AlexBayer/GIST_SetFit_HIPs_v1

SetFit with avsolatorio/GIST-Embedding-v0

This is a SetFit model that can be used for Text Classification. This SetFit model uses avsolatorio/GIST-Embedding-v0 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: avsolatorio/GIST-Embedding-v0
• Classification head: a SetFitHead 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

Evaluation

Metrics

Label	Accuracy
all	0.6

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("AlexBayer/GIST_SetFit_HIPs_v1")
# Run inference
preds = model("occupied palestinian territory cold wave dec 2013 cold wave event lasted unknown announced heavy rain fall snow storm hit west bank gaza 10 december 2013 still affecting palestinian population west bank palestine heavy rain snow generated flood several part palestine thousand family evacuated house extreme weather condition also caused several death including baby gaza reported dead family home inundated ifrc 16 dec 2013 useful link ocha opt winter storm online system palestinian red crescent society occupied palestinian territory")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	34	319.4125	2470

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• max_steps: -1
• sampling_strategy: undersampling
• body_learning_rate: (3.318622110926711e-05, 3.5664318062183154e-05)
• head_learning_rate: 0.025092743459786394
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: True
• use_amp: True
• warmup_proportion: 0.1
• l2_weight: 0.05
• max_length: 512
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.1534	25	0.2384	-
0.3067	50	0.1621	-
0.4601	75	0.1389	-
0.6135	100	0.1214	-
0.7669	125	0.1115	-
0.9202	150	0.0927	-

Framework Versions

• Python: 3.11.12
• SetFit: 1.1.2
• Sentence Transformers: 3.4.1
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Datasets: 3.5.1
• 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}
}