Merge branch 'main' of https://github.com/EleutherAI/lm-evaluation-harness into mela

lm_eval/tasks/asdiv/README.md

@@ -32,7 +32,7 @@ Homepage: https://github.com/chaochun/nlu-asdiv-dataset
 }
 ```
 
-### Groups and Tasks
+### Groups, Tags, and Tasks
 
 #### Groups
 

lm_eval/tasks/babi/README.md

@@ -21,12 +21,16 @@ Homepage: https://github.com/facebookarchive/bAbI-tasks
 }
 ```
 
-### Groups and Tasks
+### Groups, Tags, and Tasks
 
 #### Groups
 
 * Not part of a group yet
 
+#### Tags
+
+* No tags applied.
+
 #### Tasks
 
 * `babi`

lm_eval/tasks/basqueglue/README.md

@@ -43,11 +43,15 @@ Homepage: `https://github.com/hitz-zentroa/latxa`
 }
 ```
 
-### Groups and Tasks
+### Groups, Tags, and Tasks
 
 #### Groups
 
-* `basque-glue`: First version of the implementation
+None.
+
+#### Tags
+
+* `basque-glue`: First version of the implementation. Calls all subtasks, but does not average.
 
 #### Tasks
 

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/README.md

@@ -21,15 +21,19 @@ Homepage: https://github.com/suzgunmirac/BIG-Bench-Hard
 }
 ```
 
-### Groups and Tasks
+### Groups, Tags, and Tasks
 
 #### Groups
 
+- `bbh`: is the same as `bbh_cot_fewshot`.
 - `bbh_zeroshot`
 - `bbh_fewshot`
 - `bbh_cot_fewshot`
 - `bbh_cot_zeroshot`
 
+#### Tags
+
+None.
 
 #### Tasks
 

lm_eval/tasks/bbh/cot_fewshot/_bbh.yaml

+group: bbh
+task:
+  - bbh_cot_fewshot_boolean_expressions
+  - bbh_cot_fewshot_causal_judgement
+  - bbh_cot_fewshot_date_understanding
+  - bbh_cot_fewshot_disambiguation_qa
+  - bbh_cot_fewshot_dyck_languages
+  - bbh_cot_fewshot_formal_fallacies
+  - bbh_cot_fewshot_geometric_shapes
+  - bbh_cot_fewshot_hyperbaton
+  - bbh_cot_fewshot_logical_deduction_five_objects
+  - bbh_cot_fewshot_logical_deduction_seven_objects
+  - bbh_cot_fewshot_logical_deduction_three_objects
+  - bbh_cot_fewshot_movie_recommendation
+  - bbh_cot_fewshot_multistep_arithmetic_two
+  - bbh_cot_fewshot_navigate
+  - bbh_cot_fewshot_object_counting
+  - bbh_cot_fewshot_penguins_in_a_table
+  - bbh_cot_fewshot_reasoning_about_colored_objects
+  - bbh_cot_fewshot_ruin_names
+  - bbh_cot_fewshot_salient_translation_error_detection
+  - bbh_cot_fewshot_snarks
+  - bbh_cot_fewshot_sports_understanding
+  - bbh_cot_fewshot_temporal_sequences
+  - bbh_cot_fewshot_tracking_shuffled_objects_five_objects
+  - bbh_cot_fewshot_tracking_shuffled_objects_seven_objects
+  - bbh_cot_fewshot_tracking_shuffled_objects_three_objects
+  - bbh_cot_fewshot_web_of_lies
+  - bbh_cot_fewshot_word_sorting
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+    filter_list: get-answer
+metadata:
+  version: 3.0

