metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-v3-finetuned-gtzan
results: []
distilhubert-finetuned-gtzan-v3-finetuned-gtzan
This model is a fine-tuned version of MariaK/distilhubert-finetuned-gtzan-v3 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5656
- Accuracy: 0.87
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.074 | 0.99 | 56 | 0.8150 | 0.79 |
| 0.0546 | 2.0 | 113 | 0.5489 | 0.86 |
| 0.0156 | 2.99 | 169 | 0.5313 | 0.88 |
| 0.0072 | 4.0 | 226 | 0.5566 | 0.87 |
| 0.0058 | 4.96 | 280 | 0.5656 | 0.87 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3