refactor(distillation): migrate DistillationConfig, DistillationSaveS…#2527
Open
NolenLiang wants to merge 5 commits into
Open
refactor(distillation): migrate DistillationConfig, DistillationSaveS…#2527NolenLiang wants to merge 5 commits into
NolenLiang wants to merge 5 commits into
Conversation
NolenLiang
added
the
CI:Lfast
Contributor
Author
|
/ok to test 6ac197b |
Contributor
Author
|
/ok to test 018d187 |
…tate to BaseModel Convert 2 TypedDict classes to pydantic BaseModel with extra="allow": - DistillationConfig: 12 required fields - DistillationSaveState: 5 fields with defaults + val_reward float Update all dict-style access to attribute access in distillation.py. Wrap model_construct distillation/loss_fn dicts in test_distillation.py with DistillationConfig.model_construct() and DistillationLossConfig.model_construct(). Signed-off-by: nliang <nliang@nvidia.com>
Signed-off-by: nliang <nliang@nvidia.com>
NolenLiang
force-pushed
the
nliang/typeddict-to-basemodel-distillation
branch
from
018d187 to
83f9191
Compare
Contributor
Author
|
/ok to test 83f9191 |
Add defaults to DistillationConfig fields matching the reference config (distillation_math.yaml). DistillationSaveState already had defaults. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Signed-off-by: nliang <nliang@nvidia.com>
Contributor
Author
|
/ok to test 62c3b1e |
DistillationLossConfig is still a TypedDict on this branch (converted in PR2 Loss), so model_construct() is not available. Use plain dicts for loss_fn config in tests to avoid cross-PR dependency. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Signed-off-by: nliang <nliang@nvidia.com>
Contributor
Author
|
/ok to test 4ca79cc |
NolenLiang
added
CI:L1
Contributor
Author
|
/ok to test 4ca79cc |
- Convert DistillationLossConfig from TypedDict to BaseModel with defaults - DistillationLossFn.__init__ uses attribute access directly (no guard) - distillation.py needs no change (master_config.loss_fn already BaseModel via pydantic auto-conversion) - Update test_loss_functions.py and test_distillation.py to pass DistillationLossConfig(...) instead of dict Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Signed-off-by: nliang <nliang@nvidia.com>
Contributor
Author
|
/ok to test 6ccdb87 |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
…tate to BaseModel
Convert 2 TypedDict classes to pydantic BaseModel with extra="allow":
Update all dict-style access to attribute access in distillation.py. Wrap model_construct distillation/loss_fn dicts in test_distillation.py with DistillationConfig.model_construct() and DistillationLossConfig.model_construct().
What does this PR do ?
Add a one line overview of what this PR aims to accomplish.
Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Results before / after the changes