{
  "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": 294.3125,
      "epoch": 0.5714285714285714,
      "grad_norm": 0.6074583530426025,
      "kl": 0.0008409952279180288,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.133454579859972,
      "reward_std": 0.6814509630203247,
      "rewards/concensus_correctness_reward_func": 0.04206249862909317,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.42214206606149673,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.41924999561160803,
      "step": 2
    },
    {
      "completion_length": 353.125,
      "epoch": 1.0,
      "grad_norm": 47.75371551513672,
      "kl": 0.0022826601731746146,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.965188905596733,
      "reward_std": 2.484490007162094,
      "rewards/concensus_correctness_reward_func": 0.8333333333333334,
      "rewards/consensus_reward_func": 0.08333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5360221962134043,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.041666666666666664,
      "rewards/xmlcount_reward_func": 0.22083332824210325,
      "step": 4
    },
    {
      "completion_length": 322.65625,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.5006768703460693,
      "kl": 0.0008434747505816631,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.9395091831684113,
      "reward_std": 1.1901352517306805,
      "rewards/concensus_correctness_reward_func": 0.31156249600462615,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.47363421507179737,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.38868751376867294,
      "step": 6
    },
    {
      "completion_length": 304.9166666666667,
      "epoch": 2.0,
      "grad_norm": 0.315962016582489,
      "kl": 0.0009037207928486168,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.922406812508901,
      "reward_std": 0.7466032604376475,
      "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": 0.501031776269277,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.33804167062044144,
      "step": 8
    },
    {
      "completion_length": 299.6875,
      "epoch": 2.571428571428571,
      "grad_norm": 0.6998950242996216,
      "kl": 0.0009004111489048228,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 2.027998574078083,
      "reward_std": 2.434359833598137,
      "rewards/concensus_correctness_reward_func": 0.6409374997019768,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.45209239795804024,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3724687579087913,
      "step": 10
    },
    {
      "completion_length": 278.1666666666667,
      "epoch": 3.0,
      "grad_norm": 0.37337160110473633,
      "kl": 0.0008745406521484256,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.5453739960988362,
      "reward_std": 1.1052613481879234,
      "rewards/concensus_correctness_reward_func": 0.07408333414544661,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.43824899196624756,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.041666666666666664,
      "rewards/xmlcount_reward_func": 0.40804166346788406,
      "step": 12
    },
    {
      "completion_length": 298.40625,
      "epoch": 3.571428571428571,
      "grad_norm": 0.7391191124916077,
      "kl": 0.0008627813731436618,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 3.311558946967125,
      "reward_std": 4.124635513871908,
      "rewards/concensus_correctness_reward_func": 1.4486249685287476,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.6010276973247528,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.3712812513113022,
      "step": 14
    },
    {
      "completion_length": 347.25,
      "epoch": 4.0,
      "grad_norm": 0.3265421986579895,
      "kl": 0.0008276354152864466,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.2531405289967854,
      "reward_std": 0.898355116446813,
      "rewards/concensus_correctness_reward_func": 0.058666667280097805,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4269738793373108,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.35083333899577457,
      "step": 16
    },
    {
      "completion_length": 297.3125,
      "epoch": 4.571428571428571,
      "grad_norm": 0.4362623989582062,
      "kl": 0.0008101245621219277,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 2.52060616761446,
      "reward_std": 2.1808464396744967,
      "rewards/concensus_correctness_reward_func": 1.2743749991059303,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.49613741412758827,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.3438437443692237,
      "step": 18
    },
    {
      "completion_length": 309.7916666666667,
      "epoch": 5.0,
      "grad_norm": 0.25287431478500366,
      "kl": 0.0008112282569830617,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8035016556580862,
      "reward_std": 1.0816570321718852,
      "rewards/concensus_correctness_reward_func": 0.01824999942133824,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.31116832544406253,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2240833342075348,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 8.527416355263995e-07,
      "train_runtime": 1647.6492,
      "train_samples_per_second": 0.194,
      "train_steps_per_second": 0.012
    }
  ],
  "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": 4,
  "trial_name": null,
  "trial_params": null
}