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: 0.7337
- 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: 6e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1397 | 1.0 | 75 | 2.0011 | 0.45 |
| 1.4889 | 2.0 | 150 | 1.3599 | 0.66 |
| 1.0109 | 3.0 | 225 | 1.0052 | 0.74 |
| 0.7499 | 4.0 | 300 | 0.8884 | 0.77 |
| 0.5627 | 5.0 | 375 | 0.6333 | 0.86 |
| 0.4138 | 6.0 | 450 | 0.5492 | 0.81 |
| 0.2909 | 7.0 | 525 | 0.6417 | 0.81 |
| 0.1475 | 8.0 | 600 | 0.5900 | 0.84 |
| 0.0845 | 9.0 | 675 | 0.6959 | 0.84 |
| 0.0619 | 10.0 | 750 | 0.6587 | 0.86 |
| 0.0233 | 11.0 | 825 | 0.7675 | 0.82 |
| 0.0168 | 12.0 | 900 | 0.7352 | 0.83 |
| 0.0152 | 13.0 | 975 | 0.7293 | 0.87 |
| 0.0136 | 14.0 | 1050 | 0.7490 | 0.86 |
| 0.0123 | 15.0 | 1125 | 0.7337 | 0.86 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3