| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5873015873015874, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5206, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 6.392833232879639, | |
| "eval_runtime": 0.7704, | |
| "eval_samples_per_second": 129.799, | |
| "eval_steps_per_second": 9.086, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 126, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 415984426942464.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |