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
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: 0.86
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: 1.0283
- Accuracy: 0.86
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0235 | 0.99 | 28 | 1.0778 | 0.83 |
| 0.0072 | 1.98 | 56 | 1.0815 | 0.83 |
| 0.0004 | 2.97 | 84 | 1.1249 | 0.82 |
| 0.0003 | 4.0 | 113 | 1.1113 | 0.81 |
| 0.0002 | 4.99 | 141 | 1.1442 | 0.79 |
| 0.0137 | 5.98 | 169 | 1.0623 | 0.84 |
| 0.0048 | 6.97 | 197 | 1.0193 | 0.86 |
| 0.0087 | 8.0 | 226 | 1.0578 | 0.84 |
| 0.0055 | 8.99 | 254 | 1.0279 | 0.86 |
| 0.005 | 9.91 | 280 | 1.0283 | 0.86 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3