Add new SentenceTransformer model.

README.md

@@ -372,19 +372,19 @@ model-index:
       type: bge-base-en-train
     metrics:
     - type: cosine_accuracy
-      value: 0.8413461538461539
+      value: 0.8461538461538461
       name: Cosine Accuracy
     - type: dot_accuracy
-      value: 0.15865384615384615
+      value: 0.15384615384615385
       name: Dot Accuracy
     - type: manhattan_accuracy
-      value: 0.8317307692307693
+      value: 0.8557692307692307
       name: Manhattan Accuracy
     - type: euclidean_accuracy
-      value: 0.8413461538461539
+      value: 0.8461538461538461
       name: Euclidean Accuracy
     - type: max_accuracy
-      value: 0.8413461538461539
+      value: 0.8557692307692307
       name: Max Accuracy
   - task:
       type: triplet
@@ -394,19 +394,19 @@ model-index:
       type: bge-base-en-eval
     metrics:
     - type: cosine_accuracy
-      value: 0.9696969696969697
+      value: 0.9545454545454546
       name: Cosine Accuracy
     - type: dot_accuracy
-      value: 0.030303030303030304
+      value: 0.045454545454545456
       name: Dot Accuracy
     - type: manhattan_accuracy
-      value: 0.9848484848484849
+      value: 0.9545454545454546
       name: Manhattan Accuracy
     - type: euclidean_accuracy
-      value: 0.9696969696969697
+      value: 0.9545454545454546
       name: Euclidean Accuracy
     - type: max_accuracy
-      value: 0.9848484848484849
+      value: 0.9545454545454546
       name: Max Accuracy
 ---
 
@@ -508,11 +508,11 @@ You can finetune this model on your own dataset.
 
 | Metric             | Value      |
 |:-------------------|:-----------|
-| cosine_accuracy    | 0.8413     |
-| dot_accuracy       | 0.1587     |
-| manhattan_accuracy | 0.8317     |
-| euclidean_accuracy | 0.8413     |
-| **max_accuracy**   | **0.8413** |
+| cosine_accuracy    | 0.8462     |
+| dot_accuracy       | 0.1538     |
+| manhattan_accuracy | 0.8558     |
+| euclidean_accuracy | 0.8462     |
+| **max_accuracy**   | **0.8558** |
 
 #### Triplet
 * Dataset: `bge-base-en-eval`
@@ -520,11 +520,11 @@ You can finetune this model on your own dataset.
 
 | Metric             | Value      |
 |:-------------------|:-----------|
-| cosine_accuracy    | 0.9697     |
-| dot_accuracy       | 0.0303     |
-| manhattan_accuracy | 0.9848     |
-| euclidean_accuracy | 0.9697     |
-| **max_accuracy**   | **0.9848** |
+| cosine_accuracy    | 0.9545     |
+| dot_accuracy       | 0.0455     |
+| manhattan_accuracy | 0.9545     |
+| euclidean_accuracy | 0.9545     |
+| **max_accuracy**   | **0.9545** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -713,8 +713,8 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | bge-base-en-eval_max_accuracy | bge-base-en-train_max_accuracy |
 |:-----:|:----:|:-----------------------------:|:------------------------------:|
-| 0     | 0    | -                             | 0.8413                         |
-| 5.0   | 65   | 0.9848                        | -                              |
+| 0     | 0    | -                             | 0.8558                         |
+| 5.0   | 65   | 0.9545                        | -                              |
 
 
 ### Framework Versions