DCFT-scale_up_science_2K-etash / trainer_log.jsonl
EtashGuha's picture
Upload folder using huggingface_hub
e9780e4 verified
{"current_steps": 1, "total_steps": 63, "loss": 1.3198, "lr": 1.4285714285714286e-06, "epoch": 0.047619047619047616, "percentage": 1.59, "elapsed_time": "0:00:21", "remaining_time": "0:21:44"}
{"current_steps": 2, "total_steps": 63, "loss": 1.3051, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 3.17, "elapsed_time": "0:00:33", "remaining_time": "0:16:54"}
{"current_steps": 3, "total_steps": 63, "loss": 1.3078, "lr": 4.2857142857142855e-06, "epoch": 0.14285714285714285, "percentage": 4.76, "elapsed_time": "0:00:50", "remaining_time": "0:16:46"}
{"current_steps": 4, "total_steps": 63, "loss": 1.2791, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 6.35, "elapsed_time": "0:01:07", "remaining_time": "0:16:41"}
{"current_steps": 5, "total_steps": 63, "loss": 1.1623, "lr": 7.1428571428571436e-06, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "0:01:20", "remaining_time": "0:15:34"}
{"current_steps": 6, "total_steps": 63, "loss": 1.1158, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 9.52, "elapsed_time": "0:01:37", "remaining_time": "0:15:30"}
{"current_steps": 7, "total_steps": 63, "loss": 1.1061, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:01:53", "remaining_time": "0:15:10"}
{"current_steps": 8, "total_steps": 63, "loss": 1.1474, "lr": 9.992134075089085e-06, "epoch": 0.38095238095238093, "percentage": 12.7, "elapsed_time": "0:02:07", "remaining_time": "0:14:33"}
{"current_steps": 9, "total_steps": 63, "loss": 1.102, "lr": 9.968561049466214e-06, "epoch": 0.42857142857142855, "percentage": 14.29, "elapsed_time": "0:02:26", "remaining_time": "0:14:39"}
{"current_steps": 10, "total_steps": 63, "loss": 1.0749, "lr": 9.92935509259118e-06, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "0:02:39", "remaining_time": "0:14:03"}
{"current_steps": 11, "total_steps": 63, "loss": 1.075, "lr": 9.874639560909118e-06, "epoch": 0.5238095238095238, "percentage": 17.46, "elapsed_time": "0:02:51", "remaining_time": "0:13:31"}
{"current_steps": 12, "total_steps": 63, "loss": 1.0243, "lr": 9.804586609725499e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:03:11", "remaining_time": "0:13:35"}
{"current_steps": 13, "total_steps": 63, "loss": 1.0196, "lr": 9.719416651541839e-06, "epoch": 0.6190476190476191, "percentage": 20.63, "elapsed_time": "0:03:24", "remaining_time": "0:13:07"}
{"current_steps": 14, "total_steps": 63, "loss": 1.0093, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:03:35", "remaining_time": "0:12:35"}
{"current_steps": 15, "total_steps": 63, "loss": 0.9815, "lr": 9.504844339512096e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:03:49", "remaining_time": "0:12:13"}
{"current_steps": 16, "total_steps": 63, "loss": 0.947, "lr": 9.376117109543769e-06, "epoch": 0.7619047619047619, "percentage": 25.4, "elapsed_time": "0:04:05", "remaining_time": "0:12:02"}
{"current_steps": 17, "total_steps": 63, "loss": 0.9616, "lr": 9.233620996141421e-06, "epoch": 0.8095238095238095, "percentage": 26.98, "elapsed_time": "0:04:24", "remaining_time": "0:11:56"}
{"current_steps": 18, "total_steps": 63, "loss": 0.9599, "lr": 9.077804344796302e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:04:40", "remaining_time": "0:11:40"}
{"current_steps": 19, "total_steps": 63, "loss": 0.9905, "lr": 8.90915741234015e-06, "epoch": 0.9047619047619048, "percentage": 30.16, "elapsed_time": "0:04:51", "remaining_time": "0:11:14"}
{"current_steps": 20, "total_steps": 63, "loss": 0.9311, "lr": 8.728210824415829e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "0:05:04", "remaining_time": "0:10:55"}
{"current_steps": 21, "total_steps": 63, "loss": 0.9241, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:05:24", "remaining_time": "0:10:48"}
