Epoch: 0001 train_loss= 2.08248 train_acc= 0.12830 val_loss= 2.11584 val_acc= 0.13793 time= 0.17556
Epoch: 0002 train_loss= 2.07440 train_acc= 0.12453 val_loss= 2.11893 val_acc= 0.13793 time= 0.01562
Epoch: 0003 train_loss= 2.07893 train_acc= 0.13208 val_loss= 2.12368 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.06397 train_acc= 0.15094 val_loss= 2.12903 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.05715 train_acc= 0.15849 val_loss= 2.13417 val_acc= 0.13793 time= 0.01563
Epoch: 0006 train_loss= 2.05820 train_acc= 0.15472 val_loss= 2.13933 val_acc= 0.13793 time= 0.00000
Epoch: 0007 train_loss= 2.05597 train_acc= 0.15849 val_loss= 2.14523 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.04481 train_acc= 0.14340 val_loss= 2.15066 val_acc= 0.13793 time= 0.01563
Epoch: 0009 train_loss= 2.04921 train_acc= 0.21887 val_loss= 2.15666 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.03810 train_acc= 0.21509 val_loss= 2.16338 val_acc= 0.06897 time= 0.01563
Epoch: 0011 train_loss= 2.04603 train_acc= 0.17736 val_loss= 2.17067 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.03646 train_acc= 0.21509 val_loss= 2.17786 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.02959 accuracy= 0.13559 time= 0.00000 
