faodl/setfit-paraphrase-mpnet-base-v2-5ClassesDesc-multilabel-augmented

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 OneVsRestClassifier 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 OneVsRestClassifier instance
• Maximum Sequence Length: 512 tokens

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("faodl/setfit-paraphrase-mpnet-base-v2-5ClassesDesc-multilabel-augmented")
# Run inference
preds = model("Provision 1 - Access to safe nutritious food for all The package will be aimed at ending hunger and all forms of malnutrition and reduce the incidence of non-communicable diseases, enabling all people to be nourished and healthy. This suggests that all people at all times have access to sufficient quantities of affordable and safe foo")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	93.5916	1014

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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0010	1	0.3063	-
0.0524	50	0.2204	-
0.1047	100	0.1689	-
0.1571	150	0.1464	-
0.2094	200	0.1236	-
0.2618	250	0.1088	-
0.3141	300	0.0649	-
0.3665	350	0.0697	-
0.4188	400	0.0395	-
0.4712	450	0.052	-
0.5236	500	0.0263	-
0.5759	550	0.0376	-
0.6283	600	0.0307	-
0.6806	650	0.022	-
0.7330	700	0.0162	-
0.7853	750	0.012	-
0.8377	800	0.0135	-
0.8901	850	0.0173	-
0.9424	900	0.0171	-
0.9948	950	0.0117	-

Framework Versions

• Python: 3.11.11
• SetFit: 1.1.1
• Sentence Transformers: 3.4.1
• Transformers: 4.50.2
• PyTorch: 2.6.0+cu124
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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}
}