{
  "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": 156.15625,
      "epoch": 0.5714285714285714,
      "grad_norm": 1.0225909948349,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 5.676510624587536,
      "reward_std": 0.1792343765264377,
      "rewards/concensus_correctness_reward_func": 1.8677499741315842,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9376669223420322,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.93359375,
      "step": 2
    },
    {
      "completion_length": 151.29166666666666,
      "epoch": 1.0,
      "grad_norm": 1.8705910444259644,
      "kl": 0.002289636841548296,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 6.2501862446467085,
      "reward_std": 0.015200429246760905,
      "rewards/concensus_correctness_reward_func": 2.0946666399637857,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9992696046829224,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9895833333333334,
      "step": 4
    },
    {
      "completion_length": 153.0,
      "epoch": 1.5714285714285714,
      "grad_norm": 13.82950496673584,
      "kl": 0.06422327210748335,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "reward": 5.931046634912491,
      "reward_std": 0.17281945190916304,
      "rewards/concensus_correctness_reward_func": 1.9927499741315842,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9382966953562573,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9375,
      "step": 6
    },
    {
      "completion_length": 241.58333333333334,
      "epoch": 2.0,
      "grad_norm": 10.438579559326172,
      "kl": 0.019742314315711457,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 5.764677663644155,
      "reward_std": 0.46667487422625226,
      "rewards/concensus_correctness_reward_func": 1.8476666410764058,
      "rewards/consensus_reward_func": 1.9166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.958677684267362,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9583333333333334,
      "step": 8
    },
    {
      "completion_length": 328.46875,
      "epoch": 2.571428571428571,
      "grad_norm": 1.2060940265655518,
      "kl": 0.07959534629480913,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0001,
      "reward": 5.976425543427467,
      "reward_std": 0.10864399373531342,
      "rewards/concensus_correctness_reward_func": 2.052999973297119,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.9273318447521888,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.93359375,
      "step": 10
    },
    {
      "completion_length": 688.0416666666666,
      "epoch": 3.0,
      "grad_norm": 0.5728873610496521,
      "kl": 0.030441884223061304,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 5.688896477222443,
      "reward_std": 0.33814341326554614,
      "rewards/concensus_correctness_reward_func": 1.8476666410764058,
      "rewards/consensus_reward_func": 1.9166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.9922715028127035,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9322916666666666,
      "step": 12
    },
    {
      "completion_length": 649.09375,
      "epoch": 3.571428571428571,
      "grad_norm": 1.0835548639297485,
      "kl": 0.09085463339579292,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0001,
      "reward": 5.874189883470535,
      "reward_std": 0.2532270722440444,
      "rewards/concensus_correctness_reward_func": 1.9927499741315842,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.9244086839607917,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.89453125,
      "step": 14
    },
    {
      "completion_length": 688.2083333333334,
      "epoch": 4.0,
      "grad_norm": 0.02957252599298954,
      "kl": 0.049732094863429666,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 5.917583306630452,
      "reward_std": 0.014731391022602717,
      "rewards/concensus_correctness_reward_func": 1.9279999732971191,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 1.0,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9895833333333334,
      "step": 16
    },
    {
      "completion_length": 724.6875,
      "epoch": 4.571428571428571,
      "grad_norm": 0.452230840921402,
      "kl": 0.07972098368918523,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0001,
      "reward": 5.7718739956617355,
      "reward_std": 0.04437024153594393,
      "rewards/concensus_correctness_reward_func": 1.9279999732971191,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.937624009733554,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.90625,
      "step": 18
    },
    {
      "completion_length": 571.7083333333334,
      "epoch": 5.0,
      "grad_norm": 1.3899379968643188,
      "kl": 0.05015358647021154,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 5.990053792794545,
      "reward_std": 0.34443719188372296,
      "rewards/concensus_correctness_reward_func": 2.0143333077430725,
      "rewards/consensus_reward_func": 1.9166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.9965538879235586,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8958333333333334,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 4.433556200638123e-05,
      "train_runtime": 9772.9598,
      "train_samples_per_second": 0.033,
      "train_steps_per_second": 0.002
    }
  ],
  "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
}