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 +1,886 @@
+---
+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:5750
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: El seu objecte és que -prèviament a la seva execució material-
+    l'Ajuntament comprovi l'adequació de l'actuació a la normativa i planejament,
+    així com a les ordenances municipals.
+  sentences:
+  - Quin és el paper de la normativa en la llicència de tala de masses arbòries?
+  - Com puc actualitzar les meves dades de naixement al Padró?
+  - Quin és el paper de la persona tècnica competent en la llicència per a la primera
+    utilització i ocupació parcial de l'edifici?
+- source_sentence: El seu objecte és que -prèviament a la seva execució material-
+    l'Ajuntament comprovi l'adequació de l’actuació a la normativa i planejament,
+    així com a les ordenances municipals sobre l’ús del sòl i edificació.
+  sentences:
+  - Quin és el propòsit del tràmit CA05?
+  - Quin és el propòsit del tràmit de llicència d'instal·lació de producció d'energia
+    elèctrica?
+  - Quin és el paper de l'Ajuntament de Sant Quirze del Vallès en la notificació electrònica
+    de procediments?
+- source_sentence: 'PROFESSIONALS: Assistència jurídica, traducció/interpretació,
+    psicologia, o qualsevol professió o habilitat que vulgueu posar a disposició del
+    banc de recursos.'
+  sentences:
+  - Quin és el propòsit del tràmit de comunicació prèvia d'obertura d'activitat de
+    baix risc?
+  - Quin és el tipus d’autorització que es necessita per a talls de carrers?
+  - Quin és el paper dels professionals en el banc de recursos?
+- source_sentence: No està especificat
+  sentences:
+  - Quin és el percentatge de bonificació per a una família nombrosa amb 3 membres
+    i una renda màxima anual bruta de 25.815,45 euros?
+  - Quin és el propòsit del tràmit de baixa del Padró d'Habitants per defunció?
+  - Quin és el procediment per a cancel·lar les concessions de drets funeraris de
+    nínxols?
+- source_sentence: 'Import En cas de renovació per caducitat, pèrdua, sostracció o
+    deteriorament: 12,00 € (en metàl·lic i preferiblement import exacte).'
+  sentences:
+  - Quin és el procediment per a la renovació del DNI en cas de sostracció?
+  - Quin és el paper del motiu legítim en l'oposició de dades personals en cas de
+    motiu legítim i situació personal concreta?
+  - Vull fer una activitat a l'espai públic, quin és el tràmit que debo seguir?
+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: 0.0406885758998435
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.11737089201877934
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18153364632237873
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3302034428794992
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0406885758998435
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03912363067292644
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03630672926447575
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03302034428794992
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0406885758998435
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.11737089201877934
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18153364632237873
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3302034428794992
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15804646538595332
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10652433117221861
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12794271910761573
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.03912363067292645
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.107981220657277
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18153364632237873
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3286384976525822
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.03912363067292645
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03599374021909233
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03630672926447575
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03286384976525822
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.03912363067292645
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.107981220657277
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18153364632237873
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3286384976525822
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15506867908727437
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10328203790645119
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12470788174358402
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0406885758998435
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.10172143974960876
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.16588419405320814
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3223787167449139
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0406885758998435
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.033907146583202916
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03317683881064163
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03223787167449139
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0406885758998435
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.10172143974960876
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.16588419405320814
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3223787167449139
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15172399342641055
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1010190774275283
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12301092660478197
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.04225352112676056
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.10954616588419405
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.18466353677621283
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3270735524256651
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.04225352112676056
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03651538862806468
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03693270735524257
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03270735524256651
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.04225352112676056
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.10954616588419405
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.18466353677621283
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3270735524256651
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15644008525556197
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10541458628313109
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1273528705075161
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0406885758998435
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.11267605633802817
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17996870109546165
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3145539906103286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0406885758998435
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03755868544600939
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03599374021909233
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03145539906103287
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0406885758998435
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.11267605633802817
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17996870109546165
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3145539906103286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15177339619789426
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.10291936806021326
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12605282457123526
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0406885758998435
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.09859154929577464
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1596244131455399
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.29107981220657275
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0406885758998435
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.03286384976525822
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03192488262910798
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.02910798122065728
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0406885758998435
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.09859154929577464
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1596244131455399
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.29107981220657275
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.14046451788883374
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.09552562287304085
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.11941800675417487
+      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/sqv-5ep")
+# Run inference
+sentences = [
+    'Import En cas de renovació per caducitat, pèrdua, sostracció o deteriorament: 12,00 € (en metàl·lic i preferiblement import exacte).',
+    'Quin és el procediment per a la renovació del DNI en cas de sostracció?',
+    "Quin és el paper del motiu legítim en l'oposició de dades personals en cas de motiu legítim i situació personal concreta?",
+]
+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   | 0.0407     |
+| cosine_accuracy@3   | 0.1174     |
+| cosine_accuracy@5   | 0.1815     |
+| cosine_accuracy@10  | 0.3302     |
+| cosine_precision@1  | 0.0407     |
+| cosine_precision@3  | 0.0391     |
+| cosine_precision@5  | 0.0363     |
+| cosine_precision@10 | 0.033      |
+| cosine_recall@1     | 0.0407     |
+| cosine_recall@3     | 0.1174     |
+| cosine_recall@5     | 0.1815     |
+| cosine_recall@10    | 0.3302     |
+| cosine_ndcg@10      | 0.158      |
+| cosine_mrr@10       | 0.1065     |
+| **cosine_map@100**  | **0.1279** |
+
+#### 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   | 0.0391     |
+| cosine_accuracy@3   | 0.108      |
+| cosine_accuracy@5   | 0.1815     |
+| cosine_accuracy@10  | 0.3286     |
+| cosine_precision@1  | 0.0391     |
+| cosine_precision@3  | 0.036      |
+| cosine_precision@5  | 0.0363     |
+| cosine_precision@10 | 0.0329     |
+| cosine_recall@1     | 0.0391     |
+| cosine_recall@3     | 0.108      |
+| cosine_recall@5     | 0.1815     |
+| cosine_recall@10    | 0.3286     |
+| cosine_ndcg@10      | 0.1551     |
+| cosine_mrr@10       | 0.1033     |
+| **cosine_map@100**  | **0.1247** |
+
+#### 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   | 0.0407    |
+| cosine_accuracy@3   | 0.1017    |
+| cosine_accuracy@5   | 0.1659    |
+| cosine_accuracy@10  | 0.3224    |
+| cosine_precision@1  | 0.0407    |
+| cosine_precision@3  | 0.0339    |
+| cosine_precision@5  | 0.0332    |
+| cosine_precision@10 | 0.0322    |
+| cosine_recall@1     | 0.0407    |
+| cosine_recall@3     | 0.1017    |
+| cosine_recall@5     | 0.1659    |
+| cosine_recall@10    | 0.3224    |
+| cosine_ndcg@10      | 0.1517    |
+| cosine_mrr@10       | 0.101     |
+| **cosine_map@100**  | **0.123** |
+
+#### 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   | 0.0423     |
