Merge branch 'EleutherAI:main' into main

lm_eval/tasks/bbh/cot_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: Let's think step by step.\n(0) At the start: Alice: yellow, Bob: blue, Claire: pink.\n(1) Claire and Alice swap balls: Alice: pink, Bob: blue, Claire: yellow.\n(2)  Alice and Bob swap balls: Alice: blue, Bob: pink, Claire: yellow.\n(3) Claire and Bob swap balls: Alice: blue, Bob: yellow, Claire: pink.\nAt the end of the game, Bob has the yellow ball. So the answer is (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: Let's think step by step.\n(0) At the start: Alice: white, Bob: purple, Claire: pink.\n(1) Bob and Alice swap balls: Alice: purple, Bob: white, Claire: pink.\n(2) Bob and Claire swap balls: Alice: purple, Bob: pink, Claire: white.\n(3) Bob and Alice swap balls: Alice: pink, Bob: purple, Claire: white.\nAt the end of the game, Alice has the pink ball. So the answer is (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: Let's think step by step.\n(0) At the start: Alice: Lola, Bob: Rodrigo, Claire: Patrick.\n(1) Alice and Bob switch partners: Alice: Rodrigo, Bob: Lola, Claire: Patrick.\n(2) Claire and Bob switch partners: Alice: Rodrigo, Bob: Patrick, Claire: Lola.\n(3) Bob and Alice switch partners: Alice: Patrick, Bob: Rodrigo, Claire: Lola.\nAt the end of the dance, Alice is dancing with Patrick. So the answer is (C).\n\nQ: {{input}}\nA: Let's think step by step.\n"
-"include": "_cot_fewshot_template_yaml"
-"task": "bbh_cot_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: Let''s think step by step.
+
+  '
+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: 'Let''s think step by step.
+
+      (0) At the start: Alice: yellow, Bob: blue, Claire: pink.
+
+      (1) Claire and Alice swap balls: Alice: pink, Bob: blue, Claire: yellow.
+
+      (2)  Alice and Bob swap balls: Alice: blue, Bob: pink, Claire: yellow.
+
+      (3) Claire and Bob swap balls: Alice: blue, Bob: yellow, Claire: pink.
+
+      At the end of the game, Bob has the yellow ball. So the answer is (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: 'Let''s think step by step.
+
+      (0) At the start: Alice: white, Bob: purple, Claire: pink.
+
+      (1) Bob and Alice swap balls: Alice: purple, Bob: white, Claire: pink.
+
+      (2) Bob and Claire swap balls: Alice: purple, Bob: pink, Claire: white.
+
+      (3) Bob and Alice swap balls: Alice: pink, Bob: purple, Claire: white.
+
+      At the end of the game, Alice has the pink ball. So the answer is (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: 'Let''s think step by step.
+
+      (0) At the start: Alice: Lola, Bob: Rodrigo, Claire: Patrick.
+
+      (1) Alice and Bob switch partners: Alice: Rodrigo, Bob: Lola, Claire: Patrick.
+
+      (2) Claire and Bob switch partners: Alice: Rodrigo, Bob: Patrick, Claire: Lola.
+
+      (3) Bob and Alice switch partners: Alice: Patrick, Bob: Rodrigo, Claire: Lola.
+
+      At the end of the dance, Alice is dancing with Patrick. So the answer is (C).'
+include: _cot_fewshot_template_yaml
+task: bbh_cot_fewshot_tracking_shuffled_objects_three_objects

