donut-base-my_model_rapido_2_new_check_3

This model is a fine-tuned version of Manab/donut-base-my_model_rapido_2_new_check_2 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.3896

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

Training results

Training Loss	Epoch	Step	Validation Loss
2.8694	0.69	50	2.0758
2.2421	1.39	100	1.7321
1.6972	2.08	150	1.4280
1.5866	2.78	200	1.3896

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3