diff --git a/FallenMerick__Smart-Lemon-Cookie-7B/.ipynb_checkpoints/results_2024-06-28T14-56-07.716918-checkpoint.json b/FallenMerick__Smart-Lemon-Cookie-7B/.ipynb_checkpoints/results_2024-06-28T14-56-07.716918-checkpoint.json new file mode 100644 index 0000000000000000000000000000000000000000..9a2f104e8cba6d24182ceadad21a8f788548c78a --- /dev/null +++ b/FallenMerick__Smart-Lemon-Cookie-7B/.ipynb_checkpoints/results_2024-06-28T14-56-07.716918-checkpoint.json @@ -0,0 +1,4035 @@ +{ + "results": { + "Open LLM Leaderboard": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571269, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "acc_norm,none": 0.8349384697699305, + "acc_norm_stderr,none": 0.0034656728893589055, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "acc,none": 0.6524833304898358, + "acc_stderr,none": 0.002755144452920947, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": "Open LLM Leaderboard" + }, + "arc_challenge": { + "acc,none": 0.6390784982935154, + "acc_stderr,none": 0.014034761386175458, + "acc_norm,none": 0.6706484641638225, + "acc_norm_stderr,none": 0.013734057652635473, + "alias": " - arc_challenge" + }, + "gsm8k": { + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571267, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "alias": " - gsm8k" + }, + "hellaswag": { + "acc,none": 0.6714797849034057, + "acc_stderr,none": 0.00468715199479105, + "acc_norm,none": 0.8541127265484963, + "acc_norm_stderr,none": 0.0035227174995242872, + "alias": " - hellaswag" + }, + "mmlu": { + "acc,none": 0.6370175188719556, + "acc_stderr,none": 0.0038187579064371084, + "alias": " - mmlu" + }, + "mmlu_humanities": { + "alias": " - humanities", + "acc,none": 0.593836344314559, + "acc_stderr,none": 0.006701956606258013 + }, + "mmlu_formal_logic": { + "alias": " - formal_logic", + "acc,none": 0.4523809523809524, + "acc_stderr,none": 0.044518079590553275 + }, + "mmlu_high_school_european_history": { + "alias": " - high_school_european_history", + "acc,none": 0.7757575757575758, + "acc_stderr,none": 0.03256866661681102 + }, + "mmlu_high_school_us_history": { + "alias": " - high_school_us_history", + "acc,none": 0.8480392156862745, + "acc_stderr,none": 0.025195658428931792 + }, + "mmlu_high_school_world_history": { + "alias": " - high_school_world_history", + "acc,none": 0.8227848101265823, + "acc_stderr,none": 0.024856364184503238 + }, + "mmlu_international_law": { + "alias": " - international_law", + "acc,none": 0.8181818181818182, + "acc_stderr,none": 0.03520893951097654 + }, + "mmlu_jurisprudence": { + "alias": " - jurisprudence", + "acc,none": 0.8240740740740741, + "acc_stderr,none": 0.036809181416738807 + }, + "mmlu_logical_fallacies": { + "alias": " - logical_fallacies", + "acc,none": 0.7852760736196319, + "acc_stderr,none": 0.03226219377286774 + }, + "mmlu_moral_disputes": { + "alias": " - moral_disputes", + "acc,none": 0.7225433526011561, + "acc_stderr,none": 0.024105712607754307 + }, + "mmlu_moral_scenarios": { + "alias": " - moral_scenarios", + "acc,none": 0.37206703910614525, + "acc_stderr,none": 0.016165847583563302 + }, + "mmlu_philosophy": { + "alias": " - philosophy", + "acc,none": 0.7170418006430869, + "acc_stderr,none": 0.02558306248998483 + }, + "mmlu_prehistory": { + "alias": " - prehistory", + "acc,none": 0.7345679012345679, + "acc_stderr,none": 0.02456922360046085 + }, + "mmlu_professional_law": { + "alias": " - professional_law", + "acc,none": 0.47979139504563234, + "acc_stderr,none": 0.01275980142776756 + }, + "mmlu_world_religions": { + "alias": " - world_religions", + "acc,none": 0.847953216374269, + "acc_stderr,none": 0.02753912288906145 + }, + "mmlu_other": { + "alias": " - other", + "acc,none": 0.702928870292887, + "acc_stderr,none": 0.007868349963426575 + }, + "mmlu_business_ethics": { + "alias": " - business_ethics", + "acc,none": 0.57, + "acc_stderr,none": 0.049756985195624284 + }, + "mmlu_clinical_knowledge": { + "alias": " - clinical_knowledge", + "acc,none": 0.6943396226415094, + "acc_stderr,none": 0.028353298073322666 + }, + "mmlu_college_medicine": { + "alias": " - college_medicine", + "acc,none": 0.6763005780346821, + "acc_stderr,none": 0.0356760379963917 + }, + "mmlu_global_facts": { + "alias": " - global_facts", + "acc,none": 0.32, + "acc_stderr,none": 0.046882617226215034 + }, + "mmlu_human_aging": { + "alias": " - human_aging", + "acc,none": 0.695067264573991, + "acc_stderr,none": 0.030898610882477518 + }, + "mmlu_management": { + "alias": " - management", + "acc,none": 0.7864077669902912, + "acc_stderr,none": 0.04058042015646034 + }, + "mmlu_marketing": { + "alias": " - marketing", + "acc,none": 0.8675213675213675, + "acc_stderr,none": 0.022209309073165616 + }, + "mmlu_medical_genetics": { + "alias": " - medical_genetics", + "acc,none": 0.7, + "acc_stderr,none": 0.046056618647183814 + }, + "mmlu_miscellaneous": { + "alias": " - miscellaneous", + "acc,none": 0.8275862068965517, + "acc_stderr,none": 0.013507943909371802 + }, + "mmlu_nutrition": { + "alias": " - nutrition", + "acc,none": 0.7320261437908496, + "acc_stderr,none": 0.025360603796242553 + }, + "mmlu_professional_accounting": { + "alias": " - professional_accounting", + "acc,none": 0.48936170212765956, + "acc_stderr,none": 0.029820747191422466 + }, + "mmlu_professional_medicine": { + "alias": " - professional_medicine", + "acc,none": 0.6838235294117647, + "acc_stderr,none": 0.028245687391462913 + }, + "mmlu_virology": { + "alias": " - virology", + "acc,none": 0.536144578313253, + "acc_stderr,none": 0.03882310850890593 + }, + "mmlu_social_sciences": { + "alias": " - social_sciences", + "acc,none": 0.7409814754631134, + "acc_stderr,none": 0.0077233871931608284 + }, + "mmlu_econometrics": { + "alias": " - econometrics", + "acc,none": 0.5087719298245614, + "acc_stderr,none": 0.04702880432049615 + }, + "mmlu_high_school_geography": { + "alias": " - high_school_geography", + "acc,none": 0.803030303030303, + "acc_stderr,none": 0.028335609732463362 + }, + "mmlu_high_school_government_and_politics": { + "alias": " - high_school_government_and_politics", + "acc,none": 0.8808290155440415, + "acc_stderr,none": 0.023381935348121427 + }, + "mmlu_high_school_macroeconomics": { + "alias": " - high_school_macroeconomics", + "acc,none": 0.6717948717948717, + "acc_stderr,none": 0.023807633198657266 + }, + "mmlu_high_school_microeconomics": { + "alias": " - high_school_microeconomics", + "acc,none": 0.7100840336134454, + "acc_stderr,none": 0.029472485833136094 + }, + "mmlu_high_school_psychology": { + "alias": " - high_school_psychology", + "acc,none": 0.8366972477064221, + "acc_stderr,none": 0.01584825580650152 + }, + "mmlu_human_sexuality": { + "alias": " - human_sexuality", + "acc,none": 0.7557251908396947, + "acc_stderr,none": 0.037683359597287434 + }, + "mmlu_professional_psychology": { + "alias": " - professional_psychology", + "acc,none": 0.6454248366013072, + "acc_stderr,none": 0.019353360547553693 + }, + "mmlu_public_relations": { + "alias": " - public_relations", + "acc,none": 0.6727272727272727, + "acc_stderr,none": 0.0449429086625209 + }, + "mmlu_security_studies": { + "alias": " - security_studies", + "acc,none": 0.7346938775510204, + "acc_stderr,none": 0.028263889943784603 + }, + "mmlu_sociology": { + "alias": " - sociology", + "acc,none": 0.8507462686567164, + "acc_stderr,none": 0.0251969298748271 + }, + "mmlu_us_foreign_policy": { + "alias": " - us_foreign_policy", + "acc,none": 0.87, + "acc_stderr,none": 0.03379976689896308 + }, + "mmlu_stem": { + "alias": " - stem", + "acc,none": 0.5350459879479861, + "acc_stderr,none": 0.008502490762016599 + }, + "mmlu_abstract_algebra": { + "alias": " - abstract_algebra", + "acc,none": 0.35, + "acc_stderr,none": 0.0479372485441102 + }, + "mmlu_anatomy": { + "alias": " - anatomy", + "acc,none": 0.6222222222222222, + "acc_stderr,none": 0.04188307537595853 + }, + "mmlu_astronomy": { + "alias": " - astronomy", + "acc,none": 0.6578947368421053, + "acc_stderr,none": 0.038607315993160904 + }, + "mmlu_college_biology": { + "alias": " - college_biology", + "acc,none": 0.7638888888888888, + "acc_stderr,none": 0.03551446610810826 + }, + "mmlu_college_chemistry": { + "alias": " - college_chemistry", + "acc,none": 0.47, + "acc_stderr,none": 0.05016135580465919 + }, + "mmlu_college_computer_science": { + "alias": " - college_computer_science", + "acc,none": 0.54, + "acc_stderr,none": 0.05009082659620332 + }, + "mmlu_college_mathematics": { + "alias": " - college_mathematics", + "acc,none": 0.4, + "acc_stderr,none": 0.049236596391733084 + }, + "mmlu_college_physics": { + "alias": " - college_physics", + "acc,none": 0.4117647058823529, + "acc_stderr,none": 0.04897104952726366 + }, + "mmlu_computer_security": { + "alias": " - computer_security", + "acc,none": 0.8, + "acc_stderr,none": 0.04020151261036846 + }, + "mmlu_conceptual_physics": { + "alias": " - conceptual_physics", + "acc,none": 0.5787234042553191, + "acc_stderr,none": 0.03227834510146268 + }, + "mmlu_electrical_engineering": { + "alias": " - electrical_engineering", + "acc,none": 0.5793103448275863, + "acc_stderr,none": 0.04113914981189261 + }, + "mmlu_elementary_mathematics": { + "alias": " - elementary_mathematics", + "acc,none": 0.3968253968253968, + "acc_stderr,none": 0.025197101074246483 + }, + "mmlu_high_school_biology": { + "alias": " - high_school_biology", + "acc,none": 0.7774193548387097, + "acc_stderr,none": 0.023664216671642525 + }, + "mmlu_high_school_chemistry": { + "alias": " - high_school_chemistry", + "acc,none": 0.5073891625615764, + "acc_stderr,none": 0.0351760354036101 + }, + "mmlu_high_school_computer_science": { + "alias": " - high_school_computer_science", + "acc,none": 0.72, + "acc_stderr,none": 0.045126085985421276 + }, + "mmlu_high_school_mathematics": { + "alias": " - high_school_mathematics", + "acc,none": 0.34814814814814815, + "acc_stderr,none": 0.029045600290616258 + }, + "mmlu_high_school_physics": { + "alias": " - high_school_physics", + "acc,none": 0.3509933774834437, + "acc_stderr,none": 0.03896981964257375 + }, + "mmlu_high_school_statistics": { + "alias": " - high_school_statistics", + "acc,none": 0.5046296296296297, + "acc_stderr,none": 0.03409825519163572 + }, + "mmlu_machine_learning": { + "alias": " - machine_learning", + "acc,none": 0.4732142857142857, + "acc_stderr,none": 0.047389751192741546 + }, + "truthfulqa": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "acc,none": 0.5163944376892423, + "acc_stderr,none": 0.011629460414206856, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa" + }, + "truthfulqa_gen": { + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374931, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799713, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa_gen" + }, + "truthfulqa_mc1": { + "acc,none": 0.4320685434516524, + "acc_stderr,none": 0.01734120239498826, + "alias": " - truthfulqa_mc1" + }, + "truthfulqa_mc2": { + "acc,none": 0.6007203319268323, + "acc_stderr,none": 0.015500325725560432, + "alias": " - truthfulqa_mc2" + }, + "winogrande": { + "acc,none": 0.7734806629834254, + "acc_stderr,none": 0.01176414905469832, + "alias": " - winogrande" + }, + "eq_bench": { + "eqbench,none": 68.12395548919517, + "eqbench_stderr,none": 2.1553076487761045, + "percent_parseable,none": 100.0, + "percent_parseable_stderr,none": 0.0, + "alias": "eq_bench" + } + }, + "groups": { + "Open LLM Leaderboard": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571269, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "acc_norm,none": 0.8349384697699305, + "acc_norm_stderr,none": 0.0034656728893589055, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "acc,none": 0.6524833304898358, + "acc_stderr,none": 0.002755144452920947, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": "Open LLM Leaderboard" + }, + "mmlu": { + "acc,none": 0.6370175188719556, + "acc_stderr,none": 0.0038187579064371084, + "alias": " - mmlu" + }, + "mmlu_humanities": { + "alias": " - humanities", + "acc,none": 0.593836344314559, + "acc_stderr,none": 0.006701956606258013 + }, + "mmlu_other": { + "alias": " - other", + "acc,none": 0.702928870292887, + "acc_stderr,none": 0.007868349963426575 + }, + "mmlu_social_sciences": { + "alias": " - social_sciences", + "acc,none": 0.7409814754631134, + "acc_stderr,none": 0.0077233871931608284 + }, + "mmlu_stem": { + "alias": " - stem", + "acc,none": 0.5350459879479861, + "acc_stderr,none": 0.008502490762016599 + }, + "truthfulqa": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "acc,none": 0.5163944376892423, + "acc_stderr,none": 0.011629460414206856, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa" + } + }, + "group_subtasks": { + "eq_bench": [], + "truthfulqa": [ + "truthfulqa_gen", + "truthfulqa_mc1", + "truthfulqa_mc2" + ], + "mmlu_stem": [ + "mmlu_high_school_chemistry", + "mmlu_college_physics", + "mmlu_college_mathematics", + "mmlu_astronomy", + "mmlu_high_school_physics", + "mmlu_computer_security", + "mmlu_elementary_mathematics", + "mmlu_electrical_engineering", + "mmlu_college_biology", + "mmlu_machine_learning", + "mmlu_high_school_biology", + "mmlu_high_school_mathematics", + "mmlu_anatomy", + "mmlu_high_school_statistics", + "mmlu_college_chemistry", + "mmlu_conceptual_physics", + "mmlu_high_school_computer_science", + "mmlu_college_computer_science", + "mmlu_abstract_algebra" + ], + "mmlu_other": [ + "mmlu_professional_medicine", + "mmlu_professional_accounting", + "mmlu_management", + "mmlu_global_facts", + "mmlu_college_medicine", + "mmlu_business_ethics", + "mmlu_nutrition", + "mmlu_medical_genetics", + "mmlu_virology", + "mmlu_human_aging", + "mmlu_clinical_knowledge", + "mmlu_miscellaneous", + "mmlu_marketing" + ], + "mmlu_social_sciences": [ + "mmlu_high_school_psychology", + "mmlu_sociology", + "mmlu_high_school_government_and_politics", + "mmlu_public_relations", + "mmlu_high_school_macroeconomics", + "mmlu_high_school_geography", + "mmlu_high_school_microeconomics", + "mmlu_security_studies", + "mmlu_us_foreign_policy", + "mmlu_professional_psychology", + "mmlu_human_sexuality", + "mmlu_econometrics" + ], + "mmlu_humanities": [ + "mmlu_high_school_european_history", + "mmlu_formal_logic", + "mmlu_moral_scenarios", + "mmlu_moral_disputes", + "mmlu_world_religions", + "mmlu_high_school_world_history", + "mmlu_logical_fallacies", + "mmlu_international_law", + "mmlu_philosophy", + "mmlu_professional_law", + "mmlu_high_school_us_history", + "mmlu_prehistory", + "mmlu_jurisprudence" + ], + "mmlu": [ + "mmlu_humanities", + "mmlu_social_sciences", + "mmlu_other", + "mmlu_stem" + ], + "Open LLM Leaderboard": [ + "gsm8k", + "winogrande", + "mmlu", + "truthfulqa", + "hellaswag", + "arc_challenge" + ] + }, + "configs": { + "arc_challenge": { + "task": "arc_challenge", + "group": "Open LLM Leaderboard", + "dataset_path": "allenai/ai2_arc", + "dataset_name": "ARC-Challenge", + "training_split": "train", + "validation_split": "validation", + "test_split": "test", + "fewshot_split": "validation", + "doc_to_text": "Question: {{question}}\nAnswer:", + "doc_to_target": "{{choices.label.index(answerKey)}}", + "doc_to_choice": "{{choices.text}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 25, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "acc_norm", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "Question: {{question}}\nAnswer:", + "metadata": { + "version": 1.0 + } + }, + "eq_bench": { + "task": "eq_bench", + "dataset_path": "pbevan11/EQ-Bench", + "validation_split": "validation", + "doc_to_text": "prompt", + "doc_to_target": "reference_answer_fullscale", + "process_results": "def calculate_score_fullscale(docs, results):\n reference = eval(docs[\"reference_answer_fullscale\"])\n user = dict(re.findall(r\"(\\w+):\\s+(\\d+)\", results[0]))\n # First check that the emotions specified in the answer match those in the reference\n if len(user.items()) != 4:\n # print('! Error: 4 emotions were not returned')\n # print(user)\n return {\"eqbench\": 0, \"percent_parseable\": 0}\n emotions_dict = {}\n for emotion, user_emotion_score in user.items():\n for i in range(1, 5):\n if emotion == reference[f\"emotion{i}\"]:\n emotions_dict[emotion] = True\n if len(emotions_dict) != 4:\n print(\"! Error: emotions did not match reference\")\n print(user)\n return {\"eqbench\": 0, \"percent_parseable\": 0}\n\n difference_tally = (\n 0 # Tally of differerence from reference answers for this question\n )\n\n # Iterate over each emotion in the user's answers.\n for emotion, user_emotion_score in user.items():\n # If this emotion is in the reference, calculate the difference between the user's score and the reference score.\n for i in range(1, 5):\n if emotion == reference[f\"emotion{i}\"]:\n d = abs(\n float(user_emotion_score) - float(reference[f\"emotion{i}_score\"])\n )\n # this will be a value between 0 and 10\n if d == 0:\n scaled_difference = 0\n elif d <= 5:\n # S-shaped scaling function\n # https://www.desmos.com/calculator\n # 6.5\\cdot\\ \\frac{1}{\\left(1\\ +\\ e^{\\left(-1.2\\cdot\\left(x-4\\right)\\right)}\\right)}\n scaled_difference = 6.5 * (1 / (1 + math.e ** (-1.2 * (d - 4))))\n\n else:\n scaled_difference = d\n difference_tally += scaled_difference\n\n # Inverting the difference tally so that the closer the answer is to reference, the higher the score.\n # The adjustment constant is chosen such that answering randomly produces a score of zero.\n adjust_const = 0.7477\n final_score = 10 - (difference_tally * adjust_const)\n final_score_percent = final_score * 10\n\n return {\"eqbench\": final_score_percent, \"percent_parseable\": 100}\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "eqbench", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "percent_parseable", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "do_sample": false, + "temperature": 0.0, + "max_gen_toks": 80, + "until": [ + "\n\n" + ] + }, + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 2.1 + } + }, + "gsm8k": { + "task": "gsm8k", + "group": "Open LLM Leaderboard", + "dataset_path": "gsm8k", + "dataset_name": "main", + "training_split": "train", + "test_split": "test", + "fewshot_split": "train", + "doc_to_text": "Question: {{question}}\nAnswer:", + "doc_to_target": "{{answer}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 5, + "metric_list": [ + { + "metric": "exact_match", + "aggregation": "mean", + "higher_is_better": true, + "ignore_case": true, + "ignore_punctuation": false, + "regexes_to_ignore": [ + ",", + "\\$", + "(?s).*#### ", + "\\.$" + ] + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "until": [ + "Question:", + "", + "<|im_end|>" + ], + "do_sample": false, + "temperature": 0.0 + }, + "repeats": 1, + "filter_list": [ + { + "name": "strict-match", + "filter": [ + { + "function": "regex", + "regex_pattern": "#### (\\-?[0-9\\.\\,]+)" + }, + { + "function": "take_first" + } + ] + }, + { + "name": "flexible-extract", + "filter": [ + { + "function": "regex", + "group_select": -1, + "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" + }, + { + "function": "take_first" + } + ] + } + ], + "should_decontaminate": false, + "metadata": { + "version": 3.0 + } + }, + "hellaswag": { + "task": "hellaswag", + "group": "Open LLM Leaderboard", + "dataset_path": "hellaswag", + "training_split": "train", + "validation_split": "validation", + "fewshot_split": "train", + "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n", + "doc_to_text": "{{query}}", + "doc_to_target": "{{label}}", + "doc_to_choice": "choices", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 10, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "acc_norm", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 1.0 + } + }, + "mmlu_abstract_algebra": { + "task": "mmlu_abstract_algebra", + "task_alias": "abstract_algebra", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "abstract_algebra", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_anatomy": { + "task": "mmlu_anatomy", + "task_alias": "anatomy", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "anatomy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about anatomy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_astronomy": { + "task": "mmlu_astronomy", + "task_alias": "astronomy", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "astronomy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about astronomy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_business_ethics": { + "task": "mmlu_business_ethics", + "task_alias": "business_ethics", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "business_ethics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about business ethics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_clinical_knowledge": { + "task": "mmlu_clinical_knowledge", + "task_alias": "clinical_knowledge", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "clinical_knowledge", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_biology": { + "task": "mmlu_college_biology", + "task_alias": "college_biology", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_biology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college biology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_chemistry": { + "task": "mmlu_college_chemistry", + "task_alias": "college_chemistry", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_chemistry", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_computer_science": { + "task": "mmlu_college_computer_science", + "task_alias": "college_computer_science", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_computer_science", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college computer science.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_mathematics": { + "task": "mmlu_college_mathematics", + "task_alias": "college_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_medicine": { + "task": "mmlu_college_medicine", + "task_alias": "college_medicine", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_medicine", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college medicine.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_physics": { + "task": "mmlu_college_physics", + "task_alias": "college_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_computer_security": { + "task": "mmlu_computer_security", + "task_alias": "computer_security", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "computer_security", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about computer security.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_conceptual_physics": { + "task": "mmlu_conceptual_physics", + "task_alias": "conceptual_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "conceptual_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_econometrics": { + "task": "mmlu_econometrics", + "task_alias": "econometrics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "econometrics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about econometrics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_electrical_engineering": { + "task": "mmlu_electrical_engineering", + "task_alias": "electrical_engineering", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "electrical_engineering", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_elementary_mathematics": { + "task": "mmlu_elementary_mathematics", + "task_alias": "elementary_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "elementary_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_formal_logic": { + "task": "mmlu_formal_logic", + "task_alias": "formal_logic", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "formal_logic", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about formal logic.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_global_facts": { + "task": "mmlu_global_facts", + "task_alias": "global_facts", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "global_facts", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about global facts.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_biology": { + "task": "mmlu_high_school_biology", + "task_alias": "high_school_biology", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_biology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school biology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_chemistry": { + "task": "mmlu_high_school_chemistry", + "task_alias": "high_school_chemistry", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_chemistry", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_computer_science": { + "task": "mmlu_high_school_computer_science", + "task_alias": "high_school_computer_science", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_computer_science", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_european_history": { + "task": "mmlu_high_school_european_history", + "task_alias": "high_school_european_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_european_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school european history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_geography": { + "task": "mmlu_high_school_geography", + "task_alias": "high_school_geography", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_geography", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school geography.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_government_and_politics": { + "task": "mmlu_high_school_government_and_politics", + "task_alias": "high_school_government_and_politics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_government_and_politics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_macroeconomics": { + "task": "mmlu_high_school_macroeconomics", + "task_alias": "high_school_macroeconomics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_macroeconomics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_mathematics": { + "task": "mmlu_high_school_mathematics", + "task_alias": "high_school_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_microeconomics": { + "task": "mmlu_high_school_microeconomics", + "task_alias": "high_school_microeconomics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_microeconomics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_physics": { + "task": "mmlu_high_school_physics", + "task_alias": "high_school_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_psychology": { + "task": "mmlu_high_school_psychology", + "task_alias": "high_school_psychology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_psychology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_statistics": { + "task": "mmlu_high_school_statistics", + "task_alias": "high_school_statistics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_statistics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_us_history": { + "task": "mmlu_high_school_us_history", + "task_alias": "high_school_us_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_us_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school us history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_world_history": { + "task": "mmlu_high_school_world_history", + "task_alias": "high_school_world_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_world_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school world history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_human_aging": { + "task": "mmlu_human_aging", + "task_alias": "human_aging", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "human_aging", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about human aging.