| {"current_steps": 10, "total_steps": 1500, "loss": 0.9981, "accuracy": 0.3499999940395355, "learning_rate": 4.999451708687114e-06, "epoch": 0.012698412698412698, "percentage": 0.67, "elapsed_time": "0:01:19", "remaining_time": "3:17:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9967, "accuracy": 0.26249998807907104, "learning_rate": 4.997807075247147e-06, "epoch": 0.025396825396825397, "percentage": 1.33, "elapsed_time": "0:02:37", "remaining_time": "3:14:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9988, "accuracy": 0.3125, "learning_rate": 4.9950668210706795e-06, "epoch": 0.0380952380952381, "percentage": 2.0, "elapsed_time": "0:03:57", "remaining_time": "3:14:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.9841, "accuracy": 0.375, "learning_rate": 4.9912321481237616e-06, "epoch": 0.050793650793650794, "percentage": 2.67, "elapsed_time": "0:05:17", "remaining_time": "3:13:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.9953, "accuracy": 0.3499999940395355, "learning_rate": 4.986304738420684e-06, "epoch": 0.06349206349206349, "percentage": 3.33, "elapsed_time": "0:06:37", "remaining_time": "3:12:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9914231300354004, "epoch": 0.06349206349206349, "percentage": 3.33, "elapsed_time": "0:06:56", "remaining_time": "3:21:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 1.0022, "accuracy": 0.25, "learning_rate": 4.980286753286196e-06, "epoch": 0.0761904761904762, "percentage": 4.0, "elapsed_time": "0:08:22", "remaining_time": "3:20:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9849, "accuracy": 0.4000000059604645, "learning_rate": 4.973180832407471e-06, "epoch": 0.08888888888888889, "percentage": 4.67, "elapsed_time": "0:09:37", "remaining_time": "3:16:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9886, "accuracy": 0.3125, "learning_rate": 4.964990092676263e-06, "epoch": 0.10158730158730159, "percentage": 5.33, "elapsed_time": "0:10:51", "remaining_time": "3:12:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.981, "accuracy": 0.2750000059604645, "learning_rate": 4.9557181268217225e-06, "epoch": 0.11428571428571428, "percentage": 6.0, "elapsed_time": "0:12:11", "remaining_time": "3:11:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9883, "accuracy": 0.2750000059604645, "learning_rate": 4.9453690018345144e-06, "epoch": 0.12698412698412698, "percentage": 6.67, "elapsed_time": "0:13:28", "remaining_time": "3:08:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9836427569389343, "epoch": 0.12698412698412698, "percentage": 6.67, "elapsed_time": "0:13:47", "remaining_time": "3:13:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.9852, "accuracy": 0.4124999940395355, "learning_rate": 4.933947257182901e-06, "epoch": 0.13968253968253969, "percentage": 7.33, "elapsed_time": "0:15:08", "remaining_time": "3:11:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9839, "accuracy": 0.38749998807907104, "learning_rate": 4.921457902821578e-06, "epoch": 0.1523809523809524, "percentage": 8.0, "elapsed_time": "0:16:25", "remaining_time": "3:08:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9737, "accuracy": 0.4749999940395355, "learning_rate": 4.907906416994146e-06, "epoch": 0.16507936507936508, "percentage": 8.67, "elapsed_time": "0:17:44", "remaining_time": "3:07:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9804, "accuracy": 0.375, "learning_rate": 4.893298743830168e-06, "epoch": 0.17777777777777778, "percentage": 9.33, "elapsed_time": "0:19:04", "remaining_time": "3:05:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9728, "accuracy": 0.4749999940395355, "learning_rate": 4.8776412907378845e-06, "epoch": 0.19047619047619047, "percentage": 10.0, "elapsed_time": "0:20:22", "remaining_time": "3:03:20", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9609583616256714, "epoch": 0.19047619047619047, "percentage": 10.0, "elapsed_time": "0:20:40", "remaining_time": "3:06:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.9531, "accuracy": 0.5249999761581421, "learning_rate": 4.860940925593703e-06, "epoch": 0.20317460317460317, "percentage": 10.67, "elapsed_time": "0:22:07", "remaining_time": "3:05:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.9386, "accuracy": 0.5, "learning_rate": 