Fix Learning Rate and Loss Handling in Tile Classifier MaskRCNN EfficientNet

[eugene123tw]

Summary

• Custom Learning Rate Adjustment: Fixed an issue with the customized learning rate for MaskRCNN EfficientNet that caused 0% accuracy when the tile classifier was enabled.
• Loss Dictionary Update: stable training by removing "acc" from loss_dict to prevent gradient explosion

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

[chuneuny-emily]

Can you add unit test code for this case?