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: 1.1326
- Accuracy: 0.86
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.0942 | 1.0 | 225 | 1.9649 | 0.33 |
1.1113 | 2.0 | 450 | 1.2162 | 0.74 |
0.7961 | 3.0 | 675 | 0.9466 | 0.7 |
0.9005 | 4.0 | 900 | 0.6644 | 0.83 |
0.3228 | 5.0 | 1125 | 0.5374 | 0.85 |
0.4422 | 6.0 | 1350 | 0.7370 | 0.76 |
0.1283 | 7.0 | 1575 | 0.7234 | 0.84 |
0.0076 | 8.0 | 1800 | 0.8727 | 0.85 |
0.0037 | 9.0 | 2025 | 0.9373 | 0.84 |
0.1723 | 10.0 | 2250 | 0.9524 | 0.86 |
0.0016 | 11.0 | 2475 | 1.0349 | 0.84 |
0.0016 | 12.0 | 2700 | 1.0471 | 0.85 |
0.0011 | 13.0 | 2925 | 1.0802 | 0.85 |
0.0009 | 14.0 | 3150 | 1.0722 | 0.85 |
0.0007 | 15.0 | 3375 | 1.0931 | 0.85 |
0.0007 | 16.0 | 3600 | 1.1442 | 0.85 |
0.0007 | 17.0 | 3825 | 1.1239 | 0.85 |
0.0005 | 18.0 | 4050 | 1.1810 | 0.85 |
0.0006 | 19.0 | 4275 | 1.1560 | 0.85 |
0.0005 | 20.0 | 4500 | 1.1326 | 0.86 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3