Epoch: 0001 train_loss= 1.41310 train_acc= 0.24430 val_loss= 1.38045 val_acc= 0.28571 time= 0.07813
Epoch: 0002 train_loss= 1.41021 train_acc= 0.24104 val_loss= 1.37972 val_acc= 0.33929 time= 0.01563
Epoch: 0003 train_loss= 1.39502 train_acc= 0.26384 val_loss= 1.37964 val_acc= 0.32143 time= 0.01563
Epoch: 0004 train_loss= 1.38924 train_acc= 0.27036 val_loss= 1.37993 val_acc= 0.32143 time= 0.01563
Epoch: 0005 train_loss= 1.38633 train_acc= 0.26710 val_loss= 1.38002 val_acc= 0.32143 time= 0.01562
Epoch: 0006 train_loss= 1.38642 train_acc= 0.27687 val_loss= 1.38042 val_acc= 0.32143 time= 0.01563
Epoch: 0007 train_loss= 1.38298 train_acc= 0.27687 val_loss= 1.38097 val_acc= 0.32143 time= 0.01563
Epoch: 0008 train_loss= 1.38816 train_acc= 0.28990 val_loss= 1.38184 val_acc= 0.28571 time= 0.01562
Epoch: 0009 train_loss= 1.39083 train_acc= 0.22801 val_loss= 1.38239 val_acc= 0.28571 time= 0.01563
Epoch: 0010 train_loss= 1.39005 train_acc= 0.28990 val_loss= 1.38333 val_acc= 0.26786 time= 0.01563
Epoch: 0011 train_loss= 1.38974 train_acc= 0.30293 val_loss= 1.38467 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.38009 train_acc= 0.31596 val_loss= 1.38618 val_acc= 0.25000 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.39097 accuracy= 0.31858 time= 0.00000 
