test

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2843
• Precision: 0.4118
• Recall: 0.8235
• F1: 0.5490
• Accuracy: 0.9485

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	0.6271	0.1864	0.6471	0.2895	0.8757
No log	16.67	200	0.1736	0.52	0.7647	0.6190	0.9734
No log	25.0	300	0.1302	0.5714	0.9412	0.7111	0.9734
No log	33.33	400	0.2835	0.5333	0.9412	0.6809	0.9556
0.287	41.67	500	0.0924	0.4828	0.8235	0.6087	0.9805
0.287	50.0	600	0.2594	0.4412	0.8824	0.5882	0.9485
0.287	58.33	700	0.3172	0.4412	0.8824	0.5882	0.9467
0.287	66.67	800	0.2447	0.4545	0.8824	0.6	0.9520
0.287	75.0	900	0.2941	0.4118	0.8235	0.5490	0.9485
0.013	83.33	1000	0.2843	0.4118	0.8235	0.5490	0.9485

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3