--- tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: The Operations Lead drives team performance by securing vendor partnerships, managing field equipment budgets, and reallocating resources to meet seasonal project demands; they personally oversee the assembly and maintenance of outdoor signage systems, troubleshoot mechanical failures on-site, and train crews in safe tool operations, while also conceptualizing branded environmental installations that blend functional design with bold visual storytelling to enhance public engagement. - text: The Field Operations Supervisor installs and maintains irrigation systems across rural properties, troubleshoots mechanical failures using hand and power tools, and leads a team of technicians to meet seasonal deployment targets. They coordinate logistics, manage equipment budgets, and motivate crews to maintain high service standards while providing on-site training and support to ensure community agricultural needs are met reliably and compassionately. - text: The Field Maintenance Technician performs routine inspections and repairs on industrial equipment using hand and power tools, troubleshoots mechanical failures on-site, and documents operational conditions in rugged outdoor environments. They analyze performance logs to identify patterns of wear or inefficiency, interpret technical manuals to diagnose complex system anomalies, and apply standardized repair protocols to ensure consistency. They maintain detailed service records, update asset tracking databases, and verify compliance with safety and maintenance schedules. - text: The Program Development Lead drives the design and rollout of employee wellness initiatives, securing buy-in from senior leadership and allocating budget resources to maximize engagement. They mentor team members through personalized coaching sessions, foster inclusive group dynamics, and cultivate a culture of psychological safety. Drawing on creative insight, they conceptualize visually compelling campaign materials, branded storytelling tools, and interactive workshops that turn policy into meaningful human experience. - text: The Data Systems Analyst investigates patterns in organizational performance metrics by designing analytical models, interpreting complex datasets, and recommending data-driven strategies to improve operational efficiency. They lead cross-functional initiatives to align stakeholders with optimization goals, securing buy-in through persuasive presentations and targeted negotiations. They maintain precise records of analytical workflows, ensure adherence to data governance protocols, and standardize reporting templates for consistent quarterly reviews. metrics: - accuracy pipeline_tag: text-classification library_name: setfit inference: true base_model: sentence-transformers/paraphrase-mpnet-base-v2 model-index: - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.7666666666666667 name: Accuracy --- # SetFit with sentence-transformers/paraphrase-mpnet-base-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-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) 