large_crafting_sft_fail / trainer_log.jsonl
izzcw's picture
Training in progress, step 1548
6674123 verified
raw
history blame
35.7 kB
{"current_steps": 10, "total_steps": 1548, "loss": 1.4776, "lr": 6.451612903225807e-07, "epoch": 0.006457341189765114, "percentage": 0.65, "elapsed_time": "0:02:09", "remaining_time": "5:31:39"}
{"current_steps": 20, "total_steps": 1548, "loss": 1.0088, "lr": 1.2903225806451614e-06, "epoch": 0.012914682379530229, "percentage": 1.29, "elapsed_time": "0:04:15", "remaining_time": "5:25:00"}
{"current_steps": 30, "total_steps": 1548, "loss": 0.7032, "lr": 1.935483870967742e-06, "epoch": 0.019372023569295342, "percentage": 1.94, "elapsed_time": "0:06:20", "remaining_time": "5:20:32"}
{"current_steps": 40, "total_steps": 1548, "loss": 0.6113, "lr": 2.580645161290323e-06, "epoch": 0.025829364759060457, "percentage": 2.58, "elapsed_time": "0:08:26", "remaining_time": "5:18:20"}
{"current_steps": 50, "total_steps": 1548, "loss": 0.5429, "lr": 3.225806451612903e-06, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:10:32", "remaining_time": "5:15:55"}
{"current_steps": 50, "total_steps": 1548, "eval_loss": 0.4979822635650635, "epoch": 0.03228670594882557, "percentage": 3.23, "elapsed_time": "0:12:24", "remaining_time": "6:11:50"}
{"current_steps": 60, "total_steps": 1548, "loss": 0.5324, "lr": 3.870967741935484e-06, "epoch": 0.038744047138590684, "percentage": 3.88, "elapsed_time": "0:14:31", "remaining_time": "6:00:14"}
{"current_steps": 70, "total_steps": 1548, "loss": 0.5465, "lr": 4.516129032258065e-06, "epoch": 0.0452013883283558, "percentage": 4.52, "elapsed_time": "0:16:36", "remaining_time": "5:50:41"}
{"current_steps": 80, "total_steps": 1548, "loss": 0.5395, "lr": 5.161290322580646e-06, "epoch": 0.051658729518120915, "percentage": 5.17, "elapsed_time": "0:18:41", "remaining_time": "5:43:05"}
{"current_steps": 90, "total_steps": 1548, "loss": 0.5142, "lr": 5.806451612903226e-06, "epoch": 0.058116070707886026, "percentage": 5.81, "elapsed_time": "0:20:49", "remaining_time": "5:37:13"}
{"current_steps": 100, "total_steps": 1548, "loss": 0.5398, "lr": 6.451612903225806e-06, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:22:54", "remaining_time": "5:31:36"}
{"current_steps": 100, "total_steps": 1548, "eval_loss": 0.4740481972694397, "epoch": 0.06457341189765115, "percentage": 6.46, "elapsed_time": "0:24:45", "remaining_time": "5:58:36"}
{"current_steps": 110, "total_steps": 1548, "loss": 0.5428, "lr": 7.096774193548388e-06, "epoch": 0.07103075308741626, "percentage": 7.11, "elapsed_time": "0:26:52", "remaining_time": "5:51:13"}
{"current_steps": 120, "total_steps": 1548, "loss": 0.5282, "lr": 7.741935483870968e-06, "epoch": 0.07748809427718137, "percentage": 7.75, "elapsed_time": "0:28:57", "remaining_time": "5:44:31"}
{"current_steps": 130, "total_steps": 1548, "loss": 0.559, "lr": 8.387096774193549e-06, "epoch": 0.08394543546694648, "percentage": 8.4, "elapsed_time": "0:31:02", "remaining_time": "5:38:36"}
{"current_steps": 140, "total_steps": 1548, "loss": 0.5582, "lr": 9.03225806451613e-06, "epoch": 0.0904027766567116, "percentage": 9.04, "elapsed_time": "0:33:09", "remaining_time": "5:33:29"}
{"current_steps": 150, "total_steps": 1548, "loss": 0.5484, "lr": 9.67741935483871e-06, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:35:13", "remaining_time": "5:28:17"}
{"current_steps": 150, "total_steps": 1548, "eval_loss": 0.4832856059074402, "epoch": 0.09686011784647672, "percentage": 9.69, "elapsed_time": "0:37:05", "remaining_time": "5:45:40"}
{"current_steps": 160, "total_steps": 1548, "loss": 0.5607, "lr": 9.999682112882774e-06, "epoch": 0.10331745903624183, "percentage": 10.34, "elapsed_time": "0:39:11", "remaining_time": "5:39:57"}
{"current_steps": 170, "total_steps": 1548, "loss": 0.5586, "lr": 9.997139258465151e-06, "epoch": 0.10977480022600694, "percentage": 10.98, "elapsed_time": "0:41:18", "remaining_time": "5:34:52"}
{"current_steps": 180, "total_steps": 1548, "loss": 0.5564, "lr": 9.992054842933846e-06, "epoch": 0.11623214141577205, "percentage": 11.63, "elapsed_time": "0:43:24", "remaining_time": "5:29:52"}
{"current_steps": 190, "total_steps": 1548, "loss": 0.5253, "lr": 9.984431452238968e-06, "epoch": 0.12268948260553716, "percentage": 12.27, "elapsed_time": "0:45:30", "remaining_time": "5:25:13"}
