{ "results": { "arc_challenge_chat": { "name": "arc_challenge_chat", "alias": "arc_challenge_chat", "sample_len": 150, "exact_match,remove_whitespace": 0.0, "exact_match_stderr,remove_whitespace": 0.0 }, "gsm8k_cot_llama": { "name": "gsm8k_cot_llama", "alias": "gsm8k_cot_llama", "sample_len": 150, "exact_match,strict-match": 0.9066666666666666, "exact_match_stderr,strict-match": 0.023831373802832928, "exact_match,flexible-extract": 0.9066666666666666, "exact_match_stderr,flexible-extract": 0.023831373802832928 }, "mmlu_llama_abstract_algebra": { "name": "mmlu_llama_abstract_algebra", "alias": "abstract algebra", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_anatomy": { "name": "mmlu_llama_anatomy", "alias": "anatomy", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_astronomy": { "name": "mmlu_llama_astronomy", "alias": "astronomy", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_business_ethics": { "name": "mmlu_llama_business_ethics", "alias": "business ethics", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_clinical_knowledge": { "name": "mmlu_llama_clinical_knowledge", "alias": "clinical knowledge", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_college_biology": { "name": "mmlu_llama_college_biology", "alias": "college biology", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_college_chemistry": { "name": "mmlu_llama_college_chemistry", "alias": "college chemistry", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_college_mathematics": { "name": "mmlu_llama_college_mathematics", "alias": "college mathematics", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_college_medicine": { "name": "mmlu_llama_college_medicine", "alias": "college medicine", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_college_physics": { "name": "mmlu_llama_college_physics", "alias": "college physics", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_conceptual_physics": { "name": "mmlu_llama_conceptual_physics", "alias": "conceptual physics", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_electrical_engineering": { "name": "mmlu_llama_electrical_engineering", "alias": "electrical engineering", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_elementary_mathematics": { "name": "mmlu_llama_elementary_mathematics", "alias": "elementary mathematics", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_global_facts": { "name": "mmlu_llama_global_facts", "alias": "global facts", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_high_school_biology": { "name": "mmlu_llama_high_school_biology", "alias": "high school biology", "sample_len": 6, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_chemistry": { "name": "mmlu_llama_high_school_chemistry", "alias": "high school chemistry", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_computer_science": { "name": "mmlu_llama_high_school_computer_science", "alias": "high school computer science", "sample_len": 4, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_geography": { "name": "mmlu_llama_high_school_geography", "alias": "high school geography", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_government_and_politics": { "name": "mmlu_llama_high_school_government_and_politics", "alias": "high school government and politics", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_macroeconomics": { "name": "mmlu_llama_high_school_macroeconomics", "alias": "high school macroeconomics", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_mathematics": { "name": "mmlu_llama_high_school_mathematics", "alias": "high school mathematics", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_microeconomics": { "name": "mmlu_llama_high_school_microeconomics", "alias": "high school microeconomics", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_physics": { "name": "mmlu_llama_high_school_physics", "alias": "high school physics", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_psychology": { "name": "mmlu_llama_high_school_psychology", "alias": "high school psychology", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_statistics": { "name": "mmlu_llama_high_school_statistics", "alias": "high school statistics", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_us_history": { "name": "mmlu_llama_high_school_us_history", "alias": "high school us history", "sample_len": 4, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_high_school_world_history": { "name": "mmlu_llama_high_school_world_history", "alias": "high school world history", "sample_len": 6, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_human_aging": { "name": "mmlu_llama_human_aging", "alias": "human aging", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_human_sexuality": { "name": "mmlu_llama_human_sexuality", "alias": "human sexuality", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_international_law": { "name": "mmlu_llama_international_law", "alias": "international law", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_jurisprudence": { "name": "mmlu_llama_jurisprudence", "alias": "jurisprudence", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_logical_fallacies": { "name": "mmlu_llama_logical_fallacies", "alias": "logical fallacies", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_management": { "name": "mmlu_llama_management", "alias": "management", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_marketing": { "name": "mmlu_llama_marketing", "alias": "marketing", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_medical_genetics": { "name": "mmlu_llama_medical_genetics", "alias": "medical