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:
- 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: 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
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.8041 |
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("waterabbit114/my-setfit-classifier")
# Run inference
preds = model("\" link thanks for fixing that disambiguation link on usher's album ) flash; \"")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 69.1481 | 898 |
Training Hyperparameters
- batch_size: (1, 1)
- 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 |
---|---|---|---|
0.0005 | 1 | 0.2094 | - |
0.0231 | 50 | 0.033 | - |
0.0463 | 100 | 0.0439 | - |
0.0694 | 150 | 0.001 | - |
0.0926 | 200 | 0.0245 | - |
0.1157 | 250 | 0.0008 | - |
0.1389 | 300 | 0.0001 | - |
0.1620 | 350 | 0.0 | - |
0.1852 | 400 | 0.0012 | - |
0.2083 | 450 | 0.0 | - |
0.2315 | 500 | 0.0002 | - |
0.2546 | 550 | 0.0006 | - |
0.2778 | 600 | 0.002 | - |
0.3009 | 650 | 0.0044 | - |
0.3241 | 700 | 0.0015 | - |
0.3472 | 750 | 0.0007 | - |
0.3704 | 800 | 0.0001 | - |
0.3935 | 850 | 0.0001 | - |
0.4167 | 900 | 0.0001 | - |
0.4398 | 950 | 0.0004 | - |
0.4630 | 1000 | 0.0001 | - |
0.4861 | 1050 | 0.0001 | - |
0.5093 | 1100 | 0.0 | - |
0.5324 | 1150 | 0.0052 | - |
0.5556 | 1200 | 0.0002 | - |
0.5787 | 1250 | 0.0 | - |
0.6019 | 1300 | 0.0003 | - |
0.625 | 1350 | 0.0 | - |
0.6481 | 1400 | 0.0001 | - |
0.6713 | 1450 | 0.0 | - |
0.6944 | 1500 | 0.0 | - |
0.7176 | 1550 | 0.0 | - |
0.7407 | 1600 | 0.0002 | - |
0.7639 | 1650 | 0.0001 | - |
0.7870 | 1700 | 0.0011 | - |
0.8102 | 1750 | 0.0001 | - |
0.8333 | 1800 | 0.0 | - |
0.8565 | 1850 | 0.0001 | - |
0.8796 | 1900 | 0.0006 | - |
0.9028 | 1950 | 0.0002 | - |
0.9259 | 2000 | 0.0002 | - |
0.9491 | 2050 | 0.0 | - |
0.9722 | 2100 | 0.0001 | - |
0.9954 | 2150 | 0.0 | - |
Framework Versions
- Python: 3.11.7
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.1+cu121
- Datasets: 2.14.5
- Tokenizers: 0.15.1
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
- 3
Model tree for waterabbit114/my-setfit-classifier
Finetuned
this model