Epoch: 0001 train_loss= 1.39420 train_acc= 0.33203 val_loss= 1.39165 val_acc= 0.25000 time= 0.25002
Epoch: 0002 train_loss= 1.39085 train_acc= 0.33203 val_loss= 1.38977 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.38818 train_acc= 0.33203 val_loss= 1.38859 val_acc= 0.25000 time= 0.01562
Epoch: 0004 train_loss= 1.38611 train_acc= 0.33203 val_loss= 1.38806 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38451 train_acc= 0.33203 val_loss= 1.38805 val_acc= 0.25000 time= 0.01562
Epoch: 0006 train_loss= 1.38307 train_acc= 0.33203 val_loss= 1.38845 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38203 train_acc= 0.33203 val_loss= 1.38918 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38132 train_acc= 0.33203 val_loss= 1.39004 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.38033 train_acc= 0.33203 val_loss= 1.39095 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.38001 train_acc= 0.33203 val_loss= 1.39189 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.38008 train_acc= 0.33203 val_loss= 1.39270 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37916 train_acc= 0.33203 val_loss= 1.39326 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38766 accuracy= 0.29204 time= 0.00000 
