LayoutLMv3_5_entities_filtred_23

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: 1.0226
• Precision: 0.625
• Recall: 0.6696
• F1: 0.6466
• Accuracy: 0.8338

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	8.33	100	1.1422	0.34	0.3036	0.3208	0.7406
No log	16.67	200	0.9707	0.5378	0.5714	0.5541	0.8010
No log	25.0	300	0.9193	0.5966	0.6339	0.6147	0.8212
No log	33.33	400	0.9467	0.6116	0.6607	0.6352	0.8262
0.3877	41.67	500	0.9490	0.616	0.6875	0.6498	0.8338
0.3877	50.0	600	0.9990	0.6610	0.6964	0.6783	0.8413
0.3877	58.33	700	1.0088	0.6446	0.6964	0.6695	0.8388
0.3877	66.67	800	1.0104	0.6098	0.6696	0.6383	0.8338
0.3877	75.0	900	1.0196	0.6198	0.6696	0.6438	0.8312
0.0192	83.33	1000	1.0226	0.625	0.6696	0.6466	0.8338

Framework versions

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