LayoutLMv3_5_entities_filtred_16

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: 0.3150
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

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	0.5249	1.0	1.0	1.0	1.0
No log	200.0	200	0.3782	1.0	1.0	1.0	1.0
No log	300.0	300	0.3620	1.0	1.0	1.0	1.0
No log	400.0	400	0.3469	1.0	1.0	1.0	1.0
0.1209	500.0	500	0.3474	1.0	1.0	1.0	1.0
0.1209	600.0	600	0.3127	1.0	1.0	1.0	1.0
0.1209	700.0	700	0.3182	1.0	1.0	1.0	1.0
0.1209	800.0	800	0.3144	1.0	1.0	1.0	1.0
0.1209	900.0	900	0.3122	1.0	1.0	1.0	1.0
0.0009	1000.0	1000	0.3184	1.0	1.0	1.0	1.0
0.0009	1100.0	1100	0.3125	1.0	1.0	1.0	1.0
0.0009	1200.0	1200	0.3159	1.0	1.0	1.0	1.0
0.0009	1300.0	1300	0.3247	1.0	1.0	1.0	1.0
0.0009	1400.0	1400	0.3188	1.0	1.0	1.0	1.0
0.0005	1500.0	1500	0.3401	1.0	1.0	1.0	1.0
0.0005	1600.0	1600	0.2962	1.0	1.0	1.0	1.0
0.0005	1700.0	1700	0.3104	1.0	1.0	1.0	1.0
0.0005	1800.0	1800	0.3141	1.0	1.0	1.0	1.0
0.0005	1900.0	1900	0.3140	1.0	1.0	1.0	1.0
0.0004	2000.0	2000	0.3150	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.29.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.13.3