---
language:
- fr
tags:
- nli
metrics:
- f1
---

## Eval results
We obtain the following results on ```validation``` and ```test``` sets:

| Set        | F1<sub>micro</sub> | F1<sub>macro</sub> |
|------------|--------------------|--------------------|
| validation | 83.1               | 82.2               |
| test       | 86.0               | 85.0               |