Add evaluation results on the conll2003 config and test split of conll2003

README.md

@@ -35,6 +35,35 @@ model-index:
       type: loss
       value: 0.06707527488470078
       verified: true
+  - task:
+      type: token-classification
+      name: Token Classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: test
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9753642704233133
+      verified: true
+    - name: Precision
+      type: precision
+      value: 0.980519710720363
+      verified: true
+    - name: Recall
+      type: recall
+      value: 0.9807630935073224
+      verified: true
+    - name: F1
+      type: f1
+      value: 0.9806413870127106
+      verified: true
+    - name: loss
+      type: loss
+      value: 0.12067878246307373
+      verified: true
 ---
 
 [DistilBERT base uncased](https://huggingface.co/distilbert-base-uncased), fine-tuned for NER using the [conll03 english dataset](https://huggingface.co/datasets/conll2003). Note that this model is **not** sensitive to capital letters — "english" is the same as "English". For the case sensitive version, please use [elastic/distilbert-base-cased-finetuned-conll03-english](https://huggingface.co/elastic/distilbert-base-cased-finetuned-conll03-english).