{"current_steps": 22, "total_steps": 63, "loss": 0.8451, "lr": 8.331732889760021e-06, "epoch": 1.0476190476190477, "percentage": 34.92, "elapsed_time": "0:06:04", "remaining_time": "0:11:19"}
{"current_steps": 23, "total_steps": 63, "loss": 0.806, "lr": 8.117449009293668e-06, "epoch": 1.0952380952380953, "percentage": 36.51, "elapsed_time": "0:06:17", "remaining_time": "0:10:56"}
{"current_steps": 24, "total_steps": 63, "loss": 0.8083, "lr": 7.89335648089903e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:06:34", "remaining_time": "0:10:40"}
{"current_steps": 25, "total_steps": 63, "loss": 0.8011, "lr": 7.660160382576683e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "0:06:56", "remaining_time": "0:10:33"}
{"current_steps": 26, "total_steps": 63, "loss": 0.8378, "lr": 7.4185944355261996e-06, "epoch": 1.2380952380952381, "percentage": 41.27, "elapsed_time": "0:07:09", "remaining_time": "0:10:11"}
{"current_steps": 27, "total_steps": 63, "loss": 0.8089, "lr": 7.169418695587791e-06, "epoch": 1.2857142857142856, "percentage": 42.86, "elapsed_time": "0:07:21", "remaining_time": "0:09:49"}
{"current_steps": 28, "total_steps": 63, "loss": 0.8151, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:07:39", "remaining_time": "0:09:33"}
{"current_steps": 29, "total_steps": 63, "loss": 0.8017, "lr": 6.651395309775837e-06, "epoch": 1.380952380952381, "percentage": 46.03, "elapsed_time": "0:07:52", "remaining_time": "0:09:13"}
{"current_steps": 30, "total_steps": 63, "loss": 0.7828, "lr": 6.384177557124247e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:08:08", "remaining_time": "0:08:56"}
{"current_steps": 31, "total_steps": 63, "loss": 0.7929, "lr": 6.112604669781572e-06, "epoch": 1.4761904761904763, "percentage": 49.21, "elapsed_time": "0:08:24", "remaining_time": "0:08:40"}
{"current_steps": 32, "total_steps": 63, "loss": 0.784, "lr": 5.837531116523683e-06, "epoch": 1.5238095238095237, "percentage": 50.79, "elapsed_time": "0:08:39", "remaining_time": "0:08:23"}
{"current_steps": 33, "total_steps": 63, "loss": 0.7909, "lr": 5.559822380516539e-06, "epoch": 1.5714285714285714, "percentage": 52.38, "elapsed_time": "0:08:50", "remaining_time": "0:08:02"}
{"current_steps": 34, "total_steps": 63, "loss": 0.7893, "lr": 5.2803522361859596e-06, "epoch": 1.619047619047619, "percentage": 53.97, "elapsed_time": "0:09:09", "remaining_time": "0:07:48"}
{"current_steps": 35, "total_steps": 63, "loss": 0.7701, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:09:27", "remaining_time": "0:07:33"}
{"current_steps": 36, "total_steps": 63, "loss": 0.7703, "lr": 4.719647763814041e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:09:39", "remaining_time": "0:07:14"}
{"current_steps": 37, "total_steps": 63, "loss": 0.7812, "lr": 4.4401776194834615e-06, "epoch": 1.7619047619047619, "percentage": 58.73, "elapsed_time": "0:09:54", "remaining_time": "0:06:57"}
{"current_steps": 38, "total_steps": 63, "loss": 0.7861, "lr": 4.162468883476319e-06, "epoch": 1.8095238095238095, "percentage": 60.32, "elapsed_time": "0:10:07", "remaining_time": "0:06:39"}
{"current_steps": 39, "total_steps": 63, "loss": 0.8001, "lr": 3.887395330218429e-06, "epoch": 1.8571428571428572, "percentage": 61.9, "elapsed_time": "0:10:21", "remaining_time": "0:06:22"}
{"current_steps": 40, "total_steps": 63, "loss": 0.7768, "lr": 3.6158224428757538e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "0:10:36", "remaining_time": "0:06:06"}
{"current_steps": 41, "total_steps": 63, "loss": 0.7732, "lr": 3.3486046902241663e-06, "epoch": 1.9523809523809523, "percentage": 65.08, "elapsed_time": "0:10:48", "remaining_time": "0:05:47"}
{"current_steps": 42, "total_steps": 63, "loss": 0.7878, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:11:08", "remaining_time": "0:05:34"}
