<!-- 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. -->
EASA10.0-base-2000-paddle
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: 0.0308
- Precision: 0.9762
- Recall: 0.9670
- F1: 0.9716
- Accuracy: 0.9963
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 | 0.88 | 100 | 0.1486 | 0.9387 | 0.9387 | 0.9387 | 0.9890 |
No log | 1.75 | 200 | 0.0354 | 0.9763 | 0.9717 | 0.9740 | 0.9963 |
No log | 2.63 | 300 | 0.0264 | 0.9811 | 0.9811 | 0.9811 | 0.9972 |
No log | 3.51 | 400 | 0.0281 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.1349 | 4.39 | 500 | 0.0292 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.1349 | 5.26 | 600 | 0.0289 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.1349 | 6.14 | 700 | 0.0292 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.1349 | 7.02 | 800 | 0.0279 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.1349 | 7.89 | 900 | 0.0279 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0147 | 8.77 | 1000 | 0.0288 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0147 | 9.65 | 1100 | 0.0292 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0147 | 10.53 | 1200 | 0.0305 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0147 | 11.4 | 1300 | 0.0296 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0147 | 12.28 | 1400 | 0.0300 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0084 | 13.16 | 1500 | 0.0309 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0084 | 14.04 | 1600 | 0.0299 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0084 | 14.91 | 1700 | 0.0307 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0084 | 15.79 | 1800 | 0.0304 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0084 | 16.67 | 1900 | 0.0310 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
0.0069 | 17.54 | 2000 | 0.0308 | 0.9762 | 0.9670 | 0.9716 | 0.9963 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3