SetFit with sentence-transformers/distiluse-base-multilingual-cased-v1
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/distiluse-base-multilingual-cased-v1 as the Sentence Transformer embedding model. A LogisticRegression 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/distiluse-base-multilingual-cased-v1
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 128 tokens
- Number of Classes: 3 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
Label | Examples |
---|---|
opposed |
|
supportive |
|
neutral |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.4545 |
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("cbpuschmann/distiluse-base-multilingual-cased-klimacoder_v0.9")
# Run inference
preds = model("Fans und Gegner des Automobils stehen sich zunehmend unversöhnlich gegenüber: Der Zwist über den Ausbau von Autobahnen und ein Tempolimit könnte sogar die Ampelkoalition sprengen. Die SPIEGEL-Titelgeschichte.")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 17 | 70.4091 | 231 |
Label | Training Sample Count |
---|---|
neutral | 59 |
opposed | 55 |
supportive | 62 |
Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- 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: 0.1
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0016 | 1 | 0.2815 | - |
0.0775 | 50 | 0.2603 | - |
0.1550 | 100 | 0.2237 | - |
0.2326 | 150 | 0.095 | - |
0.3101 | 200 | 0.015 | - |
0.3876 | 250 | 0.0083 | - |
0.4651 | 300 | 0.0069 | - |
0.5426 | 350 | 0.0056 | - |
0.6202 | 400 | 0.0079 | - |
0.6977 | 450 | 0.0027 | - |
0.7752 | 500 | 0.0064 | - |
0.8527 | 550 | 0.005 | - |
0.9302 | 600 | 0.0034 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.42.2
- PyTorch: 2.5.1+cu121
- Datasets: 3.2.0
- 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
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.