Add new SentenceTransformer model

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:111470
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: sentence-transformers/all-MiniLM-L12-v2
 widget:
 - source_sentence: why are some rocks radioactive
   sentences:
@@ -106,7 +106,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
   results:
   - task:
       type: information-retrieval
@@ -116,49 +116,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.32
+      value: 0.36
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.54
+      value: 0.58
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.62
+      value: 0.68
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.74
+      value: 0.76
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.32
+      value: 0.36
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18
+      value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.124
+      value: 0.136
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07400000000000001
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.32
+      value: 0.36
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.54
+      value: 0.58
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.62
+      value: 0.68
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.74
+      value: 0.76
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5189661789845982
+      value: 0.5522122196843595
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4499126984126983
+      value: 0.48633333333333334
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4616522119994847
+      value: 0.4958040190560276
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -168,49 +168,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.34
+      value: 0.44
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.54
+      value: 0.56
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.58
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 0.66
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.34
+      value: 0.44
       name: Cosine Precision@1
     - type: cosine_precision@3
       value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.12400000000000003
+      value: 0.128
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07200000000000001
+      value: 0.07
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.31
+      value: 0.41
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.52
+      value: 0.53
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.56
+      value: 0.58
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.65
+      value: 0.64
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.495936841468424
+      value: 0.5277371826996979
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.455388888888889
+      value: 0.505079365079365
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.45517920150439706
+      value: 0.5002333969355556
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -220,61 +220,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.33
+      value: 0.4
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.54
+      value: 0.5700000000000001
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.64
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.7
+      value: 0.71
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.33
+      value: 0.4
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18666666666666665
+      value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.12400000000000001
+      value: 0.132
       name: Cosine Precision@5
     - type: cosine_precision@10
       value: 0.07300000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.315
+      value: 0.385
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.53
+      value: 0.5549999999999999
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.5900000000000001
+      value: 0.63
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.6950000000000001
+      value: 0.7
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5074515102265111
+      value: 0.5399747011920287
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.45265079365079364
+      value: 0.49570634920634915
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4584157067519409
+      value: 0.4980187079957916
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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 [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 936af83a2ecce5fe87a09109ff5cbcefe073173a -->
 - **Maximum Sequence Length:** 128 tokens
 - **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
@@ -327,9 +327,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.9705],
-#         [1.0000, 1.0000, 0.9705],
-#         [0.9705, 0.9705, 1.0000]])
+# tensor([[0.9999, 0.9999, 0.9775],
+#         [0.9999, 0.9999, 0.9775],
+#         [0.9775, 0.9775, 1.0000]])
 ```
 
 <!--
@@ -367,21 +367,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.32        | 0.34       |
-| cosine_accuracy@3   | 0.54        | 0.54       |
-| cosine_accuracy@5   | 0.62        | 0.58       |
-| cosine_accuracy@10  | 0.74        | 0.66       |
-| cosine_precision@1  | 0.32        | 0.34       |
-| cosine_precision@3  | 0.18        | 0.1933     |
-| cosine_precision@5  | 0.124       | 0.124      |
-| cosine_precision@10 | 0.074       | 0.072      |
-| cosine_recall@1     | 0.32        | 0.31       |
-| cosine_recall@3     | 0.54        | 0.52       |
-| cosine_recall@5     | 0.62        | 0.56       |
-| cosine_recall@10    | 0.74        | 0.65       |
-| **cosine_ndcg@10**  | **0.519**   | **0.4959** |
-| cosine_mrr@10       | 0.4499      | 0.4554     |
-| cosine_map@100      | 0.4617      | 0.4552     |
+| cosine_accuracy@1   | 0.36        | 0.44       |
+| cosine_accuracy@3   | 0.58        | 0.56       |
+| cosine_accuracy@5   | 0.68        | 0.6        |
+| cosine_accuracy@10  | 0.76        | 0.66       |
+| cosine_precision@1  | 0.36        | 0.44       |
+| cosine_precision@3  | 0.1933      | 0.1933     |
+| cosine_precision@5  | 0.136       | 0.128      |
+| cosine_precision@10 | 0.076       | 0.07       |
+| cosine_recall@1     | 0.36        | 0.41       |
+| cosine_recall@3     | 0.58        | 0.53       |
+| cosine_recall@5     | 0.68        | 0.58       |
+| cosine_recall@10    | 0.76        | 0.64       |
+| **cosine_ndcg@10**  | **0.5522**  | **0.5277** |
+| cosine_mrr@10       | 0.4863      | 0.5051     |
+| cosine_map@100      | 0.4958      | 0.5002     |
 
 #### Nano BEIR
 
@@ -397,23 +397,23 @@ You can finetune this model on your own dataset.
   }
   ```
 
