metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results: []
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: 0.6869
- Accuracy: 0.7889
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 |
|---|---|---|---|---|
| 1.9903 | 1.0 | 102 | 1.9462 | 0.5333 |
| 1.4477 | 2.0 | 204 | 1.3659 | 0.5111 |
| 1.082 | 3.0 | 306 | 1.1169 | 0.6444 |
| 0.967 | 4.0 | 408 | 0.8758 | 0.8111 |
| 0.4794 | 5.0 | 510 | 0.7574 | 0.8 |
| 0.4756 | 6.0 | 612 | 0.7637 | 0.7667 |
| 0.2381 | 7.0 | 714 | 0.7337 | 0.7889 |
| 0.2841 | 8.0 | 816 | 0.6546 | 0.8111 |
| 0.098 | 9.0 | 918 | 0.6680 | 0.8111 |
| 0.1294 | 10.0 | 1020 | 0.6869 | 0.7889 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3