Merge branch 'big-refactor' of...

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into openai_completions

lm_eval/tasks/mgsm/en_cot/cot_yaml

+# 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: generate_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"

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/cot_yaml

@@ -4,7 +4,7 @@
 group: mgsm_cot_native
 dataset_path: juletxara/mgsm
 dataset_name: null  # Overridden by language-specific config.
-output_type: greedy_until
+output_type: generate_until
 training_split: train
 test_split: test
 target_delimiter: ""
@@ -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/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
+task: mgsm_bn_native_cot

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
+task: mgsm_de_native_cot

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_en.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[20+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else
   %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
-task: mgsm_en_direct
+task: mgsm_en_native_cot

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_es.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[22+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nRespuesta paso a paso:"}}{%
   else %}{{"Pregunta: "+question+"\nRespuesta paso a paso:"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
-task: mgsm_es_direct
+task: mgsm_es_native_cot

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_fr.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[25+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nRéponse étape par étape :"}}{%
   else %}{{"Question : "+question+"\nRéponse étape par étape :"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
-task: mgsm_fr_direct
+task: mgsm_fr_native_cot

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ja.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[10+1]}}{% else %}{{answer_nu
   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 %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
-task: mgsm_ja_direct
+task: mgsm_ja_native_cot

lm_eval/tasks/mgsm/native_cot/mgsm_cot_native_ru.yaml

@@ -4,11 +4,5 @@ doc_to_target: '{% if answer is not none %}{{answer[17+1]}}{% else %}{{answer_nu
   endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nПошаговоерешение:"}}{% else
   %}{{"Задача: "+question+"\nПошаговоерешение:"}}{% endif %}'
-filter:
-- function: regex
-  regex_pattern: The answer is (\-?[0-9\.\,]+)
-- function: take_first
-filter_list:
-- name: get-answer
 include: cot_yaml
-task: mgsm_ru_direct
+task: mgsm_ru_native_cot