Epoch: 0001 train_loss= 1.39712 train_acc= 0.28516 val_loss= 1.38472 val_acc= 0.33929 time= 0.50050
Epoch: 0002 train_loss= 1.39161 train_acc= 0.30469 val_loss= 1.38161 val_acc= 0.33929 time= 0.00000
Epoch: 0003 train_loss= 1.38903 train_acc= 0.31641 val_loss= 1.37943 val_acc= 0.33929 time= 0.01562
Epoch: 0004 train_loss= 1.38530 train_acc= 0.31055 val_loss= 1.37811 val_acc= 0.33929 time= 0.00000
Epoch: 0005 train_loss= 1.38176 train_acc= 0.31250 val_loss= 1.37760 val_acc= 0.33929 time= 0.01563
Epoch: 0006 train_loss= 1.38120 train_acc= 0.31445 val_loss= 1.37769 val_acc= 0.33929 time= 0.00000
Epoch: 0007 train_loss= 1.37727 train_acc= 0.31250 val_loss= 1.37813 val_acc= 0.33929 time= 0.01563
Epoch: 0008 train_loss= 1.37856 train_acc= 0.31250 val_loss= 1.37881 val_acc= 0.33929 time= 0.00000
Epoch: 0009 train_loss= 1.37845 train_acc= 0.31250 val_loss= 1.37948 val_acc= 0.33929 time= 0.01562
Epoch: 0010 train_loss= 1.37835 train_acc= 0.31250 val_loss= 1.37992 val_acc= 0.33929 time= 0.00000
Epoch: 0011 train_loss= 1.37585 train_acc= 0.31250 val_loss= 1.38014 val_acc= 0.33929 time= 0.01563
Epoch: 0012 train_loss= 1.37950 train_acc= 0.31250 val_loss= 1.38008 val_acc= 0.33929 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37720 accuracy= 0.29204 time= 0.01563 
