|
--- |
|
license: cc-by-nc-sa-4.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- cord-layoutlmv3 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv3-finetuned-cord_100 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: cord-layoutlmv3 |
|
type: cord-layoutlmv3 |
|
config: cord |
|
split: train |
|
args: cord |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9457652303120356 |
|
- name: Recall |
|
type: recall |
|
value: 0.9528443113772455 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9492915734526474 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9490662139219015 |
|
--- |
|
|
|
<!-- 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](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2296 |
|
- Precision: 0.9458 |
|
- Recall: 0.9528 |
|
- F1: 0.9493 |
|
- Accuracy: 0.9491 |
|
|
|
## 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 | 1.1659 | 0.6767 | 0.7552 | 0.7138 | 0.7738 | |
|
| 1.4723 | 3.12 | 500 | 0.6092 | 0.8320 | 0.8600 | 0.8458 | 0.8667 | |
|
| 1.4723 | 4.69 | 750 | 0.4107 | 0.8730 | 0.9004 | 0.8865 | 0.9045 | |
|
| 0.4246 | 6.25 | 1000 | 0.3370 | 0.9143 | 0.9259 | 0.9200 | 0.9270 | |
|
| 0.4246 | 7.81 | 1250 | 0.2909 | 0.9267 | 0.9371 | 0.9319 | 0.9372 | |
|
| 0.2225 | 9.38 | 1500 | 0.2571 | 0.9355 | 0.9439 | 0.9396 | 0.9414 | |
|
| 0.2225 | 10.94 | 1750 | 0.2547 | 0.9383 | 0.9454 | 0.9418 | 0.9431 | |
|
| 0.1514 | 12.5 | 2000 | 0.2412 | 0.9306 | 0.9431 | 0.9368 | 0.9435 | |
|
| 0.1514 | 14.06 | 2250 | 0.2329 | 0.9443 | 0.9513 | 0.9478 | 0.9478 | |
|
| 0.1168 | 15.62 | 2500 | 0.2296 | 0.9458 | 0.9528 | 0.9493 | 0.9491 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.10.2+cpu |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
