| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11940298507462686, |
| "eval_steps": 500, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03980099502487562, |
| "grad_norm": 9.524229049682617, |
| "learning_rate": 4.980474401576887e-07, |
| "logits/chosen": -0.1925463080406189, |
| "logits/rejected": -0.15873177349567413, |
| "logps/chosen": -239.6322021484375, |
| "logps/rejected": -242.57594299316406, |
| "loss": 0.8819, |
| "rewards/accuracies": 0.49281251430511475, |
| "rewards/chosen": -1.3072433471679688, |
| "rewards/margins": 0.008615786209702492, |
| "rewards/rejected": -1.315859079360962, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07960199004975124, |
| "grad_norm": 7.333236217498779, |
| "learning_rate": 4.922202605502572e-07, |
| "logits/chosen": 0.046361636370420456, |
| "logits/rejected": 0.08236894011497498, |
| "logps/chosen": -231.10765075683594, |
| "logps/rejected": -233.24984741210938, |
| "loss": 0.8361, |
| "rewards/accuracies": 0.48875001072883606, |
| "rewards/chosen": -0.9621695876121521, |
| "rewards/margins": -0.021255964413285255, |
| "rewards/rejected": -0.9409136772155762, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11940298507462686, |
| "grad_norm": 5.164106369018555, |
| "learning_rate": 4.82609484512869e-07, |
| "logits/chosen": 0.0250965878367424, |
| "logits/rejected": 0.054141998291015625, |
| "logps/chosen": -229.79965209960938, |
| "logps/rejected": -231.60562133789062, |
| "loss": 0.8114, |
| "rewards/accuracies": 0.48750001192092896, |
| "rewards/chosen": -0.8564431667327881, |
| "rewards/margins": -0.01034404058009386, |
| "rewards/rejected": -0.8460990786552429, |
| "step": 300 |
| } |
| ], |
| "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 |
| } |
|
|
