Update README.md
Browse files
README.md
CHANGED
|
@@ -32,3 +32,46 @@ Samples 5000, Accuracy 27%
|
|
| 32 |
[SCIENCEQA](https://tinyllava-factory.readthedocs.io/en/latest/Evaluation.html#scienceqa)
|
| 33 |
|
| 34 |
Samples 4241, Correct: 1725, Accuracy: 40.64%, IMG-Accuracy: 36.54%
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
[SCIENCEQA](https://tinyllava-factory.readthedocs.io/en/latest/Evaluation.html#scienceqa)
|
| 33 |
|
| 34 |
Samples 4241, Correct: 1725, Accuracy: 40.64%, IMG-Accuracy: 36.54%
|
| 35 |
+
|
| 36 |
+
[MMMU](https://tinyllava-factory.readthedocs.io/en/latest/Evaluation.html#mmmu)
|
| 37 |
+
|
| 38 |
+
| Category | # Samples | Accuracy |
|
| 39 |
+
|---------------------------------|-----------|----------|
|
| 40 |
+
| Overall | 900 | 0.273 |
|
| 41 |
+
| Overall-Art and Design | 120 | 0.233 |
|
| 42 |
+
| Art | 30 | 0.233 |
|
| 43 |
+
| Art Theory | 30 | 0.167 |
|
| 44 |
+
| Design | 30 | 0.367 |
|
| 45 |
+
| Music | 30 | 0.167 |
|
| 46 |
+
| Overall-Business | 150 | 0.293 |
|
| 47 |
+
| Accounting | 30 | 0.367 |
|
| 48 |
+
| Economics | 30 | 0.467 |
|
| 49 |
+
| Finance | 30 | 0.200 |
|
| 50 |
+
| Management | 30 | 0.233 |
|
| 51 |
+
| Marketing | 30 | 0.200 |
|
| 52 |
+
| Overall-Science | 150 | 0.273 |
|
| 53 |
+
| Biology | 30 | 0.267 |
|
| 54 |
+
| Chemistry | 30 | 0.100 |
|
| 55 |
+
| Geography | 30 | 0.200 |
|
| 56 |
+
| Math | 30 | 0.433 |
|
| 57 |
+
| Physics | 30 | 0.367 |
|
| 58 |
+
| Overall-Health and Medicine | 150 | 0.293 |
|
| 59 |
+
| Basic Medical Science | 30 | 0.333 |
|
| 60 |
+
| Clinical Medicine | 30 | 0.200 |
|
| 61 |
+
| Diagnostics and Laboratory Med. | 30 | 0.233 |
|
| 62 |
+
| Pharmacy | 30 | 0.333 |
|
| 63 |
+
| Public Health | 30 | 0.367 |
|
| 64 |
+
| Overall-Humanities and Soc. Sci.| 120 | 0.267 |
|
| 65 |
+
| History | 30 | 0.333 |
|
| 66 |
+
| Literature | 30 | 0.300 |
|
| 67 |
+
| Sociology | 30 | 0.133 |
|
| 68 |
+
| Psychology | 30 | 0.300 |
|
| 69 |
+
| Overall-Tech and Engineering | 210 | 0.271 |
|
| 70 |
+
| Agriculture | 30 | 0.200 |
|
| 71 |
+
| Architecture and Engineering | 30 | 0.267 |
|
| 72 |
+
| Computer Science | 30 | 0.333 |
|
| 73 |
+
| Electronics | 30 | 0.267 |
|
| 74 |
+
| Energy and Power | 30 | 0.333 |
|
| 75 |
+
| Materials | 30 | 0.267 |
|
| 76 |
+
| Mechanical Engineering | 30 | 0.233 |
|
| 77 |
+
|