Epoch: 0001 train_loss= 0.70726 train_acc= 0.50000 val_loss= 0.68699 val_acc= 0.55738 time= 0.51581
Epoch: 0002 train_loss= 0.70747 train_acc= 0.50182 val_loss= 0.68766 val_acc= 0.55738 time= 0.01563
Epoch: 0003 train_loss= 0.70059 train_acc= 0.49818 val_loss= 0.68893 val_acc= 0.55738 time= 0.00000
Epoch: 0004 train_loss= 0.69530 train_acc= 0.50364 val_loss= 0.69064 val_acc= 0.55738 time= 0.00000
Epoch: 0005 train_loss= 0.69269 train_acc= 0.49818 val_loss= 0.69257 val_acc= 0.55738 time= 0.01563
Epoch: 0006 train_loss= 0.69895 train_acc= 0.52000 val_loss= 0.69447 val_acc= 0.45902 time= 0.00000
Epoch: 0007 train_loss= 0.69357 train_acc= 0.49273 val_loss= 0.69628 val_acc= 0.40984 time= 0.01563
Epoch: 0008 train_loss= 0.69397 train_acc= 0.45818 val_loss= 0.69768 val_acc= 0.45902 time= 0.00000
Epoch: 0009 train_loss= 0.69388 train_acc= 0.48364 val_loss= 0.69857 val_acc= 0.47541 time= 0.00000
Epoch: 0010 train_loss= 0.69576 train_acc= 0.48182 val_loss= 0.69889 val_acc= 0.45902 time= 0.01563
Epoch: 0011 train_loss= 0.69447 train_acc= 0.50000 val_loss= 0.69869 val_acc= 0.45902 time= 0.00000
Epoch: 0012 train_loss= 0.69778 train_acc= 0.48182 val_loss= 0.69820 val_acc= 0.45902 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69279 accuracy= 0.52459 time= 0.00000 
