hard20 pts · first answer countsfine-tuningrlhftraining-data
Pairs where both answers are equal
About 25% of your human comparisons are marked "both equally good". What is the safest handling for a Bradley-Terry reward model?
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