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 +1,881 @@
+---
+base_model: BAAI/bge-m3
+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:4091
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Aquest tràmit permet formalitzar la matrícula a les llars d’infants
+    municipals, si l'infant ha estat admès al període de preinscripcions.
+  sentences:
+  - Quin és el tràmit que es realitza abans de la matrícula?
+  - Quin és el propòsit de l'Ajuntament en aquest tràmit?
+  - Què es pot fer amb les exclusions indegudes al Cens Electoral?
+- source_sentence: També cal que facis aquest tràmit per revocar o modificar les dades
+    de correu electrònic i/o telèfon mòbil facilitades per portar a terme les notificacions.
+  sentences:
+  - Què passa si vull canviar la meva adreça de correu electrònic?
+  - Quin és el resultat de no comunicar la finalització de les obres en el termini
+    establert?
+  - Quin és el procés de selecció de personal de l'Ajuntament de Viladecavalls?
+- source_sentence: Aquest tràmit et permet comunicar a l'ajuntament de Viladecavalls,
+    l'actuació en representació fer efectuar un tràmit, d'acord a l'article 5 de la
+    Llei 39/2015,d'1 d'octubre, del Procediment Administratiu Comú de les Administracions
+    Públiques.
+  sentences:
+  - Quin és el registre que es relaciona amb les dades que es modifiquen?
+  - Quan es pot consultar la llista definitiva d'admessos?
+  - Quin és el paper de fer efectuar un tràmit en representació a tercers?
+- source_sentence: La taxa per la prestació del Servei de Gestió dels Residus Municipals.
+  sentences:
+  - Quins són els motius per inscriure's al Servei Local d'Ocupació?
+  - Quin és el document que es necessita per a la sol·licitud de volants col·lectius
+    o de convivència?
+  - Quin és el paper de la taxa d'escombraries en aquest procés?
+- source_sentence: S'ha de comunicar la realització de focs d’esbarjo i qualsevol
+    mena de crema de vegetació agrària en microexplotacions o petites explotacions
+    agràries...
+  sentences:
+  - Què cal fer si no has rebut el document per pagar IVTM o IBI?
+  - Quin és el tipus de explotacions agràries que estan subjectes a la comunicació
+    de focs d'esbarjo o cremes de vegetació agrària en microexplotacions?
+  - Quin és el paper de les bases de la convocatòria en la sol·licitud de subvenció?
+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: 0.12408759124087591
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.22627737226277372
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3357664233576642
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5328467153284672
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.12408759124087591
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0754257907542579
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06715328467153285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05328467153284672
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12408759124087591
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.22627737226277372
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3357664233576642
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5328467153284672
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.28998901896488977
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21748928281774996
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.24037395859471752
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1386861313868613
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.26277372262773724
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3357664233576642
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5693430656934306
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1386861313868613
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08759124087591241
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06715328467153284
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05693430656934306
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1386861313868613
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.26277372262773724
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3357664233576642
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5693430656934306
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.31363827421519996
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23752751708956085
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2568041111732728
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.1386861313868613
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.27007299270072993
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3795620437956204
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5693430656934306
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.1386861313868613
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0900243309002433
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.07591240875912408
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05693430656934306
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.1386861313868613
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.27007299270072993
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3795620437956204
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5693430656934306
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.317041085199572
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.24058046576294745
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2615607719139071
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12408759124087591
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2773722627737226
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.32116788321167883
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5182481751824818
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.12408759124087591
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.09245742092457421
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06423357664233577
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.051824817518248176
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12408759124087591
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2773722627737226
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.32116788321167883
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5182481751824818
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.29042019634687105
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2218456725755996
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.24399596123266679
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.10948905109489052
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.25547445255474455
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.40145985401459855
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5401459854014599
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.10948905109489052
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08515815085158149
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08029197080291971
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05401459854014598
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.10948905109489052
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.25547445255474455
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.40145985401459855
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5401459854014599
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2983398214582463
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.22380952380952376
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2454078859030295
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.10948905109489052
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.20437956204379562
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3284671532846715
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.5547445255474452
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.10948905109489052
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.06812652068126519
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06569343065693431
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.05547445255474452
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.10948905109489052
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.20437956204379562
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3284671532846715
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.5547445255474452
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.28965339873789575
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.21023635731664925
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.22988556376565739
+      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) on the json dataset. 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:**
+    - json
+<!-- - **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/ST-tramits-VL-001-5ep")
+# Run inference
+sentences = [
+    "S'ha de comunicar la realització de focs d’esbarjo i qualsevol mena de crema de vegetació agrària en microexplotacions o petites explotacions agràries...",
+    "Quin és el tipus de explotacions agràries que estan subjectes a la comunicació de focs d'esbarjo o cremes de vegetació agrària en microexplotacions?",
+    'Quin és el paper de les bases de la convocatòria en la sol·licitud de subvenció?',
+]
+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   | 0.1241     |
+| cosine_accuracy@3   | 0.2263     |
+| cosine_accuracy@5   | 0.3358     |
+| cosine_accuracy@10  | 0.5328     |
+| cosine_precision@1  | 0.1241     |
+| cosine_precision@3  | 0.0754     |
+| cosine_precision@5  | 0.0672     |
+| cosine_precision@10 | 0.0533     |
+| cosine_recall@1     | 0.1241     |
+| cosine_recall@3     | 0.2263     |
+| cosine_recall@5     | 0.3358     |
+| cosine_recall@10    | 0.5328     |
+| cosine_ndcg@10      | 0.29       |
+| cosine_mrr@10       | 0.2175     |
+| **cosine_map@100**  | **0.2404** |
+
+#### 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   | 0.1387     |
+| cosine_accuracy@3   | 0.2628     |
+| cosine_accuracy@5   | 0.3358     |
+| cosine_accuracy@10  | 0.5693     |
+| cosine_precision@1  | 0.1387     |
+| cosine_precision@3  | 0.0876     |
+| cosine_precision@5  | 0.0672     |
+| cosine_precision@10 | 0.0569     |
+| cosine_recall@1     | 0.1387     |
+| cosine_recall@3     | 0.2628     |
+| cosine_recall@5     | 0.3358     |
+| cosine_recall@10    | 0.5693     |
+| cosine_ndcg@10      | 0.3136     |
+| cosine_mrr@10       | 0.2375     |
+| **cosine_map@100**  | **0.2568** |
+
+#### 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   | 0.1387     |
+| cosine_accuracy@3   | 0.2701     |
+| cosine_accuracy@5   | 0.3796     |
+| cosine_accuracy@10  | 0.5693     |
+| cosine_precision@1  | 0.1387     |
+| cosine_precision@3  | 0.09       |
+| cosine_precision@5  | 0.0759     |
+| cosine_precision@10 | 0.0569     |
+| cosine_recall@1     | 0.1387     |
+| cosine_recall@3     | 0.2701     |
+| cosine_recall@5     | 0.3796     |
+| cosine_recall@10    | 0.5693     |
+| cosine_ndcg@10      | 0.317      |
+| cosine_mrr@10       | 0.2406     |
+| **cosine_map@100**  | **0.2616** |
+
+#### 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   | 0.1241    |
+| cosine_accuracy@3   | 0.2774    |
+| cosine_accuracy@5   | 0.3212    |
+| cosine_accuracy@10  | 0.5182    |
+| cosine_precision@1  | 0.1241    |
