Update README.md

README.md

@@ -118,6 +118,8 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
+Customize original dataset UIT-R2GQA using function [`mine_hard_negatives`](https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negatives)
+
 * Size: 7,806 training samples
 * Columns: <code>question</code>, <code>context</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
@@ -143,8 +145,6 @@ You can finetune this model on your own dataset.
 ### Evaluation Dataset
 
 - model_id: KhoaUIT/KhoaUIT-CrossEncoder-UIT-R2GQA
-- dataset:
-    name: Custom UIT-R2GQA using function [`mine_hard_negatives`](https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negatives)
 - evaluator: [`CrossEncoderRerankingEvaluator`](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#crossencoderrerankingevaluator)
 - valid set:
   | map    | mrr@10 | ndcg@10 |
@@ -158,6 +158,8 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
+Customize original dataset UIT-R2GQA using function [`mine_hard_negatives`](https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negatives)
+
 * Size: 974 evaluation samples
 * Columns: <code>question</code>, <code>context</code>, and <code>negative</code>
 * Approximate statistics based on the first 974 samples: