{
  "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": 574.125,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.2845724821090698,
      "kl": 0.0005749856500187889,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.7415162026882172,
      "reward_std": 0.8856677860021591,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6607661917805672,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": -0.07549997000023723,
      "step": 2
    },
    {
      "completion_length": 508.0,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.35529419779777527,
      "kl": 0.0007047405898837107,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.0851636188370841,
      "reward_std": 0.9851899061884198,
      "rewards/concensus_correctness_reward_func": 0.02914285659790039,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5143064622368131,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.3631428522723062,
      "step": 4
    },
    {
      "completion_length": 542.7142857142857,
      "epoch": 2.0,
      "grad_norm": 0.3987818956375122,
      "kl": 0.0006694004363712988,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 1.1537523886987142,
      "reward_std": 1.110692071063178,
      "rewards/concensus_correctness_reward_func": 0.02914285659790039,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6857523918151855,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.0638571275132043,
      "step": 6
    },
    {
      "completion_length": 572.6875,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.45522359013557434,
      "kl": 0.0006443273268814664,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.7862032204866409,
      "reward_std": 0.8552147410809994,
      "rewards/concensus_correctness_reward_func": 0.026624999940395355,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6428594682365656,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.008281249552965164,
      "step": 8
    },
    {
      "completion_length": 477.07142857142856,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.7522605657577515,
      "kl": 0.0008250060907032873,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9303557702473232,
      "reward_std": 0.7904164152485984,
      "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": 0.5055700625692096,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.2640714320753302,
      "step": 10
    },
    {
      "completion_length": 579.2142857142857,
      "epoch": 4.0,
      "grad_norm": 0.4029735028743744,
      "kl": 0.0005824401658693594,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.1292478569916315,
      "reward_std": 0.8686830273696354,
      "rewards/concensus_correctness_reward_func": 0.030428571360451833,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5652121348040444,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2478928565979004,
      "step": 12
    },
    {
      "completion_length": 491.71875,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.4175528883934021,
      "kl": 0.0006781894153391477,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.8274601846933365,
      "reward_std": 0.827268935739994,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5699914516881108,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": -0.07065626233816147,
      "step": 14
    },
    {
      "completion_length": 584.6428571428571,
      "epoch": 5.363636363636363,
      "grad_norm": 0.6693198680877686,
      "kl": 0.0005940364166495524,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.452887875693185,
      "reward_std": 1.118608525821141,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.6081378630229405,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.20189285916941507,
      "step": 16
    },
    {
      "completion_length": 631.2142857142857,
      "epoch": 6.0,
      "grad_norm": 0.3829941749572754,
      "kl": 0.0006050001913016396,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.1395895055362157,
      "reward_std": 1.3548330409186227,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.4571609433208193,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.16457142042262213,
      "step": 18
    },
    {
      "completion_length": 467.9375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.7331616878509521,
      "kl": 0.0006881270383019,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.052180115133524,
      "reward_std": 1.0876893140375614,
      "rewards/concensus_correctness_reward_func": 0.025499999523162842,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5559613723307848,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2050937619060278,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.091722354995e-07,
      "train_runtime": 676.4725,
      "train_samples_per_second": 0.473,
      "train_steps_per_second": 0.03
    }
  ],
  "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
}