Making hardcoded few shots compatible with the chat template mechanism (#1895)

* init test 1

* fix

* this format seems to be working - need to update all other tasks with the new format

* bbh with few shot format

* fix fewshot bbh

* add mmlu flan cot

* samples of cot

* kmmlu

* fix gsm8k

* update keys for mmlu

* minerva math

* bbh

* fix

* fix samples

* small fixes to templates

* last prompt format change

* fixing prompt

* fixed minerva math format

* rm accidental commited file

* added doc for few shot samples

* Update lm_eval/loggers/evaluation_tracker.py

* Update lm_eval/loggers/evaluation_tracker.py

* Update docs/new_task_guide.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* added check in sampler per code review

* added the system from a function, plus an example in minerva math

* style

* Apply suggestions from code review
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* fix unit tests 1

* forcing use of test split

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

lm_eval/tasks/bbh/fewshot/logical_deduction_five_objects.yaml

-"dataset_name": "logical_deduction_five_objects"
-"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
-"doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_logical_deduction_five_objects"
+dataset_name: logical_deduction_five_objects
+description: 'A logical deduction task which requires deducing the order of a sequence
+  of objects.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished
+      above Amy. Eli finished below Amy.
+
+      Options:
+
+      (A) Amy finished last
+
+      (B) Eli finished last
+
+      (C) Eve finished last'
+    target: (B)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a white book, a green book, and an orange
+      book. The green book is to the right of the white book. The orange book is the
+      rightmost.
+
+      Options:
+
+      (A) The white book is the leftmost
+
+      (B) The green book is the leftmost
+
+      (C) The orange book is the leftmost'
+    target: (A)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a red book, a gray book, and a white book.
+      The white book is to the left of the gray book. The red book is the second from
+      the left.
+
+      Options:
+
+      (A) The red book is the leftmost
+
+      (B) The gray book is the leftmost
+
+      (C) The white book is the leftmost'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_logical_deduction_five_objects

lm_eval/tasks/bbh/fewshot/logical_deduction_seven_objects.yaml

-"dataset_name": "logical_deduction_seven_objects"
-"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
-"doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_logical_deduction_seven_objects"
+dataset_name: logical_deduction_seven_objects
+description: 'A logical deduction task which requires deducing the order of a sequence
+  of objects.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished
+      above Amy. Eli finished below Amy.
+
+      Options:
+
+      (A) Amy finished last
+
+      (B) Eli finished last
+
+      (C) Eve finished last'
+    target: (B)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a white book, a green book, and an orange
+      book. The green book is to the right of the white book. The orange book is the
+      rightmost.
+
+      Options:
+
+      (A) The white book is the leftmost
+
+      (B) The green book is the leftmost
+
+      (C) The orange book is the leftmost'
+    target: (A)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a red book, a gray book, and a white book.
+      The white book is to the left of the gray book. The red book is the second from
+      the left.
+
+      Options:
+
+      (A) The red book is the leftmost
+
+      (B) The gray book is the leftmost
+
+      (C) The white book is the leftmost'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_logical_deduction_seven_objects

lm_eval/tasks/bbh/fewshot/logical_deduction_three_objects.yaml

-"dataset_name": "logical_deduction_three_objects"
-"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
-"doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_logical_deduction_three_objects"
+dataset_name: logical_deduction_three_objects
+description: 'A logical deduction task which requires deducing the order of a sequence
+  of objects.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished
+      above Amy. Eli finished below Amy.
+
+      Options:
+
+      (A) Amy finished last
+
+      (B) Eli finished last
+
+      (C) Eve finished last'
+    target: (B)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a white book, a green book, and an orange
+      book. The green book is to the right of the white book. The orange book is the
+      rightmost.
+
+      Options:
+
+      (A) The white book is the leftmost
+
+      (B) The green book is the leftmost
+
+      (C) The orange book is the leftmost'
+    target: (A)
+  - input: 'The following paragraphs each describe a set of three objects arranged
+      in a fixed order. The statements are logically consistent within each paragraph.
+      On a shelf, there are three books: a red book, a gray book, and a white book.
+      The white book is to the left of the gray book. The red book is the second from
+      the left.
+
+      Options:
+
+      (A) The red book is the leftmost
+
+      (B) The gray book is the leftmost
+
+      (C) The white book is the leftmost'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_logical_deduction_three_objects

