diff --git a/flash/text/seq2seq/translation/model.py b/flash/text/seq2seq/translation/model.py
index 431c0802c4..0c421999b4 100644
--- a/flash/text/seq2seq/translation/model.py
+++ b/flash/text/seq2seq/translation/model.py
@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, Optional, Union
 
 from torchmetrics import BLEUScore
 
@@ -99,8 +99,3 @@ def compute_metrics(self, generated_tokens, batch, prefix):
         else:
             result = self.bleu(reference_corpus, translate_corpus)
         self.log(f"{prefix}_bleu_score", result, on_step=False, on_epoch=True, prog_bar=True)
-
-    @staticmethod
-    def _ci_benchmark_fn(history: List[Dict[str, Any]]):
-        """This function is used only for debugging usage with CI."""
-        assert history[-1]["val_bleu_score"] > 0.6, history[-1]["val_bleu_score"]