{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 281.96875,
      "epoch": 0.1,
      "grad_norm": 161.85971069335938,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 0.38727734284475446,
      "reward_std": 0.34449407683860045,
      "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": 0.13433983590221033,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12793749943375587,
      "step": 2
    },
    {
      "completion_length": 193.71875,
      "epoch": 0.2,
      "grad_norm": 52.69471740722656,
      "kl": 0.0018817850395862479,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.3960398626513779,
      "reward_std": 0.351779872617044,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.1437898592557758,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.002250000834465027,
      "step": 4
    },
    {
      "completion_length": 351.84375,
      "epoch": 0.3,
      "grad_norm": 92.50811004638672,
      "kl": 0.00321150932177261,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.4068023134022951,
      "reward_std": 0.4700370567588834,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.1675835606874898,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0517187500372529,
      "step": 6
    },
    {
      "completion_length": 265.875,
      "epoch": 0.4,
      "grad_norm": 31.071395874023438,
      "kl": 0.0016375983504985925,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.3407291325274855,
      "reward_std": 0.3518169648014009,
      "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": 0.11354162520729005,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.10218750050989911,
      "step": 8
    },
    {
      "completion_length": 233.09375,
      "epoch": 0.5,
      "grad_norm": 64.11283874511719,
      "kl": 0.002194851251260843,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.29012872744351625,
      "reward_std": 0.2820382189238444,
      "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": 0.1166912298212992,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.048437499441206455,
      "step": 10
    },
    {
      "completion_length": 265.03125,
      "epoch": 0.6,
      "grad_norm": 97.68123626708984,
      "kl": 0.008394282865992864,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 1.7402149540721439,
      "reward_std": 2.0602490570163354,
      "rewards/concensus_correctness_reward_func": 1.25,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.11118369019823149,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06653125025331974,
      "step": 12
    },
    {
      "completion_length": 181.96875,
      "epoch": 0.7,
      "grad_norm": 240.0782470703125,
      "kl": 0.003343942934407096,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.7692695415462367,
      "reward_std": 0.9737378221761901,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1118320461246185,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.03243749961256981,
      "step": 14
    },
    {
      "completion_length": 249.3125,
      "epoch": 0.8,
      "grad_norm": 58.18932342529297,
      "kl": 0.003145028207654832,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.274770864401944,
      "reward_std": 0.4574366433080286,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.14783336746040732,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0019375011324882507,
      "step": 16
    },
    {
      "completion_length": 202.28125,
      "epoch": 0.9,
      "grad_norm": 6.318305969238281,
      "kl": 0.001271584853384411,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.12331437465036288,
      "reward_std": 0.13753751426702365,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.1274393722997047,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0041250004433095455,
      "step": 18
    },
    {
      "completion_length": 282.65625,
      "epoch": 1.0,
      "grad_norm": 118.41968536376953,
      "kl": 0.0025129051246040035,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.09278386156074703,
      "reward_std": 0.20849884240305983,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.09925261698663235,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.006468750711064786,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.7734387003874873e-06,
      "train_runtime": 684.0995,
      "train_samples_per_second": 0.468,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}