Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4

lm_eval/tasks/afrixnli/anli prompt/en-direct/afrixnli_en_direct_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_en_direct_yaml
+task: afrixnli_en_direct_zul

lm_eval/tasks/afrixnli/anli prompt/en-direct/utils.py

+from sklearn.metrics import f1_score
+
+
+def doc_to_target(doc):
+    replacements = {0: "True", 1: "Neither", 2: "False"}
+    return replacements[doc["label"]]
+
+
+def weighted_f1_score(items):
+    unzipped_list = list(zip(*items))
+    golds = unzipped_list[0]
+    preds = unzipped_list[1]
+    fscore = f1_score(golds, preds, average="weighted")
+    return fscore

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+doc_to_choice: '{{[premise+", ትክክል? አዎ, "+hypothesis,premise+", ትክክል? እንዲሁም, "+hypothesis,premise+",
+  ትክክል? አይ, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_amh

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+doc_to_choice: '{{[premise+", Right? Yes, "+hypothesis,premise+", Right? Also, "+hypothesis,premise+",
+  Right? No, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_eng

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+doc_to_choice: '{{[premise+", Esɔ gbe? Ɛ̃, "+hypothesis,premise+", Esɔ gbe? Hã, "+hypothesis,premise+",
+  Esɔ gbe? Ao, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_ewe

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+doc_to_choice: '{{[premise+", correct? Oui, "+hypothesis,premise+", correct? Aussi,
+  "+hypothesis,premise+", correct? Non, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_fra

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_choice: '{{[premise+", Daidai? Ee, "+hypothesis,premise+", Daidai? Haka kuma,
+  "+hypothesis,premise+", Daidai? A''a, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_hau

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_choice: '{{[premise+", Ziri ezi? Éè, "+hypothesis,premise+", Ziri ezi? Ọzọkwa,
+  "+hypothesis,premise+", Ziri ezi? Mba, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_ibo

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_choice: '{{[premise+", Nibyo? Yego, "+hypothesis,premise+", Nibyo? Na none,
+  "+hypothesis,premise+", Nibyo? Oya, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_kin

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_choice: '{{[premise+", Malamu? Iyo, "+hypothesis,premise+", Malamu? Lisusu,
+  "+hypothesis,premise+", Malamu? Te, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_lin

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_choice: '{{[premise+", Kituufu? Yee, "+hypothesis,premise+", Kituufu? N’ekirala,
+  "+hypothesis,premise+", Kituufu? Nedda, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_lug

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_choice: '{{[premise+", Sirrii? Eeyyee, "+hypothesis,premise+", Sirrii? Akkasumas,
+  "+hypothesis,premise+", Sirrii? Lakki, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_orm

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+doc_to_choice: '{{[premise+", Chokwadi? Hongu, "+hypothesis,premise+", Chokwadi? Uye,
+  "+hypothesis,premise+", Chokwadi? Kwete, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_sna

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_choice: '{{[premise+", Nepile? E, "+hypothesis,premise+", Nepile? Hape, "+hypothesis,premise+",
+  Nepile? Tjhe, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_sot

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_choice: '{{[premise+", Sahihi? Ndiyo, "+hypothesis,premise+", Sahihi? Pia,
+  "+hypothesis,premise+", Sahihi? Hapana, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_swa

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_choice: '{{[premise+", Nifa? Aane, "+hypothesis,premise+", Nifa? Anaasɛ, "+hypothesis,premise+",
+  Nifa? Daabi, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_twi

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+doc_to_choice: '{{[premise+", Dëgg? Waaw, "+hypothesis,premise+", Dëgg? Itam, "+hypothesis,premise+",
+  Dëgg? Déet, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_wol

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+doc_to_choice: '{{[premise+", Ichanekile? Ewe, "+hypothesis,premise+", Ichanekile?
+  Kananjalo, "+hypothesis,premise+", Ichanekile? Hayi, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_xho

lm_eval/tasks/afrixnli/anli prompt/native-direct/afrixnli_native_direct_yaml

+group:
+    - xnli
+    - afrixnli
+    - afrixnli_native_direct
+dataset_path: masakhane/afrixnli
+dataset_name: null
+output_type: multiple_choice
+validation_split: validation
+test_split: test
+fewshot_split: validation
+doc_to_target: label
+doc_to_text: ""
+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/native-direct/afrixnli_native_direct_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_choice: '{{[premise+", Òótọ́? Bẹ́ẹ̀ni, "+hypothesis,premise+", Òótọ́? Àti pé,
+  "+hypothesis,premise+", Òótọ́? Rárá, "+hypothesis]}}'
+include: afrixnli_native_direct_yaml
+task: afrixnli_native_direct_yor