Add files using upload-large-folder tool

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_2/afrimgsm_fra.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_yaml
+task: afrimgsm_fra_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_2/afrimgsm_ibo.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ibo
+include: afrimgsm_yaml
+task: afrimgsm_ibo_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_2/afrimgsm_sna.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sna
+include: afrimgsm_yaml
+task: afrimgsm_sna_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_2/afrimgsm_yaml

@@ -0,0 +1,34 @@
+tag:
+    - afrimgsm_tasks
+    - afrimgsm_tasks_prompt_1
+dataset_path: masakhane/afrimgsm
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: "Give direct numerical answers for the question provided. \n\nQuestion: {{question}} \nAnswer: "
+target_delimiter: ""
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 2.0

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_2/afrimgsm_yor.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: yor
+include: afrimgsm_yaml
+task: afrimgsm_yor_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_amh.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_yaml
+task: afrimgsm_amh_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_fra.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_yaml
+task: afrimgsm_fra_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_ibo.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ibo
+include: afrimgsm_yaml
+task: afrimgsm_ibo_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_lin.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lin
+include: afrimgsm_yaml
+task: afrimgsm_lin_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_lug.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lug
+include: afrimgsm_yaml
+task: afrimgsm_lug_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_sot.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sot
+include: afrimgsm_yaml
+task: afrimgsm_sot_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_swa.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: swa
+include: afrimgsm_yaml
+task: afrimgsm_swa_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_vai.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: vai
+include: afrimgsm_yaml
+task: afrimgsm_vai_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_xho.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: xho
+include: afrimgsm_yaml
+task: afrimgsm_xho_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_yor.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: yor
+include: afrimgsm_yaml
+task: afrimgsm_yor_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_zul.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: zul
+include: afrimgsm_yaml
+task: afrimgsm_zul_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_ewe.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_ewe_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_hau.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_hau_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_kin.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_kin_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_lug.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_lug_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_orm.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_orm_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_sot.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: sot
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_sot_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_swa.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: swa
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_swa_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_vai.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: vai
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_vai_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_wol.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: wol
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_wol_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_yaml

@@ -0,0 +1,33 @@
+tag:
+    - afrimgsm_tasks
+    - afrimgsm_tasks_prompt_4
+dataset_path: masakhane/afrimgsm
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+target_delimiter: ""
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 2.0

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_yor.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: yor
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_yor_prompt_4

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_amh.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: amh
+doc_to_text: "For mathematical questions provided in Amharic language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_yaml
+task: afrimgsm_amh_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_eng.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: eng
+doc_to_text: "For mathematical questions provided in English language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_yaml
+task: afrimgsm_eng_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_ewe.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: "For mathematical questions provided in Ewe language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_ewe_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_fra.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: fra
+doc_to_text: "For mathematical questions provided in French language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_fra_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_hau.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "For mathematical questions provided in Hausa language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_hau_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_ibo.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: "For mathematical questions provided in Igbo language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_ibo_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_kin.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "For mathematical questions provided in Kinyarwanda language. Supply\
+  \ the accurate numeric answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_kin_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_orm.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "For mathematical questions provided in Oromo language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_orm_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_sna.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: sna
+doc_to_text: "For mathematical questions provided in chiShona language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_yaml
+task: afrimgsm_sna_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_twi.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: twi
+doc_to_text: "For mathematical questions provided in Twi language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_twi_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_wol.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: wol
+doc_to_text: "For mathematical questions provided in Wolof language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_wol_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_xho.yaml

@@ -0,0 +1,7 @@
+# Generated by utils.py
+dataset_name: xho
+doc_to_text: "For mathematical questions provided in isiXhosa language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_yaml
+task: afrimgsm_xho_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_yaml

@@ -0,0 +1,33 @@
+tag:
+    - afrimgsm_tasks
+    - afrimgsm_tasks_prompt_5
+dataset_path: masakhane/afrimgsm
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+target_delimiter: ""
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 2.0

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct/prompt_5/afrimgsm_zul.yaml

@@ -0,0 +1,6 @@
+# Generated by utils.py
+dataset_name: zul
+doc_to_text: "For mathematical questions provided in Zulu language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_zul_prompt_5

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/afrimgsm_cot.yaml

@@ -0,0 +1,9 @@
+group: afrimgsm_cot-irokobench
+task:
+  - afrimgsm_cot_tasks
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 2

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_amh.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_amh_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_fra.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_fra_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_kin.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: kin
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_kin_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_lug.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lug
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_lug_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_orm.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: orm
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_orm_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_sna.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sna
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_sna_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_sot.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sot
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_sot_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_swa.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: swa
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_swa_prompt_1