layoutlmv3-finetuned-cord-sroie
This model is a fine-tuned version of layoutlmv3 on the mp-02/cord-sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0731
- Precision: 0.9552
- Recall: 0.9647
- F1: 0.9599
- Accuracy: 0.9860
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.7483 | 250 | 0.3308 | 0.8186 | 0.7941 | 0.8062 | 0.9427 |
0.7339 | 3.4965 | 500 | 0.1450 | 0.9013 | 0.9195 | 0.9103 | 0.9722 |
0.7339 | 5.2448 | 750 | 0.1009 | 0.9314 | 0.9386 | 0.9350 | 0.9791 |
0.1726 | 6.9930 | 1000 | 0.0841 | 0.9445 | 0.9562 | 0.9503 | 0.9839 |
0.1726 | 8.7413 | 1250 | 0.0776 | 0.9563 | 0.9533 | 0.9548 | 0.9850 |
0.0918 | 10.4895 | 1500 | 0.0782 | 0.9450 | 0.9611 | 0.9530 | 0.9844 |
0.0918 | 12.2378 | 1750 | 0.0699 | 0.9539 | 0.9602 | 0.9570 | 0.9856 |
0.0587 | 13.9860 | 2000 | 0.0743 | 0.9550 | 0.9611 | 0.9581 | 0.9859 |
0.0587 | 15.7343 | 2250 | 0.0726 | 0.9596 | 0.9633 | 0.9615 | 0.9863 |
0.046 | 17.4825 | 2500 | 0.0731 | 0.9552 | 0.9647 | 0.9599 | 0.9860 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 68
Inference API (serverless) is not available, repository is disabled.
Dataset used to train mp-02/layoutlmv3-finetuned-cord-sroie
Space using mp-02/layoutlmv3-finetuned-cord-sroie 1
Evaluation results
- Precision on mp-02/cord-sroieself-reported0.955
- Recall on mp-02/cord-sroieself-reported0.965
- F1 on mp-02/cord-sroieself-reported0.960
- Accuracy on mp-02/cord-sroieself-reported0.986