wav2vec2-minds14-audio-classification
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6429
- Accuracy: 0.0912
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6536 | 0.9945 | 90 | 2.6776 | 0.0442 |
| 2.6478 | 2.0 | 181 | 2.6429 | 0.0912 |
| 2.6354 | 2.9945 | 271 | 2.6509 | 0.0691 |
| 2.648 | 4.0 | 362 | 2.6413 | 0.0414 |
| 2.6401 | 4.9724 | 450 | 2.6199 | 0.0773 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3