Kevinger/setfit-newsapi

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: 6 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
4	'The Super Mario Bros. Movie Expected To Pass $1 Billion, Biggest Movie Release This Year - Kotaku' 'Richard Lewis Has Parkinson’s Disease, Finished With Stand-Up Comedy Career - Deadline' "EXCLUSIVE Dame Mary Quant's plans for 'small funeral' near her home - Daily Mail"
3	'GPT-5 not in the works currently: OpenAI CEO Sam Altman - The Economic Times' 'The 2023 Am Law 100: Ranked by Gross Revenue
5	"I used all 2023 flagships — here's why the Galaxy S23 Ultra is my favorite phone - Android Central" "Google's AI experts on the future of artificial intelligence
0	'Fernando Tatis Jr. to make Padres return - MLB.com' 'Knicks-Cavaliers Game 3 live updates: Score, news, more from NBA Playoffs - New York Post ' 'Josh Donaldson Likely To Miss Multiple Weeks With Hamstring Strain - MLB Trade Rumors'
2	'Are Fermented Foods Actually Good for You? - Lifehacker' 'ADHD medication
1	'Creating Artificial Avians: A Novel Neural Network Generates Realistic Bird Pictures from Text using Common Sense - Neuroscience News' 'Consciousness begins with feeling, not thinking

Evaluation

Metrics

Label	Accuracy
all	0.8577

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("Kevinger/setfit-newsapi")
# Run inference
preds = model("GIANT 130-foot asteroid rushing towards Earth TODAY at 42404 kmph, NASA warns - HT Tech")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	9.1771	22

Label	Training Sample Count
0	16
1	16
2	16
3	16
4	16
5	16

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• 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
0.0021	1	0.2926	-
0.1042	50	0.0446	-
0.2083	100	0.0023	-
0.3125	150	0.0011	-
0.4167	200	0.001	-
0.5208	250	0.0007	-
0.625	300	0.0007	-
0.7292	350	0.0009	-
0.8333	400	0.0075	-
0.9375	450	0.0006	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.2.2
• Transformers: 4.35.2
• PyTorch: 2.1.0+cu121
• Datasets: 2.16.1
• Tokenizers: 0.15.0

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}
}