lm_eval/tasks/bbh/cot_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: Let's think step by step.\n(1) Fidel tells the truth. So, we know that Fidel tells the truth.\n(2) Jerry says Fidel tells the truth. Since we know from (1) that Fidel tells the truth, if Jerry says that Fidel tells the truth, then Jerry tells the truth.\n(3) Vina says Jerry tells the truth. Since we know from (2) that Jerry tells the truth, if Vina says Jerry tells the truth, then Vine tells the truth.\n(4) Millicent says Vina lies. Since we know from (3) that Vina tells the truth, if Millicent says Vina lies, then Millicent lies.\n(5) Raymond says Millicent lies. Since we know from (4) that Millicent lies, if Raymond says Millicent lies, then Raymond tells the truth.\nNow, the question asks: Does Raymond tell the truth? We know from (5) that Raymond tells the truth. So the answer is 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: Let's think step by step.\n(1) Kristian lies. So, we know that Kristian lies.\n(2) Millie says Kristian lies. Since we know from (1) that Kristian lies, if Millie says Kristian lies, then Millie tells the truth.\n(3) Maybelle says Millie tells the truth. Since we know from (2) that Millie tells the truth, if Maybelle says Millie tells the truth, then Maybelle tells the truth.\n(4) Fidel says Maybelle lies. Since we know from (3) that Maybelle tells the truth, if Fidel says Maybelle lies, then Fidel lies.\n(5) Leda says Fidel lies. Since we know from (4) that Fidel lies, if Leda says Fidel lies, then Leda tells the truth.\nNow, the question asks: Does Leda tell the truth? We know from (5) that Leda tells the truth. So the answer is 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: Let's think step by step.\n(1) Kristian tells the truth. So, we know that Kristian tells the truth.\n(2) Michaela says Kristian lies. Since we know from (1) that Kristian tells the truth, if Michaela says Kristian lies, then Michaela lies.\n(3) Raymond says Michaela tells the truth. Since we know from (2) that Michaela lies, if Raymond says Michaela tells the truth, then Raymond lies.\n(4) Osvaldo says Raymond tells the truth. Since we know from (3) that Raymond lies, if Osvaldo says Raymond tells the truth, then Osvaldo lies.\n(5) Jamey says Osvaldo tells the truth. Since we know from (4) that Osvaldo lies, if Jamey says Osvaldo tells the truth, then Jamey lies.\nNow, the question asks: Does Jamey tell the truth? We know from (5) that Jamey lies. So the answer is No.\n\nQ: {{input}}\nA: Let's think step by step.\n"
-"include": "_cot_fewshot_template_yaml"
-"task": "bbh_cot_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: Let''s think step by step.
+
+  '
+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: 'Let''s think step by step.
+
+      (1) Fidel tells the truth. So, we know that Fidel tells the truth.
+
+      (2) Jerry says Fidel tells the truth. Since we know from (1) that Fidel tells
+      the truth, if Jerry says that Fidel tells the truth, then Jerry tells the truth.
+
+      (3) Vina says Jerry tells the truth. Since we know from (2) that Jerry tells
+      the truth, if Vina says Jerry tells the truth, then Vine tells the truth.
+
+      (4) Millicent says Vina lies. Since we know from (3) that Vina tells the truth,
+      if Millicent says Vina lies, then Millicent lies.
+
+      (5) Raymond says Millicent lies. Since we know from (4) that Millicent lies,
+      if Raymond says Millicent lies, then Raymond tells the truth.
+
+      Now, the question asks: Does Raymond tell the truth? We know from (5) that Raymond
+      tells the truth. So the answer is 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: 'Let''s think step by step.
+
+      (1) Kristian lies. So, we know that Kristian lies.
+
+      (2) Millie says Kristian lies. Since we know from (1) that Kristian lies, if
+      Millie says Kristian lies, then Millie tells the truth.
+
+      (3) Maybelle says Millie tells the truth. Since we know from (2) that Millie
+      tells the truth, if Maybelle says Millie tells the truth, then Maybelle tells
+      the truth.
+
+      (4) Fidel says Maybelle lies. Since we know from (3) that Maybelle tells the
+      truth, if Fidel says Maybelle lies, then Fidel lies.
+
+      (5) Leda says Fidel lies. Since we know from (4) that Fidel lies, if Leda says
+      Fidel lies, then Leda tells the truth.
+
+      Now, the question asks: Does Leda tell the truth? We know from (5) that Leda
+      tells the truth. So the answer is 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: 'Let''s think step by step.
+
+      (1) Kristian tells the truth. So, we know that Kristian tells the truth.
+
+      (2) Michaela says Kristian lies. Since we know from (1) that Kristian tells
+      the truth, if Michaela says Kristian lies, then Michaela lies.
+
+      (3) Raymond says Michaela tells the truth. Since we know from (2) that Michaela
+      lies, if Raymond says Michaela tells the truth, then Raymond lies.
+
+      (4) Osvaldo says Raymond tells the truth. Since we know from (3) that Raymond
+      lies, if Osvaldo says Raymond tells the truth, then Osvaldo lies.
+
+      (5) Jamey says Osvaldo tells the truth. Since we know from (4) that Osvaldo
+      lies, if Jamey says Osvaldo tells the truth, then Jamey lies.
+
+      Now, the question asks: Does Jamey tell the truth? We know from (5) that Jamey
+      lies. So the answer is No.'
+include: _cot_fewshot_template_yaml
+task: bbh_cot_fewshot_web_of_lies

