training custom model, is this accuracy reasonable?

[mugenZebra]

!python /content/waifu2x-chainer/train.py --gpu 0 --dataset_dir ./jpg --patches 32 --epoch 10 --model_name reference_scale_rgb --downsampling_filters box lanczos --lr_decay_interval 3 --arch UpConv7
/usr/local/lib/python3.6/dist-packages/chainer/_environment_check.py:91: UserWarning:

---

Multiple installations of CuPy package has been detected.
You should select only one package from from ['cupy-cuda102', 'cupy-cuda101', 'cupy-cuda100', 'cupy-cuda92', 'cupy-cuda91', 'cupy-cuda90', 'cupy-cuda80', 'cupy'].
Follow these steps to resolve this issue:

1. pip list to list CuPy packages installed
2. pip uninstall <package name> to uninstall all CuPy packages
3. pip install <package name> to install the proper one

---

'''.format(name=name, pkgs=pkgs))

• loading filelist... done
• setup model... done
• check forward path... done
• starting processes of dataset sampler... done

epoch: 0

inner epoch: 0

* best loss on training dataset: 0.002381
* best score on validation dataset: PSNR 22.072546 dB
* elapsed time: 881.055754 sec

inner epoch: 1

* best loss on training dataset: 0.001941
* best score on validation dataset: PSNR 22.579106 dB
* elapsed time: 103.186740 sec

inner epoch: 2

* best loss on training dataset: 0.001810
* best score on validation dataset: PSNR 22.679653 dB
* elapsed time: 97.545877 sec

inner epoch: 3

* best loss on training dataset: 0.001732
* best score on validation dataset: PSNR 23.013222 dB
* elapsed time: 91.364418 sec

epoch: 1

inner epoch: 0

* best score on validation dataset: PSNR 23.169959 dB
* elapsed time: 106.030671 sec

inner epoch: 1

* best loss on training dataset: 0.001652
* best score on validation dataset: PSNR 23.181128 dB
* elapsed time: 102.384226 sec

inner epoch: 2

* best loss on training dataset: 0.001593
* best score on validation dataset: PSNR 23.337347 dB
* elapsed time: 99.998622 sec

inner epoch: 3

* best loss on training dataset: 0.001545
* elapsed time: 91.267800 sec

epoch: 2

inner epoch: 0

* best score on validation dataset: PSNR 23.427455 dB
* elapsed time: 106.444332 sec

inner epoch: 1

* elapsed time: 103.891084 sec

inner epoch: 2

* best loss on training dataset: 0.001530
* elapsed time: 98.481055 sec

inner epoch: 3

* best loss on training dataset: 0.001489
* best score on validation dataset: PSNR 23.479888 dB
* elapsed time: 91.023230 sec

epoch: 3

inner epoch: 0

* best score on validation dataset: PSNR 23.528935 dB
* elapsed time: 106.155661 sec

inner epoch: 1

* elapsed time: 103.248413 sec

inner epoch: 2

* best loss on training dataset: 0.001455
* elapsed time: 98.362952 sec

inner epoch: 3

* best loss on training dataset: 0.001421
* learning rate decay: 0.000225
* elapsed time: 90.741462 sec

epoch: 4

inner epoch: 0

* best score on validation dataset: PSNR 23.533943 dB
* elapsed time: 105.805502 sec

inner epoch: 1

* best score on validation dataset: PSNR 23.573726 dB
* elapsed time: 103.978917 sec

inner epoch: 2

* best score on validation dataset: PSNR 23.623575 dB
* elapsed time: 99.085195 sec

inner epoch: 3

* best loss on training dataset: 0.001405
* best score on validation dataset: PSNR 23.658209 dB
* elapsed time: 91.353107 sec

epoch: 5

inner epoch: 0

* best score on validation dataset: PSNR 23.710338 dB
* elapsed time: 106.360211 sec

inner epoch: 1

* best score on validation dataset: PSNR 23.714681 dB
* elapsed time: 104.392316 sec

inner epoch: 2

* elapsed time: 99.168070 sec

inner epoch: 3

* best loss on training dataset: 0.001383
* elapsed time: 91.488422 sec

epoch: 6

inner epoch: 0

* best score on validation dataset: PSNR 23.732231 dB
* elapsed time: 107.400784 sec

inner epoch: 1

* best score on validation dataset: PSNR 23.761270 dB
* elapsed time: 105.255023 sec

inner epoch: 2

* elapsed time: 99.553206 sec

inner epoch: 3

* elapsed time: 91.538299 sec

epoch: 7

inner epoch: 0

* best score on validation dataset: PSNR 23.764517 dB
* elapsed time: 106.978499 sec

inner epoch: 1

* elapsed time: 104.257074 sec

inner epoch: 2

* elapsed time: 99.090099 sec

inner epoch: 3

* best loss on training dataset: 0.001361
* learning rate decay: 0.000203
* elapsed time: 91.054147 sec

epoch: 8

inner epoch: 0

* best score on validation dataset: PSNR 23.816657 dB
* elapsed time: 105.482888 sec

inner epoch: 1

* best score on validation dataset: PSNR 23.883949 dB
* elapsed time: 104.894173 sec

inner epoch: 2

* elapsed time: 99.114435 sec

inner epoch: 3

* elapsed time: 90.749769 sec

epoch: 9

inner epoch: 0

* learning rate decay: 0.000182
* elapsed time: 92.891063 sec

inner epoch: 1

* elapsed time: 90.760490 sec

inner epoch: 2

* elapsed time: 90.826175 sec

inner epoch: 3

* best loss on training dataset: 0.001345
* learning rate decay: 0.000164
* elapsed time: 90.922554 sec`

I read that the PSNR for the pretrained model is 30+, is 23dB too low? Maybe my training set is bad? My training set consists of mostly black and white images, specifically Japanese comic book pages, if that matters.