Epoch: 0001 train_loss= 0.87225 train_acc= 0.46667 val_loss= 0.70560 val_acc= 0.42623 time= 0.14063
Epoch: 0002 train_loss= 1.03982 train_acc= 0.47879 val_loss= 0.69689 val_acc= 0.49180 time= 0.01562
Epoch: 0003 train_loss= 0.88189 train_acc= 0.53030 val_loss= 0.69953 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 0.94313 train_acc= 0.48788 val_loss= 0.71376 val_acc= 0.54098 time= 0.01563
Epoch: 0005 train_loss= 0.79432 train_acc= 0.50303 val_loss= 0.72676 val_acc= 0.55738 time= 0.00000
Epoch: 0006 train_loss= 0.77792 train_acc= 0.48182 val_loss= 0.74259 val_acc= 0.55738 time= 0.01563
Epoch: 0007 train_loss= 0.88846 train_acc= 0.51212 val_loss= 0.75600 val_acc= 0.57377 time= 0.01563
Epoch: 0008 train_loss= 0.83582 train_acc= 0.52121 val_loss= 0.76244 val_acc= 0.57377 time= 0.01563
Epoch: 0009 train_loss= 0.81339 train_acc= 0.49394 val_loss= 0.77114 val_acc= 0.63934 time= 0.01563
Epoch: 0010 train_loss= 0.75001 train_acc= 0.49394 val_loss= 0.78411 val_acc= 0.60656 time= 0.00000
Epoch: 0011 train_loss= 0.90486 train_acc= 0.58182 val_loss= 0.79259 val_acc= 0.55738 time= 0.01563
Epoch: 0012 train_loss= 0.84436 train_acc= 0.50303 val_loss= 0.80231 val_acc= 0.52459 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.05961 accuracy= 0.50820 time= 0.00000 
