Epoch: 0001 train_loss= 2.08063 train_acc= 0.11321 val_loss= 2.09801 val_acc= 0.06897 time= 0.88339
Epoch: 0002 train_loss= 2.07977 train_acc= 0.11321 val_loss= 2.09731 val_acc= 0.06897 time= 0.01563
Epoch: 0003 train_loss= 2.07818 train_acc= 0.12129 val_loss= 2.09681 val_acc= 0.03448 time= 0.00000
Epoch: 0004 train_loss= 2.07517 train_acc= 0.14286 val_loss= 2.09637 val_acc= 0.03448 time= 0.00000
Epoch: 0005 train_loss= 2.07478 train_acc= 0.14825 val_loss= 2.09616 val_acc= 0.03448 time= 0.01563
Epoch: 0006 train_loss= 2.07301 train_acc= 0.16173 val_loss= 2.09604 val_acc= 0.03448 time= 0.00000
Epoch: 0007 train_loss= 2.07306 train_acc= 0.16173 val_loss= 2.09601 val_acc= 0.03448 time= 0.01563
Epoch: 0008 train_loss= 2.07122 train_acc= 0.16173 val_loss= 2.09614 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.06836 train_acc= 0.16712 val_loss= 2.09641 val_acc= 0.03448 time= 0.01563
Epoch: 0010 train_loss= 2.06698 train_acc= 0.15903 val_loss= 2.09678 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.06545 train_acc= 0.16442 val_loss= 2.09732 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06404 train_acc= 0.16173 val_loss= 2.09799 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.06653 accuracy= 0.18644 time= 0.00000 