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_human_sexuality": { + "task": "mmlu_human_sexuality", + "task_alias": "human_sexuality", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "human_sexuality", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_international_law": { + "task": "mmlu_international_law", + "task_alias": "international_law", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "international_law", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about international law.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_jurisprudence": { + "task": "mmlu_jurisprudence", + "task_alias": "jurisprudence", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "jurisprudence", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_logical_fallacies": { + "task": "mmlu_logical_fallacies", + "task_alias": "logical_fallacies", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "logical_fallacies", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_machine_learning": { + "task": "mmlu_machine_learning", + "task_alias": "machine_learning", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "machine_learning", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about machine learning.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_management": { + "task": "mmlu_management", + "task_alias": "management", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "management", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about management.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_marketing": { + "task": "mmlu_marketing", + "task_alias": "marketing", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "marketing", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about marketing.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_medical_genetics": { + "task": "mmlu_medical_genetics", + "task_alias": "medical_genetics", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "medical_genetics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_miscellaneous": { + "task": "mmlu_miscellaneous", + "task_alias": "miscellaneous", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "miscellaneous", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_moral_disputes": { + "task": "mmlu_moral_disputes", + "task_alias": "moral_disputes", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "moral_disputes", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_moral_scenarios": { + "task": "mmlu_moral_scenarios", + "task_alias": "moral_scenarios", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "moral_scenarios", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_nutrition": { + "task": "mmlu_nutrition", + "task_alias": "nutrition", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "nutrition", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about nutrition.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_philosophy": { + "task": "mmlu_philosophy", + "task_alias": "philosophy", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "philosophy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about philosophy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_prehistory": { + "task": "mmlu_prehistory", + "task_alias": "prehistory", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "prehistory", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about prehistory.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_accounting": { + "task": "mmlu_professional_accounting", + "task_alias": "professional_accounting", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_accounting", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_law": { + "task": "mmlu_professional_law", + "task_alias": "professional_law", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_law", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional law.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_medicine": { + "task": "mmlu_professional_medicine", + "task_alias": "professional_medicine", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_medicine", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_psychology": { + "task": "mmlu_professional_psychology", + "task_alias": "professional_psychology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_psychology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_public_relations": { + "task": "mmlu_public_relations", + "task_alias": "public_relations", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "public_relations", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about public relations.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_security_studies": { + "task": "mmlu_security_studies", + "task_alias": "security_studies", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "security_studies", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about security studies.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_sociology": { + "task": "mmlu_sociology", + "task_alias": "sociology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "sociology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about sociology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_us_foreign_policy": { + "task": "mmlu_us_foreign_policy", + "task_alias": "us_foreign_policy", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "us_foreign_policy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_virology": { + "task": "mmlu_virology", + "task_alias": "virology", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "virology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about virology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_world_religions": { + "task": "mmlu_world_religions", + "task_alias": "world_religions", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "world_religions", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about world religions.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "truthfulqa_gen": { + "task": "truthfulqa_gen", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "generation", + "validation_split": "validation", + "process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n return dataset.map(preprocess_function)\n", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}", + "doc_to_target": " ", + "process_results": "def process_results_gen(doc, results):\n completion = results[0]\n true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n all_refs = true_refs + false_refs\n\n # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n # # BLEURT\n # bleurt_scores_true = self.bleurt.compute(\n # predictions=[completion] * len(true_refs), references=true_refs\n # )[\"scores\"]\n # bleurt_scores_false = self.bleurt.compute(\n # predictions=[completion] * len(false_refs), references=false_refs\n # )[\"scores\"]\n # bleurt_correct = max(bleurt_scores_true)\n # bleurt_incorrect = max(bleurt_scores_false)\n # bleurt_max = bleurt_correct\n # bleurt_diff = bleurt_correct - bleurt_incorrect\n # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n # BLEU\n bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n bleu_max = bleu_correct\n bleu_diff = bleu_correct - bleu_incorrect\n bleu_acc = int(bleu_correct > bleu_incorrect)\n\n # ROUGE-N\n rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n # ROUGE-1\n rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n rouge1_max = rouge1_correct\n rouge1_diff = rouge1_correct - rouge1_incorrect\n rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n # ROUGE-2\n rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n rouge2_max = rouge2_correct\n rouge2_diff = rouge2_correct - rouge2_incorrect\n rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n # ROUGE-L\n rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n rougeL_max = rougeL_correct\n rougeL_diff = rougeL_correct - rougeL_incorrect\n rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n return {\n # \"bleurt_max\": bleurt_max,\n # \"bleurt_acc\": bleurt_acc,\n # \"bleurt_diff\": bleurt_diff,\n \"bleu_max\": bleu_max,\n \"bleu_acc\": bleu_acc,\n \"bleu_diff\": bleu_diff,\n \"rouge1_max\": rouge1_max,\n \"rouge1_acc\": rouge1_acc,\n \"rouge1_diff\": rouge1_diff,\n \"rouge2_max\": rouge2_max,\n \"rouge2_acc\": rouge2_acc,\n \"rouge2_diff\": rouge2_diff,\n \"rougeL_max\": rougeL_max,\n \"rougeL_acc\": rougeL_acc,\n \"rougeL_diff\": rougeL_diff,\n }\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "bleu_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "bleu_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "bleu_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_diff", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "until": [ + "\n\n" + ], + "do_sample": false + }, + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 3.0 + } + }, + "truthfulqa_mc1": { + "task": "truthfulqa_mc1", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "multiple_choice", + "validation_split": "validation", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}", + "doc_to_target": 0, + "doc_to_choice": "{{mc1_targets.choices}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 2.0 + } + }, + "truthfulqa_mc2": { + "task": "truthfulqa_mc2", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "multiple_choice", + "validation_split": "validation", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}", + "doc_to_target": 0, + "doc_to_choice": "{{mc2_targets.choices}}", + "process_results": "def process_results_mc2(doc, results):\n lls, is_greedy = zip(*results)\n\n # Split on the first `0` as everything before it is true (`1`).\n split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n # Compute the normalized probability mass for the correct answer.\n ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n p_true = p_true / (sum(p_true) + sum(p_false))\n\n return {\"acc\": sum(p_true)}\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 2.0 + } + }, + "winogrande": { + "task": "winogrande", + "group": "Open LLM Leaderboard", + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "training_split": "train", + "validation_split": "validation", + "fewshot_split": "train", + "doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n", + "doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n", + "doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "sentence", + "metadata": { + "version": 1.0 + } + } + }, + "versions": { + "arc_challenge": 1.0, + "eq_bench": 2.1, + "gsm8k": 3.0, + "hellaswag": 1.0, + "mmlu_abstract_algebra": 0.0, + "mmlu_anatomy": 0.0, + "mmlu_astronomy": 0.0, + "mmlu_business_ethics": 0.0, + "mmlu_clinical_knowledge": 0.0, + "mmlu_college_biology": 0.0, + "mmlu_college_chemistry": 0.0, + "mmlu_college_computer_science": 0.0, + "mmlu_college_mathematics": 0.0, + "mmlu_college_medicine": 0.0, + "mmlu_college_physics": 0.0, + "mmlu_computer_security": 0.0, + "mmlu_conceptual_physics": 0.0, + "mmlu_econometrics": 0.0, + "mmlu_electrical_engineering": 0.0, + "mmlu_elementary_mathematics": 0.0, + "mmlu_formal_logic": 0.0, + "mmlu_global_facts": 0.0, + "mmlu_high_school_biology": 0.0, + "mmlu_high_school_chemistry": 0.0, + "mmlu_high_school_computer_science": 0.0, + "mmlu_high_school_european_history": 0.0, + "mmlu_high_school_geography": 0.0, + "mmlu_high_school_government_and_politics": 0.0, + "mmlu_high_school_macroeconomics": 0.0, + "mmlu_high_school_mathematics": 0.0, + "mmlu_high_school_microeconomics": 0.0, + "mmlu_high_school_physics": 0.0, + "mmlu_high_school_psychology": 0.0, + "mmlu_high_school_statistics": 0.0, + "mmlu_high_school_us_history": 0.0, + "mmlu_high_school_world_history": 0.0, + "mmlu_human_aging": 0.0, + "mmlu_human_sexuality": 0.0, + "mmlu_international_law": 0.0, + "mmlu_jurisprudence": 0.0, + "mmlu_logical_fallacies": 0.0, + "mmlu_machine_learning": 0.0, + "mmlu_management": 0.0, + "mmlu_marketing": 0.0, + "mmlu_medical_genetics": 0.0, + "mmlu_miscellaneous": 0.0, + "mmlu_moral_disputes": 0.0, + "mmlu_moral_scenarios": 0.0, + "mmlu_nutrition": 0.0, + "mmlu_philosophy": 0.0, + "mmlu_prehistory": 0.0, + "mmlu_professional_accounting": 0.0, + "mmlu_professional_law": 0.0, + "mmlu_professional_medicine": 0.0, + "mmlu_professional_psychology": 0.0, + "mmlu_public_relations": 0.0, + "mmlu_security_studies": 0.0, + "mmlu_sociology": 0.0, + "mmlu_us_foreign_policy": 0.0, + "mmlu_virology": 0.0, + "mmlu_world_religions": 0.0, + "truthfulqa_gen": 3.0, + "truthfulqa_mc1": 2.0, + "truthfulqa_mc2": 2.0, + "winogrande": 1.0 + }, + "n-shot": { + "Open LLM Leaderboard": 5, + "arc_challenge": 25, + "eq_bench": 0, + "gsm8k": 5, + "hellaswag": 10, + "mmlu": 0, + "mmlu_abstract_algebra": 5, + "mmlu_anatomy": 5, + "mmlu_astronomy": 5, + "mmlu_business_ethics": 5, + "mmlu_clinical_knowledge": 5, + "mmlu_college_biology": 5, + "mmlu_college_chemistry": 5, + "mmlu_college_computer_science": 5, + "mmlu_college_mathematics": 5, + "mmlu_college_medicine": 5, + "mmlu_college_physics": 5, + "mmlu_computer_security": 5, + "mmlu_conceptual_physics": 5, + "mmlu_econometrics": 5, + "mmlu_electrical_engineering": 5, + "mmlu_elementary_mathematics": 5, + "mmlu_formal_logic": 5, + "mmlu_global_facts": 5, + "mmlu_high_school_biology": 5, + "mmlu_high_school_chemistry": 5, + "mmlu_high_school_computer_science": 5, + "mmlu_high_school_european_history": 5, + "mmlu_high_school_geography": 5, + "mmlu_high_school_government_and_politics": 5, + "mmlu_high_school_macroeconomics": 5, + "mmlu_high_school_mathematics": 5, + "mmlu_high_school_microeconomics": 5, + "mmlu_high_school_physics": 5, + "mmlu_high_school_psychology": 5, + "mmlu_high_school_statistics": 5, + "mmlu_high_school_us_history": 5, + "mmlu_high_school_world_history": 5, + "mmlu_human_aging": 5, + "mmlu_human_sexuality": 5, + "mmlu_humanities": 5, + "mmlu_international_law": 5, + "mmlu_jurisprudence": 5, + "mmlu_logical_fallacies": 5, + "mmlu_machine_learning": 5, + "mmlu_management": 5, + "mmlu_marketing": 5, + "mmlu_medical_genetics": 5, + "mmlu_miscellaneous": 5, + "mmlu_moral_disputes": 5, + "mmlu_moral_scenarios": 5, + "mmlu_nutrition": 5, + "mmlu_other": 5, + "mmlu_philosophy": 5, + "mmlu_prehistory": 5, + "mmlu_professional_accounting": 5, + "mmlu_professional_law": 5, + "mmlu_professional_medicine": 5, + "mmlu_professional_psychology": 5, + "mmlu_public_relations": 5, + "mmlu_security_studies": 5, + "mmlu_social_sciences": 5, + "mmlu_sociology": 5, + "mmlu_stem": 5, + "mmlu_us_foreign_policy": 5, + "mmlu_virology": 5, + "mmlu_world_religions": 5, + "truthfulqa": 0, + "truthfulqa_gen": 0, + "truthfulqa_mc1": 0, + "truthfulqa_mc2": 0, + "winogrande": 5 + }, + "higher_is_better": { + "Open LLM Leaderboard": { + "exact_match": true, + "acc": true, + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true, + "acc_norm": true + }, + "arc_challenge": { + "acc": true, + "acc_norm": true + }, + "eq_bench": { + "eqbench": true, + "percent_parseable": true + }, + "gsm8k": { + "exact_match": true + }, + "hellaswag": { + "acc": true, + "acc_norm": true + }, + "mmlu": { + "acc": true + }, + "mmlu_abstract_algebra": { + "acc": true + }, + "mmlu_anatomy": { + "acc": true + }, + "mmlu_astronomy": { + "acc": true + }, + "mmlu_business_ethics": { + "acc": true + }, + "mmlu_clinical_knowledge": { + "acc": true + }, + "mmlu_college_biology": { + "acc": true + }, + "mmlu_college_chemistry": { + "acc": true + }, + "mmlu_college_computer_science": { + "acc": true + }, + "mmlu_college_mathematics": { + "acc": true + }, + "mmlu_college_medicine": { + "acc": true + }, + "mmlu_college_physics": { + "acc": true + }, + "mmlu_computer_security": { + "acc": true + }, + "mmlu_conceptual_physics": { + "acc": true + }, + "mmlu_econometrics": { + "acc": true + }, + "mmlu_electrical_engineering": { + "acc": true + }, + "mmlu_elementary_mathematics": { + "acc": true + }, + "mmlu_formal_logic": { + "acc": true + }, + "mmlu_global_facts": { + "acc": true + }, + "mmlu_high_school_biology": { + "acc": true + }, + "mmlu_high_school_chemistry": { + "acc": true + }, + "mmlu_high_school_computer_science": { + "acc": true + }, + "mmlu_high_school_european_history": { + "acc": true + }, + "mmlu_high_school_geography": { + "acc": true + }, + "mmlu_high_school_government_and_politics": { + "acc": true + }, + "mmlu_high_school_macroeconomics": { + "acc": true + }, + "mmlu_high_school_mathematics": { + "acc": true + }, + "mmlu_high_school_microeconomics": { + "acc": true + }, + "mmlu_high_school_physics": { + "acc": true + }, + "mmlu_high_school_psychology": { + "acc": true + }, + "mmlu_high_school_statistics": { + "acc": true + }, + "mmlu_high_school_us_history": { + "acc": true + }, + "mmlu_high_school_world_history": { + "acc": true + }, + "mmlu_human_aging": { + "acc": true + }, + "mmlu_human_sexuality": { + "acc": true + }, + "mmlu_humanities": { + "acc": true + }, + "mmlu_international_law": { + "acc": true + }, + "mmlu_jurisprudence": { + "acc": true + }, + "mmlu_logical_fallacies": { + "acc": true + }, + "mmlu_machine_learning": { + "acc": true + }, + "mmlu_management": { + "acc": true + }, + "mmlu_marketing": { + "acc": true + }, + "mmlu_medical_genetics": { + "acc": true + }, + "mmlu_miscellaneous": { + "acc": true + }, + "mmlu_moral_disputes": { + "acc": true + }, + "mmlu_moral_scenarios": { + "acc": true + }, + "mmlu_nutrition": { + "acc": true + }, + "mmlu_other": { + "acc": true + }, + "mmlu_philosophy": { + "acc": true + }, + "mmlu_prehistory": { + "acc": true + }, + "mmlu_professional_accounting": { + "acc": true + }, + "mmlu_professional_law": { + "acc": true + }, + "mmlu_professional_medicine": { + "acc": true + }, + "mmlu_professional_psychology": { + "acc": true + }, + "mmlu_public_relations": { + "acc": true + }, + "mmlu_security_studies": { + "acc": true + }, + "mmlu_social_sciences": { + "acc": true + }, + "mmlu_sociology": { + "acc": true + }, + "mmlu_stem": { + "acc": true + }, + "mmlu_us_foreign_policy": { + "acc": true + }, + "mmlu_virology": { + "acc": true + }, + "mmlu_world_religions": { + "acc": true + }, + "truthfulqa": { + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true, + "acc": true + }, + "truthfulqa_gen": { + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true + }, + "truthfulqa_mc1": { + "acc": true + }, + "truthfulqa_mc2": { + "acc": true + }, + "winogrande": { + "acc": true + } + }, + "n-samples": { + "gsm8k": { + "original": 1319, + "effective": 1319 + }, + "winogrande": { + "original": 1267, + "effective": 1267 + }, + "mmlu_high_school_european_history": { + "original": 165, + "effective": 165 + }, + "mmlu_formal_logic": { + "original": 126, + "effective": 126 + }, + "mmlu_moral_scenarios": { + "original": 895, + "effective": 895 + }, + "mmlu_moral_disputes": { + "original": 346, + "effective": 346 + }, + "mmlu_world_religions": { + "original": 171, + "effective": 171 + }, + "mmlu_high_school_world_history": { + "original": 237, + "effective": 237 + }, + "mmlu_logical_fallacies": { + "original": 163, + "effective": 163 + }, + "mmlu_international_law": { + "original": 121, + "effective": 121 + }, + "mmlu_philosophy": { + "original": 311, + "effective": 311 + }, + "mmlu_professional_law": { + "original": 1534, + "effective": 1534 + }, + "mmlu_high_school_us_history": { + "original": 204, + "effective": 204 + }, + "mmlu_prehistory": { + "original": 324, + "effective": 324 + }, + "mmlu_jurisprudence": { + "original": 108, + "effective": 108 + }, + "mmlu_high_school_psychology": { + "original": 545, + "effective": 545 + }, + "mmlu_sociology": { + "original": 201, + "effective": 201 + }, + "mmlu_high_school_government_and_politics": { + "original": 193, + "effective": 193 + }, + "mmlu_public_relations": { + "original": 110, + "effective": 110 + }, + "mmlu_high_school_macroeconomics": { + "original": 390, + "effective": 390 + }, + "mmlu_high_school_geography": { + "original": 198, + "effective": 198 + }, + "mmlu_high_school_microeconomics": { + "original": 238, + "effective": 238 + }, + "mmlu_security_studies": { + "original": 245, + "effective": 245 + }, + "mmlu_us_foreign_policy": { + "original": 100, + "effective": 100 + }, + "mmlu_professional_psychology": { + "original": 612, + "effective": 612 + }, + "mmlu_human_sexuality": { + "original": 131, + "effective": 131 + }, + "mmlu_econometrics": { + "original": 114, + "effective": 114 + }, + "mmlu_professional_medicine": { + "original": 272, + "effective": 272 + }, + "mmlu_professional_accounting": { + "original": 282, + "effective": 282 + }, + "mmlu_management": { + "original": 103, + "effective": 103 + }, + "mmlu_global_facts": { + "original": 100, + "effective": 100 + }, + "mmlu_college_medicine": { + "original": 173, + "effective": 173 + }, + "mmlu_business_ethics": { + "original": 100, + "effective": 100 + }, + "mmlu_nutrition": { + "original": 306, + "effective": 306 + }, + "mmlu_medical_genetics": { + "original": 100, + "effective": 100 + }, + "mmlu_virology": { + "original": 166, + "effective": 166 + }, + "mmlu_human_aging": { + "original": 223, + "effective": 223 + }, + "mmlu_clinical_knowledge": { + "original": 265, + "effective": 265 + }, + "mmlu_miscellaneous": { + "original": 783, + "effective": 783 + }, + "mmlu_marketing": { + "original": 234, + "effective": 234 + }, + "mmlu_high_school_chemistry": { + "original": 203, + "effective": 203 + }, + "mmlu_college_physics": { + "original": 102, + "effective": 102 + }, + "mmlu_college_mathematics": { + "original": 100, + "effective": 100 + }, + "mmlu_astronomy": { + "original": 152, + "effective": 152 + }, + "mmlu_high_school_physics": { + "original": 151, + "effective": 151 + }, + "mmlu_computer_security": { + "original": 100, + "effective": 100 + }, + "mmlu_elementary_mathematics": { + "original": 378, + "effective": 378 + }, + "mmlu_electrical_engineering": { + "original": 145, + "effective": 145 + }, + "mmlu_college_biology": { + "original": 144, + "effective": 144 + }, + "mmlu_machine_learning": { + "original": 112, + "effective": 112 + }, + "mmlu_high_school_biology": { + "original": 310, + "effective": 310 + }, + "mmlu_high_school_mathematics": { + "original": 270, + "effective": 270 + }, + "mmlu_anatomy": { + "original": 135, + "effective": 135 + }, + "mmlu_high_school_statistics": { + "original": 216, + "effective": 216 + }, + "mmlu_college_chemistry": { + "original": 100, + "effective": 100 + }, + "mmlu_conceptual_physics": { + "original": 235, + "effective": 235 + }, + "mmlu_high_school_computer_science": { + "original": 100, + "effective": 100 + }, + "mmlu_college_computer_science": { + "original": 100, + "effective": 100 + }, + "mmlu_abstract_algebra": { + "original": 100, + "effective": 100 + }, + "truthfulqa_gen": { + "original": 817, + "effective": 817 + }, + "truthfulqa_mc1": { + "original": 817, + "effective": 817 + }, + "truthfulqa_mc2": { + "original": 817, + "effective": 817 + }, + "hellaswag": { + "original": 10042, + "effective": 10042 + }, + "arc_challenge": { + "original": 1172, + "effective": 1172 + }, + "eq_bench": { + "original": 171, + "effective": 171 + } + }, + "config": { + "model": "hf", + "model_args": "pretrained=FallenMerick/Smart-Lemon-Cookie-7B,trust_remote_code=True", + "model_num_parameters": 7241732096, + "model_dtype": "torch.float16", + "model_revision": "main", + "model_sha": "24a18cbcb94c55811593f89026c6fe51331f4a57", + "batch_size": "auto", + "batch_sizes": [ + 2 + ], + "device": null, + "use_cache": null, + "limit": null, + "bootstrap_iters": 100000, + "gen_kwargs": null, + "random_seed": 0, + "numpy_seed": 1234, + "torch_seed": 1234, + "fewshot_seed": 1234 + }, + "git_hash": null, + "date": 1719550043.4933457, + "pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.5.0-1022-gcp-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA L4\nGPU 1: NVIDIA L4\n\nNvidia driver version: 555.42.02\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 24\nOn-line CPU(s) list: 0-23\nVendor ID: GenuineIntel\nModel name: Intel(R) Xeon(R) CPU @ 2.20GHz\nCPU family: 6\nModel: 85\nThread(s) per core: 2\nCore(s) per socket: 12\nSocket(s): 1\nStepping: 7\nBogoMIPS: 4400.47\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat avx512_vnni md_clear arch_capabilities\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 384 KiB (12 instances)\nL1i cache: 384 KiB (12 instances)\nL2 cache: 12 MiB (12 instances)\nL3 cache: 38.5 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0-23\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Mitigation; Clear CPU buffers; SMT Host state unknown\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown\nVulnerability Retbleed: Mitigation; Enhanced IBRS\nVulnerability Spec rstack overflow: Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT Host state unknown\n\nVersions of relevant libraries:\n[pip3] numpy==2.0.0\n[pip3] torch==2.3.1\n[pip3] triton==2.3.1\n[conda] Could not collect", + "transformers_version": "4.41.2", + "upper_git_hash": null, + "tokenizer_pad_token": [ + "", + 0 + ], + "tokenizer_eos_token": [ + "", + 2 + ], + "tokenizer_bos_token": [ + "", + 1 + ], + "eot_token_id": 2, + "max_length": 32768, + "task_hashes": {}, + "model_source": "hf", + "model_name": "FallenMerick/Smart-Lemon-Cookie-7B", + "model_name_sanitized": "FallenMerick__Smart-Lemon-Cookie-7B", + "system_instruction": null, + "system_instruction_sha": null, + "fewshot_as_multiturn": false, + "chat_template": null, + "chat_template_sha": null, + "start_time": 102426.774034499, + "end_time": 138957.776397903, + "total_evaluation_time_seconds": "36531.00236340401" +} \ No newline at end of file diff --git a/FallenMerick__Smart-Lemon-Cookie-7B/results_2024-06-28T14-56-07.716918.json b/FallenMerick__Smart-Lemon-Cookie-7B/results_2024-06-28T14-56-07.716918.json new file mode 100644 index 0000000000000000000000000000000000000000..9a2f104e8cba6d24182ceadad21a8f788548c78a --- /dev/null +++ b/FallenMerick__Smart-Lemon-Cookie-7B/results_2024-06-28T14-56-07.716918.json @@ -0,0 +1,4035 @@ +{ + "results": { + "Open LLM Leaderboard": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571269, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "acc_norm,none": 0.8349384697699305, + "acc_norm_stderr,none": 0.0034656728893589055, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "acc,none": 0.6524833304898358, + "acc_stderr,none": 0.002755144452920947, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": "Open LLM Leaderboard" + }, + "arc_challenge": { + "acc,none": 0.6390784982935154, + "acc_stderr,none": 0.014034761386175458, + "acc_norm,none": 0.6706484641638225, + "acc_norm_stderr,none": 0.013734057652635473, + "alias": " - arc_challenge" + }, + "gsm8k": { + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571267, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "alias": " - gsm8k" + }, + "hellaswag": { + "acc,none": 0.6714797849034057, + "acc_stderr,none": 0.00468715199479105, + "acc_norm,none": 0.8541127265484963, + "acc_norm_stderr,none": 0.0035227174995242872, + "alias": " - hellaswag" + }, + "mmlu": { + "acc,none": 0.6370175188719556, + "acc_stderr,none": 0.0038187579064371084, + "alias": " - mmlu" + }, + "mmlu_humanities": { + "alias": " - humanities", + "acc,none": 0.593836344314559, + "acc_stderr,none": 