openr1_codeforces_1k / trainer_log.jsonl
ryanmarten's picture
Training in progress, epoch 6
59a6016 verified
{"current_steps": 1, "total_steps": 70, "loss": 1.0604, "lr": 2.8571428571428573e-06, "epoch": 0.096, "percentage": 1.43, "elapsed_time": "0:01:42", "remaining_time": "1:57:21"}
{"current_steps": 2, "total_steps": 70, "loss": 1.0566, "lr": 5.7142857142857145e-06, "epoch": 0.192, "percentage": 2.86, "elapsed_time": "0:03:35", "remaining_time": "2:02:06"}
{"current_steps": 3, "total_steps": 70, "loss": 1.0483, "lr": 8.571428571428571e-06, "epoch": 0.288, "percentage": 4.29, "elapsed_time": "0:05:17", "remaining_time": "1:58:04"}
{"current_steps": 4, "total_steps": 70, "loss": 0.9819, "lr": 1.1428571428571429e-05, "epoch": 0.384, "percentage": 5.71, "elapsed_time": "0:06:50", "remaining_time": "1:52:50"}
{"current_steps": 5, "total_steps": 70, "loss": 0.9495, "lr": 1.4285714285714287e-05, "epoch": 0.48, "percentage": 7.14, "elapsed_time": "0:08:27", "remaining_time": "1:49:57"}
{"current_steps": 6, "total_steps": 70, "loss": 0.9476, "lr": 1.7142857142857142e-05, "epoch": 0.576, "percentage": 8.57, "elapsed_time": "0:10:02", "remaining_time": "1:47:05"}
{"current_steps": 7, "total_steps": 70, "loss": 0.8945, "lr": 2e-05, "epoch": 0.672, "percentage": 10.0, "elapsed_time": "0:11:33", "remaining_time": "1:44:03"}
{"current_steps": 8, "total_steps": 70, "loss": 0.8817, "lr": 1.9987569212189224e-05, "epoch": 0.768, "percentage": 11.43, "elapsed_time": "0:13:15", "remaining_time": "1:42:47"}
{"current_steps": 9, "total_steps": 70, "loss": 0.8523, "lr": 1.9950307753654016e-05, "epoch": 0.864, "percentage": 12.86, "elapsed_time": "0:14:52", "remaining_time": "1:40:48"}
{"current_steps": 10, "total_steps": 70, "loss": 0.8179, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:16:29", "remaining_time": "1:38:57"}
{"current_steps": 11, "total_steps": 70, "loss": 0.79, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:18:56", "remaining_time": "1:41:37"}
{"current_steps": 12, "total_steps": 70, "loss": 0.7653, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:20:40", "remaining_time": "1:39:58"}
{"current_steps": 13, "total_steps": 70, "loss": 0.7539, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:22:11", "remaining_time": "1:37:18"}
{"current_steps": 14, "total_steps": 70, "loss": 0.7555, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:23:42", "remaining_time": "1:34:49"}
{"current_steps": 15, "total_steps": 70, "loss": 0.7299, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:25:25", "remaining_time": "1:33:12"}
{"current_steps": 16, "total_steps": 70, "loss": 0.7253, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:27:08", "remaining_time": "1:31:36"}
{"current_steps": 17, "total_steps": 70, "loss": 0.7176, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:28:51", "remaining_time": "1:29:57"}
{"current_steps": 18, "total_steps": 70, "loss": 0.7211, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:30:32", "remaining_time": "1:28:14"}
{"current_steps": 19, "total_steps": 70, "loss": 0.6964, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:32:13", "remaining_time": "1:26:28"}
{"current_steps": 20, "total_steps": 70, "loss": 0.7113, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:33:51", "remaining_time": "1:24:39"}
{"current_steps": 21, "total_steps": 70, "loss": 0.7026, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:36:15", "remaining_time": "1:24:36"}
{"current_steps": 22, "total_steps": 70, "loss": 0.6638, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:37:59", "remaining_time": "1:22:52"}
{"current_steps": 23, "total_steps": 70, "loss": 0.6567, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:39:34", "remaining_time": "1:20:52"}
