Remove unused DPO parameters from schema and tests

docs/_static/llama-stack-spec.yaml

@@ -11163,20 +11163,6 @@ components:
     DPOAlignmentConfig:
       type: object
       properties:
-        reward_scale:
-          type: number
-          description: Scaling factor for the reward signal
-        reward_clip:
-          type: number
-          description: >-
-            Maximum absolute value for reward clipping
-        epsilon:
-          type: number
-          description: >-
-            Small value added for numerical stability
-        gamma:
-          type: number
-          description: Discount factor for future rewards
         beta:
           type: number
           description: Temperature parameter for the DPO loss
@@ -11186,10 +11172,6 @@ components:
           description: The type of loss function to use for DPO
       additionalProperties: false
       required:
-        - reward_scale
-        - reward_clip
-        - epsilon
-        - gamma
         - beta
         - loss_type
       title: DPOAlignmentConfig