining_time": "0:11:02"}
{"current_steps": 830, "total_steps": 5000, "loss": 1.9873, "lr": 4.933947257182901e-05, "epoch": 0.166, "percentage": 16.6, "elapsed_time": "0:02:11", "remaining_time": "0:11:00"}
{"current_steps": 840, "total_steps": 5000, "loss": 0.972, "lr": 4.929902501446366e-05, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:02:13", "remaining_time": "0:11:00"}
{"current_steps": 850, "total_steps": 5000, "loss": 0.9033, "lr": 4.925739315689991e-05, "epoch": 0.17, "percentage": 17.0, "elapsed_time": "0:02:14", "remaining_time": "0:10:58"}
{"current_steps": 860, "total_steps": 5000, "loss": 0.8727, "lr": 4.9214579028215776e-05, "epoch": 0.172, "percentage": 17.2, "elapsed_time": "0:02:16", "remaining_time": "0:10:54"}
{"current_steps": 870, "total_steps": 5000, "loss": 0.8317, "lr": 4.917058471511149e-05, "epoch": 0.174, "percentage": 17.4, "elapsed_time": "0:02:17", "remaining_time": "0:10:52"}
{"current_steps": 880, "total_steps": 5000, "loss": 2.0381, "lr": 4.912541236180779e-05, "epoch": 0.176, "percentage": 17.6, "elapsed_time": "0:02:18", "remaining_time": "0:10:50"}
{"current_steps": 890, "total_steps": 5000, "loss": 0.9051, "lr": 4.907906416994146e-05, "epoch": 0.178, "percentage": 17.8, "elapsed_time": "0:02:20", "remaining_time": "0:10:47"}
{"current_steps": 900, "total_steps": 5000, "loss": 1.4764, "lr": 4.9031542398457974e-05, "epoch": 0.18, "percentage": 18.0, "elapsed_time": "0:02:22", "remaining_time": "0:10:46"}
{"current_steps": 910, "total_steps": 5000, "loss": 0.356, "lr": 4.898284936350144e-05, "epoch": 0.182, "percentage": 18.2, "elapsed_time": "0:02:23", "remaining_time": "0:10:43"}
{"current_steps": 920, "total_steps": 5000, "loss": 0.638, "lr": 4.893298743830168e-05, "epoch": 0.184, "percentage": 18.4, "elapsed_time": "0:02:24", "remaining_time": "0:10:40"}
{"current_steps": 930, "total_steps": 5000, "loss": 0.7703, "lr": 4.888195905305859e-05, "epoch": 0.186, "percentage": 18.6, "elapsed_time": "0:02:26", "remaining_time": "0:10:39"}
{"current_steps": 940, "total_steps": 5000, "loss": 0.2645, "lr": 4.882976669482367e-05, "epoch": 0.188, "percentage": 18.8, "elapsed_time": "0:02:27", "remaining_time": "0:10:37"}
{"current_steps": 950, "total_steps": 5000, "loss": 0.2336, "lr": 4.877641290737884e-05, "epoch": 0.19, "percentage": 19.0, "elapsed_time": "0:02:28", "remaining_time": "0:10:32"}
{"current_steps": 960, "total_steps": 5000, "loss": 0.3605, "lr": 4.8721900291112415e-05, "epoch": 0.192, "percentage": 19.2, "elapsed_time": "0:02:29", "remaining_time": "0:10:30"}
{"current_steps": 970, "total_steps": 5000, "loss": 0.3298, "lr": 4.8666231502892415e-05, "epoch": 0.194, "percentage": 19.4, "elapsed_time": "0:02:31", "remaining_time": "0:10:27"}
{"current_steps": 980, "total_steps": 5000, "loss": 0.4169, "lr": 4.860940925593703e-05, "epoch": 0.196, "percentage": 19.6, "elapsed_time": "0:02:32", "remaining_time": "0:10:24"}
{"current_steps": 990, "total_steps": 5000, "loss": 0.7155, "lr": 4.855143631968242e-05, "epoch": 0.198, "percentage": 19.8, "elapsed_time": "0:02:33", "remaining_time": "0:10:22"}
{"current_steps": 1000, "total_steps": 5000, "loss": 0.7995, "lr": 4.849231551964771e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:02:35", "remaining_time": "0:10:21"}
{"current_steps": 1010, "total_steps": 5000, "loss": 0.896, "lr": 4.843204973729729e-05, "epoch": 0.202, "percentage": 20.2, "elapsed_time": "0:02:36", "remaining_time": "0:10:19"}
{"current_steps": 1020, "total_steps": 5000, "loss": 0.4791, "lr": 4.837064190990036e-05, "epoch": 0.204, "percentage": 20.4, "elapsed_time": "0:02:38", "remaining_time": "0:10:16"}
{"current_steps": 1030, "total_steps": 5000, "loss": 1.3894, "lr": 4.830809503038781e-05, "epoch": 0.206, "percentage": 20.6, "elapsed_time": "0:02:39", "remaining_time": "0:10:15"}
{"current_steps": 1040, "total_steps": 5000, "loss": 0.7805, "lr": 4.8244412147206284e-05, "epoch": 0.208, "percentage": 20.8, "elapsed_time": "0:02:41", "remaining_time": "0:10:14"}
{"current_steps": 1050, "total_steps": 5000, "loss": 0.7316, "lr": 4.817959636416969e-05, "epoch": 0.21, "percentage": 21.0, "elapsed_time": "0:02:42", "remaining_time": "0:10:12"}
{"current_steps": 1060, "total_steps": 5000, "loss": 0.6104, "lr": 4.8113650840307834e-05, "epoch": 0.212, "percentage": 21.2, "elapsed_time": "0:02:44", "remaining_time": "0:10:11"}
{"current_steps": 1070, "total_steps": 5000, "loss": 0.4769, "lr": 4.8046578789712515e-05, "epoch": 0.214, "percentage": 21.4, "elapsed_time": "0:02:46", "remaining_time": "0:10:09"}
{"current_steps": 1080, "total_steps": 5000, "loss": 0.9277, "lr": 4.797838348138086e-05, "epoch": 0.216, "percentage": 21.6, "elapsed_time": "0:02:47", "remaining_time": "0:10:08"}
{"current_steps": 1090, "total_steps": 5000, "loss": 1.2787, "lr": 4.790906823905599e-05, "epoch": 0.218, "percentage": 21.8, "elapsed_time": "0:02:49", "remaining_time": "0:10:06"}
{"current_steps": 1100, "total_steps": 5000, "loss": 0.9859, "lr": 4.783863644106502e-05, "epoch": 0.22, "percentage": 22.0, "elapsed_time": "0:02:50", "remaining_time": "0:10:04"}
{"current_steps": 1110, "total_steps": 5000, "loss": 0.5019, "lr": 4.776709152015443e-05, "epoch": 0.222, "percentage": 22.2, "elapsed_time": "0:02:51", "remaining_time": "0:10:01"}
{"current_steps": 1120, "total_steps": 5000, "loss": 0.3593, "lr": 4.769443696332272e-05, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:02:52", "remaining_time": "0:09:58"}
{"current_steps": 1130, "total_steps": 5000, "loss": 0.6199, "lr": 4.762067631165049e-05, "epoch": 0.226, "percentage": 22.6, "elapsed_time": "0:02:54", "remaining_time": "0:09:57"}
{"current_steps": 1140, "total_steps": 5000, "loss": 0.4687, "lr": 4.754581316012785e-05, "epoch": 0.228, "percentage": 22.8, "elapsed_time": "0:02:55", "remaining_time": "0:09:55"}
{"current_steps": 1150, "total_steps": 5000, "loss": 1.1984, "lr": 4.7469851157479177e-05, "epoch": 0.23, "percentage": 23.0, "elapsed_time": "0:02:57", "remaining_time": "0:09:52"}
{"current_steps": 1160, "total_steps": 5000, "loss": 1.0512, "lr": 4.7392794005985326e-05, "epoch": 0.232, "percentage": 23.2, "elapsed_time": "0:02:58", "remaining_time": "0:09:51"}
{"current_steps": 1170, "total_steps": 5000, "loss": 0.6368, "lr": 4.731464546130314e-05, "epoch": 0.234, "percentage": 23.4, "elapsed_time": "0:03:00", "remaining_time": "0:09:50"}
{"current_steps": 1180, "total_steps": 5000, "loss": 0.6134, "lr": 4.723540933228244e-05, "epoch": 0.236, "percentage": 23.6, "elapsed_time": "0:03:02", "remaining_time": "0:09:49"}
{"current_steps": 1190, "total_steps": 5000, "loss": 0.5656, "lr": 4.715508948078037e-05, "epoch": 0.238, "percentage": 23.8, "elapsed_time": "0:03:03", "remaining_time": "0:09:47"}
{"current_steps": 1200, "total_steps": 5000, "loss": 0.5528, "lr": 4.707368982147318e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:03:04", "remaining_time": "0:09:45"}
{"current_steps": 1210, "total_steps": 5000, "loss": 0.9509, "lr": 4.6991214321665414e-05, "epoch": 0.242, "percentage": 24.2, "elapsed_time": "0:03:06", "remaining_time": "0:09:42"}
{"current_steps": 1220, "total_steps": 5000, "loss": 0.8255, "lr": 4.690766700109659e-05, "epoch": 0.244, "percentage": 24.4, "elapsed_time": "0:03:07", "remaining_time": "0:09:41"}
{"current_steps": 1230, "total_steps": 5000, "loss": 1.0996, "lr": 4.682305193174524e-05, "epoch": 0.246, "percentage": 24.6, "elapsed_time": "0:03:09", "remaining_time": "0:09:40"}
{"current_steps": 1240, "total_steps": 5000, "loss": 0.3578, "lr": 4.6737373237630476e-05, "epoch": 0.248, "percentage": 24.8, "elapsed_time": "0:03:10", "remaining_time": "0:09:38"}
{"current_steps": 1250, "total_steps": 5000, "loss": 0.5448, "lr": 4.665063509461097e-05, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:03:11", "remaining_time": "0:09:35"}
{"current_steps": 1260, "total_steps": 5000, "loss": 0.5753, "lr": 4.656284173018144e-05, "epoch": 0.252, "percentage": 25.2, "elapsed_time": "0:03:13", "remaining_time": "0:09:33"}
{"current_steps": 1270, "total_steps": 5000, "loss": 0.492, "lr": 4.6473997423266614e-05, "epoch": 0.254, "percentage": 25.4, "elapsed_time": "0:03:14", "remaining_time": "0:09:31"}
{"current_steps": 1280, "total_steps": 5000, "loss": 0.5816, "lr": 4.638410650401267e-05, "epoch": 0.256, "percentage": 25.6, "elapsed_time": "0:03:16", "remaining_time": "0:09:30"}
{"current_steps": 1290, "total_steps": 5000, "loss": 0.9541, "lr": 4.629317335357619e-05, "epoch": 0.258, "percentage": 25.8, "elapsed_time": "0:03:17", "remaining_time": "0:09:28"}
{"current_steps": 1300, "total_steps": 5000, "loss": 0.4042, "lr": 4.620120240391065e-05, "epoch": 0.26, "percentage": 26.0, "elapsed_time": "0:03:19", "remaining_time": "0:09:26"}
{"current_steps": 1310, "total_steps": 5000, "loss": 0.7787, "lr": 4.610819813755038e-05, "epoch": 0.262, "percentage": 26.2, "elapsed_time": "0:03:20", "remaining_time": "0:09:25"}
{"current_steps": 1320, "total_steps": 5000, "loss": 0.6693, "lr": 4.601416508739211e-05, "epoch": 0.264, "percentage": 26.4, "elapsed_time": "0:03:22", "remaining_time": "0:09:24"}
{"current_steps": 1330, "total_steps": 5000, "loss": 0.509, "lr": 4.591910783647404e-05, "epoch": 0.266, "percentage": 26.6, "elapsed_time": "0:03:24", "remaining_time": "0:09:22"}
{"current_steps": 1340, "total_steps": 5000, "loss": 0.6255, "lr": 4.5823031017752485e-05, "epoch": 0.268, "percentage": 26.8, "elapsed_time": "0:03:25", "remaining_time": "0:09:20"}
