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

{
  "results": {
    "retrieval": {
      "mrr": 0.45742217160212606,
      "map": 0.4442720197418375
    },
    "generation": {
      "em": 0.05125284738041002,
      "f1": 0.5042287844817168,
      "rouge1": 0.4252992013911242,
      "rouge2": 0.25007376816549043,
      "rougeL": 0.33900256076984714,
      "accuracy": 0.4433371298405467,
      "completeness": 0.574468085106383,
      "hallucination": 0.11310904872389792,
      "utilization": 0.47642607683352733,
      "numerical_accuracy": 0.32676348547717843
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_llama3-70b-instruct",
    "generative_model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
    "generative_model_args": {
      "name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
      "num_params": 70.6,
      "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": 1.78,
      "open_source": true
    }
  }
}