distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6606
- Accuracy: 0.81
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 |
---|---|---|---|---|
1.9739 | 1.0 | 113 | 1.7836 | 0.61 |
1.3684 | 2.0 | 226 | 1.2751 | 0.66 |
1.0257 | 3.0 | 339 | 0.9829 | 0.73 |
0.8737 | 4.0 | 452 | 0.8757 | 0.76 |
0.7396 | 5.0 | 565 | 0.6852 | 0.79 |
0.3946 | 6.0 | 678 | 0.6898 | 0.78 |
0.5027 | 7.0 | 791 | 0.6836 | 0.8 |
0.2452 | 8.0 | 904 | 0.5940 | 0.82 |
0.259 | 9.0 | 1017 | 0.6510 | 0.8 |
0.1723 | 10.0 | 1130 | 0.6606 | 0.81 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 14
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.