LayoutLMv3_5_entities_filtred_12

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: 0.1405
• Precision: 0.9474
• Recall: 0.9474
• F1: 0.9474
• Accuracy: 0.9856

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	50.0	100	0.1150	0.9	0.9474	0.9231	0.9784
No log	100.0	200	0.1241	0.9474	0.9474	0.9474	0.9856
No log	150.0	300	0.1328	0.9474	0.9474	0.9474	0.9856
No log	200.0	400	0.1954	0.9	0.9474	0.9231	0.9784
0.0457	250.0	500	0.1845	0.8571	0.9474	0.9	0.9712
0.0457	300.0	600	0.0843	1.0	0.9474	0.9730	0.9928
0.0457	350.0	700	0.0896	1.0	0.9474	0.9730	0.9928
0.0457	400.0	800	0.0947	0.9474	0.9474	0.9474	0.9856
0.0457	450.0	900	0.1026	0.9474	0.9474	0.9474	0.9856
0.0005	500.0	1000	0.1118	0.9474	0.9474	0.9474	0.9856
0.0005	550.0	1100	0.1196	0.9474	0.9474	0.9474	0.9856
0.0005	600.0	1200	0.1257	0.9474	0.9474	0.9474	0.9856
0.0005	650.0	1300	0.1297	0.9474	0.9474	0.9474	0.9856
0.0005	700.0	1400	0.1334	0.9474	0.9474	0.9474	0.9856
0.0002	750.0	1500	0.1360	0.9474	0.9474	0.9474	0.9856
0.0002	800.0	1600	0.1381	0.9474	0.9474	0.9474	0.9856
0.0002	850.0	1700	0.1389	0.9474	0.9474	0.9474	0.9856
0.0002	900.0	1800	0.1396	0.9474	0.9474	0.9474	0.9856
0.0002	950.0	1900	0.1402	0.9474	0.9474	0.9474	0.9856
0.0002	1000.0	2000	0.1405	0.9474	0.9474	0.9474	0.9856

Framework versions

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