<!-- 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. -->
sogemi_ddt_1.0
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: 0.0375
- Precision: 0.9443
- Recall: 0.9713
- F1: 0.9576
- Accuracy: 0.9927
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 | 1.35 | 100 | 0.6022 | 0.2061 | 0.0774 | 0.1125 | 0.8634 |
No log | 2.7 | 200 | 0.3445 | 0.4627 | 0.3381 | 0.3907 | 0.9051 |
No log | 4.05 | 300 | 0.1820 | 0.7524 | 0.6619 | 0.7043 | 0.9583 |
No log | 5.41 | 400 | 0.1141 | 0.8742 | 0.8166 | 0.8444 | 0.9812 |
0.3555 | 6.76 | 500 | 0.0719 | 0.9229 | 0.9255 | 0.9242 | 0.9867 |
0.3555 | 8.11 | 600 | 0.0526 | 0.9202 | 0.9255 | 0.9229 | 0.9881 |
0.3555 | 9.46 | 700 | 0.0531 | 0.9197 | 0.9513 | 0.9352 | 0.9862 |
0.3555 | 10.81 | 800 | 0.0454 | 0.9167 | 0.9140 | 0.9154 | 0.9872 |
0.3555 | 12.16 | 900 | 0.0447 | 0.9284 | 0.9284 | 0.9284 | 0.9895 |
0.0479 | 13.51 | 1000 | 0.0436 | 0.9370 | 0.9370 | 0.9370 | 0.9872 |
0.0479 | 14.86 | 1100 | 0.0383 | 0.9385 | 0.9628 | 0.9505 | 0.9913 |
0.0479 | 16.22 | 1200 | 0.0389 | 0.9468 | 0.9685 | 0.9575 | 0.9908 |
0.0479 | 17.57 | 1300 | 0.0349 | 0.9743 | 0.9771 | 0.9757 | 0.9945 |
0.0479 | 18.92 | 1400 | 0.0329 | 0.9885 | 0.9857 | 0.9871 | 0.9954 |
0.0244 | 20.27 | 1500 | 0.0380 | 0.9412 | 0.9628 | 0.9518 | 0.9917 |
0.0244 | 21.62 | 1600 | 0.0447 | 0.8917 | 0.9198 | 0.9055 | 0.9853 |
0.0244 | 22.97 | 1700 | 0.0434 | 0.9148 | 0.9542 | 0.9341 | 0.9876 |
0.0244 | 24.32 | 1800 | 0.0444 | 0.9280 | 0.9599 | 0.9437 | 0.9890 |
0.0244 | 25.68 | 1900 | 0.0386 | 0.9361 | 0.9656 | 0.9506 | 0.9913 |
0.015 | 27.03 | 2000 | 0.0381 | 0.9415 | 0.9685 | 0.9548 | 0.9917 |
0.015 | 28.38 | 2100 | 0.0341 | 0.9577 | 0.9742 | 0.9659 | 0.9936 |
0.015 | 29.73 | 2200 | 0.0340 | 0.9715 | 0.9771 | 0.9743 | 0.9945 |
0.015 | 31.08 | 2300 | 0.0365 | 0.9493 | 0.9656 | 0.9574 | 0.9931 |
0.015 | 32.43 | 2400 | 0.0398 | 0.9339 | 0.9713 | 0.9522 | 0.9913 |
0.0123 | 33.78 | 2500 | 0.0375 | 0.9443 | 0.9713 | 0.9576 | 0.9927 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2