d1_science_shortest_1k / trainer_log.jsonl
ryanmarten's picture
Upload model
0f3c265 verified
{"current_steps": 1, "total_steps": 70, "loss": 1.0227, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:55", "remaining_time": "1:03:29"}
{"current_steps": 2, "total_steps": 70, "loss": 0.9996, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:17", "remaining_time": "0:44:05"}
{"current_steps": 3, "total_steps": 70, "loss": 0.9765, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:01:42", "remaining_time": "0:38:13"}
{"current_steps": 4, "total_steps": 70, "loss": 0.8893, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:05", "remaining_time": "0:34:36"}
{"current_steps": 5, "total_steps": 70, "loss": 0.9081, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:02:29", "remaining_time": "0:32:28"}
{"current_steps": 6, "total_steps": 70, "loss": 0.8802, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:03:01", "remaining_time": "0:32:11"}
{"current_steps": 7, "total_steps": 70, "loss": 0.8789, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:03:18", "remaining_time": "0:29:48"}
{"current_steps": 8, "total_steps": 70, "loss": 0.8812, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:03:39", "remaining_time": "0:28:21"}
{"current_steps": 9, "total_steps": 70, "loss": 0.8704, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:04:02", "remaining_time": "0:27:22"}
{"current_steps": 10, "total_steps": 70, "loss": 0.8102, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:04:27", "remaining_time": "0:26:44"}
{"current_steps": 11, "total_steps": 70, "loss": 1.1674, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:05:07", "remaining_time": "0:27:30"}
{"current_steps": 12, "total_steps": 70, "loss": 0.7546, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:05:26", "remaining_time": "0:26:18"}
{"current_steps": 13, "total_steps": 70, "loss": 0.6845, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:05:54", "remaining_time": "0:25:54"}
{"current_steps": 14, "total_steps": 70, "loss": 0.7132, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:06:20", "remaining_time": "0:25:22"}
{"current_steps": 15, "total_steps": 70, "loss": 0.758, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:06:43", "remaining_time": "0:24:37"}
{"current_steps": 16, "total_steps": 70, "loss": 0.672, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:07:07", "remaining_time": "0:24:01"}
{"current_steps": 17, "total_steps": 70, "loss": 0.6714, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:07:26", "remaining_time": "0:23:12"}
{"current_steps": 18, "total_steps": 70, "loss": 0.648, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:07:55", "remaining_time": "0:22:53"}
{"current_steps": 19, "total_steps": 70, "loss": 0.7103, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:08:18", "remaining_time": "0:22:18"}
{"current_steps": 20, "total_steps": 70, "loss": 0.6309, "lr": 1.7971325072229227e-05, "epoch": 1.9047619047619047, "percentage": 28.57, "elapsed_time": "0:08:38", "remaining_time": "0:21:36"}
{"current_steps": 21, "total_steps": 70, "loss": 0.9181, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:09:03", "remaining_time": "0:21:07"}
{"current_steps": 22, "total_steps": 70, "loss": 0.5679, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:09:42", "remaining_time": "0:21:11"}
{"current_steps": 23, "total_steps": 70, "loss": 0.5525, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:10:06", "remaining_time": "0:20:39"}
{"current_steps": 24, "total_steps": 70, "loss": 0.5529, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:10:31", "remaining_time": "0:20:11"}
{"current_steps": 25, "total_steps": 70, "loss": 0.5327, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:10:54", "remaining_time": "0:19:38"}
{"current_steps": 26, "total_steps": 70, "loss": 0.549, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:11:17", "remaining_time": "0:19:06"}
{"current_steps": 27, "total_steps": 70, "loss": 0.5434, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:11:42", "remaining_time": "0:18:38"}
{"current_steps": 28, "total_steps": 70, "loss": 0.5333, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:12:03", "remaining_time": "0:18:05"}
{"current_steps": 29, "total_steps": 70, "loss": 0.5221, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:12:27", "remaining_time": "0:17:36"}
{"current_steps": 30, "total_steps": 70, "loss": 0.5244, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:12:51", "remaining_time": "0:17:08"}
{"current_steps": 31, "total_steps": 70, "loss": 0.5162, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:13:18", "remaining_time": "0:16:43"}
{"current_steps": 32, "total_steps": 70, "loss": 0.7286, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:13:51", "remaining_time": "0:16:27"}
{"current_steps": 33, "total_steps": 70, "loss": 0.4108, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:14:07", "remaining_time": "0:15:50"}
{"current_steps": 34, "total_steps": 70, "loss": 0.4329, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:14:37", "remaining_time": "0:15:28"}
{"current_steps": 35, "total_steps": 70, "loss": 0.4124, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:14:59", "remaining_time": "0:14:59"}
{"current_steps": 36, "total_steps": 70, "loss": 0.4214, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:15:21", "remaining_time": "0:14:30"}
{"current_steps": 37, "total_steps": 70, "loss": 0.4383, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:15:47", "remaining_time": "0:14:05"}
{"current_steps": 38, "total_steps": 70, "loss": 0.4211, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:16:08", "remaining_time": "0:13:35"}
{"current_steps": 39, "total_steps": 70, "loss": 0.4011, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:16:29", "remaining_time": "0:13:06"}
{"current_steps": 40, "total_steps": 70, "loss": 0.4122, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:16:46", "remaining_time": "0:12:34"}
{"current_steps": 41, "total_steps": 70, "loss": 0.3929, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:17:13", "remaining_time": "0:12:10"}
{"current_steps": 42, "total_steps": 70, "loss": 0.5756, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:17:36", "remaining_time": "0:11:44"}
{"current_steps": 43, "total_steps": 70, "loss": 0.3713, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:18:16", "remaining_time": "0:11:28"}
{"current_steps": 44, "total_steps": 70, "loss": 0.3579, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:18:37", "remaining_time": "0:11:00"}
{"current_steps": 45, "total_steps": 70, "loss": 0.3312, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:19:04", "remaining_time": "0:10:36"}
{"current_steps": 46, "total_steps": 70, "loss": 0.318, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:19:24", "remaining_time": "0:10:07"}
{"current_steps": 47, "total_steps": 70, "loss": 0.3199, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:19:50", "remaining_time": "0:09:42"}
{"current_steps": 48, "total_steps": 70, "loss": 0.3085, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:20:14", "remaining_time": "0:09:16"}
{"current_steps": 49, "total_steps": 70, "loss": 0.3254, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:20:42", "remaining_time": "0:08:52"}
{"current_steps": 50, "total_steps": 70, "loss": 0.3107, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:21:03", "remaining_time": "0:08:25"}
{"current_steps": 51, "total_steps": 70, "loss": 0.2942, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:21:23", "remaining_time": "0:07:58"}
{"current_steps": 52, "total_steps": 70, "loss": 0.3078, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:21:48", "remaining_time": "0:07:32"}
{"current_steps": 53, "total_steps": 70, "loss": 0.4628, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:22:21", "remaining_time": "0:07:10"}
{"current_steps": 54, "total_steps": 70, "loss": 0.2658, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:22:43", "remaining_time": "0:06:43"}
{"current_steps": 55, "total_steps": 70, "loss": 0.2621, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:23:08", "remaining_time": "0:06:18"}
{"current_steps": 56, "total_steps": 70, "loss": 0.2846, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:23:32", "remaining_time": "0:05:53"}
{"current_steps": 57, "total_steps": 70, "loss": 0.2746, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:23:55", "remaining_time": "0:05:27"}
{"current_steps": 58, "total_steps": 70, "loss": 0.2617, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:24:15", "remaining_time": "0:05:01"}
{"current_steps": 59, "total_steps": 70, "loss": 0.3054, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:24:49", "remaining_time": "0:04:37"}
{"current_steps": 60, "total_steps": 70, "loss": 0.2455, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:25:10", "remaining_time": "0:04:11"}
{"current_steps": 61, "total_steps": 70, "loss": 0.2764, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:25:31", "remaining_time": "0:03:45"}
{"current_steps": 62, "total_steps": 70, "loss": 0.3167, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:25:57", "remaining_time": "0:03:20"}
{"current_steps": 63, "total_steps": 70, "loss": 0.3487, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:26:16", "remaining_time": "0:02:55"}
{"current_steps": 64, "total_steps": 70, "loss": 0.251, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:26:51", "remaining_time": "0:02:31"}
{"current_steps": 65, "total_steps": 70, "loss": 0.2677, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:27:19", "remaining_time": "0:02:06"}
{"current_steps": 66, "total_steps": 70, "loss": 0.2562, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:27:46", "remaining_time": "0:01:40"}
{"current_steps": 67, "total_steps": 70, "loss": 0.2554, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:28:06", "remaining_time": "0:01:15"}
{"current_steps": 68, "total_steps": 70, "loss": 0.2421, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:28:30", "remaining_time": "0:00:50"}
{"current_steps": 69, "total_steps": 70, "loss": 0.2444, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:28:48", "remaining_time": "0:00:25"}
{"current_steps": 70, "total_steps": 70, "loss": 0.2602, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:29:08", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:29:37", "remaining_time": "0:00:00"}