{
  "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": 214.03125,
      "epoch": 0.5714285714285714,
      "grad_norm": 2.25909686088562,
      "kl": 2.055882580578327,
      "learning_rate": 5e-07,
      "loss": 0.0021,
      "reward": 9.400555908679962,
      "reward_std": 7.645632594823837,
      "rewards/concensus_correctness_reward_func": 6.082437450066209,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.47852450609207153,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.089593768119812,
      "step": 2
    },
    {
      "completion_length": 186.83333333333334,
      "epoch": 1.0,
      "grad_norm": 2.7692301273345947,
      "kl": 3.8899477273225784,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0029,
      "reward": 8.638863325119019,
      "reward_std": 9.872711817423502,
      "rewards/concensus_correctness_reward_func": 5.2618333498636884,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1666666666666667,
      "rewards/question_recreation_reward_func": 0.4033632775147756,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.0153333346048992,
      "step": 4
    },
    {
      "completion_length": 205.8125,
      "epoch": 1.5714285714285714,
      "grad_norm": 1.690827488899231,
      "kl": 1.3158315289765596,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0013,
      "reward": 10.236574172973633,
      "reward_std": 8.59436348080635,
      "rewards/concensus_correctness_reward_func": 6.853062365204096,
      "rewards/consensus_reward_func": 0.8125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.75,
      "rewards/question_recreation_reward_func": 0.5572301335632801,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.0137812718749046,
      "step": 6
    },
    {
      "completion_length": 199.54166666666666,
      "epoch": 2.0,
      "grad_norm": 0.9657280445098877,
      "kl": 2.4459491223096848,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0018,
      "reward": 7.454156160354614,
      "reward_std": 4.875544846057892,
      "rewards/concensus_correctness_reward_func": 3.7049166560173035,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5833333333333333,
      "rewards/question_recreation_reward_func": 0.5354477179547151,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.3333333333333333,
      "rewards/xmlcount_reward_func": 1.0471250017484028,
      "step": 8
    },
    {
      "completion_length": 212.75,
      "epoch": 2.571428571428571,
      "grad_norm": 2.664607048034668,
      "kl": 1.9820397943258286,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.002,
      "reward": 8.188820868730545,
      "reward_std": 6.3342499807477,
      "rewards/concensus_correctness_reward_func": 4.561374917626381,
      "rewards/consensus_reward_func": 0.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0625,
      "rewards/question_recreation_reward_func": 0.5064770616590977,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.28125,
      "rewards/xmlcount_reward_func": 1.0897187441587448,
      "step": 10
    },
    {
      "completion_length": 224.75,
      "epoch": 3.0,
      "grad_norm": 1.3392062187194824,
      "kl": 1.0724541172385216,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0008,
      "reward": 9.960493564605713,
      "reward_std": 9.589544971783956,
      "rewards/concensus_correctness_reward_func": 6.262416521708171,
      "rewards/consensus_reward_func": 0.5833333333333334,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.1666666666666667,
      "rewards/question_recreation_reward_func": 0.5654099782307943,
      "rewards/soft_format_reward_func": 0.020833333333333332,
      "rewards/strict_format_reward_func": 0.3125,
      "rewards/xmlcount_reward_func": 1.0493333439032237,
      "step": 12
    },
    {
      "completion_length": 194.09375,
      "epoch": 3.571428571428571,
      "grad_norm": 2.2625324726104736,
      "kl": 11.008582189679146,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.011,
      "reward": 11.076181292533875,
      "reward_std": 9.206684939563274,
      "rewards/concensus_correctness_reward_func": 7.465874969959259,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.875,
      "rewards/question_recreation_reward_func": 0.591150302439928,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.1875,
      "rewards/xmlcount_reward_func": 1.0816562995314598,
      "step": 14
    },
    {
      "completion_length": 190.375,
      "epoch": 4.0,
      "grad_norm": 3.054802894592285,
      "kl": 3.555610882739226,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0027,
      "reward": 10.138537247975668,
      "reward_std": 6.685347358385722,
      "rewards/concensus_correctness_reward_func": 6.943416674931844,
      "rewards/consensus_reward_func": 0.8333333333333334,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.8333333333333334,
      "rewards/question_recreation_reward_func": 0.32128722469011944,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.20833333333333334,
      "rewards/xmlcount_reward_func": 0.9988333384195963,
      "step": 16
    },
    {
      "completion_length": 247.84375,
      "epoch": 4.571428571428571,
      "grad_norm": 2.052443027496338,
      "kl": 1.029653798788786,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.001,
      "reward": 13.016432762145996,
      "reward_std": 8.460283733904362,
      "rewards/concensus_correctness_reward_func": 9.081437408924103,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.25,
      "rewards/question_recreation_reward_func": 0.5980887971818447,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.234375,
      "rewards/xmlcount_reward_func": 0.9775312542915344,
      "step": 18
    },
    {
      "completion_length": 194.20833333333334,
      "epoch": 5.0,
      "grad_norm": 1.08579683303833,
      "kl": 3.6348742122451463,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0027,
      "reward": 8.196823000907898,
      "reward_std": 6.5993068019549055,
      "rewards/concensus_correctness_reward_func": 5.288250011702378,
      "rewards/consensus_reward_func": 0.6666666666666666,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5,
      "rewards/question_recreation_reward_func": 0.39248936623334885,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.2916666666666667,
      "rewards/xmlcount_reward_func": 1.057749996582667,
      "step": 20
    },
    {
      "epoch": 5.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.0028341330355033277,
      "train_runtime": 631.0603,
      "train_samples_per_second": 0.507,
      "train_steps_per_second": 0.032
    }
  ],
  "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": 4,
  "trial_name": null,
  "trial_params": null
}