khmer-trocr-base-printed

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

• Loss: 0.0478
• Cer: 0.4899

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: 4e-05
• train_batch_size: 8
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0601	0.4876	1000	0.0793	0.5256
0.0467	0.9751	2000	0.0706	0.5147
0.0242	1.4627	3000	0.0658	0.5036
0.0206	1.9503	4000	0.0587	0.5083
0.0151	2.4378	5000	0.0610	0.5104
0.0127	2.9254	6000	0.0521	0.4912
0.0059	3.4130	7000	0.0497	0.4937
0.0045	3.9005	8000	0.0478	0.4899

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1