tamasheq-99-2
This model is a fine-tuned version of ad019el/tamasheq-99-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1325
- Wer: 0.8412
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.2316 | 4.62 | 300 | 2.8431 | 1.0147 |
| 2.0332 | 9.23 | 600 | 1.2104 | 0.8265 |
| 1.307 | 13.85 | 900 | 1.0923 | 0.8324 |
| 1.0941 | 18.46 | 1200 | 1.1327 | 0.8176 |
| 1.016 | 23.08 | 1500 | 1.1560 | 0.8235 |
| 0.9744 | 27.69 | 1800 | 1.1325 | 0.8412 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3