|
--- |
|
base_model: BAAI/bge-m3 |
|
datasets: [] |
|
language: |
|
- es |
|
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:2947 |
|
- loss:MatryoshkaLoss |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: Es uso privativo el que determina la ocupación de una porción del |
|
dominio público, de modo que se limita o excluye la utilización del mismo por |
|
otros interesados. |
|
sentences: |
|
- ¿Qué es el uso privativo de los bienes de dominio público? |
|
- ¿Qué es la sanidad ambiental? |
|
- ¿Qué información básica debe contener la información que se facilita al afectado |
|
cuando se obtienen datos personales de él? |
|
- source_sentence: 'Las retribuciones básicas, que se fijan en la Ley de Presupuestos |
|
Generales del Estado, estarán integradas única y exclusivamente por: a) El sueldo |
|
asignado a cada Subgrupo o Grupo de clasificación profesional, en el supuesto |
|
de que éste no tenga Subgrupo. b) Los trienios, que consisten en una cantidad, |
|
que será igual para cada Subgrupo o Grupo de clasificación profesional, en el |
|
supuesto de que éste no tenga Subgrupo, por cada tres años de servicio.' |
|
sentences: |
|
- ¿Qué se entiende por retribuciones básicas? |
|
- ¿Cuál es el título competencial de esta ley orgánica? |
|
- ¿Qué se aprueba a propuesta del Ministro de Hacienda? |
|
- source_sentence: Se reconoce el valor social de las niñas, niños y adolescentes |
|
como personas que realizan un aporte afectivo, cultural y ético al caudal social, |
|
y cuyo protagonismo, creatividad y posicionamiento activo enriquecen la vida colectiva. |
|
sentences: |
|
- ¿Qué sucede si se produce un incumplimiento de las actuaciones establecidas en |
|
el Plan de inclusión sociolaboral? |
|
- ¿Qué se reconoce en cuanto al valor social de la infancia? |
|
- ¿Cuál es el plazo de prescripción de las infracciones? |
|
- source_sentence: Las empresas y las universidades podrán promover y participar en |
|
programas de voluntariado que cumplan los requisitos establecidos en esta Ley. |
|
sentences: |
|
- ¿Cuál es la consideración de las infracciones muy graves? |
|
- ¿Qué tipo de empresas pueden promover y participar en programas de voluntariado? |
|
- ¿Qué tipo de entidades están obligadas a cumplir con las obligaciones de publicidad |
|
activa? |
|
- source_sentence: Artículo 6. Definiciones. 1. Discriminación directa e indirecta. |
|
b) La discriminación indirecta se produce cuando una disposición, criterio o práctica |
|
aparentemente neutros ocasiona o puede ocasionar a una o varias personas una desventaja |
|
particular con respecto a otras por razón de las causas previstas en el apartado |
|
1 del artículo 2. |
|
sentences: |
|
- ¿Cuál es el papel del Consejo de Salud de Área? |
|
- ¿Qué se considera discriminación indirecta? |
|
- ¿Qué tipo de información se considera veraz? |
|
model-index: |
|
- name: BGE large Legal Spanish |
|
results: |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 1024 |
|
type: dim_1024 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.551829268292683 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.8048780487804879 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.8445121951219512 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9024390243902439 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.551829268292683 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.2682926829268293 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.16890243902439023 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.09024390243902437 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.551829268292683 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.8048780487804879 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.8445121951219512 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9024390243902439 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.7379864083246442 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6841608594657377 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6880865147668174 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 768 |
|
type: dim_768 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.5487804878048781 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.8048780487804879 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.850609756097561 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.9024390243902439 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.5487804878048781 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.2682926829268293 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.17012195121951218 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.09024390243902437 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.5487804878048781 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.8048780487804879 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.850609756097561 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.9024390243902439 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.736128283939538 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6815560878823075 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6854885550473444 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 512 |
|
type: dim_512 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.5579268292682927 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.8109756097560976 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.850609756097561 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.8932926829268293 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.5579268292682927 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.27032520325203246 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.17012195121951218 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08932926829268292 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.5579268292682927 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.8109756097560976 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.850609756097561 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.8932926829268293 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.7362627915663099 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6845153406891215 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6889302518809046 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 256 |
|
type: dim_256 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.5548780487804879 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.7957317073170732 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.8323170731707317 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.8841463414634146 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.5548780487804879 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.2652439024390244 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.16646341463414632 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08841463414634146 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.5548780487804879 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.7957317073170732 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.8323170731707317 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.8841463414634146 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.7307377627264078 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6803994870305846 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6851337079025414 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 128 |
|
type: dim_128 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.5213414634146342 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.7621951219512195 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.8140243902439024 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.8658536585365854 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.5213414634146342 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.25406504065040647 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.16280487804878047 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08658536585365853 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.5213414634146342 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.7621951219512195 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.8140243902439024 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.8658536585365854 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.7028480041122221 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6495075977545491 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6549966797371862 |
|
name: Cosine Map@100 |
|
- task: |
|
type: information-retrieval |
|
name: Information Retrieval |
|
dataset: |
|
name: dim 64 |
|
type: dim_64 |
|
metrics: |
|
- type: cosine_accuracy@1 |
|
value: 0.4847560975609756 |
|
name: Cosine Accuracy@1 |
|
- type: cosine_accuracy@3 |
|
value: 0.725609756097561 |
|
name: Cosine Accuracy@3 |
|
- type: cosine_accuracy@5 |
|
value: 0.7804878048780488 |
|
name: Cosine Accuracy@5 |
|
- type: cosine_accuracy@10 |
|
value: 0.8536585365853658 |
|
name: Cosine Accuracy@10 |
|
- type: cosine_precision@1 |
|
value: 0.4847560975609756 |
|
name: Cosine Precision@1 |
|
- type: cosine_precision@3 |
|
value: 0.24186991869918703 |
|
name: Cosine Precision@3 |
|
- type: cosine_precision@5 |
|
value: 0.15609756097560976 |
|
name: Cosine Precision@5 |
|
- type: cosine_precision@10 |
|
value: 0.08536585365853658 |
|
name: Cosine Precision@10 |
|
- type: cosine_recall@1 |
|
value: 0.4847560975609756 |
|
name: Cosine Recall@1 |
|
- type: cosine_recall@3 |
|
value: 0.725609756097561 |
|
name: Cosine Recall@3 |
|
- type: cosine_recall@5 |
|
value: 0.7804878048780488 |
|
name: Cosine Recall@5 |
|
- type: cosine_recall@10 |
|
value: 0.8536585365853658 |
|
name: Cosine Recall@10 |
|
- type: cosine_ndcg@10 |
|
value: 0.6729421249114532 |
|
name: Cosine Ndcg@10 |
|
- type: cosine_mrr@10 |
|
value: 0.6146668118466899 |
|
name: Cosine Mrr@10 |
|
- type: cosine_map@100 |
|
value: 0.6198317239083065 |
|
name: Cosine Map@100 |
|
--- |
|
|
|
# BGE large Legal Spanish |
|
|
|
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:** es |
|
- **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': 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("dariolopez/bge-m3-es-legal-tmp-6") |
|
# Run inference |
|
sentences = [ |
|
'Artículo 6. Definiciones. 1. Discriminación directa e indirecta. b) La discriminación indirecta se produce cuando una disposición, criterio o práctica aparentemente neutros ocasiona o puede ocasionar a una o varias personas una desventaja particular con respecto a otras por razón de las causas previstas en el apartado 1 del artículo 2.', |
