add more explicit group configs

lm_eval/tasks/aclue/_aclue.yaml

@@ -15,7 +15,7 @@ task:
   - aclue_polysemy_resolution
   - aclue_reading_comprehension
   - aclue_sentence_segmentation
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     aggregation: mean
     weight_by_size: true

lm_eval/tasks/aexams/_aexams.yaml

@@ -5,7 +5,7 @@ task:
   - aexams_Physics
   - aexams_Science
   - aexams_Social
-aggregate_metric:
+aggregate_metric_list:
   - metric: acc
     aggregation: mean
     weight_by_size: true

lm_eval/tasks/blimp/_template_yaml

-group: blimp
 dataset_path: blimp
 output_type: multiple_choice
 validation_split: train

lm_eval/tasks/crows_pairs/crows_pairs_english.yaml

 tag:
   - crows_pairs
-  - social_bias
 task: crows_pairs_english
 dataset_path: BigScienceBiasEval/crows_pairs_multilingual
 dataset_name: english

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

@@ -61,7 +61,7 @@ generation_kwargs:
   - 'Q:'
   - </s>
   - <|im_end|>
-group:
+tag:
 - chain_of_thought
 metadata:
   version: 3.0

lm_eval/tasks/gsm8k/gsm8k.yaml

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

lm_eval/tasks/hellaswag/hellaswag.yaml

-group:
+tag:
   - multiple_choice
 task: hellaswag
 dataset_path: hellaswag

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

lm_eval/tasks/kobest/kobest_boolq.yaml

-group:
+tag:
   - kobest
 task: kobest_boolq
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_copa.yaml

-group:
+tag:
   - kobest
 task: kobest_copa
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_hellaswag.yaml

-group:
+tag:
   - kobest
 task: kobest_hellaswag
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_sentineg.yaml

-group:
+tag:
   - kobest
 task: kobest_sentineg
 dataset_path: skt/kobest_v1

lm_eval/tasks/kobest/kobest_wic.yaml

-group:
+tag:
   - kobest
 task: kobest_wic
 dataset_path: skt/kobest_v1

lm_eval/tasks/qasper/bool.yaml

-group: qasper
+tag: qasper
 task: qasper_bool
 dataset_path: allenai/qasper
 output_type: multiple_choice

lm_eval/tasks/qasper/freeform.yaml

-group: qasper
+tag: qasper
 task: qasper_freeform
 dataset_path: allenai/qasper
 output_type: generate_until