{"current_steps": 200, "total_steps": 1548, "loss": 0.5265, "lr": 9.974272963661561e-06, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:47:36", "remaining_time": "5:20:50"}
{"current_steps": 200, "total_steps": 1548, "eval_loss": 0.47804030776023865, "epoch": 0.1291468237953023, "percentage": 12.92, "elapsed_time": "0:49:28", "remaining_time": "5:33:24"}
{"current_steps": 210, "total_steps": 1548, "loss": 0.5329, "lr": 9.961584543841625e-06, "epoch": 0.1356041649850674, "percentage": 13.57, "elapsed_time": "0:51:34", "remaining_time": "5:28:34"}
{"current_steps": 220, "total_steps": 1548, "loss": 0.5534, "lr": 9.946372646150322e-06, "epoch": 0.1420615061748325, "percentage": 14.21, "elapsed_time": "0:53:38", "remaining_time": "5:23:50"}
{"current_steps": 230, "total_steps": 1548, "loss": 0.5365, "lr": 9.928645007407791e-06, "epoch": 0.14851884736459764, "percentage": 14.86, "elapsed_time": "0:55:45", "remaining_time": "5:19:30"}
{"current_steps": 240, "total_steps": 1548, "loss": 0.5118, "lr": 9.908410643948162e-06, "epoch": 0.15497618855436274, "percentage": 15.5, "elapsed_time": "0:57:50", "remaining_time": "5:15:11"}
{"current_steps": 250, "total_steps": 1548, "loss": 0.5278, "lr": 9.885679847033832e-06, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "0:59:55", "remaining_time": "5:11:06"}
{"current_steps": 250, "total_steps": 1548, "eval_loss": 0.47931385040283203, "epoch": 0.16143352974412786, "percentage": 16.15, "elapsed_time": "1:01:47", "remaining_time": "5:20:47"}
{"current_steps": 260, "total_steps": 1548, "loss": 0.5422, "lr": 9.860464177621286e-06, "epoch": 0.16789087093389296, "percentage": 16.8, "elapsed_time": "1:03:53", "remaining_time": "5:16:31"}
{"current_steps": 270, "total_steps": 1548, "loss": 0.4994, "lr": 9.832776460481162e-06, "epoch": 0.1743482121236581, "percentage": 17.44, "elapsed_time": "1:05:59", "remaining_time": "5:12:20"}
{"current_steps": 280, "total_steps": 1548, "loss": 0.5331, "lr": 9.802630777675528e-06, "epoch": 0.1808055533134232, "percentage": 18.09, "elapsed_time": "1:08:04", "remaining_time": "5:08:16"}
{"current_steps": 290, "total_steps": 1548, "loss": 0.5277, "lr": 9.770042461395705e-06, "epoch": 0.1872628945031883, "percentage": 18.73, "elapsed_time": "1:10:09", "remaining_time": "5:04:21"}
{"current_steps": 300, "total_steps": 1548, "loss": 0.5259, "lr": 9.735028086164265e-06, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:12:17", "remaining_time": "5:00:43"}
{"current_steps": 300, "total_steps": 1548, "eval_loss": 0.45192769169807434, "epoch": 0.19372023569295344, "percentage": 19.38, "elapsed_time": "1:14:09", "remaining_time": "5:08:28"}
{"current_steps": 310, "total_steps": 1548, "loss": 0.5184, "lr": 9.697605460405162e-06, "epoch": 0.20017757688271853, "percentage": 20.03, "elapsed_time": "1:16:14", "remaining_time": "5:04:30"}
{"current_steps": 320, "total_steps": 1548, "loss": 0.5183, "lr": 9.657793617386337e-06, "epoch": 0.20663491807248366, "percentage": 20.67, "elapsed_time": "1:18:19", "remaining_time": "5:00:34"}
{"current_steps": 330, "total_steps": 1548, "loss": 0.5109, "lr": 9.615612805539305e-06, "epoch": 0.21309225926224876, "percentage": 21.32, "elapsed_time": "1:20:26", "remaining_time": "4:56:53"}
{"current_steps": 340, "total_steps": 1548, "loss": 0.5056, "lr": 9.571084478160763e-06, "epoch": 0.21954960045201388, "percentage": 21.96, "elapsed_time": "1:22:32", "remaining_time": "4:53:14"}
{"current_steps": 350, "total_steps": 1548, "loss": 0.5293, "lr": 9.524231282501362e-06, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:24:39", "remaining_time": "4:49:46"}
{"current_steps": 350, "total_steps": 1548, "eval_loss": 0.4497073292732239, "epoch": 0.226006941641779, "percentage": 22.61, "elapsed_time": "1:26:31", "remaining_time": "4:56:09"}
{"current_steps": 360, "total_steps": 1548, "loss": 0.4857, "lr": 9.475077048247243e-06, "epoch": 0.2324642828315441, "percentage": 23.26, "elapsed_time": "1:28:36", "remaining_time": "4:52:25"}
{"current_steps": 370, "total_steps": 1548, "loss": 0.5132, "lr": 9.423646775400186e-06, "epoch": 0.23892162402130923, "percentage": 23.9, "elapsed_time": "1:30:41", "remaining_time": "4:48:45"}
{"current_steps": 380, "total_steps": 1548, "loss": 0.494, "lr": 9.369966621562525e-06, "epoch": 0.24537896521107433, "percentage": 24.55, "elapsed_time": "1:32:47", "remaining_time": "4:45:12"}
{"current_steps": 390, "total_steps": 1548, "loss": 0.5045, "lr": 9.314063888633312e-06, "epoch": 0.2518363064008394, "percentage": 25.19, "elapsed_time": "1:34:52", "remaining_time": "4:41:43"}
