{
  "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": 460.625,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4580991864204407,
      "kl": 0.0014632435268140398,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 1.0820730347186327,
      "reward_std": 1.0185851007699966,
      "rewards/concensus_correctness_reward_func": 0.025875000283122063,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.42435428500175476,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3193437550216913,
      "step": 2
    },
    {
      "completion_length": 447.4642857142857,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.2990836203098297,
      "kl": 0.001089990945599441,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 1.4377138274056571,
      "reward_std": 0.9948101043701172,
      "rewards/concensus_correctness_reward_func": 0.014714285731315613,
      "rewards/consensus_reward_func": 0.42857142857142855,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.7040709725448063,
      "rewards/soft_format_reward_func": 0.017857142857142856,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2010714305298669,
      "step": 4
    },
    {
      "completion_length": 474.67857142857144,
      "epoch": 2.0,
      "grad_norm": 0.2666090726852417,
      "kl": 0.000972354634931045,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9860758504697255,
      "reward_std": 0.8850901254585811,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.44025441472019466,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.18867859563657216,
      "step": 6
    },
    {
      "completion_length": 504.90625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5152686834335327,
      "kl": 0.0009930281885317527,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.0614157486706972,
      "reward_std": 1.2066142186522484,
      "rewards/concensus_correctness_reward_func": 0.03356250002980232,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5757595151662827,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04790624789893627,
      "step": 8
    },
    {
      "completion_length": 417.7857142857143,
      "epoch": 3.3636363636363638,
      "grad_norm": 0.7660165429115295,
      "kl": 0.0011763513736825968,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9584103226661682,
      "reward_std": 0.9261777102947235,
      "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": 0.5655174798199109,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.10717858427337237,
      "step": 10
    },
    {
      "completion_length": 531.4642857142857,
      "epoch": 4.0,
      "grad_norm": 0.36486443877220154,
      "kl": 0.0009575320208179099,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.310478311564241,
      "reward_std": 1.163662137729781,
      "rewards/concensus_correctness_reward_func": 0.029571428894996643,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.41362116166523527,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.3494286047560828,
      "step": 12
    },
    {
      "completion_length": 506.34375,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.37397682666778564,
      "kl": 0.0010467314714333043,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.415127757936716,
      "reward_std": 1.0043870881199837,
      "rewards/concensus_correctness_reward_func": 0.012875000014901161,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.6339715048670769,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.3776562474668026,
      "step": 14
    },
    {
      "completion_length": 476.85714285714283,
      "epoch": 5.363636363636363,
      "grad_norm": 5.369744300842285,
      "kl": 0.0014133166239064718,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 1.1496772201997894,
      "reward_std": 1.1013595866305488,
      "rewards/concensus_correctness_reward_func": 0.008928571428571428,
      "rewards/consensus_reward_func": 0.5714285714285714,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.33957007953098844,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.03571428571428571,
      "rewards/xmlcount_reward_func": 0.19403571103300368,
      "step": 16
    },
    {
      "completion_length": 509.42857142857144,
      "epoch": 6.0,
      "grad_norm": 0.42024892568588257,
      "kl": 0.0011925910782468105,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.1356084644794464,
      "reward_std": 0.9839833123343331,
      "rewards/concensus_correctness_reward_func": 0.06549999969346183,
      "rewards/consensus_reward_func": 0.21428571428571427,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5933941645281655,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2624285763927868,
      "step": 18
    },
    {
      "completion_length": 541.03125,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4161539077758789,
      "kl": 0.0010402965126559138,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.0116392225027084,
      "reward_std": 0.7309225779026747,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5514517435804009,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.21018750162329525,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.029877665814638e-06,
      "train_runtime": 1225.2116,
      "train_samples_per_second": 0.261,
      "train_steps_per_second": 0.016
    }
  ],
  "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
}