06 · GENERALIZATION

Verified

Loss, Overfitting, and Forgetting

Do not confuse loss with business quality; combine domain, format, safety, and retention metrics.

QUICK LOOK
  • Train↓ Val↑ = overfitting
  • Domain↑ General↓ = forgetting
  • Loss ≠ quality
  • Checkpoint pick is multi-metric

KNOW THESE FIRST

losssteptrainvalidationoverfit onsetCONCEPT DIAGRAM

The budget, window, and …Training loss tracks fit to the optimized target; validation loss tracks generalization on an unseen split. Falling train loss with rising validation loss is an overfitting signal.

Catastrophic forgetting is different: the new domain improves while prior/general ability declines. LoRA preserves the base but an active adapter can still create behavioral interference.

01

First thought

Lower validation loss always means the better production model.

02

Correction

Loss measures the token objective; JSON validity, task accuracy, and safety require separate metrics.

03

Decision rule

Select checkpoints with validation loss + task metric + retention threshold.

CONCEPT DEPTH

Read the same concept at three depths. Pick a level, switch instantly. Recommended starting point for university students: UNDERGRAD.

UNDERGRAD

Training loss measures fit to the optimized target. Validation loss measures generalization on an unseen split. If train falls while validation rises, that is overfitting. Catastrophic forgetting is different: new ability improves while prior/general ability declines. Loss is not by itself a quality proof; domain/format/safety metrics must also be measured.