metadata
base_model: klue/roberta-base
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 7 GRAB ME 레드 생로랑 Volupte 리퀴드 컬러 Balm 풀사이즈 B 20대여자 옵션없음 남인터내셔널
- text: 힐러랩 울트라본드 케라틴 단백질 트리트먼트 500ml 옵션없음 주식회사 와이제이비앤
- text: 바이오더마 센시비오 클렌징밀크 250ml 옵션없음 주식회사 하이유로
- text: 에스테티카 데미지 케어 컨센트레이트120ml /헤어오일 에센스 세럼 옵션없음 주식회사 베로유코스메틱
- text: 브이티코스메틱 VT 리들샷 700 시너지리페어 크림 옵션없음 북극곰마켓
inference: true
model-index:
- name: SetFit with klue/roberta-base
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.7873765467135884
name: Accuracy
SetFit with klue/roberta-base
This is a SetFit model that can be used for Text Classification. This SetFit model uses klue/roberta-base 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: klue/roberta-base
- 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 |
---|---|
1.0 |
|
7.0 |
|
12.0 |
|
2.0 |
|
8.0 |
|
6.0 |
|
0.0 |
|
4.0 |
|
9.0 |
|
10.0 |
|
11.0 |
|
5.0 |
|
3.0 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.7874 |
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_item_bt_test")
# Run inference
preds = model("바이오더마 센시비오 클렌징밀크 250ml 옵션없음 주식회사 하이유로")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.3971 | 26 |
Label | Training Sample Count |
---|---|
0.0 | 242 |
1.0 | 134 |
2.0 | 161 |
3.0 | 324 |
4.0 | 141 |
5.0 | 130 |
6.0 | 267 |
7.0 | 133 |
8.0 | 257 |
9.0 | 251 |
10.0 | 63 |
11.0 | 117 |
12.0 | 152 |
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 |
---|---|---|---|
0.0036 | 1 | 0.4112 | - |
0.1799 | 50 | 0.3996 | - |
0.3597 | 100 | 0.3542 | - |
0.5396 | 150 | 0.3073 | - |
0.7194 | 200 | 0.2654 | - |
0.8993 | 250 | 0.2289 | - |
1.0791 | 300 | 0.1949 | - |
1.2590 | 350 | 0.1619 | - |
1.4388 | 400 | 0.1254 | - |
1.6187 | 450 | 0.0899 | - |
1.7986 | 500 | 0.0645 | - |
1.9784 | 550 | 0.0506 | - |
2.1583 | 600 | 0.0403 | - |
2.3381 | 650 | 0.0365 | - |
2.5180 | 700 | 0.0342 | - |
2.6978 | 750 | 0.0329 | - |
2.8777 | 800 | 0.0302 | - |
3.0576 | 850 | 0.0286 | - |
3.2374 | 900 | 0.0272 | - |
3.4173 | 950 | 0.0246 | - |
3.5971 | 1000 | 0.0229 | - |
3.7770 | 1050 | 0.0206 | - |
3.9568 | 1100 | 0.0139 | - |
4.1367 | 1150 | 0.0083 | - |
4.3165 | 1200 | 0.0071 | - |
4.4964 | 1250 | 0.0071 | - |
4.6763 | 1300 | 0.0057 | - |
4.8561 | 1350 | 0.0045 | - |
5.0360 | 1400 | 0.0036 | - |
5.2158 | 1450 | 0.0031 | - |
5.3957 | 1500 | 0.0011 | - |
5.5755 | 1550 | 0.0006 | - |
