Epoch: 0001 train_loss= 2.08566 train_acc= 0.13208 val_loss= 2.08247 val_acc= 0.24138 time= 0.29689
Epoch: 0002 train_loss= 2.08433 train_acc= 0.13208 val_loss= 2.08247 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.08318 train_acc= 0.18329 val_loss= 2.08213 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08253 train_acc= 0.18329 val_loss= 2.08121 val_acc= 0.13793 time= 0.01562
Epoch: 0005 train_loss= 2.08128 train_acc= 0.18059 val_loss= 2.07986 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.08057 train_acc= 0.17520 val_loss= 2.07825 val_acc= 0.13793 time= 0.01563
Epoch: 0007 train_loss= 2.07946 train_acc= 0.17520 val_loss= 2.07649 val_acc= 0.13793 time= 0.01563
Epoch: 0008 train_loss= 2.07843 train_acc= 0.17790 val_loss= 2.07453 val_acc= 0.13793 time= 0.00000
Epoch: 0009 train_loss= 2.07708 train_acc= 0.17790 val_loss= 2.07247 val_acc= 0.13793 time= 0.01563
Epoch: 0010 train_loss= 2.07616 train_acc= 0.17520 val_loss= 2.07049 val_acc= 0.13793 time= 0.00000
Epoch: 0011 train_loss= 2.07490 train_acc= 0.17790 val_loss= 2.06857 val_acc= 0.13793 time= 0.01562
Epoch: 0012 train_loss= 2.07275 train_acc= 0.17790 val_loss= 2.06679 val_acc= 0.13793 time= 0.01563
Epoch: 0013 train_loss= 2.07208 train_acc= 0.17790 val_loss= 2.06520 val_acc= 0.13793 time= 0.00000
Epoch: 0014 train_loss= 2.07041 train_acc= 0.17790 val_loss= 2.06382 val_acc= 0.13793 time= 0.01563
Epoch: 0015 train_loss= 2.06889 train_acc= 0.17790 val_loss= 2.06260 val_acc= 0.13793 time= 0.00000
Epoch: 0016 train_loss= 2.06807 train_acc= 0.17790 val_loss= 2.06160 val_acc= 0.13793 time= 0.01563
Epoch: 0017 train_loss= 2.06601 train_acc= 0.17790 val_loss= 2.06086 val_acc= 0.13793 time= 0.00000
Epoch: 0018 train_loss= 2.06518 train_acc= 0.17520 val_loss= 2.06036 val_acc= 0.13793 time= 0.01563
Epoch: 0019 train_loss= 2.06431 train_acc= 0.17790 val_loss= 2.06008 val_acc= 0.13793 time= 0.01563
Epoch: 0020 train_loss= 2.06171 train_acc= 0.17790 val_loss= 2.06004 val_acc= 0.13793 time= 0.00000
Epoch: 0021 train_loss= 2.06079 train_acc= 0.17790 val_loss= 2.06023 val_acc= 0.13793 time= 0.01563
Epoch: 0022 train_loss= 2.05905 train_acc= 0.17790 val_loss= 2.06065 val_acc= 0.13793 time= 0.00000
Epoch: 0023 train_loss= 2.05777 train_acc= 0.17790 val_loss= 2.06123 val_acc= 0.13793 time= 0.01563
Epoch: 0024 train_loss= 2.05684 train_acc= 0.17790 val_loss= 2.06194 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07808 accuracy= 0.16949 time= 0.01563 
