layoutlmv2-base-uncased_finetuned_passport

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9620

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
2.409	2.78	50	2.3859
1.959	5.56	100	2.1196
1.5433	8.33	150	1.7951
1.1748	11.11	200	1.5172
0.87	13.89	250	1.3040
0.6342	16.67	300	1.1525
0.4597	19.44	350	1.0532
0.3338	22.22	400	0.9942
0.2429	25.0	450	0.9632
0.1786	27.78	500	0.9509
0.1347	30.56	550	0.9486
0.143	33.33	600	0.9500
0.0976	36.11	650	0.9527
0.0874	38.89	700	0.9556
0.0808	41.67	750	0.9582
0.0746	44.44	800	0.9603
0.073	47.22	850	0.9615
0.0717	50.0	900	0.9620

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2