lm_eval/tasks/bbh/cot_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: Let's think step by step.\nThe first letter: \"oven\": \"o\" (15). \"costume\": \"c\" (3). \"counterpart\": \"c\" (3). We now have: (3) [\"costume\" ? \"counterpart\"] < (15) \"oven\". Now let's sort this subpart [\"costume\" ? \"counterpart\"] by looking at their second letters.\nThe second letter: \"costume\": \"o\" (15). \"counterpart\": \"o\" (15). We now have: (15) [\"costume\" ? \"counterpart\"]. Now let's sort this subpart [\"costume\" ? \"counterpart\"] by looking at their third letters.\nThe third letter: \"costume\": \"s\" (19). \"counterpart\": \"u\" (21). We now have: (19) \"costume\" < (21) \"counterpart\". Hence, we have [\"costume\" < \"counterpart\"] < \"oven\". So the answer is costume counterpart oven.\n\nQ: Sort the following words alphabetically: List: hypochlorite ponderosa phone credulity\nA: Let's think step by step.\nThe first letter: \"hypochlorite\": \"h\" (8). \"ponderosa\": \"p\" (16). \"phone\": \"p\" (16). \"credulity\": \"c\" (3). We now have: (3) \"credulity\" < (8) \"hypochlorite\" < (16) [\"ponderosa\" ? \"phone\"]. Now let's sort this subpart [\"ponderosa\" ? \"phone\"] by looking at their second letters.\nThe second letter: \"ponderosa\": \"o\" (15). \"phone\": \"h\" (8). We now have: (8) \"phone\" < (15) \"ponderosa\". Hence, we have \"credulity\" < \"hypochlorite\" < [\"phone\" <\"ponderosa\"]. So the answer is credulity hypochlorite phone ponderosa.\n\nQ: Sort the following words alphabetically: List: newt arson parthia seismography mugho aspect census\nA: Let's think step by step.\nThe first letter: \"newt\": \"n\" (14). \"arson\": \"a\" (1). \"parthia\": \"p\" (16). \"seismography\": \"s\" (19). \"mugho\": \"m\" (13). \"aspect\": \"a\" (1). \"census\": \"c\" (3). We now have: (1) [\"arson\" ? \"aspect\"] < (3) \"census\" < (13) \"mugho\" < (14) \"newt\" < (16) \"parthia\" < (19) \"seismography\". Now let's sort this subpart [\"arson\" ? \"aspect\"] by looking at their second letters.\nThe second letter: \"arson\": \"r\" (18). \"aspect\": \"s\" (19). We now have: (18) \"arson\" < (19) \"aspect\". Hence, we have [\"arson\" < \"aspect\"] < \"census\" < \"mugho\" < \"newt\" < \"parthia\" < \"seismography\". So the answer is arson aspect census mugho newt parthia seismography.\n\nQ: {{input}}\nA: Let's think step by step.\n"
-"include": "_cot_fewshot_template_yaml"
-"task": "bbh_cot_fewshot_word_sorting"
+dataset_name: word_sorting
+description: 'Sort a list of words.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A: Let''s think step by step.
+
+  '
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Sort the following words alphabetically: List: oven costume counterpart'
+    target: 'Let''s think step by step.
+
+      The first letter: "oven": "o" (15). "costume": "c" (3). "counterpart": "c" (3).
+      We now have: (3) ["costume" ? "counterpart"] < (15) "oven". Now let''s sort
+      this subpart ["costume" ? "counterpart"] by looking at their second letters.
+
+      The second letter: "costume": "o" (15). "counterpart": "o" (15). We now have:
+      (15) ["costume" ? "counterpart"]. Now let''s sort this subpart ["costume" ?
+      "counterpart"] by looking at their third letters.
+
+      The third letter: "costume": "s" (19). "counterpart": "u" (21). We now have:
+      (19) "costume" < (21) "counterpart". Hence, we have ["costume" < "counterpart"]
+      < "oven". So the answer is costume counterpart oven.'
+  - input: 'Sort the following words alphabetically: List: hypochlorite ponderosa
+      phone credulity'
+    target: 'Let''s think step by step.
+
+      The first letter: "hypochlorite": "h" (8). "ponderosa": "p" (16). "phone": "p"
+      (16). "credulity": "c" (3). We now have: (3) "credulity" < (8) "hypochlorite"
+      < (16) ["ponderosa" ? "phone"]. Now let''s sort this subpart ["ponderosa" ?
+      "phone"] by looking at their second letters.
+
+      The second letter: "ponderosa": "o" (15). "phone": "h" (8). We now have: (8)
+      "phone" < (15) "ponderosa". Hence, we have "credulity" < "hypochlorite" < ["phone"
+      <"ponderosa"]. So the answer is credulity hypochlorite phone ponderosa.'
+  - input: 'Sort the following words alphabetically: List: newt arson parthia seismography
+      mugho aspect census'
+    target: 'Let''s think step by step.
+
+      The first letter: "newt": "n" (14). "arson": "a" (1). "parthia": "p" (16). "seismography":
+      "s" (19). "mugho": "m" (13). "aspect": "a" (1). "census": "c" (3). We now have:
+      (1) ["arson" ? "aspect"] < (3) "census" < (13) "mugho" < (14) "newt" < (16)
+      "parthia" < (19) "seismography". Now let''s sort this subpart ["arson" ? "aspect"]
+      by looking at their second letters.
+
+      The second letter: "arson": "r" (18). "aspect": "s" (19). We now have: (18)
+      "arson" < (19) "aspect". Hence, we have ["arson" < "aspect"] < "census" < "mugho"
+      < "newt" < "parthia" < "seismography". So the answer is arson aspect census
+      mugho newt parthia seismography.'
+include: _cot_fewshot_template_yaml
+task: bbh_cot_fewshot_word_sorting

lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml

@@ -16,7 +16,6 @@ generation_kwargs:
     - "\n\n"
   do_sample: false
   temperature: 0.0
-num_fewshot: 0
+num_fewshot: 3
 metadata:
   version: 1.0
-  num_fewshot: 3 # will be printed in results table

lm_eval/tasks/bbh/fewshot/boolean_expressions.yaml

-"dataset_name": "boolean_expressions"
-"description": "Evaluate the result of a random Boolean expression.\n\n"
-"doc_to_text": "Q: not ( ( not not True ) ) is\nA: False\n\nQ: True and False and not True and True is\nA: False\n\nQ: not not ( not ( False ) ) is\nA: True\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_boolean_expressions"
+dataset_name: boolean_expressions
+description: 'Evaluate the result of a random Boolean expression.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: not ( ( not not True ) ) is
+    target: 'False'
+  - input: True and False and not True and True is
+    target: 'False'
+  - input: not not ( not ( False ) ) is
+    target: 'True'
+include: _fewshot_template_yaml
+task: bbh_fewshot_boolean_expressions

lm_eval/tasks/bbh/fewshot/causal_judgement.yaml

-"dataset_name": "causal_judgement"
-"description": "Answer questions about causal attribution.\n\n"
-"doc_to_text": "Q: How would a typical person answer each of the following questions about causation?\nFrank T., had an ongoing dispute with his neighbor over a stretch of land and one day decided to shoot his neighbor in the body. Frank T. had no experience with guns, his hand slipped on the barrel of the gun, and the shot went wild. Nonetheless, the bullet bounced off a large boulder several feet away and hit the neighbor's body, causing significant injury. Did Frank T. intentionally shoot his neighbor in the body?\nOptions:\n- Yes\n- No\nA: No\n\nQ: How would a typical person answer each of the following questions about causation?\nSuzy and Billy are working on a project that is very important for our nation's security. The boss tells them both: \"Be sure that you are here at exactly 9 am. It is absolutely essential that you arrive at that time.\" Both Billy and Suzy arrive at 9 am. As it happens, there was a motion detector installed in the room where they arrived. The motion detector was set up to be triggered if at least one person appeared in the room at the same time. So the motion detector went off. Did Billy cause the motion detector to go off?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: How would a typical person answer each of the following questions about causation?\nGeorge and his sister Lena reunite at their parents' house for Thanksgiving. Whereas George just got into medical school, Lena is unhappy in her marriage and recently lost her job. Over the course of the day, George and Lena get into a number of heated arguments. Later in the afternoon they play a game of darts. They split the first two games, and the third game is close until the end. Who will win comes down to George's last shot. If he hits a high point region, he wins; if he hits a low point region, Lena wins. George thinks of the difficult time Lena is having, and he really wants to let her win. He aims the dart at the low point region. He sets up his shot and the dart lands in the low point region. After his shot, Lena wins the game and is very happy. Did George hit the low point region intentionally?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_causal_judgement"
+dataset_name: causal_judgement
+description: 'Answer questions about causal attribution.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      Frank T., had an ongoing dispute with his neighbor over a stretch of land and
+      one day decided to shoot his neighbor in the body. Frank T. had no experience
+      with guns, his hand slipped on the barrel of the gun, and the shot went wild.
