GIZ/vulnerability_multilabel_v2

SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-mpnet-base-v2 as the Sentence Transformer embedding model. A SetFitHead 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-multilingual-mpnet-base-v2
• Classification head: a SetFitHead instance
• Maximum Sequence Length: 128 tokens
• Number of Classes: 18 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("GIZ/vulnerability_multilabel_v2")
# Run inference
preds = model("Poor rural households in marginal territories that have a low productive potential and/or that are far from markets and infrastructure are highly vulnerable to climate-change impacts and could easily fall into poverty-environment traps 9. This means that communities that are already struggling economically and geographically isolated are at greater risk of experiencing the negative impacts of climate change on their agricultural livelihoods.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	61.2897	164

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 0)
• max_steps: -1
• sampling_strategy: undersampling
• 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: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0002	1	0.2095	-
0.2084	1000	0.0307	0.1211
0.4168	2000	0.0165	0.1275
0.6251	3000	0.0085	0.131
0.8335	4000	0.0317	0.1171

Framework Versions

• Python: 3.9.5
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.44.2
• PyTorch: 2.4.0+cu121
• Datasets: 2.3.0
• Tokenizers: 0.19.1

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.155 kg of CO2
• Hours Used: 1.08 hours

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}
}