metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-2
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-2
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: 0.6290
- 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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|
| 1.9857 | 1.0 | 90 | 1.8850 | 0.56 |
| 1.2735 | 2.0 | 180 | 1.3243 | 0.64 |
| 1.0297 | 3.0 | 270 | 1.0371 | 0.7 |
| 0.6856 | 4.0 | 360 | 0.9535 | 0.74 |
| 0.5659 | 5.0 | 450 | 0.7661 | 0.78 |
| 0.4125 | 6.0 | 540 | 0.6502 | 0.81 |
| 0.3883 | 7.0 | 630 | 0.6516 | 0.83 |
| 0.2705 | 8.0 | 720 | 0.6270 | 0.81 |
| 0.2147 | 9.0 | 810 | 0.6383 | 0.83 |
| 0.17 | 10.0 | 900 | 0.6290 | 0.83 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1