test

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

• Loss: 0.6568
• Precision: 0.8876
• Recall: 0.9066
• F1: 0.8970
• Accuracy: 0.8601

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	0.6157	0.7621	0.8400	0.7991	0.8051
No log	2.67	200	0.4834	0.7915	0.8902	0.8380	0.8334
No log	4.0	300	0.4929	0.8484	0.8922	0.8697	0.8493
No log	5.33	400	0.5191	0.8746	0.9006	0.8874	0.8556
0.5561	6.67	500	0.5553	0.8671	0.9041	0.8852	0.8487
0.5561	8.0	600	0.5766	0.8723	0.9091	0.8903	0.8388
0.5561	9.33	700	0.6486	0.8816	0.8917	0.8866	0.8511
0.5561	10.67	800	0.6188	0.8861	0.9086	0.8972	0.8608
0.5561	12.0	900	0.6317	0.8890	0.9071	0.8980	0.8630
0.1298	13.33	1000	0.6568	0.8876	0.9066	0.8970	0.8601

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cpu
• Datasets 2.12.0
• Tokenizers 0.13.3