src/backend/tasks/ifeval/ifeval.yaml

task: ifeval
dataset_path: wis-k/instruction-following-eval
dataset_name: null
output_type: generate_until
test_split: train
num_fewshot: 0
doc_to_text: prompt
doc_to_target: 0
generation_kwargs:
  until: []
  do_sample: false
  temperature: 0.0
  max_gen_toks: 1024
process_results: !function utils.process_results
metric_list:
  - metric: prompt_level_strict_acc
    aggregation: mean
    higher_is_better: true
  - metric: inst_level_strict_acc
    aggregation: !function utils.agg_inst_level_acc
    higher_is_better: true
  - metric: prompt_level_loose_acc
    aggregation: mean
    higher_is_better: true
  - metric: inst_level_loose_acc
    aggregation: !function utils.agg_inst_level_acc
    higher_is_better: true
metadata:
  - version: 1.0