ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6230
- 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: 2
- eval_batch_size: 2
- 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 |
---|---|---|---|---|
2.1198 | 1.0 | 450 | 1.8429 | 0.47 |
0.0005 | 2.0 | 900 | 1.6282 | 0.71 |
0.3129 | 3.0 | 1350 | 1.0553 | 0.73 |
0.0225 | 4.0 | 1800 | 0.9422 | 0.82 |
0.0025 | 5.0 | 2250 | 0.6008 | 0.85 |
0.0 | 6.0 | 2700 | 0.7194 | 0.86 |
0.0 | 7.0 | 3150 | 0.6268 | 0.89 |
0.0 | 8.0 | 3600 | 0.6372 | 0.89 |
0.0 | 9.0 | 4050 | 0.6167 | 0.89 |
0.0 | 10.0 | 4500 | 0.6230 | 0.89 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.