{"current_steps": 1350, "total_steps": 5000, "loss": 0.2688, "lr": 4.572593931387604e-05, "epoch": 0.27, "percentage": 27.0, "elapsed_time": "0:03:26", "remaining_time": "0:09:18"}
{"current_steps": 1360, "total_steps": 5000, "loss": 1.1364, "lr": 4.562783745695738e-05, "epoch": 0.272, "percentage": 27.2, "elapsed_time": "0:03:28", "remaining_time": "0:09:16"}
{"current_steps": 1370, "total_steps": 5000, "loss": 0.8806, "lr": 4.5528730228342605e-05, "epoch": 0.274, "percentage": 27.4, "elapsed_time": "0:03:29", "remaining_time": "0:09:14"}
{"current_steps": 1380, "total_steps": 5000, "loss": 0.492, "lr": 4.542862245837821e-05, "epoch": 0.276, "percentage": 27.6, "elapsed_time": "0:03:30", "remaining_time": "0:09:12"}
{"current_steps": 1390, "total_steps": 5000, "loss": 0.4463, "lr": 4.532751902617569e-05, "epoch": 0.278, "percentage": 27.8, "elapsed_time": "0:03:31", "remaining_time": "0:09:10"}
{"current_steps": 1400, "total_steps": 5000, "loss": 0.6709, "lr": 4.522542485937369e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:03:33", "remaining_time": "0:09:08"}
{"current_steps": 1410, "total_steps": 5000, "loss": 0.7535, "lr": 4.512234493389785e-05, "epoch": 0.282, "percentage": 28.2, "elapsed_time": "0:03:35", "remaining_time": "0:09:08"}
{"current_steps": 1420, "total_steps": 5000, "loss": 0.593, "lr": 4.5018284273718336e-05, "epoch": 0.284, "percentage": 28.4, "elapsed_time": "0:03:36", "remaining_time": "0:09:06"}
{"current_steps": 1430, "total_steps": 5000, "loss": 1.3771, "lr": 4.491324795060491e-05, "epoch": 0.286, "percentage": 28.6, "elapsed_time": "0:03:38", "remaining_time": "0:09:04"}
{"current_steps": 1440, "total_steps": 5000, "loss": 0.6399, "lr": 4.480724108387977e-05, "epoch": 0.288, "percentage": 28.8, "elapsed_time": "0:03:39", "remaining_time": "0:09:03"}
{"current_steps": 1450, "total_steps": 5000, "loss": 1.7451, "lr": 4.4700268840168045e-05, "epoch": 0.29, "percentage": 29.0, "elapsed_time": "0:03:41", "remaining_time": "0:09:02"}
{"current_steps": 1460, "total_steps": 5000, "loss": 0.6852, "lr": 4.4592336433146e-05, "epoch": 0.292, "percentage": 29.2, "elapsed_time": "0:03:42", "remaining_time": "0:09:00"}
{"current_steps": 1470, "total_steps": 5000, "loss": 1.3182, "lr": 4.448344912328686e-05, "epoch": 0.294, "percentage": 29.4, "elapsed_time": "0:03:44", "remaining_time": "0:08:59"}
{"current_steps": 1480, "total_steps": 5000, "loss": 0.5018, "lr": 4.4373612217604496e-05, "epoch": 0.296, "percentage": 29.6, "elapsed_time": "0:03:45", "remaining_time": "0:08:56"}
{"current_steps": 1490, "total_steps": 5000, "loss": 0.5594, "lr": 4.426283106939474e-05, "epoch": 0.298, "percentage": 29.8, "elapsed_time": "0:03:47", "remaining_time": "0:08:54"}
{"current_steps": 1500, "total_steps": 5000, "loss": 0.5015, "lr": 4.415111107797445e-05, "epoch": 0.3, "percentage": 30.0, "elapsed_time": "0:03:48", "remaining_time": "0:08:53"}
{"current_steps": 1510, "total_steps": 5000, "loss": 0.6153, "lr": 4.403845768841842e-05, "epoch": 0.302, "percentage": 30.2, "elapsed_time": "0:03:50", "remaining_time": "0:08:51"}
{"current_steps": 1520, "total_steps": 5000, "loss": 0.7155, "lr": 4.3924876391293915e-05, "epoch": 0.304, "percentage": 30.4, "elapsed_time": "0:03:50", "remaining_time": "0:08:48"}
{"current_steps": 1530, "total_steps": 5000, "loss": 1.5828, "lr": 4.381037272239311e-05, "epoch": 0.306, "percentage": 30.6, "elapsed_time": "0:03:52", "remaining_time": "0:08:46"}
{"current_steps": 1540, "total_steps": 5000, "loss": 0.437, "lr": 4.36949522624633e-05, "epoch": 0.308, "percentage": 30.8, "elapsed_time": "0:03:53", "remaining_time": "0:08:45"}
{"current_steps": 1550, "total_steps": 5000, "loss": 1.0841, "lr": 4.357862063693486e-05, "epoch": 0.31, "percentage": 31.0, "elapsed_time": "0:03:55", "remaining_time": "0:08:43"}
{"current_steps": 1560, "total_steps": 5000, "loss": 0.6135, "lr": 4.3461383515647106e-05, "epoch": 0.312, "percentage": 31.2, "elapsed_time": "0:03:56", "remaining_time": "0:08:41"}
{"current_steps": 1570, "total_steps": 5000, "loss": 0.7842, "lr": 4.334324661257191e-05, "epoch": 0.314, "percentage": 31.4, "elapsed_time": "0:03:58", "remaining_time": "0:08:40"}
{"current_steps": 1580, "total_steps": 5000, "loss": 0.9022, "lr": 4.3224215685535294e-05, "epoch": 0.316, "percentage": 31.6, "elapsed_time": "0:03:59", "remaining_time": "0:08:38"}
{"current_steps": 1590, "total_steps": 5000, "loss": 1.5357, "lr": 4.3104296535936695e-05, "epoch": 0.318, "percentage": 31.8, "elapsed_time": "0:04:01", "remaining_time": "0:08:37"}
{"current_steps": 1600, "total_steps": 5000, "loss": 0.8859, "lr": 4.2983495008466276e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:04:02", "remaining_time": "0:08:35"}
{"current_steps": 1610, "total_steps": 5000, "loss": 0.6634, "lr": 4.2861816990820084e-05, "epoch": 0.322, "percentage": 32.2, "elapsed_time": "0:04:04", "remaining_time": "0:08:35"}
{"current_steps": 1620, "total_steps": 5000, "loss": 0.6081, "lr": 4.273926841341302e-05, "epoch": 0.324, "percentage": 32.4, "elapsed_time": "0:04:06", "remaining_time": "0:08:33"}
{"current_steps": 1630, "total_steps": 5000, "loss": 0.4987, "lr": 4.261585524908987e-05, "epoch": 0.326, "percentage": 32.6, "elapsed_time": "0:04:07", "remaining_time": "0:08:32"}
{"current_steps": 1640, "total_steps": 5000, "loss": 0.4292, "lr": 4.249158351283414e-05, "epoch": 0.328, "percentage": 32.8, "elapsed_time": "0:04:08", "remaining_time": "0:08:29"}
{"current_steps": 1650, "total_steps": 5000, "loss": 0.388, "lr": 4.2366459261474933e-05, "epoch": 0.33, "percentage": 33.0, "elapsed_time": "0:04:10", "remaining_time": "0:08:27"}
{"current_steps": 1660, "total_steps": 5000, "loss": 0.7921, "lr": 4.224048859339175e-05, "epoch": 0.332, "percentage": 33.2, "elapsed_time": "0:04:11", "remaining_time": "0:08:26"}
{"current_steps": 1670, "total_steps": 5000, "loss": 0.4273, "lr": 4.211367764821722e-05, "epoch": 0.334, "percentage": 33.4, "elapsed_time": "0:04:12", "remaining_time": "0:08:24"}
{"current_steps": 1680, "total_steps": 5000, "loss": 1.3453, "lr": 4.198603260653792e-05, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:04:14", "remaining_time": "0:08:22"}
{"current_steps": 1690, "total_steps": 5000, "loss": 1.2634, "lr": 4.185755968959308e-05, "epoch": 0.338, "percentage": 33.8, "elapsed_time": "0:04:16", "remaining_time": "0:08:21"}
{"current_steps": 1700, "total_steps": 5000, "loss": 1.1337, "lr": 4.172826515897146e-05, "epoch": 0.34, "percentage": 34.0, "elapsed_time": "0:04:17", "remaining_time": "0:08:19"}
{"current_steps": 1710, "total_steps": 5000, "loss": 0.8494, "lr": 4.1598155316306044e-05, "epoch": 0.342, "percentage": 34.2, "elapsed_time": "0:04:18", "remaining_time": "0:08:17"}
{"current_steps": 1720, "total_steps": 5000, "loss": 0.6478, "lr": 4.146723650296701e-05, "epoch": 0.344, "percentage": 34.4, "elapsed_time": "0:04:20", "remaining_time": "0:08:16"}
{"current_steps": 1730, "total_steps": 5000, "loss": 0.3581, "lr": 4.133551509975264e-05, "epoch": 0.346, "percentage": 34.6, "elapsed_time": "0:04:21", "remaining_time": "0:08:14"}
{"current_steps": 1740, "total_steps": 5000, "loss": 1.4538, "lr": 4.1202997526578276e-05, "epoch": 0.348, "percentage": 34.8, "elapsed_time": "0:04:23", "remaining_time": "0:08:13"}
{"current_steps": 1750, "total_steps": 5000, "loss": 1.9496, "lr": 4.1069690242163484e-05, "epoch": 0.35, "percentage": 35.0, "elapsed_time": "0:04:24", "remaining_time": "0:08:11"}
{"current_steps": 1760, "total_steps": 5000, "loss": 0.596, "lr": 4.093559974371725e-05, "epoch": 0.352, "percentage": 35.2, "elapsed_time": "0:04:26", "remaining_time": "0:08:10"}
{"current_steps": 1770, "total_steps": 5000, "loss": 0.8232, "lr": 4.080073256662127e-05, "epoch": 0.354, "percentage": 35.4, "elapsed_time": "0:04:28", "remaining_time": "0:08:09"}
{"current_steps": 1780, "total_steps": 5000, "loss": 0.7489, "lr": 4.066509528411152e-05, "epoch": 0.356, "percentage": 35.6, "elapsed_time": "0:04:29", "remaining_time": "0:08:08"}
{"current_steps": 1790, "total_steps": 5000, "loss": 0.5811, "lr": 4.052869450695776e-05, "epoch": 0.358, "percentage": 35.8, "elapsed_time": "0:04:31", "remaining_time": "0:08:06"}
{"current_steps": 1800, "total_steps": 5000, "loss": 0.7109, "lr": 4.039153688314145e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:04:32", "remaining_time": "0:08:05"}
{"current_steps": 1810, "total_steps": 5000, "loss": 0.6032, "lr": 4.02536290975317e-05, "epoch": 0.362, "percentage": 36.2, "elapsed_time": "0:04:34", "remaining_time": "0:08:03"}
{"current_steps": 1820, "total_steps": 5000, "loss": 1.4854, "lr": 4.011497787155938e-05, "epoch": 0.364, "percentage": 36.4, "elapsed_time": "0:04:35", "remaining_time": "0:08:01"}
{"current_steps": 1830, "total_steps": 5000, "loss": 0.8269, "lr": 3.997558996288965e-05, "epoch": 0.366, "percentage": 36.6, "elapsed_time": "0:04:37", "remaining_time": "0:08:00"}
{"current_steps": 1840, "total_steps": 5000, "loss": 0.5917, "lr": 3.983547216509254e-05, "epoch": 0.368, "percentage": 36.8, "elapsed_time": "0:04:38", "remaining_time": "0:07:58"}
{"current_steps": 1850, "total_steps": 5000, "loss": 0.4239, "lr": 3.969463130731183e-05, "epoch": 0.37, "percentage": 37.0, "elapsed_time": "0:04:39", "remaining_time": "0:07:56"}
{"current_steps": 1860, "total_steps": 5000, "loss": 0.6007, "lr": 3.955307425393224e-05, "epoch": 0.372, "percentage": 37.2, "elapsed_time": "0:04:41", "remaining_time": "0:07:55"}
{"current_steps": 1870, "total_steps": 5000, "loss": 1.358, "lr": 3.941080790424484e-05, "epoch": 0.374, "percentage": 37.4, "elapsed_time": "0:04:42", "remaining_time": "0:07:53"}
