distilhubert-finetuned-gtzan-v3
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: 0.7165
- Accuracy: 0.87
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: 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0466 | 1.0 | 57 | 0.8249 | 0.79 |
0.0332 | 2.0 | 114 | 0.6831 | 0.86 |
0.0109 | 3.0 | 171 | 0.7949 | 0.82 |
0.006 | 4.0 | 228 | 0.7148 | 0.86 |
0.005 | 5.0 | 285 | 0.8089 | 0.84 |
0.0032 | 6.0 | 342 | 0.7125 | 0.85 |
0.0025 | 7.0 | 399 | 0.7267 | 0.87 |
0.0028 | 8.0 | 456 | 0.6992 | 0.87 |
0.0021 | 9.0 | 513 | 0.7227 | 0.86 |
0.0021 | 10.0 | 570 | 0.7165 | 0.87 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 4
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.