{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "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": 188.25,
      "epoch": 0.5714285714285714,
      "grad_norm": 294.656005859375,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 2.8357814326882362,
      "reward_std": 1.259905411321597,
      "rewards/concensus_correctness_reward_func": 0.5761874951422215,
      "rewards/consensus_reward_func": 0.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.6327814008109272,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.109375,
      "rewards/xmlcount_reward_func": 0.7674374980852008,
      "step": 2
    },
    {
      "completion_length": 146.91666666666666,
      "epoch": 1.0,
      "grad_norm": 76.77713775634766,
      "kl": 13.654948055744171,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0102,
      "reward": 5.330667932828267,
      "reward_std": 0.8708862774074078,
      "rewards/concensus_correctness_reward_func": 1.5764166563749313,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.7261679470539093,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.0489166676998138,
      "step": 4
    },
    {
      "completion_length": 131.78125,
      "epoch": 1.5714285714285714,
      "grad_norm": 89.60893249511719,
      "kl": 9.794984132546233,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0098,
      "reward": 5.313216768205166,
      "reward_std": 0.6214285232999828,
      "rewards/concensus_correctness_reward_func": 1.4918124936521053,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.7866854909807444,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.328125,
      "rewards/xmlcount_reward_func": 1.0815937519073486,
      "step": 6
    },
    {
      "completion_length": 122.29166666666667,
      "epoch": 2.0,
      "grad_norm": 195.7334747314453,
      "kl": 20.494624653520685,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0154,
      "reward": 3.7418640603621802,
      "reward_std": 0.8505224600958172,
      "rewards/concensus_correctness_reward_func": 1.0169999940941732,
      "rewards/consensus_reward_func": 0.9166666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6136973790513972,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2708333333333333,
      "rewards/xmlcount_reward_func": 0.9236666659514109,
      "step": 8
    },
    {
      "completion_length": 133.28125,
      "epoch": 2.571428571428571,
      "grad_norm": 5171.01611328125,
      "kl": 821.5899913753092,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.8216,
      "reward": 4.067712027579546,
      "reward_std": 0.522601830016356,
      "rewards/concensus_correctness_reward_func": 0.9896249957382679,
      "rewards/consensus_reward_func": 1.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6928683569421992,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.265625,
      "rewards/xmlcount_reward_func": 0.9945937469601631,
      "step": 10
    },
    {
      "completion_length": 123.5,
      "epoch": 3.0,
      "grad_norm": 221.9038848876953,
      "kl": 7.754779587810238,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0058,
      "reward": 5.002866193652153,
      "reward_std": 0.8892809633786479,
      "rewards/concensus_correctness_reward_func": 1.5877499878406525,
      "rewards/consensus_reward_func": 1.1666666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.7837411157476405,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2708333333333333,
      "rewards/xmlcount_reward_func": 1.027208335697651,
      "step": 12
    },
    {
      "completion_length": 141.25,
      "epoch": 3.571428571428571,
      "grad_norm": 143.69752502441406,
      "kl": 15.431037136120722,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0154,
      "reward": 4.483005654066801,
      "reward_std": 1.070481608647242,
      "rewards/concensus_correctness_reward_func": 1.249812494032085,
      "rewards/consensus_reward_func": 1.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.6482555402908474,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.28125,
      "rewards/xmlcount_reward_func": 0.9911874998360872,
      "step": 14
    },
    {
      "completion_length": 111.625,
      "epoch": 4.0,
      "grad_norm": 69.18689727783203,
      "kl": 1.4936193202932675,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0011,
      "reward": 4.76157025496165,
      "reward_std": 0.3775015217446101,
      "rewards/concensus_correctness_reward_func": 1.3215833256642024,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7950703254900873,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.0824166635672252,
      "step": 16
    },
    {
      "completion_length": 106.75,
      "epoch": 4.571428571428571,
      "grad_norm": 186.60618591308594,
      "kl": 2.3649307107552886,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0024,
      "reward": 4.832870416343212,
      "reward_std": 0.8347923850524239,
      "rewards/concensus_correctness_reward_func": 1.4267499893903732,
      "rewards/consensus_reward_func": 1.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.7312766302493401,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.0498437508940697,
      "step": 18
    },
    {
      "completion_length": 149.45833333333334,
      "epoch": 5.0,
      "grad_norm": 980.093017578125,
      "kl": 18.321802072227,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0137,
      "reward": 4.157890935738881,
      "reward_std": 0.9452465834910981,
      "rewards/concensus_correctness_reward_func": 1.1503333300352097,
      "rewards/consensus_reward_func": 0.9166666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.6799325756728649,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 0.9526249965031942,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.08954811465227977,
      "train_runtime": 132.9611,
      "train_samples_per_second": 2.407,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}