diff --git a/fast_llm/engine/schedule/runner.py b/fast_llm/engine/schedule/runner.py
index a8cc4f6d1..acde3320d 100644
--- a/fast_llm/engine/schedule/runner.py
+++ b/fast_llm/engine/schedule/runner.py
@@ -159,6 +159,9 @@ def run_step(
             assert self._support_training
 
         metrics = {} if return_metrics else None
+        if metrics is not None:
+            # Always present on logging steps so "no wait" shows as 0 rather than a gap.
+            metrics["data_wait_time_ms"] = 0.0
         # Set the context.
         context = BatchContext(
             iteration=iteration,
@@ -433,6 +436,8 @@ def _get_forward_input(self, context: BatchContext, step: Step) -> torch.Tensor:
                 next(context.data_iterator)
 
             data_time = (time.perf_counter() - start_time) * 1000
+            if context.metrics is not None:
+                context.metrics["data_wait_time_ms"] += data_time
             if data_time > self._config.data_batch_warn_time_ms:
                 logger.warning(f"Data loading took {data_time:,.2f} ms")
         return context.inputs.pop(step.global_index).detach().requires_grad_(step.stage != 0)
diff --git a/fast_llm/logging.py b/fast_llm/logging.py
index 2619883d6..20f2c4ecc 100644
--- a/fast_llm/logging.py
+++ b/fast_llm/logging.py
@@ -65,6 +65,7 @@
     "skipped_iters",
     "nan_iters",
     "step_time_average_ms",
+    "data_wait_time_ms",
     "remaining_time",
     "completion_time",
     "percent_done",
@@ -77,6 +78,7 @@
     " | skipped iterations: {skipped_iters:3.0f}"
     " | nan iterations: {nan_iters:3.0f}"
     " | average step time {step_time_average_ms:.2f} ms"
+    " | data wait: {data_wait_time_ms:.2f} ms"
     " | remaining {remaining_time} "
     " | completion {completion_time} ({percent_done:.2f} %)"
 )