Epoch: 0001 train_loss= 2.08565 train_acc= 0.13747 val_loss= 2.08593 val_acc= 0.03448 time= 0.32816
Epoch: 0002 train_loss= 2.08443 train_acc= 0.13477 val_loss= 2.08589 val_acc= 0.03448 time= 0.00000
Epoch: 0003 train_loss= 2.08360 train_acc= 0.13477 val_loss= 2.08579 val_acc= 0.03448 time= 0.01562
Epoch: 0004 train_loss= 2.08283 train_acc= 0.13477 val_loss= 2.08566 val_acc= 0.03448 time= 0.01563
Epoch: 0005 train_loss= 2.08208 train_acc= 0.13477 val_loss= 2.08552 val_acc= 0.03448 time= 0.00000
Epoch: 0006 train_loss= 2.08115 train_acc= 0.13477 val_loss= 2.08538 val_acc= 0.03448 time= 0.01563
Epoch: 0007 train_loss= 2.07998 train_acc= 0.13477 val_loss= 2.08521 val_acc= 0.03448 time= 0.00000
Epoch: 0008 train_loss= 2.07870 train_acc= 0.13477 val_loss= 2.08502 val_acc= 0.03448 time= 0.01563
Epoch: 0009 train_loss= 2.07819 train_acc= 0.13208 val_loss= 2.08481 val_acc= 0.03448 time= 0.01563
Epoch: 0010 train_loss= 2.07641 train_acc= 0.13477 val_loss= 2.08463 val_acc= 0.03448 time= 0.00000
Epoch: 0011 train_loss= 2.07566 train_acc= 0.13477 val_loss= 2.08448 val_acc= 0.03448 time= 0.01562
Epoch: 0012 train_loss= 2.07457 train_acc= 0.13477 val_loss= 2.08431 val_acc= 0.03448 time= 0.00000
Epoch: 0013 train_loss= 2.07292 train_acc= 0.13477 val_loss= 2.08410 val_acc= 0.03448 time= 0.01563
Epoch: 0014 train_loss= 2.07233 train_acc= 0.13477 val_loss= 2.08372 val_acc= 0.03448 time= 0.00000
Epoch: 0015 train_loss= 2.07097 train_acc= 0.13208 val_loss= 2.08329 val_acc= 0.03448 time= 0.01562
Epoch: 0016 train_loss= 2.07028 train_acc= 0.14286 val_loss= 2.08292 val_acc= 0.10345 time= 0.01563
Epoch: 0017 train_loss= 2.06918 train_acc= 0.13747 val_loss= 2.08248 val_acc= 0.10345 time= 0.00000
Epoch: 0018 train_loss= 2.06730 train_acc= 0.14555 val_loss= 2.08206 val_acc= 0.10345 time= 0.01563
Epoch: 0019 train_loss= 2.06611 train_acc= 0.15364 val_loss= 2.08160 val_acc= 0.10345 time= 0.00000
Epoch: 0020 train_loss= 2.06568 train_acc= 0.16442 val_loss= 2.08113 val_acc= 0.10345 time= 0.01563
Epoch: 0021 train_loss= 2.06361 train_acc= 0.15364 val_loss= 2.08072 val_acc= 0.10345 time= 0.01563
Epoch: 0022 train_loss= 2.06462 train_acc= 0.15364 val_loss= 2.08038 val_acc= 0.10345 time= 0.00000
Epoch: 0023 train_loss= 2.06405 train_acc= 0.15364 val_loss= 2.07985 val_acc= 0.10345 time= 0.01562
Epoch: 0024 train_loss= 2.06290 train_acc= 0.15364 val_loss= 2.07923 val_acc= 0.10345 time= 0.00000
Epoch: 0025 train_loss= 2.06304 train_acc= 0.15364 val_loss= 2.07842 val_acc= 0.10345 time= 0.01563
Epoch: 0026 train_loss= 2.06272 train_acc= 0.15364 val_loss= 2.07756 val_acc= 0.10345 time= 0.00000
Epoch: 0027 train_loss= 2.06280 train_acc= 0.15364 val_loss= 2.07640 val_acc= 0.10345 time= 0.01562
Epoch: 0028 train_loss= 2.06138 train_acc= 0.15364 val_loss= 2.07518 val_acc= 0.10345 time= 0.01563
Epoch: 0029 train_loss= 2.06114 train_acc= 0.15364 val_loss= 2.07373 val_acc= 0.10345 time= 0.00000
Epoch: 0030 train_loss= 2.06147 train_acc= 0.15364 val_loss= 2.07207 val_acc= 0.10345 time= 0.01563
Epoch: 0031 train_loss= 2.06161 train_acc= 0.15364 val_loss= 2.06994 val_acc= 0.10345 time= 0.00000
Epoch: 0032 train_loss= 2.06134 train_acc= 0.15364 val_loss= 2.06779 val_acc= 0.10345 time= 0.01562
Epoch: 0033 train_loss= 2.06068 train_acc= 0.15364 val_loss= 2.06540 val_acc= 0.10345 time= 0.01563
Epoch: 0034 train_loss= 2.06193 train_acc= 0.15364 val_loss= 2.06295 val_acc= 0.10345 time= 0.00000
Epoch: 0035 train_loss= 2.05991 train_acc= 0.15364 val_loss= 2.06043 val_acc= 0.10345 time= 0.01563
Epoch: 0036 train_loss= 2.05948 train_acc= 0.16712 val_loss= 2.05807 val_acc= 0.24138 time= 0.00000
Epoch: 0037 train_loss= 2.05939 train_acc= 0.15633 val_loss= 2.05617 val_acc= 0.24138 time= 0.01562
Epoch: 0038 train_loss= 2.05888 train_acc= 0.15633 val_loss= 2.05479 val_acc= 0.24138 time= 0.01563
Epoch: 0039 train_loss= 2.05909 train_acc= 0.15633 val_loss= 2.05365 val_acc= 0.24138 time= 0.00000
Epoch: 0040 train_loss= 2.06044 train_acc= 0.15903 val_loss= 2.05284 val_acc= 0.24138 time= 0.01563
Epoch: 0041 train_loss= 2.05964 train_acc= 0.15633 val_loss= 2.05238 val_acc= 0.24138 time= 0.00000
Epoch: 0042 train_loss= 2.05927 train_acc= 0.15903 val_loss= 2.05233 val_acc= 0.24138 time= 0.01562
Epoch: 0043 train_loss= 2.05877 train_acc= 0.15903 val_loss= 2.05255 val_acc= 0.24138 time= 0.01563
Epoch: 0044 train_loss= 2.05832 train_acc= 0.15903 val_loss= 2.05305 val_acc= 0.24138 time= 0.00000
Epoch: 0045 train_loss= 2.05852 train_acc= 0.15903 val_loss= 2.05347 val_acc= 0.24138 time= 0.01562
Epoch: 0046 train_loss= 2.05846 train_acc= 0.15903 val_loss= 2.05378 val_acc= 0.24138 time= 0.00000
Epoch: 0047 train_loss= 2.05854 train_acc= 0.15903 val_loss= 2.05409 val_acc= 0.24138 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09495 accuracy= 0.13559 time= 0.00000 
