|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: microsoft/layoutlmv3-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- funsd-layoutlmv3 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: test |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: funsd-layoutlmv3 |
|
type: funsd-layoutlmv3 |
|
config: funsd |
|
split: test |
|
args: funsd |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9002457002457003 |
|
- name: Recall |
|
type: recall |
|
value: 0.9100844510680576 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9051383399209486 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8547486033519553 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# test |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the funsd-layoutlmv3 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6194 |
|
- Precision: 0.9002 |
|
- Recall: 0.9101 |
|
- F1: 0.9051 |
|
- Accuracy: 0.8547 |
|
|
|
## 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 | 1.33 | 100 | 0.6953 | 0.7761 | 0.8058 | 0.7906 | 0.7680 | |
|
| No log | 2.67 | 200 | 0.5117 | 0.8250 | 0.8808 | 0.8520 | 0.8290 | |
|
| No log | 4.0 | 300 | 0.5177 | 0.8397 | 0.8897 | 0.8640 | 0.8337 | |
|
| No log | 5.33 | 400 | 0.5165 | 0.8642 | 0.9106 | 0.8868 | 0.8509 | |
|
| 0.5653 | 6.67 | 500 | 0.5378 | 0.8735 | 0.9091 | 0.8909 | 0.8458 | |
|
| 0.5653 | 8.0 | 600 | 0.5698 | 0.8733 | 0.9111 | 0.8918 | 0.8482 | |
|
| 0.5653 | 9.33 | 700 | 0.5773 | 0.8934 | 0.9076 | 0.9004 | 0.8557 | |
|
| 0.5653 | 10.67 | 800 | 0.6073 | 0.8905 | 0.9006 | 0.8955 | 0.8520 | |
|
| 0.5653 | 12.0 | 900 | 0.6090 | 0.8940 | 0.9091 | 0.9015 | 0.8513 | |
|
| 0.1357 | 13.33 | 1000 | 0.6194 | 0.9002 | 0.9101 | 0.9051 | 0.8547 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
