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
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: 0.83
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: 0.6581
- 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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 2.1424 | 1.0 | 57 | 2.0456 | 0.45 |
| 1.5766 | 2.0 | 114 | 1.5045 | 0.68 |
| 1.2474 | 3.0 | 171 | 1.2068 | 0.68 |
| 0.9574 | 4.0 | 228 | 1.1053 | 0.67 |
| 0.8741 | 5.0 | 285 | 0.8743 | 0.78 |
| 0.721 | 6.0 | 342 | 0.8041 | 0.77 |
| 0.6497 | 7.0 | 399 | 0.7521 | 0.81 |
| 0.5037 | 8.0 | 456 | 0.7051 | 0.82 |
| 0.5083 | 9.0 | 513 | 0.6693 | 0.82 |
| 0.4939 | 10.0 | 570 | 0.6581 | 0.83 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0