SFT pipeline integrated for aicrowd/ChessExplained dataset #35
+517
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
|
Awesome, thanks Mike! |
jlonge4
reviewed
Nov 18, 2025
EmilyWebber
requested changes
Nov 19, 2025
Contributor
EmilyWebber
left a comment
EmilyWebber
left a comment
There was a problem hiding this comment.
Hey Mike - we need the max_model_len from the compilation and inference to match (512!=2048)
michael-L-i
changed the title
jlonge4
approved these changes
Nov 19, 2025
labs/FineTuning/HuggingFaceExample/01_finetuning/FT-Qwen3-1.7B-chess.ipynb
Outdated
Show resolved
Hide resolved
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Code tailored to SFT training on Dipam's dataset using Qwen3-1.7B. The Colab is a similar replica to the Qwen SFT example already present, but adjusted for our chess case.
After installing dependencies, simply run the same torchrun command pointing to the
finetune_chess_model.pyfile. In that file, you can control the train/eval dataset accordingly.This pipeline I verified by training a small 5000 position dataset on a trn1.2xlarge instance with relatively good results already.