{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.7272727272727275,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 472.21875,
      "epoch": 0.7272727272727273,
      "grad_norm": 4.534781455993652,
      "kl": 0.008206730344682,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.335196889936924,
      "reward_std": 0.4634492734912783,
      "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": 0.254853137768805,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08034374378621578,
      "step": 2
    },
    {
      "completion_length": 434.25,
      "epoch": 1.3636363636363638,
      "grad_norm": 3.990346670150757,
      "kl": 0.004460517333687416,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.23956100004059927,
      "reward_std": 0.39508587813803125,
      "rewards/concensus_correctness_reward_func": 0.052571428673607964,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2285252841455596,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04153571490730558,
      "step": 4
    },
    {
      "completion_length": 320.64285714285717,
      "epoch": 2.0,
      "grad_norm": 2.0588278770446777,
      "kl": 0.11155916550861937,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "reward": 0.31050378642976284,
      "reward_std": 0.31080392096191645,
      "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": 0.2616466488689184,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.04885714128613472,
      "step": 6
    },
    {
      "completion_length": 378.03125,
      "epoch": 2.7272727272727275,
      "grad_norm": 30.297046661376953,
      "kl": 0.4378207582485629,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0004,
      "reward": 0.22754877456463873,
      "reward_std": 0.9356243578367867,
      "rewards/concensus_correctness_reward_func": 0.07725000008940697,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.23864254099316895,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.16646875580772758,
      "step": 8
    },
    {
      "completion_length": 470.35714285714283,
      "epoch": 3.3636363636363638,
      "grad_norm": 41.05766296386719,
      "kl": 4.791061709136037,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0042,
      "reward": 0.2232233083673886,
      "reward_std": 0.32254474077905926,
      "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": 0.188544737175107,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.034678573054926734,
      "step": 10
    },
    {
      "completion_length": 589.3571428571429,
      "epoch": 4.0,
      "grad_norm": 2.7544920444488525,
      "kl": 0.012513568525069527,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.36643355978386744,
      "reward_std": 0.39640770692910465,
      "rewards/concensus_correctness_reward_func": 0.052571428673607964,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2045407114284379,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1093214281967708,
      "step": 12
    },
    {
      "completion_length": 374.875,
      "epoch": 4.7272727272727275,
      "grad_norm": 1.7192025184631348,
      "kl": 0.0048929502663668245,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.30030711740255356,
      "reward_std": 0.4493426423287019,
      "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": 0.23215085780248046,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06815625180024654,
      "step": 14
    },
    {
      "completion_length": 525.7857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 2.8850600719451904,
      "kl": 0.06893503013166732,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0001,
      "reward": 0.3723179179110697,
      "reward_std": 0.6978639279093061,
      "rewards/concensus_correctness_reward_func": 0.07142857142857142,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2334607969969511,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.07542857208422252,
      "step": 16
    },
    {
      "completion_length": 356.7142857142857,
      "epoch": 6.0,
      "grad_norm": 36.78139114379883,
      "kl": 0.10154176016970139,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0001,
      "reward": 0.4411936615194593,
      "reward_std": 0.49921108103756395,
      "rewards/concensus_correctness_reward_func": 0.07142857142857142,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.21180081207837378,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.015107142073767526,
      "step": 18
    },
    {
      "completion_length": 408.0625,
      "epoch": 6.7272727272727275,
      "grad_norm": 1.6329376697540283,
      "kl": 0.006408709974493831,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.37784312618896365,
      "reward_std": 0.4983527325093746,
      "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": 0.19749936903826892,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18034374713897705,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0004911098741558817,
      "train_runtime": 327.6226,
      "train_samples_per_second": 0.977,
      "train_steps_per_second": 0.061
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}