--- base_model: BAAI/bge-small-en-v1.5 library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: "NEW DELHI: In a country known for conformity, Yusaku Maezawa has always sought\ \ to stand out.He skipped college, moved to California to play in a rock band\ \ and started his own e-commerce company. After making it big, the 42-year-old\ \ started dropping hundreds of millions of dollars on artwork. Now the billionaire\ \ founder of Start Today Co. is set to become the first paying passenger to the\ \ moon on a SpaceX rocket scheduled to blast off in 2023. Itâ\x80\x99s the latest\ \ headline-grabbing project by Maezawa, whose Twitter handle is @yousuck2020.While\ \ Maezawa is relatively unknown outside the archipelago and the art world, heâ\x80\ \x99s guaranteed to become more famous with his plan to fly to Earthâ\x80\x99\ s biggest satellite with a cabal of artists. A self-professed art lover, the Japanese\ \ entrepreneur intends to take a combination of painters, musicians, dancers,\ \ photographers, film directors, fashion designers and architects on a week-long\ \ lunar loop, where heâ\x80\x99ll get to watch as they get inspired and create\ \ art along the way.â\x80\x9CI thought long and hard about how valuable it would\ \ be to be the first passenger to the moon,â\x80? Maezawa said at an announcement\ \ at Space Exploration Technologies Corp.â\x80\x99s headquarters in Hawthorne,\ \ California, sitting next to the rocket companyâ\x80\x99s CEO, Elon Musk. â\x80\ \x9CI choose to go to the moon with artists.â\x80?The flight around the moon is\ \ a marriage of Maezawaâ\x80\x99s diverse interests: to be a visionary, to support\ \ art and to promote his company. Taking the enormous personal risk of orbiting\ \ the moon as the first private citizen would cement him in history books. Maezawa\ \ said he hopes the art created during the trip will inspire more interest and\ \ support for artists. Maezawa and Musk declined to say how much the lunar trip\ \ would cost.â\x80\x9CThis is not us choosing him,â\x80? Musk said. â\x80\x9C\ He chose us. He is a very brave person to do this.â\x80?Maezawa made a name and\ \ fortune for himself by defying the norms of Japanese society. A former drummer\ \ in a rock band, he built shopping website Zozotown, a popular destination for\ \ younger consumers, from a mail-order music album business.With a net worth of\ \ $2.3 billion, according to the Bloomberg Billionaires Index, Maezawa made a\ \ splash in the art world in 2017 when he spent $110.5 million on a single Jean-Michel\ \ Basquiat painting at a Sothebyâ\x80\x99s auction, setting a record for an American\ \ artistâ\x80\x99s work at the time. By then, Maezawa had already bought several\ \ Basquiat pieces.Maezawa has funded his art binge by selling shares in the company\ \ he founded. He sold about $250 million worth of stock in 2016 and used most\ \ of it to add to his art collection over the following two years. In May, Start\ \ Today said he had sold about 23 billion yen ($205 million) worth of the companyâ\x80\ \x99s shares. He has not announced major art purchases so far this year, suggesting\ \ at least some of the funds may have been used to participate in Muskâ\x80\x99\ s mission.â\x80\x9CI love art, so I want to see what artists will collaborate\ \ on together and" - text: "WASHINGTON: Three major Indian IT companies â\x80\x94 Infosys, Tata Consultancy\ \ Services and Wipro â\x80\x94 have joined US President Barack Obama's ambitious\ \ 'computer science for all' initiative as part of a public-private collaboration,\ \ pledging thousands of dollars in grants. Obama announced his 'Computer Sciences\ \ for All' plan in his weekly address on Saturday as he emphasized on the need\ \ for teaching the subject as a \"basic skill\" to all children across schools\ \ in the country in a changing economy. While Infosys has pledged a $1 million\ \ in donation, Tata Consultancy Services is providing support in the form of grants\ \ to teachers in 27 US cities, the White House said in a fact sheet, also issued\ \ on Saturday. Wipro announced a $2.8 million grant for multi-year project in\ \ partnership with the Michigan University to involve over a hundred school teachers,\ \ with the aim of nurturing excellence in science and mathematics. This would\ \ start with the public school systems of Chicago, Obama's hometown. According\ \ to White House, the TCS and Infosys pledge is part of the National Science Foundation's\ \ (NSF) effort to collaborate with the private sector to support high-school CS\ \ teachers. \"Infosys Foundation USA will be a founding member of this public-private\ \ collaboration with a $1 million philanthropic donation, and, as an initial participant,\ \ Tata Consultancy Services is providing additional support in the form of grants\ \ to teachers in 27 US cities. \"This collaboration will ultimately provide opportunities\ \ for as many as 2,000 middle- and high-school teachers to deepen their understanding\ \ of CS,\" said the White House. A joint Wipro and Michigan University statement\ \ said the Wipro STEM Fellowship Programme will focus on building leadership in\ \ these disciplines in urban schools by leveraging on research validated expertise\ \ of the College of Education at the university in designing transformative and\ \ innovative instructional experiences. Wipro's initiative is aligned with the\ \ US national goal to significantly improve the quality of education in science,\ \ technology, engineering and mathematics (STEM), it said. \"Wipro is committed\ \ to being an involved participant in its communities. This initiative seeks to\ \ develop and inspire young people to contribute to excellence in STEM education,\"\ \ said T K Kurien, chief executive officer and Member of the Board, Wipro Ltd.\ \ \"There is a critical shortage of excellent math and science teachers nationwide\ \ and even more so in urban school districts,\" said project co-leader Sonya Gunnings-Moton,\ \ assistant dean in the College of Education, Michigan State University. Aarti\ \ Dhupelia, chief officer of College and Career Success at Chicago Public Schools\ \ said this partnership with Wipro and Michigan State University that will have\ \ a transformational impact in classrooms and communities." - text: "When 21-year-old Sriram Srikant started nurturing dreams of making it to\ \ Harvard a couple of years back, he believed that he could achieve his dream.\ \ It would, however, require a great deal of initiative , dedication and work\ \ on the part of the IIT graduate in order to ultimately fulfil what he set out\ \ to achieve. â\x80\x9CIâ\x80\x99ve always loved studying biology, and opted for\ \ the subject in class XI as one of my majors, in addition to physics and chemistry.\ \ As I began studying the sciences, I decided that it was time that I started\ \ narrowing down my interests within biology itself,â\x80? says Srikant. It was\ \ while at the IIT that he could pin-point where his interest lay. â\x80\x9CIn\ \ the course of narrowing down my interests to a focal point, I realised that\ \ I wanted to study more about sub-cellular mechanics,â\x80? says Srikant. His\ \ interests then paved the way for an entry into Harvard widely considered as\ \ the pinnacle of higher education â\x80\x94 where Sriram will pursue a PhD programme\ \ in engineering and physical biology on a scholarship offered by the department\ \ of molecular and cellular biology. The five-and-a-half year programme, which\ \ includes guaranteed funding for Sriramâ\x80\x99s research project and a qualifying\ \ examination, will complement his interest . â\x80\x9CIn a way, the programme\ \ strikes a chord with my interests,â\x80? he says. â\x80\x9CEngineering and physical\ \ biology focuses on integrating quantitative sciences like physics and mathematics\ \ with the more qualitative and traditional sciences like biology and chemistry.â\x80\ ? Incidentally, Sriram is the only Indian to be admitted into the prestigious\ \ programme this academic year. The Harvard scholar now has his sights trained\ \ on research and academia. He would love to be a professor and teach at a college.\ \ He says, â\x80\x9CResearch is also one of my many interests; so I would spend\ \ a few years in a research programme and then begin to teach.â\x80?" - text: "Rannvijay Singh Singha sure can't live without his dose of action. And it's\ \ not just stunts that he craves for. His real passion is biking. \"\"Biking is\ \ not just a hobby for me, it's my passion. I live for the adrenaline rush. I\ \ often hear people crib that they have no time to pursue their interests. But\ \ I just don't agree with it. When you enjoy something it's not a chore. If I\ \ am travelling to Karjat for a shoot then I send my stuff in a car and ride to\ \ the location.\"\" Akshaye Khanna (TOI Photo) More picsHe loves to cook in his\ \ spare time. Besides acting and celebrating bachelorhood guess what Akshaye Khannaâ\x80\ \x99s hobby is? He loves to cook in his spare time. And his favourite shows on\ \ TV these days are cookery shows from across the world. Although I donâ\x80\x99\ t know much about cooking, I keep watching the cookery shows to know more about\ \ it, he smiles. We wonder why this sudden interest in cookery. Is the bachelor\ \ boy finally getting hooked and booked?" - text: 'PANAJI: Come mid-November, and it''s not uncommon to see a bridge being painted, streets being done up and buildings receiving their much-needed fresh coats of paint. Closer to November-end and the Entertainment Society of Goa (ESG) complex turns into a hub of activity. From festive lights and chattering delegates to a buzzing street and a variety of food stalls, they''re all there. It then dawns on you that it''s that time of the year again, when movie aficionados will soon be glancing through their film screening schedules, journalists prioritizing which press conferences to attend and casual passersby taking time out to walk the bedecked corniche or savouring some of those kebabs that sell like they wouldn''t at any other time of the year. There are, of course, the ever-enthusiastic bunch of film students that descend upon Goa and the delegates-national and international-who hobnob with each other, making sure they don''t miss out on the good movies. With a selection of 300 films from 61 countries to be screened at 11 theatres, the international film festival of India is here again. And better than ever, it seems. "Iffi this year could well be the best film festival Goa''s ever seen," says organizing committee member Raju Nayak. "With five years of experience, ESG has ensured that Iffi 2010 is going to be more professional and systematic than in the previous years," he adds. ESG CEO Manoj Srivastava agrees. "This year''s film festival aims at discipline in management, a professional attitude and less of ad-hocism. The entire effort is to manage Iffi efficiently and in a seamless manner rather than try to incorporate new things into each passing festival."The street across the ESG, too, is as noisy as it is nice. Walking along the corniche, one can sample some Bombay bhel puri, or perhaps some Mysore gobi Manchurian or American corn and then wash it down with some Nasik ice gola. They''re all bursting with enthusiasm and ready for business. If one''s not in the mood for food, one could just walk the lit-up street and pity the fish meekly peeking at you from an aquarium or stare in horror at an intimidating big black gorilla. "I''ve decided that this year around, the street will be decorated with scenes of different famous films like the Titanic or Batman. There will also be an underwater aquarium," says the brain behind the spruced-up corniche and a member of the organizing committee Francisco Martins. Martins, who says work commenced just ten days ago, admits that though it''s the eve of Iffi, work is not yet complete. However, he is confident of pulling