Add Jigsaw Toxicity Classification to Full Benchmark

[epavlick]

[trishalaneeraj]

I can do this one.

[oskarvanderwal]

@trishalaneeraj, do you need any help?

[aneveol]

@trishalaneeraj We are discussing how to contribute to this issue in the bias, fairness and social impact evaluation subgroup. It would be great to coordinate on this. We have an upcoming meeting Monday September 6 at 10 pm CET (details are in slack channel)

[oskarvanderwal]

@aneveol and I will work on making Jigsaw ready for the prompt evaluation:

• Write prompts for the dataset.
• Write evaluation code.