Epoch: 0001 train_loss= 0.71808 train_acc= 0.45091 val_loss= 0.66959 val_acc= 0.63934 time= 0.54744
Epoch: 0002 train_loss= 0.71117 train_acc= 0.44000 val_loss= 0.67302 val_acc= 0.63934 time= 0.00000
Epoch: 0003 train_loss= 0.70485 train_acc= 0.44182 val_loss= 0.67652 val_acc= 0.63934 time= 0.01563
Epoch: 0004 train_loss= 0.70249 train_acc= 0.44000 val_loss= 0.68022 val_acc= 0.63934 time= 0.00000
Epoch: 0005 train_loss= 0.69889 train_acc= 0.45818 val_loss= 0.68427 val_acc= 0.63934 time= 0.00000
Epoch: 0006 train_loss= 0.69781 train_acc= 0.44182 val_loss= 0.68866 val_acc= 0.63934 time= 0.01563
Epoch: 0007 train_loss= 0.69548 train_acc= 0.42545 val_loss= 0.69329 val_acc= 0.52459 time= 0.00000
Epoch: 0008 train_loss= 0.69381 train_acc= 0.49091 val_loss= 0.69824 val_acc= 0.36066 time= 0.00000
Epoch: 0009 train_loss= 0.69253 train_acc= 0.54909 val_loss= 0.70350 val_acc= 0.36066 time= 0.01563
Epoch: 0010 train_loss= 0.69254 train_acc= 0.51636 val_loss= 0.70909 val_acc= 0.36066 time= 0.00000
Epoch: 0011 train_loss= 0.68985 train_acc= 0.54545 val_loss= 0.71491 val_acc= 0.36066 time= 0.00000
Epoch: 0012 train_loss= 0.68869 train_acc= 0.55273 val_loss= 0.72089 val_acc= 0.36066 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70818 accuracy= 0.44262 time= 0.00000 
