Update README.md

README.md

@@ -56,6 +56,7 @@ YModel2 is the most powerful Large Language Model (LLM) trained by SnifferCaptai
 |  Groups   |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
 |-----------|------:|------|------|--------|---|-----:|---|-----:|
 |ceval-valid|      2|none  |     0|acc     |↑  |0.2303|±  |0.0115|
+|      cmmlu|      1|none  |     5|acc     |↑  |0.2515|±  | 0.004|
 <details style="color:rgb(128,128,128)">
 <summary>ceval bench result</summary>
 
@@ -115,6 +116,81 @@ YModel2 is the most powerful Large Language Model (LLM) trained by SnifferCaptai
 |ceval-valid_urban_and_rural_planner                 |      2|none  |     0|acc     |↑  |0.2174|±  |0.0615|
 |ceval-valid_veterinary_medicine                     |      2|none  |     0|acc     |↑  |0.2174|±  |0.0879|
 
+</details>
+<details style="color:rgb(128,128,128)">
+<summary>cmmlu bench result</summary>
+
+|                    Tasks                     |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|----------------------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
+|cmmlu                                         |      1|none  |      |acc     |↑  |0.2515|±  |0.0040|
+| - cmmlu_agronomy                             |      1|none  |     5|acc     |↑  |0.2544|±  |0.0336|
+| - cmmlu_anatomy                              |      1|none  |     5|acc     |↑  |0.2432|±  |0.0354|
+| - cmmlu_ancient_chinese                      |      1|none  |     5|acc     |↑  |0.2317|±  |0.0330|
+| - cmmlu_arts                                 |      1|none  |     5|acc     |↑  |0.2562|±  |0.0346|
+| - cmmlu_astronomy                            |      1|none  |     5|acc     |↑  |0.2485|±  |0.0337|
+| - cmmlu_business_ethics                      |      1|none  |     5|acc     |↑  |0.2344|±  |0.0294|
+| - cmmlu_chinese_civil_service_exam           |      1|none  |     5|acc     |↑  |0.2562|±  |0.0346|
+| - cmmlu_chinese_driving_rule                 |      1|none  |     5|acc     |↑  |0.2519|±  |0.0381|
+| - cmmlu_chinese_food_culture                 |      1|none  |     5|acc     |↑  |0.2574|±  |0.0376|
+| - cmmlu_chinese_foreign_policy               |      1|none  |     5|acc     |↑  |0.2710|±  |0.0432|
+| - cmmlu_chinese_history                      |      1|none  |     5|acc     |↑  |0.2508|±  |0.0242|
+| - cmmlu_chinese_literature                   |      1|none  |     5|acc     |↑  |0.2549|±  |0.0306|
+| - cmmlu_chinese_teacher_qualification        |      1|none  |     5|acc     |↑  |0.2458|±  |0.0323|
+| - cmmlu_clinical_knowledge                   |      1|none  |     5|acc     |↑  |0.2532|±  |0.0283|
+| - cmmlu_college_actuarial_science            |      1|none  |     5|acc     |↑  |0.3019|±  |0.0448|
+| - cmmlu_college_education                    |      1|none  |     5|acc     |↑  |0.3178|±  |0.0452|
+| - cmmlu_college_engineering_hydrology        |      1|none  |     5|acc     |↑  |0.3019|±  |0.0448|
+| - cmmlu_college_law                          |      1|none  |     5|acc     |↑  |0.1667|±  |0.0360|
+| - cmmlu_college_mathematics                  |      1|none  |     5|acc     |↑  |0.2381|±  |0.0418|
+| - cmmlu_college_medical_statistics           |      1|none  |     5|acc     |↑  |0.2547|±  |0.0425|
+| - cmmlu_college_medicine                     |      1|none  |     5|acc     |↑  |0.2234|±  |0.0253|
+| - cmmlu_computer_science                     |      1|none  |     5|acc     |↑  |0.2500|±  |0.0304|
+| - cmmlu_computer_security                    |      1|none  |     5|acc     |↑  |0.2632|±  |0.0338|
+| - cmmlu_conceptual_physics                   |      1|none  |     5|acc     |↑  |0.2721|±  |0.0368|
+| - cmmlu_construction_project_management      |      1|none  |     5|acc     |↑  |0.2230|±  |0.0354|
+| - cmmlu_economics                            |      1|none  |     5|acc     |↑  |0.2264|±  |0.0333|
+| - cmmlu_education                            |      1|none  |     5|acc     |↑  |0.2454|±  |0.0338|
+| - cmmlu_electrical_engineering               |      1|none  |     5|acc     |↑  |0.2500|±  |0.0331|
+| - cmmlu_elementary_chinese                   |      1|none  |     5|acc     |↑  |0.2778|±  |0.0283|
+| - cmmlu_elementary_commonsense               |      1|none  |     5|acc     |↑  |0.2273|±  |0.0299|
+| - cmmlu_elementary_information_and_technology|      1|none  |     5|acc     |↑  |0.2731|±  |0.0289|
+| - cmmlu_elementary_mathematics               |      1|none  |     5|acc     |↑  |0.2304|±  |0.0278|
+| - cmmlu_ethnology                            |      1|none  |     5|acc     |↑  |0.2519|±  |0.0375|
+| - cmmlu_food_science                         |      1|none  |     5|acc     |↑  |0.2448|±  |0.0361|
+| - cmmlu_genetics                             |      1|none  |     5|acc     |↑  |0.2443|±  |0.0325|
+| - cmmlu_global_facts                         |      1|none  |     5|acc     |↑  |0.2617|±  |0.0361|
+| - cmmlu_high_school_biology                  |      1|none  |     5|acc     |↑  |0.2485|±  |0.0333|
+| - cmmlu_high_school_chemistry                |      1|none  |     5|acc     |↑  |0.2273|±  |0.0366|
+| - cmmlu_high_school_geography                |      1|none  |     5|acc     |↑  |0.2542|±  |0.0403|
+| - cmmlu_high_school_mathematics              |      1|none  |     5|acc     |↑  |0.2500|±  |0.0339|
+| - cmmlu_high_school_physics                  |      1|none  |     5|acc     |↑  |0.2545|±  |0.0417|
+| - cmmlu_high_school_politics                 |      1|none  |     5|acc     |↑  |0.2378|±  |0.0357|
+| - cmmlu_human_sexuality                      |      1|none  |     5|acc     |↑  |0.2619|±  |0.0393|
+| - cmmlu_international_law                    |      1|none  |     5|acc     |↑  |0.2432|±  |0.0316|
+| - cmmlu_journalism                           |      1|none  |     5|acc     |↑  |0.2442|±  |0.0329|
+| - cmmlu_jurisprudence                        |      1|none  |     5|acc     |↑  |0.2506|±  |0.0214|
+| - cmmlu_legal_and_moral_basis                |      1|none  |     5|acc     |↑  |0.2290|±  |0.0288|
+| - cmmlu_logical                              |      1|none  |     5|acc     |↑  |0.2602|±  |0.0397|
+| - cmmlu_machine_learning                     |      1|none  |     5|acc     |↑  |0.2623|±  |0.0400|
+| - cmmlu_management                           |      1|none  |     5|acc     |↑  |0.2667|±  |0.0306|
+| - cmmlu_marketing                            |      1|none  |     5|acc     |↑  |0.2722|±  |0.0333|
+| - cmmlu_marxist_theory                       |      1|none  |     5|acc     |↑  |0.2434|±  |0.0313|
+| - cmmlu_modern_chinese                       |      1|none  |     5|acc     |↑  |0.2500|±  |0.0404|
+| - cmmlu_nutrition                            |      1|none  |     5|acc     |↑  |0.2138|±  |0.0342|
+| - cmmlu_philosophy                           |      1|none  |     5|acc     |↑  |0.2476|±  |0.0423|
+| - cmmlu_professional_accounting              |      1|none  |     5|acc     |↑  |0.2571|±  |0.0331|
+| - cmmlu_professional_law                     |      1|none  |     5|acc     |↑  |0.2749|±  |0.0308|
+| - cmmlu_professional_medicine                |      1|none  |     5|acc     |↑  |0.2553|±  |0.0225|
+| - cmmlu_professional_psychology              |      1|none  |     5|acc     |↑  |0.2500|±  |0.0285|
+| - cmmlu_public_relations                     |      1|none  |     5|acc     |↑  |0.2529|±  |0.0330|
+| - cmmlu_security_study                       |      1|none  |     5|acc     |↑  |0.2370|±  |0.0367|
+| - cmmlu_sociology                            |      1|none  |     5|acc     |↑  |0.2699|±  |0.0296|
+| - cmmlu_sports_science                       |      1|none  |     5|acc     |↑  |0.2485|±  |0.0337|
+| - cmmlu_traditional_chinese_medicine         |      1|none  |     5|acc     |↑  |0.2595|±  |0.0323|
+| - cmmlu_virology                             |      1|none  |     5|acc     |↑  |0.2485|±  |0.0333|
+| - cmmlu_world_history                        |      1|none  |     5|acc     |↑  |0.2857|±  |0.0357|
+| - cmmlu_world_religions                      |      1|none  |     5|acc     |↑  |0.2625|±  |0.0349|
+
 </details>
 
 以下是模型的问答输出：