| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 13094, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.44370460510254, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.3365, | |
| "step": 6547 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9064616511074501, | |
| "eval_loss": 0.23984280228614807, | |
| "eval_runtime": 23.1983, | |
| "eval_samples_per_second": 235.492, | |
| "eval_steps_per_second": 29.442, | |
| "step": 6547 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.31856870651245117, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1938, | |
| "step": 13094 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9108548416620904, | |
| "eval_loss": 0.2898029088973999, | |
| "eval_runtime": 23.2441, | |
| "eval_samples_per_second": 235.027, | |
| "eval_steps_per_second": 29.384, | |
| "step": 13094 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 19641, | |
| "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": 5.511808254314496e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |