SAN (Self Attention Network) model is one of the most popular deep learning architectures used for various natural language processing (NLP) tasks. In this Jupyter notebook, we demonstrate how to effectively evaluate the performance of SAN model on a given NLP dataset using different evaluation metrics. We also provide a step-by-step guide on how to interpret the evaluation results and fine-tune the model for better performance. This notebook is intended for researchers and practitioners working in the field of NLP and deep learning.