lm_eval/tasks/bbh/fewshot/movie_recommendation.yaml

-"dataset_name": "movie_recommendation"
-"description": "Recommend movies similar to the given list of movies.\n\n"
-"doc_to_text": "Q: Find a movie similar to Star Wars Episode IV - A New Hope, Indiana Jones and the Last Crusade, Star Wars Episode V - The Empire Strikes Back, The Big Lebowski:\nOptions:\n(A) Tetsuo\n(B) the Ironman\n(C) The Princess Bride\n(D) The Barkley Marathons The Race That Eats Its Young\n(E) Bug\nA: (C)\n\nQ: Find a movie similar to Twister, The Silence of the Lambs, Independence Day, Braveheart:\nOptions:\n(A) They Shoot Horses\n(B) Don't They\n(C) Forrest Gump\n(D) The Salton Sea\n(E) Extreme Days\nA: (C)\n\nQ: Find a movie similar to Minority Report, Total Recall, Inside Out, Forrest Gump:\nOptions:\n(A) Phenomena\n(B) Lilting\n(C) Catwoman\n(D) Edge of Tomorrow\nA: (D)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_movie_recommendation"
+dataset_name: movie_recommendation
+description: 'Recommend movies similar to the given list of movies.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Find a movie similar to Star Wars Episode IV - A New Hope, Indiana Jones
+      and the Last Crusade, Star Wars Episode V - The Empire Strikes Back, The Big
+      Lebowski:
+
+      Options:
+
+      (A) Tetsuo
+
+      (B) the Ironman
+
+      (C) The Princess Bride
+
+      (D) The Barkley Marathons The Race That Eats Its Young
+
+      (E) Bug'
+    target: (C)
+  - input: 'Find a movie similar to Twister, The Silence of the Lambs, Independence
+      Day, Braveheart:
+
+      Options:
+
+      (A) They Shoot Horses
+
+      (B) Don''t They
+
+      (C) Forrest Gump
+
+      (D) The Salton Sea
+
+      (E) Extreme Days'
+    target: (C)
+  - input: 'Find a movie similar to Minority Report, Total Recall, Inside Out, Forrest
+      Gump:
+
+      Options:
+
+      (A) Phenomena
+
+      (B) Lilting
+
+      (C) Catwoman
+
+      (D) Edge of Tomorrow'
+    target: (D)
+include: _fewshot_template_yaml
+task: bbh_fewshot_movie_recommendation

lm_eval/tasks/bbh/fewshot/multistep_arithmetic_two.yaml

-"dataset_name": "multistep_arithmetic_two"
-"description": "Solve multi-step arithmetic problems.\n\n"
-"doc_to_text": "Q: ((-5 + 9 * -4 - 0) * (4 + -7 + 0 * -5)) =\nA: 123\n\nQ: ((-9 * 7 * 7 * -9) + (4 * -9 - 8 - -4)) =\nA: 3929\n\nQ: ((-3 + 5 * 8 * -4) - (9 - 8 * -7 + -9)) =\nA: -219\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_multistep_arithmetic_two"
+dataset_name: multistep_arithmetic_two
+description: 'Solve multi-step arithmetic problems.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: ((-5 + 9 * -4 - 0) * (4 + -7 + 0 * -5)) =
+    target: '123'
+  - input: ((-9 * 7 * 7 * -9) + (4 * -9 - 8 - -4)) =
+    target: '3929'
+  - input: ((-3 + 5 * 8 * -4) - (9 - 8 * -7 + -9)) =
+    target: '-219'
+include: _fewshot_template_yaml
+task: bbh_fewshot_multistep_arithmetic_two

lm_eval/tasks/bbh/fewshot/navigate.yaml

-"dataset_name": "navigate"
-"description": "Given a series of navigation instructions, determine whether one would end up back at the starting point.\n\n"
-"doc_to_text": "Q: If you follow these instructions, do you return to the starting point? Turn left. Turn around. Turn left. Take 7 steps. Take 2 steps. Take 4 steps. Take 8 steps.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Turn around. Take 1 step. Take 6 steps. Turn around. Take 6 steps. Take 9 steps. Take 1 step.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Always face forward. Take 2 steps right. Take 9 steps left. Take 7 steps right.\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_navigate"
+dataset_name: navigate
+description: 'Given a series of navigation instructions, determine whether one would
+  end up back at the starting point.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'If you follow these instructions, do you return to the starting point?
+      Turn left. Turn around. Turn left. Take 7 steps. Take 2 steps. Take 4 steps.
+      Take 8 steps.
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'No'
+  - input: 'If you follow these instructions, do you return to the starting point?
+      Turn around. Take 1 step. Take 6 steps. Turn around. Take 6 steps. Take 9 steps.
+      Take 1 step.
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'No'
+  - input: 'If you follow these instructions, do you return to the starting point?
+      Always face forward. Take 2 steps right. Take 9 steps left. Take 7 steps right.
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'Yes'
+include: _fewshot_template_yaml
+task: bbh_fewshot_navigate

lm_eval/tasks/bbh/fewshot/object_counting.yaml

-"dataset_name": "object_counting"
-"description": "Questions that involve enumerating objects and asking the model to count them.\n\n"
-"doc_to_text": "Q: I have a blackberry, a clarinet, a nectarine, a plum, a strawberry, a banana, a flute, an orange, and a violin. How many fruits do I have?\nA: 6\n\nQ: I have an orange, a raspberry, two peaches, a blackberry, an apple, a grape, a nectarine, and three plums. How many fruits do I have?\nA: 11\n\nQ: I have a lettuce head, a head of broccoli, an onion, a stalk of celery, two carrots, a garlic, and a yam. How many vegetables do I have?\nA: 8\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_object_counting"
+dataset_name: object_counting
+description: 'Questions that involve enumerating objects and asking the model to count
+  them.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: I have a blackberry, a clarinet, a nectarine, a plum, a strawberry, a banana,
+      a flute, an orange, and a violin. How many fruits do I have?
+    target: '6'
+  - input: I have an orange, a raspberry, two peaches, a blackberry, an apple, a grape,
+      a nectarine, and three plums. How many fruits do I have?
+    target: '11'
+  - input: I have a lettuce head, a head of broccoli, an onion, a stalk of celery,
+      two carrots, a garlic, and a yam. How many vegetables do I have?
+    target: '8'
+include: _fewshot_template_yaml
+task: bbh_fewshot_object_counting

lm_eval/tasks/bbh/fewshot/penguins_in_a_table.yaml

-"dataset_name": "penguins_in_a_table"
-"description": "Answer questions about a table of penguins and their attributes.\n\n"
-"doc_to_text": "Q: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  We now add a penguin to the table:\nJames, 12, 90, 12\nHow many penguins are less than 8 years old?\nOptions:\n(A) 1\n(B) 2\n(C) 3\n(D) 4\n(E) 5\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  Which is the youngest penguin?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  What is the name of the second penguin sorted by alphabetic order?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (D)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_penguins_in_a_table"
+dataset_name: penguins_in_a_table
+description: 'Answer questions about a table of penguins and their attributes.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Here is a table where the first line is a header and each subsequent line
+      is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard,
+      5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis
+      is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  We now add
+      a penguin to the table:
+
+      James, 12, 90, 12
+
+      How many penguins are less than 8 years old?
+
+      Options:
+
+      (A) 1
+
+      (B) 2
+
+      (C) 3
+
+      (D) 4
+
+      (E) 5'
+    target: (B)
+  - input: 'Here is a table where the first line is a header and each subsequent line
+      is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard,
+      5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis
+      is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  Which is
+      the youngest penguin?
+
+      Options:
+
+      (A) Louis
+
+      (B) Bernard
+
+      (C) Vincent
+
+      (D) Gwen
+
+      (E) James'
+    target: (B)
+  - input: 'Here is a table where the first line is a header and each subsequent line
+      is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard,
+      5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis
+      is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  What is
+      the name of the second penguin sorted by alphabetic order?
+
+      Options:
+
+      (A) Louis
+
+      (B) Bernard
+
+      (C) Vincent
+
+      (D) Gwen
+
+      (E) James'
+    target: (D)
+include: _fewshot_template_yaml
+task: bbh_fewshot_penguins_in_a_table

lm_eval/tasks/bbh/fewshot/reasoning_about_colored_objects.yaml

-"dataset_name": "reasoning_about_colored_objects"
-"description": "Answer extremely simple questions about the colors of objects on a surface.\n\n"
-"doc_to_text": "Q: On the nightstand, there is a red pencil, a purple mug, a burgundy keychain, a fuchsia teddy bear, a black plate, and a blue stress ball. What color is the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (E)\n\nQ: On the table, you see a bunch of objects arranged in a row: a purple paperclip, a pink stress ball, a brown keychain, a green scrunchiephone charger, a mauve fidget spinner, and a burgundy pen. What is the color of the object directly to the right of the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (F)\n\nQ: On the nightstand, you see the following items arranged in a row: a teal plate, a burgundy keychain, a yellow scrunchiephone charger, an orange mug, a pink notebook, and a grey cup. How many non-orange items do you see to the left of the teal item?\nOptions:\n(A) zero\n(B) one\n(C) two\n(D) three\n(E) four\n(F) five\n(G) six\nA: (A)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_reasoning_about_colored_objects"
+dataset_name: reasoning_about_colored_objects
+description: 'Answer extremely simple questions about the colors of objects on a surface.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'On the nightstand, there is a red pencil, a purple mug, a burgundy keychain,
+      a fuchsia teddy bear, a black plate, and a blue stress ball. What color is the
+      stress ball?
+
+      Options:
+
+      (A) red
+
+      (B) orange
+
+      (C) yellow
+
+      (D) green
+
+      (E) blue
+
+      (F) brown
+
+      (G) magenta
+
+      (H) fuchsia
+
+      (I) mauve
+
+      (J) teal
+
+      (K) turquoise
+
+      (L) burgundy
+
+      (M) silver
+
+      (N) gold
+
+      (O) black
+
+      (P) grey
+
+      (Q) purple
+
+      (R) pink'
+    target: (E)
+  - input: 'On the table, you see a bunch of objects arranged in a row: a purple paperclip,
+      a pink stress ball, a brown keychain, a green scrunchiephone charger, a mauve
+      fidget spinner, and a burgundy pen. What is the color of the object directly
+      to the right of the stress ball?
+
+      Options:
+
+      (A) red
+
+      (B) orange
+
+      (C) yellow
+
+      (D) green
+
+      (E) blue
+
+      (F) brown
+
+      (G) magenta
+
+      (H) fuchsia
+
+      (I) mauve
+
+      (J) teal
+
+      (K) turquoise
+
+      (L) burgundy
+
+      (M) silver
+
+      (N) gold
+
+      (O) black
+
+      (P) grey
+
+      (Q) purple
+
+      (R) pink'
+    target: (F)
+  - input: 'On the nightstand, you see the following items arranged in a row: a teal
+      plate, a burgundy keychain, a yellow scrunchiephone charger, an orange mug,
+      a pink notebook, and a grey cup. How many non-orange items do you see to the
+      left of the teal item?
+
+      Options:
+
+      (A) zero
+
+      (B) one
+
+      (C) two
+
+      (D) three
+
+      (E) four
+
+      (F) five
+
+      (G) six'
+    target: (A)
+include: _fewshot_template_yaml
+task: bbh_fewshot_reasoning_about_colored_objects

lm_eval/tasks/bbh/fewshot/ruin_names.yaml

-"dataset_name": "ruin_names"
-"description": "Select the humorous edit that 'ruins' the input movie or musical artist name.\n\n"
-"doc_to_text": "Q: Which of the following is a humorous edit of this artist or movie name: 'whitesnake'?\nOptions:\n(A) whitesnape\n(B) whitesnapke\n(C) whitesnuake\n(D) mwhitesnake\nA: (A)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'one of our dinosaurs is missing'?\nOptions:\n(A) ofne of our dinosaurs is missing\n(B) one af our dinosaurs is missing\n(C) one of our dinosaurs is pissing\n(D) one of our dinosaur is missing\nA: (C)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'counting crows'?\nOptions:\n(A) countingy crows\n(B) counting cows\n(C) courting crows\n(D) coutnting crows\nA: (B)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_ruin_names"
+dataset_name: ruin_names
+description: 'Select the humorous edit that ''ruins'' the input movie or musical artist
+  name.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Which of the following is a humorous edit of this artist or movie name:
+      ''whitesnake''?
+
+      Options:
+
+      (A) whitesnape
+
+      (B) whitesnapke
+
+      (C) whitesnuake
+
+      (D) mwhitesnake'
+    target: (A)
+  - input: 'Which of the following is a humorous edit of this artist or movie name:
+      ''one of our dinosaurs is missing''?
+
+      Options:
+
+      (A) ofne of our dinosaurs is missing
+
+      (B) one af our dinosaurs is missing
+
+      (C) one of our dinosaurs is pissing
+
+      (D) one of our dinosaur is missing'
+    target: (C)
+  - input: 'Which of the following is a humorous edit of this artist or movie name:
+      ''counting crows''?
+
+      Options:
+
+      (A) countingy crows
+
+      (B) counting cows
+
+      (C) courting crows
+
+      (D) coutnting crows'
+    target: (B)
+include: _fewshot_template_yaml
+task: bbh_fewshot_ruin_names

lm_eval/tasks/bbh/fewshot/salient_translation_error_detection.yaml

-"dataset_name": "salient_translation_error_detection"
-"description": "Detect the type of error in an English translation of a German source sentence.\n\n"
-"doc_to_text": "Q: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: In der Liste der Baudenkmale in Lenzen (Elbe) sind alle Baudenkmale der brandenburgischen Stadt Lenzen (Elbe) und ihrer Ortsteile aufgelistet.\nTranslation: In the list of architectural monuments in Lenzen all architectural monuments of the Brandenburg city of Lenzen and its districts are listed.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (D)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Auf dieser Seite sind die Baudenkmäler der oberbayerischen Großen Kreisstadt Landsberg am Lech zusammengestellt.\nTranslation: On this page are compiled the architectural monuments of the town of Landsberg am Lech.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (E)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Łeba ist eine Kleinstadt und ein Badeort im Powiat Lęborski der polnischen Woiwodschaft Pommern.\nTranslation: Eba is not a small town and seaside resort in the Powiat Léborski county of the Pomeranian Voivodeship of Poland.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_salient_translation_error_detection"
+dataset_name: salient_translation_error_detection
+description: 'Detect the type of error in an English translation of a German source
+  sentence.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'The following translations from German to English contain a particular
+      error. That error will be one of the following types: Named Entities: An entity
+      (names, places, locations, etc.) is changed to a different entity. Numerical
+      Values: Numerical values (ordinals or cardinals), dates, and/or units are changed.
+      Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are
+      changed. Negation or Antonyms: Introduce or remove a negation or change comparatives
+      to their antonyms. Facts: Trivial factual errors not pertaining to the above
+      classes are introduced in the translations. Dropped Content: A significant clause
+      in the translation is removed. Please identify that error.  Source: In der Liste
+      der Baudenkmale in Lenzen (Elbe) sind alle Baudenkmale der brandenburgischen
+      Stadt Lenzen (Elbe) und ihrer Ortsteile aufgelistet.
+
+      Translation: In the list of architectural monuments in Lenzen all architectural
+      monuments of the Brandenburg city of Lenzen and its districts are listed.
+
+      The translation contains an error pertaining to
+
+      Options:
+
+      (A) Modifiers or Adjectives
+
+      (B) Numerical Values
+
+      (C) Negation or Antonyms
+
+      (D) Named Entities
+
+      (E) Dropped Content
+
+      (F) Facts'
+    target: (D)
+  - input: "The following translations from German to English contain a particular\
+      \ error. That error will be one of the following types: Named Entities: An entity\
+      \ (names, places, locations, etc.) is changed to a different entity. Numerical\
+      \ Values: Numerical values (ordinals or cardinals), dates, and/or units are\
+      \ changed. Modifiers or Adjectives: The modifiers and adjectives pertaining\
+      \ to a noun are changed. Negation or Antonyms: Introduce or remove a negation\
+      \ or change comparatives to their antonyms. Facts: Trivial factual errors not\
+      \ pertaining to the above classes are introduced in the translations. Dropped\
+      \ Content: A significant clause in the translation is removed. Please identify\
+      \ that error.  Source: Auf dieser Seite sind die Baudenkm\xE4ler der oberbayerischen\
+      \ Gro\xDFen Kreisstadt Landsberg am Lech zusammengestellt.\nTranslation: On\
+      \ this page are compiled the architectural monuments of the town of Landsberg\
+      \ am Lech.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers\
+      \ or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n\
+      (E) Dropped Content\n(F) Facts"
+    target: (E)
+  - input: "The following translations from German to English contain a particular\
+      \ error. That error will be one of the following types: Named Entities: An entity\
+      \ (names, places, locations, etc.) is changed to a different entity. Numerical\
+      \ Values: Numerical values (ordinals or cardinals), dates, and/or units are\
+      \ changed. Modifiers or Adjectives: The modifiers and adjectives pertaining\
+      \ to a noun are changed. Negation or Antonyms: Introduce or remove a negation\
+      \ or change comparatives to their antonyms. Facts: Trivial factual errors not\
+      \ pertaining to the above classes are introduced in the translations. Dropped\
+      \ Content: A significant clause in the translation is removed. Please identify\
+      \ that error.  Source: \u0141eba ist eine Kleinstadt und ein Badeort im Powiat\
+      \ L\u0119borski der polnischen Woiwodschaft Pommern.\nTranslation: Eba is not\
+      \ a small town and seaside resort in the Powiat L\xE9borski county of the Pomeranian\
+      \ Voivodeship of Poland.\nThe translation contains an error pertaining to\n\
+      Options:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or\
+      \ Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts"
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_salient_translation_error_detection

lm_eval/tasks/bbh/fewshot/snarks.yaml

-"dataset_name": "snarks"
-"description": "Determine which of two sentences is sarcastic.\n\nAccording to Cambridge University Dictionary, sarcasm is \"the use of remarks that clearly mean the opposite of what they say, made in order to hurt someone's feelings or to criticize something in a humorous way.\" Sarcastic sentences often contain satirical or ironic utterances, hyperboles, ambivalent or witty remarks.\n\n"
-"doc_to_text": "Q: Which statement is sarcastic?\nOptions:\n(A) Yes, because having interests and actively researching them is a huge waste\n(B) Yes, because having interests and actively researching them is a huge deal\nA: (A)\n\nQ: Which statement is sarcastic?\nOptions:\n(A) No one is going to disagree with you on this. Avoiding ad hominem attacks really help your case\n(B) No one is going to disagree with you on this. Ad hominem attacks really help your case\nA: (B)\n\nQ: Which statement is sarcastic?\nOptions:\n(A) Consistency in the league's punishments? What do you think this is supposed to be, politics?\n(B) Consistency in the league's punishments? What do you think this is supposed to be, moral?\nA: (A)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_snarks"
+dataset_name: snarks
+description: 'Determine which of two sentences is sarcastic.
+
+
+  According to Cambridge University Dictionary, sarcasm is "the use of remarks that
+  clearly mean the opposite of what they say, made in order to hurt someone''s feelings
+  or to criticize something in a humorous way." Sarcastic sentences often contain
+  satirical or ironic utterances, hyperboles, ambivalent or witty remarks.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Which statement is sarcastic?
+
+      Options:
+
+      (A) Yes, because having interests and actively researching them is a huge waste
+
+      (B) Yes, because having interests and actively researching them is a huge deal'
+    target: (A)
+  - input: 'Which statement is sarcastic?
+
+      Options:
+
+      (A) No one is going to disagree with you on this. Avoiding ad hominem attacks
+      really help your case
+
+      (B) No one is going to disagree with you on this. Ad hominem attacks really
+      help your case'
+    target: (B)
+  - input: 'Which statement is sarcastic?
+
+      Options:
+
+      (A) Consistency in the league''s punishments? What do you think this is supposed
+      to be, politics?
+
+      (B) Consistency in the league''s punishments? What do you think this is supposed
+      to be, moral?'
+    target: (A)
+include: _fewshot_template_yaml
+task: bbh_fewshot_snarks

lm_eval/tasks/bbh/fewshot/sports_understanding.yaml

-"dataset_name": "sports_understanding"
-"description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n\n"
-"doc_to_text": "Q: Is the following sentence plausible? \"Bam Adebayo scored a reverse layup in the Western Conference Finals.\"\nA: yes\n\nQ: Is the following sentence plausible? \"Santi Cazorla scored a touchdown.\"\nA: no\n\nQ: Is the following sentence plausible? \"DeMar DeRozan was called for the goal tend.\"\nA: yes\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_sports_understanding"
+dataset_name: sports_understanding
+description: 'Determine whether an artificially constructed sentence relating to sports
+  is plausible or not.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: Is the following sentence plausible? "Bam Adebayo scored a reverse layup
+      in the Western Conference Finals."
+    target: 'yes'
+  - input: Is the following sentence plausible? "Santi Cazorla scored a touchdown."
+    target: 'no'
+  - input: Is the following sentence plausible? "DeMar DeRozan was called for the
+      goal tend."
+    target: 'yes'
+include: _fewshot_template_yaml
+task: bbh_fewshot_sports_understanding

