<!-- 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. -->
saviola1.0
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: 0.0829
- Precision: 0.8712
- Recall: 0.9010
- F1: 0.8858
- Accuracy: 0.9847
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: 2500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.35 | 100 | 0.2981 | 0.0423 | 0.0038 | 0.0070 | 0.9178 |
No log | 0.7 | 200 | 0.1707 | 0.7509 | 0.7995 | 0.7744 | 0.9670 |
No log | 1.05 | 300 | 0.0950 | 0.7939 | 0.8211 | 0.8072 | 0.9778 |
No log | 1.4 | 400 | 0.0648 | 0.8191 | 0.8503 | 0.8344 | 0.9850 |
0.2168 | 1.75 | 500 | 0.0612 | 0.8316 | 0.8896 | 0.8596 | 0.9860 |
0.2168 | 2.1 | 600 | 0.0546 | 0.8752 | 0.9162 | 0.8952 | 0.9884 |
0.2168 | 2.45 | 700 | 0.0537 | 0.8789 | 0.9213 | 0.8996 | 0.9885 |
0.2168 | 2.8 | 800 | 0.0547 | 0.8669 | 0.9175 | 0.8915 | 0.9881 |
0.2168 | 3.15 | 900 | 0.0581 | 0.8672 | 0.9201 | 0.8929 | 0.9879 |
0.0364 | 3.5 | 1000 | 0.0591 | 0.8714 | 0.9112 | 0.8908 | 0.9866 |
0.0364 | 3.85 | 1100 | 0.0587 | 0.8697 | 0.9061 | 0.8875 | 0.9878 |
0.0364 | 4.2 | 1200 | 0.0591 | 0.8626 | 0.9162 | 0.8886 | 0.9879 |
0.0364 | 4.55 | 1300 | 0.0718 | 0.8642 | 0.8883 | 0.8761 | 0.9844 |
0.0364 | 4.9 | 1400 | 0.0757 | 0.8520 | 0.8985 | 0.8746 | 0.9843 |
0.0227 | 5.24 | 1500 | 0.0784 | 0.8414 | 0.8820 | 0.8612 | 0.9831 |
0.0227 | 5.59 | 1600 | 0.0729 | 0.8587 | 0.9023 | 0.8800 | 0.9847 |
0.0227 | 5.94 | 1700 | 0.0738 | 0.8667 | 0.8997 | 0.8829 | 0.9849 |
0.0227 | 6.29 | 1800 | 0.0772 | 0.8722 | 0.9010 | 0.8864 | 0.9847 |
0.0227 | 6.64 | 1900 | 0.0756 | 0.8676 | 0.8985 | 0.8828 | 0.9851 |
0.0213 | 6.99 | 2000 | 0.0745 | 0.8707 | 0.9061 | 0.8881 | 0.9847 |
0.0213 | 7.34 | 2100 | 0.0771 | 0.8681 | 0.9023 | 0.8849 | 0.9848 |
0.0213 | 7.69 | 2200 | 0.0794 | 0.8765 | 0.9099 | 0.8929 | 0.9856 |
0.0213 | 8.04 | 2300 | 0.0824 | 0.8679 | 0.8921 | 0.8798 | 0.9844 |
0.0213 | 8.39 | 2400 | 0.0831 | 0.8687 | 0.8985 | 0.8833 | 0.9842 |
0.0163 | 8.74 | 2500 | 0.0829 | 0.8712 | 0.9010 | 0.8858 | 0.9847 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2