[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
This commit is contained in:
@@ -398,14 +398,16 @@ def main():
|
||||
raise ValueError("--do_train requires a train dataset")
|
||||
train_dataset = lm_datasets["train"]
|
||||
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 training_args.do_eval:
|
||||
if "validation" not in tokenized_datasets:
|
||||
raise ValueError("--do_eval requires a validation dataset")
|
||||
eval_dataset = lm_datasets["validation"]
|
||||
if data_args.max_eval_samples is not None:
|
||||
eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
|
||||
max_eval_samples = min(len(eval_dataset), data_args.max_eval_samples)
|
||||
eval_dataset = eval_dataset.select(range(max_eval_samples))
|
||||
|
||||
# Enable tensorboard only on the master node
|
||||
has_tensorboard = is_tensorboard_available()
|
||||
|
||||
Reference in New Issue
Block a user