{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "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": 226.125,
      "epoch": 0.5714285714285714,
      "grad_norm": 95.34217834472656,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 3.317263310775161,
      "reward_std": 0.7623368987697177,
      "rewards/concensus_correctness_reward_func": 0.7034375071525574,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.8094507567584515,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.1875,
      "rewards/xmlcount_reward_func": 0.6168750058859587,
      "step": 2
    },
    {
      "completion_length": 226.25,
      "epoch": 1.0,
      "grad_norm": 12.096796035766602,
      "kl": 0.36931437719613314,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0003,
      "reward": 5.054104218880336,
      "reward_std": 0.6514259271401291,
      "rewards/concensus_correctness_reward_func": 1.5468333189686139,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8888541584213575,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.0767500028014183,
      "step": 4
    },
    {
      "completion_length": 230.8125,
      "epoch": 1.5714285714285714,
      "grad_norm": 1704.6728515625,
      "kl": 538.2474660237785,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.5383,
      "reward": 5.211234629154205,
      "reward_std": 0.7910094170511002,
      "rewards/concensus_correctness_reward_func": 1.531874991953373,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9016721583902836,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.090187506750226,
      "step": 6
    },
    {
      "completion_length": 251.58333333333334,
      "epoch": 2.0,
      "grad_norm": 553.1924438476562,
      "kl": 32052595394.726242,
      "learning_rate": 3.867370395306068e-07,
      "loss": 24039448.0,
      "reward": 5.353926002979279,
      "reward_std": 0.5099359281981984,
      "rewards/concensus_correctness_reward_func": 1.399833324054877,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.9367175698280334,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2708333333333333,
      "rewards/xmlcount_reward_func": 1.1632083356380463,
      "step": 8
    },
    {
      "completion_length": 151.875,
      "epoch": 2.571428571428571,
      "grad_norm": 36.49054718017578,
      "kl": 919743488.4859731,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 919743.5625,
      "reward": 5.4931019097566605,
      "reward_std": 0.18205567242694087,
      "rewards/concensus_correctness_reward_func": 1.4473749864846468,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9017893611453474,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.1751875020563602,
      "step": 10
    },
    {
      "completion_length": 199.66666666666666,
      "epoch": 3.0,
      "grad_norm": 277.873046875,
      "kl": 1.6430801190435886,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0012,
      "reward": 5.224228014548619,
      "reward_std": 0.7860883808073899,
      "rewards/concensus_correctness_reward_func": 1.4592500030994415,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.8800196101268133,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3958333333333333,
      "rewards/xmlcount_reward_func": 1.072458339234193,
      "step": 12
    },
    {
      "completion_length": 170.5,
      "epoch": 3.571428571428571,
      "grad_norm": 789.8179321289062,
      "kl": 49.930873655714095,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0499,
      "reward": 5.666330635547638,
      "reward_std": 0.4050608313991688,
      "rewards/concensus_correctness_reward_func": 1.5347499996423721,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.9514243565499783,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.296875,
      "rewards/xmlcount_reward_func": 1.1957812458276749,
      "step": 14
    },
    {
      "completion_length": 174.95833333333334,
      "epoch": 4.0,
      "grad_norm": 65.40475463867188,
      "kl": 12807.581744248668,
      "learning_rate": 8.067960709356478e-08,
      "loss": 9.6057,
      "reward": 5.111119508743286,
      "reward_std": 0.7853585355915129,
      "rewards/concensus_correctness_reward_func": 1.4379166476428509,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9771194805701574,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.112749993801117,
      "step": 16
    },
    {
      "completion_length": 194.15625,
      "epoch": 4.571428571428571,
      "grad_norm": 211.3500518798828,
      "kl": 2574419094.178031,
      "learning_rate": 3.013156219837776e-08,
      "loss": 2574419.0,
      "reward": 5.727417126297951,
      "reward_std": 0.4276373315078672,
      "rewards/concensus_correctness_reward_func": 1.5562499929219484,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.9604795426130295,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.1794374957680702,
      "step": 18
    },
    {
      "completion_length": 304.1666666666667,
      "epoch": 5.0,
      "grad_norm": 215.08251953125,
      "kl": 6.090956116095185,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0046,
      "reward": 5.549857000509898,
      "reward_std": 0.45215619466034696,
      "rewards/concensus_correctness_reward_func": 1.5639999906222026,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.9101070041457812,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.075750008225441,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2753362.076245628,
      "train_runtime": 176.7383,
      "train_samples_per_second": 1.811,
      "train_steps_per_second": 0.113
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}