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: 0.5663
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.9532 | 1.0 | 113 | 1.7671 | 0.43 |
1.2976 | 2.0 | 226 | 1.1920 | 0.6 |
1.062 | 3.0 | 339 | 0.8834 | 0.73 |
0.8596 | 4.0 | 452 | 0.7682 | 0.75 |
0.5926 | 5.0 | 565 | 0.6428 | 0.82 |
0.406 | 6.0 | 678 | 0.6709 | 0.78 |
0.4717 | 7.0 | 791 | 0.5713 | 0.82 |
0.1326 | 8.0 | 904 | 0.5567 | 0.82 |
0.3459 | 9.0 | 1017 | 0.5477 | 0.83 |
0.091 | 10.0 | 1130 | 0.5663 | 0.81 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 24
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Suhaanthvv/distilhubert-finetuned-gtzan
Base model
ntu-spml/distilhubert