a1_math_open2math_1k / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 6
d483f2d verified
{"current_steps": 1, "total_steps": 70, "loss": 0.8155, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:00:58", "remaining_time": "1:07:18"}
{"current_steps": 2, "total_steps": 70, "loss": 0.8298, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:01:48", "remaining_time": "1:01:40"}
{"current_steps": 3, "total_steps": 70, "loss": 0.8198, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:02:55", "remaining_time": "1:05:17"}
{"current_steps": 4, "total_steps": 70, "loss": 0.6921, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:03:41", "remaining_time": "1:00:57"}
{"current_steps": 5, "total_steps": 70, "loss": 0.6764, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:04:32", "remaining_time": "0:59:00"}
{"current_steps": 6, "total_steps": 70, "loss": 0.6736, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:05:26", "remaining_time": "0:57:59"}
{"current_steps": 7, "total_steps": 70, "loss": 0.6185, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:06:20", "remaining_time": "0:57:01"}
{"current_steps": 8, "total_steps": 70, "loss": 0.6112, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:07:26", "remaining_time": "0:57:39"}
{"current_steps": 9, "total_steps": 70, "loss": 0.5765, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:08:35", "remaining_time": "0:58:13"}
{"current_steps": 10, "total_steps": 70, "loss": 0.5501, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:09:25", "remaining_time": "0:56:31"}
{"current_steps": 11, "total_steps": 70, "loss": 0.5217, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:11:15", "remaining_time": "1:00:20"}
{"current_steps": 12, "total_steps": 70, "loss": 0.5067, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:12:13", "remaining_time": "0:59:05"}
{"current_steps": 13, "total_steps": 70, "loss": 0.4686, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:12:59", "remaining_time": "0:56:56"}
{"current_steps": 14, "total_steps": 70, "loss": 0.4775, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:13:53", "remaining_time": "0:55:32"}
{"current_steps": 15, "total_steps": 70, "loss": 0.4518, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:14:46", "remaining_time": "0:54:10"}
{"current_steps": 16, "total_steps": 70, "loss": 0.4745, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:15:53", "remaining_time": "0:53:36"}
{"current_steps": 17, "total_steps": 70, "loss": 0.4635, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:16:42", "remaining_time": "0:52:05"}
{"current_steps": 18, "total_steps": 70, "loss": 0.4357, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:17:29", "remaining_time": "0:50:31"}
{"current_steps": 19, "total_steps": 70, "loss": 0.4394, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:18:19", "remaining_time": "0:49:11"}
{"current_steps": 20, "total_steps": 70, "loss": 0.46, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:19:25", "remaining_time": "0:48:33"}
{"current_steps": 21, "total_steps": 70, "loss": 0.4408, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:21:17", "remaining_time": "0:49:40"}
{"current_steps": 22, "total_steps": 70, "loss": 0.3624, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:22:13", "remaining_time": "0:48:28"}
{"current_steps": 23, "total_steps": 70, "loss": 0.3643, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:22:59", "remaining_time": "0:46:59"}
{"current_steps": 24, "total_steps": 70, "loss": 0.3603, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:23:54", "remaining_time": "0:45:49"}
{"current_steps": 25, "total_steps": 70, "loss": 0.3358, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:24:45", "remaining_time": "0:44:34"}
{"current_steps": 26, "total_steps": 70, "loss": 0.3537, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:25:41", "remaining_time": "0:43:28"}
{"current_steps": 27, "total_steps": 70, "loss": 0.3473, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:26:36", "remaining_time": "0:42:22"}
{"current_steps": 28, "total_steps": 70, "loss": 0.3404, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:27:28", "remaining_time": "0:41:12"}
{"current_steps": 29, "total_steps": 70, "loss": 0.3645, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "0:28:30", "remaining_time": "0:40:17"}
{"current_steps": 30, "total_steps": 70, "loss": 0.3279, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "0:29:31", "remaining_time": "0:39:22"}
{"current_steps": 31, "total_steps": 70, "loss": 0.3245, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "0:30:25", "remaining_time": "0:38:16"}
{"current_steps": 32, "total_steps": 70, "loss": 0.3059, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "0:32:22", "remaining_time": "0:38:26"}
{"current_steps": 33, "total_steps": 70, "loss": 0.2872, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "0:33:20", "remaining_time": "0:37:22"}
{"current_steps": 34, "total_steps": 70, "loss": 0.266, "lr": 1.2225209339563144e-05, "epoch": 3.2640000000000002, "percentage": 48.57, "elapsed_time": "0:34:23", "remaining_time": "0:36:25"}
{"current_steps": 35, "total_steps": 70, "loss": 0.2457, "lr": 1.1736481776669307e-05, "epoch": 3.36, "percentage": 50.0, "elapsed_time": "0:35:12", "remaining_time": "0:35:12"}
{"current_steps": 36, "total_steps": 70, "loss": 0.2426, "lr": 1.1243437046474854e-05, "epoch": 3.456, "percentage": 51.43, "elapsed_time": "0:35:56", "remaining_time": "0:33:56"}
