make explicit group configs for leaderboard and other newer tasks

lm_eval/tasks/arc_mt/arc_challenge_mt_fi.yaml

-group:
+tag:
   - arc_challenge_mt
 task: arc_challenge_mt_fi
 dataset_path: LumiOpen/arc_challenge_mt

lm_eval/tasks/basqueglue/bec.yaml

-group: basque-glue
+tag: basque-glue
 task: bec2016eu
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: bec

lm_eval/tasks/basqueglue/bhtc.yaml

-group: basque-glue
+tag: basque-glue
 task: bhtc_v2
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: bhtc

lm_eval/tasks/basqueglue/coref.yaml

-group: basque-glue
+tag: basque-glue
 task: epec_koref_bin
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: coref

lm_eval/tasks/basqueglue/qnli.yaml

-group: basque-glue
+tag: basque-glue
 task: qnlieu
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: qnli

lm_eval/tasks/basqueglue/vaxx.yaml

-group: basque-glue
+tag: basque-glue
 task: vaxx_stance
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: vaxx

lm_eval/tasks/basqueglue/wic.yaml

-group: basque-glue
+tag: basque-glue
 task: wiceu
 dataset_path: orai-nlp/basqueGLUE
 dataset_name: wic

lm_eval/tasks/bbh/cot_fewshot/_bbh.yaml

@@ -5,7 +5,7 @@ task:
   - bbh_cot_fewshot_date_understanding
   - bbh_cot_fewshot_disambiguation_qa
   - bbh_cot_fewshot_dyck_languages
-  - bbh_cot_fewshot_formal_languages
+  - bbh_cot_fewshot_formal_fallacies
   - bbh_cot_fewshot_geometric_shapes
   - bbh_cot_fewshot_hyperbaton
   - bbh_cot_fewshot_logical_deduction_five_objects

lm_eval/tasks/bertaqa/_bertaqa_template

-group: bertaqa
+tag: bertaqa
 dataset_path: HiTZ/BertaQA
 dataset_name: null
 validation_split: null

lm_eval/tasks/inverse_scaling/_inverse_scaling_mc_yaml

-group:
+tag:
   - inverse_scaling_mc
 output_type: multiple_choice
 test_split: train

lm_eval/tasks/inverse_scaling/_some_results

+# |                   Tasks                   |Version|Filter|n-shot| Metric |Value |   |Stderr|
+# |-------------------------------------------|-------|------|-----:|--------|-----:|---|-----:|
+# | - inverse_scaling_hindsight_neglect_10shot|      0|none  |     0|acc     |0.4476|±  |0.0281|
+# |                                           |       |none  |     0|acc_norm|0.4476|±  |0.0281|
+# |inverse_scaling_mc                         |N/A    |none  |     0|acc_norm|0.6273|±  |0.0096|
+# |                                           |       |none  |     0|acc     |0.6210|±  |0.0095|
+# | - inverse_scaling_neqa                    |      0|none  |     0|acc     |0.5300|±  |0.0289|
+# |                                           |       |none  |     0|acc_norm|0.5300|±  |0.0289|
+# | - inverse_scaling_quote_repetition        |      0|none  |     0|acc     |0.9367|±  |0.0141|
+# |                                           |       |none  |     0|acc_norm|0.9367|±  |0.0141|
+# | - inverse_scaling_redefine_math           |      0|none  |     0|acc     |0.7178|±  |0.0150|
+# |                                           |       |none  |     0|acc_norm|0.7178|±  |0.0150|
+# | - inverse_scaling_winobias_antistereotype |      0|none  |     0|acc     |0.3786|±  |0.0239|
+# |                                           |       |none  |     0|acc_norm|0.4126|±  |0.0243|
+
+# |      Groups      |Version|Filter|n-shot| Metric |Value |   |Stderr|
+# |------------------|-------|------|-----:|--------|-----:|---|-----:|
+# |inverse_scaling_mc|N/A    |none  |     0|acc_norm|0.6273|±  |0.0096|
+# |                  |       |none  |     0|acc     |0.6210|±  |0.0095|
+# hf (pretrained=facebook/opt-2.7b,add_bos_token=True,dtype=float32), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto (32)
+# |                   Tasks                   |Version|Filter|n-shot| Metric |Value |   |Stderr|
+# |-------------------------------------------|-------|------|-----:|--------|-----:|---|-----:|
+# | - inverse_scaling_hindsight_neglect_10shot|      0|none  |     0|acc     |0.4476|±  |0.0281|
+# |                                           |       |none  |     0|acc_norm|0.4476|±  |0.0281|
+# |inverse_scaling_mc                         |N/A    |none  |     0|acc_norm|0.6291|±  |0.0095|
+# |                                           |       |none  |     0|acc     |0.6219|±  |0.0095|
+# | - inverse_scaling_neqa                    |      0|none  |     0|acc     |0.5267|±  |0.0289|
+# |                                           |       |none  |     0|acc_norm|0.5267|±  |0.0289|
+# | - inverse_scaling_quote_repetition        |      0|none  |     0|acc     |0.9433|±  |0.0134|
+# |                                           |       |none  |     0|acc_norm|0.9433|±  |0.0134|
+# | - inverse_scaling_redefine_math           |      0|none  |     0|acc     |0.7200|±  |0.0150|
+# |                                           |       |none  |     0|acc_norm|0.7200|±  |0.0150|
+# | - inverse_scaling_winobias_antistereotype |      0|none  |     0|acc     |0.3762|±  |0.0239|
+# |                                           |       |none  |     0|acc_norm|0.4150|±  |0.0243|
+
+# |      Groups      |Version|Filter|n-shot| Metric |Value |   |Stderr|
+# |------------------|-------|------|-----:|--------|-----:|---|-----:|
+# |inverse_scaling_mc|N/A    |none  |     0|acc_norm|0.6291|±  |0.0095|
+# |                  |       |none  |     0|acc     |0.6219|±  |0.0095|

