Remove rewrite reminder comment from everything except SuperGLUE

lm_eval/tasks/anli.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from . common import HFTask
 
 class ANLIBase(HFTask):

lm_eval/tasks/arc.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from . common import HFTask
 
 class ARCEasy(HFTask):

lm_eval/tasks/drop.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 import json
 from scipy.stats import pearsonr, spearmanr

lm_eval/tasks/glue.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from lm_eval.base import rf, mean, f1_score, matthews_corrcoef
 from scipy.stats import pearsonr, spearmanr

lm_eval/tasks/hellaswag.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from scipy.stats import pearsonr, spearmanr
 from sklearn.metrics import f1_score, matthews_corrcoef

lm_eval/tasks/lambada.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from lm_eval.base import Dataset
 from lm_eval.utils import sh
 import json

lm_eval/tasks/naturalqs.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from . common import HFTask
 from itertools import islice
 

lm_eval/tasks/openbookqa.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from scipy.stats import pearsonr, spearmanr
 from sklearn.metrics import f1_score, matthews_corrcoef
@@ -34,7 +32,8 @@ class OpenBookQA(HFTask):
             return self.data["test"]
 
     def fewshot_description(self):
-        return "Text of the question prompt\nText of the answer completion"
+        # TODO: figure out fewshot description
+        return ""
 
     def doc_to_text(self, doc):
         return doc['question_stem'] + '\n'

lm_eval/tasks/piqa.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import json
 import random
 from lm_eval.base import Dataset

lm_eval/tasks/quac.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import json
 import random
 import os

lm_eval/tasks/race.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from . common import HFTask
 from ..utils_stream import X, each, apply, join, filt, one
 import collections

lm_eval/tasks/squad.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from scipy.stats import pearsonr, spearmanr
 from sklearn.metrics import f1_score, matthews_corrcoef

lm_eval/tasks/storycloze.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import json
 import random
 from lm_eval.base import Dataset

lm_eval/tasks/triviaqa.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import json
 import random
 from lm_eval.base import Dataset

lm_eval/tasks/webqs.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 from . common import HFTask
 
 class WebQs(HFTask):

lm_eval/tasks/wikitext.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from scipy.stats import pearsonr, spearmanr
 from sklearn.metrics import f1_score, matthews_corrcoef

lm_eval/tasks/winogrande.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import numpy as np
 from scipy.stats import pearsonr, spearmanr
 from sklearn.metrics import f1_score, matthews_corrcoef

lm_eval/tasks/wsc273.py

-# REMINDER: this code needs to be rewritten for the new framework. Remove this comment when the code is fully converted.
-
 import json
 import random
 import os