End of training

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.963984674329502
+      value: 0.96771714066103
     - name: Recall
       type: recall
-      value: 0.9767080745341615
+      value: 0.9774844720496895
     - name: F1
       type: f1
-      value: 0.9703046664095644
+      value: 0.9725762842796446
     - name: Accuracy
       type: accuracy
-      value: 0.9702886247877759
+      value: 0.9711375212224108
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ 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: 0.2044
-- Precision: 0.9640
-- Recall: 0.9767
-- F1: 0.9703
-- Accuracy: 0.9703
+- Loss: 0.1836
+- Precision: 0.9677
+- Recall: 0.9775
+- F1: 0.9726
+- Accuracy: 0.9711
 
 ## Model description
 
@@ -64,9 +64,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 14
-- eval_batch_size: 14
+- learning_rate: 6e-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
@@ -74,18 +74,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.7241  | 100  | 0.4595          | 0.8310    | 0.8859 | 0.8576 | 0.8786   |
-| No log        | 3.4483  | 200  | 0.2637          | 0.9284    | 0.9565 | 0.9423 | 0.9469   |
-| No log        | 5.1724  | 300  | 0.2096          | 0.9513    | 0.9697 | 0.9604 | 0.9626   |
-| No log        | 6.8966  | 400  | 0.2016          | 0.9512    | 0.9689 | 0.96   | 0.9622   |
-| 0.3892        | 8.6207  | 500  | 0.2418          | 0.9453    | 0.9658 | 0.9555 | 0.9593   |
-| 0.3892        | 10.3448 | 600  | 0.2149          | 0.9579    | 0.9713 | 0.9645 | 0.9660   |
-| 0.3892        | 12.0690 | 700  | 0.2090          | 0.9608    | 0.9713 | 0.9660 | 0.9652   |
-| 0.3892        | 13.7931 | 800  | 0.2202          | 0.9580    | 0.9728 | 0.9653 | 0.9673   |
-| 0.3892        | 15.5172 | 900  | 0.2217          | 0.9595    | 0.9744 | 0.9669 | 0.9682   |
-| 0.0278        | 17.2414 | 1000 | 0.2044          | 0.9640    | 0.9767 | 0.9703 | 0.9703   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.25  | 100  | 0.5222          | 0.8284    | 0.8773 | 0.8522 | 0.8680   |
+| No log        | 2.5   | 200  | 0.2594          | 0.9147    | 0.9488 | 0.9314 | 0.9393   |
+| No log        | 3.75  | 300  | 0.2472          | 0.9294    | 0.9511 | 0.9401 | 0.9448   |
+| No log        | 5.0   | 400  | 0.1958          | 0.9496    | 0.9651 | 0.9573 | 0.9580   |
+| 0.4078        | 6.25  | 500  | 0.2005          | 0.9547    | 0.9658 | 0.9602 | 0.9597   |
+| 0.4078        | 7.5   | 600  | 0.2083          | 0.9555    | 0.9674 | 0.9614 | 0.9631   |
+| 0.4078        | 8.75  | 700  | 0.2104          | 0.9608    | 0.9697 | 0.9652 | 0.9631   |
+| 0.4078        | 10.0  | 800  | 0.1793          | 0.9685    | 0.9775 | 0.9730 | 0.9724   |
+| 0.4078        | 11.25 | 900  | 0.1972          | 0.9646    | 0.9744 | 0.9695 | 0.9686   |
+| 0.0332        | 12.5  | 1000 | 0.1836          | 0.9677    | 0.9775 | 0.9726 | 0.9711   |
 
 
 ### Framework versions

runs/Aug26_23-18-01_bernini/events.out.tfevents.1724707740.bernini.31199.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113b7580ecb802bd76012700b08a9ba3ad2d7ed5d041a1dee7c2acd2d76462aa
+size 560