LayoutLMv3_5_entities

This model is a fine-tuned version of microsoft/layoutlmv3-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1966
• Precision: 0.8679
• Recall: 0.8519
• F1: 0.8598
• Accuracy: 0.9772

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	2.56	100	0.1209	0.8602	0.7407	0.7960	0.9666
No log	5.13	200	0.1267	0.8365	0.8056	0.8208	0.9710
No log	7.69	300	0.1673	0.8830	0.7685	0.8218	0.9701
No log	10.26	400	0.1428	0.8911	0.8333	0.8612	0.9745
0.0687	12.82	500	0.1457	0.8636	0.8796	0.8716	0.9763
0.0687	15.38	600	0.1854	0.9062	0.8056	0.8529	0.9754
0.0687	17.95	700	0.1841	0.8835	0.8426	0.8626	0.9772
0.0687	20.51	800	0.1728	0.8505	0.8426	0.8465	0.9754
0.0687	23.08	900	0.1986	0.8505	0.8426	0.8465	0.9745
0.0038	25.64	1000	0.2087	0.8558	0.8241	0.8396	0.9737
0.0038	28.21	1100	0.1949	0.8545	0.8704	0.8624	0.9772
0.0038	30.77	1200	0.1954	0.8532	0.8611	0.8571	0.9763
0.0038	33.33	1300	0.1912	0.8624	0.8704	0.8664	0.9781
0.0038	35.9	1400	0.1926	0.8611	0.8611	0.8611	0.9772
0.0003	38.46	1500	0.1969	0.8692	0.8611	0.8651	0.9763
0.0003	41.03	1600	0.1979	0.8611	0.8611	0.8611	0.9772
0.0003	43.59	1700	0.1976	0.8598	0.8519	0.8558	0.9763
0.0003	46.15	1800	0.1979	0.8598	0.8519	0.8558	0.9763
0.0003	48.72	1900	0.1979	0.8679	0.8519	0.8598	0.9772
0.0001	51.28	2000	0.1966	0.8679	0.8519	0.8598	0.9772

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3