Epoch: 0001 train_loss= 0.86976 train_acc= 0.54727 val_loss= 1.24533 val_acc= 0.42623 time= 0.17189
Epoch: 0002 train_loss= 1.16024 train_acc= 0.52364 val_loss= 1.00230 val_acc= 0.44262 time= 0.01562
Epoch: 0003 train_loss= 0.90214 train_acc= 0.55091 val_loss= 0.81740 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 1.43825 train_acc= 0.56000 val_loss= 0.71451 val_acc= 0.57377 time= 0.01563
Epoch: 0005 train_loss= 0.92052 train_acc= 0.46364 val_loss= 0.73105 val_acc= 0.55738 time= 0.01563
Epoch: 0006 train_loss= 1.34062 train_acc= 0.55455 val_loss= 0.82408 val_acc= 0.59016 time= 0.00000
Epoch: 0007 train_loss= 1.34735 train_acc= 0.45273 val_loss= 0.88271 val_acc= 0.59016 time= 0.01563
Epoch: 0008 train_loss= 0.93557 train_acc= 0.47455 val_loss= 0.88358 val_acc= 0.59016 time= 0.01563
Epoch: 0009 train_loss= 0.98446 train_acc= 0.44364 val_loss= 0.85038 val_acc= 0.59016 time= 0.01563
Epoch: 0010 train_loss= 1.25116 train_acc= 0.47091 val_loss= 0.78618 val_acc= 0.59016 time= 0.01563
Epoch: 0011 train_loss= 0.84548 train_acc= 0.51455 val_loss= 0.74740 val_acc= 0.59016 time= 0.00000
Epoch: 0012 train_loss= 0.80678 train_acc= 0.48909 val_loss= 0.72292 val_acc= 0.55738 time= 0.01563
Epoch: 0013 train_loss= 0.87408 train_acc= 0.52545 val_loss= 0.71266 val_acc= 0.55738 time= 0.01563
Epoch: 0014 train_loss= 0.85803 train_acc= 0.45818 val_loss= 0.70946 val_acc= 0.54098 time= 0.01563
Epoch: 0015 train_loss= 0.73719 train_acc= 0.51818 val_loss= 0.71472 val_acc= 0.45902 time= 0.01563
Epoch: 0016 train_loss= 0.74100 train_acc= 0.49818 val_loss= 0.72713 val_acc= 0.44262 time= 0.00000
Epoch: 0017 train_loss= 0.87724 train_acc= 0.43636 val_loss= 0.74910 val_acc= 0.40984 time= 0.01563
Epoch: 0018 train_loss= 0.75554 train_acc= 0.48364 val_loss= 0.78061 val_acc= 0.39344 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.76835 accuracy= 0.48361 time= 0.00000 
