update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9278601460500111
+      value: 0.9272043367629162
     - name: Recall
       type: recall
-      value: 0.9381362568519969
+      value: 0.9375769101689228
     - name: F1
       type: f1
-      value: 0.9329699059909885
+      value: 0.932361775503393
     - name: Accuracy
       type: accuracy
-      value: 0.9841295057746994
+      value: 0.984193051297123
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0602
-- Precision: 0.9279
-- Recall: 0.9381
-- F1: 0.9330
-- Accuracy: 0.9841
+- Loss: 0.0612
+- Precision: 0.9272
+- Recall: 0.9376
+- F1: 0.9324
+- Accuracy: 0.9842
 
 ## Model description
 
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2379        | 1.0   | 878  | 0.0679          | 0.9193    | 0.9242 | 0.9217 | 0.9818   |
-| 0.0508        | 2.0   | 1756 | 0.0609          | 0.9220    | 0.9355 | 0.9287 | 0.9835   |
-| 0.0306        | 3.0   | 2634 | 0.0602          | 0.9279    | 0.9381 | 0.9330 | 0.9841   |
+| 0.2495        | 1.0   | 878  | 0.0701          | 0.9191    | 0.9229 | 0.9210 | 0.9815   |
+| 0.0526        | 2.0   | 1756 | 0.0613          | 0.9216    | 0.9350 | 0.9283 | 0.9832   |
+| 0.0312        | 3.0   | 2634 | 0.0612          | 0.9272    | 0.9376 | 0.9324 | 0.9842   |
 
 
 ### Framework versions