TrOCR_0208

This model is a fine-tuned version of microsoft/trocr-base-stage1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8231
  • Cer: 0.0842

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
1.8364 0.68 200 1.5199 0.1926
1.3561 1.37 400 1.4427 0.1711
0.382 2.05 600 0.9931 0.1115
0.343 2.74 800 0.8231 0.0842

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
18
Safetensors
Model size
385M params
Tensor type
F32
·
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for yoon1000/TrOCR_0208

Finetuned
(15)
this model