--- 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: 쿠쿠 CP-PS011T 자동살균직수정수기 (등록설치비면제/3년무상AS/조리수무료/3년정품필터 ) 쿠쿠본사무료설치/색상선택가능 골드(CP-PS011G)_미설치(X) 쿠쿠홈시스공식인증점 - text: LG전자 오브제컬렉션 매직스페이스 냉장고 (S834PB35) (UP) 주식회사 디깅(Digging Inc.) - text: 리큅 10단 풀스텐 식품건조기 고추건조기 과일건조기 LID-1904S 주식회사 이스트코퍼레이션 - text: '[공인판매점] 키친에이드 아톰 오븐 5KCO211EBM 그릴 베이킹 토스트 (주)디아씨앤씨' - text: 쿠첸 인버터 복합 레인지 COV-i231KGF 홀리데이마켓 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: 0.8617920942607373 name: Metric --- # SetFit with mini1013/master_domain This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [mini1013/master_domain](https://huggingface.co/mini1013/master_domain) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. 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](https://huggingface.co/mini1013/master_domain) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 47 classes ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 45 | | | 0 | | | 32 | | | 39 | | | 3 | | | 13 | | | 41 | | | 18 | | | 42 | | | 38 | | | 33 | | | 37 | | | 27 | | | 31 | | | 43 | | | 2 | | | 26 | | | 44 | | | 5 | | | 22 | | | 30 | | | 34 | | | 14 | | | 4 | | | 21 | | | 17 | | | 36 | | | 10 | | | 16 | | | 20 | | | 40 | | | 15 | | | 23 | | | 7 | | | 25 | | | 46 | | | 24 | | | 29 | | | 12 | | | 11 | | | 28 | | | 1 | | | 6 | | | 9 | | | 35 | | | 8 | | | 19 | | ## Evaluation ### Metrics | Label | Metric | |:--------|:-------| | **all** | 0.8618 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("mini1013/master_cate_el17") # Run inference preds = model("쿠첸 인버터 복합 레인지 COV-i231KGF 홀리데이마켓") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:-------|:----| | Word count | 3 | 8.4377 | 25 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 50 | | 1 | 50 | | 2 | 50 | | 3 | 50 | | 4 | 50 | | 5 | 50 | | 6 | 50 | | 7 | 50 | | 8 | 4 | | 9 | 50 | | 10 | 50 | | 11 | 50 | | 12 | 50 | | 13 | 50 | | 14 | 50 | | 15 | 13 | | 16 | 50 | | 17 | 50 | | 18 | 50 | | 19 | 3 | | 20 | 50 | | 21 | 50 | | 22 | 50 | | 23 | 50 | | 24 | 50 | | 25 | 50 | | 26 | 50 | | 27 | 50 | | 28 | 50 | | 29 | 50 | | 30 | 50 | | 31 | 50 | | 32 | 50 | | 33 | 50 | | 34 | 50 | | 35 | 2 | | 36 | 50 | | 37 | 50 | | 38 | 50 | | 39 | 37 | | 40 | 50 | | 41 | 50 | | 42 | 50 | | 43 | 50 | | 44 | 50 | | 45 | 50 | | 46 | 50 | ### 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 | |:-------:|:----:|:-------------:|:---------------:| | 0.0030 | 1 | 0.4981 | - | | 0.1479 | 50 | 0.4962 | - | | 0.2959 | 100 | 0.3194 | - | | 0.4438 | 150 | 0.2125 | - | | 0.5917 | 200 | 0.1649 | - | | 0.7396 | 250 | 0.1254 | - | | 0.8876 | 300 | 0.0936 | - | | 1.0355 | 350 | 0.0739 | - | | 1.1834 | 400 | 0.0466 | - | | 1.3314 | 450 | 0.0464 | - | | 1.4793 | 500 | 0.0444 | - | | 1.6272 | 550 | 0.0447 | - | | 1.7751 | 600 | 0.0254 | - | | 1.9231 | 650 | 0.0264 | - | | 2.0710 | 700 | 0.0251 | - | | 2.2189 | 750 | 0.0321 | - | | 2.3669 | 800 | 0.0237 | - | | 2.5148 | 850 | 0.0203 | - | | 2.6627 | 900 | 0.0217 | - | | 2.8107 | 950 | 0.016 | - | | 2.9586 | 1000 | 0.014 | - | | 3.1065 | 1050 | 0.0076 | - | | 3.2544 | 1100 | 0.0096 | - | | 3.4024 | 1150 | 0.0118 | - | | 3.5503 | 1200 | 0.0058 | - | | 3.6982 | 1250 | 0.0121 | - | | 3.8462 | 1300 | 0.0126 | - | | 3.9941 | 1350 | 0.0064 | - | | 4.1420 | 1400 | 0.0046 | - | | 4.2899 | 1450 | 0.0061 | - | | 4.4379 | 1500 | 0.008 | - | | 4.5858 | 1550 | 0.0018 | - | | 4.7337 | 1600 | 0.0081 | - | | 4.8817 | 1650 | 0.0131 | - | | 5.0296 | 1700 | 0.008 | - | | 5.1775 | 1750 | 0.0069 | - | | 5.3254 | 1800 | 0.006 | - | | 5.4734 | 1850 | 0.0021 | - | | 5.6213 | 1900 | 0.0039 | - | | 5.7692 | 1950 | 0.0045 | - | | 5.9172 | 2000 | 0.0032 | - | | 6.0651 | 2050 | 0.0016 | - | | 6.2130 | 2100 | 0.0014 | - | | 6.3609 | 2150 | 0.0008 | - | | 6.5089 | 2200 | 0.0012 | - | | 6.6568 | 2250 | 0.0025 | - | | 6.8047 | 2300 | 0.0004 | - | | 6.9527 | 2350 | 0.0025 | - | | 7.1006 | 2400 | 0.0023 | - | | 7.2485 | 2450 | 0.0019 | - | | 7.3964 | 2500 | 0.004 | - | | 7.5444 | 2550 | 0.0021 | - | | 7.6923 | 2600 | 0.0019 | - | | 7.8402 | 2650 | 0.0041 | - | | 7.9882 | 2700 | 0.0014 | - | | 8.1361 | 2750 | 0.001 | - | | 8.2840 | 2800 | 0.0024 | - | | 8.4320 | 2850 | 0.0044 | - | | 8.5799 | 2900 | 0.0022 | - | | 8.7278 | 2950 | 0.0003 | - | | 8.8757 | 3000 | 0.0021 | - | | 9.0237 | 3050 | 0.0002 | - | | 9.1716 | 3100 | 0.0002 | - | | 9.3195 | 3150 | 0.002 | - | | 9.4675 | 3200 | 0.0002 | - | | 9.6154 | 3250 | 0.0002 | - | | 9.7633 | 3300 | 0.0002 | - | | 9.9112 | 3350 | 0.0003 | - | | 10.0592 | 3400 | 0.0002 | - | | 10.2071 | 3450 | 0.0003 | - | | 10.3550 | 3500 | 0.0003 | - | | 10.5030 | 3550 | 0.0002 | - | | 10.6509 | 3600 | 0.002 | - | | 10.7988 | 3650 | 0.0002 | - | | 10.9467 | 3700 | 0.0002 | - | | 11.0947 | 3750 | 0.0014 | - | | 11.2426 | 3800 | 0.0003 | - | | 11.3905 | 3850 | 0.0001 | - | | 11.5385 | 3900 | 0.0034 | - | | 11.6864 | 3950 | 0.0017 | - | | 11.8343 | 4000 | 0.0016 | - | | 11.9822 | 4050 | 0.0002 | - | | 12.1302 | 4100 | 0.0002 | - | | 12.2781 | 4150 | 0.0004 | - | | 12.4260 | 4200 | 0.0002 | - | | 12.5740 | 4250 | 0.0002 | - | | 12.7219 | 4300 | 0.0002 | - | | 12.8698 | 4350 | 0.0001 | - | | 13.0178 | 4400 | 0.0003 | - | | 13.1657 | 4450 | 0.0002 | - | | 13.3136 | 4500 | 0.0001 | - | | 13.4615 | 4550 | 0.0019 | - | | 13.6095 | 4600 | 0.0002 | - | | 13.7574 | 4650 | 0.0001 | - | | 13.9053 | 4700 | 0.0001 | - | | 14.0533 | 4750 | 0.0001 | - | | 14.2012 | 4800 | 0.0001 | - | | 14.3491 | 4850 | 0.0001 | - | | 14.4970 | 4900 | 0.0001 | - | | 14.6450 | 4950 | 0.0001 | - | | 14.7929 | 5000 | 0.0001 | - | | 14.9408 | 5050 | 0.0001 | - | | 15.0888 | 5100 | 0.0001 | - | | 15.2367 | 5150 | 0.0001 | - | | 15.3846 | 5200 | 0.0001 | - | | 15.5325 | 5250 | 0.0001 | - | | 15.6805 | 5300 | 0.0001 | - | | 15.8284 | 5350 | 0.0001 | - | | 15.9763 | 5400 | 0.0001 | - | | 16.1243 | 5450 | 0.0019 | - | | 16.2722 | 5500 | 0.0001 | - | | 16.4201 | 5550 | 0.0001 | - | | 16.5680 | 5600 | 0.0002 | - | | 16.7160 | 5650 | 0.0001 | - | | 16.8639 | 5700 | 0.0001 | - | | 17.0118 | 5750 | 0.0001 | - | | 17.1598 | 5800 | 0.0001 | - | | 17.3077 | 5850 | 0.0001 | - | | 17.4556 | 5900 | 0.0001 | - | | 17.6036 | 5950 | 0.0001 | - | | 17.7515 | 6000 | 0.0001 | - | | 17.8994 | 6050 | 0.0017 | - | | 18.0473 | 6100 | 0.0001 | - | | 18.1953 | 6150 | 0.0001 | - | | 18.3432 | 6200 | 0.0001 | - | | 18.4911 | 6250 | 0.0001 | - | | 18.6391 | 6300 | 0.0001 | - | | 18.7870 | 6350 | 0.0001 | - | | 18.9349 | 6400 | 0.0001 | - | | 19.0828 | 6450 | 0.0001 | - | | 19.2308 | 6500 | 0.0001 | - | | 19.3787 | 6550 | 0.0001 | - | | 19.5266 | 6600 | 0.0019 | - | | 19.6746 | 6650 | 0.0001 | - | | 19.8225 | 6700 | 0.0001 | - | | 19.9704 | 6750 | 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 ```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} } ```