Epoch: 0001 train_loss= 1.41812 train_acc= 0.18241 val_loss= 1.39073 val_acc= 0.23214 time= 0.12535
Epoch: 0002 train_loss= 1.41440 train_acc= 0.20521 val_loss= 1.38161 val_acc= 0.25000 time= 0.00000
Epoch: 0003 train_loss= 1.42064 train_acc= 0.18893 val_loss= 1.37507 val_acc= 0.32143 time= 0.01563
Epoch: 0004 train_loss= 1.40482 train_acc= 0.23779 val_loss= 1.36968 val_acc= 0.42857 time= 0.01563
Epoch: 0005 train_loss= 1.39924 train_acc= 0.31922 val_loss= 1.36628 val_acc= 0.42857 time= 0.01563
Epoch: 0006 train_loss= 1.39295 train_acc= 0.30945 val_loss= 1.36407 val_acc= 0.41071 time= 0.01563
Epoch: 0007 train_loss= 1.39254 train_acc= 0.29642 val_loss= 1.36247 val_acc= 0.41071 time= 0.00000
Epoch: 0008 train_loss= 1.38779 train_acc= 0.29642 val_loss= 1.36105 val_acc= 0.41071 time= 0.01563
Epoch: 0009 train_loss= 1.38674 train_acc= 0.30293 val_loss= 1.35988 val_acc= 0.39286 time= 0.01563
Epoch: 0010 train_loss= 1.38625 train_acc= 0.29316 val_loss= 1.35948 val_acc= 0.39286 time= 0.01563
Epoch: 0011 train_loss= 1.37964 train_acc= 0.30293 val_loss= 1.35888 val_acc= 0.39286 time= 0.00000
Epoch: 0012 train_loss= 1.37705 train_acc= 0.29967 val_loss= 1.35850 val_acc= 0.39286 time= 0.01563
Epoch: 0013 train_loss= 1.37884 train_acc= 0.30293 val_loss= 1.35795 val_acc= 0.39286 time= 0.01562
Epoch: 0014 train_loss= 1.38136 train_acc= 0.29967 val_loss= 1.35809 val_acc= 0.39286 time= 0.01563
Epoch: 0015 train_loss= 1.37781 train_acc= 0.29642 val_loss= 1.35798 val_acc= 0.37500 time= 0.01563
Epoch: 0016 train_loss= 1.37766 train_acc= 0.31270 val_loss= 1.35861 val_acc= 0.37500 time= 0.00000
Epoch: 0017 train_loss= 1.37158 train_acc= 0.29642 val_loss= 1.35858 val_acc= 0.37500 time= 0.01563
Epoch: 0018 train_loss= 1.37704 train_acc= 0.30619 val_loss= 1.35903 val_acc= 0.37500 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.40487 accuracy= 0.30088 time= 0.00000 
