<!-- 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_v3.7
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: 0.0736
- Precision: 0.8682
- Recall: 0.8908
- F1: 0.8794
- Accuracy: 0.9823
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: 1000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.16 | 100 | 0.2940 | 0.6870 | 0.7990 | 0.7388 | 0.9421 |
No log | 2.33 | 200 | 0.0959 | 0.8571 | 0.8943 | 0.8753 | 0.9774 |
No log | 3.49 | 300 | 0.0801 | 0.8616 | 0.8631 | 0.8623 | 0.9789 |
No log | 4.65 | 400 | 0.0771 | 0.8514 | 0.8839 | 0.8673 | 0.9789 |
0.1356 | 5.81 | 500 | 0.0729 | 0.8627 | 0.8821 | 0.8723 | 0.9816 |
0.1356 | 6.98 | 600 | 0.0722 | 0.8908 | 0.9185 | 0.9044 | 0.9846 |
0.1356 | 8.14 | 700 | 0.0773 | 0.8627 | 0.8821 | 0.8723 | 0.9819 |
0.1356 | 9.3 | 800 | 0.0801 | 0.8615 | 0.8839 | 0.8725 | 0.9816 |
0.1356 | 10.47 | 900 | 0.0740 | 0.8682 | 0.8908 | 0.8794 | 0.9823 |
0.0131 | 11.63 | 1000 | 0.0736 | 0.8682 | 0.8908 | 0.8794 | 0.9823 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2