{
  "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": 376.28125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.3437902331352234,
      "kl": 0.000827149415272288,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.9650179520249367,
      "reward_std": 0.9399564154446125,
      "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": 0.48545546270906925,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.26081249862909317,
      "step": 2
    },
    {
      "completion_length": 451.2857142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.5616311430931091,
      "kl": 0.0006403406815869468,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.5441367796489172,
      "reward_std": 1.3162878240857805,
      "rewards/concensus_correctness_reward_func": 0.0816428576196943,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6427796483039856,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3197142779827118,
      "step": 4
    },
    {
      "completion_length": 462.10714285714283,
      "epoch": 2.0,
      "grad_norm": 0.4168936312198639,
      "kl": 0.000719171848946384,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.8503530536379132,
      "reward_std": 1.232443732874734,
      "rewards/concensus_correctness_reward_func": 0.1277142869574683,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5647101657731193,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.1456428606595312,
      "step": 6
    },
    {
      "completion_length": 422.0625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5831401944160461,
      "kl": 0.0006976408658374567,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.1317045465111732,
      "reward_std": 1.075602475553751,
      "rewards/concensus_correctness_reward_func": 0.05581250041723251,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5921108238399029,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.3431562567129731,
      "step": 8
    },
    {
      "completion_length": 443.64285714285717,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.4295225143432617,
      "kl": 0.0007067695010586508,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 1.6077298362340247,
      "reward_std": 1.0551166534423828,
      "rewards/concensus_correctness_reward_func": 0.1914999932050705,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4601941300289972,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.366749997649874,
      "step": 10
    },
    {
      "completion_length": 512.8571428571429,
      "epoch": 4.0,
      "grad_norm": 0.42578762769699097,
      "kl": 0.0006562869945940163,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.4705148552145277,
      "reward_std": 0.6741891162736076,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.43669344059058596,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.03760716106210436,
      "step": 12
    },
    {
      "completion_length": 460.1875,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5053578615188599,
      "kl": 0.0006863677699584514,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.2665400207042694,
      "reward_std": 1.1816745065152645,
      "rewards/concensus_correctness_reward_func": 0.1038750009611249,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6119150072336197,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.17575000412762165,
      "step": 14
    },
    {
      "completion_length": 596.8928571428571,
      "epoch": 5.363636363636363,
      "grad_norm": 0.40903177857398987,
      "kl": 0.0006001410407147237,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.8541636381830487,
      "reward_std": 1.013209513255528,
      "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": 0.48498509185654776,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.20846428615706308,
      "step": 16
    },
    {
      "completion_length": 388.64285714285717,
      "epoch": 6.0,
      "grad_norm": 0.3834454119205475,
      "kl": 0.0007274486041361732,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.0557954971279417,
      "reward_std": 1.018987434250968,
      "rewards/concensus_correctness_reward_func": 0.009000000144754137,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5256883757455009,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.19967857216085708,
      "step": 18
    },
    {
      "completion_length": 399.28125,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4910911023616791,
      "kl": 0.0007835296382836532,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 0.9040417112410069,
      "reward_std": 0.9552651233971119,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5213229823857546,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0625,
      "rewards/xmlcount_reward_func": 0.25771874852944165,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.35625968925524e-07,
      "train_runtime": 597.6366,
      "train_samples_per_second": 0.535,
      "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
}