|
--- |
|
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:5175 |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: Caldrà executar l'obra comunicada prèviament d'acord amb les condicions |
|
específiques que es contenen en el model normalitzat CT02. |
|
sentences: |
|
- Quin és el propòsit de la instal·lació d'un circ sense animals a la via pública? |
|
- Quin és el destinatari de les dades bloquejades? |
|
- Quin és el format de presentació de la comunicació prèvia? |
|
- source_sentence: Armes utilitzables en activitats lúdico-esportives d’airsoft i |
|
paintball... |
|
sentences: |
|
- Quin és el paper de l'AFA en la venda de llibres? |
|
- Quin és el benefici de tenir dades personals correctes? |
|
- Quin és el tipus d'activitats que es poden practicar amb les armes de 4a categoria? |
|
- source_sentence: En les activitats sotmeses al règim d’autorització ambiental o |
|
llicència municipal d’activitat (Annex I o Annex II de la Llei 20/2009) cal demanar |
|
aquest certificat previ a la presentació de la sol·licitud d’autorització ambiental |
|
o llicència municipal. |
|
sentences: |
|
- Quin és el benefici de tenir el certificat de compatibilitat urbanística en les |
|
activitats sotmeses a llicència municipal d’activitat? |
|
- Com puc controlar la recepció de propaganda electoral per correu? |
|
- Quin és el benefici de la cessió d'un compostador domèstic per a l'entorn? |
|
- source_sentence: La persona interessada posa en coneixement de l’Administració, |
|
les actuacions urbanístiques que pretén dur a terme consistents en l'apuntalament |
|
o reforç provisional d'estructures existents fins a la intervenció definitiva. |
|
sentences: |
|
- Qui pot participar en el Consell d'Adolescents? |
|
- Quin és el resultat de la presentació de la comunicació prèvia? |
|
- Quin és el paper de la persona interessada en relació amb la presentació de la |
|
comunicació prèvia? |
|
- source_sentence: La persona consumidora presenti la reclamació davant de l'entitat |
|
acreditada en un termini superior a un any des de la data en què va presentar |
|
la reclamació a l'empresa. |
|
sentences: |
|
- Quin és el tràmit per inscriure'm al Padró d'Habitants sense tenir constància |
|
de la meva anterior residència? |
|
- Quin és el resultat de la modificació substancial de la llicència d'obres en relació |
|
a les autoritzacions administratives? |
|
- Quin és el paper de l'entitat acreditada en la tramitació d'una reclamació? |
|
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: 0.057391304347826085 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.15304347826086956 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.23478260869565218 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.41739130434782606 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.057391304347826085 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.051014492753623186 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.04695652173913043 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.04173913043478261 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.057391304347826085 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.15304347826086956 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.23478260869565218 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.41739130434782606 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.20551130934080394 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.14188060731539 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.16516795239083046 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.16 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.24 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.40695652173913044 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.05333333333333333 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.048 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.04069565217391305 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.16 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.24 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.40695652173913044 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.20158774447839253 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.13959282263630102 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.16377775492511307 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.06956521739130435 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.16695652173913045 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.24869565217391304 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.4260869565217391 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.06956521739130435 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.05565217391304348 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.04973913043478261 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.042608695652173914 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.06956521739130435 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.16695652173913045 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.24869565217391304 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.4260869565217391 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.21580306349457917 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.1526128364389235 