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
  2. Llama 3, April 2024, predecessor2 stages
  3. Whether Llama 3.1 continues these checkpoints: not stated
  4. Llama 3 pre-training15T+ tokens at 8K15T8Knot statednot stated
  5. Llama 3 post-trainingSFT, RS, PPO, DPOnot statednot statedSFTPPODPOnot stated
  6. Llama 3 (April 2024)
  7. Initial pre-trainingat 4K, then 8K15.6T8KNTPall
  9. Long-context pre-trainingsix stages, 8K to 128K800B128KNTPallcontext to 128K
  10. Annealinglearning rate to 040M128KNTPall
  11. Pre-trained model
  12. Off this path: Reward model1 stage
  13. Reward modelin each roundnot statednot statedRMLlama 2’s, no marginnot stated
  14. Reward model
  15. × 6 roundsRejection sampling and SFTthen DPO, each roundnot stated128KSFTRS and synthetic datanot stated
  16. DPOafter SFT, each roundnot statedshortDPO+ NLL 0.2not stated
  17. 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 (April 2024)

×

Checkpoint

The predecessor: 8B and 70B, a context of 8,192, unscaled RoPE.

Llama 3 in the atlas →

Weights
Its model card: Llama 3 in 8B and 70B, pretrained and instruction tuned, released April 2024.
Sources5
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