Training

Pinned sources The Llama 3 Herd of Models (arXiv 2407.21783v3), whose results are all for Llama 3.1 · for Llama 3, its model card (meta-llama/llama3 @ a0940f9) and Meta’s post of April 2024 · no training code is published · How to read

  1. Start of training
  3. Initial pre-trainingat 4K, then 8K15.6T8KNTPall
  4. Off this path: domain experts (code, multilingual)2 stages
  5. Branched from the pre-training run; the point is not named
  6. Code expert1T tokens, mostly code1T16KNTPnot stated
  7. Multilingual expert90% multilingual tokensnot statednot statedNTPnot stated
  8. Long-context pre-trainingsix stages, 8K to 128K800B128KNTPallcontext to 128K
  9. Annealinglearning rate to 040M128KNTPall
  10. Pre-trained model
  12. × 6 roundsRejection sampling and SFTthen DPO, each roundnot stated128KSFTRS and synthetic datanot stated
  13. DPOafter SFT, each roundnot statedshortDPO+ NLL 0.2not stated
  14. Llama 3.1 405B Instruct
  • tokens, log scale
  • derived: computed from stated numbers
  • context length
  • all parameters train
  • a part trains
  • all but a part trains
  • NTPdashed: concluded, no source names it
  • not stated by the sources
  • the architecture changes
  • checkpoint
  • checkpoint, weights published
  • a join the sources leave unexplained
  • data from a branch into a stage
  • stages repeated together

Llama 3.1 405B Instruct

×

Checkpoint

Weights
Table 1 lists Llama 3.1 405B Instruct, released July 2024.
Sources1
Key
stage
tokens, log scale
a total no source states, computed from steps × batch × length
checkpoint
checkpoint, weights published
a join the sources leave unexplained
stages of a released model, folded into one row
derived
computed from reported values; the arithmetic is shown
not disclosed
no pinned source states it; nothing is filled in

Llama 3.1

All models, with previews →

Meta · Jul 2024Dense decoder · follows Llama 3

405B