{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 339.0625,
      "epoch": 0.7272727272727273,
      "grad_norm": 159.21080017089844,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 2.149061784846708,
      "reward_std": 0.5872901907423511,
      "rewards/concensus_correctness_reward_func": 1.25,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.36281182791572064,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.286250002682209,
      "step": 2
    },
    {
      "completion_length": 373.10714285714283,
      "epoch": 1.3636363636363638,
      "grad_norm": 8.481891632080078,
      "kl": 0.0013382230494503997,
      "learning_rate": 4.752422169756047e-07,
      "loss": 0.0,
      "reward": 0.7975434958934784,
      "reward_std": 0.9021987184283456,
      "rewards/concensus_correctness_reward_func": 0.0065714285842009956,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.3671863339841366,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.20950000573481833,
      "step": 4
    },
    {
      "completion_length": 460.89285714285717,
      "epoch": 2.0,
      "grad_norm": 6.806843280792236,
      "kl": 98.88055705858486,
      "learning_rate": 4.058724504646834e-07,
      "loss": 0.0865,
      "reward": 0.6992480934464506,
      "reward_std": 0.7328717685096697,
      "rewards/concensus_correctness_reward_func": 0.026142856904438565,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.44917667218084845,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08107144172702517,
      "step": 6
    },
    {
      "completion_length": 382.5,
      "epoch": 2.7272727272727275,
      "grad_norm": 4.367931365966797,
      "kl": 0.022643437314400217,
      "learning_rate": 3.056302334890786e-07,
      "loss": 0.0,
      "reward": 1.372615270782262,
      "reward_std": 1.5901283603161573,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.3863340192474425,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.23628125060349703,
      "step": 8
    },
    {
      "completion_length": 329.7857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 54.86536407470703,
      "kl": 0.04375256254570559,
      "learning_rate": 1.9436976651092142e-07,
      "loss": 0.0,
      "reward": 2.1406553887895177,
      "reward_std": 2.0013393280761584,
      "rewards/concensus_correctness_reward_func": 0.786714285079922,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.4365125641758953,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4888571522065571,
      "step": 10
    },
    {
      "completion_length": 404.10714285714283,
      "epoch": 4.0,
      "grad_norm": 3.3620553016662598,
      "kl": 0.001507662024648328,
      "learning_rate": 9.412754953531663e-08,
      "loss": 0.0,
      "reward": 1.4721720404922962,
      "reward_std": 1.412929367141,
      "rewards/concensus_correctness_reward_func": 0.7142857142857143,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.3543505490358387,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3321071480001722,
      "step": 12
    },
    {
      "completion_length": 410.40625,
      "epoch": 4.7272727272727275,
      "grad_norm": 5.982357978820801,
      "kl": 0.007274331575899851,
      "learning_rate": 2.475778302439524e-08,
      "loss": 0.0,
      "reward": 2.401631656102836,
      "reward_std": 2.540218022186309,
      "rewards/concensus_correctness_reward_func": 1.4245000071823597,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.4692254235269502,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2579062422737479,
      "step": 14
    },
    {
      "completion_length": 304.3333333333333,
      "epoch": 5.0,
      "kl": 0.08397372621887673,
      "reward": 0.8354225680232048,
      "reward_std": 0.4316548115263383,
      "rewards/concensus_correctness_reward_func": 0.06000000238418579,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.36858925223350525,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.24016666722794375,
      "step": 15,
      "total_flos": 0.0,
      "train_loss": 0.011549665033817292,
      "train_runtime": 207.717,
      "train_samples_per_second": 1.155,
      "train_steps_per_second": 0.072
    }
  ],
  "logging_steps": 2,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}