Merged commit includes the following changes: (#7119)

* Merged commit includes the following changes:
255493073  by hongkuny<hongkuny@google.com>:

    BERT initial OSS readme update.

--
255470372  by dmchen<dmchen@google.com>:

    Slightly expand expected range for F1 score in BERT SQuAD accuracy test

--
255109240  by hongkuny<hongkuny@google.com>:

    Update eval/predict batch sizes.

--
255010016  by hongkuny<hongkuny@google.com>:

    Internal

--
254874613  by hongkuny<hongkuny@google.com>:

    Update glue tasks enum to match directory name

--
254866171  by taylorrobie<taylorrobie@google.com>:

    Internal change

254785517  by zongweiz<zongweiz@google.com>:

    Use train_single_step for BERT GPU models to temporarily work around some performance bugs in GPU runs

--
254497647  by hongkuny<hongkuny@google.com>:

    Fix device placement for TPU export model.

--

PiperOrigin-RevId: 255493073

* Update README.md

official/README.md

@@ -21,7 +21,7 @@ Please follow the below steps before running models in this repo:
    ```
    export PYTHONPATH="$PYTHONPATH:/path/to/models"
    ```
-   
+
    Using Colab:
    ```
    import os
@@ -45,6 +45,8 @@ To make Official Models easier to use, we are planning to create a pip installab
 
 **NOTE:** Please make sure to follow the steps in the [Requirements](#requirements) section.
 
+* [bert](bert): A powerful pre-trained language representation model: BERT, which
+  stands for Bidirectional Encoder Representations from Transformers.
 * [boosted_trees](boosted_trees): A Gradient Boosted Trees model to classify higgs boson process from HIGGS Data Set.
 * [mnist](mnist): A basic model to classify digits from the MNIST dataset.
 * [resnet](resnet): A deep residual network that can be used to classify both CIFAR-10 and ImageNet's dataset of 1000 classes.