GRPO on Sagemaker using TRL Tutorial #2596
add: tutorial for GRPO on Sagemaker using TRL
cc6dcecf
dwarez
marked this pull request as draft 15 days ago
cursor
commented
on 2026-06-25
dwarez
commented
on 2026-06-25
change: using ml.p4d.24xlarge instance to enable beta>0.0
5afe9b4d
change: revert back to default Sagemaker launcher + sagemaker torchrun
93b429fb
change: notebook login as auth, better markdown cells
a358e09b
fix: now relying on public image
f80c46e0
dwarez
marked this pull request as ready for review 9 days ago
dwarez
merged
e3c99455
into main 3 days ago
dwarez
deleted the grpo-llm-trl-tutorial branch 3 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub