Fix zero-shot learning performance degradation after PTQ

[sungchul2]

Summary

ticket no : 145764

Current benchmark dataset for zsl has a very small sample in trainset, so insufficient statistics for PTQ can be obtained.
By temporarily changing dataset from trainset to valset, more samples can be used during PTQ.

How to test

Checklist

• I have added unit tests to cover my changes.​
• I have added integration tests to cover my changes.​
• I have ran e2e tests and there is no issues.
• I have added the description of my changes into CHANGELOG in my target branch (e.g., CHANGELOG in develop).​
• I have updated the documentation in my target branch accordingly (e.g., documentation in develop).
• I have linked related issues.

License

• I submit my code changes under the same Apache License that covers the project.
  Feel free to contact the maintainers if that's a concern.
• I have updated the license header for each file (see an example below).

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

[harimkang]

This isn't a proper fix, is it? Shouldn't we be raising an issue with the dataset?
@chuneuny-emily What do you think? We should consider either skipping small case for PTQ score comparisons or increasing the dataset.