[train_custom_diffusion.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env

[AnandK27]

What does this PR do?

Part of #8384

Test Script

export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export OUTPUT_DIR="cat_model"
export INSTANCE_DIR="./data/cat"

accelerate launch train_custom_diffusion.py \
  --pretrained_model_name_or_path=$MODEL_NAME  \
  --instance_data_dir=$INSTANCE_DIR \
  --output_dir=$OUTPUT_DIR \
  --class_data_dir=./real_reg/cat/ \
  --with_prior_preservation --prior_loss_weight=1.0 \
  --class_prompt="cat" --num_class_images=20 \
  --instance_prompt="photo of a <new1> cat"  \
  --resolution=512  \
  --train_batch_size=2  \
  --learning_rate=1e-5  \
  --lr_warmup_steps=0 \
  --num_train_epochs=5 \
  --enable_xformers_memory_efficient_attention \
  --scale_lr --hflip  \
  --modifier_token "<new1>" \
  --validation_prompt="<new1> cat sitting in a bucket" \
  --report_to="wandb"

Fixes # (issue)
Fixed the num_train_epoch for train_custom_diffusion.py and a small fix to saving the text token during safe serialization.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

@sayakpaul and @geniuspatrick
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[sayakpaul]

Looks clean. Thank you!

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[AnandK27]

Hey @sayakpaul,
Fixed the formatting issue, the tests should pass now!

[AnandK27]

@sayakpaul, it can be merged ig

[sayakpaul]

Thanks for your contributions!