Epoch: 0001 train_loss= 2.10043 train_acc= 0.09811 val_loss= 2.08777 val_acc= 0.13793 time= 0.37228
Epoch: 0002 train_loss= 2.09365 train_acc= 0.11321 val_loss= 2.08230 val_acc= 0.17241 time= 0.00800
Epoch: 0003 train_loss= 2.08947 train_acc= 0.13585 val_loss= 2.07791 val_acc= 0.10345 time= 0.01000
Epoch: 0004 train_loss= 2.08088 train_acc= 0.12075 val_loss= 2.07423 val_acc= 0.10345 time= 0.01000
Epoch: 0005 train_loss= 2.08141 train_acc= 0.11698 val_loss= 2.07108 val_acc= 0.13793 time= 0.00700
Epoch: 0006 train_loss= 2.06990 train_acc= 0.16226 val_loss= 2.06855 val_acc= 0.13793 time= 0.00700
Epoch: 0007 train_loss= 2.06636 train_acc= 0.15849 val_loss= 2.06606 val_acc= 0.13793 time= 0.00800
Epoch: 0008 train_loss= 2.06274 train_acc= 0.13208 val_loss= 2.06348 val_acc= 0.13793 time= 0.00900
Epoch: 0009 train_loss= 2.05824 train_acc= 0.13208 val_loss= 2.06125 val_acc= 0.13793 time= 0.00800
Epoch: 0010 train_loss= 2.05860 train_acc= 0.16981 val_loss= 2.05917 val_acc= 0.17241 time= 0.00900
Epoch: 0011 train_loss= 2.05588 train_acc= 0.19623 val_loss= 2.05700 val_acc= 0.17241 time= 0.00800
Epoch: 0012 train_loss= 2.05334 train_acc= 0.19245 val_loss= 2.05485 val_acc= 0.20690 time= 0.00900
Epoch: 0013 train_loss= 2.05513 train_acc= 0.18113 val_loss= 2.05271 val_acc= 0.24138 time= 0.00800
Epoch: 0014 train_loss= 2.05592 train_acc= 0.17358 val_loss= 2.05030 val_acc= 0.20690 time= 0.01000
Epoch: 0015 train_loss= 2.05760 train_acc= 0.18113 val_loss= 2.04800 val_acc= 0.20690 time= 0.01000
Epoch: 0016 train_loss= 2.05408 train_acc= 0.16981 val_loss= 2.04610 val_acc= 0.20690 time= 0.00800
Epoch: 0017 train_loss= 2.05150 train_acc= 0.18113 val_loss= 2.04467 val_acc= 0.17241 time= 0.00800
Epoch: 0018 train_loss= 2.04342 train_acc= 0.20755 val_loss= 2.04332 val_acc= 0.20690 time= 0.00800
Epoch: 0019 train_loss= 2.04953 train_acc= 0.18113 val_loss= 2.04232 val_acc= 0.24138 time= 0.00800
Epoch: 0020 train_loss= 2.04198 train_acc= 0.18491 val_loss= 2.04150 val_acc= 0.24138 time= 0.00800
Epoch: 0021 train_loss= 2.05268 train_acc= 0.18491 val_loss= 2.04104 val_acc= 0.24138 time= 0.00700
Epoch: 0022 train_loss= 2.05098 train_acc= 0.18113 val_loss= 2.04065 val_acc= 0.24138 time= 0.00800
Epoch: 0023 train_loss= 2.04764 train_acc= 0.16226 val_loss= 2.04000 val_acc= 0.24138 time= 0.00600
Epoch: 0024 train_loss= 2.04953 train_acc= 0.16604 val_loss= 2.03944 val_acc= 0.24138 time= 0.00800
Epoch: 0025 train_loss= 2.03774 train_acc= 0.17358 val_loss= 2.03905 val_acc= 0.24138 time= 0.00700
Epoch: 0026 train_loss= 2.03863 train_acc= 0.19623 val_loss= 2.03857 val_acc= 0.24138 time= 0.00900
Epoch: 0027 train_loss= 2.04371 train_acc= 0.20377 val_loss= 2.03817 val_acc= 0.24138 time= 0.00800
Epoch: 0028 train_loss= 2.04351 train_acc= 0.21132 val_loss= 2.03794 val_acc= 0.24138 time= 0.00900
Epoch: 0029 train_loss= 2.03442 train_acc= 0.20000 val_loss= 2.03794 val_acc= 0.24138 time= 0.00800
Epoch: 0030 train_loss= 2.02898 train_acc= 0.20755 val_loss= 2.03827 val_acc= 0.24138 time= 0.00800
Epoch: 0031 train_loss= 2.03277 train_acc= 0.19245 val_loss= 2.03856 val_acc= 0.24138 time= 0.00700
Epoch: 0032 train_loss= 2.04370 train_acc= 0.17736 val_loss= 2.03955 val_acc= 0.24138 time= 0.00800
Early stopping...
Optimization Finished!
Test set results: cost= 2.07428 accuracy= 0.11864 time= 0.00300 
