Closed samuelhoglund closed 1 year ago
Could be related to the comment in https://github.com/lvwerra/trl/blob/main/examples/stack_llama/scripts/rl_training.py#L43
Have you tried GPT-Neo models?
same error
Here's a potential workaround https://github.com/lvwerra/trl/issues/274#issuecomment-1562135869
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Hello!
I am trying to get the
reward_modeling.py
file to work on a smaller scale by using gpt2 as a reward model.The only changes I made to the file from its current version in the repo was to make the subsets for the data smaller, setting these values instead:
(Otherwise these are set to 100K and 50K, respectively.)
As well as retrieving a modified, smaller sample of the stack-exchange dataset consisting of one file instead of 12 or 20:
However, when running the script, training fails. This is the error with the whole traceback included:
Does anyone have any tips on how to proceed?
Thanks in advance!