Epoch: 0001 train_loss= 2.08710 train_acc= 0.12668 val_loss= 2.08648 val_acc= 0.03448 time= 0.35940
Epoch: 0002 train_loss= 2.08459 train_acc= 0.18059 val_loss= 2.08660 val_acc= 0.03448 time= 0.00000
Epoch: 0003 train_loss= 2.08232 train_acc= 0.18059 val_loss= 2.08716 val_acc= 0.03448 time= 0.01563
Epoch: 0004 train_loss= 2.08028 train_acc= 0.18059 val_loss= 2.08796 val_acc= 0.03448 time= 0.01563
Epoch: 0005 train_loss= 2.07824 train_acc= 0.18598 val_loss= 2.08910 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.07607 train_acc= 0.18059 val_loss= 2.09062 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07460 train_acc= 0.17790 val_loss= 2.09243 val_acc= 0.03448 time= 0.01563
Epoch: 0008 train_loss= 2.07268 train_acc= 0.18868 val_loss= 2.09432 val_acc= 0.03448 time= 0.00000
Epoch: 0009 train_loss= 2.07073 train_acc= 0.18868 val_loss= 2.09625 val_acc= 0.03448 time= 0.01563
Epoch: 0010 train_loss= 2.06947 train_acc= 0.17790 val_loss= 2.09826 val_acc= 0.03448 time= 0.01563
Epoch: 0011 train_loss= 2.06775 train_acc= 0.18598 val_loss= 2.10031 val_acc= 0.03448 time= 0.00000
Epoch: 0012 train_loss= 2.06661 train_acc= 0.17520 val_loss= 2.10235 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09750 accuracy= 0.13559 time= 0.00000 
