C.W.K.
Stream
Quiz · 5 questions

🏋️ Training Technique

The knobs that make or break results

Level 0Observer
0 XP0/43 lessons0/11 achievements
0/120 XP to next level120 XP to go0% complete

Quiz

01What is the recommended starting learning rate for LoRA/QLoRA fine-tuning?
02What does gradient accumulation do?
03What is the canonical sign of overfitting in fine-tuning loss curves?
04What advantage does DPO have over traditional RLHF?
05When using LLM-as-judge for pairwise comparison, why randomize A/B position?
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.