model update

README.md

@@ -102,7 +102,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5901639344262295
+      value: 0.5573770491803278
   - task:
       name: Analogy Questions (NELL-ONE Analogy)
       type: multiple-choice-qa
@@ -198,7 +198,7 @@ This model achieves the following results on the relation understanding tasks:
     - Accuracy on U4: 0.5717592592592593
     - Accuracy on Google: 0.902
     - Accuracy on ConceptNet Analogy: 0.3850671140939597
-    - Accuracy on T-Rex Analogy: 0.5901639344262295
+    - Accuracy on T-Rex Analogy: 0.5573770491803278
     - Accuracy on NELL-ONE Analogy: 0.685
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-b-semeval2012/raw/main/classification.json)):
     - Micro F1 score on BLESS: 0.9053789362663854