feat: remove invalid LMEval tasks

Author: adolfo-ab

tests/model_explainability/lm_eval/data/new_task_list.csv

@@ -2492,7 +2492,6 @@ kobest,4306,true,Unknown,false,3
 kobest_sentineg,4306,true,skt/kobest_v1,false,3
 kobest_copa,4306,true,skt/kobest_v1,false,3
 realtoxicityprompts,4024,true,allenai/real-toxicity-prompts,false,3
-tinyMMLU,3799,true,tinyBenchmarks/tinyMMLU,false,3
 arabicmmlu_biology_high_school,3548,true,MBZUAI/ArabicMMLU,false,3
 arabicmmlu_other_tasks,3548,false,Unknown,false,3
 arabicmmlu_economics_middle_school,3548,true,MBZUAI/ArabicMMLU,false,3
@@ -3075,70 +3074,11 @@ mmlu_prox_en,2213,false,Unknown,false,3
 gsm_plus_mini,2097,true,qintongli/GSM-Plus,false,3
 gsm_plus,2097,true,qintongli/GSM-Plus,false,3
 afrobench_mmlu_tasks,2022,false,Unknown,false,3
-tmlu_CAP_earth_science,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_chinese,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_civics,2013,true,miulab/tmlu,false,3
-tmlu_basic_traditional_chinese_medicine,2013,true,miulab/tmlu,false,3
-tmlu_AST_biology,2013,true,miulab/tmlu,false,3
-tmlu_nutritionist,2013,true,miulab/tmlu,false,3
-tmlu_CAP_chinese,2013,true,miulab/tmlu,false,3
-tmlu_clinical_traditional_chinese_medicine,2013,true,miulab/tmlu,false,3
-tmlu_humanities_tasks,2013,false,Unknown,false,3
-tmlu_tour_guide,2013,true,miulab/tmlu,false,3
-tmlu_teacher_qualification,2013,true,miulab/tmlu,false,3
-tmlu,2013,true,Unknown,false,3
-tmlu_stem_tasks,2013,false,Unknown,false,3
-tmlu_other_tasks,2013,false,Unknown,false,3
-tmlu_taiwan_specific_tasks,2013,false,Unknown,false,3
-tmlu_social_sciences_tasks,2013,false,Unknown,false,3
-tmlu_AST_history,2013,true,miulab/tmlu,false,3
-tmlu_CAP_biology,2013,true,miulab/tmlu,false,3
-tmlu_clinical_psychologist,2013,true,miulab/tmlu,false,3
-tmlu_AST_geography,2013,true,miulab/tmlu,false,3
-tmlu_CAP_civics,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_earth_science,2013,true,miulab/tmlu,false,3
-tmlu_AST_chinese,2013,true,miulab/tmlu,false,3
-tmlu_taiwan_tourist_resources,2013,true,miulab/tmlu,false,3
-tmlu_CAP_history,2013,true,miulab/tmlu,false,3
-tmlu_CAP_geography,2013,true,miulab/tmlu,false,3
-tmlu_CAP_chemistry,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_biology,2013,true,miulab/tmlu,false,3
-tmlu_AST_civics,2013,true,miulab/tmlu,false,3
-tmlu_lawyer_qualification,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_chemistry,2013,true,miulab/tmlu,false,3
-tmlu_driving_rule,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_history,2013,true,miulab/tmlu,false,3
-tmlu_accountant,2013,true,miulab/tmlu,false,3
-tmlu_tour_leader,2013,true,miulab/tmlu,false,3
-tmlu_AST_chemistry,2013,true,miulab/tmlu,false,3
-tmlu_GSAT_geography,2013,true,miulab/tmlu,false,3
 gsm8k_platinum_cot_self_consistency,2002,false,Unknown,false,3
 gsm8k_platinum_cot_llama,2002,false,Unknown,false,3
 gsm8k_platinum_cot_zeroshot,2002,false,Unknown,false,3
 gsm8k_platinum_cot,2002,false,Unknown,false,3
 gsm8k_platinum,2002,false,Unknown,false,3
-pile_ubuntu-irc,1990,true,EleutherAI/pile,false,3
-pile_philpapers,1990,true,EleutherAI/pile,false,3
-pile_bookcorpus2,1990,true,EleutherAI/pile,false,3
