Commit
•
a6a7cdf
1
Parent(s):
db55776
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,15 @@ This model is a fine-tuned version of [ajibawa-2023/Code-Llama-3-8B](https://hug
|
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.4550
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
More information needed
|
|
|
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.4550
|
| 21 |
|
| 22 |
+
Test set:
|
| 23 |
+
- BLEU: 38.48
|
| 24 |
+
- COMET: 79.28
|
| 25 |
+
- CodeBLEU: 64.11
|
| 26 |
+
- N-gram match score: 40.15
|
| 27 |
+
- Weighted n-gram match score: 77.11
|
| 28 |
+
- Syntax match score: 67.02
|
| 29 |
+
- Dataflow match score: 72.13
|
| 30 |
+
|
| 31 |
## Model description
|
| 32 |
|
| 33 |
More information needed
|