{
  "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": 448.96875,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4079512357711792,
      "kl": 0.0006960896716918796,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.014976717531681,
      "reward_std": 0.931159220635891,
      "rewards/concensus_correctness_reward_func": 0.019187500700354576,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.4754454605281353,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.042156245559453964,
      "step": 2
    },
    {
      "completion_length": 503.35714285714283,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.3215738534927368,
      "kl": 0.0007693321510617222,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.7434799671173096,
      "reward_std": 1.4438068866729736,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.2857142857142857,
      "rewards/question_recreation_reward_func": 0.545658535190991,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.5343214379889625,
      "step": 4
    },
    {
      "completion_length": 501.5,
      "epoch": 2.0,
      "grad_norm": 0.4019313454627991,
      "kl": 0.0007268055175830211,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.6937032427106584,
      "reward_std": 2.689331420830318,
      "rewards/concensus_correctness_reward_func": 0.7362142865146909,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5813103488513401,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.05239285635096686,
      "step": 6
    },
    {
      "completion_length": 454.6875,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.433057576417923,
      "kl": 0.0007550113077741116,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.1343575585633516,
      "reward_std": 2.4107902091927826,
      "rewards/concensus_correctness_reward_func": 0.6973749808967113,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.589295007288456,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.050812505185604095,
      "step": 8
    },
    {
      "completion_length": 545.7857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.33662065863609314,
      "kl": 0.0006870871750704412,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 2.292337281363351,
      "reward_std": 2.4016739779285023,
      "rewards/concensus_correctness_reward_func": 0.7142857142857143,
      "rewards/consensus_reward_func": 0.6428571428571429,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.6199443808623722,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.05357142857142857,
      "rewards/xmlcount_reward_func": 0.11882142403296062,
      "step": 10
    },
    {
      "completion_length": 430.32142857142856,
      "epoch": 4.0,
      "grad_norm": 0.37114790081977844,
      "kl": 0.0007296750430084233,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.9510723671742848,
      "reward_std": 1.1165074642215456,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.47832239099911283,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.04417857527732849,
      "step": 12
    },
    {
      "completion_length": 552.34375,
      "epoch": 4.7272727272727275,
      "grad_norm": 2.1891822814941406,
      "kl": 0.0006460850017901976,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.6809651907533407,
      "reward_std": 1.454764710739255,
      "rewards/concensus_correctness_reward_func": 0.03125,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5482776816934347,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.3360625049099326,
      "step": 14
    },
    {
      "completion_length": 487.89285714285717,
      "epoch": 5.363636363636363,
      "grad_norm": 0.29302528500556946,
      "kl": 0.000639179945989911,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.9617090416806084,
      "reward_std": 0.9098760443074363,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.4583519186292376,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.1997857200247901,
      "step": 16
    },
    {
      "completion_length": 432.17857142857144,
      "epoch": 6.0,
      "grad_norm": 4.430377006530762,
      "kl": 0.0008528920589014888,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.4834006769316537,
      "reward_std": 1.13985803936209,
      "rewards/concensus_correctness_reward_func": 0.043857144457953315,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.14285714285714285,
      "rewards/question_recreation_reward_func": 0.6183649897575378,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.0890357175043651,
      "step": 18
    },
    {
      "completion_length": 538.59375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4364769458770752,
      "kl": 0.0006118008568591904,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.3893648125231266,
      "reward_std": 1.4084616005420685,
      "rewards/concensus_correctness_reward_func": 0.053187502548098564,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.5439273174852133,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.15162499900907278,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.502134226593625e-07,
      "train_runtime": 650.1533,
      "train_samples_per_second": 0.492,
      "train_steps_per_second": 0.031
    }
  ],
  "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
}