Epoch: 0001 train_loss= 2.08702 train_acc= 0.12830 val_loss= 2.08733 val_acc= 0.13793 time= 0.48487
Epoch: 0002 train_loss= 2.08398 train_acc= 0.17736 val_loss= 2.08754 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.08069 train_acc= 0.15472 val_loss= 2.08827 val_acc= 0.24138 time= 0.01563
Epoch: 0004 train_loss= 2.07797 train_acc= 0.16226 val_loss= 2.08952 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.07553 train_acc= 0.14717 val_loss= 2.09123 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.07296 train_acc= 0.15472 val_loss= 2.09335 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.07108 train_acc= 0.15472 val_loss= 2.09575 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.06925 train_acc= 0.18113 val_loss= 2.09841 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.06693 train_acc= 0.18491 val_loss= 2.10111 val_acc= 0.17241 time= 0.01563
Epoch: 0010 train_loss= 2.06663 train_acc= 0.14717 val_loss= 2.10373 val_acc= 0.20690 time= 0.00000
Epoch: 0011 train_loss= 2.06459 train_acc= 0.17736 val_loss= 2.10632 val_acc= 0.24138 time= 0.01563
Epoch: 0012 train_loss= 2.06464 train_acc= 0.16981 val_loss= 2.10881 val_acc= 0.13793 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08136 accuracy= 0.10169 time= 0.01563 
