starcoder icon indicating copy to clipboard operation
starcoder copied to clipboard
verified publisher icon bigcode-project

some concern in "mask_user_labels"?

Open DoffeBupt opened this issue 2 years ago • 1 comments

  1. file chat/dialogues.py:239 should while labels[current_idx] != assistant_token_id and current_idx < len(labels): be while current_idx < len(labels) and labels[current_idx] != assistant_token_id: ?

  2. chat/train.py:204 should mask_user_labels(tokenizer, dialogue_template, labels) be: for _ in labels: mask_user_labels(tokenizer, dialogue_template, _)

DoffeBupt avatar Aug 26 '23 19:08 DoffeBupt

otherwise seems the mask_user_labels has bugs itself(1) and can not be used correctly(2)?

DoffeBupt avatar Aug 27 '23 04:08 DoffeBupt