<!-- 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. -->
HojadeRuta2.0
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: 0.0127
- Precision: 0.9639
- Recall: 0.9842
- F1: 0.9740
- Accuracy: 0.9986
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 | 0.76 | 100 | 0.0136 | 0.9482 | 0.9632 | 0.9556 | 0.9943 |
No log | 1.52 | 200 | 0.0104 | 0.9536 | 0.9737 | 0.9635 | 0.9981 |
No log | 2.27 | 300 | 0.0116 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
No log | 3.03 | 400 | 0.0121 | 0.9536 | 0.9737 | 0.9635 | 0.9981 |
0.0139 | 3.79 | 500 | 0.0126 | 0.9536 | 0.9737 | 0.9635 | 0.9981 |
0.0139 | 4.55 | 600 | 0.0102 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0139 | 5.3 | 700 | 0.0146 | 0.9536 | 0.9737 | 0.9635 | 0.9981 |
0.0139 | 6.06 | 800 | 0.0151 | 0.9536 | 0.9737 | 0.9635 | 0.9981 |
0.0139 | 6.82 | 900 | 0.0116 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0005 | 7.58 | 1000 | 0.0126 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0005 | 8.33 | 1100 | 0.0126 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0005 | 9.09 | 1200 | 0.0127 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0005 | 9.85 | 1300 | 0.0127 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0005 | 10.61 | 1400 | 0.0127 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
0.0002 | 11.36 | 1500 | 0.0127 | 0.9639 | 0.9842 | 0.9740 | 0.9986 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2