Epoch: 0001 train_loss= 2.08607 train_acc= 0.14825 val_loss= 2.06604 val_acc= 0.24138 time= 0.29690
Epoch: 0002 train_loss= 2.08412 train_acc= 0.14555 val_loss= 2.07050 val_acc= 0.17241 time= 0.01562
Epoch: 0003 train_loss= 2.08036 train_acc= 0.17790 val_loss= 2.07564 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07705 train_acc= 0.15364 val_loss= 2.08226 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.06686 train_acc= 0.14016 val_loss= 2.08931 val_acc= 0.10345 time= 0.00000
Epoch: 0006 train_loss= 2.06151 train_acc= 0.16173 val_loss= 2.09709 val_acc= 0.10345 time= 0.01563
Epoch: 0007 train_loss= 2.06497 train_acc= 0.15633 val_loss= 2.10590 val_acc= 0.06897 time= 0.00000
Epoch: 0008 train_loss= 2.05746 train_acc= 0.15364 val_loss= 2.11468 val_acc= 0.06897 time= 0.01563
Epoch: 0009 train_loss= 2.06011 train_acc= 0.14555 val_loss= 2.12187 val_acc= 0.06897 time= 0.01563
Epoch: 0010 train_loss= 2.05525 train_acc= 0.15094 val_loss= 2.12884 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.05468 train_acc= 0.18059 val_loss= 2.13470 val_acc= 0.03448 time= 0.01563
Epoch: 0012 train_loss= 2.05352 train_acc= 0.18868 val_loss= 2.14093 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08743 accuracy= 0.11864 time= 0.01563 
