<!-- 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_v8.5
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: 0.0207
- Precision: 0.9485
- Recall: 0.9707
- F1: 0.9595
- Accuracy: 0.9952
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: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.33 | 100 | 0.1734 | 0.6829 | 0.7349 | 0.7080 | 0.9542 |
No log | 0.65 | 200 | 0.0776 | 0.7971 | 0.8666 | 0.8304 | 0.9740 |
No log | 0.98 | 300 | 0.0421 | 0.8923 | 0.9338 | 0.9126 | 0.9885 |
No log | 1.31 | 400 | 0.0307 | 0.9167 | 0.9524 | 0.9342 | 0.9917 |
0.1671 | 1.63 | 500 | 0.0421 | 0.8738 | 0.9407 | 0.9060 | 0.9883 |
0.1671 | 1.96 | 600 | 0.0247 | 0.9322 | 0.9576 | 0.9447 | 0.9931 |
0.1671 | 2.29 | 700 | 0.0250 | 0.9351 | 0.9593 | 0.9471 | 0.9933 |
0.1671 | 2.61 | 800 | 0.0248 | 0.9380 | 0.9645 | 0.9511 | 0.9939 |
0.1671 | 2.94 | 900 | 0.0231 | 0.9323 | 0.9638 | 0.9478 | 0.9934 |
0.0284 | 3.27 | 1000 | 0.0212 | 0.9480 | 0.9673 | 0.9575 | 0.9949 |
0.0284 | 3.59 | 1100 | 0.0204 | 0.9471 | 0.9683 | 0.9576 | 0.9950 |
0.0284 | 3.92 | 1200 | 0.0199 | 0.9450 | 0.9662 | 0.9555 | 0.9946 |
0.0284 | 4.25 | 1300 | 0.0239 | 0.9349 | 0.9652 | 0.9498 | 0.9938 |
0.0284 | 4.58 | 1400 | 0.0213 | 0.9556 | 0.9728 | 0.9641 | 0.9956 |
0.0153 | 4.9 | 1500 | 0.0210 | 0.9459 | 0.9707 | 0.9581 | 0.9950 |
0.0153 | 5.23 | 1600 | 0.0211 | 0.9478 | 0.9707 | 0.9591 | 0.9952 |
0.0153 | 5.56 | 1700 | 0.0197 | 0.9533 | 0.9714 | 0.9623 | 0.9955 |
0.0153 | 5.88 | 1800 | 0.0201 | 0.9483 | 0.9683 | 0.9582 | 0.9951 |
0.0153 | 6.21 | 1900 | 0.0200 | 0.9520 | 0.9707 | 0.9613 | 0.9953 |
0.011 | 6.54 | 2000 | 0.0207 | 0.9485 | 0.9707 | 0.9595 | 0.9952 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3