In the field of vehicle aerodynamic simulation, Reynold Averaged Navier-Stokes (RANS) model is widely used due to its high efficiency. However, it has some limitations in capturing complex flow features and simulating large separated flows. In order to improve the computational accuracy within a suitable cost, the Field Inversion and Machine Learning (FIML) method, based on a data-driven approach, has received increasing attention in recent years. In this paper, the optimal coefficients of the Generalized k-ω (GEKO) model are firstly obtained by the discrete adjoint method of FIML, utilizing the results of wind tunnel experiments. Then, the mapping relationship between the flow field characteristics and the optimal coefficients is established by a neural network to augment the turbulence model. On the basis of that, the study further investigates the effects of hyperparameters such as epoch, batch size, activation function, and learning rate on the accuracy of the augmented GEKO model. The result shows that with the drag coefficient (CD) as the target, batch size and activation function significantly influence the accuracy of the trained model. When a batch size of 512 and either Softsign or Leaky-ReLU activation function are employed, the trained model predicts CD value closest to the experimental values in the condition of 2000 epochs and a learning rate of 0.001. Increasing the batch size to 1024 or the learning rate to 0.002 provides some improvement in model accuracy, but the effect is not obvious. This work is an important reference for the debugging and improvement of FIML method.