Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrixnli_translate_yaml
+task: afrixnli_translate_orm_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sna_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sot_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrixnli_translate_yaml
+task: afrixnli_translate_swa_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrixnli_translate_yaml
+task: afrixnli_translate_twi_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrixnli_translate_yaml
+task: afrixnli_translate_wol_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrixnli_translate_yaml
+task: afrixnli_translate_xho_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_yaml

+tag: afrixnli_tt_tasks
+dataset_path: masakhane/afrixnli-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+fewshot_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/translate/prompt_2/afrixnli_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrixnli_translate_yaml
+task: afrixnli_translate_yor_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_translate_yaml
+task: afrixnli_translate_zul_prompt_2

lm_eval/tasks/afrixnli/translate/prompt_2/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/translate/prompt_3/afrixnli_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+doc_to_text: "Given the following premise and hypothesis in Amharic, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_amh_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: "Given the following premise and hypothesis in Ewe, identify if the premise\
+  \ entails, contradicts, or is neutral towards the hypothesis. Please respond with\
+  \ exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}} \n\
+  Hypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ewe_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+doc_to_text: "Given the following premise and hypothesis in French, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_fra_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "Given the following premise and hypothesis in Hausa, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_hau_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: "Given the following premise and hypothesis in Igbo, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ibo_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "Given the following premise and hypothesis in Kinyarwanda, identify\
+  \ if the premise entails, contradicts, or is neutral towards the hypothesis. Please\
+  \ respond with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_kin_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_text: "Given the following premise and hypothesis in Lingala, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lin_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "Given the following premise and hypothesis in Luganda, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lug_prompt_3

lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "Given the following premise and hypothesis in Oromo, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_orm_prompt_3