| { | |
| "results": { | |
| "mmlu_pro": { | |
| "exact_match,custom-extract": 0.6050531914893617, | |
| "exact_match_stderr,custom-extract": 0.004324280084491081, | |
| "alias": "mmlu_pro" | |
| }, | |
| "mmlu_pro_biology": { | |
| "alias": " - biology", | |
| "exact_match,custom-extract": 0.797768479776848, | |
| "exact_match_stderr,custom-extract": 0.01501088675930961 | |
| }, | |
| "mmlu_pro_business": { | |
| "alias": " - business", | |
| "exact_match,custom-extract": 0.6501901140684411, | |
| "exact_match_stderr,custom-extract": 0.01698920714561709 | |
| }, | |
| "mmlu_pro_chemistry": { | |
| "alias": " - chemistry", | |
| "exact_match,custom-extract": 0.4628975265017668, | |
| "exact_match_stderr,custom-extract": 0.014826536252330106 | |
| }, | |
| "mmlu_pro_computer_science": { | |
| "alias": " - computer_science", | |
| "exact_match,custom-extract": 0.6292682926829268, | |
| "exact_match_stderr,custom-extract": 0.023882849188210376 | |
| }, | |
| "mmlu_pro_economics": { | |
| "alias": " - economics", | |
| "exact_match,custom-extract": 0.7571090047393365, | |
| "exact_match_stderr,custom-extract": 0.01476968134954848 | |
| }, | |
| "mmlu_pro_engineering": { | |
| "alias": " - engineering", | |
| "exact_match,custom-extract": 0.4107327141382869, | |
| "exact_match_stderr,custom-extract": 0.015812412469129674 | |
| }, | |
| "mmlu_pro_health": { | |
| "alias": " - health", | |
| "exact_match,custom-extract": 0.6894865525672371, | |
| "exact_match_stderr,custom-extract": 0.01618795835147117 | |
| }, | |
| "mmlu_pro_history": { | |
| "alias": " - history", | |
| "exact_match,custom-extract": 0.6456692913385826, | |
| "exact_match_stderr,custom-extract": 0.02453678535763431 | |
| }, | |
| "mmlu_pro_law": { | |
| "alias": " - law", | |
| "exact_match,custom-extract": 0.46684831970935514, | |
| "exact_match_stderr,custom-extract": 0.01504239361072275 | |
| }, | |
| "mmlu_pro_math": { | |
| "alias": " - math", | |
| "exact_match,custom-extract": 0.5758697261287935, | |
| "exact_match_stderr,custom-extract": 0.013450699683222997 | |
| }, | |
| "mmlu_pro_other": { | |
| "alias": " - other", | |
| "exact_match,custom-extract": 0.6829004329004329, | |
| "exact_match_stderr,custom-extract": 0.015317068975451516 | |
| }, | |
| "mmlu_pro_philosophy": { | |
| "alias": " - philosophy", | |
| "exact_match,custom-extract": 0.6132264529058116, | |
| "exact_match_stderr,custom-extract": 0.02182348732721747 | |
| }, | |
| "mmlu_pro_physics": { | |
| "alias": " - physics", | |
| "exact_match,custom-extract": 0.5481139337952271, | |
| "exact_match_stderr,custom-extract": 0.013813780478397373 | |
| }, | |
| "mmlu_pro_psychology": { | |
| "alias": " - psychology", | |
| "exact_match,custom-extract": 0.7832080200501254, | |
| "exact_match_stderr,custom-extract": 0.014595904333460285 | |
| } | |
| }, | |
| "groups": { | |
| "mmlu_pro": { | |
| "exact_match,custom-extract": 0.6050531914893617, | |
| "exact_match_stderr,custom-extract": 0.004324280084491081, | |
| "alias": "mmlu_pro" | |
| } | |
| }, | |
| "group_subtasks": { | |
| "mmlu_pro": [ | |
| "mmlu_pro_biology", | |
| "mmlu_pro_business", | |
| "mmlu_pro_chemistry", | |
| "mmlu_pro_computer_science", | |
| "mmlu_pro_economics", | |
| "mmlu_pro_engineering", | |
| "mmlu_pro_health", | |
| "mmlu_pro_history", | |
| "mmlu_pro_law", | |
| "mmlu_pro_math", | |
| "mmlu_pro_other", | |
| "mmlu_pro_philosophy", | |
| "mmlu_pro_physics", | |
| "mmlu_pro_psychology" | |
| ] | |
| }, | |
| "configs": { | |
| "mmlu_pro_biology": { | |
| "task": "mmlu_pro_biology", | |
| "task_alias": "biology", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176f89d0>, subject='biology')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fa3b0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about biology. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9510>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_business": { | |
| "task": "mmlu_pro_business", | |
| "task_alias": "business", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176f9c60>, subject='business')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9a20>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about business. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fbe20>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_chemistry": { | |
| "task": "mmlu_pro_chemistry", | |
| "task_alias": "chemistry", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x145717718040>, subject='chemistry')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x145717718280>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about chemistry. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457177181f0>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_computer_science": { | |
| "task": "mmlu_pro_computer_science", | |
| "task_alias": "computer_science", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176fbb50>, subject='computer science')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176faef0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about computer science. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f8e50>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_economics": { | |
| "task": "mmlu_pro_economics", | |
| "task_alias": "economics", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176fa710>, subject='economics')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fa7a0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about economics. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fa0e0>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_engineering": { | |
| "task": "mmlu_pro_engineering", | |
| "task_alias": "engineering", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176fbc70>, subject='engineering')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fbbe0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about engineering. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fbd00>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_health": { | |
| "task": "mmlu_pro_health", | |
| "task_alias": "health", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176fb640>, subject='health')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fbd90>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about health. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fab90>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_history": { | |
| "task": "mmlu_pro_history", | |
| "task_alias": "history", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176f8dc0>, subject='history')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9120>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about history. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9240>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_law": { | |
| "task": "mmlu_pro_law", | |
| "task_alias": "law", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176f9750>, subject='law')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9fc0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about law. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fb130>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_math": { | |
| "task": "mmlu_pro_math", | |
| "task_alias": "math", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176fa9e0>, subject='math')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fb5b0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about math. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176fb490>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_other": { | |
| "task": "mmlu_pro_other", | |
| "task_alias": "other", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457176f8d30>, subject='other')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f97e0>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about other. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f83a0>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_philosophy": { | |
| "task": "mmlu_pro_philosophy", | |
| "task_alias": "philosophy", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x1457458368c0>, subject='philosophy')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x145745837d00>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about philosophy. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x1457176f9630>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_physics": { | |
| "task": "mmlu_pro_physics", | |
| "task_alias": "physics", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x145745837d90>, subject='physics')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x145745837c70>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about physics. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x14574572beb0>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "mmlu_pro_psychology": { | |
| "task": "mmlu_pro_psychology", | |
| "task_alias": "psychology", | |
| "dataset_path": "TIGER-Lab/MMLU-Pro", | |
| "test_split": "test", | |
| "fewshot_split": "validation", | |
| "process_docs": "functools.partial(<function process_docs at 0x145745837f40>, subject='psychology')", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x14574569c040>, including_answer=False)", | |
| "doc_to_target": "answer", | |
| "description": "The following are multiple choice questions (with answers) about psychology. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "fewshot_config": { | |
| "sampler": "first_n", | |
| "doc_to_text": "functools.partial(<function format_cot_example at 0x14574569c160>, including_answer=True)", | |
| "doc_to_target": "" | |
| }, | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "exact_match", | |
| "aggregation": "mean", | |
| "higher_is_better": true, | |
| "ignore_case": true, | |
| "ignore_punctuation": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "until": [ | |
| "</s>", | |
| "Q:", | |
| "<|im_end|>" | |
| ], | |
| "do_sample": false, | |
| "temperature": 0.0 | |
| }, | |
| "repeats": 1, | |
| "filter_list": [ | |
| { | |
| "name": "custom-extract", | |
| "filter": [ | |
| { | |
| "function": "regex", | |
| "regex_pattern": "answer is \\(?([ABCDEFGHIJ])\\)?" | |
| }, | |
| { | |
| "function": "take_first" | |
| } | |
| ] | |
| } | |
| ], | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "mmlu_pro": 2.0, | |
| "mmlu_pro_biology": 1.0, | |
| "mmlu_pro_business": 1.0, | |
| "mmlu_pro_chemistry": 1.0, | |
| "mmlu_pro_computer_science": 1.0, | |
| "mmlu_pro_economics": 1.0, | |
| "mmlu_pro_engineering": 1.0, | |
| "mmlu_pro_health": 1.0, | |
| "mmlu_pro_history": 1.0, | |
| "mmlu_pro_law": 1.0, | |
| "mmlu_pro_math": 1.0, | |
| "mmlu_pro_other": 1.0, | |
| "mmlu_pro_philosophy": 1.0, | |
| "mmlu_pro_physics": 1.0, | |
| "mmlu_pro_psychology": 1.0 | |
