try to use 48xlarge runners for llava-runner and eval_llama-mmlu

[swolchok]

These jobs are timing out. I found big gaps in the timestamps of the logs even before the blame PR, which to me suggests swapping. Let's try bigger runners and see what happens on this PR.

Fixes #8180 (if it lands)

[swolchok]

Stack from ghstack (oldest at bottom):

• -> try to use 48xlarge runners for llava-runner and eval_llama-mmlu #8181

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8181

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• ROCM Infra failures during checkout of PyTorch

❌ 1 New Failure, 2 Pending

As of commit ae0eb57 with merge base 58c725c ():

NEW FAILURE - The following job has failed:

• Check Labels / Check labels (gh)
  RuntimeError: Error checking labels: PR does not have required labels

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your changes are user facing and intended to be a part of release notes, please use a label starting with release notes:.

If not, please add the topic: not user facing label.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "topic: not user facing"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[swolchok]

1. looks like there may be no such thing as a 48xlarge runner. The runners appear to use c5 AWS instances, and 24xlarge is the largest in that category.
2. c5.24xlarge instances have 192 GB of RAM. If we're swapping on one of those, something is probably wrong.