"vscode:/vscode.git/clone" did not exist on "c06170cc8e324f4fe6a0c26b57d09e8c958e11bc"
Commit 4eecbabb authored by Baber's avatar Baber
Browse files

Merge branch 'main' into prefill

parents dac8b534 fb963f0f
task: arabic_leaderboard_arabic_mmlu_college_medicine
dataset_path: OALL/Arabic_MMLU
dataset_name: college_medicine
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_college_physics
dataset_path: OALL/Arabic_MMLU
dataset_name: college_physics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_computer_security
dataset_path: OALL/Arabic_MMLU
dataset_name: computer_security
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_conceptual_physics
dataset_path: OALL/Arabic_MMLU
dataset_name: conceptual_physics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_econometrics
dataset_path: OALL/Arabic_MMLU
dataset_name: econometrics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_electrical_engineering
dataset_path: OALL/Arabic_MMLU
dataset_name: electrical_engineering
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_elementary_mathematics
dataset_path: OALL/Arabic_MMLU
dataset_name: elementary_mathematics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_formal_logic
dataset_path: OALL/Arabic_MMLU
dataset_name: formal_logic
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_global_facts
dataset_path: OALL/Arabic_MMLU
dataset_name: global_facts
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_biology
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_biology
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_chemistry
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_chemistry
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_computer_science
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_computer_science
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_european_history
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_european_history
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_geography
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_geography
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_government_and_politics
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_government_and_politics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_macroeconomics
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_macroeconomics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_mathematics
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_mathematics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_microeconomics
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_microeconomics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_physics
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_physics
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
task: arabic_leaderboard_arabic_mmlu_high_school_psychology
dataset_path: OALL/Arabic_MMLU
dataset_name: high_school_psychology
output_type: multiple_choice
training_split: null
validation_split: dev
test_split: test
process_docs: !function utils.process_docs
doc_to_text: "{{query}}"
doc_to_target: "{{gold}}"
doc_to_choice: "choices"
fewshot_split: dev
fewshot_config:
sampler: first_n
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
- metric: acc_norm
aggregation: mean
higher_is_better: true
metadata:
version: 1.0
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