{
  "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": 424.6875,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.43405377864837646,
      "kl": 0.0006831735299783759,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.8635006062686443,
      "reward_std": 0.9787142872810364,
      "rewards/concensus_correctness_reward_func": 0.035999998450279236,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4570631179958582,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.1048125009983778,
      "step": 2
    },
    {
      "completion_length": 378.2857142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 1.0889649391174316,
      "kl": 0.0006943551125004888,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.5840824406061854,
      "reward_std": 0.6718125343322754,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3689038535313947,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14375001617840358,
      "step": 4
    },
    {
      "completion_length": 408.42857142857144,
      "epoch": 2.0,
      "grad_norm": 5.749520778656006,
      "kl": 0.0008105350176005491,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.5108186176845007,
      "reward_std": 1.2569768513951982,
      "rewards/concensus_correctness_reward_func": 0.11528571162905012,
      "rewards/consensus_reward_func": 0.6428571428571429,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5690686276980809,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18360714720828192,
      "step": 6
    },
    {
      "completion_length": 541.09375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.27186667919158936,
      "kl": 0.0006820280032115988,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.114719219505787,
      "reward_std": 1.1962014511227608,
      "rewards/concensus_correctness_reward_func": 0.00787500012665987,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.5445942096412182,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18725000135600567,
      "step": 8
    },
    {
      "completion_length": 381.64285714285717,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.4672013223171234,
      "kl": 0.0007658531373765852,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.027580979679312,
      "reward_std": 1.0205590171473367,
      "rewards/concensus_correctness_reward_func": 0.06171428305762155,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.45865238670791897,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.1322142971413476,
      "step": 10
    },
    {
      "completion_length": 493.4642857142857,
      "epoch": 4.0,
      "grad_norm": 0.33820706605911255,
      "kl": 0.0006163329900508481,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.9565395074231284,
      "reward_std": 1.093166755778449,
      "rewards/concensus_correctness_reward_func": 0.03142857125827244,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5024323686957359,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.11910714794482503,
      "step": 12
    },
    {
      "completion_length": 440.40625,
      "epoch": 4.7272727272727275,
      "grad_norm": 1.1928702592849731,
      "kl": 0.000714650159352459,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.2266200836747885,
      "reward_std": 1.2259398996829987,
      "rewards/concensus_correctness_reward_func": 0.10087499767541885,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.40987010672688484,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.26275000162422657,
      "step": 14
    },
    {
      "completion_length": 463.17857142857144,
      "epoch": 5.363636363636363,
      "grad_norm": 0.31915608048439026,
      "kl": 0.000624320494742798,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.2959183220352446,
      "reward_std": 1.0866505248206002,
      "rewards/concensus_correctness_reward_func": 0.05357142857142857,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5370612144470215,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2767142930201122,
      "step": 16
    },
    {
      "completion_length": 362.85714285714283,
      "epoch": 6.0,
      "grad_norm": 0.6950757503509521,
      "kl": 0.0008193998697346874,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.9905583645616259,
      "reward_std": 1.0358542374202184,
      "rewards/concensus_correctness_reward_func": 0.06171428305762155,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3102726340293884,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11857143257345472,
      "step": 18
    },
    {
      "completion_length": 394.25,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.523013710975647,
      "kl": 0.0007893772781244479,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.7763789296150208,
      "reward_std": 0.8996854834258556,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.48691016249358654,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.03946874663233757,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.585680921489257e-07,
      "train_runtime": 1575.2293,
      "train_samples_per_second": 0.203,
      "train_steps_per_second": 0.013
    }
  ],
  "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
}