Epoch: 0001 train_loss= 1.39362 train_acc= 0.23045 val_loss= 1.38191 val_acc= 0.32143 time= 0.79730
Epoch: 0002 train_loss= 1.39098 train_acc= 0.23184 val_loss= 1.37923 val_acc= 0.32143 time= 0.01563
Epoch: 0003 train_loss= 1.38969 train_acc= 0.23324 val_loss= 1.37680 val_acc= 0.32143 time= 0.00000
Epoch: 0004 train_loss= 1.38843 train_acc= 0.24721 val_loss= 1.37443 val_acc= 0.30357 time= 0.01563
Epoch: 0005 train_loss= 1.38714 train_acc= 0.27933 val_loss= 1.37230 val_acc= 0.30357 time= 0.00000
Epoch: 0006 train_loss= 1.38554 train_acc= 0.29888 val_loss= 1.37017 val_acc= 0.30357 time= 0.01563
Epoch: 0007 train_loss= 1.38571 train_acc= 0.30307 val_loss= 1.36821 val_acc= 0.30357 time= 0.00000
Epoch: 0008 train_loss= 1.38487 train_acc= 0.30028 val_loss= 1.36645 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.38481 train_acc= 0.30307 val_loss= 1.36501 val_acc= 0.30357 time= 0.00000
Epoch: 0010 train_loss= 1.38323 train_acc= 0.30168 val_loss= 1.36364 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.38197 train_acc= 0.30168 val_loss= 1.36232 val_acc= 0.30357 time= 0.01563
Epoch: 0012 train_loss= 1.38205 train_acc= 0.30168 val_loss= 1.36119 val_acc= 0.30357 time= 0.00000
Epoch: 0013 train_loss= 1.38160 train_acc= 0.30028 val_loss= 1.36026 val_acc= 0.30357 time= 0.01563
Epoch: 0014 train_loss= 1.38188 train_acc= 0.30168 val_loss= 1.35960 val_acc= 0.30357 time= 0.00000
Epoch: 0015 train_loss= 1.38064 train_acc= 0.30307 val_loss= 1.35928 val_acc= 0.30357 time= 0.01563
Epoch: 0016 train_loss= 1.38014 train_acc= 0.30028 val_loss= 1.35929 val_acc= 0.30357 time= 0.00000
Epoch: 0017 train_loss= 1.37983 train_acc= 0.30168 val_loss= 1.35958 val_acc= 0.30357 time= 0.01563
Epoch: 0018 train_loss= 1.38113 train_acc= 0.30168 val_loss= 1.36024 val_acc= 0.30357 time= 0.00000
Epoch: 0019 train_loss= 1.38110 train_acc= 0.30168 val_loss= 1.36121 val_acc= 0.30357 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37475 accuracy= 0.29204 time= 0.00000 