5.7554 | 1600 | 0.0004 | - |
5.9353 | 1650 | 0.0004 | - |
6.1151 | 1700 | 0.0003 | - |
6.2950 | 1750 | 0.0003 | - |
6.4748 | 1800 | 0.0002 | - |
6.6547 | 1850 | 0.0002 | - |
6.8345 | 1900 | 0.0002 | - |
7.0144 | 1950 | 0.0002 | - |
7.1942 | 2000 | 0.0002 | - |
7.3741 | 2050 | 0.0002 | - |
7.5540 | 2100 | 0.0001 | - |
7.7338 | 2150 | 0.0002 | - |
7.9137 | 2200 | 0.0001 | - |
8.0935 | 2250 | 0.0001 | - |
8.2734 | 2300 | 0.0002 | - |
8.4532 | 2350 | 0.0002 | - |
8.6331 | 2400 | 0.0005 | - |
8.8129 | 2450 | 0.0003 | - |
8.9928 | 2500 | 0.0002 | - |
9.1727 | 2550 | 0.0001 | - |
9.3525 | 2600 | 0.0001 | - |
9.5324 | 2650 | 0.0002 | - |
9.7122 | 2700 | 0.0001 | - |
9.8921 | 2750 | 0.0002 | - |
10.0719 | 2800 | 0.0001 | - |
10.2518 | 2850 | 0.0001 | - |
10.4317 | 2900 | 0.0002 | - |
10.6115 | 2950 | 0.0003 | - |
10.7914 | 3000 | 0.0002 | - |
10.9712 | 3050 | 0.0004 | - |
11.1511 | 3100 | 0.0003 | - |
11.3309 | 3150 | 0.0002 | - |
11.5108 | 3200 | 0.0001 | - |
11.6906 | 3250 | 0.0001 | - |
11.8705 | 3300 | 0.0001 | - |
12.0504 | 3350 | 0.0001 | - |
12.2302 | 3400 | 0.0 | - |
12.4101 | 3450 | 0.0 | - |
12.5899 | 3500 | 0.0001 | - |
12.7698 | 3550 | 0.0001 | - |
12.9496 | 3600 | 0.0003 | - |
13.1295 | 3650 | 0.0002 | - |
13.3094 | 3700 | 0.0002 | - |
13.4892 | 3750 | 0.0004 | - |
13.6691 | 3800 | 0.0002 | - |
13.8489 | 3850 | 0.0001 | - |
14.0288 | 3900 | 0.0001 | - |
14.2086 | 3950 | 0.0002 | - |
14.3885 | 4000 | 0.0001 | - |
14.5683 | 4050 | 0.0001 | - |
14.7482 | 4100 | 0.0 | - |
14.9281 | 4150 | 0.0001 | - |
15.1079 | 4200 | 0.0003 | - |
15.2878 | 4250 | 0.0002 | - |
15.4676 | 4300 | 0.0001 | - |
15.6475 | 4350 | 0.0001 | - |
15.8273 | 4400 | 0.0 | - |
16.0072 | 4450 | 0.0 | - |
16.1871 | 4500 | 0.0 | - |
16.3669 | 4550 | 0.0 | - |
16.5468 | 4600 | 0.0 | - |
16.7266 | 4650 | 0.0 | - |
16.9065 | 4700 | 0.0 | - |
17.0863 | 4750 | 0.0 | - |
17.2662 | 4800 | 0.0001 | - |
17.4460 | 4850 | 0.0 | - |
17.6259 | 4900 | 0.0 | - |
17.8058 | 4950 | 0.0 | - |
17.9856 | 5000 | 0.0002 | - |
18.1655 | 5050 | 0.0002 | - |
18.3453 | 5100 | 0.0002 | - |
18.5252 | 5150 | 0.0005 | - |
18.7050 | 5200 | 0.0001 | - |
18.8849 | 5250 | 0.0 | - |
19.0647 | 5300 | 0.0 | - |
19.2446 | 5350 | 0.0 | - |
19.4245 | 5400 | 0.0 | - |
19.6043 | 5450 | 0.0 | - |
19.7842 | 5500 | 0.0 | - |
19.9640 | 5550 | 0.0001 | - |
20.1439 | 5600 | 0.0 | - |
