| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 8420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.1736228466033936, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.221, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9254587155963303, | |
| "eval_loss": 0.24894081056118011, | |
| "eval_runtime": 4.0813, | |
| "eval_samples_per_second": 213.657, | |
| "eval_steps_per_second": 26.707, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 43.896240234375, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1201, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9139908256880734, | |
| "eval_loss": 0.29328054189682007, | |
| "eval_runtime": 4.1012, | |
| "eval_samples_per_second": 212.62, | |
| "eval_steps_per_second": 26.578, | |
| "step": 8420 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12630, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.544053293488128e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |