{
  "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": 442.46875,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.5991543531417847,
      "kl": 0.0007749500146019273,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.3889684304594994,
      "reward_std": 1.309515006840229,
      "rewards/concensus_correctness_reward_func": 0.048500001430511475,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.44768718257546425,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2677812520414591,
      "step": 2
    },
    {
      "completion_length": 505.5357142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.3918515145778656,
      "kl": 0.0007179479746680174,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.4672155209950037,
      "reward_std": 1.435799777507782,
      "rewards/concensus_correctness_reward_func": 0.09328571387699672,
      "rewards/consensus_reward_func": 0.6428571428571429,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5747869280832154,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.15628571595464433,
      "step": 4
    },
    {
      "completion_length": 403.67857142857144,
      "epoch": 2.0,
      "grad_norm": 0.43622881174087524,
      "kl": 0.0007206426318069654,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 3.182981014251709,
      "reward_std": 2.6137921043804715,
      "rewards/concensus_correctness_reward_func": 1.4762142854077476,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.2857142857142857,
      "rewards/question_recreation_reward_func": 0.5557669103145599,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.41885715403727125,
      "step": 6
    },
    {
      "completion_length": 400.25,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.40697142481803894,
      "kl": 0.0007051618376863189,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.549363426864147,
      "reward_std": 2.5611291229724884,
      "rewards/concensus_correctness_reward_func": 0.7308750003576279,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5245196153409779,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.48146875388920307,
      "step": 8
    },
    {
      "completion_length": 367.85714285714283,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.5716286897659302,
      "kl": 0.000788627308793366,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.304913112095424,
      "reward_std": 0.8771725382123675,
      "rewards/concensus_correctness_reward_func": 0.01792857050895691,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5422702112368175,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.05357142857142857,
      "rewards/xmlcount_reward_func": 0.4054285671029772,
      "step": 10
    },
    {
      "completion_length": 476.60714285714283,
      "epoch": 4.0,
      "grad_norm": 0.3252517282962799,
      "kl": 0.0006907685476887439,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 3.995438354355948,
      "reward_std": 2.7802960106304715,
      "rewards/concensus_correctness_reward_func": 2.142857142857143,
      "rewards/consensus_reward_func": 0.7142857142857143,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.2857142857142857,
      "rewards/question_recreation_reward_func": 0.5197239475590842,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.33285714260169436,
      "step": 12
    },
    {
      "completion_length": 404.0625,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.395914763212204,
      "kl": 0.000713749454007484,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.381257563829422,
      "reward_std": 1.204833347350359,
      "rewards/concensus_correctness_reward_func": 0.0833749994635582,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.46469501964747906,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.046875,
      "rewards/xmlcount_reward_func": 0.2863125056028366,
      "step": 14
    },
    {
      "completion_length": 431.7857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.4147193431854248,
      "kl": 0.0006908452321243073,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.8860733594213213,
      "reward_std": 1.2617861075060708,
      "rewards/concensus_correctness_reward_func": 0.12271428959710258,
      "rewards/consensus_reward_func": 0.6428571428571429,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.5446448081306049,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.3437142851097243,
      "step": 16
    },
    {
      "completion_length": 495.57142857142856,
      "epoch": 6.0,
      "grad_norm": 0.30478447675704956,
      "kl": 0.0006883361326929714,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.7385921393121992,
      "reward_std": 1.5500890357153756,
      "rewards/concensus_correctness_reward_func": 0.11321428418159485,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.5604849649327142,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5648928880691528,
      "step": 18
    },
    {
      "completion_length": 387.59375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4601048231124878,
      "kl": 0.0007431526173604652,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 2.224214667454362,
      "reward_std": 2.225543730892241,
      "rewards/concensus_correctness_reward_func": 0.7394375018775463,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.4345896728336811,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5501874964684248,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.705659131966968e-07,
      "train_runtime": 586.0026,
      "train_samples_per_second": 0.546,
      "train_steps_per_second": 0.034
    }
  ],
  "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
}