support interleave probs

This commit is contained in:
hiyouga committed 2023-08-04 21:27:35 +08:00
1 parent 6bdb7f0910
commit 69744c17e8
3 files changed
+17 -7

No files matched your search

+1 -1
View File
@@ -111,6 +111,6 @@ def get_dataset(
if not data_args.streaming:
logger.warning("We recommend using `mix_strategy=concat` in non-streaming mode.")
stopping_strategy = "first_exhausted" if data_args.mix_strategy.endswith("under") else "all_exhausted"
return interleave_datasets(all_datasets, stopping_strategy=stopping_strategy)
return interleave_datasets(all_datasets, data_args.interleave_probs, stopping_strategy=stopping_strategy)
else:
raise ValueError("Unknown mixing strategy.")