test_model

This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:

• Loss: 0.0114
• Precision: 0.9343
• Recall: 0.9697
• F1: 0.9517
• Accuracy: 0.9976

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	0.0292	0.8732	0.9394	0.9051	0.9928
No log	16.67	200	0.0110	0.9343	0.9697	0.9517	0.9976
No log	25.0	300	0.0130	0.9209	0.9697	0.9446	0.9971
No log	33.33	400	0.0110	0.9412	0.9697	0.9552	0.9981
0.0466	41.67	500	0.0114	0.9275	0.9697	0.9481	0.9976
0.0466	50.0	600	0.0117	0.9275	0.9697	0.9481	0.9976
0.0466	58.33	700	0.0114	0.9275	0.9697	0.9481	0.9976
0.0466	66.67	800	0.0114	0.9343	0.9697	0.9517	0.9976
0.0466	75.0	900	0.0115	0.9343	0.9697	0.9517	0.9976
0.0006	83.33	1000	0.0114	0.9343	0.9697	0.9517	0.9976

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.2.2
• Tokenizers 0.13.3