<!-- 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. -->
Nexan_model
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: 0.003200
- Precision: 0.998213
- Recall: 0.998213
- F1: 0.998213
- Accuracy: 0.999915
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
Step | Training Loss | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|
2500 | 0.004000 | 0.001310 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
2600 | 0.004000 | 0.001307 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
2700 | 0.004000 | 0.001266 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
2800 | 0.004000 | 0.001327 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
2900 | 0.004000 | 0.001278 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
3000 | 0.003200 | 0.001334 | 0.998213 | 0.998213 | 0.998213 | 0.999915 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2