update evaluation

README.md

@@ -15,3 +15,18 @@ tags:
 
 [AdminBERT-16GB](example) is a French language model adapted on a large corpus of 50 millions French administrative texts. It is a derivative of CamemBERT model, which is based on the RoBERTa architecture. AdminBERT-16GB is trained using the Whole Word Masking (WWM) objective with 30% mask rate for 3 epochs on 24 A100 GPUs. The dataset used for training is [Adminset](https://huggingface.co/datasets/taln-ls2n/Adminset).
 
+
+## Evaluation
+
+### Model Performance
+
+| Model                  | P (%)   | R (%)   | F1 (%)  |
+|------------------------|---------|---------|---------|
+| Wikineural-NER FT      | 77.49   | 75.40   | 75.70   |
+| NERmemBERT-Large FT    | 77.43   | 78.38   | 77.13   |
+| CamemBERT FT           | 77.62   | 79.59   | 77.26   |
+| NERmemBERT-Base FT     | 77.99   | 79.59   | 78.34   |
+| AdminBERT-NER 4GB      | 78.47   | 80.35   | 79.26   |
+| AdminBERT-NER 16GB     | 78.79   | 82.07   | 80.11   |
+
+To evaluate each model, we performed five runs and averaged the results on the test set of Adminset-NER.