{
  "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": 277.4375,
      "epoch": 0.5714285714285714,
      "grad_norm": 6.789405822753906,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 2.3237390760332346,
      "reward_std": 1.5290137782576494,
      "rewards/concensus_correctness_reward_func": 0.8025624714791775,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5013640912948176,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6916875028982759,
      "step": 2
    },
    {
      "completion_length": 240.41666666666666,
      "epoch": 1.0,
      "grad_norm": 4.878081798553467,
      "kl": 0.002382916432300893,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 2.5553423265616098,
      "reward_std": 0.5683276208971316,
      "rewards/concensus_correctness_reward_func": 0.42125000059604645,
      "rewards/consensus_reward_func": 0.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6468839564671119,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.0705416450897853,
      "step": 4
    },
    {
      "completion_length": 320.875,
      "epoch": 1.5714285714285714,
      "grad_norm": 81.54737091064453,
      "kl": 0.0035806876549031585,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 2.4654137454926968,
      "reward_std": 1.087094948044978,
      "rewards/concensus_correctness_reward_func": 0.2971874997019768,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7451949981041253,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9230312146246433,
      "step": 6
    },
    {
      "completion_length": 322.5416666666667,
      "epoch": 2.0,
      "grad_norm": 4.378849506378174,
      "kl": 0.006137622442717354,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 2.417641818523407,
      "reward_std": 0.9718923264493545,
      "rewards/concensus_correctness_reward_func": 0.27650000154972076,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.7511000943680605,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8067083209753036,
      "step": 8
    },
    {
      "completion_length": 263.78125,
      "epoch": 2.571428571428571,
      "grad_norm": 7.5848822593688965,
      "kl": 0.010713139752624556,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 2.334370069205761,
      "reward_std": 1.0359732687065843,
      "rewards/concensus_correctness_reward_func": 0.2455000001937151,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6358388164080679,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.0155312195420265,
      "step": 10
    },
    {
      "completion_length": 265.6666666666667,
      "epoch": 3.0,
      "grad_norm": 6.6377458572387695,
      "kl": 0.0317639890126884,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 2.7291881144046783,
      "reward_std": 0.9668942355783656,
      "rewards/concensus_correctness_reward_func": 0.49399999777475995,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.6956047763427099,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9562499796350797,
      "step": 12
    },
    {
      "completion_length": 258.9375,
      "epoch": 3.571428571428571,
      "grad_norm": 5.181027889251709,
      "kl": 0.01114592287922278,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 2.9897976852953434,
      "reward_std": 1.4940979477250949,
      "rewards/concensus_correctness_reward_func": 0.7932500019669533,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.7159852180629969,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.1055624894797802,
      "step": 14
    },
    {
      "completion_length": 292.5,
      "epoch": 4.0,
      "grad_norm": 5.158603191375732,
      "kl": 0.03570538493416583,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 2.0371210873126984,
      "reward_std": 0.7878820024585972,
      "rewards/concensus_correctness_reward_func": 0.23308333257834116,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6077877643207709,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9462499924314519,
      "step": 16
    },
    {
      "completion_length": 276.5625,
      "epoch": 4.571428571428571,
      "grad_norm": 5.967617988586426,
      "kl": 0.018310003797523677,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 2.2351491451263428,
      "reward_std": 0.8348404020653106,
      "rewards/concensus_correctness_reward_func": 0.1536250002682209,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.7462741751223803,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9602499902248383,
      "step": 18
    },
    {
      "completion_length": 427.9583333333333,
      "epoch": 5.0,
      "grad_norm": 4.099704265594482,
      "kl": 356.1126844395476,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.2671,
      "reward": 1.3956897395352523,
      "reward_std": 1.659088636127611,
      "rewards/concensus_correctness_reward_func": 0.18975000083446503,
      "rewards/consensus_reward_func": 0.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6243564016185701,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2482500026623408,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.026718258014625462,
      "train_runtime": 202.5588,
      "train_samples_per_second": 1.58,
      "train_steps_per_second": 0.099
    }
  ],
  "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
}