OpenChatKit icon indicating copy to clipboard operation
OpenChatKit copied to clipboard

Pythia feedback

Open LorrinWWW opened this issue 1 year ago • 0 comments

This PR did several things:

  • Add feedback data in data/OIG/prepare.py
  • Add a fine-tuning script in training/finetune_Pythia-Chat-Base-7B-feedback.sh, which further fine-tune upon the ckpt produced by training/finetune_Pythia-Chat-Base-7B.sh.
  • Some trivial changes:
    • Add --checkpoint-load-path: load another ckpt before training starts
    • Restart step counting with --init-steps

LorrinWWW avatar Mar 31 '23 03:03 LorrinWWW