ULMFiT

4 statements across 1 episodes · 1 bullish · 2 bearish · 1 people on the record · first statement Oct 20, 2023 by Jeremy Howard · said 20 times in 3 episodes since 2023 · across every show →

Mentions by year

brought up most by Jeremy Howard (9)

tap a year for its mentions
008115220232024episodesmentions
01220232024episodes it came up in
007.5115220232024episodesmentions per episode
2024 7 mentions in 2 episodes 4 per episode
2023 13 mentions in 1 episode

every mention, scene by scene, with the transcript →

Everything said about ULMFiT, oldest first

Oct 20, 2023 negative
Insight
Alignment tax happens because models are fine-tuned instead of continued pre-trained
“ULM fit is the wrong approach and that's why we're seeing a lot of these You know, so-called alignment tax, and this view of like, oh, a model can't both code and do other things. You know, I think it's actually because people are training them wrong.”
Jeremy Howard Oct 20, 2023 ▶ 46:32 The End of Finetuning — with Jeremy Howard of Fast.ai
Oct 20, 2023 neutral
Assertion Partly supported
Howard: Modern LLMs like ChatGPT still follow ULMFiT's three-step training framework
“So we generated this three-step system. So step one was train a language model on a big corpus. Step two was fine-tune a language model on a more curated corpus, and step three was further fine-tune that model on a task. And of course, that's what everybody st…”
Jeremy Howard Oct 20, 2023 ▶ 14:04 The End of Finetuning — with Jeremy Howard of Fast.ai
Oct 20, 2023 positive
Assertion Not publicly verifiable
Howard: Alec Radford Built OpenAI's GPT After Reading ULMFiT
“I organized a chat for both of us with Kate Metz in the New York Times, and Kate Metz answered, sorry, and Alec answered this question for Kate, and Kate just like, so how did, you know, GPT come about? And he said, well, I was pretty sure that pre-training on…”
Jeremy Howard Oct 20, 2023 ▶ 15:41 The End of Finetuning — with Jeremy Howard of Fast.ai
Oct 20, 2023 negative
Opinion
Jeremy Howard: The three-step ULMFiT fine-tuning approach is wrong and obsolete
“Even though I originally created the three-step approach that everybody now does, my view is it's actually wrong, and we shouldn't use it.”
Jeremy Howard Oct 20, 2023 ▶ 44:27 The End of Finetuning — with Jeremy Howard of Fast.ai
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.