{
  "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": 473.125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.47395309805870056,
      "kl": 0.0007194303179858252,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.0330365039408207,
      "reward_std": 0.8502509072422981,
      "rewards/concensus_correctness_reward_func": 0.12487500160932541,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.40381778590381145,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2387187471613288,
      "step": 2
    },
    {
      "completion_length": 438.92857142857144,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.7307482361793518,
      "kl": 0.000792368157168052,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.1922784277370997,
      "reward_std": 1.0465660755123412,
      "rewards/concensus_correctness_reward_func": 0.04221428717885699,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.48559985416276114,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.43232143776757376,
      "step": 4
    },
    {
      "completion_length": 504.35714285714283,
      "epoch": 2.0,
      "grad_norm": 0.5159506797790527,
      "kl": 0.0007334664613673729,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.8352767441953931,
      "reward_std": 0.8559413254261017,
      "rewards/concensus_correctness_reward_func": 0.05357142857142857,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3499195910990238,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.2710714191198349,
      "step": 6
    },
    {
      "completion_length": 455.71875,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.45576661825180054,
      "kl": 0.0007681748211325612,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.2727090716362,
      "reward_std": 0.8306444603949785,
      "rewards/concensus_correctness_reward_func": 0.039000000804662704,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.43352156039327383,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4251874964684248,
      "step": 8
    },
    {
      "completion_length": 614.7857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.3708077073097229,
      "kl": 0.0005846833519171923,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9227776953152248,
      "reward_std": 1.1642258380140578,
      "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": 0.5982062688895634,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.03885713006768908,
      "step": 10
    },
    {
      "completion_length": 506.32142857142856,
      "epoch": 4.0,
      "grad_norm": 0.3548920750617981,
      "kl": 0.00077266401162238,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.336006041084017,
      "reward_std": 0.8086139815194267,
      "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": 0.5260417546544757,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.524250002843993,
      "step": 12
    },
    {
      "completion_length": 585.0625,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.6056526899337769,
      "kl": 0.0006429032546293456,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.0751310326159,
      "reward_std": 0.9033161960542202,
      "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": 0.5824123099446297,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.30521874129772186,
      "step": 14
    },
    {
      "completion_length": 475.67857142857144,
      "epoch": 5.363636363636363,
      "grad_norm": 0.3054889440536499,
      "kl": 0.0006323940885652389,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.0472202003002167,
      "reward_std": 1.2190494877951485,
      "rewards/concensus_correctness_reward_func": 0.11892857296126229,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.40439875211034504,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09532143601349422,
      "step": 16
    },
    {
      "completion_length": 409.07142857142856,
      "epoch": 6.0,
      "grad_norm": 0.46863505244255066,
      "kl": 0.0008968169734414135,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.8927415055888039,
      "reward_std": 1.1446925912584578,
      "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": 0.32149150116103037,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.30339285145912853,
      "step": 18
    },
    {
      "completion_length": 581.09375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.42784228920936584,
      "kl": 0.0016935703897615895,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.1855993624776602,
      "reward_std": 1.0335762538015842,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.48631811887025833,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2617812678217888,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 7.703036885686743e-07,
      "train_runtime": 604.569,
      "train_samples_per_second": 0.529,
      "train_steps_per_second": 0.033
    }
  ],
  "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
}