LayoutLMv3_5_entities_filtred_28

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: 0.4741
• Precision: 0.7687
• Recall: 0.7578
• F1: 0.7632
• Accuracy: 0.8952

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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.14	100	1.0872	0.5252	0.2365	0.3262	0.7533
No log	2.27	200	0.7878	0.6234	0.4901	0.5488	0.8279
No log	3.41	300	0.6203	0.6555	0.6091	0.6314	0.8564
No log	4.55	400	0.5551	0.6928	0.6771	0.6848	0.8706
0.8634	5.68	500	0.5183	0.7226	0.6898	0.7058	0.8758
0.8634	6.82	600	0.5000	0.7386	0.7323	0.7354	0.8849
0.8634	7.95	700	0.4561	0.7518	0.7422	0.7470	0.8922
0.8634	9.09	800	0.4499	0.7697	0.7620	0.7658	0.8995
0.8634	10.23	900	0.4759	0.7629	0.7521	0.7575	0.8956
0.2807	11.36	1000	0.4741	0.7687	0.7578	0.7632	0.8952

Framework versions

• Transformers 4.29.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.13.3