{
  "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": 463.46875,
      "epoch": 0.7272727272727273,
      "grad_norm": 4.7122392654418945,
      "kl": 0.0023938784142956138,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.3335974533110857,
      "reward_std": 0.9099930226802826,
      "rewards/concensus_correctness_reward_func": 0.11125000193715096,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5996600110083818,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.27893750881776214,
      "step": 2
    },
    {
      "completion_length": 473.5357142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.35275641083717346,
      "kl": 0.00162335585004517,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.2401375004223414,
      "reward_std": 1.1636551831449782,
      "rewards/concensus_correctness_reward_func": 0.03235714137554169,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.6997446715831757,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07946428337267467,
      "step": 4
    },
    {
      "completion_length": 548.2142857142857,
      "epoch": 2.0,
      "grad_norm": 0.29174864292144775,
      "kl": 0.001679773342662624,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.5835289103644234,
      "reward_std": 1.2641019523143768,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5858860335179737,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.35478571483067106,
      "step": 6
    },
    {
      "completion_length": 506.09375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.43735402822494507,
      "kl": 0.0018278197894687764,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.307539526373148,
      "reward_std": 0.752528958953917,
      "rewards/concensus_correctness_reward_func": 0.0260624997317791,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6156957671046257,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22828123718500137,
      "step": 8
    },
    {
      "completion_length": 529.3571428571429,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.46579766273498535,
      "kl": 0.0015770103948722994,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.6101772274289812,
      "reward_std": 1.2770880801337106,
      "rewards/concensus_correctness_reward_func": 0.07957142804350172,
      "rewards/consensus_reward_func": 0.6428571428571429,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7367129921913147,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.13317857363394328,
      "step": 10
    },
    {
      "completion_length": 488.75,
      "epoch": 4.0,
      "grad_norm": 0.43027985095977783,
      "kl": 0.0018851734598034195,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.1790043881961279,
      "reward_std": 0.9463666294302259,
      "rewards/concensus_correctness_reward_func": 0.021571427583694458,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5378972675119128,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.29810712380068644,
      "step": 12
    },
    {
      "completion_length": 443.28125,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.35241565108299255,
      "kl": 0.0019940045895054936,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.4534906595945358,
      "reward_std": 1.537332609295845,
      "rewards/concensus_correctness_reward_func": 0.0293125007301569,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6077094078063965,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.42584373615682125,
      "step": 14
    },
    {
      "completion_length": 404.2857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.41596055030822754,
      "kl": 0.0019185203293870603,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.3030461839267187,
      "reward_std": 1.104127287864685,
      "rewards/concensus_correctness_reward_func": 0.04614285698958805,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5750104912689754,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.3068928521658693,
      "step": 16
    },
    {
      "completion_length": 512.0714285714286,
      "epoch": 6.0,
      "grad_norm": 0.3919805586338043,
      "kl": 0.0017016392750000314,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.4165151970727103,
      "reward_std": 1.0552355008465903,
      "rewards/concensus_correctness_reward_func": 0.04207142761775425,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.71719377381461,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.13939285171883448,
      "step": 18
    },
    {
      "completion_length": 558.65625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.35119664669036865,
      "kl": 0.0012935696577187628,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.1207781359553337,
      "reward_std": 1.0906498096883297,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7737468928098679,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.21546875592321157,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.6483349213558541e-06,
      "train_runtime": 611.4563,
      "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
}