4.84320497372973e-06, "epoch": 0.21587301587301588, "percentage": 11.33, "elapsed_time": "0:23:23", "remaining_time": "3:03:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.9313, "accuracy": 0.4124999940395355, "learning_rate": 4.824441214720629e-06, "epoch": 0.22857142857142856, "percentage": 12.0, "elapsed_time": "0:24:39", "remaining_time": "3:00:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.9406, "accuracy": 0.375, "learning_rate": 4.804657878971252e-06, "epoch": 0.24126984126984127, "percentage": 12.67, "elapsed_time": "0:25:57", "remaining_time": "2:59:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.9031, "accuracy": 0.4749999940395355, "learning_rate": 4.783863644106502e-06, "epoch": 0.25396825396825395, "percentage": 13.33, "elapsed_time": "0:27:13", "remaining_time": "2:56:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.9153187274932861, "epoch": 0.25396825396825395, "percentage": 13.33, "elapsed_time": "0:27:32", "remaining_time": "2:58:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8977, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.26666666666666666, "percentage": 14.0, "elapsed_time": "0:28:56", "remaining_time": "2:57:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.9074, "accuracy": 0.42500001192092896, "learning_rate": 4.7392794005985324e-06, "epoch": 0.27936507936507937, "percentage": 14.67, "elapsed_time": "0:30:14", "remaining_time": "2:55:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.896, "accuracy": 0.512499988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.2920634920634921, "percentage": 15.33, "elapsed_time": "0:31:29", "remaining_time": "2:53:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.891, "accuracy": 0.512499988079071, "learning_rate": 4.690766700109659e-06, "epoch": 0.3047619047619048, "percentage": 16.0, "elapsed_time": "0:32:46", "remaining_time": "2:52:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.8621, "accuracy": 0.5, "learning_rate": 4.665063509461098e-06, "epoch": 0.31746031746031744, "percentage": 16.67, "elapsed_time": "0:34:03", "remaining_time": "2:50:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7948001623153687, "epoch": 0.31746031746031744, "percentage": 16.67, "elapsed_time": "0:34:22", "remaining_time": "2:51:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.7939, "accuracy": 0.5375000238418579, "learning_rate": 4.638410650401267e-06, "epoch": 0.33015873015873015, "percentage": 17.33, "elapsed_time": "0:35:48", "remaining_time": "2:50:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.7635, "accuracy": 0.5375000238418579, "learning_rate": 4.610819813755038e-06, "epoch": 0.34285714285714286, "percentage": 18.0, "elapsed_time": "0:37:04", "remaining_time": "2:48:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.7678, "accuracy": 0.48750001192092896, "learning_rate": 4.582303101775249e-06, "epoch": 0.35555555555555557, "percentage": 18.67, "elapsed_time": "0:38:19", "remaining_time": "2:46:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.7719, "accuracy": 0.5874999761581421, "learning_rate": 4.55287302283426e-06, "epoch": 0.3682539682539683, "percentage": 19.33, "elapsed_time": "0:39:42", "remaining_time": "2:45:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.7644, "accuracy": 0.4749999940395355, "learning_rate": 4.522542485937369e-06, "epoch": 0.38095238095238093, "percentage": 20.0, "elapsed_time": "0:40:54", "remaining_time": "2:43:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.7514793872833252, "epoch": 0.38095238095238093, "percentage": 20.0, "elapsed_time": "0:41:13", "remaining_time": "2:44:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.7092, "accuracy": 0.5249999761581421, "learning_rate": 4.491324795060491e-06, "epoch": 0.39365079365079364, "percentage": 20.67, "elapsed_time": "0:42:37", "remaining_time": "2:43:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.7364, "accuracy": 0.512499988079071, "learning_rate": 4.4592336433146e-06, "epoch": 0.40634920634920635, "percentage": 21.33, "elapsed_time": "0:43:58", "remaining_time": "2:42:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.748, "accuracy": 0.612500011920929, "learning_rate": 4.426283106939474e-06, "epoch": 0.41904761904761906, "percentage": 