thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Advanced

Catastrophic Forgetting

When fine-tuning on new data causes a model to lose previously learned capabilities.

Definition

Aggressive full fine-tuning on narrow data can degrade general skills. Mitigations include PEFT, lower learning rates, fewer epochs and mixing in general data.

Exam tip

PEFT methods and mixing in general data reduce catastrophic forgetting compared with full fine-tuning.

Related terms