--- tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: 'The NAP process was initiated under the United Nations Framework Convention on Climate Change (UNFCCC) to address medium- and long-term climate adaptation needs. The process was established in 2010 under the Cancun Adaptation Framework8 at the 16th Conference of Parties to the UNFCCC, and its targets were refined as part of the 2015 Paris Agreement. 13. The NAP process is intended as an iterative, country-owned planning process that allows each country to identify, address and review their evolving adaptation needs, issues, gaps, priorities, and related resource requirements within the context of national adaptation plans9. It is also envisioned as an 8 See: https://unfccc.int/process/conferences/pastconferences/cancun-climate-change-conference-november -2010/statements-and-resources/Agreements 9 See: https://unfccc.int/index.php/topics/adaptation-and-resilience/workstreams/national-adaptation-plans organic continuation of the formulation and implementation of countries’ Nationally Determined Contributions (NDC). 14. The objectives of the UNFCCC’s NAP process are to reduce vulnerability to the adverse impacts of CC by building adaptive capacity and resilience, and to facilitate the integration of climate change adaptation into fiscal, regulatory and development policies, programs and activities,10 as well as to accelerate strategic investments in CC resilient development. 15. Implementation of the NAP will help the country to achieve its Sustainable Development Goals (hereinafter - SDGs), and achieving the SDGs will facilitate country-based efforts to mitigate and adapt to CC' - text: 'Agriculture in Armenia has always been remarkable with the high level of climate risks (hail damage, frost damage, drought, etc.). As it is already mentioned, agriculture has suffered losses from natural disasters worth of AMD 110 billion during the recent 6 years. Climate risks in Armenia are a serious problem since there are no clearly formed such state, political or institutional mechanisms, the application of which would make it possible to noticeably mitigate the existing risks. Due to the lack of such mechanisms, the mechanism of full assessment of the agricultural losses does not work too, as well as the risks are not assessed in advance. In this context, to reduce the agricultural risks, to introduce loss compensation mechanisms in a systemized way, and to provide sustainable income levels for economic entities, it is necessary to address the critical issue of agricultural risk insurance. ' - text: 'Strategy 6.3: Strengthen monitoring, evaluation and surveillance systems for routine information sharing and data utilization at all levels Activities Stakeholder Conduct bi-annual nutrition M&E coordination meetings. ND, M&ED, INS Collaborate with HIS Department (HISD) and M&E Department MOH to conduct routine nutrition data quality assessments and audits (RDQA). ND, HISD, M&ED, INS In collaboration with HISD MOH and M&E Department, train M&E officers, DPHO nutrition, nutrition focal points and Municipality Health Services on data management (collection analyses, interpreting and reporting) at all levels. ND, HISD, M&ED, INS Develop and disseminate the Nutrition M&E Plan. ND, M&ED Strengthen the nutrition information system within the HMIS by integrating key nutrition indicators and databases. ND, HISD, M&ED Establish and scale up a nutrition surveillance system for real time monitoring at all levels. ND, M&ED, INS Conduct mid-term and end-term evaluation of the nutrition strategic plan. ND, HISD, M&ED, INS Conduct a food and nutrition survey every 5 years. ND, HISD, M&ED, INS Conduct knowledge attitude and practices (KAP) survey on nutrition. ND, HISD, M&ED, HPD, INS Liaise with HMIS to introduce real-time data collection linked to DHIS2. ND, HISD, M&ED Periodic publishing of nutrition bulletin/report ND, HISD, M&ED Develop and regularly review nutrition indicators monitoring and evaluation guideline. ND, HMIS, M&ED, INS ' - text: 'Food security of the population is one of the key challenges of the twenty-first century. In the mid-term perspective, it is one of the main directions of ensuring the country’s national security, a factor in maintaining statehood and sovereignty, and the most important component of demographic policy implementation. Furthermore, food security is a sough- for precondition in terms of improving population’s quality of life by safeguarding appropriate livelihood standards. 8. The problem of providing the population with food has long been there, however since mid-20th century, in the context of streamlining the problems of scarce world food resources, this issue gained a special attention. The development of fundamental human rights documents, such as the Universal Declaration of Human Rights, 1948, the International Covenant on Economic, Social and Cultural Rights, 1966 and others, also played a crucial role. The term "food security" has been first coined by the WFS of 1974, which was defined as: “Maintaining stability and availability of food stuff in the markets for all countries of the world.” 9. At the current stage of development, the perception of food security has significantly expanded. Thus, in 1996, World Food Security Summit, “food security” has been defined ' - text: As of June 2022, the level of food insecurity in the country was 23.2% and in this regard, the northern regions of Armenia were more susceptible. In particular, 6 food insecurity in Tavush Marz was 25%, 31% in Lori Marz, and 35% in Shirak Marz of Armenia metrics: - accuracy pipeline_tag: text-classification library_name: setfit inference: true base_model: sentence-transformers/paraphrase-mpnet-base-v2 --- # 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:** 13 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 | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 4.3 Poverty and inequality: Addresses the root causes and manifestations of poverty, income disparities, and social inequities, particularly in rural areas and agrifood value chains, striving for inclusive growth. | | | 4.2 Access to Essential Infrastructure and Services: Ensures that rural and agrifood communities benefit from infrastructure (energy, transport, communications) and social services (health, education), improving well-being and productivity. | | | 6.3.4 Effectiveness of Policy Implementation: Assesses how well policies are executed, supported, and monitored, ensuring that institutions deliver on their commitments and enable positive outcomes. | | | 1.1. Food Security & Nutrition: Encompasses ensuring everyone’s access to sufficient, safe, and nutritious food, improving overall dietary intake and nutritional well-being. | | | 5.2 Resilience Capacities (absorptive, adaptive & transformative): Promotes building skills, diversifying options, strengthening networks, and improving surveillance systems so that communities, ecosystems, and value chains can withstand and recover from disruptions. | | | 6.3.2 Creation of supportive regulatory framework: Promotes clear, predictable rules and supportive policies that foster investment, innovation, and responsible business conduct in agrifood sectors. | | | 6.4.1 Scope and effectiveness of Government budgetary support: Evaluates the allocation and effectiveness of public funds, ensuring they support sustainable, inclusive growth rather than distort markets or harm the environment., Examines public spending priorities, ensuring that investments meet development goals, promote equity, and enhance agrifood productivity and resilience. | | | 6.1.1 Rights of women, children, youth, indigenous groups and other vulnerable groups: Ensures that policies and actions respect, protect, and fulfill human rights, giving vulnerable populations equal opportunities and a voice in agrifood decisions. | | | 5.1. Exposure to shocks: Examines the vulnerabilities of agrifood systems to various shocks—environmental, economic, conflict-related, health—and how these risks affect food security and livelihoods. | | | 1.2. Diet quality: Focuses on the balance, diversity, and healthfulness of what people eat, aiming to prevent malnutrition and diet-related diseases. | | | 2.1. Primary Production: Concerned with sustainable increases