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: 0.8078
- Accuracy: 0.81
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: 12
- eval_batch_size: 12
- 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 |
|---|---|---|---|---|
| 2.1001 | 1.0 | 75 | 2.0810 | 0.45 |
| 1.563 | 2.0 | 150 | 1.5605 | 0.59 |
| 1.1348 | 3.0 | 225 | 1.1216 | 0.73 |
| 0.8687 | 4.0 | 300 | 0.9611 | 0.75 |
| 0.6107 | 5.0 | 375 | 0.9266 | 0.71 |
| 0.55 | 6.0 | 450 | 0.7138 | 0.81 |
| 0.3267 | 7.0 | 525 | 0.7121 | 0.84 |
| 0.3366 | 8.0 | 600 | 0.7213 | 0.81 |
| 0.2463 | 9.0 | 675 | 0.7768 | 0.79 |
| 0.1388 | 10.0 | 750 | 0.8165 | 0.79 |
| 0.1413 | 11.0 | 825 | 0.7713 | 0.82 |
| 0.0578 | 12.0 | 900 | 0.7860 | 0.8 |
| 0.0329 | 13.0 | 975 | 0.7821 | 0.82 |
| 0.0287 | 14.0 | 1050 | 0.8172 | 0.82 |
| 0.0277 | 15.0 | 1125 | 0.8078 | 0.81 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3