{"current_steps": 43, "total_steps": 63, "loss": 0.6674, "lr": 2.83058130441221e-06, "epoch": 2.0476190476190474, "percentage": 68.25, "elapsed_time": "0:11:55", "remaining_time": "0:05:32"}
{"current_steps": 44, "total_steps": 63, "loss": 0.6872, "lr": 2.5814055644738013e-06, "epoch": 2.0952380952380953, "percentage": 69.84, "elapsed_time": "0:12:08", "remaining_time": "0:05:14"}
{"current_steps": 45, "total_steps": 63, "loss": 0.6671, "lr": 2.339839617423318e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "0:12:23", "remaining_time": "0:04:57"}
{"current_steps": 46, "total_steps": 63, "loss": 0.6564, "lr": 2.1066435191009717e-06, "epoch": 2.1904761904761907, "percentage": 73.02, "elapsed_time": "0:12:42", "remaining_time": "0:04:41"}
{"current_steps": 47, "total_steps": 63, "loss": 0.694, "lr": 1.8825509907063328e-06, "epoch": 2.238095238095238, "percentage": 74.6, "elapsed_time": "0:12:59", "remaining_time": "0:04:25"}
{"current_steps": 48, "total_steps": 63, "loss": 0.6795, "lr": 1.6682671102399806e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:13:10", "remaining_time": "0:04:06"}
{"current_steps": 49, "total_steps": 63, "loss": 0.6608, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:13:31", "remaining_time": "0:03:51"}
{"current_steps": 50, "total_steps": 63, "loss": 0.6669, "lr": 1.2717891755841722e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "0:13:52", "remaining_time": "0:03:36"}
{"current_steps": 51, "total_steps": 63, "loss": 0.6477, "lr": 1.0908425876598512e-06, "epoch": 2.4285714285714284, "percentage": 80.95, "elapsed_time": "0:14:08", "remaining_time": "0:03:19"}
{"current_steps": 52, "total_steps": 63, "loss": 0.6524, "lr": 9.221956552036992e-07, "epoch": 2.4761904761904763, "percentage": 82.54, "elapsed_time": "0:14:19", "remaining_time": "0:03:01"}
{"current_steps": 53, "total_steps": 63, "loss": 0.6624, "lr": 7.663790038585794e-07, "epoch": 2.5238095238095237, "percentage": 84.13, "elapsed_time": "0:14:30", "remaining_time": "0:02:44"}
{"current_steps": 54, "total_steps": 63, "loss": 0.6741, "lr": 6.238828904562316e-07, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:14:48", "remaining_time": "0:02:28"}
{"current_steps": 55, "total_steps": 63, "loss": 0.6568, "lr": 4.951556604879049e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "0:15:08", "remaining_time": "0:02:12"}
{"current_steps": 56, "total_steps": 63, "loss": 0.6452, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:15:21", "remaining_time": "0:01:55"}
{"current_steps": 57, "total_steps": 63, "loss": 0.6488, "lr": 2.8058334845816214e-07, "epoch": 2.7142857142857144, "percentage": 90.48, "elapsed_time": "0:15:33", "remaining_time": "0:01:38"}
{"current_steps": 58, "total_steps": 63, "loss": 0.6744, "lr": 1.9541339027450256e-07, "epoch": 2.761904761904762, "percentage": 92.06, "elapsed_time": "0:15:47", "remaining_time": "0:01:21"}
{"current_steps": 59, "total_steps": 63, "loss": 0.6758, "lr": 1.253604390908819e-07, "epoch": 2.8095238095238093, "percentage": 93.65, "elapsed_time": "0:15:59", "remaining_time": "0:01:05"}
{"current_steps": 60, "total_steps": 63, "loss": 0.6754, "lr": 7.064490740882057e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:16:15", "remaining_time": "0:00:48"}
{"current_steps": 61, "total_steps": 63, "loss": 0.6651, "lr": 3.143895053378698e-08, "epoch": 2.9047619047619047, "percentage": 96.83, "elapsed_time": "0:16:27", "remaining_time": "0:00:32"}
{"current_steps": 62, "total_steps": 63, "loss": 0.6819, "lr": 7.865924910916977e-09, "epoch": 2.9523809523809526, "percentage": 98.41, "elapsed_time": "0:16:45", "remaining_time": "0:00:16"}
{"current_steps": 63, "total_steps": 63, "loss": 0.6686, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:17:00", "remaining_time": "0:00:00"}
{"current_steps": 63, "total_steps": 63, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:17:58", "remaining_time": "0:00:00"}