add output for train loss in assertian err

2025-04-18 08:11:11 -07:00
parent 08f287b57f
commit a0670abc94
12 changed files with 25 additions and 25 deletions
--- a/tests/e2e/multigpu/test_sp.py
+++ b/tests/e2e/multigpu/test_sp.py
@@ -93,7 +93,7 @@ class TestSequenceParallelism:
        )

        check_tensorboard(
-            temp_dir + "/runs", "train/train_loss", 2.6, "Train Loss is too high"
+            temp_dir + "/runs", "train/train_loss", 2.6, "Train loss (%s) is too high"
        )

    @pytest.mark.parametrize(