Skip to content

[chatgpt] add supervised learning fine-tune code#3183

Merged
ht-zhou merged 7 commits intohpcaitech:mainfrom
pgzhang:main
Mar 22, 2023
Merged

[chatgpt] add supervised learning fine-tune code#3183
ht-zhou merged 7 commits intohpcaitech:mainfrom
pgzhang:main

Conversation

@pgzhang
Copy link
Copy Markdown
Contributor

@pgzhang pgzhang commented Mar 20, 2023

📌 Checklist before creating the PR

  • I have created an issue for this PR for traceability
  • The title follows the standard format: [doc/gemini/tensor/...]: A concise description
  • I have added relevant tags if possible for us to better distinguish different PRs

🚨 Issue number

resolved #3182

📝 What does this PR do?

Add supervised learning fine-tune code as mentioned in InstructGPT(step 1)

💥 Checklist before requesting a review

  • I have linked my PR to an issue (instruction)
  • My issue clearly describes the problem/feature/proposal, with diagrams/charts/table/code if possible
  • I have performed a self-review of my code
  • I have added thorough tests.
  • I have added docstrings for all the functions/methods I implemented

⭐️ Do you enjoy contributing to Colossal-AI?

  • 🌝 Yes, I do.

Tell us more if you don't enjoy contributing to Colossal-AI.

@ht-zhou ht-zhou added the chatgpt ChatGPT Application label Mar 21, 2023
Comment thread applications/ChatGPT/chatgpt/trainer/sft.py Outdated
Comment thread applications/ChatGPT/examples/train_sft.py Outdated
@pgzhang pgzhang requested a review from ht-zhou March 21, 2023 03:41
Comment thread applications/ChatGPT/chatgpt/dataset/sft_dataset.py Outdated
@pgzhang pgzhang requested a review from ht-zhou March 21, 2023 07:54
@ht-zhou ht-zhou merged commit b429529 into hpcaitech:main Mar 22, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

chatgpt ChatGPT Application

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[PROPOSAL]: [chatgpt] add code for fine-tuning supervised model

2 participants