Epoch: 0001 train_loss= 2.08380 train_acc= 0.14717 val_loss= 2.08174 val_acc= 0.13793 time= 0.35940
Epoch: 0002 train_loss= 2.08171 train_acc= 0.13962 val_loss= 2.08106 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.07958 train_acc= 0.16226 val_loss= 2.08028 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07694 train_acc= 0.16226 val_loss= 2.07961 val_acc= 0.13793 time= 0.01562
Epoch: 0005 train_loss= 2.07476 train_acc= 0.15849 val_loss= 2.07903 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.07230 train_acc= 0.15849 val_loss= 2.07865 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.07042 train_acc= 0.15849 val_loss= 2.07855 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.06784 train_acc= 0.15849 val_loss= 2.07878 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.06505 train_acc= 0.15849 val_loss= 2.07946 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.06346 train_acc= 0.15849 val_loss= 2.08063 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.06283 train_acc= 0.15849 val_loss= 2.08230 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.06010 train_acc= 0.15849 val_loss= 2.08448 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07998 accuracy= 0.13559 time= 0.00000 
