diff --git a/.pylintrc b/.pylintrc
index 222bdf6cb..f54599d18 100644
--- a/.pylintrc
+++ b/.pylintrc
@@ -333,7 +333,7 @@ indent-string='    '
 max-line-length=100
 
 # Maximum number of lines in a module.
-max-module-lines=1200
+max-module-lines=1400
 
 # Allow the body of a class to be on the same line as the declaration if body
 # contains single statement.
diff --git a/tests/artifacts/testdata/jsonl/twitter_complaints_small_2.jsonl b/tests/artifacts/testdata/jsonl/twitter_complaints_small_2.jsonl
new file mode 100644
index 000000000..0837217c3
--- /dev/null
+++ b/tests/artifacts/testdata/jsonl/twitter_complaints_small_2.jsonl
@@ -0,0 +1,10 @@
+{"Tweet text":"@NortonSupport Thanks much.","ID":10,"Label":2,"text_label":"no complaint","output":"### Text: @NortonSupport Thanks much.\n\n### Label: no complaint"}
+{"Tweet text":"@VerizonSupport all of a sudden I can't connect to my primary wireless network but guest one works","ID":11,"Label":2,"text_label":"no complaint","output":"### Text: @VerizonSupport all of a sudden I can't connect to my primary wireless network but guest one works\n\n### Label: no complaint"}
+{"Tweet text":"Aaaahhhhh!!!! My @Razer @PlayOverwatch d.va meka headset came in!!! I didn't even know it had shipped!!! So excited\u2026 https:\/\/t.co\/4gXy9xED8d","ID":12,"Label":2,"text_label":"no complaint","output":"### Text: Aaaahhhhh!!!! My @Razer @PlayOverwatch d.va meka headset came in!!! I didn't even know it had shipped!!! So excited\u2026 https:\/\/t.co\/4gXy9xED8d\n\n### Label: no complaint"}
+{"Tweet text":"@Lin_Manuel @jmessinaphoto @VAMNit Omg a little squish!!!!! Enjoy and congrats!!!! I miss mine being so young! \ufffd\ufffd\ufffd\ufffd\ufffd\ufffd","ID":13,"Label":2,"text_label":"no complaint","output":"### Text: @Lin_Manuel @jmessinaphoto @VAMNit Omg a little squish!!!!! Enjoy and congrats!!!! I miss mine being so young! \ufffd\ufffd\ufffd\ufffd\ufffd\ufffd\n\n### Label: no complaint"}
+{"Tweet text":"@IanJamesPoulter What's your secret to poaching eggs? Mine NEVER look that good.","ID":14,"Label":2,"text_label":"no complaint","output":"### Text: @IanJamesPoulter What's your secret to poaching eggs? Mine NEVER look that good.\n\n### Label: no complaint"}
+{"Tweet text":"@AWSSupport When will be able Kinesis Firehose compatible with Elasticsearch 6.0? Thank you!","ID":15,"Label":2,"text_label":"no complaint","output":"### Text: @AWSSupport When will be able Kinesis Firehose compatible with Elasticsearch 6.0? Thank you!\n\n### Label: no complaint"}
+{"Tweet text":"@NCIS_CBS https:\/\/t.co\/eeVL9Eu3bE","ID":16,"Label":2,"text_label":"no complaint","output":"### Text: @NCIS_CBS https:\/\/t.co\/eeVL9Eu3bE\n\n### Label: no complaint"}
+{"Tweet text":"@msetchell Via the settings? That\u2019s how I do it on master T\u2019s","ID":17,"Label":2,"text_label":"no complaint","output":"### Text: @msetchell Via the settings? That\u2019s how I do it on master T\u2019s\n\n### Label: no complaint"}
+{"Tweet text":"Today at work there was a low flying duck heading toward a crowd of people, and I yelled \"watch out! and I'm very disappointed with myself.","ID":18,"Label":2,"text_label":"no complaint","output":"### Text: Today at work there was a low flying duck heading toward a crowd of people, and I yelled \"watch out! and I'm very disappointed with myself.\n\n### Label: no complaint"}
+{"Tweet text":"@NortonSupport @NortonOnline What the hell is a dm 5-10 days to get money back bank account now overdrawn thanks guys","ID":19,"Label":1,"text_label":"complaint","output":"### Text: @NortonSupport @NortonOnline What the hell is a dm 5-10 days to get money back bank account now overdrawn thanks guys\n\n### Label: complaint"}
diff --git a/tests/data/test_data_preprocessing_utils.py b/tests/data/test_data_preprocessing_utils.py
index 5559ac8ec..801f75bee 100644
--- a/tests/data/test_data_preprocessing_utils.py
+++ b/tests/data/test_data_preprocessing_utils.py
@@ -13,7 +13,9 @@
 # limitations under the License.
 
 # Standard
+import glob
 import json
+import os
 import tempfile
 
 # Third Party
@@ -613,6 +615,54 @@ def test_process_dataconfig_multiple_files(data_config_path, data_path_list):
         assert formatted_dataset_field in set(train_set.column_names)
 
 
+@pytest.mark.parametrize(
+    "data_config_path, data_path",
+    [
+        (
+            DATA_CONFIG_APPLY_CUSTOM_TEMPLATE_YAML,
+            os.path.join(
+                os.path.dirname(TWITTER_COMPLAINTS_DATA_JSONL), "*small*.jsonl"
+            ),
+        ),
+    ],
+)
+def test_process_dataconfig_multiple_files_with_globbing(data_config_path, data_path):
+    """Ensure that datasets files matching globbing pattern are formatted and validated correctly based on the arguments passed in config file."""
+    with open(data_config_path, "r") as f:
+        yaml_content = yaml.safe_load(f)
+
+    PATTERN_TWITTER_COMPLAINTS_DATA_JSONL = data_path.replace(
+        "twitter_complaints_small.jsonl", "*small*.jsonl"
+    )
+    yaml_content["datasets"][0]["data_paths"][0] = PATTERN_TWITTER_COMPLAINTS_DATA_JSONL
+
+    # Modify dataset_text_field and template according to dataset
+    formatted_dataset_field = "formatted_data_field"
+    template = "### Input: {{Tweet text}} \n\n ### Response: {{text_label}}"
+    yaml_content["datasets"][0]["data_handlers"][0]["arguments"]["fn_kwargs"] = {
+        "dataset_text_field": formatted_dataset_field,
+        "template": template,
+    }
+
+    with tempfile.NamedTemporaryFile(
+        "w", delete=False, suffix=".yaml"
+    ) as temp_yaml_file:
+        yaml.dump(yaml_content, temp_yaml_file)
+        temp_yaml_file_path = temp_yaml_file.name
+        data_args = configs.DataArguments(data_config_path=temp_yaml_file_path)
+
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    (train_set, _, _) = _process_dataconfig_file(data_args, tokenizer)
+    assert isinstance(train_set, Dataset)
+    assert formatted_dataset_field in set(train_set.column_names)
+
+    data_len = sum(
+        sum(1 for _ in open(file, "r"))  # Count lines in each JSONL file
+        for file in glob.glob(PATTERN_TWITTER_COMPLAINTS_DATA_JSONL)
+    )
+    assert len(train_set) == data_len
+
+
 @pytest.mark.parametrize(
     "datafiles, datasetconfigname",
     [
diff --git a/tuning/data/data_config.py b/tuning/data/data_config.py
index 4da83d720..ed8af3f8c 100644
--- a/tuning/data/data_config.py
+++ b/tuning/data/data_config.py
@@ -79,7 +79,6 @@ def _validate_dataset_config(dataset_config) -> DataSetConfig:
     c.data_paths = []
     for p in data_paths:
         assert isinstance(p, str), f"path {p} should be of the type string"
-        assert os.path.exists(p), f"data_paths {p} does not exist"
         if not os.path.isabs(p):
             _p = os.path.abspath(p)
             logging.warning(
diff --git a/tuning/utils/utils.py b/tuning/utils/utils.py
index 6eef6b2cf..b6c6a38b0 100644
--- a/tuning/utils/utils.py
+++ b/tuning/utils/utils.py
@@ -31,9 +31,9 @@ def get_loader_for_filepath(file_path: str) -> str:
         return "text"
     if ext in (".json", ".jsonl"):
         return "json"
-    if ext in (".arrow"):
+    if ext in (".arrow",):
         return "arrow"
-    if ext in (".parquet"):
+    if ext in (".parquet",):
         return "parquet"
     return ext