Closed natolambert closed 1 month ago
Did you end up testing this?
@hamishivi yup, just launched a bogus job to immediately error post wandb init, but here's my new project https://wandb.ai/natolambert/open_instruct_dpo
Also, with --wandb_entity rlhf-llm-dev
https://wandb.ai/rlhf-llm-dev/open_instruct_dpo
LGTM! Seems like your run hit some error we might need to work out at some point, but unrelated to this change.
Yeah @hamishivi there was a llama 2 dpo tokenizer error that I was confused by, the assert was failing, but I commented it out to just get things running quickly to make sure this works.
Will test more soon.
Will test this shortly.