lm_eval/tasks/bbh/cot_fewshot/_bbh_cot_fewshot.yaml

+group: bbh_cot_fewshot
+task:
+  - bbh_cot_fewshot_boolean_expressions
+  - bbh_cot_fewshot_causal_judgement
+  - bbh_cot_fewshot_date_understanding
+  - bbh_cot_fewshot_disambiguation_qa
+  - bbh_cot_fewshot_dyck_languages
+  - bbh_cot_fewshot_formal_fallacies
+  - bbh_cot_fewshot_geometric_shapes
+  - bbh_cot_fewshot_hyperbaton
+  - bbh_cot_fewshot_logical_deduction_five_objects
+  - bbh_cot_fewshot_logical_deduction_seven_objects
+  - bbh_cot_fewshot_logical_deduction_three_objects
+  - bbh_cot_fewshot_movie_recommendation
+  - bbh_cot_fewshot_multistep_arithmetic_two
+  - bbh_cot_fewshot_navigate
+  - bbh_cot_fewshot_object_counting
+  - bbh_cot_fewshot_penguins_in_a_table
+  - bbh_cot_fewshot_reasoning_about_colored_objects
+  - bbh_cot_fewshot_ruin_names
+  - bbh_cot_fewshot_salient_translation_error_detection
+  - bbh_cot_fewshot_snarks
+  - bbh_cot_fewshot_sports_understanding
+  - bbh_cot_fewshot_temporal_sequences
+  - bbh_cot_fewshot_tracking_shuffled_objects_five_objects
+  - bbh_cot_fewshot_tracking_shuffled_objects_seven_objects
+  - bbh_cot_fewshot_tracking_shuffled_objects_three_objects
+  - bbh_cot_fewshot_web_of_lies
+  - bbh_cot_fewshot_word_sorting
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+    filter_list: get-answer
+metadata:
+  version: 3.0

lm_eval/tasks/bbh/cot_fewshot/_cot_fewshot_template_yaml

-group:
-- bbh
-- bbh_cot_fewshot
 dataset_path: lukaemon/bbh
 output_type: generate_until
 test_split: test
@@ -27,4 +24,4 @@ filter_list:
       - function: "take_first"
 num_fewshot: 3
 metadata:
-  version: 2.0
+  version: 3.0

lm_eval/tasks/bbh/cot_zeroshot/_bbh_cot_zeroshot.yaml

+group: bbh_cot_zeroshot
+task:
+  - bbh_cot_zeroshot_boolean_expressions
+  - bbh_cot_zeroshot_causal_judgement
+  - bbh_cot_zeroshot_date_understanding
+  - bbh_cot_zeroshot_disambiguation_qa
+  - bbh_cot_zeroshot_dyck_languages
+  - bbh_cot_zeroshot_formal_fallacies
+  - bbh_cot_zeroshot_geometric_shapes
+  - bbh_cot_zeroshot_hyperbaton
+  - bbh_cot_zeroshot_logical_deduction_five_objects
+  - bbh_cot_zeroshot_logical_deduction_seven_objects
+  - bbh_cot_zeroshot_logical_deduction_three_objects
+  - bbh_cot_zeroshot_movie_recommendation
+  - bbh_cot_zeroshot_multistep_arithmetic_two
+  - bbh_cot_zeroshot_navigate
+  - bbh_cot_zeroshot_object_counting
+  - bbh_cot_zeroshot_penguins_in_a_table
+  - bbh_cot_zeroshot_reasoning_about_colored_objects
+  - bbh_cot_zeroshot_ruin_names
+  - bbh_cot_zeroshot_salient_translation_error_detection
+  - bbh_cot_zeroshot_snarks
+  - bbh_cot_zeroshot_sports_understanding
+  - bbh_cot_zeroshot_temporal_sequences
+  - bbh_cot_zeroshot_tracking_shuffled_objects_five_objects
+  - bbh_cot_zeroshot_tracking_shuffled_objects_seven_objects
+  - bbh_cot_zeroshot_tracking_shuffled_objects_three_objects
+  - bbh_cot_zeroshot_web_of_lies
+  - bbh_cot_zeroshot_word_sorting
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+    filter_list: flexible-extract
+metadata:
+  version: 3.0

lm_eval/tasks/bbh/cot_zeroshot/_cot_zeroshot_template_yaml

-group: bbh_cot_zeroshot
 dataset_path: lukaemon/bbh
 output_type: generate_until
 test_split: test
@@ -24,4 +23,4 @@ generation_kwargs:
   temperature: 0.0
 num_fewshot: 0
 metadata:
-  version: 2.0
+  version: 3.0