20.3237 | 5650 | 0.0001 | - |
20.5036 | 5700 | 0.0002 | - |
20.6835 | 5750 | 0.0001 | - |
20.8633 | 5800 | 0.0001 | - |
21.0432 | 5850 | 0.0003 | - |
21.2230 | 5900 | 0.0002 | - |
21.4029 | 5950 | 0.0001 | - |
21.5827 | 6000 | 0.0 | - |
21.7626 | 6050 | 0.0 | - |
21.9424 | 6100 | 0.0 | - |
22.1223 | 6150 | 0.0 | - |
22.3022 | 6200 | 0.0 | - |
22.4820 | 6250 | 0.0 | - |
22.6619 | 6300 | 0.0 | - |
22.8417 | 6350 | 0.0 | - |
23.0216 | 6400 | 0.0 | - |
23.2014 | 6450 | 0.0 | - |
23.3813 | 6500 | 0.0 | - |
23.5612 | 6550 | 0.0 | - |
23.7410 | 6600 | 0.0 | - |
23.9209 | 6650 | 0.0 | - |
24.1007 | 6700 | 0.0 | - |
24.2806 | 6750 | 0.0 | - |
24.4604 | 6800 | 0.0 | - |
24.6403 | 6850 | 0.0 | - |
24.8201 | 6900 | 0.0 | - |
25.0 | 6950 | 0.0 | - |
25.1799 | 7000 | 0.0 | - |
25.3597 | 7050 | 0.0 | - |
25.5396 | 7100 | 0.0 | - |
25.7194 | 7150 | 0.0 | - |
25.8993 | 7200 | 0.0001 | - |
26.0791 | 7250 | 0.0001 | - |
26.2590 | 7300 | 0.0005 | - |
26.4388 | 7350 | 0.0002 | - |
26.6187 | 7400 | 0.0 | - |
26.7986 | 7450 | 0.0 | - |
26.9784 | 7500 | 0.0 | - |
27.1583 | 7550 | 0.0 | - |
27.3381 | 7600 | 0.0 | - |
27.5180 | 7650 | 0.0 | - |
27.6978 | 7700 | 0.0 | - |
27.8777 | 7750 | 0.0002 | - |
28.0576 | 7800 | 0.0001 | - |
28.2374 | 7850 | 0.0001 | - |
28.4173 | 7900 | 0.0 | - |
28.5971 | 7950 | 0.0001 | - |
28.7770 | 8000 | 0.0001 | - |
28.9568 | 8050 | 0.0001 | - |
29.1367 | 8100 | 0.0001 | - |
29.3165 | 8150 | 0.0001 | - |
29.4964 | 8200 | 0.0 | - |
29.6763 | 8250 | 0.0 | - |
29.8561 | 8300 | 0.0 | - |
30.0360 | 8350 | 0.0 | - |
30.2158 | 8400 | 0.0 | - |
30.3957 | 8450 | 0.0 | - |
30.5755 | 8500 | 0.0 | - |
30.7554 | 8550 | 0.0 | - |
30.9353 | 8600 | 0.0 | - |
31.1151 | 8650 | 0.0 | - |
31.2950 | 8700 | 0.0 | - |
31.4748 | 8750 | 0.0 | - |
31.6547 | 8800 | 0.0 | - |
31.8345 | 8850 | 0.0 | - |
32.0144 | 8900 | 0.0 | - |
32.1942 | 8950 | 0.0 | - |
32.3741 | 9000 | 0.0 | - |
32.5540 | 9050 | 0.0 | - |
32.7338 | 9100 | 0.0 | - |
32.9137 | 9150 | 0.0 | - |
33.0935 | 9200 | 0.0 | - |
33.2734 | 9250 | 0.0 | - |
33.4532 | 9300 | 0.0 | - |
33.6331 | 9350 | 0.0 | - |
33.8129 | 9400 | 0.0 | - |
33.9928 | 9450 | 0.0 | - |
34.1727 | 9500 | 0.0 | - |
34.3525 | 9550 | 0.0001 | - |
34.5324 | 9600 | 0.0 | - |
34.7122 | 9650 | 0.0 | - |
34.8921 | 9700 | 0.0 | - |
35.0719 | 9750 | 0.0 | - |
35.2518 | 9800 | 0.0 | - |
