princeton-nlp
commited on
Commit
•
16c27b0
1
Parent(s):
c580d90
Update README.md
Browse files
README.md
CHANGED
@@ -61,32 +61,11 @@ Fine-tuning the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-
|
|
61 |
|
62 |
## Evaluation
|
63 |
|
64 |
-
### Testing Data, Factors & Metrics
|
65 |
-
|
66 |
-
#### Testing Data
|
67 |
-
|
68 |
-
<!-- This should link to a Dataset Card if possible. -->
|
69 |
-
|
70 |
-
[More Information Needed]
|
71 |
-
|
72 |
-
#### Factors
|
73 |
-
|
74 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
75 |
-
|
76 |
-
[More Information Needed]
|
77 |
-
|
78 |
-
#### Metrics
|
79 |
-
|
80 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
81 |
-
|
82 |
-
[More Information Needed]
|
83 |
-
|
84 |
-
### Results
|
85 |
-
|
86 |
-
[More Information Needed]
|
87 |
-
|
88 |
-
#### Summary
|
89 |
|
|
|
|
|
|
|
|
|
90 |
|
91 |
|
92 |
## Technical Specifications
|
|
|
61 |
|
62 |
## Evaluation
|
63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
+
| Model | AlpacaEval 2 LC Win Rate | AlpacaEval 2 Raw Win Rate | Arena-Hard Win Rate | WildBench Elo |
|
66 |
+
| :-------- | :------- | :------- | :------- | :------- |
|
67 |
+
| gemma-2-9b-it | 51.1 | 38.1 | 40.8 | 1049.5 |
|
68 |
+
| gemma-2-9b-it-SimPO | | | | |
|
69 |
|
70 |
|
71 |
## Technical Specifications
|