asianpaints / trainer_log.jsonl
sizhkhy's picture
Upload folder using huggingface_hub
aa3e8c8 verified
raw
history blame
124 kB
{"current_steps": 1, "total_steps": 540, "loss": 0.0591, "lr": 1.8518518518518519e-06, "epoch": 0.009195402298850575, "percentage": 0.19, "elapsed_time": "0:00:25", "remaining_time": "3:46:23"}
{"current_steps": 2, "total_steps": 540, "loss": 0.0572, "lr": 3.7037037037037037e-06, "epoch": 0.01839080459770115, "percentage": 0.37, "elapsed_time": "0:00:42", "remaining_time": "3:09:25"}
{"current_steps": 3, "total_steps": 540, "loss": 0.0586, "lr": 5.555555555555556e-06, "epoch": 0.027586206896551724, "percentage": 0.56, "elapsed_time": "0:00:56", "remaining_time": "2:47:04"}
{"current_steps": 4, "total_steps": 540, "loss": 0.0521, "lr": 7.4074074074074075e-06, "epoch": 0.0367816091954023, "percentage": 0.74, "elapsed_time": "0:01:13", "remaining_time": "2:43:16"}
{"current_steps": 5, "total_steps": 540, "loss": 0.0567, "lr": 9.259259259259259e-06, "epoch": 0.04597701149425287, "percentage": 0.93, "elapsed_time": "0:01:27", "remaining_time": "2:36:33"}
{"current_steps": 5, "total_steps": 540, "eval_loss": 0.0583593025803566, "epoch": 0.04597701149425287, "percentage": 0.93, "elapsed_time": "0:01:38", "remaining_time": "2:54:52"}
{"current_steps": 6, "total_steps": 540, "loss": 0.0485, "lr": 1.1111111111111112e-05, "epoch": 0.05517241379310345, "percentage": 1.11, "elapsed_time": "0:01:53", "remaining_time": "2:48:32"}
{"current_steps": 7, "total_steps": 540, "loss": 0.0439, "lr": 1.2962962962962962e-05, "epoch": 0.06436781609195402, "percentage": 1.3, "elapsed_time": "0:02:08", "remaining_time": "2:42:36"}
{"current_steps": 8, "total_steps": 540, "loss": 0.0402, "lr": 1.4814814814814815e-05, "epoch": 0.0735632183908046, "percentage": 1.48, "elapsed_time": "0:02:21", "remaining_time": "2:37:11"}
{"current_steps": 9, "total_steps": 540, "loss": 0.0374, "lr": 1.6666666666666667e-05, "epoch": 0.08275862068965517, "percentage": 1.67, "elapsed_time": "0:02:35", "remaining_time": "2:33:21"}
{"current_steps": 10, "total_steps": 540, "loss": 0.0378, "lr": 1.8518518518518518e-05, "epoch": 0.09195402298850575, "percentage": 1.85, "elapsed_time": "0:02:48", "remaining_time": "2:29:14"}
{"current_steps": 10, "total_steps": 540, "eval_loss": 0.0383976586163044, "epoch": 0.09195402298850575, "percentage": 1.85, "elapsed_time": "0:02:56", "remaining_time": "2:35:56"}
{"current_steps": 11, "total_steps": 540, "loss": 0.0335, "lr": 2.037037037037037e-05, "epoch": 0.10114942528735632, "percentage": 2.04, "elapsed_time": "0:03:10", "remaining_time": "2:32:43"}
{"current_steps": 12, "total_steps": 540, "loss": 0.0314, "lr": 2.2222222222222223e-05, "epoch": 0.1103448275862069, "percentage": 2.22, "elapsed_time": "0:03:24", "remaining_time": "2:29:36"}
{"current_steps": 13, "total_steps": 540, "loss": 0.0347, "lr": 2.4074074074074074e-05, "epoch": 0.11954022988505747, "percentage": 2.41, "elapsed_time": "0:03:36", "remaining_time": "2:26:31"}
{"current_steps": 14, "total_steps": 540, "loss": 0.03, "lr": 2.5925925925925925e-05, "epoch": 0.12873563218390804, "percentage": 2.59, "elapsed_time": "0:03:52", "remaining_time": "2:25:23"}
{"current_steps": 15, "total_steps": 540, "loss": 0.0301, "lr": 2.777777777777778e-05, "epoch": 0.13793103448275862, "percentage": 2.78, "elapsed_time": "0:04:04", "remaining_time": "2:22:39"}
{"current_steps": 15, "total_steps": 540, "eval_loss": 0.0318371020257473, "epoch": 0.13793103448275862, "percentage": 2.78, "elapsed_time": "0:04:12", "remaining_time": "2:27:06"}
{"current_steps": 16, "total_steps": 540, "loss": 0.0286, "lr": 2.962962962962963e-05, "epoch": 0.1471264367816092, "percentage": 2.96, "elapsed_time": "0:04:26", "remaining_time": "2:25:14"}
{"current_steps": 17, "total_steps": 540, "loss": 0.0281, "lr": 3.148148148148148e-05, "epoch": 0.15632183908045977, "percentage": 3.15, "elapsed_time": "0:04:41", "remaining_time": "2:24:13"}
{"current_steps": 18, "total_steps": 540, "loss": 0.0248, "lr": 3.3333333333333335e-05, "epoch": 0.16551724137931034, "percentage": 3.33, "elapsed_time": "0:04:54", "remaining_time": "2:22:26"}
{"current_steps": 19, "total_steps": 540, "loss": 0.0256, "lr": 3.518518518518519e-05, "epoch": 0.17471264367816092, "percentage": 3.52, "elapsed_time": "0:05:07", "remaining_time": "2:20:32"}
{"current_steps": 20, "total_steps": 540, "loss": 0.0248, "lr": 3.7037037037037037e-05, "epoch": 0.1839080459770115, "percentage": 3.7, "elapsed_time": "0:05:21", "remaining_time": "2:19:08"}
{"current_steps": 20, "total_steps": 540, "eval_loss": 0.028074176982045174, "epoch": 0.1839080459770115, "percentage": 3.7, "elapsed_time": "0:05:28", "remaining_time": "2:22:28"}
{"current_steps": 21, "total_steps": 540, "loss": 0.0231, "lr": 3.888888888888889e-05, "epoch": 0.19310344827586207, "percentage": 3.89, "elapsed_time": "0:05:40", "remaining_time": "2:20:27"}
{"current_steps": 22, "total_steps": 540, "loss": 0.0236, "lr": 4.074074074074074e-05, "epoch": 0.20229885057471264, "percentage": 4.07, "elapsed_time": "0:05:55", "remaining_time": "2:19:22"}
{"current_steps": 23, "total_steps": 540, "loss": 0.0227, "lr": 4.259259259259259e-05, "epoch": 0.21149425287356322, "percentage": 4.26, "elapsed_time": "0:06:09", "remaining_time": "2:18:32"}
{"current_steps": 24, "total_steps": 540, "loss": 0.0277, "lr": 4.4444444444444447e-05, "epoch": 0.2206896551724138, "percentage": 4.44, "elapsed_time": "0:06:22", "remaining_time": "2:17:07"}
{"current_steps": 25, "total_steps": 540, "loss": 0.0241, "lr": 4.62962962962963e-05, "epoch": 0.22988505747126436, "percentage": 4.63, "elapsed_time": "0:06:36", "remaining_time": "2:16:01"}
{"current_steps": 25, "total_steps": 540, "eval_loss": 0.025574278086423874, "epoch": 0.22988505747126436, "percentage": 4.63, "elapsed_time": "0:06:43", "remaining_time": "2:18:37"}
{"current_steps": 26, "total_steps": 540, "loss": 0.0253, "lr": 4.814814814814815e-05, "epoch": 0.23908045977011494, "percentage": 4.81, "elapsed_time": "0:06:59", "remaining_time": "2:18:03"}
{"current_steps": 27, "total_steps": 540, "loss": 0.0231, "lr": 5e-05, "epoch": 0.2482758620689655, "percentage": 5.0, "elapsed_time": "0:07:12", "remaining_time": "2:16:53"}
{"current_steps": 28, "total_steps": 540, "loss": 0.0244, "lr": 5.185185185185185e-05, "epoch": 0.2574712643678161, "percentage": 5.19, "elapsed_time": "0:07:25", "remaining_time": "2:15:37"}
{"current_steps": 29, "total_steps": 540, "loss": 0.0219, "lr": 5.370370370370371e-05, "epoch": 0.26666666666666666, "percentage": 5.37, "elapsed_time": "0:07:37", "remaining_time": "2:14:29"}
{"current_steps": 30, "total_steps": 540, "loss": 0.021, "lr": 5.555555555555556e-05, "epoch": 0.27586206896551724, "percentage": 5.56, "elapsed_time": "0:07:50", "remaining_time": "2:13:19"}
{"current_steps": 30, "total_steps": 540, "eval_loss": 0.0234465803951025, "epoch": 0.27586206896551724, "percentage": 5.56, "elapsed_time": "0:07:58", "remaining_time": "2:15:28"}
{"current_steps": 31, "total_steps": 540, "loss": 0.0213, "lr": 5.740740740740741e-05, "epoch": 0.2850574712643678, "percentage": 5.74, "elapsed_time": "0:08:11", "remaining_time": "2:14:23"}
{"current_steps": 32, "total_steps": 540, "loss": 0.0215, "lr": 5.925925925925926e-05, "epoch": 0.2942528735632184, "percentage": 5.93, "elapsed_time": "0:08:24", "remaining_time": "2:13:34"}
{"current_steps": 33, "total_steps": 540, "loss": 0.0211, "lr": 6.111111111111112e-05, "epoch": 0.30344827586206896, "percentage": 6.11, "elapsed_time": "0:08:38", "remaining_time": "2:12:40"}
{"current_steps": 34, "total_steps": 540, "loss": 0.0196, "lr": 6.296296296296296e-05, "epoch": 0.31264367816091954, "percentage": 6.3, "elapsed_time": "0:08:51", "remaining_time": "2:11:49"}
{"current_steps": 35, "total_steps": 540, "loss": 0.0213, "lr": 6.481481481481482e-05, "epoch": 0.3218390804597701, "percentage": 6.48, "elapsed_time": "0:09:06", "remaining_time": "2:11:19"}
{"current_steps": 35, "total_steps": 540, "eval_loss": 0.022549211978912354, "epoch": 0.3218390804597701, "percentage": 6.48, "elapsed_time": "0:09:13", "remaining_time": "2:13:09"}
{"current_steps": 36, "total_steps": 540, "loss": 0.0191, "lr": 6.666666666666667e-05, "epoch": 0.3310344827586207, "percentage": 6.67, "elapsed_time": "0:09:27", "remaining_time": "2:12:27"}
{"current_steps": 37, "total_steps": 540, "loss": 0.0194, "lr": 6.851851851851852e-05, "epoch": 0.34022988505747126, "percentage": 6.85, "elapsed_time": "0:09:41", "remaining_time": "2:11:39"}
{"current_steps": 38, "total_steps": 540, "loss": 0.0209, "lr": 7.037037037037038e-05, "epoch": 0.34942528735632183, "percentage": 7.04, "elapsed_time": "0:09:54", "remaining_time": "2:10:56"}
{"current_steps": 39, "total_steps": 540, "loss": 0.0195, "lr": 7.222222222222222e-05, "epoch": 0.3586206896551724, "percentage": 7.22, "elapsed_time": "0:10:09", "remaining_time": "2:10:29"}
{"current_steps": 40, "total_steps": 540, "loss": 0.0211, "lr": 7.407407407407407e-05, "epoch": 0.367816091954023, "percentage": 7.41, "elapsed_time": "0:10:23", "remaining_time": "2:09:52"}
{"current_steps": 40, "total_steps": 540, "eval_loss": 0.0213603638112545, "epoch": 0.367816091954023, "percentage": 7.41, "elapsed_time": "0:10:31", "remaining_time": "2:11:28"}
{"current_steps": 41, "total_steps": 540, "loss": 0.0199, "lr": 7.592592592592593e-05, "epoch": 0.37701149425287356, "percentage": 7.59, "elapsed_time": "0:10:43", "remaining_time": "2:10:35"}
{"current_steps": 42, "total_steps": 540, "loss": 0.0188, "lr": 7.777777777777778e-05, "epoch": 0.38620689655172413, "percentage": 7.78, "elapsed_time": "0:10:57", "remaining_time": "2:09:58"}
{"current_steps": 43, "total_steps": 540, "loss": 0.0203, "lr": 7.962962962962964e-05, "epoch": 0.3954022988505747, "percentage": 7.96, "elapsed_time": "0:11:12", "remaining_time": "2:09:31"}
{"current_steps": 44, "total_steps": 540, "loss": 0.0184, "lr": 8.148148148148148e-05, "epoch": 0.4045977011494253, "percentage": 8.15, "elapsed_time": "0:11:26", "remaining_time": "2:08:57"}
{"current_steps": 45, "total_steps": 540, "loss": 0.0185, "lr": 8.333333333333334e-05, "epoch": 0.41379310344827586, "percentage": 8.33, "elapsed_time": "0:11:42", "remaining_time": "2:08:46"}
{"current_steps": 45, "total_steps": 540, "eval_loss": 0.020027954131364822, "epoch": 0.41379310344827586, "percentage": 8.33, "elapsed_time": "0:11:49", "remaining_time": "2:10:09"}
{"current_steps": 46, "total_steps": 540, "loss": 0.0175, "lr": 8.518518518518518e-05, "epoch": 0.42298850574712643, "percentage": 8.52, "elapsed_time": "0:12:03", "remaining_time": "2:09:27"}
{"current_steps": 47, "total_steps": 540, "loss": 0.017, "lr": 8.703703703703704e-05, "epoch": 0.432183908045977, "percentage": 8.7, "elapsed_time": "0:12:18", "remaining_time": "2:09:05"}
{"current_steps": 48, "total_steps": 540, "loss": 0.018, "lr": 8.888888888888889e-05, "epoch": 0.4413793103448276, "percentage": 8.89, "elapsed_time": "0:12:31", "remaining_time": "2:08:25"}
{"current_steps": 49, "total_steps": 540, "loss": 0.0165, "lr": 9.074074074074075e-05, "epoch": 0.45057471264367815, "percentage": 9.07, "elapsed_time": "0:12:45", "remaining_time": "2:07:54"}
{"current_steps": 50, "total_steps": 540, "loss": 0.0162, "lr": 9.25925925925926e-05, "epoch": 0.45977011494252873, "percentage": 9.26, "elapsed_time": "0:12:58", "remaining_time": "2:07:12"}
{"current_steps": 50, "total_steps": 540, "eval_loss": 0.019592924043536186, "epoch": 0.45977011494252873, "percentage": 9.26, "elapsed_time": "0:13:06", "remaining_time": "2:08:26"}
{"current_steps": 51, "total_steps": 540, "loss": 0.0183, "lr": 9.444444444444444e-05, "epoch": 0.4689655172413793, "percentage": 9.44, "elapsed_time": "0:13:25", "remaining_time": "2:08:47"}
{"current_steps": 52, "total_steps": 540, "loss": 0.0189, "lr": 9.62962962962963e-05, "epoch": 0.4781609195402299, "percentage": 9.63, "elapsed_time": "0:13:39", "remaining_time": "2:08:06"}
{"current_steps": 53, "total_steps": 540, "loss": 0.0188, "lr": 9.814814814814815e-05, "epoch": 0.48735632183908045, "percentage": 9.81, "elapsed_time": "0:13:56", "remaining_time": "2:08:07"}
{"current_steps": 54, "total_steps": 540, "loss": 0.0167, "lr": 0.0001, "epoch": 0.496551724137931, "percentage": 10.0, "elapsed_time": "0:14:09", "remaining_time": "2:07:25"}
{"current_steps": 55, "total_steps": 540, "loss": 0.0177, "lr": 9.99989553622803e-05, "epoch": 0.5057471264367817, "percentage": 10.19, "elapsed_time": "0:14:23", "remaining_time": "2:06:54"}
{"current_steps": 55, "total_steps": 540, "eval_loss": 0.0189231988042593, "epoch": 0.5057471264367817, "percentage": 10.19, "elapsed_time": "0:14:31", "remaining_time": "2:08:01"}
{"current_steps": 56, "total_steps": 540, "loss": 0.0162, "lr": 9.999582149277187e-05, "epoch": 0.5149425287356322, "percentage": 10.37, "elapsed_time": "0:14:44", "remaining_time": "2:07:28"}
{"current_steps": 57, "total_steps": 540, "loss": 0.0153, "lr": 9.999059852242507e-05, "epoch": 0.5241379310344828, "percentage": 10.56, "elapsed_time": "0:14:59", "remaining_time": "2:07:00"}
{"current_steps": 58, "total_steps": 540, "loss": 0.0189, "lr": 9.998328666948438e-05, "epoch": 0.5333333333333333, "percentage": 10.74, "elapsed_time": "0:15:13", "remaining_time": "2:06:33"}
{"current_steps": 59, "total_steps": 540, "loss": 0.0158, "lr": 9.997388623947928e-05, "epoch": 0.542528735632184, "percentage": 10.93, "elapsed_time": "0:15:28", "remaining_time": "2:06:10"}
{"current_steps": 60, "total_steps": 540, "loss": 0.0168, "lr": 9.996239762521151e-05, "epoch": 0.5517241379310345, "percentage": 11.11, "elapsed_time": "0:15:41", "remaining_time": "2:05:34"}
{"current_steps": 60, "total_steps": 540, "eval_loss": 0.018419023603200912, "epoch": 0.5517241379310345, "percentage": 11.11, "elapsed_time": "0:15:49", "remaining_time": "2:06:36"}
{"current_steps": 61, "total_steps": 540, "loss": 0.0186, "lr": 9.994882130673868e-05, "epoch": 0.5609195402298851, "percentage": 11.3, "elapsed_time": "0:16:03", "remaining_time": "2:06:02"}
{"current_steps": 62, "total_steps": 540, "loss": 0.0175, "lr": 9.993315785135416e-05, "epoch": 0.5701149425287356, "percentage": 11.48, "elapsed_time": "0:16:17", "remaining_time": "2:05:36"}
{"current_steps": 63, "total_steps": 540, "loss": 0.0148, "lr": 9.991540791356342e-05, "epoch": 0.5793103448275863, "percentage": 11.67, "elapsed_time": "0:16:32", "remaining_time": "2:05:13"}
{"current_steps": 64, "total_steps": 540, "loss": 0.0163, "lr": 9.989557223505661e-05, "epoch": 0.5885057471264368, "percentage": 11.85, "elapsed_time": "0:16:46", "remaining_time": "2:04:48"}
{"current_steps": 65, "total_steps": 540, "loss": 0.017, "lr": 9.987365164467767e-05, "epoch": 0.5977011494252874, "percentage": 12.04, "elapsed_time": "0:17:01", "remaining_time": "2:04:26"}
{"current_steps": 65, "total_steps": 540, "eval_loss": 0.01821504347026348, "epoch": 0.5977011494252874, "percentage": 12.04, "elapsed_time": "0:17:09", "remaining_time": "2:05:21"}
{"current_steps": 66, "total_steps": 540, "loss": 0.016, "lr": 9.98496470583896e-05, "epoch": 0.6068965517241379, "percentage": 12.22, "elapsed_time": "0:17:22", "remaining_time": "2:04:50"}
{"current_steps": 67, "total_steps": 540, "loss": 0.017, "lr": 9.982355947923629e-05, "epoch": 0.6160919540229886, "percentage": 12.41, "elapsed_time": "0:17:37", "remaining_time": "2:04:24"}
{"current_steps": 68, "total_steps": 540, "loss": 0.0149, "lr": 9.979538999730047e-05, "epoch": 0.6252873563218391, "percentage": 12.59, "elapsed_time": "0:17:50", "remaining_time": "2:03:52"}
