medium10 pts · first answer countsfine-tuningrlhf
Win probability from a reward gap
Under the Bradley-Terry model, response A scores 2.0 and response B scores 0.0 on the reward model. What is the modelled probability that A is preferred?
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