result/light_eval/avg_kpb3xza6.json

{
  "model_name": "newmindai/Qwen2.5-72b-Instruct",
  "overall_average": 0.3432,
  "mmlu_average": 0.2421,
  "truthfulqa": 0.4463,
  "winogrande": 0.5039,
  "hellaswag": 0.2772,
  "hellaswag_norm": 0.2783,
  "gsm8k": 0.35,
  "arc_challenge": 0.24,
  "arc_challenge_norm": 0.2423,
  "total_samples": 62000,
  "run_id": "kpb3xza6"
}