| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold4/checkpoint-5", | |
| "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": 0.0, | |
| "eval_loss": 2.0908453464508057, | |
| "eval_runtime": 0.176, | |
| "eval_samples_per_second": 62.496, | |
| "eval_steps_per_second": 5.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 1.8863940238952637, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.07, | |
| "eval_steps_per_second": 6.006, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 1.531255841255188, | |
| "eval_runtime": 0.1783, | |
| "eval_samples_per_second": 61.703, | |
| "eval_steps_per_second": 5.609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.36363636363636365, | |
| "eval_loss": 1.152018427848816, | |
| "eval_runtime": 0.1729, | |
| "eval_samples_per_second": 63.617, | |
| "eval_steps_per_second": 5.783, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9542110562324524, | |
| "eval_runtime": 0.1767, | |
| "eval_samples_per_second": 62.268, | |
| "eval_steps_per_second": 5.661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0324329137802124, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 64.704, | |
| "eval_steps_per_second": 5.882, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1791726350784302, | |
| "eval_runtime": 0.1753, | |
| "eval_samples_per_second": 62.76, | |
| "eval_steps_per_second": 5.705, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2680414915084839, | |
| "eval_runtime": 0.1732, | |
| "eval_samples_per_second": 63.512, | |
| "eval_steps_per_second": 5.774, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2078349590301514, | |
| "eval_runtime": 0.1753, | |
| "eval_samples_per_second": 62.764, | |
| "eval_steps_per_second": 5.706, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.6796222925186157, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4805, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.159353494644165, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.535, | |
| "eval_steps_per_second": 5.867, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1603728532791138, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 65.006, | |
| "eval_steps_per_second": 5.91, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1109801530838013, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.449, | |
| "eval_steps_per_second": 5.859, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1073939800262451, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.813, | |
| "eval_steps_per_second": 5.892, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1010178327560425, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.604, | |
| "eval_steps_per_second": 5.964, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0594475269317627, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.406, | |
| "eval_steps_per_second": 5.946, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0675151348114014, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.438, | |
| "eval_steps_per_second": 5.949, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.168864130973816, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.924, | |
| "eval_steps_per_second": 5.902, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2629767656326294, | |
| "eval_runtime": 0.1679, | |
| "eval_samples_per_second": 65.502, | |
| "eval_steps_per_second": 5.955, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3017388582229614, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.373, | |
| "eval_steps_per_second": 5.943, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.425222158432007, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1904, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3082902431488037, | |
| "eval_runtime": 0.1663, | |
| "eval_samples_per_second": 66.163, | |
| "eval_steps_per_second": 6.015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3764029741287231, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.912, | |
| "eval_steps_per_second": 6.083, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4228819608688354, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.281, | |
| "eval_steps_per_second": 5.935, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4829826354980469, | |
| "eval_runtime": 0.1675, | |
| "eval_samples_per_second": 65.667, | |
| "eval_steps_per_second": 5.97, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4698455333709717, | |
| "eval_runtime": 0.1727, | |
| "eval_samples_per_second": 63.676, | |
| "eval_steps_per_second": 5.789, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4946540594100952, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.2, | |
| "eval_steps_per_second": 5.745, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5838810205459595, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 61.761, | |
| "eval_steps_per_second": 5.615, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7219489812850952, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.317, | |
| "eval_steps_per_second": 5.847, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7473819255828857, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.576, | |
| "eval_steps_per_second": 5.961, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6644595861434937, | |
| "eval_runtime": 0.1699, | |
| "eval_samples_per_second": 64.736, | |
| "eval_steps_per_second": 5.885, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 1.4546806812286377, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1472, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5987972021102905, | |
| "eval_runtime": 0.1768, | |
| "eval_samples_per_second": 62.212, | |
| "eval_steps_per_second": 5.656, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.570302128791809, | |
| "eval_runtime": 0.1813, | |
| "eval_samples_per_second": 60.658, | |
| "eval_steps_per_second": 5.514, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5965434312820435, | |
| "eval_runtime": 0.1753, | |
| "eval_samples_per_second": 62.751, | |
| "eval_steps_per_second": 5.705, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.661800742149353, | |
| "eval_runtime": 0.1773, | |
| "eval_samples_per_second": 62.046, | |
| "eval_steps_per_second": 5.641, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6431862115859985, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 64.381, | |
| "eval_steps_per_second": 5.853, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5392369031906128, | |
