"...lm-evaluation-harness.git" did not exist on "057dc2d7e2188d6d12c9b5a77030e0adf1de5915"
Commit 0348ed97 authored by lintangsutawika's avatar lintangsutawika
Browse files

merged latest update

parents 451a1873 6769119f
# Generated by utils.py
dataset_name: en
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_en_direct
# Generated by utils.py
dataset_name: es
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Pregunta: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_es_direct
# Generated by utils.py
dataset_name: fr
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question : "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_fr_direct
# Generated by utils.py
dataset_name: ja
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"問題: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_ja_direct
# Generated by utils.py
dataset_name: ru
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Задача: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_ru_direct
# Generated by utils.py
dataset_name: sw
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Swali: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_sw_direct
# Generated by utils.py
dataset_name: te
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"ప్రశ్న: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_te_direct
# Generated by utils.py
dataset_name: th
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"โจทย์: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_th_direct
# Generated by utils.py
dataset_name: zh
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{% endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"问题: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_zh_direct
# This file will be included in the generated language-specific task configs.
# It doesn't have a yaml file extension as it is not meant to be imported directly
# by the harness.
group: mgsm_cot_native
dataset_path: juletxara/mgsm
dataset_name: null # Overridden by language-specific config.
output_type: greedy_until
training_split: train
test_split: test
target_delimiter: ""
generation_kwargs:
until:
- "\n\n"
- "\n"
do_sample: false
temperature: 0.0
target_delimiter: " "
metric_list:
- metric: exact_match
aggregation: mean
higher_is_better: true
ignore_case: true
ignore_punctuation: true
filter_list:
- name: "get-answer"
filter:
- function: "regex"
regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)"
- function: "take_first"
# Generated by utils.py
dataset_name: bn
doc_to_target: '{% if answer is not none %}{{answer[16+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nধাপে ধাপে উত্তর:"}}{% else
%}{{"প্রশ্ন: "+question+"\nধাপে ধাপে উত্তর:"}}{% endif %}'
include: cot_yaml
task: mgsm_bn_native_cot
# Generated by utils.py
dataset_name: de
doc_to_target: '{% if answer is not none %}{{answer[28+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nSchritt-für-Schritt-Antwort:"}}{%
else %}{{"Frage: "+question+"\nSchritt-für-Schritt-Antwort:"}}{% endif %}'
include: cot_yaml
task: mgsm_de_native_cot
# Generated by utils.py
dataset_name: en
doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else
%}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
include: cot_yaml
task: mgsm_en_native_cot
# Generated by utils.py
dataset_name: es
doc_to_target: '{% if answer is not none %}{{answer[22+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nRespuesta paso a paso:"}}{%
else %}{{"Pregunta: "+question+"\nRespuesta paso a paso:"}}{% endif %}'
include: cot_yaml
task: mgsm_es_native_cot
# Generated by utils.py
dataset_name: fr
doc_to_target: '{% if answer is not none %}{{answer[25+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nRéponse étape par étape :"}}{%
else %}{{"Question : "+question+"\nRéponse étape par étape :"}}{% endif %}'
include: cot_yaml
task: mgsm_fr_native_cot
# Generated by utils.py
dataset_name: ja
doc_to_target: '{% if answer is not none %}{{answer[10+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nステップごとの答え:"}}{% else %}{{"問題:
"+question+"\nステップごとの答え:"}}{% endif %}'
include: cot_yaml
task: mgsm_ja_native_cot
# Generated by utils.py
dataset_name: ru
doc_to_target: '{% if answer is not none %}{{answer[17+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nПошаговоерешение:"}}{% else
%}{{"Задача: "+question+"\nПошаговоерешение:"}}{% endif %}'
include: cot_yaml
task: mgsm_ru_native_cot
# Generated by utils.py
dataset_name: sw
doc_to_target: '{% if answer is not none %}{{answer[24+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nJibu la Hatua kwa Hatua:"}}{%
else %}{{"Swali: "+question+"\nJibu la Hatua kwa Hatua:"}}{% endif %}'
include: cot_yaml
task: mgsm_sw_native_cot
# Generated by utils.py
dataset_name: te
doc_to_target: '{% if answer is not none %}{{answer[18+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nదశలవారీగా సమాధానం:"}}{% else
%}{{"ప్రశ్న: "+question+"\nదశలవారీగా సమాధానం:"}}{% endif %}'
include: cot_yaml
task: mgsm_te_native_cot
# Generated by utils.py
dataset_name: th
doc_to_target: '{% if answer is not none %}{{answer[17+1]}}{% else %}{{answer_number|string}}{%
endif %}'
doc_to_text: '{% if answer is not none %}{{question+"\nคำตอบทีละขั้นตอน:"}}{% else
%}{{"โจทย์: "+question+"\nคำตอบทีละขั้นตอน:"}}{% endif %}'
include: cot_yaml
task: mgsm_th_native_cot
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment