model-2024-06-04

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: 1.4164
• Precision: 0.6190
• Recall: 0.8387
• F1: 0.7123
• Accuracy: 0.7907

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	25.0	100	1.1670	0.5152	0.5484	0.5312	0.7442
No log	50.0	200	1.0020	0.5676	0.6774	0.6176	0.7791
No log	75.0	300	1.2200	0.6111	0.7097	0.6567	0.7791
No log	100.0	400	1.2976	0.6	0.7742	0.6761	0.7791
0.4049	125.0	500	1.3549	0.6098	0.8065	0.6944	0.7791
0.4049	150.0	600	1.2864	0.625	0.8065	0.7042	0.7907
0.4049	175.0	700	1.2832	0.6486	0.7742	0.7059	0.8023
0.4049	200.0	800	1.3822	0.625	0.8065	0.7042	0.7907
0.4049	225.0	900	1.3862	0.6098	0.8065	0.6944	0.7907
0.021	250.0	1000	1.4164	0.6190	0.8387	0.7123	0.7907

Framework versions

• Transformers 4.29.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.13.3