lm_eval/tasks/bbh/fewshot/_bbh_fewshot.yaml

+group: bbh_fewshot
+task:
+  - bbh_fewshot_boolean_expressions
+  - bbh_fewshot_causal_judgement
+  - bbh_fewshot_date_understanding
+  - bbh_fewshot_disambiguation_qa
+  - bbh_fewshot_dyck_languages
+  - bbh_fewshot_formal_fallacies
+  - bbh_fewshot_geometric_shapes
+  - bbh_fewshot_hyperbaton
+  - bbh_fewshot_logical_deduction_five_objects
+  - bbh_fewshot_logical_deduction_seven_objects
+  - bbh_fewshot_logical_deduction_three_objects
+  - bbh_fewshot_movie_recommendation
+  - bbh_fewshot_multistep_arithmetic_two
+  - bbh_fewshot_navigate
+  - bbh_fewshot_object_counting
+  - bbh_fewshot_penguins_in_a_table
+  - bbh_fewshot_reasoning_about_colored_objects
+  - bbh_fewshot_ruin_names
+  - bbh_fewshot_salient_translation_error_detection
+  - bbh_fewshot_snarks
+  - bbh_fewshot_sports_understanding
+  - bbh_fewshot_temporal_sequences
+  - bbh_fewshot_tracking_shuffled_objects_five_objects
+  - bbh_fewshot_tracking_shuffled_objects_seven_objects
+  - bbh_fewshot_tracking_shuffled_objects_three_objects
+  - bbh_fewshot_web_of_lies
+  - bbh_fewshot_word_sorting
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 3.0

lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml

-group: bbh_fewshot
 dataset_path: lukaemon/bbh
 output_type: generate_until
 test_split: test
@@ -18,4 +17,4 @@ generation_kwargs:
   temperature: 0.0
 num_fewshot: 3
 metadata:
-  version: 1.0
+  version: 2.0

lm_eval/tasks/bbh/zeroshot/_bbh_zeroshot.yaml

+group: bbh_zeroshot
+task:
+  - bbh_zeroshot_boolean_expressions
+  - bbh_zeroshot_causal_judgement
+  - bbh_zeroshot_date_understanding
+  - bbh_zeroshot_disambiguation_qa
+  - bbh_zeroshot_dyck_languages
+  - bbh_zeroshot_formal_fallacies
+  - bbh_zeroshot_geometric_shapes
+  - bbh_zeroshot_hyperbaton
+  - bbh_zeroshot_logical_deduction_five_objects
+  - bbh_zeroshot_logical_deduction_seven_objects
+  - bbh_zeroshot_logical_deduction_three_objects
+  - bbh_zeroshot_movie_recommendation
+  - bbh_zeroshot_multistep_arithmetic_two
+  - bbh_zeroshot_navigate
+  - bbh_zeroshot_object_counting
+  - bbh_zeroshot_penguins_in_a_table
+  - bbh_zeroshot_reasoning_about_colored_objects
+  - bbh_zeroshot_ruin_names
+  - bbh_zeroshot_salient_translation_error_detection
+  - bbh_zeroshot_snarks
+  - bbh_zeroshot_sports_understanding
+  - bbh_zeroshot_temporal_sequences
+  - bbh_zeroshot_tracking_shuffled_objects_five_objects
+  - bbh_zeroshot_tracking_shuffled_objects_seven_objects
+  - bbh_zeroshot_tracking_shuffled_objects_three_objects
+  - bbh_zeroshot_web_of_lies
+  - bbh_zeroshot_word_sorting
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+    filter_list: flexible-extract
+metadata:
+  version: 3.0

lm_eval/tasks/bbh/zeroshot/_zeroshot_template_yaml

-group: bbh_zeroshot
 dataset_path: lukaemon/bbh
 output_type: generate_until
 test_split: test
@@ -24,4 +23,4 @@ generation_kwargs:
   temperature: 0.0
 num_fewshot: 0
 metadata:
-  version: 2.0
+  version: 3.0