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:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) - **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:** 120 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 | |:------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | RIA | | | RIS | | | RIE | | | RIC | | | RAI | | | RAS | | | RAE | | | RAC | | | RSI | | | RSA | | | RSE | | | RSC | | | REI | | | REA | | | RES | | | REC | | | RCI | | | RCA | | | RCS | | | RCE | | | IRA | | | IRS | | | IRE | | | IRC | | | IAR | | | IAS | | | IAE | | | IAC | | | ISR | | | ISA | | | ISE | | | ISC | | | IER | | | IEA | | | IES | | | IEC | | | ICR | | | ICA | | | ICS | | | ICE | | | ARI | | | ARS | | | ARE | | | ARC | | | AIR | | | AIS | | | AIE | | | AIC | | | ASR | | | ASI | | | ASE | | | ASC | | | AER | | | AEI | | | AES | | | AEC | | | ACR | | | ACI | | | ACS | | | ACE | | | SRI | | | SRA | | | SRE | | | SRC | | | SIR | | | SIA | | | SIE | | | SIC | | | SAR | | | SAI | | | SAE | | | SAC | | | SER | | | SEI | | | SEA | | | SEC | | | SCR | | | SCI | | | SCA | | | SCE | | | ERI | | | ERA | | | ERS | | | ERC | | | EIR | | | EIA | | | EIS | | | EIC | | | EAR | | | EAI | | | EAS | | | EAC | | | ESR | | | ESI | | | ESA | | | ESC | | | ECR | | | ECI | | | ECA | | | ECS | | | CRI | | | CRA | | | CRS | | | CRE | | | CIR | | | CIA | | | CIS | | | CIE | | | CAR | | | CAI | | | CAS | | | CAE | | | CSR | | | CSI | | | CSA | | | CSE | | | CER | | | CEI | | | CEA | | | CES | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.7667 | ## 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("dnth/setfit-riasec-classifier") # Run inference preds = model("The Field Operations Supervisor installs and maintains irrigation systems across rural properties, troubleshoots mechanical failures using hand and power tools, and leads a team of technicians to meet seasonal deployment targets. They coordinate logistics, manage equipment budgets, and motivate crews to maintain high service standards while providing on-site training and support to ensure community agricultural needs are met reliably and compassionately.") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 30 | 57.3033 | 78 | | Label | Training Sample Count | |:------|:----------------------| | RIA | 3 | | RIS | 3 | | RIE | 3 | | RIC | 3 | | RAI | 3 | | RAS | 3 | | RAE | 3 | | RAC | 3 | | RSI | 3 | | RSA | 3 | | RSE | 3 | | RSC | 3 | | REI | 3 | | REA | 3 | | RES | 3 | | REC | 3 | | RCI | 3 | | RCA | 3 | | RCS | 3 | | RCE | 3 | | IRA | 3 | | IRS | 3 | | IRE | 3 | | IRC | 3 | | IAR | 3 | | IAS | 3 | | IAE | 3 | | IAC | 3 | | ISR | 3 | | ISA | 3 | | ISE | 3 | | ISC | 3 | | IER | 3 | | IEA | 3 | | IES | 3 | | IEC | 3 | | ICR | 3 | | ICA | 3 | | ICS | 3 | | ICE | 6 | | ARI | 3 | | ARS | 3 | | ARE | 3 | | ARC | 3 | | AIR | 3 | | AIS | 3 | | AIE | 3 | | AIC | 6 | | ASR | 3 | | ASI | 3 | | ASE | 3 | | ASC | 3 | | AER | 3 | | AEI | 3 | | AES | 3 | | AEC | 3 | | ACR | 3 | | ACI | 3 | | ACS | 3 | | ACE | 3 | | SRI | 3 | | SRA | 3 | | SRE | 3 | | SRC | 3 | | SIR | 3 | | SIA | 3 | | SIE | 3 | | SIC | 3 | | SAR | 3 | | SAI | 3 | | SAE | 3 | | SAC | 3 | | SER | 3 | | SEI | 3 | | SEA | 3 | | SEC | 3 | | SCR | 3 | | SCI | 3 | | SCA | 3 | | SCE | 3 | | ERI | 3 | | ERA | 3 | | ERS | 3 | | ERC | 3 | | EIR | 3 | | EIA | 3 | | EIS | 3 | | EIC | 3 | | EAR | 3 | | EAI | 3 | | EAS | 3 | | EAC | 3 | | ESR | 3 | | ESI | 3 | | ESA | 3 | | ESC | 3 | | ECR | 3 | | ECI | 3 | | ECA | 3 | | ECS | 3 | | CRI | 3 | | CRA | 3 | | CRS | 3 | | CRE | 3 | | CIR | 3 | | CIA | 3 | | CIS | 3 | | CIE | 3 | | CAR | 3 | | CAI | 3 | | CAS | 3 | | CAE | 3 | | CSR | 3 | | CSI | 3 | | CSA | 3 | | CSE | 3 | | CER | 3 | | CEI | 3 | | CEA | 3 | | CES | 3 | ### Training Hyperparameters - batch_size: (64, 64) - num_epochs: (4, 4) - max_steps: -1 - sampling_strategy: oversampling - 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: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:----:|:-------------:|:---------------:| | 0.0005 | 1 | 0.1531 | - | | 0.0241 | 50 | 0.1275 | - | | 0.0482 | 100 | 0.0997 | - | | 0.0723 | 150 | 0.0836 | - | | 0.0963 | 200 | 0.066 | - | | 0.1204 | 250 | 0.0549 | - | | 0.1445 | 300 | 0.0435 | - | | 0.1686 | 350 | 0.0327 | - | | 0.1927 | 400 | 0.0281 | - | | 0.2168 | 450 | 0.0231 | - | | 0.2408 | 500 | 0.0204 | - | | 0.2649 | 550 | 0.019 | - | | 0.2890 | 600 | 0.0179 | - | | 0.3131 | 650 | 0.0153 | - | | 0.3372 | 700 | 0.0144 | - | | 0.3613 | 750 | 0.0116 | - | | 0.3854 | 800 | 0.0112 | - | | 0.4094 | 850 | 0.01 | - | | 0.4335 | 900 | 0.0109 | - | | 0.4576 | 950 | 0.0107 | - | | 0.4817 | 1000 | 0.0095 | - | | 0.5058 | 1050 | 0.0094 | - | | 0.5299 | 1100 | 0.0074 | - | | 0.5539 | 1150 | 0.0101 | - | | 0.5780 | 1200 | 0.0072 | - | | 0.6021 | 1250 | 0.0074 | - | | 0.6262 | 1300 | 0.0066 | - | | 0.6503 | 1350 | 0.0063 | - | | 0.6744 | 1400 | 0.0062 | - | | 0.6985 | 1450 | 0.0059 | - | | 0.7225 | 1500 | 0.0055 | - | | 0.7466 | 1550 | 0.0055 | - | | 0.7707 | 1600 | 0.0037 | - | | 0.7948 | 1650 | 0.004 | - | | 0.8189 | 1700 | 0.0047 | - | | 0.8430 | 1750 | 0.004 | - | | 0.8671 | 1800 | 0.0048 | - | | 0.8911 | 1850 | 0.0043 | - | | 0.9152 | 1900 | 0.0048 | - | | 0.9393 | 1950 | 0.0034 | - | | 0.9634 | 2000 | 0.0044 | - | | 0.9875 | 2050 | 0.0056 | - | | 1.0 | 2076 | - | 0.0042 | | 1.0116 | 2100 | 0.0037 | - | | 1.0356 | 2150 | 0.0037 | - | | 1.0597 | 2200 | 0.003 | - | | 1.0838 | 2250 | 0.0032 | - | | 1.1079 | 2300 | 0.0027 | - | | 1.1320 | 2350 | 0.0027 | - | | 1.1561 | 2400 | 0.0021 | - | | 1.1802 | 2450 | 0.003 | - | | 1.2042 | 2500 | 0.0028 | - | | 1.2283 | 2550 | 0.0023 | - | | 1.2524 | 2600 | 0.0028 | - | | 1.2765 | 2650 | 0.0028 | - | | 1.3006 | 2700 | 0.0027 | - | | 1.3247 | 2750 | 0.0036 | - | | 1.3487 | 2800 | 0.0025 | - | | 1.3728 | 2850 | 0.0027 | - | | 1.3969 | 2900 | 0.0023 | - | | 1.4210 | 2950 | 0.0026 | - | | 1.4451 | 3000 | 0.0022 | - | | 1.4692 | 3050 | 0.0027 | - | | 1.4933 | 3100 | 0.0029 | - | | 1.5173 | 3150 | 0.0018 | - | | 1.5414 | 3200 | 0.002 | - | | 1.5655 | 3250 | 0.0017 | - | | 1.5896 | 3300 | 0.0017 | - | | 1.6137 | 3350 | 0.0019 | - | | 1.6378 | 3400 | 0.0017 | - | | 1.6618 | 3450 | 0.0014 | - | | 1.6859 | 3500 | 0.0013 | - | | 1.7100 | 3550 | 0.0013 | - | | 1.7341 | 3600 | 0.0014 | - | | 1.7582 | 3650 | 0.0016 | - | | 1.7823 | 3700 | 0.0019 | - | | 1.8064 | 3750 | 