Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 384,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

README.md

@@ -7,7 +7,7 @@ tags:
 - generated_from_trainer
 - dataset_size:111468
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L12-v2
+base_model: Alibaba-NLP/gte-modernbert-base
 widget:
 - source_sentence: What is something you do (or don’t do), even though you feel conflicted
     about it?
@@ -60,7 +60,7 @@ metrics:
 - cosine_mrr@10
 - cosine_map@100
 model-index:
-- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+- name: SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
   results:
   - task:
       type: information-retrieval
@@ -70,49 +70,49 @@ model-index:
       type: NanoMSMARCO
     metrics:
     - type: cosine_accuracy@1
-      value: 0.22
+      value: 0.16
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.42
+      value: 0.3
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.56
+      value: 0.32
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.64
+      value: 0.4
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.22
+      value: 0.16
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.13999999999999999
+      value: 0.09999999999999998
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.11200000000000002
+      value: 0.064
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.06400000000000002
+      value: 0.04000000000000001
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.22
+      value: 0.16
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.42
+      value: 0.3
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.56
+      value: 0.32
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.64
+      value: 0.4
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.4253611031601517
+      value: 0.2797381138841459
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.3573571428571428
+      value: 0.24177777777777776
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.37029891648053065
+      value: 0.25452652172848145
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -122,49 +122,49 @@ model-index:
       type: NanoNQ
     metrics:
     - type: cosine_accuracy@1
-      value: 0.18
+      value: 0.1
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.34
+      value: 0.12
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.4
+      value: 0.16
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.48
+      value: 0.26
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.18
+      value: 0.1
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.11333333333333333
+      value: 0.04
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.08
+      value: 0.032
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.04800000000000001
+      value: 0.026000000000000002
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.16
+      value: 0.08
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.32
+      value: 0.09
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.37
+      value: 0.13
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.45
+      value: 0.23
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.30483462455030724
+      value: 0.13826388457522362
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.27455555555555555
+      value: 0.12794444444444442
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.26647869540792385
+      value: 0.10725400911912068
       name: Cosine Map@100
   - task:
       type: nano-beir
@@ -174,63 +174,63 @@ model-index:
       type: NanoBEIR_mean
     metrics:
     - type: cosine_accuracy@1
-      value: 0.2
+      value: 0.13
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.38
+      value: 0.21
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.48000000000000004
+      value: 0.24
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.56
+      value: 0.33
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.2
+      value: 0.13
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.12666666666666665
+      value: 0.06999999999999999
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.096
+      value: 0.048
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.05600000000000001
+      value: 0.033
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.19
+      value: 0.12
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.37
+      value: 0.195
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.465
+      value: 0.225
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.545
+      value: 0.315
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.36509786385522947
+      value: 0.20900099922968474
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.3159563492063492
+      value: 0.1848611111111111
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.31838880594422725
+      value: 0.18089026542380107
       name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
 
-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.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base). 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:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 936af83a2ecce5fe87a09109ff5cbcefe073173a -->
+- **Base model:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -246,9 +246,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-  (2): Normalize()
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
 )
 ```
 
@@ -276,14 +275,14 @@ sentences = [
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 384]
+# [3, 768]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.4197],
-#         [1.0000, 1.0000, 0.4197],
-#         [0.4197, 0.4197, 1.0000]])
+# tensor([[1.0000, 1.0000, 0.1015],
+#         [1.0000, 1.0000, 0.1015],
+#         [0.1015, 0.1015, 1.0000]])
 ```
 