{"current_steps": 1880, "total_steps": 5000, "loss": 0.7246, "lr": 3.92678391921108e-05, "epoch": 0.376, "percentage": 37.6, "elapsed_time": "0:04:44", "remaining_time": "0:07:52"}
{"current_steps": 1890, "total_steps": 5000, "loss": 0.6441, "lr": 3.912417508562345e-05, "epoch": 0.378, "percentage": 37.8, "elapsed_time": "0:04:45", "remaining_time": "0:07:50"}
{"current_steps": 1900, "total_steps": 5000, "loss": 1.1391, "lr": 3.897982258676867e-05, "epoch": 0.38, "percentage": 38.0, "elapsed_time": "0:04:47", "remaining_time": "0:07:48"}
{"current_steps": 1910, "total_steps": 5000, "loss": 0.9372, "lr": 3.883478873108361e-05, "epoch": 0.382, "percentage": 38.2, "elapsed_time": "0:04:48", "remaining_time": "0:07:47"}
{"current_steps": 1920, "total_steps": 5000, "loss": 0.4182, "lr": 3.868908058731376e-05, "epoch": 0.384, "percentage": 38.4, "elapsed_time": "0:04:50", "remaining_time": "0:07:45"}
{"current_steps": 1930, "total_steps": 5000, "loss": 0.4093, "lr": 3.85427052570685e-05, "epoch": 0.386, "percentage": 38.6, "elapsed_time": "0:04:51", "remaining_time": "0:07:43"}
{"current_steps": 1940, "total_steps": 5000, "loss": 0.5726, "lr": 3.8395669874474915e-05, "epoch": 0.388, "percentage": 38.8, "elapsed_time": "0:04:53", "remaining_time": "0:07:42"}
{"current_steps": 1950, "total_steps": 5000, "loss": 0.4036, "lr": 3.824798160583012e-05, "epoch": 0.39, "percentage": 39.0, "elapsed_time": "0:04:53", "remaining_time": "0:07:39"}
{"current_steps": 1960, "total_steps": 5000, "loss": 1.0484, "lr": 3.8099647649251986e-05, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:04:55", "remaining_time": "0:07:38"}
{"current_steps": 1970, "total_steps": 5000, "loss": 0.494, "lr": 3.795067523432826e-05, "epoch": 0.394, "percentage": 39.4, "elapsed_time": "0:04:57", "remaining_time": "0:07:37"}
{"current_steps": 1980, "total_steps": 5000, "loss": 0.5173, "lr": 3.780107162176429e-05, "epoch": 0.396, "percentage": 39.6, "elapsed_time": "0:04:58", "remaining_time": "0:07:35"}
{"current_steps": 1990, "total_steps": 5000, "loss": 1.3572, "lr": 3.765084410302909e-05, "epoch": 0.398, "percentage": 39.8, "elapsed_time": "0:05:00", "remaining_time": "0:07:34"}
{"current_steps": 2000, "total_steps": 5000, "loss": 1.0208, "lr": 3.7500000000000003e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:05:01", "remaining_time": "0:07:32"}
{"current_steps": 2010, "total_steps": 5000, "loss": 0.6554, "lr": 3.7348546664605777e-05, "epoch": 0.402, "percentage": 40.2, "elapsed_time": "0:05:03", "remaining_time": "0:07:31"}
{"current_steps": 2020, "total_steps": 5000, "loss": 0.5559, "lr": 3.719649147846832e-05, "epoch": 0.404, "percentage": 40.4, "elapsed_time": "0:05:04", "remaining_time": "0:07:29"}
{"current_steps": 2030, "total_steps": 5000, "loss": 0.7931, "lr": 3.704384185254288e-05, "epoch": 0.406, "percentage": 40.6, "elapsed_time": "0:05:06", "remaining_time": "0:07:28"}
{"current_steps": 2040, "total_steps": 5000, "loss": 1.703, "lr": 3.689060522675689e-05, "epoch": 0.408, "percentage": 40.8, "elapsed_time": "0:05:07", "remaining_time": "0:07:26"}
{"current_steps": 2050, "total_steps": 5000, "loss": 0.7714, "lr": 3.673678906964727e-05, "epoch": 0.41, "percentage": 41.0, "elapsed_time": "0:05:08", "remaining_time": "0:07:24"}
{"current_steps": 2060, "total_steps": 5000, "loss": 0.83, "lr": 3.6582400877996546e-05, "epoch": 0.412, "percentage": 41.2, "elapsed_time": "0:05:10", "remaining_time": "0:07:23"}
{"current_steps": 2070, "total_steps": 5000, "loss": 0.9586, "lr": 3.642744817646736e-05, "epoch": 0.414, "percentage": 41.4, "elapsed_time": "0:05:12", "remaining_time": "0:07:21"}
{"current_steps": 2080, "total_steps": 5000, "loss": 0.4846, "lr": 3.627193851723577e-05, "epoch": 0.416, "percentage": 41.6, "elapsed_time": "0:05:13", "remaining_time": "0:07:20"}
{"current_steps": 2090, "total_steps": 5000, "loss": 1.0133, "lr": 3.611587947962319e-05, "epoch": 0.418, "percentage": 41.8, "elapsed_time": "0:05:14", "remaining_time": "0:07:18"}
{"current_steps": 2100, "total_steps": 5000, "loss": 2.5543, "lr": 3.5959278669726935e-05, "epoch": 0.42, "percentage": 42.0, "elapsed_time": "0:05:16", "remaining_time": "0:07:17"}
{"current_steps": 2110, "total_steps": 5000, "loss": 0.6897, "lr": 3.580214372004956e-05, "epoch": 0.422, "percentage": 42.2, "elapsed_time": "0:05:18", "remaining_time": "0:07:15"}
{"current_steps": 2120, "total_steps": 5000, "loss": 1.9548, "lr": 3.564448228912682e-05, "epoch": 0.424, "percentage": 42.4, "elapsed_time": "0:05:19", "remaining_time": "0:07:13"}
{"current_steps": 2130, "total_steps": 5000, "loss": 0.3453, "lr": 3.548630206115443e-05, "epoch": 0.426, "percentage": 42.6, "elapsed_time": "0:05:20", "remaining_time": "0:07:11"}
{"current_steps": 2140, "total_steps": 5000, "loss": 0.684, "lr": 3.532761074561355e-05, "epoch": 0.428, "percentage": 42.8, "elapsed_time": "0:05:22", "remaining_time": "0:07:10"}
{"current_steps": 2150, "total_steps": 5000, "loss": 0.6245, "lr": 3.516841607689501e-05, "epoch": 0.43, "percentage": 43.0, "elapsed_time": "0:05:23", "remaining_time": "0:07:08"}
{"current_steps": 2160, "total_steps": 5000, "loss": 0.7087, "lr": 3.5008725813922386e-05, "epoch": 0.432, "percentage": 43.2, "elapsed_time": "0:05:25", "remaining_time": "0:07:07"}
{"current_steps": 2170, "total_steps": 5000, "loss": 1.3645, "lr": 3.484854773977378e-05, "epoch": 0.434, "percentage": 43.4, "elapsed_time": "0:05:26", "remaining_time": "0:07:05"}
{"current_steps": 2180, "total_steps": 5000, "loss": 0.4, "lr": 3.4687889661302576e-05, "epoch": 0.436, "percentage": 43.6, "elapsed_time": "0:05:28", "remaining_time": "0:07:04"}
{"current_steps": 2190, "total_steps": 5000, "loss": 0.836, "lr": 3.452675940875686e-05, "epoch": 0.438, "percentage": 43.8, "elapsed_time": "0:05:29", "remaining_time": "0:07:02"}
{"current_steps": 2200, "total_steps": 5000, "loss": 0.936, "lr": 3.436516483539781e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:05:31", "remaining_time": "0:07:01"}
{"current_steps": 2210, "total_steps": 5000, "loss": 0.4429, "lr": 3.4203113817116957e-05, "epoch": 0.442, "percentage": 44.2, "elapsed_time": "0:05:32", "remaining_time": "0:06:59"}
{"current_steps": 2220, "total_steps": 5000, "loss": 0.8114, "lr": 3.4040614252052305e-05, "epoch": 0.444, "percentage": 44.4, "elapsed_time": "0:05:34", "remaining_time": "0:06:58"}
{"current_steps": 2230, "total_steps": 5000, "loss": 0.9497, "lr": 3.387767406020343e-05, "epoch": 0.446, "percentage": 44.6, "elapsed_time": "0:05:35", "remaining_time": "0:06:57"}
{"current_steps": 2240, "total_steps": 5000, "loss": 1.0161, "lr": 3.3714301183045385e-05, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:05:37", "remaining_time": "0:06:55"}
{"current_steps": 2250, "total_steps": 5000, "loss": 1.7385, "lr": 3.355050358314172e-05, "epoch": 0.45, "percentage": 45.0, "elapsed_time": "0:05:38", "remaining_time": "0:06:54"}
{"current_steps": 2260, "total_steps": 5000, "loss": 0.4246, "lr": 3.338628924375638e-05, "epoch": 0.452, "percentage": 45.2, "elapsed_time": "0:05:40", "remaining_time": "0:06:52"}
{"current_steps": 2270, "total_steps": 5000, "loss": 0.4762, "lr": 3.322166616846458e-05, "epoch": 0.454, "percentage": 45.4, "elapsed_time": "0:05:41", "remaining_time": "0:06:51"}
{"current_steps": 2280, "total_steps": 5000, "loss": 1.0733, "lr": 3.305664238076278e-05, "epoch": 0.456, "percentage": 45.6, "elapsed_time": "0:05:43", "remaining_time": "0:06:49"}
{"current_steps": 2290, "total_steps": 5000, "loss": 0.3982, "lr": 3.289122592367757e-05, "epoch": 0.458, "percentage": 45.8, "elapsed_time": "0:05:44", "remaining_time": "0:06:47"}
{"current_steps": 2300, "total_steps": 5000, "loss": 0.5295, "lr": 3.272542485937369e-05, "epoch": 0.46, "percentage": 46.0, "elapsed_time": "0:05:45", "remaining_time": "0:06:46"}
{"current_steps": 2310, "total_steps": 5000, "loss": 0.5606, "lr": 3.2559247268761115e-05, "epoch": 0.462, "percentage": 46.2, "elapsed_time": "0:05:47", "remaining_time": "0:06:44"}
{"current_steps": 2320, "total_steps": 5000, "loss": 1.2333, "lr": 3.239270125110117e-05, "epoch": 0.464, "percentage": 46.4, "elapsed_time": "0:05:49", "remaining_time": "0:06:43"}
{"current_steps": 2330, "total_steps": 5000, "loss": 0.3269, "lr": 3.222579492361179e-05, "epoch": 0.466, "percentage": 46.6, "elapsed_time": "0:05:50", "remaining_time": "0:06:41"}
{"current_steps": 2340, "total_steps": 5000, "loss": 0.8138, "lr": 3.205853642107192e-05, "epoch": 0.468, "percentage": 46.8, "elapsed_time": "0:05:52", "remaining_time": "0:06:40"}
{"current_steps": 2350, "total_steps": 5000, "loss": 1.0379, "lr": 3.1890933895424976e-05, "epoch": 0.47, "percentage": 47.0, "elapsed_time": "0:05:53", "remaining_time": "0:06:38"}
{"current_steps": 2360, "total_steps": 5000, "loss": 0.7049, "lr": 3.172299551538164e-05, "epoch": 0.472, "percentage": 47.2, "elapsed_time": "0:05:54", "remaining_time": "0:06:37"}
{"current_steps": 2370, "total_steps": 5000, "loss": 1.0858, "lr": 3.155472946602162e-05, "epoch": 0.474, "percentage": 47.4, "elapsed_time": "0:05:56", "remaining_time": "0:06:35"}
{"current_steps": 2380, "total_steps": 5000, "loss": 0.7222, "lr": 3.138614394839476e-05, "epoch": 0.476, "percentage": 47.6, "elapsed_time": "0:05:57", "remaining_time": "0:06:33"}
{"current_steps": 2390, "total_steps": 5000, "loss": 0.468, "lr": 3.121724717912138e-05, "epoch": 0.478, "percentage": 47.8, "elapsed_time": "0:05:58", "remaining_time": "0:06:31"}
