{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9473684210526315,
  "eval_steps": 1000,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.229126261001155,
      "learning_rate": 5e-07,
      "logits/chosen": -2.720445156097412,
      "logits/rejected": -2.7002451419830322,
      "logps/chosen": -348.28216552734375,
      "logps/rejected": -279.3660888671875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.9473684210526315,
      "step": 9,
      "total_flos": 0.0,
      "train_loss": 0.6919338438245985,
      "train_runtime": 257.607,
      "train_samples_per_second": 37.685,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 9,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}