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: 0.5358
- Accuracy: 0.88
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 |
---|---|---|---|---|
1.8758 | 1.0 | 57 | 1.7723 | 0.51 |
1.2291 | 2.0 | 114 | 1.1713 | 0.69 |
0.8029 | 3.0 | 171 | 0.8953 | 0.75 |
0.7314 | 4.0 | 228 | 0.8242 | 0.73 |
0.3424 | 5.0 | 285 | 0.6117 | 0.82 |
0.229 | 6.0 | 342 | 0.5272 | 0.82 |
0.1571 | 7.0 | 399 | 0.5470 | 0.87 |
0.0777 | 8.0 | 456 | 0.5393 | 0.88 |
0.0539 | 9.0 | 513 | 0.5087 | 0.88 |
0.0688 | 10.0 | 570 | 0.5358 | 0.88 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 27
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.