SetFit with meedan/paraphrase-filipino-mpnet-base-v2
This is a SetFit model trained on the bsen26/eyeR-classification-multi-label-category2 dataset that can be used for Text Classification. This SetFit model uses meedan/paraphrase-filipino-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:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: meedan/paraphrase-filipino-mpnet-base-v2
- Classification head: a OneVsRestClassifier instance
- Maximum Sequence Length: 128 tokens
- Training Dataset: bsen26/eyeR-classification-multi-label-category2
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 | 0.5407 |
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("bsen26/eyeR-category2-multilabel")
# Run inference
preds = model("Wrong coffee / no ketchup / cold fries. Ugh")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 1 | 18.3958 | 41 |
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 |
---|---|---|---|
0.0010 | 1 | 0.0919 | - |
0.0521 | 50 | 0.1443 | - |
0.1042 | 100 | 0.0682 | - |
0.1562 | 150 | 0.1043 | - |
0.2083 | 200 | 0.0653 | - |
0.2604 | 250 | 0.0136 | - |
0.3125 | 300 | 0.0025 | - |
0.3646 | 350 | 0.0195 | - |
0.4167 | 400 | 0.0073 | - |
0.4688 | 450 | 0.0115 | - |
0.5208 | 500 | 0.0045 | - |
0.5729 | 550 | 0.0052 | - |
0.625 | 600 | 0.0091 | - |
0.6771 | 650 | 0.0037 | - |
0.7292 | 700 | 0.0027 | - |
0.7812 | 750 | 0.0058 | - |
0.8333 | 800 | 0.0118 | - |
0.8854 | 850 | 0.0025 | - |
0.9375 | 900 | 0.0005 | - |
0.9896 | 950 | 0.0085 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.7.0
- Transformers: 4.40.2
- PyTorch: 2.2.1+cu121
- Datasets: 2.19.1
- Tokenizers: 0.19.1
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}
}
- Downloads last month
- 4
Model tree for bsen26/eyeR-category2-multilabel
Base model
meedan/paraphrase-filipino-mpnet-base-v2
Finetuned
this model
Dataset used to train bsen26/eyeR-category2-multilabel
Evaluation results
- Accuracy on bsen26/eyeR-classification-multi-label-category2test set self-reported0.541