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.1754746652296583 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.16695652173913045 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.25217391304347825 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.42434782608695654 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.05565217391304348 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.05043478260869566 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.042434782608695654 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.05565217391304348 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.16695652173913045 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.25217391304347825 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.42434782608695654 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.2100045076980214 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.14526432022084196 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.1684764968624273 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.1617391304347826 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.2608695652173913 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.4434782608695652 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.05391304347826087 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.05217391304347826 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.04434782608695652 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.1617391304347826 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.2608695652173913 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.4434782608695652 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.21805066438366894 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.15018150448585244 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.17220421856187046 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.15478260869565216 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.24521739130434783 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.42782608695652175 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.05159420289855072 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.04904347826086957 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.042782608695652175 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.06086956521739131 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.15478260869565216 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.24521739130434783 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.42782608695652175 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.21079002748958972 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.14568875086266406 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.16756200348857653 |
|
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/sqv-v4-10ep") |
|
# Run inference |
|
sentences = [ |
|
"La persona consumidora presenti la reclamació davant de l'entitat acreditada en un termini superior a un any des de la data en què va presentar la reclamació a l'empresa.", |
|
"Quin és el paper de l'entitat acreditada en la tramitació d'una reclamació?", |
|
"Quin és el resultat de la modificació substancial de la llicència d'obres en relació a les autoritzacions administratives?", |
|
] |
|
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 | 0.0574 | |
|
| cosine_accuracy@3 | 0.153 | |
|
| cosine_accuracy@5 | 0.2348 | |
|
| cosine_accuracy@10 | 0.4174 | |
|
| cosine_precision@1 | 0.0574 | |
|
| cosine_precision@3 | 0.051 | |
|
| cosine_precision@5 | 0.047 | |
|
| cosine_precision@10 | 0.0417 | |
|
| cosine_recall@1 | 0.0574 | |
|
| cosine_recall@3 | 0.153 | |
|
| cosine_recall@5 | 0.2348 | |
|
| cosine_recall@10 | 0.4174 | |
|
| cosine_ndcg@10 | 0.2055 | |
|
| cosine_mrr@10 | 0.1419 | |
|
| **cosine_map@100** | **0.1652** | |
|
|
|
#### 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 | 0.0557 | |
|
| cosine_accuracy@3 | 0.16 | |
|
| cosine_accuracy@5 | 0.24 | |
|
| cosine_accuracy@10 | 0.407 | |
|
| cosine_precision@1 | 0.0557 | |
|
| cosine_precision@3 | 0.0533 | |
|
| cosine_precision@5 | 0.048 | |
|
| cosine_precision@10 | 0.0407 | |
|
| cosine_recall@1 | 0.0557 | |
|
| cosine_recall@3 | 0.16 | |
|
| cosine_recall@5 | 0.24 | |
|
| cosine_recall@10 | 0.407 | |
|
| cosine_ndcg@10 | 0.2016 | |
|
| cosine_mrr@10 | 0.1396 | |
|
| **cosine_map@100** | **0.1638** | |
|
|
|
#### 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 | 0.0696 | |
|
| cosine_accuracy@3 | 0.167 | |
|
| cosine_accuracy@5 | 0.2487 | |
|
| cosine_accuracy@10 | 0.4261 | |
|
| cosine_precision@1 | 0.0696 | |
|
| cosine_precision@3 | 0.0557 | |
|
| cosine_precision@5 | 0.0497 | |
|
| cosine_precision@10 | 0.0426 | |
|
| cosine_recall@1 | 0.0696 | |
|
| cosine_recall@3 | 0.167 | |
|
| cosine_recall@5 | 0.2487 | |
|
| cosine_recall@10 | 0.4261 | |
|
| cosine_ndcg@10 | 0.2158 | |
|
| cosine_mrr@10 | 0.1526 | |
|
| **cosine_map@100** | **0.1755** | |
|
|
|
#### 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 | 0.0557 | |
|
| cosine_accuracy@3 | 0.167 | |
|
| cosine_accuracy@5 | 0.2522 | |
|
| cosine_accuracy@10 | 0.4243 | |
|
| cosine_precision@1 | 0.0557 | |
|
| cosine_precision@3 | 0.0557 | |
|
| cosine_precision@5 | 0.0504 | |
|
| cosine_precision@10 | 0.0424 | |
|
| cosine_recall@1 | 0.0557 | |
|
| cosine_recall@3 | 0.167 | |
|
| cosine_recall@5 | 0.2522 | |
