Merge pull request jiaweizzhao#11 from darthjaja6/patch-1

Update torchrun_main.py - c4
antoine311200 · Mar 15, 2024 · 864eeb3 · 864eeb3
2 parents e4fe249 + 29bea7c
commit 864eeb3
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/torchrun_main.py b/torchrun_main.py
@@ -167,7 +167,7 @@ def main(args):
         logger.info(f"{k:30} {v}")
     logger.info("*" * 40)
 
-    data = datasets.load_dataset("c4", "en", split="train", streaming=True)
+    data = datasets.load_dataset("allenai/c4", "en", split="train", streaming=True)
 
     seed_for_shuffle = 42