c1_math_0d_16s_1k / trainer_log.jsonl
ryanmarten's picture
Upload model
dacc396 verified
{"current_steps": 1, "total_steps": 70, "loss": 0.8233, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:48", "remaining_time": "0:55:57"}
{"current_steps": 2, "total_steps": 70, "loss": 0.8304, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:27", "remaining_time": "0:49:23"}
{"current_steps": 3, "total_steps": 70, "loss": 0.7657, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:02:05", "remaining_time": "0:46:32"}
{"current_steps": 4, "total_steps": 70, "loss": 0.7137, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:41", "remaining_time": "0:44:17"}
{"current_steps": 5, "total_steps": 70, "loss": 0.7344, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:03:17", "remaining_time": "0:42:42"}
{"current_steps": 6, "total_steps": 70, "loss": 0.7425, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:03:55", "remaining_time": "0:41:54"}
{"current_steps": 7, "total_steps": 70, "loss": 0.6917, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:04:34", "remaining_time": "0:41:11"}
{"current_steps": 8, "total_steps": 70, "loss": 0.6805, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:05:12", "remaining_time": "0:40:25"}
{"current_steps": 9, "total_steps": 70, "loss": 0.6464, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:05:51", "remaining_time": "0:39:39"}
{"current_steps": 10, "total_steps": 70, "loss": 0.6255, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:06:27", "remaining_time": "0:38:46"}
{"current_steps": 11, "total_steps": 70, "loss": 0.9136, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:07:24", "remaining_time": "0:39:46"}
{"current_steps": 12, "total_steps": 70, "loss": 0.5967, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:08:02", "remaining_time": "0:38:50"}
{"current_steps": 13, "total_steps": 70, "loss": 0.5809, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:08:39", "remaining_time": "0:37:57"}
{"current_steps": 14, "total_steps": 70, "loss": 0.5452, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:09:17", "remaining_time": "0:37:11"}
{"current_steps": 15, "total_steps": 70, "loss": 0.5676, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:09:54", "remaining_time": "0:36:21"}
{"current_steps": 16, "total_steps": 70, "loss": 0.5428, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:10:32", "remaining_time": "0:35:34"}
{"current_steps": 17, "total_steps": 70, "loss": 0.5498, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:11:10", "remaining_time": "0:34:50"}
{"current_steps": 18, "total_steps": 70, "loss": 0.5303, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:11:46", "remaining_time": "0:34:01"}
{"current_steps": 19, "total_steps": 70, "loss": 0.5367, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:12:25", "remaining_time": "0:33:22"}
{"current_steps": 20, "total_steps": 70, "loss": 0.5313, "lr": 1.7971325072229227e-05, "epoch": 1.9047619047619047, "percentage": 28.57, "elapsed_time": "0:13:00", "remaining_time": "0:32:32"}
{"current_steps": 21, "total_steps": 70, "loss": 0.7569, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:13:37", "remaining_time": "0:31:48"}
{"current_steps": 22, "total_steps": 70, "loss": 0.4821, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:14:31", "remaining_time": "0:31:42"}
{"current_steps": 23, "total_steps": 70, "loss": 0.4765, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:15:09", "remaining_time": "0:30:59"}
{"current_steps": 24, "total_steps": 70, "loss": 0.4771, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:15:47", "remaining_time": "0:30:15"}
{"current_steps": 25, "total_steps": 70, "loss": 0.4765, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:16:25", "remaining_time": "0:29:33"}
{"current_steps": 26, "total_steps": 70, "loss": 0.491, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:17:04", "remaining_time": "0:28:53"}
{"current_steps": 27, "total_steps": 70, "loss": 0.4672, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:17:40", "remaining_time": "0:28:09"}
{"current_steps": 28, "total_steps": 70, "loss": 0.4672, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:18:17", "remaining_time": "0:27:25"}
{"current_steps": 29, "total_steps": 70, "loss": 0.4643, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:18:53", "remaining_time": "0:26:42"}
{"current_steps": 30, "total_steps": 70, "loss": 0.4584, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:19:31", "remaining_time": "0:26:01"}
{"current_steps": 31, "total_steps": 70, "loss": 0.4644, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:20:06", "remaining_time": "0:25:18"}
{"current_steps": 32, "total_steps": 70, "loss": 0.684, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:20:56", "remaining_time": "0:24:52"}
{"current_steps": 33, "total_steps": 70, "loss": 0.4266, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:21:32", "remaining_time": "0:24:08"}
{"current_steps": 34, "total_steps": 70, "loss": 0.431, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:22:09", "remaining_time": "0:23:27"}
{"current_steps": 35, "total_steps": 70, "loss": 0.4191, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:22:47", "remaining_time": "0:22:47"}
