{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.7272727272727275,
  "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": 418.59375,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.705902099609375,
      "kl": 0.0007176655053626746,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.2138379961252213,
      "reward_std": 0.9511784389615059,
      "rewards/concensus_correctness_reward_func": 0.052000001072883606,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6546192467212677,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.19471874088048935,
      "step": 2
    },
    {
      "completion_length": 545.6785714285714,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4254428744316101,
      "kl": 0.0007325080223381519,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.7083579770156315,
      "reward_std": 1.2698204985686712,
      "rewards/concensus_correctness_reward_func": 0.02971428632736206,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.38753653903092655,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.005392868603978839,
      "step": 4
    },
    {
      "completion_length": 521.8214285714286,
      "epoch": 2.0,
      "grad_norm": 0.26565220952033997,
      "kl": 0.0006595713951225792,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.7453854935509818,
      "reward_std": 1.2103857483182634,
      "rewards/concensus_correctness_reward_func": 0.0025000000106436865,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.7418498141424996,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.429607161453792,
      "step": 6
    },
    {
      "completion_length": 398.34375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.707371175289154,
      "kl": 0.0008318861873704009,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.9764930829405785,
      "reward_std": 1.182244822382927,
      "rewards/concensus_correctness_reward_func": 0.026000000536441803,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.494743081741035,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.19012501090765,
      "step": 8
    },
    {
      "completion_length": 586.8571428571429,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.4055241346359253,
      "kl": 0.0006922878757385271,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9346474262752703,
      "reward_std": 0.8339587066854749,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5591831388218063,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.14332143430198943,
      "step": 10
    },
    {
      "completion_length": 424.0357142857143,
      "epoch": 4.0,
      "grad_norm": 0.6968374848365784,
      "kl": 0.0007245375101254987,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.283107191324234,
      "reward_std": 1.1396433966500419,
      "rewards/concensus_correctness_reward_func": 0.0675714271409171,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6747857428022793,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.030678574528012956,
      "step": 12
    },
    {
      "completion_length": 482.78125,
      "epoch": 4.7272727272727275,
      "grad_norm": 18.94466209411621,
      "kl": 0.0011837783531518653,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.2526901960372925,
      "reward_std": 0.9441794194281101,
      "rewards/concensus_correctness_reward_func": 0.05925000109709799,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.542658930644393,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3382812477648258,
      "step": 14
    },
    {
      "completion_length": 439.5357142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.509993851184845,
      "kl": 0.0012793634170001106,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.9020633314337049,
      "reward_std": 0.9196936445576804,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.588849025113242,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.043928576367242,
      "step": 16
    },
    {
      "completion_length": 420.57142857142856,
      "epoch": 6.0,
      "grad_norm": 0.4443037807941437,
      "kl": 0.0007548547083778041,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.938133961388043,
      "reward_std": 1.0177770512444633,
      "rewards/concensus_correctness_reward_func": 0.03785714081355503,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5216696602957589,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09289286392075675,
      "step": 18
    },
    {
      "completion_length": 508.03125,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.43586501479148865,
      "kl": 0.0006341933367366437,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.1600369960069656,
      "reward_std": 1.1098762974143028,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6399120055139065,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0826250072568655,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 7.721477743416472e-07,
      "train_runtime": 1665.8377,
      "train_samples_per_second": 0.192,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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
}