On a small BERT multi-task model, rank-1 LoRA with automatic mixed precision matches higher-rank and full fine-tuning accuracy while saving memory and time.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Efficient Learning of Small BERT Networks with LoRA and DoRA
On a small BERT multi-task model, rank-1 LoRA with automatic mixed precision matches higher-rank and full fine-tuning accuracy while saving memory and time.