Merge branch 'main' of https://github.com/JessicaOjo/lm-evaluation-harness into africamgsm

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_amh.yaml

 # Generated by utils.py
 dataset_name: amh
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_target: '{% if answer is not none %}{{answer[15:]}}{% else %}{{answer_number|string}}{% endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
 generation_kwargs:
   do_sample: false

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_yor.yaml

 # Generated by utils.py
 dataset_name: yor
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_target: '{% if answer is not none %}{{answer[16:]}}{% else %}{{answer_number|string}}{% endif %}'
 doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
 generation_kwargs:
   do_sample: false

lm_eval/tasks/afrimgsm/direct/direct_yaml

@@ -5,7 +5,7 @@ group: afrimgsm_direct
 dataset_path: masakhane/afrimgsm
 dataset_name: null  # Overridden by language-specific config.
 output_type: generate_until
-training_split: train
+# training_split: train
 test_split: test
 target_delimiter: ""
 generation_kwargs:

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+doc_to_target: '{% if answer is not none %}{{answer[15:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"ጥያቄ: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'ጥያቄ:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_amh

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_eng

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_ewe

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_fra

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_hau

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_ibo

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_kin

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_lin

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_lug

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_orm

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_sna

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_sot

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_swa

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_twi

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_wol

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_xho

lm_eval/tasks/afrimgsm/direct_native/afrimgsm_direct_native_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_target: '{% if answer is not none %}{{answer[16:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Ìbéèrè: "+question+"\nAnswer:"}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Ìbéèrè:'
+  - </s>
+  - <|im_end|>
+include: direct_native_yaml
+task: afrimgsm_direct_native_yor