<!-- 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. -->
marazzi2.0
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: 0.0477
- Precision: 0.8218
- Recall: 0.7386
- F1: 0.7780
- Accuracy: 0.9937
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 | 0.24 | 100 | 0.1429 | 0.5870 | 0.0882 | 0.1534 | 0.9809 |
No log | 0.47 | 200 | 0.1163 | 0.5870 | 0.0882 | 0.1534 | 0.9809 |
No log | 0.71 | 300 | 0.0919 | 0.5690 | 0.1078 | 0.1813 | 0.9815 |
No log | 0.95 | 400 | 0.0787 | 0.6304 | 0.2843 | 0.3919 | 0.9858 |
0.0844 | 1.18 | 500 | 0.0755 | 0.6522 | 0.4412 | 0.5263 | 0.9873 |
0.0844 | 1.42 | 600 | 0.0621 | 0.6533 | 0.4804 | 0.5537 | 0.9872 |
0.0844 | 1.66 | 700 | 0.0631 | 0.7415 | 0.4967 | 0.5949 | 0.9895 |
0.0844 | 1.9 | 800 | 0.0463 | 0.7764 | 0.6013 | 0.6777 | 0.9912 |
0.0844 | 2.13 | 900 | 0.0429 | 0.7821 | 0.6569 | 0.7140 | 0.9922 |
0.0265 | 2.37 | 1000 | 0.0421 | 0.7881 | 0.6928 | 0.7374 | 0.9929 |
0.0265 | 2.61 | 1100 | 0.0516 | 0.8050 | 0.6340 | 0.7093 | 0.9919 |
0.0265 | 2.84 | 1200 | 0.0474 | 0.7854 | 0.6340 | 0.7016 | 0.9917 |
0.0265 | 3.08 | 1300 | 0.0378 | 0.8134 | 0.7549 | 0.7831 | 0.9942 |
0.0265 | 3.32 | 1400 | 0.0374 | 0.8143 | 0.7451 | 0.7782 | 0.9938 |
0.0116 | 3.55 | 1500 | 0.0466 | 0.8213 | 0.7059 | 0.7592 | 0.9933 |
0.0116 | 3.79 | 1600 | 0.0444 | 0.8172 | 0.7157 | 0.7631 | 0.9933 |
0.0116 | 4.03 | 1700 | 0.0442 | 0.8218 | 0.7386 | 0.7780 | 0.9937 |
0.0116 | 4.27 | 1800 | 0.0473 | 0.8118 | 0.7190 | 0.7626 | 0.9933 |
0.0116 | 4.5 | 1900 | 0.0520 | 0.8030 | 0.7059 | 0.7513 | 0.9932 |
0.0074 | 4.74 | 2000 | 0.0476 | 0.8155 | 0.7222 | 0.7660 | 0.9936 |
0.0074 | 4.98 | 2100 | 0.0504 | 0.8038 | 0.6830 | 0.7385 | 0.9931 |
0.0074 | 5.21 | 2200 | 0.0475 | 0.8267 | 0.7484 | 0.7856 | 0.9937 |
0.0074 | 5.45 | 2300 | 0.0506 | 0.8081 | 0.7157 | 0.7591 | 0.9933 |
0.0074 | 5.69 | 2400 | 0.0508 | 0.8168 | 0.7288 | 0.7703 | 0.9936 |
0.005 | 5.92 | 2500 | 0.0477 | 0.8218 | 0.7386 | 0.7780 | 0.9937 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.2.2
- Tokenizers 0.13.2