{"current_steps": 2400, "total_steps": 5000, "loss": 0.3253, "lr": 3.104804738999169e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:06:00", "remaining_time": "0:06:30"}
{"current_steps": 2410, "total_steps": 5000, "loss": 0.5421, "lr": 3.087855282756475e-05, "epoch": 0.482, "percentage": 48.2, "elapsed_time": "0:06:01", "remaining_time": "0:06:28"}
{"current_steps": 2420, "total_steps": 5000, "loss": 0.8433, "lr": 3.0708771752766394e-05, "epoch": 0.484, "percentage": 48.4, "elapsed_time": "0:06:03", "remaining_time": "0:06:27"}
{"current_steps": 2430, "total_steps": 5000, "loss": 0.3927, "lr": 3.053871244048669e-05, "epoch": 0.486, "percentage": 48.6, "elapsed_time": "0:06:04", "remaining_time": "0:06:25"}
{"current_steps": 2440, "total_steps": 5000, "loss": 0.2711, "lr": 3.0368383179176585e-05, "epoch": 0.488, "percentage": 48.8, "elapsed_time": "0:06:06", "remaining_time": "0:06:24"}
{"current_steps": 2450, "total_steps": 5000, "loss": 0.4577, "lr": 3.0197792270443982e-05, "epoch": 0.49, "percentage": 49.0, "elapsed_time": "0:06:08", "remaining_time": "0:06:23"}
{"current_steps": 2460, "total_steps": 5000, "loss": 0.7375, "lr": 3.002694802864912e-05, "epoch": 0.492, "percentage": 49.2, "elapsed_time": "0:06:09", "remaining_time": "0:06:21"}
{"current_steps": 2470, "total_steps": 5000, "loss": 0.8524, "lr": 2.98558587804993e-05, "epoch": 0.494, "percentage": 49.4, "elapsed_time": "0:06:11", "remaining_time": "0:06:20"}
{"current_steps": 2480, "total_steps": 5000, "loss": 0.9756, "lr": 2.9684532864643122e-05, "epoch": 0.496, "percentage": 49.6, "elapsed_time": "0:06:12", "remaining_time": "0:06:18"}
{"current_steps": 2490, "total_steps": 5000, "loss": 0.8588, "lr": 2.9512978631264006e-05, "epoch": 0.498, "percentage": 49.8, "elapsed_time": "0:06:14", "remaining_time": "0:06:17"}
{"current_steps": 2500, "total_steps": 5000, "loss": 0.74, "lr": 2.9341204441673266e-05, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:06:15", "remaining_time": "0:06:15"}
{"current_steps": 2510, "total_steps": 5000, "loss": 0.62, "lr": 2.916921866790256e-05, "epoch": 0.502, "percentage": 50.2, "elapsed_time": "0:06:16", "remaining_time": "0:06:13"}
{"current_steps": 2520, "total_steps": 5000, "loss": 0.5052, "lr": 2.8997029692295874e-05, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:06:18", "remaining_time": "0:06:12"}
{"current_steps": 2530, "total_steps": 5000, "loss": 0.9656, "lr": 2.8824645907100954e-05, "epoch": 0.506, "percentage": 50.6, "elapsed_time": "0:06:19", "remaining_time": "0:06:10"}
{"current_steps": 2540, "total_steps": 5000, "loss": 0.4028, "lr": 2.8652075714060295e-05, "epoch": 0.508, "percentage": 50.8, "elapsed_time": "0:06:21", "remaining_time": "0:06:09"}
{"current_steps": 2550, "total_steps": 5000, "loss": 0.594, "lr": 2.8479327524001636e-05, "epoch": 0.51, "percentage": 51.0, "elapsed_time": "0:06:21", "remaining_time": "0:06:06"}
{"current_steps": 2560, "total_steps": 5000, "loss": 0.6103, "lr": 2.8306409756428064e-05, "epoch": 0.512, "percentage": 51.2, "elapsed_time": "0:06:23", "remaining_time": "0:06:05"}
{"current_steps": 2570, "total_steps": 5000, "loss": 0.732, "lr": 2.8133330839107608e-05, "epoch": 0.514, "percentage": 51.4, "elapsed_time": "0:06:25", "remaining_time": "0:06:04"}
{"current_steps": 2580, "total_steps": 5000, "loss": 0.609, "lr": 2.7960099207662532e-05, "epoch": 0.516, "percentage": 51.6, "elapsed_time": "0:06:26", "remaining_time": "0:06:02"}
{"current_steps": 2590, "total_steps": 5000, "loss": 0.3862, "lr": 2.7786723305158136e-05, "epoch": 0.518, "percentage": 51.8, "elapsed_time": "0:06:27", "remaining_time": "0:06:00"}
{"current_steps": 2600, "total_steps": 5000, "loss": 0.815, "lr": 2.761321158169134e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:06:29", "remaining_time": "0:05:59"}
{"current_steps": 2610, "total_steps": 5000, "loss": 1.06, "lr": 2.7439572493978736e-05, "epoch": 0.522, "percentage": 52.2, "elapsed_time": "0:06:30", "remaining_time": "0:05:57"}
{"current_steps": 2620, "total_steps": 5000, "loss": 0.5301, "lr": 2.726581450494451e-05, "epoch": 0.524, "percentage": 52.4, "elapsed_time": "0:06:31", "remaining_time": "0:05:55"}
{"current_steps": 2630, "total_steps": 5000, "loss": 0.9168, "lr": 2.7091946083307896e-05, "epoch": 0.526, "percentage": 52.6, "elapsed_time": "0:06:33", "remaining_time": "0:05:54"}
{"current_steps": 2640, "total_steps": 5000, "loss": 0.6632, "lr": 2.6917975703170466e-05, "epoch": 0.528, "percentage": 52.8, "elapsed_time": "0:06:34", "remaining_time": "0:05:52"}
{"current_steps": 2650, "total_steps": 5000, "loss": 0.4707, "lr": 2.674391184360313e-05, "epoch": 0.53, "percentage": 53.0, "elapsed_time": "0:06:35", "remaining_time": "0:05:51"}
{"current_steps": 2660, "total_steps": 5000, "loss": 0.4239, "lr": 2.656976298823284e-05, "epoch": 0.532, "percentage": 53.2, "elapsed_time": "0:06:37", "remaining_time": "0:05:49"}
{"current_steps": 2670, "total_steps": 5000, "loss": 0.9173, "lr": 2.6395537624829096e-05, "epoch": 0.534, "percentage": 53.4, "elapsed_time": "0:06:38", "remaining_time": "0:05:47"}
{"current_steps": 2680, "total_steps": 5000, "loss": 0.5302, "lr": 2.6221244244890336e-05, "epoch": 0.536, "percentage": 53.6, "elapsed_time": "0:06:39", "remaining_time": "0:05:46"}
{"current_steps": 2690, "total_steps": 5000, "loss": 0.3321, "lr": 2.604689134322999e-05, "epoch": 0.538, "percentage": 53.8, "elapsed_time": "0:06:41", "remaining_time": "0:05:44"}
{"current_steps": 2700, "total_steps": 5000, "loss": 0.4862, "lr": 2.587248741756253e-05, "epoch": 0.54, "percentage": 54.0, "elapsed_time": "0:06:42", "remaining_time": "0:05:42"}
{"current_steps": 2710, "total_steps": 5000, "loss": 1.0757, "lr": 2.5698040968089225e-05, "epoch": 0.542, "percentage": 54.2, "elapsed_time": "0:06:43", "remaining_time": "0:05:41"}
{"current_steps": 2720, "total_steps": 5000, "loss": 1.0691, "lr": 2.5523560497083926e-05, "epoch": 0.544, "percentage": 54.4, "elapsed_time": "0:06:45", "remaining_time": "0:05:39"}
{"current_steps": 2730, "total_steps": 5000, "loss": 0.4269, "lr": 2.5349054508478637e-05, "epoch": 0.546, "percentage": 54.6, "elapsed_time": "0:06:46", "remaining_time": "0:05:38"}
{"current_steps": 2740, "total_steps": 5000, "loss": 0.2879, "lr": 2.517453150744904e-05, "epoch": 0.548, "percentage": 54.8, "elapsed_time": "0:06:47", "remaining_time": "0:05:36"}
{"current_steps": 2750, "total_steps": 5000, "loss": 0.5823, "lr": 2.5e-05, "epoch": 0.55, "percentage": 55.0, "elapsed_time": "0:06:48", "remaining_time": "0:05:34"}
{"current_steps": 2760, "total_steps": 5000, "loss": 0.821, "lr": 2.4825468492550964e-05, "epoch": 0.552, "percentage": 55.2, "elapsed_time": "0:06:50", "remaining_time": "0:05:32"}
{"current_steps": 2770, "total_steps": 5000, "loss": 1.1698, "lr": 2.4650945491521372e-05, "epoch": 0.554, "percentage": 55.4, "elapsed_time": "0:06:51", "remaining_time": "0:05:31"}
{"current_steps": 2780, "total_steps": 5000, "loss": 0.5302, "lr": 2.447643950291608e-05, "epoch": 0.556, "percentage": 55.6, "elapsed_time": "0:06:53", "remaining_time": "0:05:30"}
{"current_steps": 2790, "total_steps": 5000, "loss": 0.4541, "lr": 2.4301959031910784e-05, "epoch": 0.558, "percentage": 55.8, "elapsed_time": "0:06:54", "remaining_time": "0:05:28"}
{"current_steps": 2800, "total_steps": 5000, "loss": 0.8067, "lr": 2.4127512582437485e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:06:56", "remaining_time": "0:05:26"}
{"current_steps": 2810, "total_steps": 5000, "loss": 1.6585, "lr": 2.3953108656770016e-05, "epoch": 0.562, "percentage": 56.2, "elapsed_time": "0:06:57", "remaining_time": "0:05:25"}
{"current_steps": 2820, "total_steps": 5000, "loss": 0.5553, "lr": 2.377875575510967e-05, "epoch": 0.564, "percentage": 56.4, "elapsed_time": "0:06:58", "remaining_time": "0:05:23"}
{"current_steps": 2830, "total_steps": 5000, "loss": 0.8689, "lr": 2.3604462375170906e-05, "epoch": 0.566, "percentage": 56.6, "elapsed_time": "0:07:00", "remaining_time": "0:05:22"}
{"current_steps": 2840, "total_steps": 5000, "loss": 0.8926, "lr": 2.3430237011767167e-05, "epoch": 0.568, "percentage": 56.8, "elapsed_time": "0:07:02", "remaining_time": "0:05:21"}
{"current_steps": 2850, "total_steps": 5000, "loss": 0.288, "lr": 2.3256088156396868e-05, "epoch": 0.57, "percentage": 57.0, "elapsed_time": "0:07:03", "remaining_time": "0:05:19"}
{"current_steps": 2860, "total_steps": 5000, "loss": 0.9472, "lr": 2.3082024296829536e-05, "epoch": 0.572, "percentage": 57.2, "elapsed_time": "0:07:04", "remaining_time": "0:05:17"}
{"current_steps": 2870, "total_steps": 5000, "loss": 0.5556, "lr": 2.2908053916692117e-05, "epoch": 0.574, "percentage": 57.4, "elapsed_time": "0:07:05", "remaining_time": "0:05:16"}
{"current_steps": 2880, "total_steps": 5000, "loss": 0.5373, "lr": 2.2734185495055503e-05, "epoch": 0.576, "percentage": 57.6, "elapsed_time": "0:07:07", "remaining_time": "0:05:14"}
{"current_steps": 2890, "total_steps": 5000, "loss": 0.5617, "lr": 2.2560427506021266e-05, "epoch": 0.578, "percentage": 57.8, "elapsed_time": "0:07:09", "remaining_time": "0:05:13"}
{"current_steps": 2900, "total_steps": 5000, "loss": 0.4768, "lr": 2.238678841830867e-05, "epoch": 0.58, "percentage": 58.0, "elapsed_time": "0:07:10", "remaining_time": "0:05:11"}
{"current_steps": 2910, "total_steps": 5000, "loss": 0.7331, "lr": 2.2213276694841866e-05, "epoch": 0.582, "percentage": 58.2, "elapsed_time": "0:07:11", "remaining_time": "0:05:10"}
