Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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
+}

README.md

@@ -0,0 +1,893 @@
+---
+base_model: BAAI/bge-m3
+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: L'Espai d'escalada és una instal·lació municipal en forma de túnel
+    a una sala interior, amb una llargada de 10m, una amplada de 4,6m i una alçada
+    de 4m.
+  sentences:
+  - Quin és el registre on es comprova la inscripció dels estrangers amb ciutadania
+    de l'Espai Econòmic Europeu?
+  - On es pot trobar les bases generals de les convocatòries de selecció de personal
+    de l'Ajuntament?
+  - Quina és la llargada de l'Espai d'Escalada?
+- source_sentence: Les activitats s’organitzen per setmanes.
+  sentences:
+  - Quin és el format en què es desenvolupen les activitats de l'Estiu Jove?
+  - Quin és el paper del subjecte passiu en la gestió de pagaments?
+  - Quin és el benefici de les subvencions?
+- source_sentence: Les Estades Esportives cerquen que els infants aprenguin a relacionar-se
+    i a compartir mitjançant l'esport, experiències i vivències amb d'altres infants
+    amb qui no estan en contacte durant la resta de l'any.
+  sentences:
+  - Quin és el propòsit de l'ajut per a la creació de noves empreses?
+  - Quin és el propòsit de la llicència de parcel·lació?
+  - Quin és el benefici principal de les Estades Esportives?
+- source_sentence: Declaració tributària mitjançant la qual es sol·licita la baixa
+    d'una activitat de la Taxa pel servei municipal complementari de recollida, tractament
+    i eliminació de residus comercials.
+  sentences:
+  - Quin és el format de la Declaració de baixa?
+  - Quin és el resultat de justificar una sol·licitud de canvi a les estades esportives?
+  - Quin és el període de celebració de la Fira d'Art de Sitges?
+- source_sentence: Les entitats inscrites en el Registre resten obligades a comunicar
+    a l’Ajuntament qualsevol modificació en les seves dades registrals, podent sol·licitar
+    la seva cancel·lació o comunicant la seva dissolució.
+  sentences:
+  - Quin és el procediment per cancel·lar la inscripció d'una entitat al Registre
+    municipal d'entitats?
+  - Quin és el propòsit de la quota del servei de les Llars d'Infants Municipals?
+  - Quin és el paper de les entitats de protecció dels animals en la gestió de les
+    colònies urbanes felines?
+model-index:
+- name: SentenceTransformer based on BAAI/bge-m3
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08620689655172414
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.21551724137931033
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3275862068965517
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5107758620689655
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08620689655172414
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.07183908045977011
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06551724137931034
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05107758620689654
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08620689655172414
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.21551724137931033
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3275862068965517
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5107758620689655
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.26401643418499254
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1896731321839082
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2150866107809785
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08405172413793104
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.20905172413793102
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.31896551724137934
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08405172413793104
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.069683908045977
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06379310344827585
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04999999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08405172413793104
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.20905172413793102
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.31896551724137934
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2594763687925116
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.18673713738368922
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.21319033477988852
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08620689655172414
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.21120689655172414
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.32112068965517243
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5129310344827587
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08620689655172414
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.07040229885057471
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06422413793103447
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.051293103448275854
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08620689655172414
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.21120689655172414
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.32112068965517243
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5129310344827587
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2646539120704089
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1899279898741108
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.21554766038692458
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08189655172413793
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.20474137931034483
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.30603448275862066
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5043103448275862
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08189655172413793
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0682471264367816
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.061206896551724135
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05043103448275862
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08189655172413793
