{
  "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": 158.84375,
      "epoch": 0.1,
      "grad_norm": 92.82727813720703,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.1468239967362024,
      "reward_std": 0.17140711040701717,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1628240012214519,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.016000002156943083,
      "step": 2
    },
    {
      "completion_length": 88.96875,
      "epoch": 0.2,
      "grad_norm": 17.767974853515625,
      "kl": 0.0021755212871994445,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.5362368610221893,
      "reward_std": 0.18039140166092693,
      "rewards/concensus_correctness_reward_func": 0.1185000017285347,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.17770562344230711,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1150312521494925,
      "step": 4
    },
    {
      "completion_length": 161.3125,
      "epoch": 0.3,
      "grad_norm": 7.2867231369018555,
      "kl": 0.004310879157856107,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.4580355920479633,
      "reward_std": 0.26154627031223754,
      "rewards/concensus_correctness_reward_func": 0.0599374994635582,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.179504333762452,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14046875084750354,
      "step": 6
    },
    {
      "completion_length": 138.25,
      "epoch": 0.4,
      "grad_norm": 7.924788951873779,
      "kl": 0.011087903680163436,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.5225309516536072,
      "reward_std": 0.49480345542542636,
      "rewards/concensus_correctness_reward_func": 0.04700000025331974,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.12593720143195242,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16209374903701246,
      "step": 8
    },
    {
      "completion_length": 166.46875,
      "epoch": 0.5,
      "grad_norm": 10.63830852508545,
      "kl": 0.013151258695870638,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.4802669673226774,
      "reward_std": 0.3484726174501702,
      "rewards/concensus_correctness_reward_func": 0.02800000086426735,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.16017321776598692,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22959374566562474,
      "step": 10
    },
    {
      "completion_length": 173.4375,
      "epoch": 0.6,
      "grad_norm": 9.655745506286621,
      "kl": 0.016364283743314445,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.8550984656903893,
      "reward_std": 0.33143275073962286,
      "rewards/concensus_correctness_reward_func": 0.2682499997317791,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.14825469313655049,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12609374476596713,
      "step": 12
    },
    {
      "completion_length": 109.84375,
      "epoch": 0.7,
      "grad_norm": 7.929982662200928,
      "kl": 0.021056591620435938,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.378742050845176,
      "reward_std": 0.1508836179878017,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.14089830702869222,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.23784374445676804,
      "step": 14
    },
    {
      "completion_length": 146.1875,
      "epoch": 0.8,
      "grad_norm": 6.844194412231445,
      "kl": 0.016575219749938697,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 1.0233479777816683,
      "reward_std": 0.34056491823866963,
      "rewards/concensus_correctness_reward_func": 0.2397499978542328,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.24947296862956136,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.15912500116974115,
      "step": 16
    },
    {
      "completion_length": 128.4375,
      "epoch": 0.9,
      "grad_norm": 25.0986270904541,
      "kl": 0.022347735619405285,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.8327681426890194,
      "reward_std": 0.3936522727308329,
      "rewards/concensus_correctness_reward_func": 0.15112500078976154,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.2066118831280619,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16253125155344605,
      "step": 18
    },
    {
      "completion_length": 138.625,
      "epoch": 1.0,
      "grad_norm": 20.88378143310547,
      "kl": 0.02928804296971066,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.8610214402433485,
      "reward_std": 0.6351559593313141,
      "rewards/concensus_correctness_reward_func": 0.14743749983608723,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.19989642850123346,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3261875007301569,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.3666093832398473e-05,
      "train_runtime": 806.7775,
      "train_samples_per_second": 0.397,
      "train_steps_per_second": 0.025
    }
  ],
  "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
}