{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.533333333333333,
  "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": 266.28125,
      "epoch": 0.26666666666666666,
      "grad_norm": 8.141995429992676,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 1.424088518600911,
      "reward_std": 1.5162724429828813,
      "rewards/concensus_correctness_reward_func": 0.7984375022351742,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.23296350735472515,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.20518749789334834,
      "step": 2
    },
    {
      "completion_length": 386.6875,
      "epoch": 0.5333333333333333,
      "grad_norm": 13.386856079101562,
      "kl": 0.0009829530590650393,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.4425873305881396,
      "reward_std": 0.5438859037785733,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.21777483861660585,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16231250297278166,
      "step": 4
    },
    {
      "completion_length": 432.3125,
      "epoch": 0.8,
      "grad_norm": 6.167685031890869,
      "kl": 0.0009359349714941345,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.3409410311141983,
      "reward_std": 2.039761731866747,
      "rewards/concensus_correctness_reward_func": 0.8625000044703484,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.29850351018831134,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0549375070258975,
      "step": 6
    },
    {
      "completion_length": 454.25,
      "epoch": 1.0,
      "grad_norm": 6.142190933227539,
      "kl": 0.0009890225483104587,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.737714820386221,
      "reward_std": 2.133114734509339,
      "rewards/concensus_correctness_reward_func": 0.9953333338101705,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.21858982291693488,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2737916558980942,
      "step": 8
    },
    {
      "completion_length": 368.125,
      "epoch": 1.2666666666666666,
      "grad_norm": 6.768038749694824,
      "kl": 0.0013801488876197254,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.5209990027360618,
      "reward_std": 0.31013503335998394,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.3073427475756034,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1511562536470592,
      "step": 10
    },
    {
      "completion_length": 426.875,
      "epoch": 1.5333333333333332,
      "grad_norm": 7.938072681427002,
      "kl": 0.002378987972406321,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.3561361387837678,
      "reward_std": 0.6410467773093842,
      "rewards/concensus_correctness_reward_func": 0.06006250157952309,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.19357362412847579,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": -0.038124993443489075,
      "step": 12
    },
    {
      "completion_length": 307.125,
      "epoch": 1.8,
      "grad_norm": 10.00179386138916,
      "kl": 0.0017145342389994767,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.63448842021171,
      "reward_std": 0.5480758486446575,
      "rewards/concensus_correctness_reward_func": 0.12150000035762787,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.3178321768937167,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.05453124921768904,
      "step": 14
    },
    {
      "completion_length": 316.625,
      "epoch": 2.0,
      "grad_norm": 6.416198253631592,
      "kl": 0.001730306171036015,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.6352979155878226,
      "reward_std": 0.6209855465325139,
      "rewards/concensus_correctness_reward_func": 0.07616666456063588,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.28025625739246607,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.09137499332427979,
      "step": 16
    },
    {
      "completion_length": 363.34375,
      "epoch": 2.2666666666666666,
      "grad_norm": 6.9517621994018555,
      "kl": 0.0017399428979842924,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 2.2221032098168507,
      "reward_std": 2.9361006908584386,
      "rewards/concensus_correctness_reward_func": 1.4221250005066395,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.22985316393896937,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.2420000028796494,
      "step": 18
    },
    {
      "completion_length": 458.0625,
      "epoch": 2.533333333333333,
      "grad_norm": 7.372166633605957,
      "kl": 0.0013834526780556189,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.27183452215831494,
      "reward_std": 0.3158404653077014,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1614907661205507,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11034375289455056,
      "step": 20
    },
    {
      "epoch": 2.533333333333333,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.1945143342018127e-06,
      "train_runtime": 1334.148,
      "train_samples_per_second": 0.24,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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
}