metadata
base_model: mini1013/master_domain
library_name: setfit
metrics:
- metric
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 파인트리 홀그레인 머스타드 850g (주)우주식품디씨오피
- text: 오뚜기 오쉐프 마요네스 3.2kg 이금기 팬더굴소스 2kg 디에치커머스 주식회사
- text: 샘표 샤브샤브 담백한 육수 200g 외 10종 / 샤브육수소스 10. 티아시아 피넛소스 275g 주식회사 통통마트
- text: 해천 시그니처 굴소스 캔 2.27kg 대륙 깊은맛 주식회사 다솜식자재유통
- text: 청정원 토마토와 생크림 로제 스파게티소스 2kg 호호푸드
inference: true
model-index:
- name: SetFit with mini1013/master_domain
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: metric
value: 0.9092549161104095
name: Metric
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: 13 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 |
|
11.0 |
|
2.0 |
|
6.0 |
|
0.0 |
|
4.0 |
|
8.0 |
|
3.0 |
|
10.0 |
|
1.0 |
|
7.0 |
|
9.0 |
|
12.0 |
|
Evaluation
Metrics
Label | Metric |
---|---|
all | 0.9093 |
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_fd10")
# Run inference
preds = model("파인트리 홀그레인 머스타드 850g (주)우주식품디씨오피")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 8.5284 | 19 |
Label | Training Sample Count |
---|---|
0.0 | 50 |
1.0 | 50 |
2.0 | 50 |
3.0 | 50 |
4.0 | 50 |
5.0 | 50 |
6.0 | 50 |
7.0 | 50 |
8.0 | 50 |
9.0 | 16 |
10.0 | 50 |
11.0 | 50 |
12.0 | 15 |
Training Hyperparameters
- batch_size: (512, 512)
- num_epochs: (20, 20)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 40
- 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 |
---|---|---|---|
0.0110 | 1 | 0.4378 | - |
0.5495 | 50 | 0.381 | - |
1.0989 | 100 | 0.1591 | - |
1.6484 | 150 | 0.0501 | - |
2.1978 | 200 | 0.0362 | - |
2.7473 | 250 | 0.0292 | - |
3.2967 | 300 | 0.0296 | - |
3.8462 | 350 | 0.0276 | - |
4.3956 | 400 | 0.0177 | - |
4.9451 | 450 | 0.007 | - |
5.4945 | 500 | 0.014 | - |
6.0440 | 550 | 0.0012 | - |
6.5934 | 600 | 0.0001 | - |
7.1429 | 650 | 0.0001 | - |
7.6923 | 700 | 0.0001 | - |
8.2418 | 750 | 0.0001 | - |
8.7912 | 800 | 0.0001 | - |
9.3407 | 850 | 0.0001 | - |
9.8901 | 900 | 0.0001 | - |
10.4396 | 950 | 0.0001 | - |
10.9890 | 1000 | 0.0001 | - |
11.5385 | 1050 | 0.0001 | - |
12.0879 | 1100 | 0.0001 | - |
12.6374 | 1150 | 0.0001 | - |
13.1868 | 1200 | 0.0001 | - |
13.7363 | 1250 | 0.0001 | - |
14.2857 | 1300 | 0.0001 | - |
14.8352 | 1350 | 0.0 | - |
15.3846 | 1400 | 0.0001 | - |
15.9341 | 1450 | 0.0001 | - |
16.4835 | 1500 | 0.0001 | - |
17.0330 | 1550 | 0.0001 | - |
17.5824 | 1600 | 0.0 | - |
18.1319 | 1650 | 0.0 | - |
18.6813 | 1700 | 0.0 | - |
19.2308 | 1750 | 0.0 | - |
19.7802 | 1800 | 0.0001 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0.dev0
- Sentence Transformers: 3.1.1
- Transformers: 4.46.1
- PyTorch: 2.4.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.20.0
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}
}