{"current_steps": 400, "total_steps": 1548, "loss": 0.5098, "lr": 9.255967008922475e-06, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:36:59", "remaining_time": "4:38:20"}
{"current_steps": 400, "total_steps": 1548, "eval_loss": 0.43027767539024353, "epoch": 0.2582936475906046, "percentage": 25.84, "elapsed_time": "1:38:51", "remaining_time": "4:43:42"}
{"current_steps": 410, "total_steps": 1548, "loss": 0.5018, "lr": 9.19570553069006e-06, "epoch": 0.2647509887803697, "percentage": 26.49, "elapsed_time": "1:40:58", "remaining_time": "4:40:14"}
{"current_steps": 420, "total_steps": 1548, "loss": 0.4794, "lr": 9.133310103117891e-06, "epoch": 0.2712083299701348, "percentage": 27.13, "elapsed_time": "1:43:03", "remaining_time": "4:36:47"}
{"current_steps": 430, "total_steps": 1548, "loss": 0.477, "lr": 9.068812460721296e-06, "epoch": 0.27766567115989993, "percentage": 27.78, "elapsed_time": "1:45:09", "remaining_time": "4:33:25"}
{"current_steps": 440, "total_steps": 1548, "loss": 0.5121, "lr": 9.002245407208831e-06, "epoch": 0.284123012349665, "percentage": 28.42, "elapsed_time": "1:47:14", "remaining_time": "4:30:03"}
{"current_steps": 450, "total_steps": 1548, "loss": 0.482, "lr": 8.9336427987982e-06, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:49:21", "remaining_time": "4:26:49"}
{"current_steps": 450, "total_steps": 1548, "eval_loss": 0.4249188303947449, "epoch": 0.2905803535394301, "percentage": 29.07, "elapsed_time": "1:51:13", "remaining_time": "4:31:22"}
{"current_steps": 460, "total_steps": 1548, "loss": 0.4717, "lr": 8.863039526996891e-06, "epoch": 0.2970376947291953, "percentage": 29.72, "elapsed_time": "1:53:19", "remaining_time": "4:28:01"}
{"current_steps": 470, "total_steps": 1548, "loss": 0.4905, "lr": 8.790471500856229e-06, "epoch": 0.3034950359189604, "percentage": 30.36, "elapsed_time": "1:55:24", "remaining_time": "4:24:41"}
{"current_steps": 480, "total_steps": 1548, "loss": 0.5077, "lr": 8.715975628707917e-06, "epoch": 0.3099523771087255, "percentage": 31.01, "elapsed_time": "1:57:29", "remaining_time": "4:21:25"}
{"current_steps": 490, "total_steps": 1548, "loss": 0.485, "lr": 8.63958979939235e-06, "epoch": 0.31640971829849057, "percentage": 31.65, "elapsed_time": "1:59:34", "remaining_time": "4:18:11"}
{"current_steps": 500, "total_steps": 1548, "loss": 0.4683, "lr": 8.56135286298822e-06, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:01:40", "remaining_time": "4:15:02"}
{"current_steps": 500, "total_steps": 1548, "eval_loss": 0.4224134683609009, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:03:32", "remaining_time": "4:18:56"}
{"current_steps": 510, "total_steps": 1548, "loss": 0.4983, "lr": 8.48130461105324e-06, "epoch": 0.3293244006780208, "percentage": 32.95, "elapsed_time": "2:06:59", "remaining_time": "4:18:26"}
{"current_steps": 520, "total_steps": 1548, "loss": 0.4568, "lr": 8.399485756386038e-06, "epoch": 0.3357817418677859, "percentage": 33.59, "elapsed_time": "2:09:04", "remaining_time": "4:15:10"}
{"current_steps": 530, "total_steps": 1548, "loss": 0.47, "lr": 8.315937912319493e-06, "epoch": 0.3422390830575511, "percentage": 34.24, "elapsed_time": "2:11:11", "remaining_time": "4:11:59"}
{"current_steps": 540, "total_steps": 1548, "loss": 0.4703, "lr": 8.23070357155605e-06, "epoch": 0.3486964242473162, "percentage": 34.88, "elapsed_time": "2:13:16", "remaining_time": "4:08:47"}
{"current_steps": 550, "total_steps": 1548, "loss": 0.4572, "lr": 8.143826084555809e-06, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:15:22", "remaining_time": "4:05:38"}
{"current_steps": 550, "total_steps": 1548, "eval_loss": 0.4135887324810028, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:17:14", "remaining_time": "4:09:01"}
{"current_steps": 560, "total_steps": 1548, "loss": 0.4639, "lr": 8.055349637488336e-06, "epoch": 0.3616111066268464, "percentage": 36.18, "elapsed_time": "2:19:20", "remaining_time": "4:05:50"}
{"current_steps": 570, "total_steps": 1548, "loss": 0.4606, "lr": 7.965319229759435e-06, "epoch": 0.3680684478166115, "percentage": 36.82, "elapsed_time": "2:21:26", "remaining_time": "4:02:41"}
{"current_steps": 580, "total_steps": 1548, "loss": 0.4764, "lr": 7.873780651124302e-06, "epoch": 0.3745257890063766, "percentage": 37.47, "elapsed_time": "2:23:33", "remaining_time": "3:59:35"}
{"current_steps": 590, "total_steps": 1548, "loss": 0.4473, "lr": 7.78078045839871e-06, "epoch": 0.3809831301961417, "percentage": 38.11, "elapsed_time": "2:25:38", "remaining_time": "3:56:28"}
{"current_steps": 600, "total_steps": 1548, "loss": 0.456, "lr": 7.686365951780071e-06, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:27:44", "remaining_time": "3:53:26"}
{"current_steps": 600, "total_steps": 1548, "eval_loss": 0.4034173786640167, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:29:36", "remaining_time": "3:56:22"}
{"current_steps": 610, "total_steps": 1548, "loss": 0.4416, "lr": 7.590585150790388e-06, "epoch": 0.39389781257567197, "percentage": 39.41, "elapsed_time": "2:31:42", "remaining_time": "3:53:17"}
{"current_steps": 620, "total_steps": 1548, "loss": 0.4652, "lr": 7.493486769853383e-06, "epoch": 0.40035515376543707, "percentage": 40.05, "elapsed_time": "2:33:47", "remaining_time": "3:50:11"}
{"current_steps": 630, "total_steps": 1548, "loss": 0.4558, "lr": 7.39512019351818e-06, "epoch": 0.4068124949552022, "percentage": 40.7, "elapsed_time": "2:35:52", "remaining_time": "3:47:07"}
{"current_steps": 640, "total_steps": 1548, "loss": 0.4351, "lr": 7.295535451342166e-06, "epoch": 0.4132698361449673, "percentage": 41.34, "elapsed_time": "2:37:57", "remaining_time": "3:44:06"}
{"current_steps": 650, "total_steps": 1548, "loss": 0.4606, "lr": 7.194783192445795e-06, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:40:03", "remaining_time": "3:41:07"}
{"current_steps": 650, "total_steps": 1548, "eval_loss": 0.39828598499298096, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:41:55", "remaining_time": "3:43:42"}
{"current_steps": 660, "total_steps": 1548, "loss": 0.4533, "lr": 7.092914659752286e-06, "epoch": 0.4261845185244975, "percentage": 42.64, "elapsed_time": "2:44:02", "remaining_time": "3:40:43"}
{"current_steps": 670, "total_steps": 1548, "loss": 0.4521, "lr": 6.989981663925301e-06, "epoch": 0.43264185971426267, "percentage": 43.28, "elapsed_time": "2:46:08", "remaining_time": "3:37:43"}
{"current_steps": 680, "total_steps": 1548, "loss": 0.4658, "lr": 6.886036557017881e-06, "epoch": 0.43909920090402776, "percentage": 43.93, "elapsed_time": "2:48:13", "remaining_time": "3:34:43"}
{"current_steps": 690, "total_steps": 1548, "loss": 0.4476, "lr": 6.781132205846019e-06, "epoch": 0.44555654209379286, "percentage": 44.57, "elapsed_time": "2:50:19", "remaining_time": "3:31:47"}
{"current_steps": 700, "total_steps": 1548, "loss": 0.4285, "lr": 6.675321965100431e-06, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:52:25", "remaining_time": "3:28:53"}
{"current_steps": 700, "total_steps": 1548, "eval_loss": 0.38738012313842773, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:54:17", "remaining_time": "3:31:08"}
{"current_steps": 710, "total_steps": 1548, "loss": 0.4381, "lr": 6.568659650210184e-06, "epoch": 0.4584712244733231, "percentage": 45.87, "elapsed_time": "2:56:23", "remaining_time": "3:28:11"}
{"current_steps": 720, "total_steps": 1548, "loss": 0.4264, "lr": 6.461199509972001e-06, "epoch": 0.4649285656630882, "percentage": 46.51, "elapsed_time": "2:58:30", "remaining_time": "3:25:16"}
{"current_steps": 730, "total_steps": 1548, "loss": 0.4143, "lr": 6.35299619895914e-06, "epoch": 0.47138590685285336, "percentage": 47.16, "elapsed_time": "3:00:35", "remaining_time": "3:22:21"}
{"current_steps": 740, "total_steps": 1548, "loss": 0.4364, "lr": 6.244104749723916e-06, "epoch": 0.47784324804261846, "percentage": 47.8, "elapsed_time": "3:02:39", "remaining_time": "3:19:26"}
{"current_steps": 750, "total_steps": 1548, "loss": 0.4499, "lr": 6.134580544807951e-06, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:04:45", "remaining_time": "3:16:34"}
{"current_steps": 750, "total_steps": 1548, "eval_loss": 0.38058942556381226, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:06:37", "remaining_time": "3:18:33"}
{"current_steps": 760, "total_steps": 1548, "loss": 0.4374, "lr": 6.024479288574448e-06, "epoch": 0.49075793042214866, "percentage": 49.1, "elapsed_time": "3:08:42", "remaining_time": "3:15:39"}
{"current_steps": 770, "total_steps": 1548, "loss": 0.4201, "lr": 5.9138569788767645e-06, "epoch": 0.4972152716119138, "percentage": 49.74, "elapsed_time": "3:10:47", "remaining_time": "3:12:46"}
{"current_steps": 780, "total_steps": 1548, "loss": 0.4201, "lr": 5.802769878577729e-06, "epoch": 0.5036726128016789, "percentage": 50.39, "elapsed_time": "3:12:55", "remaining_time": "3:09:57"}