in agricultural, livestock, fisheries, and forestry outputs, ensuring efficiency, productivity, and resource stewardship at the farm and natural resource base level. | | | 1.4. Food environments: Examines the conditions—physical, economic, political, social, and cultural—that influence the availability, affordability, and appeal of healthy foods. | | | 6.3.3 Awareness and use of the evidence-based / agrifood systems approach: Encourages long-term, integrated planning for agrifood systems, guided by robust data, stakeholder consensus, and strategic foresight. | | ## 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("faodl/setfit-paraphrase-mpnet-base-v2-13ClassesDesc") # Run inference preds = model("As of June 2022, the level of food insecurity in the country was 23.2% and in this regard, the northern regions of Armenia were more susceptible. In particular, 6 food insecurity in Tavush Marz was 25%, 31% in Lori Marz, and 35% in Shirak Marz of Armenia") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:---------|:-----| | Word count | 4 | 118.1581 | 1014 | | Label | Training Sample Count | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------| | 4.3 Poverty and inequality: Addresses the root causes and manifestations of poverty, income disparities, and social inequities, particularly in rural areas and agrifood value chains, striving for inclusive growth. | 10 | | 4.2 Access to Essential Infrastructure and Services: Ensures that rural and agrifood communities benefit from infrastructure (energy, transport, communications) and social services (health, education), improving well-being and productivity. | 11 | | 6.3.4 Effectiveness of Policy Implementation: Assesses how well policies are executed, supported, and monitored, ensuring that institutions deliver on their commitments and enable positive outcomes. | 22 | | 1.1. Food Security & Nutrition: Encompasses ensuring everyone’s access to sufficient, safe, and nutritious food, improving overall dietary intake and nutritional well-being. | 62 | | 5.2 Resilience Capacities (absorptive, adaptive & transformative): Promotes building skills, diversifying options, strengthening networks, and improving surveillance systems so that communities, ecosystems, and value chains can withstand and recover from disruptions. | 17 | | 6.3.2 Creation of supportive regulatory framework: Promotes clear, predictable rules and supportive policies that foster investment, innovation, and responsible business conduct in agrifood sectors. | 12 | | 6.4.1 Scope and effectiveness of Government budgetary support: Evaluates the allocation and effectiveness of public funds, ensuring they support sustainable, inclusive growth rather than distort markets or harm the environment., Examines public spending priorities, ensuring that investments meet development goals, promote equity, and enhance agrifood productivity and resilience. | 10 | | 6.1.1 Rights of women, children, youth, indigenous groups and other vulnerable groups: Ensures that policies and actions respect, protect, and fulfill human rights, giving vulnerable populations equal opportunities and a voice in agrifood decisions. | 8 | | 5.1. Exposure to shocks: Examines the vulnerabilities of agrifood systems to various shocks—environmental, economic, conflict-related, health—and how these risks affect food security and livelihoods. | 14 | | 1.2. Diet quality: Focuses on the balance, diversity, and healthfulness of what people eat, aiming to prevent malnutrition and diet-related diseases. | 18 | | 2.1. Primary Production: Concerned with sustainable increases in agricultural, livestock, fisheries, and forestry outputs, ensuring efficiency, productivity, and resource stewardship at the farm and natural resource base level. | 9 | | 1.4. Food environments: Examines the conditions—physical, economic, political, social, and cultural—that influence the availability, affordability, and appeal of healthy foods. | 11 | | 6.3.3 Awareness and use of the evidence-based / agrifood systems approach: Encourages long-term, integrated planning for agrifood systems, guided by robust data, stakeholder consensus, and strategic