diff --git a/vime/backends/megatron_utils/model.py b/vime/backends/megatron_utils/model.py
index 684ae2b4d..9ff9e5151 100644
--- a/vime/backends/megatron_utils/model.py
+++ b/vime/backends/megatron_utils/model.py
@@ -769,6 +769,9 @@ def train(
             log_dict["train/step"] = accumulated_step_id
             logging_utils.log(args, log_dict, step_key="train/step")
 
+            if args.ci_test and "train/train_rollout_logprob_abs_diff" in log_dict:
+                assert log_dict["train/train_rollout_logprob_abs_diff"] <= 0.1, f"{log_dict=}"
+
             if args.ci_test and not args.ci_disable_kl_checker:
                 if step_id == 0 and "train/ppo_kl" in log_dict and "train/pg_clipfrac" in log_dict:
                     # TODO: figure out why KL is not exactly zero when using PPO loss with KL clipping, and whether this is expected behavior or a bug.