Updated metrics and number of samples for training and test set

README.md

@@ -23,19 +23,19 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value:
+      value: 0.92
       name: Cosine Accuracy
     - type: cosine_f1
-      value:
+      value: 0.93
       name: Cosine F1
     - type: cosine_precision
-      value:
+      value: 0.92
       name: Cosine Precision
     - type: cosine_recall
-      value:
+      value: 0.93
       name: Cosine Recall
     - type: cosine_ap
-      value:
+      value: 0.97
       name: Cosine Ap
 ---
 
@@ -106,11 +106,11 @@ print(similarities.shape)
 
 | Metric                    | Value     |
 |:--------------------------|:----------|
-| cosine_accuracy           |     |
-| cosine_f1                 |     |
-| cosine_precision          |    |
-| cosine_recall             |     |
-| **cosine_ap**             |  |
+| cosine_accuracy           |  0.92   |
+| cosine_f1                 |  0.93   |
+| cosine_precision          |  0.92   |
+| cosine_recall             |  0.93   |
+| **cosine_ap**             |  0.97   |
 
 
 ### Training Dataset
@@ -118,7 +118,7 @@ print(similarities.shape)
 #### Medical
 
 * Dataset: [Medical dataset]( https://www.kaggle.com/datasets/thedevastator/medical-question-pair-classification/data)
-* Size:  
+* Size: 2438 samples
 * Columns: <code>question_1</code>, <code>question_2</code>, and <code>label</code>
 
 ### Evaluation Dataset
@@ -126,7 +126,7 @@ print(similarities.shape)
 #### Medical
 
 * Dataset: [Medical dataset]( https://www.kaggle.com/datasets/thedevastator/medical-question-pair-classification/data)
-* Size:
+* Size: 610 samples
 * Columns: <code>question_1</code>, <code>question_2</code>, and <code>label</code>
 
 ## Citation