{
"results": {
"agieval": {
"acc,none": 0.5544267053701016,
"acc_stderr,none": 0.004859843455357734,
"alias": "agieval"
},
"agieval_aqua_rat": {
"alias": " - agieval_aqua_rat",
"acc,none": 0.3700787401574803,
"acc_stderr,none": 0.03035497929089593,
"acc_norm,none": 0.38188976377952755,
"acc_norm_stderr,none": 0.03054511159403859
},
"agieval_gaokao_biology": {
"alias": " - agieval_gaokao_biology",
"acc,none": 0.7380952380952381,
"acc_stderr,none": 0.030412684459928757,
"acc_norm,none": 0.7047619047619048,
"acc_norm_stderr,none": 0.03155253554505398
},
"agieval_gaokao_chemistry": {
"alias": " - agieval_gaokao_chemistry",
"acc,none": 0.4444444444444444,
"acc_stderr,none": 0.034620941824986436,
"acc_norm,none": 0.36231884057971014,
"acc_norm_stderr,none": 0.033489883876211865
},
"agieval_gaokao_chinese": {
"alias": " - agieval_gaokao_chinese",
"acc,none": 0.5528455284552846,
"acc_stderr,none": 0.031764911338391044,
"acc_norm,none": 0.5447154471544715,
"acc_norm_stderr,none": 0.03181583027784235
},
"agieval_gaokao_english": {
"alias": " - agieval_gaokao_english",
"acc,none": 0.8464052287581699,
"acc_stderr,none": 0.020645597910418787,
"acc_norm,none": 0.8431372549019608,
"acc_norm_stderr,none": 0.020823758837580905
},
"agieval_gaokao_geography": {
"alias": " - agieval_gaokao_geography",
"acc,none": 0.7688442211055276,
"acc_stderr,none": 0.029959803439140443,
"acc_norm,none": 0.7638190954773869,
"acc_norm_stderr,none": 0.030184574030479208
},
"agieval_gaokao_history": {
"alias": " - agieval_gaokao_history",
"acc,none": 0.7489361702127659,
"acc_stderr,none": 0.028346963777162452,
"acc_norm,none": 0.7361702127659574,
"acc_norm_stderr,none": 0.02880998985410295
},
"agieval_gaokao_mathcloze": {
"alias": " - agieval_gaokao_mathcloze",
"acc,none": 0.025423728813559324,
"acc_stderr,none": 0.01455239952216708
},
"agieval_gaokao_mathqa": {
"alias": " - agieval_gaokao_mathqa",
"acc,none": 0.4188034188034188,
"acc_stderr,none": 0.026371365163318804,
"acc_norm,none": 0.37606837606837606,
"acc_norm_stderr,none": 0.0258921362904796
},
"agieval_gaokao_physics": {
"alias": " - agieval_gaokao_physics",
"acc,none": 0.59,
"acc_stderr,none": 0.034865138597849274,
"acc_norm,none": 0.56,
"acc_norm_stderr,none": 0.03518793763172071
},
"agieval_jec_qa_ca": {
"alias": " - agieval_jec_qa_ca",
"acc,none": 0.6466466466466466,
"acc_stderr,none": 0.015131181922110867,
"acc_norm,none": 0.5565565565565566,
"acc_norm_stderr,none": 0.01572564618087532
},
"agieval_jec_qa_kd": {
"alias": " - agieval_jec_qa_kd",
"acc,none": 0.703,
"acc_stderr,none": 0.0144568322948011,
"acc_norm,none": 0.629,
"acc_norm_stderr,none": 0.015283736211823187
},
"agieval_logiqa_en": {
"alias": " - agieval_logiqa_en",
"acc,none": 0.5944700460829493,
"acc_stderr,none": 0.019258381208154284,
"acc_norm,none": 0.533026113671275,
"acc_norm_stderr,none": 0.01956878502638526
},
"agieval_logiqa_zh": {
"alias": " - agieval_logiqa_zh",
"acc,none": 0.5775729646697388,
"acc_stderr,none": 0.01937414753071922,
"acc_norm,none": 0.5253456221198156,
"acc_norm_stderr,none": 0.019586400283373922
},
"agieval_lsat_ar": {
"alias": " - agieval_lsat_ar",
"acc,none": 0.33043478260869563,
"acc_stderr,none": 0.031082903446842964,
"acc_norm,none": 0.33043478260869563,
"acc_norm_stderr,none": 0.031082903446842964
},
"agieval_lsat_lr": {
"alias": " - agieval_lsat_lr",
"acc,none": 0.7235294117647059,
"acc_stderr,none": 0.019824108780753007,
"acc_norm,none": 0.6313725490196078,
"acc_norm_stderr,none": 0.021383450873181317
},
"agieval_lsat_rc": {
"alias": " - agieval_lsat_rc",
"acc,none": 0.7992565055762082,
"acc_stderr,none": 0.024467885125224527,
"acc_norm,none": 0.6728624535315985,
"acc_norm_stderr,none": 0.02865899432669078
},
"agieval_math": {
"alias": " - agieval_math",
"acc,none": 0.069,
"acc_stderr,none": 0.008018934050315138
},
"agieval_sat_en": {
"alias": " - agieval_sat_en",
"acc,none": 0.8640776699029126,
"acc_stderr,none": 0.023935630169275284,
"acc_norm,none": 0.7669902912621359,
"acc_norm_stderr,none": 0.029526026912337827
},
"agieval_sat_en_without_passage": {
"alias": " - agieval_sat_en_without_passage",
"acc,none": 0.5145631067961165,
"acc_stderr,none": 0.034906699050989067,
"acc_norm,none": 0.4320388349514563,
"acc_norm_stderr,none": 0.0345974255383149
},
"agieval_sat_math": {
"alias": " - agieval_sat_math",
"acc,none": 0.5727272727272728,
"acc_stderr,none": 0.03342754338309286,
"acc_norm,none": 0.5227272727272727,
"acc_norm_stderr,none": 0.03375194708230163
}
},
"groups": {
"agieval": {
"acc,none": 0.5544267053701016,
