phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 00:52:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove unused DPO parameters from schema and tests

Browse source
This commit is contained in:
Nehanth 2025-07-31 15:47:58 +00:00
parent 5c33bc1353
commit b7901156f5
4 changed files with 0 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/integration/post_training/test_post_training.py
View file

@ -195,10 +195,6 @@ class TestPostTraining:
algorithm_config = DPOAlignmentConfig(
beta=0.1,
loss_type=DPOLossType.sigmoid, # Default loss type
reward_scale=1.0, # Scaling factor for reward signal (neutral scaling)
reward_clip=5.0, # Maximum absolute value for reward clipping (prevents extreme values)
epsilon=1e-8, # Small value for numerical stability
gamma=1.0,
)
data_config = DataConfig(
dataset_id=dataset.identifier,