How long does single LLM's tunning reuqired?

[alphahumancoder]

No description provided.

[alphahumancoder]

I mean 7B and 13B models

[wuxibin89]

It depends on your datasets and GPUs, we have some benchmark for reference:
https://github.com/OpenLLMAI/OpenRLHF/tree/wuxibin/benchmark/benchmark

[hijkzzz]

It depends on your datasets and GPUs, we have some benchmark for reference: https://github.com/OpenLLMAI/OpenRLHF/tree/wuxibin/benchmark/benchmark

This performance data in this branch is not optimized and we will further adjust the configs in the official technical report