{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 256.0,
      "epoch": 0.4,
      "grad_norm": 2.085155963897705,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0,
      "reward": 0.3192732147872448,
      "reward_std": 0.1254079199861735,
      "rewards/<lambda>": 0.3192732147872448,
      "step": 1
    }
  ],
  "logging_steps": 1,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}