layoutlmv2-base-uncased_finetuned_docvqa

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on the block2ds dataset. It achieves the following results on the evaluation set:

• Loss: 1.9118

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
4.2361	2.17	50	3.6262
3.5312	4.35	100	3.2548
3.1763	6.52	150	2.9094
2.857	8.7	200	2.6181
2.5854	10.87	250	2.3748
2.365	13.04	300	2.1822
2.1976	15.22	350	2.0389
2.0745	17.39	400	1.9492
2.0104	19.57	450	1.9118

Framework versions

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