+| cosine_precision@3  | 0.0925    |
+| cosine_precision@5  | 0.0642    |
+| cosine_precision@10 | 0.0518    |
+| cosine_recall@1     | 0.1241    |
+| cosine_recall@3     | 0.2774    |
+| cosine_recall@5     | 0.3212    |
+| cosine_recall@10    | 0.5182    |
+| cosine_ndcg@10      | 0.2904    |
+| cosine_mrr@10       | 0.2218    |
+| **cosine_map@100**  | **0.244** |
+
+#### 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   | 0.1095     |
+| cosine_accuracy@3   | 0.2555     |
+| cosine_accuracy@5   | 0.4015     |
+| cosine_accuracy@10  | 0.5401     |
+| cosine_precision@1  | 0.1095     |
+| cosine_precision@3  | 0.0852     |
+| cosine_precision@5  | 0.0803     |
+| cosine_precision@10 | 0.054      |
+| cosine_recall@1     | 0.1095     |
+| cosine_recall@3     | 0.2555     |
+| cosine_recall@5     | 0.4015     |
+| cosine_recall@10    | 0.5401     |
+| cosine_ndcg@10      | 0.2983     |
+| cosine_mrr@10       | 0.2238     |
+| **cosine_map@100**  | **0.2454** |
+
+#### 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   | 0.1095     |
+| cosine_accuracy@3   | 0.2044     |
+| cosine_accuracy@5   | 0.3285     |
+| cosine_accuracy@10  | 0.5547     |
+| cosine_precision@1  | 0.1095     |
+| cosine_precision@3  | 0.0681     |
+| cosine_precision@5  | 0.0657     |
+| cosine_precision@10 | 0.0555     |
+| cosine_recall@1     | 0.1095     |
+| cosine_recall@3     | 0.2044     |
+| cosine_recall@5     | 0.3285     |
+| cosine_recall@10    | 0.5547     |
+| cosine_ndcg@10      | 0.2897     |
+| cosine_mrr@10       | 0.2102     |
+| **cosine_map@100**  | **0.2299** |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 4,091 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: 6 tokens</li><li>mean: 39.34 tokens</li><li>max: 164 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 20.77 tokens</li><li>max: 49 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                               | anchor                                                                                                               |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------|
+  | <code>Posteriorment a l’obtenció de l’informe favorable, caldrà realitzar l’acte de comprovació en matèria d’incendis i procedir a efectuar la comunicació prèvia corresponent.</code> | <code>Quin és el resultat esperat després d'obtenir l'informe previ en matèria d'incendis?</code>                    |
+  | <code>El certificat tècnic és un requisit per a l'exercici d'una activitat econòmica innòcua.</code>                                                                                   | <code>Quin és el paper del certificat tècnic en la Declaració responsable d'obertura?</code>                         |
+  | <code>El document necessari per realitzar l'autoliquidació de taxa per llicència de primera ocupació és la llicència de primera ocupació de l'immoble.</code>                          | <code>Quin és el document necessari per realitzar l'autoliquidació de taxa per llicència de primera ocupació?</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
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.2
+- `bf16`: True
+- `tf32`: True
+- `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
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: 5
+- `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`: True
+- `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
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_1024_cosine_map@100 | dim_768_cosine_map@100 | dim_512_cosine_map@100 | dim_256_cosine_map@100 | dim_128_cosine_map@100 | dim_64_cosine_map@100 |
+|:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.625      | 10     | 4.3533        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.0        | 16     | -             | 0.2076                  | 0.2123                 | 0.2055                 | 0.1996                 | 0.2188                 | 0.1861                |
+| 1.2461     | 20     | 2.4149        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.8711     | 30     | 1.1968        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.9961     | 32     | -             | 0.2056                  | 0.2318                 | 0.2363                 | 0.1932                 | 0.2330                 | 0.2255                |
+| 2.4922     | 40     | 0.7983        | -                       | -                      | -                      | -                      | -                      | -                     |
+| **2.9922** | **48** | **-**         | **0.2322**              | **0.2512**             | **0.2514**             | **0.2385**             | **0.2437**             | **0.2489**            |
+| 3.1133     | 50     | 0.4869        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.7383     | 60     | 0.3793        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.9883     | 64     | -             | 0.2414                  | 0.2364                 | 0.2365                 | 0.2244                 | 0.2167                 | 0.2190                |
+| 4.3594     | 70     | 0.3421        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 4.9844     | 80     | 0.2925        | 0.2404                  | 0.2568                 | 0.2616                 | 0.2440                 | 0.2454                 | 0.2299                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.44.2
+- PyTorch: 2.5.0+cu121
+- Accelerate: 1.1.0.dev0
+- Datasets: 3.1.0
+- 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": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.5.0+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:a8a3bf5134171f5555c620b509eb73a811fb99eb17130d793bdeeea802fde0bc
+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>"
+}