{
  "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": 247.96875,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.8010811805725098,
      "kl": 0.019702246645465493,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 6.358962595462799,
      "reward_std": 5.9570339396595955,
      "rewards/concensus_correctness_reward_func": 3.879124917089939,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.5039626322686672,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.41337500140070915,
      "step": 2
    },
    {
      "completion_length": 238.83333333333334,
      "epoch": 1.0,
      "grad_norm": 0.5217065811157227,
      "kl": 0.01854657397295038,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 6.90355630715688,
      "reward_std": 7.463931441307068,
      "rewards/concensus_correctness_reward_func": 4.435749997695287,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8333333333333334,
      "rewards/question_recreation_reward_func": 0.4824729959170024,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7353333433469137,
      "step": 4
    },
    {
      "completion_length": 278.75,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.7691784501075745,
      "kl": 0.018247827072627842,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 6.612219661474228,
      "reward_std": 6.372465223073959,
      "rewards/concensus_correctness_reward_func": 3.9843124710023403,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.125,
      "rewards/question_recreation_reward_func": 0.518469788134098,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5313124936074018,
      "step": 6
    },
    {
      "completion_length": 269.5,
      "epoch": 2.0,
      "grad_norm": 0.3396792709827423,
      "kl": 0.01360964464644591,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 8.294459501902262,
      "reward_std": 9.611950885504484,
      "rewards/concensus_correctness_reward_func": 5.185000002384186,
      "rewards/consensus_reward_func": 0.8333333333333334,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.5659175018469492,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.041666666666666664,
      "rewards/xmlcount_reward_func": 0.6685416574279467,
      "step": 8
    },
    {
      "completion_length": 268.15625,
      "epoch": 2.571428571428571,
      "grad_norm": 1.2183020114898682,
      "kl": 0.017386948107741773,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 5.708646282553673,
      "reward_std": 6.0934536680579185,
      "rewards/concensus_correctness_reward_func": 3.3134999983012676,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.5308025721460581,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.046875,
      "rewards/xmlcount_reward_func": 0.3174687586724758,
      "step": 10
    },
    {
      "completion_length": 261.7083333333333,
      "epoch": 3.0,
      "grad_norm": 0.43166789412498474,
      "kl": 0.01620952303831776,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 6.960117697715759,
      "reward_std": 6.693348368008931,
      "rewards/concensus_correctness_reward_func": 4.011333306630452,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.4166666666666667,
      "rewards/question_recreation_reward_func": 0.4418676992257436,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.5694166744748751,
      "step": 12
    },
    {
      "completion_length": 227.34375,
      "epoch": 3.571428571428571,
      "grad_norm": 1.3438464403152466,
      "kl": 0.01737916993442923,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 9.795244306325912,
      "reward_std": 8.31887637078762,
      "rewards/concensus_correctness_reward_func": 6.6009374894201756,
      "rewards/consensus_reward_func": 0.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1875,
      "rewards/question_recreation_reward_func": 0.5840878151357174,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.5789687428623438,
      "step": 14
    },
    {
      "completion_length": 254.54166666666666,
      "epoch": 4.0,
      "grad_norm": 0.40249231457710266,
      "kl": 0.018325194871673983,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 5.305556386709213,
      "reward_std": 6.021024058262507,
      "rewards/concensus_correctness_reward_func": 2.9476666202147803,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.35226469735304516,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.40145833293596905,
      "step": 16
    },
    {
      "completion_length": 247.1875,
      "epoch": 4.571428571428571,
      "grad_norm": 0.5813286900520325,
      "kl": 0.019225917756557465,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 8.893802970647812,
      "reward_std": 8.175329744815826,
      "rewards/concensus_correctness_reward_func": 5.639312408864498,
      "rewards/consensus_reward_func": 0.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1875,
      "rewards/question_recreation_reward_func": 0.6366780698299408,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.6021875012665987,
      "step": 18
    },
    {
      "completion_length": 291.125,
      "epoch": 5.0,
      "grad_norm": 0.5054320096969604,
      "kl": 0.014116137598951658,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 5.380371883511543,
      "reward_std": 5.594302038351695,
      "rewards/concensus_correctness_reward_func": 3.2625832756360373,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0833333333333333,
      "rewards/question_recreation_reward_func": 0.5376218656698862,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2468333343664805,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.5284208802768263e-05,
      "train_runtime": 438.1597,
      "train_samples_per_second": 0.73,
      "train_steps_per_second": 0.046
    }
  ],
  "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": 4,
  "trial_name": null,
  "trial_params": null
}