update model card README.md

README.md

@@ -1,9 +1,8 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
-- conll2003
+- wikiann
 metrics:
 - precision
 - recall
@@ -16,24 +15,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: conll2003
-      type: conll2003
-      config: conll2003
+      name: wikiann
+      type: wikiann
+      config: es
       split: train
-      args: conll2003
+      args: es
     metrics:
     - name: Precision
       type: precision
-      value: 0.9338296112489661
+      value: 0.8655875585178132
     - name: Recall
       type: recall
-      value: 0.9500168293503871
+      value: 0.889079054604727
     - name: F1
       type: f1
-      value: 0.9418536748143823
+      value: 0.8771760543561292
     - name: Accuracy
       type: accuracy
-      value: 0.9861364572908695
+      value: 0.9432045651459472
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,13 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
+This model was trained from scratch on the wikiann dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0587
-- Precision: 0.9338
-- Recall: 0.9500
-- F1: 0.9419
-- Accuracy: 0.9861
+- Loss: 0.2685
+- Precision: 0.8656
+- Recall: 0.8891
+- F1: 0.8772
+- Accuracy: 0.9432
 
 ## Model description
 
@@ -78,9 +77,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0889        | 1.0   | 1756 | 0.0711          | 0.9132    | 0.9297 | 0.9214 | 0.9809   |
-| 0.0338        | 2.0   | 3512 | 0.0597          | 0.9315    | 0.9475 | 0.9394 | 0.9860   |
-| 0.0184        | 3.0   | 5268 | 0.0587          | 0.9338    | 0.9500 | 0.9419 | 0.9861   |
+| 0.245         | 1.0   | 2500 | 0.2470          | 0.8224    | 0.8577 | 0.8397 | 0.9303   |
+| 0.1472        | 2.0   | 5000 | 0.2469          | 0.8651    | 0.8876 | 0.8762 | 0.9415   |
+| 0.0965        | 3.0   | 7500 | 0.2685          | 0.8656    | 0.8891 | 0.8772 | 0.9432   |
 
 
 ### Framework versions