update model card README.md

README.md

@@ -19,10 +19,10 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6507
-- Precision: 0.8810
-- Recall: 0.8409
-- F1: 0.8605
+- Loss: 0.5736
+- Precision: 0.8837
+- Recall: 0.8636
+- F1: 0.8736
 - Accuracy: 0.9206
 
 ## Model description
@@ -54,13 +54,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 3.33  | 50   | 0.9554          | 0.6744    | 0.6591 | 0.6667 | 0.7778   |
-| No log        | 6.67  | 100  | 0.6507          | 0.8810    | 0.8409 | 0.8605 | 0.9206   |
+| No log        | 3.33  | 50   | 0.9050          | 0.8140    | 0.7955 | 0.8046 | 0.8730   |
+| No log        | 6.67  | 100  | 0.5736          | 0.8837    | 0.8636 | 0.8736 | 0.9206   |
 
 
 ### Framework versions
 
-- Transformers 4.28.0
+- Transformers 4.29.2
 - Pytorch 2.0.1+cu118
 - Datasets 2.12.0
 - Tokenizers 0.13.3