SetFit with sentence-transformers/all-MiniLM-L12-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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:
- 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: sentence-transformers/all-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 |
|---|---|
| Non event | 'The National Emergency Centre (COE) indicated that for this Saturday, alerts continued in 18 provinces for possible floods, urban and rural droughts, rising rivers, hurricanes and floods, as well as landslides.''The City of Temiscouta-sur-Le-Lac informs its citizens near the Bernard River of the risk of floods for the next few days. The detention base should contain water scarcity, but the municipality recommends preventive measures.''Extreme warning for torrents with a point of more than 250 mm, bordered and electric currents in the specified areas' |
| Event | 'A broken down car in floodwater near Derwentwater, Keswick, in Cumbria (Owen Humphreys/PA)''A middle school boy was missing after he was swept away by flood waters in a ditch, NHK added.''Floods, thunderstorms and landslides also hit various regions in northern Italy.' |
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("setfit_model_id")
# Run inference
preds = model("Floods, thunderstorms and landslides also hit various regions in northern Italy.")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 9 | 52.4062 | 237 |
| Label | Training Sample Count |
|---|---|
| Event | 16 |
| Non event | 16 |
Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (2, 2)
- 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 |
|---|---|---|---|
| 0.0588 | 1 | 0.2487 | - |
Framework Versions
- Python: 3.11.15
- SetFit: 1.0.0
- Sentence Transformers: 2.2.2
- Transformers: 4.32.1
- PyTorch: 2.12.0
- Datasets: 2.14.7
- Tokenizers: 0.13.3
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}
}