Training process just ends

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• [Yes ] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• [ I hope so] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [ Yes] I checked to make sure that this issue has not been filed already.

1. The entire URL of the file you are using

python model_main_tf2.py --model_dir=models\my_ssd_resnet50_v1_fpn --pipeline_config_path=models\my_ssd_resnet50_v1_fpn\pipeline.config
http://download.tensorflow.org/models/object_detection/tf2/20200711/ssd_mobilenet_v2_fpnlite_640x640_coco17_tpu-8.tar.gz

2. Describe the bug

After a couple of seconds training just ends.

3. Steps to reproduce

Not sure, but I followed this guide: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html#create-label-map I am on the last step where I start the training:
"python model_main_tf2.py --model_dir=models/my_ssd_resnet50_v1_fpn --pipeline_config_path=models/my_ssd_resnet50_v1_fpn/pipeline.config"

4. Expected behavior

Training process in progress.

5. Additional context

https://colab.research.google.com/drive/1YB5NOeguicb01ZIgRmv-nxzlKBUUDGyT?usp=sharing

6. System information

• Windows 10
• TensorFlow installed from pip 2.3.0
• Python version: 3.8.5
• GPU model and memory: Sapphire Radeon TOXIC R9 280X 3GB GDDR5 (running on CPU)