| { |
| "best_global_step": 57, |
| "best_metric": 0.92, |
| "best_model_checkpoint": "output/checkpoint-57", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 171, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.077239513397217, |
| "learning_rate": 3.362573099415205e-05, |
| "loss": 0.2666, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.22009876370429993, |
| "eval_runtime": 0.1902, |
| "eval_samples_per_second": 525.655, |
| "eval_steps_per_second": 21.026, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.3537070751190186, |
| "learning_rate": 1.695906432748538e-05, |
| "loss": 0.2206, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.92, |
| "eval_loss": 0.24563072621822357, |
| "eval_runtime": 0.1933, |
| "eval_samples_per_second": 517.292, |
| "eval_steps_per_second": 20.692, |
| "step": 114 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.7208755016326904, |
| "learning_rate": 2.9239766081871344e-07, |
| "loss": 0.1495, |
| "step": 171 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9, |
| "eval_loss": 0.2698853015899658, |
| "eval_runtime": 0.1893, |
| "eval_samples_per_second": 528.381, |
| "eval_steps_per_second": 21.135, |
| "step": 171 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 171, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 178830988185600.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
