LAION-AI / LAION-AI/Open-Assistant

KeyError when running command for training reward model

Open
#3,687 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
37.4k
Forks
3.3k
PR merge metrics
No merged PRs in 30d

Description

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

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Compare the commands in model/README.md and model/model_training/README.md with the entries in model/model_training/configs/config_rm.yaml. Start by reproducing the command from the README, then inspect how trainer_rm.py resolves the named configuration. Done means the documented training command matches an available reward-model configuration and no longer raises the reported KeyError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.