[examples] max samples can't be bigger than the len of dataset (#16501)

* [examples] max samples can't be bigger than then len of dataset * do tf and flax
2022-03-30 12:33:16 -07:00
parent c4deb7b3ae
commit a73281e3e4
26 changed files with 154 additions and 77 deletions
--- a/examples/research_projects/wav2vec2/run_common_voice.py
+++ b/examples/research_projects/wav2vec2/run_common_voice.py
@@ -375,7 +375,8 @@ def main():
    )

    if data_args.max_train_samples is not None:
-        train_dataset = train_dataset.select(range(data_args.max_train_samples))
+        max_train_samples = min(len(train_dataset), data_args.max_train_samples)
+        train_dataset = train_dataset.select(range(max_train_samples))

    if data_args.max_val_samples is not None:
        eval_dataset = eval_dataset.select(range(data_args.max_val_samples))