| {"current_steps": 10, "total_steps": 1500, "loss": 1.0007, "accuracy": 0.36250001192092896, "learning_rate": 4.999451708687114e-06, "epoch": 0.012698412698412698, "percentage": 0.67, "elapsed_time": "0:01:19", "remaining_time": "3:17:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9984, "accuracy": 0.26249998807907104, "learning_rate": 4.997807075247147e-06, "epoch": 0.025396825396825397, "percentage": 1.33, "elapsed_time": "0:02:33", "remaining_time": "3:09:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9991, "accuracy": 0.2874999940395355, "learning_rate": 4.9950668210706795e-06, "epoch": 0.0380952380952381, "percentage": 2.0, "elapsed_time": "0:03:47", "remaining_time": "3:06:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9849, "accuracy": 0.36250001192092896, "learning_rate": 4.9912321481237616e-06, "epoch": 0.050793650793650794, "percentage": 2.67, "elapsed_time": "0:05:00", "remaining_time": "3:02:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9991, "accuracy": 0.3499999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.06349206349206349, "percentage": 3.33, "elapsed_time": "0:06:16", "remaining_time": "3:01:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9846106171607971, "epoch": 0.06349206349206349, "percentage": 3.33, "elapsed_time": "0:06:34", "remaining_time": "3:10:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 1.0063, "accuracy": 0.22499999403953552, "learning_rate": 4.980286753286196e-06, "epoch": 0.0761904761904762, "percentage": 4.0, "elapsed_time": "0:08:01", "remaining_time": "3:12:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9888, "accuracy": 0.3499999940395355, "learning_rate": 4.973180832407471e-06, "epoch": 0.08888888888888889, "percentage": 4.67, "elapsed_time": "0:09:18", "remaining_time": "3:10:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9926, "accuracy": 0.3375000059604645, "learning_rate": 4.964990092676263e-06, "epoch": 0.10158730158730159, "percentage": 5.33, "elapsed_time": "0:10:33", "remaining_time": "3:07:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9812, "accuracy": 0.22499999403953552, "learning_rate": 4.9557181268217225e-06, "epoch": 0.11428571428571428, "percentage": 6.0, "elapsed_time": "0:11:49", "remaining_time": "3:05:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.981, "accuracy": 0.2750000059604645, "learning_rate": 4.9453690018345144e-06, "epoch": 0.12698412698412698, "percentage": 6.67, "elapsed_time": "0:13:05", "remaining_time": "3:03:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9764130115509033, "epoch": 0.12698412698412698, "percentage": 6.67, "elapsed_time": "0:13:23", "remaining_time": "3:07:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.9859, "accuracy": 0.4124999940395355, "learning_rate": 4.933947257182901e-06, "epoch": 0.13968253968253969, "percentage": 7.33, "elapsed_time": "0:14:53", "remaining_time": "3:08:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9827, "accuracy": 0.375, "learning_rate": 4.921457902821578e-06, "epoch": 0.1523809523809524, "percentage": 8.0, "elapsed_time": "0:16:10", "remaining_time": "3:06:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9743, "accuracy": 0.48750001192092896, "learning_rate": 4.907906416994146e-06, "epoch": 0.16507936507936508, "percentage": 8.67, "elapsed_time": "0:17:28", "remaining_time": "3:04:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9824, "accuracy": 0.36250001192092896, "learning_rate": 4.893298743830168e-06, "epoch": 0.17777777777777778, "percentage": 9.33, "elapsed_time": "0:18:45", "remaining_time": "3:02:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9727, "accuracy": 0.5, "learning_rate": 4.8776412907378845e-06, "epoch": 0.19047619047619047, "percentage": 10.0, "elapsed_time": "0:20:01", "remaining_time": "3:00:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9540849328041077, "epoch": 0.19047619047619047, "percentage": 10.0, "elapsed_time": "0:20:20", "remaining_time": "3:03:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9517, "accuracy": 0.5249999761581421, "learning_rate": 4.860940925593703e-06, "epoch": 0.20317460317460317, "percentage": 10.67, "elapsed_time": "0:21:55", "remaining_time": "3:03:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.9439, "accuracy": 0.5, "learning_rate": 4.84320497372973e-06, "epoch": 0.21587301587301588, "percentage": 11.33, "elapsed_time": "0:23:12", "remaining_time": "3:01:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.9369, "accuracy": 0.38749998807907104, "learning_rate": 4.824441214720629e-06, "epoch": 0.22857142857142856, "percentage": 12.0, "elapsed_time": "0:24:28", "remaining_time": "2:59:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9443, "accuracy": 0.38749998807907104, "learning_rate": 4.804657878971252e-06, "epoch": 0.24126984126984127, "percentage": 12.67, "elapsed_time": "0:25:45", "remaining_time": "2:57:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.9034, "accuracy": 0.48750001192092896, "learning_rate": 4.783863644106502e-06, "epoch": 0.25396825396825395, "percentage": 13.33, "elapsed_time": "0:27:00", "remaining_time": "2:55:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.9075753092765808, "epoch": 0.25396825396825395, "percentage": 