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: 0.3548
- Accuracy: 0.9
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.9569 | 1.0 | 112 | 0.6467 | 0.77 |
0.5441 | 2.0 | 225 | 0.5895 | 0.8 |
0.4536 | 3.0 | 337 | 0.4070 | 0.82 |
0.1096 | 4.0 | 450 | 0.3812 | 0.89 |
0.0116 | 5.0 | 562 | 1.1661 | 0.78 |
0.0165 | 6.0 | 675 | 0.4822 | 0.91 |
0.1206 | 7.0 | 787 | 0.5000 | 0.88 |
0.0001 | 8.0 | 900 | 0.4074 | 0.89 |
0.2068 | 9.0 | 1012 | 0.4769 | 0.87 |
0.0001 | 10.0 | 1125 | 0.3743 | 0.89 |
0.0001 | 11.0 | 1237 | 0.3673 | 0.89 |
0.0001 | 12.0 | 1350 | 0.3952 | 0.91 |
0.0001 | 13.0 | 1462 | 0.3710 | 0.91 |
0.0001 | 14.0 | 1575 | 0.3460 | 0.92 |
0.0 | 15.0 | 1687 | 0.3481 | 0.92 |
0.0 | 16.0 | 1800 | 0.3473 | 0.92 |
0.0 | 17.0 | 1912 | 0.3491 | 0.91 |
0.0 | 18.0 | 2025 | 0.3507 | 0.91 |
0.0 | 19.0 | 2137 | 0.3548 | 0.9 |
0.0001 | 19.91 | 2240 | 0.3548 | 0.9 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 80
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.