"tests/models/roberta/test_modeling_tf_roberta.py" did not exist on "e78c1103385f2d2f9cd4980f61a8e71baa655356"
Commit 620d8a36 authored by haileyschoelkopf's avatar haileyschoelkopf
Browse files

add draft abstract algebra task, fix genning script

parent 25a4e2c6
...@@ -40,6 +40,6 @@ repos: ...@@ -40,6 +40,6 @@ repos:
- id: codespell - id: codespell
exclude: > exclude: >
(?x)^( (?x)^(
.*\.json|ignore.txt .*\.json|ignore.txt|.*\.yaml
)$ )$
args: [--check-filenames, --check-hidden, --ignore-words=ignore.txt] args: [--check-filenames, --check-hidden, --ignore-words=ignore.txt]
...@@ -97,6 +97,7 @@ if __name__ == "__main__": ...@@ -97,6 +97,7 @@ if __name__ == "__main__":
"include": base_yaml_name, "include": base_yaml_name,
"task": base_yaml["task"].strip("abstract_algebra") + "subject", "task": base_yaml["task"].strip("abstract_algebra") + "subject",
"dataset_name": subject, "dataset_name": subject,
"description": f"The following are multiple choice questions (with answers) about {' '.join(subject.split('_'))}.\n\n",
} }
file_save_path = args.task_save_path + f"_{subject}.yaml" file_save_path = args.task_save_path + f"_{subject}.yaml"
......
...@@ -2,16 +2,16 @@ group: ...@@ -2,16 +2,16 @@ group:
- mmlu - mmlu
- mmlu_original - mmlu_original
- multiple_choice - multiple_choice
task: mmlu_original_ task: mmlu_original_abstract_algebra
dataset_path: cais/mmlu dataset_path: cais/mmlu
dataset_name: abstract_algebra dataset_name: abstract_algebra
output_type: multiple_choice output_type: multiple_choice
training_split: train
validation_split: validation validation_split: validation
test_split: test test_split: test
doc_to_text: "Question: {{question}}\nAnswer:" description: "The following are multiple choice questions (with answers) about abstract algebra.\n\n"
doc_to_target: "{{choices.label.index(answerKey)}}" doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
doc_to_choice: "{{choices.text}}" doc_to_choice: "{{choices}}"
doc_to_target: "{{answer}}"
metric_list: metric_list:
- metric: acc - metric: acc
aggregation: mean aggregation: mean
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment