layoutlmv3-finetuned-FUNSD

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

• Loss: 0.6088
• Precision: 0.9024
• Recall: 0.9190
• F1: 0.9107
• Accuracy: 0.8544

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	1.33	100	0.6659	0.7835	0.8217	0.8021	0.7825
No log	2.67	200	0.5631	0.8229	0.8912	0.8557	0.7903
No log	4.0	300	0.4653	0.8470	0.8992	0.8723	0.8389
No log	5.33	400	0.5080	0.8526	0.9081	0.8795	0.8324
0.5612	6.67	500	0.5200	0.8733	0.9036	0.8882	0.8429
0.5612	8.0	600	0.5480	0.8878	0.9160	0.9017	0.8531
0.5612	9.33	700	0.5655	0.8894	0.9146	0.9018	0.8521
0.5612	10.67	800	0.5971	0.8943	0.9160	0.9050	0.8514
0.5612	12.0	900	0.5873	0.9022	0.9215	0.9118	0.8583
0.1425	13.33	1000	0.6088	0.9024	0.9190	0.9107	0.8544

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1