<!-- 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. -->
Bol1.0
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: 0.5251
- Precision: 0.5769
- Recall: 0.5
- F1: 0.5357
- Accuracy: 0.9027
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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.61 | 100 | 2.0701 | 0.0476 | 0.0333 | 0.0392 | 0.3717 |
| No log | 3.23 | 200 | 1.5988 | 0.1852 | 0.1667 | 0.1754 | 0.6726 |
| No log | 4.84 | 300 | 1.2027 | 0.3846 | 0.3333 | 0.3571 | 0.6726 |
| No log | 6.45 | 400 | 0.9370 | 0.45 | 0.3 | 0.3600 | 0.8142 |
| 0.7987 | 8.06 | 500 | 0.7833 | 0.3333 | 0.2667 | 0.2963 | 0.8230 |
| 0.7987 | 9.68 | 600 | 0.6820 | 0.4348 | 0.3333 | 0.3774 | 0.8319 |
| 0.7987 | 11.29 | 700 | 0.6220 | 0.4074 | 0.3667 | 0.3860 | 0.8319 |
| 0.7987 | 12.9 | 800 | 0.5621 | 0.4815 | 0.4333 | 0.4561 | 0.8496 |
| 0.7987 | 14.52 | 900 | 0.5351 | 0.5 | 0.4667 | 0.4828 | 0.8938 |
| 0.2748 | 16.13 | 1000 | 0.5251 | 0.5769 | 0.5 | 0.5357 | 0.9027 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3
