Open-Assistant icon indicating copy to clipboard operation
Open-Assistant copied to clipboard

KeyError when running command for training reward model

Open bhauptvogel opened this issue 2 years ago • 0 comments

The README.md files in the model and the model/model_training folder include the following command python trainer_rm.py --configs defaults_rm oasst-rm-1-pythia-1b to train the reward model. Running this command returns a KeyError: 'oasst-rm-1-pythia-1b' since the model/model_training/configs/config_rm.yaml file only has the following model options

  • oasst-rm-1-pythia-6.9b
  • oasst-rm-1-pythia-2.8b
  • oasst-rm-1-pythia-1.4b

bhauptvogel avatar Sep 14 '23 14:09 bhauptvogel