Epoch: 0001 train_loss= 2.08235 train_acc= 0.12129 val_loss= 2.09827 val_acc= 0.03448 time= 0.85978
Epoch: 0002 train_loss= 2.08031 train_acc= 0.11590 val_loss= 2.09502 val_acc= 0.03448 time= 0.01563
Epoch: 0003 train_loss= 2.07894 train_acc= 0.11051 val_loss= 2.09207 val_acc= 0.17241 time= 0.00000
Epoch: 0004 train_loss= 2.07727 train_acc= 0.15633 val_loss= 2.08926 val_acc= 0.24138 time= 0.01563
Epoch: 0005 train_loss= 2.07487 train_acc= 0.15364 val_loss= 2.08649 val_acc= 0.24138 time= 0.00000
Epoch: 0006 train_loss= 2.07337 train_acc= 0.15903 val_loss= 2.08377 val_acc= 0.24138 time= 0.01563
Epoch: 0007 train_loss= 2.07350 train_acc= 0.15633 val_loss= 2.08117 val_acc= 0.24138 time= 0.00000
Epoch: 0008 train_loss= 2.07279 train_acc= 0.14825 val_loss= 2.07870 val_acc= 0.24138 time= 0.00000
Epoch: 0009 train_loss= 2.07104 train_acc= 0.15364 val_loss= 2.07633 val_acc= 0.24138 time= 0.01563
Epoch: 0010 train_loss= 2.07003 train_acc= 0.15094 val_loss= 2.07396 val_acc= 0.24138 time= 0.00000
Epoch: 0011 train_loss= 2.07009 train_acc= 0.15633 val_loss= 2.07155 val_acc= 0.24138 time= 0.00000
Epoch: 0012 train_loss= 2.06782 train_acc= 0.15633 val_loss= 2.06919 val_acc= 0.24138 time= 0.01563
Epoch: 0013 train_loss= 2.06596 train_acc= 0.15094 val_loss= 2.06683 val_acc= 0.24138 time= 0.00000
Epoch: 0014 train_loss= 2.06523 train_acc= 0.15364 val_loss= 2.06442 val_acc= 0.24138 time= 0.01620
Epoch: 0015 train_loss= 2.06461 train_acc= 0.15633 val_loss= 2.06208 val_acc= 0.24138 time= 0.00800
Epoch: 0016 train_loss= 2.06425 train_acc= 0.15364 val_loss= 2.05971 val_acc= 0.24138 time= 0.00600
Epoch: 0017 train_loss= 2.06287 train_acc= 0.15094 val_loss= 2.05736 val_acc= 0.24138 time= 0.00600
Epoch: 0018 train_loss= 2.06034 train_acc= 0.14825 val_loss= 2.05511 val_acc= 0.24138 time= 0.00600
Epoch: 0019 train_loss= 2.06048 train_acc= 0.14825 val_loss= 2.05292 val_acc= 0.24138 time= 0.00600
Epoch: 0020 train_loss= 2.06138 train_acc= 0.15094 val_loss= 2.05084 val_acc= 0.24138 time= 0.00600
Epoch: 0021 train_loss= 2.05919 train_acc= 0.15364 val_loss= 2.04879 val_acc= 0.24138 time= 0.00600
Epoch: 0022 train_loss= 2.05933 train_acc= 0.15094 val_loss= 2.04698 val_acc= 0.24138 time= 0.00500
Epoch: 0023 train_loss= 2.05840 train_acc= 0.15094 val_loss= 2.04546 val_acc= 0.24138 time= 0.00600
Epoch: 0024 train_loss= 2.05773 train_acc= 0.14825 val_loss= 2.04420 val_acc= 0.24138 time= 0.00600
Epoch: 0025 train_loss= 2.05772 train_acc= 0.14555 val_loss= 2.04322 val_acc= 0.24138 time= 0.00500
Epoch: 0026 train_loss= 2.05744 train_acc= 0.15094 val_loss= 2.04250 val_acc= 0.24138 time= 0.00700
Epoch: 0027 train_loss= 2.05697 train_acc= 0.15364 val_loss= 2.04221 val_acc= 0.24138 time= 0.00500
Epoch: 0028 train_loss= 2.05882 train_acc= 0.15633 val_loss= 2.04221 val_acc= 0.24138 time= 0.00600
Epoch: 0029 train_loss= 2.05725 train_acc= 0.15094 val_loss= 2.04261 val_acc= 0.24138 time= 0.00500
Epoch: 0030 train_loss= 2.05678 train_acc= 0.15094 val_loss= 2.04330 val_acc= 0.20690 time= 0.00600
Epoch: 0031 train_loss= 2.05652 train_acc= 0.14825 val_loss= 2.04424 val_acc= 0.20690 time= 0.00600
Early stopping...
Optimization Finished!
Test set results: cost= 2.02166 accuracy= 0.20339 time= 0.00200 
