| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 2088, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0001, |
| "loss": 0.6531, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.588508129119873, |
| "eval_runtime": 243.8812, |
| "eval_samples_per_second": 13.174, |
| "eval_steps_per_second": 0.414, |
| "step": 696 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.0001, |
| "loss": 0.4828, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.5588079690933228, |
| "eval_runtime": 260.0687, |
| "eval_samples_per_second": 12.354, |
| "eval_steps_per_second": 0.388, |
| "step": 1392 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 0.0001, |
| "loss": 0.3745, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 0.0001, |
| "loss": 0.2425, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6050459146499634, |
| "eval_runtime": 257.4472, |
| "eval_samples_per_second": 12.48, |
| "eval_steps_per_second": 0.392, |
| "step": 2088 |
| } |
| ], |
| "max_steps": 3480, |
| "num_train_epochs": 5, |
| "total_flos": 35801936953344.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
