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: 0.77
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: 0.8925
- Accuracy: 0.77
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
---|---|---|---|---|
2.2921 | 0.98 | 14 | 2.2471 | 0.24 |
2.1865 | 1.96 | 28 | 2.0565 | 0.45 |
1.8969 | 2.95 | 42 | 1.7785 | 0.57 |
1.659 | 4.0 | 57 | 1.5368 | 0.6 |
1.4989 | 4.98 | 71 | 1.4186 | 0.66 |
1.3204 | 5.96 | 85 | 1.2775 | 0.68 |
1.2331 | 6.95 | 99 | 1.2127 | 0.69 |
1.1486 | 8.0 | 114 | 1.1122 | 0.73 |
1.0477 | 8.98 | 128 | 1.0672 | 0.73 |
1.0297 | 9.96 | 142 | 1.0007 | 0.77 |
0.9469 | 10.95 | 156 | 0.9488 | 0.77 |
0.8761 | 12.0 | 171 | 0.9259 | 0.77 |
0.8198 | 12.98 | 185 | 0.9115 | 0.78 |
0.8503 | 13.96 | 199 | 0.8922 | 0.78 |
0.8148 | 14.74 | 210 | 0.8925 | 0.77 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3