hard20 pts · first answer countsfine-tuningloragpu-memory
Adam state for a LoRA adapter
A LoRA adapter has 20 million trainable parameters kept in fp32, trained with AdamW. How much memory do the adapter weights, gradients and two Adam moments take together?
Discussion 0
Join free to post in the discussion.
Related questions
- What full fine-tuning changesMachine Learning Engineer
- Why begin from a pretrained modelMachine Learning Engineer
- Training only a new headMachine Learning Engineer
- Learning rate for fine-tuningMachine Learning Engineer
- Shape of SFT training dataMachine Learning Engineer
- Reading train and validation lossMachine Learning Engineer
- Meaning of PEFTMachine Learning Engineer
- What the LoRA rank r setsMachine Learning Engineer