SetFit with hackathon-pln-es/paraphrase-spanish-distilroberta
This is a SetFit model that can be used for Text Classification. This SetFit model uses hackathon-pln-es/paraphrase-spanish-distilroberta 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:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: hackathon-pln-es/paraphrase-spanish-distilroberta
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 128 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 |
---|---|
2.0 |
|
1.0 |
|
0.0 |
|
3.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.96 |
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("rovargasc/setfit-model_actividadesMedicinaLegalV1")
# Run inference
preds = model("GESTIÓN DEL SERVICIO PERICIALANTROPOLOGÍA - ANÁLISIS ANTROPOLÓGICO FORENSERealizar la toma de muestras de la escrictura osea con la anuencia del Médico.")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 6 | 26.1733 | 65 |
Label | Training Sample Count |
---|---|
0.0 | 69 |
1.0 | 79 |
2.0 | 75 |
3.0 | 77 |
Training Hyperparameters
- batch_size: (64, 64)
- num_epochs: (1, 1)
- 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 |
---|---|---|---|
0.0009 | 1 | 0.1977 | - |
0.0474 | 50 | 0.0986 | - |
0.0949 | 100 | 0.0514 | - |
0.1423 | 150 | 0.0025 | - |
0.1898 | 200 | 0.0012 | - |
0.2372 | 250 | 0.0014 | - |
0.2846 | 300 | 0.0003 | - |
0.3321 | 350 | 0.0003 | - |
0.3795 | 400 | 0.0002 | - |
0.4269 | 450 | 0.0001 | - |
0.4744 | 500 | 0.0002 | - |
0.5218 | 550 | 0.0001 | - |
0.5693 | 600 | 0.0002 | - |
0.6167 | 650 | 0.0001 | - |
0.6641 | 700 | 0.0001 | - |
0.7116 | 750 | 0.0002 | - |
0.7590 | 800 | 0.0001 | - |
0.8065 | 850 | 0.0001 | - |
0.8539 | 900 | 0.0001 | - |
0.9013 | 950 | 0.0001 | - |
0.9488 | 1000 | 0.0001 | - |
0.9962 | 1050 | 0.0001 | - |
1.0 | 1054 | - | 0.0517 |
Framework Versions
- Python: 3.10.13
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.40.0
- PyTorch: 2.1.2
- Datasets: 2.20.0
- 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}
}
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.