The arugment order of Rouge score might be wrong.

[zhaowei-wang-nlp]

I am reading the code in generate_instruction.py.
If you see the doc of Google's rouge_scorer, the input order of def _score_lcs(target_tokens, prediction_tokens): is target_tokens in the first.
at https://github.com/google-research/google-research/blob/master/rouge/rouge_scorer.py#L186

In our case, should we take new instructions as the target_tokens? It seems unnatural.

https://github.com/tatsu-lab/stanford_alpaca/blob/main/generate_instruction.py#L189