{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4705882352941178,
  "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": 255.71875,
      "epoch": 0.9411764705882353,
      "grad_norm": 3.487948179244995,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 5.0162065625190735,
      "reward_std": 1.0330485693411902,
      "rewards/concensus_correctness_reward_func": 1.684250008314848,
      "rewards/consensus_reward_func": 1.6875,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.7768628180492669,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7425937540829182,
      "step": 2
    },
    {
      "completion_length": 213.16666666666666,
      "epoch": 1.4705882352941178,
      "grad_norm": 7.842313766479492,
      "kl": 0.002754828087442244,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 4.477089087168376,
      "reward_std": 1.4975592299467988,
      "rewards/concensus_correctness_reward_func": 1.7086666756206088,
      "rewards/consensus_reward_func": 1.7777777777777777,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.6922002554767661,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.2984444366561042,
      "step": 4
    },
    {
      "completion_length": 168.61111111111111,
      "epoch": 2.0,
      "grad_norm": 1.6380842924118042,
      "kl": 0.0041018654462984866,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 5.742938200632731,
      "reward_std": 0.21626100627084574,
      "rewards/concensus_correctness_reward_func": 2.0337777932484946,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.2222222222222222,
      "rewards/question_recreation_reward_func": 0.7014382928609848,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7854999932977889,
      "step": 6
    },
    {
      "completion_length": 150.03125,
      "epoch": 2.9411764705882355,
      "grad_norm": 3.3578732013702393,
      "kl": 0.008432783608441241,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 5.191920809447765,
      "reward_std": 0.6329880520643201,
      "rewards/concensus_correctness_reward_func": 1.9247500114142895,
      "rewards/consensus_reward_func": 1.9375,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.125,
      "rewards/question_recreation_reward_func": 0.6802958373446018,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.5243750028312206,
      "step": 8
    },
    {
      "completion_length": 137.94444444444446,
      "epoch": 3.4705882352941178,
      "grad_norm": 3.12013840675354,
      "kl": 0.010559901181194518,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 5.422543207804362,
      "reward_std": 0.5203664597744743,
      "rewards/concensus_correctness_reward_func": 2.0377777881092496,
      "rewards/consensus_reward_func": 1.8888888888888888,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.2222222222222222,
      "rewards/question_recreation_reward_func": 0.4938211246497101,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.7798333267370859,
      "step": 10
    },
    {
      "epoch": 3.4705882352941178,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 3.361709309501748e-06,
      "train_runtime": 12522.5432,
      "train_samples_per_second": 0.013,
      "train_steps_per_second": 0.001
    }
  ],
  "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
}