<!-- 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_v3.1
This model is a fine-tuned version of microsoft/layoutlmv3-large on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.1395
- Precision: 0.6842
- Recall: 0.6341
- F1: 0.6582
- Accuracy: 0.9880
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: 2500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.08 | 100 | 0.1117 | 0.4396 | 0.3252 | 0.3738 | 0.9796 |
No log | 2.15 | 200 | 0.1082 | 0.5957 | 0.4553 | 0.5161 | 0.9849 |
No log | 3.23 | 300 | 0.1041 | 0.5752 | 0.5285 | 0.5508 | 0.9844 |
No log | 4.3 | 400 | 0.1024 | 0.6944 | 0.6098 | 0.6494 | 0.9872 |
0.0553 | 5.38 | 500 | 0.0826 | 0.6364 | 0.6260 | 0.6311 | 0.9880 |
0.0553 | 6.45 | 600 | 0.0795 | 0.672 | 0.6829 | 0.6774 | 0.9888 |
0.0553 | 7.53 | 700 | 0.1035 | 0.6903 | 0.6341 | 0.6610 | 0.9883 |
0.0553 | 8.6 | 800 | 0.0913 | 0.8081 | 0.6504 | 0.7207 | 0.9905 |
0.0553 | 9.68 | 900 | 0.0901 | 0.6860 | 0.6748 | 0.6803 | 0.9886 |
0.0048 | 10.75 | 1000 | 0.0868 | 0.7168 | 0.6585 | 0.6864 | 0.9891 |
0.0048 | 11.83 | 1100 | 0.1281 | 0.7179 | 0.6829 | 0.7000 | 0.9877 |
0.0048 | 12.9 | 1200 | 0.0936 | 0.6803 | 0.6748 | 0.6776 | 0.9886 |
0.0048 | 13.98 | 1300 | 0.0862 | 0.6183 | 0.6585 | 0.6378 | 0.9883 |
0.0048 | 15.05 | 1400 | 0.1058 | 0.7009 | 0.6667 | 0.6833 | 0.9877 |
0.0013 | 16.13 | 1500 | 0.1182 | 0.6754 | 0.6260 | 0.6498 | 0.9874 |
0.0013 | 17.2 | 1600 | 0.1192 | 0.7069 | 0.6667 | 0.6862 | 0.9883 |
0.0013 | 18.28 | 1700 | 0.1209 | 0.6583 | 0.6423 | 0.6502 | 0.9880 |
0.0013 | 19.35 | 1800 | 0.1324 | 0.6552 | 0.6179 | 0.6360 | 0.9874 |
0.0013 | 20.43 | 1900 | 0.1310 | 0.6610 | 0.6341 | 0.6473 | 0.9874 |
0.0004 | 21.51 | 2000 | 0.1352 | 0.6610 | 0.6341 | 0.6473 | 0.9874 |
0.0004 | 22.58 | 2100 | 0.1379 | 0.6724 | 0.6341 | 0.6527 | 0.9877 |
0.0004 | 23.66 | 2200 | 0.1397 | 0.6991 | 0.6423 | 0.6695 | 0.9883 |
0.0004 | 24.73 | 2300 | 0.1384 | 0.6964 | 0.6341 | 0.6638 | 0.9886 |
0.0004 | 25.81 | 2400 | 0.1391 | 0.6964 | 0.6341 | 0.6638 | 0.9886 |
0.0002 | 26.88 | 2500 | 0.1395 | 0.6842 | 0.6341 | 0.6582 | 0.9880 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2