The Little Book of ML Metrics provides clear, concise explanations of machine learning metrics from accuracy to obscure ones like the P4 metric. Written to fill gaps in traditional data science education, it serves as a quick-reference handbook covering 10 metric categories including regression, classification, clustering, ranking, computer vision, NLP, probabilistic metrics, bias/fairness, and data observability. The repository is open-source with a purchasable printed edition supporting ongoing development.