Hyperparameter searching is one of the significant challenges in training deep learningDeep learning models. To solve this challenge, the Bees AlgorithmBees algorithm (BA), which simulates the foraging behaviour of honey bees, is used for hyperparameter searching and finding the best set of hyperparameters for a given deep learningDeep learning model. This study applies a two-parameter version of the Bees Algorithm (BA2)Bees Algorithm (BA) to search for the best set of hyperparameters for a Convolutional Neural Network (CNN)Convolutional Neural Network (CNN) combined with a Long Short-Term Memory (LSTM)Long Short-Term Memory (LSTM) model. Then, the model is used to predict the remaining useful life (RUL)Remaining useful life (RUL) of ball bearingsBall bearings. BA2 Algorithmsuses the traplining foraging technique of bees to integrate explorative and exploitative search mechanisms, reduce the number of parameters to only two and improve the remaining useful life (RUL)Remaining useful life (RUL) predictionPrediction. The algorithmAlgorithms can find a set of hyperparameters that makes the deep learningDeep learning model perform better than the IEEEPrognosis and health management (PHM) PHM 2012 Prognostic challenge winner by 38.97%.