donut-stnk-v5_3_1-left

This model is a fine-tuned version of squantumengine/donut-stnk-v4_left on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0991

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: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1438	1.0	134	0.0991
0.1109	2.0	268	0.1079
0.0413	3.0	402	0.1219
0.0423	4.0	536	0.1188

Framework versions

• Transformers 4.37.2
• Pytorch 1.13.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.1