Add max_chunks=18 to dolma-30b export, remove max_chunks=5 from english-wiki, rename project to datapipline
This commit is contained in:
@@ -7,5 +7,4 @@ if __name__ == "__main__":
|
||||
dataset=dataset["train"],
|
||||
output_dir="./dataset",
|
||||
output_prefix="english-wiki-pretrain",
|
||||
max_chunks=5,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user