DrGwin/setfit-paraphrase-mpnet-base-v2-sst2A

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-mpnet-base-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 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
positive	'klein , charming in comedies like american pie and dead-on in election , ' 'be fruitful ' 'soulful and '
negative	'covered earlier and much better ' 'it too is a bomb . ' 'guilty about it '

Evaluation

Metrics

Label	Accuracy
all	0.89

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("DrGwin/setfit-paraphrase-mpnet-base-v2-sst2A")
# Run inference
preds = model("i had to look away - this was god awful . ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	9.55	46

Label	Training Sample Count
negative	40
positive	60

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (4, 4)
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0030	1	0.4181	-
0.1506	50	0.2514	-
0.3012	100	0.0932	-
0.4518	150	0.0029	-
0.6024	200	0.001	-
0.7530	250	0.0006	-
0.9036	300	0.0006	-
1.0	332	-	0.1722
1.0542	350	0.0014	-
1.2048	400	0.0004	-
1.3554	450	0.0004	-
1.5060	500	0.0095	-
1.6566	550	0.0003	-
1.8072	600	0.0003	-
1.9578	650	0.0003	-
2.0	664	-	0.1820
2.1084	700	0.0003	-
2.2590	750	0.0023	-
2.4096	800	0.0003	-
2.5602	850	0.0002	-
2.7108	900	0.0002	-
2.8614	950	0.0002	-
3.0	996	-	0.1970
3.0120	1000	0.0002	-
3.1627	1050	0.0003	-
3.3133	1100	0.0012	-
3.4639	1150	0.0002	-
3.6145	1200	0.0002	-
3.7651	1250	0.0003	-
3.9157	1300	0.001	-
4.0	1328	-	0.1810

Framework Versions

• Python: 3.11.11
• SetFit: 1.1.1
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.5.1+cu124
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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}
}