{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 270.71875,
      "epoch": 0.1,
      "grad_norm": 9.206330299377441,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 2.597460576798767,
      "reward_std": 1.4302402918110602,
      "rewards/concensus_correctness_reward_func": 0.5476875007152557,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.533554332330823,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.15625,
      "rewards/xmlcount_reward_func": 0.7349687502719462,
      "step": 2
    },
    {
      "completion_length": 195.90625,
      "epoch": 0.2,
      "grad_norm": 10.818861961364746,
      "kl": 0.009735427374835126,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 3.5640664994716644,
      "reward_std": 1.217298530973494,
      "rewards/concensus_correctness_reward_func": 0.6318749967031181,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.6191289681009948,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.0005625002086163,
      "step": 4
    },
    {
      "completion_length": 162.03125,
      "epoch": 0.3,
      "grad_norm": 9.000652313232422,
      "kl": 0.05125166794459801,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0001,
      "reward": 3.4397162571549416,
      "reward_std": 0.9051721117575653,
      "rewards/concensus_correctness_reward_func": 0.48787499871104956,
      "rewards/consensus_reward_func": 0.75,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7682475284673274,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.234375,
      "rewards/xmlcount_reward_func": 1.19921875,
      "step": 6
    },
    {
      "completion_length": 159.3125,
      "epoch": 0.4,
      "grad_norm": 12.259332656860352,
      "kl": 0.2993844930897467,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0003,
      "reward": 4.3061413541436195,
      "reward_std": 1.5522846769745229,
      "rewards/concensus_correctness_reward_func": 1.0002500005066395,
      "rewards/consensus_reward_func": 1.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5235163811594248,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.296875,
      "rewards/xmlcount_reward_func": 1.1730000004172325,
      "step": 8
    },
    {
      "completion_length": 205.375,
      "epoch": 0.5,
      "grad_norm": 243.9241943359375,
      "kl": 17.480981369968504,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0175,
      "reward": 5.416488420218229,
      "reward_std": 3.126060810755007,
      "rewards/concensus_correctness_reward_func": 2.234562523663044,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.6467385264113545,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.25,
      "rewards/xmlcount_reward_func": 1.0976874977350235,
      "step": 10
    },
    {
      "completion_length": 196.15625,
      "epoch": 0.6,
      "grad_norm": 53.35478591918945,
      "kl": 5.279129754489986,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0053,
      "reward": 3.6951485350728035,
      "reward_std": 1.9209107179194689,
      "rewards/concensus_correctness_reward_func": 0.846500001847744,
      "rewards/consensus_reward_func": 0.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6515547791495919,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.296875,
      "rewards/xmlcount_reward_func": 0.9627187475562096,
      "step": 12
    },
    {
      "completion_length": 175.40625,
      "epoch": 0.7,
      "grad_norm": 151.88095092773438,
      "kl": 17.868320498178946,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0179,
      "reward": 3.941804777830839,
      "reward_std": 1.4664802676998079,
      "rewards/concensus_correctness_reward_func": 0.928250003606081,
      "rewards/consensus_reward_func": 0.875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.6228047972545028,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.109499990940094,
      "step": 14
    },
    {
      "completion_length": 137.28125,
      "epoch": 0.8,
      "grad_norm": 10.238701820373535,
      "kl": 0.4484618069254793,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0004,
      "reward": 4.690679147839546,
      "reward_std": 1.1331686142657418,
      "rewards/concensus_correctness_reward_func": 1.2337500005960464,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.630147909745574,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.28125,
      "rewards/xmlcount_reward_func": 1.1705312579870224,
      "step": 16
    },
    {
      "completion_length": 183.0625,
      "epoch": 0.9,
      "grad_norm": 13.626744270324707,
      "kl": 0.5570770889171399,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0006,
      "reward": 4.399508744478226,
      "reward_std": 1.8520439052954316,
      "rewards/concensus_correctness_reward_func": 1.5268124863505363,
      "rewards/consensus_reward_func": 0.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.4939774713711813,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.296875,
      "rewards/xmlcount_reward_func": 0.8943437449634075,
      "step": 18
    },
    {
      "completion_length": 147.96875,
      "epoch": 1.0,
      "grad_norm": 16.93548011779785,
      "kl": 1.495584036631044,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0015,
      "reward": 4.470786616206169,
      "reward_std": 1.5465652456041425,
      "rewards/concensus_correctness_reward_func": 1.0081250108778477,
      "rewards/consensus_reward_func": 1.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.643411620054394,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.34375,
      "rewards/xmlcount_reward_func": 1.163000002503395,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 0.004348463743190223,
      "train_runtime": 4494.6973,
      "train_samples_per_second": 0.071,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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
}