Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,820 @@
+---
+base_model: cross-encoder/ms-marco-MiniLM-L-4-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:4173
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 'Aquelles persones (físiques o jurídiques) que es disposin a exercir
+    una de les següents activitats: ... Han de comunicar-ho a l''Ajuntament prèviament
+    a la data prevista de la seva obertura.'
+  sentences:
+  - Quin és el benefici que es pretén obtenir amb aquests ajuts econòmics per a les
+    empreses d'hostaleria i restauració?
+  - Quin és el benefici del sistema de teleassistència per a les persones que viuen
+    amb altres persones amb discapacitat?
+  - Quin és el propòsit de la comunicació prèvia d'una activitat recreativa o un espectacle
+    públic?
+- source_sentence: Les persones titulars d’activitats que generin residus comercials
+    o industrials assimilables als municipals, vindran obligats a acreditar davant
+    l’Ajuntament que tenen contractat un gestor autoritzat per la recollida, tractament
+    i eliminació dels residus que produeixi l’activitat corresponent.
+  sentences:
+  - Quin és el paper de l'Ajuntament en l'acreditació de recollida de residus?
+  - Quin és el benefici de les activitats d'animació socio-cultural?
+  - Quin és el benefici de l'ajut per a la creació de noves empreses?
+- source_sentence: Modificació de sol·licitud de permís d'ocupació de la via pública
+    per filmacions, rodatges o sessions fotogràfiques.
+  sentences:
+  - Quin és el grau de discapacitat mínim per a rebre l'ajut de 300€ anuals?
+  - Quin és el requisit per a la constitució o modificació del règim de propietat
+    horitzontal?
+  - Quin és el tipus de permís que es modifica?
+- source_sentence: El beneficiari és l'encarregat de complir les condicions de la
+    subvenció i de presentar els informes de seguiment del projecte.
+  sentences:
+  - Quin és el paper del beneficiari en el procés de subvencions?
+  - Quin és el càlcul dels interessos de demora en el fraccionament i l'ajornament?
+  - Quin és el període de temps en què es poden efectuar les despeses mèdiques per
+    a rebre l'ajuda?
+- source_sentence: Aquest tràmit permet sol·licitar la llicència per a realitzar obres
+    d'excavació a la via pública per a la instal·lació o reparació d'infraestructures
+    de serveis i subministraments.
+  sentences:
+  - Quin és el paper de la via pública en aquest tràmit?
+  - Quin és el requisit principal per obtenir el certificat?
+  - Quin és l'objectiu de presentar una denúncia per presumpta infracció urbanística?
+model-index:
+- name: SentenceTransformer based on cross-encoder/ms-marco-MiniLM-L-4-v2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.05172413793103448
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.1271551724137931
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1788793103448276
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3254310344827586
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.05172413793103448
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.042385057471264365
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03577586206896552
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.032543103448275865
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.05172413793103448
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1271551724137931
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1788793103448276
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3254310344827586
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16276692425092115
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11428999042145602
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13620420069102204
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.05172413793103448
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.1271551724137931
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1788793103448276
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3254310344827586
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.05172413793103448
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.042385057471264365
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03577586206896552
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.032543103448275865
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.05172413793103448
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1271551724137931
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1788793103448276
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3254310344827586
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.16276692425092115
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11428999042145602
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13620420069102204
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04525862068965517
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.1206896551724138
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17025862068965517
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3232758620689655
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04525862068965517
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04022988505747126
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03405172413793103
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.032327586206896554
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04525862068965517
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1206896551724138
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17025862068965517
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3232758620689655
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15757998924712813
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10828971674876857
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13108979755674435
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04741379310344827
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.1206896551724138
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17672413793103448
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3146551724137931
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04741379310344827
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04022988505747126
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0353448275862069
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03146551724137931