-pile_uspto,1990,true,EleutherAI/pile,false,3
-pile_stackexchange,1990,true,EleutherAI/pile,false,3
-pile_pubmed-abstracts,1990,true,EleutherAI/pile,false,3
-pile_arxiv,1990,true,EleutherAI/pile,false,3
-pile_wikipedia,1990,true,EleutherAI/pile,false,3
-pile_nih-exporter,1990,true,EleutherAI/pile,false,3
-pile_freelaw,1990,true,EleutherAI/pile,false,3
-pile_hackernews,1990,true,EleutherAI/pile,false,3
-pile_pile-cc,1990,true,EleutherAI/pile,false,3
-pile_github,1990,true,EleutherAI/pile,false,3
-pile_books3,1990,true,EleutherAI/pile,false,3
-pile_dm-mathematics,1990,true,EleutherAI/pile,false,3
-pile_youtubesubtitles,1990,true,EleutherAI/pile,false,3
-pile_openwebtext2,1990,true,EleutherAI/pile,false,3
-pile_opensubtitles,1990,true,EleutherAI/pile,false,3
-pile_pubmed-central,1990,true,EleutherAI/pile,false,3
-pile_europarl,1990,true,EleutherAI/pile,false,3
-pile_enron,1990,true,EleutherAI/pile,false,3
-pile_gutenberg,1990,true,EleutherAI/pile,false,3
 darijammlu_natural_science,1912,false,Unknown,false,3
 darijammlu_high_school_psychology,1912,false,Unknown,false,3
 darijammlu_high_school_world_history,1912,false,Unknown,false,3
@@ -3188,8 +3128,6 @@ darijammlu_ar_mmlu,1912,false,Unknown,false,3
 darijammlu,1912,false,Unknown,false,3
 darijammlu_professional_psychology,1912,false,Unknown,false,3
 darijammlu_geography,1912,false,Unknown,false,3
-tinyHellaswag,1871,true,tinyBenchmarks/tinyHellaswag,false,3
-tinyBenchmarks,1739,true,Unknown,false,3
 t0_eval,1693,true,Unknown,false,3
 swag,1691,true,swag,false,3
 qa4mre_2013,1650,true,qa4mre,false,3
@@ -3703,8 +3641,6 @@ masakhanews_lin_prompt_2,1380,false,Unknown,false,3
 masakhanews_yor_prompt_2,1380,false,Unknown,false,3
 masakhanews_tir_prompt_5,1380,false,Unknown,false,3
 masakhanews_fra_prompt_5,1380,false,Unknown,false,3
-tinyArc,1354,true,tinyBenchmarks/tinyAI2_arc,false,3
-tinyGSM8k,1344,true,tinyBenchmarks/tinyGSM8k,false,3
 japanese_leaderboard,1330,true,Unknown,false,3
 arabic_leaderboard_alghafa_multiple_choice_rating_sentiment_task,1326,true,OALL/AlGhafa-Arabic-LLM-Benchmark-Native,false,3
 arabic_leaderboard_alghafa_meta_ar_msa,1326,true,OALL/AlGhafa-Arabic-LLM-Benchmark-Native,false,3
@@ -4006,7 +3942,6 @@ sib_kon_prompt_2,1258,false,Unknown,false,3
 sib_som_prompt_2,1258,false,Unknown,false,3
 sib_kab_prompt_2,1258,false,Unknown,false,3
 sib_yor_prompt_2,1258,false,Unknown,false,3
-tinyWinogrande,1244,true,tinyBenchmarks/tinyWinogrande,false,3
 agieval_math,1236,true,hails/agieval-math,false,3
 bbq_generate_disambig,1198,false,Unknown,false,3
 bbq,1198,false,Unknown,false,3
@@ -4509,8 +4444,6 @@ careqa_en,843,false,Unknown,false,3
 careqa_open,843,false,Unknown,false,3
 careqa_open_perplexity,843,false,Unknown,false,3
 careqa_es,843,false,Unknown,false,3
-tinyTruthfulQA_mc1,824,true,tinyBenchmarks/tinyTruthfulQA,false,3
-tinyTruthfulQA,824,true,tinyBenchmarks/tinyTruthfulQA,false,3
 xcopa_eu,823,true,HiTZ/XCOPA-eu,false,3
 AraDiCE_ArabicMMLU_high_social-science_geography_lev,818,true,QCRI/AraDICE-ArabicMMLU-lev,false,3
 AraDiCE_ArabicMMLU_primary_social-science_geography_lev,818,true,QCRI/AraDICE-ArabicMMLU-lev,false,3