| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12978585334198572, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12978585334198572, | |
| "grad_norm": 64.38245391845703, | |
| "learning_rate": 5e-07, | |
| "logits/chosen": -1.9029332399368286, | |
| "logits/rejected": -2.053706407546997, | |
| "logps/chosen": -40.4902458190918, | |
| "logps/rejected": -25.3558406829834, | |
| "loss": 0.5968, | |
| "rewards/accuracies": 0.800000011920929, | |
| "rewards/chosen": 0.17978771030902863, | |
| "rewards/margins": 0.2116149365901947, | |
| "rewards/rejected": -0.031827230006456375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12978585334198572, | |
| "eval_logits/chosen": -1.9241564273834229, | |
| "eval_logits/rejected": -2.0354554653167725, | |
| "eval_logps/chosen": -38.01565933227539, | |
| "eval_logps/rejected": -26.247798919677734, | |
| "eval_loss": 0.454921156167984, | |
| "eval_rewards/accuracies": 1.0, | |
| "eval_rewards/chosen": 0.4693543612957001, | |
| "eval_rewards/margins": 0.5530296564102173, | |
| "eval_rewards/rejected": -0.083675317466259, | |
| "eval_runtime": 140.2735, | |
| "eval_samples_per_second": 0.585, | |
| "eval_steps_per_second": 0.585, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 384, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |