--- base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: How much should I invest in communication activities? - text: In addition, we will consider public reactions and reviews of these works. - text: Grundlagen der Fachdidaktik Pädagogik - text: 'Die Einzelthemen umfassen: * Hard- and Software-Architecture of Modern Game Systems * Time Management in Milliseconds * Asset Loading and Compression * Physically Based Realtime Rendering and Animations * Handling of Large Game Scenes * Audio Simulation and Mixing * Constraint-Based Physics Simulation * Artificial Intelligence for Games * Multiplayer-Networking * Procedural Content Creation * Integration of Scripting Languages * Optimization and parallelization of CPU and GPU Code Die Übungen enthalten Theorie- und Praxisanteile.' - text: 'Wie entsteht überhaupt eine Ausstellung und in diesem Fall: eine, die weniger auf den Wert des Originals als die Kreativität ihrer Besucher setzt?' inference: false --- # SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) as the Sentence Transformer embedding model. A MultiOutputClassifier 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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) - **Classification head:** a MultiOutputClassifier instance - **Maximum Sequence Length:** 128 tokens - **Number of Classes:** 6 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) ## 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("Chernoffface/fs-setfit-multilable-model") # Run inference preds = model("Grundlagen der Fachdidaktik Pädagogik") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 1 | 12.9119 | 131 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (2, 2) - 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 - l2_weight: 0.01 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:-----:|:-------------:|:---------------:| | 0.0001 | 1 | 0.1571 | - | | 0.0063 | 50 | 0.1986 | - | | 0.0127 | 100 | 0.1774 | - | | 0.0190 | 150 | 0.136 | - | | 0.0254 | 200 | 0.1061 | - | | 0.0317 | 250 | 0.0779 | - | | 0.0380 | 300 | 0.0671 | - | | 0.0444 | 350 | 0.0482 | - | | 0.0507 | 400 | 0.0444 | - | | 0.0571 | 450 | 0.0427 | - | | 0.0634 | 500 | 0.0323 | - | | 0.0698 | 550 | 0.0274 | - | | 0.0761 | 600 | 0.0301 | - | | 0.0824 | 650 | 0.0259 | - | | 0.0888 | 700 | 0.0274 | - | | 0.0951 | 750 | 0.0305 | - | | 0.1015 | 800 | 0.0221 | - | | 0.1078 | 850 | 0.0185 | - | | 0.1141 | 900 | 0.0208 | - | | 0.1205 | 950 | 0.0198 | - | | 0.1268 | 1000 | 0.0107 | - | | 0.1332 | 1050 | 0.0149 | - | | 0.1395 | 1100 | 0.0162 | - | | 0.1458 | 1150 | 0.0119 | - | | 0.1522 | 1200 | 0.0162 | - | | 0.1585 | 1250 | 0.0133 | - | | 0.1649 | 1300 | 0.0177 | - | | 0.1712 | 1350 | 0.0102 | - | | 0.1776 | 1400 | 0.0224 | - | | 0.1839 | 1450 | 0.0107 | - | | 0.1902 | 1500 | 0.0182 | - | | 0.1966 | 1550 | 0.0137 | - | | 0.2029 | 1600 | 0.0158 | - | | 0.2093 | 1650 | 0.0142 | - | | 0.2156 | 1700 | 0.0117 | - | | 0.2219 | 1750 | 0.0161 | - | | 0.2283 | 1800 | 0.0128 | - | | 0.2346 | 1850 | 0.0118 | - | | 0.2410 | 1900 | 0.0125 | - | | 0.2473 | 1950 | 0.0135 | - | | 0.2536 | 2000 | 0.0123 | - | | 0.2600 | 2050 | 0.0128 | - | | 0.2663 | 2100 | 0.0119 | - | | 0.2727 | 2150 | 0.0074 | - | | 0.2790 | 2200 | 0.0116 | - | | 0.2854 | 2250 | 0.0088 | - | | 0.2917 | 2300 | 0.008 | - | | 0.2980 | 2350 | 0.0137 | - | | 0.3044 | 2400 | 0.0087 | - | | 0.3107 | 2450 | 0.0107 | - | | 0.3171 | 2500 | 0.0118 | - | | 0.3234 | 2550 | 0.0096 | - | | 0.3297 | 2600 | 0.0073 | - | | 0.3361 | 2650 | 0.0125 | - | | 0.3424 | 2700 | 0.0085 | - | | 0.3488 | 2750 | 0.0081 | - | | 0.3551 | 2800 | 0.0097 | - | | 0.3614 | 2850 | 0.0104 | - | | 0.3678 | 2900 | 0.0062 | - | | 0.3741 | 2950 | 0.0124 | - | | 0.3805 | 3000 | 0.0115 | - | | 0.3868 | 3050 | 0.012 | - | | 0.3932 | 3100 | 0.0147 | - | | 0.3995 | 3150 | 0.0097 | - | | 0.4058 | 3200 | 0.0107 | - | | 0.4122 | 3250 | 0.0074 | - | | 0.4185 | 3300 | 0.013 | - | | 0.4249 | 3350 | 0.0115 | - | | 0.4312 | 3400 | 0.008 | - | | 0.4375 | 3450 | 0.0087 | - | | 0.4439 | 3500 | 0.0099 | - | | 0.4502 | 3550 | 0.0076 | - | | 0.4566 | 3600 | 0.0118 | - | | 0.4629 | 3650 | 0.013 | - | | 0.4692 | 3700 | 0.0107 | - | | 0.4756 | 3750 | 0.0123 | - | | 0.4819 | 3800 | 0.0101 | - | | 0.4883 | 3850 | 0.0095 | - | | 0.4946 | 3900 | 0.01 | - | | 0.5010 | 3950 | 0.0068 | - | | 0.5073 | 4000 | 0.0064 | - | | 0.5136 | 4050 | 0.0096 | - | | 0.5200 | 4100 | 0.0063 | - | | 0.5263 | 4150 | 0.0083 | - | | 0.5327 | 4200 | 0.0067 | - | | 0.5390 | 4250 | 0.0095 | - | | 0.5453 | 4300 | 0.0097 | - | | 0.5517 | 4350 | 0.0057 | - | | 0.5580 | 4400 | 0.0101 | - | | 0.5644 | 4450 | 0.0101 | - | | 0.5707 | 4500 | 0.0043 | - | | 0.5770 | 4550 | 0.0099 | - | | 0.5834 | 4600 | 0.0091 | - | | 0.5897 | 4650 | 0.0065 | - | | 0.5961 | 4700 | 0.0071 | - | | 0.6024 | 4750 | 0.0035 | - | | 0.6088 | 4800 | 0.0088 | - | | 0.6151 | 4850 | 0.0079 | - | | 0.6214 | 4900 | 0.0094 | - | | 0.6278 | 4950 | 0.0105 | - | | 0.6341 | 5000 | 0.0091 | - | | 0.6405 | 5050 | 0.0109 | - | | 0.6468 | 5100 | 0.0081 | - | | 0.6531 | 5150 | 0.0087 | - | | 0.6595 | 5200 | 0.0091 | - | | 0.6658 | 5250 | 0.0071 | - | | 0.6722 | 5300 | 0.0072 | - | | 0.6785 | 5350 | 0.0084 | - | | 0.6848 | 5400 | 0.0099 | - | | 0.6912 | 5450 | 0.004 | - | | 0.6975 | 5500 | 0.0038 | - | | 0.7039 | 5550 | 0.0072 | - | | 0.7102 | 5600 | 0.0084 | - | | 0.7166 | 5650 | 0.004 | - | | 0.7229 | 5700 | 0.0077 | - | | 0.7292 | 5750 | 0.0066 | - | | 0.7356 | 5800 | 0.0043 | - | | 0.7419 | 5850 | 0.0054 | - | | 0.7483 | 5900 | 0.0107 | - | | 0.7546 | 5950 | 0.0046 | - | | 0.7609 | 6000 | 0.0075 | - | | 0.7673 | 6050 | 0.0106 | - | | 0.7736 | 6100 | 0.0063 | - | | 0.7800 | 6150 | 0.007 | - | | 0.7863 | 6200 | 0.0066 | - | | 0.7926 | 6250 | 0.0067 | - | | 0.7990 | 6300 | 0.0078 | - | | 0.8053 | 6350 | 0.0093 | - | | 0.8117 | 6400 | 0.0055 | - | | 0.8180 | 6450 | 0.0074 | - | | 0.8244 | 6500 | 0.0115 | - | | 0.8307 | 6550 | 0.0058 | - | | 0.8370 | 6600 | 0.005 | - | | 0.8434 | 6650 | 0.007 | - | | 0.8497 | 6700 | 0.0053 | - | | 0.8561 | 6750 | 0.0086 | - | | 0.8624 | 6800 | 0.0054 | - | | 0.8687 | 6850 | 0.0055 | - | | 0.8751 | 6900 | 0.006 | - | | 0.8814 | 6950 | 0.0068 | - | | 0.8878 | 7000 | 0.0103 | - | | 0.8941 | 7050 | 0.0054 | - | | 0.9004 | 7100 | 0.007 | - | | 0.9068 | 7150 | 0.0047 | - | | 0.9131 | 7200 | 0.0076 | - | | 0.9195 | 7250 | 0.0077 | - | | 0.9258 | 7300 | 0.0058 | - | | 0.9321 | 7350 | 0.0056 | - | | 0.9385 | 7400 | 0.0041 | - | | 0.9448 | 7450 | 0.0062 | - | | 0.9512 | 7500 | 0.0044 | - | | 0.9575 | 7550 | 0.0042 | - | | 0.9639 | 7600 | 0.0095 | - | | 0.9702 | 7650 | 0.0045 | - | | 0.9765 | 7700 | 0.0062 | - | | 0.9829 | 7750 | 0.0036 | - | | 0.9892 | 7800 | 0.0086 | - | | 0.9956 | 7850 | 0.0071 | - | | 1.0019 | 7900 | 0.0103 | - | | 1.0082 | 7950 | 0.004 | - | | 1.0146 | 8000 | 0.0059 | - | | 1.0209 | 8050 | 0.0053 | - | | 1.0273 | 8100 | 0.0079 | - | | 1.0336 | 8150 | 0.0078 | - | | 1.0399 | 8200 | 0.0077 | - | | 1.0463 | 8250 | 0.0062 | - | | 1.0526 | 8300 | 0.005 | - | | 1.0590 | 8350 | 0.0071 | - | | 1.0653 | 8400 | 0.0042 | - | | 1.0717 | 8450 | 0.0054 | - | | 1.0780 | 8500 | 0.0048 | - | | 1.0843 | 8550 | 0.0045 | - | | 1.0907 | 8600 | 0.0062 | - | | 1.0970 | 8650 | 0.0094 | - | | 1.1034 | 8700 | 0.0043 | - | | 1.1097 | 8750 | 0.004 | - | | 1.1160 | 8800 | 0.003 | - | | 1.1224 | 8850 | 0.0026 | - | | 1.1287 | 8900 | 0.0051 | - | | 1.1351 | 8950 | 0.0046 | - | | 1.1414 | 9000 | 0.0046 | - | | 1.1477 | 9050 | 0.0075 | - | | 1.1541 | 9100 | 0.0066 | - | | 1.1604 | 9150 | 0.0078 | - | | 1.1668 | 9200 | 0.0069 | - | | 1.1731 | 9250 | 0.0087 | - | | 1.1795 | 9300 | 0.0047 | - | | 1.1858 | 9350 | 0.0037 | - | | 1.1921 | 9400 | 0.007 | - | | 1.1985 | 9450 | 0.0069 | - | | 1.2048 | 9500 | 0.0061 | - | | 1.2112 | 9550 | 0.0047 | - | | 1.2175 | 9600 | 0.0065 | - | | 1.2238 | 9650 | 0.0058 | - | | 1.2302 | 9700 | 0.0061 | - | | 1.2365 | 9750 | 0.0055 | - | | 1.2429 | 9800 | 0.0064 | - | | 1.2492 | 9850 | 0.0041 | - | | 1.2555 | 9900 | 0.0086 | - | | 1.2619 | 9950 | 0.0053 | - | | 1.2682 | 10000 | 0.0047 | - | | 1.2746 | 10050 | 0.0053 | - | | 1.2809 | 10100 | 0.003 | - | | 1.2873 | 10150 | 0.0046 | - | | 1.2936 | 10200 | 0.0052 | - | | 1.2999 | 10250 | 0.0056 | - | | 1.3063 | 10300 | 0.0052 | - | | 1.3126 | 10350 | 0.0079 | - | | 1.3190 | 10400 | 0.006 | - | | 1.3253 | 10450 | 0.0055 | - | | 1.3316 | 10500 | 0.0066 | - | | 1.3380 | 10550 | 0.0076 | - | | 1.3443 | 10600 | 0.0037 | - | | 1.3507 | 10650 | 0.0066 | - | | 1.3570 | 10700 | 0.0059 | - | | 1.3633 | 10750 | 0.0057 | - | | 1.3697 | 10800 | 0.0038 | - | | 1.3760 | 10850 | 0.0044 | - | | 1.3824 | 10900 | 0.0059 | - | | 1.3887 | 10950 | 0.0073 | - | | 1.3951 | 11000 | 0.0055 | - | | 1.4014 | 11050 | 0.0039 | - | | 1.4077 | 11100 | 0.0054 | - | | 1.4141 | 11150 | 0.0068 | - | | 1.4204 | 11200 | 0.0067 | - | | 1.4268 | 11250 | 0.0041 | - | | 1.4331 | 11300 | 0.0076 | - | | 1.4394 | 11350 | 0.0071 | - | | 1.4458 | 11400 | 0.0044 | - | | 1.4521 | 11450 | 0.0061 | - | | 