<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
passive_invoices_v2.2
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0706
- Precision: 0.9257
- Recall: 0.9261
- F1: 0.9259
- Accuracy: 0.9861
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 4000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.15 | 100 | 1.0595 | 0.3274 | 0.0121 | 0.0233 | 0.7863 |
No log | 0.29 | 200 | 0.7155 | 0.3537 | 0.3219 | 0.3370 | 0.8321 |
No log | 0.44 | 300 | 0.5414 | 0.4769 | 0.4647 | 0.4707 | 0.8713 |
No log | 0.59 | 400 | 0.3947 | 0.6884 | 0.6722 | 0.6802 | 0.9326 |
0.9149 | 0.74 | 500 | 0.2809 | 0.7644 | 0.7462 | 0.7552 | 0.9525 |
0.9149 | 0.88 | 600 | 0.2227 | 0.8161 | 0.7918 | 0.8038 | 0.9609 |
0.9149 | 1.03 | 700 | 0.1940 | 0.8468 | 0.8164 | 0.8313 | 0.9655 |
0.9149 | 1.18 | 800 | 0.1702 | 0.8481 | 0.8339 | 0.8409 | 0.9684 |
0.9149 | 1.33 | 900 | 0.1610 | 0.8573 | 0.8451 | 0.8512 | 0.9691 |
0.2477 | 1.47 | 1000 | 0.1396 | 0.8703 | 0.8497 | 0.8599 | 0.9734 |
0.2477 | 1.62 | 1100 | 0.1392 | 0.8521 | 0.8763 | 0.8640 | 0.9717 |
0.2477 | 1.77 | 1200 | 0.1229 | 0.8855 | 0.8734 | 0.8794 | 0.9757 |
0.2477 | 1.91 | 1300 | 0.1311 | 0.8531 | 0.8804 | 0.8666 | 0.9724 |
0.2477 | 2.06 | 1400 | 0.1110 | 0.8771 | 0.8800 | 0.8785 | 0.9764 |
0.1481 | 2.21 | 1500 | 0.1081 | 0.8889 | 0.8811 | 0.8850 | 0.9779 |
0.1481 | 2.36 | 1600 | 0.1045 | 0.8794 | 0.8907 | 0.8850 | 0.9775 |
0.1481 | 2.5 | 1700 | 0.1028 | 0.8867 | 0.8962 | 0.8914 | 0.9781 |
0.1481 | 2.65 | 1800 | 0.1016 | 0.9113 | 0.8837 | 0.8973 | 0.9794 |
0.1481 | 2.8 | 1900 | 0.0949 | 0.9005 | 0.8912 | 0.8958 | 0.9801 |
0.1141 | 2.95 | 2000 | 0.0926 | 0.9013 | 0.8993 | 0.9003 | 0.9806 |
0.1141 | 3.09 | 2100 | 0.0929 | 0.9109 | 0.8901 | 0.9004 | 0.9811 |
0.1141 | 3.24 | 2200 | 0.0864 | 0.9105 | 0.9043 | 0.9074 | 0.9822 |
0.1141 | 3.39 | 2300 | 0.0894 | 0.8996 | 0.9043 | 0.9020 | 0.9818 |
0.1141 | 3.53 | 2400 | 0.0851 | 0.8975 | 0.9030 | 0.9003 | 0.9814 |
0.0887 | 3.68 | 2500 | 0.0831 | 0.9069 | 0.9109 | 0.9089 | 0.9823 |
0.0887 | 3.83 | 2600 | 0.0822 | 0.9145 | 0.9103 | 0.9124 | 0.9830 |
0.0887 | 3.98 | 2700 | 0.0785 | 0.9082 | 0.9136 | 0.9109 | 0.9828 |
0.0887 | 4.12 | 2800 | 0.0799 | 0.9097 | 0.9131 | 0.9114 | 0.9835 |
0.0887 | 4.27 | 2900 | 0.0771 | 0.9211 | 0.9142 | 0.9176 | 0.9845 |
0.0732 | 4.42 | 3000 | 0.0780 | 0.9010 | 0.9182 | 0.9095 | 0.9831 |
0.0732 | 4.57 | 3100 | 0.0745 | 0.9323 | 0.9184 | 0.9253 | 0.9855 |
0.0732 | 4.71 | 3200 | 0.0723 | 0.9220 | 0.9232 | 0.9226 | 0.9856 |
0.0732 | 4.86 | 3300 | 0.0720 | 0.9302 | 0.9234 | 0.9268 | 0.9858 |
0.0732 | 5.01 | 3400 | 0.0709 | 0.9191 | 0.9243 | 0.9217 | 0.9858 |
0.0683 | 5.15 | 3500 | 0.0719 | 0.9188 | 0.9258 | 0.9223 | 0.9856 |
0.0683 | 5.3 | 3600 | 0.0712 | 0.9267 | 0.9241 | 0.9254 | 0.9861 |
0.0683 | 5.45 | 3700 | 0.0708 | 0.9222 | 0.9237 | 0.9229 | 0.9857 |
0.0683 | 5.6 | 3800 | 0.0702 | 0.9250 | 0.9256 | 0.9253 | 0.9861 |
0.0683 | 5.74 | 3900 | 0.0709 | 0.9257 | 0.9272 | 0.9264 | 0.9861 |
0.0595 | 5.89 | 4000 | 0.0706 | 0.9257 | 0.9261 | 0.9259 | 0.9861 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3