Update README.md

README.md

@@ -115,13 +115,36 @@ You can finetune this model on your own dataset.
 #### Cross Encoder Reranking
 
 * Dataset: `gooaq-dev`
-* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator)
+* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
+  ```json
+  {
+      "at_k": 10,
+      "always_rerank_positives": false
+  }
+  ```
+
+| Metric      | Value                |
+|:------------|:---------------------|
+| map         | 0.7451 (+0.2140)     |
+| mrr@10      | 0.7443 (+0.2203)     |
+| **ndcg@10** | **0.7849 (+0.1937)** |
+
+#### Cross Encoder Reranking
+
+* Dataset: `gooaq-dev`
+* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
+  ```json
+  {
+      "at_k": 10,
+      "always_rerank_positives": true
+  }
+  ```
 
 | Metric      | Value                |
 |:------------|:---------------------|
 | map         | 0.8039 (+0.2728)     |
-| mrr@10      | 0.8028 (+0.2789)     |
-| **ndcg@10** | **0.8475 (+0.2562)** |
+| mrr@10      | 0.8028 (+0.2788)     |
+| **ndcg@10** | **0.8475 (+0.2563)** |
 
 <!--
 ## Bias, Risks and Limitations