distilhubert-finetuned-(gaurav)-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: 0.5492
- Accuracy: 0.82
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: 8
- 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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.9927 | 1.0 | 113 | 1.9567 | 0.44 |
1.2473 | 2.0 | 226 | 1.3288 | 0.56 |
1.1117 | 3.0 | 339 | 0.9260 | 0.75 |
0.6962 | 4.0 | 452 | 0.9979 | 0.71 |
0.6209 | 5.0 | 565 | 0.6911 | 0.77 |
0.4144 | 6.0 | 678 | 0.5780 | 0.83 |
0.3158 | 7.0 | 791 | 0.6068 | 0.8 |
0.1404 | 8.0 | 904 | 0.5806 | 0.84 |
0.1242 | 9.0 | 1017 | 0.5406 | 0.82 |
0.1086 | 10.0 | 1130 | 0.5492 | 0.82 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 1