| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.7299, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6923056840896606, | |
| "eval_runtime": 0.73, | |
| "eval_samples_per_second": 97.265, | |
| "eval_steps_per_second": 12.329, | |
| "step": 40 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 5, | |
| "total_flos": 167075520153600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |