exclude tr-wikihow-summ until all the experiments complete

data.py

@@ -102,7 +102,7 @@ DATASET_GROUPS = {
         'description': 'Natural Language Inference (NLI) datasets in Turkish: XNLI, SNLI and MNLI.',
     },
     'SUM': {
-        'datasets': [name for name, task in DATASET_TASK_DICT.items() if task == Tasks.SUMMARIZATION],
+        'datasets': [name for name, task in DATASET_TASK_DICT.items() if task == Tasks.SUMMARIZATION and name != 'tr-wikihow-summ'],  # FIXME: include all the datasets.
         'description': 'Summarization datasets in Turkish (XLSum, MLSum, WikiLingua and TrWikiHowSumm).',
     },
     'GEC': {