1.4585 | 11500 | 0.0039 | - | | 1.4648 | 11550 | 0.006 | - | | 1.4711 | 11600 | 0.0045 | - | | 1.4775 | 11650 | 0.0044 | - | | 1.4838 | 11700 | 0.0063 | - | | 1.4902 | 11750 | 0.0061 | - | | 1.4965 | 11800 | 0.0058 | - | | 1.5029 | 11850 | 0.0039 | - | | 1.5092 | 11900 | 0.0041 | - | | 1.5155 | 11950 | 0.0052 | - | | 1.5219 | 12000 | 0.0034 | - | | 1.5282 | 12050 | 0.0078 | - | | 1.5346 | 12100 | 0.0049 | - | | 1.5409 | 12150 | 0.0064 | - | | 1.5472 | 12200 | 0.0063 | - | | 1.5536 | 12250 | 0.0068 | - | | 1.5599 | 12300 | 0.008 | - | | 1.5663 | 12350 | 0.0043 | - | | 1.5726 | 12400 | 0.0057 | - | | 1.5789 | 12450 | 0.0044 | - | | 1.5853 | 12500 | 0.0048 | - | | 1.5916 | 12550 | 0.0049 | - | | 1.5980 | 12600 | 0.0052 | - | | 1.6043 | 12650 | 0.0061 | - | | 1.6107 | 12700 | 0.0066 | - | | 1.6170 | 12750 | 0.0079 | - | | 1.6233 | 12800 | 0.0047 | - | | 1.6297 | 12850 | 0.005 | - | | 1.6360 | 12900 | 0.0034 | - | | 1.6424 | 12950 | 0.0051 | - | | 1.6487 | 13000 | 0.006 | - | | 1.6550 | 13050 | 0.0046 | - | | 1.6614 | 13100 | 0.003 | - | | 1.6677 | 13150 | 0.0055 | - | | 1.6741 | 13200 | 0.0069 | - | | 1.6804 | 13250 | 0.0033 | - | | 1.6867 | 13300 | 0.0095 | - | | 1.6931 | 13350 | 0.0043 | - | | 1.6994 | 13400 | 0.0055 | - | | 1.7058 | 13450 | 0.0081 | - | | 1.7121 | 13500 | 0.0042 | - | | 1.7185 | 13550 | 0.0081 | - | | 1.7248 | 13600 | 0.0055 | - | | 1.7311 | 13650 | 0.0043 | - | | 1.7375 | 13700 | 0.0033 | - | | 1.7438 | 13750 | 0.0044 | - | | 1.7502 | 13800 | 0.0062 | - | | 1.7565 | 13850 | 0.0032 | - | | 1.7628 | 13900 | 0.0043 | - | | 1.7692 | 13950 | 0.0079 | - | | 1.7755 | 14000 | 0.0053 | - | | 1.7819 | 14050 | 0.0044 | - | | 1.7882 | 14100 | 0.0064 | - | | 1.7945 | 14150 | 0.0051 | - | | 1.8009 | 14200 | 0.0088 | - | | 1.8072 | 14250 | 0.0048 | - | | 1.8136 | 14300 | 0.0044 | - | | 1.8199 | 14350 | 0.0071 | - | | 1.8263 | 14400 | 0.0058 | - | | 1.8326 | 14450 | 0.007 | - | | 1.8389 | 14500 | 0.0028 | - | | 1.8453 | 14550 | 0.0046 | - | | 1.8516 | 14600 | 0.0061 | - | | 1.8580 | 14650 | 0.0054 | - | | 1.8643 | 14700 | 0.004 | - | | 1.8706 | 14750 | 0.0034 | - | | 1.8770 | 14800 | 0.0044 | - | | 1.8833 | 14850 | 0.0033 | - | | 1.8897 | 14900 | 0.007 | - | | 1.8960 | 14950 | 0.0044 | - | | 1.9023 | 15000 | 0.0045 | - | | 1.9087 | 15050 | 0.0045 | - | | 1.9150 | 15100 | 0.0093 | - | | 1.9214 | 15150 | 0.0036 | - | | 1.9277 | 15200 | 0.0055 | - | | 1.9341 | 15250 | 0.0037 | - | | 1.9404 | 15300 | 0.0043 | - | | 1.9467 | 15350 | 0.0034 | - | | 1.9531 | 15400 | 0.0068 | - | | 1.9594 | 15450 | 0.0058 | - | | 1.9658 | 15500 | 0.0069 | - | | 1.9721 | 15550 | 0.0081 | - | | 1.9784 | 15600 | 0.0061 | - | | 1.9848 | 15650 | 0.0039 | - | | 1.9911 | 15700 | 0.0065 | - | | 1.9975 | 15750 | 0.0048 | - | ### Framework Versions - Python: 3.12.3 - SetFit: 1.1.0 - Sentence Transformers: 3.2.0 - Transformers: 4.45.2 - PyTorch: 2.5.0+cu121 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## 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} } ```