+| cosine_accuracy@3   | 0.1095     |
+| cosine_accuracy@5   | 0.1847     |
+| cosine_accuracy@10  | 0.3271     |
+| cosine_precision@1  | 0.0423     |
+| cosine_precision@3  | 0.0365     |
+| cosine_precision@5  | 0.0369     |
+| cosine_precision@10 | 0.0327     |
+| cosine_recall@1     | 0.0423     |
+| cosine_recall@3     | 0.1095     |
+| cosine_recall@5     | 0.1847     |
+| cosine_recall@10    | 0.3271     |
+| cosine_ndcg@10      | 0.1564     |
+| cosine_mrr@10       | 0.1054     |
+| **cosine_map@100**  | **0.1274** |
+
+#### 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   | 0.0407     |
+| cosine_accuracy@3   | 0.1127     |
+| cosine_accuracy@5   | 0.18       |
+| cosine_accuracy@10  | 0.3146     |
+| cosine_precision@1  | 0.0407     |
+| cosine_precision@3  | 0.0376     |
+| cosine_precision@5  | 0.036      |
+| cosine_precision@10 | 0.0315     |
+| cosine_recall@1     | 0.0407     |
+| cosine_recall@3     | 0.1127     |
+| cosine_recall@5     | 0.18       |
+| cosine_recall@10    | 0.3146     |
+| cosine_ndcg@10      | 0.1518     |
+| cosine_mrr@10       | 0.1029     |
+| **cosine_map@100**  | **0.1261** |
+
+#### 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   | 0.0407     |
+| cosine_accuracy@3   | 0.0986     |
+| cosine_accuracy@5   | 0.1596     |
+| cosine_accuracy@10  | 0.2911     |
+| cosine_precision@1  | 0.0407     |
+| cosine_precision@3  | 0.0329     |
+| cosine_precision@5  | 0.0319     |
+| cosine_precision@10 | 0.0291     |
+| cosine_recall@1     | 0.0407     |
+| cosine_recall@3     | 0.0986     |
+| cosine_recall@5     | 0.1596     |
+| cosine_recall@10    | 0.2911     |
+| cosine_ndcg@10      | 0.1405     |
+| cosine_mrr@10       | 0.0955     |
+| **cosine_map@100**  | **0.1194** |
+
+<!--
+## 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: 5,750 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: 4 tokens</li><li>mean: 43.32 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 20.77 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                  | anchor                                                                                 |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|
+  | <code>Aquest tràmit permet donar d'alta ofertes de treball que es gestionaran pel Servei a l'Ocupació.</code>                                                                                                                                                                                             | <code>Com puc saber si el meu perfil és compatible amb les ofertes de treball?</code>  |
+  | <code>El titular de l’activitat ha de declarar sota la seva responsabilitat, que compleix els requisits establerts per la normativa vigent per a l’exercici de l’activitat, que disposa d’un certificat tècnic justificatiu i que es compromet a mantenir-ne el compliment durant el seu exercici.</code> | <code>Quin és el paper del titular de l'activitat en la Declaració responsable?</code> |
+  | <code>Aquest tipus de transmissió entre cedent i cessionari només podrà ser de caràcter gratuït i no condicionada.</code>                                                                                                                                                                                 | <code>Quin és el paper del cedent en la transmissió de drets funeraris?</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
+- `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
+- `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 |
+|:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.4444     | 10     | 4.5093        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.8889     | 20     | 2.7989        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 0.9778     | 22     | -             | 0.1072                  | 0.1182                 | 0.1122                 | 0.1083                 | 0.1044                | 0.1082                 |
+| 1.3333     | 30     | 1.8343        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.7778     | 40     | 1.5248        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.0        | 45     | -             | 0.1182                  | 0.1203                 | 0.1163                 | 0.1188                 | 0.1209                | 0.1229                 |
+| 2.2222     | 50     | 0.9624        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.6667     | 60     | 1.1161        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **2.9778** | **67** | **-**         | **0.1235**              | **0.1324**             | **0.1302**             | **0.1252**             | **0.1213**            | **0.1239**             |
+| 3.1111     | 70     | 0.7405        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.5556     | 80     | 0.8621        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.0        | 90     | 0.6071        | 0.1249                  | 0.1282                 | 0.1310                 | 0.1280                 | 0.1181                | 0.1278                 |
+| 4.4444     | 100    | 0.7091        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.8889     | 110    | 0.606         | 0.1279                  | 0.1261                 | 0.1274                 | 0.1230                 | 0.1194                | 0.1247                 |
+
+* 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: 0.35.0.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:f37cb58aa6246ea431dbd905e2aba4548e8fa2fb12c4fa4a556f418c647fa3e6
+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>"
+}