Epoch: 0001 train_loss= 2.08724 train_acc= 0.12075 val_loss= 2.08531 val_acc= 0.13793 time= 0.45315
Epoch: 0002 train_loss= 2.08493 train_acc= 0.16226 val_loss= 2.08391 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.08299 train_acc= 0.16226 val_loss= 2.08283 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.08141 train_acc= 0.16226 val_loss= 2.08226 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.07991 train_acc= 0.16226 val_loss= 2.08206 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.07868 train_acc= 0.16226 val_loss= 2.08212 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.07796 train_acc= 0.16226 val_loss= 2.08240 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.07661 train_acc= 0.16226 val_loss= 2.08289 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.07575 train_acc= 0.16226 val_loss= 2.08361 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.07509 train_acc= 0.16226 val_loss= 2.08443 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.07472 train_acc= 0.16226 val_loss= 2.08524 val_acc= 0.13793 time= 0.00000
Epoch: 0012 train_loss= 2.07390 train_acc= 0.16226 val_loss= 2.08610 val_acc= 0.13793 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.08808 accuracy= 0.13559 time= 0.00000 
