{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 489.4166666666667,
      "epoch": 1.0,
      "kl": 0.0,
      "reward": 0.8493689298629761,
      "reward_std": 0.9399438500404358,
      "rewards/accuracy_reward": 0.4166666666666667,
      "rewards/cosine_scaled_reward": 0.12714668611685434,
      "rewards/format_reward": 0.0,
      "rewards/reasoning_steps_reward": 0.3055555671453476,
      "step": 1,
      "total_flos": 0.0,
      "train_loss": 1.862645149230957e-09,
      "train_runtime": 136.0453,
      "train_samples_per_second": 0.044,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 5,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}