Quiz · 5 questions
🎯 Trainer + PEFT
SFT, LoRA, QLoRA, DPO
Level 0Scout
0 XP0/50 lessons0/10 achievements
0/120 XP to next level120 XP to go0% complete
Quiz
01What is the effective batch size when
per_device_train_batch_size=4, gradient_accumulation_steps=8, on 2 GPUs?02Why use
DataCollatorForCompletionOnlyLM for instruction tuning?03When should you fine-tune instead of using RAG?
04What does QLoRA quantize?
05When should you train with LoRA but ship merged?
Comments 0
🔔 Reply notifications (sign in)Sign in — Please sign in to comment.
No comments yet — be the first.