lm_eval/tasks/bbh/fewshot/temporal_sequences.yaml

-"dataset_name": "temporal_sequences"
-"description": "Task description: Answer questions about which times certain events could have occurred.\n\n"
-"doc_to_text": "Q: Today, Emily went to the museum. Between what times could they have gone?\nWe know that:\nEmily woke up at 1pm.\nElizabeth saw Emily reading at the library from 2pm to 4pm.\nJessica saw Emily watching a movie at the theater from 4pm to 5pm.\nLeslie saw Emily waiting at the airport from 5pm to 6pm.\nWilliam saw Emily buying clothes at the mall from 6pm to 7pm.\nThe museum was closed after 7pm.\nBetween what times could Emily have gone to the museum?\nOptions:\n(A) 1pm to 2pm\n(B) 6pm to 7pm\n(C) 5pm to 6pm\n(D) 2pm to 4pm\nA: (A)\n\nQ: Today, Elizabeth went to the amusement park. Between what times could they have gone?\nWe know that:\nElizabeth woke up at 7am.\nDavid saw Elizabeth fixing their computer at the electronic store from 1pm to 2pm.\nSarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.\nSusan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.\nAndrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.\nEmily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.\nThe amusement park was closed after 10pm.\nBetween what times could Elizabeth have gone to the amusement park?\nOptions:\n(A) 7am to 1pm\n(B) 9pm to 10pm\n(C) 1pm to 2pm\n(D) 3pm to 6pm\nA: (A)\n\nQ: Today, Tiffany went to the beach. Between what times could they have gone?\nWe know that:\nTiffany woke up at 5am.\nBetty saw Tiffany getting a coffee at the cafe from 5am to 6am.\nJessica saw Tiffany working at the office from 6am to 9am.\nJohn saw Tiffany stretching at a yoga studio from 9am to 12pm.\nSean saw Tiffany sitting on a rooftop from 12pm to 2pm.\nSarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.\nThe beach was closed after 4pm.\nBetween what times could Tiffany have gone to the beach?\nOptions:\n(A) 9am to 12pm\n(B) 12pm to 2pm\n(C) 5am to 6am\n(D) 3pm to 4pm\nA: (D)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_temporal_sequences"
+dataset_name: temporal_sequences
+description: 'Task description: Answer questions about which times certain events
+  could have occurred.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Today, Emily went to the museum. Between what times could they have gone?
+
+      We know that:
+
+      Emily woke up at 1pm.
+
+      Elizabeth saw Emily reading at the library from 2pm to 4pm.
+
+      Jessica saw Emily watching a movie at the theater from 4pm to 5pm.
+
+      Leslie saw Emily waiting at the airport from 5pm to 6pm.
+
+      William saw Emily buying clothes at the mall from 6pm to 7pm.
+
+      The museum was closed after 7pm.
+
+      Between what times could Emily have gone to the museum?
+
+      Options:
+
+      (A) 1pm to 2pm
+
+      (B) 6pm to 7pm
+
+      (C) 5pm to 6pm
+
+      (D) 2pm to 4pm'
+    target: (A)
+  - input: 'Today, Elizabeth went to the amusement park. Between what times could
+      they have gone?
+
+      We know that:
+
+      Elizabeth woke up at 7am.
+
+      David saw Elizabeth fixing their computer at the electronic store from 1pm to
+      2pm.
+
+      Sarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.
+
+      Susan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.
+
+      Andrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.
+
+      Emily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.
+
+      The amusement park was closed after 10pm.
+
+      Between what times could Elizabeth have gone to the amusement park?
+
+      Options:
+
+      (A) 7am to 1pm
+
+      (B) 9pm to 10pm
+
+      (C) 1pm to 2pm
+
+      (D) 3pm to 6pm'
+    target: (A)
+  - input: 'Today, Tiffany went to the beach. Between what times could they have gone?
+
+      We know that:
+
+      Tiffany woke up at 5am.
+
+      Betty saw Tiffany getting a coffee at the cafe from 5am to 6am.
+
+      Jessica saw Tiffany working at the office from 6am to 9am.
+
+      John saw Tiffany stretching at a yoga studio from 9am to 12pm.
+
+      Sean saw Tiffany sitting on a rooftop from 12pm to 2pm.
+
+      Sarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.
+
+      The beach was closed after 4pm.
+
+      Between what times could Tiffany have gone to the beach?
+
+      Options:
+
+      (A) 9am to 12pm
+
+      (B) 12pm to 2pm
+
+      (C) 5am to 6am
+
+      (D) 3pm to 4pm'
+    target: (D)
+include: _fewshot_template_yaml
+task: bbh_fewshot_temporal_sequences

lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_five_objects.yaml

-"dataset_name": "tracking_shuffled_objects_five_objects"
-"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
-"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_tracking_shuffled_objects_five_objects"
+dataset_name: tracking_shuffled_objects_five_objects
+description: 'A task requiring determining the final positions of a set of objects
+  given their initial positions and a description of a sequence of swaps.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire
+      has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Claire and Alice
+      swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls.
+      At the end of the game, Bob has the
+
+      Options:
+
+      (A) yellow ball
+
+      (B) blue ball
+
+      (C) pink ball'
+    target: (A)
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a white ball, Bob has a purple ball, and
+      Claire has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Bob and Alice swap
+      balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At
+      the end of the game, Alice has the
+
+      Options:
+
+      (A) white ball
+
+      (B) purple ball
+
+      (C) pink ball'
+    target: (C)
+  - input: 'Alice, Bob, and Claire are dancers at a square dance. At the start of
+      a song, they each have a partner: Alice is dancing with Lola, Bob is dancing
+      with Rodrigo, and Claire is dancing with Patrick.
+
+      Throughout the song, the dancers often trade partners. First, Alice and Bob
+      switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice
+      switch partners. At the end of the dance, Alice is dancing with
+
+      Options:
+
+      (A) Lola
+
+      (B) Rodrigo
+
+      (C) Patrick'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_tracking_shuffled_objects_five_objects

lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_seven_objects.yaml

-"dataset_name": "tracking_shuffled_objects_seven_objects"
-"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
-"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_tracking_shuffled_objects_seven_objects"
+dataset_name: tracking_shuffled_objects_seven_objects
+description: 'A task requiring determining the final positions of a set of objects
+  given their initial positions and a description of a sequence of swaps.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire
+      has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Claire and Alice
+      swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls.
+      At the end of the game, Bob has the
+
+      Options:
+
+      (A) yellow ball
+
+      (B) blue ball
+
+      (C) pink ball'
+    target: (A)
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a white ball, Bob has a purple ball, and
+      Claire has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Bob and Alice swap
+      balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At
+      the end of the game, Alice has the
+
+      Options:
+
+      (A) white ball
+
+      (B) purple ball
+
+      (C) pink ball'
+    target: (C)
+  - input: 'Alice, Bob, and Claire are dancers at a square dance. At the start of
+      a song, they each have a partner: Alice is dancing with Lola, Bob is dancing
+      with Rodrigo, and Claire is dancing with Patrick.
+
+      Throughout the song, the dancers often trade partners. First, Alice and Bob
+      switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice
+      switch partners. At the end of the dance, Alice is dancing with
+
+      Options:
+
+      (A) Lola
+
+      (B) Rodrigo
+
+      (C) Patrick'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_tracking_shuffled_objects_seven_objects

lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_three_objects.yaml

-"dataset_name": "tracking_shuffled_objects_three_objects"
-"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
-"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_tracking_shuffled_objects_three_objects"
+dataset_name: tracking_shuffled_objects_three_objects
+description: 'A task requiring determining the final positions of a set of objects
+  given their initial positions and a description of a sequence of swaps.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire
+      has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Claire and Alice
+      swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls.
+      At the end of the game, Bob has the
+
+      Options:
+
+      (A) yellow ball
+
+      (B) blue ball
+
+      (C) pink ball'
+    target: (A)
+  - input: 'Alice, Bob, and Claire are playing a game. At the start of the game, they
+      are each holding a ball: Alice has a white ball, Bob has a purple ball, and
+      Claire has a pink ball.
+
+      As the game progresses, pairs of players trade balls. First, Bob and Alice swap
+      balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At
+      the end of the game, Alice has the
+
+      Options:
+
+      (A) white ball
+
+      (B) purple ball
+
+      (C) pink ball'
+    target: (C)
+  - input: 'Alice, Bob, and Claire are dancers at a square dance. At the start of
+      a song, they each have a partner: Alice is dancing with Lola, Bob is dancing
+      with Rodrigo, and Claire is dancing with Patrick.
+
+      Throughout the song, the dancers often trade partners. First, Alice and Bob
+      switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice
+      switch partners. At the end of the dance, Alice is dancing with
+
+      Options:
+
+      (A) Lola
+
+      (B) Rodrigo
+
+      (C) Patrick'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_tracking_shuffled_objects_three_objects

lm_eval/tasks/bbh/fewshot/web_of_lies.yaml

-"dataset_name": "web_of_lies"
-"description": "Evaluate a random boolean function expressed as a word problem.\n\n"
-"doc_to_text": "Q: Question: Fidel tells the truth. Jerry says Fidel tells the truth. Vina says Jerry tells the truth. Millicent says Vina lies. Raymond says Millicent lies. Does Raymond tell the truth?\nA: Yes\n\nQ: Question: Kristian lies. Millie says Kristian lies. Maybelle says Millie tells the truth. Fidel says Maybelle lies. Leda says Fidel lies. Does Leda tell the truth?\nA: Yes\n\nQ: Question: Kristian tells the truth. Michaela says Kristian lies. Raymond says Michaela tells the truth. Osvaldo says Raymond tells the truth. Jamey says Osvaldo tells the truth. Does Jamey tell the truth?\nA: No\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_web_of_lies"
+dataset_name: web_of_lies
+description: 'Evaluate a random boolean function expressed as a word problem.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Question: Fidel tells the truth. Jerry says Fidel tells the truth. Vina
+      says Jerry tells the truth. Millicent says Vina lies. Raymond says Millicent
+      lies. Does Raymond tell the truth?'
+    target: 'Yes'
+  - input: 'Question: Kristian lies. Millie says Kristian lies. Maybelle says Millie
+      tells the truth. Fidel says Maybelle lies. Leda says Fidel lies. Does Leda tell
+      the truth?'
+    target: 'Yes'
+  - input: 'Question: Kristian tells the truth. Michaela says Kristian lies. Raymond
+      says Michaela tells the truth. Osvaldo says Raymond tells the truth. Jamey says
+      Osvaldo tells the truth. Does Jamey tell the truth?'
+    target: 'No'
+include: _fewshot_template_yaml
+task: bbh_fewshot_web_of_lies

lm_eval/tasks/bbh/fewshot/word_sorting.yaml

-"dataset_name": "word_sorting"
-"description": "Sort a list of words.\n\n"
-"doc_to_text": "Q: Sort the following words alphabetically: List: oven costume counterpart\nA: costume counterpart oven\n\nQ: Sort the following words alphabetically: List: hypochlorite ponderosa phone credulity\nA: credulity hypochlorite phone ponderosa\n\nQ: Sort the following words alphabetically: List: newt arson parthia seismography mugho aspect census\nA: arson aspect census mugho newt parthia seismography\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_word_sorting"
+dataset_name: word_sorting
+description: 'Sort a list of words.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Sort the following words alphabetically: List: oven costume counterpart'
+    target: costume counterpart oven
+  - input: 'Sort the following words alphabetically: List: hypochlorite ponderosa
+      phone credulity'
+    target: credulity hypochlorite phone ponderosa
+  - input: 'Sort the following words alphabetically: List: newt arson parthia seismography
+      mugho aspect census'
+    target: arson aspect census mugho newt parthia seismography
+include: _fewshot_template_yaml
+task: bbh_fewshot_word_sorting

lm_eval/tasks/gsm8k/gsm8k-cot.yaml

-group:
-  - chain_of_thought
-task: gsm8k_cot
-dataset_path: gsm8k
 dataset_name: main
-output_type: generate_until
-test_split: test
-doc_to_text: "Q: There are 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done, there will be 21 trees. How many trees did the grove workers plant today?\nA: There are 15 trees originally. Then there were 21 trees after some more were planted. So there must have been 21 - 15 = 6. The answer is 6.\n\n\
-Q: If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?\nA: There are originally 3 cars. 2 more cars arrive. 3 + 2 = 5. The answer is 5.\n\n\
-Q: Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?\nA: Originally, Leah had 32 chocolates. Her sister had 42. So in total they had 32 + 42 = 74. After eating 35, they had 74 - 35 = 39. The answer is 39.\n\n\
-Q: Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?\nA: Jason started with 20 lollipops. Then he had 12 after giving some to Denny. So he gave Denny 20 - 12 = 8. The answer is 8.\n\n\
-Q: Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?\nA: Shawn started with 5 toys. If he got 2 toys each from his mom and dad, then that is 4 more toys. 5 + 4 = 9. The answer is 9.\n\n\
-Q: There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?\nA: There were originally 9 computers. For each of 4 days, 5 more computers were added. So 5 * 4 = 20 computers were added. 9 + 20 is 29. The answer is 29.\n\n\
-Q: Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many golf balls did he have at the end of wednesday?\nA: Michael started with 58 golf balls. After losing 23 on tuesday, he had 58 - 23 = 35. After losing 2 more, he had 35 - 2 = 33 golf balls. The answer is 33.\n\n\
-Q: Olivia has $23. She bought five bagels for $3 each. How much money does she have left?\nA: Olivia had 23 dollars. 5 bagels for 3 dollars each will be 5 x 3 = 15 dollars. So she has 23 - 15 dollars left. 23 - 15 is 8. The answer is 8.\n\n\
-Q: {{question}}\nA:"
-doc_to_target: "{{answer.split('####')[-1].strip()}}"
+dataset_path: gsm8k
+doc_to_target: '{{answer.split(''####'')[-1].strip() if answer is defined else target}}'
+doc_to_text: 'Q: {{question}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - question: There are 15 trees in the grove. Grove workers will plant trees in the
+      grove today. After they are done, there will be 21 trees. How many trees did
+      the grove workers plant today?
+    target: There are 15 trees originally. Then there were 21 trees after some more
+      were planted. So there must have been 21 - 15 = 6. The answer is 6.
+  - question: If there are 3 cars in the parking lot and 2 more cars arrive, how many
+      cars are in the parking lot?
+    target: There are originally 3 cars. 2 more cars arrive. 3 + 2 = 5. The answer
+      is 5.
+  - question: Leah had 32 chocolates and her sister had 42. If they ate 35, how many
+      pieces do they have left in total?
+    target: Originally, Leah had 32 chocolates. Her sister had 42. So in total they
+      had 32 + 42 = 74. After eating 35, they had 74 - 35 = 39. The answer is 39.
+  - question: Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12
+      lollipops. How many lollipops did Jason give to Denny?
+    target: Jason started with 20 lollipops. Then he had 12 after giving some to Denny.
+      So he gave Denny 20 - 12 = 8. The answer is 8.
+  - question: Shawn has five toys. For Christmas, he got two toys each from his mom and
+      dad. How many toys does he have now?
+    target: Shawn started with 5 toys. If he got 2 toys each from his mom and dad,
+      then that is 4 more toys. 5 + 4 = 9. The answer is 9.
+  - question: There were nine computers in the server room. Five more computers were
+      installed each day, from monday to thursday. How many computers are now in the
+      server room?
+    target: There were originally 9 computers. For each of 4 days, 5 more computers
+      were added. So 5 * 4 = 20 computers were added. 9 + 20 is 29. The answer is
+      29.
+  - question: Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday,
+      he lost 2 more. How many golf balls did he have at the end of wednesday?
+    target: Michael started with 58 golf balls. After losing 23 on tuesday, he had
+      58 - 23 = 35. After losing 2 more, he had 35 - 2 = 33 golf balls. The answer
+      is 33.
+  - question: Olivia has $23. She bought five bagels for $3 each. How much money does
+      she have left?
+    target: Olivia had 23 dollars. 5 bagels for 3 dollars each will be 5 x 3 = 15
+      dollars. So she has 23 - 15 dollars left. 23 - 15 is 8. The answer is 8.
+filter_list:
+- filter:
+  - function: regex
+    regex_pattern: The answer is (\-?[0-9\.\,]+).
+  - function: take_first
+  name: strict-match
+- filter:
+  - function: regex
+    group_select: -1
+    regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+  - function: take_first
+  name: flexible-extract
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Q:'
+  - </s>
+  - <|im_end|>
+group:
+- chain_of_thought
+metadata:
+  version: 3.0
 metric_list:
-  - metric: exact_match
-    aggregation: mean
+- aggregation: mean
   higher_is_better: true
   ignore_case: true
   ignore_punctuation: false
+  metric: exact_match
   regexes_to_ignore:
-      - ","
-      - "\\$"
-      - "(?s).*#### "
-      - "\\.$"
-generation_kwargs:
-  until:
-    - "Q:"
-    - "</s>"
-    - "<|im_end|>"
-  do_sample: false
+  - ','
+  - \$
+  - '(?s).*#### '
+  - \.$
+num_fewshot: 8
+output_type: generate_until
 repeats: 1
-num_fewshot: 0
-filter_list:
-  - name: "strict-match"
-    filter:
-      - function: "regex"
-        regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)."
-      - function: "take_first"
-  - name: "flexible-extract"
-    filter:
-      - function: "regex"
-        group_select: -1
-        regex_pattern: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
-      - function: "take_first"
-metadata:
-  version: 3.0
-  num_fewshot: 8
+task: gsm8k_cot
+test_split: test