Skip to content

[MNLI example] Prevent overwriting matched with mismatched metrics #16475

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

Merged
sgugger merged 2 commits into from
Mar 29, 2022
Merged

[MNLI example] Prevent overwriting matched with mismatched metrics #16475

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3e5bd4b
Prevent overwriting matched with mismatched metrics
eldarkurtic Mar 29, 2022
cccfcc0
Fix style
eldarkurtic Mar 29, 2022
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
8 changes: 7 additions & 1 deletion examples/pytorch/text-classification/run_glue.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -507,6 +507,7 @@ def compute_metrics(p: EvalPrediction):
if data_args.task_name == "mnli":
tasks.append("mnli-mm")
eval_datasets.append(raw_datasets["validation_mismatched"])
combined = {}

for eval_dataset, task in zip(eval_datasets, tasks):
metrics = trainer.evaluate(eval_dataset=eval_dataset)
Expand All @@ -516,8 +517,13 @@ def compute_metrics(p: EvalPrediction):
)
metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))

if task == "mnli-mm":
metrics = {k + "_mm": v for k, v in metrics.items()}
if "mnli" in task:
combined.update(metrics)
Comment on lines +520 to +523
Copy link
Collaborator

@sgugger sgugger Mar 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd regroup this slightly differently:

Suggested change
if task == "mnli-mm":
metrics = {k + "_mm": v for k, v in metrics.items()}
if "mnli" in task:
combined.update(metrics)
if task == "mnli-mm":
combined.update({k + "_mm": v for k, v in metrics.items()})
elif task == "mnli":
combined.update(metrics)

Copy link
Contributor Author

@eldarkurtic eldarkurtic Mar 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

With this regrouping, the trainer.log_metrics("eval", metrics) won't have the "_mm" , so the stdout will be the same as before (that's the main reason why keys in metrics are updated). Given this, should we still regroup and affect only the json log files, but not the stdout?

Copy link
Collaborator

@sgugger sgugger Mar 29, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah understood. LGTM as is then :-)


trainer.log_metrics("eval", metrics)
trainer.save_metrics("eval", metrics)
trainer.save_metrics("eval", combined if "mnli" in task else metrics)

if training_args.do_predict:
logger.info("*** Predict ***")
Expand Down