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: 0.7072
- 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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 2.0694 | 1.0 | 57 | 2.0452 | 0.42 |
| 1.6795 | 2.0 | 114 | 1.5549 | 0.55 |
| 1.1745 | 3.0 | 171 | 1.2160 | 0.73 |
| 1.1069 | 4.0 | 228 | 1.0979 | 0.73 |
| 0.7755 | 5.0 | 285 | 0.9282 | 0.73 |
| 0.7111 | 6.0 | 342 | 0.8393 | 0.78 |
| 0.5609 | 7.0 | 399 | 0.7911 | 0.79 |
| 0.4891 | 8.0 | 456 | 0.7098 | 0.81 |
| 0.518 | 9.0 | 513 | 0.7079 | 0.8 |
| 0.5737 | 10.0 | 570 | 0.7072 | 0.81 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3