22.0, "elapsed_time": "0:45:12", "remaining_time": "2:40:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.7516, "accuracy": 0.612500011920929, "learning_rate": 4.3924876391293915e-06, "epoch": 0.43174603174603177, "percentage": 22.67, "elapsed_time": "0:46:29", "remaining_time": "2:38:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.7497, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.4444444444444444, "percentage": 23.33, "elapsed_time": "0:47:42", "remaining_time": "2:36:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.7238383889198303, "epoch": 0.4444444444444444, "percentage": 23.33, "elapsed_time": "0:48:01", "remaining_time": "2:37:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.7241, "accuracy": 0.7124999761581421, "learning_rate": 4.322421568553529e-06, "epoch": 0.45714285714285713, "percentage": 24.0, "elapsed_time": "0:49:23", "remaining_time": "2:36:23", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.7141, "accuracy": 0.75, "learning_rate": 4.286181699082008e-06, "epoch": 0.46984126984126984, "percentage": 24.67, "elapsed_time": "0:50:38", "remaining_time": "2:34:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.6654, "accuracy": 0.699999988079071, "learning_rate": 4.249158351283414e-06, "epoch": 0.48253968253968255, "percentage": 25.33, "elapsed_time": "0:51:54", "remaining_time": "2:32:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.6301, "accuracy": 0.8374999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.49523809523809526, "percentage": 26.0, "elapsed_time": "0:53:08", "remaining_time": "2:31:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.6274, "accuracy": 0.800000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:28", "remaining_time": "2:29:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.590033233165741, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:47", "remaining_time": "2:30:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.6309, "accuracy": 0.8125, "learning_rate": 4.133551509975264e-06, "epoch": 0.5206349206349207, "percentage": 27.33, "elapsed_time": "0:56:11", "remaining_time": "2:29:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.5839, "accuracy": 0.824999988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.5333333333333333, "percentage": 28.0, "elapsed_time": "0:57:29", "remaining_time": "2:27:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.5266, "accuracy": 0.875, "learning_rate": 4.052869450695776e-06, "epoch": 0.546031746031746, "percentage": 28.67, "elapsed_time": "0:58:45", "remaining_time": "2:26:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.5665, "accuracy": 0.8500000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.5587301587301587, "percentage": 29.33, "elapsed_time": "1:00:04", "remaining_time": "2:24:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.5118, "accuracy": 0.824999988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:23", "remaining_time": "2:23:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.5201926827430725, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.4783, "accuracy": 0.875, "learning_rate": 3.92678391921108e-06, "epoch": 0.5841269841269842, "percentage": 30.67, "elapsed_time": "1:03:08", "remaining_time": "2:22:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.534, "accuracy": 0.875, "learning_rate": 3.88347887310836e-06, "epoch": 0.5968253968253968, "percentage": 31.33, "elapsed_time": "1:04:27", "remaining_time": "2:21:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.4829, "accuracy": 0.925000011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.6095238095238096, "percentage": 32.0, "elapsed_time": "1:05:47", "remaining_time": "2:19:47", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.4437, "accuracy": 0.949999988079071, "learning_rate": 3.795067523432826e-06, "epoch": 0.6222222222222222, "percentage": 32.67, "elapsed_time": "1:07:02", "remaining_time": "2:18:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.4411, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:17", "remaining_time": "2:16:34", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.4819534122943878, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:35", "remaining_time": "2:17:11", "throughput": "0.00", "total_tokens": 0} | |