Update modeling_longt5.py (#17777)
On line 180, `torch.tensor(-1.0, xxx)` gives the error "TypeError: 'float' object cannot be interpreted as an integer"
This is because the dtype here is `int64`. For `dtype=int64`, this needs to simply be `-1`.
This impacts the long-t5-tglogbal-x model. It does not impact the long-t5-local-x version which does not appear to call this line.
