<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
audio_classification
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6548
- Accuracy: 0.0796
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.97 | 7 | 2.6390 | 0.0354 |
| 2.6396 | 1.93 | 14 | 2.6548 | 0.0796 |
| 2.6336 | 2.9 | 21 | 2.6535 | 0.0265 |
| 2.6336 | 4.0 | 29 | 2.6682 | 0.0354 |
| 2.6235 | 4.97 | 36 | 2.6785 | 0.0442 |
| 2.6126 | 5.93 | 43 | 2.6889 | 0.0354 |
| 2.6126 | 6.9 | 50 | 2.6868 | 0.0177 |
| 2.6126 | 8.0 | 58 | 2.6888 | 0.0177 |
| 2.6085 | 8.97 | 65 | 2.6882 | 0.0265 |
| 2.6086 | 9.66 | 70 | 2.6887 | 0.0354 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
