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: 0.87
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: 0.7127
- Accuracy: 0.87
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2072 | 0.99 | 56 | 2.1364 | 0.37 |
| 1.6502 | 2.0 | 113 | 1.5282 | 0.63 |
| 1.2965 | 2.99 | 169 | 1.1371 | 0.69 |
| 1.0407 | 4.0 | 226 | 0.9643 | 0.74 |
| 0.6558 | 4.99 | 282 | 0.7303 | 0.76 |
| 0.3615 | 6.0 | 339 | 0.7688 | 0.78 |
| 0.3705 | 6.99 | 395 | 0.5905 | 0.85 |
| 0.2165 | 8.0 | 452 | 0.6988 | 0.81 |
| 0.1098 | 8.99 | 508 | 0.4604 | 0.9 |
| 0.0647 | 10.0 | 565 | 0.6756 | 0.87 |
| 0.0179 | 10.99 | 621 | 0.8108 | 0.83 |
| 0.0278 | 12.0 | 678 | 0.6674 | 0.87 |
| 0.0075 | 12.99 | 734 | 0.8230 | 0.83 |
| 0.0061 | 14.0 | 791 | 0.8155 | 0.85 |
| 0.0056 | 14.99 | 847 | 0.7233 | 0.87 |
| 0.0055 | 15.86 | 896 | 0.7127 | 0.87 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3