Big Techday 26: How not to blow up: Training a 400B MoE to 17T tokens without loss spikes - Atkins

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Teaches training large mixture-of-experts models at scale without loss instability, covering optimization techniques. Conference talk on deep learning architecture and training stability.

A 52-minute video from TNG Technology Consulting GmbH: “Big Techday 26: How not to blow up: Training a 400B MoE to 17T tokens without loss spikes - Atkins”.

Video by TNG Technology Consulting GmbH, played through YouTube's embedded player.

Part of Big Techday 26