gsm8k_judge_1.yaml

tag:
  - math_word_problems
task: gsm8k
dataset_path: gsm8k
dataset_name: main
output_type: generate_until
training_split: train
fewshot_split: train
test_split: test
doc_to_text: "Solve the following math problem step by step. The last line of your response should be of the form Answer: $ANSWER (without quotes) where $ANSWER is the answer to the problem\n\nQuestion: {{question}}\nAnswer:"
doc_to_target: "{{answer}}" #" {{answer.split('### ')[-1].rstrip()}}"
metric_list:
  - metric: bypass
    aggregation: mean
generation_kwargs:
  until:
    - "Question:"
    - "</s>"
    - "<|im_end|>"
  do_sample: false
  temperature: 0.0
repeats: 1
num_fewshot: 5
#filter_list:
#  - name: "strict-match"
#    filter:
#      - function: "regex"
#        regex_pattern: "#### (\\-?[0-9\\.\\,]+)"
#      - function: "take_first"
#  - name: "flexible-extract"
#    filter:
#      - function: "regex"
#        group_select: -1
#        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
#      - function: "take_first"
metadata:
  version: 3.0