|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- mp-02/funsd |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv3-finetuned-funsd |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: mp-02/funsd |
|
type: mp-02/funsd |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9059871350816427 |
|
- name: Recall |
|
type: recall |
|
value: 0.9155 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9107187266849044 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8407211759301791 |
|
--- |
|
|
|
<!-- 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-funsd |
|
|
|
This model is a fine-tuned version of [layoutlmv3](https://huggingface.co/layoutlmv3) on the mp-02/funsd dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8860 |
|
- Precision: 0.9060 |
|
- Recall: 0.9155 |
|
- F1: 0.9107 |
|
- Accuracy: 0.8407 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 16 |
|
- 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 | 2.63 | 100 | 0.6111 | 0.7963 | 0.864 | 0.8288 | 0.7987 | |
|
| No log | 5.26 | 200 | 0.5861 | 0.8507 | 0.883 | 0.8665 | 0.8266 | |
|
| No log | 7.89 | 300 | 0.5856 | 0.8654 | 0.9005 | 0.8826 | 0.8426 | |
|
| No log | 10.53 | 400 | 0.6502 | 0.8801 | 0.8995 | 0.8897 | 0.8427 | |
|
| 0.4088 | 13.16 | 500 | 0.7679 | 0.8880 | 0.904 | 0.8959 | 0.8373 | |
|
| 0.4088 | 15.79 | 600 | 0.8371 | 0.8820 | 0.904 | 0.8928 | 0.8333 | |
|
| 0.4088 | 18.42 | 700 | 0.8320 | 0.8931 | 0.9145 | 0.9037 | 0.8336 | |
|
| 0.4088 | 21.05 | 800 | 0.8494 | 0.8969 | 0.9135 | 0.9051 | 0.8341 | |
|
| 0.4088 | 23.68 | 900 | 0.8700 | 0.9005 | 0.914 | 0.9072 | 0.8385 | |
|
| 0.061 | 26.32 | 1000 | 0.8860 | 0.9060 | 0.9155 | 0.9107 | 0.8407 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.12.5 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.13.2 |
|
- Tokenizers 0.10.1 |
|
|
