The growing prevalence of cybersecurity threats has increased the demand for robust intrusion detection systems (IDSs). Deep learning techniques have shown promising results in detecting and mitigating these threats, making them an increasingly popular choice in IDS design. However, evaluating the performance of deep learning-based IDSs can be challenging due to the complexity of the models and the lack of standardized evaluation metrics. This review paper presents an overview of the most common evaluation metrics used in deep learning-based IDSs, including precision, confusion metrics, accuracy, F1 score, Area Under Curve (AUC), and recall. Several studies have applied machine-learning classic algorithms like Random Forest, Decision Tree, Logistic Regression, and others, but for this paper, we used a Convolutional Neural Network (CNN) that would be independent of the features in the dataset. The studied papers did not provide AUC and none of them balanced the dataset based on the feature's proportion. The dataset utilized in this study is the CSE-CIC-IDS2018 dataset, which underwent meticulous cleansing and normalization procedures to ensure the inclusion of legitimate and useful data. Furthermore, a weighting mechanism was introduced to balance the dataset and mitigate the potential for bias in the Machine Learning process.