Commit
•
f2af767
1
Parent(s):
b58ecf8
Update README.md
Browse files
README.md
CHANGED
@@ -63,5 +63,30 @@ This model was fine-tuned using my TPU-Alignment repository. https://github.com/
|
|
63 |
|
64 |
## Evaluation
|
65 |
|
66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
|
|
63 |
|
64 |
## Evaluation
|
65 |
|
66 |
+
AGIEval
|
67 |
+
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
68 |
+
|---------------------------------|-------|------|-----:|--------|-----:|---|-----:|
|
69 |
+
|agieval_nous |N/A |none | 0|acc_norm|0.3559|± |0.0093|
|
70 |
+
| | |none | 0|acc |0.3759|± |0.0093|
|
71 |
+
| - agieval_aqua_rat | 1|none | 0|acc |0.2087|± |0.0255|
|
72 |
+
| | |none | 0|acc_norm|0.2126|± |0.0257|
|
73 |
+
| - agieval_logiqa_en | 1|none | 0|acc |0.3041|± |0.0180|
|
74 |
+
| | |none | 0|acc_norm|0.3456|± |0.0187|
|
75 |
+
| - agieval_lsat_ar | 1|none | 0|acc |0.2478|± |0.0285|
|
76 |
+
| | |none | 0|acc_norm|0.2348|± |0.0280|
|
77 |
+
| - agieval_lsat_lr | 1|none | 0|acc |0.3961|± |0.0217|
|
78 |
+
| | |none | 0|acc_norm|0.3627|± |0.0213|
|
79 |
+
| - agieval_lsat_rc | 1|none | 0|acc |0.5056|± |0.0305|
|
80 |
+
| | |none | 0|acc_norm|0.4387|± |0.0303|
|
81 |
+
| - agieval_sat_en | 1|none | 0|acc |0.7136|± |0.0316|
|
82 |
+
| | |none | 0|acc_norm|0.6456|± |0.0334|
|
83 |
+
| - agieval_sat_en_without_passage| 1|none | 0|acc |0.4417|± |0.0347|
|
84 |
+
| | |none | 0|acc_norm|0.3689|± |0.0337|
|
85 |
+
| - agieval_sat_math | 1|none | 0|acc |0.3318|± |0.0318|
|
86 |
+
| | |none | 0|acc_norm|0.2773|± |0.0302|
|
87 |
+
|
88 |
+
| Groups |Version|Filter|n-shot| Metric |Value | |Stderr|
|
89 |
+
|------------|-------|------|-----:|--------|-----:|---|-----:|
|
90 |
+
|agieval_nous|N/A |none | 0|acc_norm|0.3559|± |0.0093|
|
91 |
+
| | |none | 0|acc |0.3759|± |0.0093|
|
92 |
|