Epoch: 0001 train_loss= 1.43984 train_acc= 0.25733 val_loss= 1.37978 val_acc= 0.26786 time= 0.12523
Epoch: 0002 train_loss= 1.41460 train_acc= 0.24756 val_loss= 1.38371 val_acc= 0.28571 time= 0.01540
Epoch: 0003 train_loss= 1.40618 train_acc= 0.22801 val_loss= 1.38767 val_acc= 0.28571 time= 0.00000
Epoch: 0004 train_loss= 1.38749 train_acc= 0.29967 val_loss= 1.39317 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38704 train_acc= 0.30293 val_loss= 1.39958 val_acc= 0.12500 time= 0.01563
Epoch: 0006 train_loss= 1.39068 train_acc= 0.28664 val_loss= 1.40604 val_acc= 0.17857 time= 0.01563
Epoch: 0007 train_loss= 1.39149 train_acc= 0.30293 val_loss= 1.40997 val_acc= 0.19643 time= 0.01563
Epoch: 0008 train_loss= 1.38789 train_acc= 0.26710 val_loss= 1.41353 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.38635 train_acc= 0.25733 val_loss= 1.41447 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.39611 train_acc= 0.26059 val_loss= 1.41484 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.39501 train_acc= 0.27687 val_loss= 1.41316 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.38920 train_acc= 0.28013 val_loss= 1.41048 val_acc= 0.26786 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39262 accuracy= 0.25664 time= 0.01563 
