{
"results": {
"mmlu_pro": {
"exact_match,custom-extract": 0.4747340425531915,
"exact_match_stderr,custom-extract": 0.004428757017117927,
"alias": "mmlu_pro"
},
"mmlu_pro_biology": {
"alias": " - biology",
"exact_match,custom-extract": 0.700139470013947,
"exact_match_stderr,custom-extract": 0.017123613695979267
},
"mmlu_pro_business": {
"alias": " - business",
"exact_match,custom-extract": 0.49429657794676807,
"exact_match_stderr,custom-extract": 0.017810603660812285
},
"mmlu_pro_chemistry": {
"alias": " - chemistry",
"exact_match,custom-extract": 0.33568904593639576,
"exact_match_stderr,custom-extract": 0.014041806669685108
},
"mmlu_pro_computer_science": {
"alias": " - computer_science",
"exact_match,custom-extract": 0.5414634146341464,
"exact_match_stderr,custom-extract": 0.024638252468695724
},
"mmlu_pro_economics": {
"alias": " - economics",
"exact_match,custom-extract": 0.6030805687203792,
"exact_match_stderr,custom-extract": 0.016850976027020036
},
"mmlu_pro_engineering": {
"alias": " - engineering",
"exact_match,custom-extract": 0.33436532507739936,
"exact_match_stderr,custom-extract": 0.015163201516522406
},
"mmlu_pro_health": {
"alias": " - health",
"exact_match,custom-extract": 0.5537897310513448,
"exact_match_stderr,custom-extract": 0.017391266144447512
},
"mmlu_pro_history": {
"alias": " - history",
"exact_match,custom-extract": 0.5065616797900262,
"exact_match_stderr,custom-extract": 0.025647249999209133
},
"mmlu_pro_law": {
"alias": " - law",
"exact_match,custom-extract": 0.3024523160762943,
"exact_match_stderr,custom-extract": 0.013849020726009176
},
"mmlu_pro_math": {
"alias": " - math",
"exact_match,custom-extract": 0.4722427831236121,
"exact_match_stderr,custom-extract": 0.013587290818486789
},
"mmlu_pro_other": {
"alias": " - other",
"exact_match,custom-extract": 0.5422077922077922,
"exact_match_stderr,custom-extract": 0.0163989569164936
},
"mmlu_pro_philosophy": {
"alias": " - philosophy",
"exact_match,custom-extract": 0.4969939879759519,
"exact_match_stderr,custom-extract": 0.022405130826057537
},
"mmlu_pro_physics": {
"alias": " - physics",
"exact_match,custom-extract": 0.39568899153194764,
"exact_match_stderr,custom-extract": 0.01357281377947953
},
"mmlu_pro_psychology": {
"alias": " - psychology",
"exact_match,custom-extract": 0.6328320802005013,
"exact_match_stderr,custom-extract": 0.01707447846620369
}
},
"groups": {
"mmlu_pro": {
"exact_match,custom-extract": 0.4747340425531915,
"exact_match_stderr,custom-extract": 0.004428757017117927,
"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 0x14a8d80232e0>, subject='biology')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a899d2c040>, 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 0x14a899d2c0d0>, 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 0x14a8d80c71c0>, subject='business')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c5750>, 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 0x14a8d80c5f30>, 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 0x14a8d80c4d30>, subject='chemistry')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c4700>, 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 0x14a8d80c5360>, 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 0x14a8d80c5fc0>, subject='computer science')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c6560>, 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 0x14a8d80c6b00>, 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 0x14a8d80c63b0>, subject='economics')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c6f80>, 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 0x14a8d80c5bd0>, 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 0x14a8d80c5ab0>, subject='engineering')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c7eb0>, 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 0x14a8d80c49d0>, 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 0x14a8d80c7130>, subject='health')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c72e0>, 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 0x14a8d80c6d40>, 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 0x14a8d80c5900>, subject='history')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c48b0>, 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 0x14a8d80c4ee0>, 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 0x14a8d80c6950>, subject='law')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c4f70>, 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 0x14a8d80c7250>, 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 0x14a8d80c6a70>, subject='math')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80c7640>, 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 0x14a8d80c7520>, 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 0x14a8d807f880>, subject='other')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d807f910>, 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 0x14a8d807f5b0>, 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 0x14a8d8023ac0>, subject='philosophy')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d80237f0>, 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 0x14a8d80239a0>, 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 0x14a8d807fc70>, subject='physics')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8d807fd90>, 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 0x14a8d807ff40>, 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 0x14a8ecf3b2e0>, subject='psychology')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14a8ecf3b370>, 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 0x14a8ecf3b490>, 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": "hf",
"model_args": "parallelize=False,pretrained=mistralai/Mistral-Small-Instruct-2409,trust_remote_code=True,mm=False",
"model_num_parameters": 22247282688,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "8012044390bdc1c6d8ab162f5416220f43bf517b",
"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": "3127d82f",
"date": 1731256655.6490734,
"pretty_env_info": "PyTorch version: 2.1.0a0+29c30b1\nIs debug build: False\nCUDA used to build PyTorch: 12.2\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: 4890.87\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==1.22.2\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.1.0a0+29c30b1\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==0.16.0a0\n[pip3] triton==2.0.0.dev20221202\n[conda] Could not collect",
"transformers_version": "4.38.2",
"upper_git_hash": null,
"tokenizer_pad_token": [
"</s>",
"2"
],
"tokenizer_eos_token": [
"</s>",
"2"
],
"tokenizer_bos_token": [
"<s>",
"1"
],
"eot_token_id": 2,
"max_length": 32768,
"task_hashes": {},
"model_source": "hf",
"model_name": "mistralai/Mistral-Small-Instruct-2409",
"model_name_sanitized": "mistralai__Mistral-Small-Instruct-2409",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 997.744980378,
"end_time": 151828.006223749,
"total_evaluation_time_seconds": "150830.261243371"
}