{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 166.375,
      "epoch": 0.2,
      "grad_norm": 7.8710126876831055,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 0.13969262735918164,
      "reward_std": 0.07675736572127789,
      "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": 0.1313801254145801,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.008312500081956387,
      "step": 2
    },
    {
      "completion_length": 210.84375,
      "epoch": 0.4,
      "grad_norm": 10.583489418029785,
      "kl": 0.0019007577719776236,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 0.15567871063831262,
      "reward_std": 0.13674998199712718,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.10574120536330156,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.012562500312924385,
      "step": 4
    },
    {
      "completion_length": 231.125,
      "epoch": 0.6,
      "grad_norm": 4.815499305725098,
      "kl": 0.0026396787507110275,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 0.08704034402035177,
      "reward_std": 0.021835914894381858,
      "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": 0.08704034402035177,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 206.03125,
      "epoch": 0.8,
      "grad_norm": 6.467657089233398,
      "kl": 0.004467707702133339,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 0.10983941098675132,
      "reward_std": 0.06566362897220301,
      "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": 0.12530816113576293,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.015468750149011612,
      "step": 8
    },
    {
      "completion_length": 215.3125,
      "epoch": 1.0,
      "grad_norm": 5.112537860870361,
      "kl": 0.004206662057185895,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 0.2677217012969777,
      "reward_std": 0.03383033352292841,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.13856544892769307,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.004156250040978193,
      "step": 10
    },
    {
      "epoch": 1.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 3.0319672077894213e-06,
      "train_runtime": 7464.1635,
      "train_samples_per_second": 0.021,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "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
}