End of training

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9586840091813313
+      value: 0.9609494640122511
     - name: Recall
       type: recall
-      value: 0.9728260869565217
+      value: 0.9743788819875776
     - name: F1
       type: f1
-      value: 0.9657032755298651
+      value: 0.9676175790285273
     - name: Accuracy
       type: accuracy
-      value: 0.9647707979626485
+      value: 0.9690152801358234
 ---
 
 <!-- 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: 0.2135
-- Precision: 0.9587
-- Recall: 0.9728
-- F1: 0.9657
-- Accuracy: 0.9648
+- Loss: 0.1800
+- Precision: 0.9609
+- Recall: 0.9744
+- F1: 0.9676
+- Accuracy: 0.9690
 
 ## Model description
 
@@ -64,9 +64,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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
@@ -76,16 +76,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 2.0   | 100  | 0.8783          | 0.7618    | 0.8292 | 0.7941 | 0.8145   |
-| No log        | 4.0   | 200  | 0.4090          | 0.8819    | 0.9278 | 0.9043 | 0.9177   |
-| No log        | 6.0   | 300  | 0.2944          | 0.9269    | 0.9550 | 0.9407 | 0.9389   |
-| No log        | 8.0   | 400  | 0.2637          | 0.9434    | 0.9581 | 0.9507 | 0.9495   |
-| 0.6127        | 10.0  | 500  | 0.2296          | 0.9481    | 0.9651 | 0.9565 | 0.9576   |
-| 0.6127        | 12.0  | 600  | 0.2290          | 0.9519    | 0.9682 | 0.9600 | 0.9588   |
-| 0.6127        | 14.0  | 700  | 0.2115          | 0.9542    | 0.9713 | 0.9627 | 0.9648   |
-| 0.6127        | 16.0  | 800  | 0.2238          | 0.9534    | 0.9682 | 0.9607 | 0.9610   |
-| 0.6127        | 18.0  | 900  | 0.2139          | 0.9527    | 0.9689 | 0.9607 | 0.9622   |
-| 0.0647        | 20.0  | 1000 | 0.2135          | 0.9587    | 0.9728 | 0.9657 | 0.9648   |
+| No log        | 1.25  | 100  | 0.5802          | 0.8140    | 0.8696 | 0.8408 | 0.8574   |
+| No log        | 2.5   | 200  | 0.2946          | 0.9013    | 0.9433 | 0.9219 | 0.9329   |
+| No log        | 3.75  | 300  | 0.2259          | 0.9409    | 0.9635 | 0.9521 | 0.9571   |
+| No log        | 5.0   | 400  | 0.2496          | 0.9376    | 0.9565 | 0.9470 | 0.9482   |
+| 0.4497        | 6.25  | 500  | 0.2174          | 0.9399    | 0.9596 | 0.9497 | 0.9546   |
+| 0.4497        | 7.5   | 600  | 0.1812          | 0.9535    | 0.9713 | 0.9623 | 0.9648   |
+| 0.4497        | 8.75  | 700  | 0.1699          | 0.9587    | 0.9720 | 0.9653 | 0.9699   |
+| 0.4497        | 10.0  | 800  | 0.1810          | 0.9625    | 0.9752 | 0.9688 | 0.9690   |
+| 0.4497        | 11.25 | 900  | 0.1789          | 0.9647    | 0.9767 | 0.9707 | 0.9694   |
+| 0.0416        | 12.5  | 1000 | 0.1800          | 0.9609    | 0.9744 | 0.9676 | 0.9690   |
 
 
 ### Framework versions

runs/Aug26_22-37-50_bernini/events.out.tfevents.1724705285.bernini.6608.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896275424f84c40802c4e51d73e231b0a777b6de172f579e6cf141646b143e38
+size 560