{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 89.0,
      "epoch": 0.8,
      "grad_norm": 12.796066284179688,
      "kl": -9.405291101494129e-09,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 0.08149333507753909,
      "reward_std": 0.012811240874725627,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.08149333507753909,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 123.83333333333333,
      "epoch": 1.4,
      "grad_norm": 13.832069396972656,
      "kl": 0.0004440634584170766,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 0.22940764824549356,
      "reward_std": 0.08911796410878499,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.22940764824549356,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 177.0,
      "epoch": 2.0,
      "grad_norm": 12.110893249511719,
      "kl": 0.06018957828443187,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 0.04830504208803177,
      "reward_std": 0.028637274585586663,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.04830504208803177,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 165.75,
      "epoch": 2.8,
      "grad_norm": 20.28679847717285,
      "kl": 0.02037633138388628,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 0.3683655287604779,
      "reward_std": 0.31065412698080763,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.1183655287604779,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 221.16666666666666,
      "epoch": 3.4,
      "grad_norm": 26.109365463256836,
      "kl": 0.021219971890483674,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 0.10520107050736745,
      "reward_std": 0.03691515326499939,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.10520107050736745,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "epoch": 3.4,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 1.5958398580551148e-05,
      "train_runtime": 1074.2263,
      "train_samples_per_second": 0.037,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}