Training a model is a crucial step in machine learning, but it can be overwhelming for beginners. In this talk, we provide a comprehensive introduction to the fundamentals of model training. We will introduce the different types of training, such as supervised, unsupervised and semi-supervised learning, and then delve into techniques for supervised training. We will explain the training process, including error surfaces, optimization methods and back-propagation. We will explain key concepts such as trainable parameters and data requirements. We will also discuss the main “knobs” that control the training process, such as hyperparameters, regularization and batch normalization, and will provide an overview of metrics to monitor during training, including loss curves, model accuracy and precision. Additionally, we will cover common problems that arise during training, such as overfitting and underfitting, and introduce approaches to address these issues. Finally, we will touch on popular training frameworks and provide resources for further learning.