Update README.md

README.md

@@ -182,6 +182,30 @@ You can finetune this model on your own dataset.
 
 *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
 -->
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) on [ir-eval](https://huggingface.co/datasets/tintnguyen/ir-eval/tree/main)
+```
+{'aaa_cosine_accuracy@1': 0.6465,
+ 'aaa_cosine_accuracy@3': 0.8083,
+ 'aaa_cosine_accuracy@5': 0.8598,
+ 'aaa_cosine_accuracy@10': 0.9207,
+ 'aaa_cosine_precision@1': 0.6465,
+ 'aaa_cosine_precision@3': 0.4838,
+ 'aaa_cosine_precision@5': 0.4153200000000001,
+ 'aaa_cosine_precision@10': 0.33329000000000003,
+ 'aaa_cosine_recall@1': 0.1383275111412705,
+ 'aaa_cosine_recall@3': 0.24971930213626684,
+ 'aaa_cosine_recall@5': 0.315993377810083,
+ 'aaa_cosine_recall@10': 0.42927605009627184,
+ 'aaa_cosine_ndcg@10': 0.5298122781447128,
+ 'aaa_cosine_mrr@10': 0.7379566269841226,
+ 'aaa_cosine_map@100': 0.4812504287090463}
+```
 
 ## Training Details