LayoutLMv3_5_entities_filtred_13

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

• Loss: 0.5851
• Precision: 0.875
• Recall: 0.7778
• F1: 0.8235
• Accuracy: 0.9540

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	20.0	100	0.3668	0.7917	0.7037	0.7451	0.9425
No log	40.0	200	0.5200	0.8182	0.6667	0.7347	0.9368
No log	60.0	300	0.5244	0.8333	0.7407	0.7843	0.9483
No log	80.0	400	0.5471	0.8261	0.7037	0.76	0.9425
0.0818	100.0	500	0.5854	0.8261	0.7037	0.76	0.9425
0.0818	120.0	600	0.5497	0.875	0.7778	0.8235	0.9540
0.0818	140.0	700	0.5480	0.875	0.7778	0.8235	0.9540
0.0818	160.0	800	0.5709	0.8696	0.7407	0.8000	0.9483
0.0818	180.0	900	0.5587	0.875	0.7778	0.8235	0.9540
0.0007	200.0	1000	0.5676	0.875	0.7778	0.8235	0.9540
0.0007	220.0	1100	0.5674	0.875	0.7778	0.8235	0.9540
0.0007	240.0	1200	0.5688	0.875	0.7778	0.8235	0.9540
0.0007	260.0	1300	0.5733	0.875	0.7778	0.8235	0.9540
0.0007	280.0	1400	0.5786	0.875	0.7778	0.8235	0.9540
0.0003	300.0	1500	0.5767	0.875	0.7778	0.8235	0.9540
0.0003	320.0	1600	0.5766	0.875	0.7778	0.8235	0.9540
0.0003	340.0	1700	0.5813	0.875	0.7778	0.8235	0.9540
0.0003	360.0	1800	0.5831	0.875	0.7778	0.8235	0.9540
0.0003	380.0	1900	0.5851	0.875	0.7778	0.8235	0.9540
0.0003	400.0	2000	0.5851	0.875	0.7778	0.8235	0.9540

Framework versions

• Transformers 4.29.2
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.13.3