metadata
license: apache-2.0
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: 0.84
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: 0.5916
- 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: 2.5e-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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2746 | 1.0 | 57 | 2.2507 | 0.28 |
| 2.0451 | 2.0 | 114 | 1.9551 | 0.5 |
| 1.6461 | 3.0 | 171 | 1.5926 | 0.68 |
| 1.5045 | 4.0 | 228 | 1.3429 | 0.75 |
| 1.2469 | 5.0 | 285 | 1.1902 | 0.75 |
| 1.12 | 6.0 | 342 | 1.1030 | 0.74 |
| 1.0061 | 7.0 | 399 | 0.9923 | 0.77 |
| 0.9674 | 8.0 | 456 | 0.8894 | 0.81 |
| 0.8545 | 9.0 | 513 | 0.8524 | 0.82 |
| 0.6644 | 10.0 | 570 | 0.8045 | 0.81 |
| 0.5531 | 11.0 | 627 | 0.8388 | 0.8 |
| 0.5411 | 12.0 | 684 | 0.6921 | 0.83 |
| 0.4759 | 13.0 | 741 | 0.7136 | 0.83 |
| 0.4236 | 14.0 | 798 | 0.6716 | 0.83 |
| 0.4235 | 15.0 | 855 | 0.6322 | 0.82 |
| 0.4098 | 16.0 | 912 | 0.6108 | 0.83 |
| 0.3988 | 17.0 | 969 | 0.6296 | 0.85 |
| 0.3493 | 18.0 | 1026 | 0.5921 | 0.83 |
| 0.3143 | 19.0 | 1083 | 0.5948 | 0.84 |
| 0.3036 | 20.0 | 1140 | 0.5916 | 0.84 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.3