{
  "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": 365.25,
      "epoch": 0.5714285714285714,
      "grad_norm": 9.687833786010742,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 0.6366359508829191,
      "reward_std": 0.42562710761558264,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.27201093931216747,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16931249713525176,
      "step": 2
    },
    {
      "completion_length": 351.5,
      "epoch": 1.0,
      "grad_norm": 3.906970500946045,
      "kl": 0.0019134900843103726,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.1091338998327653,
      "reward_std": 0.6725368414384624,
      "rewards/concensus_correctness_reward_func": 0.3155833364774783,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.35750888466524583,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.186041671782732,
      "step": 4
    },
    {
      "completion_length": 413.4375,
      "epoch": 1.5714285714285714,
      "grad_norm": 6.097729682922363,
      "kl": 0.0037189597824180964,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.423923869850114,
      "reward_std": 0.5216079259407707,
      "rewards/concensus_correctness_reward_func": 0.021124999970197678,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3312051228713244,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07159375073388219,
      "step": 6
    },
    {
      "completion_length": 351.6666666666667,
      "epoch": 2.0,
      "grad_norm": 4.1502275466918945,
      "kl": 0.004164224902827603,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.5243893439571062,
      "reward_std": 0.8923047657299321,
      "rewards/concensus_correctness_reward_func": 0.04041666785875956,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.2865143471087019,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.030791665116945904,
      "step": 8
    },
    {
      "completion_length": 372.25,
      "epoch": 2.571428571428571,
      "grad_norm": 8.598332405090332,
      "kl": 0.0043236340206931345,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.6380010469583794,
      "reward_std": 0.6054888924700208,
      "rewards/concensus_correctness_reward_func": 0.02368750050663948,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.3696885455865413,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18212499632500112,
      "step": 10
    },
    {
      "completion_length": 409.875,
      "epoch": 3.0,
      "grad_norm": 2.899874687194824,
      "kl": 0.04756444354522197,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.423838625351588,
      "reward_std": 1.6299960591519873,
      "rewards/concensus_correctness_reward_func": 0.8333333333333334,
      "rewards/consensus_reward_func": 0.08333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.4091719745968779,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.01466666782895724,
      "step": 12
    },
    {
      "completion_length": 335.71875,
      "epoch": 3.571428571428571,
      "grad_norm": 9.653569221496582,
      "kl": 0.005601304470474133,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.5431684302166104,
      "reward_std": 0.5011135141539853,
      "rewards/concensus_correctness_reward_func": 0.06012500077486038,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.2561059254221618,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16443750448524952,
      "step": 14
    },
    {
      "completion_length": 444.9166666666667,
      "epoch": 4.0,
      "grad_norm": 3.0845658779144287,
      "kl": 0.0030040777589116865,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.13345473275209466,
      "reward_std": 0.8536385462308923,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.29595472060221556,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.24583333109815916,
      "step": 16
    },
    {
      "completion_length": 348.8125,
      "epoch": 4.571428571428571,
      "grad_norm": 15.333535194396973,
      "kl": 0.009468320051382761,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.5691781182540581,
      "reward_std": 0.6094007580832113,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.34920937346760184,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.024656245950609446,
      "step": 18
    },
    {
      "completion_length": 446.8333333333333,
      "epoch": 5.0,
      "grad_norm": 3.190236806869507,
      "kl": 0.06790049554062232,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0001,
      "reward": 0.47946809651330113,
      "reward_std": 0.544023863816013,
      "rewards/concensus_correctness_reward_func": 0.030000001192092896,
      "rewards/consensus_reward_func": 0.08333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.2543014292605221,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.02850000187754631,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.1628679931163789e-05,
      "train_runtime": 1269.8823,
      "train_samples_per_second": 0.252,
      "train_steps_per_second": 0.016
    }
  ],
  "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": 2,
  "trial_name": null,
  "trial_params": null
}