metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- cord-layoutlmv
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-cord_100
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: cord-layoutlmv
type: cord-layoutlmv
config: default
split: train
args: default
metrics:
- name: Precision
type: precision
value: 0.8426395939086294
- name: Recall
type: recall
value: 0.8877005347593583
- name: F1
type: f1
value: 0.8645833333333333
- name: Accuracy
type: accuracy
value: 0.9807981927710844
layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv dataset. It achieves the following results on the evaluation set:
- Loss: 0.1563
- Precision: 0.8426
- Recall: 0.8877
- F1: 0.8646
- Accuracy: 0.9808
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: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 27.78 | 250 | 0.2591 | 0.7179 | 0.7487 | 0.7330 | 0.9529 |
| 0.4762 | 55.56 | 500 | 0.1563 | 0.8426 | 0.8877 | 0.8646 | 0.9808 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2