IOC

This model is a fine-tuned version of google/byt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3699
• Cer: 0.1666
• Cer Raw: 0.1865
• Exact Match: 0.1572

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Cer Raw	Exact Match
0.3578	3.5487	20000	0.3699	0.1666	0.1865	0.1572

Framework versions

• Transformers 4.57.6
• Pytorch 2.10.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.2