Rankle-Matching/setfit-section-filter-v0.2.0

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
skip	'Additional tasks may be assigned based on organizationalneeds and priorities.Culture:At the Kids’ Book Bank, we are a small but mighty team dedicated to getting more books to more children and fostering a love of reading' 'Founded in Sweden in 1907, today SKF is publicly traded on the Nasdaq Stockholm with annual sales in 2020 of approximately $10 billion' 'Compensation:$55,000-$75,000/year'
keep	'Requirements Must have at least 2 years Arizona or Colorado civil litigation experience, knowledge of both state and federal procedural rules, superior organizational skills, strong attention to detail and the ability to provide secretarial/administrative support to experienced trial attorneys' 'Experience with EMR systems Knowledge of Microsoft products (Word, Excel, Outlook)' "Requirements:A bachelor's degree in exercise science, kinesiology, sports science, or a related field preferred but not required"

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("Remote work is allowed provided the candidate has adequate home systems to support the high internet data demands required for this position")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	24.1078	84

Label	Training Sample Count
skip	52
keep	50

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (4, 4)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• body_learning_rate: (2e-05, 2e-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
0.0039	1	0.3866	-
0.1961	50	0.2075	-
0.3922	100	0.0179	-
0.5882	150	0.0005	-
0.7843	200	0.0003	-
0.9804	250	0.0002	-
1.0	255	-	0.1885
1.1765	300	0.0002	-
1.3725	350	0.0001	-
1.5686	400	0.0001	-
1.7647	450	0.0001	-
1.9608	500	0.0001	-
2.0	510	-	0.1909
2.1569	550	0.0001	-
2.3529	600	0.0001	-
2.5490	650	0.0001	-
2.7451	700	0.0001	-
2.9412	750	0.0001	-
3.0	765	-	0.1904
3.1373	800	0.0001	-
3.3333	850	0.0001	-
3.5294	900	0.0001	-
3.7255	950	0.0001	-
3.9216	1000	0.0001	-
4.0	1020	-	0.1910

Framework Versions

• Python: 3.12.3
• SetFit: 1.1.3
• Sentence Transformers: 5.2.0
• Transformers: 4.57.3
• PyTorch: 2.5.1+cu124
• Datasets: 4.4.2
• Tokenizers: 0.22.2

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}
}