{"current_steps": 2920, "total_steps": 5000, "loss": 0.7499, "lr": 2.2039900792337474e-05, "epoch": 0.584, "percentage": 58.4, "elapsed_time": "0:07:13", "remaining_time": "0:05:08"}
{"current_steps": 2930, "total_steps": 5000, "loss": 0.2326, "lr": 2.186666916089239e-05, "epoch": 0.586, "percentage": 58.6, "elapsed_time": "0:07:14", "remaining_time": "0:05:06"}
{"current_steps": 2940, "total_steps": 5000, "loss": 0.4934, "lr": 2.1693590243571938e-05, "epoch": 0.588, "percentage": 58.8, "elapsed_time": "0:07:15", "remaining_time": "0:05:05"}
{"current_steps": 2950, "total_steps": 5000, "loss": 0.4456, "lr": 2.1520672475998373e-05, "epoch": 0.59, "percentage": 59.0, "elapsed_time": "0:07:17", "remaining_time": "0:05:03"}
{"current_steps": 2960, "total_steps": 5000, "loss": 1.162, "lr": 2.1347924285939714e-05, "epoch": 0.592, "percentage": 59.2, "elapsed_time": "0:07:19", "remaining_time": "0:05:02"}
{"current_steps": 2970, "total_steps": 5000, "loss": 0.6542, "lr": 2.117535409289905e-05, "epoch": 0.594, "percentage": 59.4, "elapsed_time": "0:07:20", "remaining_time": "0:05:01"}
{"current_steps": 2980, "total_steps": 5000, "loss": 0.4165, "lr": 2.1002970307704132e-05, "epoch": 0.596, "percentage": 59.6, "elapsed_time": "0:07:22", "remaining_time": "0:04:59"}
{"current_steps": 2990, "total_steps": 5000, "loss": 0.507, "lr": 2.0830781332097446e-05, "epoch": 0.598, "percentage": 59.8, "elapsed_time": "0:07:23", "remaining_time": "0:04:58"}
{"current_steps": 3000, "total_steps": 5000, "loss": 0.3102, "lr": 2.0658795558326743e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:07:24", "remaining_time": "0:04:56"}
{"current_steps": 3010, "total_steps": 5000, "loss": 0.553, "lr": 2.0487021368736003e-05, "epoch": 0.602, "percentage": 60.2, "elapsed_time": "0:07:26", "remaining_time": "0:04:55"}
{"current_steps": 3020, "total_steps": 5000, "loss": 0.4571, "lr": 2.031546713535688e-05, "epoch": 0.604, "percentage": 60.4, "elapsed_time": "0:07:27", "remaining_time": "0:04:53"}
{"current_steps": 3030, "total_steps": 5000, "loss": 0.5669, "lr": 2.0144141219500705e-05, "epoch": 0.606, "percentage": 60.6, "elapsed_time": "0:07:29", "remaining_time": "0:04:52"}
{"current_steps": 3040, "total_steps": 5000, "loss": 1.7729, "lr": 1.9973051971350888e-05, "epoch": 0.608, "percentage": 60.8, "elapsed_time": "0:07:30", "remaining_time": "0:04:50"}
{"current_steps": 3050, "total_steps": 5000, "loss": 0.4088, "lr": 1.980220772955602e-05, "epoch": 0.61, "percentage": 61.0, "elapsed_time": "0:07:32", "remaining_time": "0:04:49"}
{"current_steps": 3060, "total_steps": 5000, "loss": 1.1587, "lr": 1.963161682082342e-05, "epoch": 0.612, "percentage": 61.2, "elapsed_time": "0:07:33", "remaining_time": "0:04:47"}
{"current_steps": 3070, "total_steps": 5000, "loss": 0.8176, "lr": 1.946128755951332e-05, "epoch": 0.614, "percentage": 61.4, "elapsed_time": "0:07:35", "remaining_time": "0:04:46"}
{"current_steps": 3080, "total_steps": 5000, "loss": 0.692, "lr": 1.9291228247233605e-05, "epoch": 0.616, "percentage": 61.6, "elapsed_time": "0:07:37", "remaining_time": "0:04:44"}
{"current_steps": 3090, "total_steps": 5000, "loss": 1.075, "lr": 1.912144717243525e-05, "epoch": 0.618, "percentage": 61.8, "elapsed_time": "0:07:38", "remaining_time": "0:04:43"}
{"current_steps": 3100, "total_steps": 5000, "loss": 0.4993, "lr": 1.895195261000831e-05, "epoch": 0.62, "percentage": 62.0, "elapsed_time": "0:07:39", "remaining_time": "0:04:41"}
{"current_steps": 3110, "total_steps": 5000, "loss": 0.4362, "lr": 1.8782752820878634e-05, "epoch": 0.622, "percentage": 62.2, "elapsed_time": "0:07:41", "remaining_time": "0:04:40"}
{"current_steps": 3120, "total_steps": 5000, "loss": 0.5678, "lr": 1.8613856051605243e-05, "epoch": 0.624, "percentage": 62.4, "elapsed_time": "0:07:42", "remaining_time": "0:04:38"}
{"current_steps": 3130, "total_steps": 5000, "loss": 0.8305, "lr": 1.8445270533978388e-05, "epoch": 0.626, "percentage": 62.6, "elapsed_time": "0:07:44", "remaining_time": "0:04:37"}
{"current_steps": 3140, "total_steps": 5000, "loss": 0.6363, "lr": 1.827700448461836e-05, "epoch": 0.628, "percentage": 62.8, "elapsed_time": "0:07:45", "remaining_time": "0:04:35"}
{"current_steps": 3150, "total_steps": 5000, "loss": 0.4256, "lr": 1.8109066104575023e-05, "epoch": 0.63, "percentage": 63.0, "elapsed_time": "0:07:46", "remaining_time": "0:04:34"}
{"current_steps": 3160, "total_steps": 5000, "loss": 0.6952, "lr": 1.7941463578928086e-05, "epoch": 0.632, "percentage": 63.2, "elapsed_time": "0:07:48", "remaining_time": "0:04:32"}
{"current_steps": 3170, "total_steps": 5000, "loss": 0.8197, "lr": 1.7774205076388206e-05, "epoch": 0.634, "percentage": 63.4, "elapsed_time": "0:07:49", "remaining_time": "0:04:31"}
{"current_steps": 3180, "total_steps": 5000, "loss": 1.2469, "lr": 1.7607298748898842e-05, "epoch": 0.636, "percentage": 63.6, "elapsed_time": "0:07:51", "remaining_time": "0:04:29"}
{"current_steps": 3190, "total_steps": 5000, "loss": 0.2531, "lr": 1.744075273123889e-05, "epoch": 0.638, "percentage": 63.8, "elapsed_time": "0:07:52", "remaining_time": "0:04:28"}
{"current_steps": 3200, "total_steps": 5000, "loss": 0.965, "lr": 1.7274575140626318e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:07:54", "remaining_time": "0:04:26"}
{"current_steps": 3210, "total_steps": 5000, "loss": 0.4128, "lr": 1.7108774076322443e-05, "epoch": 0.642, "percentage": 64.2, "elapsed_time": "0:07:55", "remaining_time": "0:04:25"}
{"current_steps": 3220, "total_steps": 5000, "loss": 0.4725, "lr": 1.6943357619237226e-05, "epoch": 0.644, "percentage": 64.4, "elapsed_time": "0:07:56", "remaining_time": "0:04:23"}
{"current_steps": 3230, "total_steps": 5000, "loss": 0.3222, "lr": 1.677833383153542e-05, "epoch": 0.646, "percentage": 64.6, "elapsed_time": "0:07:58", "remaining_time": "0:04:21"}
{"current_steps": 3240, "total_steps": 5000, "loss": 0.5883, "lr": 1.6613710756243626e-05, "epoch": 0.648, "percentage": 64.8, "elapsed_time": "0:07:59", "remaining_time": "0:04:20"}
{"current_steps": 3250, "total_steps": 5000, "loss": 0.7147, "lr": 1.6449496416858284e-05, "epoch": 0.65, "percentage": 65.0, "elapsed_time": "0:08:01", "remaining_time": "0:04:19"}
{"current_steps": 3260, "total_steps": 5000, "loss": 0.4388, "lr": 1.6285698816954624e-05, "epoch": 0.652, "percentage": 65.2, "elapsed_time": "0:08:02", "remaining_time": "0:04:17"}
{"current_steps": 3270, "total_steps": 5000, "loss": 0.6912, "lr": 1.612232593979658e-05, "epoch": 0.654, "percentage": 65.4, "elapsed_time": "0:08:03", "remaining_time": "0:04:15"}
{"current_steps": 3280, "total_steps": 5000, "loss": 0.8918, "lr": 1.5959385747947698e-05, "epoch": 0.656, "percentage": 65.6, "elapsed_time": "0:08:05", "remaining_time": "0:04:14"}
{"current_steps": 3290, "total_steps": 5000, "loss": 0.6978, "lr": 1.5796886182883053e-05, "epoch": 0.658, "percentage": 65.8, "elapsed_time": "0:08:06", "remaining_time": "0:04:12"}
{"current_steps": 3300, "total_steps": 5000, "loss": 0.567, "lr": 1.56348351646022e-05, "epoch": 0.66, "percentage": 66.0, "elapsed_time": "0:08:08", "remaining_time": "0:04:11"}
{"current_steps": 3310, "total_steps": 5000, "loss": 0.6566, "lr": 1.547324059124315e-05, "epoch": 0.662, "percentage": 66.2, "elapsed_time": "0:08:09", "remaining_time": "0:04:09"}
{"current_steps": 3320, "total_steps": 5000, "loss": 1.0336, "lr": 1.5312110338697426e-05, "epoch": 0.664, "percentage": 66.4, "elapsed_time": "0:08:10", "remaining_time": "0:04:08"}
{"current_steps": 3330, "total_steps": 5000, "loss": 0.354, "lr": 1.5151452260226224e-05, "epoch": 0.666, "percentage": 66.6, "elapsed_time": "0:08:12", "remaining_time": "0:04:06"}
{"current_steps": 3340, "total_steps": 5000, "loss": 0.6524, "lr": 1.4991274186077632e-05, "epoch": 0.668, "percentage": 66.8, "elapsed_time": "0:08:13", "remaining_time": "0:04:05"}
{"current_steps": 3350, "total_steps": 5000, "loss": 0.3062, "lr": 1.4831583923104999e-05, "epoch": 0.67, "percentage": 67.0, "elapsed_time": "0:08:14", "remaining_time": "0:04:03"}
{"current_steps": 3360, "total_steps": 5000, "loss": 0.8857, "lr": 1.467238925438646e-05, "epoch": 0.672, "percentage": 67.2, "elapsed_time": "0:08:16", "remaining_time": "0:04:02"}
{"current_steps": 3370, "total_steps": 5000, "loss": 0.5122, "lr": 1.4513697938845572e-05, "epoch": 0.674, "percentage": 67.4, "elapsed_time": "0:08:18", "remaining_time": "0:04:01"}
{"current_steps": 3380, "total_steps": 5000, "loss": 0.3351, "lr": 1.4355517710873184e-05, "epoch": 0.676, "percentage": 67.6, "elapsed_time": "0:08:19", "remaining_time": "0:03:59"}
{"current_steps": 3390, "total_steps": 5000, "loss": 0.744, "lr": 1.4197856279950438e-05, "epoch": 0.678, "percentage": 67.8, "elapsed_time": "0:08:21", "remaining_time": "0:03:58"}
{"current_steps": 3400, "total_steps": 5000, "loss": 0.3803, "lr": 1.4040721330273062e-05, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:08:22", "remaining_time": "0:03:56"}
{"current_steps": 3410, "total_steps": 5000, "loss": 0.3887, "lr": 1.388412052037682e-05, "epoch": 0.682, "percentage": 68.2, "elapsed_time": "0:08:24", "remaining_time": "0:03:55"}
{"current_steps": 3420, "total_steps": 5000, "loss": 1.3057, "lr": 1.3728061482764238e-05, "epoch": 0.684, "percentage": 68.4, "elapsed_time": "0:08:26", "remaining_time": "0:03:53"}
{"current_steps": 3430, "total_steps": 5000, "loss": 0.8347, "lr": 1.3572551823532654e-05, "epoch": 0.686, "percentage": 68.6, "elapsed_time": "0:08:27", "remaining_time": "0:03:52"}
{"current_steps": 3440, "total_steps": 5000, "loss": 0.5201, "lr": 1.3417599122003464e-05, "epoch": 0.688, "percentage": 68.8, "elapsed_time": "0:08:29", "remaining_time": "0:03:50"}