13.33, "elapsed_time": "0:27:18", "remaining_time": "2:57:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.9085, "accuracy": 0.637499988079071, "learning_rate": 4.762067631165049e-06, "epoch": 0.26666666666666666, "percentage": 14.0, "elapsed_time": "0:28:50", "remaining_time": "2:57:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.9188, "accuracy": 0.44999998807907104, "learning_rate": 4.7392794005985324e-06, "epoch": 0.27936507936507937, "percentage": 14.67, "elapsed_time": "0:30:11", "remaining_time": "2:55:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.9015, "accuracy": 0.5375000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.2920634920634921, "percentage": 15.33, "elapsed_time": "0:31:25", "remaining_time": "2:53:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.8814, "accuracy": 0.512499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.3047619047619048, "percentage": 16.0, "elapsed_time": "0:32:41", "remaining_time": "2:51:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.8478, "accuracy": 0.512499988079071, "learning_rate": 4.665063509461098e-06, "epoch": 0.31746031746031744, "percentage": 16.67, "elapsed_time": "0:33:56", "remaining_time": "2:49:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7700436115264893, "epoch": 0.31746031746031744, "percentage": 16.67, "elapsed_time": "0:34:14", "remaining_time": "2:51:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.795, "accuracy": 0.5375000238418579, "learning_rate": 4.638410650401267e-06, "epoch": 0.33015873015873015, "percentage": 17.33, "elapsed_time": "0:35:42", "remaining_time": "2:50:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7644, "accuracy": 0.5249999761581421, "learning_rate": 4.610819813755038e-06, "epoch": 0.34285714285714286, "percentage": 18.0, "elapsed_time": "0:36:58", "remaining_time": "2:48:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7671, "accuracy": 0.48750001192092896, "learning_rate": 4.582303101775249e-06, "epoch": 0.35555555555555557, "percentage": 18.67, "elapsed_time": "0:38:14", "remaining_time": "2:46:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.7922, "accuracy": 0.6000000238418579, "learning_rate": 4.55287302283426e-06, "epoch": 0.3682539682539683, "percentage": 19.33, "elapsed_time": "0:39:36", "remaining_time": "2:45:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.7506, "accuracy": 0.48750001192092896, "learning_rate": 4.522542485937369e-06, "epoch": 0.38095238095238093, "percentage": 20.0, "elapsed_time": "0:40:49", "remaining_time": "2:43:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.7391816973686218, "epoch": 0.38095238095238093, "percentage": 20.0, "elapsed_time": "0:41:07", "remaining_time": "2:44:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.7134, "accuracy": 0.550000011920929, "learning_rate": 4.491324795060491e-06, "epoch": 0.39365079365079364, "percentage": 20.67, "elapsed_time": "0:42:28", "remaining_time": "2:43:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.74, "accuracy": 0.5375000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.40634920634920635, "percentage": 21.33, "elapsed_time": "0:43:48", "remaining_time": "2:41:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.7408, "accuracy": 0.6499999761581421, "learning_rate": 4.426283106939474e-06, "epoch": 0.41904761904761906, "percentage": 22.0, "elapsed_time": "0:45:01", "remaining_time": "2:39:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.7501, "accuracy": 0.7124999761581421, "learning_rate": 4.3924876391293915e-06, "epoch": 0.43174603174603177, "percentage": 22.67, "elapsed_time": "0:46:20", "remaining_time": "2:38:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.7405, "accuracy": 0.699999988079071, "learning_rate": 4.357862063693486e-06, "epoch": 0.4444444444444444, "percentage": 23.33, "elapsed_time": "0:47:33", "remaining_time": "2:36:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.6953701972961426, "epoch": 0.4444444444444444, "percentage": 23.33, "elapsed_time": "0:47:52", "remaining_time": "2:37:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.702, "accuracy": 0.7124999761581421, "learning_rate": 4.322421568553529e-06, "epoch": 0.45714285714285713, "percentage": 24.0, "elapsed_time": "0:49:22", "remaining_time": "2:36:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.6781, "accuracy": 0.800000011920929, "learning_rate": 4.286181699082008e-06, "epoch": 0.46984126984126984, "percentage": 24.67, "elapsed_time": "0:50:36", "remaining_time": "2:34:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.6033, "accuracy": 0.7749999761581421, "learning_rate": 4.249158351283414e-06, "epoch": 0.48253968253968255, "percentage": 25.33, "elapsed_time": "0:51:55", "remaining_time": "2:33:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.5698, "accuracy": 0.949999988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.49523809523809526, "percentage": 26.0, "elapsed_time": "0:53:08", "remaining_time": "2:31:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.5869, "accuracy": 0.875, "learning_rate": 4.172826515897146e-06, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:23", "remaining_time": "2:29:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.5232856273651123, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:41", "remaining_time": "2:30:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.5774, "accuracy": 