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.20474137931034483
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.30603448275862066
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5043103448275862
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.25554093803691474
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1807856116584566
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.20657861277416045
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08405172413793104
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.20043103448275862
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3146551724137931
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.49137931034482757
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08405172413793104
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0668103448275862
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06293103448275862
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04913793103448275
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08405172413793104
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.20043103448275862
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3146551724137931
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.49137931034482757
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2516576518560222
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1794651409414343
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.20584710715396837
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.07974137931034483
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2025862068965517
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3017241379310345
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4956896551724138
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.07974137931034483
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.06752873563218391
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.0603448275862069
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04956896551724138
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.07974137931034483
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2025862068965517
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3017241379310345
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4956896551724138
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2527082338557514
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.17959085933223878
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2058214047481906
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-m3
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-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:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+  (2): Normalize()
+)
+```
+
+## 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/sitgrsBAAIbge-m3-290824")
+# Run inference
+sentences = [
+    'Les entitats inscrites en el Registre resten obligades a comunicar a l’Ajuntament qualsevol modificació en les seves dades registrals, podent sol·licitar la seva cancel·lació o comunicant la seva dissolució.',
+    "Quin és el procediment per cancel·lar la inscripció d'una entitat al Registre municipal d'entitats?",
+    'Quin és el paper de les entitats de protecció dels animals en la gestió de les colònies urbanes felines?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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_1024`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0862     |
+| cosine_accuracy@3   | 0.2155     |
+| cosine_accuracy@5   | 0.3276     |
+| cosine_accuracy@10  | 0.5108     |
+| cosine_precision@1  | 0.0862     |
+| cosine_precision@3  | 0.0718     |
+| cosine_precision@5  | 0.0655     |
+| cosine_precision@10 | 0.0511     |
+| cosine_recall@1     | 0.0862     |
+| cosine_recall@3     | 0.2155     |
+| cosine_recall@5     | 0.3276     |
+| cosine_recall@10    | 0.5108     |
+| cosine_ndcg@10      | 0.264      |
+| cosine_mrr@10       | 0.1897     |
+| **cosine_map@100**  | **0.2151** |
+
+#### 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   | 0.0841     |
+| cosine_accuracy@3   | 0.2091     |
+| cosine_accuracy@5   | 0.319      |
+| cosine_accuracy@10  | 0.5        |
+| cosine_precision@1  | 0.0841     |
+| cosine_precision@3  | 0.0697     |
+| cosine_precision@5  | 0.0638     |
+| cosine_precision@10 | 0.05       |
+| cosine_recall@1     | 0.0841     |
+| cosine_recall@3     | 0.2091     |
+| cosine_recall@5     | 0.319      |
+| cosine_recall@10    | 0.5        |
+| cosine_ndcg@10      | 0.2595     |
+| cosine_mrr@10       | 0.1867     |
+| **cosine_map@100**  | **0.2132** |
+
+#### 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   | 0.0862     |
+| cosine_accuracy@3   | 0.2112     |
+| cosine_accuracy@5   | 0.3211     |
+| cosine_accuracy@10  | 0.5129     |
+| cosine_precision@1  | 0.0862     |
+| cosine_precision@3  | 0.0704     |
+| cosine_precision@5  | 0.0642     |
+| cosine_precision@10 | 0.0513     |
+| cosine_recall@1     | 0.0862     |
+| cosine_recall@3     | 0.2112     |
+| cosine_recall@5     | 0.3211     |
+| cosine_recall@10    | 0.5129     |
+| cosine_ndcg@10      | 0.2647     |
+| cosine_mrr@10       | 0.1899     |
+| **cosine_map@100**  | **0.2155** |
+
+#### 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   | 0.0819     |
+| cosine_accuracy@3   | 0.2047     |
+| cosine_accuracy@5   | 0.306      |
+| cosine_accuracy@10  | 0.5043     |
+| cosine_precision@1  | 0.0819     |
+| cosine_precision@3  | 0.0682     |
+| cosine_precision@5  | 0.0612     |
+| cosine_precision@10 | 0.0504     |
+| cosine_recall@1     | 0.0819     |
+| cosine_recall@3     | 0.2047     |
+| cosine_recall@5     | 0.306      |
+| cosine_recall@10    | 0.5043     |
+| cosine_ndcg@10      | 0.2555     |
+| cosine_mrr@10       | 0.1808     |
+| **cosine_map@100**  | **0.2066** |
+
+#### 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   | 0.0841     |
+| cosine_accuracy@3   | 0.2004     |
+| cosine_accuracy@5   | 0.3147     |
+| cosine_accuracy@10  | 0.4914     |
+| cosine_precision@1  | 0.0841     |
+| cosine_precision@3  | 0.0668     |
+| cosine_precision@5  | 0.0629     |