{"current_steps": 3450, "total_steps": 5000, "loss": 0.7833, "lr": 1.3263210930352737e-05, "epoch": 0.69, "percentage": 69.0, "elapsed_time": "0:08:30", "remaining_time": "0:03:49"}
{"current_steps": 3460, "total_steps": 5000, "loss": 0.5767, "lr": 1.3109394773243117e-05, "epoch": 0.692, "percentage": 69.2, "elapsed_time": "0:08:32", "remaining_time": "0:03:47"}
{"current_steps": 3470, "total_steps": 5000, "loss": 0.6141, "lr": 1.2956158147457115e-05, "epoch": 0.694, "percentage": 69.4, "elapsed_time": "0:08:33", "remaining_time": "0:03:46"}
{"current_steps": 3480, "total_steps": 5000, "loss": 0.4857, "lr": 1.280350852153168e-05, "epoch": 0.696, "percentage": 69.6, "elapsed_time": "0:08:35", "remaining_time": "0:03:44"}
{"current_steps": 3490, "total_steps": 5000, "loss": 0.4343, "lr": 1.2651453335394231e-05, "epoch": 0.698, "percentage": 69.8, "elapsed_time": "0:08:36", "remaining_time": "0:03:43"}
{"current_steps": 3500, "total_steps": 5000, "loss": 0.5756, "lr": 1.2500000000000006e-05, "epoch": 0.7, "percentage": 70.0, "elapsed_time": "0:08:38", "remaining_time": "0:03:42"}
{"current_steps": 3510, "total_steps": 5000, "loss": 0.3058, "lr": 1.234915589697091e-05, "epoch": 0.702, "percentage": 70.2, "elapsed_time": "0:08:39", "remaining_time": "0:03:40"}
{"current_steps": 3520, "total_steps": 5000, "loss": 0.8025, "lr": 1.2198928378235716e-05, "epoch": 0.704, "percentage": 70.4, "elapsed_time": "0:08:40", "remaining_time": "0:03:39"}
{"current_steps": 3530, "total_steps": 5000, "loss": 0.7852, "lr": 1.2049324765671749e-05, "epoch": 0.706, "percentage": 70.6, "elapsed_time": "0:08:42", "remaining_time": "0:03:37"}
{"current_steps": 3540, "total_steps": 5000, "loss": 0.3626, "lr": 1.1900352350748026e-05, "epoch": 0.708, "percentage": 70.8, "elapsed_time": "0:08:43", "remaining_time": "0:03:36"}
{"current_steps": 3550, "total_steps": 5000, "loss": 0.5091, "lr": 1.175201839416988e-05, "epoch": 0.71, "percentage": 71.0, "elapsed_time": "0:08:45", "remaining_time": "0:03:34"}
{"current_steps": 3560, "total_steps": 5000, "loss": 0.619, "lr": 1.1604330125525079e-05, "epoch": 0.712, "percentage": 71.2, "elapsed_time": "0:08:46", "remaining_time": "0:03:33"}
{"current_steps": 3570, "total_steps": 5000, "loss": 0.5655, "lr": 1.1457294742931507e-05, "epoch": 0.714, "percentage": 71.4, "elapsed_time": "0:08:48", "remaining_time": "0:03:31"}
{"current_steps": 3580, "total_steps": 5000, "loss": 1.0515, "lr": 1.1310919412686247e-05, "epoch": 0.716, "percentage": 71.6, "elapsed_time": "0:08:49", "remaining_time": "0:03:29"}
{"current_steps": 3590, "total_steps": 5000, "loss": 0.8076, "lr": 1.11652112689164e-05, "epoch": 0.718, "percentage": 71.8, "elapsed_time": "0:08:50", "remaining_time": "0:03:28"}
{"current_steps": 3600, "total_steps": 5000, "loss": 0.6979, "lr": 1.1020177413231334e-05, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:08:51", "remaining_time": "0:03:26"}
{"current_steps": 3610, "total_steps": 5000, "loss": 0.5854, "lr": 1.0875824914376553e-05, "epoch": 0.722, "percentage": 72.2, "elapsed_time": "0:08:52", "remaining_time": "0:03:25"}
{"current_steps": 3620, "total_steps": 5000, "loss": 1.3998, "lr": 1.0732160807889211e-05, "epoch": 0.724, "percentage": 72.4, "elapsed_time": "0:08:54", "remaining_time": "0:03:23"}
{"current_steps": 3630, "total_steps": 5000, "loss": 0.651, "lr": 1.058919209575517e-05, "epoch": 0.726, "percentage": 72.6, "elapsed_time": "0:08:56", "remaining_time": "0:03:22"}
{"current_steps": 3640, "total_steps": 5000, "loss": 0.7235, "lr": 1.0446925746067768e-05, "epoch": 0.728, "percentage": 72.8, "elapsed_time": "0:08:57", "remaining_time": "0:03:20"}
{"current_steps": 3650, "total_steps": 5000, "loss": 0.616, "lr": 1.0305368692688174e-05, "epoch": 0.73, "percentage": 73.0, "elapsed_time": "0:08:59", "remaining_time": "0:03:19"}
{"current_steps": 3660, "total_steps": 5000, "loss": 0.7025, "lr": 1.0164527834907467e-05, "epoch": 0.732, "percentage": 73.2, "elapsed_time": "0:09:00", "remaining_time": "0:03:17"}
{"current_steps": 3670, "total_steps": 5000, "loss": 0.8585, "lr": 1.0024410037110357e-05, "epoch": 0.734, "percentage": 73.4, "elapsed_time": "0:09:02", "remaining_time": "0:03:16"}
{"current_steps": 3680, "total_steps": 5000, "loss": 0.5602, "lr": 9.88502212844063e-06, "epoch": 0.736, "percentage": 73.6, "elapsed_time": "0:09:03", "remaining_time": "0:03:14"}
{"current_steps": 3690, "total_steps": 5000, "loss": 0.765, "lr": 9.746370902468311e-06, "epoch": 0.738, "percentage": 73.8, "elapsed_time": "0:09:04", "remaining_time": "0:03:13"}
{"current_steps": 3700, "total_steps": 5000, "loss": 0.4188, "lr": 9.608463116858542e-06, "epoch": 0.74, "percentage": 74.0, "elapsed_time": "0:09:06", "remaining_time": "0:03:11"}
{"current_steps": 3710, "total_steps": 5000, "loss": 0.3881, "lr": 9.471305493042243e-06, "epoch": 0.742, "percentage": 74.2, "elapsed_time": "0:09:07", "remaining_time": "0:03:10"}
{"current_steps": 3720, "total_steps": 5000, "loss": 0.7391, "lr": 9.334904715888495e-06, "epoch": 0.744, "percentage": 74.4, "elapsed_time": "0:09:08", "remaining_time": "0:03:08"}
{"current_steps": 3730, "total_steps": 5000, "loss": 0.818, "lr": 9.199267433378727e-06, "epoch": 0.746, "percentage": 74.6, "elapsed_time": "0:09:10", "remaining_time": "0:03:07"}
{"current_steps": 3740, "total_steps": 5000, "loss": 0.4283, "lr": 9.064400256282757e-06, "epoch": 0.748, "percentage": 74.8, "elapsed_time": "0:09:11", "remaining_time": "0:03:05"}
{"current_steps": 3750, "total_steps": 5000, "loss": 0.7522, "lr": 8.930309757836517e-06, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:09:12", "remaining_time": "0:03:04"}
{"current_steps": 3760, "total_steps": 5000, "loss": 0.4206, "lr": 8.797002473421728e-06, "epoch": 0.752, "percentage": 75.2, "elapsed_time": "0:09:13", "remaining_time": "0:03:02"}
{"current_steps": 3770, "total_steps": 5000, "loss": 0.7134, "lr": 8.664484900247363e-06, "epoch": 0.754, "percentage": 75.4, "elapsed_time": "0:09:15", "remaining_time": "0:03:01"}
{"current_steps": 3780, "total_steps": 5000, "loss": 1.3107, "lr": 8.532763497032987e-06, "epoch": 0.756, "percentage": 75.6, "elapsed_time": "0:09:17", "remaining_time": "0:02:59"}
{"current_steps": 3790, "total_steps": 5000, "loss": 0.4646, "lr": 8.40184468369396e-06, "epoch": 0.758, "percentage": 75.8, "elapsed_time": "0:09:18", "remaining_time": "0:02:58"}
{"current_steps": 3800, "total_steps": 5000, "loss": 0.9086, "lr": 8.271734841028553e-06, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:09:20", "remaining_time": "0:02:56"}
{"current_steps": 3810, "total_steps": 5000, "loss": 0.8141, "lr": 8.142440310406924e-06, "epoch": 0.762, "percentage": 76.2, "elapsed_time": "0:09:21", "remaining_time": "0:02:55"}
{"current_steps": 3820, "total_steps": 5000, "loss": 0.5139, "lr": 8.013967393462094e-06, "epoch": 0.764, "percentage": 76.4, "elapsed_time": "0:09:23", "remaining_time": "0:02:54"}
{"current_steps": 3830, "total_steps": 5000, "loss": 0.7961, "lr": 7.886322351782783e-06, "epoch": 0.766, "percentage": 76.6, "elapsed_time": "0:09:25", "remaining_time": "0:02:52"}
{"current_steps": 3840, "total_steps": 5000, "loss": 1.0111, "lr": 7.759511406608255e-06, "epoch": 0.768, "percentage": 76.8, "elapsed_time": "0:09:26", "remaining_time": "0:02:51"}
{"current_steps": 3850, "total_steps": 5000, "loss": 0.796, "lr": 7.633540738525066e-06, "epoch": 0.77, "percentage": 77.0, "elapsed_time": "0:09:28", "remaining_time": "0:02:49"}
{"current_steps": 3860, "total_steps": 5000, "loss": 0.6173, "lr": 7.508416487165862e-06, "epoch": 0.772, "percentage": 77.2, "elapsed_time": "0:09:29", "remaining_time": "0:02:48"}
{"current_steps": 3870, "total_steps": 5000, "loss": 0.524, "lr": 7.384144750910133e-06, "epoch": 0.774, "percentage": 77.4, "elapsed_time": "0:09:31", "remaining_time": "0:02:46"}
{"current_steps": 3880, "total_steps": 5000, "loss": 0.8207, "lr": 7.260731586586983e-06, "epoch": 0.776, "percentage": 77.6, "elapsed_time": "0:09:32", "remaining_time": "0:02:45"}
{"current_steps": 3890, "total_steps": 5000, "loss": 0.3658, "lr": 7.138183009179922e-06, "epoch": 0.778, "percentage": 77.8, "elapsed_time": "0:09:33", "remaining_time": "0:02:43"}
{"current_steps": 3900, "total_steps": 5000, "loss": 1.2585, "lr": 7.016504991533726e-06, "epoch": 0.78, "percentage": 78.0, "elapsed_time": "0:09:35", "remaining_time": "0:02:42"}
{"current_steps": 3910, "total_steps": 5000, "loss": 0.2703, "lr": 6.895703464063319e-06, "epoch": 0.782, "percentage": 78.2, "elapsed_time": "0:09:36", "remaining_time": "0:02:40"}
{"current_steps": 3920, "total_steps": 5000, "loss": 0.6309, "lr": 6.775784314464717e-06, "epoch": 0.784, "percentage": 78.4, "elapsed_time": "0:09:38", "remaining_time": "0:02:39"}
{"current_steps": 3930, "total_steps": 5000, "loss": 1.43, "lr": 6.656753387428089e-06, "epoch": 0.786, "percentage": 78.6, "elapsed_time": "0:09:39", "remaining_time": "0:02:37"}
{"current_steps": 3940, "total_steps": 5000, "loss": 0.4932, "lr": 6.538616484352902e-06, "epoch": 0.788, "percentage": 78.8, "elapsed_time": "0:09:41", "remaining_time": "0:02:36"}
{"current_steps": 3950, "total_steps": 5000, "loss": 1.3789, "lr": 6.421379363065142e-06, "epoch": 0.79, "percentage": 79.0, "elapsed_time": "0:09:42", "remaining_time": "0:02:34"}
{"current_steps": 3960, "total_steps": 5000, "loss": 0.61, "lr": 6.305047737536707e-06, "epoch": 0.792, "percentage": 79.2, "elapsed_time": "0:09:44", "remaining_time": "0:02:33"}
