my_trocr

This model is a fine-tuned version of microsoft/trocr-small-printed on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3975
• Cer: 0.0185

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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	Cer
13.6251	1.0	82	0.5465	0.1229
13.6251	2.0	164	0.4406	0.0274
13.6251	3.0	246	0.3975	0.0185

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3