update model card README.md

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9255213505461768
+      value: 0.9233990962195525
     - name: Recall
       type: recall
-      value: 0.9383599955252265
+      value: 0.9372413021590782
     - name: F1
       type: f1
-      value: 0.931896455949339
+      value: 0.9302687097490562
     - name: Accuracy
       type: accuracy
-      value: 0.9840977330134876
+      value: 0.9833193003637981
 ---
 
 <!-- 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: 0.0582
-- Precision: 0.9255
-- Recall: 0.9384
-- F1: 0.9319
-- Accuracy: 0.9841
+- Loss: 0.0619
+- Precision: 0.9234
+- Recall: 0.9372
+- F1: 0.9303
+- Accuracy: 0.9833
 
 ## Model description
 
@@ -76,14 +76,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2429        | 1.0   | 878  | 0.0697          | 0.9094    | 0.9182 | 0.9138 | 0.9805   |
-| 0.0555        | 2.0   | 1756 | 0.0581          | 0.9206    | 0.9351 | 0.9278 | 0.9833   |
-| 0.0296        | 3.0   | 2634 | 0.0582          | 0.9255    | 0.9384 | 0.9319 | 0.9841   |
+| 0.2421        | 1.0   | 878  | 0.0750          | 0.9086    | 0.9178 | 0.9132 | 0.9797   |
+| 0.056         | 2.0   | 1756 | 0.0601          | 0.9213    | 0.9363 | 0.9288 | 0.9828   |
+| 0.0319        | 3.0   | 2634 | 0.0619          | 0.9234    | 0.9372 | 0.9303 | 0.9833   |
 
 
 ### Framework versions
 
-- Transformers 4.18.0
-- Pytorch 1.10.0+cu111
+- Transformers 4.17.0
+- Pytorch 1.9.0
 - Datasets 2.0.0
 - Tokenizers 0.11.6