merged with latest big-refactor

lm_eval/benchmarks/pythia.yaml → lm_eval/tasks/benchmarks/pythia.yaml

 group: pythia
 task:
   - lambada_openai
-  - wikitext
+  - logiqa
   - piqa
   - sciq
-  - wsc
+  - wikitext
   - winogrande
-  - arc
-  - logiqa
+  - wsc
+  - ai2_arc
   - blimp
   - hendrycksTest*

lm_eval/tasks/mgsm/native_cot/cot_yaml → lm_eval/tasks/mgsm/en_cot/cot_yaml

@@ -21,3 +21,9 @@ metric_list:
     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"

lm_eval/tasks/mgsm/en_cot/mgsm_bn_en-cot.yaml

+# Generated by utils.py
+dataset_name: bn
+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 %}{{"প্রশ্ন: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
+include: cot_yaml
+task: mgsm_bn_direct

lm_eval/tasks/mgsm/en_cot/mgsm_de_en-cot.yaml

+# Generated by utils.py
+dataset_name: de
+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 %}{{"Frage: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
+include: cot_yaml
+task: mgsm_de_direct

lm_eval/tasks/mgsm/en_cot/mgsm_en_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_es_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_fr_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_ja_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_ru_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_sw_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_te_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_th_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/en_cot/mgsm_zh_en-cot.yaml

+# 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

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_bn.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[16+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nধাপে ধাপে উত্তর:"}}{% else
   %}{{"প্রশ্ন: "+question+"\nধাপে ধাপে উত্তর:"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
 task: mgsm_bn_direct

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_de.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[28+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nSchritt-für-Schritt-Antwort:"}}{%
   else %}{{"Frage: "+question+"\nSchritt-für-Schritt-Antwort:"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
 task: mgsm_de_direct