mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-12-17 12:20:37 +08:00
@@ -59,8 +59,8 @@ def get_dataset(
|
||||
data_files=data_files,
|
||||
split=data_args.split,
|
||||
cache_dir=model_args.cache_dir,
|
||||
streaming=data_args.streaming,
|
||||
use_auth_token=True if model_args.use_auth_token else None
|
||||
token=model_args.hf_hub_token,
|
||||
streaming=data_args.streaming
|
||||
)
|
||||
|
||||
if max_samples is not None: # truncate dataset
|
||||
|
||||
@@ -257,7 +257,7 @@ def preprocess_dataset(
|
||||
if data_args.cache_path is not None and not os.path.exists(data_args.cache_path):
|
||||
if training_args.should_save:
|
||||
dataset.save_to_disk(data_args.cache_path)
|
||||
raise SystemExit("Dataset saved, rerun this script with the same `--cache_file`.")
|
||||
raise SystemExit("Dataset saved, rerun this script with the same `--cache_path`.")
|
||||
|
||||
if training_args.should_log:
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user