{"current_steps": 790, "total_steps": 1548, "loss": 0.4258, "lr": 5.691274486934166e-06, "epoch": 0.510129953991444, "percentage": 51.03, "elapsed_time": "3:15:00", "remaining_time": "3:07:06"}
{"current_steps": 800, "total_steps": 1548, "loss": 0.4198, "lr": 5.579427510861194e-06, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:17:06", "remaining_time": "3:04:17"}
{"current_steps": 800, "total_steps": 1548, "eval_loss": 0.36852195858955383, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:18:57", "remaining_time": "3:06:01"}
{"current_steps": 810, "total_steps": 1548, "loss": 0.4268, "lr": 5.4672858360909e-06, "epoch": 0.5230446363709742, "percentage": 52.33, "elapsed_time": "3:21:02", "remaining_time": "3:03:10"}
{"current_steps": 820, "total_steps": 1548, "loss": 0.4219, "lr": 5.35490649824008e-06, "epoch": 0.5295019775607394, "percentage": 52.97, "elapsed_time": "3:23:09", "remaining_time": "3:00:22"}
{"current_steps": 830, "total_steps": 1548, "loss": 0.4447, "lr": 5.242346653801739e-06, "epoch": 0.5359593187505045, "percentage": 53.62, "elapsed_time": "3:25:15", "remaining_time": "2:57:33"}
{"current_steps": 840, "total_steps": 1548, "loss": 0.4225, "lr": 5.129663551075109e-06, "epoch": 0.5424166599402696, "percentage": 54.26, "elapsed_time": "3:27:20", "remaining_time": "2:54:45"}
{"current_steps": 850, "total_steps": 1548, "loss": 0.4208, "lr": 5.016914501048988e-06, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:29:28", "remaining_time": "2:52:00"}
{"current_steps": 850, "total_steps": 1548, "eval_loss": 0.366115003824234, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:31:20", "remaining_time": "2:53:32"}
{"current_steps": 860, "total_steps": 1548, "loss": 0.415, "lr": 4.904156848253184e-06, "epoch": 0.5553313423197999, "percentage": 55.56, "elapsed_time": "3:33:27", "remaining_time": "2:50:46"}
{"current_steps": 870, "total_steps": 1548, "loss": 0.4238, "lr": 4.791447941592896e-06, "epoch": 0.5617886835095649, "percentage": 56.2, "elapsed_time": "3:35:34", "remaining_time": "2:48:00"}
{"current_steps": 880, "total_steps": 1548, "loss": 0.4075, "lr": 4.678845105180886e-06, "epoch": 0.56824602469933, "percentage": 56.85, "elapsed_time": "3:37:41", "remaining_time": "2:45:14"}
{"current_steps": 890, "total_steps": 1548, "loss": 0.4042, "lr": 4.566405609182247e-06, "epoch": 0.5747033658890952, "percentage": 57.49, "elapsed_time": "3:39:46", "remaining_time": "2:42:29"}
{"current_steps": 900, "total_steps": 1548, "loss": 0.4379, "lr": 4.454186640686607e-06, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:41:52", "remaining_time": "2:39:44"}
{"current_steps": 900, "total_steps": 1548, "eval_loss": 0.3636697232723236, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:43:44", "remaining_time": "2:41:05"}
{"current_steps": 910, "total_steps": 1548, "loss": 0.4009, "lr": 4.3422452746226e-06, "epoch": 0.5876180482686254, "percentage": 58.79, "elapsed_time": "3:45:49", "remaining_time": "2:38:19"}
{"current_steps": 920, "total_steps": 1548, "loss": 0.4368, "lr": 4.230638444729368e-06, "epoch": 0.5940753894583906, "percentage": 59.43, "elapsed_time": "3:47:53", "remaining_time": "2:35:33"}
{"current_steps": 930, "total_steps": 1548, "loss": 0.4047, "lr": 4.1194229145998795e-06, "epoch": 0.6005327306481556, "percentage": 60.08, "elapsed_time": "3:49:58", "remaining_time": "2:32:49"}
{"current_steps": 940, "total_steps": 1548, "loss": 0.3952, "lr": 4.008655248810787e-06, "epoch": 0.6069900718379208, "percentage": 60.72, "elapsed_time": "3:52:05", "remaining_time": "2:30:07"}
{"current_steps": 950, "total_steps": 1548, "loss": 0.4075, "lr": 3.898391784153494e-06, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:54:10", "remaining_time": "2:27:24"}
{"current_steps": 950, "total_steps": 1548, "eval_loss": 0.3558257520198822, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:56:02", "remaining_time": "2:28:35"}
{"current_steps": 960, "total_steps": 1548, "loss": 0.405, "lr": 3.788688600981085e-06, "epoch": 0.619904754217451, "percentage": 62.02, "elapsed_time": "3:58:08", "remaining_time": "2:25:51"}
{"current_steps": 970, "total_steps": 1548, "loss": 0.417, "lr": 3.679601494685679e-06, "epoch": 0.6263620954072161, "percentage": 62.66, "elapsed_time": "4:00:15", "remaining_time": "2:23:09"}
