Create README2.md
Browse files- README2.md +73 -0
README2.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
hf (pretrained=EpistemeAI/Hercules-gemma-3N-it-R1,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 1, batch_size: 8
|
| 2 |
+
| Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 3 |
+
|-----------------------------------------------------------|------:|------|-----:|------|---|-----:|---|-----:|
|
| 4 |
+
|global_mmlu_full_en | 0|none | |acc |↑ |0.6053|± |0.0039|
|
| 5 |
+
| - global_mmlu_full_en_humanities | 0|none | |acc |↑ |0.5515|± |0.0068|
|
| 6 |
+
| - global_mmlu_full_en_formal_logic | 0|none | 1|acc |↑ |0.4365|± |0.0444|
|
| 7 |
+
| - global_mmlu_full_en_high_school_european_history | 0|none | 1|acc |↑ |0.7455|± |0.0340|
|
| 8 |
+
| - global_mmlu_full_en_high_school_us_history | 0|none | 1|acc |↑ |0.8284|± |0.0265|
|
| 9 |
+
| - global_mmlu_full_en_high_school_world_history | 0|none | 1|acc |↑ |0.8059|± |0.0257|
|
| 10 |
+
| - global_mmlu_full_en_international_law | 0|none | 1|acc |↑ |0.7851|± |0.0375|
|
| 11 |
+
| - global_mmlu_full_en_jurisprudence | 0|none | 1|acc |↑ |0.7870|± |0.0396|
|
| 12 |
+
| - global_mmlu_full_en_logical_fallacies | 0|none | 1|acc |↑ |0.7485|± |0.0341|
|
| 13 |
+
| - global_mmlu_full_en_moral_disputes | 0|none | 1|acc |↑ |0.6532|± |0.0256|
|
| 14 |
+
| - global_mmlu_full_en_moral_scenarios | 0|none | 1|acc |↑ |0.3307|± |0.0157|
|
| 15 |
+
| - global_mmlu_full_en_philosophy | 0|none | 1|acc |↑ |0.6785|± |0.0265|
|
| 16 |
+
| - global_mmlu_full_en_prehistory | 0|none | 1|acc |↑ |0.6636|± |0.0263|
|
| 17 |
+
| - global_mmlu_full_en_professional_law | 0|none | 1|acc |↑ |0.4368|± |0.0127|
|
| 18 |
+
| - global_mmlu_full_en_world_religions | 0|none | 1|acc |↑ |0.8012|± |0.0306|
|
| 19 |
+
| - global_mmlu_full_en_other | 0|none | |acc |↑ |0.6707|± |0.0081|
|
| 20 |
+
| - global_mmlu_full_en_business_ethics | 0|none | 1|acc |↑ |0.5700|± |0.0498|
|
| 21 |
+
| - global_mmlu_full_en_clinical_knowledge | 0|none | 1|acc |↑ |0.6717|± |0.0289|
|
| 22 |
+
| - global_mmlu_full_en_college_medicine | 0|none | 1|acc |↑ |0.6301|± |0.0368|
|
| 23 |
+
| - global_mmlu_full_en_global_facts | 0|none | 1|acc |↑ |0.3700|± |0.0485|
|
| 24 |
+
| - global_mmlu_full_en_human_aging | 0|none | 1|acc |↑ |0.7085|± |0.0305|
|
| 25 |
+
| - global_mmlu_full_en_management | 0|none | 1|acc |↑ |0.8058|± |0.0392|
|
| 26 |
+
| - global_mmlu_full_en_marketing | 0|none | 1|acc |↑ |0.8504|± |0.0234|
|
| 27 |
+
| - global_mmlu_full_en_medical_genetics | 0|none | 1|acc |↑ |0.6500|± |0.0479|
|
| 28 |
+
| - global_mmlu_full_en_miscellaneous | 0|none | 1|acc |↑ |0.7918|± |0.0145|
|
| 29 |
+
| - global_mmlu_full_en_nutrition | 0|none | 1|acc |↑ |0.6503|± |0.0273|
|
| 30 |
+
| - global_mmlu_full_en_professional_accounting | 0|none | 1|acc |↑ |0.4468|± |0.0297|
|
| 31 |
+
| - global_mmlu_full_en_professional_medicine | 0|none | 1|acc |↑ |0.6250|± |0.0294|
|
| 32 |
+
| - global_mmlu_full_en_virology | 0|none | 1|acc |↑ |0.5000|± |0.0389|
|
| 33 |
+
| - global_mmlu_full_en_social_sciences | 0|none | |acc |↑ |0.7251|± |0.0078|
|
| 34 |
+
| - global_mmlu_full_en_econometrics | 0|none | 1|acc |↑ |0.4035|± |0.0462|
|
| 35 |
+
| - global_mmlu_full_en_high_school_geography | 0|none | 1|acc |↑ |0.8535|± |0.0252|
|
| 36 |
+
| - global_mmlu_full_en_high_school_government_and_politics| 0|none | 1|acc |↑ |0.8653|± |0.0246|
|
| 37 |
+
| - global_mmlu_full_en_high_school_macroeconomics | 0|none | 1|acc |↑ |0.6462|± |0.0242|
|
| 38 |
+
| - global_mmlu_full_en_high_school_microeconomics | 0|none | 1|acc |↑ |0.6807|± |0.0303|
|
| 39 |
+
| - global_mmlu_full_en_high_school_psychology | 0|none | 1|acc |↑ |0.8330|± |0.0160|
|
| 40 |
+
| - global_mmlu_full_en_human_sexuality | 0|none | 1|acc |↑ |0.6947|± |0.0404|
|
| 41 |
+
| - global_mmlu_full_en_professional_psychology | 0|none | 1|acc |↑ |0.6193|± |0.0196|
|
| 42 |
+
| - global_mmlu_full_en_public_relations | 0|none | 1|acc |↑ |0.7000|± |0.0439|
|
| 43 |
+
| - global_mmlu_full_en_security_studies | 0|none | 1|acc |↑ |0.7755|± |0.0267|
|
| 44 |
+
| - global_mmlu_full_en_sociology | 0|none | 1|acc |↑ |0.8060|± |0.0280|
|
| 45 |
+
| - global_mmlu_full_en_us_foreign_policy | 0|none | 1|acc |↑ |0.8200|± |0.0386|
|
| 46 |
+
| - global_mmlu_full_en_stem | 0|none | |acc |↑ |0.5043|± |0.0084|
|
| 47 |
+
| - global_mmlu_full_en_abstract_algebra | 0|none | 1|acc |↑ |0.3100|± |0.0465|
|
| 48 |
+
| - global_mmlu_full_en_anatomy | 0|none | 1|acc |↑ |0.6148|± |0.0420|
|
| 49 |
+
| - global_mmlu_full_en_astronomy | 0|none | 1|acc |↑ |0.7237|± |0.0364|
|
| 50 |
+
| - global_mmlu_full_en_college_biology | 0|none | 1|acc |↑ |0.7083|± |0.0380|
|
| 51 |
+
| - global_mmlu_full_en_college_chemistry | 0|none | 1|acc |↑ |0.4700|± |0.0502|
|
| 52 |
+
| - global_mmlu_full_en_college_computer_science | 0|none | 1|acc |↑ |0.4900|± |0.0502|
|
| 53 |
+
| - global_mmlu_full_en_college_mathematics | 0|none | 1|acc |↑ |0.3200|± |0.0469|
|
| 54 |
+
| - global_mmlu_full_en_college_physics | 0|none | 1|acc |↑ |0.3529|± |0.0476|
|
| 55 |
+
| - global_mmlu_full_en_computer_security | 0|none | 1|acc |↑ |0.7400|± |0.0441|
|
| 56 |
+
| - global_mmlu_full_en_conceptual_physics | 0|none | 1|acc |↑ |0.5660|± |0.0324|
|
| 57 |
+
| - global_mmlu_full_en_electrical_engineering | 0|none | 1|acc |↑ |0.6000|± |0.0408|
|
| 58 |
+
| - global_mmlu_full_en_elementary_mathematics | 0|none | 1|acc |↑ |0.3968|± |0.0252|
|
| 59 |
+
| - global_mmlu_full_en_high_school_biology | 0|none | 1|acc |↑ |0.7613|± |0.0243|
|
| 60 |
+
| - global_mmlu_full_en_high_school_chemistry | 0|none | 1|acc |↑ |0.4975|± |0.0352|
|
| 61 |
+
| - global_mmlu_full_en_high_school_computer_science | 0|none | 1|acc |↑ |0.6500|± |0.0479|
|
| 62 |
+
| - global_mmlu_full_en_high_school_mathematics | 0|none | 1|acc |↑ |0.2556|± |0.0266|
|
| 63 |
+
| - global_mmlu_full_en_high_school_physics | 0|none | 1|acc |↑ |0.3245|± |0.0382|
|
| 64 |
+
| - global_mmlu_full_en_high_school_statistics | 0|none | 1|acc |↑ |0.4213|± |0.0337|
|
| 65 |
+
| - global_mmlu_full_en_machine_learning | 0|none | 1|acc |↑ |0.4018|± |0.0465|
|
| 66 |
+
|
| 67 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 68 |
+
|--------------------------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 69 |
+
|global_mmlu_full_en | 0|none | |acc |↑ |0.6053|± |0.0039|
|
| 70 |
+
| - global_mmlu_full_en_humanities | 0|none | |acc |↑ |0.5515|± |0.0068|
|
| 71 |
+
| - global_mmlu_full_en_other | 0|none | |acc |↑ |0.6707|± |0.0081|
|
| 72 |
+
| - global_mmlu_full_en_social_sciences| 0|none | |acc |↑ |0.7251|± |0.0078|
|
| 73 |
+
| - global_mmlu_full_en_stem | 0|none | |acc |↑ |0.5043|± |0.0084|
|