Epoch: 0001 train_loss= 2.93494 train_acc= 0.52424 val_loss= 0.81901 val_acc= 0.55738 time= 0.35940
Epoch: 0002 train_loss= 0.86691 train_acc= 0.53636 val_loss= 0.81887 val_acc= 0.54098 time= 0.01563
Epoch: 0003 train_loss= 1.16985 train_acc= 0.53333 val_loss= 0.78596 val_acc= 0.55738 time= 0.01563
Epoch: 0004 train_loss= 3.38606 train_acc= 0.53333 val_loss= 0.80889 val_acc= 0.55738 time= 0.01573
Epoch: 0005 train_loss= 0.95828 train_acc= 0.55758 val_loss= 0.68229 val_acc= 0.57377 time= 0.01563
Epoch: 0006 train_loss= 2.45583 train_acc= 0.51515 val_loss= 0.68197 val_acc= 0.55738 time= 0.03125
Epoch: 0007 train_loss= 2.31080 train_acc= 0.51818 val_loss= 0.72753 val_acc= 0.52459 time= 0.01563
Epoch: 0008 train_loss= 2.69067 train_acc= 0.50606 val_loss= 0.69556 val_acc= 0.54098 time= 0.03125
Epoch: 0009 train_loss= 0.88239 train_acc= 0.53030 val_loss= 0.71612 val_acc= 0.54098 time= 0.01563
Epoch: 0010 train_loss= 0.77760 train_acc= 0.55455 val_loss= 0.74656 val_acc= 0.55738 time= 0.01563
Epoch: 0011 train_loss= 1.05233 train_acc= 0.53636 val_loss= 0.77866 val_acc= 0.55738 time= 0.03125
Epoch: 0012 train_loss= 0.94983 train_acc= 0.53939 val_loss= 0.78360 val_acc= 0.54098 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.73207 accuracy= 0.47541 time= 0.01563 
