{
  "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": 525.125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.3608642816543579,
      "kl": 0.0006143059144960716,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.5608648490160704,
      "reward_std": 1.0222108997404575,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5961773414164782,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.28531250287778676,
      "step": 2
    },
    {
      "completion_length": 460.0,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.5428079962730408,
      "kl": 0.0007601975895730513,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.5838006500686918,
      "reward_std": 0.804934425013406,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.49690777701990946,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.05596427193709782,
      "step": 4
    },
    {
      "completion_length": 488.14285714285717,
      "epoch": 2.0,
      "grad_norm": 0.8935153484344482,
      "kl": 0.0007490423699242196,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9144215328352792,
      "reward_std": 0.7190878838300705,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4790643964494978,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.203214273921081,
      "step": 6
    },
    {
      "completion_length": 438.78125,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.47657153010368347,
      "kl": 0.0008095718003460206,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.7231580801308155,
      "reward_std": 0.8215600848197937,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4932205602526665,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.08931250590831041,
      "step": 8
    },
    {
      "completion_length": 537.5357142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.38067469000816345,
      "kl": 0.0007165856160489577,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.5994923753397805,
      "reward_std": 1.0666048697062902,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5457423755100795,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.08910714302744184,
      "step": 10
    },
    {
      "completion_length": 444.17857142857144,
      "epoch": 4.0,
      "grad_norm": 0.36448630690574646,
      "kl": 0.0006463666754176042,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.6938098456178393,
      "reward_std": 0.7231421300343105,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6181312714304242,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.13860713464340993,
      "step": 12
    },
    {
      "completion_length": 522.40625,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.3578232228755951,
      "kl": 0.0007084836906869896,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.8141302950680256,
      "reward_std": 1.2437973320484161,
      "rewards/concensus_correctness_reward_func": 0.0013749999925494194,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5410053096711636,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04074999690055847,
      "step": 14
    },
    {
      "completion_length": 464.9642857142857,
      "epoch": 5.363636363636363,
      "grad_norm": 0.3252517282962799,
      "kl": 0.0005667324169605438,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.1408257484436035,
      "reward_std": 1.0813172715050834,
      "rewards/concensus_correctness_reward_func": 0.03200000098773411,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.49575433135032654,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09521429347140449,
      "step": 16
    },
    {
      "completion_length": 500.7857142857143,
      "epoch": 6.0,
      "grad_norm": 0.46374425292015076,
      "kl": 0.0006648623301381511,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 0.9500235191413334,
      "reward_std": 1.0528212296111243,
      "rewards/concensus_correctness_reward_func": 0.016000000493867055,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5561663721288953,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.23499999408211028,
      "step": 18
    },
    {
      "completion_length": 527.25,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.618638277053833,
      "kl": 0.000659027551591862,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.8378414288163185,
      "reward_std": 1.0202128142118454,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5720602013170719,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.12515626475214958,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.387914027072838e-07,
      "train_runtime": 637.4258,
      "train_samples_per_second": 0.502,
      "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
}