Epoch: 0001 train_loss= 0.70403 train_acc= 0.52545 val_loss= 0.67299 val_acc= 0.63934 time= 0.56254
Epoch: 0002 train_loss= 0.70154 train_acc= 0.52545 val_loss= 0.67353 val_acc= 0.63934 time= 0.00000
Epoch: 0003 train_loss= 0.70110 train_acc= 0.52909 val_loss= 0.67436 val_acc= 0.63934 time= 0.01562
Epoch: 0004 train_loss= 0.70085 train_acc= 0.52545 val_loss= 0.67537 val_acc= 0.63934 time= 0.00000
Epoch: 0005 train_loss= 0.69934 train_acc= 0.52727 val_loss= 0.67658 val_acc= 0.63934 time= 0.00000
Epoch: 0006 train_loss= 0.69700 train_acc= 0.52182 val_loss= 0.67792 val_acc= 0.63934 time= 0.01563
Epoch: 0007 train_loss= 0.69480 train_acc= 0.53273 val_loss= 0.67929 val_acc= 0.63934 time= 0.00000
Epoch: 0008 train_loss= 0.69679 train_acc= 0.52000 val_loss= 0.68064 val_acc= 0.63934 time= 0.01563
Epoch: 0009 train_loss= 0.69649 train_acc= 0.51636 val_loss= 0.68206 val_acc= 0.63934 time= 0.00000
Epoch: 0010 train_loss= 0.69250 train_acc= 0.53091 val_loss= 0.68345 val_acc= 0.63934 time= 0.00000
Epoch: 0011 train_loss= 0.69311 train_acc= 0.52545 val_loss= 0.68486 val_acc= 0.63934 time= 0.01563
Epoch: 0012 train_loss= 0.69527 train_acc= 0.50545 val_loss= 0.68625 val_acc= 0.63934 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69094 accuracy= 0.54918 time= 0.00000 