| "eval_runtime": 0.1749, | |
| "eval_samples_per_second": 62.897, | |
| "eval_steps_per_second": 5.718, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4367867708206177, | |
| "eval_runtime": 0.1732, | |
| "eval_samples_per_second": 63.525, | |
| "eval_steps_per_second": 5.775, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4018795490264893, | |
| "eval_runtime": 0.1763, | |
| "eval_samples_per_second": 62.392, | |
| "eval_steps_per_second": 5.672, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4714306592941284, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.459, | |
| "eval_steps_per_second": 5.86, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7523380517959595, | |
| "eval_runtime": 0.1761, | |
| "eval_samples_per_second": 62.479, | |
| "eval_steps_per_second": 5.68, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 3.4498791694641113, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0741, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.865343451499939, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.911, | |
| "eval_steps_per_second": 5.992, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8965870141983032, | |
| "eval_runtime": 0.1763, | |
| "eval_samples_per_second": 62.394, | |
| "eval_steps_per_second": 5.672, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8252369165420532, | |
| "eval_runtime": 0.1737, | |
| "eval_samples_per_second": 63.318, | |
| "eval_steps_per_second": 5.756, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8432804346084595, | |
| "eval_runtime": 0.175, | |
| "eval_samples_per_second": 62.868, | |
| "eval_steps_per_second": 5.715, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7326781749725342, | |
| "eval_runtime": 0.1711, | |
| "eval_samples_per_second": 64.288, | |
| "eval_steps_per_second": 5.844, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.745629906654358, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.769, | |
| "eval_steps_per_second": 5.888, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.894829273223877, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.945, | |
| "eval_steps_per_second": 5.904, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8810946941375732, | |
| "eval_runtime": 0.174, | |
| "eval_samples_per_second": 63.202, | |
| "eval_steps_per_second": 5.746, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8930473327636719, | |
| "eval_runtime": 0.1802, | |
| "eval_samples_per_second": 61.031, | |
| "eval_steps_per_second": 5.548, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8065048456192017, | |
| "eval_runtime": 0.1789, | |
| "eval_samples_per_second": 61.489, | |
| "eval_steps_per_second": 5.59, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 1.586561918258667, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0506, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7629249095916748, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.915, | |
| "eval_steps_per_second": 6.174, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7893092632293701, | |
| "eval_runtime": 0.1708, | |
| "eval_samples_per_second": 64.418, | |
| "eval_steps_per_second": 5.856, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.876960277557373, | |
| "eval_runtime": 0.1703, | |
| "eval_samples_per_second": 64.587, | |
| "eval_steps_per_second": 5.872, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9144260883331299, | |
| "eval_runtime": 0.176, | |
| "eval_samples_per_second": 62.497, | |
| "eval_steps_per_second": 5.682, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0357284545898438, | |
| "eval_runtime": 0.1764, | |
| "eval_samples_per_second": 62.356, | |
| "eval_steps_per_second": 5.669, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.210261583328247, | |
| "eval_runtime": 0.1794, | |
| "eval_samples_per_second": 61.314, | |
| "eval_steps_per_second": 5.574, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.256763219833374, | |
| "eval_runtime": 0.1747, | |
| "eval_samples_per_second": 62.979, | |
| "eval_steps_per_second": 5.725, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2400619983673096, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.515, | |
| "eval_steps_per_second": 5.865, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.140550374984741, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 63.306, | |
| "eval_steps_per_second": 5.755, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.027967929840088, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.703, | |
| "eval_steps_per_second": 5.973, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.3207845091819763, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0355, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9516960382461548, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.399, | |
| "eval_steps_per_second": 5.945, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8787117004394531, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.52, | |
| "eval_steps_per_second": 5.865, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8958450555801392, | |
| "eval_runtime": 0.1776, | |
| "eval_samples_per_second": 61.949, | |
| "eval_steps_per_second": 5.632, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9893440008163452, | |
| "eval_runtime": 0.1715, | |
| "eval_samples_per_second": 64.156, | |
| "eval_steps_per_second": 5.832, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1194653511047363, | |
| "eval_runtime": 0.169, | |
| "eval_samples_per_second": 65.094, | |
| "eval_steps_per_second": 5.918, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.271503210067749, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 62.532, | |
| "eval_steps_per_second": 5.685, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.364030599594116, | |
| "eval_runtime": 0.1726, | |
| "eval_samples_per_second": 63.725, | |
| "eval_steps_per_second": 5.793, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4390556812286377, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.312, | |
| "eval_steps_per_second": 5.847, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4633097648620605, | |
| "eval_runtime": 0.1695, | |
| "eval_samples_per_second": 64.911, | |
| "eval_steps_per_second": 5.901, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.44889235496521, | |
| "eval_runtime": 0.1727, | |
| "eval_samples_per_second": 63.701, | |
