{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 0.546875,
      "learning_rate": 5e-06,
      "logits/chosen": -3.2339999675750732,
      "logits/rejected": -3.2524003982543945,
      "logps/chosen": -330.6106262207031,
      "logps/rejected": -271.2039794921875,
      "loss": 0.5011,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.037355951964855194,
      "rewards/margins": -0.008914755657315254,
      "rewards/rejected": -0.02844119817018509,
      "step": 1
    },
    {
      "epoch": 1.0,
      "step": 2,
      "total_flos": 0.0,
      "train_loss": 0.5023353099822998,
      "train_runtime": 47.6763,
      "train_samples_per_second": 0.629,
      "train_steps_per_second": 0.042
    }
  ],
  "logging_steps": 10,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}