Epoch: 0001 train_loss= 0.87312 train_acc= 0.51212 val_loss= 0.92349 val_acc= 0.50820 time= 0.07814
Epoch: 0002 train_loss= 1.68257 train_acc= 0.50606 val_loss= 0.74568 val_acc= 0.50820 time= 0.01562
Epoch: 0003 train_loss= 1.05674 train_acc= 0.50909 val_loss= 0.72994 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.84393 train_acc= 0.51818 val_loss= 0.78950 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 0.84362 train_acc= 0.50606 val_loss= 0.85834 val_acc= 0.44262 time= 0.01562
Epoch: 0006 train_loss= 0.80422 train_acc= 0.47576 val_loss= 0.95108 val_acc= 0.45902 time= 0.00000
Epoch: 0007 train_loss= 0.90748 train_acc= 0.46970 val_loss= 0.95454 val_acc= 0.45902 time= 0.01563
Epoch: 0008 train_loss= 0.87164 train_acc= 0.49394 val_loss= 0.91603 val_acc= 0.45902 time= 0.01562
Epoch: 0009 train_loss= 0.83545 train_acc= 0.49697 val_loss= 0.92294 val_acc= 0.45902 time= 0.01563
Epoch: 0010 train_loss= 0.86345 train_acc= 0.50303 val_loss= 0.98533 val_acc= 0.45902 time= 0.01563
Epoch: 0011 train_loss= 0.77950 train_acc= 0.51818 val_loss= 1.05291 val_acc= 0.49180 time= 0.00000
Epoch: 0012 train_loss= 0.85601 train_acc= 0.50606 val_loss= 1.15183 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.89770 accuracy= 0.44262 time= 0.01563 