 <!--
@@ -321,21 +320,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | NanoMSMARCO | NanoNQ     |
 |:--------------------|:------------|:-----------|
-| cosine_accuracy@1   | 0.22        | 0.18       |
-| cosine_accuracy@3   | 0.42        | 0.34       |
-| cosine_accuracy@5   | 0.56        | 0.4        |
-| cosine_accuracy@10  | 0.64        | 0.48       |
-| cosine_precision@1  | 0.22        | 0.18       |
-| cosine_precision@3  | 0.14        | 0.1133     |
-| cosine_precision@5  | 0.112       | 0.08       |
-| cosine_precision@10 | 0.064       | 0.048      |
-| cosine_recall@1     | 0.22        | 0.16       |
-| cosine_recall@3     | 0.42        | 0.32       |
-| cosine_recall@5     | 0.56        | 0.37       |
-| cosine_recall@10    | 0.64        | 0.45       |
-| **cosine_ndcg@10**  | **0.4254**  | **0.3048** |
-| cosine_mrr@10       | 0.3574      | 0.2746     |
-| cosine_map@100      | 0.3703      | 0.2665     |
+| cosine_accuracy@1   | 0.16        | 0.1        |
+| cosine_accuracy@3   | 0.3         | 0.12       |
+| cosine_accuracy@5   | 0.32        | 0.16       |
+| cosine_accuracy@10  | 0.4         | 0.26       |
+| cosine_precision@1  | 0.16        | 0.1        |
+| cosine_precision@3  | 0.1         | 0.04       |
+| cosine_precision@5  | 0.064       | 0.032      |
+| cosine_precision@10 | 0.04        | 0.026      |
+| cosine_recall@1     | 0.16        | 0.08       |
+| cosine_recall@3     | 0.3         | 0.09       |
+| cosine_recall@5     | 0.32        | 0.13       |
+| cosine_recall@10    | 0.4         | 0.23       |
+| **cosine_ndcg@10**  | **0.2797**  | **0.1383** |
+| cosine_mrr@10       | 0.2418      | 0.1279     |
+| cosine_map@100      | 0.2545      | 0.1073     |
 
