model-v2-2024-04-22

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: 0.7650
• Precision: 0.7666
• Recall: 0.7514
• F1: 0.7589
• Accuracy: 0.8762

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	2.22	100	1.2087	0.5724	0.2458	0.3439	0.7248
No log	4.44	200	0.7936	0.6667	0.5650	0.6116	0.82
No log	6.67	300	0.6730	0.7273	0.6780	0.7018	0.8543
No log	8.89	400	0.6465	0.7618	0.7316	0.7464	0.8724
0.7871	11.11	500	0.6474	0.7388	0.7429	0.7408	0.8657
0.7871	13.33	600	0.7060	0.7514	0.7429	0.7472	0.8724
0.7871	15.56	700	0.7356	0.7507	0.7401	0.7454	0.8705
0.7871	17.78	800	0.7483	0.7522	0.7373	0.7447	0.8695
0.7871	20.0	900	0.7577	0.7572	0.7401	0.7486	0.8724
0.1672	22.22	1000	0.7650	0.7666	0.7514	0.7589	0.8762

Framework versions

• Transformers 4.29.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.13.3