Epoch: 0001 train_loss= 1.39397 train_acc= 0.18715 val_loss= 1.39153 val_acc= 0.26786 time= 0.70317
Epoch: 0002 train_loss= 1.39223 train_acc= 0.25838 val_loss= 1.39153 val_acc= 0.26786 time= 0.00000
Epoch: 0003 train_loss= 1.39070 train_acc= 0.24581 val_loss= 1.39138 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38934 train_acc= 0.31425 val_loss= 1.39104 val_acc= 0.25000 time= 0.01562
Epoch: 0005 train_loss= 1.38817 train_acc= 0.33240 val_loss= 1.39070 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38693 train_acc= 0.33380 val_loss= 1.39038 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38559 train_acc= 0.33240 val_loss= 1.39011 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38457 train_acc= 0.33240 val_loss= 1.38990 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.38265 train_acc= 0.33380 val_loss= 1.38976 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.38135 train_acc= 0.33380 val_loss= 1.38972 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.37966 train_acc= 0.33380 val_loss= 1.38978 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37828 train_acc= 0.33380 val_loss= 1.38996 val_acc= 0.25000 time= 0.00000
Epoch: 0013 train_loss= 1.37780 train_acc= 0.33380 val_loss= 1.39024 val_acc= 0.25000 time= 0.01563
Epoch: 0014 train_loss= 1.37639 train_acc= 0.33380 val_loss= 1.39067 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38886 accuracy= 0.28319 time= 0.01563 
