| { | |
| "best_metric": 0.8278869986534119, | |
| "best_model_checkpoint": "verbnet_train/checkpoint-20820", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 20820, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 13.90185260772705, | |
| "learning_rate": 1.960034582132565e-05, | |
| "loss": 1.9688, | |
| "step": 10410 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0218104124069214, | |
| "eval_runtime": 27.1535, | |
| "eval_samples_per_second": 161.453, | |
| "eval_steps_per_second": 20.182, | |
| "step": 10410 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 35.40193176269531, | |
| "learning_rate": 1.9200499519692607e-05, | |
| "loss": 0.9642, | |
| "step": 20820 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8278869986534119, | |
| "eval_runtime": 27.1826, | |
| "eval_samples_per_second": 161.28, | |
| "eval_steps_per_second": 20.16, | |
| "step": 20820 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 520500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.847222160724723e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |