diff --git a/src/projected_grpo/train.py b/src/projected_grpo/train.py
index 98a8b7d..cb4d3fc 100644
--- a/src/projected_grpo/train.py
+++ b/src/projected_grpo/train.py
@@ -389,6 +389,7 @@ def main(cfg: Config) -> int:
                             "top_k": str(min(cfg.v_hack_extract_top_k, len(VHACK_PAIRS) - 2)),
                             "tau_axis": "0.0", "schema": "v2_with_sv"})
         # extract zeros grads at exit; opt is built below so no opt-state taint.
+        model.train()  # restore train mode; eval was set only for the extract pass
     v_hack_cpu, _v_sv_cpu = load_v_hack(v_hack_path, model_name, wrappers, k_use=cfg.v_hack_k)
     v_hack = {name: v.to(device) for name, v in v_hack_cpu.items()}
     # Teacher pool: pre-generated rollouts on disk keyed by problem_id. Each step's