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.33       |
-| cosine_accuracy@3   | 0.54       |
-| cosine_accuracy@5   | 0.6        |
-| cosine_accuracy@10  | 0.7        |
-| cosine_precision@1  | 0.33       |
-| cosine_precision@3  | 0.1867     |
-| cosine_precision@5  | 0.124      |
-| cosine_precision@10 | 0.073      |
-| cosine_recall@1     | 0.315      |
-| cosine_recall@3     | 0.53       |
-| cosine_recall@5     | 0.59       |
-| cosine_recall@10    | 0.695      |
-| **cosine_ndcg@10**  | **0.5075** |
-| cosine_mrr@10       | 0.4527     |
-| cosine_map@100      | 0.4584     |
+| Metric              | Value    |
+|:--------------------|:---------|
+| cosine_accuracy@1   | 0.4      |
+| cosine_accuracy@3   | 0.57     |
+| cosine_accuracy@5   | 0.64     |
+| cosine_accuracy@10  | 0.71     |
+| cosine_precision@1  | 0.4      |
+| cosine_precision@3  | 0.1933   |
+| cosine_precision@5  | 0.132    |
+| cosine_precision@10 | 0.073    |
+| cosine_recall@1     | 0.385    |
+| cosine_recall@3     | 0.555    |
+| cosine_recall@5     | 0.63     |
+| cosine_recall@10    | 0.7      |
+| **cosine_ndcg@10**  | **0.54** |
+| cosine_mrr@10       | 0.4957   |
+| cosine_map@100      | 0.498    |
 
 <!--
 ## Bias, Risks and Limitations
@@ -630,19 +630,19 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
 |:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
-| 0      | 0    | -             | 1.1445          | 0.5540                     | 0.5931                | 0.5735                       |
-| 0.2874 | 250  | 1.1834        | 0.9135          | 0.4900                     | 0.5098                | 0.4999                       |
-| 0.5747 | 500  | 1.0424        | 0.8651          | 0.4979                     | 0.4970                | 0.4974                       |
-| 0.8621 | 750  | 1.0133        | 0.8524          | 0.5118                     | 0.4987                | 0.5052                       |
-| 1.1494 | 1000 | 0.9885        | 0.8441          | 0.5232                     | 0.5085                | 0.5159                       |
-| 1.4368 | 1250 | 0.9788        | 0.8383          | 0.5204                     | 0.5039                | 0.5122                       |
-| 1.7241 | 1500 | 0.9689        | 0.8339          | 0.5184                     | 0.5220                | 0.5202                       |
-| 2.0115 | 1750 | 0.9641        | 0.8292          | 0.5192                     | 0.4993                | 0.5093                       |
-| 2.2989 | 2000 | 0.9523        | 0.8269          | 0.5173                     | 0.4896                | 0.5034                       |
-| 2.5862 | 2250 | 0.9492        | 0.8248          | 0.5181                     | 0.5132                | 0.5157                       |
-| 2.8736 | 2500 | 0.936         | 0.8241          | 0.5187                     | 0.5082                | 0.5134                       |
-| 3.1609 | 2750 | 0.9427        | 0.8228          | 0.5193                     | 0.4957                | 0.5075                       |
-| 3.4483 | 3000 | 0.9363        | 0.8225          | 0.5190                     | 0.4959                | 0.5075                       |
+| 0      | 0    | -             | 1.1142          | 0.5887                     | 0.5786                | 0.5836                       |
+| 0.2874 | 250  | 1.1156        | 0.8606          | 0.5535                     | 0.5483                | 0.5509                       |
+| 0.5747 | 500  | 0.972         | 0.8202          | 0.5383                     | 0.5521                | 0.5452                       |
+| 0.8621 | 750  | 0.9475        | 0.8071          | 0.5445                     | 0.5372                | 0.5409                       |
+| 1.1494 | 1000 | 0.924         | 0.8011          | 0.5444                     | 0.5591                | 0.5517                       |
+| 1.4368 | 1250 | 0.9108        | 0.7953          | 0.5390                     | 0.5372                | 0.5381                       |
+| 1.7241 | 1500 | 0.9024        | 0.7896          | 0.5473                     | 0.5381                | 0.5427                       |
+| 2.0115 | 1750 | 0.8971        | 0.7864          | 0.5539                     | 0.5201                | 0.5370                       |
+| 2.2989 | 2000 | 0.8815        | 0.7842          | 0.5580                     | 0.5329                | 0.5455                       |
+| 2.5862 | 2250 | 0.8791        | 0.7824          | 0.5569                     | 0.5286                | 0.5427                       |
+| 2.8736 | 2500 | 0.8667        | 0.7821          | 0.5565                     | 0.5188                | 0.5376                       |
+| 3.1609 | 2750 | 0.8709        | 0.7807          | 0.5536                     | 0.5213                | 0.5374                       |
+| 3.4483 | 3000 | 0.8642        | 0.7802          | 0.5522                     | 0.5277                | 0.5400                       |
 
 
 ### Framework Versions