<!-- 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. -->
layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2188
- Precision: 0.9430
- Recall: 0.9543
- F1: 0.9487
- Accuracy: 0.9580
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: 5
- eval_batch_size: 5
- 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 | 1.56 | 250 | 1.0024 | 0.7392 | 0.7957 | 0.7664 | 0.8060 |
| 1.3949 | 3.12 | 500 | 0.5684 | 0.8330 | 0.8660 | 0.8492 | 0.8727 |
| 1.3949 | 4.69 | 750 | 0.3929 | 0.8931 | 0.9072 | 0.9001 | 0.9160 |
| 0.3964 | 6.25 | 1000 | 0.3312 | 0.9236 | 0.9326 | 0.9281 | 0.9321 |
| 0.3964 | 7.81 | 1250 | 0.2754 | 0.9275 | 0.9386 | 0.9330 | 0.9410 |
| 0.216 | 9.38 | 1500 | 0.2447 | 0.9328 | 0.9454 | 0.9390 | 0.9478 |
| 0.216 | 10.94 | 1750 | 0.2467 | 0.9363 | 0.9461 | 0.9412 | 0.9478 |
| 0.1534 | 12.5 | 2000 | 0.2300 | 0.9436 | 0.9521 | 0.9478 | 0.9537 |
| 0.1534 | 14.06 | 2250 | 0.2155 | 0.9459 | 0.9558 | 0.9509 | 0.9597 |
| 0.119 | 15.62 | 2500 | 0.2188 | 0.9430 | 0.9543 | 0.9487 | 0.9580 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
