| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 31, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16260162601626016, |
| "grad_norm": 5.161210536956787, |
| "learning_rate": 9.99695413509548e-06, |
| "loss": 0.5608, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3252032520325203, |
| "grad_norm": 6.177091598510742, |
| "learning_rate": 9.890738003669029e-06, |
| "loss": 0.5238, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4878048780487805, |
| "grad_norm": 6.1841721534729, |
| "learning_rate": 9.635919272833938e-06, |
| "loss": 0.5466, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6504065040650406, |
| "grad_norm": 5.84893798828125, |
| "learning_rate": 9.24024048078213e-06, |
| "loss": 0.5678, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8130081300813008, |
| "grad_norm": 5.548550605773926, |
| "learning_rate": 8.715724127386971e-06, |
| "loss": 0.5773, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 7.234514236450195, |
| "learning_rate": 8.078307376628292e-06, |
| "loss": 0.6229, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 93, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.766990109474816e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
