Merge branch 'master' into researcher2

lm_eval/tasks/headqa.py

@@ -2,10 +2,9 @@ from . common import HFTask
 from lm_eval.base import MultipleChoiceTask
 
 
-class HeadQA(HFTask, MultipleChoiceTask):
+class HeadQABase(HFTask, MultipleChoiceTask):
     VERSION = 0
     DATASET_PATH = "head_qa"
-    DATASET_NAME = None
 
     def has_training_docs(self):
         return True
@@ -25,9 +24,19 @@ class HeadQA(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]
+
+class HeadQAEn(HeadQABase):
+    DATASET_NAME = "en"
+
+class HeadQAEs(HeadQABase):
+    DATASET_NAME = "es"
+
+# for backwards compatibility
+class HeadQAEsDeprecated(HeadQABase):
+    DATASET_NAME = "es"
+
+    def __init__(self):
+        super().__init__()
+        print("WARNING: headqa is deprecated. Please use headqa_es or headqa_en instead. See https://github.com/EleutherAI/lm-evaluation-harness/pull/240 for more info.")
\ No newline at end of file

lm_eval/tasks/hellaswag.py

@@ -35,11 +35,6 @@ class HellaSwag(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        return "Label for the relevant action: Sentences describing the " \
-            "context, with an incomplete sentence trailing\nanswer that " \
-            "plausibly completes the situation."
-
     def doc_to_text(self, doc):
         return doc["query"]
 

lm_eval/tasks/hendrycks_ethics.py

@@ -20,7 +20,7 @@ class Ethics(Task):
     def download(self):
         if not os.path.exists('data/ethics/done'):
             sh("mkdir -p data")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/ethics.tar", "data/ethics.tar", "40acbf1ac0da79a2aabef394d58889136b8d38b05be09482006de2453fb06333")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/ethics.tar", local_file="data/ethics.tar", expected_checksum="40acbf1ac0da79a2aabef394d58889136b8d38b05be09482006de2453fb06333")
             sh("""
             tar -xf data/ethics.tar -C data/
             rm data/ethics.tar
@@ -237,9 +237,6 @@ class EthicsUtilitarianismOriginal(Ethics):
         for doc in docs:
             yield {"activity": doc[0], "baseline": doc[1], "rating": ""}
 
-    def fewshot_description(self):
-        return "Rate how pleasant each of the following activities is on a scale from 1 (very unpleasant) to 10 (very pleasant).\n\n"
-
     def fewshot_examples(self, k, rnd):
         # Overwriting fewshot examples as k can be max 5
         assert k <= 5, "There are only 5 possible shots for this task. Refer to the V2 for more."
@@ -350,9 +347,6 @@ class EthicsVirtue(Ethics):
     def get_prefix(self):
         return "virtue/virtue"
 
-    def fewshot_description(self):
-        return "The following is a list of sentences and traits, along with whether the trait is exhibited in that sentence.\n\n"
-
     def process_doc(self, doc):
         # Append identifiers before shuffling to calculate exact matches lateron & skip the first element of headers
         return [x + [i] for i, x in enumerate(doc[1:])]

lm_eval/tasks/hendrycks_math.py

@@ -18,7 +18,7 @@ class Math(Task):
     def download(self):
         if not (self.DATASET_PATH / 'test').exists() or not (self.DATASET_PATH / 'done').exists():
             sh(f"mkdir -p {self.DATASET_PATH}")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/MATH.tar", f"{self.DATASET_PATH}.tar", "01256fd7cd5430596fdf07e6e6a5827111b5235b7ffed679c662a12f898932da")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/MATH.tar", local_file=f"{self.DATASET_PATH}.tar", expected_checksum="01256fd7cd5430596fdf07e6e6a5827111b5235b7ffed679c662a12f898932da")
             sh(f"""
             tar -xf {self.DATASET_PATH}.tar -C data/ && touch {self.DATASET_PATH / 'done'}
             rm {self.DATASET_PATH}.tar
@@ -55,9 +55,6 @@ class Math(Task):
     def test_docs(self):
         return self._load_docs(self.DATASET_PATH / "test" / self.get_file_info())
 
-    def fewshot_description(self):
-        return "Given a mathematics problem, determine the answer. Simplify your answer as much as possible."
-
     def doc_to_text(self, doc):
         return "Problem: " + doc["problem"] + "\nAnswer:"
 

lm_eval/tasks/hendrycks_test.py

@@ -45,7 +45,7 @@ class GeneralHendrycksTest(MultipleChoiceTask):
     def download(self):
         if not (self.DATASET_PATH / 'done').exists():
             sh("mkdir -p data")
-            download_file("https://people.eecs.berkeley.edu/~hendrycks/data.tar", "data/data.tar", "78a804365a59028188fb19bd1adcadc5e0c260b220a9d8b2e33a5ea7d5fbe3b4")
+            download_file("https://people.eecs.berkeley.edu/~hendrycks/data.tar", local_file="data/data.tar", expected_checksum="78a804365a59028188fb19bd1adcadc5e0c260b220a9d8b2e33a5ea7d5fbe3b4")
             sh("""
             tar -xf data/data.tar -C data/
             rm data/data.tar
@@ -114,9 +114,5 @@ class GeneralHendrycksTest(MultipleChoiceTask):
 
         return rnd.sample(list(self._fewshot_docs), k)
 
-    def fewshot_description(self):
-        subject = self.subject.replace("_", " ")
-        return f"The following are multiple choice questions (with answers) about {subject}."
-
     def doc_to_text(self, doc):
         return doc["query"]

lm_eval/tasks/lambada.py

@@ -14,8 +14,8 @@ class LAMBADA(Task):
             if not os.path.exists("data/lambada/lambada_test.jsonl"):
                 download_file(
                     "http://eaidata.bmk.sh/data/lambada_test.jsonl", 
-                    "data/lambada/lambada_test.jsonl", 
-                    "4aa8d02cd17c719165fc8a7887fddd641f43fcafa4b1c806ca8abc31fabdb226"
+                    local_file="data/lambada/lambada_test.jsonl",
+                    expected_checksum="4aa8d02cd17c719165fc8a7887fddd641f43fcafa4b1c806ca8abc31fabdb226"
                 )
         except:
             # fallback - for some reason best_download doesnt work all the time here
@@ -54,10 +54,6 @@ class LAMBADA(Task):
     def doc_to_target(self, doc):
         return " " + doc['text'].rsplit(' ', 1)[1]
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def construct_requests(self, doc, ctx):
         ll, is_greedy = rf.loglikelihood(ctx, self.doc_to_target(doc))
 

lm_eval/tasks/lambada_cloze.py

@@ -13,6 +13,3 @@ class LAMBADA_cloze(LAMBADA):
 
     def doc_to_target(self, doc):
         return " " + doc['text'].rsplit(' ', 1)[1]
-    
-    def fewshot_description(self):
-        return "Fill in blank:\n"

lm_eval/tasks/lambada_multilingual.py

@@ -32,8 +32,8 @@ class MultilingualLAMBADA(lambada.LAMBADA):
         if not os.path.exists(f):
           download_file(
               url, 
-              f, 
-              CHECKSUMS[self.LANG]
+              local_file=f,
+              expected_checksum=CHECKSUMS[self.LANG]
           )
       except:
         # fallback - for some reason best_download doesnt work all the time here

lm_eval/tasks/logiqa.py

@@ -19,7 +19,7 @@ class LogiQA(MultipleChoiceTask):
         ]
         for split in splits:
             file = self.DATASET_PATH / f"{split['name']}.txt"
-            download_file(f"{base_url}/{split['name']}.txt", str(file), split["checksum"])
+            download_file(f"{base_url}/{split['name']}.txt", local_file=str(file), expected_checksum=split["checksum"])
 
     def has_training_docs(self):
         return True
@@ -81,10 +81,6 @@ class LogiQA(MultipleChoiceTask):
     def test_docs(self):
         return self._load_docs(self.DATASET_PATH / "Test.txt")
 
-    def fewshot_description(self):
-        # TODO: figure out actual description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]
 

lm_eval/tasks/mathqa.py

@@ -29,10 +29,6 @@ class MathQA(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]
 

lm_eval/tasks/mc_taco.py

@@ -39,9 +39,6 @@ class MCTACO(HFTask):
     def has_test_docs(self):
         return True
 
-    def fewshot_description(self):
-        return "Determine whether the candidate answer is plausible (\"yes\") or not (\"no\")"
-
     def doc_to_text(self, doc):
         return f"{doc['sentence']}\nQuestion: {doc['question']}\n"\
             f"Answer: {doc['answer']}\nPlausible:"

lm_eval/tasks/mutual.py

@@ -36,8 +36,8 @@ class MuTualBase(Task):
         master_zip = Path("data/master.zip")
         download_file(
             "https://github.com/Nealcly/MuTual/archive/master.zip",
-            str(master_zip),
-            "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9")
+            local_file=str(master_zip),
+            expected_checksum="bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9")
         with zipfile.ZipFile(master_zip, 'r') as zip:
             zip.extractall("data")
         Path("data/MuTual-master/data").rename(str(self.BASE_PATH))
@@ -70,10 +70,6 @@ class MuTualBase(Task):
     def test_docs(self):
         return NotImplemented
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def doc_to_text(self, doc):
         return self.detokenize(doc["article"])
 

lm_eval/tasks/naturalqs.py

@@ -21,10 +21,6 @@ class NaturalQs(HFTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out description
-        return ""
-
     def training_docs(self):
         # Cache training for faster few-shot.
         # Data is too large to fit in memory.

lm_eval/tasks/openbookqa.py

@@ -25,9 +25,5 @@ class OpenBookQA(HFTask, MultipleChoiceTask):
         }
         return out_doc
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def doc_to_text(self, doc):
         return doc["query"]

lm_eval/tasks/pile.py

@@ -10,7 +10,7 @@ from best_download import download_file
 
 
 class PilePerplexityTask(PerplexityTask, abc.ABC):
-    VERSION = 0
+    VERSION = 1
 
     PILE_SET_NAME = None
     VAL_PATH = 'data/pile/val.jsonl.zst'
@@ -18,9 +18,11 @@ class PilePerplexityTask(PerplexityTask, abc.ABC):
 
     def download(self):
         # TODO: separate pile val/test out by component so we don't have to scan the entire file once per set
+        if not os.path.exists("data/pile/test.jsonl.zst"):
+            # todo use new best_download fallback api
             os.makedirs("data/pile/", exist_ok=True)
-        download_file("https://the-eye.eu/public/AI/pile/val.jsonl.zst", self.VAL_PATH, "264c875d8bbd355d8daa9d032b75fd8fb91606218bb84dd1155b203fcd5fab92")
-        download_file("https://the-eye.eu/public/AI/pile/test.jsonl.zst", self.TEST_PATH, "0bb28c52d0b5596d389bf179ce2d43bf7f7ffae76b0d2d20b180c97f62e0975e")
+            download_file("http://eaidata.bmk.sh/data/pile/val.jsonl.zst", local_file=self.VAL_PATH, expected_checksum="264c875d8bbd355d8daa9d032b75fd8fb91606218bb84dd1155b203fcd5fab92")
+            download_file("http://eaidata.bmk.sh/data/pile/test.jsonl.zst", local_file=self.TEST_PATH, expected_checksum="0bb28c52d0b5596d389bf179ce2d43bf7f7ffae76b0d2d20b180c97f62e0975e")
 
     def validation_docs(self):
         rdr = lm_dataformat.Reader(self.VAL_PATH)

lm_eval/tasks/piqa.py

@@ -18,10 +18,6 @@ class PiQA(HFTask, MultipleChoiceTask):
     def has_test_docs(self):
         return False
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
     def _convert_standard(self, doc):
         out_doc = {
             "goal": doc["goal"],

lm_eval/tasks/prost.py

@@ -36,13 +36,14 @@ class PROST(HFTask, MultipleChoiceTask):
     def has_test_docs(self):
         return True
 
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        return ""
-
-    def fewshot_context(self, doc, num_fewshot, provide_description, rnd):
+    def fewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None):
         assert num_fewshot == 0, 'PROST is designed to probe models in a zero-shot fashion only.'
-        return super().fewshot_context(doc, num_fewshot, provide_description, rnd)
+        return super().fewshot_context(
+            doc=doc,
+            num_fewshot=num_fewshot,
+            rnd=rnd,
+            description=description
+        )
 
     def _convert_standard(self, doc):
         out_doc = {

lm_eval/tasks/pubmedqa.py

@@ -23,11 +23,6 @@ class Pubmed_QA(HFTask):
             # HF is labelled as train but its really just for testing
             return self.data["train"]
 
-    def fewshot_description(self):
-        # Average ctx length in labelled dataset is 238.9
-        # 2 few-shot exmamples pushes it beyond context window
-        return ""
-
     def doc_to_text(self, doc):
         ctxs = "\n".join(doc["context"]["contexts"])
         return "Abstract: {}\nQuestion: {}\nAnswer:".format(

lm_eval/tasks/qa4mre.py

@@ -32,8 +32,8 @@ class QA4MRE(MultipleChoiceTask):
         if not os.path.isfile(f"data/qa4mre/QA4MRE-{year}-{lang}"):
             download_file(
                 url_path,
-                f"data/qa4mre/QA4MRE-{year}-{lang}_GS.xml",
-                sha256sums[year],
+                local_file=f"data/qa4mre/QA4MRE-{year}-{lang}_GS.xml",
+                expected_checksum=sha256sums[year],
                 )
 
     def has_training_docs(self):
@@ -67,9 +67,6 @@ class QA4MRE(MultipleChoiceTask):
                 out_doc['source'] = src
                 yield out_doc
 
-    def fewshot_description(self):
-        return ""
-
     def test_docs(self):
         return self.load_docs(f"data/qa4mre/QA4MRE-{self.YEAR}-EN_GS.xml")
 

lm_eval/tasks/quac.py

@@ -51,11 +51,6 @@ class QuAC(Task):
     def test_docs(self):
         raise NotImplementedError("QuAC has no test docs.")
     
-    def fewshot_description(self):
-        # TODO: figure out fewshot description
-        desc = "TITLE: Title of the context passage - subtitle of the passage\nPARAGRAPH: Passage describing the relevant information for answering questions.\n\nQ: Text of a question.\n\nA: Answer to the question, based on the passage. If it cannot be answered based on the passage, write CANNOTANSWER"
-        return desc
-
     def load_doc(self, myjson):
         docs = []
         for item in myjson: