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: 1.0498
Precision: 0.8132
Recall: 0.8376
F1: 0.8252
Accuracy: 0.8408

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	41.67	250	1.0301	0.7519	0.7964	0.7735	0.7954
1.0019	83.33	500	0.8414	0.7996	0.8331	0.8160	0.8396
1.0019	125.0	750	0.9117	0.8097	0.8376	0.8234	0.8417
0.0561	166.67	1000	0.9434	0.8097	0.8376	0.8234	0.8408
0.0561	208.33	1250	1.0014	0.8049	0.8338	0.8191	0.8404
0.0208	250.0	1500	1.0132	0.8081	0.8353	0.8215	0.8400
0.0208	291.67	1750	1.0279	0.8154	0.8398	0.8274	0.8417
0.0133	333.33	2000	1.0402	0.8119	0.8368	0.8242	0.8408
0.0133	375.0	2250	1.0495	0.8154	0.8398	0.8274	0.8417
0.0108	416.67	2500	1.0498	0.8132	0.8376	0.8252	0.8408

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3

shrestha-prabin/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

shrestha-prabin/
layoutlmv3-finetuned-cord_100