rkoh/setfit-bert-a6

SetFit

This is a SetFit model that can be used for Text Classification. 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
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 tokens
• Number of Classes: 200 classes

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

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("rkoh/setfit-bert-a6")
# Run inference
preds = model("The purpose of this Part is to establish the new source review (NSR) preconstruction, construction and operation requirements for new and modified facilities in a manner which furthers the policy and objectives of article 19 of the Environmental Conservation Law, and meets the plan requirements for nonattainment areas (part D) and prevention of significant deterioration (PSD) of air quality (part C) of subchapter I of the act.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	tensor(15)	tensor(242.2050)	tensor(4265)

Label	Training Sample Count
Purpose - Regulatory Objective	0
Scope and Applicability	0
Authority and Legal Basis	0
Administrative Details	0
Non-Purpose	0

Training Hyperparameters

• batch_size: (32, 32)
• 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
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.004	1	0.3869	-
0.04	10	0.4354	-
0.08	20	0.3435	-
0.12	30	0.2742	-
0.16	40	0.2615	-
0.2	50	0.2462	-
0.24	60	0.2092	-
0.28	70	0.2323	-
0.32	80	0.1956	-
0.36	90	0.2324	-
0.4	100	0.2026	-
0.44	110	0.1941	-
0.48	120	0.1728	-
0.52	130	0.1674	-
0.56	140	0.1754	-
0.6	150	0.1746	-
0.64	160	0.1502	-
0.68	170	0.1704	-
0.72	180	0.1373	-
0.76	190	0.152	-
0.8	200	0.15	-
0.84	210	0.1397	-
0.88	220	0.135	-
0.92	230	0.137	-
0.96	240	0.106	-
1.0	250	0.1309	0.2323

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.2.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Datasets: 3.0.2
• 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}
}