| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 24544, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.7143, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7503820682628629, | |
| "eval_loss": 0.6168540120124817, | |
| "eval_runtime": 71.4698, | |
| "eval_samples_per_second": 137.331, | |
| "eval_steps_per_second": 17.168, | |
| "step": 24544 | |
| } | |
| ], | |
| "max_steps": 73632, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.98386665512448e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |