Epoch: 0001 train_loss= 1.39153 train_acc= 0.33225 val_loss= 1.39031 val_acc= 0.37500 time= 0.11847
Epoch: 0002 train_loss= 1.38990 train_acc= 0.33225 val_loss= 1.38895 val_acc= 0.37500 time= 0.01563
Epoch: 0003 train_loss= 1.38859 train_acc= 0.33225 val_loss= 1.38767 val_acc= 0.37500 time= 0.01563
Epoch: 0004 train_loss= 1.38705 train_acc= 0.33225 val_loss= 1.38638 val_acc= 0.37500 time= 0.01563
Epoch: 0005 train_loss= 1.38517 train_acc= 0.33225 val_loss= 1.38510 val_acc= 0.37500 time= 0.01563
Epoch: 0006 train_loss= 1.38400 train_acc= 0.33225 val_loss= 1.38385 val_acc= 0.37500 time= 0.01999
Epoch: 0007 train_loss= 1.38257 train_acc= 0.33225 val_loss= 1.38264 val_acc= 0.37500 time= 0.00805
Epoch: 0008 train_loss= 1.38122 train_acc= 0.33225 val_loss= 1.38147 val_acc= 0.37500 time= 0.01563
Epoch: 0009 train_loss= 1.37933 train_acc= 0.33225 val_loss= 1.38038 val_acc= 0.37500 time= 0.01562
Epoch: 0010 train_loss= 1.37830 train_acc= 0.33225 val_loss= 1.37942 val_acc= 0.37500 time= 0.01563
Epoch: 0011 train_loss= 1.37719 train_acc= 0.33225 val_loss= 1.37863 val_acc= 0.37500 time= 0.01563
Epoch: 0012 train_loss= 1.37599 train_acc= 0.33225 val_loss= 1.37803 val_acc= 0.37500 time= 0.01563
Epoch: 0013 train_loss= 1.37545 train_acc= 0.33225 val_loss= 1.37763 val_acc= 0.37500 time= 0.01563
Epoch: 0014 train_loss= 1.37443 train_acc= 0.33225 val_loss= 1.37741 val_acc= 0.37500 time= 0.01563
Epoch: 0015 train_loss= 1.37330 train_acc= 0.33225 val_loss= 1.37738 val_acc= 0.37500 time= 0.01563
Epoch: 0016 train_loss= 1.37294 train_acc= 0.33225 val_loss= 1.37752 val_acc= 0.37500 time= 0.01563
Epoch: 0017 train_loss= 1.37187 train_acc= 0.33225 val_loss= 1.37782 val_acc= 0.37500 time= 0.01563
Epoch: 0018 train_loss= 1.37166 train_acc= 0.33225 val_loss= 1.37825 val_acc= 0.37500 time= 0.01563
Epoch: 0019 train_loss= 1.37245 train_acc= 0.33225 val_loss= 1.37867 val_acc= 0.37500 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38274 accuracy= 0.28319 time= 0.00000 
