Epoch: 0001 train_loss= 0.69503 train_acc= 0.53636 val_loss= 0.71364 val_acc= 0.44262 time= 0.45315
Epoch: 0002 train_loss= 0.69638 train_acc= 0.53273 val_loss= 0.71928 val_acc= 0.44262 time= 0.00000
Epoch: 0003 train_loss= 0.69233 train_acc= 0.54545 val_loss= 0.72342 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 0.69191 train_acc= 0.54727 val_loss= 0.72321 val_acc= 0.44262 time= 0.00000
Epoch: 0005 train_loss= 0.69528 train_acc= 0.54545 val_loss= 0.72045 val_acc= 0.44262 time= 0.00000
Epoch: 0006 train_loss= 0.69045 train_acc= 0.54727 val_loss= 0.71725 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.69241 train_acc= 0.54909 val_loss= 0.71446 val_acc= 0.44262 time= 0.00000
Epoch: 0008 train_loss= 0.69342 train_acc= 0.53636 val_loss= 0.71184 val_acc= 0.44262 time= 0.00000
Epoch: 0009 train_loss= 0.69076 train_acc= 0.55455 val_loss= 0.70983 val_acc= 0.44262 time= 0.01563
Epoch: 0010 train_loss= 0.69174 train_acc= 0.55091 val_loss= 0.70835 val_acc= 0.44262 time= 0.00000
Epoch: 0011 train_loss= 0.69097 train_acc= 0.54909 val_loss= 0.70760 val_acc= 0.44262 time= 0.00000
Epoch: 0012 train_loss= 0.68978 train_acc= 0.54909 val_loss= 0.70729 val_acc= 0.44262 time= 0.01563
Epoch: 0013 train_loss= 0.69142 train_acc= 0.54909 val_loss= 0.70728 val_acc= 0.44262 time= 0.00000
Epoch: 0014 train_loss= 0.69031 train_acc= 0.53636 val_loss= 0.70774 val_acc= 0.44262 time= 0.01563
Epoch: 0015 train_loss= 0.69133 train_acc= 0.53818 val_loss= 0.70835 val_acc= 0.44262 time= 0.00000
Epoch: 0016 train_loss= 0.68751 train_acc= 0.55091 val_loss= 0.70938 val_acc= 0.44262 time= 0.00000
Epoch: 0017 train_loss= 0.69071 train_acc= 0.54545 val_loss= 0.71023 val_acc= 0.44262 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.71019 accuracy= 0.44262 time= 0.00000 
