Epoch: 0001 train_loss= 0.70110 train_acc= 0.47273 val_loss= 0.69635 val_acc= 0.65574 time= 0.25002
Epoch: 0002 train_loss= 0.69803 train_acc= 0.53273 val_loss= 0.69177 val_acc= 0.65574 time= 0.01563
Epoch: 0003 train_loss= 0.69575 train_acc= 0.53091 val_loss= 0.68794 val_acc= 0.65574 time= 0.00000
Epoch: 0004 train_loss= 0.69416 train_acc= 0.53091 val_loss= 0.68480 val_acc= 0.65574 time= 0.01563
Epoch: 0005 train_loss= 0.69324 train_acc= 0.53091 val_loss= 0.68229 val_acc= 0.65574 time= 0.01563
Epoch: 0006 train_loss= 0.69265 train_acc= 0.53091 val_loss= 0.68037 val_acc= 0.65574 time= 0.00000
Epoch: 0007 train_loss= 0.69254 train_acc= 0.53273 val_loss= 0.67948 val_acc= 0.65574 time= 0.01563
Epoch: 0008 train_loss= 0.69239 train_acc= 0.53091 val_loss= 0.67930 val_acc= 0.65574 time= 0.01563
Epoch: 0009 train_loss= 0.69222 train_acc= 0.53273 val_loss= 0.67936 val_acc= 0.65574 time= 0.01563
Epoch: 0010 train_loss= 0.69241 train_acc= 0.53273 val_loss= 0.67936 val_acc= 0.65574 time= 0.00000
Epoch: 0011 train_loss= 0.69235 train_acc= 0.53091 val_loss= 0.67976 val_acc= 0.65574 time= 0.01563
Epoch: 0012 train_loss= 0.69228 train_acc= 0.53091 val_loss= 0.68022 val_acc= 0.65574 time= 0.01563
Epoch: 0013 train_loss= 0.69240 train_acc= 0.53636 val_loss= 0.68033 val_acc= 0.65574 time= 0.00000
Epoch: 0014 train_loss= 0.69196 train_acc= 0.53273 val_loss= 0.68036 val_acc= 0.65574 time= 0.01563
Epoch: 0015 train_loss= 0.69138 train_acc= 0.53818 val_loss= 0.68030 val_acc= 0.65574 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69228 accuracy= 0.52459 time= 0.00000 
