metadata
library_name: transformers
license: apache-2.0
base_model: MariaK/distilhubert-finetuned-gtzan-v2
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
model-index:
- name: MariaK/distilhubert-finetuned-gtzan-v2-finetuned-gtzan
results: []
MariaK/distilhubert-finetuned-gtzan-v2-finetuned-gtzan
This model is a fine-tuned version of MariaK/distilhubert-finetuned-gtzan-v2 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.3159
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0042 | 1.0 | 100 | 0.2518 |
| 0.0021 | 2.0 | 200 | 0.2875 |
| 0.0013 | 3.0 | 300 | 0.2987 |
| 0.0009 | 4.0 | 400 | 0.3040 |
| 0.0007 | 5.0 | 500 | 0.3037 |
| 0.0007 | 6.0 | 600 | 0.3100 |
| 0.0005 | 7.0 | 700 | 0.3114 |
| 0.0005 | 8.0 | 800 | 0.3095 |
| 0.0005 | 9.0 | 900 | 0.3147 |
| 0.0005 | 10.0 | 1000 | 0.3159 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0