{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3333333333333333,
  "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": 89.9375,
      "epoch": 0.03333333333333333,
      "grad_norm": 23.210905075073242,
      "kl": -1.435419799689086e-08,
      "learning_rate": 4.965903258506806e-07,
      "loss": -0.0,
      "reward": 0.07646713079884648,
      "reward_std": 0.03834086412098259,
      "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": 0.06859213160350919,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.00787500012665987,
      "step": 2
    },
    {
      "completion_length": 334.6875,
      "epoch": 0.06666666666666667,
      "grad_norm": 7.414389610290527,
      "kl": 0.0015819505424587987,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.06847984250634909,
      "reward_std": 0.02964116230577929,
      "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": 0.06847984250634909,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 207.0,
      "epoch": 0.1,
      "grad_norm": 8.015021324157715,
      "kl": 0.00830799954928807,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.09859450592193753,
      "reward_std": 0.03891285555437207,
      "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": 0.09859450592193753,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 248.25,
      "epoch": 0.13333333333333333,
      "grad_norm": 30.997661590576172,
      "kl": 0.00972236494999379,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.114964205538854,
      "reward_std": 0.04997973030549474,
      "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": 0.114964205538854,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 263.75,
      "epoch": 0.16666666666666666,
      "grad_norm": 6.208876609802246,
      "kl": 0.003906876590917818,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.07485395605908707,
      "reward_std": 0.04933022583645652,
      "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": 0.07485395605908707,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "completion_length": 323.625,
      "epoch": 0.2,
      "grad_norm": 4.191387176513672,
      "kl": 0.005759889456385281,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.0255373198306188,
      "reward_std": 0.011456945620011538,
      "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": 0.0255373198306188,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 12
    },
    {
      "completion_length": 279.375,
      "epoch": 0.23333333333333334,
      "grad_norm": 7.944534778594971,
      "kl": 0.004698720731539652,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.07817272481042892,
      "reward_std": 0.03459818737974274,
      "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": 0.07817272481042892,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 14
    },
    {
      "completion_length": 320.75,
      "epoch": 0.26666666666666666,
      "grad_norm": 7.197661399841309,
      "kl": 0.005463704765134025,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.04742856038501486,
      "reward_std": 0.020018141498439945,
      "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": 0.04742856038501486,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 16
    },
    {
      "completion_length": 216.0625,
      "epoch": 0.3,
      "grad_norm": 85.55599975585938,
      "kl": 0.045808882532583084,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.11241933924611658,
      "reward_std": 0.03139883271069266,
      "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": 0.11241933924611658,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 18
    },
    {
      "completion_length": 303.625,
      "epoch": 0.3333333333333333,
      "grad_norm": 11.537041664123535,
      "kl": 0.02477177143737208,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.08405531366588548,
      "reward_std": 0.05363292060792446,
      "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": 0.08405531366588548,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 20
    },
    {
      "epoch": 0.3333333333333333,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.1069758693338372e-05,
      "train_runtime": 3224.3032,
      "train_samples_per_second": 0.05,
      "train_steps_per_second": 0.006
    }
  ],
  "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
}