fix(readme): metrics table
Browse files
README.md
CHANGED
|
@@ -18,7 +18,8 @@ Currently in pre-alpha, later releases will include more details regarding train
|
|
| 18 |
The model was tested using the following benchmarks:
|
| 19 |
- [ruIFEval](https://github.com/NLP-Core-Team/ruIFEval)
|
| 20 |
- [ifeval](https://github.com/google-research/google-research/tree/master/instruction_following_eval)
|
| 21 |
-
|
|
|
|
| 22 |
|---------------------------------|----|----|
|
| 23 |
|Avg. |*44.99*|*47.47*|
|
| 24 |
|ifeval-prompt-level |45.84|48.05|
|
|
|
|
| 18 |
The model was tested using the following benchmarks:
|
| 19 |
- [ruIFEval](https://github.com/NLP-Core-Team/ruIFEval)
|
| 20 |
- [ifeval](https://github.com/google-research/google-research/tree/master/instruction_following_eval)
|
| 21 |
+
|
| 22 |
+
| Eval name |Strict Value| Loose Value |
|
| 23 |
|---------------------------------|----|----|
|
| 24 |
|Avg. |*44.99*|*47.47*|
|
| 25 |
|ifeval-prompt-level |45.84|48.05|
|