metadata
tags:
- generated_from_trainer
model-index:
- name: khmer-trocr-base-printed-4045
results: []
khmer-trocr-base-printed-4045
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Cer: 2.3299
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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 2.7307 | 1.0 | 4342 | nan | 2.3299 |
| 0.0 | 2.0 | 8684 | nan | 2.3299 |
| 0.0 | 3.0 | 13026 | nan | 2.3299 |
| 0.0 | 4.0 | 17368 | nan | 2.3299 |
| 0.0 | 5.0 | 21710 | nan | 2.3299 |
| 0.0 | 6.0 | 26052 | nan | 2.3299 |
| 0.0 | 7.0 | 30394 | nan | 2.3299 |
| 0.0 | 8.0 | 34736 | nan | 2.3299 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1