+| cosine_precision@10 | 0.0491     |
+| cosine_recall@1     | 0.0841     |
+| cosine_recall@3     | 0.2004     |
+| cosine_recall@5     | 0.3147     |
+| cosine_recall@10    | 0.4914     |
+| cosine_ndcg@10      | 0.2517     |
+| cosine_mrr@10       | 0.1795     |
+| **cosine_map@100**  | **0.2058** |
+
+#### 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   | 0.0797     |
+| cosine_accuracy@3   | 0.2026     |
+| cosine_accuracy@5   | 0.3017     |
+| cosine_accuracy@10  | 0.4957     |
+| cosine_precision@1  | 0.0797     |
+| cosine_precision@3  | 0.0675     |
+| cosine_precision@5  | 0.0603     |
+| cosine_precision@10 | 0.0496     |
+| cosine_recall@1     | 0.0797     |
+| cosine_recall@3     | 0.2026     |
+| cosine_recall@5     | 0.3017     |
+| cosine_recall@10    | 0.4957     |
+| cosine_ndcg@10      | 0.2527     |
+| cosine_mrr@10       | 0.1796     |
+| **cosine_map@100**  | **0.2058** |
+
+<!--
+## 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: 8 tokens</li><li>mean: 48.75 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 21.07 tokens</li><li>max: 47 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                           | anchor                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------|
+  | <code>Els ajuts per a la realització d'activitats en el lleure esportiu estan destinats a les entitats sense ànim de lucre que desenvolupen activitats esportives i de lleure.</code>                                                              | <code>Quins són els sectors que es beneficien dels ajuts?</code>                                                |
+  | <code>En el certificat s'indiquen les dades de planejament vigent, classificació del sòl, qualificació urbanística, condicions de l’edificació i usos admesos referides a una finca o solar concreta.</code>                                       | <code>Quin és el contingut de les condicions de l'edificació en el certificat d'aprofitament urbanístic?</code> |
+  | <code>Aportació de documentació. Ajuts per compensar la disminució d'ingressos de les empreses o establiments del sector de l'hosteleria i restauració afectats per les mesures adoptades per la situació de crisis provocada pel SARS-CoV2</code> | <code>Quin és el paper dels ajuts en la situació de crisis?</code>                                              |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `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`: 16
+- `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_1024_cosine_map@100 | 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      | 3.0594        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9808     | 16      | -             | 0.2047                  | 0.1922                 | 0.2020                 | 0.2016                 | 0.1774                | 0.2115                 |
+| 1.2261     | 20      | 1.525         | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.8391     | 30      | 0.7434        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9617     | 32      | -             | 0.2186                  | 0.2003                 | 0.2102                 | 0.2092                 | 0.1870                | 0.2101                 |
+| 2.4521     | 40      | 0.4451        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9425     | 48      | -             | 0.2083                  | 0.2054                 | 0.2091                 | 0.2118                 | 0.2009                | 0.2140                 |
+| 3.0651     | 50      | 0.2518        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.6782     | 60      | 0.1801        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9847     | 65      | -             | 0.2135                  | 0.2071                 | 0.2037                 | 0.2115                 | 0.2030                | 0.2191                 |
+| 4.2912     | 70      | 0.1483        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.9042     | 80      | 0.0893        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.9655     | 81      | -             | 0.2066                  | 0.2053                 | 0.2057                 | 0.2137                 | 0.1982                | 0.2176                 |
+| 5.5172     | 90      | 0.0748        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 5.9464     | 97      | -             | 0.2171                  | 0.2113                 | 0.2086                 | 0.2178                 | 0.2120                | 0.2193                 |
+| 6.1303     | 100     | 0.064         | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.7433     | 110     | 0.0458        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 6.9885     | 114     | -             | 0.2294                  | 0.2132                 | 0.2151                 | 0.2227                 | 0.2054                | 0.2138                 |
+| 7.3563     | 120     | 0.0436        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 7.9693     | 130     | 0.0241        | 0.2133                  | 0.2083                 | 0.2096                 | 0.2138                 | 0.2080                | 0.2124                 |
+| 8.5824     | 140     | 0.021         | -                       | -                      | -                      | -                      | -                     | -                      |
+| **8.9502** | **146** | **-**         | **0.216**               | **0.2074**             | **0.2081**             | **0.2162**             | **0.2094**            | **0.2177**             |
+| 9.1954     | 150     | 0.0237        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 9.8084     | 160     | 0.0145        | 0.2151                  | 0.2058                 | 0.2066                 | 0.2155                 | 0.2058                | 0.2132                 |
+
+* 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 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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 sha256:133bdb11af88bb24c05ec94a7c4cdfae2a36f1eaa5822250faee340896351749
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}