metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 탑키드 만들기 경찰관 놀이 세트 3인용 가구/인테리어>수예>기타수예
- text: 일상공방 코 손뜨개 6종세트 인디핑크 421114 가구/인테리어>수예>뜨개질>완제품
- text: 퀼트가게6마 반폭롤 면 100 20수 도기 프렌즈 WS 792 원단 가구/인테리어>수예>퀼트/펠트>원단
- text: 펠트 구절초 대 SET 환경꾸미기재료 가구/인테리어>수예>퀼트/펠트>도안
- text: 광목침구 촬영용 빈티지 플라워 코튼 포플린 드레스 셔츠 섬유 린넨 대폭원단 가구/인테리어>수예>자수>원단
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: mini1013/master_domain
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: 1
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: 7 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 |
---|---|
6.0 |
|
4.0 |
|
3.0 |
|
1.0 |
|
0.0 |
|
5.0 |
|
2.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 1.0 |
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_fi6")
# Run inference
preds = model("탑키드 만들기 경찰관 놀이 세트 3인용 가구/인테리어>수예>기타수예")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 2 | 8.8714 | 24 |
Label | Training Sample Count |
---|---|
0.0 | 70 |
1.0 | 70 |
2.0 | 70 |
3.0 | 70 |
4.0 | 70 |
5.0 | 70 |
6.0 | 70 |
Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- 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 |
---|---|---|---|
0.0104 | 1 | 0.5007 | - |
0.5208 | 50 | 0.4969 | - |
1.0417 | 100 | 0.4332 | - |
1.5625 | 150 | 0.0551 | - |
2.0833 | 200 | 0.0001 | - |
2.6042 | 250 | 0.0 | - |
3.125 | 300 | 0.0 | - |
3.6458 | 350 | 0.0 | - |
4.1667 | 400 | 0.0 | - |
4.6875 | 450 | 0.0 | - |
5.2083 | 500 | 0.0 | - |
5.7292 | 550 | 0.0 | - |
6.25 | 600 | 0.0 | - |
6.7708 | 650 | 0.0 | - |
7.2917 | 700 | 0.0 | - |
7.8125 | 750 | 0.0 | - |
8.3333 | 800 | 0.0 | - |
8.8542 | 850 | 0.0 | - |
9.375 | 900 | 0.0 | - |
9.8958 | 950 | 0.0 | - |
10.4167 | 1000 | 0.0 | - |
10.9375 | 1050 | 0.0 | - |
11.4583 | 1100 | 0.0 | - |
11.9792 | 1150 | 0.0 | - |
12.5 | 1200 | 0.0 | - |
13.0208 | 1250 | 0.0 | - |
13.5417 | 1300 | 0.0 | - |
14.0625 | 1350 | 0.0 | - |
14.5833 | 1400 | 0.0 | - |
15.1042 | 1450 | 0.0 | - |
15.625 | 1500 | 0.0 | - |
16.1458 | 1550 | 0.0 | - |
16.6667 | 1600 | 0.0 | - |
17.1875 | 1650 | 0.0 | - |
17.7083 | 1700 | 0.0 | - |
18.2292 | 1750 | 0.0 | - |
18.75 | 1800 | 0.0 | - |
19.2708 | 1850 | 0.0 | - |
19.7917 | 1900 | 0.0 | - |
20.3125 | 1950 | 0.0 | - |
20.8333 | 2000 | 0.0 | - |
21.3542 | 2050 | 0.0 | - |
21.875 | 2100 | 0.0 | - |
22.3958 | 2150 | 0.0 | - |
22.9167 | 2200 | 0.0 | - |
23.4375 | 2250 | 0.0 | - |
23.9583 | 2300 | 0.0 | - |
24.4792 | 2350 | 0.0 | - |
25.0 | 2400 | 0.0 | - |
25.5208 | 2450 | 0.0 | - |
26.0417 | 2500 | 0.0 | - |
26.5625 | 2550 | 0.0 | - |
27.0833 | 2600 | 0.0 | - |
27.6042 | 2650 | 0.0 | - |
28.125 | 2700 | 0.0 | - |
28.6458 | 2750 | 0.0 | - |
29.1667 | 2800 | 0.0 | - |
29.6875 | 2850 | 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}
}