| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 24591, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.3901427351470052e-05, | |
| "loss": 0.1006, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.972805888299768, | |
| "eval_f1": 0.9542635564090959, | |
| "eval_loss": 0.07431062310934067, | |
| "eval_precision": 0.9702985074626865, | |
| "eval_recall": 0.9387499699164882, | |
| "eval_runtime": 29.2474, | |
| "eval_samples_per_second": 236.021, | |
| "eval_steps_per_second": 14.771, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.780407466146151e-05, | |
| "loss": 0.0687, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.9766388107030903, | |
| "eval_f1": 0.9604958921631328, | |
| "eval_loss": 0.06732712686061859, | |
| "eval_precision": 0.9821666624745328, | |
| "eval_recall": 0.9397607759139371, | |
| "eval_runtime": 28.7775, | |
| "eval_samples_per_second": 239.875, | |
| "eval_steps_per_second": 15.012, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.170550201293156e-05, | |
| "loss": 0.0555, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.9789952943058919, | |
| "eval_f1": 0.9645339555446395, | |
| "eval_loss": 0.06241472437977791, | |
| "eval_precision": 0.9847538804884777, | |
| "eval_recall": 0.9451276744242015, | |
| "eval_runtime": 28.8228, | |
| "eval_samples_per_second": 239.498, | |
| "eval_steps_per_second": 14.988, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.610589239965841e-06, | |
| "loss": 0.0444, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.9803844559359386, | |
| "eval_f1": 0.9670321610620118, | |
| "eval_loss": 0.06139765679836273, | |
| "eval_precision": 0.9825864467408585, | |
| "eval_recall": 0.9519626483117133, | |
| "eval_runtime": 29.0028, | |
| "eval_samples_per_second": 238.011, | |
| "eval_steps_per_second": 14.895, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 24591, | |
| "total_flos": 3.1729035119402496e+16, | |
| "train_loss": 0.06211166688984918, | |
| "train_runtime": 4046.4754, | |
| "train_samples_per_second": 97.228, | |
| "train_steps_per_second": 6.077 | |
| } | |
| ], | |
| "max_steps": 24591, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.1729035119402496e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |