diff --git a/src/lighteval/logging/evaluation_tracker.py b/src/lighteval/logging/evaluation_tracker.py
index fe27c8f0f..bf5d75227 100644
--- a/src/lighteval/logging/evaluation_tracker.py
+++ b/src/lighteval/logging/evaluation_tracker.py
@@ -27,6 +27,7 @@
 import time
 from dataclasses import asdict, is_dataclass
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
 
 from datasets import Dataset, load_dataset
@@ -59,6 +60,8 @@ def default(self, o):
             return asdict(o)
         if callable(o):
             return o.__name__
+        if isinstance(o, Enum):
+            return o.name
         return super().default(o)
 
 
diff --git a/src/lighteval/metrics/utils.py b/src/lighteval/metrics/utils.py
index e0db60897..52e8e0665 100644
--- a/src/lighteval/metrics/utils.py
+++ b/src/lighteval/metrics/utils.py
@@ -69,7 +69,7 @@ def compute(self, **kwargs) -> dict:  # result: Union[list[ModelReturn], ModelRe
             return {}
         if isinstance(self, MetricGrouping):
             return self.sample_level_fn(**kwargs)  # result, formatted_doc,
-        return {self.name: self.sample_level_fn(**kwargs)}  # result, formatted_doc,
+        return {self.metric_name: self.sample_level_fn(**kwargs)}  # result, formatted_doc,
 
 
 @dataclass