| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.07960199004975124, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03980099502487562, |
| "grad_norm": 2.466599941253662, |
| "learning_rate": 4.980474401576887e-07, |
| "logits/chosen": -1.0382839441299438, |
| "logits/rejected": -1.054585576057434, |
| "logps/chosen": -180.16372680664062, |
| "logps/rejected": -179.63958740234375, |
| "loss": 0.7169, |
| "rewards/accuracies": 0.508593738079071, |
| "rewards/chosen": -0.278283029794693, |
| "rewards/margins": 0.017729664221405983, |
| "rewards/rejected": -0.2960126996040344, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07960199004975124, |
| "grad_norm": 1.6285502910614014, |
| "learning_rate": 4.922202605502572e-07, |
| "logits/chosen": -1.0206574201583862, |
| "logits/rejected": -1.0379180908203125, |
| "logps/chosen": -180.13119506835938, |
| "logps/rejected": -180.29315185546875, |
| "loss": 0.7103, |
| "rewards/accuracies": 0.5193750262260437, |
| "rewards/chosen": -0.2392772138118744, |
| "rewards/margins": 0.0195913203060627, |
| "rewards/rejected": -0.2588685154914856, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2512, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
