End of training

README.md

@@ -15,19 +15,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0859
-- Nswer Precision: 1.0
-- Nswer Recall: 1.0
-- Nswer F1: 1.0
+- Loss: 0.1332
+- Nswer Precision: 0.9759
+- Nswer Recall: 0.9878
+- Nswer F1: 0.9818
 - Nswer Number: 82
-- Uestion Precision: 1.0
+- Uestion Precision: 0.9880
 - Uestion Recall: 1.0
-- Uestion F1: 1.0
+- Uestion F1: 0.9939
 - Uestion Number: 82
-- Overall Precision: 1.0
-- Overall Recall: 1.0
-- Overall F1: 1.0
-- Overall Accuracy: 1.0
+- Overall Precision: 0.9819
+- Overall Recall: 0.9939
+- Overall F1: 0.9879
+- Overall Accuracy: 0.9959
 
 ## Model description
 
@@ -47,19 +47,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 4
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Nswer Precision | Nswer Recall | Nswer F1 | Nswer Number | Uestion Precision | Uestion Recall | Uestion F1 | Uestion Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.2545        | 1.0   | 41   | 0.0986          | 1.0             | 1.0          | 1.0      | 82           | 1.0               | 1.0            | 1.0        | 82             | 1.0               | 1.0            | 1.0        | 1.0              |
-| 0.1017        | 2.0   | 82   | 0.0859          | 1.0             | 1.0          | 1.0      | 82           | 1.0               | 1.0            | 1.0        | 82             | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.2778        | 1.0   | 41   | 0.1332          | 0.9759          | 0.9878       | 0.9818   | 82           | 0.9880            | 1.0            | 0.9939     | 82             | 0.9819            | 0.9939         | 0.9879     | 0.9959           |
 
 
 ### Framework versions