{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 344.25,
      "epoch": 0.1,
      "grad_norm": 5.403124809265137,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 2.3487942395731807,
      "reward_std": 1.331467665731907,
      "rewards/concensus_correctness_reward_func": 0.6510000005364418,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.46238797600381076,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.46978125628083944,
      "step": 2
    },
    {
      "completion_length": 364.75,
      "epoch": 0.2,
      "grad_norm": 6.2670817375183105,
      "kl": 0.0021806862114317482,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 2.635450964793563,
      "reward_std": 2.075526769272983,
      "rewards/concensus_correctness_reward_func": 0.9166250005364418,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.4957009544596076,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4731249902397394,
      "step": 4
    },
    {
      "completion_length": 404.71875,
      "epoch": 0.3,
      "grad_norm": 5.5379438400268555,
      "kl": 0.0030734814645256847,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 2.522380673326552,
      "reward_std": 2.0315658951876685,
      "rewards/concensus_correctness_reward_func": 0.895562507212162,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5827869249042124,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6065312507562339,
      "step": 6
    },
    {
      "completion_length": 354.0,
      "epoch": 0.4,
      "grad_norm": 6.651269435882568,
      "kl": 0.003421090141273453,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.4581775926053524,
      "reward_std": 1.335879288148135,
      "rewards/concensus_correctness_reward_func": 0.6216250024735928,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.4378338464302942,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7112187594175339,
      "step": 8
    },
    {
      "completion_length": 300.0,
      "epoch": 0.5,
      "grad_norm": 6.796236038208008,
      "kl": 0.004635282557501341,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 2.6668134666979313,
      "reward_std": 1.702367587480694,
      "rewards/concensus_correctness_reward_func": 0.6051250025629997,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.375,
      "rewards/question_recreation_reward_func": 0.61225092317909,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5744375269860029,
      "step": 10
    },
    {
      "completion_length": 246.28125,
      "epoch": 0.6,
      "grad_norm": 4.856728553771973,
      "kl": 0.006234622225747444,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.907209224998951,
      "reward_std": 1.2923782205325551,
      "rewards/concensus_correctness_reward_func": 0.2936249990016222,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.48558421013876796,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7530000098049641,
      "step": 12
    },
    {
      "completion_length": 277.84375,
      "epoch": 0.7,
      "grad_norm": 38.3473014831543,
      "kl": 0.005429227188869845,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 2.3881534561514854,
      "reward_std": 1.1518572303466499,
      "rewards/concensus_correctness_reward_func": 0.43924999982118607,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.557153444038704,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7667500115931034,
      "step": 14
    },
    {
      "completion_length": 289.0,
      "epoch": 0.8,
      "grad_norm": 8.100913047790527,
      "kl": 0.006314124533673748,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 2.4665270633995533,
      "reward_std": 1.5265621307771653,
      "rewards/concensus_correctness_reward_func": 0.5556250028312206,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5798395671881735,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6435625050216913,
      "step": 16
    },
    {
      "completion_length": 378.90625,
      "epoch": 0.9,
      "grad_norm": 4.619319915771484,
      "kl": 0.0059225473523838446,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 2.774918533861637,
      "reward_std": 1.6789401592686772,
      "rewards/concensus_correctness_reward_func": 0.5491875000298023,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.5945435594767332,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8186875078827143,
      "step": 18
    },
    {
      "completion_length": 296.0625,
      "epoch": 1.0,
      "grad_norm": 6.017106056213379,
      "kl": 0.006086832385335583,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 2.033856872469187,
      "reward_std": 1.216237832326442,
      "rewards/concensus_correctness_reward_func": 0.262687498703599,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5571068990975618,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7765624914318323,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 4.321709275245666e-06,
      "train_runtime": 239.6333,
      "train_samples_per_second": 1.335,
      "train_steps_per_second": 0.083
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}