feat: add WMDP dataset integration

[ruidazeng]

Add WMDP cyber dataset configuration for unlearning

What does this PR do?

Fixes #80

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Have you gone through the contributions guide?
• Are your changes documented? Read documentation guidelines here.

[molereddy]

need to update just before merge

[filyp]

It's the same as WMDP_cyber_forget.yaml
Is it needed for something? If for testing performance disruption, IIRC MMLU was used.

[Dornavineeth]

@ruidazeng I don't see the path existing for this dataset in hf.
cais/wmdp-corpora

[filyp]

You mean for MMLU? Yeah, it's not in cais/wmdp-corpora but in https://huggingface.co/datasets/cais/mmlu

From what I understand, in original setup, training is done on:

• "cais/wmdp-corpora" - "cyber-forget-corpus"
• "cais/wmdp-corpora" - "cyber-retain-corpus"

And evaluation on:

• "cais/wmdp" - "wmdp-cyber"
• "cais/mmlu" - "all"

[filyp]

I see you mentioned in #80 that evaluation won't be done here anyway, but only afterwards, so I guess WMDP_cyber_forget.yaml and WMDP_cyber_retain.yaml just aren't needed.

[Dornavineeth]

Yes

[Dornavineeth]

Hey @ruidazeng thanks for initiating this work. We now integrated WMDP and lm-eval-harness in #104 .

[ruidazeng]

Hey @ruidazeng thanks for initiating this work. We now integrated WMDP and lm-eval-harness in #104 .

Fantastic love the progress!