Add new SentenceTransformer model

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:89998
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+base_model: sentence-transformers/all-MiniLM-L12-v2
 widget:
 - source_sentence: Indian university which follow" international education "type system?
   sentences:
@@ -57,7 +57,7 @@ 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
@@ -67,49 +67,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.26
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.5
+      value: 0.56
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.72
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.74
+      value: 0.82
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.26
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.16666666666666669
+      value: 0.18666666666666665
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.12
+      value: 0.14400000000000002
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07400000000000001
+      value: 0.08199999999999999
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.26
+      value: 0.32
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.5
+      value: 0.56
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.6
+      value: 0.72
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.74
+      value: 0.82
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.48774998633566824
+      value: 0.5574382679738011
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4093333333333333
+      value: 0.4747460317460317
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4245357678657921
+      value: 0.4820380014583416
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -119,49 +119,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.34
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.48
+      value: 0.54
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.62
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
       value: 0.68
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.34
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.16666666666666663
+      value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.124
+      value: 0.132
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07400000000000001
+      value: 0.07200000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.32
+      value: 0.31
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.46
+      value: 0.53
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.57
+      value: 0.6
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.67
+      value: 0.66
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.4959822522649102
+      value: 0.492580214786822
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.447095238095238
+      value: 0.4418809523809524
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4450391558194697
+      value: 0.4462290155539738
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -171,61 +171,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.30000000000000004
+      value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.49
+      value: 0.55
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.6699999999999999
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.71
+      value: 0.75
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.30000000000000004
+      value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.16666666666666666
+      value: 0.19
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.122
+      value: 0.138
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07400000000000001
+      value: 0.077
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.29000000000000004
+      value: 0.315
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.48
+      value: 0.545
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.585
+      value: 0.6599999999999999
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.7050000000000001
+      value: 0.74
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.49186611930028923
+      value: 0.5250092413803116
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.42821428571428566
+      value: 0.45831349206349203
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4347874618426309
+      value: 0.4641335085061577
       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
@@ -278,9 +278,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.7596,  0.0004],
-#         [ 0.7596,  1.0000, -0.0846],
-#         [ 0.0004, -0.0846,  1.0000]])
+# tensor([[ 1.0000,  0.8663,  0.0078],
+#         [ 0.8663,  1.0000, -0.0501],
+#         [ 0.0078, -0.0501,  1.0000]])
 ```
 
 <!--
@@ -316,23 +316,23 @@ You can finetune this model on your own dataset.
 * Datasets: `NanoMSMARCO` and `NanoNQ`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | NanoMSMARCO | NanoNQ    |
-|:--------------------|:------------|:----------|
-| cosine_accuracy@1   | 0.26        | 0.34      |
-| cosine_accuracy@3   | 0.5         | 0.48      |
-| cosine_accuracy@5   | 0.6         | 0.6       |
-| cosine_accuracy@10  | 0.74        | 0.68      |
-| cosine_precision@1  | 0.26        | 0.34      |
-| cosine_precision@3  | 0.1667      | 0.1667    |
-| cosine_precision@5  | 0.12        | 0.124     |
-| cosine_precision@10 | 0.074       | 0.074     |
-| cosine_recall@1     | 0.26        | 0.32      |
-| cosine_recall@3     | 0.5         | 0.46      |
-| cosine_recall@5     | 0.6         | 0.57      |
-| cosine_recall@10    | 0.74        | 0.67      |
-| **cosine_ndcg@10**  | **0.4877**  | **0.496** |
-| cosine_mrr@10       | 0.4093      | 0.4471    |
-| cosine_map@100      | 0.4245      | 0.445     |
+| Metric              | NanoMSMARCO | NanoNQ     |
+|:--------------------|:------------|:-----------|
+| cosine_accuracy@1   | 0.32        | 0.32       |
+| cosine_accuracy@3   | 0.56        | 0.54       |
+| cosine_accuracy@5   | 0.72        | 0.62       |
+| cosine_accuracy@10  | 0.82        | 0.68       |
+| cosine_precision@1  | 0.32        | 0.32       |
+| cosine_precision@3  | 0.1867      | 0.1933     |
+| cosine_precision@5  | 0.144       | 0.132      |
+| cosine_precision@10 | 0.082       | 0.072      |
+| cosine_recall@1     | 0.32        | 0.31       |
+| cosine_recall@3     | 0.56        | 0.53       |
+| cosine_recall@5     | 0.72        | 0.6        |
+| cosine_recall@10    | 0.82        | 0.66       |
+| **cosine_ndcg@10**  | **0.5574**  | **0.4926** |
+| cosine_mrr@10       | 0.4747      | 0.4419     |
+| cosine_map@100      | 0.482       | 0.4462     |
 
 #### Nano BEIR
 
@@ -348,23 +348,23 @@ You can finetune this model on your own dataset.
   }
   ```
 
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.3        |
-| cosine_accuracy@3   | 0.49       |
-| cosine_accuracy@5   | 0.6        |
-| cosine_accuracy@10  | 0.71       |
-| cosine_precision@1  | 0.3        |
-| cosine_precision@3  | 0.1667     |
-| cosine_precision@5  | 0.122      |
-| cosine_precision@10 | 0.074      |
-| cosine_recall@1     | 0.29       |
-| cosine_recall@3     | 0.48       |
-| cosine_recall@5     | 0.585      |
-| cosine_recall@10    | 0.705      |
-| **cosine_ndcg@10**  | **0.4919** |
-| cosine_mrr@10       | 0.4282     |
-| cosine_map@100      | 0.4348     |
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.32      |
+| cosine_accuracy@3   | 0.55      |
+| cosine_accuracy@5   | 0.67      |
+| cosine_accuracy@10  | 0.75      |
+| cosine_precision@1  | 0.32      |
+| cosine_precision@3  | 0.19      |
+| cosine_precision@5  | 0.138     |
+| cosine_precision@10 | 0.077     |
+| cosine_recall@1     | 0.315     |
+| cosine_recall@3     | 0.545     |
+| cosine_recall@5     | 0.66      |
+| cosine_recall@10    | 0.74      |
+| **cosine_ndcg@10**  | **0.525** |
+| cosine_mrr@10       | 0.4583    |
+| cosine_map@100      | 0.4641    |
 
 <!--
 ## Bias, Risks and Limitations
@@ -581,19 +581,19 @@ 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    | -             | 0.5439          | 0.5540                     | 0.5931                | 0.5735                       |
-| 0.3556 | 250  | 0.61          | 0.4258          | 0.5310                     | 0.5623                | 0.5466                       |
-| 0.7112 | 500  | 0.5484        | 0.4127          | 0.5289                     | 0.5387                | 0.5338                       |
-| 1.0669 | 750  | 0.5286        | 0.4054          | 0.5110                     | 0.5322                | 0.5216                       |
-| 1.4225 | 1000 | 0.5138        | 0.4005          | 0.5065                     | 0.5266                | 0.5165                       |
-| 1.7781 | 1250 | 0.508         | 0.3972          | 0.4863                     | 0.5172                | 0.5018                       |
-| 2.1337 | 1500 | 0.4986        | 0.3955          | 0.4837                     | 0.5191                | 0.5014                       |
-| 2.4893 | 1750 | 0.4936        | 0.3933          | 0.4908                     | 0.5175                | 0.5041                       |
-| 2.8450 | 2000 | 0.4896        | 0.3920          | 0.4867                     | 0.4974                | 0.4920                       |
-| 3.2006 | 2250 | 0.486         | 0.3910          | 0.4820                     | 0.4963                | 0.4891                       |
-| 3.5562 | 2500 | 0.482         | 0.3903          | 0.4814                     | 0.4961                | 0.4887                       |
-| 3.9118 | 2750 | 0.481         | 0.3897          | 0.4877                     | 0.4956                | 0.4917                       |
-| 4.2674 | 3000 | 0.4798        | 0.3894          | 0.4877                     | 0.4960                | 0.4919                       |
+| 0      | 0    | -             | 0.5972          | 0.5887                     | 0.5786                | 0.5836                       |
+| 0.3556 | 250  | 0.5902        | 0.4140          | 0.5596                     | 0.5395                | 0.5495                       |
+| 0.7112 | 500  | 0.5168        | 0.4000          | 0.5798                     | 0.5206                | 0.5502                       |
+| 1.0669 | 750  | 0.4977        | 0.3934          | 0.5722                     | 0.5079                | 0.5401                       |
+| 1.4225 | 1000 | 0.4825        | 0.3875          | 0.5612                     | 0.5129                | 0.5370                       |
+| 1.7781 | 1250 | 0.4764        | 0.3843          | 0.5734                     | 0.5179                | 0.5457                       |
+| 2.1337 | 1500 | 0.4672        | 0.3821          | 0.5740                     | 0.5065                | 0.5402                       |
+| 2.4893 | 1750 | 0.4612        | 0.3804          | 0.5721                     | 0.4950                | 0.5335                       |
+| 2.8450 | 2000 | 0.4576        | 0.3791          | 0.5588                     | 0.4836                | 0.5212                       |
+| 3.2006 | 2250 | 0.4533        | 0.3775          | 0.5550                     | 0.5005                | 0.5278                       |
+| 3.5562 | 2500 | 0.4491        | 0.3770          | 0.5604                     | 0.4919                | 0.5262                       |
+| 3.9118 | 2750 | 0.4483        | 0.3763          | 0.5569                     | 0.4897                | 0.5233                       |
+| 4.2674 | 3000 | 0.446         | 0.3760          | 0.5574                     | 0.4926                | 0.5250                       |
 
 
 ### Framework Versions