why model compiling?

[xprabhudayal]

does there any usage of the models (nanogpt, nanogpt_lite ...) in later time in launch_scientist.py or is it just for comparing with the baseline results?

in this image we are compiling the model, & upon later analysis or the code in launch_scientist.py
we are just comparing with the baseline results

[conglu1997]

Yes these are the baseline runs to compare any future ideas or proposals against.

[xprabhudayal]

Can't we just distribute the cached baseline results, to avoid the heavy task of compiling 🤔

…

On Sun, Sep 1, 2024, 11:16 PM Cong Lu ***@***.***> wrote: Yes these are the baseline runs to compare any future ideas or proposals against. — Reply to this email directly, view it on GitHub <#91 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/A6UFP3B4NHDAWLPYW5WDHJTZUNHI5AVCNFSM6AAAAABNOUCO46VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGMRTGQZTSMZWGY> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[conglu1997]

See the FAQ, no because things like runtime comparisons are machine dependent :)

[xprabhudayal]

@conglu1997 i've been using cloud instance to run this ai scientist, it works fine.
i just wanna know that if all these work in COLAB PRO with A100? as many of the code were TERMINAL based../?