| "eval_steps_per_second": 5.791, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.9859403371810913, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.021, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4176981449127197, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.773, | |
| "eval_steps_per_second": 5.888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3674123287200928, | |
| "eval_runtime": 0.1737, | |
| "eval_samples_per_second": 63.324, | |
| "eval_steps_per_second": 5.757, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.306504011154175, | |
| "eval_runtime": 0.1712, | |
| "eval_samples_per_second": 64.26, | |
| "eval_steps_per_second": 5.842, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.297823190689087, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.433, | |
| "eval_steps_per_second": 5.858, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.358968496322632, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 62.545, | |
| "eval_steps_per_second": 5.686, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4276845455169678, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 64.358, | |
| "eval_steps_per_second": 5.851, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.5219666957855225, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.046, | |
| "eval_steps_per_second": 6.004, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.6248342990875244, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.551, | |
| "eval_steps_per_second": 5.868, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.6924915313720703, | |
| "eval_runtime": 0.1781, | |
| "eval_samples_per_second": 61.76, | |
| "eval_steps_per_second": 5.615, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.7284491062164307, | |
| "eval_runtime": 0.1728, | |
| "eval_samples_per_second": 63.641, | |
| "eval_steps_per_second": 5.786, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 1.2645738124847412, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0346, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.740863084793091, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.083, | |
| "eval_steps_per_second": 6.008, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.7218360900878906, | |
| "eval_runtime": 0.1684, | |
| "eval_samples_per_second": 65.316, | |
| "eval_steps_per_second": 5.938, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.6717374324798584, | |
| "eval_runtime": 0.1706, | |
| "eval_samples_per_second": 64.491, | |
| "eval_steps_per_second": 5.863, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.614175796508789, | |
| "eval_runtime": 0.1719, | |
| "eval_samples_per_second": 64.002, | |
| "eval_steps_per_second": 5.818, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.519634485244751, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.169, | |
| "eval_steps_per_second": 6.015, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4437661170959473, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.155, | |
| "eval_steps_per_second": 5.923, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.381150007247925, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.318, | |
| "eval_steps_per_second": 5.847, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3026392459869385, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 62.625, | |
| "eval_steps_per_second": 5.693, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.269089460372925, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.567, | |
| "eval_steps_per_second": 5.87, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2665257453918457, | |
| "eval_runtime": 0.1725, | |
| "eval_samples_per_second": 63.767, | |
| "eval_steps_per_second": 5.797, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.038275957107544, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0219, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2659270763397217, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.891, | |
| "eval_steps_per_second": 6.081, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.27345609664917, | |
| "eval_runtime": 0.172, | |
| "eval_samples_per_second": 63.936, | |
| "eval_steps_per_second": 5.812, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.300039529800415, | |
| "eval_runtime": 0.1731, | |
| "eval_samples_per_second": 63.552, | |
| "eval_steps_per_second": 5.777, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.313608407974243, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.87, | |
| "eval_steps_per_second": 5.897, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.324737071990967, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.032, | |
| "eval_steps_per_second": 5.821, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3388283252716064, | |
| "eval_runtime": 0.1708, | |
| "eval_samples_per_second": 64.404, | |
| "eval_steps_per_second": 5.855, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3597023487091064, | |
| "eval_runtime": 0.1716, | |
| "eval_samples_per_second": 64.094, | |
| "eval_steps_per_second": 5.827, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3746063709259033, | |
| "eval_runtime": 0.1715, | |
| "eval_samples_per_second": 64.137, | |
| "eval_steps_per_second": 5.831, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.386420488357544, | |
| "eval_runtime": 0.1732, | |
| "eval_samples_per_second": 63.509, | |
| "eval_steps_per_second": 5.774, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.391254186630249, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 64.995, | |
| "eval_steps_per_second": 5.909, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.8429810404777527, | |
| "learning_rate": 0.0, | |
| "loss": 0.0286, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3933160305023193, | |
| "eval_runtime": 0.1621, | |
| "eval_samples_per_second": 67.872, | |
| "eval_steps_per_second": 6.17, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.572150213593088e+17, | |
| "train_loss": 0.10843914225697518, | |
| "train_runtime": 416.0402, | |
| "train_samples_per_second": 14.181, | |
| "train_steps_per_second": 0.24 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9542110562324524, | |
| "eval_runtime": 0.2165, | |
| "eval_samples_per_second": 50.803, | |
| "eval_steps_per_second": 4.618, | |
| "step": 100 | |
| } | |
| ], | |
| "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": 4.572150213593088e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |