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: 0.2730
Precision: 0.9350
Recall: 0.9469
F1: 0.9409
Accuracy: 0.9491

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	4.17	250	1.0147	0.7119	0.7807	0.7447	0.7963
1.3916	8.33	500	0.5211	0.8428	0.8705	0.8564	0.8786
1.3916	12.5	750	0.3842	0.8961	0.9169	0.9064	0.9181
0.3265	16.67	1000	0.3158	0.9225	0.9349	0.9286	0.9393
0.3265	20.83	1250	0.2874	0.9162	0.9334	0.9247	0.9414
0.139	25.0	1500	0.2738	0.9255	0.9394	0.9324	0.9461
0.139	29.17	1750	0.2774	0.9354	0.9431	0.9392	0.9491
0.0798	33.33	2000	0.2695	0.9342	0.9461	0.9401	0.9508
0.0798	37.5	2250	0.2759	0.9356	0.9461	0.9408	0.9495
0.0592	41.67	2500	0.2730	0.9350	0.9469	0.9409	0.9491

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Hieu2911/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

Hieu2911/
layoutlmv3-finetuned-cord_100