Epoch: 0001 train_loss= 0.69962 train_acc= 0.45818 val_loss= 0.69918 val_acc= 0.44262 time= 0.21877
Epoch: 0002 train_loss= 0.69851 train_acc= 0.53091 val_loss= 0.69959 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 0.69754 train_acc= 0.54000 val_loss= 0.70006 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 0.69693 train_acc= 0.54182 val_loss= 0.70054 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.69630 train_acc= 0.54000 val_loss= 0.70107 val_acc= 0.44262 time= 0.00000
Epoch: 0006 train_loss= 0.69573 train_acc= 0.54000 val_loss= 0.70165 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.69532 train_acc= 0.54000 val_loss= 0.70224 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 0.69478 train_acc= 0.54000 val_loss= 0.70281 val_acc= 0.44262 time= 0.01563
Epoch: 0009 train_loss= 0.69462 train_acc= 0.54000 val_loss= 0.70331 val_acc= 0.44262 time= 0.01563
Epoch: 0010 train_loss= 0.69445 train_acc= 0.54000 val_loss= 0.70372 val_acc= 0.44262 time= 0.01563
Epoch: 0011 train_loss= 0.69381 train_acc= 0.54000 val_loss= 0.70404 val_acc= 0.44262 time= 0.01563
Epoch: 0012 train_loss= 0.69334 train_acc= 0.54000 val_loss= 0.70421 val_acc= 0.44262 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69999 accuracy= 0.46721 time= 0.00000 
