update model card README.md

README.md

@@ -24,16 +24,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9476439790575916
+      value: 0.8426395939086294
     - name: Recall
       type: recall
-      value: 0.9679144385026738
+      value: 0.8877005347593583
     - name: F1
       type: f1
-      value: 0.9576719576719576
+      value: 0.8645833333333333
     - name: Accuracy
       type: accuracy
-      value: 0.9905873493975904
+      value: 0.9807981927710844
 ---
 
 <!-- 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 [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0693
-- Precision: 0.9476
-- Recall: 0.9679
-- F1: 0.9577
-- Accuracy: 0.9906
+- Loss: 0.1563
+- Precision: 0.8426
+- Recall: 0.8877
+- F1: 0.8646
+- Accuracy: 0.9808
 
 ## 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        | 27.78 | 250  | 0.0689          | 0.9175    | 0.9519 | 0.9344 | 0.9898   |
-| 0.0141        | 55.56 | 500  | 0.0693          | 0.9476    | 0.9679 | 0.9577 | 0.9906   |
+| No log        | 27.78 | 250  | 0.2591          | 0.7179    | 0.7487 | 0.7330 | 0.9529   |
+| 0.4762        | 55.56 | 500  | 0.1563          | 0.8426    | 0.8877 | 0.8646 | 0.9808   |
 
 
 ### Framework versions