Vi-gec7
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1733
- Wer: 1.6393
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1167
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.7375 | 77.57 | 233 | 0.5493 | 144.2623 |
| 0.1833 | 155.29 | 466 | 0.2070 | 9.8361 |
| 0.0154 | 232.86 | 699 | 0.1677 | 1.6393 |
| 0.0061 | 310.57 | 932 | 0.1768 | 1.6393 |
| 0.0039 | 388.29 | 1165 | 0.1733 | 1.6393 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2