lm_eval/tasks/belebele/_belebele.yaml

+group: belebele
+task:
+  - belebele_acm_Arab
+  - belebele_arz_Arab
+  - belebele_ceb_Latn
+  - belebele_fin_Latn
+  - belebele_hin_Deva
+  - belebele_ita_Latn
+  - belebele_khm_Khmr
+  - belebele_lvs_Latn
+  - belebele_npi_Deva
+  - belebele_pol_Latn
+  - belebele_slv_Latn
+  - belebele_swe_Latn
+  - belebele_tso_Latn
+  - belebele_xho_Latn
+  - belebele_afr_Latn
+  - belebele_asm_Beng
+  - belebele_ces_Latn
+  - belebele_fra_Latn
+  - belebele_hin_Latn
+  - belebele_jav_Latn
+  - belebele_kin_Latn
+  - belebele_mal_Mlym
+  - belebele_npi_Latn
+  - belebele_por_Latn
+  - belebele_sna_Latn
+  - belebele_swh_Latn
+  - belebele_tur_Latn
+  - belebele_yor_Latn
+  - belebele_als_Latn
+  - belebele_azj_Latn
+  - belebele_ckb_Arab
+  - belebele_fuv_Latn
+  - belebele_hrv_Latn
+  - belebele_jpn_Jpan
+  - belebele_kir_Cyrl
+  - belebele_mar_Deva
+  - belebele_nso_Latn
+  - belebele_snd_Arab
+  - belebele_tam_Taml
+  - belebele_ukr_Cyrl
+  - belebele_zho_Hans
+  - belebele_amh_Ethi
+  - belebele_bam_Latn
+  - belebele_dan_Latn
+  - belebele_gaz_Latn
+  - belebele_hun_Latn
+  - belebele_kac_Latn
+  - belebele_kor_Hang
+  - belebele_mkd_Cyrl
+  - belebele_nya_Latn
+  - belebele_ron_Latn
+  - belebele_som_Latn
+  - belebele_tel_Telu
+  - belebele_urd_Arab
+  - belebele_zho_Hant
+  - belebele_apc_Arab
+  - belebele_ben_Beng
+  - belebele_deu_Latn
+  - belebele_grn_Latn
+  - belebele_hye_Armn
+  - belebele_kan_Knda
+  - belebele_lao_Laoo
+  - belebele_mlt_Latn
+  - belebele_ory_Orya
+  - belebele_rus_Cyrl
+  - belebele_sot_Latn
+  - belebele_tgk_Cyrl
+  - belebele_urd_Latn
+  - belebele_zsm_Latn
+  - belebele_arb_Arab
+  - belebele_ben_Latn
+  - belebele_ell_Grek
+  - belebele_guj_Gujr
+  - belebele_ibo_Latn
+  - belebele_kat_Geor
+  - belebele_lin_Latn
+  - belebele_mri_Latn
+  - belebele_pan_Guru
+  - belebele_shn_Mymr
+  - belebele_spa_Latn
+  - belebele_tgl_Latn
+  - belebele_uzn_Latn
+  - belebele_zul_Latn
+  - belebele_arb_Latn
+  - belebele_bod_Tibt
+  - belebele_eng_Latn
+  - belebele_hat_Latn
+  - belebele_ilo_Latn
+  - belebele_kaz_Cyrl
+  - belebele_lit_Latn
+  - belebele_mya_Mymr
+  - belebele_pbt_Arab
+  - belebele_sin_Latn
+  - belebele_srp_Cyrl
+  - belebele_tha_Thai
+  - belebele_vie_Latn
+  - belebele_ars_Arab
+  - belebele_bul_Cyrl
+  - belebele_est_Latn
+  - belebele_hau_Latn
+  - belebele_ind_Latn
+  - belebele_kea_Latn
+  - belebele_lug_Latn
+  - belebele_nld_Latn
+  - belebele_pes_Arab
+  - belebele_sin_Sinh
+  - belebele_ssw_Latn
+  - belebele_tir_Ethi
+  - belebele_war_Latn
+  - belebele_ary_Arab
+  - belebele_cat_Latn
+  - belebele_eus_Latn
+  - belebele_heb_Hebr
+  - belebele_isl_Latn
+  - belebele_khk_Cyrl
+  - belebele_luo_Latn
+  - belebele_nob_Latn
+  - belebele_plt_Latn
+  - belebele_slk_Latn
+  - belebele_sun_Latn
+  - belebele_tsn_Latn
+  - belebele_wol_Latn
+aggregate_metric_list:
+  - aggregation: mean
+    metric: acc
+    weight_by_size: true
+  - aggregation: mean
+    metric: acc_norm
+    weight_by_size: true
+metadata:
+  version: 0.1