SetFit with mini1013/master_domain
This is a SetFit model that can be used for Text Classification. This SetFit model uses mini1013/master_domain 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: mini1013/master_domain
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 12 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 |
---|---|
5.0 |
|
9.0 |
|
3.0 |
|
10.0 |
|
2.0 |
|
0.0 |
|
11.0 |
|
8.0 |
|
6.0 |
|
7.0 |
|
4.0 |
|
1.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.6903 |
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("mini1013/master_cate_bt9_test")
# Run inference
preds = model("[당일출고] 비플레인 녹두 약산성 클렌징폼 160ml 옵션없음 제이에이치컴퍼니")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.0359 | 19 |
Label | Training Sample Count |
---|---|
0.0 | 20 |
1.0 | 27 |
2.0 | 20 |
3.0 | 27 |
4.0 | 15 |
5.0 | 20 |
6.0 | 20 |
7.0 | 18 |
8.0 | 20 |
9.0 | 22 |
10.0 | 17 |
11.0 | 25 |
Training Hyperparameters
- batch_size: (512, 512)
- num_epochs: (50, 50)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 60
- 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 |
---|---|---|---|
0.0333 | 1 | 0.4927 | - |
1.6667 | 50 | 0.4009 | - |
3.3333 | 100 | 0.1238 | - |
5.0 | 150 | 0.0523 | - |
6.6667 | 200 | 0.0156 | - |
8.3333 | 250 | 0.0022 | - |
10.0 | 300 | 0.0003 | - |
11.6667 | 350 | 0.0002 | - |
13.3333 | 400 | 0.0002 | - |
15.0 | 450 | 0.0001 | - |
16.6667 | 500 | 0.0001 | - |
18.3333 | 550 | 0.0001 | - |
20.0 | 600 | 0.0001 | - |
21.6667 | 650 | 0.0001 | - |
23.3333 | 700 | 0.0001 | - |
25.0 | 750 | 0.0001 | - |
26.6667 | 800 | 0.0001 | - |
28.3333 | 850 | 0.0001 | - |
30.0 | 900 | 0.0001 | - |
31.6667 | 950 | 0.0001 | - |
33.3333 | 1000 | 0.0001 | - |
35.0 | 1050 | 0.0001 | - |
36.6667 | 1100 | 0.0001 | - |
38.3333 | 1150 | 0.0001 | - |
40.0 | 1200 | 0.0001 | - |
41.6667 | 1250 | 0.0001 | - |
43.3333 | 1300 | 0.0001 | - |
45.0 | 1350 | 0.0 | - |
46.6667 | 1400 | 0.0 | - |
48.3333 | 1450 | 0.0001 | - |
50.0 | 1500 | 0.0 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- 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.