wav2vec2-xlsr-breton-accent_clf
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0021
- Accuracy: 1.0
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0925 | 0.07 | 10 | 0.9869 | 0.5467 |
| 0.9016 | 0.13 | 20 | 0.5994 | 0.7200 |
| 0.5128 | 0.2 | 30 | 0.2064 | 1.0 |
| 0.2018 | 0.27 | 40 | 0.0560 | 1.0 |
| 0.1868 | 0.33 | 50 | 0.0220 | 1.0 |
| 0.032 | 0.4 | 60 | 0.0070 | 1.0 |
| 0.0551 | 0.47 | 70 | 0.0046 | 1.0 |
| 0.1755 | 0.53 | 80 | 0.0036 | 1.0 |
| 0.0053 | 0.6 | 90 | 0.0025 | 1.0 |
| 0.1213 | 0.67 | 100 | 0.0023 | 1.0 |
| 0.0847 | 0.73 | 110 | 0.0026 | 1.0 |
| 0.1274 | 0.8 | 120 | 0.0022 | 1.0 |
| 0.0421 | 0.87 | 130 | 0.0022 | 1.0 |
| 0.0685 | 0.93 | 140 | 0.0022 | 1.0 |
| 0.0294 | 1.0 | 150 | 0.0021 | 1.0 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3