{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.975609756097561,
  "eval_steps": 100,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 1.2033172845840454,
      "learning_rate": 2.5e-07,
      "logits/chosen": -3.296875,
      "logits/rejected": -3.234375,
      "logps/chosen": -40.65625,
      "logps/rejected": -39.75,
      "loss": 0.6914,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.5706184506416321,
      "learning_rate": 1.6134877823936607e-07,
      "logits/chosen": -3.2595486640930176,
      "logits/rejected": -3.248914957046509,
      "logps/chosen": -39.62673568725586,
      "logps/rejected": -38.33854293823242,
      "loss": 0.6917,
      "rewards/accuracies": 0.2586805522441864,
      "rewards/chosen": 0.0023028056602925062,
      "rewards/margins": 0.0009113947744481266,
      "rewards/rejected": 0.0013909869594499469,
      "step": 10
    },
    {
      "epoch": 0.975609756097561,
      "step": 15,
      "total_flos": 0.0,
      "train_loss": 0.6916259765625,
      "train_runtime": 59.3905,
      "train_samples_per_second": 16.467,
      "train_steps_per_second": 0.253
    }
  ],
  "logging_steps": 10,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}