SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-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 Sources
Model Labels
Label |
Examples |
0 |
- 'Well, I wore these under my dress and I must say they fit well and I received several compliments .'
- 'Gildan makes a sweatshirt as they should be made.'
- 'It is very pretty except for the dark color of the felt that was provided for the reindeer.'
|
1 |
- 'If it had a weighted bottom I would have given it 4/5 stars.'
- "I can definitely wear a t-shirt over this bra without the bra showing, but I wish it were padded so nipples don't show through shirts that are more fitted."
- '"But oddly enough, the bottoms are a little too loose in the waist (37\) and could have used another inch or two in the inseam ( I normally take a 35\"" or 36\"" in jeans, depending on the brand if this helps)."""'
|
Evaluation
Metrics
Label |
Accuracy |
all |
0.7284 |
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("vidhi0206/setfit-paraphrase-mpnet-amazon_cf")
preds = model("I wished it had the output on back instead of on the side.")
Training Details
Training Set Metrics
Training set |
Min |
Median |
Max |
Word count |
9 |
21.875 |
50 |
Label |
Training Sample Count |
0 |
8 |
1 |
8 |
Training Hyperparameters
- batch_size: (8, 8)
- 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 |
0.0125 |
1 |
0.2688 |
- |
0.625 |
50 |
0.0015 |
- |
Framework Versions
- Python: 3.8.10
- SetFit: 1.0.3
- Sentence Transformers: 2.3.1
- Transformers: 4.37.2
- PyTorch: 2.2.0+cu121
- Datasets: 2.17.0
- 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}
}