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: 0.83
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: 0.6334
- 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: 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: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.172 | 0.99 | 56 | 2.0068 | 0.5 |
| 1.6062 | 2.0 | 113 | 1.4539 | 0.57 |
| 1.2326 | 2.99 | 169 | 1.1605 | 0.67 |
| 1.0537 | 4.0 | 226 | 1.0225 | 0.73 |
| 0.8398 | 4.99 | 282 | 0.8392 | 0.8 |
| 0.7322 | 6.0 | 339 | 0.8435 | 0.76 |
| 0.6144 | 6.99 | 395 | 0.7217 | 0.83 |
| 0.5545 | 8.0 | 452 | 0.6526 | 0.84 |
| 0.4077 | 8.99 | 508 | 0.6378 | 0.83 |
| 0.4029 | 9.91 | 560 | 0.6334 | 0.83 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3