{"current_steps": 37, "total_steps": 70, "loss": 0.2957, "lr": 1.0747300935864245e-05, "epoch": 3.552, "percentage": 52.86, "elapsed_time": "0:36:53", "remaining_time": "0:32:54"}
{"current_steps": 38, "total_steps": 70, "loss": 0.2473, "lr": 1.0249306917380731e-05, "epoch": 3.648, "percentage": 54.29, "elapsed_time": "0:37:48", "remaining_time": "0:31:50"}
{"current_steps": 39, "total_steps": 70, "loss": 0.2702, "lr": 9.750693082619274e-06, "epoch": 3.7439999999999998, "percentage": 55.71, "elapsed_time": "0:38:46", "remaining_time": "0:30:49"}
{"current_steps": 40, "total_steps": 70, "loss": 0.2237, "lr": 9.252699064135759e-06, "epoch": 3.84, "percentage": 57.14, "elapsed_time": "0:39:33", "remaining_time": "0:29:40"}
{"current_steps": 41, "total_steps": 70, "loss": 0.2563, "lr": 8.756562953525151e-06, "epoch": 3.936, "percentage": 58.57, "elapsed_time": "0:40:30", "remaining_time": "0:28:38"}
{"current_steps": 42, "total_steps": 70, "loss": 0.2312, "lr": 8.263518223330698e-06, "epoch": 4.032, "percentage": 60.0, "elapsed_time": "0:42:17", "remaining_time": "0:28:11"}
{"current_steps": 43, "total_steps": 70, "loss": 0.2555, "lr": 7.774790660436857e-06, "epoch": 4.128, "percentage": 61.43, "elapsed_time": "0:43:26", "remaining_time": "0:27:16"}
{"current_steps": 44, "total_steps": 70, "loss": 0.2122, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "0:44:17", "remaining_time": "0:26:10"}
{"current_steps": 45, "total_steps": 70, "loss": 0.2007, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "0:45:06", "remaining_time": "0:25:03"}
{"current_steps": 46, "total_steps": 70, "loss": 0.2322, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "0:46:16", "remaining_time": "0:24:08"}
{"current_steps": 47, "total_steps": 70, "loss": 0.188, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "0:47:11", "remaining_time": "0:23:05"}
{"current_steps": 48, "total_steps": 70, "loss": 0.2053, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "0:48:03", "remaining_time": "0:22:01"}
{"current_steps": 49, "total_steps": 70, "loss": 0.1797, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "0:48:56", "remaining_time": "0:20:58"}
{"current_steps": 50, "total_steps": 70, "loss": 0.1965, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "0:49:47", "remaining_time": "0:19:55"}
{"current_steps": 51, "total_steps": 70, "loss": 0.1812, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "0:50:37", "remaining_time": "0:18:51"}
{"current_steps": 52, "total_steps": 70, "loss": 0.2158, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "0:51:29", "remaining_time": "0:17:49"}
{"current_steps": 53, "total_steps": 70, "loss": 0.1557, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "0:53:21", "remaining_time": "0:17:06"}
{"current_steps": 54, "total_steps": 70, "loss": 0.1879, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "0:54:16", "remaining_time": "0:16:04"}
{"current_steps": 55, "total_steps": 70, "loss": 0.1747, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "0:55:11", "remaining_time": "0:15:03"}
{"current_steps": 56, "total_steps": 70, "loss": 0.1873, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "0:56:11", "remaining_time": "0:14:02"}
{"current_steps": 57, "total_steps": 70, "loss": 0.1833, "lr": 2.0286749277707783e-06, "epoch": 5.4719999999999995, "percentage": 81.43, "elapsed_time": "0:57:24", "remaining_time": "0:13:05"}
{"current_steps": 58, "total_steps": 70, "loss": 0.1727, "lr": 1.7376122568400533e-06, "epoch": 5.568, "percentage": 82.86, "elapsed_time": "0:58:18", "remaining_time": "0:12:03"}
{"current_steps": 59, "total_steps": 70, "loss": 0.1967, "lr": 1.467091183678444e-06, "epoch": 5.664, "percentage": 84.29, "elapsed_time": "0:59:13", "remaining_time": "0:11:02"}
{"current_steps": 60, "total_steps": 70, "loss": 0.1823, "lr": 1.2177842662977136e-06, "epoch": 5.76, "percentage": 85.71, "elapsed_time": "1:00:11", "remaining_time": "0:10:01"}
{"current_steps": 61, "total_steps": 70, "loss": 0.1877, "lr": 9.903113209758098e-07, "epoch": 5.856, "percentage": 87.14, "elapsed_time": "1:01:04", "remaining_time": "0:09:00"}
{"current_steps": 62, "total_steps": 70, "loss": 0.1469, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "1:01:51", "remaining_time": "0:07:58"}
{"current_steps": 63, "total_steps": 70, "loss": 0.1573, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "1:03:55", "remaining_time": "0:07:06"}
{"current_steps": 64, "total_steps": 70, "loss": 0.1579, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "1:04:54", "remaining_time": "0:06:05"}
{"current_steps": 65, "total_steps": 70, "loss": 0.1788, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "1:05:52", "remaining_time": "0:05:04"}
{"current_steps": 66, "total_steps": 70, "loss": 0.1761, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "1:06:57", "remaining_time": "0:04:03"}
{"current_steps": 67, "total_steps": 70, "loss": 0.1666, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "1:07:53", "remaining_time": "0:03:02"}
{"current_steps": 68, "total_steps": 70, "loss": 0.1787, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "1:08:57", "remaining_time": "0:02:01"}
{"current_steps": 69, "total_steps": 70, "loss": 0.165, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "1:09:51", "remaining_time": "0:01:00"}
{"current_steps": 70, "total_steps": 70, "loss": 0.1363, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:10:38", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:12:48", "remaining_time": "0:00:00"}