diff --git a/README.md b/README.md
index f57d6d4fb..ab1c919df 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
   src="./docs/assets/logo.png">
 </h1>
 <p align="center">
-  <i>SOTA metrics for evaluating Retrieval Augmented Generation (RAG)</i>
+  <i>Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines</i>
 </p>
 
 <p align="center">
diff --git a/src/ragas/metrics/__init__.py b/src/ragas/metrics/__init__.py
index ce96f04ae..b54689e25 100644
--- a/src/ragas/metrics/__init__.py
+++ b/src/ragas/metrics/__init__.py
@@ -1,6 +1,6 @@
 from ragas.metrics.answer_relevance import AnswerRelevancy, answer_relevancy
 from ragas.metrics.context_relevance import ContextRelevancy, context_relevancy
-from ragas.metrics.factual import Faithfulness, faithfulness
+from ragas.metrics.faithfulnes import Faithfulness, faithfulness
 
 __all__ = [
     "Faithfulness",
diff --git a/src/ragas/metrics/context_relevance.py b/src/ragas/metrics/context_relevance.py
index 8560ed55d..93cc7acae 100644
--- a/src/ragas/metrics/context_relevance.py
+++ b/src/ragas/metrics/context_relevance.py
@@ -8,6 +8,7 @@
 import numpy as np
 from datasets import Dataset
 from sentence_transformers import CrossEncoder
+from tqdm import tqdm
 
 from ragas.metrics.base import Metric
 from ragas.metrics.llms import openai_completion
@@ -135,7 +136,7 @@ def score(self: t.Self, dataset: Dataset) -> Dataset:
             prompts.append(prompt)
 
         responses = []
-        for batch_idx in range(0, len(prompts), 20):
+        for batch_idx in tqdm(range(0, len(prompts), 20)):
             batch_responses = openai_completion(
                 prompts[batch_idx : batch_idx + 20], n=self.strictness
             )
diff --git a/src/ragas/metrics/factual.py b/src/ragas/metrics/faithfulnes.py
similarity index 100%
rename from src/ragas/metrics/factual.py
rename to src/ragas/metrics/faithfulnes.py
diff --git a/tests/benchmarks/benchmark_eval.py b/tests/benchmarks/benchmark_eval.py
index 5a09c18cd..7d5a30905 100644
--- a/tests/benchmarks/benchmark_eval.py
+++ b/tests/benchmarks/benchmark_eval.py
@@ -8,14 +8,8 @@
 
 DEVICE = "cuda" if is_available() else "cpu"
 
-PATH_TO_DATSET_GIT_REPO = "../../../datasets/fiqa/"
-dataset_dir = os.environ.get("DATASET_DIR", PATH_TO_DATSET_GIT_REPO)
-if os.path.isdir(dataset_dir):
-    ds = Dataset.from_csv(os.path.join(dataset_dir, "baseline.csv"))
-    assert isinstance(ds, Dataset)
-else:
-    # data
-    ds = load_dataset("explodinggradients/fiqa", "ragas_eval")["baseline"]
+# data
+ds = load_dataset("explodinggradients/fiqa", "ragas_eval")["baseline"]
 
 if __name__ == "__main__":
     result = evaluate(