layoutlmv3-finetuned-invoice

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

• Loss: 0.0048
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.0	100	0.0785	0.9	0.9128	0.9063	0.9895
No log	4.0	200	0.0226	0.972	0.9858	0.9789	0.9971
No log	6.0	300	0.0167	0.972	0.9858	0.9789	0.9971
No log	8.0	400	0.0119	0.972	0.9858	0.9789	0.9971
0.1245	10.0	500	0.0048	1.0	1.0	1.0	1.0
0.1245	12.0	600	0.0034	1.0	1.0	1.0	1.0
0.1245	14.0	700	0.0026	1.0	1.0	1.0	1.0
0.1245	16.0	800	0.0022	1.0	1.0	1.0	1.0
0.1245	18.0	900	0.0019	1.0	1.0	1.0	1.0
0.0051	20.0	1000	0.0017	1.0	1.0	1.0	1.0
0.0051	22.0	1100	0.0015	1.0	1.0	1.0	1.0
0.0051	24.0	1200	0.0014	1.0	1.0	1.0	1.0
0.0051	26.0	1300	0.0013	1.0	1.0	1.0	1.0
0.0051	28.0	1400	0.0012	1.0	1.0	1.0	1.0
0.0026	30.0	1500	0.0011	1.0	1.0	1.0	1.0
0.0026	32.0	1600	0.0011	1.0	1.0	1.0	1.0
0.0026	34.0	1700	0.0010	1.0	1.0	1.0	1.0
0.0026	36.0	1800	0.0010	1.0	1.0	1.0	1.0
0.0026	38.0	1900	0.0010	1.0	1.0	1.0	1.0
0.0019	40.0	2000	0.0010	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2