Epoch: 0001 train_loss= 2.37540 train_acc= 0.25698 val_loss= 1.52905 val_acc= 0.21429 time= 0.92194
Epoch: 0002 train_loss= 1.97622 train_acc= 0.26257 val_loss= 1.69858 val_acc= 0.25000 time= 0.03125
Epoch: 0003 train_loss= 2.10797 train_acc= 0.24860 val_loss= 1.71214 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 2.40209 train_acc= 0.28631 val_loss= 1.61808 val_acc= 0.26786 time= 0.03125
Epoch: 0005 train_loss= 2.71334 train_acc= 0.27933 val_loss= 1.50725 val_acc= 0.26786 time= 0.03125
Epoch: 0006 train_loss= 2.31625 train_acc= 0.28631 val_loss= 1.41677 val_acc= 0.28571 time= 0.03125
Epoch: 0007 train_loss= 1.56386 train_acc= 0.29190 val_loss= 1.36367 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.67077 train_acc= 0.26117 val_loss= 1.36762 val_acc= 0.32143 time= 0.01563
Epoch: 0009 train_loss= 1.69157 train_acc= 0.25698 val_loss= 1.37842 val_acc= 0.28571 time= 0.03125
Epoch: 0010 train_loss= 1.48709 train_acc= 0.27374 val_loss= 1.37232 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.61417 train_acc= 0.25978 val_loss= 1.36993 val_acc= 0.30357 time= 0.03125
Epoch: 0012 train_loss= 1.49926 train_acc= 0.25559 val_loss= 1.36801 val_acc= 0.32143 time= 0.01563
Epoch: 0013 train_loss= 1.47952 train_acc= 0.29749 val_loss= 1.36978 val_acc= 0.30357 time= 0.03125
Epoch: 0014 train_loss= 1.54151 train_acc= 0.23184 val_loss= 1.37821 val_acc= 0.28571 time= 0.01563
Epoch: 0015 train_loss= 1.42089 train_acc= 0.28352 val_loss= 1.39344 val_acc= 0.28571 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.40923 accuracy= 0.22124 time= 0.00000 
