{
  "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": 451.3125,
      "epoch": 0.1,
      "grad_norm": 4.55145788192749,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 1.14838100457564,
      "reward_std": 1.4648844352923334,
      "rewards/concensus_correctness_reward_func": 0.3653124999254942,
      "rewards/consensus_reward_func": 0.4375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.36994350305758417,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.0243749946821481,
      "step": 2
    },
    {
      "completion_length": 319.09375,
      "epoch": 0.2,
      "grad_norm": 5.600566387176514,
      "kl": 0.0016100590109999757,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 2.7462965343147516,
      "reward_std": 1.8164186510257423,
      "rewards/concensus_correctness_reward_func": 0.6357499938458204,
      "rewards/consensus_reward_func": 0.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.5983590607065707,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7621875014156103,
      "step": 4
    },
    {
      "completion_length": 439.125,
      "epoch": 0.3,
      "grad_norm": 4.503983020782471,
      "kl": 0.002360808866797015,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 2.1509911492466927,
      "reward_std": 1.3198209893889725,
      "rewards/concensus_correctness_reward_func": 0.4263750035315752,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.44299112958833575,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6566249988973141,
      "step": 6
    },
    {
      "completion_length": 348.0625,
      "epoch": 0.4,
      "grad_norm": 4.3034987449646,
      "kl": 0.005087370787805412,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 3.177116136997938,
      "reward_std": 2.1376988533884287,
      "rewards/concensus_correctness_reward_func": 1.100312501192093,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.6318661202676594,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.6324375094845891,
      "step": 8
    },
    {
      "completion_length": 341.90625,
      "epoch": 0.5,
      "grad_norm": 5.0985107421875,
      "kl": 0.006734212307492271,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 3.466143324971199,
      "reward_std": 1.717540071113035,
      "rewards/concensus_correctness_reward_func": 1.255187513306737,
      "rewards/consensus_reward_func": 0.5625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.25,
      "rewards/question_recreation_reward_func": 0.6659870097064413,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7324687419459224,
      "step": 10
    },
    {
      "completion_length": 345.125,
      "epoch": 0.6,
      "grad_norm": 5.1420440673828125,
      "kl": 0.009895556868286803,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 1.718095177784562,
      "reward_std": 1.091934118885547,
      "rewards/concensus_correctness_reward_func": 0.16075000166893005,
      "rewards/consensus_reward_func": 0.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6077201636508107,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.699625002220273,
      "step": 12
    },
    {
      "completion_length": 420.21875,
      "epoch": 0.7,
      "grad_norm": 4.497544765472412,
      "kl": 0.008676771001773886,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 2.482669457793236,
      "reward_std": 1.6823535598814487,
      "rewards/concensus_correctness_reward_func": 0.48518749326467514,
      "rewards/consensus_reward_func": 0.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6140757068060338,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.570906262844801,
      "step": 14
    },
    {
      "completion_length": 333.25,
      "epoch": 0.8,
      "grad_norm": 6.063222885131836,
      "kl": 0.025907800074492116,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 2.952958069741726,
      "reward_std": 1.9994886703789234,
      "rewards/concensus_correctness_reward_func": 0.7735625021159649,
      "rewards/consensus_reward_func": 0.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0625,
      "rewards/question_recreation_reward_func": 0.6262080864980817,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5531874988228083,
      "step": 16
    },
    {
      "completion_length": 318.65625,
      "epoch": 0.9,
      "grad_norm": 4.5946550369262695,
      "kl": 0.010048380005173385,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 2.5494979918003082,
      "reward_std": 1.0372722303145565,
      "rewards/concensus_correctness_reward_func": 0.3228750005364418,
      "rewards/consensus_reward_func": 0.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.7127792425453663,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8263437589630485,
      "step": 18
    },
    {
      "completion_length": 296.5,
      "epoch": 1.0,
      "grad_norm": 4.735755443572998,
      "kl": 0.010132168332347646,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 2.574199102818966,
      "reward_std": 1.4411136759445071,
      "rewards/concensus_correctness_reward_func": 0.45224999636411667,
      "rewards/consensus_reward_func": 0.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6332928789779544,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7386562433093786,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 8.027511148611665e-06,
      "train_runtime": 250.5075,
      "train_samples_per_second": 1.277,
      "train_steps_per_second": 0.08
    }
  ],
  "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
}