| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0, |
| "eval_steps": 500, |
| "global_step": 0, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_loss": 1.851607322692871, |
| "eval_runtime": 2.1728, |
| "eval_samples_per_second": 60.75, |
| "eval_steps_per_second": 2.301, |
| "step": 0 |
| }, |
| { |
| "epoch": 0, |
| "eval_loss": 1.8677929639816284, |
| "eval_runtime": 1.5067, |
| "eval_samples_per_second": 87.607, |
| "eval_steps_per_second": 3.318, |
| "step": 0 |
| }, |
| { |
| "epoch": 0, |
| "step": 0, |
| "total_flos": 85819486371840.0, |
| "train_loss": 0.15227320790290833, |
| "train_runtime": 75.1479, |
| "train_samples_per_second": 31.405, |
| "train_steps_per_second": 0.027 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 85819486371840.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
