Add new SentenceTransformer model

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:90000
 - loss:MultipleNegativesRankingLoss
-base_model: thenlper/gte-small
+base_model: sentence-transformers/all-MiniLM-L6-v2
 widget:
 - source_sentence: what is the maximum i can contribute to a traditional ira
   sentences:
@@ -121,7 +121,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on thenlper/gte-small
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
   results:
   - task:
       type: information-retrieval
@@ -134,46 +134,46 @@ model-index:
       value: 0.32
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.56
+      value: 0.54
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
       value: 0.62
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.74
+      value: 0.72
       name: Cosine Accuracy@10
     - type: cosine_precision@1
       value: 0.32
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18666666666666668
+      value: 0.18
       name: Cosine Precision@3
     - type: cosine_precision@5
       value: 0.124
       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
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.56
+      value: 0.54
       name: Cosine Recall@3
     - type: cosine_recall@5
       value: 0.62
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.74
+      value: 0.72
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.522258803283639
+      value: 0.5113600890173079
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.4534126984126985
+      value: 0.44588095238095227
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4638252994171221
+      value: 0.46015815095025
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -183,49 +183,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.32
+      value: 0.34
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.54
+      value: 0.5
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.54
+      value: 0.58
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.74
+      value: 0.62
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.32
+      value: 0.34
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18666666666666665
+      value: 0.18
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.11600000000000002
+      value: 0.12400000000000003
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07800000000000001
+      value: 0.068
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.29
+      value: 0.31
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.52
+      value: 0.49
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.53
+      value: 0.56
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.71
+      value: 0.61
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5000975716574514
+      value: 0.47606860320855016
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.44801587301587303
+      value: 0.44116666666666665
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.435720694785091
+      value: 0.4435242837774235
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -235,61 +235,61 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.32
+      value: 0.33
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.55
+      value: 0.52
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.5800000000000001
+      value: 0.6
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.74
+      value: 0.6699999999999999
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.32
+      value: 0.33
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.18666666666666665
+      value: 0.18
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.12000000000000001
+      value: 0.12400000000000001
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.07600000000000001
+      value: 0.07
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.305
+      value: 0.315
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.54
+      value: 0.515
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.575
+      value: 0.5900000000000001
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.725
+      value: 0.665
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.5111781874705452
+      value: 0.493714346112929
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.45071428571428573
+      value: 0.44352380952380943
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.4497729971011065
+      value: 0.45184121736383676
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on thenlper/gte-small
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). 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-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.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) <!-- at revision 17e1f347d17fe144873b1201da91788898c639cd -->
+- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
 - **Maximum Sequence Length:** 128 tokens
 - **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
@@ -342,9 +342,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.5348, 0.4287],
-#         [0.5348, 1.0000, 0.3212],
-#         [0.4287, 0.3212, 1.0000]])
+# tensor([[1.0000, 0.5834, 0.4906],
+#         [0.5834, 1.0000, 0.2633],
+#         [0.4906, 0.2633, 1.0000]])
 ```
 
 <!--
@@ -382,21 +382,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.32        | 0.32       |
-| cosine_accuracy@3   | 0.56        | 0.54       |
-| cosine_accuracy@5   | 0.62        | 0.54       |
-| cosine_accuracy@10  | 0.74        | 0.74       |
-| cosine_precision@1  | 0.32        | 0.32       |
-| cosine_precision@3  | 0.1867      | 0.1867     |
-| cosine_precision@5  | 0.124       | 0.116      |
-| cosine_precision@10 | 0.074       | 0.078      |
-| cosine_recall@1     | 0.32        | 0.29       |
-| cosine_recall@3     | 0.56        | 0.52       |
-| cosine_recall@5     | 0.62        | 0.53       |
-| cosine_recall@10    | 0.74        | 0.71       |
-| **cosine_ndcg@10**  | **0.5223**  | **0.5001** |
-| cosine_mrr@10       | 0.4534      | 0.448      |
-| cosine_map@100      | 0.4638      | 0.4357     |
+| cosine_accuracy@1   | 0.32        | 0.34       |
+| cosine_accuracy@3   | 0.54        | 0.5        |
+| cosine_accuracy@5   | 0.62        | 0.58       |
+| cosine_accuracy@10  | 0.72        | 0.62       |
+| cosine_precision@1  | 0.32        | 0.34       |
+| cosine_precision@3  | 0.18        | 0.18       |
+| cosine_precision@5  | 0.124       | 0.124      |
+| cosine_precision@10 | 0.072       | 0.068      |
+| cosine_recall@1     | 0.32        | 0.31       |
+| cosine_recall@3     | 0.54        | 0.49       |
+| cosine_recall@5     | 0.62        | 0.56       |
+| cosine_recall@10    | 0.72        | 0.61       |
+| **cosine_ndcg@10**  | **0.5114**  | **0.4761** |
+| cosine_mrr@10       | 0.4459      | 0.4412     |
+| cosine_map@100      | 0.4602      | 0.4435     |
 
 #### Nano BEIR
 
@@ -414,21 +414,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.32       |
-| cosine_accuracy@3   | 0.55       |
-| cosine_accuracy@5   | 0.58       |
-| cosine_accuracy@10  | 0.74       |
-| cosine_precision@1  | 0.32       |
-| cosine_precision@3  | 0.1867     |
-| cosine_precision@5  | 0.12       |
-| cosine_precision@10 | 0.076      |
-| cosine_recall@1     | 0.305      |
-| cosine_recall@3     | 0.54       |
-| cosine_recall@5     | 0.575      |
-| cosine_recall@10    | 0.725      |
-| **cosine_ndcg@10**  | **0.5112** |
-| cosine_mrr@10       | 0.4507     |
-| cosine_map@100      | 0.4498     |
+| cosine_accuracy@1   | 0.33       |
+| cosine_accuracy@3   | 0.52       |
+| cosine_accuracy@5   | 0.6        |
+| cosine_accuracy@10  | 0.67       |
+| cosine_precision@1  | 0.33       |
+| cosine_precision@3  | 0.18       |
+| cosine_precision@5  | 0.124      |
+| cosine_precision@10 | 0.07       |
+| cosine_recall@1     | 0.315      |
+| cosine_recall@3     | 0.515      |
+| cosine_recall@5     | 0.59       |
+| cosine_recall@10    | 0.665      |
+| **cosine_ndcg@10**  | **0.4937** |
+| cosine_mrr@10       | 0.4435     |
+| cosine_map@100      | 0.4518     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -502,7 +502,7 @@ You can finetune this model on your own dataset.
