| { | |
| "best_global_step": 118, | |
| "best_metric": 0.31218037009239197, | |
| "best_model_checkpoint": "./fine-tuned-model-8\\checkpoint-118", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 118, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8519701810436635, | |
| "grad_norm": 0.3398423194885254, | |
| "learning_rate": 3.655172413793104e-05, | |
| "loss": 0.7607, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.41808420419692993, | |
| "eval_runtime": 179.321, | |
| "eval_samples_per_second": 0.586, | |
| "eval_steps_per_second": 0.586, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.698615548455804, | |
| "grad_norm": 0.16843748092651367, | |
| "learning_rate": 3.310344827586207e-05, | |
| "loss": 0.2266, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.31218037009239197, | |
| "eval_runtime": 179.2637, | |
| "eval_samples_per_second": 0.586, | |
| "eval_steps_per_second": 0.586, | |
| "step": 118 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 580, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 4.578334359434035e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |