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: 17 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 |
|
13.0 |
|
12.0 |
|
8.0 |
|
11.0 |
|
1.0 |
|
6.0 |
|
14.0 |
|
0.0 |
|
7.0 |
|
3.0 |
|
15.0 |
|
4.0 |
|
2.0 |
|
9.0 |
|
16.0 |
|
10.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.7189 |
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_bt3_test")
# Run inference
preds = model("아로마티카 퓨어 앤 소프트 여성청결제 170ml (폼타입) 옵션없음 포사도")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.3333 | 20 |
Label | Training Sample Count |
---|---|
0.0 | 22 |
1.0 | 20 |
2.0 | 20 |
3.0 | 12 |
4.0 | 21 |
5.0 | 18 |
6.0 | 23 |
7.0 | 15 |
8.0 | 20 |
9.0 | 20 |
10.0 | 11 |
11.0 | 15 |
12.0 | 20 |
13.0 | 23 |
14.0 | 21 |
15.0 | 22 |
16.0 | 21 |
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 |
---|---|---|---|
0.0263 | 1 | 0.5057 | - |
1.3158 | 50 | 0.423 | - |
2.6316 | 100 | 0.1568 | - |
3.9474 | 150 | 0.067 | - |
5.2632 | 200 | 0.0479 | - |
6.5789 | 250 | 0.0324 | - |
7.8947 | 300 | 0.0196 | - |
9.2105 | 350 | 0.0138 | - |
10.5263 | 400 | 0.0111 | - |
11.8421 | 450 | 0.0051 | - |
13.1579 | 500 | 0.0041 | - |
14.4737 | 550 | 0.0043 | - |
15.7895 | 600 | 0.0026 | - |
17.1053 | 650 | 0.0005 | - |
18.4211 | 700 | 0.0003 | - |
19.7368 | 750 | 0.0002 | - |
21.0526 | 800 | 0.0002 | - |
22.3684 | 850 | 0.0002 | - |
23.6842 | 900 | 0.0002 | - |
25.0 | 950 | 0.0002 | - |
26.3158 | 1000 | 0.0001 | - |
27.6316 | 1050 | 0.0001 | - |
28.9474 | 1100 | 0.0001 | - |
30.2632 | 1150 | 0.0001 | - |
31.5789 | 1200 | 0.0001 | - |
32.8947 | 1250 | 0.0001 | - |
34.2105 | 1300 | 0.0001 | - |
35.5263 | 1350 | 0.0001 | - |
36.8421 | 1400 | 0.0001 | - |
38.1579 | 1450 | 0.0001 | - |
39.4737 | 1500 | 0.0001 | - |
40.7895 | 1550 | 0.0001 | - |
42.1053 | 1600 | 0.0001 | - |
43.4211 | 1650 | 0.0001 | - |
44.7368 | 1700 | 0.0001 | - |
46.0526 | 1750 | 0.0001 | - |
47.3684 | 1800 | 0.0001 | - |
48.6842 | 1850 | 0.0001 | - |
50.0 | 1900 | 0.0001 | - |
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
- 13
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.