lm_eval/tasks/leaderboard/bbh_mc/_fewshot_template_yaml

-group: leaderboard_bbh
 dataset_path: SaylorTwift/bbh
 output_type: multiple_choice
 test_split: test

lm_eval/tasks/leaderboard/bbh_mc/_leaderboard_bbh.yaml

+group: leaderboard_bbh
+task:
+  - leaderboard_bbh_boolean_expressions
+  - leaderboard_bbh_causal_judgement
+  - leaderboard_bbh_date_understanding
+  - leaderboard_bbh_disambiguation_qa
+  - leaderboard_bbh_formal_fallacies
+  - leaderboard_bbh_geometric_shapes
+  - leaderboard_bbh_hyperbaton
+  - leaderboard_bbh_logical_deduction_five_objects
+  - leaderboard_bbh_logical_deduction_seven_objects
+  - leaderboard_bbh_logical_deduction_three_objects
+  - leaderboard_bbh_movie_recommendation
+  - leaderboard_bbh_navigate
+  - leaderboard_bbh_object_counting
+  - leaderboard_bbh_penguins_in_a_table
+  - leaderboard_bbh_reasoning_about_colored_objects
+  - leaderboard_bbh_ruin_names
+  - leaderboard_bbh_salient_translation_error_detection
+  - leaderboard_bbh_snarks
+  - leaderboard_bbh_sports_understanding
+  - leaderboard_bbh_temporal_sequences
+  - leaderboard_bbh_tracking_shuffled_objects_five_objects
+  - leaderboard_bbh_tracking_shuffled_objects_seven_objects
+  - leaderboard_bbh_tracking_shuffled_objects_three_objects
+  - leaderboard_bbh_web_of_lies

lm_eval/tasks/leaderboard/gpqa/_leaderboard_gpqa.yaml

+group: leaderboard_gpqa
+task:
+  - leaderboard_gpqa_diamond
+  - leaderboard_gpqa_extended
+  - leaderboard_gpqa_main

lm_eval/tasks/leaderboard/gpqa/_template_yaml

 dataset_path: Idavidrein/gpqa
-group: leaderboard_gpqa
 output_type: multiple_choice
 process_docs: !function utils.process_docs
 training_split: train

lm_eval/tasks/leaderboard/ifeval/_leaderboard_instruction_following.yaml

+group: leaderboard_instruction_following
+task:
+  - leaderboard_ifeval

lm_eval/tasks/leaderboard/ifeval/ifeval.yaml

 task: leaderboard_ifeval
-group: leaderboard_instruction_following
 dataset_path: wis-k/instruction-following-eval
 dataset_name: null
 output_type: generate_until

lm_eval/tasks/leaderboard/math/_leaderboard_math.yaml

+group: leaderboard_math_hard
+task:
+  - leaderboard_math_algebra_hard
+  - leaderboard_math_counting_and_prob_hard
+  - leaderboard_math_geometry_hard
+  - leaderboard_math_intermediate_algebra_hard
+  - leaderboard_math_num_theory_hard
+  - leaderboard_math_prealgebra_hard
+  - leaderboard_math_precalculus_hard

lm_eval/tasks/leaderboard/math/_template_yaml

-group:
-  - leaderboard_math_hard
 dataset_path: lighteval/MATH-Hard
 process_docs: !function utils.process_docs
 output_type: generate_until

lm_eval/tasks/leaderboard/musr/_musr.yaml

+group: leaderboard_musr
+task:
+  - leaderboard_musr_murder_mysteries
+  - leaderboard_musr_object_placements
+  - leaderboard_musr_team_allocation