{"current_steps": 980, "total_steps": 1548, "loss": 0.4077, "lr": 3.571185947320712e-06, "epoch": 0.6328194365969811, "percentage": 63.31, "elapsed_time": "4:02:22", "remaining_time": "2:20:28"}
{"current_steps": 990, "total_steps": 1548, "loss": 0.3983, "lr": 3.4634970993825854e-06, "epoch": 0.6392767777867463, "percentage": 63.95, "elapsed_time": "4:04:29", "remaining_time": "2:17:48"}
{"current_steps": 1000, "total_steps": 1548, "loss": 0.4121, "lr": 3.356589721766034e-06, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:06:34", "remaining_time": "2:15:07"}
{"current_steps": 1000, "total_steps": 1548, "eval_loss": 0.35134828090667725, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:08:26", "remaining_time": "2:16:08"}
{"current_steps": 1010, "total_steps": 1548, "loss": 0.3869, "lr": 3.250518187907469e-06, "epoch": 0.6521914601662765, "percentage": 65.25, "elapsed_time": "4:11:44", "remaining_time": "2:14:05"}
{"current_steps": 1020, "total_steps": 1548, "loss": 0.3753, "lr": 3.1453364461304795e-06, "epoch": 0.6586488013560416, "percentage": 65.89, "elapsed_time": "4:13:50", "remaining_time": "2:11:23"}
{"current_steps": 1030, "total_steps": 1548, "loss": 0.3915, "lr": 3.0410979922075344e-06, "epoch": 0.6651061425458068, "percentage": 66.54, "elapsed_time": "4:15:55", "remaining_time": "2:08:42"}
{"current_steps": 1040, "total_steps": 1548, "loss": 0.4089, "lr": 2.9378558421518645e-06, "epoch": 0.6715634837355718, "percentage": 67.18, "elapsed_time": "4:18:01", "remaining_time": "2:06:02"}
{"current_steps": 1050, "total_steps": 1548, "loss": 0.4112, "lr": 2.835662505253344e-06, "epoch": 0.678020824925337, "percentage": 67.83, "elapsed_time": "4:20:05", "remaining_time": "2:03:21"}
{"current_steps": 1050, "total_steps": 1548, "eval_loss": 0.34539544582366943, "epoch": 0.678020824925337, "percentage": 67.83, "elapsed_time": "4:21:57", "remaining_time": "2:04:14"}
{"current_steps": 1060, "total_steps": 1548, "loss": 0.3993, "lr": 2.7345699573721014e-06, "epoch": 0.6844781661151021, "percentage": 68.48, "elapsed_time": "4:24:04", "remaining_time": "2:01:34"}
{"current_steps": 1070, "total_steps": 1548, "loss": 0.388, "lr": 2.634629614503428e-06, "epoch": 0.6909355073048672, "percentage": 69.12, "elapsed_time": "4:26:10", "remaining_time": "1:58:54"}
{"current_steps": 1080, "total_steps": 1548, "loss": 0.3992, "lr": 2.5358923066274354e-06, "epoch": 0.6973928484946323, "percentage": 69.77, "elapsed_time": "4:28:15", "remaining_time": "1:56:14"}
{"current_steps": 1090, "total_steps": 1548, "loss": 0.3801, "lr": 2.4384082518567643e-06, "epoch": 0.7038501896843975, "percentage": 70.41, "elapsed_time": "4:30:21", "remaining_time": "1:53:36"}
{"current_steps": 1100, "total_steps": 1548, "loss": 0.4041, "lr": 2.3422270308954936e-06, "epoch": 0.7103075308741625, "percentage": 71.06, "elapsed_time": "4:32:26", "remaining_time": "1:50:57"}
{"current_steps": 1100, "total_steps": 1548, "eval_loss": 0.3457443118095398, "epoch": 0.7103075308741625, "percentage": 71.06, "elapsed_time": "4:34:18", "remaining_time": "1:51:43"}
{"current_steps": 1110, "total_steps": 1548, "loss": 0.3909, "lr": 2.2473975618222304e-06, "epoch": 0.7167648720639277, "percentage": 71.71, "elapsed_time": "4:36:24", "remaining_time": "1:49:04"}
{"current_steps": 1120, "total_steps": 1548, "loss": 0.3952, "lr": 2.1539680752102217e-06, "epoch": 0.7232222132536928, "percentage": 72.35, "elapsed_time": "4:38:31", "remaining_time": "1:46:26"}
{"current_steps": 1130, "total_steps": 1548, "loss": 0.3736, "lr": 2.0619860895971266e-06, "epoch": 0.7296795544434579, "percentage": 73.0, "elapsed_time": "4:40:36", "remaining_time": "1:43:47"}
{"current_steps": 1140, "total_steps": 1548, "loss": 0.4042, "lr": 1.9714983873169376e-06, "epoch": 0.736136895633223, "percentage": 73.64, "elapsed_time": "4:42:42", "remaining_time": "1:41:10"}
{"current_steps": 1150, "total_steps": 1548, "loss": 0.3852, "lr": 1.8825509907063328e-06, "epoch": 0.7425942368229881, "percentage": 74.29, "elapsed_time": "4:44:48", "remaining_time": "1:38:34"}
{"current_steps": 1150, "total_steps": 1548, "eval_loss": 0.33838221430778503, "epoch": 0.7425942368229881, "percentage": 74.29, "elapsed_time": "4:46:40", "remaining_time": "1:39:12"}
{"current_steps": 1160, "total_steps": 1548, "loss": 0.3756, "lr": 1.7951891386975684e-06, "epoch": 0.7490515780127532, "percentage": 74.94, "elapsed_time": "4:48:45", "remaining_time": "1:36:35"}
