riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 18:22:34 +06:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Tidy Pytorch GLUE benchmark example (#23134)

Browse Source 
Migration to Evaluate for metric is not quite complete
This commit is contained in:
Robert Stone 2023-05-03 12:50:41 -07:00 committed by GitHub
parent b0a78091a5
commit b6933d76d2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
examples/pytorch/text-classification/run_glue.py
View File

@ -486,6 +486,8 @@ def main():
# Get the metric function # Get the metric function
if data_args.task_name is not None: if data_args.task_name is not None:
metric = evaluate.load("glue", data_args.task_name) metric = evaluate.load("glue", data_args.task_name)
elif is_regression:
metric = evaluate.load("mse")
else: else:
metric = evaluate.load("accuracy") metric = evaluate.load("accuracy")
@ -494,15 +496,10 @@ def main():
def compute_metrics(p: EvalPrediction): def compute_metrics(p: EvalPrediction):
preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions
preds = np.squeeze(preds) if is_regression else np.argmax(preds, axis=1) preds = np.squeeze(preds) if is_regression else np.argmax(preds, axis=1)
if data_args.task_name is not None: result = metric.compute(predictions=preds, references=p.label_ids)
result = metric.compute(predictions=preds, references=p.label_ids) if len(result) > 1:
if len(result) > 1: result["combined_score"] = np.mean(list(result.values())).item()
result["combined_score"] = np.mean(list(result.values())).item() return result
return result
elif is_regression:
return {"mse": ((preds - p.label_ids) ** 2).mean().item()}
else:
return {"accuracy": (preds == p.label_ids).astype(np.float32).mean().item()}
# Data collator will default to DataCollatorWithPadding when the tokenizer is passed to Trainer, so we change it if # Data collator will default to DataCollatorWithPadding when the tokenizer is passed to Trainer, so we change it if
# we already did the padding. # we already did the padding.