aci-yoruba-phase8
This model is a fine-tuned version of Awesome-x/aci-yoruba-phase8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5843
- Wer: 0.3410
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5396 | 3.2258 | 100 | 1.6619 | 0.3997 |
| 0.5710 | 6.4516 | 200 | 1.6049 | 0.3858 |
| 0.5009 | 9.6774 | 300 | 1.7193 | 0.3812 |
| 0.5580 | 12.9032 | 400 | 1.6232 | 0.3719 |
| 0.5314 | 16.1290 | 500 | 1.5857 | 0.3565 |
| 0.3366 | 19.3548 | 600 | 1.5526 | 0.3627 |
| 0.2690 | 22.5806 | 700 | 1.6499 | 0.3534 |
| 0.3401 | 25.8065 | 800 | 1.5899 | 0.3410 |
| 0.2160 | 29.0323 | 900 | 1.5843 | 0.3410 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2