Epoch: 0001 train_loss= 1.38808 train_acc= 0.25733 val_loss= 1.36694 val_acc= 0.33929 time= 0.20314
Epoch: 0002 train_loss= 1.38436 train_acc= 0.29642 val_loss= 1.36363 val_acc= 0.26786 time= 0.01563
Epoch: 0003 train_loss= 1.38503 train_acc= 0.27036 val_loss= 1.36034 val_acc= 0.28571 time= 0.00000
Epoch: 0004 train_loss= 1.38433 train_acc= 0.27362 val_loss= 1.35713 val_acc= 0.28571 time= 0.01563
Epoch: 0005 train_loss= 1.38313 train_acc= 0.27036 val_loss= 1.35414 val_acc= 0.28571 time= 0.00000
Epoch: 0006 train_loss= 1.38215 train_acc= 0.27036 val_loss= 1.35157 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.38080 train_acc= 0.27036 val_loss= 1.34949 val_acc= 0.28571 time= 0.00000
Epoch: 0008 train_loss= 1.38159 train_acc= 0.27036 val_loss= 1.34833 val_acc= 0.28571 time= 0.00000
Epoch: 0009 train_loss= 1.37993 train_acc= 0.27036 val_loss= 1.34756 val_acc= 0.28571 time= 0.01563
Epoch: 0010 train_loss= 1.38277 train_acc= 0.27036 val_loss= 1.34782 val_acc= 0.28571 time= 0.00000
Epoch: 0011 train_loss= 1.38052 train_acc= 0.27036 val_loss= 1.34819 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.38155 train_acc= 0.27036 val_loss= 1.34854 val_acc= 0.28571 time= 0.00000
Epoch: 0013 train_loss= 1.37902 train_acc= 0.27036 val_loss= 1.34872 val_acc= 0.28571 time= 0.00000
Epoch: 0014 train_loss= 1.37998 train_acc= 0.27036 val_loss= 1.34908 val_acc= 0.28571 time= 0.00000
Epoch: 0015 train_loss= 1.38004 train_acc= 0.27036 val_loss= 1.34952 val_acc= 0.28571 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.39052 accuracy= 0.25664 time= 0.01563 
