Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

45 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Please run data.py in the trainers folder first in the same directory where the training code lives.

Sample usage:

python train_muon.py --experiment_name muon

For logging:

python logger.py --experiment_name muon

Sample for profiling:

python train_muon.py --experiment_name muon --enable_profiling

About

This repo is an attempt to port all changes of nanogpt modded by Keller Jordan to MoE(Mixture of Experts) architecture

GitHub: Nanogpt-modded

Doc listing all changes: Nanogpt Modded Change Log

Architecture details:

  • Mixtral-style Mixture of Experts (MoE)
  • Top-2 experts chosen
  • Noisy Top-K router to avoid expert bias

PRs are welcome.

Checklist of all completed changes:

  • Tuned learning rate & rotary embeddings
  • Introduced the Muon optimizer
  • Muon improvements
  • Pad embeddings, ReLU², zero-init projections, QK-norm
  • Distributed the overhead of Muon
  • Untied embedding and head
  • Value and embedding skip connections, momentum warmup, logit softcap
  • Bfloat16 activations
  • U-net pattern skip connections & double lr
  • 1024-ctx dense causal attention → 64K-ctx FlexAttention ( post this change due to some bug in flex attention for B,S,H values, all of the following scripts have a torch compile bug<<working to solve :)>>)
  • Attention window warmup
  • Value Embeddings
  • U-net pattern value embeddings, assorted code optimizations
  • Split value embeddings, block sliding window, separate block mask
  • Sparsify value embeddings, improve rotary embeddings, drop an attn layer
  • Lower logit softcap from 30 to 15
  • FP8 head, offset logits, lr decay to 0.1 instead of 0.0
  • Merged QKV weights, long-short attention, attention scale, lower Adam epsilon, batched Muon
  • Reduced batch size
  • Faster gradient all reduce
  • Overlap computation and gradient communication

About

moe_speedrun_test

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages