Merge branch 'EleutherAI:main' into main

lm_eval/tasks/glue/sst2/default.yaml

-group: glue
+tag: glue
 task: sst2
 dataset_path: glue
 dataset_name: sst2

lm_eval/tasks/glue/wnli/default.yaml

-group: glue
+tag: glue
 task: wnli
 dataset_path: glue
 dataset_name: wnli

lm_eval/tasks/gpqa/README.md

@@ -25,11 +25,15 @@ Homepage: `https://github.com/idavidrein/gpqa/tree/main`
 
 This dataset is gated, so you will have to accept the terms of use at https://huggingface.co/datasets/Idavidrein/gpqa and login via `huggingface-cli login` using your HF Hub token before running this task.
 
-### Groups and Tasks
+### Groups, Tags, and Tasks
 
 #### Groups
 
-* `gpqa`
+None
+
+#### Tags
+
+* `gpqa`: runs all GPQA variants.
 
 #### Tasks
 

lm_eval/tasks/gpqa/cot_n_shot/_gpqa_cot_n_shot_yaml

 dataset_path: Idavidrein/gpqa
-group: gpqa
+tag: gpqa
 output_type: generate_until
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/gpqa/cot_zeroshot/_gpqa_cot_zeroshot_yaml

 dataset_path: Idavidrein/gpqa
-group: gpqa
+tag: gpqa
 output_type: generate_until
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/gpqa/generative/_gpqa_generative_n_shot_yaml

 dataset_path: Idavidrein/gpqa
-group: gpqa
+tag: gpqa
 output_type: generate_until
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/gpqa/n_shot/_gpqa_n_shot_yaml

 dataset_path: Idavidrein/gpqa
-group: gpqa
+tag: gpqa
 output_type: multiple_choice
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/gpqa/zeroshot/_gpqa_zeroshot_yaml

 dataset_path: Idavidrein/gpqa
-group: gpqa
+tag: gpqa
 output_type: multiple_choice
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml

 include: gsm8k-cot.yaml
-group:
+tag:
   - chain_of_thought
   - self_consistency
 task: gsm8k_cot_self_consistency

lm_eval/tasks/gsm8k/gsm8k-cot-zeroshot.yaml

-group:
+tag:
   - math_word_problems
 task: gsm8k_cot_zeroshot
 dataset_path: gsm8k

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 $3 each. How much money does she have left?\nA: Olivia had 23 dollars. 5 bagels for 3 dollars each will be 5 x 3 = 15 dollars. So she has 23 - 15 dollars left. 23 - 15 is 8. The answer is 8.\n\n\
-Q: {{question}}\nA:"
-doc_to_target: "{{answer.split('####')[-1].strip()}}"
-metric_list:
-  - metric: exact_match
-    aggregation: mean
-    higher_is_better: true
-    ignore_case: true
-    ignore_punctuation: false
-    regexes_to_ignore:
-      - ","
-      - "\\$"
-      - "(?s).*#### "
-      - "\\.$"
+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:
-  until:
-    - "Q:"
-    - "</s>"
-    - "<|im_end|>"
   do_sample: false
-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: "(-?[$0-9.,]{2,})|(-?[0-9]+)"
-      - function: "take_first"
+  until:
+  - 'Q:'
+  - </s>
+  - <|im_end|>
+tag:
+- chain_of_thought
 metadata:
   version: 3.0
-  num_fewshot: 8
+metric_list:
+- aggregation: mean
+  higher_is_better: true
+  ignore_case: true
+  ignore_punctuation: false
+  metric: exact_match
+  regexes_to_ignore:
+  - ','
+  - \$
+  - '(?s).*#### '
+  - \.$
+num_fewshot: 8
+output_type: generate_until
+repeats: 1
+task: gsm8k_cot
+test_split: test

lm_eval/tasks/gsm8k/gsm8k.yaml

-group:
+tag:
   - math_word_problems
 task: gsm8k
 dataset_path: gsm8k

lm_eval/tasks/haerae/_default_haerae_yaml

-group: haerae
 dataset_path: HAERAE-HUB/HAE_RAE_BENCH
 test_split: test
 fewshot_split: test

lm_eval/tasks/haerae/_haerae.yaml

+group: haerae
+task:
+  - haerae_gk
+  - haerae_hi
+  - haerae_lw
+  - haerae_rw
+  - haerae_sn
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+  - metric: acc_norm
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 1.0

lm_eval/tasks/headqa/headqa_en.yaml

-group:
-  - headqa
+tag: headqa
 task: headqa_en
 dataset_path: EleutherAI/headqa
 dataset_name: en

lm_eval/tasks/hellaswag/hellaswag.yaml

-group:
+tag:
   - multiple_choice
 task: hellaswag
 dataset_path: hellaswag
@@ -20,3 +20,5 @@ metric_list:
     higher_is_better: true
 metadata:
   version: 1.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/hendrycks_ethics/commonsense.yaml

-group:
+tag:
   - hendrycks_ethics
 task: ethics_cm
 dataset_path: EleutherAI/hendrycks_ethics

lm_eval/tasks/hendrycks_ethics/justice.yaml

 include: deontology.yaml
-group:
+tag:
   - hendrycks_ethics
 task: ethics_justice
 dataset_name: justice

lm_eval/tasks/hendrycks_ethics/utilitarianism.yaml

 include: commonsense.yaml
-group:
+tag:
   - hendrycks_ethics
 task: ethics_utilitarianism
 dataset_name: utilitarianism

lm_eval/tasks/hendrycks_ethics/virtue.yaml

 include: commonsense.yaml
-group:
+tag:
   - hendrycks_ethics
 task: ethics_virtue
 dataset_name: virtue