Epoch: 0001 train_loss= 2.08299 train_acc= 0.16352 val_loss= 2.08652 val_acc= 0.24138 time= 0.09376
Epoch: 0002 train_loss= 2.08173 train_acc= 0.16352 val_loss= 2.08503 val_acc= 0.24138 time= 0.00000
Epoch: 0003 train_loss= 2.08038 train_acc= 0.16352 val_loss= 2.08355 val_acc= 0.24138 time= 0.01563
Epoch: 0004 train_loss= 2.07860 train_acc= 0.16352 val_loss= 2.08234 val_acc= 0.24138 time= 0.00000
Epoch: 0005 train_loss= 2.07768 train_acc= 0.16352 val_loss= 2.08167 val_acc= 0.24138 time= 0.01563
Epoch: 0006 train_loss= 2.07578 train_acc= 0.16352 val_loss= 2.08137 val_acc= 0.24138 time= 0.00000
Epoch: 0007 train_loss= 2.07410 train_acc= 0.16352 val_loss= 2.08122 val_acc= 0.24138 time= 0.01563
Epoch: 0008 train_loss= 2.07309 train_acc= 0.16352 val_loss= 2.08120 val_acc= 0.24138 time= 0.00000
Epoch: 0009 train_loss= 2.07243 train_acc= 0.16352 val_loss= 2.08163 val_acc= 0.24138 time= 0.01563
Epoch: 0010 train_loss= 2.07117 train_acc= 0.16352 val_loss= 2.08215 val_acc= 0.24138 time= 0.00000
Epoch: 0011 train_loss= 2.07087 train_acc= 0.16352 val_loss= 2.08266 val_acc= 0.24138 time= 0.01563
Epoch: 0012 train_loss= 2.07026 train_acc= 0.16352 val_loss= 2.08307 val_acc= 0.24138 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07158 accuracy= 0.13559 time= 0.00000 
