{
  "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": 379.625,
      "epoch": 0.7272727272727273,
      "grad_norm": 2.0845367908477783,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 1.0464008646085858,
      "reward_std": 0.8577102832496166,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6478696241974831,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.211031261831522,
      "step": 2
    },
    {
      "completion_length": 521.3214285714286,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.62913978099823,
      "kl": 0.0008032359349142228,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.9113494753837585,
      "reward_std": 0.9215784285749707,
      "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": 0.5891351784978595,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.10792855811970574,
      "step": 4
    },
    {
      "completion_length": 348.2857142857143,
      "epoch": 2.0,
      "grad_norm": 0.7531375885009766,
      "kl": 0.0008565662428736687,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.34744736126491,
      "reward_std": 0.9178757199219295,
      "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": 0.6254117020538875,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.47203571775129866,
      "step": 6
    },
    {
      "completion_length": 416.21875,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5220724940299988,
      "kl": 0.0009152014463325031,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.8013468980789185,
      "reward_std": 1.1010007336735725,
      "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": 0.6636594086885452,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.04393750987946987,
      "step": 8
    },
    {
      "completion_length": 374.2857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.9102826714515686,
      "kl": 0.000852442579343915,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.1417701925550188,
      "reward_std": 0.8960793933698109,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5468416203345571,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.07142857142857142,
      "rewards/xmlcount_reward_func": 0.43421428331307005,
      "step": 10
    },
    {
      "completion_length": 384.9642857142857,
      "epoch": 4.0,
      "grad_norm": 0.38932564854621887,
      "kl": 0.0008554482400151235,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.8314903655222484,
      "reward_std": 0.7095571075166974,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5702403719936099,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18982143061501638,
      "step": 12
    },
    {
      "completion_length": 481.5,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5498029589653015,
      "kl": 0.001051962244673632,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.3533218130469322,
      "reward_std": 1.19077692553401,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6365718133747578,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.2636250052601099,
      "step": 14
    },
    {
      "completion_length": 464.5,
      "epoch": 5.363636363636363,
      "grad_norm": 0.575084388256073,
      "kl": 0.0009180556766555778,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.6909804833786828,
      "reward_std": 1.1710218105997359,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6612304768392018,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04167857553277697,
      "step": 16
    },
    {
      "completion_length": 474.9642857142857,
      "epoch": 6.0,
      "grad_norm": 1.0498607158660889,
      "kl": 0.0009472336054646543,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.7536937232528415,
      "reward_std": 0.8095326593944004,
      "rewards/concensus_correctness_reward_func": 0.008928571428571428,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5244079849549702,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07750000485352107,
      "step": 18
    },
    {
      "completion_length": 401.625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.5665810704231262,
      "kl": 0.0009209893833030947,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.1352272666990757,
      "reward_std": 1.017869208008051,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5484459716826677,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.078125,
      "rewards/xmlcount_reward_func": 0.31334374099969864,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 7.359022154318495e-07,
      "train_runtime": 818.7745,
      "train_samples_per_second": 0.391,
      "train_steps_per_second": 0.024
    }
  ],
  "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
}