Should I prefer the model with the lowest validation loss or the highest validation accuracy to deploy?

I trained a ResNet20 on Cifar10 and obtained the following learning curves. From the figures, I see at epoch 52, my validation loss is 0.323 (the lowest), and my validation accuracy is 89.7%. On the other hand, at the end of the training (epoch 120), my validation loss is 0.413 and my validation accuracy is…

Should I prefer the model with the lowest validation loss or the highest validation accuracy to deploy?

I trained a ResNet20 on Cifar10 and obtained the following learning curves. From the figures, I see at epoch 52, my validation loss is 0.323 (the lowest), and my validation accuracy is 89.7%. On the other hand, at the end of the training (epoch 120), my validation loss is 0.413 and my validation accuracy is…

Should I prefer the model with the lowest validation loss or the lowest validation accuracy to deploy?

I trained a ResNet20 on Cifar10 and obtained the following learning curves. From the figures, I see at epoch 52, my validation loss is 0.323 (the lowest), and my validation accuracy is 89.7%. On the other hand, at the end of the training (epoch 120), my validation loss is 0.413 and my validation accuracy is…