{ "results": { "Open LLM Leaderboard": { "bleu_diff,none": 3.006407428437984, "bleu_diff_stderr,none": 0.6902983955128965, "bleu_max,none": 22.15536379157621, "bleu_max_stderr,none": 0.7500703499499018, "rouge2_max,none": 33.70863440140025, "rouge2_max_stderr,none": 0.9588688279748141, "rougeL_diff,none": 3.7826634155902985, "rougeL_diff_stderr,none": 0.958164425989176, "exact_match,strict-match": 0.6277482941622441, "exact_match_stderr,strict-match": 0.013315375362565036, "acc_norm,none": 0.8359193864811842, "acc_norm_stderr,none": 0.00345585439013916, "exact_match,flexible-extract": 0.6315390447308568, "exact_match_stderr,flexible-extract": 0.013287342651674573, "rouge1_acc,none": 0.5410036719706243, "rouge1_acc_stderr,none": 0.017444544447661182, "rouge1_max,none": 47.813085751155874, "rouge1_max_stderr,none": 0.8351008973483007, "rouge2_acc,none": 0.4541003671970624, "rouge2_acc_stderr,none": 0.017429593091323504, "bleu_acc,none": 0.5091799265605875, "bleu_acc_stderr,none": 0.01750055072481974, "rougeL_max,none": 44.3329487904666, "rougeL_max_stderr,none": 0.8588505055776223, "rouge2_diff,none": 3.5225531232870635, "rouge2_diff_stderr,none": 1.0505034205658943, "rouge1_diff,none": 4.221115729669922, "rouge1_diff_stderr,none": 0.9451610499576943, "acc,none": 0.6514042969190568, "acc_stderr,none": 0.0027599234131481932, "rougeL_acc,none": 0.5128518971848225, "rougeL_acc_stderr,none": 0.017497717944299843, "alias": "Open LLM Leaderboard" }, "arc_challenge": { "acc,none": 0.6382252559726962, "acc_stderr,none": 0.014041957945038085, "acc_norm,none": 0.6689419795221843, "acc_norm_stderr,none": 0.013752062419817841, "alias": " - arc_challenge" }, "gsm8k": { "exact_match,strict-match": 0.6277482941622441, "exact_match_stderr,strict-match": 0.013315375362565036, "exact_match,flexible-extract": 0.6315390447308568, "exact_match_stderr,flexible-extract": 0.013287342651674573, "alias": " - gsm8k" }, "hellaswag": { "acc,none": 0.6691894045010954, "acc_stderr,none": 0.00469543410395854, "acc_norm,none": 0.8554072893845848, "acc_norm_stderr,none": 0.0035097096477919466, "alias": " - hellaswag" }, "mmlu": { "acc,none": 0.6364477994587665, "acc_stderr,none": 0.0038271694585367516, "alias": " - mmlu" }, "mmlu_humanities": { "alias": " - humanities", "acc,none": 0.5895855472901169, "acc_stderr,none": 0.006760272274548804 }, "mmlu_formal_logic": { "alias": " - formal_logic", "acc,none": 0.4444444444444444, "acc_stderr,none": 0.04444444444444449 }, "mmlu_high_school_european_history": { "alias": " - high_school_european_history", "acc,none": 0.7696969696969697, "acc_stderr,none": 0.0328766675860349 }, "mmlu_high_school_us_history": { "alias": " - high_school_us_history", "acc,none": 0.8333333333333334, "acc_stderr,none": 0.026156867523931055 }, "mmlu_high_school_world_history": { "alias": " - high_school_world_history", "acc,none": 0.8185654008438819, "acc_stderr,none": 0.02508596114457965 }, "mmlu_international_law": { "alias": " - international_law", "acc,none": 0.7933884297520661, "acc_stderr,none": 0.03695980128098823 }, "mmlu_jurisprudence": { "alias": " - jurisprudence", "acc,none": 0.7962962962962963, "acc_stderr,none": 0.03893542518824847 }, "mmlu_logical_fallacies": { "alias": " - logical_fallacies", "acc,none": 0.7668711656441718, "acc_stderr,none": 0.033220157957767414 }, "mmlu_moral_disputes": { "alias": " - moral_disputes", "acc,none": 0.7138728323699421, "acc_stderr,none": 0.024332146779134128 }, "mmlu_moral_scenarios": { "alias": " - moral_scenarios", "acc,none": 0.39664804469273746, "acc_stderr,none": 0.01636135476982247 }, "mmlu_philosophy": { "alias": " - philosophy", "acc,none": 0.6913183279742765, "acc_stderr,none": 0.02623696588115326 }, "mmlu_prehistory": { "alias": " - prehistory", "acc,none": 0.7345679012345679, "acc_stderr,none": 0.02456922360046085 }, "mmlu_professional_law": { "alias": " - professional_law", "acc,none": 0.46936114732724904, "acc_stderr,none": 0.012746237711716634 }, "mmlu_world_religions": { "alias": " - world_religions", "acc,none": 0.847953216374269, "acc_stderr,none": 0.02753912288906145 }, "mmlu_other": { "alias": " - other", "acc,none": 0.7055037013196009, "acc_stderr,none": 0.007845586852292294 }, "mmlu_business_ethics": { "alias": " - business_ethics", "acc,none": 0.58, "acc_stderr,none": 0.049604496374885836 }, "mmlu_clinical_knowledge": { "alias": " - clinical_knowledge", "acc,none": 0.7018867924528301, "acc_stderr,none": 0.028152837942493868 }, "mmlu_college_medicine": { "alias": " - college_medicine", "acc,none": 0.6647398843930635, "acc_stderr,none": 0.03599586301247077 }, "mmlu_global_facts": { "alias": " - global_facts", "acc,none": 0.38, "acc_stderr,none": 0.04878317312145632 }, "mmlu_human_aging": { "alias": " - human_aging", "acc,none": 0.6771300448430493, "acc_stderr,none": 0.031381476375755 }, "mmlu_management": { "alias": " - management", "acc,none": 0.7864077669902912, "acc_stderr,none": 0.04058042015646034 }, "mmlu_marketing": { "alias": " - marketing", "acc,none": 0.8803418803418803, "acc_stderr,none": 0.021262719400406964 }, "mmlu_medical_genetics": { "alias": " - medical_genetics", "acc,none": 0.71, "acc_stderr,none": 0.045604802157206845 }, "mmlu_miscellaneous": { "alias": " - miscellaneous", "acc,none": 0.8326947637292464, "acc_stderr,none": 0.01334732720292033 }, "mmlu_nutrition": { "alias": " - nutrition", "acc,none": 0.7352941176470589, "acc_stderr,none": 0.025261691219729494 }, "mmlu_professional_accounting": { "alias": " - professional_accounting", "acc,none": 0.46808510638297873, "acc_stderr,none": 0.02976667507587387 }, "mmlu_professional_medicine": { "alias": " - professional_medicine", "acc,none": 0.6875, "acc_stderr,none": 0.02815637344037142 }, "mmlu_virology": { "alias": " - virology", "acc,none": 0.5421686746987951, "acc_stderr,none": 0.038786267710023595 }, "mmlu_social_sciences": { "alias": " - social_sciences", "acc,none": 0.7432564185895353, "acc_stderr,none": 0.007701333272557918 }, "mmlu_econometrics": { "alias": " - econometrics", "acc,none": 0.5087719298245614, "acc_stderr,none": 0.04702880432049615 }, "mmlu_high_school_geography": { "alias": " - high_school_geography", "acc,none": 0.8181818181818182, "acc_stderr,none": 0.027479603010538804 }, "mmlu_high_school_government_and_politics": { "alias": " - high_school_government_and_politics", "acc,none": 0.9015544041450777, "acc_stderr,none": 0.021500249576033463 }, "mmlu_high_school_macroeconomics": { "alias": " - high_school_macroeconomics", "acc,none": 0.658974358974359, "acc_stderr,none": 0.02403548967633508 }, "mmlu_high_school_microeconomics": { "alias": " - high_school_microeconomics", "acc,none": 