c1_math_0d_4s_1k / trainer_log.jsonl
ryanmarten's picture
Upload model
737c19f verified
raw
history blame
13.5 kB
{"current_steps": 1, "total_steps": 70, "loss": 0.8419, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:46", "remaining_time": "0:53:47"}
{"current_steps": 2, "total_steps": 70, "loss": 0.8347, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:24", "remaining_time": "0:47:53"}
{"current_steps": 3, "total_steps": 70, "loss": 0.7892, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:02:02", "remaining_time": "0:45:34"}
{"current_steps": 4, "total_steps": 70, "loss": 0.7191, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:37", "remaining_time": "0:43:24"}
{"current_steps": 5, "total_steps": 70, "loss": 0.7275, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:03:14", "remaining_time": "0:42:02"}
{"current_steps": 6, "total_steps": 70, "loss": 0.7245, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:03:51", "remaining_time": "0:41:05"}
{"current_steps": 7, "total_steps": 70, "loss": 0.6869, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:04:28", "remaining_time": "0:40:17"}
{"current_steps": 8, "total_steps": 70, "loss": 0.6701, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:05:07", "remaining_time": "0:39:43"}
{"current_steps": 9, "total_steps": 70, "loss": 0.6473, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:05:45", "remaining_time": "0:39:02"}
{"current_steps": 10, "total_steps": 70, "loss": 0.6124, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:06:23", "remaining_time": "0:38:22"}
{"current_steps": 11, "total_steps": 70, "loss": 0.9323, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:07:22", "remaining_time": "0:39:33"}
{"current_steps": 12, "total_steps": 70, "loss": 0.5877, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:08:01", "remaining_time": "0:38:47"}
{"current_steps": 13, "total_steps": 70, "loss": 0.5601, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:08:37", "remaining_time": "0:37:49"}
{"current_steps": 14, "total_steps": 70, "loss": 0.5828, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:09:15", "remaining_time": "0:37:03"}
{"current_steps": 15, "total_steps": 70, "loss": 0.5557, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:09:55", "remaining_time": "0:36:24"}
{"current_steps": 16, "total_steps": 70, "loss": 0.5344, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:10:31", "remaining_time": "0:35:30"}
{"current_steps": 17, "total_steps": 70, "loss": 0.5558, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:11:08", "remaining_time": "0:34:43"}
{"current_steps": 18, "total_steps": 70, "loss": 0.5179, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:11:45", "remaining_time": "0:33:57"}
{"current_steps": 19, "total_steps": 70, "loss": 0.529, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:12:24", "remaining_time": "0:33:18"}
{"current_steps": 20, "total_steps": 70, "loss": 0.528, "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": 0.7894, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:13:38", "remaining_time": "0:31:50"}
{"current_steps": 22, "total_steps": 70, "loss": 0.4923, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:14:39", "remaining_time": "0:31:59"}
{"current_steps": 23, "total_steps": 70, "loss": 0.4884, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:15:16", "remaining_time": "0:31:13"}
{"current_steps": 24, "total_steps": 70, "loss": 0.4665, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:15:56", "remaining_time": "0:30:33"}
{"current_steps": 25, "total_steps": 70, "loss": 0.4782, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:16:33", "remaining_time": "0:29:47"}
{"current_steps": 26, "total_steps": 70, "loss": 0.4858, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:17:11", "remaining_time": "0:29:05"}
{"current_steps": 27, "total_steps": 70, "loss": 0.4796, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:17:48", "remaining_time": "0:28:21"}
{"current_steps": 28, "total_steps": 70, "loss": 0.4516, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:18:25", "remaining_time": "0:27:38"}
{"current_steps": 29, "total_steps": 70, "loss": 0.4749, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:19:00", "remaining_time": "0:26:52"}
{"current_steps": 30, "total_steps": 70, "loss": 0.467, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:19:38", "remaining_time": "0:26:10"}
{"current_steps": 31, "total_steps": 70, "loss": 0.4706, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:20:16", "remaining_time": "0:25:30"}
{"current_steps": 32, "total_steps": 70, "loss": 0.6569, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:21:13", "remaining_time": "0:25:12"}
{"current_steps": 33, "total_steps": 70, "loss": 0.4292, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:21:53", "remaining_time": "0:24:32"}
{"current_steps": 34, "total_steps": 70, "loss": 0.4378, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:22:30", "remaining_time": "0:23:49"}
{"current_steps": 35, "total_steps": 70, "loss": 0.4262, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:23:07", "remaining_time": "0:23:07"}
