Epoch: 0001 train_loss= 2.08724 train_acc= 0.13208 val_loss= 2.08649 val_acc= 0.06897 time= 0.15626
Epoch: 0002 train_loss= 2.08484 train_acc= 0.16352 val_loss= 2.08576 val_acc= 0.06897 time= 0.01562
Epoch: 0003 train_loss= 2.08261 train_acc= 0.16352 val_loss= 2.08532 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.08094 train_acc= 0.16352 val_loss= 2.08513 val_acc= 0.06897 time= 0.00000
Epoch: 0005 train_loss= 2.07905 train_acc= 0.16352 val_loss= 2.08524 val_acc= 0.06897 time= 0.01563
Epoch: 0006 train_loss= 2.07758 train_acc= 0.16352 val_loss= 2.08563 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.07646 train_acc= 0.16352 val_loss= 2.08629 val_acc= 0.06897 time= 0.00000
Epoch: 0008 train_loss= 2.07532 train_acc= 0.16352 val_loss= 2.08688 val_acc= 0.06897 time= 0.01563
Epoch: 0009 train_loss= 2.07419 train_acc= 0.16352 val_loss= 2.08747 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.07278 train_acc= 0.16352 val_loss= 2.08812 val_acc= 0.06897 time= 0.00000
Epoch: 0011 train_loss= 2.07223 train_acc= 0.16352 val_loss= 2.08874 val_acc= 0.06897 time= 0.01563
Epoch: 0012 train_loss= 2.07079 train_acc= 0.16352 val_loss= 2.08936 val_acc= 0.06897 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09594 accuracy= 0.13559 time= 0.00000 