genetics", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_miscellaneous": { "name": "mmlu_llama_miscellaneous", "alias": "miscellaneous", "sample_len": 11, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_moral_disputes": { "name": "mmlu_llama_moral_disputes", "alias": "moral disputes", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_moral_scenarios": { "name": "mmlu_llama_moral_scenarios", "alias": "moral scenarios", "sample_len": 15, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_nutrition": { "name": "mmlu_llama_nutrition", "alias": "nutrition", "sample_len": 6, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_philosophy": { "name": "mmlu_llama_philosophy", "alias": "philosophy", "sample_len": 9, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_prehistory": { "name": "mmlu_llama_prehistory", "alias": "prehistory", "sample_len": 4, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_professional_accounting": { "name": "mmlu_llama_professional_accounting", "alias": "professional accounting", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_professional_law": { "name": "mmlu_llama_professional_law", "alias": "professional law", "sample_len": 26, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_professional_medicine": { "name": "mmlu_llama_professional_medicine", "alias": "professional medicine", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_professional_psychology": { "name": "mmlu_llama_professional_psychology", "alias": "professional psychology", "sample_len": 7, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_public_relations": { "name": "mmlu_llama_public_relations", "alias": "public relations", "sample_len": 1, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": "N/A" }, "mmlu_llama_security_studies": { "name": "mmlu_llama_security_studies", "alias": "security studies", "sample_len": 5, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_sociology": { "name": "mmlu_llama_sociology", "alias": "sociology", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_us_foreign_policy": { "name": "mmlu_llama_us_foreign_policy", "alias": "us foreign policy", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_virology": { "name": "mmlu_llama_virology", "alias": "virology", "sample_len": 2, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 }, "mmlu_llama_world_religions": { "name": "mmlu_llama_world_religions", "alias": "world religions", "sample_len": 3, "exact_match,strict_match": 0.0, "exact_match_stderr,strict_match": 0.0 } }, "group_subtasks": {}, "configs": { "arc_challenge_chat": { "task": "arc_challenge_chat", "dataset_path": "allenai/ai2_arc", "dataset_name": "ARC-Challenge", "training_split": "train", "validation_split": "validation", "test_split": "test", "fewshot_split": "train", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\\nQuestion: {{question.strip()}}\\nA. {{choices.text[0]}}\\nB. {{choices.text[1]}}\\nC. {{choices.text[2]}}{% if choices.text|length > 3 %}\\nD. {{choices.text[3]}}{% endif %}\\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{ 'ABCD'[answerKey|int - 1] if answerKey|string in '1234' else answerKey }}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "default", "split": "train", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\\nQuestion: {{question.strip()}}\\nA. {{choices.text[0]}}\\nB. {{choices.text[1]}}\\nC. {{choices.text[2]}}{% if choices.text|length > 3 %}\\nD. {{choices.text[3]}}{% endif %}\\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{ 'ABCD'[answerKey|int - 1] if answerKey|string in '1234' else answerKey }}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 0, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true } ], "output_type": "generate_until", "generation_kwargs": { "max_gen_toks": 1024, "until": [ "\n\n", "." ], "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "remove_whitespace", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\arc\\arc_challenge_chat.yaml" } }, "gsm8k_cot_llama": { "task": "gsm8k_cot_llama", "dataset_path": "openai/gsm8k", "dataset_name": "main", "test_split": "test", "doc_to_text": "Given the following problem, reason and give a final answer to the problem.\nProblem: {{question}}\nYour response should end with \"The final answer is [answer]\" where [answer] is the response to the problem.\n", "doc_to_target": "{{answer.split('####')[-1].strip() if answer is defined else target}}", "unsafe_code": false, "description": "", "target_delimiter": "", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": null, "process_docs": null, "fewshot_indices": null, "samples": [ { "question": "There are 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done, there will be 21 trees. How many trees did the grove workers plant today?", "target": "There are 15 trees originally. Then there were 21 trees after some more were planted. So there must have been 21 - 15 = 6. The final answer is 6" }, { "question": "If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?", "target": "There are originally 3 cars. 2 more cars arrive. 3 + 2 = 5. The final answer is 5" }, { "question": "Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?", "target": "Originally, Leah had 32 chocolates. Her sister had 42. So in total they had 32 + 42 = 74. After eating 35, they had 74 - 35 = 39. The final answer is 39" }, { "question": "Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?", "target": "Jason started with 20 lollipops. Then he had 12 after giving some to Denny. So he gave Denny 20 - 12 = 8. The final answer is 8" }, { "question": "Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?", "target": "Shawn started with 5 toys. If he got 2 toys each from his mom and dad, then that is 4 more toys. 5 + 4 = 9. The final answer is 9" }, { "question": "There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?", "target": "There were originally 9 computers. For each of 4 days, 5 more computers were added. So 5 * 4 = 20 computers were added. 9 + 20 is 29. The final answer is 29" }, { "question": "Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many golf balls did he have at the end of wednesday?", "target": "Michael started with 58 golf balls. After losing 23 on tuesday, he had 58 - 23 = 35. After losing 2 more, he had 35 - 2 = 33 golf balls. The final answer is 33" }, { "question": "Olivia has $23. She bought five bagels for $3 each. How much money does she have left?", "target": "Olivia had 23 dollars. 5 bagels for 3 dollars each will be 5 x 3 = 15 dollars. So she has 23 - 15 dollars left. 23 - 15 is 8. The final answer is 8" } ], "doc_to_text": "Given the following problem, reason and give a final answer to the problem.\nProblem: {{question}}\nYour response should end with \"The final answer is [answer]\" where [answer] is the response to the problem.\n", "doc_to_choice": null, "doc_to_target": "{{answer.split('####')[-1].strip() if answer is defined else target}}", "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": "" }, "num_fewshot": 8, "metric_list": [ { "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": false, "metric": "exact_match", "regexes_to_ignore": [ ",", "\\$", "(?s).*#### ", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "<|eot_id|>", "<|start_header_id|>user<|end_header_id|>", "Q:", "", "<|im_end|>" ], "temperature": 0, "max_gen_toks": 1024 }, "repeats": 1, "filter_list": [ { "filter": [ { "function": "regex", "group_select": -1, "regex_pattern": "The final answer is ((-?[$0-9.,]{2,})|(-?[0-9]+))" }, { "function": "take_first" } ], "name": "strict-match" }, { "filter": [ { "function": "regex", "group_select": -1, "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" }, { "function": "take_first" } ], "name": "flexible-extract" } ], "should_decontaminate": false, "metadata": { "version": 4.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\gsm8k\\gsm8k-cot-llama.yaml" } }, "mmlu_llama_abstract_algebra": { "task": "mmlu_llama_abstract_algebra", "task_alias": "abstract algebra", "dataset_path": "hails/mmlu_no_train", "dataset_name": "abstract_algebra", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_abstract_algebra.yaml" } }, "mmlu_llama_anatomy": { "task": "mmlu_llama_anatomy", "task_alias": "anatomy", "dataset_path": "hails/mmlu_no_train", "dataset_name": "anatomy", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_anatomy.yaml" } }, "mmlu_llama_astronomy": { "task": "mmlu_llama_astronomy", "task_alias": "astronomy", "dataset_path": "hails/mmlu_no_train", "dataset_name": "astronomy", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_astronomy.yaml" } }, "mmlu_llama_business_ethics": { "task": "mmlu_llama_business_ethics", "task_alias": "business ethics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "business_ethics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_business_ethics.yaml" } }, "mmlu_llama_clinical_knowledge": { "task": "mmlu_llama_clinical_knowledge", "task_alias": "clinical knowledge", "dataset_path": "hails/mmlu_no_train", "dataset_name": "clinical_knowledge", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_clinical_knowledge.yaml" } }, "mmlu_llama_college_biology": { "task": "mmlu_llama_college_biology", "task_alias": "college biology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_biology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_college_biology.yaml" } }, "mmlu_llama_college_chemistry": { "task": "mmlu_llama_college_chemistry", "task_alias": "college chemistry", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_chemistry", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_college_chemistry.yaml" } }, "mmlu_llama_college_mathematics": { "task": "mmlu_llama_college_mathematics", "task_alias": "college mathematics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_mathematics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_college_mathematics.yaml" } }, "mmlu_llama_college_medicine": { "task": "mmlu_llama_college_medicine", "task_alias": "college medicine", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_medicine", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_college_medicine.yaml" } }, "mmlu_llama_college_physics": { "task": "mmlu_llama_college_physics", "task_alias": "college physics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_physics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_college_physics.yaml" } }, "mmlu_llama_conceptual_physics": { "task": "mmlu_llama_conceptual_physics", "task_alias": "conceptual physics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "conceptual_physics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_conceptual_physics.yaml" } }, "mmlu_llama_electrical_engineering": { "task": "mmlu_llama_electrical_engineering", "task_alias": "electrical engineering", "dataset_path": "hails/mmlu_no_train", "dataset_name": "electrical_engineering", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_electrical_engineering.yaml" } }, "mmlu_llama_elementary_mathematics": { "task": "mmlu_llama_elementary_mathematics", "task_alias": "elementary mathematics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "elementary_mathematics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_elementary_mathematics.yaml" } }, "mmlu_llama_global_facts": { "task": "mmlu_llama_global_facts", "task_alias": "global facts", "dataset_path": "hails/mmlu_no_train", "dataset_name": "global_facts", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_global_facts.yaml" } }, "mmlu_llama_high_school_biology": { "task": "mmlu_llama_high_school_biology", "task_alias": "high school biology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_biology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_biology.yaml" } }, "mmlu_llama_high_school_chemistry": { "task": "mmlu_llama_high_school_chemistry", "task_alias": "high school chemistry", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_chemistry", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_chemistry.yaml" } }, "mmlu_llama_high_school_computer_science": { "task": "mmlu_llama_high_school_computer_science", "task_alias": "high school computer science", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_computer_science", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_computer_science.yaml" } }, "mmlu_llama_high_school_geography": { "task": "mmlu_llama_high_school_geography", "task_alias": "high school geography", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_geography", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_geography.yaml" } }, "mmlu_llama_high_school_government_and_politics": { "task": "mmlu_llama_high_school_government_and_politics", "task_alias": "high school government and politics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_government_and_politics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_government_and_politics.yaml" } }, "mmlu_llama_high_school_macroeconomics": { "task": "mmlu_llama_high_school_macroeconomics", "task_alias": "high school macroeconomics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_macroeconomics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_macroeconomics.yaml" } }, "mmlu_llama_high_school_mathematics": { "task": "mmlu_llama_high_school_mathematics", "task_alias": "high school mathematics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_mathematics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_mathematics.yaml" } }, "mmlu_llama_high_school_microeconomics": { "task": "mmlu_llama_high_school_microeconomics", "task_alias": "high school microeconomics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_microeconomics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_microeconomics.yaml" } }, "mmlu_llama_high_school_physics": { "task": "mmlu_llama_high_school_physics", "task_alias": "high school physics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_physics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_physics.yaml" } }, "mmlu_llama_high_school_psychology": { "task": "mmlu_llama_high_school_psychology", "task_alias": "high school psychology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_psychology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_psychology.yaml" } }, "mmlu_llama_high_school_statistics": { "task": "mmlu_llama_high_school_statistics", "task_alias": "high school statistics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_statistics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_statistics.yaml" } }, "mmlu_llama_high_school_us_history": { "task": "mmlu_llama_high_school_us_history", "task_alias": "high school us history", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_us_history", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_us_history.yaml" } }, "mmlu_llama_high_school_world_history": { "task": "mmlu_llama_high_school_world_history", "task_alias": "high school world history", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_world_history", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_high_school_world_history.yaml" } }, "mmlu_llama_human_aging": { "task": "mmlu_llama_human_aging", "task_alias": "human aging", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_aging", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_human_aging.yaml" } }, "mmlu_llama_human_sexuality": { "task": "mmlu_llama_human_sexuality", "task_alias": "human sexuality", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_sexuality", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_human_sexuality.yaml" } }, "mmlu_llama_international_law": { "task": "mmlu_llama_international_law", "task_alias": "international law", "dataset_path": "hails/mmlu_no_train", "dataset_name": "international_law", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_international_law.yaml" } }, "mmlu_llama_jurisprudence": { "task": "mmlu_llama_jurisprudence", "task_alias": "jurisprudence", "dataset_path": "hails/mmlu_no_train", "dataset_name": "jurisprudence", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_jurisprudence.yaml" } }, "mmlu_llama_logical_fallacies": { "task": "mmlu_llama_logical_fallacies", "task_alias": "logical fallacies", "dataset_path": "hails/mmlu_no_train", "dataset_name": "logical_fallacies", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_logical_fallacies.yaml" } }, "mmlu_llama_management": { "task": "mmlu_llama_management", "task_alias": "management", "dataset_path": "hails/mmlu_no_train", "dataset_name": "management", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_management.yaml" } }, "mmlu_llama_marketing": { "task": "mmlu_llama_marketing", "task_alias": "marketing", "dataset_path": "hails/mmlu_no_train", "dataset_name": "marketing", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_marketing.yaml" } }, "mmlu_llama_medical_genetics": { "task": "mmlu_llama_medical_genetics", "task_alias": "medical