LayoutLMv3_5_entities_filtred_11

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: 2.2520
• Precision: 0.5
• Recall: 0.1818
• F1: 0.2667
• Accuracy: 0.7959

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	100.0	100	1.2300	0.4	0.1818	0.2500	0.7755
No log	200.0	200	1.6008	0.5	0.1818	0.2667	0.7959
No log	300.0	300	1.7235	0.5	0.1818	0.2667	0.7959
No log	400.0	400	1.8766	0.5	0.1818	0.2667	0.7959
0.0576	500.0	500	1.9181	0.5	0.1818	0.2667	0.7959
0.0576	600.0	600	1.9628	0.5	0.1818	0.2667	0.7959
0.0576	700.0	700	2.0079	0.5	0.1818	0.2667	0.7959
0.0576	800.0	800	2.0811	0.5	0.1818	0.2667	0.7959
0.0576	900.0	900	2.1047	0.5	0.1818	0.2667	0.7959
0.0004	1000.0	1000	2.1393	0.5	0.1818	0.2667	0.7959
0.0004	1100.0	1100	2.1754	0.5	0.1818	0.2667	0.7959
0.0004	1200.0	1200	2.1824	0.5	0.1818	0.2667	0.7959
0.0004	1300.0	1300	2.2005	0.5	0.1818	0.2667	0.7959
0.0004	1400.0	1400	2.1555	0.5	0.1818	0.2667	0.7959
0.0003	1500.0	1500	2.2045	0.5	0.1818	0.2667	0.7959
0.0003	1600.0	1600	2.2249	0.5	0.1818	0.2667	0.7959
0.0003	1700.0	1700	2.2358	0.5	0.1818	0.2667	0.7959
0.0003	1800.0	1800	2.2460	0.5	0.1818	0.2667	0.7959
0.0003	1900.0	1900	2.2514	0.5	0.1818	0.2667	0.7959
0.0002	2000.0	2000	2.2520	0.5	0.1818	0.2667	0.7959

Framework versions

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