Epoch: 0001 train_loss= 2.08091 train_acc= 0.17358 val_loss= 2.11298 val_acc= 0.03448 time= 0.51603
Epoch: 0002 train_loss= 2.07780 train_acc= 0.18113 val_loss= 2.11313 val_acc= 0.03448 time= 0.00000
Epoch: 0003 train_loss= 2.07937 train_acc= 0.16226 val_loss= 2.11332 val_acc= 0.03448 time= 0.01562
Epoch: 0004 train_loss= 2.07985 train_acc= 0.16604 val_loss= 2.11360 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07485 train_acc= 0.16981 val_loss= 2.11395 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07615 train_acc= 0.16604 val_loss= 2.11439 val_acc= 0.03448 time= 0.00000
Epoch: 0007 train_loss= 2.07026 train_acc= 0.16604 val_loss= 2.11494 val_acc= 0.03448 time= 0.01563
Epoch: 0008 train_loss= 2.06660 train_acc= 0.16981 val_loss= 2.11564 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.06670 train_acc= 0.16981 val_loss= 2.11650 val_acc= 0.03448 time= 0.00000
Epoch: 0010 train_loss= 2.06491 train_acc= 0.16981 val_loss= 2.11757 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.06443 train_acc= 0.16604 val_loss= 2.11881 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06182 train_acc= 0.16981 val_loss= 2.12016 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07493 accuracy= 0.16949 time= 0.01563 
