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: 0.9462
- Accuracy: 0.82
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: 0.0001
- 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 |
0.5455 |
1.0 |
57 |
0.7144 |
0.76 |
0.5342 |
2.0 |
114 |
0.8039 |
0.75 |
0.1636 |
3.0 |
171 |
0.6388 |
0.83 |
0.1868 |
4.0 |
228 |
0.6027 |
0.81 |
0.0643 |
5.0 |
285 |
0.6728 |
0.83 |
0.0418 |
6.0 |
342 |
0.6726 |
0.82 |
0.0925 |
7.0 |
399 |
0.9795 |
0.81 |
0.0047 |
8.0 |
456 |
1.0072 |
0.82 |
0.0296 |
9.0 |
513 |
0.9450 |
0.82 |
0.0031 |
10.0 |
570 |
0.9462 |
0.82 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3