{"current_steps": 69, "total_steps": 540, "loss": 0.0165, "lr": 9.976513978965829e-05, "epoch": 0.6344827586206897, "percentage": 12.78, "elapsed_time": "0:18:03", "remaining_time": "2:03:13"}
{"current_steps": 70, "total_steps": 540, "loss": 0.0143, "lr": 9.973281012033007e-05, "epoch": 0.6436781609195402, "percentage": 12.96, "elapsed_time": "0:18:16", "remaining_time": "2:02:44"}
{"current_steps": 70, "total_steps": 540, "eval_loss": 0.017700908705592155, "epoch": 0.6436781609195402, "percentage": 12.96, "elapsed_time": "0:18:24", "remaining_time": "2:03:35"}
{"current_steps": 71, "total_steps": 540, "loss": 0.0154, "lr": 9.969840234022749e-05, "epoch": 0.6528735632183909, "percentage": 13.15, "elapsed_time": "0:18:38", "remaining_time": "2:03:07"}
{"current_steps": 72, "total_steps": 540, "loss": 0.0163, "lr": 9.966191788709716e-05, "epoch": 0.6620689655172414, "percentage": 13.33, "elapsed_time": "0:18:51", "remaining_time": "2:02:31"}
{"current_steps": 73, "total_steps": 540, "loss": 0.0155, "lr": 9.962335828546048e-05, "epoch": 0.671264367816092, "percentage": 13.52, "elapsed_time": "0:19:05", "remaining_time": "2:02:08"}
{"current_steps": 74, "total_steps": 540, "loss": 0.0145, "lr": 9.958272514655006e-05, "epoch": 0.6804597701149425, "percentage": 13.7, "elapsed_time": "0:19:19", "remaining_time": "2:01:43"}
{"current_steps": 75, "total_steps": 540, "loss": 0.0143, "lr": 9.954002016824227e-05, "epoch": 0.6896551724137931, "percentage": 13.89, "elapsed_time": "0:19:33", "remaining_time": "2:01:13"}
{"current_steps": 75, "total_steps": 540, "eval_loss": 0.017578113824129105, "epoch": 0.6896551724137931, "percentage": 13.89, "elapsed_time": "0:19:40", "remaining_time": "2:02:00"}
{"current_steps": 76, "total_steps": 540, "loss": 0.0168, "lr": 9.949524513498636e-05, "epoch": 0.6988505747126437, "percentage": 14.07, "elapsed_time": "0:19:55", "remaining_time": "2:01:36"}
{"current_steps": 77, "total_steps": 540, "loss": 0.0159, "lr": 9.944840191772987e-05, "epoch": 0.7080459770114943, "percentage": 14.26, "elapsed_time": "0:20:08", "remaining_time": "2:01:09"}
{"current_steps": 78, "total_steps": 540, "loss": 0.0167, "lr": 9.939949247384046e-05, "epoch": 0.7172413793103448, "percentage": 14.44, "elapsed_time": "0:20:23", "remaining_time": "2:00:49"}
{"current_steps": 79, "total_steps": 540, "loss": 0.0159, "lr": 9.934851884702414e-05, "epoch": 0.7264367816091954, "percentage": 14.63, "elapsed_time": "0:20:37", "remaining_time": "2:00:22"}
{"current_steps": 80, "total_steps": 540, "loss": 0.0155, "lr": 9.929548316723982e-05, "epoch": 0.735632183908046, "percentage": 14.81, "elapsed_time": "0:20:49", "remaining_time": "1:59:44"}
{"current_steps": 80, "total_steps": 540, "eval_loss": 0.01759597845375538, "epoch": 0.735632183908046, "percentage": 14.81, "elapsed_time": "0:20:57", "remaining_time": "2:00:28"}
{"current_steps": 81, "total_steps": 540, "loss": 0.0156, "lr": 9.924038765061042e-05, "epoch": 0.7448275862068966, "percentage": 15.0, "elapsed_time": "0:21:11", "remaining_time": "2:00:07"}
{"current_steps": 82, "total_steps": 540, "loss": 0.017, "lr": 9.918323459933005e-05, "epoch": 0.7540229885057471, "percentage": 15.19, "elapsed_time": "0:21:25", "remaining_time": "1:59:39"}
{"current_steps": 83, "total_steps": 540, "loss": 0.0151, "lr": 9.912402640156811e-05, "epoch": 0.7632183908045977, "percentage": 15.37, "elapsed_time": "0:21:39", "remaining_time": "1:59:14"}
{"current_steps": 84, "total_steps": 540, "loss": 0.0174, "lr": 9.906276553136923e-05, "epoch": 0.7724137931034483, "percentage": 15.56, "elapsed_time": "0:21:55", "remaining_time": "1:59:02"}
{"current_steps": 85, "total_steps": 540, "loss": 0.0162, "lr": 9.899945454855006e-05, "epoch": 0.7816091954022989, "percentage": 15.74, "elapsed_time": "0:22:08", "remaining_time": "1:58:29"}
{"current_steps": 85, "total_steps": 540, "eval_loss": 0.016866466030478477, "epoch": 0.7816091954022989, "percentage": 15.74, "elapsed_time": "0:22:15", "remaining_time": "1:59:10"}
{"current_steps": 86, "total_steps": 540, "loss": 0.0152, "lr": 9.893409609859222e-05, "epoch": 0.7908045977011494, "percentage": 15.93, "elapsed_time": "0:22:30", "remaining_time": "1:58:47"}
{"current_steps": 87, "total_steps": 540, "loss": 0.0156, "lr": 9.88666929125318e-05, "epoch": 0.8, "percentage": 16.11, "elapsed_time": "0:22:44", "remaining_time": "1:58:24"}
{"current_steps": 88, "total_steps": 540, "loss": 0.0162, "lr": 9.879724780684519e-05, "epoch": 0.8091954022988506, "percentage": 16.3, "elapsed_time": "0:22:58", "remaining_time": "1:58:00"}
{"current_steps": 89, "total_steps": 540, "loss": 0.0138, "lr": 9.872576368333151e-05, "epoch": 0.8183908045977012, "percentage": 16.48, "elapsed_time": "0:23:11", "remaining_time": "1:57:32"}
{"current_steps": 90, "total_steps": 540, "loss": 0.0164, "lr": 9.865224352899119e-05, "epoch": 0.8275862068965517, "percentage": 16.67, "elapsed_time": "0:23:25", "remaining_time": "1:57:06"}
{"current_steps": 90, "total_steps": 540, "eval_loss": 0.01638174243271351, "epoch": 0.8275862068965517, "percentage": 16.67, "elapsed_time": "0:23:32", "remaining_time": "1:57:44"}
{"current_steps": 91, "total_steps": 540, "loss": 0.0158, "lr": 9.857669041590134e-05, "epoch": 0.8367816091954023, "percentage": 16.85, "elapsed_time": "0:23:44", "remaining_time": "1:57:09"}
{"current_steps": 92, "total_steps": 540, "loss": 0.0149, "lr": 9.849910750108717e-05, "epoch": 0.8459770114942529, "percentage": 17.04, "elapsed_time": "0:23:57", "remaining_time": "1:56:41"}
{"current_steps": 93, "total_steps": 540, "loss": 0.0147, "lr": 9.84194980263903e-05, "epoch": 0.8551724137931035, "percentage": 17.22, "elapsed_time": "0:24:12", "remaining_time": "1:56:20"}
{"current_steps": 94, "total_steps": 540, "loss": 0.0148, "lr": 9.83378653183331e-05, "epoch": 0.864367816091954, "percentage": 17.41, "elapsed_time": "0:24:25", "remaining_time": "1:55:55"}
{"current_steps": 95, "total_steps": 540, "loss": 0.0154, "lr": 9.825421278797983e-05, "epoch": 0.8735632183908046, "percentage": 17.59, "elapsed_time": "0:24:40", "remaining_time": "1:55:34"}
{"current_steps": 95, "total_steps": 540, "eval_loss": 0.0161591824144125, "epoch": 0.8735632183908046, "percentage": 17.59, "elapsed_time": "0:24:47", "remaining_time": "1:56:10"}
{"current_steps": 96, "total_steps": 540, "loss": 0.0159, "lr": 9.816854393079403e-05, "epoch": 0.8827586206896552, "percentage": 17.78, "elapsed_time": "0:25:00", "remaining_time": "1:55:41"}
{"current_steps": 97, "total_steps": 540, "loss": 0.0154, "lr": 9.808086232649246e-05, "epoch": 0.8919540229885058, "percentage": 17.96, "elapsed_time": "0:25:15", "remaining_time": "1:55:20"}
{"current_steps": 98, "total_steps": 540, "loss": 0.0152, "lr": 9.799117163889559e-05, "epoch": 0.9011494252873563, "percentage": 18.15, "elapsed_time": "0:25:30", "remaining_time": "1:55:01"}
{"current_steps": 99, "total_steps": 540, "loss": 0.0135, "lr": 9.789947561577445e-05, "epoch": 0.9103448275862069, "percentage": 18.33, "elapsed_time": "0:25:42", "remaining_time": "1:54:28"}
{"current_steps": 100, "total_steps": 540, "loss": 0.0164, "lr": 9.780577808869398e-05, "epoch": 0.9195402298850575, "percentage": 18.52, "elapsed_time": "0:25:54", "remaining_time": "1:54:01"}
{"current_steps": 100, "total_steps": 540, "eval_loss": 0.015854647383093834, "epoch": 0.9195402298850575, "percentage": 18.52, "elapsed_time": "0:26:02", "remaining_time": "1:54:35"}
{"current_steps": 101, "total_steps": 540, "loss": 0.0144, "lr": 9.771008297285307e-05, "epoch": 0.9287356321839081, "percentage": 18.7, "elapsed_time": "0:26:22", "remaining_time": "1:54:37"}
{"current_steps": 102, "total_steps": 540, "loss": 0.0136, "lr": 9.761239426692077e-05, "epoch": 0.9379310344827586, "percentage": 18.89, "elapsed_time": "0:26:36", "remaining_time": "1:54:15"}
{"current_steps": 103, "total_steps": 540, "loss": 0.0133, "lr": 9.751271605286941e-05, "epoch": 0.9471264367816092, "percentage": 19.07, "elapsed_time": "0:26:50", "remaining_time": "1:53:52"}
{"current_steps": 104, "total_steps": 540, "loss": 0.0142, "lr": 9.741105249580383e-05, "epoch": 0.9563218390804598, "percentage": 19.26, "elapsed_time": "0:27:03", "remaining_time": "1:53:28"}
{"current_steps": 105, "total_steps": 540, "loss": 0.0156, "lr": 9.730740784378753e-05, "epoch": 0.9655172413793104, "percentage": 19.44, "elapsed_time": "0:27:18", "remaining_time": "1:53:06"}
{"current_steps": 105, "total_steps": 540, "eval_loss": 0.01596776954829693, "epoch": 0.9655172413793104, "percentage": 19.44, "elapsed_time": "0:27:25", "remaining_time": "1:53:37"}
{"current_steps": 106, "total_steps": 540, "loss": 0.0142, "lr": 9.7201786427665e-05, "epoch": 0.9747126436781609, "percentage": 19.63, "elapsed_time": "0:27:38", "remaining_time": "1:53:09"}
{"current_steps": 107, "total_steps": 540, "loss": 0.0149, "lr": 9.709419266088086e-05, "epoch": 0.9839080459770115, "percentage": 19.81, "elapsed_time": "0:27:52", "remaining_time": "1:52:46"}
{"current_steps": 108, "total_steps": 540, "loss": 0.0145, "lr": 9.698463103929542e-05, "epoch": 0.993103448275862, "percentage": 20.0, "elapsed_time": "0:28:05", "remaining_time": "1:52:23"}
{"current_steps": 109, "total_steps": 540, "loss": 0.0165, "lr": 9.687310614099675e-05, "epoch": 1.0022988505747126, "percentage": 20.19, "elapsed_time": "0:28:20", "remaining_time": "1:52:02"}
{"current_steps": 110, "total_steps": 540, "loss": 0.0145, "lr": 9.67596226261095e-05, "epoch": 1.0114942528735633, "percentage": 20.37, "elapsed_time": "0:28:32", "remaining_time": "1:51:34"}
{"current_steps": 110, "total_steps": 540, "eval_loss": 0.01590101048350334, "epoch": 1.0114942528735633, "percentage": 20.37, "elapsed_time": "0:28:40", "remaining_time": "1:52:03"}
{"current_steps": 111, "total_steps": 540, "loss": 0.0131, "lr": 9.664418523660004e-05, "epoch": 1.0206896551724138, "percentage": 20.56, "elapsed_time": "0:28:55", "remaining_time": "1:51:45"}
{"current_steps": 112, "total_steps": 540, "loss": 0.0129, "lr": 9.652679879607843e-05, "epoch": 1.0298850574712644, "percentage": 20.74, "elapsed_time": "0:29:07", "remaining_time": "1:51:17"}
{"current_steps": 113, "total_steps": 540, "loss": 0.0147, "lr": 9.640746820959684e-05, "epoch": 1.0390804597701149, "percentage": 20.93, "elapsed_time": "0:29:21", "remaining_time": "1:50:56"}
{"current_steps": 114, "total_steps": 540, "loss": 0.0131, "lr": 9.628619846344454e-05, "epoch": 1.0482758620689656, "percentage": 21.11, "elapsed_time": "0:29:36", "remaining_time": "1:50:36"}
{"current_steps": 115, "total_steps": 540, "loss": 0.0133, "lr": 9.616299462493952e-05, "epoch": 1.0574712643678161, "percentage": 21.3, "elapsed_time": "0:29:51", "remaining_time": "1:50:19"}
{"current_steps": 115, "total_steps": 540, "eval_loss": 0.015581479296088219, "epoch": 1.0574712643678161, "percentage": 21.3, "elapsed_time": "0:29:58", "remaining_time": "1:50:47"}
{"current_steps": 116, "total_steps": 540, "loss": 0.0154, "lr": 9.603786184221693e-05, "epoch": 1.0666666666666667, "percentage": 21.48, "elapsed_time": "0:30:10", "remaining_time": "1:50:19"}
{"current_steps": 117, "total_steps": 540, "loss": 0.0136, "lr": 9.591080534401371e-05, "epoch": 1.0758620689655172, "percentage": 21.67, "elapsed_time": "0:30:23", "remaining_time": "1:49:54"}
{"current_steps": 118, "total_steps": 540, "loss": 0.0142, "lr": 9.57818304394503e-05, "epoch": 1.085057471264368, "percentage": 21.85, "elapsed_time": "0:30:38", "remaining_time": "1:49:35"}
{"current_steps": 119, "total_steps": 540, "loss": 0.0144, "lr": 9.565094251780871e-05, "epoch": 1.0942528735632184, "percentage": 22.04, "elapsed_time": "0:30:50", "remaining_time": "1:49:06"}
{"current_steps": 120, "total_steps": 540, "loss": 0.0126, "lr": 9.551814704830734e-05, "epoch": 1.103448275862069, "percentage": 22.22, "elapsed_time": "0:31:02", "remaining_time": "1:48:39"}
{"current_steps": 120, "total_steps": 540, "eval_loss": 0.01549120806157589, "epoch": 1.103448275862069, "percentage": 22.22, "elapsed_time": "0:31:10", "remaining_time": "1:49:06"}
{"current_steps": 121, "total_steps": 540, "loss": 0.0144, "lr": 9.538344957987244e-05, "epoch": 1.1126436781609195, "percentage": 22.41, "elapsed_time": "0:31:23", "remaining_time": "1:48:40"}
{"current_steps": 122, "total_steps": 540, "loss": 0.0149, "lr": 9.524685574090627e-05, "epoch": 1.1218390804597702, "percentage": 22.59, "elapsed_time": "0:31:36", "remaining_time": "1:48:17"}
{"current_steps": 123, "total_steps": 540, "loss": 0.0137, "lr": 9.51083712390519e-05, "epoch": 1.1310344827586207, "percentage": 22.78, "elapsed_time": "0:31:49", "remaining_time": "1:47:53"}
{"current_steps": 124, "total_steps": 540, "loss": 0.0131, "lr": 9.496800186095466e-05, "epoch": 1.1402298850574712, "percentage": 22.96, "elapsed_time": "0:32:02", "remaining_time": "1:47:31"}
{"current_steps": 125, "total_steps": 540, "loss": 0.0145, "lr": 9.482575347202047e-05, "epoch": 1.1494252873563218, "percentage": 23.15, "elapsed_time": "0:32:17", "remaining_time": "1:47:12"}
{"current_steps": 125, "total_steps": 540, "eval_loss": 0.015383351594209671, "epoch": 1.1494252873563218, "percentage": 23.15, "elapsed_time": "0:32:24", "remaining_time": "1:47:37"}
{"current_steps": 126, "total_steps": 540, "loss": 0.0133, "lr": 9.468163201617062e-05, "epoch": 1.1586206896551725, "percentage": 23.33, "elapsed_time": "0:32:37", "remaining_time": "1:47:10"}
{"current_steps": 127, "total_steps": 540, "loss": 0.0145, "lr": 9.453564351559348e-05, "epoch": 1.167816091954023, "percentage": 23.52, "elapsed_time": "0:32:51", "remaining_time": "1:46:52"}
{"current_steps": 128, "total_steps": 540, "loss": 0.0133, "lr": 9.438779407049281e-05, "epoch": 1.1770114942528735, "percentage": 23.7, "elapsed_time": "0:33:06", "remaining_time": "1:46:35"}
{"current_steps": 129, "total_steps": 540, "loss": 0.013, "lr": 9.423808985883289e-05, "epoch": 1.186206896551724, "percentage": 23.89, "elapsed_time": "0:33:20", "remaining_time": "1:46:12"}
{"current_steps": 130, "total_steps": 540, "loss": 0.0125, "lr": 9.40865371360804e-05, "epoch": 1.1954022988505748, "percentage": 24.07, "elapsed_time": "0:33:33", "remaining_time": "1:45:49"}
{"current_steps": 130, "total_steps": 540, "eval_loss": 0.014952810481190681, "epoch": 1.1954022988505748, "percentage": 24.07, "elapsed_time": "0:33:40", "remaining_time": "1:46:13"}
{"current_steps": 131, "total_steps": 540, "loss": 0.0111, "lr": 9.393314223494296e-05, "epoch": 1.2045977011494253, "percentage": 24.26, "elapsed_time": "0:33:54", "remaining_time": "1:45:51"}
{"current_steps": 132, "total_steps": 540, "loss": 0.0132, "lr": 9.377791156510455e-05, "epoch": 1.2137931034482758, "percentage": 24.44, "elapsed_time": "0:34:08", "remaining_time": "1:45:30"}
{"current_steps": 133, "total_steps": 540, "loss": 0.0119, "lr": 9.362085161295769e-05, "epoch": 1.2229885057471264, "percentage": 24.63, "elapsed_time": "0:34:21", "remaining_time": "1:45:09"}
{"current_steps": 134, "total_steps": 540, "loss": 0.0119, "lr": 9.346196894133239e-05, "epoch": 1.232183908045977, "percentage": 24.81, "elapsed_time": "0:34:34", "remaining_time": "1:44:46"}
{"current_steps": 135, "total_steps": 540, "loss": 0.0122, "lr": 9.330127018922194e-05, "epoch": 1.2413793103448276, "percentage": 25.0, "elapsed_time": "0:34:47", "remaining_time": "1:44:23"}
{"current_steps": 135, "total_steps": 540, "eval_loss": 0.014751402661204338, "epoch": 1.2413793103448276, "percentage": 25.0, "elapsed_time": "0:34:55", "remaining_time": "1:44:46"}
