{
  "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": 484.34375,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.31932416558265686,
      "kl": 0.0006641301006311551,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.8911791052669287,
      "reward_std": 0.7616452053189278,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6187728717923164,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14740624837577343,
      "step": 2
    },
    {
      "completion_length": 510.0,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.320825457572937,
      "kl": 0.000691832770826295,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.6444876875196185,
      "reward_std": 1.1091752818652563,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6262734468494143,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.19607143529823848,
      "step": 4
    },
    {
      "completion_length": 513.75,
      "epoch": 2.0,
      "grad_norm": 0.25413331389427185,
      "kl": 0.0009799751902132162,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.084031228508268,
      "reward_std": 1.2072510463850838,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.47388836635010584,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.05357142857142857,
      "rewards/xmlcount_reward_func": 0.27085714042186737,
      "step": 6
    },
    {
      "completion_length": 435.15625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.48664921522140503,
      "kl": 0.0007914057750895154,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.1346675045788288,
      "reward_std": 0.7414112240076065,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6151049984619021,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.19143750052899122,
      "step": 8
    },
    {
      "completion_length": 524.1428571428571,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.3309638500213623,
      "kl": 0.0006425218764759068,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.8435536708150592,
      "reward_std": 0.9221388867923191,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4326251213039671,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.05378572004181998,
      "step": 10
    },
    {
      "completion_length": 490.2142857142857,
      "epoch": 4.0,
      "grad_norm": 6.519441604614258,
      "kl": 0.0008424879675398447,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.295002749988011,
      "reward_std": 1.0125029901308673,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7125027477741241,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.33250001072883606,
      "step": 12
    },
    {
      "completion_length": 425.90625,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.4380124807357788,
      "kl": 0.0006226709811016917,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.8414656817913055,
      "reward_std": 0.802082123234868,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.46252819150686264,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12893750285729766,
      "step": 14
    },
    {
      "completion_length": 471.2857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.5062863826751709,
      "kl": 0.0006774923281877168,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.7448562851973942,
      "reward_std": 1.0423502794333868,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5749991663864681,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.009142858641488212,
      "step": 16
    },
    {
      "completion_length": 504.92857142857144,
      "epoch": 6.0,
      "grad_norm": 0.2513563632965088,
      "kl": 0.0007265556279370296,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.7107706474406379,
      "reward_std": 1.2383961762700761,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6080563430275235,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.32585713480200085,
      "step": 18
    },
    {
      "completion_length": 437.65625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.3156798481941223,
      "kl": 0.0006726395040459465,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8750260164961219,
      "reward_std": 0.9098680801689625,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3959010145626962,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.21349999587982893,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.662672547008697e-07,
      "train_runtime": 1726.6167,
      "train_samples_per_second": 0.185,
      "train_steps_per_second": 0.012
    }
  ],
  "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
}