metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-dropout0.25-split3-speed
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.8233333333333334
distilhubert-finetuned-gtzan-dropout0.25-split3-speed
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: 1.0262
- Accuracy: 0.8233
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1701 | 1.0 | 169 | 1.2158 | 0.6633 |
| 1.0623 | 2.0 | 338 | 0.9563 | 0.7033 |
| 0.6686 | 3.0 | 507 | 0.8979 | 0.7067 |
| 0.4958 | 4.0 | 676 | 0.8167 | 0.79 |
| 0.3174 | 5.0 | 845 | 0.8568 | 0.8033 |
| 0.1967 | 6.0 | 1014 | 0.8837 | 0.8067 |
| 0.1126 | 7.0 | 1183 | 0.9364 | 0.8267 |
| 0.0536 | 8.0 | 1352 | 1.0097 | 0.8233 |
| 0.039 | 9.0 | 1521 | 1.0470 | 0.82 |
| 0.0227 | 10.0 | 1690 | 1.0262 | 0.8233 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0
- Datasets 3.3.2
- Tokenizers 0.21.0