{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5111821086261981,
  "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": 342.625,
      "epoch": 0.051118210862619806,
      "grad_norm": 15.148255348205566,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": -0.0,
      "reward": 0.7240377963753417,
      "reward_std": 0.6348305878636893,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.20631906169001013,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.06459375051781535,
      "step": 2
    },
    {
      "completion_length": 283.09375,
      "epoch": 0.10223642172523961,
      "grad_norm": 15.798726081848145,
      "kl": 0.0015486050524486927,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 0.3603720617829822,
      "reward_std": 0.37563509584288113,
      "rewards/concensus_correctness_reward_func": 0.015687499195337296,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.13715331605635583,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.06690624775364995,
      "step": 4
    },
    {
      "completion_length": 327.03125,
      "epoch": 0.15335463258785942,
      "grad_norm": 7.624619007110596,
      "kl": 0.0010978869522659807,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.18218056572368369,
      "reward_std": 0.3838965173268889,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.18049306463217363,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0016874969005584717,
      "step": 6
    },
    {
      "completion_length": 266.28125,
      "epoch": 0.20447284345047922,
      "grad_norm": 15.941994667053223,
      "kl": 0.0029154180010664277,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 1.2010675654746592,
      "reward_std": 0.7865874714043457,
      "rewards/concensus_correctness_reward_func": 1.25,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.2003800495294854,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.3118125111795962,
      "step": 8
    },
    {
      "completion_length": 276.34375,
      "epoch": 0.25559105431309903,
      "grad_norm": 61.404579162597656,
      "kl": 0.006715945266478229,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 0.9648341918364167,
      "reward_std": 1.2789382922055665,
      "rewards/concensus_correctness_reward_func": 0.6520000007003546,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.11999044855474494,
      "rewards/soft_format_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.010281249415129423,
      "step": 10
    },
    {
      "completion_length": 189.25,
      "epoch": 0.30670926517571884,
      "grad_norm": 20.328174591064453,
      "kl": 0.002795509539282648,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.5898678143857978,
      "reward_std": 0.5214371645852225,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.20630531013011932,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07106250058859587,
      "step": 12
    },
    {
      "completion_length": 277.5625,
      "epoch": 0.35782747603833864,
      "grad_norm": 55.7784309387207,
      "kl": 0.004133160149649484,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 0.36360683606471866,
      "reward_std": 0.45650438783923164,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.11298183986218646,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0006250003352761269,
      "step": 14
    },
    {
      "completion_length": 203.6875,
      "epoch": 0.40894568690095845,
      "grad_norm": 99.87662506103516,
      "kl": 0.0015285918743757065,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.29848256206605583,
      "reward_std": 0.30471055436646566,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.1232013130793348,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.11278125131502748,
      "step": 16
    },
    {
      "completion_length": 290.1875,
      "epoch": 0.46006389776357826,
      "grad_norm": 39.584346771240234,
      "kl": 0.002846648452759837,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 0.5509365236212034,
      "reward_std": 0.34556947788223624,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.1635302850336302,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.07490624720230699,
      "step": 18
    },
    {
      "completion_length": 334.3125,
      "epoch": 0.5111821086261981,
      "grad_norm": 10.867012977600098,
      "kl": 0.01757594760056236,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.2466562440386042,
      "reward_std": 0.25576979311881587,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.09499999973922968,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.011031251982785761,
      "step": 20
    },
    {
      "epoch": 0.5111821086261981,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 4.0803197634886604e-06,
      "train_runtime": 451.4068,
      "train_samples_per_second": 0.709,
      "train_steps_per_second": 0.044
    }
  ],
  "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
}