Added the results on the conll-endava mixed v2 dataset.

README.md

@@ -25,6 +25,11 @@ This model is a fine-tuned version of [BERT](https://huggingface.co/bert-base-ca
 - [NERPERDemo dataset](https://huggingface.co/datasets/BeardedJohn/NERPERDemo)
 - 12000 instances of the [wikiann, english version dataset](https://huggingface.co/datasets/wikiann/viewer/en/train).
 
+It achieves the following results on the conll-endava mixed, second version evaluation set:
+- Train Loss: 0.0190
+- Validation Loss: 0.0310
+- Epoch: 2
+- 
 It achieves the following results on the NERPERDemo evaluation set:
 - Train Loss: 0.0005
 - Validation Loss: 0.0002
@@ -67,6 +72,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+On conll-endava mixed, second version:
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.2091     | 0.0391          | 0     |
+| 0.0336     | 0.0322          | 1     |
+| 0.0190     | 0.0310          | 2     |
+
+
 On NERPERDemo:
 
 | Train Loss | Validation Loss | Epoch |