|
'¿Qué se considera discriminación indirecta?', |
|
'¿Qué tipo de información se considera veraz?', |
|
] |
|
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 | 0.5518 | |
|
| cosine_accuracy@3 | 0.8049 | |
|
| cosine_accuracy@5 | 0.8445 | |
|
| cosine_accuracy@10 | 0.9024 | |
|
| cosine_precision@1 | 0.5518 | |
|
| cosine_precision@3 | 0.2683 | |
|
| cosine_precision@5 | 0.1689 | |
|
| cosine_precision@10 | 0.0902 | |
|
| cosine_recall@1 | 0.5518 | |
|
| cosine_recall@3 | 0.8049 | |
|
| cosine_recall@5 | 0.8445 | |
|
| cosine_recall@10 | 0.9024 | |
|
| cosine_ndcg@10 | 0.738 | |
|
| cosine_mrr@10 | 0.6842 | |
|
| **cosine_map@100** | **0.6881** | |
|
|
|
#### 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 | 0.5488 | |
|
| cosine_accuracy@3 | 0.8049 | |
|
| cosine_accuracy@5 | 0.8506 | |
|
| cosine_accuracy@10 | 0.9024 | |
|
| cosine_precision@1 | 0.5488 | |
|
| cosine_precision@3 | 0.2683 | |
|
| cosine_precision@5 | 0.1701 | |
|
| cosine_precision@10 | 0.0902 | |
|
| cosine_recall@1 | 0.5488 | |
|
| cosine_recall@3 | 0.8049 | |
|
| cosine_recall@5 | 0.8506 | |
|
| cosine_recall@10 | 0.9024 | |
|
| cosine_ndcg@10 | 0.7361 | |
|
| cosine_mrr@10 | 0.6816 | |
|
| **cosine_map@100** | **0.6855** | |
|
|
|
#### 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 | 0.5579 | |
|
| cosine_accuracy@3 | 0.811 | |
|
| cosine_accuracy@5 | 0.8506 | |
|
| cosine_accuracy@10 | 0.8933 | |
|
| cosine_precision@1 | 0.5579 | |
|
| cosine_precision@3 | 0.2703 | |
|
| cosine_precision@5 | 0.1701 | |
|
| cosine_precision@10 | 0.0893 | |
|
| cosine_recall@1 | 0.5579 | |
|
| cosine_recall@3 | 0.811 | |
|
| cosine_recall@5 | 0.8506 | |
|
| cosine_recall@10 | 0.8933 | |
|
| cosine_ndcg@10 | 0.7363 | |
|
| cosine_mrr@10 | 0.6845 | |
|
| **cosine_map@100** | **0.6889** | |
|
|
|
#### 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 | 0.5549 | |
|
| cosine_accuracy@3 | 0.7957 | |
|
| cosine_accuracy@5 | 0.8323 | |
|
| cosine_accuracy@10 | 0.8841 | |
|
| cosine_precision@1 | 0.5549 | |
|
| cosine_precision@3 | 0.2652 | |
|
| cosine_precision@5 | 0.1665 | |
|
| cosine_precision@10 | 0.0884 | |
|
| cosine_recall@1 | 0.5549 | |
|
| cosine_recall@3 | 0.7957 | |
|
| cosine_recall@5 | 0.8323 | |
|
| cosine_recall@10 | 0.8841 | |
|
| cosine_ndcg@10 | 0.7307 | |
|
| cosine_mrr@10 | 0.6804 | |
|
| **cosine_map@100** | **0.6851** | |
|
|
|
#### 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 | 0.5213 | |
|
| cosine_accuracy@3 | 0.7622 | |
|
| cosine_accuracy@5 | 0.814 | |
|
| cosine_accuracy@10 | 0.8659 | |
|
| cosine_precision@1 | 0.5213 | |
|
| cosine_precision@3 | 0.2541 | |
|
| cosine_precision@5 | 0.1628 | |
|
| cosine_precision@10 | 0.0866 | |
|
| cosine_recall@1 | 0.5213 | |
|
| cosine_recall@3 | 0.7622 | |
|
| cosine_recall@5 | 0.814 | |
|
| cosine_recall@10 | 0.8659 | |
|
| cosine_ndcg@10 | 0.7028 | |
|
| cosine_mrr@10 | 0.6495 | |
|
| **cosine_map@100** | **0.655** | |
|
|
|
#### 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 | 0.4848 | |
|
| cosine_accuracy@3 | 0.7256 | |
|
| cosine_accuracy@5 | 0.7805 | |
|
| cosine_accuracy@10 | 0.8537 | |
|
| cosine_precision@1 | 0.4848 | |
|
| cosine_precision@3 | 0.2419 | |
|
| cosine_precision@5 | 0.1561 | |
|
| cosine_precision@10 | 0.0854 | |
|
| cosine_recall@1 | 0.4848 | |
|
| cosine_recall@3 | 0.7256 | |
|
| cosine_recall@5 | 0.7805 | |
|
| cosine_recall@10 | 0.8537 | |
|
| cosine_ndcg@10 | 0.6729 | |
|
| cosine_mrr@10 | 0.6147 | |
|
| **cosine_map@100** | **0.6198** | |
|
|
|
<!-- |
|
## 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`: 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`: 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`: 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 | 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 | |
|
|:----------:|:------:|:-------------:|:----------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
|
| 0.4324 | 5 | 1.6507 | - | - | - | - | - | - | - | |
|
| 0.8649 | 10 | 0.9598 | - | - | - | - | - | - | - | |
|
| 0.9514 | 11 | - | 0.5477 | 0.6833 | 0.6616 | 0.6836 | 0.6758 | 0.5994 | 0.6744 | |
|
| 1.2973 | 15 | 0.8248 | - | - | - | - | - | - | - | |
|
| 1.7297 | 20 | 0.3858 | - | - | - | - | - | - | - | |
|
| 1.9892 | 23 | - | 0.4242 | 0.6748 | 0.6544 | 0.6833 | 0.6740 | 0.6233 | 0.6697 | |
|
| 2.1622 | 25 | 0.32 | - | - | - | - | - | - | - | |
|
| 2.5946 | 30 | 0.1703 | - | - | - | - | - | - | - | |
|
| 2.9405 | 34 | - | 0.3940 | 0.6755 | 0.6523 | 0.6823 | 0.6797 | 0.6196 | 0.6776 | |
|
| 3.0270 | 35 | 0.1337 | - | - | - | - | - | - | - | |
|
| 3.4595 | 40 | 0.0949 | - | - | - | - | - | - | - | |
|
| 3.8919 | 45 | 0.0594 | - | - | - | - | - | - | - | |
|
| **3.9784** | **46** | **-** | **0.3735** | **0.6867** | **0.6588** | **0.6865** | **0.6854** | **0.6189** | **0.6826** | |
|
| 4.3243 | 50 | 0.07 | - | - | - | - | - | - | - | |
|
| 4.7568 | 55 | 0.0524 | - | - | - | - | - | - | - | |
|
| 4.9297 | 57 | - | 0.3642 | 0.6870 | 0.6577 | 0.6858 | 0.6871 | 0.6228 | 0.6853 | |
|
| 5.1892 | 60 | 0.0598 | - | - | - | - | - | - | - | |
|
| 5.6216 | 65 | 0.0491 | - | - | - | - | - | - | - | |
|
| 5.7081 | 66 | - | 0.3626 | 0.6881 | 0.6550 | 0.6851 | 0.6889 | 0.6198 | 0.6855 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.0.1 |
|
- Transformers: 4.42.3 |
|
- PyTorch: 2.2.0+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.* |
|
--> |
