mms-1b-dhivehi-v2
This model is a fine-tuned version of Serialtechlab/mms-1b-dhivehi-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3861
- Wer: 0.5432
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: 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6271 | 0.8292 | 500 | 0.3889 | 0.5458 |
| 0.5948 | 1.6584 | 1000 | 0.3871 | 0.5438 |
| 0.5946 | 2.4876 | 1500 | 0.3861 | 0.5432 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- -