|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: microsoft/layoutlmv3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv3-cordv2-binary |
|
results: [] |
|
--- |
|
|
|
<!-- 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-cordv2-binary |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0490 |
|
- Precision: 0.9529 |
|
- Recall: 0.9564 |
|
- F1: 0.9546 |
|
- Accuracy: 0.9941 |
|
|
|
## 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: 1500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 0.3333 | 100 | 0.0970 | 0.7517 | 0.8145 | 0.7818 | 0.9788 | |
|
| No log | 0.6667 | 200 | 0.0520 | 0.8715 | 0.9127 | 0.8917 | 0.9894 | |
|
| No log | 1.0 | 300 | 0.0630 | 0.9143 | 0.9309 | 0.9225 | 0.9919 | |
|
| No log | 1.3333 | 400 | 0.0459 | 0.925 | 0.9418 | 0.9333 | 0.9936 | |
|
| 0.0764 | 1.6667 | 500 | 0.0540 | 0.9457 | 0.9491 | 0.9474 | 0.9936 | |
|
| 0.0764 | 2.0 | 600 | 0.0395 | 0.9393 | 0.9564 | 0.9477 | 0.9945 | |
|
| 0.0764 | 2.3333 | 700 | 0.0455 | 0.9457 | 0.9491 | 0.9474 | 0.9945 | |
|
| 0.0764 | 2.6667 | 800 | 0.0490 | 0.9562 | 0.9527 | 0.9545 | 0.9941 | |
|
| 0.0764 | 3.0 | 900 | 0.0422 | 0.9395 | 0.96 | 0.9496 | 0.9958 | |
|
| 0.02 | 3.3333 | 1000 | 0.0524 | 0.9529 | 0.9564 | 0.9546 | 0.9941 | |
|
| 0.02 | 3.6667 | 1100 | 0.0466 | 0.9529 | 0.9564 | 0.9546 | 0.9941 | |
|
| 0.02 | 4.0 | 1200 | 0.0482 | 0.9568 | 0.9673 | 0.9620 | 0.9953 | |
|
| 0.02 | 4.3333 | 1300 | 0.0444 | 0.9529 | 0.9564 | 0.9546 | 0.9941 | |
|
| 0.02 | 4.6667 | 1400 | 0.0493 | 0.9529 | 0.9564 | 0.9546 | 0.9941 | |
|
| 0.0103 | 5.0 | 1500 | 0.0490 | 0.9529 | 0.9564 | 0.9546 | 0.9941 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.0.dev0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