0.6638655462184874, "acc_stderr,none": 0.03068473711513537 }, "mmlu_high_school_psychology": { "alias": " - high_school_psychology", "acc,none": 0.8311926605504587, "acc_stderr,none": 0.016060056268530368 }, "mmlu_human_sexuality": { "alias": " - human_sexuality", "acc,none": 0.7862595419847328, "acc_stderr,none": 0.0359546161177469 }, "mmlu_professional_psychology": { "alias": " - professional_psychology", "acc,none": 0.6699346405228758, "acc_stderr,none": 0.01902372616072455 }, "mmlu_public_relations": { "alias": " - public_relations", "acc,none": 0.6909090909090909, "acc_stderr,none": 0.044262946482000985 }, "mmlu_security_studies": { "alias": " - security_studies", "acc,none": 0.7387755102040816, "acc_stderr,none": 0.02812342933514278 }, "mmlu_sociology": { "alias": " - sociology", "acc,none": 0.8407960199004975, "acc_stderr,none": 0.02587064676616913 }, "mmlu_us_foreign_policy": { "alias": " - us_foreign_policy", "acc,none": 0.86, "acc_stderr,none": 0.03487350880197768 }, "mmlu_stem": { "alias": " - stem", "acc,none": 0.5340945131620679, "acc_stderr,none": 0.008514164103258936 }, "mmlu_abstract_algebra": { "alias": " - abstract_algebra", "acc,none": 0.38, "acc_stderr,none": 0.048783173121456316 }, "mmlu_anatomy": { "alias": " - anatomy", "acc,none": 0.6222222222222222, "acc_stderr,none": 0.04188307537595853 }, "mmlu_astronomy": { "alias": " - astronomy", "acc,none": 0.6907894736842105, "acc_stderr,none": 0.037610708698674805 }, "mmlu_college_biology": { "alias": " - college_biology", "acc,none": 0.7569444444444444, "acc_stderr,none": 0.03586879280080341 }, "mmlu_college_chemistry": { "alias": " - college_chemistry", "acc,none": 0.42, "acc_stderr,none": 0.049604496374885836 }, "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": 0.32, "acc_stderr,none": 0.04688261722621505 }, "mmlu_college_physics": { "alias": " - college_physics", "acc,none": 0.4411764705882353, "acc_stderr,none": 0.04940635630605659 }, "mmlu_computer_security": { "alias": " - computer_security", "acc,none": 0.79, "acc_stderr,none": 0.040936018074033256 }, "mmlu_conceptual_physics": { "alias": " - conceptual_physics", "acc,none": 0.574468085106383, "acc_stderr,none": 0.03232146916224468 }, "mmlu_electrical_engineering": { "alias": " - electrical_engineering", "acc,none": 0.5862068965517241, "acc_stderr,none": 0.04104269211806232 }, "mmlu_elementary_mathematics": { "alias": " - elementary_mathematics", "acc,none": 0.3915343915343915, "acc_stderr,none": 0.02513809138885111 }, "mmlu_high_school_biology": { "alias": " - high_school_biology", "acc,none": 0.7645161290322581, "acc_stderr,none": 0.02413763242933771 }, "mmlu_high_school_chemistry": { "alias": " - high_school_chemistry", "acc,none": 0.5172413793103449, "acc_stderr,none": 0.035158955511656986 }, "mmlu_high_school_computer_science": { "alias": " - high_school_computer_science", "acc,none": 0.71, "acc_stderr,none": 0.045604802157206845 }, "mmlu_high_school_mathematics": { "alias": " - high_school_mathematics", "acc,none": 0.3592592592592593, "acc_stderr,none": 0.029252905927251972 }, "mmlu_high_school_physics": { "alias": " - high_school_physics", "acc,none": 0.37748344370860926, "acc_stderr,none": 0.0395802723112157 }, "mmlu_high_school_statistics": { "alias": " - high_school_statistics", "acc,none": 0.49074074074074076, "acc_stderr,none": 0.034093869469927006 }, "mmlu_machine_learning": { "alias": " - machine_learning", "acc,none": 0.49107142857142855, "acc_stderr,none": 0.04745033255489123 }, "truthfulqa": { "bleu_diff,none": 3.006407428437984, "bleu_diff_stderr,none": 0.6902983955128965, "bleu_max,none": 22.15536379157621, "bleu_max_stderr,none": 0.7500703499499018, "rouge2_max,none": 33.70863440140025, "rouge2_max_stderr,none": 0.9588688279748141, "rougeL_acc,none": 0.5128518971848225, "rougeL_acc_stderr,none": 0.017497717944299843, "rougeL_diff,none": 3.7826634155902985, "rougeL_diff_stderr,none": 0.958164425989176, "rouge1_acc,none": 0.5410036719706243, "rouge1_acc_stderr,none": 0.017444544447661182, "rouge1_max,none": 47.813085751155874, "rouge1_max_stderr,none": 0.8351008973483007, "rouge2_acc,none": 0.4541003671970624, "rouge2_acc_stderr,none": 0.017429593091323504, "bleu_acc,none": 0.5091799265605875, "bleu_acc_stderr,none": 0.01750055072481974, "rouge2_diff,none": 3.5225531232870635, "rouge2_diff_stderr,none": 1.0505034205658943, "rouge1_diff,none": 4.221115729669922, "rouge1_diff_stderr,none": 0.9451610499576943, "acc,none": 0.5182294709510535, "acc_stderr,none": 0.011594047810301133, "rougeL_max,none": 44.3329487904666, "rougeL_max_stderr,none": 0.8588505055776223, "alias": " - truthfulqa" }, "truthfulqa_gen": { "bleu_max,none": 22.15536379157621, "bleu_max_stderr,none": 0.7500703499499018, "bleu_acc,none": 0.5091799265605875, "bleu_acc_stderr,none": 0.01750055072481974, "bleu_diff,none": 3.006407428437984, "bleu_diff_stderr,none": 0.6902983955128965, "rouge1_max,none": 47.813085751155874, "rouge1_max_stderr,none": 0.8351008973483007, "rouge1_acc,none": 0.5410036719706243, "rouge1_acc_stderr,none": 0.01744454444766118, "rouge1_diff,none": 4.221115729669922, "rouge1_diff_stderr,none": 0.9451610499576943, "rouge2_max,none": 33.70863440140025, "rouge2_max_stderr,none": 0.9588688279748141, "rouge2_acc,none": 0.4541003671970624, "rouge2_acc_stderr,none": 0.017429593091323504, "rouge2_diff,none": 3.5225531232870635, "rouge2_diff_stderr,none": 1.0505034205658943, "rougeL_max,none": 44.3329487904666, "rougeL_max_stderr,none": 0.8588505055776224, "rougeL_acc,none": 0.5128518971848225, "rougeL_acc_stderr,none": 0.017497717944299843, "rougeL_diff,none": 3.7826634155902985, "rougeL_diff_stderr,none": 0.958164425989176, "alias": " - truthfulqa_gen" }, "truthfulqa_mc1": { "acc,none": 0.42962056303549573, "acc_stderr,none": 0.017329234580409095, "alias": " - truthfulqa_mc1" }, "truthfulqa_mc2": { "acc,none": 0.6068383788666114, "acc_stderr,none": 0.01540731668290581, "alias": " - truthfulqa_mc2" }, "winogrande": { "acc,none": 0.7742699289660616, "acc_stderr,none": 0.011749626260902557, "alias": " - winogrande" }, "eq_bench": { "eqbench,none": 71.54290317887124, "eqbench_stderr,none": 2.0457017558365664, "percent_parseable,none": 100.0, "percent_parseable_stderr,none": 0.0, "alias": "eq_bench" } }, "groups": { "Open LLM Leaderboard": { "bleu_diff,none": 3.006407428437984, "bleu_diff_stderr,none": 0.6902983955128965, "bleu_max,none": 22.15536379157621, "bleu_max_stderr,none": 0.7500703499499018, "rouge2_max,none": 33.70863440140025, "rouge2_max_stderr,none": 0.9588688279748141, "rougeL_diff,none": 3.7826634155902985, "rougeL_diff_stderr,none": 0.958164425989176, "exact_match,strict-match": 0.6277482941622441, "exact_match_stderr,strict-match": 