 - `eval_strategy`: steps
 - `per_device_train_batch_size`: 128
 - `per_device_eval_batch_size`: 128
-- `learning_rate`: 1e-06
+- `learning_rate`: 1e-05
 - `weight_decay`: 0.001
 - `max_steps`: 3000
 - `warmup_ratio`: 0.1
@@ -531,7 +531,7 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 1e-06
+- `learning_rate`: 1e-05
 - `weight_decay`: 0.001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
@@ -645,19 +645,19 @@ 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    | -             | 4.1735          | 0.6259                     | 0.6583                | 0.6421                       |
-| 0.3556 | 250  | 4.3112        | 3.9428          | 0.6062                     | 0.6473                | 0.6268                       |
-| 0.7112 | 500  | 3.8846        | 3.1810          | 0.5977                     | 0.6251                | 0.6114                       |
-| 1.0669 | 750  | 2.9479        | 1.8567          | 0.5628                     | 0.5082                | 0.5355                       |
-| 1.4225 | 1000 | 1.9026        | 1.2819          | 0.5229                     | 0.4809                | 0.5019                       |
-| 1.7781 | 1250 | 1.5448        | 1.1522          | 0.5112                     | 0.4845                | 0.4978                       |
-| 2.1337 | 1500 | 1.4335        | 1.1065          | 0.5183                     | 0.4899                | 0.5041                       |
-| 2.4893 | 1750 | 1.3748        | 1.0820          | 0.5231                     | 0.4896                | 0.5064                       |
-| 2.8450 | 2000 | 1.3445        | 1.0667          | 0.5184                     | 0.4962                | 0.5073                       |
-| 3.2006 | 2250 | 1.3173        | 1.0577          | 0.5231                     | 0.4971                | 0.5101                       |
-| 3.5562 | 2500 | 1.3099        | 1.0517          | 0.5165                     | 0.4999                | 0.5082                       |
-| 3.9118 | 2750 | 1.2945        | 1.0483          | 0.5218                     | 0.4999                | 0.5108                       |
-| 4.2674 | 3000 | 1.288         | 1.0476          | 0.5223                     | 0.5001                | 0.5112                       |
+| 0      | 0    | -             | 1.2542          | 0.5540                     | 0.5931                | 0.5735                       |
+| 0.3556 | 250  | 1.2668        | 0.9745          | 0.5174                     | 0.5317                | 0.5246                       |
+| 0.7112 | 500  | 1.1283        | 0.9461          | 0.5013                     | 0.5121                | 0.5067                       |
+| 1.0669 | 750  | 1.1038        | 0.9351          | 0.5139                     | 0.5015                | 0.5077                       |
+| 1.4225 | 1000 | 1.0775        | 0.9264          | 0.5211                     | 0.5268                | 0.5239                       |
+| 1.7781 | 1250 | 1.0688        | 0.9222          | 0.5290                     | 0.4973                | 0.5132                       |
+| 2.1337 | 1500 | 1.0564        | 0.9181          | 0.5224                     | 0.4688                | 0.4956                       |
+| 2.4893 | 1750 | 1.0411        | 0.9167          | 0.5210                     | 0.5014                | 0.5112                       |
+| 2.8450 | 2000 | 1.0432        | 0.9141          | 0.5257                     | 0.4661                | 0.4959                       |
+| 3.2006 | 2250 | 1.0299        | 0.9124          | 0.5122                     | 0.4895                | 0.5008                       |
+| 3.5562 | 2500 | 1.0308        | 0.9112          | 0.5131                     | 0.4848                | 0.4989                       |
+| 3.9118 | 2750 | 1.0231        | 0.9106          | 0.5106                     | 0.4843                | 0.4975                       |
+| 4.2674 | 3000 | 1.0183        | 0.9105          | 0.5114                     | 0.4761                | 0.4937                       |
 
 
 ### Framework Versions

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
-  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
+  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""