<!-- 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. -->
vgm_model_0.2
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: 0.0477
- Precision: 0.8
- Recall: 0.7304
- F1: 0.7636
- Accuracy: 0.9935
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: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.33 | 100 | 0.0826 | 0.1538 | 0.0348 | 0.0567 | 0.9783 |
No log | 2.67 | 200 | 0.0633 | 0.4907 | 0.4609 | 0.4753 | 0.9859 |
No log | 4.0 | 300 | 0.0433 | 0.7358 | 0.6783 | 0.7059 | 0.9927 |
No log | 5.33 | 400 | 0.0412 | 0.76 | 0.6609 | 0.7070 | 0.9916 |
0.0937 | 6.67 | 500 | 0.0390 | 0.6885 | 0.7304 | 0.7089 | 0.9919 |
0.0937 | 8.0 | 600 | 0.0400 | 0.7177 | 0.7739 | 0.7448 | 0.9914 |
0.0937 | 9.33 | 700 | 0.0457 | 0.7619 | 0.6957 | 0.7273 | 0.9924 |
0.0937 | 10.67 | 800 | 0.0370 | 0.7154 | 0.8087 | 0.7592 | 0.9922 |
0.0937 | 12.0 | 900 | 0.0369 | 0.7759 | 0.7826 | 0.7792 | 0.9945 |
0.0105 | 13.33 | 1000 | 0.0373 | 0.7672 | 0.7739 | 0.7706 | 0.9940 |
0.0105 | 14.67 | 1100 | 0.0419 | 0.8190 | 0.7478 | 0.7818 | 0.9940 |
0.0105 | 16.0 | 1200 | 0.0396 | 0.8018 | 0.7739 | 0.7876 | 0.9945 |
0.0105 | 17.33 | 1300 | 0.0428 | 0.7568 | 0.7304 | 0.7434 | 0.9940 |
0.0105 | 18.67 | 1400 | 0.0450 | 0.7522 | 0.7391 | 0.7456 | 0.9940 |
0.003 | 20.0 | 1500 | 0.0397 | 0.7541 | 0.8 | 0.7764 | 0.9937 |
0.003 | 21.33 | 1600 | 0.0415 | 0.8349 | 0.7913 | 0.8125 | 0.9948 |
0.003 | 22.67 | 1700 | 0.0427 | 0.7739 | 0.7739 | 0.7739 | 0.9945 |
0.003 | 24.0 | 1800 | 0.0455 | 0.7727 | 0.7391 | 0.7556 | 0.9935 |
0.003 | 25.33 | 1900 | 0.0464 | 0.7830 | 0.7217 | 0.7511 | 0.9932 |
0.0016 | 26.67 | 2000 | 0.0477 | 0.8 | 0.7304 | 0.7636 | 0.9935 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2