Linear Regression Model - Why predictions are so far away from real values?

[grzegorz-gomza]

Hi all,
I made a linear model from file 01_pytorch_workflow_exercises and checked it with the notebook from Daniel.
In both cases I get the same result and the error in the calculation of weight and bias is unacceptable from my point of view. Increasing the epochs no longer improves the result.
Is this the way it should be?