{
  "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": 421.84375,
      "epoch": 0.1,
      "grad_norm": 7.744514465332031,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": -0.0,
      "reward": 0.3874333486892283,
      "reward_std": 0.8486921527073719,
      "rewards/concensus_correctness_reward_func": 0.03393750078976154,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.3380895941518247,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04709374811500311,
      "step": 2
    },
    {
      "completion_length": 391.84375,
      "epoch": 0.2,
      "grad_norm": 5.300667762756348,
      "kl": 0.0019505722484609578,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 1.3110849247314036,
      "reward_std": 1.6469321683980525,
      "rewards/concensus_correctness_reward_func": 0.625,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.3452412204351276,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.21584375109523535,
      "step": 4
    },
    {
      "completion_length": 394.46875,
      "epoch": 0.3,
      "grad_norm": 46.67064666748047,
      "kl": 0.0019083435508946422,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 0.3914839383214712,
      "reward_std": 1.3497825153172016,
      "rewards/concensus_correctness_reward_func": 0.05831250175833702,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.31582766558858566,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.10765624674968421,
      "step": 6
    },
    {
      "completion_length": 411.25,
      "epoch": 0.4,
      "grad_norm": 16.974180221557617,
      "kl": 0.00413768243015511,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 0.5314379204064608,
      "reward_std": 0.5463541564531624,
      "rewards/concensus_correctness_reward_func": 0.0018749999580904841,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.2779379215789959,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0641250021290034,
      "step": 8
    },
    {
      "completion_length": 385.9375,
      "epoch": 0.5,
      "grad_norm": 11.258064270019531,
      "kl": 0.002582737106422428,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 2.051718756556511,
      "reward_std": 0.7069938564673066,
      "rewards/concensus_correctness_reward_func": 1.3228750005364418,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.4470312101766467,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0318124967161566,
      "step": 10
    },
    {
      "completion_length": 446.59375,
      "epoch": 0.6,
      "grad_norm": 4.753056526184082,
      "kl": 0.004790044869878329,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 0.8615806391462684,
      "reward_std": 0.8717811293900013,
      "rewards/concensus_correctness_reward_func": 0.08181250095367432,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.474549381993711,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0072812524158507586,
      "step": 12
    },
    {
      "completion_length": 401.125,
      "epoch": 0.7,
      "grad_norm": 6.981433868408203,
      "kl": 0.0025986589171225205,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 2.256255905609578,
      "reward_std": 2.391559364972636,
      "rewards/concensus_correctness_reward_func": 1.361625000834465,
      "rewards/consensus_reward_func": 0.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.35309968960064,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.22903124894946814,
      "step": 14
    },
    {
      "completion_length": 395.125,
      "epoch": 0.8,
      "grad_norm": 7.406398773193359,
      "kl": 0.008011827812879346,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 0.8543199766427279,
      "reward_std": 1.0620909905992448,
      "rewards/concensus_correctness_reward_func": 0.13006250001490116,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.5446637291461229,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.00790624599903822,
      "step": 16
    },
    {
      "completion_length": 370.03125,
      "epoch": 0.9,
      "grad_norm": 56.691341400146484,
      "kl": 0.011987929798124242,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 1.4162302482873201,
      "reward_std": 1.8340731484349817,
      "rewards/concensus_correctness_reward_func": 0.6328125,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.4869490059791133,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.23396874405443668,
      "step": 18
    },
    {
      "completion_length": 429.40625,
      "epoch": 1.0,
      "grad_norm": 5.524323463439941,
      "kl": 0.00813784722413402,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 1.216457948088646,
      "reward_std": 0.9376593017950654,
      "rewards/concensus_correctness_reward_func": 0.2383749932050705,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.44552044360898435,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2825624970719218,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 4.647485911846161e-06,
      "train_runtime": 435.1003,
      "train_samples_per_second": 0.735,
      "train_steps_per_second": 0.046
    }
  ],
  "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
}