Home Explore Help
Register Sign In
david
/
flash-attention
mirror of https://github.com/Dao-AILab/flash-attention
1
0
Fork 0
Files Issues 0 Wiki
Branch: fa3-fp8-varlen
Branches Tags
flash-attention
/
training
/
configs
/
scheduler
/
cosine-warmup.yaml

cosine-warmup.yaml 82 B
Permalink History Raw

12 
  1. # @package train.scheduler
    2. 

  2. _target_: transformers.get_cosine_schedule_with_warmup
    3.