Epoch: 0001 train_loss= 1.39382 train_acc= 0.25000 val_loss= 1.39302 val_acc= 0.23214 time= 0.53128
Epoch: 0002 train_loss= 1.39116 train_acc= 0.24609 val_loss= 1.39209 val_acc= 0.23214 time= 0.01562
Epoch: 0003 train_loss= 1.39165 train_acc= 0.24219 val_loss= 1.39123 val_acc= 0.23214 time= 0.00000
Epoch: 0004 train_loss= 1.38942 train_acc= 0.25000 val_loss= 1.39045 val_acc= 0.23214 time= 0.01562
Epoch: 0005 train_loss= 1.38865 train_acc= 0.24219 val_loss= 1.38974 val_acc= 0.23214 time= 0.00000
Epoch: 0006 train_loss= 1.38762 train_acc= 0.23828 val_loss= 1.38913 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.38667 train_acc= 0.23828 val_loss= 1.38860 val_acc= 0.23214 time= 0.00000
Epoch: 0008 train_loss= 1.38564 train_acc= 0.24219 val_loss= 1.38813 val_acc= 0.23214 time= 0.00000
Epoch: 0009 train_loss= 1.38491 train_acc= 0.26172 val_loss= 1.38773 val_acc= 0.28571 time= 0.01563
Epoch: 0010 train_loss= 1.38316 train_acc= 0.31445 val_loss= 1.38741 val_acc= 0.28571 time= 0.00000
Epoch: 0011 train_loss= 1.38161 train_acc= 0.30859 val_loss= 1.38712 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.38202 train_acc= 0.30078 val_loss= 1.38691 val_acc= 0.28571 time= 0.00000
Epoch: 0013 train_loss= 1.38193 train_acc= 0.30469 val_loss= 1.38679 val_acc= 0.28571 time= 0.00000
Epoch: 0014 train_loss= 1.38050 train_acc= 0.30273 val_loss= 1.38674 val_acc= 0.28571 time= 0.01563
Epoch: 0015 train_loss= 1.38046 train_acc= 0.30469 val_loss= 1.38676 val_acc= 0.28571 time= 0.00000
Epoch: 0016 train_loss= 1.37950 train_acc= 0.30273 val_loss= 1.38687 val_acc= 0.28571 time= 0.01563
Epoch: 0017 train_loss= 1.37825 train_acc= 0.30273 val_loss= 1.38708 val_acc= 0.28571 time= 0.00000
Epoch: 0018 train_loss= 1.37694 train_acc= 0.30469 val_loss= 1.38737 val_acc= 0.28571 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37513 accuracy= 0.29204 time= 0.00000 
