QRNN Hyper parameters for Language modeling on PTB

I tried to run Quasi RNN implementation with the same hyperparameters in the original repository (https://github.com/salesforce/awd-lstm-lm), but the perplexity in fastai implementation and original implementation is not close to each other. For example, in the original qrnn implementation, learning-rate for PBT is 30, while this learning-rate value in fastai caused the infinite perplexity. Do I miss something? Would you please give me a hand to get the same result on Penn Tree Bank dataset?