<!-- 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_v7.4
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: 0.0436
- Precision: 0.8786
- Recall: 0.8922
- F1: 0.8853
- Accuracy: 0.9950
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: 6000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.38 | 100 | 0.0535 | 0.7775 | 0.8319 | 0.8038 | 0.9910 |
No log | 0.75 | 200 | 0.0463 | 0.8455 | 0.8431 | 0.8443 | 0.9928 |
No log | 1.13 | 300 | 0.0490 | 0.8326 | 0.8431 | 0.8379 | 0.9930 |
No log | 1.5 | 400 | 0.0434 | 0.8128 | 0.8207 | 0.8167 | 0.9921 |
0.0043 | 1.88 | 500 | 0.0454 | 0.8443 | 0.8277 | 0.8359 | 0.9931 |
0.0043 | 2.26 | 600 | 0.0472 | 0.8363 | 0.8585 | 0.8473 | 0.9932 |
0.0043 | 2.63 | 700 | 0.0492 | 0.8479 | 0.8431 | 0.8455 | 0.9933 |
0.0043 | 3.01 | 800 | 0.0436 | 0.8549 | 0.8501 | 0.8525 | 0.9939 |
0.0043 | 3.38 | 900 | 0.0529 | 0.8636 | 0.8249 | 0.8438 | 0.9933 |
0.0034 | 3.76 | 1000 | 0.0370 | 0.8746 | 0.8501 | 0.8622 | 0.9942 |
0.0034 | 4.14 | 1100 | 0.0415 | 0.8926 | 0.8263 | 0.8582 | 0.9939 |
0.0034 | 4.51 | 1200 | 0.0418 | 0.8829 | 0.8557 | 0.8691 | 0.9941 |
0.0034 | 4.89 | 1300 | 0.0467 | 0.9032 | 0.8361 | 0.8684 | 0.9940 |
0.0034 | 5.26 | 1400 | 0.0427 | 0.8787 | 0.8824 | 0.8805 | 0.9947 |
0.0017 | 5.64 | 1500 | 0.0405 | 0.8911 | 0.8599 | 0.8753 | 0.9944 |
0.0017 | 6.02 | 1600 | 0.0401 | 0.8820 | 0.8585 | 0.8701 | 0.9942 |
0.0017 | 6.39 | 1700 | 0.0443 | 0.8755 | 0.8768 | 0.8761 | 0.9944 |
0.0017 | 6.77 | 1800 | 0.0469 | 0.8873 | 0.8487 | 0.8676 | 0.9941 |
0.0017 | 7.14 | 1900 | 0.0502 | 0.8434 | 0.8599 | 0.8516 | 0.9937 |
0.0015 | 7.52 | 2000 | 0.0526 | 0.8219 | 0.8529 | 0.8371 | 0.9928 |
0.0015 | 7.89 | 2100 | 0.0499 | 0.8236 | 0.8501 | 0.8367 | 0.9929 |
0.0015 | 8.27 | 2200 | 0.0415 | 0.8936 | 0.8473 | 0.8699 | 0.9944 |
0.0015 | 8.65 | 2300 | 0.0415 | 0.8579 | 0.8627 | 0.8603 | 0.9941 |
0.0015 | 9.02 | 2400 | 0.0432 | 0.8905 | 0.8543 | 0.8721 | 0.9947 |
0.0009 | 9.4 | 2500 | 0.0441 | 0.8682 | 0.8669 | 0.8676 | 0.9944 |
0.0009 | 9.77 | 2600 | 0.0434 | 0.8969 | 0.8529 | 0.8744 | 0.9946 |
0.0009 | 10.15 | 2700 | 0.0433 | 0.8943 | 0.8529 | 0.8731 | 0.9946 |
0.0009 | 10.53 | 2800 | 0.0442 | 0.8838 | 0.8627 | 0.8731 | 0.9945 |
0.0009 | 10.9 | 2900 | 0.0422 | 0.8703 | 0.8739 | 0.8721 | 0.9944 |
0.0005 | 11.28 | 3000 | 0.0464 | 0.8632 | 0.8571 | 0.8602 | 0.9939 |
0.0005 | 11.65 | 3100 | 0.0449 | 0.8584 | 0.8487 | 0.8535 | 0.9938 |
0.0005 | 12.03 | 3200 | 0.0395 | 0.8701 | 0.8627 | 0.8664 | 0.9943 |
0.0005 | 12.41 | 3300 | 0.0413 | 0.8874 | 0.8613 | 0.8742 | 0.9946 |
0.0005 | 12.78 | 3400 | 0.0448 | 0.9083 | 0.8739 | 0.8908 | 0.9950 |
0.0009 | 13.16 | 3500 | 0.0438 | 0.8550 | 0.8922 | 0.8732 | 0.9943 |
0.0009 | 13.53 | 3600 | 0.0364 | 0.8841 | 0.8655 | 0.8747 | 0.9947 |
0.0009 | 13.91 | 3700 | 0.0456 | 0.8741 | 0.8852 | 0.8796 | 0.9946 |
0.0009 | 14.29 | 3800 | 0.0461 | 0.8940 | 0.8627 | 0.8781 | 0.9947 |
0.0009 | 14.66 | 3900 | 0.0449 | 0.8830 | 0.8669 | 0.8749 | 0.9946 |
0.0003 | 15.04 | 4000 | 0.0491 | 0.8416 | 0.8782 | 0.8595 | 0.9938 |
0.0003 | 15.41 | 4100 | 0.0468 | 0.8827 | 0.8641 | 0.8733 | 0.9945 |
0.0003 | 15.79 | 4200 | 0.0508 | 0.8848 | 0.8389 | 0.8613 | 0.9940 |
0.0003 | 16.17 | 4300 | 0.0471 | 0.8878 | 0.8641 | 0.8758 | 0.9946 |
0.0003 | 16.54 | 4400 | 0.0459 | 0.8828 | 0.8866 | 0.8847 | 0.9949 |
0.0002 | 16.92 | 4500 | 0.0456 | 0.8830 | 0.8669 | 0.8749 | 0.9945 |
0.0002 | 17.29 | 4600 | 0.0465 | 0.8693 | 0.8291 | 0.8487 | 0.9938 |
0.0002 | 17.67 | 4700 | 0.0442 | 0.8603 | 0.8711 | 0.8657 | 0.9942 |
0.0002 | 18.05 | 4800 | 0.0454 | 0.8525 | 0.8824 | 0.8672 | 0.9943 |
0.0002 | 18.42 | 4900 | 0.0421 | 0.8922 | 0.8810 | 0.8865 | 0.9951 |
0.0004 | 18.8 | 5000 | 0.0418 | 0.8889 | 0.8627 | 0.8756 | 0.9945 |
0.0004 | 19.17 | 5100 | 0.0418 | 0.8773 | 0.8711 | 0.8742 | 0.9946 |
0.0004 | 19.55 | 5200 | 0.0415 | 0.8829 | 0.8768 | 0.8798 | 0.9948 |
0.0004 | 19.92 | 5300 | 0.0429 | 0.8790 | 0.8754 | 0.8772 | 0.9947 |
0.0004 | 20.3 | 5400 | 0.0411 | 0.8958 | 0.8669 | 0.8811 | 0.9950 |
0.0001 | 20.68 | 5500 | 0.0415 | 0.8848 | 0.8711 | 0.8779 | 0.9947 |
0.0001 | 21.05 | 5600 | 0.0418 | 0.8848 | 0.8711 | 0.8779 | 0.9947 |
0.0001 | 21.43 | 5700 | 0.0426 | 0.8794 | 0.8782 | 0.8788 | 0.9948 |
0.0001 | 21.8 | 5800 | 0.0434 | 0.8807 | 0.8894 | 0.8850 | 0.9950 |
0.0001 | 22.18 | 5900 | 0.0437 | 0.8786 | 0.8922 | 0.8853 | 0.9950 |
0.0001 | 22.56 | 6000 | 0.0436 | 0.8786 | 0.8922 | 0.8853 | 0.9950 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3