Epoch: 0001 train_loss= 1.38994 train_acc= 0.23743 val_loss= 1.39112 val_acc= 0.23214 time= 0.89591
Epoch: 0002 train_loss= 1.38789 train_acc= 0.23743 val_loss= 1.39179 val_acc= 0.23214 time= 0.00000
Epoch: 0003 train_loss= 1.38517 train_acc= 0.23883 val_loss= 1.39258 val_acc= 0.23214 time= 0.01050
Epoch: 0004 train_loss= 1.38390 train_acc= 0.23883 val_loss= 1.39349 val_acc= 0.23214 time= 0.00000
Epoch: 0005 train_loss= 1.38319 train_acc= 0.24302 val_loss= 1.39449 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38004 train_acc= 0.25140 val_loss= 1.39562 val_acc= 0.28571 time= 0.00000
Epoch: 0007 train_loss= 1.37897 train_acc= 0.26955 val_loss= 1.39685 val_acc= 0.23214 time= 0.01563
Epoch: 0008 train_loss= 1.37919 train_acc= 0.28631 val_loss= 1.39825 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.37722 train_acc= 0.32542 val_loss= 1.39979 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.37400 train_acc= 0.32263 val_loss= 1.40149 val_acc= 0.23214 time= 0.00000
Epoch: 0011 train_loss= 1.37429 train_acc= 0.32402 val_loss= 1.40339 val_acc= 0.23214 time= 0.00000
Epoch: 0012 train_loss= 1.37327 train_acc= 0.32402 val_loss= 1.40550 val_acc= 0.23214 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.35282 accuracy= 0.36283 time= 0.00000 
