{
  "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": 293.9375,
      "epoch": 0.1,
      "grad_norm": 6.770710468292236,
      "kl": 0.0,
      "learning_rate": 4.965903258506806e-07,
      "loss": 0.0,
      "reward": 3.5183496065437794,
      "reward_std": 1.0502195749431849,
      "rewards/concensus_correctness_reward_func": 1.138875000178814,
      "rewards/consensus_reward_func": 0.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.48494323156774044,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7695312444120646,
      "step": 2
    },
    {
      "completion_length": 210.59375,
      "epoch": 0.2,
      "grad_norm": 6.464553356170654,
      "kl": 0.0018149094612454064,
      "learning_rate": 4.698684378016222e-07,
      "loss": 0.0,
      "reward": 4.079099643975496,
      "reward_std": 1.969818017911166,
      "rewards/concensus_correctness_reward_func": 1.1915000043809414,
      "rewards/consensus_reward_func": 1.25,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.5635058376938105,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9490937646478415,
      "step": 4
    },
    {
      "completion_length": 215.53125,
      "epoch": 0.3,
      "grad_norm": 5.030552387237549,
      "kl": 0.003946434873796534,
      "learning_rate": 4.193203929064353e-07,
      "loss": 0.0,
      "reward": 4.147871345281601,
      "reward_std": 1.0617804976936895,
      "rewards/concensus_correctness_reward_func": 1.0716250063851476,
      "rewards/consensus_reward_func": 1.3125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6966837849467993,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.9420624990016222,
      "step": 6
    },
    {
      "completion_length": 226.46875,
      "epoch": 0.4,
      "grad_norm": 7.530874729156494,
      "kl": 0.006505107507109642,
      "learning_rate": 3.5042385616324236e-07,
      "loss": 0.0,
      "reward": 4.872692108154297,
      "reward_std": 0.8820353185292333,
      "rewards/concensus_correctness_reward_func": 1.5794374831020832,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.6452545756474137,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.015625,
      "rewards/xmlcount_reward_func": 0.9448750074952841,
      "step": 8
    },
    {
      "completion_length": 224.125,
      "epoch": 0.5,
      "grad_norm": 6.26947546005249,
      "kl": 0.017573315155459568,
      "learning_rate": 2.706448363680831e-07,
      "loss": 0.0,
      "reward": 4.589567497372627,
      "reward_std": 0.5632297637930606,
      "rewards/concensus_correctness_reward_func": 1.3103125058114529,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6878798566758633,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.0913749746978283,
      "step": 10
    },
    {
      "completion_length": 227.375,
      "epoch": 0.6,
      "grad_norm": 10.787705421447754,
      "kl": 0.032559632032644004,
      "learning_rate": 1.886286282148002e-07,
      "loss": 0.0,
      "reward": 3.704581528902054,
      "reward_std": 1.7604766907170415,
      "rewards/concensus_correctness_reward_func": 1.080749999731779,
      "rewards/consensus_reward_func": 1.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.574769021011889,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8615624755620956,
      "step": 12
    },
    {
      "completion_length": 207.5625,
      "epoch": 0.7,
      "grad_norm": 6.204675197601318,
      "kl": 0.020694108097814023,
      "learning_rate": 1.1326296046939333e-07,
      "loss": 0.0,
      "reward": 5.430970191955566,
      "reward_std": 2.625548861164134,
      "rewards/concensus_correctness_reward_func": 2.4031250346451998,
      "rewards/consensus_reward_func": 1.125,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.1875,
      "rewards/question_recreation_reward_func": 0.6678765239194036,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.0474687423557043,
      "step": 14
    },
    {
      "completion_length": 215.90625,
      "epoch": 0.8,
      "grad_norm": 6.539551734924316,
      "kl": 0.028862927720183507,
      "learning_rate": 5.271487265090163e-08,
      "loss": 0.0,
      "reward": 4.224169656634331,
      "reward_std": 1.8053380789060611,
      "rewards/concensus_correctness_reward_func": 1.1609375067055225,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.7501071402803063,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.8131249994039536,
      "step": 16
    },
    {
      "completion_length": 317.59375,
      "epoch": 0.9,
      "grad_norm": 9.371740341186523,
      "kl": 0.03664331749314442,
      "learning_rate": 1.3545689574841341e-08,
      "loss": 0.0,
      "reward": 4.034522108733654,
      "reward_std": 2.011725899297744,
      "rewards/concensus_correctness_reward_func": 1.1518124975264072,
      "rewards/consensus_reward_func": 1.1875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.3125,
      "rewards/question_recreation_reward_func": 0.619115877430886,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.763593751937151,
      "step": 18
    },
    {
      "completion_length": 176.09375,
      "epoch": 1.0,
      "grad_norm": 10.470930099487305,
      "kl": 0.042090884468052536,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 5.190935835242271,
      "reward_std": 0.9041912718676031,
      "rewards/concensus_correctness_reward_func": 1.5460625067353249,
      "rewards/consensus_reward_func": 1.625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.7477482073009014,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 1.1471249982714653,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 20,
      "total_flos": 0.0,
      "train_loss": 1.9222072114644107e-05,
      "train_runtime": 253.6955,
      "train_samples_per_second": 1.261,
      "train_steps_per_second": 0.079
    }
  ],
  "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
}