| { | |
| "best_global_step": 49, | |
| "best_metric": 0.8367346938775511, | |
| "best_model_checkpoint": "efficientnet-b0-accidents/checkpoint-49", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4897959183673469, | |
| "eval_loss": 0.7069449424743652, | |
| "eval_runtime": 1.2343, | |
| "eval_samples_per_second": 79.397, | |
| "eval_steps_per_second": 0.81, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4897959183673469, | |
| "eval_loss": 0.7112836837768555, | |
| "eval_runtime": 1.1578, | |
| "eval_samples_per_second": 84.646, | |
| "eval_steps_per_second": 0.864, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5102040816326531, | |
| "eval_loss": 0.7033699750900269, | |
| "eval_runtime": 1.18, | |
| "eval_samples_per_second": 83.053, | |
| "eval_steps_per_second": 0.847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5408163265306123, | |
| "eval_loss": 0.6949645280838013, | |
| "eval_runtime": 1.1744, | |
| "eval_samples_per_second": 83.45, | |
| "eval_steps_per_second": 0.852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5612244897959183, | |
| "eval_loss": 0.694236695766449, | |
| "eval_runtime": 1.1848, | |
| "eval_samples_per_second": 82.713, | |
| "eval_steps_per_second": 0.844, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5306122448979592, | |
| "eval_loss": 0.6846552491188049, | |
| "eval_runtime": 1.159, | |
| "eval_samples_per_second": 84.554, | |
| "eval_steps_per_second": 0.863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5204081632653061, | |
| "eval_loss": 0.6865835189819336, | |
| "eval_runtime": 1.1556, | |
| "eval_samples_per_second": 84.803, | |
| "eval_steps_per_second": 0.865, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5816326530612245, | |
| "eval_loss": 0.6743000745773315, | |
| "eval_runtime": 1.176, | |
| "eval_samples_per_second": 83.332, | |
| "eval_steps_per_second": 0.85, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 0.6716513633728027, | |
| "eval_runtime": 1.1533, | |
| "eval_samples_per_second": 84.974, | |
| "eval_steps_per_second": 0.867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.6979305148124695, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_loss": 0.6547528505325317, | |
| "eval_runtime": 1.1525, | |
| "eval_samples_per_second": 85.03, | |
| "eval_steps_per_second": 0.868, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6020408163265306, | |
| "eval_loss": 0.6551060676574707, | |
| "eval_runtime": 1.1814, | |
| "eval_samples_per_second": 82.95, | |
| "eval_steps_per_second": 0.846, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5918367346938775, | |
| "eval_loss": 0.6481595039367676, | |
| "eval_runtime": 1.1945, | |
| "eval_samples_per_second": 82.042, | |
| "eval_steps_per_second": 0.837, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6632653061224489, | |
| "eval_loss": 0.6407487988471985, | |
| "eval_runtime": 1.2052, | |
| "eval_samples_per_second": 81.317, | |
| "eval_steps_per_second": 0.83, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7040816326530612, | |
| "eval_loss": 0.6281946301460266, | |
| "eval_runtime": 1.1797, | |
| "eval_samples_per_second": 83.069, | |
| "eval_steps_per_second": 0.848, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6836734693877551, | |
| "eval_loss": 0.6241097450256348, | |
| "eval_runtime": 1.1429, | |
| "eval_samples_per_second": 85.746, | |
| "eval_steps_per_second": 0.875, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.6189384460449219, | |
| "eval_runtime": 1.1668, | |
| "eval_samples_per_second": 83.988, | |
| "eval_steps_per_second": 0.857, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6836734693877551, | |
| "eval_loss": 0.5998439192771912, | |
| "eval_runtime": 1.1666, | |
| "eval_samples_per_second": 84.007, | |
| "eval_steps_per_second": 0.857, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6632653061224489, | |
| "eval_loss": 0.609135627746582, | |
| "eval_runtime": 1.2178, | |
| "eval_samples_per_second": 80.476, | |
| "eval_steps_per_second": 0.821, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.5961523056030273, | |
| "eval_runtime": 1.1716, | |
| "eval_samples_per_second": 83.647, | |
