model-2024-06-05
This model is a fine-tuned version of microsoft/layoutlmv3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4986
- Precision: 0.7474
- Recall: 0.7807
- F1: 0.7637
- Accuracy: 0.8733
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 | 1.02 | 100 | 1.1715 | 0.4678 | 0.1928 | 0.2730 | 0.6988 |
No log | 2.04 | 200 | 0.7350 | 0.7285 | 0.6337 | 0.6778 | 0.8296 |
No log | 3.06 | 300 | 0.6022 | 0.7073 | 0.6843 | 0.6957 | 0.8428 |
No log | 4.08 | 400 | 0.5440 | 0.7218 | 0.7096 | 0.7157 | 0.8498 |
0.9898 | 5.1 | 500 | 0.5059 | 0.7300 | 0.7458 | 0.7378 | 0.8610 |
0.9898 | 6.12 | 600 | 0.4998 | 0.7438 | 0.7554 | 0.7496 | 0.8696 |
0.9898 | 7.14 | 700 | 0.5104 | 0.7549 | 0.7458 | 0.7503 | 0.8663 |
0.9898 | 8.16 | 800 | 0.4817 | 0.7608 | 0.7627 | 0.7617 | 0.8758 |
0.9898 | 9.18 | 900 | 0.4845 | 0.76 | 0.7783 | 0.7690 | 0.8758 |
0.3448 | 10.2 | 1000 | 0.4986 | 0.7474 | 0.7807 | 0.7637 | 0.8733 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.13.3
- Downloads last month
- 0