Epoch: 0001 train_loss= 1.76378 train_acc= 0.25000 val_loss= 1.81701 val_acc= 0.26786 time= 0.96960
Epoch: 0002 train_loss= 2.05363 train_acc= 0.24302 val_loss= 2.16970 val_acc= 0.21429 time= 0.03125
Epoch: 0003 train_loss= 2.34216 train_acc= 0.22486 val_loss= 2.44726 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 2.00532 train_acc= 0.27793 val_loss= 2.64173 val_acc= 0.23214 time= 0.03125
Epoch: 0005 train_loss= 2.05158 train_acc= 0.31145 val_loss= 2.74695 val_acc= 0.19643 time= 0.01563
Epoch: 0006 train_loss= 2.39499 train_acc= 0.30726 val_loss= 2.64567 val_acc= 0.19643 time= 0.03125
Epoch: 0007 train_loss= 2.61009 train_acc= 0.28771 val_loss= 2.31967 val_acc= 0.21429 time= 0.01563
Epoch: 0008 train_loss= 2.01331 train_acc= 0.30726 val_loss= 1.97045 val_acc= 0.21429 time= 0.03125
Epoch: 0009 train_loss= 1.97662 train_acc= 0.24721 val_loss= 1.75050 val_acc= 0.26786 time= 0.01562
Epoch: 0010 train_loss= 2.00038 train_acc= 0.31425 val_loss= 1.56082 val_acc= 0.26786 time= 0.03125
Epoch: 0011 train_loss= 1.88475 train_acc= 0.23603 val_loss= 1.48203 val_acc= 0.26786 time= 0.01562
Epoch: 0012 train_loss= 2.78989 train_acc= 0.23464 val_loss= 1.49798 val_acc= 0.25000 time= 0.03125
Epoch: 0013 train_loss= 1.51976 train_acc= 0.26816 val_loss= 1.53772 val_acc= 0.23214 time= 0.01563
Epoch: 0014 train_loss= 2.31592 train_acc= 0.27095 val_loss= 1.58267 val_acc= 0.25000 time= 0.03125
Epoch: 0015 train_loss= 1.66957 train_acc= 0.29749 val_loss= 1.58180 val_acc= 0.23214 time= 0.01563
Epoch: 0016 train_loss= 1.46978 train_acc= 0.28352 val_loss= 1.60525 val_acc= 0.21429 time= 0.03125
Epoch: 0017 train_loss= 1.74756 train_acc= 0.23883 val_loss= 1.65896 val_acc= 0.23214 time= 0.01563
Epoch: 0018 train_loss= 1.75484 train_acc= 0.24860 val_loss= 1.67444 val_acc= 0.23214 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.51448 accuracy= 0.26549 time= 0.00000 
