updating nlp notebook

[liususan091219]

Why are these changes needed?

Update the nlp notebook:

• Replaced the sentiment classification & model selection example with Colab built in GPU experiment.
• Rerun multiple choice and text summarization on Ray Tune with 4 V100 GPU.

Related issue number

Checks

• I've used pre-commit to lint the changes in this PR, or I've made sure lint with flake8 output is two 0s.
• I've included any doc changes needed for https://microsoft.github.io/FLAML/. See https://microsoft.github.io/FLAML/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[qingyun-wu]

clear this cell's output?

[qingyun-wu]

Suggested change

"Let's will run FLAML for 30 mins. Here we will Electra's [small model](https://huggingface.co/google/electra-small-discriminator) for the tuning. We set gpu_per_trial to 1, and n_concurrent_trials to 1 (the number of trials running at the same time). Make sure gpu_per_trial * n_concurrent_trials does not exceed the GPU number you have. While running you can observe the resource usage (including the GPU) on the right. "

"Let's run FLAML for 30 mins. Here we use Electra's [small model](https://huggingface.co/google/electra-small-discriminator) for the tuning. We set gpu_per_trial to 1, and n_concurrent_trials to 1 (the number of trials running at the same time). Make sure gpu_per_trial * n_concurrent_trials does not exceed the GPU number you have. While running you can observe the resource usage (including the GPU) on the right. "

[qingyun-wu]

When the PR is approved, can you please also make sure changes in this notebook are also included in the tutorial branch? Also can you add a version number at the end of this line pip install flaml[nlp,notebook,blendsearch] in the notebook (similar to the pip install in this notebook: https://github.com/microsoft/FLAML/blob/tutorial/notebook/automl_classification.ipynb) in the tutorial branch?

Thank you!