diff --git a/examples/dppo/lora/sd3_5/geneval_teacher.yaml b/examples/dppo/lora/sd3_5/geneval_teacher.yaml
index 6468bc53..a03d2277 100644
--- a/examples/dppo/lora/sd3_5/geneval_teacher.yaml
+++ b/examples/dppo/lora/sd3_5/geneval_teacher.yaml
@@ -1,6 +1,4 @@
 # Checkpoint: https://huggingface.co/Jayce-Ping/GenEval-Teacher
-# DPPO teacher config migrated from private flow_dppo/geneval.yaml.
-# Mapping: grpo + mask_type: kl_adv -> dppo + kl_mask_type: v-based; kl_beta=0.
 # Trains SD3.5-Medium LoRA on dataset/geneval with GenEval reward (float32, sync).
 
 # Environment Configuration
diff --git a/examples/dppo/lora/sd3_5/ocr_teacher.yaml b/examples/dppo/lora/sd3_5/ocr_teacher.yaml
index 7c92d4e3..0b7a9a55 100644
--- a/examples/dppo/lora/sd3_5/ocr_teacher.yaml
+++ b/examples/dppo/lora/sd3_5/ocr_teacher.yaml
@@ -1,6 +1,4 @@
 # Checkpoint: https://huggingface.co/Jayce-Ping/OCR-Teacher
-# DPPO teacher config migrated from private flow_dppo/ocr.yaml.
-# Mapping: grpo + mask_type: kl_adv -> dppo + kl_mask_type: v-based; kl_beta=0.
 # Trains SD3.5-Medium LoRA on dataset/ocr with OCR reward (sync).
 
 # Environment Configuration
diff --git a/examples/dppo/lora/sd3_5/pickscore_teacher.yaml b/examples/dppo/lora/sd3_5/pickscore_teacher.yaml
index 02310c7f..8bce38db 100644
--- a/examples/dppo/lora/sd3_5/pickscore_teacher.yaml
+++ b/examples/dppo/lora/sd3_5/pickscore_teacher.yaml
@@ -1,6 +1,4 @@
 # Checkpoint: https://huggingface.co/Jayce-Ping/Pickscore-Teacher
-# DPPO teacher config migrated from private flow_dppo/pickscore.yaml.
-# Mapping: grpo + mask_type: kl_adv -> dppo + kl_mask_type: v-based; kl_beta=0.
 # Trains SD3.5-Medium LoRA on dataset/pickscore with PickScore reward (async).
 
 # Environment Configuration