simplify accuracy eval

[vkuzo]

Summary:

1. move model creation to a separate script, so it can be reused by future perf benchmarks
2. move lm_eval call to shell script, which is simpler than calling it from a python subprocess
3. simplify the for loop by moving the None baseline case inside the loop

Test Plan:

benchmarks/quantization/eval_accuracy_for_readme.sh

Reviewers:

Subscribers:

Tasks:

Tags:

[vkuzo]

Stack from ghstack (oldest at bottom):

• make eval script also handle performance measurement #3473
• refactor accuracy eval script to be organized by hardware #3472
• -> simplify accuracy eval #3470

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3470

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit cf212a9 with merge base 2ae2994 ():
💚 Looks good so far! There are no failures yet. 💚

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