0.887499988079071, "learning_rate": 4.133551509975264e-06, "epoch": 0.5206349206349207, "percentage": 27.33, "elapsed_time": "0:56:13", "remaining_time": "2:29:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.5084, "accuracy": 0.862500011920929, "learning_rate": 4.093559974371725e-06, "epoch": 0.5333333333333333, "percentage": 28.0, "elapsed_time": "0:57:31", "remaining_time": "2:27:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.5233, "accuracy": 0.875, "learning_rate": 4.052869450695776e-06, "epoch": 0.546031746031746, "percentage": 28.67, "elapsed_time": "0:58:48", "remaining_time": "2:26:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.5272, "accuracy": 0.824999988079071, "learning_rate": 4.011497787155938e-06, "epoch": 0.5587301587301587, "percentage": 29.33, "elapsed_time": "1:00:01", "remaining_time": "2:24:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.5717, "accuracy": 0.800000011920929, "learning_rate": 3.969463130731183e-06, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:22", "remaining_time": "2:23:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.4568406939506531, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:40", "remaining_time": "2:23:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.4803, "accuracy": 0.887499988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.5841269841269842, "percentage": 30.67, "elapsed_time": "1:03:19", "remaining_time": "2:23:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.4733, "accuracy": 0.9125000238418579, "learning_rate": 3.88347887310836e-06, "epoch": 0.5968253968253968, "percentage": 31.33, "elapsed_time": "1:04:39", "remaining_time": "2:21:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.5048, "accuracy": 0.9125000238418579, "learning_rate": 3.839566987447492e-06, "epoch": 0.6095238095238096, "percentage": 32.0, "elapsed_time": "1:05:58", "remaining_time": "2:20:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.4728, "accuracy": 0.949999988079071, "learning_rate": 3.795067523432826e-06, "epoch": 0.6222222222222222, "percentage": 32.67, "elapsed_time": "1:07:15", "remaining_time": "2:18:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.4296, "accuracy": 0.9125000238418579, "learning_rate": 3.7500000000000005e-06, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:27", "remaining_time": "2:16:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.4266711175441742, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:46", "remaining_time": "2:17:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.4981, "accuracy": 0.875, "learning_rate": 3.7043841852542884e-06, "epoch": 0.6476190476190476, "percentage": 34.0, "elapsed_time": "1:10:17", "remaining_time": "2:16:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.4736, "accuracy": 0.8374999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.6603174603174603, "percentage": 34.67, "elapsed_time": "1:11:30", "remaining_time": "2:14:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.502, "accuracy": 0.887499988079071, "learning_rate": 3.611587947962319e-06, "epoch": 0.6730158730158731, "percentage": 35.33, "elapsed_time": "1:12:49", "remaining_time": "2:13:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.44, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.6857142857142857, "percentage": 36.0, "elapsed_time": "1:14:01", "remaining_time": "2:11:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.4751, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:21", "remaining_time": "2:10:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.3922204077243805, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:39", "remaining_time": "2:10:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 560, "total_steps": 1500, "loss": 0.4127, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.7111111111111111, "percentage": 37.33, "elapsed_time": "1:17:08", "remaining_time": "2:09:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 570, "total_steps": 1500, "loss": 0.4436, "accuracy": 0.9375, "learning_rate": 3.4203113817116955e-06, "epoch": 0.7238095238095238, "percentage": 38.0, "elapsed_time": "1:18:25", "remaining_time": "2:07:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 580, "total_steps": 1500, "loss": 0.411, "accuracy": 0.9624999761581421, "learning_rate": 3.3714301183045382e-06, "epoch": 0.7365079365079366, "percentage": 38.67, "elapsed_time": "1:19:42", "remaining_time": "2:06:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 590, "total_steps": 1500, "loss": 0.4297, "accuracy": 0.8500000238418579, "learning_rate": 3.3221666168464584e-06, "epoch": 0.7492063492063492, "percentage": 39.33, "elapsed_time": "1:21:00", "remaining_time": "2:04:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "loss": 0.4537, "accuracy": 0.9125000238418579, "learning_rate": 3.272542485937369e-06, "epoch": 0.7619047619047619, "percentage": 40.0, "elapsed_time": "1:22:22", "remaining_time": "2:03:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.368425577878952, "epoch": 0.7619047619047619, "percentage": 40.0, "elapsed_time": "1:22:40", "remaining_time": "2:04:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 610, "total_steps": 1500, "loss": 0.4315, "accuracy": 0.862500011920929, "learning_rate": 3.222579492361179e-06, "epoch": 0.7746031746031746, "percentage": 40.67, "elapsed_time": "1:24:08", "remaining_time": "2:02:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 620, "total_steps": 1500, "loss": 0.4161, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.7873015873015873, "percentage": 41.33, "elapsed_time": "1:25:25", "remaining_time": "2:01:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 630, "total_steps": 1500, "loss": 0.3621, "accuracy": 0.925000011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.8, "percentage": 42.0, "elapsed_time": "1:26:41", "remaining_time": "1:59:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 640, "total_steps": 1500, "loss": 0.4325, "accuracy": 0.8999999761581421, "learning_rate": 3.0708771752766397e-06, "epoch": 0.8126984126984127, "percentage": 42.67, "elapsed_time": "1:27:56", "remaining_time": "1:58:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "loss": 0.4376, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.8253968253968254, "percentage": 43.33, "elapsed_time": "1:29:11", "remaining_time": "1:56:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.3507956266403198, "epoch": 0.8253968253968254, "percentage": 43.33, "elapsed_time": "1:29:29", "remaining_time": "1:57:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 660, "total_steps": 1500, "loss": 0.381, "accuracy": 0.8999999761581421, "learning_rate": 2.9684532864643123e-06, "epoch": 0.8380952380952381, "percentage": 44.0, "elapsed_time": "1:30:54", "remaining_time": "1:55:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 670, "total_steps": 1500, "loss": 0.4385, "accuracy": 0.8500000238418579, "learning_rate": 2.9169218667902562e-06, "epoch": 0.8507936507936508, "percentage": 44.67, "elapsed_time": "1:32:10", "remaining_time": "1:54:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 680, "total_steps": 1500, "loss": 0.3879, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.8634920634920635, "percentage": 45.33, "elapsed_time": "1:33:29", "remaining_time": "1:52:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 690, "total_steps": 1500, "loss": 0.3451, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.8761904761904762, "percentage": 46.0, "elapsed_time": "1:34:43", "remaining_time": "1:51:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "loss": 0.4094, "accuracy": 0.8500000238418579, "learning_rate": 2.761321158169134e-06, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:35:57", "remaining_time": "1:49:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 700, "total_steps": 1500, "eval_loss": 0.33448922634124756, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:36:15", "remaining_time": "1:50:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 710, "total_steps": 1500, "loss": 0.3604, "accuracy": 0.925000011920929, "learning_rate": 2.70919460833079e-06, "epoch": 0.9015873015873016, "percentage": 47.33, "elapsed_time": "1:37:45", "remaining_time": "1:48:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 720, "total_steps": 1500, "loss": 0.3682, "accuracy": 0.9375, "learning_rate": 2.6569762988232838e-06, "epoch": 0.9142857142857143, "percentage": 48.0, "elapsed_time": "1:38:59", "remaining_time": "1:47:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 730, "total_steps": 1500, "loss": 0.3886, "accuracy": 0.8500000238418579, "learning_rate": 2.604689134322999e-06, "epoch": 0.926984126984127, "percentage": 48.67, "elapsed_time": "1:40:12", "remaining_time": "1:45:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 740, "total_steps": 1500, "loss": 0.3548, "accuracy": 0.9125000238418579, "learning_rate": 2.5523560497083927e-06, "epoch": 0.9396825396825397, "percentage": 49.33, "elapsed_time": "1:41:30", "remaining_time": "1:44:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "loss": 0.3706, "accuracy": 0.925000011920929, "learning_rate": 2.5e-06, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:42:48", "remaining_time": "1:42:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.31834185123443604, "epoch": 0.9523809523809523, "percentage": 50.0, "elapsed_time": "1:43:06", "remaining_time": "1:43:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 760, "total_steps": 1500, "loss": 0.3938, "accuracy": 0.8999999761581421, "learning_rate": 2.447643950291608e-06, "epoch": 0.9650793650793651, "percentage": 50.67, "elapsed_time": "1:44:37", "remaining_time": "1:41:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 770, "total_steps": 1500, "loss": 0.3744, "accuracy": 0.887499988079071, "learning_rate": 2.3953108656770018e-06, "epoch": 0.9777777777777777, "percentage": 51.33, "elapsed_time": "1:45:55", "remaining_time": "1:40:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 780, "total_steps": 1500, "loss": 0.3914, "accuracy": 0.925000011920929, "learning_rate": 2.3430237011767166e-06, "epoch": 0.9904761904761905, "percentage": 52.0, "elapsed_time": "1:47:10", "remaining_time": "1:38:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 790, "total_steps": 1500, "loss": 0.3467, "accuracy": 0.8947368264198303, "learning_rate": 2.290805391669212e-06, "epoch": 1.0025396825396826, "percentage": 52.67, "elapsed_time": "1:48:24", "remaining_time": "1:37:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "loss": 