{"current_steps": 36, "total_steps": 70, "loss": 0.4497, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:23:27", "remaining_time": "0:22:09"}
{"current_steps": 37, "total_steps": 70, "loss": 0.3956, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:24:02", "remaining_time": "0:21:26"}
{"current_steps": 38, "total_steps": 70, "loss": 0.4056, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:24:39", "remaining_time": "0:20:45"}
{"current_steps": 39, "total_steps": 70, "loss": 0.4245, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:25:18", "remaining_time": "0:20:07"}
{"current_steps": 40, "total_steps": 70, "loss": 0.4401, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:25:56", "remaining_time": "0:19:27"}
{"current_steps": 41, "total_steps": 70, "loss": 0.4108, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:26:32", "remaining_time": "0:18:46"}
{"current_steps": 42, "total_steps": 70, "loss": 0.595, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:27:07", "remaining_time": "0:18:05"}
{"current_steps": 43, "total_steps": 70, "loss": 0.4106, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:28:02", "remaining_time": "0:17:36"}
{"current_steps": 44, "total_steps": 70, "loss": 0.3898, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:28:39", "remaining_time": "0:16:56"}
{"current_steps": 45, "total_steps": 70, "loss": 0.3785, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:29:16", "remaining_time": "0:16:15"}
{"current_steps": 46, "total_steps": 70, "loss": 0.3839, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:29:54", "remaining_time": "0:15:36"}
{"current_steps": 47, "total_steps": 70, "loss": 0.3769, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:30:29", "remaining_time": "0:14:55"}
{"current_steps": 48, "total_steps": 70, "loss": 0.4029, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:31:07", "remaining_time": "0:14:16"}
{"current_steps": 49, "total_steps": 70, "loss": 0.3745, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:31:46", "remaining_time": "0:13:37"}
{"current_steps": 50, "total_steps": 70, "loss": 0.3697, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:32:22", "remaining_time": "0:12:57"}
{"current_steps": 51, "total_steps": 70, "loss": 0.3759, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:32:59", "remaining_time": "0:12:17"}
{"current_steps": 52, "total_steps": 70, "loss": 0.3842, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:33:38", "remaining_time": "0:11:38"}
{"current_steps": 53, "total_steps": 70, "loss": 0.56, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:34:33", "remaining_time": "0:11:05"}
{"current_steps": 54, "total_steps": 70, "loss": 0.3562, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:35:07", "remaining_time": "0:10:24"}
{"current_steps": 55, "total_steps": 70, "loss": 0.3751, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:35:44", "remaining_time": "0:09:44"}
{"current_steps": 56, "total_steps": 70, "loss": 0.3732, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:36:23", "remaining_time": "0:09:05"}
{"current_steps": 57, "total_steps": 70, "loss": 0.3636, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:37:01", "remaining_time": "0:08:26"}
{"current_steps": 58, "total_steps": 70, "loss": 0.3618, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:37:37", "remaining_time": "0:07:47"}
{"current_steps": 59, "total_steps": 70, "loss": 0.3584, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:38:14", "remaining_time": "0:07:07"}
{"current_steps": 60, "total_steps": 70, "loss": 0.3682, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:38:54", "remaining_time": "0:06:29"}
{"current_steps": 61, "total_steps": 70, "loss": 0.3592, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:39:30", "remaining_time": "0:05:49"}
{"current_steps": 62, "total_steps": 70, "loss": 0.3667, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:40:07", "remaining_time": "0:05:10"}
{"current_steps": 63, "total_steps": 70, "loss": 0.5279, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:40:44", "remaining_time": "0:04:31"}
{"current_steps": 64, "total_steps": 70, "loss": 0.3703, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:41:31", "remaining_time": "0:03:53"}
{"current_steps": 65, "total_steps": 70, "loss": 0.3555, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:42:09", "remaining_time": "0:03:14"}
{"current_steps": 66, "total_steps": 70, "loss": 0.3583, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:42:45", "remaining_time": "0:02:35"}
{"current_steps": 67, "total_steps": 70, "loss": 0.3582, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:43:21", "remaining_time": "0:01:56"}
{"current_steps": 68, "total_steps": 70, "loss": 0.353, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:43:58", "remaining_time": "0:01:17"}
{"current_steps": 69, "total_steps": 70, "loss": 0.3689, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:44:37", "remaining_time": "0:00:38"}
{"current_steps": 70, "total_steps": 70, "loss": 0.3441, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:45:16", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:45:49", "remaining_time": "0:00:00"}