Merge pull request #209 from EleutherAI/sdtblck-patch-1

Don't download lambada if it already exists

lm_eval/tasks/lambada.py

@@ -3,6 +3,7 @@ from lm_eval.base import Task, rf
 from lm_eval.metrics import mean, perplexity
 from lm_eval.utils import sh
 from best_download import download_file
+import os
 
 
 class LAMBADA(Task):
@@ -10,11 +11,12 @@ class LAMBADA(Task):
     def download(self):
         sh("mkdir -p data/lambada")
         try:
-            download_file(
-                "http://eaidata.bmk.sh/data/lambada_test.jsonl", 
-                "data/lambada/lambada_test.jsonl", 
-                "4aa8d02cd17c719165fc8a7887fddd641f43fcafa4b1c806ca8abc31fabdb226"
-            )
+            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"
+                )
         except:
             # fallback - for some reason best_download doesnt work all the time here
             sh("wget http://eaidata.bmk.sh/data/lambada_test.jsonl -O data/lambada/lambada_test.jsonl")