0.3404, "accuracy": 0.9125000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 1.0152380952380953, "percentage": 53.33, "elapsed_time": "1:49:42", "remaining_time": "1:35:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.30234017968177795, "epoch": 1.0152380952380953, "percentage": 53.33, "elapsed_time": "1:50:00", "remaining_time": "1:36:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 810, "total_steps": 1500, "loss": 0.3517, "accuracy": 0.8999999761581421, "learning_rate": 2.186666916089239e-06, "epoch": 1.027936507936508, "percentage": 54.0, "elapsed_time": "1:51:39", "remaining_time": "1:35:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 820, "total_steps": 1500, "loss": 0.3525, "accuracy": 0.8999999761581421, "learning_rate": 2.134792428593971e-06, "epoch": 1.0406349206349206, "percentage": 54.67, "elapsed_time": "1:52:54", "remaining_time": "1:33:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 830, "total_steps": 1500, "loss": 0.3423, "accuracy": 0.9125000238418579, "learning_rate": 2.0830781332097446e-06, "epoch": 1.0533333333333332, "percentage": 55.33, "elapsed_time": "1:54:08", "remaining_time": "1:32:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 840, "total_steps": 1500, "loss": 0.327, "accuracy": 0.9375, "learning_rate": 2.031546713535688e-06, "epoch": 1.066031746031746, "percentage": 56.0, "elapsed_time": "1:55:26", "remaining_time": "1:30:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "loss": 0.3587, "accuracy": 0.875, "learning_rate": 1.9802207729556023e-06, "epoch": 1.0787301587301588, "percentage": 56.67, "elapsed_time": "1:56:43", "remaining_time": "1:29:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2958359122276306, "epoch": 1.0787301587301588, "percentage": 56.67, "elapsed_time": "1:57:01", "remaining_time": "1:29:29", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 860, "total_steps": 1500, "loss": 0.3297, "accuracy": 0.875, "learning_rate": 1.9291228247233607e-06, "epoch": 1.0914285714285714, "percentage": 57.33, "elapsed_time": "1:58:34", "remaining_time": "1:28:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 870, "total_steps": 1500, "loss": 0.339, "accuracy": 0.9125000238418579, "learning_rate": 1.8782752820878636e-06, "epoch": 1.104126984126984, "percentage": 58.0, "elapsed_time": "1:59:51", "remaining_time": "1:26:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 880, "total_steps": 1500, "loss": 0.304, "accuracy": 0.925000011920929, "learning_rate": 1.827700448461836e-06, "epoch": 1.116825396825397, "percentage": 58.67, "elapsed_time": "2:01:05", "remaining_time": "1:25:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 890, "total_steps": 1500, "loss": 0.3124, "accuracy": 0.8999999761581421, "learning_rate": 1.7774205076388207e-06, "epoch": 1.1295238095238096, "percentage": 59.33, "elapsed_time": "2:02:20", "remaining_time": "1:23:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "loss": 0.3122, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 1.1422222222222222, "percentage": 60.0, "elapsed_time": "2:03:41", "remaining_time": "1:22:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.28521302342414856, "epoch": 1.1422222222222222, "percentage": 60.0, "elapsed_time": "2:03:59", "remaining_time": "1:22:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 910, "total_steps": 1500, "loss": 0.3277, "accuracy": 0.875, "learning_rate": 1.677833383153542e-06, "epoch": 1.154920634920635, "percentage": 60.67, "elapsed_time": "2:05:30", "remaining_time": "1:21:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 920, "total_steps": 1500, "loss": 0.3212, "accuracy": 0.9375, "learning_rate": 1.6285698816954626e-06, "epoch": 1.1676190476190476, "percentage": 61.33, "elapsed_time": "2:06:51", "remaining_time": "1:19:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 930, "total_steps": 1500, "loss": 0.3472, "accuracy": 0.925000011920929, "learning_rate": 1.5796886182883053e-06, "epoch": 1.1803174603174602, "percentage": 62.0, "elapsed_time": "2:08:10", "remaining_time": "1:18:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 940, "total_steps": 1500, "loss": 0.3193, "accuracy": 0.8999999761581421, "learning_rate": 1.5312110338697427e-06, "epoch": 1.193015873015873, "percentage": 62.67, "elapsed_time": "2:09:29", "remaining_time": "1:17:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "loss": 0.3267, "accuracy": 0.8999999761581421, "learning_rate": 1.4831583923105e-06, "epoch": 1.2057142857142857, "percentage": 63.33, "elapsed_time": "2:10:47", "remaining_time": "1:15:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 950, "total_steps": 1500, "eval_loss": 0.27200350165367126, "epoch": 1.2057142857142857, "percentage": 63.33, "elapsed_time": "2:11:05", "remaining_time": "1:15:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 960, "total_steps": 1500, "loss": 0.3554, "accuracy": 0.949999988079071, "learning_rate": 1.4355517710873184e-06, "epoch": 1.2184126984126984, "percentage": 64.0, "elapsed_time": "2:12:35", "remaining_time": "1:14:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 970, "total_steps": 1500, "loss": 0.2867, "accuracy": 0.925000011920929, "learning_rate": 1.388412052037682e-06, "epoch": 1.231111111111111, "percentage": 