---
library_name: peft
tags:
- peft
- product
- LoRA
---
## Training procedure

per_device_train_batch_size=4, 
gradient_accumulation_steps=4,
warmup_steps=100,
max_steps=100,
learning_rate=1e-3, 
fp16=True,
logging_steps=1, 
output_dir='outputs'

### Framework versions


- PEFT 0.5.0.dev0