donut-base3-sroie

This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.8022

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: 2e-05
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.2121	1.0	49	1.8428
0.9559	2.0	98	1.8141
1.1816	3.0	147	1.7794
1.7836	4.0	196	1.7935
0.9037	5.0	245	1.8022

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1