Add new SentenceTransformer model.

README.md

@@ -6,7 +6,7 @@ tags:
 - generated_from_trainer
 - dataset_size:208
 - loss:BatchSemiHardTripletLoss
-base_model: BAAI/bge-base-en
+base_model: BAAI/bge-base-en-v1.5
 widget:
 - source_sentence: '
 
@@ -362,7 +362,7 @@ metrics:
 - euclidean_accuracy
 - max_accuracy
 model-index:
-- name: SentenceTransformer based on BAAI/bge-base-en
+- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
   results:
   - task:
       type: triplet
@@ -372,19 +372,19 @@ model-index:
       type: bge-base-en-v1.5-train
     metrics:
     - type: cosine_accuracy
-      value: 0.8269230769230769
+      value: 0.8461538461538461
       name: Cosine Accuracy
     - type: dot_accuracy
-      value: 0.17307692307692307
+      value: 0.15384615384615385
       name: Dot Accuracy
     - type: manhattan_accuracy
-      value: 0.8269230769230769
+      value: 0.8509615384615384
       name: Manhattan Accuracy
     - type: euclidean_accuracy
-      value: 0.8269230769230769
+      value: 0.8461538461538461
       name: Euclidean Accuracy
     - type: max_accuracy
-      value: 0.8269230769230769
+      value: 0.8509615384615384
       name: Max Accuracy
   - task:
       type: triplet
@@ -394,31 +394,46 @@ model-index:
       type: bge-base-en-v1.5-eval
     metrics:
     - type: cosine_accuracy
-      value: 0.9848484848484849
+      value: 1.0
       name: Cosine Accuracy
     - type: dot_accuracy
-      value: 0.015151515151515152
+      value: 0.0
       name: Dot Accuracy
     - type: manhattan_accuracy
-      value: 0.9696969696969697
+      value: 1.0
       name: Manhattan Accuracy
     - type: euclidean_accuracy
-      value: 0.9848484848484849
+      value: 1.0
       name: Euclidean Accuracy
     - type: max_accuracy
-      value: 0.9848484848484849
+      value: 1.0
+      name: Max Accuracy
+    - type: cosine_accuracy
+      value: 1.0
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.0
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 1.0
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 1.0
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 1.0
       name: Max Accuracy
 ---
 
-# SentenceTransformer based on BAAI/bge-base-en
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
+- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
 - **Maximum Sequence Length:** 512 tokens
 - **Output Dimensionality:** 768 tokens
 - **Similarity Function:** Cosine Similarity
@@ -506,25 +521,37 @@ You can finetune this model on your own dataset.
 * Dataset: `bge-base-en-v1.5-train`
 * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
 
-| Metric             | Value      |
-|:-------------------|:-----------|
-| cosine_accuracy    | 0.8269     |
-| dot_accuracy       | 0.1731     |
-| manhattan_accuracy | 0.8269     |
-| euclidean_accuracy | 0.8269     |
-| **max_accuracy**   | **0.8269** |
+| Metric             | Value     |
+|:-------------------|:----------|
+| cosine_accuracy    | 0.8462    |
+| dot_accuracy       | 0.1538    |
+| manhattan_accuracy | 0.851     |
+| euclidean_accuracy | 0.8462    |
+| **max_accuracy**   | **0.851** |
+
+#### Triplet
+* Dataset: `bge-base-en-v1.5-eval`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value   |
+|:-------------------|:--------|
+| cosine_accuracy    | 1.0     |
+| dot_accuracy       | 0.0     |
+| manhattan_accuracy | 1.0     |
+| euclidean_accuracy | 1.0     |
+| **max_accuracy**   | **1.0** |
 
 #### Triplet
 * Dataset: `bge-base-en-v1.5-eval`
 * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
 
-| Metric             | Value      |
-|:-------------------|:-----------|
-| cosine_accuracy    | 0.9848     |
-| dot_accuracy       | 0.0152     |
-| manhattan_accuracy | 0.9697     |
-| euclidean_accuracy | 0.9848     |
-| **max_accuracy**   | **0.9848** |
+| Metric             | Value   |
+|:-------------------|:--------|
+| cosine_accuracy    | 1.0     |
+| dot_accuracy       | 0.0     |
+| manhattan_accuracy | 1.0     |
+| euclidean_accuracy | 1.0     |
+| **max_accuracy**   | **1.0** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -713,8 +740,8 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | bge-base-en-v1.5-eval_max_accuracy | bge-base-en-v1.5-train_max_accuracy |
 |:-----:|:----:|:----------------------------------:|:-----------------------------------:|
-| 0     | 0    | -                                  | 0.8269                              |
-| 5.0   | 65   | 0.9848                             | -                                   |
+| 0     | 0    | -                                  | 0.8510                              |
+| 5.0   | 65   | 1.0                                | -                                   |
 
 
 ### Framework Versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "BAAI/bge-base-en",
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
   "architectures": [
     "BertModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c3b053b4a39609fc2ccc2808f96eac1aae385bf74c3147f5532c3e80fdf055
+oid sha256:4226550437f27f985a4aaa7684a4bfcf05baedd330b64315cbdf0882a4d02c57
 size 437951328