Catastrophic Forgetting

Walk through the triage order when a customer-support LoRA tanks MMLU by 4 points post-deploy

Replay-buffer mix for domain SFT: how much general data, and from where?

Designing a code-assistant SFT mix: how should domain and general data balance?

Pretraining vs fine-tuning: two key differences in data and objective.

Which of these belong on the ship-checklist for a production fine-tune?

Why 'fine-tune on our company docs' usually fails: and what to do instead

Best architecture for a chatbot over a frequently-updated company knowledge base?

Match training regime to sensible peak LR range

Why does fine-tuning on company docs often raise hallucination instead of lowering it?

Design the post-FT eval suite for a customer-support fine-tune

Which buckets MUST a post-FT eval suite include for a customer-support fine-tune?

Which of these reduce catastrophic forgetting in practice?

How do you detect catastrophic forgetting after a domain fine-tune?

Which signal is the most reliable indicator of catastrophic forgetting?