423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update loader.py

Browse Source 
Former-commit-id: aa7f335e3ad5a78e4ed5f99c120be28e9733ea2e
This commit is contained in:
hoshi-hiyouga 2024-05-30 00:17:21 +08:00 committed by GitHub
parent 5f67fdaac9
commit a67199246d
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/llamafactory/data/loader.py
View File

@ -108,7 +108,13 @@ def load_single_dataset(
dataset = dataset.to_iterable_dataset() # TODO: add num shards parameter
if dataset_attr.num_samples is not None and not data_args.streaming:
indexes = np.random.permutation(len(dataset))[: dataset_attr.num_samples]
target_num = dataset_attr.num_samples
indexes = np.random.permutation(len(dataset))[:target_num]
target_num -= len(indexes)
if target_num > 0:
expand_indexes = np.random.choice(len(dataset), target_num)
indexes = np.concatenate((indexes, expand_indexes), axis=0)
dataset = dataset.select(indexes)
logger.info("Sampled {} examples from dataset {}.".format(dataset_attr.num_samples, dataset_attr))