{
  "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": 283.8125,
      "epoch": 0.5714285714285714,
      "grad_norm": 1.1532014608383179,
      "kl": 0.013067460153251886,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 5.535428494215012,
      "reward_std": 6.1332239508628845,
      "rewards/concensus_correctness_reward_func": 2.964875027537346,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8125,
      "rewards/question_recreation_reward_func": 0.5587721578776836,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.046875,
      "rewards/xmlcount_reward_func": 0.6524062640964985,
      "step": 2
    },
    {
      "completion_length": 243.58333333333334,
      "epoch": 1.0,
      "grad_norm": 0.8902457356452942,
      "kl": 0.014269542104254166,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 4.376810510953267,
      "reward_std": 3.2900354166825614,
      "rewards/concensus_correctness_reward_func": 1.6458333333333333,
      "rewards/consensus_reward_func": 0.08333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5833333333333333,
      "rewards/question_recreation_reward_func": 0.5328105284521977,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.5106666708985964,
      "step": 4
    },
    {
      "completion_length": 273.125,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.4976244568824768,
      "kl": 0.011306149302981794,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 7.522334858775139,
      "reward_std": 7.5043724700808525,
      "rewards/concensus_correctness_reward_func": 4.937187507748604,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.5563972145318985,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5287500089034438,
      "step": 6
    },
    {
      "completion_length": 244.66666666666666,
      "epoch": 2.0,
      "grad_norm": 0.44919872283935547,
      "kl": 0.014499408192932606,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 5.386006702979405,
      "reward_std": 6.149055267373721,
      "rewards/concensus_correctness_reward_func": 2.773583302895228,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.5773818517724673,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4517083341876666,
      "step": 8
    },
    {
      "completion_length": 261.0625,
      "epoch": 2.571428571428571,
      "grad_norm": 0.5340657234191895,
      "kl": 0.012978739512618631,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 7.555992126464844,
      "reward_std": 8.598402701318264,
      "rewards/concensus_correctness_reward_func": 5.023000039160252,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.5316797159612179,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.563812492415309,
      "step": 10
    },
    {
      "completion_length": 258.4166666666667,
      "epoch": 3.0,
      "grad_norm": 0.4479375183582306,
      "kl": 0.012453029553095499,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 7.487985849380493,
      "reward_std": 7.63406256834666,
      "rewards/concensus_correctness_reward_func": 4.7774166117111845,
      "rewards/consensus_reward_func": 0.6666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.5623606691757838,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.4607083350419998,
      "step": 12
    },
    {
      "completion_length": 276.59375,
      "epoch": 3.571428571428571,
      "grad_norm": 1.0146440267562866,
      "kl": 0.013750494923442602,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 7.103241473436356,
      "reward_std": 6.38451437279582,
      "rewards/concensus_correctness_reward_func": 4.362937547266483,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1875,
      "rewards/question_recreation_reward_func": 0.6148039405234158,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.547375014051795,
      "step": 14
    },
    {
      "completion_length": 268.5,
      "epoch": 4.0,
      "grad_norm": 0.4467558264732361,
      "kl": 0.013235996011644602,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 6.3883426288763685,
      "reward_std": 6.176097631454468,
      "rewards/concensus_correctness_reward_func": 3.920333390434583,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.31771781543890637,
      "rewards/soft_format_reward_func": 0.020833333333333332,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.6502916713555654,
      "step": 16
    },
    {
      "completion_length": 230.25,
      "epoch": 4.571428571428571,
      "grad_norm": 0.7665261626243591,
      "kl": 0.014356082305312157,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 8.594983696937561,
      "reward_std": 6.361941149458289,
      "rewards/concensus_correctness_reward_func": 5.92093750089407,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8125,
      "rewards/question_recreation_reward_func": 0.49420230463147163,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6173437759280205,
      "step": 18
    },
    {
      "completion_length": 246.75,
      "epoch": 5.0,
      "grad_norm": 0.45120424032211304,
      "kl": 0.014536370212833086,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 3.8146777749061584,
      "reward_std": 3.0375414018829665,
      "rewards/concensus_correctness_reward_func": 1.2678333421548207,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.42113616565863293,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7090416798988978,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.1729459947673604e-05,
      "train_runtime": 312.4193,
      "train_samples_per_second": 1.024,
      "train_steps_per_second": 0.064
    }
  ],
  "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": 4,
  "trial_name": null,
  "trial_params": null
}