| }, | |
| "n-shot": { | |
| "mmlu_pro_biology": 5, | |
| "mmlu_pro_business": 5, | |
| "mmlu_pro_chemistry": 5, | |
| "mmlu_pro_computer_science": 5, | |
| "mmlu_pro_economics": 5, | |
| "mmlu_pro_engineering": 5, | |
| "mmlu_pro_health": 5, | |
| "mmlu_pro_history": 5, | |
| "mmlu_pro_law": 5, | |
| "mmlu_pro_math": 5, | |
| "mmlu_pro_other": 5, | |
| "mmlu_pro_philosophy": 5, | |
| "mmlu_pro_physics": 5, | |
| "mmlu_pro_psychology": 5 | |
| }, | |
| "higher_is_better": { | |
| "mmlu_pro": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_biology": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_business": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_chemistry": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_computer_science": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_economics": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_engineering": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_health": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_history": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_law": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_math": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_other": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_philosophy": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_physics": { | |
| "exact_match": true | |
| }, | |
| "mmlu_pro_psychology": { | |
| "exact_match": true | |
| } | |
| }, | |
| "n-samples": { | |
| "mmlu_pro_biology": { | |
| "original": 717, | |
| "effective": 717 | |
| }, | |
| "mmlu_pro_business": { | |
| "original": 789, | |
| "effective": 789 | |
| }, | |
| "mmlu_pro_chemistry": { | |
| "original": 1132, | |
| "effective": 1132 | |
| }, | |
| "mmlu_pro_computer_science": { | |
| "original": 410, | |
| "effective": 410 | |
| }, | |
| "mmlu_pro_economics": { | |
| "original": 844, | |
| "effective": 844 | |
| }, | |
| "mmlu_pro_engineering": { | |
| "original": 969, | |
| "effective": 969 | |
| }, | |
| "mmlu_pro_health": { | |
| "original": 818, | |
| "effective": 818 | |
| }, | |
| "mmlu_pro_history": { | |
| "original": 381, | |
| "effective": 381 | |
| }, | |
| "mmlu_pro_law": { | |
| "original": 1101, | |
| "effective": 1101 | |
| }, | |
| "mmlu_pro_math": { | |
| "original": 1351, | |
| "effective": 1351 | |
| }, | |
| "mmlu_pro_other": { | |
| "original": 924, | |
| "effective": 924 | |
| }, | |
| "mmlu_pro_philosophy": { | |
| "original": 499, | |
| "effective": 499 | |
| }, | |
| "mmlu_pro_physics": { | |
| "original": 1299, | |
| "effective": 1299 | |
| }, | |
| "mmlu_pro_psychology": { | |
| "original": 798, | |
| "effective": 798 | |
| } | |
| }, | |
| "config": { | |
| "model": "vllm", | |
| "model_args": "pretrained=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.8,download_dir=/tmp,enforce_eager=True", | |
| "batch_size": 1, | |
| "batch_sizes": [], | |
| "device": null, | |
| "use_cache": null, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null, | |
| "random_seed": 0, | |
| "numpy_seed": 1234, | |
| "torch_seed": 1234, | |
| "fewshot_seed": 1234 | |
| }, | |
| "git_hash": "788a3672", | |
| "date": 1737968180.8770437, | |
| "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect", | |
| "transformers_version": "4.48.1", | |
| "upper_git_hash": null, | |
| "tokenizer_pad_token": [ | |
| "<|finetune_right_pad_id|>", | |
| "128004" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "<|eot_id|>", | |
| "128009" | |
| ], | |
| "tokenizer_bos_token": [ | |
| "<|begin_of_text|>", | |
| "128000" | |
| ], | |
| "eot_token_id": 128009, | |
| "max_length": 131072, | |
| "task_hashes": { | |
| "mmlu_pro_biology": "78a27f3d4ea386dd0f7b5045f25bf654ba560ee9feac7b22eab763c73b4c37b9", | |
| "mmlu_pro_business": "9d10f8702f23d8d5aa9546ebf453e9333a6998a272450bc468b8f74bca8a1824", | |
| "mmlu_pro_chemistry": "0e3a8823fed7bd895e42f5053851f12b125f62edfcb36809e4c0aebec80f4506", | |
| "mmlu_pro_computer_science": "26e8d9026807a7552684e4ddd1a373873449548e0f0ac8abeada18f32cc5f685", | |
| "mmlu_pro_economics": "427580d476e69dc8f095f487f3081cbff1dbfdd3a05a4c13c024ae5bd6907262", | |
| "mmlu_pro_engineering": "66bc34b22bf2c19eab04a753e65e8aea2e6834544b27516a6aa2769a9be0b9e5", | |
| "mmlu_pro_health": "62edd914028ea5b83013192e458af0d22b843d25ce0ac6e280244d819615cdc4", | |
| "mmlu_pro_history": "8295796e4901f2a6b42a2bd8b6e888f2e64ae24ce451f8ecef70db6351f3583d", | |
| "mmlu_pro_law": "6969a0ecb6ac565ee29e658094231ddcf1016237aff3d903f5d219dd68a2e5dd", | |
| "mmlu_pro_math": "eb48989afd83cb45e2dfd8c769fbe986927de9eb06ac775a7237e939150f20ec", | |
| "mmlu_pro_other": "82e12fde3ce84ca4d478ce4623e9dd3877b8bd46c7fc1346c3d9e534df9cbba3", | |
| "mmlu_pro_philosophy": "1cd86d5d342a6029560af9a2d51e397df4f537d81d4e6249a0917267c91073e1", | |
| "mmlu_pro_physics": "dce786711af6f503b9b1463ca9e245de515859363f4ee7f0aa94656c3357a288", | |
| "mmlu_pro_psychology": "526f25dba79a26df39f911b7d6010990c8e21d7c473c89a94e4298566d7cdeda" | |
| }, | |
| "model_source": "vllm", | |
| "model_name": "meta-llama/Llama-3.3-70B-Instruct", | |
| "model_name_sanitized": "meta-llama__Llama-3.3-70B-Instruct", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": null, | |
| "chat_template_sha": null, | |
| "start_time": 69200.147843926, | |
| "end_time": 72294.189406545, | |
| "total_evaluation_time_seconds": "3094.041562619008" | |
| } |