<!-- 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. -->
layoutlm_coc_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: 0.0331
- Precision: 0.7949
- Recall: 0.7323
- F1: 0.7623
- Accuracy: 0.9944
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 | 1.33 | 100 | 0.0609 | 0.4576 | 0.4252 | 0.4408 | 0.9855 |
No log | 2.67 | 200 | 0.0336 | 0.6697 | 0.5748 | 0.6186 | 0.9912 |
No log | 4.0 | 300 | 0.0299 | 0.6957 | 0.6299 | 0.6612 | 0.9922 |
No log | 5.33 | 400 | 0.0287 | 0.7311 | 0.6850 | 0.7073 | 0.9929 |
0.064 | 6.67 | 500 | 0.0311 | 0.7863 | 0.7244 | 0.7541 | 0.9941 |
0.064 | 8.0 | 600 | 0.0317 | 0.7419 | 0.7244 | 0.7331 | 0.9936 |
0.064 | 9.33 | 700 | 0.0330 | 0.7297 | 0.6378 | 0.6807 | 0.9926 |
0.064 | 10.67 | 800 | 0.0315 | 0.7692 | 0.7087 | 0.7377 | 0.9939 |
0.064 | 12.0 | 900 | 0.0341 | 0.8148 | 0.6929 | 0.7489 | 0.9941 |
0.0063 | 13.33 | 1000 | 0.0331 | 0.7949 | 0.7323 | 0.7623 | 0.9944 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2