eval-results/demo-leaderboard/gte-qwen2-1.5b_llama3-70b-instruct/results_2023-12-08 15:46:20.425378.json

{
  "results": {
    "retrieval": {
      "mrr": 0.36173120728929387,
      "map": 0.3512338648443432
    },
    "generation": {
      "em": 0.04555808656036447,
      "f1": 0.4907954247383474,
      "rouge1": 0.4080491070348775,
      "rouge2": 0.23130474174425783,
      "rougeL": 0.3217574785678875,
      "accuracy": 0.4216970387243736,
      "completeness": 0.5688146380270486,
      "hallucination": 0.11832946635730858,
      "utilization": 0.4491869918699187,
      "numerical_accuracy": 0.288981288981289
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_llama3-70b-instruct",
    "generation_model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
    "generation_model_args": {
      "name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
      "num_params": 70,
      "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
    }
  }
}