|
--- |
|
library_name: transformers |
|
base_model: layoutlmv3 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- mp-02/cord |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv3-finetuned-cord |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: mp-02/cord |
|
type: mp-02/cord |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9609494640122511 |
|
- name: Recall |
|
type: recall |
|
value: 0.9743788819875776 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9676175790285273 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9690152801358234 |
|
--- |
|
|
|
<!-- 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 |
|
|
|
This model is a fine-tuned version of [layoutlmv3](https://huggingface.co/layoutlmv3) on the mp-02/cord dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1800 |
|
- Precision: 0.9609 |
|
- Recall: 0.9744 |
|
- F1: 0.9676 |
|
- Accuracy: 0.9690 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 10 |
|
- eval_batch_size: 10 |
|
- 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 | 1.25 | 100 | 0.5802 | 0.8140 | 0.8696 | 0.8408 | 0.8574 | |
|
| No log | 2.5 | 200 | 0.2946 | 0.9013 | 0.9433 | 0.9219 | 0.9329 | |
|
| No log | 3.75 | 300 | 0.2259 | 0.9409 | 0.9635 | 0.9521 | 0.9571 | |
|
| No log | 5.0 | 400 | 0.2496 | 0.9376 | 0.9565 | 0.9470 | 0.9482 | |
|
| 0.4497 | 6.25 | 500 | 0.2174 | 0.9399 | 0.9596 | 0.9497 | 0.9546 | |
|
| 0.4497 | 7.5 | 600 | 0.1812 | 0.9535 | 0.9713 | 0.9623 | 0.9648 | |
|
| 0.4497 | 8.75 | 700 | 0.1699 | 0.9587 | 0.9720 | 0.9653 | 0.9699 | |
|
| 0.4497 | 10.0 | 800 | 0.1810 | 0.9625 | 0.9752 | 0.9688 | 0.9690 | |
|
| 0.4497 | 11.25 | 900 | 0.1789 | 0.9647 | 0.9767 | 0.9707 | 0.9694 | |
|
| 0.0416 | 12.5 | 1000 | 0.1800 | 0.9609 | 0.9744 | 0.9676 | 0.9690 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu118 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