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04741379310344827
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.1206896551724138
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17672413793103448
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3146551724137931
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15563167494658142
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10829484811165858
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.13156999055462598
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.036637931034482756
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.10129310344827586
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.15301724137931033
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.28448275862068967
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.036637931034482756
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.033764367816091954
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03060344827586207
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.028448275862068963
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.036637931034482756
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.10129310344827586
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.15301724137931033
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.28448275862068967
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.13580741965441598
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.09167179802955677
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1149404289076573
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on cross-encoder/ms-marco-MiniLM-L-4-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [cross-encoder/ms-marco-MiniLM-L-4-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-4-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:** [cross-encoder/ms-marco-MiniLM-L-4-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-4-v2) <!-- at revision 1f1ab0943a42a52afd702e7e8337bec985c189ea -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: 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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("adriansanz/sitges10242608-4ep-rerankv3")
+# Run inference
+sentences = [
+    "Aquest tràmit permet sol·licitar la llicència per a realitzar obres d'excavació a la via pública per a la instal·lació o reparació d'infraestructures de serveis i subministraments.",
+    'Quin és el paper de la via pública en aquest tràmit?',
+    "Quin és l'objectiu de presentar una denúncia per presumpta infracció urbanística?",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0517     |
+| cosine_accuracy@3   | 0.1272     |
+| cosine_accuracy@5   | 0.1789     |
+| cosine_accuracy@10  | 0.3254     |
+| cosine_precision@1  | 0.0517     |
+| cosine_precision@3  | 0.0424     |
+| cosine_precision@5  | 0.0358     |
+| cosine_precision@10 | 0.0325     |
+| cosine_recall@1     | 0.0517     |
+| cosine_recall@3     | 0.1272     |
+| cosine_recall@5     | 0.1789     |
+| cosine_recall@10    | 0.3254     |
+| cosine_ndcg@10      | 0.1628     |
+| cosine_mrr@10       | 0.1143     |
+| **cosine_map@100**  | **0.1362** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0517     |
+| cosine_accuracy@3   | 0.1272     |
+| cosine_accuracy@5   | 0.1789     |
+| cosine_accuracy@10  | 0.3254     |
+| cosine_precision@1  | 0.0517     |
+| cosine_precision@3  | 0.0424     |
+| cosine_precision@5  | 0.0358     |
+| cosine_precision@10 | 0.0325     |
+| cosine_recall@1     | 0.0517     |
+| cosine_recall@3     | 0.1272     |
+| cosine_recall@5     | 0.1789     |
+| cosine_recall@10    | 0.3254     |
+| cosine_ndcg@10      | 0.1628     |
+| cosine_mrr@10       | 0.1143     |
+| **cosine_map@100**  | **0.1362** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0453     |
+| cosine_accuracy@3   | 0.1207     |
+| cosine_accuracy@5   | 0.1703     |
+| cosine_accuracy@10  | 0.3233     |
+| cosine_precision@1  | 0.0453     |
+| cosine_precision@3  | 0.0402     |
+| cosine_precision@5  | 0.0341     |
+| cosine_precision@10 | 0.0323     |
+| cosine_recall@1     | 0.0453     |
+| cosine_recall@3     | 0.1207     |
+| cosine_recall@5     | 0.1703     |
+| cosine_recall@10    | 0.3233     |
+| cosine_ndcg@10      | 0.1576     |
+| cosine_mrr@10       | 0.1083     |
+| **cosine_map@100**  | **0.1311** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0474     |
+| cosine_accuracy@3   | 0.1207     |
+| cosine_accuracy@5   | 0.1767     |
+| cosine_accuracy@10  | 0.3147     |
+| cosine_precision@1  | 0.0474     |
+| cosine_precision@3  | 0.0402     |
+| cosine_precision@5  | 0.0353     |
+| cosine_precision@10 | 0.0315     |
+| cosine_recall@1     | 0.0474     |
+| cosine_recall@3     | 0.1207     |
+| cosine_recall@5     | 0.1767     |
+| cosine_recall@10    | 0.3147     |
+| cosine_ndcg@10      | 0.1556     |
+| cosine_mrr@10       | 0.1083     |
+| **cosine_map@100**  | **0.1316** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0366     |
+| cosine_accuracy@3   | 0.1013     |
+| cosine_accuracy@5   | 0.153      |
+| cosine_accuracy@10  | 0.2845     |
+| cosine_precision@1  | 0.0366     |
+| cosine_precision@3  | 0.0338     |
+| cosine_precision@5  | 0.0306     |
+| cosine_precision@10 | 0.0284     |
+| cosine_recall@1     | 0.0366     |
+| cosine_recall@3     | 0.1013     |
+| cosine_recall@5     | 0.153      |
+| cosine_recall@10    | 0.2845     |
+| cosine_ndcg@10      | 0.1358     |
+| cosine_mrr@10       | 0.0917     |
+| **cosine_map@100**  | **0.1149** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 4,173 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                            | anchor                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 67.49 tokens</li><li>max: 214 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 28.0 tokens</li><li>max: 61 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                             | anchor                                                                                         |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
+  | <code>Havent-se d'acreditar la matriculació i inscripció en el respectiu centre públic o concertat, així com el cost de les llars d'infants, de l'educació especialitzada per les discapacitats físiques, psíquiques i sensorials en centres públics, concertats o privats.</code>                                                                                                                                                   | <code>Quin és el requisit per acreditar la llar d'infants?</code>                              |
+  | <code>El volant històric de convivència és el document que informa de la residencia en el municipi de Sitges, així com altres fets relatius a l'empadronament d'una persona, i detalla tots els domicilis, la data inicial i final en els que ha estat empadronada en cadascun d'ells, i les persones amb les què constava inscrites, segons les dades que consten al Padró Municipal d'Habitants fins a la data d'expedició.</code> | <code>Quin és el propòsit del volant històric de convivència?</code>                           |
+  | <code>Instal·lació de tanques sense obra.</code>                                                                                                                                                                                                                                                                                                                                                                                     | <code>Quins són els exemples d'instal·lacions que es poden comunicar amb aquest tràmit?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          384,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `num_train_epochs`: 10
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.2
+- `bf16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.2
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.6130     | 10     | 11.3695       | -                      | -                      | -                      | -                     | -                      |
+| 0.9808     | 16     | -             | 0.0214                 | 0.0243                 | 0.0234                 | 0.0199                | 0.0234                 |
+| 1.2261     | 20     | 10.653        | -                      | -                      | -                      | -                     | -                      |
+| 1.8391     | 30     | 9.0745        | -                      | -                      | -                      | -                     | -                      |
+| 1.9617     | 32     | -             | 0.0495                 | 0.0517                 | 0.0589                 | 0.0481                | 0.0589                 |
+| 2.4521     | 40     | 7.3468        | -                      | -                      | -                      | -                     | -                      |
+| 2.9425     | 48     | -             | 0.0764                 | 0.0734                 | 0.0811                 | 0.0709                | 0.0811                 |
+| 3.0651     | 50     | 5.887         | -                      | -                      | -                      | -                     | -                      |
+| 3.6782     | 60     | 5.3568        | -                      | -                      | -                      | -                     | -                      |
+| 3.9847     | 65     | -             | 0.0922                 | 0.0857                 | 0.0896                 | 0.0808                | 0.0896                 |
+| 4.2912     | 70     | 4.8338        | -                      | -                      | -                      | -                     | -                      |
+| **4.9042** | **80** | **4.9251**    | **0.0899**             | **0.0899**             | **0.0906**             | **0.0837**            | **0.0906**             |
+| 0.9771     | 8      | -             | 0.0953                 | 0.0965                 | 0.0957                 | 0.0841                | 0.0957                 |
+| 1.2214     | 10     | 6.7779        | -                      | -                      | -                      | -                     | -                      |
+| 1.9542     | 16     | -             | 0.1056                 | 0.1036                 | 0.1078                 | 0.0948                | 0.1078                 |
+| 2.4427     | 20     | 5.8485        | -                      | -                      | -                      | -                     | -                      |
+| 2.9313     | 24     | -             | 0.1112                 | 0.1107                 | 0.1170                 | 0.1009                | 0.1170                 |
+| 3.6641     | 30     | 4.6394        | -                      | -                      | -                      | -                     | -                      |
+| 3.9084     | 32     | -             | 0.1243                 | 0.1189                 | 0.1247                 | 0.1152                | 0.1247                 |
+| 4.8855     | 40     | 3.8786        | 0.1248                 | 0.1248                 | 0.1335                 | 0.1148                | 0.1335                 |
+| 5.9847     | 49     | -             | 0.1298                 | 0.1298                 | 0.1371                 | 0.1204                | 0.1371                 |
+| 6.1069     | 50     | 3.3198        | -                      | -                      | -                      | -                     | -                      |
+| 6.9618     | 57     | -             | 0.1284                 | 0.1347                 | 0.1370                 | 0.1208                | 0.1370                 |
+| 7.3282     | 60     | 3.081         | -                      | -                      | -                      | -                     | -                      |
+| 7.9389     | 65     | -             | 0.1273                 | 0.1344                 | 0.1360                 | 0.1215                | 0.1360                 |
+| 8.5496     | 70     | 2.8556        | -                      | -                      | -                      | -                     | -                      |
+| 8.9160     | 73     | -             | 0.1313                 | 0.1315                 | 0.1350                 | 0.1147                | 0.1350                 |
+| **9.771**  | **80** | **2.7635**    | **0.1316**             | **0.1311**             | **0.1362**             | **0.1149**            | **0.1362**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.34.0.dev0
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "cross-encoder/ms-marco-MiniLM-L-4-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f60ab0540c338e932a990dbded312712ec584063bb84c5c193f43760574192
+size 76664936

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}