{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 437.53125,
      "epoch": 0.1,
      "grad_norm": 4.8424882888793945,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 1.2424767836928368,
      "reward_std": 1.3980925279902294,
      "rewards/concensus_correctness_reward_func": 0.19799999985843897,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.4963517915457487,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.17312499787658453,
      "step": 2
    },
    {
      "completion_length": 343.53125,
      "epoch": 0.2,
      "grad_norm": 4.962473392486572,
      "kl": 0.0009593008035153616,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 1.5136843903455883,
      "reward_std": 1.0464290648233145,
      "rewards/concensus_correctness_reward_func": 0.38618749380111694,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.3337156834313646,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2937812586314976,
      "step": 4
    },
    {
      "completion_length": 417.5,
      "epoch": 0.3,
      "grad_norm": 4.399540901184082,
      "kl": 0.0012396429829095723,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.9039205983281136,
      "reward_std": 0.6271124193444848,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.5170456022024155,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.26187500078231096,
      "step": 6
    },
    {
      "completion_length": 438.84375,
      "epoch": 0.4,
      "grad_norm": 5.020246505737305,
      "kl": 0.0013312701448739972,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.44116408098489046,
      "reward_std": 0.9189364665653557,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.3922890628455207,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.07612498779781163,
      "step": 8
    },
    {
      "completion_length": 331.75,
      "epoch": 0.5,
      "grad_norm": 7.140576362609863,
      "kl": 0.0021912034681008663,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 2.658341580070555,
      "reward_std": 2.510888500371948,
      "rewards/concensus_correctness_reward_func": 1.4297499991953373,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.49171655043028295,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.34625000646337867,
      "step": 10
    },
    {
      "completion_length": 329.78125,
      "epoch": 0.6,
      "grad_norm": 3.903331995010376,
      "kl": 0.0027665450907079503,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 1.1588133568875492,
      "reward_std": 0.6736997785046697,
      "rewards/concensus_correctness_reward_func": 0.02437499910593033,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.481500833760947,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.34043748676776886,
      "step": 12
    },
    {
      "completion_length": 400.28125,
      "epoch": 0.7,
      "grad_norm": 4.698159694671631,
      "kl": 0.002569452590250876,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 1.884350948035717,
      "reward_std": 1.5795070074964315,
      "rewards/concensus_correctness_reward_func": 0.6115624997764826,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.6498196963220835,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.37296874553430825,
      "step": 14
    },
    {
      "completion_length": 341.34375,
      "epoch": 0.8,
      "grad_norm": 4.873336315155029,
      "kl": 0.0027480914432089776,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 1.1319349324330688,
      "reward_std": 0.6429186534369364,
      "rewards/concensus_correctness_reward_func": 0.028562499210238457,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.5588411949574947,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.41953124897554517,
      "step": 16
    },
    {
      "completion_length": 490.25,
      "epoch": 0.9,
      "grad_norm": 3.5482892990112305,
      "kl": 0.0023091254115570337,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 1.1968865301460028,
      "reward_std": 2.025821363553405,
      "rewards/concensus_correctness_reward_func": 0.7219999991357327,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5161052519106306,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.10371874924749136,
      "step": 18
    },
    {
      "completion_length": 311.625,
      "epoch": 1.0,
      "grad_norm": 4.714698314666748,
      "kl": 0.003313427048851736,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 2.276610472239554,
      "reward_std": 1.5040997514151968,
      "rewards/concensus_correctness_reward_func": 0.7425625007599592,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.375,
      "rewards/question_recreation_reward_func": 0.578172966837883,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.455875005107373,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.965649425983429e-06,
      "train_runtime": 312.2766,
      "train_samples_per_second": 1.025,
      "train_steps_per_second": 0.064
    }
  ],
  "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
}