{
  "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": 456.28125,
      "epoch": 0.7272727272727273,
      "grad_norm": 1.1658414602279663,
      "kl": 0.0009225553694705013,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.5958388317376375,
      "reward_std": 1.0339283626526594,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.41733881644904613,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.10037502087652683,
      "step": 2
    },
    {
      "completion_length": 483.14285714285717,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.2886810600757599,
      "kl": 0.0006020833056287042,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.8047345685107368,
      "reward_std": 0.611581197806767,
      "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": 0.3887345769575664,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.39814286146845135,
      "step": 4
    },
    {
      "completion_length": 424.5,
      "epoch": 2.0,
      "grad_norm": 0.3278331458568573,
      "kl": 0.0005954150443098374,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.8565868820462909,
      "reward_std": 0.9214419679982322,
      "rewards/concensus_correctness_reward_func": 0.015428571828774043,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5159439998013633,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2537857251507895,
      "step": 6
    },
    {
      "completion_length": 469.15625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.3174148201942444,
      "kl": 0.0005489450850291178,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.110235832631588,
      "reward_std": 0.8479745015501976,
      "rewards/concensus_correctness_reward_func": 0.013500000350177288,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6265483107417822,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.34518749825656414,
      "step": 8
    },
    {
      "completion_length": 424.10714285714283,
      "epoch": 3.3636363636363638,
      "grad_norm": 4.965213775634766,
      "kl": 0.0008727898197581194,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.134776200566973,
      "reward_std": 0.9922715510640826,
      "rewards/concensus_correctness_reward_func": 0.015500000278864588,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3687761734638895,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.4290714349065508,
      "step": 10
    },
    {
      "completion_length": 472.9642857142857,
      "epoch": 4.0,
      "grad_norm": 6.830959796905518,
      "kl": 0.0011083015290621137,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.5893996320664883,
      "reward_std": 1.2301939662013734,
      "rewards/concensus_correctness_reward_func": 0.03571428571428571,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4319710433483124,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.03242858286414828,
      "step": 12
    },
    {
      "completion_length": 488.375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.3196428716182709,
      "kl": 0.0006084925407776609,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.7141946814954281,
      "reward_std": 1.1040537096560001,
      "rewards/concensus_correctness_reward_func": 0.013500000350177288,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5245071910321712,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.011312478221952915,
      "step": 14
    },
    {
      "completion_length": 526.7857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.36402690410614014,
      "kl": 0.0006533784159858312,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.9942480155399868,
      "reward_std": 1.1206721578325545,
      "rewards/concensus_correctness_reward_func": 0.002785714343190193,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6340694555214473,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14310714496033533,
      "step": 16
    },
    {
      "completion_length": 409.67857142857144,
      "epoch": 6.0,
      "grad_norm": 0.31962138414382935,
      "kl": 0.0007612127394947622,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.9467200892312186,
      "reward_std": 1.0022244964327132,
      "rewards/concensus_correctness_reward_func": 0.015428571828774043,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.43318439381463186,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.28382142686418127,
      "step": 18
    },
    {
      "completion_length": 482.375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.3032238483428955,
      "kl": 0.000580788342631422,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.0357788391411304,
      "reward_std": 0.9345870595425367,
      "rewards/concensus_correctness_reward_func": 0.015937500400468707,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.47309133782982826,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.28112500719726086,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.637569072154292e-07,
      "train_runtime": 618.9894,
      "train_samples_per_second": 0.517,
      "train_steps_per_second": 0.032
    }
  ],
  "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
}