it all together by Monday noon.On that note, lets draw up a checklist. Food stalls? check. Delegates aplenty? check. A street that makes one feel like they''ve stepped into a movie set? check. That unmistakable animated buzz? check. Lights? check. And of course, cameras and lots of action.' inference: true --- # SetFit with BAAI/bge-small-en-v1.5 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) 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:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) - **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:** 26 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 | |:------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | food and drinks | | | technology and computing | | | family and relationships | | | real estate | | | careers | | | home and garden | | | hobbies and interests | | | personal finance | | | health | | | healthy living | | | pharmaceuticals, conditions, and symptoms | | | movies | | | academic interests | | | travel | | | books and literature | | | style and fashion | | | television | | | business and finance | | | pets | | | arts and culture | | | news and politics | | | music and audio | | | shopping | | | automotives | | | video gaming | | | sports | | ## 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("biggy-smiley/setfit-bge-small-v1.5-sst2-8-shot") # Run inference preds = model("Rannvijay Singh Singha sure can't live without his dose of action. And it's not just stunts that he craves for. His real passion is biking. \"\"Biking is not just a hobby for me, it's my passion. I live for the adrenaline rush. I often hear people crib that they have no time to pursue their interests. But I just don't agree with it. When you enjoy something it's not a chore. If I am travelling to Karjat for a shoot then I send my stuff in a car and ride to the location.\"\" Akshaye Khanna (TOI Photo) More picsHe loves to cook in his spare time. Besides acting and celebrating bachelorhood guess what Akshaye Khanna’s hobby is? He loves to cook in his spare time. And his favourite shows on TV these days are cookery shows from across the world. Although I don’t know much about cooking, I keep watching the cookery shows to know more about it, he smiles. We wonder why this sudden interest in cookery. Is the bachelor boy finally getting hooked and booked?") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:---------|:----| | Word count | 99 | 304.2269 | 733 | | Label | Training Sample Count | |:------------------------------------------|:----------------------| | academic interests | 20 | | arts and culture | 20 | | automotives | 20 | | books and literature | 20 | | business and finance | 20 | | careers | 20 | | family and relationships | 20 | | food and drinks | 20 | | health | 20 | | healthy living | 20 | | hobbies and interests | 20 | | home and garden | 20 | | movies | 20 | | music and audio | 20 | | news and politics | 20 | | personal finance | 20 | | pets | 20 | | pharmaceuticals, conditions, and symptoms | 20 | | real estate | 20 | | shopping | 20 | | sports | 20 | | style and fashion | 20 | | technology and computing | 20 | | television | 20 | | travel | 20 | | video gaming | 20 | ### Training Hyperparameters - batch_size: (32, 32) - num_epochs: (5, 5) - 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: False ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:----:|:-------------:|:---------------:| | 0.0002 | 1 | 0.2217 | - | | 0.0123 | 50 | 0.2178 | - | | 0.0246 | 100 | 0.2161 | - | | 0.0369 | 150 | 0.2156 | - | | 0.0492 | 200 | 0.2108 | - | | 0.0615 | 250 | 0.2049 | - | | 0.0738 | 300 | 0.2042 | - | | 0.0861 | 350 | 0.1972 | - | | 0.0984 | 400 | 0.1869 | - | | 0.1108 | 450 | 0.1748 | - | | 0.1231 | 500 | 0.1662 | - | | 0.1354 | 550 | 0.1585 | - | | 0.1477 | 600 | 0.143 | - | | 0.1600 | 650 | 0.1219 | - | | 0.1723 | 700 | 0.1101 | - | | 0.1846 | 750 | 0.0902 | - | | 0.1969 | 800 | 0.0816 | - | | 0.2092 | 850 | 0.0689 | - | | 0.2215 | 