update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.40298507462686567
+      value: 0.4262295081967213
     - name: Recall
       type: recall
-      value: 0.20018535681186284
+      value: 0.1927710843373494
     - name: F1
       type: f1
-      value: 0.2674922600619195
+      value: 0.26547543075941293
     - name: Accuracy
       type: accuracy
-      value: 0.9358727715788123
+      value: 0.9353597537514429
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ 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 wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2994
-- Precision: 0.4030
-- Recall: 0.2002
-- F1: 0.2675
-- Accuracy: 0.9359
+- Loss: 0.2958
+- Precision: 0.4262
+- Recall: 0.1928
+- F1: 0.2655
+- Accuracy: 0.9354
 
 ## Model description
 
@@ -78,8 +78,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 107  | 0.3173          | 0.3081    | 0.1057 | 0.1573 | 0.9315   |
-| No log        | 2.0   | 214  | 0.2994          | 0.4030    | 0.2002 | 0.2675 | 0.9359   |
+| No log        | 1.0   | 107  | 0.3133          | 0.3077    | 0.0556 | 0.0942 | 0.9298   |
+| No log        | 2.0   | 214  | 0.2958          | 0.4262    | 0.1928 | 0.2655 | 0.9354   |
 
 
 ### Framework versions