|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: microsoft/layoutlmv3-base |
|
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: test |
|
args: cord |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9516369047619048 |
|
- name: Recall |
|
type: recall |
|
value: 0.9573353293413174 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9544776119402986 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9630730050933786 |
|
--- |
|
|
|
<!-- 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: 0.2085 |
|
- Precision: 0.9516 |
|
- Recall: 0.9573 |
|
- F1: 0.9545 |
|
- Accuracy: 0.9631 |
|
|
|
## 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 | 1.0211 | 0.7533 | 0.8024 | 0.7771 | 0.8073 | |
|
| 1.3874 | 3.12 | 500 | 0.5352 | 0.8488 | 0.8698 | 0.8591 | 0.8778 | |
|
| 1.3874 | 4.69 | 750 | 0.3738 | 0.8865 | 0.9124 | 0.8993 | 0.9228 | |
|
| 0.3827 | 6.25 | 1000 | 0.2868 | 0.9253 | 0.9364 | 0.9308 | 0.9402 | |
|
| 0.3827 | 7.81 | 1250 | 0.2506 | 0.9289 | 0.9394 | 0.9341 | 0.9457 | |
|
| 0.2046 | 9.38 | 1500 | 0.2312 | 0.9427 | 0.9484 | 0.9455 | 0.9537 | |
|
| 0.2046 | 10.94 | 1750 | 0.2194 | 0.9450 | 0.9513 | 0.9482 | 0.9588 | |
|
| 0.1365 | 12.5 | 2000 | 0.2105 | 0.9495 | 0.9566 | 0.9530 | 0.9631 | |
|
| 0.1365 | 14.06 | 2250 | 0.2115 | 0.9509 | 0.9573 | 0.9541 | 0.9631 | |
|
| 0.1066 | 15.62 | 2500 | 0.2085 | 0.9516 | 0.9573 | 0.9545 | 0.9631 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 1.12.1+cu116 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.12.1 |
|
|