64.67, "elapsed_time": "2:13:52", "remaining_time": "1:13:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 980, "total_steps": 1500, "loss": 0.3064, "accuracy": 0.949999988079071, "learning_rate": 1.3417599122003464e-06, "epoch": 1.243809523809524, "percentage": 65.33, "elapsed_time": "2:15:13", "remaining_time": "1:11:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 990, "total_steps": 1500, "loss": 0.3079, "accuracy": 0.8999999761581421, "learning_rate": 1.2956158147457116e-06, "epoch": 1.2565079365079366, "percentage": 66.0, "elapsed_time": "2:16:30", "remaining_time": "1:10:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "loss": 0.3158, "accuracy": 0.9125000238418579, "learning_rate": 1.2500000000000007e-06, "epoch": 1.2692063492063492, "percentage": 66.67, "elapsed_time": "2:17:44", "remaining_time": "1:08:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.26795223355293274, "epoch": 1.2692063492063492, "percentage": 66.67, "elapsed_time": "2:18:02", "remaining_time": "1:09:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1010, "total_steps": 1500, "loss": 0.3142, "accuracy": 0.875, "learning_rate": 1.204932476567175e-06, "epoch": 1.2819047619047619, "percentage": 67.33, "elapsed_time": "2:19:26", "remaining_time": "1:07:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1020, "total_steps": 1500, "loss": 0.3226, "accuracy": 0.925000011920929, "learning_rate": 1.160433012552508e-06, "epoch": 1.2946031746031745, "percentage": 68.0, "elapsed_time": "2:20:42", "remaining_time": "1:06:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1030, "total_steps": 1500, "loss": 0.2998, "accuracy": 0.875, "learning_rate": 1.11652112689164e-06, "epoch": 1.3073015873015872, "percentage": 68.67, "elapsed_time": "2:21:58", "remaining_time": "1:04:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1040, "total_steps": 1500, "loss": 0.2691, "accuracy": 0.9624999761581421, "learning_rate": 1.073216080788921e-06, "epoch": 1.32, "percentage": 69.33, "elapsed_time": "2:23:10", "remaining_time": "1:03:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "loss": 0.3026, "accuracy": 0.9125000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 1.3326984126984127, "percentage": 70.0, "elapsed_time": "2:24:30", "remaining_time": "1:01:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.26340675354003906, "epoch": 1.3326984126984127, "percentage": 70.0, "elapsed_time": "2:24:48", "remaining_time": "1:02:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1060, "total_steps": 1500, "loss": 0.2872, "accuracy": 0.9375, "learning_rate": 9.88502212844063e-07, "epoch": 1.3453968253968254, "percentage": 70.67, "elapsed_time": "2:26:12", "remaining_time": "1:00:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1070, "total_steps": 1500, "loss": 0.2794, "accuracy": 0.925000011920929, "learning_rate": 9.471305493042243e-07, "epoch": 1.358095238095238, "percentage": 71.33, "elapsed_time": "2:27:24", "remaining_time": "0:59:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1080, "total_steps": 1500, "loss": 0.3154, "accuracy": 0.949999988079071, "learning_rate": 9.064400256282757e-07, "epoch": 1.370793650793651, "percentage": 72.0, "elapsed_time": "2:28:41", "remaining_time": "0:57:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1090, "total_steps": 1500, "loss": 0.3541, "accuracy": 0.8999999761581421, "learning_rate": 8.664484900247363e-07, "epoch": 1.3834920634920636, "percentage": 72.67, "elapsed_time": "2:29:59", "remaining_time": "0:56:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "loss": 0.3048, "accuracy": 0.925000011920929, "learning_rate": 8.271734841028553e-07, "epoch": 1.3961904761904762, "percentage": 73.33, "elapsed_time": "2:31:17", "remaining_time": "0:55:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2575596570968628, "epoch": 1.3961904761904762, "percentage": 73.33, "elapsed_time": "2:31:36", "remaining_time": "0:55:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1110, "total_steps": 1500, "loss": 0.2757, "accuracy": 0.949999988079071, "learning_rate": 7.886322351782782e-07, "epoch": 1.4088888888888889, "percentage": 74.0, "elapsed_time": "2:33:00", "remaining_time": "0:53:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1120, "total_steps": 1500, "loss": 0.2697, "accuracy": 0.9375, "learning_rate": 7.508416487165862e-07, "epoch": 1.4215873015873015, "percentage": 74.67, "elapsed_time": "2:34:16", "remaining_time": "0:52:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1130, "total_steps": 1500, "loss": 0.2766, "accuracy": 0.949999988079071, "learning_rate": 7.138183009179922e-07, "epoch": 1.4342857142857142, "percentage": 75.33, "elapsed_time": "2:35:33", "remaining_time": "0:50:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1140, "total_steps": 1500, "loss": 0.2988, "accuracy": 0.887499988079071, "learning_rate": 6.775784314464717e-07, "epoch": 1.446984126984127, "percentage": 76.0, "elapsed_time": "2:36:49", "remaining_time": "0:49:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "loss": 0.2704, "accuracy": 0.9125000238418579, "learning_rate": 6.421379363065142e-07, "epoch": 1.4596825396825397, "percentage": 76.67, "elapsed_time": "2:38:06", "remaining_time": "0:48:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.25360986590385437, "epoch": 