From 2ebb336141b0f41d8e0325e8fce68afd2dbf251e Mon Sep 17 00:00:00 2001 From: "jack.butler" Date: Fri, 10 Feb 2023 15:18:31 +0000 Subject: [PATCH] update readme --- model/reward/instructor/README.md | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/model/reward/instructor/README.md b/model/reward/instructor/README.md index 655d6469..1613da27 100644 --- a/model/reward/instructor/README.md +++ b/model/reward/instructor/README.md @@ -2,20 +2,21 @@ Trainer code based on huggingface. Compatible with deepspeed or accelerate -Requirements - -``` -wandb -evaluate -datasets -transformers -torch==1.12 -``` - -Start training reward model +Install Python requirements ```bash -python trainer.py configs/electra-base-dis-webgpt.yml +pip install -r requirements.txt +``` + +Write or inherit a `configs/.yml` file to store training +configuration details. + +> The configuration file must have _at least_ all the keys present in dummy.yml + +Run training procedure + +```bash +python trainer.py configs/.yml ``` Additional axis labeling, this outputs a 4 summary quality evaluation metrics