<!-- 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. -->
perioli_vgm_v4.0
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: 0.0692
- Precision: 0.7059
- Recall: 0.6713
- F1: 0.6882
- Accuracy: 0.9912
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 | 0.89 | 100 | 0.0794 | 0.6 | 0.6294 | 0.6143 | 0.9867 |
No log | 1.79 | 200 | 0.0721 | 0.6599 | 0.6783 | 0.6690 | 0.9891 |
No log | 2.68 | 300 | 0.0820 | 0.6370 | 0.6014 | 0.6187 | 0.9867 |
No log | 3.57 | 400 | 0.0771 | 0.6544 | 0.6224 | 0.6380 | 0.9891 |
0.0072 | 4.46 | 500 | 0.0656 | 0.7132 | 0.6434 | 0.6765 | 0.9905 |
0.0072 | 5.36 | 600 | 0.0727 | 0.6395 | 0.6573 | 0.6483 | 0.9884 |
0.0072 | 6.25 | 700 | 0.0827 | 0.6870 | 0.6294 | 0.6569 | 0.9888 |
0.0072 | 7.14 | 800 | 0.0703 | 0.6947 | 0.6364 | 0.6642 | 0.9910 |
0.0072 | 8.04 | 900 | 0.0706 | 0.6716 | 0.6294 | 0.6498 | 0.9903 |
0.0022 | 8.93 | 1000 | 0.0692 | 0.7059 | 0.6713 | 0.6882 | 0.9912 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2