metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
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: 0.4454
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: 9.349509030319398e-05
- train_batch_size: 12
- 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: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.904 | 1.0 | 75 | 1.7595 |
| 1.2214 | 2.0 | 150 | 1.1147 |
| 0.862 | 3.0 | 225 | 0.7765 |
| 0.6679 | 4.0 | 300 | 0.6600 |
| 0.4188 | 5.0 | 375 | 0.4797 |
| 0.3369 | 6.0 | 450 | 0.5607 |
| 0.1591 | 7.0 | 525 | 0.4668 |
| 0.0591 | 8.0 | 600 | 0.4493 |
| 0.0718 | 9.0 | 675 | 0.4454 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3