distil-ast-audioset-finetuned-gtzan
This model is a fine-tuned version of bookbot/distil-ast-audioset on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4629
- Accuracy: 0.89
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: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 1.3117 | 1.0 | 113 | 1.0134 | 0.65 |
| 0.5748 | 2.0 | 226 | 0.4728 | 0.91 |
| 0.4554 | 3.0 | 339 | 0.5475 | 0.88 |
| 0.1809 | 4.0 | 452 | 0.5119 | 0.88 |
| 0.0564 | 5.0 | 565 | 0.4898 | 0.88 |
| 0.0014 | 6.0 | 678 | 0.4669 | 0.87 |
| 0.0484 | 7.0 | 791 | 0.5143 | 0.88 |
| 0.0002 | 8.0 | 904 | 0.4885 | 0.88 |
| 0.0562 | 9.0 | 1017 | 0.4628 | 0.88 |
| 0.0002 | 10.0 | 1130 | 0.4629 | 0.89 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3