|
| cosine_recall@10 | 0.4243 | |
|
| cosine_ndcg@10 | 0.21 | |
|
| cosine_mrr@10 | 0.1453 | |
|
| **cosine_map@100** | **0.1685** | |
|
|
|
#### 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 | 0.0609 | |
|
| cosine_accuracy@3 | 0.1617 | |
|
| cosine_accuracy@5 | 0.2609 | |
|
| cosine_accuracy@10 | 0.4435 | |
|
| cosine_precision@1 | 0.0609 | |
|
| cosine_precision@3 | 0.0539 | |
|
| cosine_precision@5 | 0.0522 | |
|
| cosine_precision@10 | 0.0443 | |
|
| cosine_recall@1 | 0.0609 | |
|
| cosine_recall@3 | 0.1617 | |
|
| cosine_recall@5 | 0.2609 | |
|
| cosine_recall@10 | 0.4435 | |
|
| cosine_ndcg@10 | 0.2181 | |
|
| cosine_mrr@10 | 0.1502 | |
|
| **cosine_map@100** | **0.1722** | |
|
|
|
#### 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 | 0.0609 | |
|
| cosine_accuracy@3 | 0.1548 | |
|
| cosine_accuracy@5 | 0.2452 | |
|
| cosine_accuracy@10 | 0.4278 | |
|
| cosine_precision@1 | 0.0609 | |
|
| cosine_precision@3 | 0.0516 | |
|
| cosine_precision@5 | 0.049 | |
|
| cosine_precision@10 | 0.0428 | |
|
| cosine_recall@1 | 0.0609 | |
|
| cosine_recall@3 | 0.1548 | |
|
| cosine_recall@5 | 0.2452 | |
|
| cosine_recall@10 | 0.4278 | |
|
| cosine_ndcg@10 | 0.2108 | |
|
| cosine_mrr@10 | 0.1457 | |
|
| **cosine_map@100** | **0.1676** | |
|
|
|
<!-- |
|
## 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: 5,175 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: 5 tokens</li><li>mean: 43.23 tokens</li><li>max: 117 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.25 tokens</li><li>max: 46 tokens</li></ul> | |
|
* Samples: |
|
| positive | anchor | |
|
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------| |
|
| <code>Aquest tràmit us permet consultar informació de les anotacions d'entrada i sortida que hi consten al registre de l'Ajuntament de Sant Quirze del Vallès.</code> | <code>Quin és el format de les dades de sortida del tràmit?</code> | |
|
| <code>Tràmit a través del qual la persona interessada posa en coneixement de l’Ajuntament la voluntat de: ... Renunciar a una llicència prèviament atorgada.</code> | <code>Quin és el resultat de la renúncia a una llicència urbanística prèviament atorgada?</code> | |
|
| <code>D’acord amb el plànol d'ubicació de parades: Mercat de diumenges a Les Fonts</code> | <code>Quin és el plànol d'ubicació de parades del mercat de diumenges a Les Fonts?</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`: 10 |
|
- `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`: 10 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: cosine |
|
- `lr_scheduler_kwargs`: {} |
|
- `warmup_ratio`: 0.2 |
|
- `warmup_steps`: 0 |
|
- `log_level`: passive |
|
- `log_level_replica`: warning |
|
- `log_on_each_node`: True |
|
- `logging_nan_inf_filter`: True |
|
- `save_safetensors`: True |
|
- `save_on_each_node`: False |
|
- `save_only_model`: False |
|
- `restore_callback_states_from_checkpoint`: False |
|
- `no_cuda`: False |
|
- `use_cpu`: False |
|
- `use_mps_device`: False |
|
- `seed`: 42 |
|
- `data_seed`: None |
|
- `jit_mode_eval`: False |
|
- `use_ipex`: False |
|
- `bf16`: True |
|
- `fp16`: False |
|
- `fp16_opt_level`: O1 |
|
- `half_precision_backend`: auto |
|
- `bf16_full_eval`: False |
|
- `fp16_full_eval`: False |
|
- `tf32`: 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_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |
|
|:---------:|:-------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
|
| 0.4938 | 10 | 4.1082 | - | - | - | - | - | - | |
|
| 0.9877 | 20 | 3.2445 | 0.1490 | 0.1440 | 0.1466 | 0.1546 | 0.1249 | 0.1521 | |
|
| 1.4815 | 30 | 1.9296 | - | - | - | - | - | - | |
|
| 1.9753 | 40 | 1.7067 | 0.1607 | 0.1548 | 0.1567 | 0.1648 | 0.1448 | 0.1593 | |
|
| 2.4691 | 50 | 0.9578 | - | - | - | - | - | - | |
|
| 2.9630 | 60 | 1.003 | 0.1640 | 0.1699 | 0.1660 | 0.1695 | 0.1568 | 0.1592 | |
|
| 3.4568 | 70 | 0.6298 | - | - | - | - | - | - | |
|
| 3.9506 | 80 | 0.7035 | - | - | - | - | - | - | |
|
| 4.0 | 81 | - | 0.1707 | 0.1657 | 0.1769 | 0.1690 | 0.1610 | 0.1719 | |
|
| 4.4444 | 90 | 0.4606 | - | - | - | - | - | - | |
|
| 4.9383 | 100 | 0.5131 | - | - | - | - | - | - | |
|
| 4.9877 | 101 | - | 0.1645 | 0.1686 | 0.1669 | 0.1620 | 0.1580 | 0.1722 | |
|
| 5.4321 | 110 | 0.3748 | - | - | - | - | - | - | |
|
| 5.9259 | 120 | 0.4799 | - | - | - | - | - | - | |
|
| 5.9753 | 121 | - | 0.1670 | 0.1670 | 0.1725 | 0.1711 | 0.1628 | 0.1715 | |
|
| 6.4198 | 130 | 0.3237 | - | - | - | - | - | - | |
|
| 6.9136 | 140 | 0.4132 | - | - | - | - | - | - | |
|
| **6.963** | **141** | **-** | **0.1746** | **0.1757** | **0.1697** | **0.1746** | **0.1655** | **0.1746** | |
|
| 7.4074 | 150 | 0.3169 | - | - | - | - | - | - | |
|
| 7.9012 | 160 | 0.3438 | - | - | - | - | - | - | |
|
| 8.0 | 162 | - | 0.1692 | 0.1698 | 0.1718 | 0.1735 | 0.1707 | 0.1656 | |
|
| 8.3951 | 170 | 0.2987 | - | - | - | - | - | - | |
|
| 8.8889 | 180 | 0.3193 | - | - | - | - | - | - | |
|
| 8.9877 | 182 | - | 0.1703 | 0.1703 | 0.1695 | 0.1710 | 0.1619 | 0.1666 | |
|
| 9.3827 | 190 | 0.2883 | - | - | - | - | - | - | |
|
| 9.8765 | 200 | 0.3098 | 0.1652 | 0.1722 | 0.1685 | 0.1755 | 0.1676 | 0.1638 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.1.1 |
|
- Transformers: 4.44.2 |
|
- PyTorch: 2.4.1+cu121 |
|
- Accelerate: 0.35.0.dev0 |
|
- Datasets: 3.0.1 |
|
- 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.* |
|
--> |
