SetFit with distilbert/distilbert-base-uncased-finetuned-sst-2-english
This is a SetFit model trained on the wikd/customer_data dataset that can be used for Text Classification. This SetFit model uses distilbert/distilbert-base-uncased-finetuned-sst-2-english 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 |
0 |
- 'I need to speak to a real person, not a dumb machine.'
- 'Stop with the automated nonsense and connect me to a human!'
- 'Your automated system is beyond frustrating, let me talk to someone!'
|
1 |
- 'I love your new product!'
- 'The delivery was very quick!'
- 'I would recommend this company to a friend'
|
Evaluation
Metrics
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("setfit_model_id")
preds = model("The product is out of stock")
Training Details
Training Set Metrics
Training set |
Min |
Median |
Max |
Word count |
4 |
10.0 |
14 |
Label |
Training Sample Count |
0 |
46 |
1 |
6 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
0.0077 |
1 |
0.1479 |
- |
0.3846 |
50 |
0.0008 |
- |
0.7692 |
100 |
0.0005 |
- |
Framework Versions
- Python: 3.11.8
- SetFit: 1.0.3
- Sentence Transformers: 2.5.1
- Transformers: 4.38.2
- PyTorch: 2.2.1
- Datasets: 2.18.0
- 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}
}