Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Lee, Sangyoon, Lee, Jaeho
Materialtyp: Preprint
Publicerad: 2026
Ämnen:
Länkar:https://arxiv.org/abs/2602.09492
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!
Innehållsförteckning:
  • Low-rank adaptation (LoRA) is a standard approach for fine-tuning large language models, yet its many variants report conflicting empirical gains, often on the same benchmarks. We show that these contradictions arise from a single overlooked factor: the batch size. When properly tuned, vanilla LoRA often matches the performance of more complex variants. We further propose a proxy-based, cost-efficient strategy for batch size tuning, revealing the impact of rank, dataset size, and model capacity on the optimal batch size. Our findings elevate batch size from a minor implementation detail to a first-order design parameter, reconciling prior inconsistencies and enabling more reliable evaluations of LoRA variants.