Merge branch 'smolrefact' into tasklist

# Conflicts:
#	lm_eval/__main__.py
#	lm_eval/api/group.py
#	lm_eval/api/task.py
#	lm_eval/evaluator_utils.py
#	lm_eval/tasks/__init__.py
#	lm_eval/utils.py
#	pyproject.toml

lm_eval/tasks/bhs/basque-S-S_DO_V_AUX.yaml

+dataset_name: basque-S-S_DO_V_AUX
+include: _template_yaml
+task: bhs__basque__S__S_DO_V_AUX

lm_eval/tasks/bhs/basque-S-S_IO_DO_V_AUX.yaml

+dataset_name: basque-S-S_IO_DO_V_AUX
+include: _template_yaml
+task: bhs__basque__S__S_IO_DO_V_AUX

lm_eval/tasks/bhs/basque-S-S_V_AUX.yaml

+dataset_name: basque-S-S_V_AUX
+include: _template_yaml
+task: bhs__basque__S__S_V_AUX

lm_eval/tasks/bhs/bhs_basque.yaml

+group: bhs_basque
+task:
+  - bhs__basque__DO__S_DO_V_AUX
+  - bhs__basque__DO__S_IO_DO_V_AUX
+  - bhs__basque__IO__IO_S_V_AUX
+  - bhs__basque__IO__S_IO_DO_V_AUX
+  - bhs__basque__S__IO_S_V_AUX
+  - bhs__basque__S__S_DO_V_AUX
+  - bhs__basque__S__S_IO_DO_V_AUX
+  - bhs__basque__S__S_V_AUX
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: false

lm_eval/tasks/bhs/bhs_hindi.yaml

+group: bhs_hindi
+task:
+  - bhs__hindi__S_O_V
+  - bhs__hindi__S_PossPRN_O_V
+  - bhs__hindi__S_PossPRN_PossN_O_V
+  - bhs__hindi__S_ne_O_V
+  - bhs__hindi__S_ne_PossPRN_O_V
+  - bhs__hindi__S_ne_PossPRN_PossN_O_V
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: false

lm_eval/tasks/bhs/bhs_swahili.yaml

+group: bhs_swahili
+task:
+  - bhs__swahili__N_of_Poss_D_AP_V_ni_AN
+  - bhs__swahili__N_of_Poss_D_AP_ni_AN
+  - bhs__swahili__N_of_Poss_D_A_V
+  - bhs__swahili__N_of_Poss_D_A_V1_V2
+  - bhs__swahili__N_of_Poss_D_V
+  - bhs__swahili__N_of_Poss_D_ni_A
+  - bhs__swahili__N_of_Poss_V
+  - bhs__swahili__N_of_Poss_ni_A
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: false

lm_eval/tasks/bhs/hindi-S_O_V.yaml

+dataset_name: hindi-S_O_V
+include: _template_yaml
+task: bhs__hindi__S_O_V

lm_eval/tasks/bhs/hindi-S_PossPRN_O_V.yaml

+dataset_name: hindi-S_PossPRN_O_V
+include: _template_yaml
+task: bhs__hindi__S_PossPRN_O_V

lm_eval/tasks/bhs/hindi-S_PossPRN_PossN_O_V.yaml

+dataset_name: hindi-S_PossPRN_PossN_O_V
+include: _template_yaml
+task: bhs__hindi__S_PossPRN_PossN_O_V

lm_eval/tasks/bhs/hindi-S_ne_O_V.yaml

+dataset_name: hindi-S_ne_O_V
+include: _template_yaml
+task: bhs__hindi__S_ne_O_V

lm_eval/tasks/bhs/hindi-S_ne_PossPRN_O_V.yaml

+dataset_name: hindi-S_ne_PossPRN_O_V
+include: _template_yaml
+task: bhs__hindi__S_ne_PossPRN_O_V

lm_eval/tasks/bhs/hindi-S_ne_PossPRN_PossN_O_V.yaml

+dataset_name: hindi-S_ne_PossPRN_PossN_O_V
+include: _template_yaml
+task: bhs__hindi__S_ne_PossPRN_PossN_O_V

lm_eval/tasks/bhs/swahili-N_of_Poss_D_AP_V_ni_AN.yaml

+dataset_name: swahili-N_of_Poss_D_AP_V_ni_AN
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_AP_V_ni_AN

lm_eval/tasks/bhs/swahili-N_of_Poss_D_AP_ni_AN.yaml

+dataset_name: swahili-N_of_Poss_D_AP_ni_AN
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_AP_ni_AN

lm_eval/tasks/bhs/swahili-N_of_Poss_D_A_V.yaml

+dataset_name: swahili-N_of_Poss_D_A_V
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_A_V

lm_eval/tasks/bhs/swahili-N_of_Poss_D_A_V1_V2.yaml

+dataset_name: swahili-N_of_Poss_D_A_V1_V2
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_A_V1_V2

lm_eval/tasks/bhs/swahili-N_of_Poss_D_V.yaml

+dataset_name: swahili-N_of_Poss_D_V
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_V

lm_eval/tasks/bhs/swahili-N_of_Poss_D_ni_A.yaml

+dataset_name: swahili-N_of_Poss_D_ni_A
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_D_ni_A

lm_eval/tasks/bhs/swahili-N_of_Poss_V.yaml

+dataset_name: swahili-N_of_Poss_V
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_V

lm_eval/tasks/bhs/swahili-N_of_Poss_ni_A.yaml

+dataset_name: swahili-N_of_Poss_ni_A
+include: _template_yaml
+task: bhs__swahili__N_of_Poss_ni_A