| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.303030303030305, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6893180012702942, | |
| "eval_runtime": 28.4889, | |
| "eval_samples_per_second": 18.218, | |
| "eval_steps_per_second": 1.158, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3626828193664551, | |
| "eval_runtime": 29.737, | |
| "eval_samples_per_second": 17.453, | |
| "eval_steps_per_second": 1.11, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.21266968548297882, | |
| "eval_runtime": 28.4545, | |
| "eval_samples_per_second": 18.24, | |
| "eval_steps_per_second": 1.16, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.1356026828289032, | |
| "eval_runtime": 28.8969, | |
| "eval_samples_per_second": 17.96, | |
| "eval_steps_per_second": 1.142, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.09372802078723907, | |
| "eval_runtime": 42.6352, | |
| "eval_samples_per_second": 12.173, | |
| "eval_steps_per_second": 0.774, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.06550699472427368, | |
| "eval_runtime": 30.8112, | |
| "eval_samples_per_second": 16.845, | |
| "eval_steps_per_second": 1.071, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.04331357032060623, | |
| "eval_runtime": 138.921, | |
| "eval_samples_per_second": 3.736, | |
| "eval_steps_per_second": 0.238, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.030439287424087524, | |
| "eval_runtime": 29.4747, | |
| "eval_samples_per_second": 17.608, | |
| "eval_steps_per_second": 1.12, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.02328161522746086, | |
| "eval_runtime": 42.9504, | |
| "eval_samples_per_second": 12.084, | |
| "eval_steps_per_second": 0.768, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.015175359323620796, | |
| "eval_runtime": 34.7922, | |
| "eval_samples_per_second": 14.917, | |
| "eval_steps_per_second": 0.948, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.011942080222070217, | |
| "eval_runtime": 33.7878, | |
| "eval_samples_per_second": 15.361, | |
| "eval_steps_per_second": 0.977, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.011739258654415607, | |
| "eval_runtime": 33.1657, | |
| "eval_samples_per_second": 15.649, | |
| "eval_steps_per_second": 0.995, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.00850769504904747, | |
| "eval_runtime": 26.9611, | |
| "eval_samples_per_second": 19.25, | |
| "eval_steps_per_second": 1.224, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.008818953298032284, | |
| "eval_runtime": 25.3516, | |
| "eval_samples_per_second": 20.472, | |
| "eval_steps_per_second": 1.302, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.0071915010921657085, | |
| "eval_runtime": 29.0211, | |
| "eval_samples_per_second": 17.884, | |
| "eval_steps_per_second": 1.137, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 1.2424242424242425e-05, | |
| "loss": 0.172, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.0059341141022741795, | |
| "eval_runtime": 27.1402, | |
| "eval_samples_per_second": 19.123, | |
| "eval_steps_per_second": 1.216, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.0058893621899187565, | |
| "eval_runtime": 65.963, | |
| "eval_samples_per_second": 7.868, | |
| "eval_steps_per_second": 0.5, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.005850458517670631, | |
| "eval_runtime": 41.3311, | |
| "eval_samples_per_second": 12.557, | |
| "eval_steps_per_second": 0.798, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.004295774735510349, | |
| "eval_runtime": 46.3744, | |
| "eval_samples_per_second": 11.192, | |
| "eval_steps_per_second": 0.712, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.004227998200803995, | |
| "eval_runtime": 41.1438, | |
| "eval_samples_per_second": 12.614, | |
| "eval_steps_per_second": 0.802, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.004431780893355608, | |
| "eval_runtime": 41.907, | |
| "eval_samples_per_second": 12.385, | |
| "eval_steps_per_second": 0.787, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.0034626370761543512, | |
| "eval_runtime": 41.1621, | |
| "eval_samples_per_second": 12.609, | |
| "eval_steps_per_second": 0.802, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.0033035443630069494, | |
| "eval_runtime": 44.2482, | |
| "eval_samples_per_second": 11.729, | |
| "eval_steps_per_second": 0.746, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.003542479360476136, | |
| "eval_runtime": 42.5796, | |
| "eval_samples_per_second": 12.189, | |
| "eval_steps_per_second": 0.775, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.00354805332608521, | |
| "eval_runtime": 40.0541, | |
| "eval_samples_per_second": 12.957, | |
| "eval_steps_per_second": 0.824, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.002963385311886668, | |
| "eval_runtime": 41.546, | |
| "eval_samples_per_second": 12.492, | |
| "eval_steps_per_second": 0.794, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.0030358233489096165, | |
| "eval_runtime": 48.7828, | |
| "eval_samples_per_second": 10.639, | |
| "eval_steps_per_second": 0.676, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.002670546527951956, | |
| "eval_runtime": 40.7799, | |
| "eval_samples_per_second": 12.727, | |
| "eval_steps_per_second": 0.809, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.002638536971062422, | |
| "eval_runtime": 69.2191, | |
| "eval_samples_per_second": 7.498, | |
| "eval_steps_per_second": 0.477, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.002552107907831669, | |
| "eval_runtime": 47.5572, | |
| "eval_samples_per_second": 10.913, | |
| "eval_steps_per_second": 0.694, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 0.0077, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1320, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 278856790097838.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |