--- base_model: sentence-transformers/paraphrase-mpnet-base-v2 datasets: - clareandme/multiLabelClassification library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: The AI and user talk about how sleep problems are affecting the user's daily life. The AI suggests improvements like sticking to a regular sleep schedule, establishing a bedtime routine, and reducing screen time before bed. The user acknowledges the challenge of implementing these changes but is willing to give them a try for better sleep quality. - text: The AI inquires about the user’s overall well-being and offers to talk about managing work and study demands. The user reveals they’re feeling swamped by job and exam pressures but find comfort in having a well-organized schedule. - text: The AI and user talk about a recent falling out with a close friend who has been giving them the cold shoulder. The user feels hurt and is uncertain about the future of their friendship. - text: The AI and user have a conversation about ways to manage and cope with the loss of a loved partner. - text: The AI engages the user in a conversation about their current challenges. The user discloses that they’re feeling stressed and anxious due to financial instability and rising debt. inference: false model-index: - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: clareandme/multiLabelClassification type: clareandme/multiLabelClassification split: test metrics: - type: accuracy value: 0.32142857142857145 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [clareandme/multiLabelClassification](https://huggingface.co/datasets/clareandme/multiLabelClassification) dataset that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-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:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) - **Classification head:** a OneVsRestClassifier instance - **Maximum Sequence Length:** 512 tokens - **Training Dataset:** [clareandme/multiLabelClassification](https://huggingface.co/datasets/clareandme/multiLabelClassification) ### 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** | 0.3214 | ## 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("clareandme/multilabel-setfit-model-v2") # Run inference preds = model("The AI and user have a conversation about ways to manage and cope with the loss of a loved partner.") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:-------|:----| | Word count | 10 | 33.475 | 68 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (4, 4) - max_steps: -1 - sampling_strategy: oversampling - num_iterations: 20 - 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 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:-------:|:-------------:|:---------------:| | 0.0033 | 1 | 0.1896 | - | | 0.1667 | 50 | 0.2453 | - | | 0.3333 | 100 | 0.1182 | - | | 0.5 | 150 | 0.2458 | - | | 0.6667 | 200 | 0.0401 | - | | 0.8333 | 250 | 0.0763 | - | | 1.0 | 300 | 0.0915 | 0.1302 | | 1.1667 | 350 | 0.1105 | - | | 1.3333 | 400 | 0.0715 | - | | 1.5 | 450 | 0.126 | - | | 1.6667 | 500 | 0.1074 | - | | 1.8333 | 550 | 0.0781 | - | | 2.0 | 600 | 0.0608 | 0.1102 | | 2.1667 | 650 | 0.1246 | - | | 2.3333 | 700 | 0.0791 | - | | 2.5 | 750 | 0.0662 | - | | 2.6667 | 800 | 0.0906 | - | | 2.8333 | 850 | 0.0763 | - | | **3.0** | **900** | **0.0656** | **0.1026** | | 3.1667 | 950 | 0.0476 | - | | 3.3333 | 1000 | 0.1086 | - | | 3.5 | 1050 | 0.0903 | - | | 3.6667 | 1100 | 0.0552 | - | | 3.8333 | 1150 | 0.0335 | - | | 4.0 | 1200 | 0.0689 | 0.1028 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - SetFit: 1.0.3 - Sentence Transformers: 3.0.1 - Transformers: 4.39.0 - PyTorch: 2.3.1+cu121 - Datasets: 2.21.0 - Tokenizers: 0.15.2 ## 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} } ```