GIZ/TARGET-VULNERABILITY-multiclass-mpnet

SetFit with sentence-transformers/all-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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/all-mpnet-base-v2
• Classification head: a OneVsRestClassifier instance
• Maximum Sequence Length: 384 tokens

Model Sources

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

Evaluation

Metrics

Label	Precision_Micro	Precision_Weighted	Precision_Samples	Recall_Micro	Recall_Weighted	Recall_Samples	F1-Score	Accuracy
all	0.7762	0.7969	0.7762	0.7762	0.7762	0.7762	0.7762	0.7762

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("leavoigt/vulnerability_target")
# Run inference
preds = model("To support the traditional knowledge and adaptive capacity of indigenous peoples in the face of climate change, we aim to establish 50 community-based adaptation projects led by indigenous peoples by 2030, focusing on the sustainable management of natural resources and the preservation of cultural practices.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	15	70.8675	238

Training Hyperparameters

• batch_size: (16, 16)
• 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
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0012	1	0.3493	-
0.0602	50	0.2285	-
0.1205	100	0.1092	-
0.1807	150	0.1348	-
0.2410	200	0.0365	-
0.3012	250	0.0052	-
0.3614	300	0.0012	-
0.4217	350	0.0031	-
0.4819	400	0.0001	-
0.5422	450	0.0011	-
0.6024	500	0.0001	-
0.6627	550	0.0001	-
0.7229	600	0.0001	-
0.7831	650	0.0002	-
0.8434	700	0.0001	-
0.9036	750	0.0001	-
0.9639	800	0.0001	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.1
• Sentence Transformers: 2.2.2
• Transformers: 4.25.1
• PyTorch: 2.1.0+cu121
• Datasets: 2.16.1
• Tokenizers: 0.13.3

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}
}