| "eval_steps_per_second": 0.854, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.5801095366477966, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6177, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6938775510204082, | |
| "eval_loss": 0.5860151648521423, | |
| "eval_runtime": 1.162, | |
| "eval_samples_per_second": 84.34, | |
| "eval_steps_per_second": 0.861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6836734693877551, | |
| "eval_loss": 0.6065893173217773, | |
| "eval_runtime": 1.156, | |
| "eval_samples_per_second": 84.777, | |
| "eval_steps_per_second": 0.865, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7448979591836735, | |
| "eval_loss": 0.5802229642868042, | |
| "eval_runtime": 1.1717, | |
| "eval_samples_per_second": 83.64, | |
| "eval_steps_per_second": 0.853, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7448979591836735, | |
| "eval_loss": 0.5803083777427673, | |
| "eval_runtime": 1.1718, | |
| "eval_samples_per_second": 83.634, | |
| "eval_steps_per_second": 0.853, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.5717583894729614, | |
| "eval_runtime": 1.1582, | |
| "eval_samples_per_second": 84.613, | |
| "eval_steps_per_second": 0.863, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7040816326530612, | |
| "eval_loss": 0.5688303112983704, | |
| "eval_runtime": 1.169, | |
| "eval_samples_per_second": 83.83, | |
| "eval_steps_per_second": 0.855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7244897959183674, | |
| "eval_loss": 0.558906614780426, | |
| "eval_runtime": 1.1606, | |
| "eval_samples_per_second": 84.442, | |
| "eval_steps_per_second": 0.862, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7244897959183674, | |
| "eval_loss": 0.5467594861984253, | |
| "eval_runtime": 1.228, | |
| "eval_samples_per_second": 79.805, | |
| "eval_steps_per_second": 0.814, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6938775510204082, | |
| "eval_loss": 0.5388599634170532, | |
| "eval_runtime": 1.1813, | |
| "eval_samples_per_second": 82.963, | |
| "eval_steps_per_second": 0.847, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.5336747169494629, | |
| "eval_runtime": 1.1683, | |
| "eval_samples_per_second": 83.881, | |
| "eval_steps_per_second": 0.856, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.5761419534683228, | |
| "learning_rate": 7.88888888888889e-05, | |
| "loss": 0.5545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7346938775510204, | |
| "eval_loss": 0.528902530670166, | |
| "eval_runtime": 1.1716, | |
| "eval_samples_per_second": 83.645, | |
| "eval_steps_per_second": 0.854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7448979591836735, | |
| "eval_loss": 0.5381345748901367, | |
| "eval_runtime": 1.1607, | |
| "eval_samples_per_second": 84.429, | |
| "eval_steps_per_second": 0.862, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.5213983654975891, | |
| "eval_runtime": 1.1897, | |
| "eval_samples_per_second": 82.372, | |
| "eval_steps_per_second": 0.841, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7346938775510204, | |
| "eval_loss": 0.5152321457862854, | |
| "eval_runtime": 1.159, | |
| "eval_samples_per_second": 84.555, | |
| "eval_steps_per_second": 0.863, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7040816326530612, | |
| "eval_loss": 0.509580671787262, | |
| "eval_runtime": 1.1649, | |
| "eval_samples_per_second": 84.127, | |
| "eval_steps_per_second": 0.858, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6836734693877551, | |
| "eval_loss": 0.5266232490539551, | |
| "eval_runtime": 1.1617, | |
| "eval_samples_per_second": 84.359, | |
| "eval_steps_per_second": 0.861, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.5110865831375122, | |
| "eval_runtime": 1.1708, | |
| "eval_samples_per_second": 83.701, | |
| "eval_steps_per_second": 0.854, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.49542251229286194, | |
| "eval_runtime": 1.1679, | |
| "eval_samples_per_second": 83.913, | |
| "eval_steps_per_second": 0.856, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.510901927947998, | |
| "eval_runtime": 1.1533, | |
| "eval_samples_per_second": 84.976, | |
| "eval_steps_per_second": 0.867, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7653061224489796, | |
