dd-turbo-q
This model is a fine-tuned version of Akbarkhon/dd-turbo-g on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0879
- Wer: 8.4041
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1741 | 0.0319 | 1000 | 0.1419 | 12.6098 |
| 0.1299 | 0.0638 | 2000 | 0.1273 | 11.1191 |
| 0.1227 | 0.0957 | 3000 | 0.1075 | 9.9237 |
| 0.1071 | 0.1277 | 4000 | 0.0940 | 9.0883 |
| 0.0949 | 0.1596 | 5000 | 0.0879 | 8.4041 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 3