d1_math_mc_llm_1k / trainer_log.jsonl
ryanmarten's picture
Training in progress, epoch 6
f7bbf9a verified
{"current_steps": 1, "total_steps": 70, "loss": 0.8588, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:02:01", "remaining_time": "2:20:15"}
{"current_steps": 2, "total_steps": 70, "loss": 0.8102, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:04:06", "remaining_time": "2:19:28"}
{"current_steps": 3, "total_steps": 70, "loss": 0.8042, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:06:12", "remaining_time": "2:18:42"}
{"current_steps": 4, "total_steps": 70, "loss": 0.7318, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:07:58", "remaining_time": "2:11:31"}
{"current_steps": 5, "total_steps": 70, "loss": 0.7388, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:10:32", "remaining_time": "2:16:59"}
{"current_steps": 6, "total_steps": 70, "loss": 0.7484, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:14:12", "remaining_time": "2:31:31"}
{"current_steps": 7, "total_steps": 70, "loss": 0.7025, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:19:04", "remaining_time": "2:51:39"}
{"current_steps": 8, "total_steps": 70, "loss": 0.6754, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:23:31", "remaining_time": "3:02:16"}
{"current_steps": 9, "total_steps": 70, "loss": 0.6494, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:28:16", "remaining_time": "3:11:36"}
{"current_steps": 10, "total_steps": 70, "loss": 0.6309, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:30:15", "remaining_time": "3:01:35"}
{"current_steps": 11, "total_steps": 70, "loss": 0.6093, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:32:50", "remaining_time": "2:56:10"}
{"current_steps": 12, "total_steps": 70, "loss": 0.5916, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:34:50", "remaining_time": "2:48:25"}
{"current_steps": 13, "total_steps": 70, "loss": 0.5654, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:36:52", "remaining_time": "2:41:41"}
{"current_steps": 14, "total_steps": 70, "loss": 0.5616, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:38:53", "remaining_time": "2:35:35"}
{"current_steps": 15, "total_steps": 70, "loss": 0.5602, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:40:47", "remaining_time": "2:29:33"}
{"current_steps": 16, "total_steps": 70, "loss": 0.5547, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:42:45", "remaining_time": "2:24:19"}
{"current_steps": 17, "total_steps": 70, "loss": 0.5325, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:44:37", "remaining_time": "2:19:06"}
{"current_steps": 18, "total_steps": 70, "loss": 0.5347, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:46:47", "remaining_time": "2:15:10"}
{"current_steps": 19, "total_steps": 70, "loss": 0.5559, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:48:50", "remaining_time": "2:11:06"}
{"current_steps": 20, "total_steps": 70, "loss": 0.5395, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:50:51", "remaining_time": "2:07:08"}
{"current_steps": 21, "total_steps": 70, "loss": 0.4874, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:53:39", "remaining_time": "2:05:13"}
{"current_steps": 22, "total_steps": 70, "loss": 0.4879, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:55:36", "remaining_time": "2:01:19"}
{"current_steps": 23, "total_steps": 70, "loss": 0.4958, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:57:45", "remaining_time": "1:58:01"}
{"current_steps": 24, "total_steps": 70, "loss": 0.4749, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:59:46", "remaining_time": "1:54:33"}
{"current_steps": 25, "total_steps": 70, "loss": 0.4835, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "1:01:49", "remaining_time": "1:51:17"}
{"current_steps": 26, "total_steps": 70, "loss": 0.4707, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "1:03:34", "remaining_time": "1:47:36"}
{"current_steps": 27, "total_steps": 70, "loss": 0.4626, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "1:05:32", "remaining_time": "1:44:22"}
{"current_steps": 28, "total_steps": 70, "loss": 0.4775, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "1:07:37", "remaining_time": "1:41:25"}
{"current_steps": 29, "total_steps": 70, "loss": 0.4518, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "1:09:28", "remaining_time": "1:38:13"}
{"current_steps": 30, "total_steps": 70, "loss": 0.4686, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "1:11:33", "remaining_time": "1:35:24"}
{"current_steps": 31, "total_steps": 70, "loss": 0.4525, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "1:13:24", "remaining_time": "1:32:21"}
{"current_steps": 32, "total_steps": 70, "loss": 0.4451, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "1:16:16", "remaining_time": "1:30:35"}
{"current_steps": 33, "total_steps": 70, "loss": 0.4244, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "1:18:17", "remaining_time": "1:27:46"}
{"current_steps": 34, "total_steps": 70, "loss": 0.4224, "lr": 1.2225209339563144e-05, "epoch": 3.2640000000000002, "percentage": 48.57, "elapsed_time": "1:20:17", "remaining_time": "1:25:01"}
{"current_steps": 35, "total_steps": 70, "loss": 0.4382, "lr": 1.1736481776669307e-05, "epoch": 3.36, "percentage": 50.0, "elapsed_time": "1:22:13", "remaining_time": "1:22:13"}
{"current_steps": 36, "total_steps": 70, "loss": 0.4062, "lr": 1.1243437046474854e-05, "epoch": 3.456, "percentage": 51.43, "elapsed_time": "1:24:09", "remaining_time": "1:19:29"}
{"current_steps": 37, "total_steps": 70, "loss": 0.4235, "lr": 1.0747300935864245e-05, "epoch": 3.552, "percentage": 52.86, "elapsed_time": "1:26:09", "remaining_time": "1:16:50"}
{"current_steps": 38, "total_steps": 70, "loss": 0.4078, "lr": 1.0249306917380731e-05, "epoch": 3.648, "percentage": 54.29, "elapsed_time": "1:28:18", "remaining_time": "1:14:21"}
{"current_steps": 39, "total_steps": 70, "loss": 0.4089, "lr": 9.750693082619274e-06, "epoch": 3.7439999999999998, "percentage": 55.71, "elapsed_time": "1:30:18", "remaining_time": "1:11:47"}
{"current_steps": 40, "total_steps": 70, "loss": 0.4156, "lr": 9.252699064135759e-06, "epoch": 3.84, "percentage": 57.14, "elapsed_time": "1:32:14", "remaining_time": "1:09:10"}
{"current_steps": 41, "total_steps": 70, "loss": 0.4083, "lr": 8.756562953525151e-06, "epoch": 3.936, "percentage": 58.57, "elapsed_time": "1:34:09", "remaining_time": "1:06:36"}
{"current_steps": 42, "total_steps": 70, "loss": 0.4079, "lr": 8.263518223330698e-06, "epoch": 4.032, "percentage": 60.0, "elapsed_time": "1:37:01", "remaining_time": "1:04:41"}
{"current_steps": 43, "total_steps": 70, "loss": 0.3906, "lr": 7.774790660436857e-06, "epoch": 4.128, "percentage": 61.43, "elapsed_time": "1:39:00", "remaining_time": "1:02:10"}
{"current_steps": 44, "total_steps": 70, "loss": 0.3828, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "1:41:09", "remaining_time": "0:59:46"}
{"current_steps": 45, "total_steps": 70, "loss": 0.3872, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "1:43:11", "remaining_time": "0:57:19"}
{"current_steps": 46, "total_steps": 70, "loss": 0.3794, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "1:45:04", "remaining_time": "0:54:49"}
{"current_steps": 47, "total_steps": 70, "loss": 0.3668, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "1:47:04", "remaining_time": "0:52:24"}
{"current_steps": 48, "total_steps": 70, "loss": 0.3879, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "1:48:57", "remaining_time": "0:49:56"}
{"current_steps": 49, "total_steps": 70, "loss": 0.3708, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "1:50:46", "remaining_time": "0:47:28"}
{"current_steps": 50, "total_steps": 70, "loss": 0.3746, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "1:52:43", "remaining_time": "0:45:05"}
{"current_steps": 51, "total_steps": 70, "loss": 0.3763, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "1:54:45", "remaining_time": "0:42:45"}
{"current_steps": 52, "total_steps": 70, "loss": 0.365, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "1:56:49", "remaining_time": "0:40:26"}
{"current_steps": 53, "total_steps": 70, "loss": 0.3611, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "1:59:50", "remaining_time": "0:38:26"}
{"current_steps": 54, "total_steps": 70, "loss": 0.3583, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "2:01:46", "remaining_time": "0:36:04"}
{"current_steps": 55, "total_steps": 70, "loss": 0.3525, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "2:03:50", "remaining_time": "0:33:46"}
{"current_steps": 56, "total_steps": 70, "loss": 0.3522, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "2:05:47", "remaining_time": "0:31:26"}
{"current_steps": 57, "total_steps": 70, "loss": 0.3475, "lr": 2.0286749277707783e-06, "epoch": 5.4719999999999995, "percentage": 81.43, "elapsed_time": "2:07:52", "remaining_time": "0:29:09"}
{"current_steps": 58, "total_steps": 70, "loss": 0.366, "lr": 1.7376122568400533e-06, "epoch": 5.568, "percentage": 82.86, "elapsed_time": "2:09:57", "remaining_time": "0:26:53"}
{"current_steps": 59, "total_steps": 70, "loss": 0.3744, "lr": 1.467091183678444e-06, "epoch": 5.664, "percentage": 84.29, "elapsed_time": "2:12:01", "remaining_time": "0:24:36"}
{"current_steps": 60, "total_steps": 70, "loss": 0.3569, "lr": 1.2177842662977136e-06, "epoch": 5.76, "percentage": 85.71, "elapsed_time": "2:14:00", "remaining_time": "0:22:20"}
{"current_steps": 61, "total_steps": 70, "loss": 0.3425, "lr": 9.903113209758098e-07, "epoch": 5.856, "percentage": 87.14, "elapsed_time": "2:15:53", "remaining_time": "0:20:02"}
{"current_steps": 62, "total_steps": 70, "loss": 0.355, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "2:17:48", "remaining_time": "0:17:46"}
{"current_steps": 63, "total_steps": 70, "loss": 0.3625, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "2:20:51", "remaining_time": "0:15:39"}
{"current_steps": 64, "total_steps": 70, "loss": 0.3508, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "2:22:48", "remaining_time": "0:13:23"}
{"current_steps": 65, "total_steps": 70, "loss": 0.3509, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "2:24:41", "remaining_time": "0:11:07"}
{"current_steps": 66, "total_steps": 70, "loss": 0.3488, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "2:26:48", "remaining_time": "0:08:53"}
{"current_steps": 67, "total_steps": 70, "loss": 0.342, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "2:28:51", "remaining_time": "0:06:39"}
{"current_steps": 68, "total_steps": 70, "loss": 0.3575, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "2:30:50", "remaining_time": "0:04:26"}
{"current_steps": 69, "total_steps": 70, "loss": 0.3383, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "2:32:42", "remaining_time": "0:02:12"}
{"current_steps": 70, "total_steps": 70, "loss": 0.3466, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:34:57", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:37:10", "remaining_time": "0:00:00"}