{"current_steps": 1170, "total_steps": 1548, "loss": 0.3561, "lr": 1.7094572638098122e-06, "epoch": 0.7555089192025184, "percentage": 75.58, "elapsed_time": "4:50:52", "remaining_time": "1:33:58"}
{"current_steps": 1180, "total_steps": 1548, "loss": 0.3755, "lr": 1.6253989695506207e-06, "epoch": 0.7619662603922834, "percentage": 76.23, "elapsed_time": "4:52:58", "remaining_time": "1:31:22"}
{"current_steps": 1190, "total_steps": 1548, "loss": 0.3709, "lr": 1.5430570082390545e-06, "epoch": 0.7684236015820486, "percentage": 76.87, "elapsed_time": "4:55:05", "remaining_time": "1:28:46"}
{"current_steps": 1200, "total_steps": 1548, "loss": 0.3656, "lr": 1.462473259261713e-06, "epoch": 0.7748809427718137, "percentage": 77.52, "elapsed_time": "4:57:12", "remaining_time": "1:26:11"}
{"current_steps": 1200, "total_steps": 1548, "eval_loss": 0.33403000235557556, "epoch": 0.7748809427718137, "percentage": 77.52, "elapsed_time": "4:59:04", "remaining_time": "1:26:43"}
{"current_steps": 1210, "total_steps": 1548, "loss": 0.3842, "lr": 1.3836887077727424e-06, "epoch": 0.7813382839615788, "percentage": 78.17, "elapsed_time": "5:01:10", "remaining_time": "1:24:07"}
{"current_steps": 1220, "total_steps": 1548, "loss": 0.3773, "lr": 1.3067434238486527e-06, "epoch": 0.7877956251513439, "percentage": 78.81, "elapsed_time": "5:03:16", "remaining_time": "1:21:32"}
{"current_steps": 1230, "total_steps": 1548, "loss": 0.3769, "lr": 1.2316765421085513e-06, "epoch": 0.7942529663411091, "percentage": 79.46, "elapsed_time": "5:05:24", "remaining_time": "1:18:57"}
{"current_steps": 1240, "total_steps": 1548, "loss": 0.3586, "lr": 1.1585262418101468e-06, "epoch": 0.8007103075308741, "percentage": 80.1, "elapsed_time": "5:07:30", "remaining_time": "1:16:22"}
{"current_steps": 1250, "total_steps": 1548, "loss": 0.384, "lr": 1.0873297274316568e-06, "epoch": 0.8071676487206393, "percentage": 80.75, "elapsed_time": "5:09:36", "remaining_time": "1:13:48"}
{"current_steps": 1250, "total_steps": 1548, "eval_loss": 0.3302658796310425, "epoch": 0.8071676487206393, "percentage": 80.75, "elapsed_time": "5:11:28", "remaining_time": "1:14:15"}
{"current_steps": 1260, "total_steps": 1548, "loss": 0.3816, "lr": 1.0181232097494904e-06, "epoch": 0.8136249899104044, "percentage": 81.4, "elapsed_time": "5:13:36", "remaining_time": "1:11:40"}
{"current_steps": 1270, "total_steps": 1548, "loss": 0.3651, "lr": 9.509418874213316e-07, "epoch": 0.8200823311001695, "percentage": 82.04, "elapsed_time": "5:15:42", "remaining_time": "1:09:06"}
{"current_steps": 1280, "total_steps": 1548, "loss": 0.3573, "lr": 8.858199290839859e-07, "epoch": 0.8265396722899346, "percentage": 82.69, "elapsed_time": "5:17:49", "remaining_time": "1:06:32"}
{"current_steps": 1290, "total_steps": 1548, "loss": 0.383, "lr": 8.22790455975106e-07, "epoch": 0.8329970134796998, "percentage": 83.33, "elapsed_time": "5:19:56", "remaining_time": "1:03:59"}
{"current_steps": 1300, "total_steps": 1548, "loss": 0.3605, "lr": 7.61885525087619e-07, "epoch": 0.8394543546694648, "percentage": 83.98, "elapsed_time": "5:22:02", "remaining_time": "1:01:26"}
{"current_steps": 1300, "total_steps": 1548, "eval_loss": 0.327566921710968, "epoch": 0.8394543546694648, "percentage": 83.98, "elapsed_time": "5:23:54", "remaining_time": "1:01:47"}
{"current_steps": 1310, "total_steps": 1548, "loss": 0.3508, "lr": 7.031361128654402e-07, "epoch": 0.84591169585923, "percentage": 84.63, "elapsed_time": "5:25:59", "remaining_time": "0:59:13"}
{"current_steps": 1320, "total_steps": 1548, "loss": 0.3806, "lr": 6.465720994487523e-07, "epoch": 0.852369037048995, "percentage": 85.27, "elapsed_time": "5:28:07", "remaining_time": "0:56:40"}
{"current_steps": 1330, "total_steps": 1548, "loss": 0.3838, "lr": 5.922222534768707e-07, "epoch": 0.8588263782387602, "percentage": 85.92, "elapsed_time": "5:30:11", "remaining_time": "0:54:07"}
{"current_steps": 1340, "total_steps": 1548, "loss": 0.3627, "lr": 5.401142174564195e-07, "epoch": 0.8652837194285253, "percentage": 86.56, "elapsed_time": "5:32:16", "remaining_time": "0:51:34"}
{"current_steps": 1350, "total_steps": 1548, "loss": 0.3593, "lr": 4.902744937022658e-07, "epoch": 0.8717410606182904, "percentage": 87.21, "elapsed_time": "5:34:21", "remaining_time": "0:49:02"}
{"current_steps": 1350, "total_steps": 1548, "eval_loss": 0.3246610164642334, "epoch": 0.8717410606182904, "percentage": 87.21, "elapsed_time": "5:36:13", "remaining_time": "0:49:18"}
