Skip to content

[Chat] fix the tokenizer "int too big to convert" error in SFT training#3453

Merged
Fazziekey merged 14 commits intohpcaitech:mainfrom
Camille7777:hotfix/chat
Apr 6, 2023
Merged

[Chat] fix the tokenizer "int too big to convert" error in SFT training#3453
Fazziekey merged 14 commits intohpcaitech:mainfrom
Camille7777:hotfix/chat

Conversation

@Camille7777
Copy link
Copy Markdown
Contributor

@Camille7777 Camille7777 commented Apr 5, 2023 •
edited
Loading

📌 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

Link this PR to your issue with words like fixed to automatically close the linked issue upon merge

e.g. fixed #1234, closed #1234, resolved #1234
fixed #3438

📝 What does this PR do?

Summarize your work here.
if you have any plots/diagrams/screenshots/tables, please attach them here.
add max_length setting in _tokenize_fn when using SupervisedDataset

💥 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.
  • 🌚 No, I don't.

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

Camille7777 added 14 commits April 6, 2023 09:25
@Camille7777
Add RoBERTa for RLHF Stage 2 & 3 (test)
5c69dc1 
RoBERTa for RLHF Stage 2 & 3 (still in testing)
@Camille7777
Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)"
548e499 
This reverts commit 06741d8.
@Camille7777
Add RoBERTa for RLHF stage 2 & 3
026c363 
1. add roberta folder under model folder
2. add  roberta option in train_reward_model.py
3. add some test in testci
@Camille7777
Update test_ci.sh
a6aa921
@Camille7777
Revert "Update test_ci.sh"
96dda63 
This reverts commit 9c7352b.
@Camille7777
Add RoBERTa for RLHF Stage 2 & 3 (test)
a4a860f 
RoBERTa for RLHF Stage 2 & 3 (still in testing)
@Camille7777
Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)"
2825ec4 
This reverts commit 06741d8.
@Camille7777
Add RoBERTa for RLHF stage 2 & 3
b1403ea 
1. add roberta folder under model folder
2. add  roberta option in train_reward_model.py
3. add some test in testci
@Camille7777
Update test_ci.sh
ff52770
@Camille7777
Revert "Update test_ci.sh"
512f70e 
This reverts commit 9c7352b.
@Camille7777
update roberta with coati
d643e91
@Camille7777
chat ci update
7c4dad6
@Camille7777
Revert "chat ci update"
7327cf3 
This reverts commit 17ae7ae.
@Camille7777
[Chat] fix the tokenizer "int too big to convert" error in SFT training
98b0742 
fix the tokenizer error during SFT training using Bloom and OPT
@Fazziekey Fazziekey merged commit 72cb4dd into hpcaitech:main Apr 6, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer

@Fazziekey Fazziekey Fazziekey approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

[BUG]: "OverflowError: int too big to convert" during SFT training using Bloom model

2 participants

@Camille7777 @Fazziekey