donut_marriage_RT_539-135_301123

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

• Loss: 0.1088

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: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1504	1.0	270	0.5023
0.1444	2.0	540	0.2738
0.2701	3.0	810	0.1902
0.3624	4.0	1080	0.1666
0.1274	5.0	1350	0.1542
0.0369	6.0	1620	0.1537
0.0615	7.0	1890	0.1402
0.0271	8.0	2160	0.1293
0.0142	9.0	2430	0.1262
0.2481	10.0	2700	0.1255
0.002	11.0	2970	0.1260
0.0098	12.0	3240	0.1244
0.0045	13.0	3510	0.1214
0.0001	14.0	3780	0.1278
0.0011	15.0	4050	0.1227
0.0006	16.0	4320	0.1226
0.0003	17.0	4590	0.1212
0.0022	18.0	4860	0.1170
0.0002	19.0	5130	0.1141
0.0002	20.0	5400	0.1176
0.0004	21.0	5670	0.1142
0.0001	22.0	5940	0.1096
0.0003	23.0	6210	0.1090
0.0002	24.0	6480	0.1092
0.0001	25.0	6750	0.1088

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0