diff --git a/examples/pytorch/language-modeling/run_clm.py b/examples/pytorch/language-modeling/run_clm.py
index 7aed40ed837..c3bf39ffce4 100755
--- a/examples/pytorch/language-modeling/run_clm.py
+++ b/examples/pytorch/language-modeling/run_clm.py
@@ -440,7 +440,10 @@ def main():
 
         max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
         metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
-        perplexity = math.exp(metrics["eval_loss"])
+        try:
+            perplexity = math.exp(metrics["eval_loss"])
+        except OverflowError:
+            perplexity = float("inf")
         metrics["perplexity"] = perplexity
 
         trainer.log_metrics("eval", metrics)
diff --git a/examples/pytorch/language-modeling/run_clm_no_trainer.py b/examples/pytorch/language-modeling/run_clm_no_trainer.py
index 45847246673..4005e7883c9 100755
--- a/examples/pytorch/language-modeling/run_clm_no_trainer.py
+++ b/examples/pytorch/language-modeling/run_clm_no_trainer.py
@@ -442,7 +442,10 @@ def main():
 
         losses = torch.cat(losses)
         losses = losses[: len(eval_dataset)]
-        perplexity = math.exp(torch.mean(losses))
+        try:
+            perplexity = math.exp(torch.mean(losses))
+        except OverflowError:
+            perplexity = float("inf")
 
         logger.info(f"epoch {epoch}: perplexity: {perplexity}")
 
diff --git a/examples/pytorch/language-modeling/run_mlm.py b/examples/pytorch/language-modeling/run_mlm.py
index 32a4bb537fb..60d315ef5fc 100755
--- a/examples/pytorch/language-modeling/run_mlm.py
+++ b/examples/pytorch/language-modeling/run_mlm.py
@@ -469,7 +469,10 @@ def main():
 
         max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
         metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
-        perplexity = math.exp(metrics["eval_loss"])
+        try:
+            perplexity = math.exp(metrics["eval_loss"])
+        except OverflowError:
+            perplexity = float("inf")
         metrics["perplexity"] = perplexity
 
         trainer.log_metrics("eval", metrics)
diff --git a/examples/pytorch/language-modeling/run_mlm_no_trainer.py b/examples/pytorch/language-modeling/run_mlm_no_trainer.py
index 1cf1c242ab2..1731b244dac 100755
--- a/examples/pytorch/language-modeling/run_mlm_no_trainer.py
+++ b/examples/pytorch/language-modeling/run_mlm_no_trainer.py
@@ -486,7 +486,10 @@ def main():
 
         losses = torch.cat(losses)
         losses = losses[: len(eval_dataset)]
-        perplexity = math.exp(torch.mean(losses))
+        try:
+            perplexity = math.exp(torch.mean(losses))
+        except OverflowError:
+            perplexity = float("inf")
 
         logger.info(f"epoch {epoch}: perplexity: {perplexity}")
 
diff --git a/examples/pytorch/language-modeling/run_plm.py b/examples/pytorch/language-modeling/run_plm.py
index f5cace2b6b0..e8fab3c3941 100755
--- a/examples/pytorch/language-modeling/run_plm.py
+++ b/examples/pytorch/language-modeling/run_plm.py
@@ -445,7 +445,10 @@ def main():
 
         max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
         metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
-        perplexity = math.exp(metrics["eval_loss"])
+        try:
+            perplexity = math.exp(metrics["eval_loss"])
+        except OverflowError:
+            perplexity = float("inf")
         metrics["perplexity"] = perplexity
 
         trainer.log_metrics("eval", metrics)