stephen-standd/feed-classifier

SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 256 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
0	'Sad Story of My Google Workspace Account Suspension [source: Hacker News] [topic: engineering]' '“CEO said a thing!” [source: marcus-on-ai] [topic: Leadership / Corporate Culture]' 'How to Be Silicon Valley [source: Paul Graham: Essays] [topic: startup]'
1	'Organizing in Hard Times: Lessons from Read This When Things Fall Apart [source: bluesky links] [topic: leadership

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("setfit_model_id")
# Run inference
preds = model("Code Is an Afterthought [source: Hacker News] [topic: engineering]")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	12.5652	27

Label	Training Sample Count
0	87
1	74

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• 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
• evaluation_strategy: epoch
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0025	1	0.4129	-
0.1241	50	0.2716	-
0.2481	100	0.2432	-
0.3722	150	0.2218	-
0.4963	200	0.1869	-
0.6203	250	0.1302	-
0.7444	300	0.0617	-
0.8685	350	0.0343	-
0.9926	400	0.022	-
1.0	403	-	0.2546

Framework Versions

• Python: 3.13.9
• SetFit: 1.1.3
• Sentence Transformers: 5.4.0
• Transformers: 4.50.3
• PyTorch: 2.11.0
• Datasets: 4.8.4
• Tokenizers: 0.21.4

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}
}