|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- sroie |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: layoutlmv3-finetuned-sroie |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: sroie |
|
type: sroie |
|
args: sroie |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9362154500354358 |
|
- name: Recall |
|
type: recall |
|
value: 0.9517291066282421 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9439085387638442 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9951776838044365 |
|
--- |
|
|
|
<!-- 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-sroie |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the sroie dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0288 |
|
- Precision: 0.9362 |
|
- Recall: 0.9517 |
|
- F1: 0.9439 |
|
- Accuracy: 0.9952 |
|
|
|
## 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: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 0.32 | 100 | 0.1063 | 0.6851 | 0.6599 | 0.6723 | 0.9739 | |
|
| No log | 0.64 | 200 | 0.0583 | 0.7849 | 0.7860 | 0.7855 | 0.9843 | |
|
| No log | 0.96 | 300 | 0.0475 | 0.8463 | 0.8610 | 0.8536 | 0.9884 | |
|
| No log | 1.28 | 400 | 0.0437 | 0.8566 | 0.8739 | 0.8652 | 0.9894 | |
|
| 0.1215 | 1.6 | 500 | 0.0424 | 0.8616 | 0.9063 | 0.8834 | 0.9895 | |
|
| 0.1215 | 1.92 | 600 | 0.0332 | 0.8702 | 0.9323 | 0.9002 | 0.9924 | |
|
| 0.1215 | 2.24 | 700 | 0.0318 | 0.8979 | 0.9373 | 0.9172 | 0.9932 | |
|
| 0.1215 | 2.56 | 800 | 0.0316 | 0.9092 | 0.9445 | 0.9265 | 0.9936 | |
|
| 0.1215 | 2.88 | 900 | 0.0295 | 0.8982 | 0.9467 | 0.9218 | 0.9937 | |
|
| 0.0286 | 3.19 | 1000 | 0.0329 | 0.8685 | 0.9517 | 0.9082 | 0.9930 | |
|
| 0.0286 | 3.51 | 1100 | 0.0289 | 0.9298 | 0.9352 | 0.9325 | 0.9945 | |
|
| 0.0286 | 3.83 | 1200 | 0.0287 | 0.9202 | 0.9474 | 0.9336 | 0.9946 | |
|
| 0.0286 | 4.15 | 1300 | 0.0301 | 0.9174 | 0.9524 | 0.9346 | 0.9947 | |
|
| 0.0286 | 4.47 | 1400 | 0.0268 | 0.9212 | 0.9431 | 0.9320 | 0.9946 | |
|
| 0.017 | 4.79 | 1500 | 0.0307 | 0.9236 | 0.9488 | 0.9360 | 0.9944 | |
|
| 0.017 | 5.11 | 1600 | 0.0286 | 0.9335 | 0.9503 | 0.9418 | 0.9951 | |
|
| 0.017 | 5.43 | 1700 | 0.0287 | 0.9284 | 0.9618 | 0.9448 | 0.9951 | |
|
| 0.017 | 5.75 | 1800 | 0.0278 | 0.9334 | 0.9496 | 0.9414 | 0.9952 | |
|
| 0.017 | 6.07 | 1900 | 0.0289 | 0.9337 | 0.9539 | 0.9437 | 0.9952 | |
|
| 0.0111 | 6.39 | 2000 | 0.0288 | 0.9362 | 0.9517 | 0.9439 | 0.9952 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.0.dev0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.2.2 |
|
- Tokenizers 0.12.1 |
|
|
