Update README.md

README.md

@@ -91,4 +91,72 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 <pre>
 The meaning of life is tamed in many ways. It is a state of mental and physical development. It is a state of deep emotional strength and confidence, and it is a state of physical and mental balance. In this article, we will explore the meaning of life, the different ways life is defined, and how we can apply this concept to our own lives.
-</pre>
+</pre>
+
+# MMLU Evaluation Results
+
+## **Overall Accuracy**
+**0.2549 (3579/14042)**
+
+## Breakdown by Subject:
+| Subject | Accuracy (Correct/Total) |
+|------------------------------|----------------------|
+| international_law            | 0.3636 (44/121)     |
+| anatomy                      | 0.3333 (45/135)     |
+| abstract_algebra             | 0.3200 (32/100)     |
+| global_facts                 | 0.3100 (31/100)     |
+| high_school_computer_science | 0.3100 (31/100)     |
+| college_biology              | 0.3056 (44/144)     |
+| philosophy                   | 0.3055 (95/311)     |
+| high_school_chemistry        | 0.3054 (62/203)     |
+| world_religions              | 0.3041 (52/171)     |
+| prehistory                   | 0.3025 (98/324)     |
+| high_school_european_history | 0.2970 (49/165)     |
+| elementary_mathematics       | 0.2963 (112/378)    |
+| logical_fallacies            | 0.2945 (48/163)     |
+| computer_security            | 0.2900 (29/100)     |
+| professional_psychology      | 0.2827 (173/612)    |
+| moral_disputes               | 0.2803 (97/346)     |
+| professional_accounting      | 0.2766 (78/282)     |
+| electrical_engineering       | 0.2759 (40/145)     |
+| college_computer_science     | 0.2700 (27/100)     |
+| college_mathematics          | 0.2700 (27/100)     |
+| professional_law             | 0.2692 (413/1534)   |
+| high_school_world_history    | 0.2658 (63/237)     |
+| high_school_mathematics      | 0.2630 (71/270)     |
+| high_school_geography        | 0.2626 (52/198)     |
+| high_school_biology          | 0.2613 (81/310)     |
+| astronomy                    | 0.2566 (39/152)     |
+| high_school_us_history       | 0.2549 (52/204)     |
+| econometrics                 | 0.2544 (29/114)     |
+| college_medicine             | 0.2543 (44/173)     |
+| us_foreign_policy            | 0.2500 (25/100)     |
+| moral_scenarios              | 0.2469 (221/895)    |
+| security_studies             | 0.2449 (60/245)     |
+| miscellaneous                | 0.2439 (191/783)    |
+| marketing                    | 0.2436 (57/234)     |
+| sociology                    | 0.2388 (48/201)     |
+| high_school_physics          | 0.2384 (36/151)     |
+| human_aging                  | 0.2377 (53/223)     |
+| nutrition                    | 0.2353 (72/306)     |
+| jurisprudence                | 0.2315 (25/108)     |
+| business_ethics              | 0.2300 (23/100)     |
+| high_school_government_and_politics | 0.2280 (44/193) |
+| college_physics              | 0.2255 (23/102)     |
+| clinical_knowledge           | 0.2226 (59/265)     |
+| high_school_statistics       | 0.2222 (48/216)     |
+| high_school_psychology       | 0.2220 (121/545)    |
+| conceptual_physics           | 0.2213 (52/235)     |
+| public_relations             | 0.2182 (24/110)     |
+| human_sexuality              | 0.2137 (28/131)     |
+| college_chemistry            | 0.2100 (21/100)     |
+| medical_genetics             | 0.2100 (21/100)     |
+| high_school_microeconomics   | 0.2059 (49/238)     |
+| machine_learning             | 0.2054 (23/112)     |
+| high_school_macroeconomics   | 0.2051 (80/390)     |
+| virology                     | 0.2048 (34/166)     |
+| management                   | 0.1845 (19/103)     |
+| professional_medicine        | 0.1654 (45/272)     |
+| formal_logic                 | 0.1508 (19/126)     |
+
+---