SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Incorrect setting for num_beams in translation and summarization examples (#27519)

Browse Source 
* Remove the torch main_process_first context manager from TF examples

* Correctly set num_beams=1 in our examples, and add a guard in GenerationConfig.validate()

* Update src/transformers/generation/configuration_utils.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
This commit is contained in:
Matt
2023-11-15 18:18:54 +00:00
committed by GitHub
parent e6522e49a7
commit 2e72bbab2c
7 changed files with 53 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
examples/tensorflow/multiple-choice/run_swag.py
View File

@@ -415,13 +415,12 @@ def main():
if data_args.max_train_samples is not None:
max_train_samples = min(len(train_dataset), data_args.max_train_samples)
train_dataset = train_dataset.select(range(max_train_samples))
with training_args.main_process_first(desc="train dataset map pre-processing"):
train_dataset = train_dataset.map(
preprocess_function,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
)
train_dataset = train_dataset.map(
preprocess_function,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
)
if training_args.do_eval:
if "validation" not in raw_datasets:
@@ -430,13 +429,12 @@ def main():
if data_args.max_eval_samples is not None:
max_eval_samples = min(len(eval_dataset), data_args.max_eval_samples)
eval_dataset = eval_dataset.select(range(max_eval_samples))
with training_args.main_process_first(desc="validation dataset map pre-processing"):
eval_dataset = eval_dataset.map(
preprocess_function,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
)
eval_dataset = eval_dataset.map(
preprocess_function,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
)
if data_args.pad_to_max_length:
data_collator = DefaultDataCollator(return_tensors="np")