LLMZoo icon indicating copy to clipboard operation
LLMZoo copied to clipboard

Published 20 hours ago • verified publisher icon FreedomIntelligence

Would you provide some details of model training process?

Open intelligencegear opened this issue 1 year ago • 2 comments

I noticed that you have provided instructions for deploying a large model, but there is no information about the model training process. I was wondering if it would be possible to provide more details on how the model was trained?

intelligencegear avatar Apr 20 '23 10:04 intelligencegear

Thumbs up!

RahulBhalley avatar Apr 21 '23 09:04 RahulBhalley

Sure, we will provide it very soon.

wabyking avatar Apr 21 '23 09:04 wabyking

Hi @intelligencegear and @RahulBhalley,

Thanks for your attention!

We have uploaded the training code (see here). Now you can train Phoenix. :-) We specify all the hyper-parameters in the shell scripts and also detail them in our updated technical report.

Best, Zhihong

zhjohnchan avatar May 05 '23 06:05 zhjohnchan

Could you please tell:

  • How much RAM is needed for training?
  • How long does it take to train the model?

RahulBhalley avatar May 05 '23 06:05 RahulBhalley

Hi @intelligencegear and @RahulBhalley,

Thanks for your attention!

We have uploaded the training code (see here). Now you can train Phoenix. :-) We specify all the hyper-parameters in the shell scripts and also detail them in our updated technical report.

Best, Zhihong

Thanks，so cool!

intelligencegear avatar May 06 '23 09:05 intelligencegear