{
  "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": 476.0625,
      "epoch": 0.7272727272727273,
      "grad_norm": 10.53377628326416,
      "kl": 0.0032427225669380277,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.0333673618733883,
      "reward_std": 1.089045725762844,
      "rewards/concensus_correctness_reward_func": 0.0078125,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5672736261039972,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.19265625812113285,
      "step": 2
    },
    {
      "completion_length": 499.7857142857143,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4395878314971924,
      "kl": 0.003004203500625278,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.0352854515824998,
      "reward_std": 1.028205773660115,
      "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": 0.5722498106104987,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.08803571122033256,
      "step": 4
    },
    {
      "completion_length": 524.0714285714286,
      "epoch": 2.0,
      "grad_norm": 2.6935906410217285,
      "kl": 0.003622612516794886,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.7735679277351923,
      "reward_std": 2.1254964641162326,
      "rewards/concensus_correctness_reward_func": 0.7142857142857143,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.5233893607343946,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.17874999237912043,
      "step": 6
    },
    {
      "completion_length": 525.75,
      "epoch": 2.7272727272727275,
      "grad_norm": 12.967586517333984,
      "kl": 0.002542009999160655,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.899361290037632,
      "reward_std": 2.4031090512871742,
      "rewards/concensus_correctness_reward_func": 0.6499375198036432,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5525800865143538,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": 0.10309375077486038,
      "step": 8
    },
    {
      "completion_length": 492.39285714285717,
      "epoch": 3.3636363636363638,
      "grad_norm": 4.6203131675720215,
      "kl": 0.005334377687956605,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9975986863885608,
      "reward_std": 0.7083837645394462,
      "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": 0.6341701107365745,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22057142640863145,
      "step": 10
    },
    {
      "completion_length": 521.0,
      "epoch": 4.0,
      "grad_norm": 0.3556123375892639,
      "kl": 0.00322423768895013,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.9530901972736631,
      "reward_std": 0.830559179186821,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5915901682206562,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0757857199226107,
      "step": 12
    },
    {
      "completion_length": 533.375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.4453391134738922,
      "kl": 0.0025502603384666145,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.1019916096702218,
      "reward_std": 1.050562597811222,
      "rewards/concensus_correctness_reward_func": 0.0234375,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5280541349202394,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11300000175833702,
      "step": 14
    },
    {
      "completion_length": 594.7857142857143,
      "epoch": 5.363636363636363,
      "grad_norm": 0.3583681583404541,
      "kl": 0.0023932272202468346,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.919810621866158,
      "reward_std": 1.0099013958658491,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5384177735873631,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.07782142769013133,
      "step": 16
    },
    {
      "completion_length": 470.14285714285717,
      "epoch": 6.0,
      "grad_norm": 0.4184271991252899,
      "kl": 0.0033485564137143748,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.5545862998281206,
      "reward_std": 1.0683594048023224,
      "rewards/concensus_correctness_reward_func": 0.02035714260169438,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6901934444904327,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.3797500048364912,
      "step": 18
    },
    {
      "completion_length": 558.0625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.9845871925354004,
      "kl": 0.0026532525953371078,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.2567915990948677,
      "reward_std": 1.0687441676855087,
      "rewards/concensus_correctness_reward_func": 0.017812499776482582,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6595728062093258,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.0012812372297048569,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 2.9224504714875365e-06,
      "train_runtime": 684.5779,
      "train_samples_per_second": 0.467,
      "train_steps_per_second": 0.029
    }
  ],
  "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
}