model-v2-18-04-2024

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: 1.2634
• Precision: 0.6613
• Recall: 0.6949
• F1: 0.6777
• Accuracy: 0.8140

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	1.1672	0.53	0.4492	0.4862	0.7228
No log	16.67	200	0.9729	0.6491	0.6271	0.6379	0.7895
No log	25.0	300	1.0899	0.6552	0.6441	0.6496	0.8
No log	33.33	400	1.0176	0.6532	0.6864	0.6694	0.8140
0.5362	41.67	500	1.1735	0.6325	0.6271	0.6298	0.7965
0.5362	50.0	600	1.1586	0.664	0.7034	0.6831	0.8211
0.5362	58.33	700	1.2151	0.672	0.7119	0.6914	0.8246
0.5362	66.67	800	1.2713	0.6587	0.7034	0.6803	0.8140
0.5362	75.0	900	1.2688	0.664	0.7034	0.6831	0.8175
0.0216	83.33	1000	1.2634	0.6613	0.6949	0.6777	0.8140

Framework versions

• Transformers 4.29.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3