| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1990, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8219895287958116, |
| "eval_f1": 0.0, |
| "eval_loss": 0.49132317304611206, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 1.7872, |
| "eval_samples_per_second": 106.87, |
| "eval_steps_per_second": 26.857, |
| "step": 398 |
| }, |
| { |
| "epoch": 1.2562814070351758, |
| "grad_norm": 6.496029376983643, |
| "learning_rate": 7.641025641025641e-06, |
| "loss": 0.4705, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8219895287958116, |
| "eval_f1": 0.0, |
| "eval_loss": 0.4772607386112213, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 1.7911, |
| "eval_samples_per_second": 106.639, |
| "eval_steps_per_second": 26.799, |
| "step": 796 |
| }, |
| { |
| "epoch": 2.5125628140703515, |
| "grad_norm": 2.903648614883423, |
| "learning_rate": 5.076923076923077e-06, |
| "loss": 0.4565, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8691099476439791, |
| "eval_f1": 0.5283018867924528, |
| "eval_loss": 0.3973303735256195, |
| "eval_precision": 0.7368421052631579, |
| "eval_recall": 0.4117647058823529, |
| "eval_runtime": 1.7728, |
| "eval_samples_per_second": 107.74, |
| "eval_steps_per_second": 27.076, |
| "step": 1194 |
| }, |
| { |
| "epoch": 3.7688442211055277, |
| "grad_norm": 4.556399822235107, |
| "learning_rate": 2.512820512820513e-06, |
| "loss": 0.4506, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8952879581151832, |
| "eval_f1": 0.6153846153846154, |
| "eval_loss": 0.36605867743492126, |
| "eval_precision": 0.8888888888888888, |
| "eval_recall": 0.47058823529411764, |
| "eval_runtime": 1.7731, |
| "eval_samples_per_second": 107.721, |
| "eval_steps_per_second": 27.071, |
| "step": 1592 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8795811518324608, |
| "eval_f1": 0.6349206349206349, |
| "eval_loss": 0.30428361892700195, |
| "eval_precision": 0.6896551724137931, |
| "eval_recall": 0.5882352941176471, |
| "eval_runtime": 1.7211, |
| "eval_samples_per_second": 110.973, |
| "eval_steps_per_second": 27.889, |
| "step": 1990 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1990, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 2646564940074216.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
