End of training

README.md

@@ -21,16 +21,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.7572254335260116
+      value: 0.9461305007587253
     - name: Recall
       type: recall
-      value: 0.8136645962732919
+      value: 0.968167701863354
     - name: F1
       type: f1
-      value: 0.784431137724551
+      value: 0.9570222563315426
     - name: Accuracy
       type: accuracy
-      value: 0.7975382003395586
+      value: 0.9592529711375212
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [layoutlmv3](https://huggingface.co/layoutlmv3) on the mp-02/cord dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0695
-- Precision: 0.7572
-- Recall: 0.8137
-- F1: 0.7844
-- Accuracy: 0.7975
+- Loss: 0.2268
+- Precision: 0.9461
+- Recall: 0.9682
+- F1: 0.9570
+- Accuracy: 0.9593
 
 ## Model description
 
@@ -63,7 +63,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
+- learning_rate: 5e-06
 - train_batch_size: 10
 - eval_batch_size: 10
 - seed: 42
@@ -75,11 +75,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 2.7217        | 6.25  | 500  | 1.8788          | 0.5168    | 0.6095 | 0.5593 | 0.5883   |
-| 1.7562        | 12.5  | 1000 | 1.4443          | 0.5337    | 0.6576 | 0.5892 | 0.6795   |
-| 1.4387        | 18.75 | 1500 | 1.2162          | 0.6981    | 0.7811 | 0.7373 | 0.7746   |
-| 1.2728        | 25.0  | 2000 | 1.1030          | 0.7473    | 0.8106 | 0.7777 | 0.7941   |
-| 1.1902        | 31.25 | 2500 | 1.0695          | 0.7572    | 0.8137 | 0.7844 | 0.7975   |
+| 1.5249        | 6.25  | 500  | 0.6825          | 0.8146    | 0.8595 | 0.8364 | 0.8434   |
+| 0.5103        | 12.5  | 1000 | 0.3562          | 0.9058    | 0.9410 | 0.9231 | 0.9312   |
+| 0.2872        | 18.75 | 1500 | 0.2750          | 0.9337    | 0.9620 | 0.9476 | 0.9508   |
+| 0.2008        | 25.0  | 2000 | 0.2383          | 0.9483    | 0.9689 | 0.9585 | 0.9576   |
+| 0.1611        | 31.25 | 2500 | 0.2268          | 0.9461    | 0.9682 | 0.9570 | 0.9593   |
 
 
 ### Framework versions