<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilhubert-finetuned-gtzan-bs-4-fp16-false
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: 0.7602
- Accuracy: 0.85
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: 4
- eval_batch_size: 4
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8665 | 1.0 | 225 | 1.7960 | 0.45 |
| 1.1255 | 2.0 | 450 | 1.1399 | 0.71 |
| 0.9522 | 3.0 | 675 | 0.8221 | 0.73 |
| 0.773 | 4.0 | 900 | 0.7152 | 0.73 |
| 0.1673 | 5.0 | 1125 | 0.5379 | 0.84 |
| 0.0427 | 6.0 | 1350 | 0.6805 | 0.83 |
| 0.1291 | 7.0 | 1575 | 0.6063 | 0.85 |
| 0.0115 | 8.0 | 1800 | 0.6633 | 0.84 |
| 0.0042 | 9.0 | 2025 | 0.6486 | 0.86 |
| 0.0347 | 10.0 | 2250 | 0.7214 | 0.86 |
| 0.0036 | 11.0 | 2475 | 0.8731 | 0.83 |
| 0.0018 | 12.0 | 2700 | 0.7301 | 0.85 |
| 0.0015 | 13.0 | 2925 | 0.7699 | 0.85 |
| 0.0016 | 14.0 | 3150 | 0.7569 | 0.85 |
| 0.0014 | 15.0 | 3375 | 0.7602 | 0.85 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
