GitLab

- Add macro_f1_score for multi-class task
- Add klue-ynat task
Co-authored-by: Taekyoon <tgchoi03@gmail.com>

bits_per_byte was calculated as average per-byte loglikelihood, which would work if loglikelihood was base-2 log,
but it is natural log. To correct for that, bits_per_byte should be divided by math.log(2).

Also, it should be true that 2^bits_per_byte == byte_perplexity, which is true after the fix.