edugargar/modality_model

SetFit with hiiamsid/sentence_similarity_spanish_es

This is a SetFit model that can be used for Text Classification. This SetFit model uses hiiamsid/sentence_similarity_spanish_es 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: hiiamsid/sentence_similarity_spanish_es
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 tokens
• Number of Classes: 4 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
eventual	'Estoy buscando un desarrollador para crear un sitio web corporativo.' '¿Podrían explicarme cómo funciona el sistema de cobro a freelancers?' '¿Cómo obtengo información sobre las comisiones de la plataforma?'
recurrent_part_time	'Quiero contratar un especialista en SEO para mejorar la visibilidad de mi tienda online.' 'Busco a alguien que configure un servidor y lo mantenga a largo plazo.' 'Quiero contratar un programador Python para automatizar un proceso interno de forma continua.'
recurrent_full_time	'Requiero un arquitecto de software para reestructurar mi aplicación de forma continua.' 'Quiero contratar un analista de negocios para mejorar mis KPIs a largo plazo' 'Quiero un profesional que diseñe la experiencia de usuario de mi web a largo plazo.'
no_offering	'¿Puedes decirme la contraseña de la base de datos interna de la plataforma?' 'Estoy interesado en comprar datos personales de otros usuarios de la plataforma.' 'Necesito un especialista en hacking para infiltrarse en el sistema de un competidor.'

Evaluation

Metrics

Label	Accuracy
all	0.7391

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("edugargar/modality_model")
# Run inference
preds = model("Quiero contratar un ilustrador para un proyecto puntual.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	7	11.0	17

Label	Training Sample Count
eventual	34
no_offering	16
recurrent_full_time	11
recurrent_part_time	17

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (4, 4)
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0037	1	0.4046	-
0.1873	50	0.2227	-
0.3745	100	0.1189	-
0.5618	150	0.0138	-
0.7491	200	0.0019	-
0.9363	250	0.0008	-
1.1236	300	0.0005	-
1.3109	350	0.0004	-
1.4981	400	0.0004	-
1.6854	450	0.0003	-
1.8727	500	0.0003	-
2.0599	550	0.0003	-
2.2472	600	0.0002	-
2.4345	650	0.0002	-
2.6217	700	0.0002	-
2.8090	750	0.0002	-
2.9963	800	0.0002	-
3.1835	850	0.0002	-
3.3708	900	0.0002	-
3.5581	950	0.0002	-
3.7453	1000	0.0002	-
3.9326	1050	0.0002	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.3.1
• Transformers: 4.42.2
• PyTorch: 2.5.1+cu121
• Datasets: 3.2.0
• Tokenizers: 0.19.1

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}
}