metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- calixtemayoraz/FMA-music-dataset
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-FMA-music
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: FMA-music-dataset
type: calixtemayoraz/FMA-music-dataset
metrics:
- name: Accuracy
type: accuracy
value: 0.45754716981132076
distilhubert-finetuned-FMA-music
This model is a fine-tuned version of ntu-spml/distilhubert on the FMA-music-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.8929
- Accuracy: 0.4575
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0384 | 1.0 | 238 | 2.2583 | 0.2358 |
| 1.9204 | 2.0 | 476 | 2.1387 | 0.2972 |
| 1.6768 | 3.0 | 714 | 1.9356 | 0.3774 |
| 1.7940 | 4.0 | 952 | 1.8584 | 0.3868 |
| 1.5281 | 5.0 | 1190 | 1.7814 | 0.4434 |
| 1.1608 | 6.0 | 1428 | 1.8745 | 0.4151 |
| 1.2103 | 7.0 | 1666 | 1.8066 | 0.4434 |
| 0.8522 | 8.0 | 1904 | 1.8688 | 0.4434 |
| 0.7455 | 9.0 | 2142 | 1.8818 | 0.4528 |
| 0.5444 | 10.0 | 2380 | 1.8929 | 0.4575 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2