saraestevez/setfit-minilm-bank-tweets-processed-100

SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 128 tokens
• Number of Classes: 2 classes

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
relevant	'Caixa y BBVA son los prestamistas que se benefician de la garantía en caso de impago en la financiación de inversiones, algo común también en las sociedades que avalan a comunidades autónomas.' 'El IBEX supera los 11.200 puntos gracias al impulso de la banca, liderado por Banco Sabadell con una subida del 2,05%.' 'Nuevo caso de phishing relacionado con ING, registrado el 16 de julio de 2024, con la URL /www.ingseguridad-app.com/es/login.'
discard	'El BBVA también tiene un mal servicio, ya que no aceptan billetes de 2.000 ni de 1.000 de San Martín, obligando a hacer largas filas tanto para cambiar como para depositar.' 'Merhaba, yaşadığınız deneyim için üzgünüz; Garanti BBVA ATM konum bilgilerini paylaşırsanız gerekli kontrolleri hızlıca yapacağız.' 'En la gasolinera sobre Constituyentes, mi tarjeta de crédito fue denegada y no me hicieron cargo en la aplicación.'

Evaluation

Metrics

Label	Accuracy
all	0.7594

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("saraestevez/setfit-minilm-bank-tweets-processed-100")
# Run inference
preds = model("Los resultados del Banco Sabadell impulsan al IBEX 35.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	22.0	41

Label	Training Sample Count
discard	100
relevant	100

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0008	1	0.3931	-
0.0396	50	0.2501	-
0.0792	100	0.2471	-
0.1188	150	0.1991	-
0.1584	200	0.0902	-
0.1979	250	0.0218	-
0.2375	300	0.0055	-
0.2771	350	0.0026	-
0.3167	400	0.0013	-
0.3563	450	0.0005	-
0.3959	500	0.0005	-
0.4355	550	0.001	-
0.4751	600	0.0003	-
0.5146	650	0.0003	-
0.5542	700	0.0001	-
0.5938	750	0.0003	-
0.6334	800	0.0003	-
0.6730	850	0.0004	-
0.7126	900	0.0002	-
0.7522	950	0.0001	-
0.7918	1000	0.0001	-
0.8314	1050	0.0001	-
0.8709	1100	0.0002	-
0.9105	1150	0.0002	-
0.9501	1200	0.0002	-
0.9897	1250	0.0	-

Framework Versions

• Python: 3.11.0rc1
• SetFit: 1.0.3
• Sentence Transformers: 2.7.0
• Transformers: 4.39.0
• PyTorch: 2.3.1+cu121
• Datasets: 2.19.1
• Tokenizers: 0.15.2

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}