Jeremy Howard: disagreement

Transcript context

…It does to some extent, like we know it does, like look at Code Llama, for example. So Code Llama was a, I think it was like a 500 billion token fine tuning of Llama 2 using code. And also pros about code that Meta did. And honestly, they kind of blew it because Code Llama is good at coding, but it's bad at everything else, you know, and it used to be good. Yeah, I was pretty sure it was like, before they released it, me and lots of people in the open source discords were like, oh my God, you know, we know this is coming, Jan Lukinsk saying it's coming. I hope they kept at least like 50% non-code data because otherwise it's going to forget everything else. And they didn't, only like 0.3% of their epochs were non-code data. So it did, it forgot everything else. So now it's good at code and it's bad at everything else. So we definitely have catastrophic forgetting. It's fixable, just somebody has to do, you know, somebody has to spend their time training a model on a good mix of data. Like, so, okay, so here's the thing. Even though I originally created three-step approach that everybody now does, my view is it's actually wrong and we shouldn't use it. model on a good mix of data. Like, so, okay, so here's the thing. Even though I originally created three-step approach that everybody now does, my view is it's actually wrong and we shouldn't use it. And that's because people are using it in a way different to why I created it. You know, I created it thinking the task-specific models would be more specific. You know, it's like, oh, this is like a sentiment classifier as an example of a task, you know, but the tasks now are like a, you know, RLHF, which is basically like answer questions that make people feel happy about your answer. So that's a much more general task and it's a really cool approach. And so we see, for example, RLHF also breaks models like, you know, like GPT-4, RLHDEFT, we know from kind of the work that Microsoft did, you know, the pre, the earlier, less aligned version was better. And these are all kind of examples of catastrophic forgetting. And so to me, the right way to do this is to fine-tune language models, is to actually throw away the idea of fine-tuning. There's no such thing. There's only continued pre-training. And pre-training is something where from the very start, you try to include all the kinds of data that you care about, all the kinds of problems that you care about, instructions, exercises, code, general purpose document completion, whatever. And then as you train, you gradually curate that, you know, you gradually make that higher and higher quality and more and more specific to the kinds of tasks you want it to do. But you never throw away any data. You always keep all of the data types there in reasonably high quantities. You know, maybe the quality filter, you stop training on low quality data, because that's probably fine to forget how to write badly, maybe. So yeah, that's now my view, is I think ULM fit is the wrong approach. And that's why we're seeing a lot of these, you know, so-called alignment tacks and this view of like, oh, a model can't both code and do other things. And, you know, I think it's actually because people are training them wrong. Yeah, well, I think you have a clear…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.