Updating model weights

README.md

@@ -56,6 +56,9 @@ model-index:
     - type: cosine_accuracy
       value: 0.9632217288017273
       name: Cosine Accuracy
+    - type: cosine_accuracy
+      value: 0.9583539962768555
+      name: Cosine Accuracy
 ---
 
 # SentenceTransformer
@@ -119,9 +122,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8920, 0.3277],
-#         [0.8920, 1.0000, 0.3290],
-#         [0.3277, 0.3290, 1.0000]])
+# tensor([[1.0000, 0.8800, 0.2118],
+#         [0.8800, 1.0000, 0.2279],
+#         [0.2118, 0.2279, 1.0000]])
 ```
 
 <!--
@@ -176,6 +179,14 @@ You can finetune this model on your own dataset.
 |:--------------------|:-----------|
 | **cosine_accuracy** | **0.9632** |
 
+#### Triplet
+
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| **cosine_accuracy** | **0.9584** |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -371,6 +382,13 @@ You can finetune this model on your own dataset.
 | 3.0    | 129  | 1.1581        | -               |
 | 4.0    | 172  | 1.013         | -               |
 | 5.0    | 215  | 0.9318        | -               |
+| -1     | -1   | -             | 0.9584          |
+| 0.0233 | 1    | 0.6549        | -               |
+| 1.0    | 43   | 0.5541        | -               |
+| 2.0    | 86   | 0.5269        | -               |
+| 3.0    | 129  | 0.6036        | -               |
+| 4.0    | 172  | 0.6677        | -               |
+| 5.0    | 215  | 0.7634        | -               |
 
 
 ### Framework Versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc07c00b7a4447a056133d8bcad4c913971857b920188d8c0a059fe226503a2
+oid sha256:b352bb9cccdacd9d0318f7bce4b8fc176f7c8b788c505ac48751add74176ef4f
 size 90864192