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: 0.5771
- Accuracy: 0.84
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1148 | 0.11 | 5 | 0.5865 | 0.83 |
0.1411 | 0.22 | 10 | 0.5951 | 0.83 |
0.1014 | 0.33 | 15 | 0.5964 | 0.83 |
0.085 | 0.44 | 20 | 0.5901 | 0.83 |
0.1362 | 0.56 | 25 | 0.5894 | 0.82 |
0.0917 | 0.67 | 30 | 0.5862 | 0.83 |
0.097 | 0.78 | 35 | 0.5759 | 0.84 |
0.1206 | 0.89 | 40 | 0.5701 | 0.84 |
0.0909 | 1.0 | 45 | 0.5649 | 0.84 |
0.1269 | 1.11 | 50 | 0.5674 | 0.84 |
0.1117 | 1.22 | 55 | 0.5714 | 0.84 |
0.0791 | 1.33 | 60 | 0.5730 | 0.86 |
0.1016 | 1.44 | 65 | 0.5745 | 0.84 |
0.0712 | 1.56 | 70 | 0.5744 | 0.85 |
0.1212 | 1.67 | 75 | 0.5773 | 0.85 |
0.0724 | 1.78 | 80 | 0.5782 | 0.85 |
0.0831 | 1.89 | 85 | 0.5777 | 0.85 |
0.1429 | 2.0 | 90 | 0.5771 | 0.84 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 13
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for cryptoque/distilhubert-finetuned-gtzan
Base model
ntu-spml/distilhubert