{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00013085579691180318,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-06,
      "logits/chosen": -2.2677314281463623,
      "logits/rejected": -2.4281933307647705,
      "logps/chosen": -220.6212615966797,
      "logps/rejected": -317.206298828125,
      "loss": 0.0999,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0,
      "step": 2,
      "total_flos": 0.0,
      "train_loss": 0.0697836373001337,
      "train_runtime": 17.89,
      "train_samples_per_second": 0.342,
      "train_steps_per_second": 0.112
    }
  ],
  "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": 2,
  "trial_name": null,
  "trial_params": null
}