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: 0.7078
- Accuracy: 0.84
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: 4e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.1881 | 1.0 | 57 | 2.0850 | 0.49 |
1.6641 | 2.0 | 114 | 1.5873 | 0.6 |
1.4182 | 3.0 | 171 | 1.3048 | 0.65 |
1.0799 | 4.0 | 228 | 1.1585 | 0.69 |
0.992 | 5.0 | 285 | 0.9368 | 0.78 |
0.8826 | 6.0 | 342 | 0.8714 | 0.82 |
0.8583 | 7.0 | 399 | 0.7905 | 0.83 |
0.6817 | 8.0 | 456 | 0.7487 | 0.82 |
0.6471 | 9.0 | 513 | 0.7416 | 0.82 |
0.6505 | 10.0 | 570 | 0.7078 | 0.84 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 256
Inference API (serverless) is not available, repository is disabled.
Model tree for sfedar/distilhubert-finetuned-gtzan
Base model
ntu-spml/distilhubert
Finetuned
this model