<!-- 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_manifesto_bigdataset
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: 0.0080
- Precision: 0.9911
- Recall: 0.9928
- F1: 0.9919
- Accuracy: 0.9989
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: 1500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 2.0 | 100 | 0.0820 | 0.9071 | 0.9104 | 0.9088 | 0.9855 |
| No log | 4.0 | 200 | 0.0291 | 0.9441 | 0.9677 | 0.9558 | 0.9946 |
| No log | 6.0 | 300 | 0.0121 | 0.9751 | 0.9821 | 0.9786 | 0.9977 |
| No log | 8.0 | 400 | 0.0089 | 0.9911 | 0.9946 | 0.9928 | 0.9989 |
| 0.1049 | 10.0 | 500 | 0.0083 | 0.9840 | 0.9892 | 0.9866 | 0.9983 |
| 0.1049 | 12.0 | 600 | 0.0077 | 0.9875 | 0.9928 | 0.9902 | 0.9986 |
| 0.1049 | 14.0 | 700 | 0.0081 | 0.9893 | 0.9910 | 0.9902 | 0.9986 |
| 0.1049 | 16.0 | 800 | 0.0081 | 0.9875 | 0.9892 | 0.9884 | 0.9983 |
| 0.1049 | 18.0 | 900 | 0.0081 | 0.9893 | 0.9910 | 0.9902 | 0.9986 |
| 0.0051 | 20.0 | 1000 | 0.0074 | 0.9822 | 0.9875 | 0.9848 | 0.9980 |
| 0.0051 | 22.0 | 1100 | 0.0083 | 0.9911 | 0.9928 | 0.9919 | 0.9989 |
| 0.0051 | 24.0 | 1200 | 0.0073 | 0.9893 | 0.9910 | 0.9902 | 0.9986 |
| 0.0051 | 26.0 | 1300 | 0.0070 | 0.9911 | 0.9928 | 0.9919 | 0.9989 |
| 0.0051 | 28.0 | 1400 | 0.0081 | 0.9911 | 0.9928 | 0.9919 | 0.9989 |
| 0.0022 | 30.0 | 1500 | 0.0080 | 0.9911 | 0.9928 | 0.9919 | 0.9989 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2
