Chevron Left
Back to Deep Learning NLP: Training GPT-2 from scratch

Learner Reviews & Feedback for Deep Learning NLP: Training GPT-2 from scratch by Coursera Project Network

47 ratings
11 reviews

About the Course

In this 1-hour long project-based course, we will explore Transformer-based Natural Language Processing. Specifically, we will be taking a look at re-training or fine-tuning GPT-2, which is an NLP machine learning model based on the Transformer architecture. We will cover the history of GPT-2 and it's development, cover basics about the Transformer architecture, learn what type of training data to use and how to collect it, and finally, perform the fine tuning process. In the final task, we will discuss use cases and what the future holds for Transformer-based NLP. I would encourage learners to do further research and experimentation with the GPT-2 model, as well as other NLP models! Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....

Top reviews

Filter by:

1 - 11 of 11 Reviews for Deep Learning NLP: Training GPT-2 from scratch

By Shalankin M

Aug 23, 2020

dont buy it. Everything here is opensource and you can easely find it

By Karthik C

Aug 20, 2020

I enjoyed the simplicity of how things were explained.

By Wenjin Z

Oct 03, 2020

very helpful


Sep 20, 2020


By Gudimetla v n r

Sep 03, 2020


By Hamora H

Aug 09, 2020


By Paul M

Sep 21, 2020

Demo looks great but with missing file in examples and not using GPT2 on video this is disappointing. Pretty poor value for $10USD

By Mario A C S

Sep 20, 2020

The programming assignment was kind of disapointing

By Vivek G K

Aug 12, 2020

The entire setup was very confusing - there was no reference or guide given on how to attend the guided project. Since it was not exactly intuitive i had a hard time understanding what to do next.

sometime the window would expand and collapse on its own, and i was really never sure when i was supposed to try out the code on my own and when not. Also, one of the files mentioned were missing.

By Ayush G

Oct 06, 2020

resources not provided, teaching approach was not interactive

By Maxim T

Sep 15, 2020

This supper short segment really doesn't accomplish it goals of using the GPT2 model. Virtual environment is very glitchy and I wasn't able to refine the model on my data since it takes time but you only have ~1hr of virtual machine time. I would not recommend the course.