eval-results/omnieval-human/gte-qwen2-1.5b_yi15-34b/results_2023-12-08 15:46:20.425378.json

{
  "results": {
    "retrieval": {
      "mrr": 0.45742217160212606,
      "map": 0.4442720197418375
    },
    "generation": {
      "em": 0.0,
      "f1": 0.15831651384807305,
      "rouge1": 0.2195147064138981,
      "rouge2": 0.09922121332360972,
      "rougeL": 0.08869793021948827,
      "accuracy": 0.3365603644646925,
      "completeness": 0.5820836621941594,
      "hallucination": 0.0648202710665881,
      "utilization": 0.4234421364985163,
      "numerical_accuracy": 0.18561001042752867
    }
  },
  "config": {
    "eval_name": "gte-qwen2-1.5b_yi15-34b",
    "generative_model": "01ai/Yi-1.5-34B-Chat-16K",
    "generative_model_args": {
      "name": "01ai/Yi-1.5-34B-Chat-16K",
      "num_params": 34.4,
      "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
    }
  }
}