Epoch: 0001 train_loss= 1.40016 train_acc= 0.19531 val_loss= 1.39408 val_acc= 0.26786 time= 0.53128
Epoch: 0002 train_loss= 1.39697 train_acc= 0.19922 val_loss= 1.39097 val_acc= 0.26786 time= 0.00000
Epoch: 0003 train_loss= 1.39394 train_acc= 0.19922 val_loss= 1.38828 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 1.39017 train_acc= 0.21680 val_loss= 1.38625 val_acc= 0.32143 time= 0.00000
Epoch: 0005 train_loss= 1.38980 train_acc= 0.30469 val_loss= 1.38450 val_acc= 0.32143 time= 0.00000
Epoch: 0006 train_loss= 1.38840 train_acc= 0.32812 val_loss= 1.38296 val_acc= 0.32143 time= 0.01563
Epoch: 0007 train_loss= 1.38567 train_acc= 0.33789 val_loss= 1.38160 val_acc= 0.32143 time= 0.00000
Epoch: 0008 train_loss= 1.38367 train_acc= 0.33789 val_loss= 1.38041 val_acc= 0.32143 time= 0.01562
Epoch: 0009 train_loss= 1.38227 train_acc= 0.33789 val_loss= 1.37937 val_acc= 0.32143 time= 0.00000
Epoch: 0010 train_loss= 1.38120 train_acc= 0.33789 val_loss= 1.37845 val_acc= 0.32143 time= 0.01563
Epoch: 0011 train_loss= 1.37851 train_acc= 0.33789 val_loss= 1.37762 val_acc= 0.32143 time= 0.00000
Epoch: 0012 train_loss= 1.37932 train_acc= 0.33789 val_loss= 1.37696 val_acc= 0.32143 time= 0.00000
Epoch: 0013 train_loss= 1.37619 train_acc= 0.33789 val_loss= 1.37643 val_acc= 0.32143 time= 0.01563
Epoch: 0014 train_loss= 1.37461 train_acc= 0.33789 val_loss= 1.37603 val_acc= 0.32143 time= 0.00000
Epoch: 0015 train_loss= 1.37313 train_acc= 0.33789 val_loss= 1.37583 val_acc= 0.32143 time= 0.01563
Epoch: 0016 train_loss= 1.37229 train_acc= 0.33789 val_loss= 1.37585 val_acc= 0.32143 time= 0.00000
Epoch: 0017 train_loss= 1.37206 train_acc= 0.33789 val_loss= 1.37612 val_acc= 0.32143 time= 0.01563
Epoch: 0018 train_loss= 1.37033 train_acc= 0.33789 val_loss= 1.37672 val_acc= 0.32143 time= 0.00000
Epoch: 0019 train_loss= 1.36946 train_acc= 0.33789 val_loss= 1.37764 val_acc= 0.32143 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37795 accuracy= 0.30973 time= 0.01563 
