Tuning GPT-3 on a Single GPU via Zero-Shot Hyperparameter Transfer

Tuning GPT-3 on a Single GPU via Zero-Shot Hyperparameter Transfer

MIT Embodied Intelligence via YouTube Direct link

Introduction

1 of 19

1 of 19

Introduction

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Tuning GPT-3 on a Single GPU via Zero-Shot Hyperparameter Transfer

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

  1. 1 Introduction
  2. 2 Material
  3. 3 Underlying Technology
  4. 4 Primary Stability
  5. 5 Other Parameters
  6. 6 Methodology
  7. 7 Training Curves
  8. 8 Summary
  9. 9 Intensive vs Extensive Properties
  10. 10 Extensive vs Intensive Properties
  11. 11 The Plan
  12. 12 Example
  13. 13 General Tuning
  14. 14 Experimental Results
  15. 15 BIRD
  16. 16 Evaluation Results
  17. 17 Vertical Foundation
  18. 18 Primarization
  19. 19 Theory of Everything

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.