training on CIFAR-10 performs not well, whether L2 loss or FID

[chengyiqiu1121]

hi developers: I am sorry to bother you! I am training on CIFAR-10, with setting train_num_step=500k, batch=16, unet dim 64. But get FID 21.57 not well. And when i increase the train step to 1000k, the FID increases to 23. when I change the dataset to GTSRB, with train step 500k, it gets FID 7.9, and change dataset to CelebA($64\times 64$), it gets FID 13. That is really confusing. Now i am training the model from scratch again using CIFAR-10 with unet dim 128. The loss (L2) is decreasing very slowly(around 0.05). I would appreciate it if you could help me!