{"current_steps": 1360, "total_steps": 1548, "loss": 0.3804, "lr": 4.4272843085835515e-07, "epoch": 0.8781984018080555, "percentage": 87.86, "elapsed_time": "5:38:18", "remaining_time": "0:46:46"}
{"current_steps": 1370, "total_steps": 1548, "loss": 0.3764, "lr": 3.9750021100531e-07, "epoch": 0.8846557429978207, "percentage": 88.5, "elapsed_time": "5:40:25", "remaining_time": "0:44:13"}
{"current_steps": 1380, "total_steps": 1548, "loss": 0.3743, "lr": 3.546128373613472e-07, "epoch": 0.8911130841875857, "percentage": 89.15, "elapsed_time": "5:42:31", "remaining_time": "0:41:41"}
{"current_steps": 1390, "total_steps": 1548, "loss": 0.3566, "lr": 3.1408812258276575e-07, "epoch": 0.8975704253773509, "percentage": 89.79, "elapsed_time": "5:44:39", "remaining_time": "0:39:10"}
{"current_steps": 1400, "total_steps": 1548, "loss": 0.3624, "lr": 2.7594667766995933e-07, "epoch": 0.904027766567116, "percentage": 90.44, "elapsed_time": "5:46:45", "remaining_time": "0:36:39"}
{"current_steps": 1400, "total_steps": 1548, "eval_loss": 0.323292076587677, "epoch": 0.904027766567116, "percentage": 90.44, "elapsed_time": "5:48:37", "remaining_time": "0:36:51"}
{"current_steps": 1410, "total_steps": 1548, "loss": 0.3792, "lr": 2.402079014845943e-07, "epoch": 0.9104851077568811, "percentage": 91.09, "elapsed_time": "5:50:43", "remaining_time": "0:34:19"}
{"current_steps": 1420, "total_steps": 1548, "loss": 0.3812, "lr": 2.068899708832911e-07, "epoch": 0.9169424489466462, "percentage": 91.73, "elapsed_time": "5:52:49", "remaining_time": "0:31:48"}
{"current_steps": 1430, "total_steps": 1548, "loss": 0.3579, "lr": 1.7600983147280982e-07, "epoch": 0.9233997901364114, "percentage": 92.38, "elapsed_time": "5:54:54", "remaining_time": "0:29:17"}
{"current_steps": 1440, "total_steps": 1548, "loss": 0.3504, "lr": 1.475831889914642e-07, "epoch": 0.9298571313261764, "percentage": 93.02, "elapsed_time": "5:57:00", "remaining_time": "0:26:46"}
{"current_steps": 1450, "total_steps": 1548, "loss": 0.3734, "lr": 1.2162450132113202e-07, "epoch": 0.9363144725159416, "percentage": 93.67, "elapsed_time": "5:59:05", "remaining_time": "0:24:16"}
{"current_steps": 1450, "total_steps": 1548, "eval_loss": 0.3228907585144043, "epoch": 0.9363144725159416, "percentage": 93.67, "elapsed_time": "6:00:57", "remaining_time": "0:24:23"}
{"current_steps": 1460, "total_steps": 1548, "loss": 0.3687, "lr": 9.814697113392835e-08, "epoch": 0.9427718137057067, "percentage": 94.32, "elapsed_time": "6:03:00", "remaining_time": "0:21:52"}
{"current_steps": 1470, "total_steps": 1548, "loss": 0.3485, "lr": 7.716253917728622e-08, "epoch": 0.9492291548954718, "percentage": 94.96, "elapsed_time": "6:05:04", "remaining_time": "0:19:22"}
{"current_steps": 1480, "total_steps": 1548, "loss": 0.3713, "lr": 5.8681878200850805e-08, "epoch": 0.9556864960852369, "percentage": 95.61, "elapsed_time": "6:07:11", "remaining_time": "0:16:52"}
{"current_steps": 1490, "total_steps": 1548, "loss": 0.3499, "lr": 4.27143875282876e-08, "epoch": 0.962143837275002, "percentage": 96.25, "elapsed_time": "6:09:17", "remaining_time": "0:14:22"}
{"current_steps": 1500, "total_steps": 1548, "loss": 0.3609, "lr": 2.9268188276757035e-08, "epoch": 0.9686011784647671, "percentage": 96.9, "elapsed_time": "6:11:22", "remaining_time": "0:11:53"}
{"current_steps": 1500, "total_steps": 1548, "eval_loss": 0.3223486840724945, "epoch": 0.9686011784647671, "percentage": 96.9, "elapsed_time": "6:13:14", "remaining_time": "0:11:56"}
{"current_steps": 1510, "total_steps": 1548, "loss": 0.3609, "lr": 1.8350119226483442e-08, "epoch": 0.9750585196545323, "percentage": 97.55, "elapsed_time": "6:16:31", "remaining_time": "0:09:28"}
{"current_steps": 1520, "total_steps": 1548, "loss": 0.4155, "lr": 9.965733342532925e-09, "epoch": 0.9815158608442973, "percentage": 98.19, "elapsed_time": "6:18:38", "remaining_time": "0:06:58"}
{"current_steps": 1530, "total_steps": 1548, "loss": 0.3591, "lr": 4.119294950558072e-09, "epoch": 0.9879732020340625, "percentage": 98.84, "elapsed_time": "6:20:45", "remaining_time": "0:04:28"}
{"current_steps": 1540, "total_steps": 1548, "loss": 0.3655, "lr": 8.137775679456505e-10, "epoch": 0.9944305432238276, "percentage": 99.48, "elapsed_time": "6:22:49", "remaining_time": "0:01:59"}
{"current_steps": 1548, "total_steps": 1548, "epoch": 0.9995964161756397, "percentage": 100.0, "elapsed_time": "6:25:29", "remaining_time": "0:00:00"}