0.013315375362565036, "acc_norm,none": 0.8359193864811842, "acc_norm_stderr,none": 0.00345585439013916, "exact_match,flexible-extract": 0.6315390447308568, "exact_match_stderr,flexible-extract": 0.013287342651674573, "rouge1_acc,none": 0.5410036719706243, "rouge1_acc_stderr,none": 0.017444544447661182, "rouge1_max,none": 47.813085751155874, "rouge1_max_stderr,none": 0.8351008973483007, "rouge2_acc,none": 0.4541003671970624, "rouge2_acc_stderr,none": 0.017429593091323504, "bleu_acc,none": 0.5091799265605875, "bleu_acc_stderr,none": 0.01750055072481974, "rougeL_max,none": 44.3329487904666, "rougeL_max_stderr,none": 0.8588505055776223, "rouge2_diff,none": 3.5225531232870635, "rouge2_diff_stderr,none": 1.0505034205658943, "rouge1_diff,none": 4.221115729669922, "rouge1_diff_stderr,none": 0.9451610499576943, "acc,none": 0.6514042969190568, "acc_stderr,none": 0.0027599234131481932, "rougeL_acc,none": 0.5128518971848225, "rougeL_acc_stderr,none": 0.017497717944299843, "alias": "Open LLM Leaderboard" }, "mmlu": { "acc,none": 0.6364477994587665, "acc_stderr,none": 0.0038271694585367516, "alias": " - mmlu" }, "mmlu_humanities": { "alias": " - humanities", "acc,none": 0.5895855472901169, "acc_stderr,none": 0.006760272274548804 }, "mmlu_other": { "alias": " - other", "acc,none": 0.7055037013196009, "acc_stderr,none": 0.007845586852292294 }, "mmlu_social_sciences": { "alias": " - social_sciences", "acc,none": 0.7432564185895353, "acc_stderr,none": 0.007701333272557918 }, "mmlu_stem": { "alias": " - stem", "acc,none": 0.5340945131620679, "acc_stderr,none": 0.008514164103258936 }, "truthfulqa": { "bleu_diff,none": 3.006407428437984, "bleu_diff_stderr,none": 0.6902983955128965, "bleu_max,none": 22.15536379157621, "bleu_max_stderr,none": 0.7500703499499018, "rouge2_max,none": 33.70863440140025, "rouge2_max_stderr,none": 0.9588688279748141, "rougeL_acc,none": 0.5128518971848225, "rougeL_acc_stderr,none": 0.017497717944299843, "rougeL_diff,none": 3.7826634155902985, "rougeL_diff_stderr,none": 0.958164425989176, "rouge1_acc,none": 0.5410036719706243, "rouge1_acc_stderr,none": 0.017444544447661182, "rouge1_max,none": 47.813085751155874, "rouge1_max_stderr,none": 0.8351008973483007, "rouge2_acc,none": 0.4541003671970624, "rouge2_acc_stderr,none": 0.017429593091323504, "bleu_acc,none": 0.5091799265605875, "bleu_acc_stderr,none": 0.01750055072481974, "rouge2_diff,none": 3.5225531232870635, "rouge2_diff_stderr,none": 1.0505034205658943, "rouge1_diff,none": 4.221115729669922, "rouge1_diff_stderr,none": 0.9451610499576943, "acc,none": 0.5182294709510535, "acc_stderr,none": 0.011594047810301133, "rougeL_max,none": 44.3329487904666, "rougeL_max_stderr,none": 0.8588505055776223, "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/Iced-Lemon-Cookie-7B,trust_remote_code=True", "model_num_parameters": 7241732096, "model_dtype": "torch.float16", "model_revision": "main", "model_sha": "e0656657a5d5cc73bc16d9852f5894f31ed7fcb5", "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": 1719586774.8240964, "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/Iced-Lemon-Cookie-7B", "model_name_sanitized": "FallenMerick__Iced-Lemon-Cookie-7B", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 139158.078961917, "end_time": 175571.331573164, "total_evaluation_time_seconds": "36413.25261124701" }