SetFit with BAAI/bge-small-en-v1.5
This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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 Sources
Model Labels
Label |
Examples |
negative |
- 'there might be some sort of credible gender-provoking philosophy submerged here , but who the hell cares ?'
- 'represents the depths to which the girls-behaving-badly film has fallen .'
- '-lrb- a -rrb- crushing disappointment .'
|
positive |
- 'what saves it ... and makes it one of the better video-game-based flicks , is that the film acknowledges upfront that the plot makes no sense , such that the lack of linearity is the point of emotional and moral departure for protagonist alice .'
- 'but it could be , by its art and heart , a necessary one .'
- 'a culture-clash comedy that , in addition to being very funny , captures some of the discomfort and embarrassment of being a bumbling american in europe .'
|
Evaluation
Metrics
Label |
Accuracy |
all |
0.8479 |
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
model = SetFitModel.from_pretrained("skylord/setfit-bge-small-v1.5-sst2-8-shot")
preds = model("it 's refreshing to see a romance this smart .")
Training Details
Training Set Metrics
Training set |
Min |
Median |
Max |
Word count |
6 |
22.5 |
45 |
Label |
Training Sample Count |
negative |
8 |
positive |
8 |
Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (10, 10)
- 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 |
0.2 |
1 |
0.2109 |
- |
10.0 |
50 |
0.01 |
- |
Framework Versions
- Python: 3.10.11
- SetFit: 1.0.3
- Sentence Transformers: 2.3.1
- Transformers: 4.37.2
- PyTorch: 2.2.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.1
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}
}