Modify label errors in catcola and paws-x (#2434)

* Modify label errors in catcola and paws

* Update version to 1.0 in pawsx_template_yaml

* add changelog

---------
Co-authored-by: Baber <baber@hey.com>

lm_eval/tasks/catalan_bench/catcola.yaml

@@ -5,7 +5,7 @@ training_split: train
 validation_split: validation
 test_split: null
 doc_to_text: "{{Sentence}}\nPregunta: Té sentit aquesta frase?\nResposta:"
-doc_to_target: label
+doc_to_target: Label
 doc_to_choice: ["no", "sí"]
 metric_list:
   - metric: mcc

lm_eval/tasks/paws-x/README.md

@@ -77,3 +77,7 @@ If other tasks on this dataset are already supported:
 * [ ] Is the "Main" variant of this task clearly denoted?
 * [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
 * [ ] Have you noted which, if any, published evaluation setups are matched by this variant?
+
+### Changelog
+
+* v1 (2024-11-05) PR #2434 corrected doc_to_choice labels to the correct order

lm_eval/tasks/paws-x/paws_de.yaml

 # Generated by utils.py
 dataset_name: de
-doc_to_choice: '{{[sentence1+", richtig? Ja, "+sentence2, sentence1+", richtig? Nein,
+doc_to_choice: '{{[sentence1+", richtig? Nein, "+sentence2, sentence1+", richtig? Ja,
   "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml

lm_eval/tasks/paws-x/paws_en.yaml

 # Generated by utils.py
 dataset_name: en
-doc_to_choice: '{{[sentence1+", right? Yes, "+sentence2, sentence1+", right? No, "+sentence2]}}'
+doc_to_choice: '{{[sentence1+", right? No, "+sentence2, sentence1+", right? Yes, "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml
 task: paws_en

lm_eval/tasks/paws-x/paws_es.yaml

 # Generated by utils.py
 dataset_name: es
-doc_to_choice: '{{[sentence1+", verdad? Sí, "+sentence2, sentence1+", verdad? No,
+doc_to_choice: '{{[sentence1+", verdad? No, "+sentence2, sentence1+", verdad? Sí,
   "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml

lm_eval/tasks/paws-x/paws_fr.yaml

 # Generated by utils.py
 dataset_name: fr
-doc_to_choice: '{{[sentence1+", n''est-ce pas? Oui, "+sentence2, sentence1+", n''est-ce
-  pas? No, "+sentence2]}}'
+doc_to_choice: '{{[sentence1+", n''est-ce pas? Non, "+sentence2, sentence1+", n''est-ce
+  pas? Oui, "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml
 task: paws_fr

lm_eval/tasks/paws-x/paws_ja.yaml

 # Generated by utils.py
 dataset_name: ja
-doc_to_choice: '{{[sentence1+", ですね? はい, "+sentence2, sentence1+", ですね? いいえ, "+sentence2]}}'
+doc_to_choice: '{{[sentence1+", ですね? いいえ, "+sentence2, sentence1+", ですね? はい, "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml
 task: paws_ja

lm_eval/tasks/paws-x/paws_ko.yaml

 # Generated by utils.py
 dataset_name: ko
-doc_to_choice: '{{[sentence1+", 맞죠? 예, "+sentence2, sentence1+", 맞죠? 아니요, "+sentence2]}}'
+doc_to_choice: '{{[sentence1+", 맞죠? 아니요, "+sentence2, sentence1+", 맞죠? 예, "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml
 task: paws_ko

lm_eval/tasks/paws-x/paws_zh.yaml

 # Generated by utils.py
 dataset_name: zh
-doc_to_choice: '{{[sentence1+", 对吧? 是, "+sentence2, sentence1+", 对吧? 不是, "+sentence2]}}'
+doc_to_choice: '{{[sentence1+", 对吧? 不是, "+sentence2, sentence1+", 对吧? 是, "+sentence2]}}'
 doc_to_text: ''
 include: pawsx_template_yaml
 task: paws_zh

lm_eval/tasks/paws-x/pawsx_template_yaml

@@ -16,4 +16,4 @@ metric_list:
     aggregation: mean
     higher_is_better: true
 metadata:
-  version: 0.0
+  version: 1.0