diff --git a/moderation_classifier/eval_BERT.py b/moderation_classifier/eval_BERT.py
new file mode 100644
index 0000000000000000000000000000000000000000..242b874d36e5880b13a4146b339095bb662f8113
--- /dev/null
+++ b/moderation_classifier/eval_BERT.py
@@ -0,0 +1,19 @@
+from datasets import load_dataset
+from evaluate import evaluator
+from transformers import pipeline
+
+data = load_dataset("imdb", split="test").shuffle(seed=42).select(range(10))
+
+task_evaluator = evaluator("text-classification")
+
+pipe = pipeline("text-classification", model="../saved_models/20230630-103946/")
+
+eval_results = task_evaluator.compute(
+    model_or_pipeline=pipe,
+    data=data,
+    label_mapping={"NEGATIVE": 0, "POSITIVE": 1}
+)
+
+import pdb; pdb.set_trace()
+print(eval_results)
+
diff --git a/moderation_classifier/predict_BERT.py b/moderation_classifier/predict_BERT.py
index f930809ba3cd3438543a02435b4a56c4940185ff..242b874d36e5880b13a4146b339095bb662f8113 100644
--- a/moderation_classifier/predict_BERT.py
+++ b/moderation_classifier/predict_BERT.py
@@ -1,6 +1,19 @@
+from datasets import load_dataset
+from evaluate import evaluator
 from transformers import pipeline
 
-text = "This was a masterpiece. Not completely faithful to the books, but enthralling from beginning to end. Might be my favorite of the three."
+data = load_dataset("imdb", split="test").shuffle(seed=42).select(range(10))
+
+task_evaluator = evaluator("text-classification")
+
+pipe = pipeline("text-classification", model="../saved_models/20230630-103946/")
+
+eval_results = task_evaluator.compute(
+    model_or_pipeline=pipe,
+    data=data,
+    label_mapping={"NEGATIVE": 0, "POSITIVE": 1}
+)
+
+import pdb; pdb.set_trace()
+print(eval_results)
 
-classifier = pipeline("sentiment-analysis", model="../saved_models/")
-classifier(text)