{
  "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": 602.90625,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.26202690601348877,
      "kl": 0.0006193344670464285,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.6007783152163029,
      "reward_std": 1.054974022321403,
      "rewards/concensus_correctness_reward_func": -0.0062500000931322575,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.5449657998979092,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.06293748691678047,
      "step": 2
    },
    {
      "completion_length": 570.0714285714286,
      "epoch": 1.3636363636363638,
      "grad_norm": 0.3803218603134155,
      "kl": 0.0006781103937620563,
      "learning_rate": 4.864543104251586e-07,
      "loss": 0.0,
      "reward": 0.9640254293169294,
      "reward_std": 1.3422321038586753,
      "rewards/concensus_correctness_reward_func": 0.06657142724309649,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6193468336548124,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.07903571959052767,
      "step": 4
    },
    {
      "completion_length": 638.4642857142857,
      "epoch": 2.0,
      "grad_norm": 0.34380704164505005,
      "kl": 0.0006454742022989583,
      "learning_rate": 4.472851273490984e-07,
      "loss": 0.0,
      "reward": 0.9659793547221592,
      "reward_std": 1.8055980546133858,
      "rewards/concensus_correctness_reward_func": 0.033285713621548245,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.21428571428571427,
      "rewards/question_recreation_reward_func": 0.49051505752972197,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.12924998572894505,
      "step": 6
    },
    {
      "completion_length": 519.0625,
      "epoch": 2.7272727272727275,
      "grad_norm": 0.3809269666671753,
      "kl": 0.0006924861227162182,
      "learning_rate": 3.867370395306068e-07,
      "loss": 0.0,
      "reward": 1.2059303894639015,
      "reward_std": 0.993331428617239,
      "rewards/concensus_correctness_reward_func": 0.029124999418854713,
      "rewards/consensus_reward_func": 0.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.49008665699511766,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.3742187339812517,
      "step": 8
    },
    {
      "completion_length": 445.9642857142857,
      "epoch": 3.3636363636363638,
      "grad_norm": 3.0325539112091064,
      "kl": 0.0008280072610692254,
      "learning_rate": 3.1137137178519977e-07,
      "loss": 0.0,
      "reward": 0.9488396261419568,
      "reward_std": 1.2023867283548628,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5393039073262896,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.019035710287945613,
      "step": 10
    },
    {
      "completion_length": 504.82142857142856,
      "epoch": 4.0,
      "grad_norm": 0.2832128703594208,
      "kl": 0.0007283560615698141,
      "learning_rate": 2.2935516363191693e-07,
      "loss": 0.0,
      "reward": 1.199350425175258,
      "reward_std": 1.165402889251709,
      "rewards/concensus_correctness_reward_func": 0.02485714214188712,
      "rewards/consensus_reward_func": 0.35714285714285715,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5799218820674079,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": 0.148142864129373,
      "step": 12
    },
    {
      "completion_length": 533.625,
      "epoch": 4.7272727272727275,
      "grad_norm": 0.33684295415878296,
      "kl": 0.0007086097175488248,
      "learning_rate": 1.4957614383675767e-07,
      "loss": 0.0,
      "reward": 1.1680068522691727,
      "reward_std": 1.0993028162047267,
      "rewards/concensus_correctness_reward_func": -0.0062500000931322575,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.4582256153225899,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.32540624029934406,
      "step": 14
    },
    {
      "completion_length": 672.4285714285714,
      "epoch": 5.363636363636363,
      "grad_norm": 0.33270055055618286,
      "kl": 0.0005702339320643139,
      "learning_rate": 8.067960709356478e-08,
      "loss": 0.0,
      "reward": 0.7594810937132154,
      "reward_std": 1.2062485728945052,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.14285714285714285,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.07142857142857142,
      "rewards/question_recreation_reward_func": 0.5573739877768925,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.017857142857142856,
      "rewards/xmlcount_reward_func": -0.030035704906497682,
      "step": 16
    },
    {
      "completion_length": 684.3214285714286,
      "epoch": 6.0,
      "grad_norm": 0.3152960240840912,
      "kl": 0.0006245412680852626,
      "learning_rate": 3.013156219837776e-08,
      "loss": 0.0,
      "reward": 1.0633109552519662,
      "reward_std": 1.2574050894805364,
      "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": 0.5418823701994759,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.021428580795015608,
      "step": 18
    },
    {
      "completion_length": 564.5625,
      "epoch": 6.7272727272727275,
      "grad_norm": 0.25563544034957886,
      "kl": 0.0006875254330225289,
      "learning_rate": 3.4096741493194193e-09,
      "loss": 0.0,
      "reward": 1.01290044747293,
      "reward_std": 1.1850747503340244,
      "rewards/concensus_correctness_reward_func": 0.029124999418854713,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5581192104145885,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.035031260922551155,
      "step": 20
    },
    {
      "epoch": 6.7272727272727275,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 6.195858134105947e-07,
      "train_runtime": 1936.9016,
      "train_samples_per_second": 0.165,
      "train_steps_per_second": 0.01
    }
  ],
  "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
}