0.0012 | - | | 1.8304 | 3800 | 0.0013 | - | | 1.8545 | 3850 | 0.0014 | - | | 1.8786 | 3900 | 0.0013 | - | | 1.9027 | 3950 | 0.0012 | - | | 1.9268 | 4000 | 0.0011 | - | | 1.9509 | 4050 | 0.0011 | - | | 1.9750 | 4100 | 0.0008 | - | | 1.9990 | 4150 | 0.0009 | - | | 2.0 | 4152 | - | 0.0025 | | 2.0231 | 4200 | 0.0014 | - | | 2.0472 | 4250 | 0.0008 | - | | 2.0713 | 4300 | 0.0011 | - | | 2.0954 | 4350 | 0.0008 | - | | 2.1195 | 4400 | 0.0009 | - | | 2.1435 | 4450 | 0.0009 | - | | 2.1676 | 4500 | 0.0007 | - | | 2.1917 | 4550 | 0.0008 | - | | 2.2158 | 4600 | 0.0007 | - | | 2.2399 | 4650 | 0.0007 | - | | 2.2640 | 4700 | 0.0006 | - | | 2.2881 | 4750 | 0.0005 | - | | 2.3121 | 4800 | 0.0006 | - | | 2.3362 | 4850 | 0.0005 | - | | 2.3603 | 4900 | 0.0004 | - | | 2.3844 | 4950 | 0.0005 | - | | 2.4085 | 5000 | 0.0007 | - | | 2.4326 | 5050 | 0.0005 | - | | 2.4566 | 5100 | 0.0004 | - | | 2.4807 | 5150 | 0.0004 | - | | 2.5048 | 5200 | 0.0004 | - | | 2.5289 | 5250 | 0.0004 | - | | 2.5530 | 5300 | 0.0004 | - | | 2.5771 | 5350 | 0.0004 | - | | 2.6012 | 5400 | 0.0004 | - | | 2.6252 | 5450 | 0.0003 | - | | 2.6493 | 5500 | 0.0003 | - | | 2.6734 | 5550 | 0.0003 | - | | 2.6975 | 5600 | 0.0003 | - | | 2.7216 | 5650 | 0.0003 | - | | 2.7457 | 5700 | 0.0004 | - | | 2.7697 | 5750 | 0.0003 | - | | 2.7938 | 5800 | 0.0003 | - | | 2.8179 | 5850 | 0.0003 | - | | 2.8420 | 5900 | 0.0002 | - | | 2.8661 | 5950 | 0.0002 | - | | 2.8902 | 6000 | 0.0002 | - | | 2.9143 | 6050 | 0.0002 | - | | 2.9383 | 6100 | 0.0002 | - | | 2.9624 | 6150 | 0.0002 | - | | 2.9865 | 6200 | 0.0002 | - | | 3.0 | 6228 | - | 0.0021 | | 3.0106 | 6250 | 0.0002 | - | | 3.0347 | 6300 | 0.0002 | - | | 3.0588 | 6350 | 0.0002 | - | | 3.0829 | 6400 | 0.0002 | - | | 3.1069 | 6450 | 0.0002 | - | | 3.1310 | 6500 | 0.0002 | - | | 3.1551 | 6550 | 0.0002 | - | | 3.1792 | 6600 | 0.0002 | - | | 3.2033 | 6650 | 0.0002 | - | | 3.2274 | 6700 | 0.0002 | - | | 3.2514 | 6750 | 0.0002 | - | | 3.2755 | 6800 | 0.0002 | - | | 3.2996 | 6850 | 0.0002 | - | | 3.3237 | 6900 | 0.0002 | - | | 3.3478 | 6950 | 0.0001 | - | | 3.3719 | 7000 | 0.0002 | - | | 3.3960 | 7050 | 0.0002 | - | | 3.4200 | 7100 | 0.0001 | - | | 3.4441 | 7150 | 0.0001 | - | | 3.4682 | 7200 | 0.0001 | - | | 3.4923 | 7250 | 0.0001 | - | | 3.5164 | 7300 | 0.0001 | - | | 3.5405 | 7350 | 0.0001 | - | | 3.5645 | 7400 | 0.0001 | - | | 3.5886 | 7450 | 0.0001 | - | | 3.6127 | 7500 | 0.0001 | - | | 3.6368 | 7550 | 0.0001 | - | | 3.6609 | 7600 | 0.0001 | - | | 3.6850 | 7650 | 0.0001 | - | | 3.7091 | 7700 | 0.0001 | - | | 3.7331 | 7750 | 0.0001 | - | | 3.7572 | 7800 | 0.0001 | - | | 3.7813 | 7850 | 0.0001 | - | | 3.8054 | 7900 | 0.0001 | - | | 3.8295 | 7950 | 0.0001 | - | | 3.8536 | 8000 | 0.0001 | - | | 3.8776 | 8050 | 0.0001 | - | | 3.9017 | 8100 | 0.0001 | - | | 3.9258 | 8150 | 0.0001 | - | | 3.9499 | 8200 | 0.0001 | - | | 3.9740 | 8250 | 0.0001 | - | | 3.9981 | 8300 | 0.0001 | - | | 4.0 | 8304 | - | 0.0020 | ### Framework Versions - Python: 3.12.8 - SetFit: 1.1.3 - Sentence Transformers: 5.1.1 - Transformers: 4.56.2 - PyTorch: 2.8.0+cu128 - Datasets: 4.1.1 - Tokenizers: 0.22.1 ## 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} } ```