|
icl_tasks: |
|
- |
|
label: jeopardy |
|
dataset_uri: eval/local_data/world_knowledge/jeopardy_all.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
continuation_delimiter: "\nAnswer: " |
|
has_categories: true |
|
- |
|
label: bigbench_qa_wikidata |
|
dataset_uri: eval/local_data/world_knowledge/bigbench_qa_wikidata.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: lambada_openai |
|
dataset_uri: eval/local_data/language_understanding/lambada_openai.jsonl |
|
num_fewshot: [0] |
|
icl_task_type: language_modeling |
|
- |
|
label: bigbench_conlang_translation |
|
dataset_uri: eval/local_data/language_understanding/bigbench_conlang_translation.jsonl |
|
num_fewshot: [0] |
|
icl_task_type: language_modeling |
|
- |
|
label: bigbench_dyck_languages |
|
dataset_uri: eval/local_data/symbolic_problem_solving/bigbench_dyck_languages.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: bigbench_cs_algorithms |
|
dataset_uri: eval/local_data/symbolic_problem_solving/bigbench_cs_algorithms.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: bigbench_operators |
|
dataset_uri: eval/local_data/symbolic_problem_solving/bigbench_operators.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: bigbench_repeat_copy_logic |
|
dataset_uri: eval/local_data/symbolic_problem_solving/bigbench_repeat_copy_logic.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: simple_arithmetic_nospaces |
|
dataset_uri: eval/local_data/symbolic_problem_solving/simple_arithmetic_nospaces.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: simple_arithmetic_withspaces |
|
dataset_uri: eval/local_data/symbolic_problem_solving/simple_arithmetic_withspaces.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: pubmed_qa_labeled |
|
dataset_uri: eval/local_data/reading_comprehension/pubmed_qa_labeled.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
- |
|
label: squad |
|
dataset_uri: eval/local_data/reading_comprehension/squad.jsonl |
|
num_fewshot: [10] |
|
icl_task_type: language_modeling |
|
|