+      Nonetheless, the bullet bounced off a large boulder several feet away and hit
+      the neighbor''s body, causing significant injury. Did Frank T. intentionally
+      shoot his neighbor in the body?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'No'
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      Suzy and Billy are working on a project that is very important for our nation''s
+      security. The boss tells them both: "Be sure that you are here at exactly 9
+      am. It is absolutely essential that you arrive at that time." Both Billy and
+      Suzy arrive at 9 am. As it happens, there was a motion detector installed in
+      the room where they arrived. The motion detector was set up to be triggered
+      if at least one person appeared in the room at the same time. So the motion
+      detector went off. Did Billy cause the motion detector to go off?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'Yes'
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      George and his sister Lena reunite at their parents'' house for Thanksgiving.
+      Whereas George just got into medical school, Lena is unhappy in her marriage
+      and recently lost her job. Over the course of the day, George and Lena get into
+      a number of heated arguments. Later in the afternoon they play a game of darts.
+      They split the first two games, and the third game is close until the end. Who
+      will win comes down to George''s last shot. If he hits a high point region,
+      he wins; if he hits a low point region, Lena wins. George thinks of the difficult
+      time Lena is having, and he really wants to let her win. He aims the dart at
+      the low point region. He sets up his shot and the dart lands in the low point
+      region. After his shot, Lena wins the game and is very happy. Did George hit
+      the low point region intentionally?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'Yes'
+include: _fewshot_template_yaml
+task: bbh_fewshot_causal_judgement

lm_eval/tasks/bbh/fewshot/date_understanding.yaml

-"dataset_name": "date_understanding"
-"description": "Infer the date from context.\n\n"
-"doc_to_text": "Q: Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?\nOptions:\n(A) 12/14/2026\n(B) 12/14/1950\n(C) 12/14/2007\n(D) 12/14/1937\n(E) 07/14/1938\n(F) 12/14/1988\nA: (D)\n\nQ: Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?\nOptions:\n(A) 09/04/2018\n(B) 11/11/2018\n(C) 08/25/2018\n(D) 11/02/2018\n(E) 11/04/2018\nA: (B)\n\nQ: Jane and John married on Jan 2, 1958. It is their 5-year anniversary today. What is the date tomorrow in MM/DD/YYYY?\nOptions:\n(A) 01/11/1961\n(B) 01/03/1963\n(C) 01/18/1961\n(D) 10/14/1960\n(E) 01/03/1982\n(F) 12/03/1960\nA: (B)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_date_understanding"
+dataset_name: date_understanding
+description: 'Infer the date from context.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?
+
+      Options:
+
+      (A) 12/14/2026
+
+      (B) 12/14/1950
+
+      (C) 12/14/2007
+
+      (D) 12/14/1937
+
+      (E) 07/14/1938
+
+      (F) 12/14/1988'
+    target: (D)
+  - input: 'Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?
+
+      Options:
+
+      (A) 09/04/2018
+
+      (B) 11/11/2018
+
+      (C) 08/25/2018
+
+      (D) 11/02/2018
+
+      (E) 11/04/2018'
+    target: (B)
+  - input: 'Jane and John married on Jan 2, 1958. It is their 5-year anniversary today.
+      What is the date tomorrow in MM/DD/YYYY?
+
+      Options:
+
+      (A) 01/11/1961
+
+      (B) 01/03/1963
+
+      (C) 01/18/1961
+
+      (D) 10/14/1960
+
+      (E) 01/03/1982
+
+      (F) 12/03/1960'
+    target: (B)
+include: _fewshot_template_yaml
+task: bbh_fewshot_date_understanding

