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: 0.5757
- Accuracy: 0.83
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 |
|---|---|---|---|---|
| 1.7582 | 1.0 | 113 | 1.7912 | 0.45 |
| 1.2332 | 2.0 | 226 | 1.3051 | 0.64 |
| 1.0058 | 3.0 | 339 | 1.0200 | 0.71 |
| 0.6894 | 4.0 | 452 | 0.8303 | 0.79 |
| 0.5041 | 5.0 | 565 | 0.7038 | 0.79 |
| 0.3281 | 6.0 | 678 | 0.6500 | 0.82 |
| 0.2457 | 7.0 | 791 | 0.5476 | 0.82 |
| 0.3409 | 8.0 | 904 | 0.5793 | 0.83 |
| 0.1521 | 9.0 | 1017 | 0.5568 | 0.82 |
| 0.3542 | 10.0 | 1130 | 0.5757 | 0.83 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3