scripts/bold_suite.py

import evaluate
from evaluate.evaluation_suite import SubTask


class Suite(evaluate.EvaluationSuite):
    def __init__(self, name):
        super().__init__(name)
        self.preprocessor = lambda x: {"text": x["text"].lower()}
        self.suite = [
            SubTask(
                task_type="text-classification",
                data="glue",
                subset="sst2",
                split="validation[:10]",
                args_for_task={
                    "metric": "accuracy",
                    "input_column": "sentence",
                    "label_column": "label",
                    "label_mapping": {
                        "LABEL_0": 0.0,
                        "LABEL_1": 1.0
                    }
                }
            ),
        ]


suite = Suite(
    name="AVID: LLM Evaluations – BOLD"
)
results = suite.run("EleutherAI/gpt-neo-125M")

print(results)