NVIDIA-NeMo / NVIDIA-NeMo/RL

Megatron LoRA is slow with tulu3 dataset

Open
#1,719 0 comments 0 reactions 0 assignees View on GitHub
bug
Dominant language
Python
Stars
2k
Forks
561
Avg merge
4d 5h
Merged PRs (30d)
145

Description

Megatron LoRA's perf w/ squad dataset is fine, but is bad when using tulu3 dataset.

Repro:
`bash tests/test_suites/llm/sft-llama3.1-8b-1n8g-megatron-lora.sh` in https://github.com/NVIDIA-NeMo/RL/pull/1629.

Test Result:
https://wandb.ai/nvidia/lora-rl/panel/o7jy6zley?nw=nwuservadams
Image

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.