{"current_steps": 136, "total_steps": 540, "loss": 0.0128, "lr": 9.313876207150543e-05, "epoch": 1.2505747126436781, "percentage": 25.19, "elapsed_time": "0:35:08", "remaining_time": "1:44:23"}
{"current_steps": 137, "total_steps": 540, "loss": 0.0119, "lr": 9.297445137866727e-05, "epoch": 1.2597701149425287, "percentage": 25.37, "elapsed_time": "0:35:21", "remaining_time": "1:44:00"}
{"current_steps": 138, "total_steps": 540, "loss": 0.0133, "lr": 9.280834497651334e-05, "epoch": 1.2689655172413792, "percentage": 25.56, "elapsed_time": "0:35:36", "remaining_time": "1:43:43"}
{"current_steps": 139, "total_steps": 540, "loss": 0.0129, "lr": 9.264044980588416e-05, "epoch": 1.27816091954023, "percentage": 25.74, "elapsed_time": "0:35:49", "remaining_time": "1:43:20"}
{"current_steps": 140, "total_steps": 540, "loss": 0.0127, "lr": 9.247077288236488e-05, "epoch": 1.2873563218390804, "percentage": 25.93, "elapsed_time": "0:36:03", "remaining_time": "1:43:01"}
{"current_steps": 140, "total_steps": 540, "eval_loss": 0.014655789360404015, "epoch": 1.2873563218390804, "percentage": 25.93, "elapsed_time": "0:36:11", "remaining_time": "1:43:23"}
{"current_steps": 141, "total_steps": 540, "loss": 0.0126, "lr": 9.229932129599205e-05, "epoch": 1.296551724137931, "percentage": 26.11, "elapsed_time": "0:36:25", "remaining_time": "1:43:05"}
{"current_steps": 142, "total_steps": 540, "loss": 0.0126, "lr": 9.212610221095748e-05, "epoch": 1.3057471264367817, "percentage": 26.3, "elapsed_time": "0:36:40", "remaining_time": "1:42:46"}
{"current_steps": 143, "total_steps": 540, "loss": 0.0113, "lr": 9.195112286530873e-05, "epoch": 1.3149425287356322, "percentage": 26.48, "elapsed_time": "0:36:53", "remaining_time": "1:42:25"}
{"current_steps": 144, "total_steps": 540, "loss": 0.0118, "lr": 9.177439057064683e-05, "epoch": 1.3241379310344827, "percentage": 26.67, "elapsed_time": "0:37:06", "remaining_time": "1:42:03"}
{"current_steps": 145, "total_steps": 540, "loss": 0.0139, "lr": 9.159591271182058e-05, "epoch": 1.3333333333333333, "percentage": 26.85, "elapsed_time": "0:37:20", "remaining_time": "1:41:43"}
{"current_steps": 145, "total_steps": 540, "eval_loss": 0.014428853057324886, "epoch": 1.3333333333333333, "percentage": 26.85, "elapsed_time": "0:37:28", "remaining_time": "1:42:03"}
{"current_steps": 146, "total_steps": 540, "loss": 0.0122, "lr": 9.141569674661817e-05, "epoch": 1.3425287356321838, "percentage": 27.04, "elapsed_time": "0:37:40", "remaining_time": "1:41:39"}
{"current_steps": 147, "total_steps": 540, "loss": 0.0123, "lr": 9.123375020545535e-05, "epoch": 1.3517241379310345, "percentage": 27.22, "elapsed_time": "0:37:54", "remaining_time": "1:41:21"}
{"current_steps": 148, "total_steps": 540, "loss": 0.0117, "lr": 9.105008069106093e-05, "epoch": 1.360919540229885, "percentage": 27.41, "elapsed_time": "0:38:08", "remaining_time": "1:41:00"}
{"current_steps": 149, "total_steps": 540, "loss": 0.0123, "lr": 9.086469587815904e-05, "epoch": 1.3701149425287356, "percentage": 27.59, "elapsed_time": "0:38:21", "remaining_time": "1:40:39"}
{"current_steps": 150, "total_steps": 540, "loss": 0.0122, "lr": 9.067760351314838e-05, "epoch": 1.3793103448275863, "percentage": 27.78, "elapsed_time": "0:38:34", "remaining_time": "1:40:18"}
{"current_steps": 150, "total_steps": 540, "eval_loss": 0.014377254992723465, "epoch": 1.3793103448275863, "percentage": 27.78, "elapsed_time": "0:38:42", "remaining_time": "1:40:37"}
{"current_steps": 151, "total_steps": 540, "loss": 0.0126, "lr": 9.048881141377863e-05, "epoch": 1.3885057471264368, "percentage": 27.96, "elapsed_time": "0:39:02", "remaining_time": "1:40:33"}
{"current_steps": 152, "total_steps": 540, "loss": 0.013, "lr": 9.029832746882371e-05, "epoch": 1.3977011494252873, "percentage": 28.15, "elapsed_time": "0:39:16", "remaining_time": "1:40:14"}
{"current_steps": 153, "total_steps": 540, "loss": 0.0114, "lr": 9.01061596377522e-05, "epoch": 1.4068965517241379, "percentage": 28.33, "elapsed_time": "0:39:29", "remaining_time": "1:39:53"}
{"current_steps": 154, "total_steps": 540, "loss": 0.0136, "lr": 8.991231595039465e-05, "epoch": 1.4160919540229884, "percentage": 28.52, "elapsed_time": "0:39:42", "remaining_time": "1:39:32"}
{"current_steps": 155, "total_steps": 540, "loss": 0.0138, "lr": 8.97168045066082e-05, "epoch": 1.4252873563218391, "percentage": 28.7, "elapsed_time": "0:39:55", "remaining_time": "1:39:09"}
{"current_steps": 155, "total_steps": 540, "eval_loss": 0.013892178423702717, "epoch": 1.4252873563218391, "percentage": 28.7, "elapsed_time": "0:40:02", "remaining_time": "1:39:28"}
{"current_steps": 156, "total_steps": 540, "loss": 0.0118, "lr": 8.951963347593797e-05, "epoch": 1.4344827586206896, "percentage": 28.89, "elapsed_time": "0:40:17", "remaining_time": "1:39:09"}
{"current_steps": 157, "total_steps": 540, "loss": 0.011, "lr": 8.932081109727582e-05, "epoch": 1.4436781609195402, "percentage": 29.07, "elapsed_time": "0:40:32", "remaining_time": "1:38:53"}
{"current_steps": 158, "total_steps": 540, "loss": 0.0115, "lr": 8.912034567851599e-05, "epoch": 1.452873563218391, "percentage": 29.26, "elapsed_time": "0:40:46", "remaining_time": "1:38:34"}
{"current_steps": 159, "total_steps": 540, "loss": 0.0115, "lr": 8.891824559620801e-05, "epoch": 1.4620689655172414, "percentage": 29.44, "elapsed_time": "0:41:00", "remaining_time": "1:38:14"}
{"current_steps": 160, "total_steps": 540, "loss": 0.0143, "lr": 8.871451929520663e-05, "epoch": 1.471264367816092, "percentage": 29.63, "elapsed_time": "0:41:14", "remaining_time": "1:37:57"}
{"current_steps": 160, "total_steps": 540, "eval_loss": 0.013947720639407635, "epoch": 1.471264367816092, "percentage": 29.63, "elapsed_time": "0:41:22", "remaining_time": "1:38:15"}
{"current_steps": 161, "total_steps": 540, "loss": 0.0131, "lr": 8.850917528831899e-05, "epoch": 1.4804597701149425, "percentage": 29.81, "elapsed_time": "0:41:34", "remaining_time": "1:37:52"}
{"current_steps": 162, "total_steps": 540, "loss": 0.0109, "lr": 8.83022221559489e-05, "epoch": 1.489655172413793, "percentage": 30.0, "elapsed_time": "0:41:48", "remaining_time": "1:37:33"}
{"current_steps": 163, "total_steps": 540, "loss": 0.0117, "lr": 8.809366854573831e-05, "epoch": 1.4988505747126437, "percentage": 30.19, "elapsed_time": "0:42:01", "remaining_time": "1:37:13"}
{"current_steps": 164, "total_steps": 540, "loss": 0.013, "lr": 8.78835231722059e-05, "epoch": 1.5080459770114942, "percentage": 30.37, "elapsed_time": "0:42:15", "remaining_time": "1:36:53"}
{"current_steps": 165, "total_steps": 540, "loss": 0.0124, "lr": 8.767179481638303e-05, "epoch": 1.5172413793103448, "percentage": 30.56, "elapsed_time": "0:42:30", "remaining_time": "1:36:37"}
{"current_steps": 165, "total_steps": 540, "eval_loss": 0.013795728795230389, "epoch": 1.5172413793103448, "percentage": 30.56, "elapsed_time": "0:42:38", "remaining_time": "1:36:54"}
{"current_steps": 166, "total_steps": 540, "loss": 0.0113, "lr": 8.745849232544681e-05, "epoch": 1.5264367816091955, "percentage": 30.74, "elapsed_time": "0:42:52", "remaining_time": "1:36:34"}
{"current_steps": 167, "total_steps": 540, "loss": 0.0137, "lr": 8.724362461235029e-05, "epoch": 1.535632183908046, "percentage": 30.93, "elapsed_time": "0:43:07", "remaining_time": "1:36:18"}
{"current_steps": 168, "total_steps": 540, "loss": 0.0117, "lr": 8.702720065545024e-05, "epoch": 1.5448275862068965, "percentage": 31.11, "elapsed_time": "0:43:21", "remaining_time": "1:36:01"}
{"current_steps": 169, "total_steps": 540, "loss": 0.0122, "lr": 8.680922949813178e-05, "epoch": 1.5540229885057473, "percentage": 31.3, "elapsed_time": "0:43:36", "remaining_time": "1:35:42"}
{"current_steps": 170, "total_steps": 540, "loss": 0.0124, "lr": 8.658972024843062e-05, "epoch": 1.5632183908045976, "percentage": 31.48, "elapsed_time": "0:43:49", "remaining_time": "1:35:24"}
{"current_steps": 170, "total_steps": 540, "eval_loss": 0.013545939698815346, "epoch": 1.5632183908045976, "percentage": 31.48, "elapsed_time": "0:43:57", "remaining_time": "1:35:40"}
{"current_steps": 171, "total_steps": 540, "loss": 0.0126, "lr": 8.636868207865244e-05, "epoch": 1.5724137931034483, "percentage": 31.67, "elapsed_time": "0:44:11", "remaining_time": "1:35:22"}
{"current_steps": 172, "total_steps": 540, "loss": 0.0129, "lr": 8.614612422498964e-05, "epoch": 1.5816091954022988, "percentage": 31.85, "elapsed_time": "0:44:25", "remaining_time": "1:35:02"}
{"current_steps": 173, "total_steps": 540, "loss": 0.0133, "lr": 8.592205598713539e-05, "epoch": 1.5908045977011493, "percentage": 32.04, "elapsed_time": "0:44:38", "remaining_time": "1:34:42"}
{"current_steps": 174, "total_steps": 540, "loss": 0.0113, "lr": 8.569648672789497e-05, "epoch": 1.6, "percentage": 32.22, "elapsed_time": "0:44:53", "remaining_time": "1:34:24"}
{"current_steps": 175, "total_steps": 540, "loss": 0.0138, "lr": 8.546942587279465e-05, "epoch": 1.6091954022988506, "percentage": 32.41, "elapsed_time": "0:45:05", "remaining_time": "1:34:02"}
{"current_steps": 175, "total_steps": 540, "eval_loss": 0.01319777499884367, "epoch": 1.6091954022988506, "percentage": 32.41, "elapsed_time": "0:45:13", "remaining_time": "1:34:18"}
{"current_steps": 176, "total_steps": 540, "loss": 0.0127, "lr": 8.524088290968781e-05, "epoch": 1.6183908045977011, "percentage": 32.59, "elapsed_time": "0:45:26", "remaining_time": "1:33:59"}
{"current_steps": 177, "total_steps": 540, "loss": 0.0131, "lr": 8.501086738835843e-05, "epoch": 1.6275862068965519, "percentage": 32.78, "elapsed_time": "0:45:40", "remaining_time": "1:33:40"}
{"current_steps": 178, "total_steps": 540, "loss": 0.0118, "lr": 8.47793889201221e-05, "epoch": 1.6367816091954022, "percentage": 32.96, "elapsed_time": "0:45:54", "remaining_time": "1:33:22"}
{"current_steps": 179, "total_steps": 540, "loss": 0.0149, "lr": 8.45464571774244e-05, "epoch": 1.645977011494253, "percentage": 33.15, "elapsed_time": "0:46:10", "remaining_time": "1:33:07"}
{"current_steps": 180, "total_steps": 540, "loss": 0.0112, "lr": 8.43120818934367e-05, "epoch": 1.6551724137931034, "percentage": 33.33, "elapsed_time": "0:46:23", "remaining_time": "1:32:47"}
{"current_steps": 180, "total_steps": 540, "eval_loss": 0.013563334941864014, "epoch": 1.6551724137931034, "percentage": 33.33, "elapsed_time": "0:46:31", "remaining_time": "1:33:03"}
{"current_steps": 181, "total_steps": 540, "loss": 0.0121, "lr": 8.407627286164948e-05, "epoch": 1.664367816091954, "percentage": 33.52, "elapsed_time": "0:46:45", "remaining_time": "1:32:44"}
{"current_steps": 182, "total_steps": 540, "loss": 0.0118, "lr": 8.383903993546311e-05, "epoch": 1.6735632183908047, "percentage": 33.7, "elapsed_time": "0:46:59", "remaining_time": "1:32:25"}
{"current_steps": 183, "total_steps": 540, "loss": 0.0123, "lr": 8.360039302777612e-05, "epoch": 1.6827586206896552, "percentage": 33.89, "elapsed_time": "0:47:12", "remaining_time": "1:32:06"}
{"current_steps": 184, "total_steps": 540, "loss": 0.0124, "lr": 8.336034211057098e-05, "epoch": 1.6919540229885057, "percentage": 34.07, "elapsed_time": "0:47:27", "remaining_time": "1:31:49"}
{"current_steps": 185, "total_steps": 540, "loss": 0.0102, "lr": 8.31188972144974e-05, "epoch": 1.7011494252873565, "percentage": 34.26, "elapsed_time": "0:47:41", "remaining_time": "1:31:30"}
{"current_steps": 185, "total_steps": 540, "eval_loss": 0.013533576391637325, "epoch": 1.7011494252873565, "percentage": 34.26, "elapsed_time": "0:47:49", "remaining_time": "1:31:45"}
{"current_steps": 186, "total_steps": 540, "loss": 0.0104, "lr": 8.28760684284532e-05, "epoch": 1.7103448275862068, "percentage": 34.44, "elapsed_time": "0:48:03", "remaining_time": "1:31:28"}
{"current_steps": 187, "total_steps": 540, "loss": 0.0129, "lr": 8.263186589916273e-05, "epoch": 1.7195402298850575, "percentage": 34.63, "elapsed_time": "0:48:17", "remaining_time": "1:31:08"}
{"current_steps": 188, "total_steps": 540, "loss": 0.0124, "lr": 8.238629983075294e-05, "epoch": 1.728735632183908, "percentage": 34.81, "elapsed_time": "0:48:31", "remaining_time": "1:30:50"}
{"current_steps": 189, "total_steps": 540, "loss": 0.0135, "lr": 8.213938048432697e-05, "epoch": 1.7379310344827585, "percentage": 35.0, "elapsed_time": "0:48:45", "remaining_time": "1:30:32"}
{"current_steps": 190, "total_steps": 540, "loss": 0.0135, "lr": 8.18911181775353e-05, "epoch": 1.7471264367816093, "percentage": 35.19, "elapsed_time": "0:48:59", "remaining_time": "1:30:14"}
{"current_steps": 190, "total_steps": 540, "eval_loss": 0.013264240697026253, "epoch": 1.7471264367816093, "percentage": 35.19, "elapsed_time": "0:49:06", "remaining_time": "1:30:27"}
{"current_steps": 191, "total_steps": 540, "loss": 0.0118, "lr": 8.164152328414476e-05, "epoch": 1.7563218390804598, "percentage": 35.37, "elapsed_time": "0:49:19", "remaining_time": "1:30:08"}
{"current_steps": 192, "total_steps": 540, "loss": 0.0126, "lr": 8.139060623360493e-05, "epoch": 1.7655172413793103, "percentage": 35.56, "elapsed_time": "0:49:32", "remaining_time": "1:29:48"}
{"current_steps": 193, "total_steps": 540, "loss": 0.0103, "lr": 8.113837751061246e-05, "epoch": 1.774712643678161, "percentage": 35.74, "elapsed_time": "0:49:46", "remaining_time": "1:29:29"}
{"current_steps": 194, "total_steps": 540, "loss": 0.0111, "lr": 8.088484765467286e-05, "epoch": 1.7839080459770114, "percentage": 35.93, "elapsed_time": "0:50:00", "remaining_time": "1:29:11"}
{"current_steps": 195, "total_steps": 540, "loss": 0.01, "lr": 8.063002725966015e-05, "epoch": 1.793103448275862, "percentage": 36.11, "elapsed_time": "0:50:14", "remaining_time": "1:28:53"}
{"current_steps": 195, "total_steps": 540, "eval_loss": 0.013534443452954292, "epoch": 1.793103448275862, "percentage": 36.11, "elapsed_time": "0:50:22", "remaining_time": "1:29:06"}
{"current_steps": 196, "total_steps": 540, "loss": 0.0143, "lr": 8.037392697337418e-05, "epoch": 1.8022988505747126, "percentage": 36.3, "elapsed_time": "0:50:37", "remaining_time": "1:28:51"}
{"current_steps": 197, "total_steps": 540, "loss": 0.011, "lr": 8.011655749709575e-05, "epoch": 1.8114942528735631, "percentage": 36.48, "elapsed_time": "0:50:50", "remaining_time": "1:28:31"}
{"current_steps": 198, "total_steps": 540, "loss": 0.0101, "lr": 7.985792958513931e-05, "epoch": 1.8206896551724139, "percentage": 36.67, "elapsed_time": "0:51:04", "remaining_time": "1:28:13"}
{"current_steps": 199, "total_steps": 540, "loss": 0.0124, "lr": 7.95980540444038e-05, "epoch": 1.8298850574712644, "percentage": 36.85, "elapsed_time": "0:51:19", "remaining_time": "1:27:56"}
{"current_steps": 200, "total_steps": 540, "loss": 0.0115, "lr": 7.93369417339209e-05, "epoch": 1.839080459770115, "percentage": 37.04, "elapsed_time": "0:51:32", "remaining_time": "1:27:37"}
{"current_steps": 200, "total_steps": 540, "eval_loss": 0.01306515745818615, "epoch": 1.839080459770115, "percentage": 37.04, "elapsed_time": "0:51:40", "remaining_time": "1:27:50"}
{"current_steps": 201, "total_steps": 540, "loss": 0.0133, "lr": 7.907460356440133e-05, "epoch": 1.8482758620689657, "percentage": 37.22, "elapsed_time": "0:52:01", "remaining_time": "1:27:44"}
{"current_steps": 202, "total_steps": 540, "loss": 0.0093, "lr": 7.881105049777901e-05, "epoch": 1.857471264367816, "percentage": 37.41, "elapsed_time": "0:52:16", "remaining_time": "1:27:28"}
{"current_steps": 203, "total_steps": 540, "loss": 0.0125, "lr": 7.854629354675291e-05, "epoch": 1.8666666666666667, "percentage": 37.59, "elapsed_time": "0:52:30", "remaining_time": "1:27:09"}
{"current_steps": 204, "total_steps": 540, "loss": 0.0111, "lr": 7.828034377432693e-05, "epoch": 1.8758620689655172, "percentage": 37.78, "elapsed_time": "0:52:43", "remaining_time": "1:26:50"}
{"current_steps": 205, "total_steps": 540, "loss": 0.0113, "lr": 7.801321229334764e-05, "epoch": 1.8850574712643677, "percentage": 37.96, "elapsed_time": "0:52:58", "remaining_time": "1:26:33"}
{"current_steps": 205, "total_steps": 540, "eval_loss": 0.012708608992397785, "epoch": 1.8850574712643677, "percentage": 37.96, "elapsed_time": "0:53:05", "remaining_time": "1:26:46"}
{"current_steps": 206, "total_steps": 540, "loss": 0.013, "lr": 7.774491026603985e-05, "epoch": 1.8942528735632185, "percentage": 38.15, "elapsed_time": "0:53:19", "remaining_time": "1:26:28"}
{"current_steps": 207, "total_steps": 540, "loss": 0.0106, "lr": 7.74754489035403e-05, "epoch": 1.903448275862069, "percentage": 38.33, "elapsed_time": "0:53:34", "remaining_time": "1:26:10"}
{"current_steps": 208, "total_steps": 540, "loss": 0.0112, "lr": 7.720483946542914e-05, "epoch": 1.9126436781609195, "percentage": 38.52, "elapsed_time": "0:53:48", "remaining_time": "1:25:53"}
{"current_steps": 209, "total_steps": 540, "loss": 0.0119, "lr": 7.69330932592594e-05, "epoch": 1.9218390804597703, "percentage": 38.7, "elapsed_time": "0:54:03", "remaining_time": "1:25:36"}
{"current_steps": 210, "total_steps": 540, "loss": 0.0107, "lr": 7.666022164008457e-05, "epoch": 1.9310344827586206, "percentage": 38.89, "elapsed_time": "0:54:17", "remaining_time": "1:25:19"}
{"current_steps": 210, "total_steps": 540, "eval_loss": 0.012785980477929115, "epoch": 1.9310344827586206, "percentage": 38.89, "elapsed_time": "0:54:25", "remaining_time": "1:25:31"}
{"current_steps": 211, "total_steps": 540, "loss": 0.0106, "lr": 7.63862360099841e-05, "epoch": 1.9402298850574713, "percentage": 39.07, "elapsed_time": "0:54:37", "remaining_time": "1:25:10"}
{"current_steps": 212, "total_steps": 540, "loss": 0.0107, "lr": 7.611114781758692e-05, "epoch": 1.9494252873563218, "percentage": 39.26, "elapsed_time": "0:54:51", "remaining_time": "1:24:51"}
{"current_steps": 213, "total_steps": 540, "loss": 0.0124, "lr": 7.583496855759316e-05, "epoch": 1.9586206896551723, "percentage": 39.44, "elapsed_time": "0:55:04", "remaining_time": "1:24:32"}
{"current_steps": 214, "total_steps": 540, "loss": 0.0115, "lr": 7.555770977029367e-05, "epoch": 1.967816091954023, "percentage": 39.63, "elapsed_time": "0:55:18", "remaining_time": "1:24:15"}
{"current_steps": 215, "total_steps": 540, "loss": 0.0122, "lr": 7.527938304108795e-05, "epoch": 1.9770114942528736, "percentage": 39.81, "elapsed_time": "0:55:32", "remaining_time": "1:23:57"}
{"current_steps": 215, "total_steps": 540, "eval_loss": 0.01276768371462822, "epoch": 1.9770114942528736, "percentage": 39.81, "elapsed_time": "0:55:40", "remaining_time": "1:24:08"}
{"current_steps": 216, "total_steps": 540, "loss": 0.0109, "lr": 7.500000000000001e-05, "epoch": 1.986206896551724, "percentage": 40.0, "elapsed_time": "0:55:54", "remaining_time": "1:23:51"}
{"current_steps": 217, "total_steps": 540, "loss": 0.0114, "lr": 7.471957232119234e-05, "epoch": 1.9954022988505749, "percentage": 40.19, "elapsed_time": "0:56:07", "remaining_time": "1:23:32"}
{"current_steps": 218, "total_steps": 540, "loss": 0.0123, "lr": 7.443811172247821e-05, "epoch": 2.004597701149425, "percentage": 40.37, "elapsed_time": "0:56:21", "remaining_time": "1:23:14"}
{"current_steps": 219, "total_steps": 540, "loss": 0.0081, "lr": 7.415562996483192e-05, "epoch": 2.013793103448276, "percentage": 40.56, "elapsed_time": "0:56:36", "remaining_time": "1:22:59"}
{"current_steps": 220, "total_steps": 540, "loss": 0.0099, "lr": 7.387213885189746e-05, "epoch": 2.0229885057471266, "percentage": 40.74, "elapsed_time": "0:56:51", "remaining_time": "1:22:41"}
{"current_steps": 220, "total_steps": 540, "eval_loss": 0.012783367186784744, "epoch": 2.0229885057471266, "percentage": 40.74, "elapsed_time": "0:56:58", "remaining_time": "1:22:53"}
{"current_steps": 221, "total_steps": 540, "loss": 0.0088, "lr": 7.358765022949519e-05, "epoch": 2.032183908045977, "percentage": 40.93, "elapsed_time": "0:57:13", "remaining_time": "1:22:36"}
{"current_steps": 222, "total_steps": 540, "loss": 0.0112, "lr": 7.330217598512695e-05, "epoch": 2.0413793103448277, "percentage": 41.11, "elapsed_time": "0:57:27", "remaining_time": "1:22:18"}
{"current_steps": 223, "total_steps": 540, "loss": 0.0092, "lr": 7.30157280474793e-05, "epoch": 2.050574712643678, "percentage": 41.3, "elapsed_time": "0:57:39", "remaining_time": "1:21:58"}
{"current_steps": 224, "total_steps": 540, "loss": 0.0091, "lr": 7.272831838592503e-05, "epoch": 2.0597701149425287, "percentage": 41.48, "elapsed_time": "0:57:53", "remaining_time": "1:21:40"}
{"current_steps": 225, "total_steps": 540, "loss": 0.0121, "lr": 7.243995901002312e-05, "epoch": 2.0689655172413794, "percentage": 41.67, "elapsed_time": "0:58:08", "remaining_time": "1:21:23"}
{"current_steps": 225, "total_steps": 540, "eval_loss": 0.012876266613602638, "epoch": 2.0689655172413794, "percentage": 41.67, "elapsed_time": "0:58:15", "remaining_time": "1:21:34"}
{"current_steps": 226, "total_steps": 540, "loss": 0.0095, "lr": 7.215066196901676e-05, "epoch": 2.0781609195402297, "percentage": 41.85, "elapsed_time": "0:58:28", "remaining_time": "1:21:15"}
{"current_steps": 227, "total_steps": 540, "loss": 0.0095, "lr": 7.186043935133005e-05, "epoch": 2.0873563218390805, "percentage": 42.04, "elapsed_time": "0:58:42", "remaining_time": "1:20:56"}
{"current_steps": 228, "total_steps": 540, "loss": 0.0099, "lr": 7.156930328406268e-05, "epoch": 2.0965517241379312, "percentage": 42.22, "elapsed_time": "0:58:55", "remaining_time": "1:20:37"}
{"current_steps": 229, "total_steps": 540, "loss": 0.0108, "lr": 7.127726593248337e-05, "epoch": 2.1057471264367815, "percentage": 42.41, "elapsed_time": "0:59:08", "remaining_time": "1:20:18"}
{"current_steps": 230, "total_steps": 540, "loss": 0.0103, "lr": 7.098433949952146e-05, "epoch": 2.1149425287356323, "percentage": 42.59, "elapsed_time": "0:59:21", "remaining_time": "1:20:00"}
{"current_steps": 230, "total_steps": 540, "eval_loss": 0.012764949351549149, "epoch": 2.1149425287356323, "percentage": 42.59, "elapsed_time": "0:59:29", "remaining_time": "1:20:10"}
{"current_steps": 231, "total_steps": 540, "loss": 0.0095, "lr": 7.069053622525696e-05, "epoch": 2.1241379310344826, "percentage": 42.78, "elapsed_time": "0:59:43", "remaining_time": "1:19:53"}
{"current_steps": 232, "total_steps": 540, "loss": 0.0101, "lr": 7.039586838640919e-05, "epoch": 2.1333333333333333, "percentage": 42.96, "elapsed_time": "0:59:56", "remaining_time": "1:19:35"}
{"current_steps": 233, "total_steps": 540, "loss": 0.009, "lr": 7.01003482958237e-05, "epoch": 2.142528735632184, "percentage": 43.15, "elapsed_time": "1:00:08", "remaining_time": "1:19:15"}
{"current_steps": 234, "total_steps": 540, "loss": 0.0115, "lr": 6.980398830195785e-05, "epoch": 2.1517241379310343, "percentage": 43.33, "elapsed_time": "1:00:22", "remaining_time": "1:18:56"}
{"current_steps": 235, "total_steps": 540, "loss": 0.01, "lr": 6.950680078836474e-05, "epoch": 2.160919540229885, "percentage": 43.52, "elapsed_time": "1:00:35", "remaining_time": "1:18:38"}
{"current_steps": 235, "total_steps": 540, "eval_loss": 0.012695999816060066, "epoch": 2.160919540229885, "percentage": 43.52, "elapsed_time": "1:00:42", "remaining_time": "1:18:47"}
{"current_steps": 236, "total_steps": 540, "loss": 0.0108, "lr": 6.920879817317589e-05, "epoch": 2.170114942528736, "percentage": 43.7, "elapsed_time": "1:00:56", "remaining_time": "1:18:29"}
{"current_steps": 237, "total_steps": 540, "loss": 0.0089, "lr": 6.890999290858214e-05, "epoch": 2.179310344827586, "percentage": 43.89, "elapsed_time": "1:01:07", "remaining_time": "1:18:09"}
{"current_steps": 238, "total_steps": 540, "loss": 0.0094, "lr": 6.861039748031351e-05, "epoch": 2.188505747126437, "percentage": 44.07, "elapsed_time": "1:01:19", "remaining_time": "1:17:48"}
{"current_steps": 239, "total_steps": 540, "loss": 0.0099, "lr": 6.83100244071174e-05, "epoch": 2.197701149425287, "percentage": 44.26, "elapsed_time": "1:01:34", "remaining_time": "1:17:32"}
{"current_steps": 240, "total_steps": 540, "loss": 0.0089, "lr": 6.800888624023553e-05, "epoch": 2.206896551724138, "percentage": 44.44, "elapsed_time": "1:01:47", "remaining_time": "1:17:14"}
{"current_steps": 240, "total_steps": 540, "eval_loss": 0.01267631258815527, "epoch": 2.206896551724138, "percentage": 44.44, "elapsed_time": "1:01:55", "remaining_time": "1:17:24"}
{"current_steps": 241, "total_steps": 540, "loss": 0.0105, "lr": 6.770699556287939e-05, "epoch": 2.2160919540229886, "percentage": 44.63, "elapsed_time": "1:02:10", "remaining_time": "1:17:08"}
{"current_steps": 242, "total_steps": 540, "loss": 0.0099, "lr": 6.740436498970452e-05, "epoch": 2.225287356321839, "percentage": 44.81, "elapsed_time": "1:02:24", "remaining_time": "1:16:51"}
{"current_steps": 243, "total_steps": 540, "loss": 0.0099, "lr": 6.710100716628344e-05, "epoch": 2.2344827586206897, "percentage": 45.0, "elapsed_time": "1:02:38", "remaining_time": "1:16:34"}
{"current_steps": 244, "total_steps": 540, "loss": 0.0085, "lr": 6.679693476857711e-05, "epoch": 2.2436781609195404, "percentage": 45.19, "elapsed_time": "1:02:50", "remaining_time": "1:16:14"}
{"current_steps": 245, "total_steps": 540, "loss": 0.0089, "lr": 6.649216050240539e-05, "epoch": 2.2528735632183907, "percentage": 45.37, "elapsed_time": "1:03:05", "remaining_time": "1:15:57"}
{"current_steps": 245, "total_steps": 540, "eval_loss": 0.012675927020609379, "epoch": 2.2528735632183907, "percentage": 45.37, "elapsed_time": "1:03:12", "remaining_time": "1:16:06"}
{"current_steps": 246, "total_steps": 540, "loss": 0.0092, "lr": 6.618669710291606e-05, "epoch": 2.2620689655172415, "percentage": 45.56, "elapsed_time": "1:03:27", "remaining_time": "1:15:50"}
{"current_steps": 247, "total_steps": 540, "loss": 0.0102, "lr": 6.588055733405266e-05, "epoch": 2.2712643678160918, "percentage": 45.74, "elapsed_time": "1:03:41", "remaining_time": "1:15:32"}
{"current_steps": 248, "total_steps": 540, "loss": 0.0095, "lr": 6.557375398802123e-05, "epoch": 2.2804597701149425, "percentage": 45.93, "elapsed_time": "1:03:55", "remaining_time": "1:15:15"}
{"current_steps": 249, "total_steps": 540, "loss": 0.0092, "lr": 6.526629988475567e-05, "epoch": 2.2896551724137932, "percentage": 46.11, "elapsed_time": "1:04:10", "remaining_time": "1:15:00"}
{"current_steps": 250, "total_steps": 540, "loss": 0.0105, "lr": 6.495820787138209e-05, "epoch": 2.2988505747126435, "percentage": 46.3, "elapsed_time": "1:04:24", "remaining_time": "1:14:42"}
{"current_steps": 250, "total_steps": 540, "eval_loss": 0.012465451844036579, "epoch": 2.2988505747126435, "percentage": 46.3, "elapsed_time": "1:04:31", "remaining_time": "1:14:51"}
{"current_steps": 251, "total_steps": 540, "loss": 0.0093, "lr": 6.464949082168204e-05, "epoch": 2.3080459770114943, "percentage": 46.48, "elapsed_time": "1:04:52", "remaining_time": "1:14:41"}
{"current_steps": 252, "total_steps": 540, "loss": 0.0102, "lr": 6.434016163555452e-05, "epoch": 2.317241379310345, "percentage": 46.67, "elapsed_time": "1:05:06", "remaining_time": "1:14:24"}
{"current_steps": 253, "total_steps": 540, "loss": 0.0093, "lr": 6.403023323847695e-05, "epoch": 2.3264367816091953, "percentage": 46.85, "elapsed_time": "1:05:21", "remaining_time": "1:14:08"}
{"current_steps": 254, "total_steps": 540, "loss": 0.0096, "lr": 6.371971858096508e-05, "epoch": 2.335632183908046, "percentage": 47.04, "elapsed_time": "1:05:36", "remaining_time": "1:13:52"}
{"current_steps": 255, "total_steps": 540, "loss": 0.0093, "lr": 6.340863063803188e-05, "epoch": 2.344827586206897, "percentage": 47.22, "elapsed_time": "1:05:49", "remaining_time": "1:13:33"}
{"current_steps": 255, "total_steps": 540, "eval_loss": 0.012436559423804283, "epoch": 2.344827586206897, "percentage": 47.22, "elapsed_time": "1:05:56", "remaining_time": "1:13:42"}
{"current_steps": 256, "total_steps": 540, "loss": 0.0107, "lr": 6.30969824086453e-05, "epoch": 2.354022988505747, "percentage": 47.41, "elapsed_time": "1:06:10", "remaining_time": "1:13:25"}
{"current_steps": 257, "total_steps": 540, "loss": 0.0103, "lr": 6.27847869151852e-05, "epoch": 2.363218390804598, "percentage": 47.59, "elapsed_time": "1:06:23", "remaining_time": "1:13:06"}
{"current_steps": 258, "total_steps": 540, "loss": 0.0099, "lr": 6.247205720289907e-05, "epoch": 2.372413793103448, "percentage": 47.78, "elapsed_time": "1:06:37", "remaining_time": "1:12:49"}
{"current_steps": 259, "total_steps": 540, "loss": 0.0105, "lr": 6.215880633935708e-05, "epoch": 2.381609195402299, "percentage": 47.96, "elapsed_time": "1:06:51", "remaining_time": "1:12:32"}
{"current_steps": 260, "total_steps": 540, "loss": 0.0097, "lr": 6.184504741390596e-05, "epoch": 2.3908045977011496, "percentage": 48.15, "elapsed_time": "1:07:06", "remaining_time": "1:12:16"}
{"current_steps": 260, "total_steps": 540, "eval_loss": 0.01255771517753601, "epoch": 2.3908045977011496, "percentage": 48.15, "elapsed_time": "1:07:14", "remaining_time": "1:12:24"}
{"current_steps": 261, "total_steps": 540, "loss": 0.0116, "lr": 6.153079353712201e-05, "epoch": 2.4, "percentage": 48.33, "elapsed_time": "1:07:28", "remaining_time": "1:12:07"}
{"current_steps": 262, "total_steps": 540, "loss": 0.0098, "lr": 6.121605784026339e-05, "epoch": 2.4091954022988507, "percentage": 48.52, "elapsed_time": "1:07:42", "remaining_time": "1:11:50"}
{"current_steps": 263, "total_steps": 540, "loss": 0.0085, "lr": 6.09008534747213e-05, "epoch": 2.418390804597701, "percentage": 48.7, "elapsed_time": "1:07:56", "remaining_time": "1:11:33"}
{"current_steps": 264, "total_steps": 540, "loss": 0.0096, "lr": 6.058519361147055e-05, "epoch": 2.4275862068965517, "percentage": 48.89, "elapsed_time": "1:08:10", "remaining_time": "1:11:16"}
{"current_steps": 265, "total_steps": 540, "loss": 0.0091, "lr": 6.02690914405191e-05, "epoch": 2.4367816091954024, "percentage": 49.07, "elapsed_time": "1:08:24", "remaining_time": "1:10:59"}
{"current_steps": 265, "total_steps": 540, "eval_loss": 0.0126058179885149, "epoch": 2.4367816091954024, "percentage": 49.07, "elapsed_time": "1:08:31", "remaining_time": "1:11:07"}
{"current_steps": 266, "total_steps": 540, "loss": 0.0102, "lr": 5.995256017035703e-05, "epoch": 2.4459770114942527, "percentage": 49.26, "elapsed_time": "1:08:43", "remaining_time": "1:10:47"}
{"current_steps": 267, "total_steps": 540, "loss": 0.0091, "lr": 5.963561302740449e-05, "epoch": 2.4551724137931035, "percentage": 49.44, "elapsed_time": "1:08:57", "remaining_time": "1:10:30"}
{"current_steps": 268, "total_steps": 540, "loss": 0.0097, "lr": 5.9318263255459116e-05, "epoch": 2.464367816091954, "percentage": 49.63, "elapsed_time": "1:09:11", "remaining_time": "1:10:13"}
{"current_steps": 269, "total_steps": 540, "loss": 0.0095, "lr": 5.900052411514257e-05, "epoch": 2.4735632183908045, "percentage": 49.81, "elapsed_time": "1:09:24", "remaining_time": "1:09:55"}
{"current_steps": 270, "total_steps": 540, "loss": 0.0095, "lr": 5.868240888334653e-05, "epoch": 2.4827586206896552, "percentage": 50.0, "elapsed_time": "1:09:39", "remaining_time": "1:09:39"}
{"current_steps": 270, "total_steps": 540, "eval_loss": 0.01236729696393013, "epoch": 2.4827586206896552, "percentage": 50.0, "elapsed_time": "1:09:47", "remaining_time": "1:09:47"}
{"current_steps": 271, "total_steps": 540, "loss": 0.0091, "lr": 5.836393085267776e-05, "epoch": 2.491954022988506, "percentage": 50.19, "elapsed_time": "1:10:02", "remaining_time": "1:09:31"}
{"current_steps": 272, "total_steps": 540, "loss": 0.0087, "lr": 5.804510333090287e-05, "epoch": 2.5011494252873563, "percentage": 50.37, "elapsed_time": "1:10:13", "remaining_time": "1:09:11"}
{"current_steps": 273, "total_steps": 540, "loss": 0.0088, "lr": 5.772593964039203e-05, "epoch": 2.510344827586207, "percentage": 50.56, "elapsed_time": "1:10:26", "remaining_time": "1:08:53"}
{"current_steps": 274, "total_steps": 540, "loss": 0.0095, "lr": 5.740645311756245e-05, "epoch": 2.5195402298850573, "percentage": 50.74, "elapsed_time": "1:10:40", "remaining_time": "1:08:37"}
{"current_steps": 275, "total_steps": 540, "loss": 0.0094, "lr": 5.708665711232103e-05, "epoch": 2.528735632183908, "percentage": 50.93, "elapsed_time": "1:10:54", "remaining_time": "1:08:19"}
{"current_steps": 275, "total_steps": 540, "eval_loss": 0.012253012508153915, "epoch": 2.528735632183908, "percentage": 50.93, "elapsed_time": "1:11:01", "remaining_time": "1:08:26"}
{"current_steps": 276, "total_steps": 540, "loss": 0.0102, "lr": 5.6766564987506566e-05, "epoch": 2.5379310344827584, "percentage": 51.11, "elapsed_time": "1:11:16", "remaining_time": "1:08:10"}
{"current_steps": 277, "total_steps": 540, "loss": 0.0089, "lr": 5.644619011833133e-05, "epoch": 2.547126436781609, "percentage": 51.3, "elapsed_time": "1:11:29", "remaining_time": "1:07:52"}
{"current_steps": 278, "total_steps": 540, "loss": 0.009, "lr": 5.6125545891822274e-05, "epoch": 2.55632183908046, "percentage": 51.48, "elapsed_time": "1:11:44", "remaining_time": "1:07:36"}
{"current_steps": 279, "total_steps": 540, "loss": 0.0103, "lr": 5.5804645706261514e-05, "epoch": 2.56551724137931, "percentage": 51.67, "elapsed_time": "1:11:58", "remaining_time": "1:07:19"}
{"current_steps": 280, "total_steps": 540, "loss": 0.0092, "lr": 5.548350297062659e-05, "epoch": 2.574712643678161, "percentage": 51.85, "elapsed_time": "1:12:12", "remaining_time": "1:07:03"}
{"current_steps": 280, "total_steps": 540, "eval_loss": 0.011931383982300758, "epoch": 2.574712643678161, "percentage": 51.85, "elapsed_time": "1:12:20", "remaining_time": "1:07:10"}
{"current_steps": 281, "total_steps": 540, "loss": 0.0093, "lr": 5.516213110403009e-05, "epoch": 2.5839080459770116, "percentage": 52.04, "elapsed_time": "1:12:33", "remaining_time": "1:06:52"}
{"current_steps": 282, "total_steps": 540, "loss": 0.0116, "lr": 5.484054353515896e-05, "epoch": 2.593103448275862, "percentage": 52.22, "elapsed_time": "1:12:47", "remaining_time": "1:06:36"}
{"current_steps": 283, "total_steps": 540, "loss": 0.0076, "lr": 5.451875370171341e-05, "epoch": 2.6022988505747127, "percentage": 52.41, "elapsed_time": "1:13:01", "remaining_time": "1:06:19"}
{"current_steps": 284, "total_steps": 540, "loss": 0.0088, "lr": 5.419677504984534e-05, "epoch": 2.6114942528735634, "percentage": 52.59, "elapsed_time": "1:13:16", "remaining_time": "1:06:03"}
{"current_steps": 285, "total_steps": 540, "loss": 0.0084, "lr": 5.387462103359655e-05, "epoch": 2.6206896551724137, "percentage": 52.78, "elapsed_time": "1:13:30", "remaining_time": "1:05:46"}
{"current_steps": 285, "total_steps": 540, "eval_loss": 0.012128188274800777, "epoch": 2.6206896551724137, "percentage": 52.78, "elapsed_time": "1:13:38", "remaining_time": "1:05:52"}
{"current_steps": 286, "total_steps": 540, "loss": 0.0109, "lr": 5.355230511433651e-05, "epoch": 2.6298850574712644, "percentage": 52.96, "elapsed_time": "1:13:52", "remaining_time": "1:05:36"}
{"current_steps": 287, "total_steps": 540, "loss": 0.009, "lr": 5.32298407601999e-05, "epoch": 2.639080459770115, "percentage": 53.15, "elapsed_time": "1:14:07", "remaining_time": "1:05:20"}
{"current_steps": 288, "total_steps": 540, "loss": 0.0091, "lr": 5.290724144552379e-05, "epoch": 2.6482758620689655, "percentage": 53.33, "elapsed_time": "1:14:22", "remaining_time": "1:05:04"}
{"current_steps": 289, "total_steps": 540, "loss": 0.0096, "lr": 5.258452065028473e-05, "epoch": 2.657471264367816, "percentage": 53.52, "elapsed_time": "1:14:36", "remaining_time": "1:04:47"}
{"current_steps": 290, "total_steps": 540, "loss": 0.0098, "lr": 5.226169185953532e-05, "epoch": 2.6666666666666665, "percentage": 53.7, "elapsed_time": "1:14:51", "remaining_time": "1:04:31"}
{"current_steps": 290, "total_steps": 540, "eval_loss": 0.01195099763572216, "epoch": 2.6666666666666665, "percentage": 53.7, "elapsed_time": "1:14:59", "remaining_time": "1:04:38"}
{"current_steps": 291, "total_steps": 540, "loss": 0.0088, "lr": 5.193876856284085e-05, "epoch": 2.6758620689655173, "percentage": 53.89, "elapsed_time": "1:15:13", "remaining_time": "1:04:22"}
{"current_steps": 292, "total_steps": 540, "loss": 0.0089, "lr": 5.1615764253715536e-05, "epoch": 2.6850574712643676, "percentage": 54.07, "elapsed_time": "1:15:27", "remaining_time": "1:04:05"}
{"current_steps": 293, "total_steps": 540, "loss": 0.0104, "lr": 5.129269242905882e-05, "epoch": 2.6942528735632183, "percentage": 54.26, "elapsed_time": "1:15:41", "remaining_time": "1:03:48"}
{"current_steps": 294, "total_steps": 540, "loss": 0.0087, "lr": 5.096956658859122e-05, "epoch": 2.703448275862069, "percentage": 54.44, "elapsed_time": "1:15:56", "remaining_time": "1:03:32"}
{"current_steps": 295, "total_steps": 540, "loss": 0.0097, "lr": 5.064640023429043e-05, "epoch": 2.7126436781609193, "percentage": 54.63, "elapsed_time": "1:16:09", "remaining_time": "1:03:15"}
{"current_steps": 295, "total_steps": 540, "eval_loss": 0.012155573815107346, "epoch": 2.7126436781609193, "percentage": 54.63, "elapsed_time": "1:16:17", "remaining_time": "1:03:21"}
{"current_steps": 296, "total_steps": 540, "loss": 0.0095, "lr": 5.0323206869826966e-05, "epoch": 2.72183908045977, "percentage": 54.81, "elapsed_time": "1:16:30", "remaining_time": "1:03:04"}
{"current_steps": 297, "total_steps": 540, "loss": 0.0094, "lr": 5e-05, "epoch": 2.731034482758621, "percentage": 55.0, "elapsed_time": "1:16:44", "remaining_time": "1:02:47"}
{"current_steps": 298, "total_steps": 540, "loss": 0.0079, "lr": 4.967679313017303e-05, "epoch": 2.740229885057471, "percentage": 55.19, "elapsed_time": "1:16:58", "remaining_time": "1:02:30"}
{"current_steps": 299, "total_steps": 540, "loss": 0.0088, "lr": 4.9353599765709584e-05, "epoch": 2.749425287356322, "percentage": 55.37, "elapsed_time": "1:17:12", "remaining_time": "1:02:13"}
{"current_steps": 300, "total_steps": 540, "loss": 0.0093, "lr": 4.903043341140879e-05, "epoch": 2.7586206896551726, "percentage": 55.56, "elapsed_time": "1:17:25", "remaining_time": "1:01:56"}
{"current_steps": 300, "total_steps": 540, "eval_loss": 0.012067421339452267, "epoch": 2.7586206896551726, "percentage": 55.56, "elapsed_time": "1:17:33", "remaining_time": "1:02:02"}
{"current_steps": 301, "total_steps": 540, "loss": 0.0099, "lr": 4.870730757094121e-05, "epoch": 2.767816091954023, "percentage": 55.74, "elapsed_time": "1:17:54", "remaining_time": "1:01:52"}
{"current_steps": 302, "total_steps": 540, "loss": 0.0077, "lr": 4.8384235746284476e-05, "epoch": 2.7770114942528736, "percentage": 55.93, "elapsed_time": "1:18:08", "remaining_time": "1:01:34"}
{"current_steps": 303, "total_steps": 540, "loss": 0.0084, "lr": 4.806123143715916e-05, "epoch": 2.7862068965517244, "percentage": 56.11, "elapsed_time": "1:18:23", "remaining_time": "1:01:18"}
{"current_steps": 304, "total_steps": 540, "loss": 0.0089, "lr": 4.7738308140464685e-05, "epoch": 2.7954022988505747, "percentage": 56.3, "elapsed_time": "1:18:36", "remaining_time": "1:01:01"}
{"current_steps": 305, "total_steps": 540, "loss": 0.0096, "lr": 4.7415479349715275e-05, "epoch": 2.8045977011494254, "percentage": 56.48, "elapsed_time": "1:18:51", "remaining_time": "1:00:45"}
{"current_steps": 305, "total_steps": 540, "eval_loss": 0.011938001029193401, "epoch": 2.8045977011494254, "percentage": 56.48, "elapsed_time": "1:18:59", "remaining_time": "1:00:51"}
{"current_steps": 306, "total_steps": 540, "loss": 0.0091, "lr": 4.709275855447621e-05, "epoch": 2.8137931034482757, "percentage": 56.67, "elapsed_time": "1:19:12", "remaining_time": "1:00:34"}
{"current_steps": 307, "total_steps": 540, "loss": 0.0101, "lr": 4.677015923980011e-05, "epoch": 2.8229885057471265, "percentage": 56.85, "elapsed_time": "1:19:26", "remaining_time": "1:00:17"}
{"current_steps": 308, "total_steps": 540, "loss": 0.009, "lr": 4.6447694885663514e-05, "epoch": 2.8321839080459768, "percentage": 57.04, "elapsed_time": "1:19:39", "remaining_time": "0:59:59"}
{"current_steps": 309, "total_steps": 540, "loss": 0.0089, "lr": 4.612537896640346e-05, "epoch": 2.8413793103448275, "percentage": 57.22, "elapsed_time": "1:19:54", "remaining_time": "0:59:43"}
{"current_steps": 310, "total_steps": 540, "loss": 0.0097, "lr": 4.5803224950154656e-05, "epoch": 2.8505747126436782, "percentage": 57.41, "elapsed_time": "1:20:07", "remaining_time": "0:59:27"}
{"current_steps": 310, "total_steps": 540, "eval_loss": 0.01165664754807949, "epoch": 2.8505747126436782, "percentage": 57.41, "elapsed_time": "1:20:15", "remaining_time": "0:59:32"}
{"current_steps": 311, "total_steps": 540, "loss": 0.0082, "lr": 4.54812462982866e-05, "epoch": 2.8597701149425285, "percentage": 57.59, "elapsed_time": "1:20:29", "remaining_time": "0:59:15"}
{"current_steps": 312, "total_steps": 540, "loss": 0.0105, "lr": 4.515945646484105e-05, "epoch": 2.8689655172413793, "percentage": 57.78, "elapsed_time": "1:20:42", "remaining_time": "0:58:58"}
{"current_steps": 313, "total_steps": 540, "loss": 0.0085, "lr": 4.4837868895969936e-05, "epoch": 2.87816091954023, "percentage": 57.96, "elapsed_time": "1:20:54", "remaining_time": "0:58:40"}
{"current_steps": 314, "total_steps": 540, "loss": 0.008, "lr": 4.451649702937342e-05, "epoch": 2.8873563218390803, "percentage": 58.15, "elapsed_time": "1:21:07", "remaining_time": "0:58:23"}
{"current_steps": 315, "total_steps": 540, "loss": 0.0101, "lr": 4.4195354293738484e-05, "epoch": 2.896551724137931, "percentage": 58.33, "elapsed_time": "1:21:21", "remaining_time": "0:58:07"}
{"current_steps": 315, "total_steps": 540, "eval_loss": 0.011835181154310703, "epoch": 2.896551724137931, "percentage": 58.33, "elapsed_time": "1:21:29", "remaining_time": "0:58:12"}
{"current_steps": 316, "total_steps": 540, "loss": 0.0091, "lr": 4.387445410817774e-05, "epoch": 2.905747126436782, "percentage": 58.52, "elapsed_time": "1:21:44", "remaining_time": "0:57:56"}
{"current_steps": 317, "total_steps": 540, "loss": 0.0085, "lr": 4.355380988166867e-05, "epoch": 2.914942528735632, "percentage": 58.7, "elapsed_time": "1:21:59", "remaining_time": "0:57:40"}
{"current_steps": 318, "total_steps": 540, "loss": 0.0089, "lr": 4.323343501249346e-05, "epoch": 2.924137931034483, "percentage": 58.89, "elapsed_time": "1:22:12", "remaining_time": "0:57:23"}
{"current_steps": 319, "total_steps": 540, "loss": 0.0088, "lr": 4.2913342887678985e-05, "epoch": 2.9333333333333336, "percentage": 59.07, "elapsed_time": "1:22:27", "remaining_time": "0:57:07"}
{"current_steps": 320, "total_steps": 540, "loss": 0.0088, "lr": 4.259354688243757e-05, "epoch": 2.942528735632184, "percentage": 59.26, "elapsed_time": "1:22:39", "remaining_time": "0:56:49"}
{"current_steps": 320, "total_steps": 540, "eval_loss": 0.011810057796537876, "epoch": 2.942528735632184, "percentage": 59.26, "elapsed_time": "1:22:47", "remaining_time": "0:56:55"}
{"current_steps": 321, "total_steps": 540, "loss": 0.0093, "lr": 4.227406035960798e-05, "epoch": 2.9517241379310346, "percentage": 59.44, "elapsed_time": "1:23:00", "remaining_time": "0:56:37"}
{"current_steps": 322, "total_steps": 540, "loss": 0.0081, "lr": 4.195489666909713e-05, "epoch": 2.960919540229885, "percentage": 59.63, "elapsed_time": "1:23:14", "remaining_time": "0:56:21"}
{"current_steps": 323, "total_steps": 540, "loss": 0.0072, "lr": 4.1636069147322246e-05, "epoch": 2.9701149425287356, "percentage": 59.81, "elapsed_time": "1:23:27", "remaining_time": "0:56:04"}
{"current_steps": 324, "total_steps": 540, "loss": 0.0094, "lr": 4.131759111665349e-05, "epoch": 2.979310344827586, "percentage": 60.0, "elapsed_time": "1:23:41", "remaining_time": "0:55:47"}
{"current_steps": 325, "total_steps": 540, "loss": 0.0096, "lr": 4.099947588485744e-05, "epoch": 2.9885057471264367, "percentage": 60.19, "elapsed_time": "1:23:54", "remaining_time": "0:55:30"}
{"current_steps": 325, "total_steps": 540, "eval_loss": 0.011837408877909184, "epoch": 2.9885057471264367, "percentage": 60.19, "elapsed_time": "1:24:02", "remaining_time": "0:55:35"}
{"current_steps": 326, "total_steps": 540, "loss": 0.0093, "lr": 4.06817367445409e-05, "epoch": 2.9977011494252874, "percentage": 60.37, "elapsed_time": "1:24:18", "remaining_time": "0:55:20"}
{"current_steps": 327, "total_steps": 540, "loss": 0.0072, "lr": 4.036438697259551e-05, "epoch": 3.0068965517241377, "percentage": 60.56, "elapsed_time": "1:24:32", "remaining_time": "0:55:04"}
{"current_steps": 328, "total_steps": 540, "loss": 0.0069, "lr": 4.004743982964298e-05, "epoch": 3.0160919540229885, "percentage": 60.74, "elapsed_time": "1:24:46", "remaining_time": "0:54:47"}
{"current_steps": 329, "total_steps": 540, "loss": 0.0095, "lr": 3.97309085594809e-05, "epoch": 3.025287356321839, "percentage": 60.93, "elapsed_time": "1:25:01", "remaining_time": "0:54:31"}
{"current_steps": 330, "total_steps": 540, "loss": 0.0078, "lr": 3.941480638852948e-05, "epoch": 3.0344827586206895, "percentage": 61.11, "elapsed_time": "1:25:15", "remaining_time": "0:54:15"}
{"current_steps": 330, "total_steps": 540, "eval_loss": 0.011860949918627739, "epoch": 3.0344827586206895, "percentage": 61.11, "elapsed_time": "1:25:23", "remaining_time": "0:54:20"}
{"current_steps": 331, "total_steps": 540, "loss": 0.0073, "lr": 3.909914652527871e-05, "epoch": 3.0436781609195402, "percentage": 61.3, "elapsed_time": "1:25:36", "remaining_time": "0:54:03"}
{"current_steps": 332, "total_steps": 540, "loss": 0.0074, "lr": 3.878394215973663e-05, "epoch": 3.052873563218391, "percentage": 61.48, "elapsed_time": "1:25:51", "remaining_time": "0:53:47"}
{"current_steps": 333, "total_steps": 540, "loss": 0.0077, "lr": 3.846920646287799e-05, "epoch": 3.0620689655172413, "percentage": 61.67, "elapsed_time": "1:26:05", "remaining_time": "0:53:31"}
{"current_steps": 334, "total_steps": 540, "loss": 0.0077, "lr": 3.815495258609404e-05, "epoch": 3.071264367816092, "percentage": 61.85, "elapsed_time": "1:26:18", "remaining_time": "0:53:13"}
{"current_steps": 335, "total_steps": 540, "loss": 0.0064, "lr": 3.784119366064293e-05, "epoch": 3.0804597701149423, "percentage": 62.04, "elapsed_time": "1:26:32", "remaining_time": "0:52:57"}
{"current_steps": 335, "total_steps": 540, "eval_loss": 0.01191374659538269, "epoch": 3.0804597701149423, "percentage": 62.04, "elapsed_time": "1:26:40", "remaining_time": "0:53:02"}
{"current_steps": 336, "total_steps": 540, "loss": 0.007, "lr": 3.752794279710094e-05, "epoch": 3.089655172413793, "percentage": 62.22, "elapsed_time": "1:26:52", "remaining_time": "0:52:44"}
{"current_steps": 337, "total_steps": 540, "loss": 0.0083, "lr": 3.721521308481482e-05, "epoch": 3.098850574712644, "percentage": 62.41, "elapsed_time": "1:27:07", "remaining_time": "0:52:28"}
{"current_steps": 338, "total_steps": 540, "loss": 0.0062, "lr": 3.6903017591354706e-05, "epoch": 3.108045977011494, "percentage": 62.59, "elapsed_time": "1:27:19", "remaining_time": "0:52:11"}
{"current_steps": 339, "total_steps": 540, "loss": 0.0068, "lr": 3.6591369361968124e-05, "epoch": 3.117241379310345, "percentage": 62.78, "elapsed_time": "1:27:33", "remaining_time": "0:51:54"}
{"current_steps": 340, "total_steps": 540, "loss": 0.0073, "lr": 3.628028141903493e-05, "epoch": 3.1264367816091956, "percentage": 62.96, "elapsed_time": "1:27:45", "remaining_time": "0:51:37"}
{"current_steps": 340, "total_steps": 540, "eval_loss": 0.01213847566395998, "epoch": 3.1264367816091956, "percentage": 62.96, "elapsed_time": "1:27:52", "remaining_time": "0:51:41"}
{"current_steps": 341, "total_steps": 540, "loss": 0.0074, "lr": 3.596976676152306e-05, "epoch": 3.135632183908046, "percentage": 63.15, "elapsed_time": "1:28:06", "remaining_time": "0:51:25"}
{"current_steps": 342, "total_steps": 540, "loss": 0.0071, "lr": 3.5659838364445505e-05, "epoch": 3.1448275862068966, "percentage": 63.33, "elapsed_time": "1:28:20", "remaining_time": "0:51:08"}
{"current_steps": 343, "total_steps": 540, "loss": 0.0072, "lr": 3.535050917831797e-05, "epoch": 3.154022988505747, "percentage": 63.52, "elapsed_time": "1:28:33", "remaining_time": "0:50:51"}
{"current_steps": 344, "total_steps": 540, "loss": 0.0063, "lr": 3.5041792128617927e-05, "epoch": 3.1632183908045977, "percentage": 63.7, "elapsed_time": "1:28:47", "remaining_time": "0:50:35"}
{"current_steps": 345, "total_steps": 540, "loss": 0.0066, "lr": 3.473370011524435e-05, "epoch": 3.1724137931034484, "percentage": 63.89, "elapsed_time": "1:29:01", "remaining_time": "0:50:19"}
{"current_steps": 345, "total_steps": 540, "eval_loss": 0.012059099040925503, "epoch": 3.1724137931034484, "percentage": 63.89, "elapsed_time": "1:29:09", "remaining_time": "0:50:23"}
{"current_steps": 346, "total_steps": 540, "loss": 0.0076, "lr": 3.442624601197877e-05, "epoch": 3.1816091954022987, "percentage": 64.07, "elapsed_time": "1:29:23", "remaining_time": "0:50:07"}
{"current_steps": 347, "total_steps": 540, "loss": 0.0064, "lr": 3.4119442665947344e-05, "epoch": 3.1908045977011494, "percentage": 64.26, "elapsed_time": "1:29:35", "remaining_time": "0:49:49"}
{"current_steps": 348, "total_steps": 540, "loss": 0.0082, "lr": 3.381330289708396e-05, "epoch": 3.2, "percentage": 64.44, "elapsed_time": "1:29:50", "remaining_time": "0:49:33"}
{"current_steps": 349, "total_steps": 540, "loss": 0.0072, "lr": 3.350783949759462e-05, "epoch": 3.2091954022988505, "percentage": 64.63, "elapsed_time": "1:30:02", "remaining_time": "0:49:16"}
{"current_steps": 350, "total_steps": 540, "loss": 0.0067, "lr": 3.3203065231422904e-05, "epoch": 3.218390804597701, "percentage": 64.81, "elapsed_time": "1:30:17", "remaining_time": "0:49:01"}
{"current_steps": 350, "total_steps": 540, "eval_loss": 0.011746257543563843, "epoch": 3.218390804597701, "percentage": 64.81, "elapsed_time": "1:30:25", "remaining_time": "0:49:05"}
{"current_steps": 351, "total_steps": 540, "loss": 0.0082, "lr": 3.289899283371657e-05, "epoch": 3.227586206896552, "percentage": 65.0, "elapsed_time": "1:30:46", "remaining_time": "0:48:52"}
{"current_steps": 352, "total_steps": 540, "loss": 0.007, "lr": 3.2595635010295475e-05, "epoch": 3.2367816091954023, "percentage": 65.19, "elapsed_time": "1:30:58", "remaining_time": "0:48:35"}
{"current_steps": 353, "total_steps": 540, "loss": 0.0073, "lr": 3.2293004437120624e-05, "epoch": 3.245977011494253, "percentage": 65.37, "elapsed_time": "1:31:13", "remaining_time": "0:48:19"}
{"current_steps": 354, "total_steps": 540, "loss": 0.0075, "lr": 3.199111375976449e-05, "epoch": 3.2551724137931033, "percentage": 65.56, "elapsed_time": "1:31:26", "remaining_time": "0:48:02"}
{"current_steps": 355, "total_steps": 540, "loss": 0.007, "lr": 3.1689975592882603e-05, "epoch": 3.264367816091954, "percentage": 65.74, "elapsed_time": "1:31:40", "remaining_time": "0:47:46"}
{"current_steps": 355, "total_steps": 540, "eval_loss": 0.011750459671020508, "epoch": 3.264367816091954, "percentage": 65.74, "elapsed_time": "1:31:48", "remaining_time": "0:47:50"}
{"current_steps": 356, "total_steps": 540, "loss": 0.0078, "lr": 3.1389602519686515e-05, "epoch": 3.2735632183908048, "percentage": 65.93, "elapsed_time": "1:32:03", "remaining_time": "0:47:34"}
{"current_steps": 357, "total_steps": 540, "loss": 0.007, "lr": 3.109000709141788e-05, "epoch": 3.282758620689655, "percentage": 66.11, "elapsed_time": "1:32:16", "remaining_time": "0:47:17"}
{"current_steps": 358, "total_steps": 540, "loss": 0.0061, "lr": 3.079120182682412e-05, "epoch": 3.291954022988506, "percentage": 66.3, "elapsed_time": "1:32:28", "remaining_time": "0:47:00"}
{"current_steps": 359, "total_steps": 540, "loss": 0.0085, "lr": 3.049319921163526e-05, "epoch": 3.301149425287356, "percentage": 66.48, "elapsed_time": "1:32:41", "remaining_time": "0:46:44"}
{"current_steps": 360, "total_steps": 540, "loss": 0.0072, "lr": 3.019601169804216e-05, "epoch": 3.310344827586207, "percentage": 66.67, "elapsed_time": "1:32:57", "remaining_time": "0:46:28"}
{"current_steps": 360, "total_steps": 540, "eval_loss": 0.011605262756347656, "epoch": 3.310344827586207, "percentage": 66.67, "elapsed_time": "1:33:04", "remaining_time": "0:46:32"}
{"current_steps": 361, "total_steps": 540, "loss": 0.0075, "lr": 2.9899651704176325e-05, "epoch": 3.3195402298850576, "percentage": 66.85, "elapsed_time": "1:33:17", "remaining_time": "0:46:15"}
{"current_steps": 362, "total_steps": 540, "loss": 0.0059, "lr": 2.9604131613590824e-05, "epoch": 3.328735632183908, "percentage": 67.04, "elapsed_time": "1:33:30", "remaining_time": "0:45:58"}
{"current_steps": 363, "total_steps": 540, "loss": 0.0068, "lr": 2.9309463774743046e-05, "epoch": 3.3379310344827586, "percentage": 67.22, "elapsed_time": "1:33:44", "remaining_time": "0:45:42"}
{"current_steps": 364, "total_steps": 540, "loss": 0.0076, "lr": 2.901566050047855e-05, "epoch": 3.3471264367816094, "percentage": 67.41, "elapsed_time": "1:33:58", "remaining_time": "0:45:26"}
{"current_steps": 365, "total_steps": 540, "loss": 0.0074, "lr": 2.872273406751664e-05, "epoch": 3.3563218390804597, "percentage": 67.59, "elapsed_time": "1:34:11", "remaining_time": "0:45:09"}
{"current_steps": 365, "total_steps": 540, "eval_loss": 0.011744478717446327, "epoch": 3.3563218390804597, "percentage": 67.59, "elapsed_time": "1:34:19", "remaining_time": "0:45:13"}
{"current_steps": 366, "total_steps": 540, "loss": 0.007, "lr": 2.8430696715937337e-05, "epoch": 3.3655172413793104, "percentage": 67.78, "elapsed_time": "1:34:32", "remaining_time": "0:44:56"}
{"current_steps": 367, "total_steps": 540, "loss": 0.0062, "lr": 2.8139560648669962e-05, "epoch": 3.374712643678161, "percentage": 67.96, "elapsed_time": "1:34:44", "remaining_time": "0:44:39"}
{"current_steps": 368, "total_steps": 540, "loss": 0.0065, "lr": 2.7849338030983257e-05, "epoch": 3.3839080459770114, "percentage": 68.15, "elapsed_time": "1:34:59", "remaining_time": "0:44:24"}
{"current_steps": 369, "total_steps": 540, "loss": 0.0062, "lr": 2.7560040989976892e-05, "epoch": 3.393103448275862, "percentage": 68.33, "elapsed_time": "1:35:13", "remaining_time": "0:44:07"}
{"current_steps": 370, "total_steps": 540, "loss": 0.0067, "lr": 2.7271681614074973e-05, "epoch": 3.4022988505747125, "percentage": 68.52, "elapsed_time": "1:35:27", "remaining_time": "0:43:51"}
{"current_steps": 370, "total_steps": 540, "eval_loss": 0.011655151844024658, "epoch": 3.4022988505747125, "percentage": 68.52, "elapsed_time": "1:35:35", "remaining_time": "0:43:55"}
{"current_steps": 371, "total_steps": 540, "loss": 0.0074, "lr": 2.6984271952520722e-05, "epoch": 3.4114942528735632, "percentage": 68.7, "elapsed_time": "1:35:48", "remaining_time": "0:43:38"}
{"current_steps": 372, "total_steps": 540, "loss": 0.0069, "lr": 2.6697824014873075e-05, "epoch": 3.420689655172414, "percentage": 68.89, "elapsed_time": "1:36:03", "remaining_time": "0:43:22"}
{"current_steps": 373, "total_steps": 540, "loss": 0.007, "lr": 2.641234977050484e-05, "epoch": 3.4298850574712643, "percentage": 69.07, "elapsed_time": "1:36:17", "remaining_time": "0:43:06"}
{"current_steps": 374, "total_steps": 540, "loss": 0.006, "lr": 2.612786114810255e-05, "epoch": 3.439080459770115, "percentage": 69.26, "elapsed_time": "1:36:31", "remaining_time": "0:42:50"}
{"current_steps": 375, "total_steps": 540, "loss": 0.0072, "lr": 2.5844370035168073e-05, "epoch": 3.4482758620689653, "percentage": 69.44, "elapsed_time": "1:36:46", "remaining_time": "0:42:35"}
{"current_steps": 375, "total_steps": 540, "eval_loss": 0.01167826447635889, "epoch": 3.4482758620689653, "percentage": 69.44, "elapsed_time": "1:36:54", "remaining_time": "0:42:38"}
{"current_steps": 376, "total_steps": 540, "loss": 0.0073, "lr": 2.5561888277521794e-05, "epoch": 3.457471264367816, "percentage": 69.63, "elapsed_time": "1:37:08", "remaining_time": "0:42:22"}
{"current_steps": 377, "total_steps": 540, "loss": 0.0063, "lr": 2.528042767880766e-05, "epoch": 3.466666666666667, "percentage": 69.81, "elapsed_time": "1:37:21", "remaining_time": "0:42:05"}
{"current_steps": 378, "total_steps": 540, "loss": 0.0073, "lr": 2.500000000000001e-05, "epoch": 3.475862068965517, "percentage": 70.0, "elapsed_time": "1:37:34", "remaining_time": "0:41:49"}
{"current_steps": 379, "total_steps": 540, "loss": 0.0077, "lr": 2.4720616958912053e-05, "epoch": 3.485057471264368, "percentage": 70.19, "elapsed_time": "1:37:49", "remaining_time": "0:41:33"}
{"current_steps": 380, "total_steps": 540, "loss": 0.0069, "lr": 2.4442290229706344e-05, "epoch": 3.4942528735632186, "percentage": 70.37, "elapsed_time": "1:38:02", "remaining_time": "0:41:16"}
{"current_steps": 380, "total_steps": 540, "eval_loss": 0.011730669066309929, "epoch": 3.4942528735632186, "percentage": 70.37, "elapsed_time": "1:38:10", "remaining_time": "0:41:20"}
{"current_steps": 381, "total_steps": 540, "loss": 0.0066, "lr": 2.4165031442406855e-05, "epoch": 3.503448275862069, "percentage": 70.56, "elapsed_time": "1:38:23", "remaining_time": "0:41:03"}
{"current_steps": 382, "total_steps": 540, "loss": 0.0068, "lr": 2.3888852182413085e-05, "epoch": 3.5126436781609196, "percentage": 70.74, "elapsed_time": "1:38:38", "remaining_time": "0:40:48"}
{"current_steps": 383, "total_steps": 540, "loss": 0.0069, "lr": 2.361376399001592e-05, "epoch": 3.5218390804597703, "percentage": 70.93, "elapsed_time": "1:38:52", "remaining_time": "0:40:31"}
{"current_steps": 384, "total_steps": 540, "loss": 0.0077, "lr": 2.333977835991545e-05, "epoch": 3.5310344827586206, "percentage": 71.11, "elapsed_time": "1:39:05", "remaining_time": "0:40:15"}
{"current_steps": 385, "total_steps": 540, "loss": 0.0076, "lr": 2.3066906740740623e-05, "epoch": 3.5402298850574714, "percentage": 71.3, "elapsed_time": "1:39:19", "remaining_time": "0:39:59"}
{"current_steps": 385, "total_steps": 540, "eval_loss": 0.011591249145567417, "epoch": 3.5402298850574714, "percentage": 71.3, "elapsed_time": "1:39:27", "remaining_time": "0:40:02"}
{"current_steps": 386, "total_steps": 540, "loss": 0.0073, "lr": 2.2795160534570864e-05, "epoch": 3.5494252873563217, "percentage": 71.48, "elapsed_time": "1:39:42", "remaining_time": "0:39:46"}
{"current_steps": 387, "total_steps": 540, "loss": 0.0067, "lr": 2.25245510964597e-05, "epoch": 3.5586206896551724, "percentage": 71.67, "elapsed_time": "1:39:56", "remaining_time": "0:39:30"}
{"current_steps": 388, "total_steps": 540, "loss": 0.0066, "lr": 2.225508973396016e-05, "epoch": 3.5678160919540227, "percentage": 71.85, "elapsed_time": "1:40:08", "remaining_time": "0:39:13"}
{"current_steps": 389, "total_steps": 540, "loss": 0.0062, "lr": 2.198678770665238e-05, "epoch": 3.5770114942528735, "percentage": 72.04, "elapsed_time": "1:40:22", "remaining_time": "0:38:57"}
{"current_steps": 390, "total_steps": 540, "loss": 0.0068, "lr": 2.171965622567308e-05, "epoch": 3.586206896551724, "percentage": 72.22, "elapsed_time": "1:40:35", "remaining_time": "0:38:41"}
{"current_steps": 390, "total_steps": 540, "eval_loss": 0.011386090889573097, "epoch": 3.586206896551724, "percentage": 72.22, "elapsed_time": "1:40:43", "remaining_time": "0:38:44"}
{"current_steps": 391, "total_steps": 540, "loss": 0.0064, "lr": 2.1453706453247087e-05, "epoch": 3.5954022988505745, "percentage": 72.41, "elapsed_time": "1:40:57", "remaining_time": "0:38:28"}
{"current_steps": 392, "total_steps": 540, "loss": 0.0073, "lr": 2.1188949502220983e-05, "epoch": 3.6045977011494252, "percentage": 72.59, "elapsed_time": "1:41:10", "remaining_time": "0:38:12"}
{"current_steps": 393, "total_steps": 540, "loss": 0.0063, "lr": 2.0925396435598664e-05, "epoch": 3.613793103448276, "percentage": 72.78, "elapsed_time": "1:41:24", "remaining_time": "0:37:55"}
{"current_steps": 394, "total_steps": 540, "loss": 0.0077, "lr": 2.066305826607911e-05, "epoch": 3.6229885057471263, "percentage": 72.96, "elapsed_time": "1:41:37", "remaining_time": "0:37:39"}
{"current_steps": 395, "total_steps": 540, "loss": 0.0074, "lr": 2.0401945955596206e-05, "epoch": 3.632183908045977, "percentage": 73.15, "elapsed_time": "1:41:51", "remaining_time": "0:37:23"}
{"current_steps": 395, "total_steps": 540, "eval_loss": 0.011461833491921425, "epoch": 3.632183908045977, "percentage": 73.15, "elapsed_time": "1:41:59", "remaining_time": "0:37:26"}
{"current_steps": 396, "total_steps": 540, "loss": 0.0077, "lr": 2.0142070414860704e-05, "epoch": 3.6413793103448278, "percentage": 73.33, "elapsed_time": "1:42:13", "remaining_time": "0:37:10"}
{"current_steps": 397, "total_steps": 540, "loss": 0.0075, "lr": 1.9883442502904283e-05, "epoch": 3.650574712643678, "percentage": 73.52, "elapsed_time": "1:42:27", "remaining_time": "0:36:54"}
{"current_steps": 398, "total_steps": 540, "loss": 0.0077, "lr": 1.9626073026625818e-05, "epoch": 3.659770114942529, "percentage": 73.7, "elapsed_time": "1:42:42", "remaining_time": "0:36:38"}
{"current_steps": 399, "total_steps": 540, "loss": 0.0062, "lr": 1.936997274033986e-05, "epoch": 3.6689655172413795, "percentage": 73.89, "elapsed_time": "1:42:56", "remaining_time": "0:36:22"}
{"current_steps": 400, "total_steps": 540, "loss": 0.0065, "lr": 1.9115152345327152e-05, "epoch": 3.67816091954023, "percentage": 74.07, "elapsed_time": "1:43:09", "remaining_time": "0:36:06"}
{"current_steps": 400, "total_steps": 540, "eval_loss": 0.011437707580626011, "epoch": 3.67816091954023, "percentage": 74.07, "elapsed_time": "1:43:17", "remaining_time": "0:36:08"}
{"current_steps": 401, "total_steps": 540, "loss": 0.0062, "lr": 1.8861622489387555e-05, "epoch": 3.6873563218390806, "percentage": 74.26, "elapsed_time": "1:43:36", "remaining_time": "0:35:54"}
{"current_steps": 402, "total_steps": 540, "loss": 0.0079, "lr": 1.8609393766395085e-05, "epoch": 3.696551724137931, "percentage": 74.44, "elapsed_time": "1:43:50", "remaining_time": "0:35:38"}
{"current_steps": 403, "total_steps": 540, "loss": 0.0068, "lr": 1.835847671585526e-05, "epoch": 3.7057471264367816, "percentage": 74.63, "elapsed_time": "1:44:04", "remaining_time": "0:35:22"}
{"current_steps": 404, "total_steps": 540, "loss": 0.0066, "lr": 1.8108881822464696e-05, "epoch": 3.714942528735632, "percentage": 74.81, "elapsed_time": "1:44:19", "remaining_time": "0:35:07"}
{"current_steps": 405, "total_steps": 540, "loss": 0.007, "lr": 1.7860619515673033e-05, "epoch": 3.7241379310344827, "percentage": 75.0, "elapsed_time": "1:44:34", "remaining_time": "0:34:51"}
{"current_steps": 405, "total_steps": 540, "eval_loss": 0.011230139061808586, "epoch": 3.7241379310344827, "percentage": 75.0, "elapsed_time": "1:44:42", "remaining_time": "0:34:54"}
{"current_steps": 406, "total_steps": 540, "loss": 0.0078, "lr": 1.7613700169247056e-05, "epoch": 3.7333333333333334, "percentage": 75.19, "elapsed_time": "1:44:54", "remaining_time": "0:34:37"}
{"current_steps": 407, "total_steps": 540, "loss": 0.0077, "lr": 1.7368134100837287e-05, "epoch": 3.7425287356321837, "percentage": 75.37, "elapsed_time": "1:45:07", "remaining_time": "0:34:21"}
{"current_steps": 408, "total_steps": 540, "loss": 0.0073, "lr": 1.7123931571546827e-05, "epoch": 3.7517241379310344, "percentage": 75.56, "elapsed_time": "1:45:20", "remaining_time": "0:34:05"}
{"current_steps": 409, "total_steps": 540, "loss": 0.0081, "lr": 1.6881102785502616e-05, "epoch": 3.760919540229885, "percentage": 75.74, "elapsed_time": "1:45:34", "remaining_time": "0:33:48"}
{"current_steps": 410, "total_steps": 540, "loss": 0.0064, "lr": 1.6639657889429018e-05, "epoch": 3.7701149425287355, "percentage": 75.93, "elapsed_time": "1:45:48", "remaining_time": "0:33:33"}
{"current_steps": 410, "total_steps": 540, "eval_loss": 0.01116408035159111, "epoch": 3.7701149425287355, "percentage": 75.93, "elapsed_time": "1:45:56", "remaining_time": "0:33:35"}
{"current_steps": 411, "total_steps": 540, "loss": 0.0063, "lr": 1.639960697222388e-05, "epoch": 3.779310344827586, "percentage": 76.11, "elapsed_time": "1:46:10", "remaining_time": "0:33:19"}
{"current_steps": 412, "total_steps": 540, "loss": 0.0074, "lr": 1.6160960064536908e-05, "epoch": 3.788505747126437, "percentage": 76.3, "elapsed_time": "1:46:23", "remaining_time": "0:33:03"}
{"current_steps": 413, "total_steps": 540, "loss": 0.0068, "lr": 1.592372713835055e-05, "epoch": 3.7977011494252872, "percentage": 76.48, "elapsed_time": "1:46:37", "remaining_time": "0:32:47"}
{"current_steps": 414, "total_steps": 540, "loss": 0.007, "lr": 1.5687918106563326e-05, "epoch": 3.806896551724138, "percentage": 76.67, "elapsed_time": "1:46:52", "remaining_time": "0:32:31"}
{"current_steps": 415, "total_steps": 540, "loss": 0.0073, "lr": 1.545354282257562e-05, "epoch": 3.8160919540229887, "percentage": 76.85, "elapsed_time": "1:47:05", "remaining_time": "0:32:15"}
{"current_steps": 415, "total_steps": 540, "eval_loss": 0.011113017797470093, "epoch": 3.8160919540229887, "percentage": 76.85, "elapsed_time": "1:47:12", "remaining_time": "0:32:17"}
{"current_steps": 416, "total_steps": 540, "loss": 0.0058, "lr": 1.52206110798779e-05, "epoch": 3.825287356321839, "percentage": 77.04, "elapsed_time": "1:47:24", "remaining_time": "0:32:00"}
{"current_steps": 417, "total_steps": 540, "loss": 0.0071, "lr": 1.4989132611641576e-05, "epoch": 3.8344827586206898, "percentage": 77.22, "elapsed_time": "1:47:37", "remaining_time": "0:31:44"}
{"current_steps": 418, "total_steps": 540, "loss": 0.0061, "lr": 1.4759117090312197e-05, "epoch": 3.84367816091954, "percentage": 77.41, "elapsed_time": "1:47:50", "remaining_time": "0:31:28"}
{"current_steps": 419, "total_steps": 540, "loss": 0.0067, "lr": 1.453057412720536e-05, "epoch": 3.852873563218391, "percentage": 77.59, "elapsed_time": "1:48:04", "remaining_time": "0:31:12"}
{"current_steps": 420, "total_steps": 540, "loss": 0.0065, "lr": 1.4303513272105057e-05, "epoch": 3.862068965517241, "percentage": 77.78, "elapsed_time": "1:48:19", "remaining_time": "0:30:56"}
{"current_steps": 420, "total_steps": 540, "eval_loss": 0.011265527456998825, "epoch": 3.862068965517241, "percentage": 77.78, "elapsed_time": "1:48:26", "remaining_time": "0:30:59"}
{"current_steps": 421, "total_steps": 540, "loss": 0.0072, "lr": 1.4077944012864636e-05, "epoch": 3.871264367816092, "percentage": 77.96, "elapsed_time": "1:48:41", "remaining_time": "0:30:43"}
{"current_steps": 422, "total_steps": 540, "loss": 0.0078, "lr": 1.3853875775010355e-05, "epoch": 3.8804597701149426, "percentage": 78.15, "elapsed_time": "1:48:56", "remaining_time": "0:30:27"}
{"current_steps": 423, "total_steps": 540, "loss": 0.007, "lr": 1.3631317921347563e-05, "epoch": 3.889655172413793, "percentage": 78.33, "elapsed_time": "1:49:10", "remaining_time": "0:30:11"}
{"current_steps": 424, "total_steps": 540, "loss": 0.0066, "lr": 1.3410279751569399e-05, "epoch": 3.8988505747126436, "percentage": 78.52, "elapsed_time": "1:49:22", "remaining_time": "0:29:55"}
{"current_steps": 425, "total_steps": 540, "loss": 0.0069, "lr": 1.3190770501868243e-05, "epoch": 3.9080459770114944, "percentage": 78.7, "elapsed_time": "1:49:36", "remaining_time": "0:29:39"}
{"current_steps": 425, "total_steps": 540, "eval_loss": 0.011119170114398003, "epoch": 3.9080459770114944, "percentage": 78.7, "elapsed_time": "1:49:43", "remaining_time": "0:29:41"}
{"current_steps": 426, "total_steps": 540, "loss": 0.007, "lr": 1.297279934454978e-05, "epoch": 3.9172413793103447, "percentage": 78.89, "elapsed_time": "1:49:56", "remaining_time": "0:29:25"}
{"current_steps": 427, "total_steps": 540, "loss": 0.007, "lr": 1.2756375387649716e-05, "epoch": 3.9264367816091954, "percentage": 79.07, "elapsed_time": "1:50:09", "remaining_time": "0:29:09"}
{"current_steps": 428, "total_steps": 540, "loss": 0.0069, "lr": 1.25415076745532e-05, "epoch": 3.935632183908046, "percentage": 79.26, "elapsed_time": "1:50:21", "remaining_time": "0:28:52"}
{"current_steps": 429, "total_steps": 540, "loss": 0.0064, "lr": 1.2328205183616965e-05, "epoch": 3.9448275862068964, "percentage": 79.44, "elapsed_time": "1:50:36", "remaining_time": "0:28:37"}
{"current_steps": 430, "total_steps": 540, "loss": 0.0065, "lr": 1.2116476827794104e-05, "epoch": 3.954022988505747, "percentage": 79.63, "elapsed_time": "1:50:51", "remaining_time": "0:28:21"}
{"current_steps": 430, "total_steps": 540, "eval_loss": 0.01107843779027462, "epoch": 3.954022988505747, "percentage": 79.63, "elapsed_time": "1:50:58", "remaining_time": "0:28:23"}
{"current_steps": 431, "total_steps": 540, "loss": 0.006, "lr": 1.1906331454261704e-05, "epoch": 3.963218390804598, "percentage": 79.81, "elapsed_time": "1:51:11", "remaining_time": "0:28:07"}
{"current_steps": 432, "total_steps": 540, "loss": 0.0071, "lr": 1.1697777844051105e-05, "epoch": 3.972413793103448, "percentage": 80.0, "elapsed_time": "1:51:24", "remaining_time": "0:27:51"}
{"current_steps": 433, "total_steps": 540, "loss": 0.0068, "lr": 1.1490824711681025e-05, "epoch": 3.981609195402299, "percentage": 80.19, "elapsed_time": "1:51:39", "remaining_time": "0:27:35"}
{"current_steps": 434, "total_steps": 540, "loss": 0.0068, "lr": 1.1285480704793377e-05, "epoch": 3.9908045977011493, "percentage": 80.37, "elapsed_time": "1:51:52", "remaining_time": "0:27:19"}
{"current_steps": 435, "total_steps": 540, "loss": 0.0076, "lr": 1.1081754403791999e-05, "epoch": 4.0, "percentage": 80.56, "elapsed_time": "1:52:07", "remaining_time": "0:27:03"}
{"current_steps": 435, "total_steps": 540, "eval_loss": 0.0111029502004385, "epoch": 4.0, "percentage": 80.56, "elapsed_time": "1:52:14", "remaining_time": "0:27:05"}
{"current_steps": 436, "total_steps": 540, "loss": 0.0051, "lr": 1.0879654321484012e-05, "epoch": 4.00919540229885, "percentage": 80.74, "elapsed_time": "1:52:28", "remaining_time": "0:26:49"}
{"current_steps": 437, "total_steps": 540, "loss": 0.0051, "lr": 1.0679188902724191e-05, "epoch": 4.0183908045977015, "percentage": 80.93, "elapsed_time": "1:52:40", "remaining_time": "0:26:33"}
{"current_steps": 438, "total_steps": 540, "loss": 0.0052, "lr": 1.0480366524062042e-05, "epoch": 4.027586206896552, "percentage": 81.11, "elapsed_time": "1:52:54", "remaining_time": "0:26:17"}
{"current_steps": 439, "total_steps": 540, "loss": 0.006, "lr": 1.0283195493391823e-05, "epoch": 4.036781609195402, "percentage": 81.3, "elapsed_time": "1:53:07", "remaining_time": "0:26:01"}
{"current_steps": 440, "total_steps": 540, "loss": 0.0047, "lr": 1.008768404960535e-05, "epoch": 4.045977011494253, "percentage": 81.48, "elapsed_time": "1:53:21", "remaining_time": "0:25:45"}
{"current_steps": 440, "total_steps": 540, "eval_loss": 0.011515479534864426, "epoch": 4.045977011494253, "percentage": 81.48, "elapsed_time": "1:53:29", "remaining_time": "0:25:47"}
{"current_steps": 441, "total_steps": 540, "loss": 0.0051, "lr": 9.893840362247809e-06, "epoch": 4.055172413793104, "percentage": 81.67, "elapsed_time": "1:53:43", "remaining_time": "0:25:31"}
{"current_steps": 442, "total_steps": 540, "loss": 0.0056, "lr": 9.701672531176286e-06, "epoch": 4.064367816091954, "percentage": 81.85, "elapsed_time": "1:53:57", "remaining_time": "0:25:16"}
{"current_steps": 443, "total_steps": 540, "loss": 0.0056, "lr": 9.511188586221376e-06, "epoch": 4.073563218390804, "percentage": 82.04, "elapsed_time": "1:54:10", "remaining_time": "0:24:59"}
{"current_steps": 444, "total_steps": 540, "loss": 0.0051, "lr": 9.322396486851626e-06, "epoch": 4.082758620689655, "percentage": 82.22, "elapsed_time": "1:54:24", "remaining_time": "0:24:44"}
{"current_steps": 445, "total_steps": 540, "loss": 0.0053, "lr": 9.135304121840976e-06, "epoch": 4.091954022988506, "percentage": 82.41, "elapsed_time": "1:54:36", "remaining_time": "0:24:28"}
{"current_steps": 445, "total_steps": 540, "eval_loss": 0.01191615965217352, "epoch": 4.091954022988506, "percentage": 82.41, "elapsed_time": "1:54:44", "remaining_time": "0:24:29"}
{"current_steps": 446, "total_steps": 540, "loss": 0.0058, "lr": 8.949919308939082e-06, "epoch": 4.101149425287356, "percentage": 82.59, "elapsed_time": "1:54:58", "remaining_time": "0:24:14"}
{"current_steps": 447, "total_steps": 540, "loss": 0.0052, "lr": 8.766249794544662e-06, "epoch": 4.110344827586207, "percentage": 82.78, "elapsed_time": "1:55:12", "remaining_time": "0:23:58"}
{"current_steps": 448, "total_steps": 540, "loss": 0.0057, "lr": 8.584303253381847e-06, "epoch": 4.119540229885057, "percentage": 82.96, "elapsed_time": "1:55:27", "remaining_time": "0:23:42"}
{"current_steps": 449, "total_steps": 540, "loss": 0.0052, "lr": 8.404087288179424e-06, "epoch": 4.128735632183908, "percentage": 83.15, "elapsed_time": "1:55:40", "remaining_time": "0:23:26"}
{"current_steps": 450, "total_steps": 540, "loss": 0.0053, "lr": 8.225609429353187e-06, "epoch": 4.137931034482759, "percentage": 83.33, "elapsed_time": "1:55:54", "remaining_time": "0:23:10"}
{"current_steps": 450, "total_steps": 540, "eval_loss": 0.011974362656474113, "epoch": 4.137931034482759, "percentage": 83.33, "elapsed_time": "1:56:02", "remaining_time": "0:23:12"}
{"current_steps": 451, "total_steps": 540, "loss": 0.0067, "lr": 8.048877134691268e-06, "epoch": 4.147126436781609, "percentage": 83.52, "elapsed_time": "1:56:20", "remaining_time": "0:22:57"}
{"current_steps": 452, "total_steps": 540, "loss": 0.0055, "lr": 7.873897789042523e-06, "epoch": 4.1563218390804595, "percentage": 83.7, "elapsed_time": "1:56:33", "remaining_time": "0:22:41"}
{"current_steps": 453, "total_steps": 540, "loss": 0.0051, "lr": 7.700678704007947e-06, "epoch": 4.165517241379311, "percentage": 83.89, "elapsed_time": "1:56:47", "remaining_time": "0:22:25"}
{"current_steps": 454, "total_steps": 540, "loss": 0.0053, "lr": 7.529227117635135e-06, "epoch": 4.174712643678161, "percentage": 84.07, "elapsed_time": "1:57:02", "remaining_time": "0:22:10"}
{"current_steps": 455, "total_steps": 540, "loss": 0.0055, "lr": 7.35955019411585e-06, "epoch": 4.183908045977011, "percentage": 84.26, "elapsed_time": "1:57:15", "remaining_time": "0:21:54"}
{"current_steps": 455, "total_steps": 540, "eval_loss": 0.01187676191329956, "epoch": 4.183908045977011, "percentage": 84.26, "elapsed_time": "1:57:23", "remaining_time": "0:21:55"}
{"current_steps": 456, "total_steps": 540, "loss": 0.0054, "lr": 7.191655023486682e-06, "epoch": 4.1931034482758625, "percentage": 84.44, "elapsed_time": "1:57:39", "remaining_time": "0:21:40"}
{"current_steps": 457, "total_steps": 540, "loss": 0.0067, "lr": 7.02554862133275e-06, "epoch": 4.202298850574713, "percentage": 84.63, "elapsed_time": "1:57:54", "remaining_time": "0:21:24"}
{"current_steps": 458, "total_steps": 540, "loss": 0.0044, "lr": 6.861237928494579e-06, "epoch": 4.211494252873563, "percentage": 84.81, "elapsed_time": "1:58:07", "remaining_time": "0:21:08"}
{"current_steps": 459, "total_steps": 540, "loss": 0.0053, "lr": 6.698729810778065e-06, "epoch": 4.220689655172414, "percentage": 85.0, "elapsed_time": "1:58:21", "remaining_time": "0:20:53"}
{"current_steps": 460, "total_steps": 540, "loss": 0.0053, "lr": 6.53803105866761e-06, "epoch": 4.2298850574712645, "percentage": 85.19, "elapsed_time": "1:58:35", "remaining_time": "0:20:37"}
{"current_steps": 460, "total_steps": 540, "eval_loss": 0.011668752878904343, "epoch": 4.2298850574712645, "percentage": 85.19, "elapsed_time": "1:58:43", "remaining_time": "0:20:38"}
{"current_steps": 461, "total_steps": 540, "loss": 0.0045, "lr": 6.379148387042316e-06, "epoch": 4.239080459770115, "percentage": 85.37, "elapsed_time": "1:58:56", "remaining_time": "0:20:22"}
{"current_steps": 462, "total_steps": 540, "loss": 0.0045, "lr": 6.222088434895462e-06, "epoch": 4.248275862068965, "percentage": 85.56, "elapsed_time": "1:59:10", "remaining_time": "0:20:07"}
{"current_steps": 463, "total_steps": 540, "loss": 0.0057, "lr": 6.066857765057055e-06, "epoch": 4.257471264367816, "percentage": 85.74, "elapsed_time": "1:59:24", "remaining_time": "0:19:51"}
{"current_steps": 464, "total_steps": 540, "loss": 0.0058, "lr": 5.9134628639196e-06, "epoch": 4.266666666666667, "percentage": 85.93, "elapsed_time": "1:59:36", "remaining_time": "0:19:35"}
{"current_steps": 465, "total_steps": 540, "loss": 0.0053, "lr": 5.7619101411671095e-06, "epoch": 4.275862068965517, "percentage": 86.11, "elapsed_time": "1:59:48", "remaining_time": "0:19:19"}
{"current_steps": 465, "total_steps": 540, "eval_loss": 0.011690051294863224, "epoch": 4.275862068965517, "percentage": 86.11, "elapsed_time": "1:59:56", "remaining_time": "0:19:20"}
{"current_steps": 466, "total_steps": 540, "loss": 0.0055, "lr": 5.6122059295072085e-06, "epoch": 4.285057471264368, "percentage": 86.3, "elapsed_time": "2:00:11", "remaining_time": "0:19:05"}
{"current_steps": 467, "total_steps": 540, "loss": 0.0047, "lr": 5.464356484406535e-06, "epoch": 4.294252873563218, "percentage": 86.48, "elapsed_time": "2:00:24", "remaining_time": "0:18:49"}
{"current_steps": 468, "total_steps": 540, "loss": 0.0061, "lr": 5.318367983829392e-06, "epoch": 4.303448275862069, "percentage": 86.67, "elapsed_time": "2:00:37", "remaining_time": "0:18:33"}
{"current_steps": 469, "total_steps": 540, "loss": 0.005, "lr": 5.174246527979531e-06, "epoch": 4.31264367816092, "percentage": 86.85, "elapsed_time": "2:00:50", "remaining_time": "0:18:17"}
{"current_steps": 470, "total_steps": 540, "loss": 0.0053, "lr": 5.031998139045352e-06, "epoch": 4.32183908045977, "percentage": 87.04, "elapsed_time": "2:01:03", "remaining_time": "0:18:01"}
{"current_steps": 470, "total_steps": 540, "eval_loss": 0.011675745248794556, "epoch": 4.32183908045977, "percentage": 87.04, "elapsed_time": "2:01:11", "remaining_time": "0:18:03"}
{"current_steps": 471, "total_steps": 540, "loss": 0.0047, "lr": 4.891628760948114e-06, "epoch": 4.3310344827586205, "percentage": 87.22, "elapsed_time": "2:01:24", "remaining_time": "0:17:47"}
{"current_steps": 472, "total_steps": 540, "loss": 0.0054, "lr": 4.7531442590937335e-06, "epoch": 4.340229885057472, "percentage": 87.41, "elapsed_time": "2:01:39", "remaining_time": "0:17:31"}
{"current_steps": 473, "total_steps": 540, "loss": 0.0052, "lr": 4.616550420127563e-06, "epoch": 4.349425287356322, "percentage": 87.59, "elapsed_time": "2:01:52", "remaining_time": "0:17:15"}
