layoutlmv3-finetuned-invoice

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: 0.2640
• 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: 800

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.56	100	2.1602	0.1927	0.1246	0.1514	0.4404
No log	3.12	200	1.3966	0.7963	0.7656	0.7806	0.7663
No log	4.69	300	0.8001	0.9852	0.9852	0.9852	0.9371
No log	6.25	400	0.4385	1.0	1.0	1.0	1.0
1.4289	7.81	500	0.2640	1.0	1.0	1.0	1.0
1.4289	9.38	600	0.1747	1.0	1.0	1.0	1.0
1.4289	10.94	700	0.1377	1.0	1.0	1.0	1.0
1.4289	12.5	800	0.1270	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0