Epoch: 0001 train_loss= 1.34334 train_acc= 0.52597 val_loss= 1.09328 val_acc= 0.39344 time= 0.74209
Epoch: 0002 train_loss= 1.38765 train_acc= 0.51429 val_loss= 1.00369 val_acc= 0.49180 time= 0.01200
Epoch: 0003 train_loss= 2.21293 train_acc= 0.50909 val_loss= 1.11630 val_acc= 0.52459 time= 0.01442
Epoch: 0004 train_loss= 1.32328 train_acc= 0.47403 val_loss= 1.18080 val_acc= 0.52459 time= 0.01200
Epoch: 0005 train_loss= 1.31548 train_acc= 0.51818 val_loss= 1.16932 val_acc= 0.52459 time= 0.01323
Epoch: 0006 train_loss= 1.01179 train_acc= 0.51429 val_loss= 1.16469 val_acc= 0.52459 time= 0.01425
Epoch: 0007 train_loss= 1.56397 train_acc= 0.46883 val_loss= 1.10847 val_acc= 0.52459 time= 0.01400
Epoch: 0008 train_loss= 1.37540 train_acc= 0.47922 val_loss= 1.04282 val_acc= 0.52459 time= 0.01612
Epoch: 0009 train_loss= 1.01659 train_acc= 0.50000 val_loss= 0.97296 val_acc= 0.52459 time= 0.01424
Epoch: 0010 train_loss= 0.99110 train_acc= 0.48571 val_loss= 0.91271 val_acc= 0.54098 time= 0.01700
Epoch: 0011 train_loss= 0.88670 train_acc= 0.48701 val_loss= 0.87509 val_acc= 0.50820 time= 0.01400
Epoch: 0012 train_loss= 1.07674 train_acc= 0.48442 val_loss= 0.87118 val_acc= 0.50820 time= 0.01400
Epoch: 0013 train_loss= 1.08042 train_acc= 0.48831 val_loss= 0.89935 val_acc= 0.42623 time= 0.01500
Epoch: 0014 train_loss= 0.81277 train_acc= 0.51558 val_loss= 0.95009 val_acc= 0.37705 time= 0.01400
Epoch: 0015 train_loss= 0.90390 train_acc= 0.49870 val_loss= 1.01335 val_acc= 0.36066 time= 0.01424
Early stopping...
Optimization Finished!
Test set results: cost= 0.77053 accuracy= 0.52459 time= 0.00677 
