metadata

library_name: transformers
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: layoutlmv3_document_classification
    results: []

layoutlmv3_document_classification

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: 1.0329
Accuracy: 0.8070
F1: 0.7806

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: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9913	0.5587	100	1.2412	0.7790	0.7459
0.9127	1.1173	200	1.2323	0.7804	0.7466
0.9307	1.6760	300	1.2167	0.7874	0.7550
0.8986	2.2346	400	1.2004	0.7888	0.7585
0.8744	2.7933	500	1.1751	0.7860	0.7572
0.7765	3.3520	600	1.1382	0.7874	0.7584
0.7695	3.9106	700	1.1275	0.7930	0.7642
0.7158	4.4693	800	1.0994	0.8056	0.7788
0.7015	5.0279	900	1.0844	0.7902	0.7619
0.6286	5.5866	1000	1.0828	0.8014	0.7728
0.693	6.1453	1100	1.0715	0.8042	0.7768
0.6291	6.7039	1200	1.0549	0.8070	0.7822
0.6422	7.2626	1300	1.0502	0.8168	0.7924
0.609	7.8212	1400	1.0368	0.8084	0.7828
0.6022	8.3799	1500	1.0407	0.8098	0.7824
0.5783	8.9385	1600	1.0343	0.8112	0.7843
0.5635	9.4972	1700	1.0329	0.8070	0.7806

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0