0.006701956606258013 + }, + "mmlu_formal_logic": { + "alias": " - formal_logic", + "acc,none": 0.4523809523809524, + "acc_stderr,none": 0.044518079590553275 + }, + "mmlu_high_school_european_history": { + "alias": " - high_school_european_history", + "acc,none": 0.7757575757575758, + "acc_stderr,none": 0.03256866661681102 + }, + "mmlu_high_school_us_history": { + "alias": " - high_school_us_history", + "acc,none": 0.8480392156862745, + "acc_stderr,none": 0.025195658428931792 + }, + "mmlu_high_school_world_history": { + "alias": " - high_school_world_history", + "acc,none": 0.8227848101265823, + "acc_stderr,none": 0.024856364184503238 + }, + "mmlu_international_law": { + "alias": " - international_law", + "acc,none": 0.8181818181818182, + "acc_stderr,none": 0.03520893951097654 + }, + "mmlu_jurisprudence": { + "alias": " - jurisprudence", + "acc,none": 0.8240740740740741, + "acc_stderr,none": 0.036809181416738807 + }, + "mmlu_logical_fallacies": { + "alias": " - logical_fallacies", + "acc,none": 0.7852760736196319, + "acc_stderr,none": 0.03226219377286774 + }, + "mmlu_moral_disputes": { + "alias": " - moral_disputes", + "acc,none": 0.7225433526011561, + "acc_stderr,none": 0.024105712607754307 + }, + "mmlu_moral_scenarios": { + "alias": " - moral_scenarios", + "acc,none": 0.37206703910614525, + "acc_stderr,none": 0.016165847583563302 + }, + "mmlu_philosophy": { + "alias": " - philosophy", + "acc,none": 0.7170418006430869, + "acc_stderr,none": 0.02558306248998483 + }, + "mmlu_prehistory": { + "alias": " - prehistory", + "acc,none": 0.7345679012345679, + "acc_stderr,none": 0.02456922360046085 + }, + "mmlu_professional_law": { + "alias": " - professional_law", + "acc,none": 0.47979139504563234, + "acc_stderr,none": 0.01275980142776756 + }, + "mmlu_world_religions": { + "alias": " - world_religions", + "acc,none": 0.847953216374269, + "acc_stderr,none": 0.02753912288906145 + }, + "mmlu_other": { + "alias": " - other", + "acc,none": 0.702928870292887, + "acc_stderr,none": 0.007868349963426575 + }, + "mmlu_business_ethics": { + "alias": " - business_ethics", + "acc,none": 0.57, + "acc_stderr,none": 0.049756985195624284 + }, + "mmlu_clinical_knowledge": { + "alias": " - clinical_knowledge", + "acc,none": 0.6943396226415094, + "acc_stderr,none": 0.028353298073322666 + }, + "mmlu_college_medicine": { + "alias": " - college_medicine", + "acc,none": 0.6763005780346821, + "acc_stderr,none": 0.0356760379963917 + }, + "mmlu_global_facts": { + "alias": " - global_facts", + "acc,none": 0.32, + "acc_stderr,none": 0.046882617226215034 + }, + "mmlu_human_aging": { + "alias": " - human_aging", + "acc,none": 0.695067264573991, + "acc_stderr,none": 0.030898610882477518 + }, + "mmlu_management": { + "alias": " - management", + "acc,none": 0.7864077669902912, + "acc_stderr,none": 0.04058042015646034 + }, + "mmlu_marketing": { + "alias": " - marketing", + "acc,none": 0.8675213675213675, + "acc_stderr,none": 0.022209309073165616 + }, + "mmlu_medical_genetics": { + "alias": " - medical_genetics", + "acc,none": 0.7, + "acc_stderr,none": 0.046056618647183814 + }, + "mmlu_miscellaneous": { + "alias": " - miscellaneous", + "acc,none": 0.8275862068965517, + "acc_stderr,none": 0.013507943909371802 + }, + "mmlu_nutrition": { + "alias": " - nutrition", + "acc,none": 0.7320261437908496, + "acc_stderr,none": 0.025360603796242553 + }, + "mmlu_professional_accounting": { + "alias": " - professional_accounting", + "acc,none": 0.48936170212765956, + "acc_stderr,none": 0.029820747191422466 + }, + "mmlu_professional_medicine": { + "alias": " - professional_medicine", + "acc,none": 0.6838235294117647, + "acc_stderr,none": 0.028245687391462913 + }, + "mmlu_virology": { + "alias": " - virology", + "acc,none": 0.536144578313253, + "acc_stderr,none": 0.03882310850890593 + }, + "mmlu_social_sciences": { + "alias": " - social_sciences", + "acc,none": 0.7409814754631134, + "acc_stderr,none": 0.0077233871931608284 + }, + "mmlu_econometrics": { + "alias": " - econometrics", + "acc,none": 0.5087719298245614, + "acc_stderr,none": 0.04702880432049615 + }, + "mmlu_high_school_geography": { + "alias": " - high_school_geography", + "acc,none": 0.803030303030303, + "acc_stderr,none": 0.028335609732463362 + }, + "mmlu_high_school_government_and_politics": { + "alias": " - high_school_government_and_politics", + "acc,none": 0.8808290155440415, + "acc_stderr,none": 0.023381935348121427 + }, + "mmlu_high_school_macroeconomics": { + "alias": " - high_school_macroeconomics", + "acc,none": 0.6717948717948717, + "acc_stderr,none": 0.023807633198657266 + }, + "mmlu_high_school_microeconomics": { + "alias": " - high_school_microeconomics", + "acc,none": 0.7100840336134454, + "acc_stderr,none": 0.029472485833136094 + }, + "mmlu_high_school_psychology": { + "alias": " - high_school_psychology", + "acc,none": 0.8366972477064221, + "acc_stderr,none": 0.01584825580650152 + }, + "mmlu_human_sexuality": { + "alias": " - human_sexuality", + "acc,none": 0.7557251908396947, + "acc_stderr,none": 0.037683359597287434 + }, + "mmlu_professional_psychology": { + "alias": " - professional_psychology", + "acc,none": 0.6454248366013072, + "acc_stderr,none": 0.019353360547553693 + }, + "mmlu_public_relations": { + "alias": " - public_relations", + "acc,none": 0.6727272727272727, + "acc_stderr,none": 0.0449429086625209 + }, + "mmlu_security_studies": { + "alias": " - security_studies", + "acc,none": 0.7346938775510204, + "acc_stderr,none": 0.028263889943784603 + }, + "mmlu_sociology": { + "alias": " - sociology", + "acc,none": 0.8507462686567164, + "acc_stderr,none": 0.0251969298748271 + }, + "mmlu_us_foreign_policy": { + "alias": " - us_foreign_policy", + "acc,none": 0.87, + "acc_stderr,none": 0.03379976689896308 + }, + "mmlu_stem": { + "alias": " - stem", + "acc,none": 0.5350459879479861, + "acc_stderr,none": 0.008502490762016599 + }, + "mmlu_abstract_algebra": { + "alias": " - abstract_algebra", + "acc,none": 0.35, + "acc_stderr,none": 0.0479372485441102 + }, + "mmlu_anatomy": { + "alias": " - anatomy", + "acc,none": 0.6222222222222222, + "acc_stderr,none": 0.04188307537595853 + }, + "mmlu_astronomy": { + "alias": " - astronomy", + "acc,none": 0.6578947368421053, + "acc_stderr,none": 0.038607315993160904 + }, + "mmlu_college_biology": { + "alias": " - college_biology", + "acc,none": 0.7638888888888888, + "acc_stderr,none": 0.03551446610810826 + }, + "mmlu_college_chemistry": { + "alias": " - college_chemistry", + "acc,none": 0.47, + "acc_stderr,none": 0.05016135580465919 + }, + "mmlu_college_computer_science": { + "alias": " - college_computer_science", + "acc,none": 0.54, + "acc_stderr,none": 0.05009082659620332 + }, + "mmlu_college_mathematics": { + "alias": " - college_mathematics", + "acc,none": 0.4, + "acc_stderr,none": 0.049236596391733084 + }, + "mmlu_college_physics": { + "alias": " - college_physics", + "acc,none": 0.4117647058823529, + "acc_stderr,none": 0.04897104952726366 + }, + "mmlu_computer_security": { + "alias": " - computer_security", + "acc,none": 0.8, + "acc_stderr,none": 0.04020151261036846 + }, + "mmlu_conceptual_physics": { + "alias": " - conceptual_physics", + "acc,none": 0.5787234042553191, + "acc_stderr,none": 0.03227834510146268 + }, + "mmlu_electrical_engineering": { + "alias": " - electrical_engineering", + "acc,none": 0.5793103448275863, + "acc_stderr,none": 0.04113914981189261 + }, + "mmlu_elementary_mathematics": { + "alias": " - elementary_mathematics", + "acc,none": 0.3968253968253968, + "acc_stderr,none": 0.025197101074246483 + }, + "mmlu_high_school_biology": { + "alias": " - high_school_biology", + "acc,none": 0.7774193548387097, + "acc_stderr,none": 0.023664216671642525 + }, + "mmlu_high_school_chemistry": { + "alias": " - high_school_chemistry", + "acc,none": 0.5073891625615764, + "acc_stderr,none": 0.0351760354036101 + }, + "mmlu_high_school_computer_science": { + "alias": " - high_school_computer_science", + "acc,none": 0.72, + "acc_stderr,none": 0.045126085985421276 + }, + "mmlu_high_school_mathematics": { + "alias": " - high_school_mathematics", + "acc,none": 0.34814814814814815, + "acc_stderr,none": 0.029045600290616258 + }, + "mmlu_high_school_physics": { + "alias": " - high_school_physics", + "acc,none": 0.3509933774834437, + "acc_stderr,none": 0.03896981964257375 + }, + "mmlu_high_school_statistics": { + "alias": " - high_school_statistics", + "acc,none": 0.5046296296296297, + "acc_stderr,none": 0.03409825519163572 + }, + "mmlu_machine_learning": { + "alias": " - machine_learning", + "acc,none": 0.4732142857142857, + "acc_stderr,none": 0.047389751192741546 + }, + "truthfulqa": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "acc,none": 0.5163944376892423, + "acc_stderr,none": 0.011629460414206856, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa" + }, + "truthfulqa_gen": { + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374931, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799713, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa_gen" + }, + "truthfulqa_mc1": { + "acc,none": 0.4320685434516524, + "acc_stderr,none": 0.01734120239498826, + "alias": " - truthfulqa_mc1" + }, + "truthfulqa_mc2": { + "acc,none": 0.6007203319268323, + "acc_stderr,none": 0.015500325725560432, + "alias": " - truthfulqa_mc2" + }, + "winogrande": { + "acc,none": 0.7734806629834254, + "acc_stderr,none": 0.01176414905469832, + "alias": " - winogrande" + }, + "eq_bench": { + "eqbench,none": 68.12395548919517, + "eqbench_stderr,none": 2.1553076487761045, + "percent_parseable,none": 100.0, + "percent_parseable_stderr,none": 0.0, + "alias": "eq_bench" + } + }, + "groups": { + "Open LLM Leaderboard": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "exact_match,flexible-extract": 0.6573161485974223, + "exact_match_stderr,flexible-extract": 0.013073030230827912, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "exact_match,strict-match": 0.6497346474601972, + "exact_match_stderr,strict-match": 0.013140409455571269, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "acc_norm,none": 0.8349384697699305, + "acc_norm_stderr,none": 0.0034656728893589055, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "acc,none": 0.6524833304898358, + "acc_stderr,none": 0.002755144452920947, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": "Open LLM Leaderboard" + }, + "mmlu": { + "acc,none": 0.6370175188719556, + "acc_stderr,none": 0.0038187579064371084, + "alias": " - mmlu" + }, + "mmlu_humanities": { + "alias": " - humanities", + "acc,none": 0.593836344314559, + "acc_stderr,none": 0.006701956606258013 + }, + "mmlu_other": { + "alias": " - other", + "acc,none": 0.702928870292887, + "acc_stderr,none": 0.007868349963426575 + }, + "mmlu_social_sciences": { + "alias": " - social_sciences", + "acc,none": 0.7409814754631134, + "acc_stderr,none": 0.0077233871931608284 + }, + "mmlu_stem": { + "alias": " - stem", + "acc,none": 0.5350459879479861, + "acc_stderr,none": 0.008502490762016599 + }, + "truthfulqa": { + "bleu_acc,none": 0.48592411260709917, + "bleu_acc_stderr,none": 0.01749656371704277, + "rouge1_diff,none": 2.0497625977348237, + "rouge1_diff_stderr,none": 0.8467979858374932, + "rouge1_acc,none": 0.5067319461444308, + "rouge1_acc_stderr,none": 0.017501914492655368, + "rouge2_diff,none": 1.3428910448034004, + "rouge2_diff_stderr,none": 0.9648647176231531, + "rougeL_acc,none": 0.4981640146878825, + "rougeL_acc_stderr,none": 0.017503383046877072, + "bleu_max,none": 20.940311645567302, + "bleu_max_stderr,none": 0.7173140178916005, + "rouge2_acc,none": 0.4320685434516524, + "rouge2_acc_stderr,none": 0.01734120239498827, + "rouge1_max,none": 46.177982007870185, + "rouge1_max_stderr,none": 0.8131363401138358, + "rouge2_max,none": 32.18242146861712, + "rouge2_max_stderr,none": 0.9183747194799712, + "rougeL_max,none": 42.81466100258748, + "rougeL_max_stderr,none": 0.8340477381054907, + "acc,none": 0.5163944376892423, + "acc_stderr,none": 0.011629460414206856, + "bleu_diff,none": 1.3935266971798104, + "bleu_diff_stderr,none": 0.6400373603862807, + "rougeL_diff,none": 1.718464887616239, + "rougeL_diff_stderr,none": 0.8631878996298543, + "alias": " - truthfulqa" + } + }, + "group_subtasks": { + "eq_bench": [], + "truthfulqa": [ + "truthfulqa_gen", + "truthfulqa_mc1", + "truthfulqa_mc2" + ], + "mmlu_stem": [ + "mmlu_high_school_chemistry", + "mmlu_college_physics", + "mmlu_college_mathematics", + "mmlu_astronomy", + "mmlu_high_school_physics", + "mmlu_computer_security", + "mmlu_elementary_mathematics", + "mmlu_electrical_engineering", + "mmlu_college_biology", + "mmlu_machine_learning", + "mmlu_high_school_biology", + "mmlu_high_school_mathematics", + "mmlu_anatomy", + "mmlu_high_school_statistics", + "mmlu_college_chemistry", + "mmlu_conceptual_physics", + "mmlu_high_school_computer_science", + "mmlu_college_computer_science", + "mmlu_abstract_algebra" + ], + "mmlu_other": [ + "mmlu_professional_medicine", + "mmlu_professional_accounting", + "mmlu_management", + "mmlu_global_facts", + "mmlu_college_medicine", + "mmlu_business_ethics", + "mmlu_nutrition", + "mmlu_medical_genetics", + "mmlu_virology", + "mmlu_human_aging", + "mmlu_clinical_knowledge", + "mmlu_miscellaneous", + "mmlu_marketing" + ], + "mmlu_social_sciences": [ + "mmlu_high_school_psychology", + "mmlu_sociology", + "mmlu_high_school_government_and_politics", + "mmlu_public_relations", + "mmlu_high_school_macroeconomics", + "mmlu_high_school_geography", + "mmlu_high_school_microeconomics", + "mmlu_security_studies", + "mmlu_us_foreign_policy", + "mmlu_professional_psychology", + "mmlu_human_sexuality", + "mmlu_econometrics" + ], + "mmlu_humanities": [ + "mmlu_high_school_european_history", + "mmlu_formal_logic", + "mmlu_moral_scenarios", + "mmlu_moral_disputes", + "mmlu_world_religions", + "mmlu_high_school_world_history", + "mmlu_logical_fallacies", + "mmlu_international_law", + "mmlu_philosophy", + "mmlu_professional_law", + "mmlu_high_school_us_history", + "mmlu_prehistory", + "mmlu_jurisprudence" + ], + "mmlu": [ + "mmlu_humanities", + "mmlu_social_sciences", + "mmlu_other", + "mmlu_stem" + ], + "Open LLM Leaderboard": [ + "gsm8k", + "winogrande", + "mmlu", + "truthfulqa", + "hellaswag", + "arc_challenge" + ] + }, + "configs": { + "arc_challenge": { + "task": "arc_challenge", + "group": "Open LLM Leaderboard", + "dataset_path": "allenai/ai2_arc", + "dataset_name": "ARC-Challenge", + "training_split": "train", + "validation_split": "validation", + "test_split": "test", + "fewshot_split": "validation", + "doc_to_text": "Question: {{question}}\nAnswer:", + "doc_to_target": "{{choices.label.index(answerKey)}}", + "doc_to_choice": "{{choices.text}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 25, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "acc_norm", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "Question: {{question}}\nAnswer:", + "metadata": { + "version": 1.0 + } + }, + "eq_bench": { + "task": "eq_bench", + "dataset_path": "pbevan11/EQ-Bench", + "validation_split": "validation", + "doc_to_text": "prompt", + "doc_to_target": "reference_answer_fullscale", + "process_results": "def calculate_score_fullscale(docs, results):\n reference = eval(docs[\"reference_answer_fullscale\"])\n user = dict(re.findall(r\"(\\w+):\\s+(\\d+)\", results[0]))\n # First check that the emotions specified in the answer match those in the reference\n if len(user.items()) != 4:\n # print('! Error: 4 emotions were not returned')\n # print(user)\n return {\"eqbench\": 0, \"percent_parseable\": 0}\n emotions_dict = {}\n for emotion, user_emotion_score in user.items():\n for i in range(1, 5):\n if emotion == reference[f\"emotion{i}\"]:\n emotions_dict[emotion] = True\n if len(emotions_dict) != 4:\n print(\"! Error: emotions did not match reference\")\n print(user)\n return {\"eqbench\": 0, \"percent_parseable\": 0}\n\n difference_tally = (\n 0 # Tally of differerence from reference answers for this question\n )\n\n # Iterate over each emotion in the user's answers.\n for emotion, user_emotion_score in user.items():\n # If this emotion is in the reference, calculate the difference between the user's score and the reference score.\n for i in range(1, 5):\n if emotion == reference[f\"emotion{i}\"]:\n d = abs(\n float(user_emotion_score) - float(reference[f\"emotion{i}_score\"])\n )\n # this will be a value between 0 and 10\n if d == 0:\n scaled_difference = 0\n elif d <= 5:\n # S-shaped scaling function\n # https://www.desmos.com/calculator\n # 6.5\\cdot\\ \\frac{1}{\\left(1\\ +\\ e^{\\left(-1.2\\cdot\\left(x-4\\right)\\right)}\\right)}\n scaled_difference = 6.5 * (1 / (1 + math.e ** (-1.2 * (d - 4))))\n\n else:\n scaled_difference = d\n difference_tally += scaled_difference\n\n # Inverting the difference tally so that the closer the answer is to reference, the higher the score.\n # The adjustment constant is chosen such that answering randomly produces a score of zero.\n adjust_const = 0.7477\n final_score = 10 - (difference_tally * adjust_const)\n final_score_percent = final_score * 10\n\n return {\"eqbench\": final_score_percent, \"percent_parseable\": 100}\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "eqbench", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "percent_parseable", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "do_sample": false, + "temperature": 0.0, + "max_gen_toks": 80, + "until": [ + "\n\n" + ] + }, + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 2.1 + } + }, + "gsm8k": { + "task": "gsm8k", + "group": "Open LLM Leaderboard", + "dataset_path": "gsm8k", + "dataset_name": "main", + "training_split": "train", + "test_split": "test", + "fewshot_split": "train", + "doc_to_text": "Question: {{question}}\nAnswer:", + "doc_to_target": "{{answer}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 5, + "metric_list": [ + { + "metric": "exact_match", + "aggregation": "mean", + "higher_is_better": true, + "ignore_case": true, + "ignore_punctuation": false, + "regexes_to_ignore": [ + ",", + "\\$", + "(?s).*#### ", + "\\.$" + ] + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "until": [ + "Question:", + "", + "<|im_end|>" + ], + "do_sample": false, + "temperature": 0.0 + }, + "repeats": 1, + "filter_list": [ + { + "name": "strict-match", + "filter": [ + { + "function": "regex", + "regex_pattern": "#### (\\-?[0-9\\.\\,]+)" + }, + { + "function": "take_first" + } + ] + }, + { + "name": "flexible-extract", + "filter": [ + { + "function": "regex", + "group_select": -1, + "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" + }, + { + "function": "take_first" + } + ] + } + ], + "should_decontaminate": false, + "metadata": { + "version": 3.0 + } + }, + "hellaswag": { + "task": "hellaswag", + "group": "Open LLM Leaderboard", + "dataset_path": "hellaswag", + "training_split": "train", + "validation_split": "validation", + "fewshot_split": "train", + "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n", + "doc_to_text": "{{query}}", + "doc_to_target": "{{label}}", + "doc_to_choice": "choices", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 10, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "acc_norm", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 1.0 + } + }, + "mmlu_abstract_algebra": { + "task": "mmlu_abstract_algebra", + "task_alias": "abstract_algebra", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "abstract_algebra", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_anatomy": { + "task": "mmlu_anatomy", + "task_alias": "anatomy", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "anatomy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about anatomy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_astronomy": { + "task": "mmlu_astronomy", + "task_alias": "astronomy", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "astronomy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about astronomy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_business_ethics": { + "task": "mmlu_business_ethics", + "task_alias": "business_ethics", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "business_ethics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about business ethics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_clinical_knowledge": { + "task": "mmlu_clinical_knowledge", + "task_alias": "clinical_knowledge", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "clinical_knowledge", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_biology": { + "task": "mmlu_college_biology", + "task_alias": "college_biology", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_biology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college biology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_chemistry": { + "task": "mmlu_college_chemistry", + "task_alias": "college_chemistry", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_chemistry", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_computer_science": { + "task": "mmlu_college_computer_science", + "task_alias": "college_computer_science", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_computer_science", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college computer science.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_mathematics": { + "task": "mmlu_college_mathematics", + "task_alias": "college_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_medicine": { + "task": "mmlu_college_medicine", + "task_alias": "college_medicine", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_medicine", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college medicine.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_college_physics": { + "task": "mmlu_college_physics", + "task_alias": "college_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "college_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about college physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_computer_security": { + "task": "mmlu_computer_security", + "task_alias": "computer_security", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "computer_security", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about computer security.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_conceptual_physics": { + "task": "mmlu_conceptual_physics", + "task_alias": "conceptual_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "conceptual_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_econometrics": { + "task": "mmlu_econometrics", + "task_alias": "econometrics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "econometrics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about econometrics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_electrical_engineering": { + "task": "mmlu_electrical_engineering", + "task_alias": "electrical_engineering", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "electrical_engineering", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_elementary_mathematics": { + "task": "mmlu_elementary_mathematics", + "task_alias": "elementary_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "elementary_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_formal_logic": { + "task": "mmlu_formal_logic", + "task_alias": "formal_logic", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "formal_logic", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about formal logic.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_global_facts": { + "task": "mmlu_global_facts", + "task_alias": "global_facts", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "global_facts", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about global facts.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_biology": { + "task": "mmlu_high_school_biology", + "task_alias": "high_school_biology", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_biology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school biology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_chemistry": { + "task": "mmlu_high_school_chemistry", + "task_alias": "high_school_chemistry", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_chemistry", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_computer_science": { + "task": "mmlu_high_school_computer_science", + "task_alias": "high_school_computer_science", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_computer_science", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_european_history": { + "task": "mmlu_high_school_european_history", + "task_alias": "high_school_european_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_european_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school european history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_geography": { + "task": "mmlu_high_school_geography", + "task_alias": "high_school_geography", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_geography", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school geography.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_government_and_politics": { + "task": "mmlu_high_school_government_and_politics", + "task_alias": "high_school_government_and_politics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_government_and_politics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_macroeconomics": { + "task": "mmlu_high_school_macroeconomics", + "task_alias": "high_school_macroeconomics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_macroeconomics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_mathematics": { + "task": "mmlu_high_school_mathematics", + "task_alias": "high_school_mathematics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_mathematics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_microeconomics": { + "task": "mmlu_high_school_microeconomics", + "task_alias": "high_school_microeconomics", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_microeconomics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_physics": { + "task": "mmlu_high_school_physics", + "task_alias": "high_school_physics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_physics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school physics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_psychology": { + "task": "mmlu_high_school_psychology", + "task_alias": "high_school_psychology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_psychology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_statistics": { + "task": "mmlu_high_school_statistics", + "task_alias": "high_school_statistics", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_statistics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_us_history": { + "task": "mmlu_high_school_us_history", + "task_alias": "high_school_us_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_us_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school us history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_high_school_world_history": { + "task": "mmlu_high_school_world_history", + "task_alias": "high_school_world_history", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "high_school_world_history", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about high school world history.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_human_aging": { + "task": "mmlu_human_aging", + "task_alias": "human_aging", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "human_aging", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about human aging.