larshubacher/setfit-paraphrase-mpnet-base-v2-sst2_SentEval-C

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model trained on the SetFit/SentEval-CR dataset 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
• Training Dataset: SetFit/SentEval-CR

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
1	'* slick-looking design and improved interface' 'as for bluetooth , no problems at all .' '2 ) storage capacity'
0	"the day finally arrived when i was sure i 'd leave sprint ." "neither message was answered ( they ask for 24 hours before replying - i 've been waiting 27 days . )" 'only problem is that is a bit heavy .'

Evaluation

Metrics

Label	Accuracy
all	0.8552

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("larshubacher/setfit-paraphrase-mpnet-base-v2-sst2_SentEval-C")
# Run inference
preds = model("the speakerphone , the radio , all features work perfectly .")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	18.0625	44

Label	Training Sample Count
0	7
1	9

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	0.188	-
0.625	50	0.0041	-

Framework Versions

• Python: 3.11.9
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.40.2
• PyTorch: 2.3.1+cu121
• Datasets: 2.20.0
• Tokenizers: 0.19.1

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}
}