| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 2290, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.18, |
| "learning_rate": 3.9082969432314415e-05, |
| "loss": 3.054, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.37, |
| "learning_rate": 2.816593886462882e-05, |
| "loss": 1.7043, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.55, |
| "learning_rate": 1.7248908296943234e-05, |
| "loss": 0.9559, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 6.3318777292576415e-06, |
| "loss": 0.506, |
| "step": 2000 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2290, |
| "total_flos": 1.0748652547325952e+16, |
| "train_loss": 1.3998875747080974, |
| "train_runtime": 1281.7447, |
| "train_samples_per_second": 17.843, |
| "train_steps_per_second": 1.787 |
| } |
| ], |
| "max_steps": 2290, |
| "num_train_epochs": 10, |
| "total_flos": 1.0748652547325952e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
