Commit bc4b922c authored by Baber's avatar Baber
Browse files

Merge branch 'main' into llama

# Conflicts:
#	lm_eval/tasks/llama3/README.md
parents 748eb47e b2c090cc
dataset_path: CohereForAI/Global-MMLU
dataset_name: am
test_split: test
fewshot_split: dev
fewshot_config:
sampler: first_n
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\nD. {{option_d}}\nAnswer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
metadata:
version: 0.0
group: global_mmlu_full_am
task:
- global_mmlu_full_am_stem
- global_mmlu_full_am_other
- global_mmlu_full_am_social_sciences
- global_mmlu_full_am_humanities
aggregate_metric_list:
- metric: acc
weight_by_size: True
metadata:
version: 1.0
group: global_mmlu_full_am_humanities
task:
- global_mmlu_full_am_humanities_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
group: global_mmlu_full_am_other
task:
- global_mmlu_full_am_other_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
group: global_mmlu_full_am_social_sciences
task:
- global_mmlu_full_am_social_sciences_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
group: global_mmlu_full_am_stem
task:
- global_mmlu_full_am_stem_tasks
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_abstract_algebra
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_abstract_algebra
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_anatomy
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_anatomy
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_astronomy
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_astronomy
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_business_ethics
tag: global_mmlu_full_am_other_tasks
task: global_mmlu_full_am_business_ethics
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_clinical_knowledge
tag: global_mmlu_full_am_other_tasks
task: global_mmlu_full_am_clinical_knowledge
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_biology
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_college_biology
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_chemistry
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_college_chemistry
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_computer_science
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_college_computer_science
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_mathematics
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_college_mathematics
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_medicine
tag: global_mmlu_full_am_other_tasks
task: global_mmlu_full_am_college_medicine
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_college_physics
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_college_physics
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_computer_security
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_computer_security
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_conceptual_physics
tag: global_mmlu_full_am_stem_tasks
task: global_mmlu_full_am_conceptual_physics
# Generated by _generate_configs.py
include: _am_template_yaml
process_docs: !function utils.process_econometrics
tag: global_mmlu_full_am_social_sciences_tasks
task: global_mmlu_full_am_econometrics
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