Save this video free

CMU Introduction To Deep Learning 11-785, Fall 2026: Lecture 20

Carnegie Mellon University Deep Learning · 1:28:58 · Watch on YouTube

Part of Carnegie Mellon University 11-785 Introduction to Deep Learning. See all 24 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

Large language models gain broad capabilities through web-scale next-token pretraining, then become useful assistants through carefully designed supervised fine-tuning and reinforcement learning. The account covers scaling laws and Chinchilla-style compute allocation, the limits of perplexity and benchmark evaluation, and the shift toward verifiable rewards and reasoning models that spend additional test-time computation on problems such as math and coding.

Key takeaways

Chapters

0:00 Foundation Models Replace Task-Specific Training Interfaces
6:30 Why Transformer Pretraining Depends on Data
13:00 Next-Token Prediction Can Teach Facts, Syntax, and Sentiment
15:00 Building a Useful Web-Scale Training Corpus
17:30 Data Mixtures and the Operational Work of Pretraining
18:30 Perplexity Measures Prediction, Not Every Capability
23:00 Benchmark Contamination and the Language-Model Evaluation Crisis
27:15 Scaling Laws Guide Compute Allocation
34:45 Chinchilla Scaling and the Model-Data Tradeoff
42:00 Diminishing Returns and the Limits of Parameter Scaling
48:30 Pretraining Creates a Foundation for Assistant Behavior
51:30 Supervised Fine-Tuning Teaches Responses by Imitation
55:30 SFT Generalization Can Turn Narrow Examples into Broad Behaviors
1:00:30 RLHF Uses Preference Rankings to Train a Reward Model
1:09:00 Verifiable Rewards and Reasoning Models Improve Technical Skills
1:16:00 Rejection Fine-Tuning, PPO, and Learning from Rollouts
1:20:00 Scaling RL Introduces Sampling, Stability, and Diversity Challenges
1:24:00 Closing Lessons and Questions on Verification

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:00 You folks see most >> uh can you folks see the slide? >> Yeah, we can. >> We can. Yeah. >> Okay. Is the quality good? Sometimes there's issues with that. It's normal. Okay, cool. Um, so yeah. Uh, thank you, Professor Ba. Thank you for uh for having me here today. Um it is always great uh to to meet the to meet the class. Like Professor Ba said, I I was a student in this this course u almost a decade ago and I was a TA after that. Um and you know this course is a big part of

0:48 why I work on what I work on today. So um you know it's always an honor to be back. So uh this is going to be a lecture on large language models. Um please uh you know interrupt me at any time. Uh I'll try to monitor the chat but also feel free to you know interrupt and uh and ask questions. Um so we'll try to cover at a high level the stages of building these models and some you know useful ideas along the way. uh we'll talk about pre-training and this will build on what you guys um have been learning in terms of the architecture for a transformer and in terms of language modeling as an objective. Um we will then talk about evaluation and scaling laws and we'll discuss you

1:38 know how we evaluate these models and um how and why um scaling them is is is its own art and science. Um, and then we'll talk about post- training and basically how we adapt them to downstream use and the behaviors that you expect to see in a chatbot or in a coding agent and in these types of uh, you know, more polished uh, form.

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Carnegie Mellon University Deep Learning.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.