foresight. | 30 | ### Training Hyperparameters - batch_size: (8, 8) - num_epochs: (1, 1) - 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 | |:------:|:----:|:-------------:|:---------------:| | 0.0002 | 1 | 0.2741 | - | | 0.0083 | 50 | 0.2208 | - | | 0.0167 | 100 | 0.2153 | - | | 0.0250 | 150 | 0.1977 | - | | 0.0333 | 200 | 0.2096 | - | | 0.0417 | 250 | 0.1936 | - | | 0.0500 | 300 | 0.1678 | - | | 0.0583 | 350 | 0.1477 | - | | 0.0667 | 400 | 0.1357 | - | | 0.0750 | 450 | 0.1304 | - | | 0.0833 | 500 | 0.1411 | - | | 0.0917 | 550 | 0.1221 | - | | 0.1000 | 600 | 0.1265 | - | | 0.1084 | 650 | 0.113 | - | | 0.1167 | 700 | 0.1053 | - | | 0.1250 | 750 | 0.0871 | - | | 0.1334 | 800 | 0.0896 | - | | 0.1417 | 850 | 0.0786 | - | | 0.1500 | 900 | 0.0921 | - | | 0.1584 | 950 | 0.0878 | - | | 0.1667 | 1000 | 0.075 | - | | 0.1750 | 1050 | 0.0985 | - | | 0.1834 | 1100 | 0.0984 | - | | 0.1917 | 1150 | 0.0848 | - | | 0.2000 | 1200 | 0.0923 | - | | 0.2084 | 1250 | 0.0894 | - | | 0.2167 | 1300 | 0.0727 | - | | 0.2250 | 1350 | 0.0807 | - | | 0.2334 | 1400 | 0.0715 | - | | 0.2417 | 1450 | 0.0728 | - | | 0.2500 | 1500 | 0.056 | - | | 0.2584 | 1550 | 0.0683 | - | | 0.2667 | 1600 | 0.0729 | - | | 0.2750 | 1650 | 0.0625 | - | | 0.2834 | 1700 | 0.0582 | - | | 0.2917 | 1750 | 0.0483 | - | | 0.3001 | 1800 | 0.0449 | - | | 0.3084 | 1850 | 0.0695 | - | | 0.3167 | 1900 | 0.0626 | - | | 0.3251 | 1950 | 0.0596 | - | | 0.3334 | 2000 | 0.072 | - | | 0.3417 | 2050 | 0.0623 | - | | 0.3501 | 2100 | 0.0689 | - | | 0.3584 | 2150 | 0.0514 | - | | 0.3667 | 2200 | 0.0646 | - | | 0.3751 | 2250 | 0.0495 | - | | 0.3834 | 2300 | 0.057 | - | | 0.3917 | 2350 | 0.0697 | - | | 0.4001 | 2400 | 0.0501 | - | | 0.4084 | 2450 | 0.0503 | - | | 0.4167 | 2500 | 0.0469 | - | | 0.4251 | 2550 | 0.0418 | - | | 0.4334 | 2600 | 0.0399 | - | | 0.4417 | 2650 | 0.0555 | - | | 0.4501 | 2700 | 0.0597 | - | | 0.4584 | 2750 | 0.0545 | - | | 0.4667 | 2800 | 0.0552 | - | | 0.4751 | 2850 | 0.0454 | - | | 0.4834 | 2900 | 0.048 | - | | 0.4917 | 2950 | 0.0524 | - | | 0.5001 | 3000 | 0.0512 | - | | 0.5084 | 3050 | 0.0594 | - | | 0.5168 | 3100 | 0.0609 | - | | 0.5251 | 3150 | 0.0479 | - | | 0.5334 | 3200 | 0.0439 | - | | 0.5418 | 3250 | 0.0519 | - | | 0.5501 | 3300 | 0.0507 | - | | 0.5584 | 3350 | 0.054 | - | | 0.5668 | 3400 | 0.0457 | - | | 0.5751 | 3450 | 0.0587 | - | | 0.5834 | 3500 | 0.0484 | - | | 0.5918 | 3550 | 0.0531 | - | | 0.6001 | 3600 | 0.0592 | - | | 0.6084 | 3650 | 0.0583 | - | | 0.6168 | 3700 | 0.0374 | - | | 0.6251 | 3750 | 0.0424 | - | | 0.6334 | 3800 | 0.049 | - | | 0.6418 | 3850 | 0.0406 | - | | 0.6501 | 3900 | 0.0476 | - | | 0.6584 | 3950 | 0.0476 | - | | 0.6668 | 4000 | 0.053 | - | | 0.6751 | 4050 | 0.0431 | - | | 0.6834 | 4100 | 0.0539 | - | | 0.6918 | 4150 | 0.0456 | - | | 0.7001 | 4200 | 0.0468 | - | | 0.7085 | 4250 | 0.0416 | - | | 0.7168 | 4300 | 0.0438 | - | | 0.7251 | 4350 | 0.0558 | - | | 0.7335 | 4400 | 0.0514 | - | | 0.7418 | 4450 | 0.0464 | - | | 0.7501 | 4500 | 0.0445 | - | | 0.7585 | 4550 | 0.0439 | - | | 0.7668 | 4600 | 0.0466 | - | | 0.7751 | 4650 | 0.053 | - | | 0.7835 | 4700 | 0.0638 | - | | 0.7918 | 4750 | 0.0438 | - | | 0.8001 | 4800 | 0.0481 | - | | 0.8085 | 4850 | 0.0431 | - | | 0.8168 | 4900 | 0.0505 | - | | 0.8251 | 4950 | 0.055 | - | | 0.8335 | 5000 | 0.0322 | - | | 0.8418 | 5050 | 0.0471 | - | | 0.8501 | 5100 | 0.0462 | - | | 0.8585 | 5150 | 0.0458 | - | | 0.8668 | 5200 | 0.0446 | - | | 0.8751 | 5250 | 0.0487 | - | | 0.8835 | 5300 | 0.0385 | - | | 0.8918 | 5350 | 0.0385 | - | | 0.9002 | 5400 | 0.0467 | - | | 0.9085 | 5450 | 0.0415 | - | | 0.9168 | 5500 | 0.0345 | - | | 0.9252 | 5550 | 0.0414 | - | | 0.9335 | 5600 | 0.0475 | - | | 0.9418 | 5650 | 0.0472 | - | | 0.9502 | 5700 | 0.0568 | - | | 0.9585 | 5750 | 0.0376 | - | | 0.9668 | 5800 | 0.0477 | - | | 0.9752 | 5850 | 0.0487 | - | | 0.9835 | 5900 | 0.0354 | - | | 0.9918 | 5950 | 0.0433 | - | | 1.0 | 5999 | - | 0.2466 | ### Framework Versions - Python: 3.11.11 - SetFit: 1.1.1 - Sentence Transformers: 3.4.1 - Transformers: 4.48.3 - PyTorch: 2.5.1+cu124 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## 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} } ```