{
  "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": 540.9375,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.37452343106269836,
      "kl": 0.0006274964398471639,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.81034174002707,
      "reward_std": 0.9283705502748489,
      "rewards/concensus_correctness_reward_func": 0.02006250061094761,
      "rewards/consensus_reward_func": 0.375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.48043547198176384,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.06515624839812517,
      "step": 2
    },
    {
      "completion_length": 490.4642857142857,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4153035581111908,
      "kl": 0.0008459048778084772,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.7054810194032533,
      "reward_std": 1.1043086307389396,
      "rewards/concensus_correctness_reward_func": 0.06878571850912911,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.39808812950338635,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.20782141919646943,
      "step": 4
    },
    {
      "completion_length": 678.9642857142857,
      "epoch": 2.0,
      "grad_norm": 0.15924641489982605,
      "kl": 0.0006268782183594469,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.5602122715541294,
      "reward_std": 1.1294751082147871,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5895694068499974,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.3150714337825775,
      "step": 6
    },
    {
      "completion_length": 575.9375,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.31094732880592346,
      "kl": 0.0006407882065104786,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 0.2878359891474247,
      "reward_std": 0.9032582081854343,
      "rewards/concensus_correctness_reward_func": 0.02006250061094761,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5208985023200512,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03125,
      "rewards/xmlcount_reward_func": -0.34687500819563866,
      "step": 8
    },
    {
      "completion_length": 633.1428571428571,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.5089343190193176,
      "kl": 0.0006442998710554093,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.43217410147190094,
      "reward_std": 1.045479723385402,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.49028123702321735,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.2902500012091228,
      "step": 10
    },
    {
      "completion_length": 548.6428571428571,
      "epoch": 4.0,
      "grad_norm": 0.2996707856655121,
      "kl": 0.0006327040069403925,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 0.6915942558220455,
      "reward_std": 0.7801709430558341,
      "rewards/concensus_correctness_reward_func": 0.012142857270581382,
      "rewards/consensus_reward_func": 0.07142857142857142,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.465487077832222,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.14253573226077215,
      "step": 12
    },
    {
      "completion_length": 495.34375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.39315488934516907,
      "kl": 0.0006917642313055694,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 0.9724428430199623,
      "reward_std": 0.9589688181877136,
      "rewards/concensus_correctness_reward_func": 0.02474999986588955,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5415678396821022,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.14049999602138996,
      "step": 14
    },
    {
      "completion_length": 452.57142857142856,
      "epoch": 5.363636363636363,
      "grad_norm": 0.5290654301643372,
      "kl": 0.0008257334037417812,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.081256091594696,
      "reward_std": 1.2742435804435186,
      "rewards/concensus_correctness_reward_func": 0.02292857212679727,
      "rewards/consensus_reward_func": 0.2857142857142857,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5685060960905892,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.20410714990326337,
      "step": 16
    },
    {
      "completion_length": 527.0,
      "epoch": 6.0,
      "grad_norm": 0.5395427942276001,
      "kl": 0.0007121102535165846,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.0074941771371024,
      "reward_std": 1.1326980761119299,
      "rewards/concensus_correctness_reward_func": 0.0565714282648904,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5554227573531014,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.1045000074165208,
      "step": 18
    },
    {
      "completion_length": 552.84375,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.35970422625541687,
      "kl": 0.0007969211110321339,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.2649705819785595,
      "reward_std": 1.0359111689031124,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5695331078022718,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2579375058412552,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.56709522672827e-07,
      "train_runtime": 680.0907,
      "train_samples_per_second": 0.471,
      "train_steps_per_second": 0.029
    }
  ],
  "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
}