# LoRA Speedrun – Public Leaderboard for Fine-Tuning Techniques Who can fine-tune Qwen2.5-1.5B the fastest on a single L40S GPU? - **Source:** [Hacker News (news.ycombinator.com)](https://brifing.si/source/13c923cd-6d99-442b-9b8b-1181f4d8cd91) - **Published:** 2026-07-20 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/54f20722-4738-4268-b011-4d19401a4937 ## The Speedrun Begins A unique platform to benchmark LoRA fine-tuning techniques: fixed hardware, fixed task, and an open leaderboard. Ready to break the record for fastest training of Qwen2.5-1.5B on GSM8K dataset with ≥57% accuracy? ## Fair Competition Environment All records are verified with 3 independent runs on identical L40S GPUs. Modal's free compute credits enable universal participation. Attempts and verifications are conducted with full transparency. ## Current Records Current GSM8K track record: 6m 05s by @Saivineeth147. SQuAD v1.1 track remains open. Two distinct model families and task types test technique generalizability. ## Verification Process Each submission is re-run with 3 fresh seeds. Code review, security screening, and performance verification are conducted. The entire process is transparently documented and publicly reported. ## Untapped Technique Opportunities Many techniques like sequence packing, LoRA+, NEFTune, Unsloth kernels remain unexplored. New records can be set through data selection, learning rate tuning, and other optimizations. Ready-to-use templates available. ## Why It Matters LoRA/QLoRA dominates real-world fine-tuning, but techniques lacked comparability. This project accelerates progress by testing approaches in standardized conditions - essentially the fine-tuning version of nanoGPT speedrunning. ## Sources covering this story - https://github.com/Saivineeth147/lora-speedrun — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._