TensorFlow uses five different levels of log messages. In ascending order of severity, they are DEBUG, INFO, WARN, ERROR, and FATAL. When you configure logging at any level, TensorFlow will output logging information corresponding to higher levels of severity and all levels. For example, if you set the wrong logging level, you will get log output containing error and fatal messages, and if you set the debug level, you will get log messages from all five levels.
By default, TensorFlow configures WARN at the logging level, but when tracking model training, you will want to adjust the level to INFO, which will provide additional feedback such as in-progress fit operations.
Add the following line to the beginning of the code (after the import)
ging.set_verbosity(tf.logging.INFO)
ensorflow:loss = 1.18812, step = 1
INFO:tensorflow:loss = 0.210323, step = 101
INFO:tensorflow:loss = 0.109025, step = 201