Epoch: 0001 train_loss= 2.08733 train_acc= 0.11698 val_loss= 2.08432 val_acc= 0.27586 time= 0.26564
Epoch: 0002 train_loss= 2.08502 train_acc= 0.12830 val_loss= 2.08140 val_acc= 0.27586 time= 0.00000
Epoch: 0003 train_loss= 2.08312 train_acc= 0.13208 val_loss= 2.07856 val_acc= 0.27586 time= 0.01563
Epoch: 0004 train_loss= 2.08157 train_acc= 0.13585 val_loss= 2.07608 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.08015 train_acc= 0.16226 val_loss= 2.07362 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.07893 train_acc= 0.16226 val_loss= 2.07109 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.07781 train_acc= 0.16226 val_loss= 2.06837 val_acc= 0.17241 time= 0.01562
Epoch: 0008 train_loss= 2.07654 train_acc= 0.16226 val_loss= 2.06565 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.07564 train_acc= 0.16226 val_loss= 2.06278 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.07444 train_acc= 0.16226 val_loss= 2.05990 val_acc= 0.17241 time= 0.01562
Epoch: 0011 train_loss= 2.07337 train_acc= 0.16226 val_loss= 2.05702 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.07327 train_acc= 0.16226 val_loss= 2.05424 val_acc= 0.17241 time= 0.01563
Epoch: 0013 train_loss= 2.07312 train_acc= 0.16226 val_loss= 2.05162 val_acc= 0.17241 time= 0.00000
Epoch: 0014 train_loss= 2.07241 train_acc= 0.16226 val_loss= 2.04915 val_acc= 0.17241 time= 0.01563
Epoch: 0015 train_loss= 2.07093 train_acc= 0.16226 val_loss= 2.04683 val_acc= 0.17241 time= 0.01563
Epoch: 0016 train_loss= 2.07048 train_acc= 0.16226 val_loss= 2.04470 val_acc= 0.17241 time= 0.00000
Epoch: 0017 train_loss= 2.06939 train_acc= 0.16226 val_loss= 2.04272 val_acc= 0.17241 time= 0.01563
Epoch: 0018 train_loss= 2.06958 train_acc= 0.16226 val_loss= 2.04106 val_acc= 0.17241 time= 0.00000
Epoch: 0019 train_loss= 2.06855 train_acc= 0.16226 val_loss= 2.03955 val_acc= 0.17241 time= 0.01563
Epoch: 0020 train_loss= 2.06850 train_acc= 0.16226 val_loss= 2.03822 val_acc= 0.17241 time= 0.01563
Epoch: 0021 train_loss= 2.06813 train_acc= 0.16226 val_loss= 2.03740 val_acc= 0.17241 time= 0.00000
Epoch: 0022 train_loss= 2.06775 train_acc= 0.16226 val_loss= 2.03678 val_acc= 0.17241 time= 0.01563
Epoch: 0023 train_loss= 2.06753 train_acc= 0.16226 val_loss= 2.03617 val_acc= 0.17241 time= 0.00000
Epoch: 0024 train_loss= 2.06677 train_acc= 0.16226 val_loss= 2.03572 val_acc= 0.17241 time= 0.01563
Epoch: 0025 train_loss= 2.06729 train_acc= 0.16226 val_loss= 2.03544 val_acc= 0.17241 time= 0.01563
Epoch: 0026 train_loss= 2.06634 train_acc= 0.16226 val_loss= 2.03490 val_acc= 0.17241 time= 0.00000
Epoch: 0027 train_loss= 2.06610 train_acc= 0.16226 val_loss= 2.03421 val_acc= 0.17241 time= 0.01562
Epoch: 0028 train_loss= 2.06461 train_acc= 0.16226 val_loss= 2.03332 val_acc= 0.17241 time= 0.00000
Epoch: 0029 train_loss= 2.06482 train_acc= 0.16604 val_loss= 2.03244 val_acc= 0.17241 time= 0.01563
Epoch: 0030 train_loss= 2.06600 train_acc= 0.16604 val_loss= 2.03153 val_acc= 0.17241 time= 0.00000
Epoch: 0031 train_loss= 2.06408 train_acc= 0.16226 val_loss= 2.03058 val_acc= 0.17241 time= 0.01562
Epoch: 0032 train_loss= 2.06461 train_acc= 0.15849 val_loss= 2.02971 val_acc= 0.17241 time= 0.01563
Epoch: 0033 train_loss= 2.06427 train_acc= 0.16981 val_loss= 2.02912 val_acc= 0.17241 time= 0.00000
Epoch: 0034 train_loss= 2.06398 train_acc= 0.16604 val_loss= 2.02872 val_acc= 0.17241 time= 0.01563
Epoch: 0035 train_loss= 2.06371 train_acc= 0.18491 val_loss= 2.02850 val_acc= 0.17241 time= 0.00000
Epoch: 0036 train_loss= 2.06291 train_acc= 0.16981 val_loss= 2.02853 val_acc= 0.17241 time= 0.01563
Epoch: 0037 train_loss= 2.06375 train_acc= 0.15849 val_loss= 2.02881 val_acc= 0.17241 time= 0.00000
Epoch: 0038 train_loss= 2.06316 train_acc= 0.19245 val_loss= 2.02926 val_acc= 0.17241 time= 0.01562
Epoch: 0039 train_loss= 2.06214 train_acc= 0.17358 val_loss= 2.02989 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07587 accuracy= 0.16949 time= 0.00000 
