{
  "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": 439.75,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.33189961314201355,
      "kl": 0.0005682226837961935,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.8935811221599579,
      "reward_std": 1.1520937494933605,
      "rewards/concensus_correctness_reward_func": 0.05575000122189522,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.49667483754456043,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.20053125359117985,
      "step": 2
    },
    {
      "completion_length": 517.5,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.34845486283302307,
      "kl": 0.0006451955580684755,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 2.103976920247078,
      "reward_std": 2.594899445772171,
      "rewards/concensus_correctness_reward_func": 1.4285714285714286,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.6586555327687945,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.4118214558277811,
      "step": 4
    },
    {
      "completion_length": 503.60714285714283,
      "epoch": 2.0,
      "grad_norm": 0.3112787902355194,
      "kl": 0.0006537369460732277,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.9017176287514823,
      "reward_std": 2.761974368776594,
      "rewards/concensus_correctness_reward_func": 0.7780000013964516,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.4881462114197867,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.007285714149475098,
      "step": 6
    },
    {
      "completion_length": 488.09375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.28854992985725403,
      "kl": 0.0006033929603290744,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.5143466033041477,
      "reward_std": 0.7794156074523926,
      "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": 0.4986591096967459,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": -0.12493750266730785,
      "step": 8
    },
    {
      "completion_length": 445.25,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.2975492477416992,
      "kl": 0.0007233569548199219,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.6810689483370099,
      "reward_std": 1.0756073594093323,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.42706896364688873,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.021857144577162608,
      "step": 10
    },
    {
      "completion_length": 436.92857142857144,
      "epoch": 4.0,
      "grad_norm": 0.3033583462238312,
      "kl": 0.0007356918441863465,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.7826846497399467,
      "reward_std": 0.9522724577358791,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.48600608323301586,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.10025001210825783,
      "step": 12
    },
    {
      "completion_length": 447.5,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.3856496512889862,
      "kl": 0.0006589046752196737,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.3541742600500584,
      "reward_std": 1.122757863253355,
      "rewards/concensus_correctness_reward_func": 0.20525000244379044,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.5546430200338364,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0942812692373991,
      "step": 14
    },
    {
      "completion_length": 478.2142857142857,
      "epoch": 5.363636363636363,
      "grad_norm": 0.39702117443084717,
      "kl": 0.0005860687191930733,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.7731724424021584,
      "reward_std": 1.3566676803997584,
      "rewards/concensus_correctness_reward_func": 0.06371428711073739,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4409581848553249,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.10649998698915754,
      "step": 16
    },
    {
      "completion_length": 483.17857142857144,
      "epoch": 6.0,
      "grad_norm": 0.2792685925960541,
      "kl": 0.0006680597808943796,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.7258293820278985,
      "reward_std": 2.5234424557004655,
      "rewards/concensus_correctness_reward_func": 0.7142857142857143,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.6093294237341199,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.04421427526644298,
      "step": 18
    },
    {
      "completion_length": 437.4375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.38684436678886414,
      "kl": 0.0006600186170544475,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.6950539969839156,
      "reward_std": 0.6780839432030916,
      "rewards/concensus_correctness_reward_func": 0.05575000122189522,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.45280400663614273,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.06349999457597733,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.047600265901565e-07,
      "train_runtime": 611.9145,
      "train_samples_per_second": 0.523,
      "train_steps_per_second": 0.033
    }
  ],
  "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
}