423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-22 06:40:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #1218

Browse Source 
Former-commit-id: b301f35bd4a3bf368159c8f5fb4e2736f922115b
This commit is contained in:
hiyouga
2023-10-19 16:17:41 +08:00
parent 142dd63b47
commit 47a1f73d0f
3 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/hparams/data_args.py
View File

@@ -60,7 +60,7 @@ class DataArguments:
)
mix_strategy: Optional[Literal["concat", "interleave_under", "interleave_over"]] = field(
default="concat",
metadata={"help": "Strategy to use in dataset mixing."}
metadata={"help": "Strategy to use in dataset mixing (concat/interleave) (undersampling/oversampling)."}
)
interleave_probs: Optional[str] = field(
default=None,
@@ -106,7 +106,8 @@ class DataArguments:
if self.streaming and self.max_samples is not None:
raise ValueError("`max_samples` is incompatible with `streaming`.")
def init_for_training(self): # support mixing multiple datasets
def init_for_training(self, seed: int): # support mixing multiple datasets
self.seed = seed
dataset_names = [ds.strip() for ds in self.dataset.split(",")] if self.dataset is not None else []
try:
with open(os.path.join(self.dataset_dir, "dataset_info.json"), "r") as f: