Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bug-fix] Text classifiation config #1545

Merged
merged 2 commits into from
May 5, 2023
Merged

[Bug-fix] Text classifiation config #1545

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4128b9e
[Bug-fix] Text classifiation config
KSGulin May 4, 2023
e28500e
Merge branch 'main' into fix_tc_config
KSGulin May 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions src/sparseml/transformers/text_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -497,6 +497,7 @@ def compute_metrics(p: EvalPrediction):
label_list=label_list,
model=model,
num_labels=num_labels,
config=config,
)
id_to_label = {id_: label for label, id_ in label_to_id.items()}

Expand Down Expand Up @@ -754,7 +755,7 @@ def _get_tokenized_and_preprocessed_raw_datasets(
# Some models have set the order of the labels to use, so let's make sure
# we do use it
label_to_id = _get_label_to_id(
data_args, is_regression, label_list, model, num_labels
data_args, is_regression, label_list, model, num_labels, config=config
)

if label_to_id is not None:
Expand Down Expand Up @@ -842,15 +843,16 @@ def preprocess_function(examples):
return tokenized_datasets, raw_datasets


def _get_label_to_id(data_args, is_regression, label_list, model, num_labels):
def _get_label_to_id(data_args, is_regression, label_list, model, num_labels, config):
label_to_id = None
config = model.config if model else config
if (
model.config.label2id != PretrainedConfig(num_labels=num_labels).label2id
config.label2id != PretrainedConfig(num_labels=num_labels).label2id
and data_args.task_name is not None
and not is_regression
):
# Some have all caps in their config, some don't.
label_name_to_id = {k.lower(): v for k, v in model.config.label2id.items()}
label_name_to_id = {k.lower(): v for k, v in config.label2id.items()}
if list(sorted(label_name_to_id.keys())) == list(sorted(label_list)):
label_to_id = {
i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)
Expand Down