This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set:

Loss: 0.2033
Precision: 0.9458
Recall: 0.9536
F1: 0.9497
Accuracy: 0.9588

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: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.56	250	1.0015	0.7227	0.7822	0.7513	0.7963
1.3862	3.12	500	0.5334	0.8591	0.8765	0.8677	0.8837
1.3862	4.69	750	0.3689	0.8925	0.9072	0.8998	0.9164
0.3835	6.25	1000	0.2877	0.9281	0.9371	0.9326	0.9431
0.3835	7.81	1250	0.2506	0.9312	0.9424	0.9368	0.9452
0.2048	9.38	1500	0.2373	0.9480	0.9543	0.9511	0.9554
0.2048	10.94	1750	0.2184	0.9379	0.9491	0.9435	0.9542
0.1365	12.5	2000	0.2057	0.9393	0.9506	0.9449	0.9567
0.1365	14.06	2250	0.2024	0.9487	0.9543	0.9515	0.9576
0.1067	15.62	2500	0.2033	0.9458	0.9536	0.9497	0.9588

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

ayuff/layoutlmv3-finetuned-cord_100

layoutlmv3-finetuned-cord_100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ayuff/
layoutlmv3-finetuned-cord_100