lm_eval/tasks/bbh/fewshot/disambiguation_qa.yaml

-"dataset_name": "disambiguation_qa"
-"description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n"
-"doc_to_text": "Q: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The chief told the counselor that they took the day off.\nOptions:\n(A) The chief took the day off\n(B) The counselor took the day off\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The manager sent a message to the secretary, but he didn't reply yet.\nOptions:\n(A) The secretary didn't reply yet\n(B) The manager didn't reply yet\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: Bailey will plan to meet the director at his office\nOptions:\n(A) It will be Bailey's office\n(B) It will be the director's office\n(C) Ambiguous\nA: (C)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_disambiguation_qa"
+dataset_name: disambiguation_qa
+description: 'Clarify the meaning of sentences with ambiguous pronouns.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: The chief told the counselor that they took the day off.
+
+      Options:
+
+      (A) The chief took the day off
+
+      (B) The counselor took the day off
+
+      (C) Ambiguous'
+    target: (A)
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: The manager sent a message to the secretary, but he didn''t reply
+      yet.
+
+      Options:
+
+      (A) The secretary didn''t reply yet
+
+      (B) The manager didn''t reply yet
+
+      (C) Ambiguous'
+    target: (A)
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: Bailey will plan to meet the director at his office
+
+      Options:
+
+      (A) It will be Bailey''s office
+
+      (B) It will be the director''s office
+
+      (C) Ambiguous'
+    target: (C)
+include: _fewshot_template_yaml
+task: bbh_fewshot_disambiguation_qa

lm_eval/tasks/bbh/fewshot/dyck_languages.yaml

-"dataset_name": "dyck_languages"
-"description": "Correctly close a Dyck-n word.\n\n"
-"doc_to_text": "Q: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: [ { [\nA: ] } ]\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < > ( ( [ [ ( { } ) [ < > ] ]\nA: ] ) )\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < [ < [ { < [ ] < { } > > } ] > { { ( ) } { < [ < > ] > }\nA: } ] >\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_dyck_languages"
+dataset_name: dyck_languages
+description: 'Correctly close a Dyck-n word.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Complete the rest of the sequence, making sure that the parentheses are
+      closed properly. Input: [ { ['
+    target: '] } ]'
+  - input: 'Complete the rest of the sequence, making sure that the parentheses are
+      closed properly. Input: < > ( ( [ [ ( { } ) [ < > ] ]'
+    target: '] ) )'
+  - input: 'Complete the rest of the sequence, making sure that the parentheses are
+      closed properly. Input: < [ < [ { < [ ] < { } > > } ] > { { ( ) } { < [ < >
+      ] > }'
+    target: '} ] >'
+include: _fewshot_template_yaml
+task: bbh_fewshot_dyck_languages

lm_eval/tasks/bbh/fewshot/formal_fallacies.yaml

-"dataset_name": "formal_fallacies"
-"description": "Distinguish deductively valid arguments from formal fallacies.\n\n"
-"doc_to_text": "Q: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: To begin with, Lesley is a close friend of Fernando. Moreover, being a close friend of Fernando or a schoolmate of Lowell is sufficient for being a great-grandfather of Leroy. It follows that Lesley is a great-grandfather of Leroy.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: Whoever is not a great-grandfather of Clyde is a stepbrother of Brian. Being an ancestor of Dana is sufficient for not being a great-grandfather of Clyde. We may conclude: Everyone who is an ancestor of Dana is a stepbrother of Brian, too.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to grasp who is consuming which products. The following argument pertains to this question: Every infrequent user of Paul Mitchell shampoo is either a rare consumer of Nioxin shampoo or a loyal buyer of Caress soap, or both. No regular consumer of Lush soap is a rare consumer of Nioxin shampoo and, in the same time, a loyal buyer of Caress soap. It follows that whoever is an infrequent user of Paul Mitchell shampoo is not a regular consumer of Lush soap.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: invalid\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_formal_fallacies"
+dataset_name: formal_fallacies
+description: 'Distinguish deductively valid arguments from formal fallacies.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: '"It is not always easy to see who is related to whom -- and in which ways.
+      The following argument pertains to this question: To begin with, Lesley is a
+      close friend of Fernando. Moreover, being a close friend of Fernando or a schoolmate
+      of Lowell is sufficient for being a great-grandfather of Leroy. It follows that
+      Lesley is a great-grandfather of Leroy."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: valid
+  - input: '"It is not always easy to see who is related to whom -- and in which ways.
+      The following argument pertains to this question: Whoever is not a great-grandfather
+      of Clyde is a stepbrother of Brian. Being an ancestor of Dana is sufficient
+      for not being a great-grandfather of Clyde. We may conclude: Everyone who is
+      an ancestor of Dana is a stepbrother of Brian, too."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: valid
+  - input: '"It is not always easy to grasp who is consuming which products. The following
+      argument pertains to this question: Every infrequent user of Paul Mitchell shampoo
+      is either a rare consumer of Nioxin shampoo or a loyal buyer of Caress soap,
+      or both. No regular consumer of Lush soap is a rare consumer of Nioxin shampoo
+      and, in the same time, a loyal buyer of Caress soap. It follows that whoever
+      is an infrequent user of Paul Mitchell shampoo is not a regular consumer of
+      Lush soap."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: invalid
+include: _fewshot_template_yaml
+task: bbh_fewshot_formal_fallacies

lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml

-"dataset_name": "geometric_shapes"
-"description": "Name geometric shapes from their SVG paths.\n\n"
-"doc_to_text": "Q: This SVG path element <path d=\"M 31.00,73.00 L 32.00,59.00 L 44.00,50.00 L 49.00,41.00 L 64.00,37.00 L 71.00,55.00 L 64.00,76.00 L 52.00,61.00 L 31.00,73.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (F)\n\nQ: This SVG path element <path d=\"M 14.19,26.04 L 51.43,39.21 L 58.44,36.69 L 56.63,30.17 L 48.53,26.66 L 14.19,26.04\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (G)\n\nQ: This SVG path element <path d=\"M 41.00,43.00 L 37.00,34.00 L 41.00,33.00 L 45.00,34.00 L 41.00,43.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (D)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_geometric_shapes"
+dataset_name: geometric_shapes
+description: 'Name geometric shapes from their SVG paths.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'This SVG path element <path d="M 31.00,73.00 L 32.00,59.00 L 44.00,50.00
+      L 49.00,41.00 L 64.00,37.00 L 71.00,55.00 L 64.00,76.00 L 52.00,61.00 L 31.00,73.00"/>
+      draws a
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (F)
+  - input: 'This SVG path element <path d="M 14.19,26.04 L 51.43,39.21 L 58.44,36.69
+      L 56.63,30.17 L 48.53,26.66 L 14.19,26.04"/> draws a
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (G)
+  - input: 'This SVG path element <path d="M 41.00,43.00 L 37.00,34.00 L 41.00,33.00
+      L 45.00,34.00 L 41.00,43.00"/> draws a
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (D)
+include: _fewshot_template_yaml
+task: bbh_fewshot_geometric_shapes

lm_eval/tasks/bbh/fewshot/hyperbaton.yaml

-"dataset_name": "hyperbaton"
-"description": "Order adjectives correctly in English sentences.\n\n"
-"doc_to_text": "Q: Which sentence has the correct adjective order:\nOptions:\n(A) rubber terrible ship\n(B) terrible rubber ship\nA: (B)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) repulsive small Brazilian exercise ship\n(B) Brazilian repulsive exercise small ship\nA: (A)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) blue gold wonderful square shoe\n(B) wonderful square blue gold shoe\nA: (B)\n\nQ: {{input}}\nA:"
-"include": "_fewshot_template_yaml"
-"task": "bbh_fewshot_hyperbaton"
+dataset_name: hyperbaton
+description: 'Order adjectives correctly in English sentences.
+
+
+  '
+doc_to_text: 'Q: {{input}}
+
+  A:'
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) rubber terrible ship
+
+      (B) terrible rubber ship'
+    target: (B)
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) repulsive small Brazilian exercise ship
+
+      (B) Brazilian repulsive exercise small ship'
+    target: (A)
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) blue gold wonderful square shoe
+
+      (B) wonderful square blue gold shoe'
+    target: (B)
+include: _fewshot_template_yaml
+task: bbh_fewshot_hyperbaton

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