{
  "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": 354.375,
      "epoch": 0.5714285714285714,
      "grad_norm": 49.52602005004883,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 0.9383160970173776,
      "reward_std": 0.6981886693974957,
      "rewards/concensus_correctness_reward_func": 0.07312500104308128,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.38715985463932157,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22803124831989408,
      "step": 2
    },
    {
      "completion_length": 356.3333333333333,
      "epoch": 1.0,
      "grad_norm": 4.169597148895264,
      "kl": 0.0012856803320270653,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 2.5887889433652163,
      "reward_std": 0.4948835385342439,
      "rewards/concensus_correctness_reward_func": 1.7216666688521702,
      "rewards/consensus_reward_func": 0.16666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.46508053798849386,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.15204168188696107,
      "step": 4
    },
    {
      "completion_length": 368.5625,
      "epoch": 1.5714285714285714,
      "grad_norm": 5.638073921203613,
      "kl": 0.0013180703645048197,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.6876568291336298,
      "reward_std": 1.839660624973476,
      "rewards/concensus_correctness_reward_func": 0.8455000091344118,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.4301255493192002,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0995312468148768,
      "step": 6
    },
    {
      "completion_length": 372.2916666666667,
      "epoch": 2.0,
      "grad_norm": 4.154600143432617,
      "kl": 0.0014752235292689875,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.8212927306691806,
      "reward_std": 0.8196525213619074,
      "rewards/concensus_correctness_reward_func": 0.1940833323945602,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3333333333333333,
      "rewards/question_recreation_reward_func": 0.5812510376175245,
      "rewards/soft_format_reward_func": 0.020833333333333332,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.4417916735013326,
      "step": 8
    },
    {
      "completion_length": 383.15625,
      "epoch": 2.571428571428571,
      "grad_norm": 16.695470809936523,
      "kl": 0.07043927300401265,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0001,
      "reward": 1.534049527719617,
      "reward_std": 1.5760781085118651,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5517057775286958,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16984374448657036,
      "step": 10
    },
    {
      "completion_length": 371.9583333333333,
      "epoch": 3.0,
      "grad_norm": 2.8863260746002197,
      "kl": 0.0017407779766169067,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.18266752983133,
      "reward_std": 0.867066275406008,
      "rewards/concensus_correctness_reward_func": 0.05316666762034098,
      "rewards/consensus_reward_func": 0.08333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.16666666666666666,
      "rewards/question_recreation_reward_func": 0.41800082971652347,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.4406666619082292,
      "step": 12
    },
    {
      "completion_length": 319.46875,
      "epoch": 3.571428571428571,
      "grad_norm": 16.16633415222168,
      "kl": 0.11263099296047585,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0001,
      "reward": 1.1694285530829802,
      "reward_std": 1.0718703293532599,
      "rewards/concensus_correctness_reward_func": 0.07856249995529652,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5383347786264494,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.17753126262687147,
      "step": 14
    },
    {
      "completion_length": 405.875,
      "epoch": 4.0,
      "grad_norm": 5.651745796203613,
      "kl": 0.0033685511152725667,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.5393020945290725,
      "reward_std": 1.078627958893776,
      "rewards/concensus_correctness_reward_func": 0.25058333824078244,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.5867187188317379,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2019999995827675,
      "step": 16
    },
    {
      "completion_length": 322.46875,
      "epoch": 4.571428571428571,
      "grad_norm": 52.18980026245117,
      "kl": 0.28215775619173655,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0003,
      "reward": 2.4000893030897714,
      "reward_std": 1.9916711993137142,
      "rewards/concensus_correctness_reward_func": 0.8871875032782555,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.5139330840320326,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.37396874791011214,
      "step": 18
    },
    {
      "completion_length": 431.25,
      "epoch": 5.0,
      "grad_norm": 3.143980026245117,
      "kl": 0.05561711380141787,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.2029351410456002,
      "reward_std": 1.5713017135082434,
      "rewards/concensus_correctness_reward_func": 0.10975000262260437,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.08333333333333333,
      "rewards/question_recreation_reward_func": 0.5286434657561282,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.020833333333333332,
      "rewards/xmlcount_reward_func": 0.2103749985496203,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 5.1419436931610105e-05,
      "train_runtime": 1252.5907,
      "train_samples_per_second": 0.255,
      "train_steps_per_second": 0.016
    }
  ],
  "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
}