{
  "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": 507.25,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.5102810263633728,
      "kl": 0.0006413383634935599,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.2246774435043335,
      "reward_std": 1.0250092409551144,
      "rewards/concensus_correctness_reward_func": 0.026750000193715096,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.6202712282538414,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.24953125789761543,
      "step": 2
    },
    {
      "completion_length": 545.5357142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.6383160948753357,
      "kl": 0.0006939700771389263,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.9871079708848681,
      "reward_std": 0.9425153072391238,
      "rewards/concensus_correctness_reward_func": 0.06157142775399344,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5393222442695073,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.10050000729305404,
      "step": 4
    },
    {
      "completion_length": 556.75,
      "epoch": 2.0,
      "grad_norm": 0.30501818656921387,
      "kl": 0.0006923160399310291,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9744588136672974,
      "reward_std": 0.997994201523917,
      "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": 0.651923132794244,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.09039285566125597,
      "step": 6
    },
    {
      "completion_length": 358.21875,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5563687086105347,
      "kl": 0.0008131818103720434,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.1429598741233349,
      "reward_std": 1.0274235233664513,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5877098739147186,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.16462498623877764,
      "step": 8
    },
    {
      "completion_length": 722.3214285714286,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.537308931350708,
      "kl": 0.0027192495430686642,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9694735769714627,
      "reward_std": 0.9623457491397858,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6571164429187775,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.02664285898208618,
      "step": 10
    },
    {
      "completion_length": 540.9285714285714,
      "epoch": 4.0,
      "grad_norm": 0.345342218875885,
      "kl": 0.0007426313989396606,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.4026029365403312,
      "reward_std": 1.0735368302890234,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6404600867203304,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.19071428264890397,
      "step": 12
    },
    {
      "completion_length": 501.375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.4603041410446167,
      "kl": 0.0007860659461584873,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.0617278590798378,
      "reward_std": 1.036953940987587,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5582278668880463,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.27693750336766243,
      "step": 14
    },
    {
      "completion_length": 536.1428571428571,
      "epoch": 5.363636363636363,
      "grad_norm": 0.5306868553161621,
      "kl": 0.0007226377077001546,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.5109271705150604,
      "reward_std": 1.1485101410320826,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6943200017724719,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.4237499992762293,
      "step": 16
    },
    {
      "completion_length": 618.7142857142857,
      "epoch": 6.0,
      "grad_norm": 0.2140144258737564,
      "kl": 0.00047585583524778485,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.1479524033410209,
      "reward_std": 1.0819738251822335,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8127023918288094,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0495357130255018,
      "step": 18
    },
    {
      "completion_length": 595.125,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.7731544375419617,
      "kl": 0.0006078763362893369,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.2466152980923653,
      "reward_std": 1.057570207864046,
      "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": 0.6501153353601694,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.2683749981224537,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 8.154420868322632e-07,
      "train_runtime": 1003.4696,
      "train_samples_per_second": 0.319,
      "train_steps_per_second": 0.02
    }
  ],
  "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
}