d1_science_gpt_1k / trainer_log.jsonl
ryanmarten's picture
Upload model
272792c verified
{"current_steps": 1, "total_steps": 70, "loss": 0.9707, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:38", "remaining_time": "0:44:36"}
{"current_steps": 2, "total_steps": 70, "loss": 0.96, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:11", "remaining_time": "0:40:23"}
{"current_steps": 3, "total_steps": 70, "loss": 0.9999, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:01:40", "remaining_time": "0:37:25"}
{"current_steps": 4, "total_steps": 70, "loss": 0.9063, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:04", "remaining_time": "0:34:06"}
{"current_steps": 5, "total_steps": 70, "loss": 0.8984, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:02:30", "remaining_time": "0:32:36"}
{"current_steps": 6, "total_steps": 70, "loss": 0.8603, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:02:55", "remaining_time": "0:31:09"}
{"current_steps": 7, "total_steps": 70, "loss": 0.9, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:03:19", "remaining_time": "0:29:51"}
{"current_steps": 8, "total_steps": 70, "loss": 0.864, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:03:39", "remaining_time": "0:28:22"}
{"current_steps": 9, "total_steps": 70, "loss": 0.8056, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:04:01", "remaining_time": "0:27:17"}
{"current_steps": 10, "total_steps": 70, "loss": 0.7777, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:04:26", "remaining_time": "0:26:41"}
{"current_steps": 11, "total_steps": 70, "loss": 1.1857, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:05:18", "remaining_time": "0:28:30"}
{"current_steps": 12, "total_steps": 70, "loss": 0.7071, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:05:40", "remaining_time": "0:27:26"}
{"current_steps": 13, "total_steps": 70, "loss": 0.6966, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:06:05", "remaining_time": "0:26:44"}
{"current_steps": 14, "total_steps": 70, "loss": 0.6491, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:06:29", "remaining_time": "0:25:57"}
{"current_steps": 15, "total_steps": 70, "loss": 0.7969, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:06:55", "remaining_time": "0:25:25"}
{"current_steps": 16, "total_steps": 70, "loss": 0.6197, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:07:20", "remaining_time": "0:24:47"}
{"current_steps": 17, "total_steps": 70, "loss": 0.63, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:07:45", "remaining_time": "0:24:10"}
{"current_steps": 18, "total_steps": 70, "loss": 0.6215, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:08:04", "remaining_time": "0:23:19"}
{"current_steps": 19, "total_steps": 70, "loss": 0.6743, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:08:34", "remaining_time": "0:23:01"}
{"current_steps": 20, "total_steps": 70, "loss": 0.6626, "lr": 1.7971325072229227e-05, "epoch": 1.9047619047619047, "percentage": 28.57, "elapsed_time": "0:09:03", "remaining_time": "0:22:39"}
{"current_steps": 21, "total_steps": 70, "loss": 1.0064, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:09:32", "remaining_time": "0:22:14"}
{"current_steps": 22, "total_steps": 70, "loss": 0.5821, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:10:11", "remaining_time": "0:22:14"}
{"current_steps": 23, "total_steps": 70, "loss": 0.5465, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:10:37", "remaining_time": "0:21:42"}
{"current_steps": 24, "total_steps": 70, "loss": 0.5166, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:11:00", "remaining_time": "0:21:06"}
{"current_steps": 25, "total_steps": 70, "loss": 0.5145, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:11:24", "remaining_time": "0:20:32"}
{"current_steps": 26, "total_steps": 70, "loss": 0.5293, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:11:54", "remaining_time": "0:20:08"}
{"current_steps": 27, "total_steps": 70, "loss": 0.552, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:12:16", "remaining_time": "0:19:32"}
{"current_steps": 28, "total_steps": 70, "loss": 0.5499, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:12:40", "remaining_time": "0:19:00"}
{"current_steps": 29, "total_steps": 70, "loss": 0.5255, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:13:05", "remaining_time": "0:18:30"}
{"current_steps": 30, "total_steps": 70, "loss": 0.4913, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:13:34", "remaining_time": "0:18:05"}
{"current_steps": 31, "total_steps": 70, "loss": 0.5178, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:14:00", "remaining_time": "0:17:37"}
{"current_steps": 32, "total_steps": 70, "loss": 0.6998, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:15:10", "remaining_time": "0:18:01"}
{"current_steps": 33, "total_steps": 70, "loss": 0.422, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:15:32", "remaining_time": "0:17:25"}
{"current_steps": 34, "total_steps": 70, "loss": 0.4443, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:15:59", "remaining_time": "0:16:55"}
{"current_steps": 35, "total_steps": 70, "loss": 0.3904, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:16:17", "remaining_time": "0:16:17"}
