Epoch: 0001 train_loss= 1.38558 train_acc= 0.31270 val_loss= 1.38405 val_acc= 0.33929 time= 0.25002
Epoch: 0002 train_loss= 1.38596 train_acc= 0.33225 val_loss= 1.38359 val_acc= 0.33929 time= 0.01562
Epoch: 0003 train_loss= 1.38417 train_acc= 0.33550 val_loss= 1.38323 val_acc= 0.33929 time= 0.00000
Epoch: 0004 train_loss= 1.38151 train_acc= 0.33876 val_loss= 1.38300 val_acc= 0.33929 time= 0.01563
Epoch: 0005 train_loss= 1.38136 train_acc= 0.34202 val_loss= 1.38290 val_acc= 0.33929 time= 0.00000
Epoch: 0006 train_loss= 1.37629 train_acc= 0.33876 val_loss= 1.38295 val_acc= 0.33929 time= 0.00000
Epoch: 0007 train_loss= 1.37829 train_acc= 0.33876 val_loss= 1.38311 val_acc= 0.33929 time= 0.01563
Epoch: 0008 train_loss= 1.37668 train_acc= 0.33876 val_loss= 1.38349 val_acc= 0.33929 time= 0.00000
Epoch: 0009 train_loss= 1.37698 train_acc= 0.33876 val_loss= 1.38400 val_acc= 0.33929 time= 0.01563
Epoch: 0010 train_loss= 1.37470 train_acc= 0.33550 val_loss= 1.38471 val_acc= 0.33929 time= 0.00000
Epoch: 0011 train_loss= 1.37222 train_acc= 0.33876 val_loss= 1.38560 val_acc= 0.33929 time= 0.01563
Epoch: 0012 train_loss= 1.37198 train_acc= 0.33550 val_loss= 1.38669 val_acc= 0.33929 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.38510 accuracy= 0.28319 time= 0.01563 
