<!-- 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. -->
perioli_manifesti_v3.4
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: 0.2080
- Precision: 0.7645
- Recall: 0.8239
- F1: 0.7931
- Accuracy: 0.9555
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: 1500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.37 | 100 | 0.2707 | 0.6027 | 0.6723 | 0.6356 | 0.9309 |
No log | 2.74 | 200 | 0.1815 | 0.7131 | 0.7860 | 0.7477 | 0.9469 |
No log | 4.11 | 300 | 0.1749 | 0.7786 | 0.8258 | 0.8015 | 0.9580 |
No log | 5.48 | 400 | 0.1742 | 0.7982 | 0.8390 | 0.8181 | 0.9601 |
0.2249 | 6.85 | 500 | 0.1471 | 0.7700 | 0.8371 | 0.8022 | 0.9590 |
0.2249 | 8.22 | 600 | 0.1908 | 0.7851 | 0.8371 | 0.8103 | 0.9580 |
0.2249 | 9.59 | 700 | 0.1710 | 0.7880 | 0.8447 | 0.8154 | 0.9601 |
0.2249 | 10.96 | 800 | 0.1801 | 0.7578 | 0.8239 | 0.7895 | 0.9580 |
0.2249 | 12.33 | 900 | 0.1796 | 0.7686 | 0.8239 | 0.7952 | 0.9569 |
0.0454 | 13.7 | 1000 | 0.1868 | 0.7776 | 0.8277 | 0.8018 | 0.9580 |
0.0454 | 15.07 | 1100 | 0.2048 | 0.7592 | 0.8239 | 0.7902 | 0.9562 |
0.0454 | 16.44 | 1200 | 0.1944 | 0.7627 | 0.8277 | 0.7938 | 0.9572 |
0.0454 | 17.81 | 1300 | 0.1980 | 0.7583 | 0.8201 | 0.7880 | 0.9558 |
0.0454 | 19.18 | 1400 | 0.2098 | 0.7632 | 0.8239 | 0.7923 | 0.9555 |
0.0269 | 20.55 | 1500 | 0.2080 | 0.7645 | 0.8239 | 0.7931 | 0.9555 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2