metadata
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned_invoices-4
results: []
layoutlmv3-finetuned_invoices-4
This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2901
- Precision: 0.4049
- Recall: 0.3689
- F1: 0.3331
- Accuracy: 0.8203
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 4 | 1.4449 | 0.2657 | 0.4611 | 0.2675 | 0.8203 |
No log | 2.0 | 8 | 1.4145 | 0.2610 | 0.4447 | 0.2472 | 0.7578 |
1.2588 | 3.0 | 12 | 1.3297 | 0.3043 | 0.3672 | 0.2979 | 0.8125 |
1.2588 | 4.0 | 16 | 1.2901 | 0.4049 | 0.3689 | 0.3331 | 0.8203 |
0.7717 | 5.0 | 20 | 1.2617 | 0.4048 | 0.3639 | 0.3279 | 0.7969 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1