{"current_steps": 24, "total_steps": 70, "loss": 0.6487, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:41:15", "remaining_time": "1:19:04"}
{"current_steps": 25, "total_steps": 70, "loss": 0.6344, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:42:55", "remaining_time": "1:17:15"}
{"current_steps": 26, "total_steps": 70, "loss": 0.6484, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:44:26", "remaining_time": "1:15:12"}
{"current_steps": 27, "total_steps": 70, "loss": 0.6299, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:46:03", "remaining_time": "1:13:21"}
{"current_steps": 28, "total_steps": 70, "loss": 0.6169, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:47:36", "remaining_time": "1:11:24"}
{"current_steps": 29, "total_steps": 70, "loss": 0.6405, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "0:49:12", "remaining_time": "1:09:34"}
{"current_steps": 30, "total_steps": 70, "loss": 0.6093, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "0:50:49", "remaining_time": "1:07:45"}
{"current_steps": 31, "total_steps": 70, "loss": 0.6015, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "0:52:28", "remaining_time": "1:06:00"}
{"current_steps": 32, "total_steps": 70, "loss": 0.5864, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "0:54:57", "remaining_time": "1:05:15"}
{"current_steps": 33, "total_steps": 70, "loss": 0.5867, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "0:56:33", "remaining_time": "1:03:24"}
{"current_steps": 34, "total_steps": 70, "loss": 0.5782, "lr": 1.2225209339563144e-05, "epoch": 3.2640000000000002, "percentage": 48.57, "elapsed_time": "0:58:05", "remaining_time": "1:01:30"}
{"current_steps": 35, "total_steps": 70, "loss": 0.5728, "lr": 1.1736481776669307e-05, "epoch": 3.36, "percentage": 50.0, "elapsed_time": "0:59:49", "remaining_time": "0:59:49"}
{"current_steps": 36, "total_steps": 70, "loss": 0.5304, "lr": 1.1243437046474854e-05, "epoch": 3.456, "percentage": 51.43, "elapsed_time": "1:01:14", "remaining_time": "0:57:50"}
{"current_steps": 37, "total_steps": 70, "loss": 0.5532, "lr": 1.0747300935864245e-05, "epoch": 3.552, "percentage": 52.86, "elapsed_time": "1:02:47", "remaining_time": "0:55:59"}
{"current_steps": 38, "total_steps": 70, "loss": 0.5714, "lr": 1.0249306917380731e-05, "epoch": 3.648, "percentage": 54.29, "elapsed_time": "1:04:16", "remaining_time": "0:54:07"}
{"current_steps": 39, "total_steps": 70, "loss": 0.5547, "lr": 9.750693082619274e-06, "epoch": 3.7439999999999998, "percentage": 55.71, "elapsed_time": "1:06:07", "remaining_time": "0:52:33"}
{"current_steps": 40, "total_steps": 70, "loss": 0.5452, "lr": 9.252699064135759e-06, "epoch": 3.84, "percentage": 57.14, "elapsed_time": "1:07:43", "remaining_time": "0:50:47"}
{"current_steps": 41, "total_steps": 70, "loss": 0.5773, "lr": 8.756562953525151e-06, "epoch": 3.936, "percentage": 58.57, "elapsed_time": "1:09:27", "remaining_time": "0:49:07"}
{"current_steps": 42, "total_steps": 70, "loss": 0.5598, "lr": 8.263518223330698e-06, "epoch": 4.032, "percentage": 60.0, "elapsed_time": "1:12:01", "remaining_time": "0:48:01"}
{"current_steps": 43, "total_steps": 70, "loss": 0.5164, "lr": 7.774790660436857e-06, "epoch": 4.128, "percentage": 61.43, "elapsed_time": "1:13:41", "remaining_time": "0:46:16"}
{"current_steps": 44, "total_steps": 70, "loss": 0.5408, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "1:15:24", "remaining_time": "0:44:33"}
{"current_steps": 45, "total_steps": 70, "loss": 0.4941, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "1:17:13", "remaining_time": "0:42:54"}
{"current_steps": 46, "total_steps": 70, "loss": 0.5284, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "1:19:02", "remaining_time": "0:41:14"}
