metadata
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
datasets:
- cord
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-cord
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: cord
type: cord
config: cord
split: test
args: cord
metrics:
- name: Precision
type: precision
value: 0.8983050847457628
- name: Recall
type: recall
value: 0.9124251497005988
- name: F1
type: f1
value: 0.9053100631266245
- name: Accuracy
type: accuracy
value: 0.9231748726655348
layoutlmv3-cord
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord dataset. It achieves the following results on the evaluation set:
- Loss: 0.3656
- Precision: 0.8983
- Recall: 0.9124
- F1: 0.9053
- Accuracy: 0.9232
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: 2e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.961 | 3.12 | 250 | 0.5549 | 0.8512 | 0.8690 | 0.86 | 0.8731 |
| 0.3714 | 6.25 | 500 | 0.3656 | 0.8983 | 0.9124 | 0.9053 | 0.9232 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.1
- Datasets 2.19.1
- Tokenizers 0.15.1