| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.5384615384615383, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.0796502828598022, |
| "eval_runtime": 1450.3858, |
| "eval_samples_per_second": 2.474, |
| "eval_steps_per_second": 0.31, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 9.743589743589744e-06, |
| "loss": 1.2984, |
| "step": 500 |
| } |
| ], |
| "max_steps": 975, |
| "num_train_epochs": 3, |
| "total_flos": 518053932000000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
