No Train No Gain - Revisiting Efficient Training Algorithms for Transformer-based Language Models

No Train No Gain - Revisiting Efficient Training Algorithms for Transformer-based Language Models

AutoML Seminars via YouTube Direct link

Potential pitfalls

4 of 17

4 of 17

Potential pitfalls

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

No Train No Gain - Revisiting Efficient Training Algorithms for Transformer-based Language Models

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Outline
  3. 3 Story
  4. 4 Potential pitfalls
  5. 5 What could go wrong
  6. 6 Scenarios
  7. 7 Job Interferences
  8. 8 Measuring Reference System Time
  9. 9 Experimental Setup
  10. 10 Model Stacking
  11. 11 Selected Backdrop
  12. 12 Question
  13. 13 Efficient Optimizers
  14. 14 Results
  15. 15 What goes wrong
  16. 16 Overheads
  17. 17 Conclusions

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.