w2v-bert-2.0-mongolian-colab-CV16.0
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0032
- Wer: 0.3466
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.3423 | 4.6929 | 300 | 1.1729 | 0.4725 |
| 0.8810 | 9.3780 | 600 | 0.9944 | 0.3638 |
| 0.8810 | 10.0 | 640 | 1.0032 | 0.3466 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.10.0+cu128
- Datasets 3.2.0
- Tokenizers 0.22.2