Merge remote-tracking branch 'origin/big-refactor' into calibration

lm_eval/tasks/belebele/belebele_ars_Arab.yaml

+"dataset_name": "ars_Arab"
+"include": "_default_template_yaml"
+"task": "belebele_ars_Arab"

lm_eval/tasks/belebele/belebele_ary_Arab.yaml

+"dataset_name": "ary_Arab"
+"include": "_default_template_yaml"
+"task": "belebele_ary_Arab"

lm_eval/tasks/belebele/belebele_arz_Arab.yaml

+"dataset_name": "arz_Arab"
+"include": "_default_template_yaml"
+"task": "belebele_arz_Arab"

lm_eval/tasks/belebele/belebele_asm_Beng.yaml

+"dataset_name": "asm_Beng"
+"include": "_default_template_yaml"
+"task": "belebele_asm_Beng"

lm_eval/tasks/belebele/belebele_azj_Latn.yaml

+"dataset_name": "azj_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_azj_Latn"

lm_eval/tasks/belebele/belebele_bam_Latn.yaml

+"dataset_name": "bam_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_bam_Latn"

lm_eval/tasks/belebele/belebele_ben_Beng.yaml

+"dataset_name": "ben_Beng"
+"include": "_default_template_yaml"
+"task": "belebele_ben_Beng"

lm_eval/tasks/belebele/belebele_ben_Latn.yaml

+"dataset_name": "ben_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_ben_Latn"

lm_eval/tasks/belebele/belebele_bod_Tibt.yaml

+"dataset_name": "bod_Tibt"
+"include": "_default_template_yaml"
+"task": "belebele_bod_Tibt"

lm_eval/tasks/belebele/belebele_bul_Cyrl.yaml

+"dataset_name": "bul_Cyrl"
+"include": "_default_template_yaml"
+"task": "belebele_bul_Cyrl"

lm_eval/tasks/belebele/belebele_cat_Latn.yaml

+"dataset_name": "cat_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_cat_Latn"

lm_eval/tasks/belebele/belebele_ceb_Latn.yaml

+"dataset_name": "ceb_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_ceb_Latn"

lm_eval/tasks/belebele/belebele_ces_Latn.yaml

+"dataset_name": "ces_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_ces_Latn"

lm_eval/tasks/belebele/belebele_ckb_Arab.yaml

+"dataset_name": "ckb_Arab"
+"include": "_default_template_yaml"
+"task": "belebele_ckb_Arab"

lm_eval/tasks/belebele/belebele_dan_Latn.yaml

+"dataset_name": "dan_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_dan_Latn"

lm_eval/tasks/belebele/belebele_deu_Latn.yaml

+"dataset_name": "deu_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_deu_Latn"

lm_eval/tasks/belebele/belebele_ell_Grek.yaml

+"dataset_name": "ell_Grek"
+"include": "_default_template_yaml"
+"task": "belebele_ell_Grek"

lm_eval/tasks/belebele/belebele_eng_Latn.yaml

+"dataset_name": "eng_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_eng_Latn"

lm_eval/tasks/belebele/belebele_est_Latn.yaml

+"dataset_name": "est_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_est_Latn"

lm_eval/tasks/belebele/belebele_eus_Latn.yaml

+"dataset_name": "eus_Latn"
+"include": "_default_template_yaml"
+"task": "belebele_eus_Latn"