Epoch: 0001 train_loss= 1.45007 train_acc= 0.48182 val_loss= 0.80096 val_acc= 0.54098 time= 0.15627
Epoch: 0002 train_loss= 1.37599 train_acc= 0.46182 val_loss= 0.96910 val_acc= 0.40984 time= 0.01562
Epoch: 0003 train_loss= 0.88915 train_acc= 0.49455 val_loss= 1.21872 val_acc= 0.39344 time= 0.01563
Epoch: 0004 train_loss= 0.85080 train_acc= 0.52727 val_loss= 1.40084 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 1.15914 train_acc= 0.53455 val_loss= 1.41647 val_acc= 0.42623 time= 0.01563
Epoch: 0006 train_loss= 1.24134 train_acc= 0.54000 val_loss= 1.37586 val_acc= 0.42623 time= 0.00000
Epoch: 0007 train_loss= 2.24991 train_acc= 0.53818 val_loss= 1.26335 val_acc= 0.42623 time= 0.01563
Epoch: 0008 train_loss= 0.82003 train_acc= 0.52000 val_loss= 1.16281 val_acc= 0.42623 time= 0.01563
Epoch: 0009 train_loss= 1.59558 train_acc= 0.54182 val_loss= 1.03776 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 1.18090 train_acc= 0.54000 val_loss= 0.90387 val_acc= 0.40984 time= 0.01563
Epoch: 0011 train_loss= 0.88516 train_acc= 0.50182 val_loss= 0.79890 val_acc= 0.37705 time= 0.00000
Epoch: 0012 train_loss= 0.94656 train_acc= 0.52000 val_loss= 0.73389 val_acc= 0.44262 time= 0.01563
Epoch: 0013 train_loss= 0.81683 train_acc= 0.48727 val_loss= 0.72563 val_acc= 0.52459 time= 0.01563
Epoch: 0014 train_loss= 1.67352 train_acc= 0.45818 val_loss= 0.73617 val_acc= 0.52459 time= 0.01563
Epoch: 0015 train_loss= 0.94513 train_acc= 0.46545 val_loss= 0.74196 val_acc= 0.52459 time= 0.01563
Epoch: 0016 train_loss= 1.01007 train_acc= 0.49091 val_loss= 0.73454 val_acc= 0.52459 time= 0.00000
Epoch: 0017 train_loss= 0.81758 train_acc= 0.54000 val_loss= 0.73027 val_acc= 0.52459 time= 0.01563
Epoch: 0018 train_loss= 1.35342 train_acc= 0.46545 val_loss= 0.71900 val_acc= 0.52459 time= 0.01562
Epoch: 0019 train_loss= 0.78585 train_acc= 0.54727 val_loss= 0.71340 val_acc= 0.49180 time= 0.01563
Epoch: 0020 train_loss= 0.87470 train_acc= 0.51818 val_loss= 0.71189 val_acc= 0.49180 time= 0.01563
Epoch: 0021 train_loss= 1.23821 train_acc= 0.47636 val_loss= 0.70878 val_acc= 0.47541 time= 0.00000
Epoch: 0022 train_loss= 1.28924 train_acc= 0.49455 val_loss= 0.72411 val_acc= 0.45902 time= 0.01562
Epoch: 0023 train_loss= 1.04660 train_acc= 0.46545 val_loss= 0.76804 val_acc= 0.45902 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.77316 accuracy= 0.47541 time= 0.00000 
