Epoch: 0001 train_loss= 0.70079 train_acc= 0.53636 val_loss= 0.70195 val_acc= 0.44262 time= 0.15625
Epoch: 0002 train_loss= 0.69716 train_acc= 0.53939 val_loss= 0.70336 val_acc= 0.44262 time= 0.00000
Epoch: 0003 train_loss= 0.69463 train_acc= 0.53939 val_loss= 0.70565 val_acc= 0.44262 time= 0.01563
Epoch: 0004 train_loss= 0.69277 train_acc= 0.53939 val_loss= 0.70854 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.69156 train_acc= 0.53939 val_loss= 0.71161 val_acc= 0.44262 time= 0.00000
Epoch: 0006 train_loss= 0.69093 train_acc= 0.53939 val_loss= 0.71445 val_acc= 0.44262 time= 0.01562
Epoch: 0007 train_loss= 0.69003 train_acc= 0.53939 val_loss= 0.71695 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 0.69072 train_acc= 0.53939 val_loss= 0.71840 val_acc= 0.44262 time= 0.00000
Epoch: 0009 train_loss= 0.69072 train_acc= 0.53939 val_loss= 0.71849 val_acc= 0.44262 time= 0.01793
Epoch: 0010 train_loss= 0.69022 train_acc= 0.53939 val_loss= 0.71804 val_acc= 0.44262 time= 0.00000
Epoch: 0011 train_loss= 0.69000 train_acc= 0.53939 val_loss= 0.71727 val_acc= 0.44262 time= 0.01563
Epoch: 0012 train_loss= 0.69041 train_acc= 0.53939 val_loss= 0.71623 val_acc= 0.44262 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69033 accuracy= 0.54918 time= 0.00000 
