| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6122448979591837, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.40816326530612246, |
| "grad_norm": 8.868049621582031, |
| "learning_rate": 1.6234898018587336e-06, |
| "logits/chosen": -1.558059573173523, |
| "logits/rejected": -2.4096293449401855, |
| "logps/chosen": -525.1146850585938, |
| "logps/rejected": -424.7851867675781, |
| "loss": 0.4797, |
| "rewards/accuracies": 0.717968761920929, |
| "rewards/chosen": 0.8314700126647949, |
| "rewards/margins": 0.73275226354599, |
| "rewards/rejected": 0.09871769696474075, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 24, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.7146746239280742e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
