about the train loss

[Usernamezhx]

thank for you work. I train the model with command:

python train.py --dataset rico --batch_size 64 --iteration 200000 --latent_size 4 --lr 1e-05 --G_d_model 256 --G_nhead 4 --G_num_layers 8 --D_d_model 256 --D_nhead 4 --D_num_layers 8

and it will show me that. does it look normal ? the generator loss become large and Discriminator loss become small :

[ktrk115]

Sorry for the late response.

The generator seems relatively weak, but I think it is a natural behavior. You may update the generator two or more times for each update of the discriminator. The number of updates is a tunable hyperparameter.

[Usernamezhx]

Sorry for the late response.

The generator seems relatively weak, but I think it is a natural behavior. You may update the generator two or more times for each update of the discriminator. The number of updates is a tunable hyperparameter.

thanks for your reply. I will try