WMACv2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2606
- Wer: 41.3106
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: 2.5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: cosine
- lr_scheduler_warmup_steps: 650
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5465 | 0.4757 | 1000 | 0.4199 | 54.1280 |
| 1.0508 | 0.9514 | 2000 | 0.2911 | 43.9422 |
| 0.6641 | 1.4267 | 3000 | 0.2649 | 44.7884 |
| 0.4569 | 1.9024 | 4000 | 0.2369 | 41.4448 |
| 0.2753 | 2.3777 | 5000 | 0.2606 | 41.3106 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2
- Downloads last month
- 111