{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "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": 218.84375,
      "epoch": 0.5714285714285714,
      "grad_norm": 16.413349151611328,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": -0.0,
      "reward": 3.463685939088464,
      "reward_std": 0.7034649187116884,
      "rewards/concensus_correctness_reward_func": 0.7219999879598618,
      "rewards/consensus_reward_func": 1.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7888422352261841,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.15625,
      "rewards/xmlcount_reward_func": 0.7340937531553209,
      "step": 2
    },
    {
      "completion_length": 136.70833333333334,
      "epoch": 1.0,
      "grad_norm": 16.801883697509766,
      "kl": 0.11107732852300008,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0001,
      "reward": 5.620846748352051,
      "reward_std": 0.8283557544151942,
      "rewards/concensus_correctness_reward_func": 1.700999992589156,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9094300220410029,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.1354166666666667,
      "step": 4
    },
    {
      "completion_length": 137.625,
      "epoch": 1.5714285714285714,
      "grad_norm": 1251.4542236328125,
      "kl": 29.201528461358976,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0292,
      "reward": 6.083442434668541,
      "reward_std": 0.6032323502004147,
      "rewards/concensus_correctness_reward_func": 1.8181874863803387,
      "rewards/consensus_reward_func": 1.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9065674878656864,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.375,
      "rewards/xmlcount_reward_func": 1.1711875014007092,
      "step": 6
    },
    {
      "completion_length": 141.95833333333334,
      "epoch": 2.0,
      "grad_norm": 80.33175659179688,
      "kl": 2238.1095382701606,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 1.6786,
      "reward": 5.476725300153096,
      "reward_std": 0.5055693089962006,
      "rewards/concensus_correctness_reward_func": 1.338249978919824,
      "rewards/consensus_reward_func": 1.5833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.9041003783543905,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3541666666666667,
      "rewards/xmlcount_reward_func": 1.2135416666666667,
      "step": 8
    },
    {
      "completion_length": 140.0625,
      "epoch": 2.571428571428571,
      "grad_norm": 5685.56640625,
      "kl": 73.77052622684278,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0738,
      "reward": 6.193239971995354,
      "reward_std": 1.6658249166794121,
      "rewards/concensus_correctness_reward_func": 1.9971249867230654,
      "rewards/consensus_reward_func": 1.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9472400806844234,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.359375,
      "rewards/xmlcount_reward_func": 1.2019999995827675,
      "step": 10
    },
    {
      "completion_length": 127.08333333333333,
      "epoch": 3.0,
      "grad_norm": 9.540337562561035,
      "kl": 3.0621676202863455,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0023,
      "reward": 5.709832270940145,
      "reward_std": 0.3538346770995607,
      "rewards/concensus_correctness_reward_func": 1.5369999806086223,
      "rewards/consensus_reward_func": 1.5833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.988540584842364,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3958333333333333,
      "rewards/xmlcount_reward_func": 1.2051250040531158,
      "step": 12
    },
    {
      "completion_length": 132.15625,
      "epoch": 3.571428571428571,
      "grad_norm": 16.967500686645508,
      "kl": 11.426087894011289,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0114,
      "reward": 5.505586206912994,
      "reward_std": 0.27794025372713804,
      "rewards/concensus_correctness_reward_func": 1.4691874869167805,
      "rewards/consensus_reward_func": 1.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9235549308359623,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.2065937519073486,
      "step": 14
    },
    {
      "completion_length": 134.25,
      "epoch": 4.0,
      "grad_norm": 16.20191192626953,
      "kl": 2.2744216828917465,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0017,
      "reward": 6.086844245592753,
      "reward_std": 0.542460098862648,
      "rewards/concensus_correctness_reward_func": 1.7269999807079632,
      "rewards/consensus_reward_func": 1.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9250942468643188,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.2055833339691162,
      "step": 16
    },
    {
      "completion_length": 149.78125,
      "epoch": 4.571428571428571,
      "grad_norm": 23.975969314575195,
      "kl": 21.27271423127968,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0213,
      "reward": 5.366471603512764,
      "reward_std": 0.9596925657242537,
      "rewards/concensus_correctness_reward_func": 1.4007499851286411,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9201591331511736,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.201812505722046,
      "step": 18
    },
    {
      "completion_length": 143.20833333333334,
      "epoch": 5.0,
      "grad_norm": 22.604459762573242,
      "kl": 0.7605764990051588,
      "learning_rate": 0.0,
      "loss": 0.0006,
      "reward": 6.170487980047862,
      "reward_std": 1.3884001096788172,
      "rewards/concensus_correctness_reward_func": 2.157916652659575,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.8883628845214844,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3333333333333333,
      "rewards/xmlcount_reward_func": 1.1242083335916202,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.18189025411120383,
      "train_runtime": 97.0582,
      "train_samples_per_second": 3.297,
      "train_steps_per_second": 0.206
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}