35.4317 | 9850 | 0.0001 | - |
35.6115 | 9900 | 0.0 | - |
35.7914 | 9950 | 0.0 | - |
35.9712 | 10000 | 0.0 | - |
36.1511 | 10050 | 0.0 | - |
36.3309 | 10100 | 0.0 | - |
36.5108 | 10150 | 0.0 | - |
36.6906 | 10200 | 0.0 | - |
36.8705 | 10250 | 0.0 | - |
37.0504 | 10300 | 0.0 | - |
37.2302 | 10350 | 0.0 | - |
37.4101 | 10400 | 0.0 | - |
37.5899 | 10450 | 0.0 | - |
37.7698 | 10500 | 0.0 | - |
37.9496 | 10550 | 0.0 | - |
38.1295 | 10600 | 0.0 | - |
38.3094 | 10650 | 0.0 | - |
38.4892 | 10700 | 0.0 | - |
38.6691 | 10750 | 0.0 | - |
38.8489 | 10800 | 0.0 | - |
39.0288 | 10850 | 0.0 | - |
39.2086 | 10900 | 0.0 | - |
39.3885 | 10950 | 0.0 | - |
39.5683 | 11000 | 0.0 | - |
39.7482 | 11050 | 0.0 | - |
39.9281 | 11100 | 0.0 | - |
40.1079 | 11150 | 0.0 | - |
40.2878 | 11200 | 0.0 | - |
40.4676 | 11250 | 0.0 | - |
40.6475 | 11300 | 0.0 | - |
40.8273 | 11350 | 0.0 | - |
41.0072 | 11400 | 0.0 | - |
41.1871 | 11450 | 0.0 | - |
41.3669 | 11500 | 0.0 | - |
41.5468 | 11550 | 0.0 | - |
41.7266 | 11600 | 0.0 | - |
41.9065 | 11650 | 0.0 | - |
42.0863 | 11700 | 0.0 | - |
42.2662 | 11750 | 0.0 | - |
42.4460 | 11800 | 0.0 | - |
42.6259 | 11850 | 0.0 | - |
42.8058 | 11900 | 0.0 | - |
42.9856 | 11950 | 0.0 | - |
43.1655 | 12000 | 0.0 | - |
43.3453 | 12050 | 0.0 | - |
43.5252 | 12100 | 0.0 | - |
43.7050 | 12150 | 0.0 | - |
43.8849 | 12200 | 0.0 | - |
44.0647 | 12250 | 0.0 | - |
44.2446 | 12300 | 0.0 | - |
44.4245 | 12350 | 0.0 | - |
44.6043 | 12400 | 0.0 | - |
44.7842 | 12450 | 0.0 | - |
44.9640 | 12500 | 0.0 | - |
45.1439 | 12550 | 0.0 | - |
45.3237 | 12600 | 0.0 | - |
45.5036 | 12650 | 0.0 | - |
45.6835 | 12700 | 0.0 | - |
45.8633 | 12750 | 0.0 | - |
46.0432 | 12800 | 0.0 | - |
46.2230 | 12850 | 0.0 | - |
46.4029 | 12900 | 0.0 | - |
46.5827 | 12950 | 0.0 | - |
46.7626 | 13000 | 0.0 | - |
46.9424 | 13050 | 0.0 | - |
47.1223 | 13100 | 0.0 | - |
47.3022 | 13150 | 0.0 | - |
47.4820 | 13200 | 0.0 | - |
47.6619 | 13250 | 0.0 | - |
47.8417 | 13300 | 0.0 | - |
48.0216 | 13350 | 0.0 | - |
48.2014 | 13400 | 0.0 | - |
48.3813 | 13450 | 0.0 | - |
48.5612 | 13500 | 0.0 | - |
48.7410 | 13550 | 0.0 | - |
48.9209 | 13600 | 0.0 | - |
49.1007 | 13650 | 0.0 | - |
49.2806 | 13700 | 0.0 | - |
49.4604 | 13750 | 0.0 | - |
49.6403 | 13800 | 0.0 | - |
49.8201 | 13850 | 0.0 | - |
50.0 | 13900 | 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}
}