{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6666666666666666,
  "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": 239.0625,
      "epoch": 0.06666666666666667,
      "grad_norm": 146.07957458496094,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.877574372687377,
      "reward_std": 1.1462637517397525,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.10407434520311654,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.023499997798353434,
      "step": 2
    },
    {
      "completion_length": 162.4375,
      "epoch": 0.13333333333333333,
      "grad_norm": 44.136566162109375,
      "kl": 0.004455144211533479,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.35211178776808083,
      "reward_std": 0.21313007855496835,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.13901804643683136,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.025593749014660716,
      "step": 4
    },
    {
      "completion_length": 372.34375,
      "epoch": 0.2,
      "grad_norm": 83.95270538330078,
      "kl": 0.0029297428282006877,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.7589346559834667,
      "reward_std": 1.4558915909874486,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1666221939958632,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.09518750477582216,
      "step": 6
    },
    {
      "completion_length": 398.0,
      "epoch": 0.26666666666666666,
      "grad_norm": 124.03618621826172,
      "kl": 0.001172584436062607,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.24589170649414882,
      "reward_std": 0.2928572448272462,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.11979795509250835,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06359374988824129,
      "step": 8
    },
    {
      "completion_length": 222.03125,
      "epoch": 0.3333333333333333,
      "grad_norm": 22.514238357543945,
      "kl": 0.002474178050761111,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.3457036364998203,
      "reward_std": 0.20316840970190242,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.13420363652403466,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0240000004414469,
      "step": 10
    },
    {
      "completion_length": 361.8125,
      "epoch": 0.4,
      "grad_norm": 31.79580307006836,
      "kl": 0.0017530460136185866,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.09715361235430464,
      "reward_std": 0.5041031258151634,
      "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": 0.11099736913456582,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.07634374964982271,
      "step": 12
    },
    {
      "completion_length": 216.8125,
      "epoch": 0.4666666666666667,
      "grad_norm": 28.405397415161133,
      "kl": 0.0028270291222725064,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.2901497831335291,
      "reward_std": 0.3146807264929521,
      "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": 0.13105603493750095,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09659374854527414,
      "step": 14
    },
    {
      "completion_length": 260.75,
      "epoch": 0.5333333333333333,
      "grad_norm": 45.744022369384766,
      "kl": 0.004110226835109643,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.18092850630637258,
      "reward_std": 0.1472014883504471,
      "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": 0.11767850333126262,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06325000035576522,
      "step": 16
    },
    {
      "completion_length": 312.4375,
      "epoch": 0.6,
      "grad_norm": 24.293758392333984,
      "kl": 0.0039952012375579216,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.3126915064640343,
      "reward_std": 0.18643183991662227,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.09559775041998364,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0295937517657876,
      "step": 18
    },
    {
      "completion_length": 203.53125,
      "epoch": 0.6666666666666666,
      "grad_norm": 121.38932800292969,
      "kl": 0.09540724094040343,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "reward": 1.114405733300373,
      "reward_std": 1.2408277603099123,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.15249946631956846,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0869062514975667,
      "step": 20
    },
    {
      "epoch": 0.6666666666666666,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.192515795764848e-05,
      "train_runtime": 1239.9836,
      "train_samples_per_second": 0.258,
      "train_steps_per_second": 0.016
    }
  ],
  "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
}