genetics", "dataset_path": "hails/mmlu_no_train", "dataset_name": "medical_genetics", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_medical_genetics.yaml" } }, "mmlu_llama_miscellaneous": { "task": "mmlu_llama_miscellaneous", "task_alias": "miscellaneous", "dataset_path": "hails/mmlu_no_train", "dataset_name": "miscellaneous", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_miscellaneous.yaml" } }, "mmlu_llama_moral_disputes": { "task": "mmlu_llama_moral_disputes", "task_alias": "moral disputes", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_disputes", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_moral_disputes.yaml" } }, "mmlu_llama_moral_scenarios": { "task": "mmlu_llama_moral_scenarios", "task_alias": "moral scenarios", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_scenarios", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_moral_scenarios.yaml" } }, "mmlu_llama_nutrition": { "task": "mmlu_llama_nutrition", "task_alias": "nutrition", "dataset_path": "hails/mmlu_no_train", "dataset_name": "nutrition", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_nutrition.yaml" } }, "mmlu_llama_philosophy": { "task": "mmlu_llama_philosophy", "task_alias": "philosophy", "dataset_path": "hails/mmlu_no_train", "dataset_name": "philosophy", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_philosophy.yaml" } }, "mmlu_llama_prehistory": { "task": "mmlu_llama_prehistory", "task_alias": "prehistory", "dataset_path": "hails/mmlu_no_train", "dataset_name": "prehistory", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_prehistory.yaml" } }, "mmlu_llama_professional_accounting": { "task": "mmlu_llama_professional_accounting", "task_alias": "professional accounting", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_accounting", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_professional_accounting.yaml" } }, "mmlu_llama_professional_law": { "task": "mmlu_llama_professional_law", "task_alias": "professional law", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_law", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_professional_law.yaml" } }, "mmlu_llama_professional_medicine": { "task": "mmlu_llama_professional_medicine", "task_alias": "professional medicine", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_medicine", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_professional_medicine.yaml" } }, "mmlu_llama_professional_psychology": { "task": "mmlu_llama_professional_psychology", "task_alias": "professional psychology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_psychology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_professional_psychology.yaml" } }, "mmlu_llama_public_relations": { "task": "mmlu_llama_public_relations", "task_alias": "public relations", "dataset_path": "hails/mmlu_no_train", "dataset_name": "public_relations", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_public_relations.yaml" } }, "mmlu_llama_security_studies": { "task": "mmlu_llama_security_studies", "task_alias": "security studies", "dataset_path": "hails/mmlu_no_train", "dataset_name": "security_studies", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_security_studies.yaml" } }, "mmlu_llama_sociology": { "task": "mmlu_llama_sociology", "task_alias": "sociology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "sociology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_sociology.yaml" } }, "mmlu_llama_us_foreign_policy": { "task": "mmlu_llama_us_foreign_policy", "task_alias": "us foreign policy", "dataset_path": "hails/mmlu_no_train", "dataset_name": "us_foreign_policy", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_us_foreign_policy.yaml" } }, "mmlu_llama_virology": { "task": "mmlu_llama_virology", "task_alias": "virology", "dataset_path": "hails/mmlu_no_train", "dataset_name": "virology", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_virology.yaml" } }, "mmlu_llama_world_religions": { "task": "mmlu_llama_world_religions", "task_alias": "world religions", "dataset_path": "hails/mmlu_no_train", "dataset_name": "world_religions", "test_split": "test", "fewshot_split": "dev", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": "dev", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\nQuestion: {{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{['A.','B.','C.','D.'][answer]}}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 5, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true, "regexes_to_ignore": [ "\\$", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "." ], "max_gen_toks": 1024, "temperature": 0 }, "repeats": 1, "filter_list": [ { "name": "strict_match", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800, "config_source": "C:\\quantdiff\\venv\\Lib\\site-packages\\lm_eval\\tasks\\llama3\\instruct\\mmlu\\mmlu_world_religions.yaml" } } }, "versions": { "arc_challenge_chat": 1.0, "gsm8k_cot_llama": 4.0, "mmlu_llama_abstract_algebra": 1.0, "mmlu_llama_anatomy": 1.0, "mmlu_llama_astronomy": 1.0, "mmlu_llama_business_ethics": 1.0, "mmlu_llama_clinical_knowledge": 1.0, "mmlu_llama_college_biology": 1.0, "mmlu_llama_college_chemistry": 1.0, "mmlu_llama_college_mathematics": 1.0, "mmlu_llama_college_medicine": 1.0, "mmlu_llama_college_physics": 1.0, "mmlu_llama_conceptual_physics": 1.0, "mmlu_llama_electrical_engineering": 1.0, "mmlu_llama_elementary_mathematics": 1.0, "mmlu_llama_global_facts": 1.0, "mmlu_llama_high_school_biology": 1.0, "mmlu_llama_high_school_chemistry": 1.0, "mmlu_llama_high_school_computer_science": 1.0, "mmlu_llama_high_school_geography": 1.0, "mmlu_llama_high_school_government_and_politics": 1.0, "mmlu_llama_high_school_macroeconomics": 1.0, "mmlu_llama_high_school_mathematics": 1.0, "mmlu_llama_high_school_microeconomics": 1.0, "mmlu_llama_high_school_physics": 