Commit
•
e06291d
1
Parent(s):
29462cb
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,15 @@ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://hugging
|
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.3938
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
More information needed
|
|
|
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.3938
|
| 21 |
|
| 22 |
+
Test evaluation:
|
| 23 |
+
- BLEU: 60.09
|
| 24 |
+
- COMET: 87.40
|
| 25 |
+
- CODEBLEU: 74.17
|
| 26 |
+
- N-gram match: 63.15
|
| 27 |
+
- Weighted n-gram match: 78.82
|
| 28 |
+
- Syntax match: 72.65
|
| 29 |
+
- Dataflow match: 82.08
|
| 30 |
+
|
| 31 |
## Model description
|
| 32 |
|
| 33 |
More information needed
|