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": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,780 @@
+---
+base_model: projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base
+datasets: []
+language:
+- ca
+library_name: sentence-transformers
+license: apache-2.0
+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: 'Queixa: Deixar constància de la vostra disconformitat per un mal
+    servei (un tracte inapropiat, un temps d''espera excessiu, etc.), sense demanar
+    cap indemnització.'
+  sentences:
+  - Quin és el format de sortida del tràmit de baixa de la llicència de gual?
+  - Quin és el tipus de venda que es realitza en els mercats setmanals?
+  - Quin és el paper de la queixa en la resolució de conflictes?
+- source_sentence: L'empleat que en l'exercici de les seves tasques tingui assignada
+    la funció de conducció de vehicles municipals, pot sol·licitar un ajut per les
+    despeses ocasionades per a la renovació del carnet de conduir (certificat mèdic
+    i administratiu).
+  sentences:
+  - Quin és el resultat esperat de les escoles que reben les subvencions?
+  - Quin és el requisit per obtenir una autorització d'estacionament?
+  - Quin és el requisit per a sol·licitar l'ajut social?
+- source_sentence: Aportació de documentació. Subvencions per finançar despeses d'hipoteca,
+    subministrament i altres serveis i la manca d'ingressos de lloguer de les entitats
+    culturals
+  sentences:
+  - Quin és el propòsit de la documentació?
+  - Quin és el paper del públic assistent en el Ple Municipal?
+  - Quin és el paper de l'ajuntament en la renovació del carnet de persona cuidadora?
+- source_sentence: la Fira de la Vila del Llibre de Sitges consistent en un conjunt
+    de parades instal·lades al Passeig Marítim
+  sentences:
+  - Quin és el paper de la llicència de parcel·lació en la construcció d'edificacions?
+  - Quin és l'objectiu del tràmit de participació en processos de selecció de personal
+    de l'Ajuntament?
+  - Quin és el lloc on es desenvolupa la Fira de la Vila del Llibre de Sitges?
+- source_sentence: Mitjançant aquest tràmit la persona interessada posa en coneixement
+    de l'Ajuntament de Sitges l'inici d'un espectacle públic o activitat recreativa
+    de caràcter extraordinari...
+  sentences:
+  - Quin és el paper de la persona interessada en la llicència per a espectacles públics
+    o activitats recreatives de caràcter extraordinari?
+  - Quin és el paper del Registre de Sol·licitants d'Habitatge amb Protecció Oficial
+    en la gestió d'habitatges?
+  - Quin és el tipus de familiars que es tenen en compte per l'ajut especial?
+model-index:
+- name: BGE SITGES  CAT
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.07327586206896551
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.15732758620689655
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21767241379310345
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.39439655172413796
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.07327586206896551
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.05244252873563218
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.043534482758620686
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03943965517241379
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.07327586206896551
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.15732758620689655
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.21767241379310345
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.39439655172413796
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.20125893142070614
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.14385604816639316
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.17098930660026063
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.07327586206896551
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.15086206896551724
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21767241379310345
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.39439655172413796
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.07327586206896551
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.050287356321839075
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.04353448275862069
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03943965517241379
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.07327586206896551
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.15086206896551724
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.21767241379310345
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.39439655172413796
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2016207682773376
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.14438799945265474
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1715919733142084
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.07327586206896551
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.14870689655172414
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21120689655172414
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.40086206896551724
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.07327586206896551
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04956896551724138
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.04224137931034483
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04008620689655173
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.07327586206896551
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.14870689655172414
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.21120689655172414
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.40086206896551724
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2021149795452301
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1433856732348113
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.16973847535400444
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.06896551724137931
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.14655172413793102
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21767241379310345
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.38146551724137934
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.06896551724137931
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.048850574712643674
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.04353448275862069
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03814655172413793
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.06896551724137931
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.14655172413793102
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.21767241379310345
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.38146551724137934
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.19535554125135882
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1398416119321293
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.16597320243564267
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.05603448275862069
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.13793103448275862
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.1939655172413793
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.36853448275862066
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.05603448275862069
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04597701149425287
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03879310344827586
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03685344827586207
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.05603448275862069
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.13793103448275862
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.1939655172413793
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.36853448275862066
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.18225870966588442
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.12688492063492074
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.15425908300208627
+      name: Cosine Map@100
+---
+
+# BGE SITGES  CAT
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base](https://huggingface.co/projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base](https://huggingface.co/projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base) <!-- at revision 3354aea2cb9d91091495e9f1e1241b488f32e47c -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** ca
+- **License:** apache-2.0
+
+### 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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("adriansanz/SITGES-aina4_moreseq")
+# Run inference
+sentences = [
+    "Mitjançant aquest tràmit la persona interessada posa en coneixement de l'Ajuntament de Sitges l'inici d'un espectacle públic o activitat recreativa de caràcter extraordinari...",
+    'Quin és el paper de la persona interessada en la llicència per a espectacles públics o activitats recreatives de caràcter extraordinari?',
+    "Quin és el paper del Registre de Sol·licitants d'Habitatge amb Protecció Oficial en la gestió d'habitatges?",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.0733    |
+| cosine_accuracy@3   | 0.1573    |
+| cosine_accuracy@5   | 0.2177    |
+| cosine_accuracy@10  | 0.3944    |
+| cosine_precision@1  | 0.0733    |
+| cosine_precision@3  | 0.0524    |
+| cosine_precision@5  | 0.0435    |
+| cosine_precision@10 | 0.0394    |
+| cosine_recall@1     | 0.0733    |
+| cosine_recall@3     | 0.1573    |
+| cosine_recall@5     | 0.2177    |
+| cosine_recall@10    | 0.3944    |
+| cosine_ndcg@10      | 0.2013    |
+| cosine_mrr@10       | 0.1439    |
+| **cosine_map@100**  | **0.171** |
+
+#### 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   | 0.0733     |
+| cosine_accuracy@3   | 0.1509     |
+| cosine_accuracy@5   | 0.2177     |
+| cosine_accuracy@10  | 0.3944     |
+| cosine_precision@1  | 0.0733     |
+| cosine_precision@3  | 0.0503     |
+| cosine_precision@5  | 0.0435     |
+| cosine_precision@10 | 0.0394     |
+| cosine_recall@1     | 0.0733     |
+| cosine_recall@3     | 0.1509     |
+| cosine_recall@5     | 0.2177     |
+| cosine_recall@10    | 0.3944     |
+| cosine_ndcg@10      | 0.2016     |
+| cosine_mrr@10       | 0.1444     |
+| **cosine_map@100**  | **0.1716** |
+
+#### 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   | 0.0733     |
+| cosine_accuracy@3   | 0.1487     |
+| cosine_accuracy@5   | 0.2112     |
+| cosine_accuracy@10  | 0.4009     |
+| cosine_precision@1  | 0.0733     |
+| cosine_precision@3  | 0.0496     |
+| cosine_precision@5  | 0.0422     |
+| cosine_precision@10 | 0.0401     |
+| cosine_recall@1     | 0.0733     |
+| cosine_recall@3     | 0.1487     |
+| cosine_recall@5     | 0.2112     |
+| cosine_recall@10    | 0.4009     |
+| cosine_ndcg@10      | 0.2021     |
+| cosine_mrr@10       | 0.1434     |
+| **cosine_map@100**  | **0.1697** |
+
+#### 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   | 0.069     |
+| cosine_accuracy@3   | 0.1466    |
+| cosine_accuracy@5   | 0.2177    |
+| cosine_accuracy@10  | 0.3815    |
+| cosine_precision@1  | 0.069     |
+| cosine_precision@3  | 0.0489    |
+| cosine_precision@5  | 0.0435    |
+| cosine_precision@10 | 0.0381    |
+| cosine_recall@1     | 0.069     |
+| cosine_recall@3     | 0.1466    |
+| cosine_recall@5     | 0.2177    |
+| cosine_recall@10    | 0.3815    |
+| cosine_ndcg@10      | 0.1954    |
+| cosine_mrr@10       | 0.1398    |
+| **cosine_map@100**  | **0.166** |
+
+#### 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   | 0.056      |
+| cosine_accuracy@3   | 0.1379     |
+| cosine_accuracy@5   | 0.194      |
+| cosine_accuracy@10  | 0.3685     |
