{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 4.0,
      "epoch": 0.4,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 3.9470547437667847,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 1.9209999963641167,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.02605471372953616,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 4.0,
      "epoch": 0.8,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.5e-07,
      "loss": 0.0,
      "reward": 4.084178194403648,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.044749990105629,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.03942817114875652,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 4.0,
      "epoch": 1.0,
      "kl": 0.0,
      "reward": 4.204539239406586,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.1720000207424164,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.03253922890871763,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 5,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 1000.8854,
      "train_samples_per_second": 0.08,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 2,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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
}