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: 0.5875
- 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: 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8128 | 1.0 | 113 | 1.8100 | 0.48 |
| 1.2095 | 2.0 | 226 | 1.2888 | 0.64 |
| 0.9621 | 3.0 | 339 | 0.9475 | 0.76 |
| 0.7657 | 4.0 | 452 | 0.8125 | 0.77 |
| 0.4597 | 5.0 | 565 | 0.6604 | 0.8 |
| 0.3496 | 6.0 | 678 | 0.6015 | 0.84 |
| 0.2164 | 7.0 | 791 | 0.6347 | 0.83 |
| 0.2563 | 8.0 | 904 | 0.6157 | 0.85 |
| 0.1157 | 9.0 | 1017 | 0.5635 | 0.84 |
| 0.2553 | 10.0 | 1130 | 0.5875 | 0.84 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.13.3
- Downloads last month
- 10
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.