metadata
base_model: microsoft/trocr-base-stage1
tags:
- generated_from_trainer
model-index:
- name: TrOCR_0208
results: []
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