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_human_sexuality": { + "task": "mmlu_human_sexuality", + "task_alias": "human_sexuality", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "human_sexuality", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_international_law": { + "task": "mmlu_international_law", + "task_alias": "international_law", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "international_law", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about international law.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_jurisprudence": { + "task": "mmlu_jurisprudence", + "task_alias": "jurisprudence", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "jurisprudence", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_logical_fallacies": { + "task": "mmlu_logical_fallacies", + "task_alias": "logical_fallacies", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "logical_fallacies", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_machine_learning": { + "task": "mmlu_machine_learning", + "task_alias": "machine_learning", + "group": "mmlu_stem", + "group_alias": "stem", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "machine_learning", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about machine learning.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_management": { + "task": "mmlu_management", + "task_alias": "management", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "management", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about management.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_marketing": { + "task": "mmlu_marketing", + "task_alias": "marketing", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "marketing", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about marketing.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_medical_genetics": { + "task": "mmlu_medical_genetics", + "task_alias": "medical_genetics", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "medical_genetics", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_miscellaneous": { + "task": "mmlu_miscellaneous", + "task_alias": "miscellaneous", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "miscellaneous", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_moral_disputes": { + "task": "mmlu_moral_disputes", + "task_alias": "moral_disputes", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "moral_disputes", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_moral_scenarios": { + "task": "mmlu_moral_scenarios", + "task_alias": "moral_scenarios", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "moral_scenarios", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_nutrition": { + "task": "mmlu_nutrition", + "task_alias": "nutrition", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "nutrition", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about nutrition.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_philosophy": { + "task": "mmlu_philosophy", + "task_alias": "philosophy", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "philosophy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about philosophy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_prehistory": { + "task": "mmlu_prehistory", + "task_alias": "prehistory", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "prehistory", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about prehistory.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_accounting": { + "task": "mmlu_professional_accounting", + "task_alias": "professional_accounting", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_accounting", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_law": { + "task": "mmlu_professional_law", + "task_alias": "professional_law", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_law", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional law.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_medicine": { + "task": "mmlu_professional_medicine", + "task_alias": "professional_medicine", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_medicine", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_professional_psychology": { + "task": "mmlu_professional_psychology", + "task_alias": "professional_psychology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "professional_psychology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_public_relations": { + "task": "mmlu_public_relations", + "task_alias": "public_relations", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "public_relations", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about public relations.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_security_studies": { + "task": "mmlu_security_studies", + "task_alias": "security_studies", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "security_studies", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about security studies.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_sociology": { + "task": "mmlu_sociology", + "task_alias": "sociology", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "sociology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about sociology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_us_foreign_policy": { + "task": "mmlu_us_foreign_policy", + "task_alias": "us_foreign_policy", + "group": "mmlu_social_sciences", + "group_alias": "social_sciences", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "us_foreign_policy", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_virology": { + "task": "mmlu_virology", + "task_alias": "virology", + "group": "mmlu_other", + "group_alias": "other", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "virology", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about virology.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "mmlu_world_religions": { + "task": "mmlu_world_religions", + "task_alias": "world_religions", + "group": "mmlu_humanities", + "group_alias": "humanities", + "dataset_path": "hails/mmlu_no_train", + "dataset_name": "world_religions", + "dataset_kwargs": { + "trust_remote_code": true + }, + "test_split": "test", + "fewshot_split": "dev", + "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", + "doc_to_target": "answer", + "doc_to_choice": [ + "A", + "B", + "C", + "D" + ], + "description": "The following are multiple choice questions (with answers) about world religions.\n\n", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "fewshot_config": { + "sampler": "first_n" + }, + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": false, + "metadata": { + "version": 0.0 + } + }, + "truthfulqa_gen": { + "task": "truthfulqa_gen", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "generation", + "validation_split": "validation", + "process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n return dataset.map(preprocess_function)\n", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}", + "doc_to_target": " ", + "process_results": "def process_results_gen(doc, results):\n completion = results[0]\n true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n all_refs = true_refs + false_refs\n\n # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n # # BLEURT\n # bleurt_scores_true = self.bleurt.compute(\n # predictions=[completion] * len(true_refs), references=true_refs\n # )[\"scores\"]\n # bleurt_scores_false = self.bleurt.compute(\n # predictions=[completion] * len(false_refs), references=false_refs\n # )[\"scores\"]\n # bleurt_correct = max(bleurt_scores_true)\n # bleurt_incorrect = max(bleurt_scores_false)\n # bleurt_max = bleurt_correct\n # bleurt_diff = bleurt_correct - bleurt_incorrect\n # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n # BLEU\n bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n bleu_max = bleu_correct\n bleu_diff = bleu_correct - bleu_incorrect\n bleu_acc = int(bleu_correct > bleu_incorrect)\n\n # ROUGE-N\n rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n # ROUGE-1\n rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n rouge1_max = rouge1_correct\n rouge1_diff = rouge1_correct - rouge1_incorrect\n rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n # ROUGE-2\n rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n rouge2_max = rouge2_correct\n rouge2_diff = rouge2_correct - rouge2_incorrect\n rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n # ROUGE-L\n rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n rougeL_max = rougeL_correct\n rougeL_diff = rougeL_correct - rougeL_incorrect\n rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n return {\n # \"bleurt_max\": bleurt_max,\n # \"bleurt_acc\": bleurt_acc,\n # \"bleurt_diff\": bleurt_diff,\n \"bleu_max\": bleu_max,\n \"bleu_acc\": bleu_acc,\n \"bleu_diff\": bleu_diff,\n \"rouge1_max\": rouge1_max,\n \"rouge1_acc\": rouge1_acc,\n \"rouge1_diff\": rouge1_diff,\n \"rouge2_max\": rouge2_max,\n \"rouge2_acc\": rouge2_acc,\n \"rouge2_diff\": rouge2_diff,\n \"rougeL_max\": rougeL_max,\n \"rougeL_acc\": rougeL_acc,\n \"rougeL_diff\": rougeL_diff,\n }\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "bleu_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "bleu_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "bleu_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge1_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rouge2_diff", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_max", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_acc", + "aggregation": "mean", + "higher_is_better": true + }, + { + "metric": "rougeL_diff", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "generate_until", + "generation_kwargs": { + "until": [ + "\n\n" + ], + "do_sample": false + }, + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 3.0 + } + }, + "truthfulqa_mc1": { + "task": "truthfulqa_mc1", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "multiple_choice", + "validation_split": "validation", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}", + "doc_to_target": 0, + "doc_to_choice": "{{mc1_targets.choices}}", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 2.0 + } + }, + "truthfulqa_mc2": { + "task": "truthfulqa_mc2", + "group": "truthfulqa", + "dataset_path": "truthful_qa", + "dataset_name": "multiple_choice", + "validation_split": "validation", + "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}", + "doc_to_target": 0, + "doc_to_choice": "{{mc2_targets.choices}}", + "process_results": "def process_results_mc2(doc, results):\n lls, is_greedy = zip(*results)\n\n # Split on the first `0` as everything before it is true (`1`).\n split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n # Compute the normalized probability mass for the correct answer.\n ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n p_true = p_true / (sum(p_true) + sum(p_false))\n\n return {\"acc\": sum(p_true)}\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 0, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "question", + "metadata": { + "version": 2.0 + } + }, + "winogrande": { + "task": "winogrande", + "group": "Open LLM Leaderboard", + "dataset_path": "winogrande", + "dataset_name": "winogrande_xl", + "training_split": "train", + "validation_split": "validation", + "fewshot_split": "train", + "doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n", + "doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n", + "doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n", + "description": "", + "target_delimiter": " ", + "fewshot_delimiter": "\n\n", + "num_fewshot": 5, + "metric_list": [ + { + "metric": "acc", + "aggregation": "mean", + "higher_is_better": true + } + ], + "output_type": "multiple_choice", + "repeats": 1, + "should_decontaminate": true, + "doc_to_decontamination_query": "sentence", + "metadata": { + "version": 1.0 + } + } + }, + "versions": { + "arc_challenge": 1.0, + "eq_bench": 2.1, + "gsm8k": 3.0, + "hellaswag": 1.0, + "mmlu_abstract_algebra": 0.0, + "mmlu_anatomy": 0.0, + "mmlu_astronomy": 0.0, + "mmlu_business_ethics": 0.0, + "mmlu_clinical_knowledge": 0.0, + "mmlu_college_biology": 0.0, + "mmlu_college_chemistry": 0.0, + "mmlu_college_computer_science": 0.0, + "mmlu_college_mathematics": 0.0, + "mmlu_college_medicine": 0.0, + "mmlu_college_physics": 0.0, + "mmlu_computer_security": 0.0, + "mmlu_conceptual_physics": 0.0, + "mmlu_econometrics": 0.0, + "mmlu_electrical_engineering": 0.0, + "mmlu_elementary_mathematics": 0.0, + "mmlu_formal_logic": 0.0, + "mmlu_global_facts": 0.0, + "mmlu_high_school_biology": 0.0, + "mmlu_high_school_chemistry": 0.0, + "mmlu_high_school_computer_science": 0.0, + "mmlu_high_school_european_history": 0.0, + "mmlu_high_school_geography": 0.0, + "mmlu_high_school_government_and_politics": 0.0, + "mmlu_high_school_macroeconomics": 0.0, + "mmlu_high_school_mathematics": 0.0, + "mmlu_high_school_microeconomics": 0.0, + "mmlu_high_school_physics": 0.0, + "mmlu_high_school_psychology": 0.0, + "mmlu_high_school_statistics": 0.0, + "mmlu_high_school_us_history": 0.0, + "mmlu_high_school_world_history": 0.0, + "mmlu_human_aging": 0.0, + "mmlu_human_sexuality": 0.0, + "mmlu_international_law": 0.0, + "mmlu_jurisprudence": 0.0, + "mmlu_logical_fallacies": 0.0, + "mmlu_machine_learning": 0.0, + "mmlu_management": 0.0, + "mmlu_marketing": 0.0, + "mmlu_medical_genetics": 0.0, + "mmlu_miscellaneous": 0.0, + "mmlu_moral_disputes": 0.0, + "mmlu_moral_scenarios": 0.0, + "mmlu_nutrition": 0.0, + "mmlu_philosophy": 0.0, + "mmlu_prehistory": 0.0, + "mmlu_professional_accounting": 0.0, + "mmlu_professional_law": 0.0, + "mmlu_professional_medicine": 0.0, + "mmlu_professional_psychology": 0.0, + "mmlu_public_relations": 0.0, + "mmlu_security_studies": 0.0, + "mmlu_sociology": 0.0, + "mmlu_us_foreign_policy": 0.0, + "mmlu_virology": 0.0, + "mmlu_world_religions": 0.0, + "truthfulqa_gen": 3.0, + "truthfulqa_mc1": 2.0, + "truthfulqa_mc2": 2.0, + "winogrande": 1.0 + }, + "n-shot": { + "Open LLM Leaderboard": 5, + "arc_challenge": 25, + "eq_bench": 0, + "gsm8k": 5, + "hellaswag": 10, + "mmlu": 0, + "mmlu_abstract_algebra": 5, + "mmlu_anatomy": 5, + "mmlu_astronomy": 5, + "mmlu_business_ethics": 5, + "mmlu_clinical_knowledge": 5, + "mmlu_college_biology": 5, + "mmlu_college_chemistry": 5, + "mmlu_college_computer_science": 5, + "mmlu_college_mathematics": 5, + "mmlu_college_medicine": 5, + "mmlu_college_physics": 5, + "mmlu_computer_security": 5, + "mmlu_conceptual_physics": 5, + "mmlu_econometrics": 5, + "mmlu_electrical_engineering": 5, + "mmlu_elementary_mathematics": 5, + "mmlu_formal_logic": 5, + "mmlu_global_facts": 5, + "mmlu_high_school_biology": 5, + "mmlu_high_school_chemistry": 5, + "mmlu_high_school_computer_science": 5, + "mmlu_high_school_european_history": 5, + "mmlu_high_school_geography": 5, + "mmlu_high_school_government_and_politics": 5, + "mmlu_high_school_macroeconomics": 5, + "mmlu_high_school_mathematics": 5, + "mmlu_high_school_microeconomics": 5, + "mmlu_high_school_physics": 5, + "mmlu_high_school_psychology": 5, + "mmlu_high_school_statistics": 5, + "mmlu_high_school_us_history": 5, + "mmlu_high_school_world_history": 5, + "mmlu_human_aging": 5, + "mmlu_human_sexuality": 5, + "mmlu_humanities": 5, + "mmlu_international_law": 5, + "mmlu_jurisprudence": 5, + "mmlu_logical_fallacies": 5, + "mmlu_machine_learning": 5, + "mmlu_management": 5, + "mmlu_marketing": 5, + "mmlu_medical_genetics": 5, + "mmlu_miscellaneous": 5, + "mmlu_moral_disputes": 5, + "mmlu_moral_scenarios": 5, + "mmlu_nutrition": 5, + "mmlu_other": 5, + "mmlu_philosophy": 5, + "mmlu_prehistory": 5, + "mmlu_professional_accounting": 5, + "mmlu_professional_law": 5, + "mmlu_professional_medicine": 5, + "mmlu_professional_psychology": 5, + "mmlu_public_relations": 5, + "mmlu_security_studies": 5, + "mmlu_social_sciences": 5, + "mmlu_sociology": 5, + "mmlu_stem": 5, + "mmlu_us_foreign_policy": 5, + "mmlu_virology": 5, + "mmlu_world_religions": 5, + "truthfulqa": 0, + "truthfulqa_gen": 0, + "truthfulqa_mc1": 0, + "truthfulqa_mc2": 0, + "winogrande": 5 + }, + "higher_is_better": { + "Open LLM Leaderboard": { + "exact_match": true, + "acc": true, + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true, + "acc_norm": true + }, + "arc_challenge": { + "acc": true, + "acc_norm": true + }, + "eq_bench": { + "eqbench": true, + "percent_parseable": true + }, + "gsm8k": { + "exact_match": true + }, + "hellaswag": { + "acc": true, + "acc_norm": true + }, + "mmlu": { + "acc": true + }, + "mmlu_abstract_algebra": { + "acc": true + }, + "mmlu_anatomy": { + "acc": true + }, + "mmlu_astronomy": { + "acc": true + }, + "mmlu_business_ethics": { + "acc": true + }, + "mmlu_clinical_knowledge": { + "acc": true + }, + "mmlu_college_biology": { + "acc": true + }, + "mmlu_college_chemistry": { + "acc": true + }, + "mmlu_college_computer_science": { + "acc": true + }, + "mmlu_college_mathematics": { + "acc": true + }, + "mmlu_college_medicine": { + "acc": true + }, + "mmlu_college_physics": { + "acc": true + }, + "mmlu_computer_security": { + "acc": true + }, + "mmlu_conceptual_physics": { + "acc": true + }, + "mmlu_econometrics": { + "acc": true + }, + "mmlu_electrical_engineering": { + "acc": true + }, + "mmlu_elementary_mathematics": { + "acc": true + }, + "mmlu_formal_logic": { + "acc": true + }, + "mmlu_global_facts": { + "acc": true + }, + "mmlu_high_school_biology": { + "acc": true + }, + "mmlu_high_school_chemistry": { + "acc": true + }, + "mmlu_high_school_computer_science": { + "acc": true + }, + "mmlu_high_school_european_history": { + "acc": true + }, + "mmlu_high_school_geography": { + "acc": true + }, + "mmlu_high_school_government_and_politics": { + "acc": true + }, + "mmlu_high_school_macroeconomics": { + "acc": true + }, + "mmlu_high_school_mathematics": { + "acc": true + }, + "mmlu_high_school_microeconomics": { + "acc": true + }, + "mmlu_high_school_physics": { + "acc": true + }, + "mmlu_high_school_psychology": { + "acc": true + }, + "mmlu_high_school_statistics": { + "acc": true + }, + "mmlu_high_school_us_history": { + "acc": true + }, + "mmlu_high_school_world_history": { + "acc": true + }, + "mmlu_human_aging": { + "acc": true + }, + "mmlu_human_sexuality": { + "acc": true + }, + "mmlu_humanities": { + "acc": true + }, + "mmlu_international_law": { + "acc": true + }, + "mmlu_jurisprudence": { + "acc": true + }, + "mmlu_logical_fallacies": { + "acc": true + }, + "mmlu_machine_learning": { + "acc": true + }, + "mmlu_management": { + "acc": true + }, + "mmlu_marketing": { + "acc": true + }, + "mmlu_medical_genetics": { + "acc": true + }, + "mmlu_miscellaneous": { + "acc": true + }, + "mmlu_moral_disputes": { + "acc": true + }, + "mmlu_moral_scenarios": { + "acc": true + }, + "mmlu_nutrition": { + "acc": true + }, + "mmlu_other": { + "acc": true + }, + "mmlu_philosophy": { + "acc": true + }, + "mmlu_prehistory": { + "acc": true + }, + "mmlu_professional_accounting": { + "acc": true + }, + "mmlu_professional_law": { + "acc": true + }, + "mmlu_professional_medicine": { + "acc": true + }, + "mmlu_professional_psychology": { + "acc": true + }, + "mmlu_public_relations": { + "acc": true + }, + "mmlu_security_studies": { + "acc": true + }, + "mmlu_social_sciences": { + "acc": true + }, + "mmlu_sociology": { + "acc": true + }, + "mmlu_stem": { + "acc": true + }, + "mmlu_us_foreign_policy": { + "acc": true + }, + "mmlu_virology": { + "acc": true + }, + "mmlu_world_religions": { + "acc": true + }, + "truthfulqa": { + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true, + "acc": true + }, + "truthfulqa_gen": { + "bleu_max": true, + "bleu_acc": true, + "bleu_diff": true, + "rouge1_max": true, + "rouge1_acc": true, + "rouge1_diff": true, + "rouge2_max": true, + "rouge2_acc": true, + "rouge2_diff": true, + "rougeL_max": true, + "rougeL_acc": true, + "rougeL_diff": true + }, + "truthfulqa_mc1": { + "acc": true + }, + "truthfulqa_mc2": { + "acc": true + }, + "winogrande": { + "acc": true + } + }, + "n-samples": { + "gsm8k": { + "original": 1319, + "effective": 1319 + }, + "winogrande": { + "original": 1267, + "effective": 1267 + }, + "mmlu_high_school_european_history": { + "original": 165, + "effective": 165 + }, + "mmlu_formal_logic": { + "original": 126, + "effective": 126 + }, + "mmlu_moral_scenarios": { + "original": 895, + "effective": 895 + }, + "mmlu_moral_disputes": { + "original": 346, + "effective": 346 + }, + "mmlu_world_religions": { + "original": 171, + "effective": 171 + }, + "mmlu_high_school_world_history": { + "original": 237, + "effective": 237 + }, + "mmlu_logical_fallacies": { + "original": 163, + "effective": 163 + }, + "mmlu_international_law": { + "original": 121, + "effective": 121 + }, + "mmlu_philosophy": { + "original": 311, + "effective": 311 + }, + "mmlu_professional_law": { + "original": 1534, + "effective": 1534 + }, + "mmlu_high_school_us_history": { + "original": 204, + "effective": 204 + }, + "mmlu_prehistory": { + "original": 324, + "effective": 324 + }, + "mmlu_jurisprudence": { + "original": 108, + "effective": 108 + }, + "mmlu_high_school_psychology": { + "original": 545, + "effective": 545 + }, + "mmlu_sociology": { + "original": 201, + "effective": 201 + }, + "mmlu_high_school_government_and_politics": { + "original": 193, + "effective": 193 + }, + "mmlu_public_relations": { + "original": 110, + "effective": 110 + }, + "mmlu_high_school_macroeconomics": { + "original": 390, + "effective": 390 + }, + "mmlu_high_school_geography": { + "original": 198, + "effective": 198 + }, + "mmlu_high_school_microeconomics": { + "original": 238, + "effective": 238 + }, + "mmlu_security_studies": { + "original": 245, + "effective": 245 + }, + "mmlu_us_foreign_policy": { + "original": 100, + "effective": 100 + }, + "mmlu_professional_psychology": { + "original": 612, + "effective": 612 + }, + "mmlu_human_sexuality": { + "original": 131, + "effective": 131 + }, + "mmlu_econometrics": { + "original": 114, + "effective": 114 + }, + "mmlu_professional_medicine": { + "original": 272, + "effective": 272 + }, + "mmlu_professional_accounting": { + "original": 282, + "effective": 282 + }, + "mmlu_management": { + "original": 103, + "effective": 103 + }, + "mmlu_global_facts": { + "original": 100, + "effective": 100 + }, + "mmlu_college_medicine": { + "original": 173, + "effective": 173 + }, + "mmlu_business_ethics": { + "original": 100, + "effective": 100 + }, + "mmlu_nutrition": { + "original": 306, + "effective": 306 + }, + "mmlu_medical_genetics": { + "original": 100, + "effective": 100 + }, + "mmlu_virology": { + "original": 166, + "effective": 166 + }, + "mmlu_human_aging": { + "original": 223, + "effective": 223 + }, + "mmlu_clinical_knowledge": { + "original": 265, + "effective": 265 + }, + "mmlu_miscellaneous": { + "original": 783, + "effective": 783 + }, + "mmlu_marketing": { + "original": 234, + "effective": 234 + }, + "mmlu_high_school_chemistry": { + "original": 203, + "effective": 203 + }, + "mmlu_college_physics": { + "original": 102, + "effective": 102 + }, + "mmlu_college_mathematics": { + "original": 100, + "effective": 100 + }, + "mmlu_astronomy": { + "original": 152, + "effective": 152 + }, + "mmlu_high_school_physics": { + "original": 151, + "effective": 151 + }, + "mmlu_computer_security": { + "original": 100, + "effective": 100 + }, + "mmlu_elementary_mathematics": { + "original": 378, + "effective": 378 + }, + "mmlu_electrical_engineering": { + "original": 145, + "effective": 145 + }, + "mmlu_college_biology": { + "original": 144, + "effective": 144 + }, + "mmlu_machine_learning": { + "original": 112, + "effective": 112 + }, + "mmlu_high_school_biology": { + "original": 310, + "effective": 310 + }, + "mmlu_high_school_mathematics": { + "original": 270, + "effective": 270 + }, + "mmlu_anatomy": { + "original": 135, + "effective": 135 + }, + "mmlu_high_school_statistics": { + "original": 216, + "effective": 216 + }, + "mmlu_college_chemistry": { + "original": 100, + "effective": 100 + }, + "mmlu_conceptual_physics": { + "original": 235, + "effective": 235 + }, + "mmlu_high_school_computer_science": { + "original": 100, + "effective": 100 + }, + "mmlu_college_computer_science": { + "original": 100, + "effective": 100 + }, + "mmlu_abstract_algebra": { + "original": 100, + "effective": 100 + }, + "truthfulqa_gen": { + "original": 817, + "effective": 817 + }, + "truthfulqa_mc1": { + "original": 817, + "effective": 817 + }, + "truthfulqa_mc2": { + "original": 817, + "effective": 817 + }, + "hellaswag": { + "original": 10042, + "effective": 10042 + }, + "arc_challenge": { + "original": 1172, + "effective": 1172 + }, + "eq_bench": { + "original": 171, + "effective": 171 + } + }, + "config": { + "model": "hf", + "model_args": "pretrained=FallenMerick/Smart-Lemon-Cookie-7B,trust_remote_code=True", + "model_num_parameters": 7241732096, + "model_dtype": "torch.float16", + "model_revision": "main", + "model_sha": "24a18cbcb94c55811593f89026c6fe51331f4a57", + "batch_size": "auto", + "batch_sizes": [ + 2 + ], + "device": null, + "use_cache": null, + "limit": null, + "bootstrap_iters": 100000, + "gen_kwargs": null, + "random_seed": 0, + "numpy_seed": 1234, + "torch_seed": 1234, + "fewshot_seed": 1234 + }, + "git_hash": null, + "date": 1719550043.4933457, + "pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-6.5.0-1022-gcp-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA L4\nGPU 1: NVIDIA L4\n\nNvidia driver version: 555.42.02\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 24\nOn-line CPU(s) list: 0-23\nVendor ID: GenuineIntel\nModel name: Intel(R) Xeon(R) CPU @ 2.20GHz\nCPU family: 6\nModel: 85\nThread(s) per core: 2\nCore(s) per socket: 12\nSocket(s): 1\nStepping: 7\nBogoMIPS: 4400.47\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves arat avx512_vnni md_clear arch_capabilities\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 384 KiB (12 instances)\nL1i cache: 384 KiB (12 instances)\nL2 cache: 12 MiB (12 instances)\nL3 cache: 38.5 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0-23\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Mitigation; Clear CPU buffers; SMT Host state unknown\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown\nVulnerability Retbleed: Mitigation; Enhanced IBRS\nVulnerability Spec rstack overflow: Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT Host state unknown\n\nVersions of relevant libraries:\n[pip3] numpy==2.0.0\n[pip3] torch==2.3.1\n[pip3] triton==2.3.1\n[conda] Could not collect", + "transformers_version": "4.41.2", + "upper_git_hash": null, + "tokenizer_pad_token": [ + "", + 0 + ], + "tokenizer_eos_token": [ + "", + 2 + ], + "tokenizer_bos_token": [ + "", + 1 + ], + "eot_token_id": 2, + "max_length": 32768, + "task_hashes": {}, + "model_source": "hf", + "model_name": "FallenMerick/Smart-Lemon-Cookie-7B", + "model_name_sanitized": "FallenMerick__Smart-Lemon-Cookie-7B", + "system_instruction": null, + "system_instruction_sha": null, + "fewshot_as_multiturn": false, + "chat_template": null, + "chat_template_sha": null, + "start_time": 102426.774034499, + "end_time": 138957.776397903, + "total_evaluation_time_seconds": "36531.00236340401" +} \ No newline at end of file