{"current_steps": 36, "total_steps": 70, "loss": 0.4155, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:16:44", "remaining_time": "0:15:48"}
{"current_steps": 37, "total_steps": 70, "loss": 0.4029, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:17:14", "remaining_time": "0:15:22"}
{"current_steps": 38, "total_steps": 70, "loss": 0.4077, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:17:34", "remaining_time": "0:14:47"}
{"current_steps": 39, "total_steps": 70, "loss": 0.3729, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:17:56", "remaining_time": "0:14:15"}
{"current_steps": 40, "total_steps": 70, "loss": 0.3925, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:18:28", "remaining_time": "0:13:51"}
{"current_steps": 41, "total_steps": 70, "loss": 0.4487, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:18:58", "remaining_time": "0:13:25"}
{"current_steps": 42, "total_steps": 70, "loss": 0.5828, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:19:21", "remaining_time": "0:12:54"}
{"current_steps": 43, "total_steps": 70, "loss": 0.3392, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:20:11", "remaining_time": "0:12:40"}
{"current_steps": 44, "total_steps": 70, "loss": 0.3498, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:20:33", "remaining_time": "0:12:09"}
{"current_steps": 45, "total_steps": 70, "loss": 0.3227, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:21:02", "remaining_time": "0:11:41"}
{"current_steps": 46, "total_steps": 70, "loss": 0.3265, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:21:28", "remaining_time": "0:11:12"}
{"current_steps": 47, "total_steps": 70, "loss": 0.3313, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:22:00", "remaining_time": "0:10:46"}
{"current_steps": 48, "total_steps": 70, "loss": 0.3138, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:22:26", "remaining_time": "0:10:17"}
{"current_steps": 49, "total_steps": 70, "loss": 0.3182, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:22:50", "remaining_time": "0:09:47"}
{"current_steps": 50, "total_steps": 70, "loss": 0.3133, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:23:14", "remaining_time": "0:09:17"}
{"current_steps": 51, "total_steps": 70, "loss": 0.2883, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:23:34", "remaining_time": "0:08:47"}
{"current_steps": 52, "total_steps": 70, "loss": 0.3216, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:23:56", "remaining_time": "0:08:17"}
{"current_steps": 53, "total_steps": 70, "loss": 0.4765, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:24:33", "remaining_time": "0:07:52"}
{"current_steps": 54, "total_steps": 70, "loss": 0.2943, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:25:01", "remaining_time": "0:07:24"}
{"current_steps": 55, "total_steps": 70, "loss": 0.2719, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:25:25", "remaining_time": "0:06:55"}
{"current_steps": 56, "total_steps": 70, "loss": 0.2929, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:25:46", "remaining_time": "0:06:26"}
{"current_steps": 57, "total_steps": 70, "loss": 0.2793, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:26:12", "remaining_time": "0:05:58"}
{"current_steps": 58, "total_steps": 70, "loss": 0.2474, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:26:40", "remaining_time": "0:05:31"}
{"current_steps": 59, "total_steps": 70, "loss": 0.2806, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:27:10", "remaining_time": "0:05:03"}
{"current_steps": 60, "total_steps": 70, "loss": 0.2507, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:27:30", "remaining_time": "0:04:35"}
{"current_steps": 61, "total_steps": 70, "loss": 0.2571, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:27:53", "remaining_time": "0:04:06"}
{"current_steps": 62, "total_steps": 70, "loss": 0.306, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:28:23", "remaining_time": "0:03:39"}
{"current_steps": 63, "total_steps": 70, "loss": 0.3736, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:28:42", "remaining_time": "0:03:11"}
{"current_steps": 64, "total_steps": 70, "loss": 0.2468, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:29:21", "remaining_time": "0:02:45"}
{"current_steps": 65, "total_steps": 70, "loss": 0.2541, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:29:45", "remaining_time": "0:02:17"}
{"current_steps": 66, "total_steps": 70, "loss": 0.2765, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:30:08", "remaining_time": "0:01:49"}
{"current_steps": 67, "total_steps": 70, "loss": 0.2458, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:30:38", "remaining_time": "0:01:22"}
{"current_steps": 68, "total_steps": 70, "loss": 0.2598, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:31:05", "remaining_time": "0:00:54"}
{"current_steps": 69, "total_steps": 70, "loss": 0.2549, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:31:32", "remaining_time": "0:00:27"}
{"current_steps": 70, "total_steps": 70, "loss": 0.2557, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:31:54", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:32:22", "remaining_time": "0:00:00"}