tau-nlp/scrolls

QuALITY validation result of LED

Closed this issue · 1 comments

jxiw commented

I try to get the validation result of LED in QuALITY. After running your code, I get the following results.

1024 27.9003
4096 23.9693
16384 20.326

Those results are very bad. Are those results consistent with what you have?

Thanks.

UriSha commented

Hi,

I don’t have the validation scores of our initial baseline. However, as you can see in Table 2 from the paper, the LED baseline did get close to random results on QuALITY, which matches your numbers.

By the way, feel free to make a private submission to the leaderboard to receive your test scores. Just remember that you'll need to create a valid submission file containing (potentially mock) predictions for each ID across all tasks. I've explained the process here.