{
  "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": 381.5625,
      "epoch": 0.7272727272727273,
      "grad_norm": 8.51944637298584,
      "kl": 0.0010858698733500205,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.2122566550970078,
      "reward_std": 1.0360601618885994,
      "rewards/concensus_correctness_reward_func": 0.02462499961256981,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5517566399648786,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.2452500108629465,
      "step": 2
    },
    {
      "completion_length": 346.0357142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 2.372509241104126,
      "kl": 0.0008861671501238431,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.2280282122748238,
      "reward_std": 0.9695348228727069,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.55777821796281,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.3488214303340231,
      "step": 4
    },
    {
      "completion_length": 400.89285714285717,
      "epoch": 2.0,
      "grad_norm": 30.910978317260742,
      "kl": 0.002466103868625526,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9417943699019296,
      "reward_std": 0.9689634442329407,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4311515545206411,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.13564284997326986,
      "step": 6
    },
    {
      "completion_length": 481.21875,
      "epoch": 2.7272727272727275,
      "grad_norm": 2.3671247959136963,
      "kl": 0.0006554951214639004,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.6971063707023859,
      "reward_std": 1.3148079439997673,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5062938686460257,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.18418749421834946,
      "step": 8
    },
    {
      "completion_length": 315.4642857142857,
      "epoch": 3.3636363636363638,
      "grad_norm": 8.664198875427246,
      "kl": 0.000979020692674177,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.4944053372102124,
      "reward_std": 0.7025247595406005,
      "rewards/concensus_correctness_reward_func": 0.08442856584276472,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4091196159965226,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.42942858380930765,
      "step": 10
    },
    {
      "completion_length": 345.07142857142856,
      "epoch": 4.0,
      "grad_norm": 0.4007492661476135,
      "kl": 0.0007108618280783828,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.6233712945665633,
      "reward_std": 1.2160399556159973,
      "rewards/concensus_correctness_reward_func": 0.056285713400159566,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6631569947515216,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.47535716210092815,
      "step": 12
    },
    {
      "completion_length": 425.46875,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5029193758964539,
      "kl": 0.0007616056900587864,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.7096736282110214,
      "reward_std": 1.2921253815293312,
      "rewards/concensus_correctness_reward_func": 0.04924999922513962,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6550173498690128,
      "rewards/soft_format_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.3335312604904175,
      "step": 14
    },
    {
      "completion_length": 387.5,
      "epoch": 5.363636363636363,
      "grad_norm": 0.4861798882484436,
      "kl": 0.0007347542310266622,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.0293196184294564,
      "reward_std": 1.0739143043756485,
      "rewards/concensus_correctness_reward_func": 0.05357142857142857,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6240696310997009,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.1195357016154698,
      "step": 16
    },
    {
      "completion_length": 337.82142857142856,
      "epoch": 6.0,
      "grad_norm": 0.4701369106769562,
      "kl": 0.0008703628388632621,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.14948656303542,
      "reward_std": 1.1583525240421295,
      "rewards/concensus_correctness_reward_func": 0.05114285860742841,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.38427224861724035,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.1069285837667329,
      "step": 18
    },
    {
      "completion_length": 425.71875,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.45120343565940857,
      "kl": 0.000811609163065441,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8713410794734955,
      "reward_std": 1.1033968962728977,
      "rewards/concensus_correctness_reward_func": 0.04268750175833702,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.4200910869985819,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.03356249979697168,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 9.033959997850616e-07,
      "train_runtime": 1624.449,
      "train_samples_per_second": 0.197,
      "train_steps_per_second": 0.012
    }
  ],
  "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
}