Epoch: 0001 train_loss= 2.08591 train_acc= 0.13836 val_loss= 2.08661 val_acc= 0.06897 time= 0.12500
Epoch: 0002 train_loss= 2.08350 train_acc= 0.14465 val_loss= 2.08389 val_acc= 0.06897 time= 0.00000
Epoch: 0003 train_loss= 2.08105 train_acc= 0.14465 val_loss= 2.08158 val_acc= 0.06897 time= 0.01563
Epoch: 0004 train_loss= 2.07911 train_acc= 0.16352 val_loss= 2.07926 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.07673 train_acc= 0.18868 val_loss= 2.07709 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.07432 train_acc= 0.20126 val_loss= 2.07542 val_acc= 0.10345 time= 0.01563
Epoch: 0007 train_loss= 2.07080 train_acc= 0.20126 val_loss= 2.07377 val_acc= 0.10345 time= 0.00000
Epoch: 0008 train_loss= 2.06935 train_acc= 0.19497 val_loss= 2.07217 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.06697 train_acc= 0.19497 val_loss= 2.07072 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.06331 train_acc= 0.19497 val_loss= 2.06952 val_acc= 0.10345 time= 0.01563
Epoch: 0011 train_loss= 2.05976 train_acc= 0.18239 val_loss= 2.06863 val_acc= 0.10345 time= 0.01563
Epoch: 0012 train_loss= 2.05962 train_acc= 0.20126 val_loss= 2.06809 val_acc= 0.10345 time= 0.00000
Epoch: 0013 train_loss= 2.05630 train_acc= 0.19497 val_loss= 2.06794 val_acc= 0.10345 time= 0.01563
Epoch: 0014 train_loss= 2.05432 train_acc= 0.19497 val_loss= 2.06815 val_acc= 0.10345 time= 0.00000
Epoch: 0015 train_loss= 2.05382 train_acc= 0.19497 val_loss= 2.06868 val_acc= 0.10345 time= 0.01563
Epoch: 0016 train_loss= 2.05013 train_acc= 0.19497 val_loss= 2.06944 val_acc= 0.10345 time= 0.01563
Epoch: 0017 train_loss= 2.04896 train_acc= 0.20126 val_loss= 2.07036 val_acc= 0.10345 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.11845 accuracy= 0.16949 time= 0.00000 
