{
  "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": 245.875,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.7527321577072144,
      "kl": 0.021911813993938267,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 5.7590044140815735,
      "reward_std": 5.257039688527584,
      "rewards/concensus_correctness_reward_func": 3.504999991506338,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5625,
      "rewards/question_recreation_reward_func": 0.5125668197870255,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5383125096559525,
      "step": 2
    },
    {
      "completion_length": 231.0,
      "epoch": 1.0,
      "grad_norm": 0.6544833183288574,
      "kl": 0.020641639983902376,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 7.92664901415507,
      "reward_std": 7.975609441598256,
      "rewards/concensus_correctness_reward_func": 4.655416717131932,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5833333333333333,
      "rewards/question_recreation_reward_func": 0.5634823093811671,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.6869166592756907,
      "step": 4
    },
    {
      "completion_length": 263.6875,
      "epoch": 1.5714285714285714,
      "grad_norm": 1.050506353378296,
      "kl": 0.019874241203069687,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 6.4608331471681595,
      "reward_std": 6.1422329396009445,
      "rewards/concensus_correctness_reward_func": 4.200937490910292,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8125,
      "rewards/question_recreation_reward_func": 0.5279268752783537,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.4507187530398369,
      "step": 6
    },
    {
      "completion_length": 236.16666666666666,
      "epoch": 2.0,
      "grad_norm": 0.5823754668235779,
      "kl": 0.019788251879314583,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 6.491782108942668,
      "reward_std": 4.88298628727595,
      "rewards/concensus_correctness_reward_func": 3.506750007470449,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.4166666666666667,
      "rewards/question_recreation_reward_func": 0.5224903101722399,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.5250416745742162,
      "step": 8
    },
    {
      "completion_length": 227.46875,
      "epoch": 2.571428571428571,
      "grad_norm": 0.9334640502929688,
      "kl": 0.02316682948730886,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 7.54842072725296,
      "reward_std": 7.575185611844063,
      "rewards/concensus_correctness_reward_func": 4.861937437206507,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.9375,
      "rewards/question_recreation_reward_func": 0.5451083504594862,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.046875,
      "rewards/xmlcount_reward_func": 0.5320000052452087,
      "step": 10
    },
    {
      "completion_length": 248.58333333333334,
      "epoch": 3.0,
      "grad_norm": 0.5745718479156494,
      "kl": 0.02394568407908082,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 6.296762814124425,
      "reward_std": 4.437843253215154,
      "rewards/concensus_correctness_reward_func": 3.5823333263397217,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.3383881400028865,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.6885416607062022,
      "step": 12
    },
    {
      "completion_length": 250.03125,
      "epoch": 3.571428571428571,
      "grad_norm": 0.7098527550697327,
      "kl": 0.02179947926197201,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 7.116845011711121,
      "reward_std": 6.763956539332867,
      "rewards/concensus_correctness_reward_func": 4.194062519818544,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.125,
      "rewards/question_recreation_reward_func": 0.6923136711120605,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5898437611758709,
      "step": 14
    },
    {
      "completion_length": 202.16666666666666,
      "epoch": 4.0,
      "grad_norm": 0.6563175916671753,
      "kl": 0.024282248069842655,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 7.37228246529897,
      "reward_std": 5.8389623661835985,
      "rewards/concensus_correctness_reward_func": 4.730333363016446,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.2509909396370252,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.5784583141406378,
      "step": 16
    },
    {
      "completion_length": 289.8125,
      "epoch": 4.571428571428571,
      "grad_norm": 0.6700316667556763,
      "kl": 0.021815102780237794,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 5.917491778731346,
      "reward_std": 6.260626524686813,
      "rewards/concensus_correctness_reward_func": 3.528875023126602,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.48792930506169796,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5725625162012875,
      "step": 18
    },
    {
      "completion_length": 217.54166666666666,
      "epoch": 5.0,
      "grad_norm": 2.9088988304138184,
      "kl": 0.023700623928258818,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 4.78704692920049,
      "reward_std": 6.283455337087314,
      "rewards/concensus_correctness_reward_func": 2.713333343466123,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.9166666666666666,
      "rewards/question_recreation_reward_func": 0.37579695383707684,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4479166679084301,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.9282869925518752e-05,
      "train_runtime": 792.851,
      "train_samples_per_second": 0.404,
      "train_steps_per_second": 0.025
    }
  ],
  "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
}