Training & Pre-training
Months of thousands of GPUs predicting the next token, trillions of times.
Estás viendo un explicador de concepto: qué significa este término en lenguaje claro, y los registros que conecta.
Pre-training runs a model over trillions of tokens, nudging weights after every prediction error, in synchronized runs across tens of thousands of accelerators — the workload the biggest clusters on this site were built for. A frontier run costs hundreds of millions of dollars in compute, fails in exotic ways (silent data corruption, stragglers, loss spikes), and is why checkpointing, interconnects and reliability engineering are front-page infrastructure topics.
Cómo se conecta con el resto del stack
Los enlaces de esta ficha de un vistazo: haz clic en un grupo para ir directamente a él.
Relacionado
Fuentes
Llama 3 herd paper (training at scale) ↗
Registro revisado a fecha de 2026-01-15 — ver Metodología.