benchmark_summary.json

{
  "config": {
    "model_name_or_path": "MyeongHo0621/Qwen2.5-3B-Korean",
    "tasks": ["gsm8k", "mmlu", "hellaswag", "winogrande", "arc_easy", "arc_challenge"]
  },
  "scores": {
    "gsm8k": {"score": 0.42, "metric": "acc"},
    "mmlu": {"score": 0.58, "metric": "acc"},
    "hellaswag": {"score": 0.71, "metric": "acc_norm"},
    "winogrande": {"score": 0.65, "metric": "acc"},
    "arc_easy": {"score": 0.78, "metric": "acc"},
    "arc_challenge": {"score": 0.48, "metric": "acc_norm"}
  }
}