Epoch: 0001 train_loss= 1.39119 train_acc= 0.24430 val_loss= 1.38787 val_acc= 0.21429 time= 0.23545
Epoch: 0002 train_loss= 1.39040 train_acc= 0.23779 val_loss= 1.38508 val_acc= 0.33929 time= 0.00000
Epoch: 0003 train_loss= 1.38746 train_acc= 0.30293 val_loss= 1.38292 val_acc= 0.33929 time= 0.00000
Epoch: 0004 train_loss= 1.38640 train_acc= 0.28664 val_loss= 1.38147 val_acc= 0.33929 time= 0.01364
Epoch: 0005 train_loss= 1.38430 train_acc= 0.29316 val_loss= 1.38056 val_acc= 0.33929 time= 0.00600
Epoch: 0006 train_loss= 1.38460 train_acc= 0.29316 val_loss= 1.38018 val_acc= 0.33929 time= 0.00656
Epoch: 0007 train_loss= 1.38335 train_acc= 0.29316 val_loss= 1.38018 val_acc= 0.33929 time= 0.00861
Epoch: 0008 train_loss= 1.38344 train_acc= 0.29316 val_loss= 1.38049 val_acc= 0.33929 time= 0.00600
Epoch: 0009 train_loss= 1.38370 train_acc= 0.29316 val_loss= 1.38071 val_acc= 0.33929 time= 0.00800
Epoch: 0010 train_loss= 1.38214 train_acc= 0.29316 val_loss= 1.38080 val_acc= 0.33929 time= 0.00900
Epoch: 0011 train_loss= 1.38206 train_acc= 0.29316 val_loss= 1.38077 val_acc= 0.33929 time= 0.00700
Epoch: 0012 train_loss= 1.38217 train_acc= 0.29316 val_loss= 1.38068 val_acc= 0.33929 time= 0.00900
Epoch: 0013 train_loss= 1.38327 train_acc= 0.29316 val_loss= 1.38073 val_acc= 0.33929 time= 0.00800
Epoch: 0014 train_loss= 1.38054 train_acc= 0.29316 val_loss= 1.38071 val_acc= 0.33929 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 1.38466 accuracy= 0.29204 time= 0.00300 
