metadata
license: apache-2.0
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: 0.84
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: 0.6100
- Accuracy: 0.84
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1237
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0099 | 1.0 | 112 | 1.8954 | 0.42 |
| 1.4882 | 2.0 | 225 | 1.2842 | 0.68 |
| 1.0753 | 3.0 | 337 | 0.9071 | 0.76 |
| 0.7429 | 4.0 | 450 | 0.7317 | 0.81 |
| 0.3772 | 5.0 | 562 | 0.7185 | 0.81 |
| 0.3127 | 6.0 | 675 | 0.5813 | 0.84 |
| 0.1909 | 7.0 | 787 | 0.6122 | 0.84 |
| 0.1504 | 8.0 | 900 | 0.5366 | 0.86 |
| 0.1015 | 9.0 | 1012 | 0.5833 | 0.85 |
| 0.0612 | 10.0 | 1125 | 0.6030 | 0.84 |
| 0.0772 | 11.0 | 1237 | 0.6100 | 0.84 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2