Epoch: 0001 train_loss= 0.69517 train_acc= 0.51212 val_loss= 0.70969 val_acc= 0.45161 time= 0.26564
Epoch: 0002 train_loss= 0.69412 train_acc= 0.50909 val_loss= 0.70718 val_acc= 0.45161 time= 0.01562
Epoch: 0003 train_loss= 0.69402 train_acc= 0.51515 val_loss= 0.70504 val_acc= 0.45161 time= 0.00000
Epoch: 0004 train_loss= 0.69318 train_acc= 0.52424 val_loss= 0.70358 val_acc= 0.45161 time= 0.00000
Epoch: 0005 train_loss= 0.69441 train_acc= 0.51818 val_loss= 0.70232 val_acc= 0.45161 time= 0.01562
Epoch: 0006 train_loss= 0.69456 train_acc= 0.50000 val_loss= 0.70133 val_acc= 0.45161 time= 0.00000
Epoch: 0007 train_loss= 0.69339 train_acc= 0.50606 val_loss= 0.70068 val_acc= 0.45161 time= 0.00000
Epoch: 0008 train_loss= 0.69378 train_acc= 0.51818 val_loss= 0.70014 val_acc= 0.45161 time= 0.01563
Epoch: 0009 train_loss= 0.69319 train_acc= 0.50909 val_loss= 0.69982 val_acc= 0.45161 time= 0.00000
Epoch: 0010 train_loss= 0.69582 train_acc= 0.47879 val_loss= 0.69962 val_acc= 0.45161 time= 0.00000
Epoch: 0011 train_loss= 0.69344 train_acc= 0.50303 val_loss= 0.69954 val_acc= 0.45161 time= 0.01563
Epoch: 0012 train_loss= 0.69371 train_acc= 0.51212 val_loss= 0.69953 val_acc= 0.45161 time= 0.00000
Epoch: 0013 train_loss= 0.69414 train_acc= 0.51818 val_loss= 0.69947 val_acc= 0.45161 time= 0.00000
Epoch: 0014 train_loss= 0.69475 train_acc= 0.50606 val_loss= 0.69935 val_acc= 0.45161 time= 0.00000
Epoch: 0015 train_loss= 0.69323 train_acc= 0.53030 val_loss= 0.69931 val_acc= 0.45161 time= 0.01563
Epoch: 0016 train_loss= 0.69204 train_acc= 0.51818 val_loss= 0.69949 val_acc= 0.45161 time= 0.00000
Epoch: 0017 train_loss= 0.69277 train_acc= 0.51212 val_loss= 0.69975 val_acc= 0.45161 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69826 accuracy= 0.44355 time= 0.01563 
