metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- data_registros_layoutv3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-registros_v3
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: data_registros_layoutv3
type: data_registros_layoutv3
config: default
split: test
args: default
metrics:
- name: Precision
type: precision
value: 0.8168168168168168
- name: Recall
type: recall
value: 0.8802588996763754
- name: F1
type: f1
value: 0.8473520249221185
- name: Accuracy
type: accuracy
value: 0.9726255293405929
layoutlmv3-finetuned-registros_v3
This model is a fine-tuned version of microsoft/layoutlmv3-base on the data_registros_layoutv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1730
- Precision: 0.8168
- Recall: 0.8803
- F1: 0.8474
- Accuracy: 0.9726
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- 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 | 10.87 | 250 | 0.4505 | 0.2272 | 0.2460 | 0.2362 | 0.8929 |
| 0.641 | 21.74 | 500 | 0.2718 | 0.6121 | 0.6715 | 0.6404 | 0.9374 |
| 0.641 | 32.61 | 750 | 0.1971 | 0.7854 | 0.8528 | 0.8177 | 0.9669 |
| 0.2206 | 43.48 | 1000 | 0.1730 | 0.8168 | 0.8803 | 0.8474 | 0.9726 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3