metadata
base_model: mini1013/setfit_robeta_base_s_domain
library_name: setfit
metrics:
- metric
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
[7매입/14매입] 마이크로바이옴 비건 모델링팩 모공 수축 수분 진정 마스크 팩 1set 1. 모델링팩 1set (7매입) 주식회사
에이치티오인터내셔널
- text: 더후 공진향 인양 넥앤페이스 탄력 리페어75ml 옵션없음 씨플랩
- text: 빌리프 슈퍼 나이츠-리제너레이팅 나이트 마스크 75ml 옵션없음 라임쇼핑
- text: 수이스킨 편안한 진정초 시트 마스크 5개입 × 1개 민물유통
- text: 참존 지안 극결 콘트롤 크림 225ml (리뉴얼제품) 옵션없음 슈슈
inference: true
model-index:
- name: SetFit with mini1013/setfit_robeta_base_s_domain
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: metric
value: 0.7714285714285715
name: Metric
SetFit with mini1013/setfit_robeta_base_s_domain
This is a SetFit model that can be used for Text Classification. This SetFit model uses mini1013/setfit_robeta_base_s_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/setfit_robeta_base_s_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 |
---|---|
4 |
|
5 |
|
3 |
|
2 |
|
6 |
|
0 |
|
1 |
|
7 |
|
Evaluation
Metrics
Label | Metric |
---|---|
all | 0.7714 |
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")
# Run inference
preds = model("수이스킨 편안한 진정초 시트 마스크 5개입 × 1개 민물유통")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.8591 | 27 |
Label | Training Sample Count |
---|---|
0 | 90 |
1 | 78 |
2 | 88 |
3 | 95 |
4 | 94 |
5 | 90 |
6 | 84 |
7 | 34 |
Training Hyperparameters
- batch_size: (512, 512)
- num_epochs: (20, 20)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 30
- 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 |
---|---|---|---|
0.0130 | 1 | 0.4922 | - |
0.6494 | 50 | 0.2317 | - |
1.2987 | 100 | 0.0726 | - |
1.9481 | 150 | 0.033 | - |
2.5974 | 200 | 0.0322 | - |
3.2468 | 250 | 0.0056 | - |
3.8961 | 300 | 0.001 | - |
4.5455 | 350 | 0.0003 | - |
5.1948 | 400 | 0.0001 | - |
5.8442 | 450 | 0.0001 | - |
6.4935 | 500 | 0.0001 | - |
7.1429 | 550 | 0.0002 | - |
7.7922 | 600 | 0.0001 | - |
8.4416 | 650 | 0.0001 | - |
9.0909 | 700 | 0.0001 | - |
9.7403 | 750 | 0.0001 | - |
10.3896 | 800 | 0.0006 | - |
11.0390 | 850 | 0.0001 | - |
11.6883 | 900 | 0.0001 | - |
12.3377 | 950 | 0.0001 | - |
12.9870 | 1000 | 0.0 | - |
13.6364 | 1050 | 0.0 | - |
14.2857 | 1100 | 0.0 | - |
14.9351 | 1150 | 0.0 | - |
15.5844 | 1200 | 0.0 | - |
16.2338 | 1250 | 0.0 | - |
16.8831 | 1300 | 0.0 | - |
17.5325 | 1350 | 0.0 | - |
18.1818 | 1400 | 0.0 | - |
18.8312 | 1450 | 0.0 | - |
19.4805 | 1500 | 0.0 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0.dev0
- Sentence Transformers: 3.1.1
- Transformers: 4.45.1
- 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}
}