| "eval_loss": 0.4929142892360687, | |
| "eval_runtime": 1.1524, | |
| "eval_samples_per_second": 85.037, | |
| "eval_steps_per_second": 0.868, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.5709299445152283, | |
| "learning_rate": 6.777777777777778e-05, | |
| "loss": 0.5215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4865826666355133, | |
| "eval_runtime": 1.1621, | |
| "eval_samples_per_second": 84.328, | |
| "eval_steps_per_second": 0.86, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7244897959183674, | |
| "eval_loss": 0.4810398519039154, | |
| "eval_runtime": 1.1724, | |
| "eval_samples_per_second": 83.587, | |
| "eval_steps_per_second": 0.853, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.48122912645339966, | |
| "eval_runtime": 1.1575, | |
| "eval_samples_per_second": 84.664, | |
| "eval_steps_per_second": 0.864, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4918031096458435, | |
| "eval_runtime": 1.1694, | |
| "eval_samples_per_second": 83.803, | |
| "eval_steps_per_second": 0.855, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4652838110923767, | |
| "eval_runtime": 1.1691, | |
| "eval_samples_per_second": 83.824, | |
| "eval_steps_per_second": 0.855, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7346938775510204, | |
| "eval_loss": 0.4883042871952057, | |
| "eval_runtime": 1.1599, | |
| "eval_samples_per_second": 84.491, | |
| "eval_steps_per_second": 0.862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.47950759530067444, | |
| "eval_runtime": 1.1792, | |
| "eval_samples_per_second": 83.11, | |
| "eval_steps_per_second": 0.848, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.5048059225082397, | |
| "eval_runtime": 1.1607, | |
| "eval_samples_per_second": 84.435, | |
| "eval_steps_per_second": 0.862, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.4864862859249115, | |
| "eval_runtime": 1.1696, | |
| "eval_samples_per_second": 83.792, | |
| "eval_steps_per_second": 0.855, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.4518675208091736, | |
| "eval_runtime": 1.2497, | |
| "eval_samples_per_second": 78.419, | |
| "eval_steps_per_second": 0.8, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.6331581473350525, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 0.4859, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7551020408163265, | |
| "eval_loss": 0.47076812386512756, | |
| "eval_runtime": 1.1678, | |
| "eval_samples_per_second": 83.921, | |
| "eval_steps_per_second": 0.856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.44281908869743347, | |
| "eval_runtime": 1.1535, | |
| "eval_samples_per_second": 84.962, | |
| "eval_steps_per_second": 0.867, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.45022523403167725, | |
| "eval_runtime": 1.1569, | |
| "eval_samples_per_second": 84.711, | |
| "eval_steps_per_second": 0.864, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4585103690624237, | |
| "eval_runtime": 1.1646, | |
| "eval_samples_per_second": 84.152, | |
| "eval_steps_per_second": 0.859, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4413427710533142, | |
| "eval_runtime": 1.1647, | |
| "eval_samples_per_second": 84.14, | |
| "eval_steps_per_second": 0.859, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4472661018371582, | |
| "eval_runtime": 1.1595, | |
| "eval_samples_per_second": 84.52, | |
| "eval_steps_per_second": 0.862, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.442340224981308, | |
| "eval_runtime": 1.2245, | |
| "eval_samples_per_second": 80.035, | |
| "eval_steps_per_second": 0.817, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.44107988476753235, | |
| "eval_runtime": 1.1697, | |
| "eval_samples_per_second": 83.784, | |
| "eval_steps_per_second": 0.855, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.43629103899002075, | |
| "eval_runtime": 1.1536, | |
| "eval_samples_per_second": 84.955, | |
| "eval_steps_per_second": 0.867, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4597272574901581, | |
| "eval_runtime": 1.1768, | |
| "eval_samples_per_second": 83.274, | |
