<!-- 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. -->
invoice_clients_CAD.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: 0.1746
- Precision: 0.6680
- Recall: 0.5923
- F1: 0.6279
- Accuracy: 0.9624
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 | 0.78 | 100 | 0.4639 | 0.3014 | 0.0383 | 0.0680 | 0.8999 |
No log | 1.55 | 200 | 0.3762 | 0.2624 | 0.0645 | 0.1035 | 0.9078 |
No log | 2.33 | 300 | 0.3180 | 0.3872 | 0.2840 | 0.3276 | 0.9303 |
No log | 3.1 | 400 | 0.2577 | 0.5460 | 0.3310 | 0.4121 | 0.9414 |
0.4395 | 3.88 | 500 | 0.2410 | 0.5443 | 0.3641 | 0.4363 | 0.9477 |
0.4395 | 4.65 | 600 | 0.2205 | 0.6449 | 0.4303 | 0.5162 | 0.9525 |
0.4395 | 5.43 | 700 | 0.2154 | 0.5960 | 0.4164 | 0.4903 | 0.9508 |
0.4395 | 6.2 | 800 | 0.2252 | 0.5841 | 0.4233 | 0.4909 | 0.9532 |
0.4395 | 6.98 | 900 | 0.2039 | 0.6397 | 0.4826 | 0.5501 | 0.9582 |
0.1677 | 7.75 | 1000 | 0.1888 | 0.6080 | 0.5052 | 0.5519 | 0.9593 |
0.1677 | 8.53 | 1100 | 0.1869 | 0.5599 | 0.4965 | 0.5263 | 0.9577 |
0.1677 | 9.3 | 1200 | 0.1701 | 0.5833 | 0.5366 | 0.5590 | 0.9594 |
0.1677 | 10.08 | 1300 | 0.1786 | 0.6292 | 0.5557 | 0.5902 | 0.9612 |
0.1677 | 10.85 | 1400 | 0.1745 | 0.6356 | 0.5470 | 0.5880 | 0.9600 |
0.0902 | 11.63 | 1500 | 0.1746 | 0.6346 | 0.5627 | 0.5965 | 0.9623 |
0.0902 | 12.4 | 1600 | 0.1687 | 0.5975 | 0.5819 | 0.5896 | 0.9606 |
0.0902 | 13.18 | 1700 | 0.1736 | 0.6594 | 0.5836 | 0.6192 | 0.9631 |
0.0902 | 13.95 | 1800 | 0.1766 | 0.6530 | 0.5836 | 0.6164 | 0.9624 |
0.0902 | 14.73 | 1900 | 0.1712 | 0.6737 | 0.6080 | 0.6392 | 0.9623 |
0.0584 | 15.5 | 2000 | 0.1746 | 0.6680 | 0.5923 | 0.6279 | 0.9624 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3