keitakurita/Practical_NLP_in_PyTorch

Question: calculation of memory length for validation in TransformerXL

Opened this issue · 0 comments

Hi, very helpful repo, learned a lot from it.

I got a question about an implementation detail in TransformerXL.

In the transformer_xl_from_scratch notebook, the memory length during validation is calculated as val_memory_length + train_bptt - val_bptt.

Why aren't it just set to val_memory_length?

Looking forward to reply.