{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T00:03:47Z","timestamp":1792886627816,"version":"4.5.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Deanship of Graduate Studies and Scientific Research-Najran University Easy Funding Program","award":["NU\/EFP\/SERC\/13\/29"],"award-info":[{"award-number":["NU\/EFP\/SERC\/13\/29"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1746511"],"award-info":[{"award-number":["1746511"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1926990"],"award-info":[{"award-number":["1926990"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1513126"],"award-info":[{"award-number":["1513126"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3470850","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:29:19Z","timestamp":1727702959000},"page":"153221-153231","source":"Crossref","is-referenced-by-count":25,"title":["Repeatability of Fine-Tuning Large Language Models Illustrated Using QLoRA"],"prefix":"10.1109","volume":"12","author":[{"given":"Saeed S.","family":"Alahmari","sequence":"first","affiliation":[{"name":"Department of Computer Science, Najran University, Najran, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7898-8456","authenticated-orcid":false,"given":"Lawrence O.","family":"Hall","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1008-4055","authenticated-orcid":false,"given":"Peter R.","family":"Mouton","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-863X","authenticated-orcid":false,"given":"Dmitry B.","family":"Goldgof","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Najran University, Najran, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"140","key":"ref4","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"120","key":"ref5","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.603"},{"key":"ref7","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref9","article-title":"MetaICL: Learning to learn in context","author":"Min","year":"2021","journal-title":"arXiv:2110.15943"},{"key":"ref10","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021","journal-title":"arXiv:2109.01652"},{"key":"ref11","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Ouyang"},{"key":"ref12","article-title":"Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref13","article-title":"QLoRA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2023","journal-title":"arXiv:2305.14314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2017.00076"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039833"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref17","author":"Chollet","year":"2015","journal-title":"Keras"},{"key":"ref18","author":"Abadi","year":"2015","journal-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref19","first-page":"316","article-title":"Randomness in neural network training: Characterizing the impact of tooling","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Zhuang"},{"key":"ref20","first-page":"9913","article-title":"Nondeterminism and instability in neural network optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Summers"},{"key":"ref21","article-title":"On the reproducibility of neural network predictions","author":"Bhojanapalli","year":"2021","journal-title":"arXiv:2102.03349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00709-3"},{"key":"ref23","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"Dodge","year":"2020","journal-title":"arXiv:2002.06305"},{"key":"ref24","article-title":"On the stability of fine-tuning Bert: Misconceptions, explanations, and strong baselines","author":"Mosbach","year":"2020","journal-title":"arXiv:2006.04884"},{"key":"ref25","article-title":"Mixout: Effective regularization to finetune large-scale pretrained language models","author":"Lee","year":"2019","journal-title":"arXiv:1909.11299"},{"key":"ref26","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref27","article-title":"PB-LLM: Partially binarized large language models","author":"Shang","year":"2023","journal-title":"arXiv:2310.00034"},{"key":"ref28","first-page":"4","volume-title":"Aident5","year":"2023"},{"key":"ref29","article-title":"Platypus: Quick, cheap, and powerful refinement of LLMs","author":"Lee","year":"2023","journal-title":"arxiv:2308.07317"},{"key":"ref30","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023","journal-title":"arXiv:2305.20050"},{"key":"ref31","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lu"},{"key":"ref32","article-title":"SciBench: Evaluating college-level scientific problem-solving abilities of large language models","author":"Wang","year":"2023","journal-title":"arXiv:2307.10635"},{"key":"ref33","first-page":"1","article-title":"ReClor: A reading comprehension dataset requiring logical reasoning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.489"},{"key":"ref35","first-page":"1","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"Proc. NeurIPS","author":"Hendrycks"},{"key":"ref36","article-title":"Arb: Advanced reasoning benchmark for large language models","author":"Sawada","year":"2023","journal-title":"arXiv:2307.13692"},{"key":"ref37","year":"2016","journal-title":"Artifact Review and Badging"},{"key":"ref38","article-title":"The pile: An 800GB dataset of diverse text for language modeling","author":"Gao","year":"2021","journal-title":"arXiv:2101.00027"},{"key":"ref39","article-title":"RoFormer: Enhanced transformer with rotary position embedding","author":"Su","year":"2021","journal-title":"arXiv:2104.09864"},{"key":"ref40","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref41","article-title":"Mesh-transformer-JAX: Model-parallel implementation of transformer language model with JAX","author":"Wang","year":"2021"},{"key":"ref42","volume-title":"GPT-Neox-Chat-20b","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref44","first-page":"1","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref45","article-title":"GLU variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv:2002.05202"},{"key":"ref46","volume-title":"LLAMA2-Chat Model","year":"2023"},{"key":"ref47","volume-title":"Perplexity of Fixed-Length Models\u2014Huggingface.co","year":"2024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10380310\/10700744-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10700744.pdf?arnumber=10700744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T19:38:21Z","timestamp":1732649901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3470850","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}