{
  "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": 271.53125,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.6156684756278992,
      "kl": 0.003713510144734755,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 4.28339558839798,
      "reward_std": 5.015739507973194,
      "rewards/concensus_correctness_reward_func": 2.1066250316798687,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8125,
      "rewards/question_recreation_reward_func": 0.49977052211761475,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3644999973475933,
      "step": 2
    },
    {
      "completion_length": 237.33333333333334,
      "epoch": 1.0,
      "grad_norm": 0.3896828293800354,
      "kl": 0.0036000795274352035,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 7.742002268632253,
      "reward_std": 8.532249887784323,
      "rewards/concensus_correctness_reward_func": 5.1745833332339926,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.4115021179119746,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.041666666666666664,
      "rewards/xmlcount_reward_func": 0.4475833574930827,
      "step": 4
    },
    {
      "completion_length": 268.1875,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.6913865208625793,
      "kl": 0.003932094754418358,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 5.461809501051903,
      "reward_std": 5.302938483655453,
      "rewards/concensus_correctness_reward_func": 3.2423125002533197,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.43490335159003735,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2845937521196902,
      "step": 6
    },
    {
      "completion_length": 248.33333333333334,
      "epoch": 2.0,
      "grad_norm": 0.40261271595954895,
      "kl": 0.0035152111668139696,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 6.17376080652078,
      "reward_std": 5.402185544371605,
      "rewards/concensus_correctness_reward_func": 3.6611666629711785,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0833333333333333,
      "rewards/question_recreation_reward_func": 0.3990109084794919,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.5094166745742162,
      "step": 8
    },
    {
      "completion_length": 239.0625,
      "epoch": 2.571428571428571,
      "grad_norm": 0.6596890687942505,
      "kl": 0.004055387194966897,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 7.403021275997162,
      "reward_std": 7.769663609564304,
      "rewards/concensus_correctness_reward_func": 4.745562508702278,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.125,
      "rewards/question_recreation_reward_func": 0.42364630103111267,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.46818749513477087,
      "step": 10
    },
    {
      "completion_length": 272.5,
      "epoch": 3.0,
      "grad_norm": 0.3865489363670349,
      "kl": 0.004031806602142751,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 3.3122252325216928,
      "reward_std": 2.822227214773496,
      "rewards/concensus_correctness_reward_func": 1.8305832520127296,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5,
      "rewards/question_recreation_reward_func": 0.477475106716156,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.3166666701436043,
      "step": 12
    },
    {
      "completion_length": 245.59375,
      "epoch": 3.571428571428571,
      "grad_norm": 0.7244676351547241,
      "kl": 0.0035437151964288205,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 6.540969520807266,
      "reward_std": 6.686426967382431,
      "rewards/concensus_correctness_reward_func": 3.60187497548759,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.5858760215342045,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.4625937454402447,
      "step": 14
    },
    {
      "completion_length": 285.8333333333333,
      "epoch": 4.0,
      "grad_norm": 0.4408351480960846,
      "kl": 0.005074007475438218,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 3.404947509368261,
      "reward_std": 2.91806568702062,
      "rewards/concensus_correctness_reward_func": 1.8025833343466122,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5833333333333334,
      "rewards/question_recreation_reward_func": 0.2744477453331153,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4945833434661229,
      "step": 16
    },
    {
      "completion_length": 245.5625,
      "epoch": 4.571428571428571,
      "grad_norm": 1.1728448867797852,
      "kl": 0.004925011526211165,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 8.376463562250137,
      "reward_std": 6.909352557733655,
      "rewards/concensus_correctness_reward_func": 5.674437500536442,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.5359011180698872,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.6348750218749046,
      "step": 18
    },
    {
      "completion_length": 228.45833333333334,
      "epoch": 5.0,
      "grad_norm": 0.5003474950790405,
      "kl": 0.003518054281206181,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 2.8317282050848007,
      "reward_std": 2.5725097159544625,
      "rewards/concensus_correctness_reward_func": 1.0097499986489613,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8333333333333334,
      "rewards/question_recreation_reward_func": 0.2900198350350062,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.36529167120655376,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 3.5113219382765236e-06,
      "train_runtime": 2215.8404,
      "train_samples_per_second": 0.144,
      "train_steps_per_second": 0.009
    }
  ],
  "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
}