{"current_steps": 36, "total_steps": 70, "loss": 0.4253, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:23:44", "remaining_time": "0:22:25"}
{"current_steps": 37, "total_steps": 70, "loss": 0.4342, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:24:22", "remaining_time": "0:21:44"}
{"current_steps": 38, "total_steps": 70, "loss": 0.4293, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:25:00", "remaining_time": "0:21:03"}
{"current_steps": 39, "total_steps": 70, "loss": 0.416, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:25:36", "remaining_time": "0:20:21"}
{"current_steps": 40, "total_steps": 70, "loss": 0.423, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:26:15", "remaining_time": "0:19:41"}
{"current_steps": 41, "total_steps": 70, "loss": 0.4052, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:26:53", "remaining_time": "0:19:01"}
{"current_steps": 42, "total_steps": 70, "loss": 0.6213, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:27:30", "remaining_time": "0:18:20"}
{"current_steps": 43, "total_steps": 70, "loss": 0.3984, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:28:27", "remaining_time": "0:17:52"}
{"current_steps": 44, "total_steps": 70, "loss": 0.3867, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:29:04", "remaining_time": "0:17:10"}
{"current_steps": 45, "total_steps": 70, "loss": 0.3847, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:29:45", "remaining_time": "0:16:31"}
{"current_steps": 46, "total_steps": 70, "loss": 0.381, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:30:24", "remaining_time": "0:15:52"}
{"current_steps": 47, "total_steps": 70, "loss": 0.3844, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:31:02", "remaining_time": "0:15:11"}
{"current_steps": 48, "total_steps": 70, "loss": 0.3874, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:31:36", "remaining_time": "0:14:29"}
{"current_steps": 49, "total_steps": 70, "loss": 0.3778, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:32:13", "remaining_time": "0:13:48"}
{"current_steps": 50, "total_steps": 70, "loss": 0.3994, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:32:49", "remaining_time": "0:13:07"}
{"current_steps": 51, "total_steps": 70, "loss": 0.3827, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:33:25", "remaining_time": "0:12:26"}
{"current_steps": 52, "total_steps": 70, "loss": 0.3892, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:34:03", "remaining_time": "0:11:47"}
{"current_steps": 53, "total_steps": 70, "loss": 0.5468, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:34:56", "remaining_time": "0:11:12"}
{"current_steps": 54, "total_steps": 70, "loss": 0.3634, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:35:33", "remaining_time": "0:10:32"}
{"current_steps": 55, "total_steps": 70, "loss": 0.3698, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:36:11", "remaining_time": "0:09:52"}
{"current_steps": 56, "total_steps": 70, "loss": 0.3714, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:36:48", "remaining_time": "0:09:12"}
{"current_steps": 57, "total_steps": 70, "loss": 0.3626, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:37:26", "remaining_time": "0:08:32"}
{"current_steps": 58, "total_steps": 70, "loss": 0.3656, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:38:04", "remaining_time": "0:07:52"}
{"current_steps": 59, "total_steps": 70, "loss": 0.3574, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:38:44", "remaining_time": "0:07:13"}
{"current_steps": 60, "total_steps": 70, "loss": 0.365, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:39:20", "remaining_time": "0:06:33"}
{"current_steps": 61, "total_steps": 70, "loss": 0.3644, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:39:56", "remaining_time": "0:05:53"}
{"current_steps": 62, "total_steps": 70, "loss": 0.3682, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:40:33", "remaining_time": "0:05:13"}
{"current_steps": 63, "total_steps": 70, "loss": 0.5551, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:41:10", "remaining_time": "0:04:34"}
{"current_steps": 64, "total_steps": 70, "loss": 0.3659, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:42:12", "remaining_time": "0:03:57"}
{"current_steps": 65, "total_steps": 70, "loss": 0.3638, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:42:49", "remaining_time": "0:03:17"}
{"current_steps": 66, "total_steps": 70, "loss": 0.3584, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:43:27", "remaining_time": "0:02:38"}
{"current_steps": 67, "total_steps": 70, "loss": 0.3661, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:44:04", "remaining_time": "0:01:58"}
{"current_steps": 68, "total_steps": 70, "loss": 0.3676, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:44:42", "remaining_time": "0:01:18"}
{"current_steps": 69, "total_steps": 70, "loss": 0.3518, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:45:21", "remaining_time": "0:00:39"}
{"current_steps": 70, "total_steps": 70, "loss": 0.3555, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:45:59", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:47:03", "remaining_time": "0:00:00"}