Merge branch 'main' into humaneval

# Conflicts:
#	lm_eval/api/task.py

lm_eval/tasks/afrixnli/anli prompt/translate/afrixnli_translate_yaml

+group:
+    - afrixnli
+    - afrixnli_translate
+dataset_path: masakhane/afrixnli-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+doc_to_text: "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither?\nAnswer:"
+# True = entailment
+# False = contradiction
+# Neither = neutral
+doc_to_target: !function utils.doc_to_target
+doc_to_choice:
+  - "True"
+  - "Neither"
+  - "False"
+should_decontaminate: true
+doc_to_decontamination_query: premise
+metric_list:
+  - metric: f1
+    aggregation: !function utils.weighted_f1_score
+    average: weighted
+    higher_is_better: True
+    ignore_case: true
+    ignore_punctuation: true
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 1.0

lm_eval/tasks/afrixnli/anli prompt/translate/afrixnli_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrixnli_translate_yaml
+task: afrixnli_translate_yor

lm_eval/tasks/afrixnli/anli prompt/translate/afrixnli_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_translate_yaml
+task: afrixnli_translate_zul

lm_eval/tasks/afrixnli/anli prompt/translate/utils.py

+from lm_eval.utils import weighted_f1_score
+
+
+def doc_to_target(doc):
+    replacements = {0: "True", 1: "Neither", 2: "False"}
+    return replacements[doc["label"]]

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_amh

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_eng

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_ewe

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_fra

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_hau

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_ibo

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_kin

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_lin

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_lug

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_orm

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_sna

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_sot

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_swa

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_twi

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_wol

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_xho