1.0, "mmlu_llama_high_school_psychology": 1.0, "mmlu_llama_high_school_statistics": 1.0, "mmlu_llama_high_school_us_history": 1.0, "mmlu_llama_high_school_world_history": 1.0, "mmlu_llama_human_aging": 1.0, "mmlu_llama_human_sexuality": 1.0, "mmlu_llama_international_law": 1.0, "mmlu_llama_jurisprudence": 1.0, "mmlu_llama_logical_fallacies": 1.0, "mmlu_llama_management": 1.0, "mmlu_llama_marketing": 1.0, "mmlu_llama_medical_genetics": 1.0, "mmlu_llama_miscellaneous": 1.0, "mmlu_llama_moral_disputes": 1.0, "mmlu_llama_moral_scenarios": 1.0, "mmlu_llama_nutrition": 1.0, "mmlu_llama_philosophy": 1.0, "mmlu_llama_prehistory": 1.0, "mmlu_llama_professional_accounting": 1.0, "mmlu_llama_professional_law": 1.0, "mmlu_llama_professional_medicine": 1.0, "mmlu_llama_professional_psychology": 1.0, "mmlu_llama_public_relations": 1.0, "mmlu_llama_security_studies": 1.0, "mmlu_llama_sociology": 1.0, "mmlu_llama_us_foreign_policy": 1.0, "mmlu_llama_virology": 1.0, "mmlu_llama_world_religions": 1.0 }, "n-shot": { "arc_challenge_chat": 0, "gsm8k_cot_llama": 8, "mmlu_llama_abstract_algebra": 5, "mmlu_llama_anatomy": 5, "mmlu_llama_astronomy": 5, "mmlu_llama_business_ethics": 5, "mmlu_llama_clinical_knowledge": 5, "mmlu_llama_college_biology": 5, "mmlu_llama_college_chemistry": 5, "mmlu_llama_college_mathematics": 5, "mmlu_llama_college_medicine": 5, "mmlu_llama_college_physics": 5, "mmlu_llama_conceptual_physics": 5, "mmlu_llama_electrical_engineering": 5, "mmlu_llama_elementary_mathematics": 5, "mmlu_llama_global_facts": 5, "mmlu_llama_high_school_biology": 5, "mmlu_llama_high_school_chemistry": 5, "mmlu_llama_high_school_computer_science": 5, "mmlu_llama_high_school_geography": 5, "mmlu_llama_high_school_government_and_politics": 5, "mmlu_llama_high_school_macroeconomics": 5, "mmlu_llama_high_school_mathematics": 5, "mmlu_llama_high_school_microeconomics": 5, "mmlu_llama_high_school_physics": 5, "mmlu_llama_high_school_psychology": 5, "mmlu_llama_high_school_statistics": 5, "mmlu_llama_high_school_us_history": 5, "mmlu_llama_high_school_world_history": 5, "mmlu_llama_human_aging": 5, "mmlu_llama_human_sexuality": 5, "mmlu_llama_international_law": 5, "mmlu_llama_jurisprudence": 5, "mmlu_llama_logical_fallacies": 5, "mmlu_llama_management": 5, "mmlu_llama_marketing": 5, "mmlu_llama_medical_genetics": 5, "mmlu_llama_miscellaneous": 5, "mmlu_llama_moral_disputes": 5, "mmlu_llama_moral_scenarios": 5, "mmlu_llama_nutrition": 5, "mmlu_llama_philosophy": 5, "mmlu_llama_prehistory": 5, "mmlu_llama_professional_accounting": 5, "mmlu_llama_professional_law": 5, "mmlu_llama_professional_medicine": 5, "mmlu_llama_professional_psychology": 5, "mmlu_llama_public_relations": 5, "mmlu_llama_security_studies": 5, "mmlu_llama_sociology": 5, "mmlu_llama_us_foreign_policy": 5, "mmlu_llama_virology": 5, "mmlu_llama_world_religions": 5 }, "higher_is_better": { "arc_challenge_chat": { "exact_match": true }, "gsm8k_cot_llama": { "exact_match": true }, "mmlu_llama_abstract_algebra": { "exact_match": true }, "mmlu_llama_anatomy": { "exact_match": true }, "mmlu_llama_astronomy": { "exact_match": true }, "mmlu_llama_business_ethics": { "exact_match": true }, "mmlu_llama_clinical_knowledge": { "exact_match": true }, "mmlu_llama_college_biology": { "exact_match": true }, "mmlu_llama_college_chemistry": { "exact_match": true }, "mmlu_llama_college_mathematics": { "exact_match": true }, "mmlu_llama_college_medicine": { "exact_match": true }, "mmlu_llama_college_physics": { "exact_match": true }, "mmlu_llama_conceptual_physics": { "exact_match": true }, "mmlu_llama_electrical_engineering": { "exact_match": true }, "mmlu_llama_elementary_mathematics": { "exact_match": true }, "mmlu_llama_global_facts": { "exact_match": true }, "mmlu_llama_high_school_biology": { "exact_match": true }, "mmlu_llama_high_school_chemistry": { "exact_match": true }, "mmlu_llama_high_school_computer_science": { "exact_match": true }, "mmlu_llama_high_school_geography": { "exact_match": true }, "mmlu_llama_high_school_government_and_politics": { "exact_match": true }, "mmlu_llama_high_school_macroeconomics": { "exact_match": true }, "mmlu_llama_high_school_mathematics": { "exact_match": true }, "mmlu_llama_high_school_microeconomics": { "exact_match": true }, "mmlu_llama_high_school_physics": { "exact_match": true }, "mmlu_llama_high_school_psychology": { "exact_match": true }, "mmlu_llama_high_school_statistics": { "exact_match": true }, "mmlu_llama_high_school_us_history": { "exact_match": true }, "mmlu_llama_high_school_world_history": { "exact_match": true }, "mmlu_llama_human_aging": { "exact_match": true }, "mmlu_llama_human_sexuality": { "exact_match": true }, "mmlu_llama_international_law": { "exact_match": true }, "mmlu_llama_jurisprudence": { "exact_match": true }, "mmlu_llama_logical_fallacies": { "exact_match": true }, "mmlu_llama_management": { "exact_match": true }, "mmlu_llama_marketing": { "exact_match": true }, "mmlu_llama_medical_genetics": { "exact_match": true }, "mmlu_llama_miscellaneous": { "exact_match": true }, "mmlu_llama_moral_disputes": { "exact_match": true }, "mmlu_llama_moral_scenarios": { "exact_match": true }, "mmlu_llama_nutrition": { "exact_match": true }, "mmlu_llama_philosophy": { "exact_match": true }, "mmlu_llama_prehistory": { "exact_match": true }, "mmlu_llama_professional_accounting": { "exact_match": true }, "mmlu_llama_professional_law": { "exact_match": true }, "mmlu_llama_professional_medicine": { "exact_match": true }, "mmlu_llama_professional_psychology": { "exact_match": true }, "mmlu_llama_public_relations": { "exact_match": true }, "mmlu_llama_security_studies": { "exact_match": true }, "mmlu_llama_sociology": { "exact_match": true }, "mmlu_llama_us_foreign_policy": { "exact_match": true }, "mmlu_llama_virology": { "exact_match": true }, "mmlu_llama_world_religions": { "exact_match": true } }, "n-samples": { "arc_challenge_chat": { "original": 1172, "effective": 150 }, "gsm8k_cot_llama": { "original": 1319, "effective": 150 }, "mmlu_llama_abstract_algebra": { "original": 100, "effective": 1 }, "mmlu_llama_anatomy": { "original": 135, "effective": 1 }, "mmlu_llama_astronomy": { "original": 152, "effective": 1 }, "mmlu_llama_business_ethics": { "original": 100, "effective": 1 }, "mmlu_llama_clinical_knowledge": { "original": 265, "effective": 5 }, "mmlu_llama_college_biology": { "original": 144, "effective": 2 }, "mmlu_llama_college_chemistry": { "original": 100, "effective": 1 }, "mmlu_llama_college_mathematics": { "original": 100, "effective": 2 }, "mmlu_llama_college_medicine": { "original": 173, "effective": 3 }, "mmlu_llama_college_physics": { "original": 102, "effective": 1 }, "mmlu_llama_conceptual_physics": { "original": 235, "effective": 5 }, "mmlu_llama_electrical_engineering": { "original": 145, "effective": 1 }, "mmlu_llama_elementary_mathematics": { "original": 378, "effective": 5 }, "mmlu_llama_global_facts": { "original": 100, "effective": 1 }, "mmlu_llama_high_school_biology": { "original": 310, "effective": 6 }, "mmlu_llama_high_school_chemistry": { "original": 203, "effective": 3 }, "mmlu_llama_high_school_computer_science": { "original": 100, "effective": 4 }, "mmlu_llama_high_school_geography": { "original": 198, "effective": 2 }, "mmlu_llama_high_school_government_and_politics": { "original": 193, "effective": 2 }, "mmlu_llama_high_school_macroeconomics": { "original": 390, "effective": 5 }, "mmlu_llama_high_school_mathematics": { "original": 270, "effective": 5 }, "mmlu_llama_high_school_microeconomics": { "original": 238, "effective": 2 }, "mmlu_llama_high_school_physics": { "original": 151, "effective": 3 }, "mmlu_llama_high_school_psychology": { "original": 545, "effective": 5 }, "mmlu_llama_high_school_statistics": { "original": 216, "effective": 3 }, "mmlu_llama_high_school_us_history": { "original": 204, "effective": 4 }, "mmlu_llama_high_school_world_history": { "original": 237, "effective": 6 }, "mmlu_llama_human_aging": { "original": 223, "effective": 5 }, "mmlu_llama_human_sexuality": { "original": 131, "effective": 1 }, "mmlu_llama_international_law": { "original": 121, "effective": 1 }, "mmlu_llama_jurisprudence": { "original": 108, "effective": 2 }, "mmlu_llama_logical_fallacies": { "original": 163, "effective": 5 }, "mmlu_llama_management": { "original": 103, "effective": 1 }, "mmlu_llama_marketing": { "original": 234, "effective": 2 }, "mmlu_llama_medical_genetics": { "original": 100, "effective": 2 }, "mmlu_llama_miscellaneous": { "original": 783, "effective": 11 }, "mmlu_llama_moral_disputes": { "original": 346, "effective": 2 }, "mmlu_llama_moral_scenarios": { "original": 895, "effective": 15 }, "mmlu_llama_nutrition": { "original": 306, "effective": 6 }, "mmlu_llama_philosophy": { "original": 311, "effective": 9 }, "mmlu_llama_prehistory": { "original": 324, "effective": 4 }, "mmlu_llama_professional_accounting": { "original": 282, "effective": 2 }, "mmlu_llama_professional_law": { "original": 1534, "effective": 26 }, "mmlu_llama_professional_medicine": { "original": 272, "effective": 3 }, "mmlu_llama_professional_psychology": { "original": 612, "effective": 7 }, "mmlu_llama_public_relations": { "original": 110, "effective": 1 }, "mmlu_llama_security_studies": { "original": 245, "effective": 5 }, "mmlu_llama_sociology": { "original": 201, "effective": 2 }, "mmlu_llama_us_foreign_policy": { "original": 100, "effective": 3 }, "mmlu_llama_virology": { "original": 166, "effective": 2 }, "mmlu_llama_world_religions": { "original": 171, "effective": 3 } }, "config": { "model": "local-chat-completions", "model_args": { "model": "quant", "base_url": "http://127.0.0.1:8094/v1/chat/completions", "num_concurrent": 4, "max_retries": 3, "tokenized_requests": false, "timeout": 1800 }, "batch_size": 1, "batch_sizes": [], "device": "cuda:0", "use_cache": "C:\\quantdiff\\results\\tasks\\20261022T052903_ornith-1.5-9b--ornith-ai--q5_k_m\\cache\\responses", "limit": null, "bootstrap_iters": 100000, "gen_kwargs": { "temperature": 0, "max_gen_toks": 1024 }, "random_seed": 1234, "numpy_seed": 1234, "torch_seed": 1234, "fewshot_seed": 1234 }, "git_hash": null, "date": 1792647406.1601212, "pretty_env_info": "PyTorch version: 2.11.0+cpu\nIs debug build: False\nCUDA used to build PyTorch: Could not collect\nROCM used to build PyTorch: N/A\n\nOS: Microsoft Windows 10 Home (10.0.19045 64-bit)\nGCC version: Could not collect\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: N/A\n\nPython version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] (64-bit runtime)\nPython platform: Windows-10-10.0.19045-SP0\nIs CUDA available: False\nCUDA runtime version: Could not collect\nCUDA_MODULE_LOADING set to: N/A\nGPU models and configuration: GPU 0: NVIDIA GeForce RTX 5070\nNvidia driver version: Could not collect\ncuDNN version: Could not collect\nIs XPU available: False\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\nCaching allocator config: N/A\n\nCPU:\nName: AMD Ryzen 7 5800X 8-Core Processor \nManufacturer: AuthenticAMD\nFamily: 107\nArchitecture: 9\nProcessorType: 3\nDeviceID: CPU0\nCurrentClockSpeed: 3801\nMaxClockSpeed: 3801\nL2CacheSize: 4096\nL2CacheSpeed: None\nRevision: 8450\n\nVersions of relevant libraries:\n[pip3] numpy==2.5.4\n[pip3] torch==2.11.0+cpu\n[conda] Could not collect", "transformers_version": "4.57.6", "lm_eval_version": "0.4.13", "upper_git_hash": null, "task_hashes": { "arc_challenge_chat": "c2c5f0f0a4f3adcfb0f7fc4b527a00bc06463efed8fd7d5aba79950c134c1518", "gsm8k_cot_llama": "ab5cab8086fe5f477d776cd1802c82273a8f27cf9d379f24055e29dea5ccef02", "mmlu_llama_abstract_algebra": "adb61f76e84206fd5086234ce4a0d5d3aabf6a6bc136ac04699b65fcf219ecb6", "mmlu_llama_anatomy": "aa6a2b137766109af74a3d612079779f650caa8c2ebd3a76000607dff5f632f2", "mmlu_llama_astronomy": "9a052c721e61fccaef8762eb4e5f37aa35df4faa1e61f9ad3f9810ca0eb0194b", "mmlu_llama_business_ethics": "50d9ee2d4781bcc65ce3c840ce569e0c7e87d44671ab5c88e778933127d1f1a4", "mmlu_llama_clinical_knowledge": "4a6ba768e2574738496fc6b3ca48bf778dac2e674bb4ec9d0144550f913fc2c1", "mmlu_llama_college_biology": "d628723c1cff9d84f5d33ed5d475615a8e0e8202ce7a678360fdf54456dff31b", "mmlu_llama_college_chemistry": "eecf21405bf0e4accb19f5d7632bfcebb42c72592fcedf5b9692c948de61dba6", "mmlu_llama_college_mathematics": "39b1b4ff9f739d92919d2545e77405d412db838f3d3237f744098e27255d26bf", "mmlu_llama_college_medicine": "1a38a7a32ef146c10d2361560f78e81d4da266a6245a84776942a498245b0525", "mmlu_llama_college_physics": "35dfa4e2506c8640edcb2ed37d6ea25048dc20d51768629b2b28f1d62f9fe74d", "mmlu_llama_conceptual_physics": "cbfdbae50b0cc58797266122c63db7aaab682c3a0c128ba81caa9ed96cf09455", "mmlu_llama_electrical_engineering": "3cf5770766c88fa774bea4db11533b2f719e3d989eec55ef7ac6d6bc58b6456b", "mmlu_llama_elementary_mathematics": "aeb0e7aefba1c83ba42a627375ce05af0f6d71286fbfb81e0e453f16d4cb4d14", "mmlu_llama_global_facts": "e858479ec4266db3854227635cfa6b9c0346979967b797b3173bff42759c7764", "mmlu_llama_high_school_biology": "2b06c2598e6ad999aee9dc5ab876115d3621ae39ef3127eb077bb242d5a35370", "mmlu_llama_high_school_chemistry": "88773882dac884c329ca70b2d5695c251086a5609de1bd1acf0c5080e4b88f2a", "mmlu_llama_high_school_computer_science": "16bc286ff68873d1e627fd6a88b9b576cd74a4b85d4fe2ff450cb00f6a5ecee5", "mmlu_llama_high_school_geography": "5a05fda6c9e581a25d1ced24f5fb5ed7b1bc5948992aaa1df9c1e275ed84e966", "mmlu_llama_high_school_government_and_politics": "ca5f1311f9d6e61753f89515ebc2b388845adacf2ff88376750c1f61ed1dd13e", "mmlu_llama_high_school_macroeconomics": "502b16acfc9b4fd43d1245dc91b8e0c74e695509773943a41bb791f9b069d698", "mmlu_llama_high_school_mathematics": "ef42e7b3d883957ede3a981b4c1b092bac7160b2056832bbc75fa2f3e8180e27", "mmlu_llama_high_school_microeconomics": "09bcde573806f48ea938924bdb15e797a0d1674a12293e04ca237e94938267b9", "mmlu_llama_high_school_physics": "5f7bc299521a286c54f3e062ea145f4f3700e56d4ea4584430bb8a72835d843a", "mmlu_llama_high_school_psychology": "fd49e9dc2a7b78156c9fed2c67e5d6f9dc63eb8dff179575e0f54c90681eedd6", "mmlu_llama_high_school_statistics": "df2f36acd4f7f315786779a68bf35d12bb125ff3c38b4f734ac9838a9837e275", "mmlu_llama_high_school_us_history": "fc67a4ed4b05f0320e4f2ab639bfb5a0fd43f3abcbd8172e4c9a0f95298732a5", "mmlu_llama_high_school_world_history": "78ad438d104138eea4d104802c971b58aabac11621d0eef0866da7acc22ce8cd", "mmlu_llama_human_aging": "f9cea0e3ee568d7ef97199ab3d203eca17a8a3cd4fbe412f447dfb12ede2fd16", "mmlu_llama_human_sexuality": "cfcc2555817aed05ca3b39f70a75ab7ddd899f4e7001b68f89cc9b5a9f686ab8", "mmlu_llama_international_law": "5f80df20fb943dc942ddbf5787bde5be6a0c4a25a112de264c445c9430a670fc", "mmlu_llama_jurisprudence": "ef63ad7143288ec5af0dc6c0048c9901f78cfb7d21522625416fe81dd47cda41", "mmlu_llama_logical_fallacies": "14b05287035ba89e86cb719cc260252097668fc534d6b3c027fcc73b1c742d41", "mmlu_llama_management": "21ec4c1fd325d85d04b353a660a92a7f6cbae112946399ee97cd46199e6cd4bf", "mmlu_llama_marketing": "33aebe99efd8a9689fbc388ac3a304acfeadbc85f873321487e50b2039d82db1", "mmlu_llama_medical_genetics": "1c6b7c81b81b062aa3213fce46530cac82c7d430535f7985a970bf42a77e6927", "mmlu_llama_miscellaneous": "deb69da71765625b2d274cb067d84b5206a047277030bf1265f5a2144bad088e", "mmlu_llama_moral_disputes": "b6e23504c38098cc1e2330d3884b3d461f56ad98713d25de49a2043e4b19f989", "mmlu_llama_moral_scenarios": "40ad5b095b66a04830dd426340a35e1fd4cafcfa96774682941fde500ab08216", "mmlu_llama_nutrition": "0c682e36bac33f91d3620dba2702bd0d03213969508c24295bb751d8c1af8a44", "mmlu_llama_philosophy": "c05ae56ffce62bf795f68dd4c79c6324cca4d51ee2cfb1c7a30965bae39cd516", "mmlu_llama_prehistory": "0b0b91f42ef1bc686c406141bc5497ac1c17e423f74e1f7cfd970b39bb71b303", "mmlu_llama_professional_accounting": "d3cfd1f321f17e8e5817b0a54560c61405e47c93a7a2ed88e54a4c8119044811", "mmlu_llama_professional_law": "ee94ba92223c02834ba68d0a2de99ecae01435e513f185862d52065e9f725075", "mmlu_llama_professional_medicine": "ee7ded16997f1820f9d3511596db238f53f3ee5a10cb5f1f8d8a939174aba4e4", "mmlu_llama_professional_psychology": "c9f9d3169dc0bd04fc1038086b806188cc7291caa38953b08a470458a91bb0b5", "mmlu_llama_public_relations": "e1510b7eb80b7d4add7e95fb6b292bddbb50bc6792cd3331da9068ea50be1802", "mmlu_llama_security_studies": "25defb4c57c575de04401697f3f829911c045e08724d59036a83bc5fdf17604d", "mmlu_llama_sociology": "38d08f8b04048ee9c1cea86c7e0fe71267a8ffa751beccce462053398ddfc66c", "mmlu_llama_us_foreign_policy": "f10e1566a442ddd09156ab5adc851871a41873f0f02adf444bccd3c2faab5268", "mmlu_llama_virology": "cfbf4df41f9f9e036d26556bed290db655bea5e9a70af2b068db371fb4f036cb", "mmlu_llama_world_religions": "979791f4018fcc80bda8c2a23fe5f567d7e7084b8a83faefe1b7068178d611ce" }, "model_source": "local-chat-completions", "model_name": "quant", "model_name_sanitized": "quant", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": true, "chat_template": "", "chat_template_sha": null, "total_evaluation_time_seconds": "194.30914269999994" }