900 | 0.0617 | - | | 0.2338 | 950 | 0.0519 | - | | 0.2461 | 1000 | 0.0427 | - | | 0.2584 | 1050 | 0.0381 | - | | 0.2707 | 1100 | 0.0378 | - | | 0.2830 | 1150 | 0.0325 | - | | 0.2953 | 1200 | 0.0306 | - | | 0.3077 | 1250 | 0.0277 | - | | 0.3200 | 1300 | 0.026 | - | | 0.3323 | 1350 | 0.023 | - | | 0.3446 | 1400 | 0.0246 | - | | 0.3569 | 1450 | 0.0202 | - | | 0.3692 | 1500 | 0.0191 | - | | 0.3815 | 1550 | 0.0205 | - | | 0.3938 | 1600 | 0.0173 | - | | 0.4061 | 1650 | 0.0173 | - | | 0.4184 | 1700 | 0.0158 | - | | 0.4307 | 1750 | 0.0144 | - | | 0.4430 | 1800 | 0.0141 | - | | 0.4553 | 1850 | 0.0126 | - | | 0.4676 | 1900 | 0.0117 | - | | 0.4799 | 1950 | 0.0082 | - | | 0.4922 | 2000 | 0.0101 | - | | 0.5046 | 2050 | 0.0096 | - | | 0.5169 | 2100 | 0.0095 | - | | 0.5292 | 2150 | 0.0096 | - | | 0.5415 | 2200 | 0.0078 | - | | 0.5538 | 2250 | 0.0086 | - | | 0.5661 | 2300 | 0.0077 | - | | 0.5784 | 2350 | 0.0086 | - | | 0.5907 | 2400 | 0.0063 | - | | 0.6030 | 2450 | 0.0084 | - | | 0.6153 | 2500 | 0.0068 | - | | 0.6276 | 2550 | 0.0066 | - | | 0.6399 | 2600 | 0.0075 | - | | 0.6522 | 2650 | 0.0058 | - | | 0.6645 | 2700 | 0.0053 | - | | 0.6768 | 2750 | 0.0047 | - | | 0.6891 | 2800 | 0.0043 | - | | 0.7015 | 2850 | 0.0048 | - | | 0.7138 | 2900 | 0.0051 | - | | 0.7261 | 2950 | 0.0048 | - | | 0.7384 | 3000 | 0.0039 | - | | 0.7507 | 3050 | 0.003 | - | | 0.7630 | 3100 | 0.0035 | - | | 0.7753 | 3150 | 0.0045 | - | | 0.7876 | 3200 | 0.0041 | - | | 0.7999 | 3250 | 0.0036 | - | | 0.8122 | 3300 | 0.003 | - | | 0.8245 | 3350 | 0.0028 | - | | 0.8368 | 3400 | 0.0031 | - | | 0.8491 | 3450 | 0.003 | - | | 0.8614 | 3500 | 0.0031 | - | | 0.8737 | 3550 | 0.0031 | - | | 0.8860 | 3600 | 0.0028 | - | | 0.8984 | 3650 | 0.0024 | - | | 0.9107 | 3700 | 0.0029 | - | | 0.9230 | 3750 | 0.0028 | - | | 0.9353 | 3800 | 0.0024 | - | | 0.9476 | 3850 | 0.002 | - | | 0.9599 | 3900 | 0.0021 | - | | 0.9722 | 3950 | 0.0018 | - | | 0.9845 | 4000 | 0.0017 | - | | 0.9968 | 4050 | 0.0017 | - | | 1.0091 | 4100 | 0.0016 | - | | 1.0214 | 4150 | 0.0016 | - | | 1.0337 | 4200 | 0.0015 | - | | 1.0460 | 4250 | 0.0015 | - | | 1.0583 | 4300 | 0.0014 | - | | 1.0706 | 4350 | 0.0014 | - | | 1.0829 | 4400 | 0.0014 | - | | 1.0952 | 4450 | 0.0014 | - | | 1.1076 | 4500 | 0.0014 | - | | 1.1199 | 4550 | 0.0013 | - | | 1.1322 | 4600 | 0.0013 | - | | 1.1445 | 4650 | 0.0013 | - | | 1.1568 | 4700 | 0.0013 | - | | 1.1691 | 4750 | 0.0013 | - | | 1.1814 | 4800 | 0.0012 | - | | 1.1937 | 4850 | 0.0012 | - | | 1.2060 | 4900 | 0.0012 | - | | 1.2183 | 4950 | 0.0012 | - | | 1.2306 | 5000 | 0.0012 | - | | 1.2429 | 5050 | 0.0012 | - | | 1.2552 | 5100 | 0.0012 | - | | 1.2675 | 5150 | 0.0012 | - | | 1.2798 | 5200 | 0.0012 | - | | 1.2921 | 5250 | 0.0012 | - | | 1.3045 | 5300 | 0.0011 | - | | 1.3168 | 5350 | 0.0011 | - | | 1.3291 | 5400 | 0.0011 | - | | 1.3414 | 5450 | 0.0011 | - | | 1.3537 | 5500 | 0.001 | - | | 1.3660 | 5550 | 0.0011 | - | | 1.3783 | 5600 | 0.001 | - | | 1.3906 | 5650 | 0.001 | - | | 1.4029 | 5700 | 0.001 | - | | 1.4152 | 5750 | 0.001 | - | | 1.4275 | 5800 | 0.001 | - | | 1.4398 | 5850 | 0.001 | - | | 1.4521 | 5900 | 0.0009 | - | | 1.4644 | 5950 | 0.001 | - | | 1.4767 | 6000 | 0.0009 | - | | 1.4890 | 6050 | 0.001 | - | | 1.5014 | 6100 | 0.0009 | - | | 1.5137 | 6150 | 0.0009 | - | | 1.5260 | 6200 | 0.0009 | - | | 1.5383 | 6250 | 0.0009 | - | | 1.5506 | 6300 | 0.0009 | - | | 1.5629 | 6350 | 0.0009 | - | | 1.5752 | 6400 | 0.0009 | - | | 1.5875 | 6450 | 0.0009 | - | | 1.5998 | 6500 | 0.0009 | - | | 1.6121 | 6550 | 0.0009 | - | | 1.6244 | 6600 | 0.0008 | - | | 1.6367 | 6650 | 0.0008 | - | | 1.6490 | 6700 | 0.0008 | - | | 1.6613 | 6750 | 0.0008 | - | | 1.6736 | 6800 | 0.0008 | - | | 1.6859 | 6850 | 0.0008 | - | | 1.6983 | 6900 | 0.0008 | - | | 1.7106 | 6950 | 0.0008 | - | | 1.7229 | 7000 | 0.0008 | - | ### Framework Versions - Python: 3.10.14 - SetFit: 1.1.0 - Sentence Transformers: 3.1.1 - Transformers: 4.44.2 - PyTorch: 2.4.0 - Datasets: 3.0.0 - 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} } ```