Update README.md

README.md

@@ -14,14 +14,11 @@ The banT5 model was pre-trained on a large-scale Bangla text dataset, amounting
 | **Total documents**   | 7,670,661 (7.67 million)       |
 ## Results
 The banT5 model demonstrated strong performance on downstream tasks, as summarized below:
-| **Task**                 | **Metric**   | **Value**  |
-|--------------------------|--------------|------------|
-| **Named Entity Recognition (NER)** | Precision  | 0.8882     |
-|                          | Recall      | 0.8563     |
-|                          | Macro F1    | 0.8686     |
-| **Part-of-Speech (POS) Tagging**    | Precision  | 0.8813     |
-|                          | Recall      | 0.8813     |
-|                          | Macro F1    | 0.8791     |
+| Task                           | Precision | Recall  | F1     |
+|--------------------------------|-----------|---------|--------|
+| Named Entity Recognition (NER) | 0.8882    | 0.8563  | 0.8686 |
+| Part-of-Speech (POS) Tagging   | 0.8813    | 0.8813  | 0.8791 |
+
 ## Using this model in `transformers`
 
 ```bash