{"current_steps": 47, "total_steps": 70, "loss": 0.5014, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "1:20:32", "remaining_time": "0:39:24"}
{"current_steps": 48, "total_steps": 70, "loss": 0.5, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "1:22:07", "remaining_time": "0:37:38"}
{"current_steps": 49, "total_steps": 70, "loss": 0.4793, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "1:23:44", "remaining_time": "0:35:53"}
{"current_steps": 50, "total_steps": 70, "loss": 0.5223, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "1:25:17", "remaining_time": "0:34:06"}
{"current_steps": 51, "total_steps": 70, "loss": 0.5474, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "1:27:01", "remaining_time": "0:32:25"}
{"current_steps": 52, "total_steps": 70, "loss": 0.5191, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "1:28:33", "remaining_time": "0:30:39"}
{"current_steps": 53, "total_steps": 70, "loss": 0.4818, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "1:31:14", "remaining_time": "0:29:15"}
{"current_steps": 54, "total_steps": 70, "loss": 0.474, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "1:33:06", "remaining_time": "0:27:35"}
{"current_steps": 55, "total_steps": 70, "loss": 0.4917, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "1:34:43", "remaining_time": "0:25:49"}
{"current_steps": 56, "total_steps": 70, "loss": 0.4908, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "1:36:16", "remaining_time": "0:24:04"}
{"current_steps": 57, "total_steps": 70, "loss": 0.4724, "lr": 2.0286749277707783e-06, "epoch": 5.4719999999999995, "percentage": 81.43, "elapsed_time": "1:37:49", "remaining_time": "0:22:18"}
{"current_steps": 58, "total_steps": 70, "loss": 0.4812, "lr": 1.7376122568400533e-06, "epoch": 5.568, "percentage": 82.86, "elapsed_time": "1:39:28", "remaining_time": "0:20:34"}
{"current_steps": 59, "total_steps": 70, "loss": 0.4915, "lr": 1.467091183678444e-06, "epoch": 5.664, "percentage": 84.29, "elapsed_time": "1:41:00", "remaining_time": "0:18:50"}
{"current_steps": 60, "total_steps": 70, "loss": 0.4941, "lr": 1.2177842662977136e-06, "epoch": 5.76, "percentage": 85.71, "elapsed_time": "1:42:32", "remaining_time": "0:17:05"}
{"current_steps": 61, "total_steps": 70, "loss": 0.4871, "lr": 9.903113209758098e-07, "epoch": 5.856, "percentage": 87.14, "elapsed_time": "1:44:14", "remaining_time": "0:15:22"}
{"current_steps": 62, "total_steps": 70, "loss": 0.5032, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "1:45:57", "remaining_time": "0:13:40"}
{"current_steps": 63, "total_steps": 70, "loss": 0.4605, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "1:48:43", "remaining_time": "0:12:04"}
{"current_steps": 64, "total_steps": 70, "loss": 0.4592, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "1:50:22", "remaining_time": "0:10:20"}
{"current_steps": 65, "total_steps": 70, "loss": 0.4724, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "1:52:01", "remaining_time": "0:08:37"}
{"current_steps": 66, "total_steps": 70, "loss": 0.4849, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "1:53:34", "remaining_time": "0:06:52"}
{"current_steps": 67, "total_steps": 70, "loss": 0.4629, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "1:55:16", "remaining_time": "0:05:09"}
{"current_steps": 68, "total_steps": 70, "loss": 0.4865, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "1:56:55", "remaining_time": "0:03:26"}
{"current_steps": 69, "total_steps": 70, "loss": 0.4741, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "1:58:25", "remaining_time": "0:01:42"}
{"current_steps": 70, "total_steps": 70, "loss": 0.4932, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:00:00", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:02:33", "remaining_time": "0:00:00"}