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: None
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: 0.7755
- 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.2322 | 1.0 | 57 | 2.1521 | 0.37 |
1.7413 | 2.0 | 114 | 1.6606 | 0.47 |
1.3543 | 3.0 | 171 | 1.2698 | 0.69 |
0.9436 | 4.0 | 228 | 1.0440 | 0.71 |
0.7976 | 5.0 | 285 | 0.8338 | 0.79 |
0.6615 | 6.0 | 342 | 0.6933 | 0.84 |
0.5743 | 7.0 | 399 | 0.6180 | 0.84 |
0.4349 | 8.0 | 456 | 0.5931 | 0.84 |
0.2949 | 9.0 | 513 | 0.5794 | 0.85 |
0.2274 | 10.0 | 570 | 0.5901 | 0.84 |
0.1067 | 11.0 | 627 | 0.6496 | 0.81 |
0.104 | 12.0 | 684 | 0.6921 | 0.82 |
0.0781 | 13.0 | 741 | 0.6653 | 0.83 |
0.0245 | 14.0 | 798 | 0.6621 | 0.84 |
0.0144 | 15.0 | 855 | 0.7015 | 0.82 |
0.0104 | 16.0 | 912 | 0.7109 | 0.85 |
0.007 | 17.0 | 969 | 0.7472 | 0.84 |
0.0163 | 18.0 | 1026 | 0.7603 | 0.86 |
0.0039 | 19.0 | 1083 | 0.7710 | 0.85 |
0.0035 | 20.0 | 1140 | 0.7755 | 0.84 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1