{"current_steps": 3970, "total_steps": 5000, "loss": 0.5308, "lr": 6.189627277606894e-06, "epoch": 0.794, "percentage": 79.4, "elapsed_time": "0:09:45", "remaining_time": "0:02:32"}
{"current_steps": 3980, "total_steps": 5000, "loss": 0.5047, "lr": 6.075123608706093e-06, "epoch": 0.796, "percentage": 79.6, "elapsed_time": "0:09:47", "remaining_time": "0:02:30"}
{"current_steps": 3990, "total_steps": 5000, "loss": 1.0775, "lr": 5.961542311581586e-06, "epoch": 0.798, "percentage": 79.8, "elapsed_time": "0:09:48", "remaining_time": "0:02:29"}
{"current_steps": 4000, "total_steps": 5000, "loss": 0.3777, "lr": 5.848888922025553e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:09:50", "remaining_time": "0:02:27"}
{"current_steps": 4010, "total_steps": 5000, "loss": 0.2574, "lr": 5.737168930605272e-06, "epoch": 0.802, "percentage": 80.2, "elapsed_time": "0:09:52", "remaining_time": "0:02:26"}
{"current_steps": 4020, "total_steps": 5000, "loss": 0.5718, "lr": 5.626387782395512e-06, "epoch": 0.804, "percentage": 80.4, "elapsed_time": "0:09:54", "remaining_time": "0:02:24"}
{"current_steps": 4030, "total_steps": 5000, "loss": 0.9235, "lr": 5.5165508767131415e-06, "epoch": 0.806, "percentage": 80.6, "elapsed_time": "0:09:55", "remaining_time": "0:02:23"}
{"current_steps": 4040, "total_steps": 5000, "loss": 1.5454, "lr": 5.4076635668540075e-06, "epoch": 0.808, "percentage": 80.8, "elapsed_time": "0:09:56", "remaining_time": "0:02:21"}
{"current_steps": 4050, "total_steps": 5000, "loss": 1.1003, "lr": 5.299731159831953e-06, "epoch": 0.81, "percentage": 81.0, "elapsed_time": "0:09:58", "remaining_time": "0:02:20"}
{"current_steps": 4060, "total_steps": 5000, "loss": 0.534, "lr": 5.192758916120236e-06, "epoch": 0.812, "percentage": 81.2, "elapsed_time": "0:09:59", "remaining_time": "0:02:18"}
{"current_steps": 4070, "total_steps": 5000, "loss": 0.4262, "lr": 5.086752049395094e-06, "epoch": 0.814, "percentage": 81.4, "elapsed_time": "0:10:01", "remaining_time": "0:02:17"}
{"current_steps": 4080, "total_steps": 5000, "loss": 0.4132, "lr": 4.981715726281666e-06, "epoch": 0.816, "percentage": 81.6, "elapsed_time": "0:10:02", "remaining_time": "0:02:15"}
{"current_steps": 4090, "total_steps": 5000, "loss": 0.5956, "lr": 4.877655066102149e-06, "epoch": 0.818, "percentage": 81.8, "elapsed_time": "0:10:04", "remaining_time": "0:02:14"}
{"current_steps": 4100, "total_steps": 5000, "loss": 0.2506, "lr": 4.7745751406263165e-06, "epoch": 0.82, "percentage": 82.0, "elapsed_time": "0:10:05", "remaining_time": "0:02:12"}
{"current_steps": 4110, "total_steps": 5000, "loss": 0.67, "lr": 4.672480973824311e-06, "epoch": 0.822, "percentage": 82.2, "elapsed_time": "0:10:07", "remaining_time": "0:02:11"}
{"current_steps": 4120, "total_steps": 5000, "loss": 0.6636, "lr": 4.571377541621788e-06, "epoch": 0.824, "percentage": 82.4, "elapsed_time": "0:10:08", "remaining_time": "0:02:10"}
{"current_steps": 4130, "total_steps": 5000, "loss": 0.489, "lr": 4.4712697716574e-06, "epoch": 0.826, "percentage": 82.6, "elapsed_time": "0:10:10", "remaining_time": "0:02:08"}
{"current_steps": 4140, "total_steps": 5000, "loss": 0.5484, "lr": 4.372162543042624e-06, "epoch": 0.828, "percentage": 82.8, "elapsed_time": "0:10:11", "remaining_time": "0:02:07"}
{"current_steps": 4150, "total_steps": 5000, "loss": 0.7981, "lr": 4.274060686123959e-06, "epoch": 0.83, "percentage": 83.0, "elapsed_time": "0:10:13", "remaining_time": "0:02:05"}
{"current_steps": 4160, "total_steps": 5000, "loss": 0.4005, "lr": 4.176968982247514e-06, "epoch": 0.832, "percentage": 83.2, "elapsed_time": "0:10:14", "remaining_time": "0:02:04"}
{"current_steps": 4170, "total_steps": 5000, "loss": 0.6218, "lr": 4.08089216352596e-06, "epoch": 0.834, "percentage": 83.4, "elapsed_time": "0:10:16", "remaining_time": "0:02:02"}
{"current_steps": 4180, "total_steps": 5000, "loss": 0.3839, "lr": 3.985834912607894e-06, "epoch": 0.836, "percentage": 83.6, "elapsed_time": "0:10:17", "remaining_time": "0:02:01"}
{"current_steps": 4190, "total_steps": 5000, "loss": 0.4054, "lr": 3.891801862449629e-06, "epoch": 0.838, "percentage": 83.8, "elapsed_time": "0:10:18", "remaining_time": "0:01:59"}
{"current_steps": 4200, "total_steps": 5000, "loss": 1.0778, "lr": 3.798797596089351e-06, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:10:20", "remaining_time": "0:01:58"}
{"current_steps": 4210, "total_steps": 5000, "loss": 0.9707, "lr": 3.7068266464238084e-06, "epoch": 0.842, "percentage": 84.2, "elapsed_time": "0:10:22", "remaining_time": "0:01:56"}
{"current_steps": 4220, "total_steps": 5000, "loss": 0.3651, "lr": 3.6158934959873353e-06, "epoch": 0.844, "percentage": 84.4, "elapsed_time": "0:10:23", "remaining_time": "0:01:55"}
{"current_steps": 4230, "total_steps": 5000, "loss": 1.3716, "lr": 3.5260025767333893e-06, "epoch": 0.846, "percentage": 84.6, "elapsed_time": "0:10:24", "remaining_time": "0:01:53"}
{"current_steps": 4240, "total_steps": 5000, "loss": 0.2041, "lr": 3.4371582698185633e-06, "epoch": 0.848, "percentage": 84.8, "elapsed_time": "0:10:26", "remaining_time": "0:01:52"}
{"current_steps": 4250, "total_steps": 5000, "loss": 0.3305, "lr": 3.3493649053890326e-06, "epoch": 0.85, "percentage": 85.0, "elapsed_time": "0:10:27", "remaining_time": "0:01:50"}
{"current_steps": 4260, "total_steps": 5000, "loss": 1.5044, "lr": 3.262626762369525e-06, "epoch": 0.852, "percentage": 85.2, "elapsed_time": "0:10:28", "remaining_time": "0:01:49"}
{"current_steps": 4270, "total_steps": 5000, "loss": 0.2929, "lr": 3.176948068254762e-06, "epoch": 0.854, "percentage": 85.4, "elapsed_time": "0:10:30", "remaining_time": "0:01:47"}
{"current_steps": 4280, "total_steps": 5000, "loss": 0.4449, "lr": 3.092332998903416e-06, "epoch": 0.856, "percentage": 85.6, "elapsed_time": "0:10:31", "remaining_time": "0:01:46"}
{"current_steps": 4290, "total_steps": 5000, "loss": 0.3881, "lr": 3.0087856783345914e-06, "epoch": 0.858, "percentage": 85.8, "elapsed_time": "0:10:33", "remaining_time": "0:01:44"}
{"current_steps": 4300, "total_steps": 5000, "loss": 0.8408, "lr": 2.9263101785268254e-06, "epoch": 0.86, "percentage": 86.0, "elapsed_time": "0:10:34", "remaining_time": "0:01:43"}
{"current_steps": 4310, "total_steps": 5000, "loss": 0.7198, "lr": 2.8449105192196316e-06, "epoch": 0.862, "percentage": 86.2, "elapsed_time": "0:10:36", "remaining_time": "0:01:41"}
{"current_steps": 4320, "total_steps": 5000, "loss": 0.4878, "lr": 2.764590667717562e-06, "epoch": 0.864, "percentage": 86.4, "elapsed_time": "0:10:38", "remaining_time": "0:01:40"}
{"current_steps": 4330, "total_steps": 5000, "loss": 0.4814, "lr": 2.6853545386968606e-06, "epoch": 0.866, "percentage": 86.6, "elapsed_time": "0:10:39", "remaining_time": "0:01:38"}
{"current_steps": 4340, "total_steps": 5000, "loss": 0.9695, "lr": 2.6072059940146775e-06, "epoch": 0.868, "percentage": 86.8, "elapsed_time": "0:10:40", "remaining_time": "0:01:37"}
{"current_steps": 4350, "total_steps": 5000, "loss": 0.3223, "lr": 2.5301488425208296e-06, "epoch": 0.87, "percentage": 87.0, "elapsed_time": "0:10:41", "remaining_time": "0:01:35"}
{"current_steps": 4360, "total_steps": 5000, "loss": 0.5006, "lr": 2.454186839872158e-06, "epoch": 0.872, "percentage": 87.2, "elapsed_time": "0:10:43", "remaining_time": "0:01:34"}
{"current_steps": 4370, "total_steps": 5000, "loss": 0.965, "lr": 2.379323688349516e-06, "epoch": 0.874, "percentage": 87.4, "elapsed_time": "0:10:45", "remaining_time": "0:01:33"}
{"current_steps": 4380, "total_steps": 5000, "loss": 0.9124, "lr": 2.3055630366772856e-06, "epoch": 0.876, "percentage": 87.6, "elapsed_time": "0:10:46", "remaining_time": "0:01:31"}
{"current_steps": 4390, "total_steps": 5000, "loss": 0.7947, "lr": 2.2329084798455746e-06, "epoch": 0.878, "percentage": 87.8, "elapsed_time": "0:10:47", "remaining_time": "0:01:30"}
{"current_steps": 4400, "total_steps": 5000, "loss": 0.7011, "lr": 2.1613635589349756e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:10:49", "remaining_time": "0:01:28"}
{"current_steps": 4410, "total_steps": 5000, "loss": 0.8777, "lr": 2.0909317609440095e-06, "epoch": 0.882, "percentage": 88.2, "elapsed_time": "0:10:50", "remaining_time": "0:01:27"}
{"current_steps": 4420, "total_steps": 5000, "loss": 0.7715, "lr": 2.0216165186191407e-06, "epoch": 0.884, "percentage": 88.4, "elapsed_time": "0:10:52", "remaining_time": "0:01:25"}
{"current_steps": 4430, "total_steps": 5000, "loss": 1.353, "lr": 1.95342121028749e-06, "epoch": 0.886, "percentage": 88.6, "elapsed_time": "0:10:54", "remaining_time": "0:01:24"}
{"current_steps": 4440, "total_steps": 5000, "loss": 0.6601, "lr": 1.8863491596921745e-06, "epoch": 0.888, "percentage": 88.8, "elapsed_time": "0:10:55", "remaining_time": "0:01:22"}
{"current_steps": 4450, "total_steps": 5000, "loss": 0.8026, "lr": 1.8204036358303173e-06, "epoch": 0.89, "percentage": 89.0, "elapsed_time": "0:10:57", "remaining_time": "0:01:21"}
{"current_steps": 4460, "total_steps": 5000, "loss": 0.8084, "lr": 1.7555878527937164e-06, "epoch": 0.892, "percentage": 89.2, "elapsed_time": "0:10:59", "remaining_time": "0:01:19"}
{"current_steps": 4470, "total_steps": 5000, "loss": 0.6885, "lr": 1.6919049696121958e-06, "epoch": 0.894, "percentage": 89.4, "elapsed_time": "0:11:00", "remaining_time": "0:01:18"}
{"current_steps": 4480, "total_steps": 5000, "loss": 0.449, "lr": 1.629358090099639e-06, "epoch": 0.896, "percentage": 89.6, "elapsed_time": "0:11:01", "remaining_time": "0:01:16"}