+| cosine_precision@1  | 0.056      |
+| cosine_precision@3  | 0.046      |
+| cosine_precision@5  | 0.0388     |
+| cosine_precision@10 | 0.0369     |
+| cosine_recall@1     | 0.056      |
+| cosine_recall@3     | 0.1379     |
+| cosine_recall@5     | 0.194      |
+| cosine_recall@10    | 0.3685     |
+| cosine_ndcg@10      | 0.1823     |
+| cosine_mrr@10       | 0.1269     |
+| **cosine_map@100**  | **0.1543** |
+
+<!--
+## 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 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`: 6
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `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`: 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`: 6
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `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 | loss       | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.3065     | 5      | 3.3947        | -          | -                      | -                      | -                      | -                     | -                      |
+| 0.6130     | 10     | 2.6401        | -          | -                      | -                      | -                      | -                     | -                      |
+| 0.9195     | 15     | 2.0152        | -          | -                      | -                      | -                      | -                     | -                      |
+| 0.9808     | 16     | -             | 1.3404     | 0.1639                 | 0.1577                 | 0.1694                 | 0.1503                | 0.1638                 |
+| 1.2261     | 20     | 1.4542        | -          | -                      | -                      | -                      | -                     | -                      |
+| 1.5326     | 25     | 1.0135        | -          | -                      | -                      | -                      | -                     | -                      |
+| 1.8391     | 30     | 0.8437        | -          | -                      | -                      | -                      | -                     | -                      |
+| 1.9617     | 32     | -             | 0.9436     | 0.1556                 | 0.1596                 | 0.1600                 | 0.1467                | 0.1701                 |
+| 2.1456     | 35     | 0.7676        | -          | -                      | -                      | -                      | -                     | -                      |
+| 2.4521     | 40     | 0.5126        | -          | -                      | -                      | -                      | -                     | -                      |
+| 2.7586     | 45     | 0.4358        | -          | -                      | -                      | -                      | -                     | -                      |
+| 2.9425     | 48     | -             | 0.7852     | 0.1650                 | 0.1693                 | 0.1720                 | 0.1511                | 0.1686                 |
+| 3.0651     | 50     | 0.4192        | -          | -                      | -                      | -                      | -                     | -                      |
+| 3.3716     | 55     | 0.3429        | -          | -                      | -                      | -                      | -                     | -                      |
+| 3.6782     | 60     | 0.3025        | -          | -                      | -                      | -                      | -                     | -                      |
+| 3.9847     | 65     | 0.2863        | 0.7401     | 0.1646                 | 0.1706                 | 0.1759                 | 0.1480                | 0.1694                 |
+| 4.2912     | 70     | 0.2474        | -          | -                      | -                      | -                      | -                     | -                      |
+| 4.5977     | 75     | 0.2324        | -          | -                      | -                      | -                      | -                     | -                      |
+| 4.9042     | 80     | 0.2344        | -          | -                      | -                      | -                      | -                     | -                      |
+| 4.9655     | 81     | -             | 0.7217     | 0.1663                 | 0.1699                 | 0.1767                 | 0.1512                | 0.1696                 |
+| 5.2107     | 85     | 0.2181        | -          | -                      | -                      | -                      | -                     | -                      |
+| 5.5172     | 90     | 0.2116        | -          | -                      | -                      | -                      | -                     | -                      |
+| 5.8238     | 95     | 0.1926        | -          | -                      | -                      | -                      | -                     | -                      |
+| **5.8851** | **96** | **-**         | **0.7154** | **0.166**              | **0.1697**             | **0.1716**             | **0.1543**            | **0.171**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.3
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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 +1,29 @@
+{
+  "_name_or_path": "projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "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": "4.42.3",
+    "pytorch": "2.3.1+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:d18300c25bcad837b5089ca8624e6ec65272c661e8c7de98354fa506f11547a6
+size 1112197096

modules.json

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

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "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:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}