| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0005002501250626, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.25, |
| "grad_norm": 17.20686149597168, |
| "learning_rate": 0.18999499749874937, |
| "loss": 26.5314, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 7.102985382080078, |
| "learning_rate": 0.17998999499749876, |
| "loss": 26.7788, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 5.944087505340576, |
| "learning_rate": 0.16998499249624813, |
| "loss": 24.8765, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 11.642237663269043, |
| "learning_rate": 0.15997998999499752, |
| "loss": 26.802, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9995, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 1.4909037950521344e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
