--- library_name: setfit tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer base_model: meedan/paraphrase-filipino-mpnet-base-v2 datasets: - bsen26/eyeR-classification-multi-label-category2 metrics: - accuracy widget: - text: i ordered shake shake fries but they give me just the plain one!! there's no ketchup or any cutlery!!! i will only give you one star!! tsk poor service ?? - text: The fries were soggy and did not taste good, there was no cutlery, the butter was already melted when I got the order. - text: i ordered crispy fillet ala king why no sauce ? and asked for iced tea and you give pineapple juice ? are you kidding me ? are you even reading some instructions? - text: Wrong coffee / no ketchup / cold fries. Ugh - text: They have forgot to put inside the toy i ordered, my child is dispointed because she's expecting the pikachu toy please fix this !! pipeline_tag: text-classification inference: false model-index: - name: SetFit with meedan/paraphrase-filipino-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: bsen26/eyeR-classification-multi-label-category2 type: bsen26/eyeR-classification-multi-label-category2 split: test metrics: - type: accuracy value: 0.5407407407407407 name: Accuracy --- # SetFit with meedan/paraphrase-filipino-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [bsen26/eyeR-classification-multi-label-category2](https://huggingface.co/datasets/bsen26/eyeR-classification-multi-label-category2) dataset that can be used for Text Classification. This SetFit model uses [meedan/paraphrase-filipino-mpnet-base-v2](https://huggingface.co/meedan/paraphrase-filipino-mpnet-base-v2) as the Sentence Transformer embedding model. A OneVsRestClassifier 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:** [meedan/paraphrase-filipino-mpnet-base-v2](https://huggingface.co/meedan/paraphrase-filipino-mpnet-base-v2) - **Classification head:** a OneVsRestClassifier instance - **Maximum Sequence Length:** 128 tokens - **Training Dataset:** [bsen26/eyeR-classification-multi-label-category2](https://huggingface.co/datasets/bsen26/eyeR-classification-multi-label-category2) ### 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) ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.5407 | ## 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("bsen26/eyeR-category2-multilabel") # Run inference preds = model("Wrong coffee / no ketchup / cold fries. Ugh") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 1 | 18.3958 | 41 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (1, 1) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 20 - 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 | |:------:|:----:|:-------------:|:---------------:| | 0.0010 | 1 | 0.0919 | - | | 0.0521 | 50 | 0.1443 | - | | 0.1042 | 100 | 0.0682 | - | | 0.1562 | 150 | 0.1043 | - | | 0.2083 | 200 | 0.0653 | - | | 0.2604 | 250 | 0.0136 | - | | 0.3125 | 300 | 0.0025 | - | | 0.3646 | 350 | 0.0195 | - | | 0.4167 | 400 | 0.0073 | - | | 0.4688 | 450 | 0.0115 | - | | 0.5208 | 500 | 0.0045 | - | | 0.5729 | 550 | 0.0052 | - | | 0.625 | 600 | 0.0091 | - | | 0.6771 | 650 | 0.0037 | - | | 0.7292 | 700 | 0.0027 | - | | 0.7812 | 750 | 0.0058 | - | | 0.8333 | 800 | 0.0118 | - | | 0.8854 | 850 | 0.0025 | - | | 0.9375 | 900 | 0.0005 | - | | 0.9896 | 950 | 0.0085 | - | ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 2.7.0 - Transformers: 4.40.2 - PyTorch: 2.2.1+cu121 - Datasets: 2.19.1 - Tokenizers: 0.19.1 ## 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} } ```