{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "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": 350.71875,
      "epoch": 0.43243243243243246,
      "grad_norm": 65.70259857177734,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.6082046327646822,
      "reward_std": 0.35992033989168704,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.17861089296638966,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11709374934434891,
      "step": 2
    },
    {
      "completion_length": 393.75,
      "epoch": 0.8648648648648649,
      "grad_norm": 7.660000801086426,
      "kl": 0.001224917887157062,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.49315808760002255,
      "reward_std": 0.6389677075203508,
      "rewards/concensus_correctness_reward_func": 0.05706249922513962,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.26434558955952525,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": -0.03137499839067459,
      "step": 4
    },
    {
      "completion_length": 497.9230769230769,
      "epoch": 1.2162162162162162,
      "grad_norm": 6.0304131507873535,
      "kl": 0.0009788802395073266,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.1541900704256617,
      "reward_std": 0.45879994098728416,
      "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": 0.22045929206965062,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.06626923153033623,
      "step": 6
    },
    {
      "completion_length": 406.78125,
      "epoch": 1.6486486486486487,
      "grad_norm": 15.076179504394531,
      "kl": 0.0017617166886338964,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.3269138870527968,
      "reward_std": 0.6460093287169002,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.22428888059221208,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.022375002328772098,
      "step": 8
    },
    {
      "completion_length": 488.7307692307692,
      "epoch": 2.0,
      "grad_norm": 6.2193827629089355,
      "kl": 0.001622364901077862,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.3494957430431476,
      "reward_std": 0.5567665794470276,
      "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": 0.29799574685211366,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.05149999948648306,
      "step": 10
    },
    {
      "completion_length": 390.0625,
      "epoch": 2.4324324324324325,
      "grad_norm": 8.906612396240234,
      "kl": 0.0037370253667177167,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.4767173932050355,
      "reward_std": 0.3033358519896865,
      "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": 0.2625923941959627,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.15162499994039536,
      "step": 12
    },
    {
      "completion_length": 408.375,
      "epoch": 2.864864864864865,
      "grad_norm": 13.671435356140137,
      "kl": 0.00329646668251371,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.4860580612439662,
      "reward_std": 0.6226890149264364,
      "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": 0.2399018236901611,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12115624523721635,
      "step": 14
    },
    {
      "completion_length": 404.03846153846155,
      "epoch": 3.2162162162162162,
      "grad_norm": 4.43944787979126,
      "kl": 0.0013814868915897722,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.47342465072870255,
      "reward_std": 0.5211216426239564,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07692307692307693,
      "rewards/question_recreation_reward_func": 0.33350156304927975,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06300000273264371,
      "step": 16
    },
    {
      "completion_length": 317.28125,
      "epoch": 3.6486486486486487,
      "grad_norm": 19.275449752807617,
      "kl": 0.0050008348443952855,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.5576832590159029,
      "reward_std": 0.3490732302016113,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.23296450590714812,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1997187520028092,
      "step": 18
    },
    {
      "completion_length": 449.61538461538464,
      "epoch": 4.0,
      "grad_norm": 2.9545230865478516,
      "kl": 0.004267214562367791,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.41548942430661273,
      "reward_std": 0.4358092499180482,
      "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": 0.33898942459088105,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07649999828292774,
      "step": 20
    },
    {
      "epoch": 4.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.185814082622528e-06,
      "train_runtime": 1108.963,
      "train_samples_per_second": 0.289,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}