297 lines
5.5 KiB
JSON
297 lines
5.5 KiB
JSON
|
|
{
|
||
|
|
"model": "/home/zeus/microllm2/microllm2-checkpoints/final_merged",
|
||
|
|
"shots": 5,
|
||
|
|
"limit": 20,
|
||
|
|
"overall": {
|
||
|
|
"correct": 318,
|
||
|
|
"total": 1140,
|
||
|
|
"accuracy": 0.2789473684210526
|
||
|
|
},
|
||
|
|
"subjects": {
|
||
|
|
"abstract_algebra": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"anatomy": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"astronomy": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"business_ethics": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"clinical_knowledge": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"college_biology": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"college_chemistry": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
},
|
||
|
|
"college_computer_science": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"college_mathematics": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"college_medicine": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"college_physics": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
},
|
||
|
|
"computer_security": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"conceptual_physics": {
|
||
|
|
"correct": 1,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.05
|
||
|
|
},
|
||
|
|
"econometrics": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"electrical_engineering": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"elementary_mathematics": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"formal_logic": {
|
||
|
|
"correct": 2,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.1
|
||
|
|
},
|
||
|
|
"global_facts": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"high_school_biology": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"high_school_chemistry": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"high_school_computer_science": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"high_school_european_history": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"high_school_geography": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"high_school_government_and_politics": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"high_school_macroeconomics": {
|
||
|
|
"correct": 0,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.0
|
||
|
|
},
|
||
|
|
"high_school_mathematics": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"high_school_microeconomics": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"high_school_physics": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"high_school_psychology": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"high_school_statistics": {
|
||
|
|
"correct": 8,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.4
|
||
|
|
},
|
||
|
|
"high_school_us_history": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"high_school_world_history": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"human_aging": {
|
||
|
|
"correct": 8,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.4
|
||
|
|
},
|
||
|
|
"human_sexuality": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
},
|
||
|
|
"international_law": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"jurisprudence": {
|
||
|
|
"correct": 8,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.4
|
||
|
|
},
|
||
|
|
"logical_fallacies": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"machine_learning": {
|
||
|
|
"correct": 10,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.5
|
||
|
|
},
|
||
|
|
"management": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"marketing": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"medical_genetics": {
|
||
|
|
"correct": 8,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.4
|
||
|
|
},
|
||
|
|
"miscellaneous": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"moral_disputes": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"moral_scenarios": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
},
|
||
|
|
"nutrition": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"philosophy": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
},
|
||
|
|
"prehistory": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"professional_accounting": {
|
||
|
|
"correct": 6,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.3
|
||
|
|
},
|
||
|
|
"professional_law": {
|
||
|
|
"correct": 7,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.35
|
||
|
|
},
|
||
|
|
"professional_medicine": {
|
||
|
|
"correct": 1,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.05
|
||
|
|
},
|
||
|
|
"professional_psychology": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"public_relations": {
|
||
|
|
"correct": 9,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.45
|
||
|
|
},
|
||
|
|
"security_studies": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"sociology": {
|
||
|
|
"correct": 4,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.2
|
||
|
|
},
|
||
|
|
"us_foreign_policy": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"virology": {
|
||
|
|
"correct": 5,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.25
|
||
|
|
},
|
||
|
|
"world_religions": {
|
||
|
|
"correct": 3,
|
||
|
|
"total": 20,
|
||
|
|
"accuracy": 0.15
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|