1.4596825396825397, "percentage": 76.67, "elapsed_time": "2:38:25", "remaining_time": "0:48:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1160, "total_steps": 1500, "loss": 0.2829, "accuracy": 0.9375, "learning_rate": 6.075123608706093e-07, "epoch": 1.4723809523809523, "percentage": 77.33, "elapsed_time": "2:39:57", "remaining_time": "0:46:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1170, "total_steps": 1500, "loss": 0.2573, "accuracy": 0.9375, "learning_rate": 5.737168930605272e-07, "epoch": 1.485079365079365, "percentage": 78.0, "elapsed_time": "2:41:11", "remaining_time": "0:45:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1180, "total_steps": 1500, "loss": 0.3046, "accuracy": 0.949999988079071, "learning_rate": 5.407663566854008e-07, "epoch": 1.4977777777777779, "percentage": 78.67, "elapsed_time": "2:42:28", "remaining_time": "0:44:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1190, "total_steps": 1500, "loss": 0.2863, "accuracy": 0.9375, "learning_rate": 5.086752049395094e-07, "epoch": 1.5104761904761905, "percentage": 79.33, "elapsed_time": "2:43:43", "remaining_time": "0:42:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "loss": 0.274, "accuracy": 0.9750000238418579, "learning_rate": 4.774575140626317e-07, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:04", "remaining_time": "0:41:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.25126969814300537, "epoch": 1.5231746031746032, "percentage": 80.0, "elapsed_time": "2:45:22", "remaining_time": "0:41:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1210, "total_steps": 1500, "loss": 0.2878, "accuracy": 0.9375, "learning_rate": 4.4712697716573994e-07, "epoch": 1.5358730158730158, "percentage": 80.67, "elapsed_time": "2:46:58", "remaining_time": "0:40:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1220, "total_steps": 1500, "loss": 0.2557, "accuracy": 0.8999999761581421, "learning_rate": 4.1769689822475147e-07, "epoch": 1.5485714285714285, "percentage": 81.33, "elapsed_time": "2:48:12", "remaining_time": "0:38:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1230, "total_steps": 1500, "loss": 0.2745, "accuracy": 0.925000011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.5612698412698411, "percentage": 82.0, "elapsed_time": "2:49:29", "remaining_time": "0:37:12", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1240, "total_steps": 1500, "loss": 0.3246, "accuracy": 0.8500000238418579, "learning_rate": 3.615893495987335e-07, "epoch": 1.573968253968254, "percentage": 82.67, "elapsed_time": "2:50:45", "remaining_time": "0:35:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "loss": 0.2725, "accuracy": 0.925000011920929, "learning_rate": 3.3493649053890325e-07, "epoch": 1.5866666666666667, "percentage": 83.33, "elapsed_time": "2:52:01", "remaining_time": "0:34:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.24976640939712524, "epoch": 1.5866666666666667, "percentage": 83.33, "elapsed_time": "2:52:19", "remaining_time": "0:34:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1260, "total_steps": 1500, "loss": 0.3262, "accuracy": 0.887499988079071, "learning_rate": 3.092332998903416e-07, "epoch": 1.5993650793650793, "percentage": 84.0, "elapsed_time": "2:53:43", "remaining_time": "0:33:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1270, "total_steps": 1500, "loss": 0.2437, "accuracy": 0.9375, "learning_rate": 2.844910519219632e-07, "epoch": 1.6120634920634922, "percentage": 84.67, "elapsed_time": "2:54:57", "remaining_time": "0:31:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1280, "total_steps": 1500, "loss": 0.2734, "accuracy": 0.9624999761581421, "learning_rate": 2.6072059940146775e-07, "epoch": 1.6247619047619049, "percentage": 85.33, "elapsed_time": "2:56:19", "remaining_time": "0:30:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1290, "total_steps": 1500, "loss": 0.3296, "accuracy": 0.925000011920929, "learning_rate": 2.3793236883495164e-07, "epoch": 1.6374603174603175, "percentage": 86.0, "elapsed_time": "2:57:37", "remaining_time": "0:28:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "loss": 0.281, "accuracy": 0.949999988079071, "learning_rate": 2.1613635589349756e-07, "epoch": 1.6501587301587302, "percentage": 86.67, "elapsed_time": "2:58:54", "remaining_time": "0:27:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.24929529428482056, "epoch": 1.6501587301587302, "percentage": 86.67, "elapsed_time": "2:59:12", "remaining_time": "0:27:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1310, "total_steps": 1500, "loss": 0.2824, "accuracy": 0.8500000238418579, "learning_rate": 1.95342121028749e-07, "epoch": 1.6628571428571428, "percentage": 87.33, "elapsed_time": "3:00:28", "remaining_time": "0:26:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1320, "total_steps": 1500, "loss": 0.2907, "accuracy": 0.9125000238418579, "learning_rate": 1.7555878527937164e-07, "epoch": 1.6755555555555555, "percentage": 88.0, "elapsed_time": "3:01:44", "remaining_time": "0:24:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1330, "total_steps": 1500, "loss": 0.2625, "accuracy": 0.987500011920929, "learning_rate": 1.567950262702714e-07, "epoch": 1.6882539682539681, "percentage": 