bangla_mmlu_test.yaml

task: bangla_mmlu
dataset_path: hishab/titulm-bangla-mmlu
dataset_name: all
description: "The following are multiple choice questions (with answers) about range of topics in Bangla"
test_split: test
fewshot_split: dev
fewshot_config:
  sampler: first_n
output_type: multiple_choice
doc_to_text: "{{question.strip()}} A. {{options[0]}} B. {{options[1]}} C. {{options[2]}} D. {{options[3]}} Answer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
  - metric: acc
    aggregation: mean
    higher_is_better: true
  - metric: acc_norm
    aggregation: mean
    higher_is_better: true