Practical PyTorch · II
Understanding & fine-tuning — how models learn, and adapting a pretrained model to your own data, still without the heavy math.
-
How a Model Learns: Being Wrong, On Purpose, A Million Times
-
The Five-Line Training Loop That Makes PyTorch Learn
-
Datasets and DataLoaders: Feeding the Beast Without Choking It
-
Transfer Learning: Standing on a Pretrained Model's Shoulders
-
Fine-Tuning the Lazy Way: Let the Trainer Run Your Loop
-
Did Your Model Actually Learn Anything? Evaluating Honestly
-
LoRA: Fine-Tune a Giant Model on a Free GPU
-
When Not to Fine-Tune: The Cheaper Things to Try First
-
The Capstone: Fine-Tune a Model and Put It on the Hub