diff --git a/src/axolotl/core/trainer_builder.py b/src/axolotl/core/trainer_builder.py
index 7537f80fe..265cfeb8c 100755
--- a/src/axolotl/core/trainer_builder.py
+++ b/src/axolotl/core/trainer_builder.py
@@ -1638,6 +1638,7 @@ class HFCausalTrainerBuilder(TrainerBuilderBase):
             trainer_kwargs["max_length"] = self.cfg.sequence_len
 
         if self.cfg.optimizer in [
+            # pylint: disable=duplicate-code
             "optimi_adamw",
             "ao_adamw_4bit",
             "ao_adamw_8bit",
diff --git a/tests/e2e/test_optimizers.py b/tests/e2e/test_optimizers.py
index 119dd3d7c..24985dde0 100644
--- a/tests/e2e/test_optimizers.py
+++ b/tests/e2e/test_optimizers.py
@@ -65,3 +65,44 @@ class TestCustomOptimizers(unittest.TestCase):
 
         train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
         assert (Path(temp_dir) / "adapter_model.bin").exists()
+
+    @with_temp_dir
+    def test_soap(self, temp_dir):
+        # pylint: disable=duplicate-code
+        cfg = DictDefault(
+            {
+                "base_model": "HuggingFaceTB/SmolLM-135M",
+                "sequence_len": 1024,
+                "load_in_8bit": True,
+                "adapter": "lora",
+                "lora_r": 8,
+                "lora_alpha": 16,
+                "lora_dropout": 0.05,
+                "lora_target_linear": True,
+                "val_set_size": 0.1,
+                "special_tokens": {
+                    "pad_token": "<|endoftext|>",
+                },
+                "datasets": [
+                    {
+                        "path": "vicgalle/alpaca-gpt4",
+                        "type": "alpaca",
+                    },
+                ],
+                "num_epochs": 1,
+                "micro_batch_size": 8,
+                "gradient_accumulation_steps": 1,
+                "output_dir": temp_dir,
+                "learning_rate": 0.00001,
+                "optimizer": "soap",
+                "optim_soap_beta1": 0.95,
+                "optim_soap_beta2": 0.95,
+                "lr_scheduler": "cosine",
+            }
+        )
+        normalize_config(cfg)
+        cli_args = TrainerCliArgs()
+        dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
+
+        train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
+        assert (Path(temp_dir) / "adapter_model.bin").exists()