Skip to content

feat(train): Add SequenceLength support for SFT, DPO, RLVR, RLAIF trainers #5898

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
guanweim wants to merge 10 commits into
base: master
Choose a base branch
from
Open

feat(train): Add SequenceLength support for SFT, DPO, RLVR, RLAIF trainers #5898

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
7bd5df9
feat(train): Add SequenceLength support for SFT, DPO, RLVR, RLAIF tra…
guanweim May 4, 2026
13e0f49
fix: use codegen for SequenceLength shape instead of manual shapes.py…
guanweim May 28, 2026
37a5996
refactor: preserve original recipe selection path when sequence_lengt…
guanweim May 28, 2026
1c6f0ef
fix: correct test imports and mock setup for sequence_length tests
guanweim May 28, 2026
3d36503
address PR review: sequence_length as recipe pre-filter and simplify …
guanweim May 28, 2026
c5747ad
fix: change hub_name default to None for consistency
guanweim May 28, 2026
6dbac48
test: add integration test for SFT trainer with sequence_length
guanweim May 28, 2026
303fa79
style: apply black formatting and remove unused import
guanweim May 28, 2026
973b62d
test: add more unit tests for sequence_length coverage
guanweim May 28, 2026
165bcad
Merge branch 'master' into context_length
guanweim May 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions sagemaker-core/sample/sagemaker/2017-07-24/service-2.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43236,6 +43236,10 @@
"EvaluatorArn":{
"shape":"EvaluatorArn",
"documentation":"<p> The evaluator Amazon Resource Name (ARN) used as reward function or reward prompt. </p>"
},
"SequenceLength":{
"shape":"SequenceLength",
"documentation":"<p> The sequence length for the training job. </p>"
}
},
"documentation":"<p> The configuration for the serverless training job. </p>"
Expand All @@ -43247,6 +43251,19 @@
"Evaluation"
]
},
"SequenceLength":{
"type":"string",
"enum":[
"1K",
"2K",
"4K",
"8K",
"16K",
"32K",
"64K",
"128K"
]
},
"ServerlessMaxConcurrency":{
"type":"integer",
"box":true,
Expand Down
2 changes: 2 additions & 0 deletions sagemaker-core/src/sagemaker/core/shapes/shapes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9588,6 +9588,7 @@ class ServerlessJobConfig(Base):
peft: The parameter-efficient fine-tuning configuration.
evaluation_type: The evaluation job type. Required when serverless job type is Evaluation.
evaluator_arn: The evaluator Amazon Resource Name (ARN) used as reward function or reward prompt.
sequence_length: The sequence length for the training job.
"""

base_model_arn: StrPipeVar
Expand All @@ -9597,6 +9598,7 @@ class ServerlessJobConfig(Base):
peft: Optional[StrPipeVar] = Unassigned()
evaluation_type: Optional[StrPipeVar] = Unassigned()
evaluator_arn: Optional[StrPipeVar] = Unassigned()
sequence_length: Optional[StrPipeVar] = Unassigned()


class MlflowConfig(Base):
Expand Down
1 change: 1 addition & 0 deletions sagemaker-core/src/sagemaker/core/utils/code_injection/shape_dag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15877,6 +15877,7 @@
{"name": "Peft", "shape": "Peft", "type": "string"},
{"name": "EvaluationType", "shape": "EvaluationType", "type": "string"},
{"name": "EvaluatorArn", "shape": "EvaluatorArn", "type": "string"},
{"name": "SequenceLength", "shape": "SequenceLength", "type": "string"},
],
"type": "structure",
},
Expand Down
Loading
Loading