<!-- 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. -->
rhenus_model
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: 0.1560
- Precision: 0.8057
- Recall: 0.8397
- F1: 0.8223
- Accuracy: 0.9734
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 | 1.96 | 100 | 0.7818 | 0.0909 | 0.0042 | 0.0081 | 0.8569 |
No log | 3.92 | 200 | 0.5681 | 0.2442 | 0.0886 | 0.1300 | 0.8708 |
No log | 5.88 | 300 | 0.4568 | 0.2803 | 0.1857 | 0.2234 | 0.8913 |
No log | 7.84 | 400 | 0.3759 | 0.5053 | 0.4051 | 0.4496 | 0.9196 |
0.5952 | 9.8 | 500 | 0.2987 | 0.6560 | 0.6034 | 0.6286 | 0.9456 |
0.5952 | 11.76 | 600 | 0.2585 | 0.6721 | 0.6920 | 0.6819 | 0.9456 |
0.5952 | 13.73 | 700 | 0.2016 | 0.7247 | 0.7553 | 0.7397 | 0.9595 |
0.5952 | 15.69 | 800 | 0.2053 | 0.704 | 0.7426 | 0.7228 | 0.9573 |
0.5952 | 17.65 | 900 | 0.1845 | 0.7782 | 0.7848 | 0.7815 | 0.9667 |
0.1097 | 19.61 | 1000 | 0.1917 | 0.75 | 0.7848 | 0.7670 | 0.9623 |
0.1097 | 21.57 | 1100 | 0.1897 | 0.8099 | 0.8270 | 0.8184 | 0.9695 |
0.1097 | 23.53 | 1200 | 0.1848 | 0.7901 | 0.8101 | 0.8 | 0.9684 |
0.1097 | 25.49 | 1300 | 0.1533 | 0.8016 | 0.8523 | 0.8262 | 0.9734 |
0.1097 | 27.45 | 1400 | 0.1534 | 0.8204 | 0.8481 | 0.8340 | 0.9750 |
0.0384 | 29.41 | 1500 | 0.1879 | 0.8024 | 0.8397 | 0.8206 | 0.9695 |
0.0384 | 31.37 | 1600 | 0.1550 | 0.816 | 0.8608 | 0.8378 | 0.9750 |
0.0384 | 33.33 | 1700 | 0.1598 | 0.8279 | 0.8523 | 0.8399 | 0.9756 |
0.0384 | 35.29 | 1800 | 0.1643 | 0.8148 | 0.8354 | 0.825 | 0.9728 |
0.0384 | 37.25 | 1900 | 0.1558 | 0.792 | 0.8354 | 0.8131 | 0.9728 |
0.02 | 39.22 | 2000 | 0.1699 | 0.7944 | 0.8312 | 0.8124 | 0.9717 |
0.02 | 41.18 | 2100 | 0.1558 | 0.8138 | 0.8481 | 0.8306 | 0.9750 |
0.02 | 43.14 | 2200 | 0.1566 | 0.8024 | 0.8397 | 0.8206 | 0.9728 |
0.02 | 45.1 | 2300 | 0.1617 | 0.8049 | 0.8354 | 0.8199 | 0.9734 |
0.02 | 47.06 | 2400 | 0.1571 | 0.8016 | 0.8354 | 0.8182 | 0.9723 |
0.014 | 49.02 | 2500 | 0.1560 | 0.8057 | 0.8397 | 0.8223 | 0.9734 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2