0PricingLogin▼
Deep Learning Academy · Lesson

Fine-Tune with a Lower Learning Rate

Gently update pretrained weights.

Beyond Just the Head

Freezing the backbone is fast, but sometimes you want the whole model to adapt. Fine-tuning unfreezes it and trains everything together. 🔧

Unfreeze the Backbone

To fine-tune, you flip requires_grad back to True so the pretrained weights can move again during training.

for p in model.parameters():
    p.requires_grad = True

All lessons in this course

  1. Freeze the Backbone, Train the Head
  2. Fine-Tune with a Lower Learning Rate
  3. Discriminative Layer-Wise Rates
  4. Fine-Tune a Hugging Face Model
← Back to Deep Learning Academy