Jeremy Howard: recommendation

Transcript context

…That's fine. Don't, you know, don't, I keep telling people, don't track validation loss, track validation accuracy because at least that will still be useful. Just another thing that's got lost since ULMFiT, nobody tracks accuracy of language models anymore. But you know, it'll still keep learning and it does, it does keep improving. But is it worse? You know, like, is it like, now that it's kind of memorized it, it's probably getting a less strong signal, you know, I don't know. So I still don't know how to fine tune language models properly and I haven't found anybody who feels like they do, like nobody really knows whether this memorization thing is, it's probably a feature in some ways. It's probably some things that you can do usefully with it. It's probably, yeah, I have a feeling it's messing up training dynamics as well. And does it come at the cost of catastrophic forgetting as well, right? Like, which is the other side of the coin.…

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