"acc_stderr,none": 0.004859843455357734,
"alias": "agieval"
}
},
"group_subtasks": {
"agieval": [
"agieval_gaokao_biology",
"agieval_gaokao_chemistry",
"agieval_gaokao_chinese",
"agieval_gaokao_geography",
"agieval_gaokao_history",
"agieval_gaokao_mathcloze",
"agieval_gaokao_mathqa",
"agieval_gaokao_physics",
"agieval_jec_qa_ca",
"agieval_jec_qa_kd",
"agieval_logiqa_zh",
"agieval_aqua_rat",
"agieval_gaokao_english",
"agieval_logiqa_en",
"agieval_lsat_ar",
"agieval_lsat_lr",
"agieval_lsat_rc",
"agieval_math",
"agieval_sat_en_without_passage",
"agieval_sat_en",
"agieval_sat_math"
]
},
"configs": {
"agieval_aqua_rat": {
"task": "agieval_aqua_rat",
"dataset_path": "hails/agieval-aqua-rat",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_biology": {
"task": "agieval_gaokao_biology",
"dataset_path": "hails/agieval-gaokao-biology",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_chemistry": {
"task": "agieval_gaokao_chemistry",
"dataset_path": "hails/agieval-gaokao-chemistry",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_chinese": {
"task": "agieval_gaokao_chinese",
"dataset_path": "hails/agieval-gaokao-chinese",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_english": {
"task": "agieval_gaokao_english",
"dataset_path": "hails/agieval-gaokao-english",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_geography": {
"task": "agieval_gaokao_geography",
"dataset_path": "hails/agieval-gaokao-geography",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_history": {
"task": "agieval_gaokao_history",
"dataset_path": "hails/agieval-gaokao-history",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_mathcloze": {
"task": "agieval_gaokao_mathcloze",
"dataset_path": "hails/agieval-gaokao-mathcloze",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{answer}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidate = results[0]\n\n gold = doc[\"answer\"]\n\n if not gold:\n print(doc, candidate, gold)\n if is_equiv(candidate, gold):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"acc\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"max_gen_toks": 32,
"do_sample": false,
"temperature": 0.0,
"until": [
"Q:"
]
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_mathqa": {
"task": "agieval_gaokao_mathqa",
"dataset_path": "hails/agieval-gaokao-mathqa",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_gaokao_physics": {
"task": "agieval_gaokao_physics",
"dataset_path": "hails/agieval-gaokao-physics",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_jec_qa_ca": {
"task": "agieval_jec_qa_ca",
"dataset_path": "hails/agieval-jec-qa-ca",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_jec_qa_kd": {
"task": "agieval_jec_qa_kd",
"dataset_path": "hails/agieval-jec-qa-kd",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_logiqa_en": {
"task": "agieval_logiqa_en",
"dataset_path": "hails/agieval-logiqa-en",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_logiqa_zh": {
"task": "agieval_logiqa_zh",
"dataset_path": "hails/agieval-logiqa-zh",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_lsat_ar": {
"task": "agieval_lsat_ar",
"dataset_path": "hails/agieval-lsat-ar",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_lsat_lr": {
"task": "agieval_lsat_lr",
"dataset_path": "hails/agieval-lsat-lr",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_lsat_rc": {
"task": "agieval_lsat_rc",
"dataset_path": "hails/agieval-lsat-rc",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_math": {
"task": "agieval_math",
"dataset_path": "hails/agieval-math",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{answer}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidate = results[0]\n\n gold = doc[\"answer\"]\n\n if not gold:\n print(doc, candidate, gold)\n if is_equiv(candidate, gold):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"acc\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"max_gen_toks": 32,
"do_sample": false,
"temperature": 0.0,
"until": [
"Q:"
]
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_sat_en": {
"task": "agieval_sat_en",
"dataset_path": "hails/agieval-sat-en",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_sat_en_without_passage": {
"task": "agieval_sat_en_without_passage",
"dataset_path": "hails/agieval-sat-en-without-passage",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"agieval_sat_math": {
"task": "agieval_sat_math",
"dataset_path": "hails/agieval-sat-math",
"test_split": "test",
"doc_to_text": "{{query}}",
"doc_to_target": "{{gold}}",
"doc_to_choice": "{{choices}}",
"process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"agieval": 0.0,
"agieval_aqua_rat": 1.0,
"agieval_gaokao_biology": 1.0,
"agieval_gaokao_chemistry": 1.0,
"agieval_gaokao_chinese": 1.0,
"agieval_gaokao_english": 1.0,
"agieval_gaokao_geography": 1.0,
"agieval_gaokao_history": 1.0,
"agieval_gaokao_mathcloze": 1.0,
"agieval_gaokao_mathqa": 1.0,
"agieval_gaokao_physics": 1.0,
"agieval_jec_qa_ca": 1.0,
"agieval_jec_qa_kd": 1.0,
"agieval_logiqa_en": 1.0,
"agieval_logiqa_zh": 1.0,
"agieval_lsat_ar": 1.0,
"agieval_lsat_lr": 1.0,
"agieval_lsat_rc": 1.0,
"agieval_math": 1.0,
"agieval_sat_en": 1.0,
"agieval_sat_en_without_passage": 1.0,
"agieval_sat_math": 1.0
},
"n-shot": {
"agieval_aqua_rat": 0,
"agieval_gaokao_biology": 0,
"agieval_gaokao_chemistry": 0,
"agieval_gaokao_chinese": 0,
"agieval_gaokao_english": 0,
"agieval_gaokao_geography": 0,
"agieval_gaokao_history": 0,
"agieval_gaokao_mathcloze": 0,
"agieval_gaokao_mathqa": 0,
"agieval_gaokao_physics": 0,
"agieval_jec_qa_ca": 0,
"agieval_jec_qa_kd": 0,
"agieval_logiqa_en": 0,
"agieval_logiqa_zh": 0,
"agieval_lsat_ar": 0,
"agieval_lsat_lr": 0,
"agieval_lsat_rc": 0,
"agieval_math": 0,
"agieval_sat_en": 0,
"agieval_sat_en_without_passage": 0,
"agieval_sat_math": 0
},
"higher_is_better": {
"agieval": {
"acc": true,
"acc_norm": true
},
"agieval_aqua_rat": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_biology": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_chemistry": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_chinese": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_english": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_geography": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_history": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_mathcloze": {
"acc": true
},
"agieval_gaokao_mathqa": {
"acc": true,
"acc_norm": true
},
"agieval_gaokao_physics": {
"acc": true,
"acc_norm": true
},
"agieval_jec_qa_ca": {
"acc": true,
"acc_norm": true
},
"agieval_jec_qa_kd": {
"acc": true,
"acc_norm": true
},
"agieval_logiqa_en": {
"acc": true,
"acc_norm": true
},
"agieval_logiqa_zh": {
"acc": true,
"acc_norm": true
},
"agieval_lsat_ar": {
"acc": true,
"acc_norm": true
},
"agieval_lsat_lr": {
"acc": true,
"acc_norm": true
},
"agieval_lsat_rc": {
"acc": true,
"acc_norm": true
},
"agieval_math": {
"acc": true
},
"agieval_sat_en": {
"acc": true,
"acc_norm": true
},
"agieval_sat_en_without_passage": {
"acc": true,
"acc_norm": true
},
"agieval_sat_math": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"agieval_gaokao_biology": {
"original": 210,
"effective": 210
},
"agieval_gaokao_chemistry": {
"original": 207,
"effective": 207
},
"agieval_gaokao_chinese": {
"original": 246,
"effective": 246
},
"agieval_gaokao_geography": {
"original": 199,
"effective": 199
},
"agieval_gaokao_history": {
"original": 235,
"effective": 235
},
"agieval_gaokao_mathcloze": {
"original": 118,
"effective": 118
},
"agieval_gaokao_mathqa": {
"original": 351,
"effective": 351
},
"agieval_gaokao_physics": {
"original": 200,
"effective": 200
},
"agieval_jec_qa_ca": {
"original": 999,
"effective": 999
},
"agieval_jec_qa_kd": {
"original": 1000,
"effective": 1000
},
"agieval_logiqa_zh": {
"original": 651,
"effective": 651
},
"agieval_aqua_rat": {
"original": 254,
"effective": 254
},
"agieval_gaokao_english": {
"original": 306,
"effective": 306
},
"agieval_logiqa_en": {
"original": 651,
"effective": 651
},
"agieval_lsat_ar": {
"original": 230,
"effective": 230
},
"agieval_lsat_lr": {
"original": 510,
"effective": 510
},
"agieval_lsat_rc": {
"original": 269,
"effective": 269
},
"agieval_math": {
"original": 1000,
"effective": 1000
},
"agieval_sat_en_without_passage": {
"original": 206,
"effective": 206
},
"agieval_sat_en": {
"original": 206,
"effective": 206
},
"agieval_sat_math": {
"original": 220,
"effective": 220
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=meta-llama/Llama-3.3-70B-Instruct,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.9,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": "150ae04f",
"date": 1737578738.814069,
"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: 4890.87\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==1.26.4\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": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
"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": {},
"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": 120759.780132137,
"end_time": 122538.423654986,
"total_evaluation_time_seconds": "1778.6435228490009"
}