deepspeedai / deepspeedai/DeepSpeedExamples

[ERROR]In Step3,load reward Model failed which trainged with zero-stage 3

Open
#429 0 comments 2 reactions 1 assignee View on GitHub

@jeffra is already working on this.

Since May 1, 2023.

deespeed chat new-config
Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

In step 3, I modified the zero-stage of the critic model and reward model from 0 to 3, and the Reward Model trained with zero-stage 3 in step 2 cannot be loaded。But we can load reward model with zero-stage 0 in rw_eval.py

err:size mismatch for rwtranrsformer.layers.0.self_attn.q_proj.weight: copying a param with shape torch.Size([4096, 4096]) from checkpoint, the shape in current model is torch.Size([0]).

modified the zero-stage of the critic model and reward model from 0 to 3:
image

Contributor guide

No contributing guide indexed for this repository

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.