update model card README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: cc-by-nc-sa-4.0
 tags:
 - generated_from_trainer
 datasets:
@@ -24,16 +23,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9871382636655949
+      value: 0.9967585089141004
     - name: Recall
       type: recall
-      value: 0.9935275080906149
+      value: 0.9951456310679612
     - name: F1
       type: f1
-      value: 0.9903225806451612
+      value: 0.9959514170040485
     - name: Accuracy
       type: accuracy
-      value: 0.9992192379762649
+      value: 0.999531542785759
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,13 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # layoutlmv3-finetuned-registros_100
 
-This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the data_registros_layoutv3 dataset.
+This model was trained from scratch on the data_registros_layoutv3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0110
-- Precision: 0.9871
-- Recall: 0.9935
-- F1: 0.9903
-- Accuracy: 0.9992
+- Loss: 0.0050
+- Precision: 0.9968
+- Recall: 0.9951
+- F1: 0.9960
+- Accuracy: 0.9995
 
 ## Model description
 
@@ -72,24 +71,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 3000
+- training_steps: 600
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 10.87  | 250  | 0.4325          | 0.2663    | 0.2638 | 0.2650 | 0.8982   |
-| 0.6304        | 21.74  | 500  | 0.2065          | 0.7715    | 0.8139 | 0.7921 | 0.9622   |
-| 0.6304        | 32.61  | 750  | 0.1058          | 0.9048    | 0.9385 | 0.9214 | 0.9866   |
-| 0.1413        | 43.48  | 1000 | 0.0600          | 0.9314    | 0.9660 | 0.9484 | 0.9944   |
-| 0.1413        | 54.35  | 1250 | 0.0377          | 0.9451    | 0.9741 | 0.9594 | 0.9969   |
-| 0.0558        | 65.22  | 1500 | 0.0277          | 0.9697    | 0.9838 | 0.9767 | 0.9981   |
-| 0.0558        | 76.09  | 1750 | 0.0199          | 0.9792    | 0.9903 | 0.9847 | 0.9988   |
-| 0.0307        | 86.96  | 2000 | 0.0160          | 0.9824    | 0.9919 | 0.9871 | 0.9989   |
-| 0.0307        | 97.83  | 2250 | 0.0147          | 0.9823    | 0.9903 | 0.9863 | 0.9988   |
-| 0.0211        | 108.7  | 2500 | 0.0122          | 0.9871    | 0.9935 | 0.9903 | 0.9992   |
-| 0.0211        | 119.57 | 2750 | 0.0113          | 0.9871    | 0.9935 | 0.9903 | 0.9992   |
-| 0.0174        | 130.43 | 3000 | 0.0110          | 0.9871    | 0.9935 | 0.9903 | 0.9992   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 4.35  | 100  | 0.0106          | 0.9871    | 0.9935 | 0.9903 | 0.9991   |
+| No log        | 8.7   | 200  | 0.0073          | 0.9984    | 0.9968 | 0.9976 | 0.9997   |
+| No log        | 13.04 | 300  | 0.0061          | 0.9968    | 0.9968 | 0.9968 | 0.9997   |
+| No log        | 17.39 | 400  | 0.0048          | 0.9968    | 0.9984 | 0.9976 | 0.9997   |
+| 0.0109        | 21.74 | 500  | 0.0053          | 0.9968    | 0.9968 | 0.9968 | 0.9997   |
+| 0.0109        | 26.09 | 600  | 0.0050          | 0.9968    | 0.9951 | 0.9960 | 0.9995   |
 
 
 ### Framework versions