eval-results/demo-leaderboard/qwen2-72b_gte-qwen2-1.5b/results_2023-12-08 15:46:20.425378.json

{
  "results": {
    "retrieval": {
      "mrr": 0.36173120728929387,
      "map": 0.3512338648443432
    },
    "generation": {
      "em": 0.002277904328018223,
      "f1": 0.3804001391052641,
      "rouge1": 0.34576336184459094,
      "rouge2": 0.1928778762677512,
      "rougeL": 0.2383694455084706,
      "accuracy": 0.4145785876993166,
      "completeness": 0.598297213622291,
      "hallucination": 0.0011627906976744186,
      "utilization": 1.13922942206655,
      "numerical_accuracy": 0.3218694885361552
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_gte-qwen2-1.5b",
    "generation_model": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
    "generation_model_args": {
      "name": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
      "num_params": 1.5,
      "open_source": true
    },
    "retrieval_model": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
    "retrieval_model_args": {
      "name": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
      "num_params": 1.5,
      "open_source": true
    }
  }
}