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: 0.7058
- Accuracy: 0.99
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
---|---|---|---|---|
1.7675 | 1.0 | 112 | 1.8184 | 0.42 |
1.2504 | 2.0 | 225 | 1.3015 | 0.62 |
1.0353 | 3.0 | 337 | 0.9890 | 0.72 |
0.8318 | 4.0 | 450 | 0.8237 | 0.8 |
0.4429 | 5.0 | 562 | 0.8123 | 0.78 |
0.4286 | 6.0 | 675 | 0.6820 | 0.8 |
0.2553 | 7.0 | 787 | 0.7826 | 0.78 |
0.3022 | 8.0 | 900 | 0.6811 | 0.77 |
0.1889 | 9.0 | 1012 | 0.6761 | 0.8 |
0.1073 | 9.96 | 1120 | 0.7058 | 0.79 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.