Milestone 1: Working pipeline on small novel usecase
Past due by 5 months
95% complete
Dataset
- Forget set: Biographical author details across all authors
- Retain set: All non-biographical questions & answers
- Train set: All synthetic authors data
Fine-tuning
- Fine-tune a small model (e.g. GPT2) on train set
- Fine-tune a small model (e.g. GPT2) on retain set
Forgetting
- Unlearn the forget set using gradient ascent [& another?]
Evaluating
- R…
Dataset
- Forget set: Biographical author details across all authors
- Retain set: All non-biographical questions & answers
- Train set: All synthetic authors data
Fine-tuning
- Fine-tune a small model (e.g. GPT2) on train set
- Fine-tune a small model (e.g. GPT2) on retain set
Forgetting
- Unlearn the forget set using gradient ascent [& another?]
Evaluating
- Run forget quality and utility evaluation.
- Initial sanity check (debug fine-tuning): GPT2 base model vs. GPT2 fine-tuned on all TOFU
- Then: GPT2 unlearnt model vs. GPT2 fine-tuned on retain (gold standard)