{"current_steps": 4490, "total_steps": 5000, "loss": 0.6524, "lr": 1.5679502627027136e-06, "epoch": 0.898, "percentage": 89.8, "elapsed_time": "0:11:03", "remaining_time": "0:01:15"}
{"current_steps": 4500, "total_steps": 5000, "loss": 0.546, "lr": 1.5076844803522922e-06, "epoch": 0.9, "percentage": 90.0, "elapsed_time": "0:11:04", "remaining_time": "0:01:13"}
{"current_steps": 4510, "total_steps": 5000, "loss": 0.6897, "lr": 1.4485636803175829e-06, "epoch": 0.902, "percentage": 90.2, "elapsed_time": "0:11:06", "remaining_time": "0:01:12"}
{"current_steps": 4520, "total_steps": 5000, "loss": 0.582, "lr": 1.3905907440629752e-06, "epoch": 0.904, "percentage": 90.4, "elapsed_time": "0:11:07", "remaining_time": "0:01:10"}
{"current_steps": 4530, "total_steps": 5000, "loss": 0.4826, "lr": 1.333768497107593e-06, "epoch": 0.906, "percentage": 90.6, "elapsed_time": "0:11:09", "remaining_time": "0:01:09"}
{"current_steps": 4540, "total_steps": 5000, "loss": 0.4091, "lr": 1.2780997088875869e-06, "epoch": 0.908, "percentage": 90.8, "elapsed_time": "0:11:10", "remaining_time": "0:01:07"}
{"current_steps": 4550, "total_steps": 5000, "loss": 0.6879, "lr": 1.2235870926211619e-06, "epoch": 0.91, "percentage": 91.0, "elapsed_time": "0:11:12", "remaining_time": "0:01:06"}
{"current_steps": 4560, "total_steps": 5000, "loss": 0.7509, "lr": 1.170233305176327e-06, "epoch": 0.912, "percentage": 91.2, "elapsed_time": "0:11:13", "remaining_time": "0:01:04"}
{"current_steps": 4570, "total_steps": 5000, "loss": 1.5482, "lr": 1.1180409469414094e-06, "epoch": 0.914, "percentage": 91.4, "elapsed_time": "0:11:14", "remaining_time": "0:01:03"}
{"current_steps": 4580, "total_steps": 5000, "loss": 1.5761, "lr": 1.067012561698319e-06, "epoch": 0.916, "percentage": 91.6, "elapsed_time": "0:11:15", "remaining_time": "0:01:01"}
{"current_steps": 4590, "total_steps": 5000, "loss": 2.6232, "lr": 1.0171506364985622e-06, "epoch": 0.918, "percentage": 91.8, "elapsed_time": "0:11:17", "remaining_time": "0:01:00"}
{"current_steps": 4600, "total_steps": 5000, "loss": 0.7789, "lr": 9.684576015420278e-07, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:11:19", "remaining_time": "0:00:59"}
{"current_steps": 4610, "total_steps": 5000, "loss": 0.5264, "lr": 9.209358300585474e-07, "epoch": 0.922, "percentage": 92.2, "elapsed_time": "0:11:20", "remaining_time": "0:00:57"}
{"current_steps": 4620, "total_steps": 5000, "loss": 0.9817, "lr": 8.745876381922147e-07, "epoch": 0.924, "percentage": 92.4, "elapsed_time": "0:11:22", "remaining_time": "0:00:56"}
{"current_steps": 4630, "total_steps": 5000, "loss": 0.5991, "lr": 8.294152848885157e-07, "epoch": 0.926, "percentage": 92.6, "elapsed_time": "0:11:24", "remaining_time": "0:00:54"}
{"current_steps": 4640, "total_steps": 5000, "loss": 0.3332, "lr": 7.854209717842231e-07, "epoch": 0.928, "percentage": 92.8, "elapsed_time": "0:11:25", "remaining_time": "0:00:53"}
{"current_steps": 4650, "total_steps": 5000, "loss": 0.5279, "lr": 7.426068431000882e-07, "epoch": 0.93, "percentage": 93.0, "elapsed_time": "0:11:27", "remaining_time": "0:00:51"}
{"current_steps": 4660, "total_steps": 5000, "loss": 0.8232, "lr": 7.009749855363456e-07, "epoch": 0.932, "percentage": 93.2, "elapsed_time": "0:11:28", "remaining_time": "0:00:50"}
{"current_steps": 4670, "total_steps": 5000, "loss": 0.3652, "lr": 6.605274281709928e-07, "epoch": 0.934, "percentage": 93.4, "elapsed_time": "0:11:30", "remaining_time": "0:00:48"}
{"current_steps": 4680, "total_steps": 5000, "loss": 0.5764, "lr": 6.212661423609184e-07, "epoch": 0.936, "percentage": 93.6, "elapsed_time": "0:11:31", "remaining_time": "0:00:47"}
{"current_steps": 4690, "total_steps": 5000, "loss": 0.3606, "lr": 5.83193041645802e-07, "epoch": 0.938, "percentage": 93.8, "elapsed_time": "0:11:33", "remaining_time": "0:00:45"}
{"current_steps": 4700, "total_steps": 5000, "loss": 0.5306, "lr": 5.463099816548579e-07, "epoch": 0.94, "percentage": 94.0, "elapsed_time": "0:11:34", "remaining_time": "0:00:44"}
{"current_steps": 4710, "total_steps": 5000, "loss": 0.8692, "lr": 5.106187600163987e-07, "epoch": 0.942, "percentage": 94.2, "elapsed_time": "0:11:35", "remaining_time": "0:00:42"}
{"current_steps": 4720, "total_steps": 5000, "loss": 0.9409, "lr": 4.7612111627021175e-07, "epoch": 0.944, "percentage": 94.4, "elapsed_time": "0:11:37", "remaining_time": "0:00:41"}
{"current_steps": 4730, "total_steps": 5000, "loss": 0.551, "lr": 4.4281873178278475e-07, "epoch": 0.946, "percentage": 94.6, "elapsed_time": "0:11:38", "remaining_time": "0:00:39"}
{"current_steps": 4740, "total_steps": 5000, "loss": 0.5758, "lr": 4.107132296653549e-07, "epoch": 0.948, "percentage": 94.8, "elapsed_time": "0:11:40", "remaining_time": "0:00:38"}
{"current_steps": 4750, "total_steps": 5000, "loss": 0.6085, "lr": 3.7980617469479953e-07, "epoch": 0.95, "percentage": 95.0, "elapsed_time": "0:11:41", "remaining_time": "0:00:36"}
{"current_steps": 4760, "total_steps": 5000, "loss": 0.8827, "lr": 3.5009907323737825e-07, "epoch": 0.952, "percentage": 95.2, "elapsed_time": "0:11:43", "remaining_time": "0:00:35"}
{"current_steps": 4770, "total_steps": 5000, "loss": 0.5734, "lr": 3.215933731753024e-07, "epoch": 0.954, "percentage": 95.4, "elapsed_time": "0:11:44", "remaining_time": "0:00:33"}
{"current_steps": 4780, "total_steps": 5000, "loss": 0.5136, "lr": 2.942904638361804e-07, "epoch": 0.956, "percentage": 95.6, "elapsed_time": "0:11:46", "remaining_time": "0:00:32"}
{"current_steps": 4790, "total_steps": 5000, "loss": 0.2626, "lr": 2.681916759252917e-07, "epoch": 0.958, "percentage": 95.8, "elapsed_time": "0:11:47", "remaining_time": "0:00:31"}
{"current_steps": 4800, "total_steps": 5000, "loss": 1.0927, "lr": 2.4329828146074095e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:11:48", "remaining_time": "0:00:29"}
{"current_steps": 4810, "total_steps": 5000, "loss": 0.5593, "lr": 2.1961149371145795e-07, "epoch": 0.962, "percentage": 96.2, "elapsed_time": "0:11:49", "remaining_time": "0:00:28"}
{"current_steps": 4820, "total_steps": 5000, "loss": 0.7596, "lr": 1.9713246713805588e-07, "epoch": 0.964, "percentage": 96.4, "elapsed_time": "0:11:51", "remaining_time": "0:00:26"}
{"current_steps": 4830, "total_steps": 5000, "loss": 0.7086, "lr": 1.7586229733657644e-07, "epoch": 0.966, "percentage": 96.6, "elapsed_time": "0:11:52", "remaining_time": "0:00:25"}
{"current_steps": 4840, "total_steps": 5000, "loss": 0.9577, "lr": 1.5580202098509077e-07, "epoch": 0.968, "percentage": 96.8, "elapsed_time": "0:11:54", "remaining_time": "0:00:23"}
{"current_steps": 4850, "total_steps": 5000, "loss": 0.8676, "lr": 1.3695261579316777e-07, "epoch": 0.97, "percentage": 97.0, "elapsed_time": "0:11:55", "remaining_time": "0:00:22"}
{"current_steps": 4860, "total_steps": 5000, "loss": 0.6059, "lr": 1.193150004542204e-07, "epoch": 0.972, "percentage": 97.2, "elapsed_time": "0:11:57", "remaining_time": "0:00:20"}
{"current_steps": 4870, "total_steps": 5000, "loss": 0.4411, "lr": 1.0289003460074165e-07, "epoch": 0.974, "percentage": 97.4, "elapsed_time": "0:11:58", "remaining_time": "0:00:19"}
{"current_steps": 4880, "total_steps": 5000, "loss": 0.9838, "lr": 8.767851876239074e-08, "epoch": 0.976, "percentage": 97.6, "elapsed_time": "0:12:00", "remaining_time": "0:00:17"}
{"current_steps": 4890, "total_steps": 5000, "loss": 0.512, "lr": 7.368119432699383e-08, "epoch": 0.978, "percentage": 97.8, "elapsed_time": "0:12:01", "remaining_time": "0:00:16"}
{"current_steps": 4900, "total_steps": 5000, "loss": 0.5021, "lr": 6.089874350439506e-08, "epoch": 0.98, "percentage": 98.0, "elapsed_time": "0:12:03", "remaining_time": "0:00:14"}
{"current_steps": 4910, "total_steps": 5000, "loss": 0.5234, "lr": 4.9331789293211026e-08, "epoch": 0.982, "percentage": 98.2, "elapsed_time": "0:12:05", "remaining_time": "0:00:13"}
{"current_steps": 4920, "total_steps": 5000, "loss": 0.5811, "lr": 3.8980895450474455e-08, "epoch": 0.984, "percentage": 98.4, "elapsed_time": "0:12:06", "remaining_time": "0:00:11"}
{"current_steps": 4930, "total_steps": 5000, "loss": 0.4558, "lr": 2.9846566464150626e-08, "epoch": 0.986, "percentage": 98.6, "elapsed_time": "0:12:07", "remaining_time": "0:00:10"}
{"current_steps": 4940, "total_steps": 5000, "loss": 0.7155, "lr": 2.192924752854042e-08, "epoch": 0.988, "percentage": 98.8, "elapsed_time": "0:12:08", "remaining_time": "0:00:08"}
{"current_steps": 4950, "total_steps": 5000, "loss": 0.4247, "lr": 1.522932452260595e-08, "epoch": 0.99, "percentage": 99.0, "elapsed_time": "0:12:10", "remaining_time": "0:00:07"}
{"current_steps": 4960, "total_steps": 5000, "loss": 0.533, "lr": 9.747123991141194e-09, "epoch": 0.992, "percentage": 99.2, "elapsed_time": "0:12:11", "remaining_time": "0:00:05"}
{"current_steps": 4970, "total_steps": 5000, "loss": 0.8961, "lr": 5.48291312886251e-09, "epoch": 0.994, "percentage": 99.4, "elapsed_time": "0:12:13", "remaining_time": "0:00:04"}
{"current_steps": 4980, "total_steps": 5000, "loss": 0.6112, "lr": 2.4368997673940297e-09, "epoch": 0.996, "percentage": 99.6, "elapsed_time": "0:12:14", "remaining_time": "0:00:02"}
{"current_steps": 4990, "total_steps": 5000, "loss": 0.9132, "lr": 6.092323651313292e-10, "epoch": 0.998, "percentage": 99.8, "elapsed_time": "0:12:16", "remaining_time": "0:00:01"}
{"current_steps": 5000, "total_steps": 5000, "loss": 0.4944, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:12:17", "remaining_time": "0:00:00"}
{"current_steps": 5000, "total_steps": 5000, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:12:17", "remaining_time": "0:00:00"}