[WIP] Add finetuning samples #36723
Open
[WIP] Add finetuning samples #36723
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
mohammadsheraj
requested review from
bobogogo1990,
dargilco,
ganeshyb and
glharper
as code owners
Copilot finished reviewing on behalf of
mohammadsheraj
November 24, 2025 07:13
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds finetuning samples for the @azure/ai-projects SDK, introducing sample data files for various finetuning methods (supervised fine-tuning, reward fine-tuning, and direct preference optimization) and a TypeScript sample demonstrating their use.
Key changes:
- Added TypeScript sample for finetuning operations
- Added JSONL training/validation datasets for SFT, RFT, and DPO methods
- Includes training data for multiple finetuning approaches
Reviewed changes
Copilot reviewed 6 out of 7 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
sample_finetuning_supervised_job.ts |
TypeScript sample demonstrating finetuning workflow (currently shows file operations only) |
sft_training_set.jsonl |
Supervised fine-tuning training dataset with 10 examples |
sft_validation_set.jsonl |
Supervised fine-tuning validation dataset with 10 examples |
rft_training_set.jsonl |
Reward fine-tuning training dataset with 100 arithmetic problem examples |
rft_validation_set.jsonl |
Reward fine-tuning validation dataset with 50 arithmetic problem examples |
dpo_training_set.jsonl |
Direct preference optimization training dataset with 20 examples |
dpo_validation_set.jsonl |
Direct preference optimization validation dataset with 2 examples |
sdk/ai/ai-projects/samples-dev/finetuning/sample_finetuning_supervised_job.ts
Outdated
Show resolved
Hide resolved
|
|
||
| const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint string>"; | ||
| const __dirname = path.dirname(fileURLToPath(import.meta.url)); | ||
| const filePath = path.join(__dirname, "data", "training_set.jsonl"); |
There was a problem hiding this comment.
The variable filePath references "data", "training_set.jsonl" but the actual data file in this PR is named sft_training_set.jsonl (for supervised fine-tuning). The path should be corrected to path.join(__dirname, "data", "sft_training_set.jsonl") to match the actual file structure.
Suggested change
| const filePath = path.join(__dirname, "data", "training_set.jsonl"); | |
| const filePath = path.join(__dirname, "data", "sft_training_set.jsonl"); |
sdk/ai/ai-projects/samples-dev/finetuning/sample_finetuning_reinforcement_job.ts
Outdated
Show resolved
Hide resolved
sdk/ai/ai-projects/samples-dev/finetuning/sample_finetuning_supervised_job.ts
Outdated
Show resolved
Hide resolved
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Packages impacted by this PR
Issues associated with this PR
Describe the problem that is addressed by this PR
What are the possible designs available to address the problem? If there are more than one possible design, why was the one in this PR chosen?
Are there test cases added in this PR? (If not, why?)
Provide a list of related PRs (if any)
Command used to generate this PR:**(Applicable only to SDK release request PRs)
Checklists