dgx1_w2v2_base_teacher_student_distillation_mozilla_epochs_100_batch_16_concatenate_datasets
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 32.7379
- Wer: 0.9997
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: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 81.1182 | 7.35 | 500 | 28.1891 | 0.9996 |
| 62.3932 | 14.7 | 1000 | 29.1354 | 0.9996 |
| 58.4025 | 22.06 | 1500 | 30.3676 | 0.9997 |
| 55.061 | 29.41 | 2000 | 30.5188 | 0.9996 |
| 52.9559 | 36.76 | 2500 | 32.1812 | 0.9996 |
| 51.1888 | 44.12 | 3000 | 32.7379 | 0.9997 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2