{
  "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": 327.65625,
      "epoch": 0.5714285714285714,
      "grad_norm": 5.439347267150879,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 5.520737506449223,
      "reward_std": 3.2909717541188,
      "rewards/concensus_correctness_reward_func": 2.5635000048205256,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.6877687377855182,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.15625,
      "rewards/xmlcount_reward_func": 0.8632187554612756,
      "step": 2
    },
    {
      "completion_length": 252.33333333333334,
      "epoch": 1.0,
      "grad_norm": 4.0184855461120605,
      "kl": 0.010818432356851796,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 8.684666375319162,
      "reward_std": 1.5065515285047393,
      "rewards/concensus_correctness_reward_func": 3.6100000143051147,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 0.7159164861465493,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.2337500055631,
      "step": 4
    },
    {
      "completion_length": 245.6875,
      "epoch": 1.5714285714285714,
      "grad_norm": 6.915022373199463,
      "kl": 0.06673898943699896,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "reward": 7.0409883707761765,
      "reward_std": 0.9532257597893476,
      "rewards/concensus_correctness_reward_func": 2.244500007480383,
      "rewards/consensus_reward_func": 1.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3125,
      "rewards/question_recreation_reward_func": 0.6557384426705539,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.1407499946653843,
      "step": 6
    },
    {
      "completion_length": 243.625,
      "epoch": 2.0,
      "grad_norm": 19.483837127685547,
      "kl": 4.200557626783848,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0032,
      "reward": 5.987198710441589,
      "reward_std": 2.036489742497603,
      "rewards/concensus_correctness_reward_func": 1.7320000020166237,
      "rewards/consensus_reward_func": 1.0833333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.6770320308084289,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.2031666735808055,
      "step": 8
    },
    {
      "completion_length": 255.1875,
      "epoch": 2.571428571428571,
      "grad_norm": 5.460272789001465,
      "kl": 0.20452789647970349,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0002,
      "reward": 6.985092893242836,
      "reward_std": 0.8012243972043507,
      "rewards/concensus_correctness_reward_func": 2.285875003784895,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.7666553407907486,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.28125,
      "rewards/xmlcount_reward_func": 1.2138125002384186,
      "step": 10
    },
    {
      "completion_length": 230.95833333333334,
      "epoch": 3.0,
      "grad_norm": 3.845531702041626,
      "kl": 0.2164986760665973,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0002,
      "reward": 7.489987115065257,
      "reward_std": 2.1764259268141664,
      "rewards/concensus_correctness_reward_func": 2.999666664749384,
      "rewards/consensus_reward_func": 1.1666666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1666666666666667,
      "rewards/question_recreation_reward_func": 0.6700704532365004,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.1952500144640605,
      "step": 12
    },
    {
      "completion_length": 248.59375,
      "epoch": 3.571428571428571,
      "grad_norm": 6.079870700836182,
      "kl": 4.278497097082436,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0043,
      "reward": 7.929257869720459,
      "reward_std": 1.9918286694446579,
      "rewards/concensus_correctness_reward_func": 3.0668124998919666,
      "rewards/consensus_reward_func": 1.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.7234140876680613,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.201531246304512,
      "step": 14
    },
    {
      "completion_length": 236.25,
      "epoch": 4.0,
      "grad_norm": 9.029818534851074,
      "kl": 0.5101165429999431,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0004,
      "reward": 7.506435265143712,
      "reward_std": 2.85386072875311,
      "rewards/concensus_correctness_reward_func": 3.479166721304258,
      "rewards/consensus_reward_func": 0.9166666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.6784769212827086,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.1821250120798747,
      "step": 16
    },
    {
      "completion_length": 247.1875,
      "epoch": 4.571428571428571,
      "grad_norm": 6.256153106689453,
      "kl": 0.19237934635020792,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0002,
      "reward": 6.571806162595749,
      "reward_std": 2.076732322340831,
      "rewards/concensus_correctness_reward_func": 2.143374997191131,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.641462342813611,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.296875,
      "rewards/xmlcount_reward_func": 1.177593745291233,
      "step": 18
    },
    {
      "completion_length": 264.5833333333333,
      "epoch": 5.0,
      "grad_norm": 28.579320907592773,
      "kl": 1.1237625325253855,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0008,
      "reward": 7.580948352813721,
      "reward_std": 2.492990162844459,
      "rewards/concensus_correctness_reward_func": 3.1105000029007592,
      "rewards/consensus_reward_func": 1.4166666666666667,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1666666666666667,
      "rewards/question_recreation_reward_func": 0.568948294967413,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.1875,
      "rewards/xmlcount_reward_func": 1.1306666526943445,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0009275825573240581,
      "train_runtime": 247.8981,
      "train_samples_per_second": 1.291,
      "train_steps_per_second": 0.081
    }
  ],
  "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
}