Epoch: 0001 train_loss= 2.37123 train_acc= 0.28771 val_loss= 1.44935 val_acc= 0.33929 time= 0.96881
Epoch: 0002 train_loss= 1.66845 train_acc= 0.24721 val_loss= 1.57646 val_acc= 0.17857 time= 0.01563
Epoch: 0003 train_loss= 2.00889 train_acc= 0.20950 val_loss= 1.48247 val_acc= 0.17857 time= 0.03125
Epoch: 0004 train_loss= 1.78033 train_acc= 0.25419 val_loss= 1.45679 val_acc= 0.16071 time= 0.03131
Epoch: 0005 train_loss= 1.58027 train_acc= 0.27514 val_loss= 1.49234 val_acc= 0.16071 time= 0.01563
Epoch: 0006 train_loss= 1.68131 train_acc= 0.23184 val_loss= 1.45758 val_acc= 0.17857 time= 0.03125
Epoch: 0007 train_loss= 2.24693 train_acc= 0.24302 val_loss= 1.36516 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.57240 train_acc= 0.24860 val_loss= 1.33186 val_acc= 0.33929 time= 0.01563
Epoch: 0009 train_loss= 1.60065 train_acc= 0.26676 val_loss= 1.33726 val_acc= 0.35714 time= 0.03125
Epoch: 0010 train_loss= 1.46077 train_acc= 0.25140 val_loss= 1.33899 val_acc= 0.35714 time= 0.03125
Epoch: 0011 train_loss= 1.77976 train_acc= 0.22067 val_loss= 1.33807 val_acc= 0.30357 time= 0.01563
Epoch: 0012 train_loss= 1.57265 train_acc= 0.31285 val_loss= 1.33667 val_acc= 0.30357 time= 0.03125
Epoch: 0013 train_loss= 1.70467 train_acc= 0.24581 val_loss= 1.33668 val_acc= 0.30357 time= 0.01562
Epoch: 0014 train_loss= 1.66670 train_acc= 0.30726 val_loss= 1.34144 val_acc= 0.35714 time= 0.03125
Epoch: 0015 train_loss= 1.82244 train_acc= 0.31425 val_loss= 1.35503 val_acc= 0.33929 time= 0.01563
Epoch: 0016 train_loss= 1.48961 train_acc= 0.30587 val_loss= 1.35550 val_acc= 0.33929 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.39028 accuracy= 0.25664 time= 0.00000 
