| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold5/checkpoint-4", | |
| "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": 0.2727272727272727, | |
| "eval_loss": 1.3529654741287231, | |
| "eval_runtime": 0.1719, | |
| "eval_samples_per_second": 64.009, | |
| "eval_steps_per_second": 5.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2727272727272727, | |
| "eval_loss": 1.1775329113006592, | |
| "eval_runtime": 0.1803, | |
| "eval_samples_per_second": 61.012, | |
| "eval_steps_per_second": 5.547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5454545454545454, | |
| "eval_loss": 0.9127957820892334, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 62.634, | |
| "eval_steps_per_second": 5.694, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7291980385780334, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.037, | |
| "eval_steps_per_second": 5.822, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7752578854560852, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.839, | |
| "eval_steps_per_second": 5.894, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9951526522636414, | |
| "eval_runtime": 0.1716, | |
| "eval_samples_per_second": 64.099, | |
| "eval_steps_per_second": 5.827, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1799362897872925, | |
| "eval_runtime": 0.1737, | |
| "eval_samples_per_second": 63.314, | |
| "eval_steps_per_second": 5.756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2698947191238403, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.189, | |
| "eval_steps_per_second": 5.744, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2729337215423584, | |
| "eval_runtime": 0.1654, | |
| "eval_samples_per_second": 66.495, | |
| "eval_steps_per_second": 6.045, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.2218341827392578, | |
| "learning_rate": 5e-05, | |
| "loss": 0.38, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2450836896896362, | |
| "eval_runtime": 0.1667, | |
| "eval_samples_per_second": 65.993, | |
| "eval_steps_per_second": 5.999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2340657711029053, | |
| "eval_runtime": 0.1699, | |
| "eval_samples_per_second": 64.761, | |
| "eval_steps_per_second": 5.887, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2152786254882812, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.166, | |
| "eval_steps_per_second": 5.742, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.184658408164978, | |
| "eval_runtime": 0.1684, | |
| "eval_samples_per_second": 65.309, | |
| "eval_steps_per_second": 5.937, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.190322995185852, | |
| "eval_runtime": 0.1708, | |
| "eval_samples_per_second": 64.413, | |
| "eval_steps_per_second": 5.856, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.21282160282135, | |
| "eval_runtime": 0.1699, | |
| "eval_samples_per_second": 64.74, | |
| "eval_steps_per_second": 5.885, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.172433853149414, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.186, | |
| "eval_steps_per_second": 5.744, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0705375671386719, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.561, | |
| "eval_steps_per_second": 5.869, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.010569453239441, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.128, | |
| "eval_steps_per_second": 5.921, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0238350629806519, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.124, | |
| "eval_steps_per_second": 6.011, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.2547463178634644, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0593870878219604, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.431, | |
| "eval_steps_per_second": 6.13, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1695011854171753, | |
| "eval_runtime": 0.189, | |
| "eval_samples_per_second": 58.212, | |
| "eval_steps_per_second": 5.292, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2465709447860718, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.775, | |
| "eval_steps_per_second": 5.889, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2861061096191406, | |
| "eval_runtime": 0.1673, | |
| "eval_samples_per_second": 65.737, | |
| "eval_steps_per_second": 5.976, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.279003381729126, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.467, | |
| "eval_steps_per_second": 6.042, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.31769859790802, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.184, | |
| "eval_steps_per_second": 5.926, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.413009524345398, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.178, | |
| "eval_steps_per_second": 5.925, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5154972076416016, | |
| "eval_runtime": 0.1702, | |
| "eval_samples_per_second": 64.632, | |
| "eval_steps_per_second": 5.876, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6224372386932373, | |
| "eval_runtime": 0.1671, | |
| "eval_samples_per_second": 65.816, | |
| "eval_steps_per_second": 5.983, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5918177366256714, | |
| "eval_runtime": 0.1724, | |
| "eval_samples_per_second": 63.792, | |
| "eval_steps_per_second": 5.799, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.9141814708709717, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0904, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4098824262619019, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.547, | |
| "eval_steps_per_second": 5.868, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.268126368522644, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.13, | |
| "eval_steps_per_second": 5.921, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1371163129806519, | |
| "eval_runtime": 0.1754, | |
| "eval_samples_per_second": 62.723, | |
| "eval_steps_per_second": 5.702, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0387264490127563, | |
| "eval_runtime": 0.1708, | |
| "eval_samples_per_second": 64.417, | |
| "eval_steps_per_second": 5.856, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.012789011001587, | |
| "eval_runtime": 0.1768, | |
| "eval_samples_per_second": 62.211, | |
| "eval_steps_per_second": 5.656, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0423420667648315, | |
| "eval_runtime": 0.1748, | |
| "eval_samples_per_second": 62.928, | |
| "eval_steps_per_second": 5.721, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1729811429977417, | |
| "eval_runtime": 0.1734, | |
| "eval_samples_per_second": 63.442, | |
| "eval_steps_per_second": 5.767, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3305331468582153, | |
| "eval_runtime": 0.1765, | |
| "eval_samples_per_second": 62.331, | |
| "eval_steps_per_second": 5.666, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.382030725479126, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 61.34, | |
| "eval_steps_per_second": 5.576, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3681752681732178, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.605, | |
| "eval_steps_per_second": 5.964, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 1.4764775037765503, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.285431981086731, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 64.708, | |
| "eval_steps_per_second": 5.883, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2000277042388916, | |
| "eval_runtime": 0.1713, | |
| "eval_samples_per_second": 64.199, | |
| "eval_steps_per_second": 5.836, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.207851767539978, | |
| "eval_runtime": 0.1864, | |
| "eval_samples_per_second": 58.998, | |
| "eval_steps_per_second": 5.363, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2967201471328735, | |
| "eval_runtime": 0.1746, | |
| "eval_samples_per_second": 63.0, | |
| "eval_steps_per_second": 5.727, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3672311305999756, | |
| "eval_runtime": 0.1673, | |
| "eval_samples_per_second": 65.735, | |
| "eval_steps_per_second": 5.976, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.370935082435608, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.553, | |
| "eval_steps_per_second": 5.868, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4370254278182983, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.189, | |
| "eval_steps_per_second": 6.017, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.486308217048645, | |
| "eval_runtime": 0.1673, | |
| "eval_samples_per_second": 65.742, | |
| "eval_steps_per_second": 5.977, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5696362257003784, | |
| "eval_runtime": 0.1724, | |
| "eval_samples_per_second": 63.797, | |
| "eval_steps_per_second": 5.8, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5678352117538452, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.684, | |
| "eval_steps_per_second": 5.88, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 1.1623984575271606, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0289, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.544366717338562, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.677, | |
| "eval_steps_per_second": 5.88, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5086143016815186, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 64.71, | |
| "eval_steps_per_second": 5.883, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4332855939865112, | |
| "eval_runtime": 0.1809, | |
| "eval_samples_per_second": 60.823, | |
| "eval_steps_per_second": 5.529, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.364355206489563, | |
| "eval_runtime": 0.1768, | |
| "eval_samples_per_second": 62.214, | |
| "eval_steps_per_second": 5.656, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3098602294921875, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.295, | |
| "eval_steps_per_second": 5.936, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3354856967926025, | |
| "eval_runtime": 0.174, | |
| "eval_samples_per_second": 63.234, | |
| "eval_steps_per_second": 5.749, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.428562045097351, | |
| "eval_runtime": 0.1728, | |
| "eval_samples_per_second": 63.669, | |
| "eval_steps_per_second": 5.788, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6121271848678589, | |
| "eval_runtime": 0.1744, | |
| "eval_samples_per_second": 63.061, | |
| "eval_steps_per_second": 5.733, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8074326515197754, | |
| "eval_runtime": 0.1723, | |
| "eval_samples_per_second": 63.851, | |
| "eval_steps_per_second": 5.805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9460711479187012, | |
| "eval_runtime": 0.1782, | |
| "eval_samples_per_second": 61.729, | |
| "eval_steps_per_second": 5.612, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.7182336449623108, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0342, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0313925743103027, | |
| "eval_runtime": 0.1782, | |
| "eval_samples_per_second": 61.712, | |
| "eval_steps_per_second": 5.61, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0407793521881104, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.12, | |
| "eval_steps_per_second": 5.92, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.047626495361328, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.868, | |
| "eval_steps_per_second": 5.897, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.051710605621338, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.196, | |
| "eval_steps_per_second": 5.745, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.021721601486206, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.951, | |
| "eval_steps_per_second": 5.996, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9581713676452637, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.17, | |
| "eval_steps_per_second": 5.743, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8824611902236938, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.782, | |
| "eval_steps_per_second": 5.889, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8085075616836548, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.719, | |
| "eval_steps_per_second": 5.974, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.787988305091858, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 64.058, | |
| "eval_steps_per_second": 5.823, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7796345949172974, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.61, | |
| "eval_steps_per_second": 5.965, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.4171023368835449, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0203, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7929339408874512, | |
| "eval_runtime": 0.1647, | |
| "eval_samples_per_second": 66.786, | |
| "eval_steps_per_second": 6.071, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8213086128234863, | |
| "eval_runtime": 0.1752, | |
| "eval_samples_per_second": 62.779, | |
| "eval_steps_per_second": 5.707, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8387740850448608, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.032, | |
| "eval_steps_per_second": 5.821, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8488353490829468, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.475, | |
| "eval_steps_per_second": 5.952, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8752758502960205, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.926, | |
| "eval_steps_per_second": 5.993, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9079365730285645, | |
| "eval_runtime": 0.175, | |
| "eval_samples_per_second": 62.846, | |
| "eval_steps_per_second": 5.713, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9395884275436401, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.091, | |
| "eval_steps_per_second": 6.008, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9556442499160767, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.665, | |
| "eval_steps_per_second": 5.879, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9590537548065186, | |
| "eval_runtime": 0.167, | |
| "eval_samples_per_second": 65.861, | |
| "eval_steps_per_second": 5.987, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.966783881187439, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 66.993, | |
| "eval_steps_per_second": 6.09, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.9364380836486816, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0324, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9864659309387207, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.403, | |
| "eval_steps_per_second": 6.128, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0098299980163574, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.144, | |
| "eval_steps_per_second": 5.922, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0383646488189697, | |
| "eval_runtime": 0.1676, | |
| "eval_samples_per_second": 65.648, | |
| "eval_steps_per_second": 5.968, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0658936500549316, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.949, | |
| "eval_steps_per_second": 5.904, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0952181816101074, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.585, | |
| "eval_steps_per_second": 5.962, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1068856716156006, | |
| "eval_runtime": 0.1624, | |
| "eval_samples_per_second": 67.74, | |
| "eval_steps_per_second": 6.158, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.113046407699585, | |
| "eval_runtime": 0.1693, | |
| "eval_samples_per_second": 64.983, | |
| "eval_steps_per_second": 5.908, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.118079423904419, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.591, | |
| "eval_steps_per_second": 5.963, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.117971658706665, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.217, | |
| "eval_steps_per_second": 6.02, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1172935962677, | |
| "eval_runtime": 0.1659, | |
| "eval_samples_per_second": 66.288, | |
| "eval_steps_per_second": 6.026, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 0.6589764356613159, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0244, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1193482875823975, | |
| "eval_runtime": 0.166, | |
| "eval_samples_per_second": 66.245, | |
| "eval_steps_per_second": 6.022, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.122624158859253, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.724, | |
| "eval_steps_per_second": 6.066, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1255929470062256, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.403, | |
| "eval_steps_per_second": 6.037, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.131207227706909, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.802, | |
| "eval_steps_per_second": 5.982, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.133344888687134, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.457, | |
| "eval_steps_per_second": 6.132, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1370675563812256, | |
| "eval_runtime": 0.2387, | |
| "eval_samples_per_second": 46.081, | |
| "eval_steps_per_second": 4.189, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1412885189056396, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.79, | |
| "eval_steps_per_second": 5.981, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.143777370452881, | |
| "eval_runtime": 0.1595, | |
| "eval_samples_per_second": 68.985, | |
| "eval_steps_per_second": 6.271, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.14536452293396, | |
| "eval_runtime": 0.173, | |
| "eval_samples_per_second": 63.578, | |
| "eval_steps_per_second": 5.78, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1451478004455566, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.109, | |
| "eval_steps_per_second": 6.192, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 1.9433962106704712, | |
| "learning_rate": 0.0, | |
| "loss": 0.027, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1447601318359375, | |
| "eval_runtime": 0.1574, | |
| "eval_samples_per_second": 69.896, | |
| "eval_steps_per_second": 6.354, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.572150213593088e+17, | |
| "train_loss": 0.0869519267976284, | |
| "train_runtime": 406.2726, | |
| "train_samples_per_second": 14.522, | |
| "train_steps_per_second": 0.246 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7291980385780334, | |
| "eval_runtime": 0.2173, | |
| "eval_samples_per_second": 50.614, | |
| "eval_steps_per_second": 4.601, | |
| "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 | |
| } | |