End of training

README.md

@@ -21,16 +21,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9220389805097451
+      value: 0.9640397857689365
     - name: Recall
       type: recall
-      value: 0.9549689440993789
+      value: 0.9782608695652174
     - name: F1
       type: f1
-      value: 0.9382151029748284
+      value: 0.9710982658959537
     - name: Accuracy
       type: accuracy
-      value: 0.934634974533107
+      value: 0.9741086587436333
 ---
 
 <!-- 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: 0.3103
-- Precision: 0.9220
-- Recall: 0.9550
-- F1: 0.9382
-- Accuracy: 0.9346
+- Loss: 0.1874
+- Precision: 0.9640
+- Recall: 0.9783
+- F1: 0.9711
+- Accuracy: 0.9741
 
 ## Model description
 
@@ -63,22 +63,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 12
-- eval_batch_size: 12
+- learning_rate: 5e-05
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 1000
+- training_steps: 2500
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 3.7313  | 250  | 0.7079          | 0.8180    | 0.8657 | 0.8412 | 0.8476   |
-| 1.064         | 7.4627  | 500  | 0.4029          | 0.8791    | 0.9255 | 0.9017 | 0.9138   |
-| 1.064         | 11.1940 | 750  | 0.3349          | 0.9132    | 0.9480 | 0.9303 | 0.9308   |
-| 0.294         | 14.9254 | 1000 | 0.3103          | 0.9220    | 0.9550 | 0.9382 | 0.9346   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.4341        | 6.25  | 500  | 0.1703          | 0.9601    | 0.9720 | 0.9660 | 0.9656   |
+| 0.0487        | 12.5  | 1000 | 0.1762          | 0.9662    | 0.9759 | 0.9710 | 0.9703   |
+| 0.0185        | 18.75 | 1500 | 0.1913          | 0.9609    | 0.9720 | 0.9664 | 0.9682   |
+| 0.0091        | 25.0  | 2000 | 0.1846          | 0.9693    | 0.9821 | 0.9757 | 0.9758   |
+| 0.0038        | 31.25 | 2500 | 0.1874          | 0.9640    | 0.9783 | 0.9711 | 0.9741   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276afb696d439b85c284a38d6dea77705656db8b2ccfbacc8c174831645cd858
+oid sha256:c2009df7c91c7d5ccff824be1409cf32f31b7e8ad40d504cf303896a07ab226e
 size 503816564