Update README.md
Browse files
README.md
CHANGED
|
@@ -55,4 +55,10 @@ dpo_trainer = DPOTrainer(
|
|
| 55 |
max_prompt_length = 512,
|
| 56 |
)
|
| 57 |
```
|
| 58 |
-
The code and parameters are borrowed from https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
max_prompt_length = 512,
|
| 56 |
)
|
| 57 |
```
|
| 58 |
+
The code and parameters are borrowed from https://colab.research.google.com/drive/1SKrKGV-BZoU4kv5q3g0jtE_OhRgPtrrQ?usp=sharing
|
| 59 |
+
|
| 60 |
+
Benchmark scores
|
| 61 |
+
|
| 62 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 63 |
+
|----------|------:|------|-----:|------|-----:|---|-----:|
|
| 64 |
+
|winogrande| 1|none | 5|acc |0.8248|± |0.0107|
|