nshepperd/gpt-2

Batch size in training GPT_2

ngocpham97 opened this issue · 1 comments

I have a question about batch size in train.py. I wonder batch_size =1 meaning 1 token will pass to model or 1024 token. Anyone explain help me ? Thank a lots

It means 1 training example in the batch with a token size of 1024.