update model card README.md

README.md

@@ -1,6 +1,5 @@
 ---
 license: cc-by-nc-sa-4.0
-base_model: microsoft/layoutlmv3-base
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # layoutlmv3-finetuned-funsd2
 
-This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6633
-- Precision: 0.9027
-- Recall: 0.9090
-- F1: 0.9058
-- Accuracy: 0.8500
+- Loss: 0.8330
+- Precision: 0.9046
+- Recall: 0.9105
+- F1: 0.9076
+- Accuracy: 0.8536
 
 ## Model description
 
@@ -44,34 +43,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 14
-- eval_batch_size: 14
+- train_batch_size: 4
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 120
+- training_steps: 500
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0.9091  | 10   | 0.9825          | 0.5685    | 0.6133 | 0.5901 | 0.6804   |
-| No log        | 1.8182  | 20   | 0.6492          | 0.7647    | 0.8215 | 0.7921 | 0.7781   |
-| No log        | 2.7273  | 30   | 0.5079          | 0.8037    | 0.8635 | 0.8326 | 0.8370   |
-| No log        | 3.6364  | 40   | 0.5371          | 0.8600    | 0.8924 | 0.8759 | 0.8428   |
-| No log        | 4.5455  | 50   | 0.5696          | 0.8753    | 0.8968 | 0.8859 | 0.8348   |
-| No log        | 5.4545  | 60   | 0.6309          | 0.8733    | 0.8863 | 0.8797 | 0.8272   |
-| No log        | 6.3636  | 70   | 0.6272          | 0.8878    | 0.9003 | 0.8940 | 0.8494   |
-| No log        | 7.2727  | 80   | 0.6168          | 0.9025    | 0.9151 | 0.9088 | 0.8688   |
-| No log        | 8.1818  | 90   | 0.6458          | 0.9094    | 0.9134 | 0.9114 | 0.8588   |
-| No log        | 9.0909  | 100  | 0.6830          | 0.8985    | 0.9064 | 0.9024 | 0.8490   |
-| No log        | 10.0    | 110  | 0.6325          | 0.9086    | 0.9221 | 0.9153 | 0.8502   |
-| No log        | 10.9091 | 120  | 0.6633          | 0.9027    | 0.9090 | 0.9058 | 0.8500   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.32  | 50   | 0.6163          | 0.8088    | 0.8965 | 0.8504 | 0.8088   |
+| No log        | 2.63  | 100  | 0.5416          | 0.8037    | 0.868  | 0.8346 | 0.8134   |
+| No log        | 3.95  | 150  | 0.5572          | 0.8446    | 0.8885 | 0.8660 | 0.8385   |
+| No log        | 5.26  | 200  | 0.7317          | 0.8458    | 0.8555 | 0.8506 | 0.8124   |
+| No log        | 6.58  | 250  | 0.7220          | 0.8877    | 0.8935 | 0.8906 | 0.8385   |
+| No log        | 7.89  | 300  | 0.8070          | 0.8778    | 0.9055 | 0.8915 | 0.8436   |
+| No log        | 9.21  | 350  | 0.7895          | 0.8969    | 0.913  | 0.9049 | 0.8477   |
+| No log        | 10.53 | 400  | 0.8168          | 0.8935    | 0.889  | 0.8912 | 0.8412   |
+| No log        | 11.84 | 450  | 0.8233          | 0.8955    | 0.917  | 0.9061 | 0.8521   |
+| 0.2564        | 13.16 | 500  | 0.8330          | 0.9046    | 0.9105 | 0.9076 | 0.8536   |
 
 
 ### Framework versions
 
-- Transformers 4.44.0
-- Pytorch 2.4.0+cu118
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- Transformers 4.12.5
+- Pytorch 1.10.0+cu111
+- Datasets 2.13.2
+- Tokenizers 0.10.1