 #### Nano BEIR
 
@@ -351,23 +350,23 @@ You can finetune this model on your own dataset.
   }
   ```
 
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.2        |
-| cosine_accuracy@3   | 0.38       |
-| cosine_accuracy@5   | 0.48       |
-| cosine_accuracy@10  | 0.56       |
-| cosine_precision@1  | 0.2        |
-| cosine_precision@3  | 0.1267     |
-| cosine_precision@5  | 0.096      |
-| cosine_precision@10 | 0.056      |
-| cosine_recall@1     | 0.19       |
-| cosine_recall@3     | 0.37       |
-| cosine_recall@5     | 0.465      |
-| cosine_recall@10    | 0.545      |
-| **cosine_ndcg@10**  | **0.3651** |
-| cosine_mrr@10       | 0.316      |
-| cosine_map@100      | 0.3184     |
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.13      |
+| cosine_accuracy@3   | 0.21      |
+| cosine_accuracy@5   | 0.24      |
+| cosine_accuracy@10  | 0.33      |
+| cosine_precision@1  | 0.13      |
+| cosine_precision@3  | 0.07      |
+| cosine_precision@5  | 0.048     |
+| cosine_precision@10 | 0.033     |
+| cosine_recall@1     | 0.12      |
+| cosine_recall@3     | 0.195     |
+| cosine_recall@5     | 0.225     |
+| cosine_recall@10    | 0.315     |
+| **cosine_ndcg@10**  | **0.209** |
+| cosine_mrr@10       | 0.1849    |
+| cosine_map@100      | 0.1809    |
 
 <!--
 ## Bias, Risks and Limitations
@@ -390,10 +389,10 @@ You can finetune this model on your own dataset.
 * Size: 111,468 training samples
 * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 16.11 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.16 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.35 tokens</li><li>max: 76 tokens</li></ul> |
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.1 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.16 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.35 tokens</li><li>max: 76 tokens</li></ul> |
 * Samples:
   | anchor                                                                                | positive                                                                              | negative                                                                                 |
   |:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------|
@@ -416,10 +415,10 @@ You can finetune this model on your own dataset.
 * Size: 12,386 evaluation samples
 * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 16.22 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.28 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.39 tokens</li><li>max: 66 tokens</li></ul> |
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.3 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.36 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.41 tokens</li><li>max: 65 tokens</li></ul> |
 * Samples:
   | anchor                                                                                                                              | positive                                                                                                                            | negative                                                                     |
   |:------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|
@@ -584,19 +583,19 @@ 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    | -             | 0.6110          | 0.5887                     | 0.5786                | 0.5836                       |
-| 0.2874 | 250  | 0.6051        | 0.4208          | 0.5346                     | 0.5338                | 0.5342                       |
-| 0.5747 | 500  | 0.5163        | 0.3991          | 0.5346                     | 0.3965                | 0.4655                       |
-| 0.8621 | 750  | 0.4918        | 0.3904          | 0.4988                     | 0.3821                | 0.4404                       |
-| 1.1494 | 1000 | 0.4788        | 0.3851          | 0.4855                     | 0.3593                | 0.4224                       |
-| 1.4368 | 1250 | 0.4676        | 0.3814          | 0.4616                     | 0.3421                | 0.4019                       |
-| 1.7241 | 1500 | 0.4636        | 0.3782          | 0.4680                     | 0.3354                | 0.4017                       |
-| 2.0115 | 1750 | 0.4604        | 0.3763          | 0.4306                     | 0.3243                | 0.3775                       |
-| 2.2989 | 2000 | 0.4523        | 0.3749          | 0.4414                     | 0.3128                | 0.3771                       |
-| 2.5862 | 2250 | 0.4497        | 0.3741          | 0.4349                     | 0.3106                | 0.3727                       |
-| 2.8736 | 2500 | 0.4451        | 0.3725          | 0.4324                     | 0.3072                | 0.3698                       |
-| 3.1609 | 2750 | 0.4439        | 0.3721          | 0.4295                     | 0.3037                | 0.3666                       |
-| 3.4483 | 3000 | 0.4411        | 0.3720          | 0.4254                     | 0.3048                | 0.3651                       |
+| 0      | 0    | -             | 2.1536          | 0.6530                     | 0.6552                | 0.6541                       |
+| 0.2874 | 250  | 0.8149        | 0.3782          | 0.5748                     | 0.6239                | 0.5994                       |
+| 0.5747 | 500  | 0.3649        | 0.3561          | 0.5529                     | 0.5583                | 0.5556                       |
+| 0.8621 | 750  | 0.3496        | 0.3456          | 0.5747                     | 0.4299                | 0.5023                       |
+| 1.1494 | 1000 | 0.3364        | 0.3416          | 0.5479                     | 0.4669                | 0.5074                       |
+| 1.4368 | 1250 | 0.3231        | 0.3385          | 0.4802                     | 0.4214                | 0.4508                       |
+| 1.7241 | 1500 | 0.3222        | 0.3349          | 0.4694                     | 0.3547                | 0.4120                       |
+| 2.0115 | 1750 | 0.3187        | 0.3340          | 0.4398                     | 0.2723                | 0.3560                       |
+| 2.2989 | 2000 | 0.3051        | 0.3347          | 0.3702                     | 0.2144                | 0.2923                       |
+| 2.5862 | 2250 | 0.3039        | 0.3339          | 0.4180                     | 0.2575                | 0.3377                       |
+| 2.8736 | 2500 | 0.2994        | 0.3328          | 0.3687                     | 0.2662                | 0.3174                       |
+| 3.1609 | 2750 | 0.2969        | 0.3339          | 0.2906                     | 0.1283                | 0.2094                       |
+| 3.4483 | 3000 | 0.2933        | 0.3343          | 0.2797                     | 0.1383                | 0.2090                       |
 
 
 ### Framework Versions

config_sentence_transformers.json

@@ -4,11 +4,11 @@
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
-  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""
   },
   "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
 }

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]