metadata
base_model: mini1013/master_domain
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 오너클랜 블랙헤드 클리닝 24개입 코팩 스킨애 대용량 참숯 옵션없음 모던벙커
- text: 히든올가 히아루론산 마스크 400g 옵션없음 판타시아
- text: '[셀러허브 1]프롬더스킨 글루타치온 콜라겐 팩 50g 1개 RS 기본 에스케이스토아주식회사'
- text: 볼라욘 스피넴 파우더500g(모델링 마스크)+샘플+팩도구세트 옵션없음 수애
- text: 피부관리실/피부 미용 실기 비타민 열석고 1kg 황토 석고 700g 주식회사 엔에프코리아
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: accuracy
value: 0.6112115732368897
name: Accuracy
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: 8 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 |
---|---|
1.0 |
|
6.0 |
|
5.0 |
|
4.0 |
|
7.0 |
|
2.0 |
|
3.0 |
|
0.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.6112 |
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_bt2_test")
# Run inference
preds = model("히든올가 히아루론산 마스크 400g 옵션없음 판타시아")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.7453 | 23 |
Label | Training Sample Count |
---|---|
0.0 | 16 |
1.0 | 10 |
2.0 | 42 |
3.0 | 21 |
4.0 | 20 |
5.0 | 19 |
6.0 | 15 |
7.0 | 18 |
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 |
---|---|---|---|
0.0526 | 1 | 0.4875 | - |
2.6316 | 50 | 0.3322 | - |
5.2632 | 100 | 0.0442 | - |
7.8947 | 150 | 0.0025 | - |
10.5263 | 200 | 0.0002 | - |
13.1579 | 250 | 0.0001 | - |
15.7895 | 300 | 0.0001 | - |
18.4211 | 350 | 0.0001 | - |
21.0526 | 400 | 0.0001 | - |
23.6842 | 450 | 0.0001 | - |
26.3158 | 500 | 0.0001 | - |
28.9474 | 550 | 0.0001 | - |
31.5789 | 600 | 0.0001 | - |
34.2105 | 650 | 0.0001 | - |
36.8421 | 700 | 0.0001 | - |
39.4737 | 750 | 0.0001 | - |
42.1053 | 800 | 0.0001 | - |
44.7368 | 850 | 0.0001 | - |
47.3684 | 900 | 0.0001 | - |
50.0 | 950 | 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}
}