| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1594202898550725, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0002, |
| "loss": 2.8625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0002, |
| "loss": 2.8987, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0002, |
| "loss": 2.7552, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002, |
| "loss": 2.8627, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.0002, |
| "loss": 2.6602, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0002, |
| "loss": 2.8089, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0002, |
| "loss": 2.7102, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002, |
| "loss": 2.772, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002, |
| "loss": 2.6953, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0002, |
| "loss": 2.6401, |
| "step": 100 |
| } |
| ], |
| "max_steps": 500, |
| "num_train_epochs": 6, |
| "total_flos": 4769254721473536.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