{"current_steps": 474, "total_steps": 540, "loss": 0.006, "lr": 4.4818529516926726e-06, "epoch": 4.358620689655172, "percentage": 87.78, "elapsed_time": "2:02:06", "remaining_time": "0:17:00"}
{"current_steps": 475, "total_steps": 540, "loss": 0.0058, "lr": 4.349057482191299e-06, "epoch": 4.3678160919540225, "percentage": 87.96, "elapsed_time": "2:02:20", "remaining_time": "0:16:44"}
{"current_steps": 475, "total_steps": 540, "eval_loss": 0.011636043898761272, "epoch": 4.3678160919540225, "percentage": 87.96, "elapsed_time": "2:02:28", "remaining_time": "0:16:45"}
{"current_steps": 476, "total_steps": 540, "loss": 0.0055, "lr": 4.218169560549706e-06, "epoch": 4.377011494252874, "percentage": 88.15, "elapsed_time": "2:02:42", "remaining_time": "0:16:29"}
{"current_steps": 477, "total_steps": 540, "loss": 0.005, "lr": 4.089194655986306e-06, "epoch": 4.386206896551724, "percentage": 88.33, "elapsed_time": "2:02:54", "remaining_time": "0:16:14"}
{"current_steps": 478, "total_steps": 540, "loss": 0.0044, "lr": 3.962138157783085e-06, "epoch": 4.395402298850574, "percentage": 88.52, "elapsed_time": "2:03:08", "remaining_time": "0:15:58"}
{"current_steps": 479, "total_steps": 540, "loss": 0.0049, "lr": 3.837005375060482e-06, "epoch": 4.4045977011494255, "percentage": 88.7, "elapsed_time": "2:03:22", "remaining_time": "0:15:42"}
{"current_steps": 480, "total_steps": 540, "loss": 0.0053, "lr": 3.7138015365554833e-06, "epoch": 4.413793103448276, "percentage": 88.89, "elapsed_time": "2:03:36", "remaining_time": "0:15:27"}
{"current_steps": 480, "total_steps": 540, "eval_loss": 0.011646818369626999, "epoch": 4.413793103448276, "percentage": 88.89, "elapsed_time": "2:03:44", "remaining_time": "0:15:28"}
{"current_steps": 481, "total_steps": 540, "loss": 0.0046, "lr": 3.5925317904031587e-06, "epoch": 4.422988505747126, "percentage": 89.07, "elapsed_time": "2:03:57", "remaining_time": "0:15:12"}
{"current_steps": 482, "total_steps": 540, "loss": 0.0051, "lr": 3.4732012039215776e-06, "epoch": 4.432183908045977, "percentage": 89.26, "elapsed_time": "2:04:12", "remaining_time": "0:14:56"}
{"current_steps": 483, "total_steps": 540, "loss": 0.0051, "lr": 3.3558147633999728e-06, "epoch": 4.441379310344828, "percentage": 89.44, "elapsed_time": "2:04:26", "remaining_time": "0:14:41"}
{"current_steps": 484, "total_steps": 540, "loss": 0.0049, "lr": 3.2403773738905187e-06, "epoch": 4.450574712643678, "percentage": 89.63, "elapsed_time": "2:04:40", "remaining_time": "0:14:25"}
{"current_steps": 485, "total_steps": 540, "loss": 0.0053, "lr": 3.126893859003249e-06, "epoch": 4.459770114942529, "percentage": 89.81, "elapsed_time": "2:04:54", "remaining_time": "0:14:09"}
{"current_steps": 485, "total_steps": 540, "eval_loss": 0.011750674806535244, "epoch": 4.459770114942529, "percentage": 89.81, "elapsed_time": "2:05:02", "remaining_time": "0:14:10"}
{"current_steps": 486, "total_steps": 540, "loss": 0.0051, "lr": 3.0153689607045845e-06, "epoch": 4.468965517241379, "percentage": 90.0, "elapsed_time": "2:05:15", "remaining_time": "0:13:55"}
{"current_steps": 487, "total_steps": 540, "loss": 0.0054, "lr": 2.9058073391191375e-06, "epoch": 4.47816091954023, "percentage": 90.19, "elapsed_time": "2:05:28", "remaining_time": "0:13:39"}
{"current_steps": 488, "total_steps": 540, "loss": 0.0061, "lr": 2.798213572335001e-06, "epoch": 4.487356321839081, "percentage": 90.37, "elapsed_time": "2:05:43", "remaining_time": "0:13:23"}
{"current_steps": 489, "total_steps": 540, "loss": 0.0063, "lr": 2.692592156212487e-06, "epoch": 4.496551724137931, "percentage": 90.56, "elapsed_time": "2:05:58", "remaining_time": "0:13:08"}
{"current_steps": 490, "total_steps": 540, "loss": 0.0051, "lr": 2.5889475041961765e-06, "epoch": 4.505747126436781, "percentage": 90.74, "elapsed_time": "2:06:11", "remaining_time": "0:12:52"}
{"current_steps": 490, "total_steps": 540, "eval_loss": 0.011716877110302448, "epoch": 4.505747126436781, "percentage": 90.74, "elapsed_time": "2:06:19", "remaining_time": "0:12:53"}
{"current_steps": 491, "total_steps": 540, "loss": 0.0052, "lr": 2.4872839471306084e-06, "epoch": 4.514942528735633, "percentage": 90.93, "elapsed_time": "2:06:34", "remaining_time": "0:12:37"}
{"current_steps": 492, "total_steps": 540, "loss": 0.0061, "lr": 2.3876057330792346e-06, "epoch": 4.524137931034483, "percentage": 91.11, "elapsed_time": "2:06:49", "remaining_time": "0:12:22"}
{"current_steps": 493, "total_steps": 540, "loss": 0.0057, "lr": 2.2899170271469428e-06, "epoch": 4.533333333333333, "percentage": 91.3, "elapsed_time": "2:07:02", "remaining_time": "0:12:06"}
{"current_steps": 494, "total_steps": 540, "loss": 0.0045, "lr": 2.1942219113060212e-06, "epoch": 4.5425287356321835, "percentage": 91.48, "elapsed_time": "2:07:16", "remaining_time": "0:11:51"}
{"current_steps": 495, "total_steps": 540, "loss": 0.0053, "lr": 2.100524384225555e-06, "epoch": 4.551724137931035, "percentage": 91.67, "elapsed_time": "2:07:30", "remaining_time": "0:11:35"}
{"current_steps": 495, "total_steps": 540, "eval_loss": 0.011710132472217083, "epoch": 4.551724137931035, "percentage": 91.67, "elapsed_time": "2:07:38", "remaining_time": "0:11:36"}
{"current_steps": 496, "total_steps": 540, "loss": 0.005, "lr": 2.0088283611044036e-06, "epoch": 4.560919540229885, "percentage": 91.85, "elapsed_time": "2:07:52", "remaining_time": "0:11:20"}
{"current_steps": 497, "total_steps": 540, "loss": 0.0051, "lr": 1.9191376735075427e-06, "epoch": 4.570114942528735, "percentage": 92.04, "elapsed_time": "2:08:07", "remaining_time": "0:11:05"}
{"current_steps": 498, "total_steps": 540, "loss": 0.0051, "lr": 1.8314560692059835e-06, "epoch": 4.5793103448275865, "percentage": 92.22, "elapsed_time": "2:08:20", "remaining_time": "0:10:49"}
{"current_steps": 499, "total_steps": 540, "loss": 0.0049, "lr": 1.7457872120201779e-06, "epoch": 4.588505747126437, "percentage": 92.41, "elapsed_time": "2:08:35", "remaining_time": "0:10:33"}
{"current_steps": 500, "total_steps": 540, "loss": 0.0059, "lr": 1.6621346816668992e-06, "epoch": 4.597701149425287, "percentage": 92.59, "elapsed_time": "2:08:48", "remaining_time": "0:10:18"}
{"current_steps": 500, "total_steps": 540, "eval_loss": 0.01169579103589058, "epoch": 4.597701149425287, "percentage": 92.59, "elapsed_time": "2:08:56", "remaining_time": "0:10:18"}
{"current_steps": 501, "total_steps": 540, "loss": 0.0058, "lr": 1.5805019736097104e-06, "epoch": 4.606896551724138, "percentage": 92.78, "elapsed_time": "2:09:16", "remaining_time": "0:10:03"}
{"current_steps": 502, "total_steps": 540, "loss": 0.0058, "lr": 1.5008924989128258e-06, "epoch": 4.6160919540229886, "percentage": 92.96, "elapsed_time": "2:09:30", "remaining_time": "0:09:48"}
{"current_steps": 503, "total_steps": 540, "loss": 0.0055, "lr": 1.4233095840986753e-06, "epoch": 4.625287356321839, "percentage": 93.15, "elapsed_time": "2:09:43", "remaining_time": "0:09:32"}
{"current_steps": 504, "total_steps": 540, "loss": 0.0049, "lr": 1.3477564710088098e-06, "epoch": 4.63448275862069, "percentage": 93.33, "elapsed_time": "2:09:57", "remaining_time": "0:09:16"}
{"current_steps": 505, "total_steps": 540, "loss": 0.0055, "lr": 1.2742363166685034e-06, "epoch": 4.64367816091954, "percentage": 93.52, "elapsed_time": "2:10:11", "remaining_time": "0:09:01"}
{"current_steps": 505, "total_steps": 540, "eval_loss": 0.011671243235468864, "epoch": 4.64367816091954, "percentage": 93.52, "elapsed_time": "2:10:18", "remaining_time": "0:09:01"}
{"current_steps": 506, "total_steps": 540, "loss": 0.0045, "lr": 1.2027521931548214e-06, "epoch": 4.652873563218391, "percentage": 93.7, "elapsed_time": "2:10:32", "remaining_time": "0:08:46"}
{"current_steps": 507, "total_steps": 540, "loss": 0.0055, "lr": 1.1333070874682216e-06, "epoch": 4.662068965517241, "percentage": 93.89, "elapsed_time": "2:10:46", "remaining_time": "0:08:30"}
{"current_steps": 508, "total_steps": 540, "loss": 0.0046, "lr": 1.0659039014077944e-06, "epoch": 4.671264367816092, "percentage": 94.07, "elapsed_time": "2:10:59", "remaining_time": "0:08:15"}
{"current_steps": 509, "total_steps": 540, "loss": 0.0055, "lr": 1.0005454514499414e-06, "epoch": 4.680459770114942, "percentage": 94.26, "elapsed_time": "2:11:11", "remaining_time": "0:07:59"}
{"current_steps": 510, "total_steps": 540, "loss": 0.0054, "lr": 9.372344686307655e-07, "epoch": 4.689655172413794, "percentage": 94.44, "elapsed_time": "2:11:26", "remaining_time": "0:07:43"}
{"current_steps": 510, "total_steps": 540, "eval_loss": 0.011643964797258377, "epoch": 4.689655172413794, "percentage": 94.44, "elapsed_time": "2:11:34", "remaining_time": "0:07:44"}
{"current_steps": 511, "total_steps": 540, "loss": 0.0057, "lr": 8.759735984318895e-07, "epoch": 4.698850574712644, "percentage": 94.63, "elapsed_time": "2:11:46", "remaining_time": "0:07:28"}
{"current_steps": 512, "total_steps": 540, "loss": 0.0054, "lr": 8.167654006699443e-07, "epoch": 4.708045977011494, "percentage": 94.81, "elapsed_time": "2:12:00", "remaining_time": "0:07:13"}
{"current_steps": 513, "total_steps": 540, "loss": 0.0059, "lr": 7.596123493895991e-07, "epoch": 4.7172413793103445, "percentage": 95.0, "elapsed_time": "2:12:16", "remaining_time": "0:06:57"}
{"current_steps": 514, "total_steps": 540, "loss": 0.0062, "lr": 7.04516832760177e-07, "epoch": 4.726436781609196, "percentage": 95.19, "elapsed_time": "2:12:30", "remaining_time": "0:06:42"}
{"current_steps": 515, "total_steps": 540, "loss": 0.0055, "lr": 6.514811529758747e-07, "epoch": 4.735632183908046, "percentage": 95.37, "elapsed_time": "2:12:43", "remaining_time": "0:06:26"}
{"current_steps": 515, "total_steps": 540, "eval_loss": 0.011669199913740158, "epoch": 4.735632183908046, "percentage": 95.37, "elapsed_time": "2:12:51", "remaining_time": "0:06:26"}
{"current_steps": 516, "total_steps": 540, "loss": 0.0053, "lr": 6.005075261595494e-07, "epoch": 4.744827586206896, "percentage": 95.56, "elapsed_time": "2:13:05", "remaining_time": "0:06:11"}
{"current_steps": 517, "total_steps": 540, "loss": 0.0055, "lr": 5.515980822701439e-07, "epoch": 4.7540229885057474, "percentage": 95.74, "elapsed_time": "2:13:18", "remaining_time": "0:05:55"}
{"current_steps": 518, "total_steps": 540, "loss": 0.0053, "lr": 5.047548650136513e-07, "epoch": 4.763218390804598, "percentage": 95.93, "elapsed_time": "2:13:32", "remaining_time": "0:05:40"}
{"current_steps": 519, "total_steps": 540, "loss": 0.0054, "lr": 4.5997983175773417e-07, "epoch": 4.772413793103448, "percentage": 96.11, "elapsed_time": "2:13:44", "remaining_time": "0:05:24"}
{"current_steps": 520, "total_steps": 540, "loss": 0.0056, "lr": 4.1727485344994486e-07, "epoch": 4.781609195402299, "percentage": 96.3, "elapsed_time": "2:13:57", "remaining_time": "0:05:09"}
{"current_steps": 520, "total_steps": 540, "eval_loss": 0.01162272784858942, "epoch": 4.781609195402299, "percentage": 96.3, "elapsed_time": "2:14:05", "remaining_time": "0:05:09"}
{"current_steps": 521, "total_steps": 540, "loss": 0.0049, "lr": 3.766417145395218e-07, "epoch": 4.7908045977011495, "percentage": 96.48, "elapsed_time": "2:14:20", "remaining_time": "0:04:53"}
{"current_steps": 522, "total_steps": 540, "loss": 0.0055, "lr": 3.380821129028489e-07, "epoch": 4.8, "percentage": 96.67, "elapsed_time": "2:14:33", "remaining_time": "0:04:38"}
{"current_steps": 523, "total_steps": 540, "loss": 0.0057, "lr": 3.0159765977250673e-07, "epoch": 4.809195402298851, "percentage": 96.85, "elapsed_time": "2:14:46", "remaining_time": "0:04:22"}
{"current_steps": 524, "total_steps": 540, "loss": 0.005, "lr": 2.671898796699268e-07, "epoch": 4.818390804597701, "percentage": 97.04, "elapsed_time": "2:14:59", "remaining_time": "0:04:07"}
{"current_steps": 525, "total_steps": 540, "loss": 0.0048, "lr": 2.3486021034170857e-07, "epoch": 4.827586206896552, "percentage": 97.22, "elapsed_time": "2:15:12", "remaining_time": "0:03:51"}
{"current_steps": 525, "total_steps": 540, "eval_loss": 0.011633777059614658, "epoch": 4.827586206896552, "percentage": 97.22, "elapsed_time": "2:15:20", "remaining_time": "0:03:52"}
{"current_steps": 526, "total_steps": 540, "loss": 0.0061, "lr": 2.0461000269953456e-07, "epoch": 4.836781609195402, "percentage": 97.41, "elapsed_time": "2:15:34", "remaining_time": "0:03:36"}
{"current_steps": 527, "total_steps": 540, "loss": 0.0054, "lr": 1.7644052076371542e-07, "epoch": 4.845977011494253, "percentage": 97.59, "elapsed_time": "2:15:49", "remaining_time": "0:03:21"}
{"current_steps": 528, "total_steps": 540, "loss": 0.0048, "lr": 1.503529416103988e-07, "epoch": 4.855172413793103, "percentage": 97.78, "elapsed_time": "2:16:04", "remaining_time": "0:03:05"}
{"current_steps": 529, "total_steps": 540, "loss": 0.0053, "lr": 1.2634835532233657e-07, "epoch": 4.864367816091954, "percentage": 97.96, "elapsed_time": "2:16:16", "remaining_time": "0:02:50"}
{"current_steps": 530, "total_steps": 540, "loss": 0.0049, "lr": 1.044277649433989e-07, "epoch": 4.873563218390805, "percentage": 98.15, "elapsed_time": "2:16:31", "remaining_time": "0:02:34"}
{"current_steps": 530, "total_steps": 540, "eval_loss": 0.01163394283503294, "epoch": 4.873563218390805, "percentage": 98.15, "elapsed_time": "2:16:39", "remaining_time": "0:02:34"}
{"current_steps": 531, "total_steps": 540, "loss": 0.0047, "lr": 8.459208643659122e-08, "epoch": 4.882758620689655, "percentage": 98.33, "elapsed_time": "2:16:52", "remaining_time": "0:02:19"}
{"current_steps": 532, "total_steps": 540, "loss": 0.0048, "lr": 6.684214864584038e-08, "epoch": 4.8919540229885055, "percentage": 98.52, "elapsed_time": "2:17:07", "remaining_time": "0:02:03"}
{"current_steps": 533, "total_steps": 540, "loss": 0.005, "lr": 5.11786932613223e-08, "epoch": 4.901149425287357, "percentage": 98.7, "elapsed_time": "2:17:20", "remaining_time": "0:01:48"}
{"current_steps": 534, "total_steps": 540, "loss": 0.0044, "lr": 3.760237478849793e-08, "epoch": 4.910344827586207, "percentage": 98.89, "elapsed_time": "2:17:33", "remaining_time": "0:01:32"}
{"current_steps": 535, "total_steps": 540, "loss": 0.0043, "lr": 2.6113760520735108e-08, "epoch": 4.919540229885057, "percentage": 99.07, "elapsed_time": "2:17:48", "remaining_time": "0:01:17"}
{"current_steps": 535, "total_steps": 540, "eval_loss": 0.011621917597949505, "epoch": 4.919540229885057, "percentage": 99.07, "elapsed_time": "2:17:56", "remaining_time": "0:01:17"}
{"current_steps": 536, "total_steps": 540, "loss": 0.0054, "lr": 1.6713330515627513e-08, "epoch": 4.928735632183908, "percentage": 99.26, "elapsed_time": "2:18:09", "remaining_time": "0:01:01"}
{"current_steps": 537, "total_steps": 540, "loss": 0.0048, "lr": 9.401477574932926e-09, "epoch": 4.937931034482759, "percentage": 99.44, "elapsed_time": "2:18:23", "remaining_time": "0:00:46"}
{"current_steps": 538, "total_steps": 540, "loss": 0.0051, "lr": 4.178507228136397e-09, "epoch": 4.947126436781609, "percentage": 99.63, "elapsed_time": "2:18:35", "remaining_time": "0:00:30"}
{"current_steps": 539, "total_steps": 540, "loss": 0.0048, "lr": 1.0446377197104173e-09, "epoch": 4.956321839080459, "percentage": 99.81, "elapsed_time": "2:18:49", "remaining_time": "0:00:15"}
{"current_steps": 540, "total_steps": 540, "loss": 0.0046, "lr": 0.0, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "2:19:02", "remaining_time": "0:00:00"}
{"current_steps": 540, "total_steps": 540, "eval_loss": 0.011626788415014744, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "2:19:10", "remaining_time": "0:00:00"}
{"current_steps": 540, "total_steps": 540, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "2:19:19", "remaining_time": "0:00:00"}