Epoch: 0001 train_loss= 0.78049 train_acc= 0.50606 val_loss= 0.80156 val_acc= 0.44262 time= 0.15626
Epoch: 0002 train_loss= 0.81591 train_acc= 0.44242 val_loss= 0.81761 val_acc= 0.40984 time= 0.00000
Epoch: 0003 train_loss= 0.86740 train_acc= 0.50000 val_loss= 0.77853 val_acc= 0.42623 time= 0.01563
Epoch: 0004 train_loss= 0.85590 train_acc= 0.50303 val_loss= 0.72164 val_acc= 0.45902 time= 0.01562
Epoch: 0005 train_loss= 0.76482 train_acc= 0.52727 val_loss= 0.71657 val_acc= 0.47541 time= 0.01563
Epoch: 0006 train_loss= 0.79244 train_acc= 0.50909 val_loss= 0.70168 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.80338 train_acc= 0.51515 val_loss= 0.70082 val_acc= 0.55738 time= 0.00000
Epoch: 0008 train_loss= 0.76177 train_acc= 0.51818 val_loss= 0.70611 val_acc= 0.57377 time= 0.01563
Epoch: 0009 train_loss= 0.86007 train_acc= 0.52121 val_loss= 0.70292 val_acc= 0.57377 time= 0.01563
Epoch: 0010 train_loss= 0.95662 train_acc= 0.52121 val_loss= 0.69773 val_acc= 0.57377 time= 0.01563
Epoch: 0011 train_loss= 0.75630 train_acc= 0.52424 val_loss= 0.70036 val_acc= 0.55738 time= 0.00000
Epoch: 0012 train_loss= 0.77278 train_acc= 0.50909 val_loss= 0.71024 val_acc= 0.49180 time= 0.01563
Epoch: 0013 train_loss= 0.74283 train_acc= 0.50606 val_loss= 0.72367 val_acc= 0.49180 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.69737 accuracy= 0.53279 time= 0.01563 
