{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4444444444444446,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 306.6875,
      "epoch": 0.8888888888888888,
      "grad_norm": 0.39643576741218567,
      "kl": 0.017112158122472465,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 5.813093453645706,
      "reward_std": 0.14963281876407564,
      "rewards/concensus_correctness_reward_func": 1.7742499868036248,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.9020308256149292,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.1368125006556511,
      "step": 2
    },
    {
      "completion_length": 305.1,
      "epoch": 1.4444444444444444,
      "grad_norm": 0.4071302115917206,
      "kl": 0.024027385748922825,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 6.344730997085572,
      "reward_std": 0.05741699002683163,
      "rewards/concensus_correctness_reward_func": 2.0456000403501093,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.2,
      "rewards/question_recreation_reward_func": 0.9993311047554017,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09979999661445618,
      "step": 4
    },
    {
      "completion_length": 301.2,
      "epoch": 2.0,
      "grad_norm": 0.14513656497001648,
      "kl": 0.018292231671512126,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 6.5120086669921875,
      "reward_std": 0.07509479415602982,
      "rewards/concensus_correctness_reward_func": 2.1467999637126924,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.2,
      "rewards/question_recreation_reward_func": 0.998508358001709,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.16669999957084655,
      "step": 6
    },
    {
      "completion_length": 315.5625,
      "epoch": 2.888888888888889,
      "grad_norm": 0.36357581615448,
      "kl": 0.018164650886319578,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 5.899516224861145,
      "reward_std": 0.0996137821348384,
      "rewards/concensus_correctness_reward_func": 1.8205000023008324,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.9989537969231606,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08006250020116568,
      "step": 8
    },
    {
      "completion_length": 302.2,
      "epoch": 3.4444444444444446,
      "grad_norm": 0.4360595941543579,
      "kl": 0.019211999699473382,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 7.314918279647827,
      "reward_std": 0.11413912773132324,
      "rewards/concensus_correctness_reward_func": 2.593599981069565,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.6,
      "rewards/question_recreation_reward_func": 0.9948183536529541,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.12649999856948851,
      "step": 10
    },
    {
      "epoch": 3.4444444444444446,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 1.4550274863722734e-05,
      "train_runtime": 4069.2289,
      "train_samples_per_second": 0.02,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}