| "eval_steps_per_second": 0.85, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.4986366033554077, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.4398, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4168866276741028, | |
| "eval_runtime": 1.161, | |
| "eval_samples_per_second": 84.413, | |
| "eval_steps_per_second": 0.861, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.42812231183052063, | |
| "eval_runtime": 1.1619, | |
| "eval_samples_per_second": 84.343, | |
| "eval_steps_per_second": 0.861, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.41872650384902954, | |
| "eval_runtime": 1.1688, | |
| "eval_samples_per_second": 83.845, | |
| "eval_steps_per_second": 0.856, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.43582549691200256, | |
| "eval_runtime": 1.2068, | |
| "eval_samples_per_second": 81.204, | |
| "eval_steps_per_second": 0.829, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7653061224489796, | |
| "eval_loss": 0.4350709319114685, | |
| "eval_runtime": 1.2449, | |
| "eval_samples_per_second": 78.72, | |
| "eval_steps_per_second": 0.803, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4329792857170105, | |
| "eval_runtime": 1.1677, | |
| "eval_samples_per_second": 83.927, | |
| "eval_steps_per_second": 0.856, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.40659093856811523, | |
| "eval_runtime": 1.154, | |
| "eval_samples_per_second": 84.918, | |
| "eval_steps_per_second": 0.867, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42853957414627075, | |
| "eval_runtime": 1.1685, | |
| "eval_samples_per_second": 83.868, | |
| "eval_steps_per_second": 0.856, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7653061224489796, | |
| "eval_loss": 0.4496270716190338, | |
| "eval_runtime": 1.1622, | |
| "eval_samples_per_second": 84.325, | |
| "eval_steps_per_second": 0.86, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.39742252230644226, | |
| "eval_runtime": 1.1891, | |
| "eval_samples_per_second": 82.413, | |
| "eval_steps_per_second": 0.841, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.5778128504753113, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.4268, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.39837557077407837, | |
| "eval_runtime": 1.1889, | |
| "eval_samples_per_second": 82.431, | |
| "eval_steps_per_second": 0.841, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4166240990161896, | |
| "eval_runtime": 1.1595, | |
| "eval_samples_per_second": 84.517, | |
| "eval_steps_per_second": 0.862, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42053714394569397, | |
| "eval_runtime": 1.168, | |
| "eval_samples_per_second": 83.903, | |
| "eval_steps_per_second": 0.856, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.43899521231651306, | |
| "eval_runtime": 1.1608, | |
| "eval_samples_per_second": 84.422, | |
| "eval_steps_per_second": 0.861, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.41976168751716614, | |
| "eval_runtime": 1.1663, | |
| "eval_samples_per_second": 84.028, | |
| "eval_steps_per_second": 0.857, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3999468684196472, | |
| "eval_runtime": 1.1522, | |
| "eval_samples_per_second": 85.051, | |
| "eval_steps_per_second": 0.868, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.4234585762023926, | |
| "eval_runtime": 1.1526, | |
| "eval_samples_per_second": 85.022, | |
| "eval_steps_per_second": 0.868, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.4313722252845764, | |
| "eval_runtime": 1.15, | |
| "eval_samples_per_second": 85.219, | |
| "eval_steps_per_second": 0.87, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.4021131694316864, | |
| "eval_runtime": 1.1683, | |
| "eval_samples_per_second": 83.886, | |
| "eval_steps_per_second": 0.856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4189140200614929, | |
| "eval_runtime": 1.1723, | |
| "eval_samples_per_second": 83.594, | |
| "eval_steps_per_second": 0.853, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.6524766087532043, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.4185, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.41430193185806274, | |
| "eval_runtime": 1.161, | |
| "eval_samples_per_second": 84.413, | |
| "eval_steps_per_second": 0.861, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.43291813135147095, | |
| "eval_runtime": 1.1491, | |
| "eval_samples_per_second": 85.281, | |
| "eval_steps_per_second": 0.87, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.42231523990631104, | |
| "eval_runtime": 1.1676, | |
| "eval_samples_per_second": 83.931, | |
| "eval_steps_per_second": 0.856, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4024517238140106, | |
| "eval_runtime": 1.1532, | |
| "eval_samples_per_second": 84.981, | |
| "eval_steps_per_second": 0.867, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.42878466844558716, | |
| "eval_runtime": 1.1683, | |
| "eval_samples_per_second": 83.884, | |
| "eval_steps_per_second": 0.856, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4215553402900696, | |
| "eval_runtime": 1.1692, | |
| "eval_samples_per_second": 83.817, | |
| "eval_steps_per_second": 0.855, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.41396430134773254, | |
| "eval_runtime": 1.1657, | |
| "eval_samples_per_second": 84.066, | |
| "eval_steps_per_second": 0.858, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3982178866863251, | |
| "eval_runtime": 1.1612, | |
| "eval_samples_per_second": 84.394, | |
| "eval_steps_per_second": 0.861, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.40849459171295166, | |
| "eval_runtime": 1.1499, | |
| "eval_samples_per_second": 85.227, | |
| "eval_steps_per_second": 0.87, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42925825715065, | |
| "eval_runtime": 1.1765, | |
| "eval_samples_per_second": 83.298, | |
| "eval_steps_per_second": 0.85, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 0.4931574761867523, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.4034, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.39117440581321716, | |
| "eval_runtime": 1.1647, | |
| "eval_samples_per_second": 84.141, | |
| "eval_steps_per_second": 0.859, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4017205238342285, | |
| "eval_runtime": 1.1624, | |
| "eval_samples_per_second": 84.311, | |
| "eval_steps_per_second": 0.86, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4331374168395996, | |
| "eval_runtime": 1.2042, | |
| "eval_samples_per_second": 81.381, | |
| "eval_steps_per_second": 0.83, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.40544551610946655, | |
| "eval_runtime": 1.1592, | |
| "eval_samples_per_second": 84.544, | |
| "eval_steps_per_second": 0.863, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3894374370574951, | |
| "eval_runtime": 1.156, | |
| "eval_samples_per_second": 84.777, | |
| "eval_steps_per_second": 0.865, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4080319404602051, | |
| "eval_runtime": 1.1486, | |
| "eval_samples_per_second": 85.321, | |
| "eval_steps_per_second": 0.871, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.40165218710899353, | |
| "eval_runtime": 1.1675, | |
| "eval_samples_per_second": 83.937, | |
| "eval_steps_per_second": 0.856, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.4095234274864197, | |
| "eval_runtime": 1.164, | |
| "eval_samples_per_second": 84.193, | |
| "eval_steps_per_second": 0.859, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42752060294151306, | |
| "eval_runtime": 1.1839, | |
| "eval_samples_per_second": 82.779, | |
| "eval_steps_per_second": 0.845, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.40013304352760315, | |
| "eval_runtime": 1.1637, | |
| "eval_samples_per_second": 84.215, | |
| "eval_steps_per_second": 0.859, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.5911010503768921, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.3955, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4125175476074219, | |
| "eval_runtime": 1.1372, | |
| "eval_samples_per_second": 86.179, | |
| "eval_steps_per_second": 0.879, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 2.86484619552768e+17, | |
| "train_loss": 0.49483771085739137, | |
| "train_runtime": 1046.6976, | |
| "train_samples_per_second": 75.571, | |
| "train_steps_per_second": 0.096 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.86484619552768e+17, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |