metadata
tags:
- generated_from_trainer
model-index:
- name: Bartpho_spelling_correction
results: []
Bartpho_spelling_correction
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0092
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0071 | 0.1111 | 2000 | 0.0097 |
| 0.0069 | 0.2222 | 4000 | 0.0099 |
| 0.006 | 0.3333 | 6000 | 0.0095 |
| 0.0053 | 0.4445 | 8000 | 0.0094 |
| 0.005 | 0.5556 | 10000 | 0.0095 |
| 0.0046 | 0.6667 | 12000 | 0.0094 |
| 0.0044 | 0.7778 | 14000 | 0.0093 |
| 0.0042 | 0.8889 | 16000 | 0.0092 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1