metadata
tags:
- generated_from_trainer
- image-to-text
model-index:
- name: ArOCRv4
results: []
ArOCRv4
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5811
- Cer: 0.1249
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.103 | 1.18 | 1000 | 8.0852 | 11.5974 |
| 1.2535 | 2.36 | 2000 | 2.0400 | 0.4904 |
| 0.5682 | 3.55 | 3000 | 1.9336 | 0.2145 |
| 0.3038 | 4.73 | 4000 | 1.5811 | 0.1249 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.9.1
- Datasets 2.1.0
- Tokenizers 0.11.6