lanawwas/ALLaM-7B-Instruct-preview
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
3e4c694337c9a4ae6c4c26280d6f4396e06a0d71
ALLaM-7B-Instruct-preview/evaluations/en/jais-family-30b-16k-chat/mmlu_pro_5_shot.json

1088 lines
37 KiB
JSON
Raw Normal View History

初始化项目，由ModelHub XC社区提供模型 Model: lanawwas/ALLaM-7B-Instruct-preview Source: Original Platform
2026-04-22 10:54:04 +08:00
{
"results": {
"mmlu_pro": {
"exact_match,custom-extract": 0.29105718085106386,
"exact_match_stderr,custom-extract": 0.004045455801481703,
"alias": "mmlu_pro"
},
"mmlu_pro_biology": {
"alias": " - biology",
"exact_match,custom-extract": 0.497907949790795,
"exact_match_stderr,custom-extract": 0.018685713754092666
},
"mmlu_pro_business": {
"alias": " - business",
"exact_match,custom-extract": 0.2965779467680608,
"exact_match_stderr,custom-extract": 0.01627100236909377
},
"mmlu_pro_chemistry": {
"alias": " - chemistry",
"exact_match,custom-extract": 0.15371024734982333,
"exact_match_stderr,custom-extract": 0.010724564101310088
},
"mmlu_pro_computer_science": {
"alias": " - computer_science",
"exact_match,custom-extract": 0.2731707317073171,
"exact_match_stderr,custom-extract": 0.022032898443099337
},
"mmlu_pro_economics": {
"alias": " - economics",
"exact_match,custom-extract": 0.38981042654028436,
"exact_match_stderr,custom-extract": 0.016797526292939735
},
"mmlu_pro_engineering": {
"alias": " - engineering",
"exact_match,custom-extract": 0.19917440660474717,
"exact_match_stderr,custom-extract": 0.012836542393424185
},
"mmlu_pro_health": {
"alias": " - health",
"exact_match,custom-extract": 0.2921760391198044,
"exact_match_stderr,custom-extract": 0.015910136307153433
},
"mmlu_pro_history": {
"alias": " - history",
"exact_match,custom-extract": 0.30183727034120733,
"exact_match_stderr,custom-extract": 0.023549026830612066
},
"mmlu_pro_law": {
"alias": " - law",
"exact_match,custom-extract": 0.21435059037238874,
"exact_match_stderr,custom-extract": 0.01237315329763305
},
"mmlu_pro_math": {
"alias": " - math",
"exact_match,custom-extract": 0.2938564026646928,
"exact_match_stderr,custom-extract": 0.012397873690981328
},
"mmlu_pro_other": {
"alias": " - other",
"exact_match,custom-extract": 0.37445887445887444,
"exact_match_stderr,custom-extract": 0.015930490460901763
},
"mmlu_pro_philosophy": {
"alias": " - philosophy",
"exact_match,custom-extract": 0.30861723446893785,
"exact_match_stderr,custom-extract": 0.02069925386475545
},
"mmlu_pro_physics": {
"alias": " - physics",
"exact_match,custom-extract": 0.19322555812163203,
"exact_match_stderr,custom-extract": 0.01095900196390405
},
"mmlu_pro_psychology": {
"alias": " - psychology",
"exact_match,custom-extract": 0.4573934837092732,
"exact_match_stderr,custom-extract": 0.01764648975617073
}
},
"groups": {
"mmlu_pro": {
"exact_match,custom-extract": 0.29105718085106386,
"exact_match_stderr,custom-extract": 0.004045455801481703,
"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 0x14bf17402cb0>, subject='biology')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf174024d0>, 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 0x14bf17401090>, 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 0x14bf174016c0>, subject='business')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17400940>, 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 0x14bf17402950>, 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 0x14bf17400f70>, subject='chemistry')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17403910>, 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 0x14bf17403eb0>, 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 0x14bf17403490>, subject='computer science')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17401bd0>, 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 0x14bf17403a30>, 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 0x14bf17401630>, subject='economics')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17402200>, 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 0x14bf17402680>, 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 0x14bf174cf400>, subject='engineering')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17402ef0>, 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 0x14bf17403880>, 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 0x14bf17400160>, subject='health')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17403760>, 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 0x14bf174011b0>, 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 0x14bf174030a0>, subject='history')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17403010>, 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 0x14bf17402f80>, 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 0x14bf174cf880>, subject='law')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf174cf2e0>, 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 0x14bf174cf130>, 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 0x14bf17400b80>, subject='math')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17400310>, 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 0x14bf17400550>, 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 0x14bf174cfe20>, subject='other')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf174cff40>, 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 0x14bf174cfa30>, 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 0x14bf175130a0>, subject='philosophy')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf17512560>, 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 0x14bf174cecb0>, 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 0x14bf174ceb00>, subject='physics')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf174cea70>, 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 0x14bf174ce9e0>, 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 0x14bf17513910>, subject='psychology')",
"doc_to_text": "functools.partial(<function format_cot_example at 0x14bf175139a0>, 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 0x14bf17513ac0>, 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=inceptionai/jais-family-30b-16k-chat,tensor_parallel_size=1,data_parallel_size=2,gpu_memory_utilization=0.98,download_dir=/tmp,enforce_eager=True,max_model_len=10000",
"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": "8e1bd48d",
"date": 1736072145.8242593,
"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 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\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): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\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: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\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.
"transformers_version": "4.47.1",
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
"tokenizer_pad_token": [
"<|endoftext|>",
"0"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"0"
],
"tokenizer_bos_token": [
"<|endoftext|>",
"0"
],
"eot_token_id": 0,
"max_length": 10000,
"task_hashes": {},
"model_source": "vllm",
"model_name": "inceptionai/jais-family-30b-16k-chat",
"model_name_sanitized": "inceptionai__jais-family-30b-16k-chat",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 16900.353835721,
"end_time": 27308.331463962,
"total_evaluation_time_seconds": "10407.977628240998"
}
Reference in New Issue Copy Permalink