update model card README.md

README.md

@@ -1,9 +1,8 @@
 ---
-license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
-- xglue
+- wikiann
 metrics:
 - precision
 - recall
@@ -16,48 +15,38 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: xglue
-      type: xglue
-      config: ner
-      split: validation.en
-      args: ner
+      name: wikiann
+      type: wikiann
+      config: es
+      split: validation
+      args: es
     metrics:
     - name: Precision
       type: precision
-      value: 0.9374277695228661
+      value: 0.8694376140239549
     - name: Recall
       type: recall
-      value: 0.9555705149781218
+      value: 0.8933170334148329
     - name: F1
       type: f1
-      value: 0.9464122010167514
+      value: 0.8812155806568316
     - name: Accuracy
       type: accuracy
-      value: 0.9875198681344558
+      value: 0.9448179020644737
 ---
 
-train-eval-index:
-- config: ner
-  task: token-classification
-  task_id: entity_extraction
-  splits:
-    eval_split: test.es
-  col_mapping:
-    words: tokens
-    ner: tags
-
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner-es-en
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the xglue dataset.
+This model was trained from scratch on the wikiann dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0753
-- Precision: 0.9374
-- Recall: 0.9556
-- F1: 0.9464
-- Accuracy: 0.9875
+- Loss: 0.2564
+- Precision: 0.8694
+- Recall: 0.8933
+- F1: 0.8812
+- Accuracy: 0.9448
 
 ## Model description
 
@@ -88,9 +77,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0184        | 1.0   | 1756 | 0.0718          | 0.9314    | 0.9440 | 0.9376 | 0.9850   |
-| 0.0115        | 2.0   | 3512 | 0.0712          | 0.9374    | 0.9544 | 0.9458 | 0.9872   |
-| 0.0048        | 3.0   | 5268 | 0.0753          | 0.9374    | 0.9556 | 0.9464 | 0.9875   |
+| 0.2459        | 1.0   | 2500 | 0.2378          | 0.8169    | 0.8606 | 0.8382 | 0.9304   |
+| 0.1441        | 2.0   | 5000 | 0.2468          | 0.8618    | 0.8876 | 0.8745 | 0.9429   |
+| 0.0972        | 3.0   | 7500 | 0.2564          | 0.8694    | 0.8933 | 0.8812 | 0.9448   |
 
 
 ### Framework versions