88.67, "elapsed_time": "3:03:04", "remaining_time": "0:23:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1340, "total_steps": 1500, "loss": 0.2956, "accuracy": 0.9375, "learning_rate": 1.3905907440629752e-07, "epoch": 1.700952380952381, "percentage": 89.33, "elapsed_time": "3:04:19", "remaining_time": "0:22:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "loss": 0.2695, "accuracy": 0.9750000238418579, "learning_rate": 1.223587092621162e-07, "epoch": 1.7136507936507936, "percentage": 90.0, "elapsed_time": "3:05:30", "remaining_time": "0:20:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.24551495909690857, "epoch": 1.7136507936507936, "percentage": 90.0, "elapsed_time": "3:05:48", "remaining_time": "0:20:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1360, "total_steps": 1500, "loss": 0.2805, "accuracy": 0.9125000238418579, "learning_rate": 1.067012561698319e-07, "epoch": 1.7263492063492063, "percentage": 90.67, "elapsed_time": "3:07:08", "remaining_time": "0:19:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1370, "total_steps": 1500, "loss": 0.3012, "accuracy": 0.9125000238418579, "learning_rate": 9.209358300585474e-08, "epoch": 1.7390476190476192, "percentage": 91.33, "elapsed_time": "3:08:26", "remaining_time": "0:17:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1380, "total_steps": 1500, "loss": 0.3039, "accuracy": 0.9375, "learning_rate": 7.854209717842231e-08, "epoch": 1.7517460317460318, "percentage": 92.0, "elapsed_time": "3:09:45", "remaining_time": "0:16:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1390, "total_steps": 1500, "loss": 0.3194, "accuracy": 0.8999999761581421, "learning_rate": 6.605274281709929e-08, "epoch": 1.7644444444444445, "percentage": 92.67, "elapsed_time": "3:11:04", "remaining_time": "0:15:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "loss": 0.2854, "accuracy": 0.8999999761581421, "learning_rate": 5.463099816548578e-08, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:19", "remaining_time": "0:13:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1400, "total_steps": 1500, "eval_loss": 0.24849724769592285, "epoch": 1.7771428571428571, "percentage": 93.33, "elapsed_time": "3:12:37", "remaining_time": "0:13:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1410, "total_steps": 1500, "loss": 0.2838, "accuracy": 0.887499988079071, "learning_rate": 4.428187317827848e-08, "epoch": 1.7898412698412698, "percentage": 94.0, "elapsed_time": "3:14:13", "remaining_time": "0:12:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1420, "total_steps": 1500, "loss": 0.2815, "accuracy": 0.925000011920929, "learning_rate": 3.5009907323737826e-08, "epoch": 1.8025396825396824, "percentage": 94.67, "elapsed_time": "3:15:29", "remaining_time": "0:11:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1430, "total_steps": 1500, "loss": 0.3363, "accuracy": 0.925000011920929, "learning_rate": 2.681916759252917e-08, "epoch": 1.815238095238095, "percentage": 95.33, "elapsed_time": "3:16:44", "remaining_time": "0:09:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1440, "total_steps": 1500, "loss": 0.2786, "accuracy": 0.949999988079071, "learning_rate": 1.9713246713805588e-08, "epoch": 1.827936507936508, "percentage": 96.0, "elapsed_time": "3:18:01", "remaining_time": "0:08:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "loss": 0.2848, "accuracy": 0.925000011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.8406349206349206, "percentage": 96.67, "elapsed_time": "3:19:15", "remaining_time": "0:06:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.24686568975448608, "epoch": 1.8406349206349206, "percentage": 96.67, "elapsed_time": "3:19:34", "remaining_time": "0:06:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1460, "total_steps": 1500, "loss": 0.3048, "accuracy": 0.925000011920929, "learning_rate": 8.767851876239075e-09, "epoch": 1.8533333333333335, "percentage": 97.33, "elapsed_time": "3:21:11", "remaining_time": "0:05:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1470, "total_steps": 1500, "loss": 0.3174, "accuracy": 0.9125000238418579, "learning_rate": 4.933178929321103e-09, "epoch": 1.8660317460317462, "percentage": 98.0, "elapsed_time": "3:22:27", "remaining_time": "0:04:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1480, "total_steps": 1500, "loss": 0.3188, "accuracy": 0.925000011920929, "learning_rate": 2.192924752854042e-09, "epoch": 1.8787301587301588, "percentage": 98.67, "elapsed_time": "3:23:41", "remaining_time": "0:02:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1490, "total_steps": 1500, "loss": 0.3129, "accuracy": 0.925000011920929, "learning_rate": 5.48291312886251e-10, "epoch": 1.8914285714285715, "percentage": 99.33, "elapsed_time": "3:24:54", "remaining_time": "0:01:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "loss": 0.2783, "accuracy": 0.925000011920929, "learning_rate": 0.0, "epoch": 1.9041269841269841, "percentage": 100.0, "elapsed_time": "3:26:10", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.24844756722450256, "epoch": 1.9041269841269841, "percentage": 100.0, "elapsed_time": "3:26:28", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 1500, "total_steps": 1500, "epoch": 1.9041269841269841, "percentage": 100.0, "elapsed_time": "3:26:35", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |