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: 0.34
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.52
+      value: 0.58
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.58
+      value: 0.7
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.7
+      value: 0.76
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.32
+      value: 0.34
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.1733333333333333
+      value: 0.19333333333333333
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.11599999999999999
+      value: 0.14
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07
+      value: 0.07600000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.32
+      value: 0.34
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.52
+      value: 0.58
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.58
+      value: 0.7
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.7
+      value: 0.76
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.49929515877847647
+      value: 0.5436893725288487
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.43693650793650785
+      value: 0.47455555555555556
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.45205401276376506
+      value: 0.4851846595537516
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -168,49 +168,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.4
+      value: 0.44
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.6
+      value: 0.58
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.6
+      value: 0.62
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.64
+      value: 0.68
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.4
+      value: 0.44
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.21333333333333332
+      value: 0.20666666666666664
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.128
+      value: 0.136
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07
+      value: 0.07400000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.38
+      value: 0.42
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.58
+      value: 0.56
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.58
+      value: 0.61
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.63
+      value: 0.67
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.526038841299356
+      value: 0.5510065553704148
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.49449999999999994
+      value: 0.5145555555555554
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.504343499124684
+      value: 0.5204271480365081
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -220,61 +220,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.36
+      value: 0.39
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.56
+      value: 0.58
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.59
+      value: 0.6599999999999999
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.6699999999999999
+      value: 0.72
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.36
+      value: 0.39
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.1933333333333333
+      value: 0.19999999999999998
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.122
+      value: 0.138
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07
+      value: 0.07500000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.35
+      value: 0.38
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.55
+      value: 0.5700000000000001
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.58
+      value: 0.655
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.665
+      value: 0.7150000000000001
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5126670000389162
+      value: 0.5473479639496317
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4657182539682539
+      value: 0.4945555555555555
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.47819875594422456
+      value: 0.5028059037951299
       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, 0.9662],
-#         [1.0000, 1.0000, 0.9662],
-#         [0.9662, 0.9662, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.9667],
+#         [1.0000, 1.0000, 0.9667],
+#         [0.9667, 0.9667, 1.0000]])
 ```
 
 <!--
@@ -367,21 +367,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ    |
 |:--------------------|:------------|:----------|
-| cosine_accuracy@1   | 0.32        | 0.4       |
-| cosine_accuracy@3   | 0.52        | 0.6       |
-| cosine_accuracy@5   | 0.58        | 0.6       |
-| cosine_accuracy@10  | 0.7         | 0.64      |
-| cosine_precision@1  | 0.32        | 0.4       |
-| cosine_precision@3  | 0.1733      | 0.2133    |
-| cosine_precision@5  | 0.116       | 0.128     |
-| cosine_precision@10 | 0.07        | 0.07      |
-| cosine_recall@1     | 0.32        | 0.38      |
-| cosine_recall@3     | 0.52        | 0.58      |
-| cosine_recall@5     | 0.58        | 0.58      |
-| cosine_recall@10    | 0.7         | 0.63      |
-| **cosine_ndcg@10**  | **0.4993**  | **0.526** |
-| cosine_mrr@10       | 0.4369      | 0.4945    |
-| cosine_map@100      | 0.4521      | 0.5043    |
+| cosine_accuracy@1   | 0.34        | 0.44      |
+| cosine_accuracy@3   | 0.58        | 0.58      |
+| cosine_accuracy@5   | 0.7         | 0.62      |
+| cosine_accuracy@10  | 0.76        | 0.68      |
+| cosine_precision@1  | 0.34        | 0.44      |
+| cosine_precision@3  | 0.1933      | 0.2067    |
+| cosine_precision@5  | 0.14        | 0.136     |
+| cosine_precision@10 | 0.076       | 0.074     |
+| cosine_recall@1     | 0.34        | 0.42      |
+| cosine_recall@3     | 0.58        | 0.56      |
+| cosine_recall@5     | 0.7         | 0.61      |
+| cosine_recall@10    | 0.76        | 0.67      |
+| **cosine_ndcg@10**  | **0.5437**  | **0.551** |
+| cosine_mrr@10       | 0.4746      | 0.5146    |
+| cosine_map@100      | 0.4852      | 0.5204    |
 
 #### Nano BEIR
 
@@ -399,21 +399,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.36       |
-| cosine_accuracy@3   | 0.56       |
-| cosine_accuracy@5   | 0.59       |
-| cosine_accuracy@10  | 0.67       |
-| cosine_precision@1  | 0.36       |
-| cosine_precision@3  | 0.1933     |
-| cosine_precision@5  | 0.122      |
-| cosine_precision@10 | 0.07       |
-| cosine_recall@1     | 0.35       |
-| cosine_recall@3     | 0.55       |
-| cosine_recall@5     | 0.58       |
-| cosine_recall@10    | 0.665      |
-| **cosine_ndcg@10**  | **0.5127** |
-| cosine_mrr@10       | 0.4657     |
-| cosine_map@100      | 0.4782     |
+| cosine_accuracy@1   | 0.39       |
+| cosine_accuracy@3   | 0.58       |
+| cosine_accuracy@5   | 0.66       |
+| cosine_accuracy@10  | 0.72       |
+| cosine_precision@1  | 0.39       |
+| cosine_precision@3  | 0.2        |
+| cosine_precision@5  | 0.138      |
+| cosine_precision@10 | 0.075      |
+| cosine_recall@1     | 0.38       |
+| cosine_recall@3     | 0.57       |
+| cosine_recall@5     | 0.655      |
+| cosine_recall@10    | 0.715      |
+| **cosine_ndcg@10**  | **0.5473** |
+| cosine_mrr@10       | 0.4946     |
+| cosine_map@100      | 0.5028     |
 
 <!--
 ## 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  | 1.2993        | 1.0253          | 0.5633                     | 0.5800                | 0.5717                       |
-| 0.5747 | 500  | 1.1589        | 0.9516          | 0.5510                     | 0.5369                | 0.5439                       |
-| 0.8621 | 750  | 1.1172        | 0.9326          | 0.5388                     | 0.5225                | 0.5307                       |
-| 1.1494 | 1000 | 1.0956        | 0.9225          | 0.5086                     | 0.5271                | 0.5179                       |
-| 1.4368 | 1250 | 1.0879        | 0.9155          | 0.5084                     | 0.5271                | 0.5178                       |
-| 1.7241 | 1500 | 1.0773        | 0.9105          | 0.5052                     | 0.5264                | 0.5158                       |
-| 2.0115 | 1750 | 1.0714        | 0.9061          | 0.5045                     | 0.5264                | 0.5155                       |
-| 2.2989 | 2000 | 1.0697        | 0.9027          | 0.5051                     | 0.5264                | 0.5158                       |
-| 2.5862 | 2250 | 1.0664        | 0.9001          | 0.4993                     | 0.5270                | 0.5132                       |
-| 2.8736 | 2500 | 1.0509        | 0.8983          | 0.4993                     | 0.5264                | 0.5129                       |
-| 3.1609 | 2750 | 1.0602        | 0.8971          | 0.4993                     | 0.5260                | 0.5127                       |
-| 3.4483 | 3000 | 1.0563        | 0.8967          | 0.4993                     | 0.5260                | 0.5127                       |
+| 0      | 0    | -             | 1.1142          | 0.5887                     | 0.5786                | 0.5836                       |
+| 0.2874 | 250  | 1.2369        | 0.9676          | 0.5820                     | 0.5623                | 0.5722                       |
+| 0.5747 | 500  | 1.0862        | 0.9027          | 0.5672                     | 0.5526                | 0.5599                       |
+| 0.8621 | 750  | 1.046         | 0.8835          | 0.5590                     | 0.5643                | 0.5616                       |
+| 1.1494 | 1000 | 1.0275        | 0.8718          | 0.5538                     | 0.5602                | 0.5570                       |
+| 1.4368 | 1250 | 1.0174        | 0.8623          | 0.5463                     | 0.5616                | 0.5540                       |
+| 1.7241 | 1500 | 1.0041        | 0.8554          | 0.5506                     | 0.5510                | 0.5508                       |
+| 2.0115 | 1750 | 0.9984        | 0.8497          | 0.5575                     | 0.5510                | 0.5543                       |
+| 2.2989 | 2000 | 0.9941        | 0.8455          | 0.5500                     | 0.5510                | 0.5505                       |
+| 2.5862 | 2250 | 0.9902        | 0.8429          | 0.5571                     | 0.5510                | 0.5540                       |
+| 2.8736 | 2500 | 0.9751        | 0.8411          | 0.5497                     | 0.5510                | 0.5504                       |
+| 3.1609 | 2750 | 0.9842        | 0.8400          | 0.5437                     | 0.5510                | 0.5473                       |
+| 3.4483 | 3000 | 0.9796        | 0.8397          | 0.5437                     | 0.5510                | 0.5473                       |
 
 
 ### Framework Versions