| { | |
| "best_metric": 0.6506678662586591, | |
| "best_model_checkpoint": "tmp_ner_fantastic-bale-19_38/run-25/checkpoint-660", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 660, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8553461689937804, | |
| "eval_loss": 0.47332701086997986, | |
| "eval_macro_f1": 0.5179058864521847, | |
| "eval_macro_precision": 0.5969084028407209, | |
| "eval_macro_recall": 0.5063081060851987, | |
| "eval_runtime": 5.987, | |
| "eval_samples_per_second": 146.651, | |
| "eval_steps_per_second": 18.373, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8667526175384364, | |
| "eval_loss": 0.423623263835907, | |
| "eval_macro_f1": 0.6126875404495669, | |
| "eval_macro_precision": 0.6399554829251698, | |
| "eval_macro_recall": 0.6102712004848894, | |
| "eval_runtime": 5.9737, | |
| "eval_samples_per_second": 146.978, | |
| "eval_steps_per_second": 18.414, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8703603248794335, | |
| "eval_loss": 0.4243398904800415, | |
| "eval_macro_f1": 0.6335065301362576, | |
| "eval_macro_precision": 0.6801343369395938, | |
| "eval_macro_recall": 0.6289027870007556, | |
| "eval_runtime": 5.9773, | |
| "eval_samples_per_second": 146.888, | |
| "eval_steps_per_second": 18.403, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "grad_norm": 0.778854250907898, | |
| "learning_rate": 9.035786517978707e-05, | |
| "loss": 0.5906, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8725375818329085, | |
| "eval_loss": 0.43925729393959045, | |
| "eval_macro_f1": 0.6506678662586591, | |
| "eval_macro_precision": 0.6623715223268644, | |
| "eval_macro_recall": 0.6448063227018537, | |
| "eval_runtime": 5.9602, | |
| "eval_samples_per_second": 147.311, | |
| "eval_steps_per_second": 18.456, | |
| "step": 660 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 32, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3213359444608236.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.767344966191627e-05, | |
| "per_device_train_batch_size": 16, | |
| "warmup_ratio": 0.021367464793327073, | |
| "weight_decay": 0.025286446963170207 | |
| } | |
| } | |