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-bs-16
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.87
distilhubert-finetuned-gtzan-bs-16
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: 0.5229
- 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: 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1955 | 1.0 | 57 | 2.1119 | 0.44 |
| 1.6916 | 2.0 | 114 | 1.5973 | 0.61 |
| 1.1805 | 3.0 | 171 | 1.1849 | 0.74 |
| 1.0924 | 4.0 | 228 | 0.9771 | 0.7 |
| 0.7794 | 5.0 | 285 | 0.8201 | 0.78 |
| 0.6335 | 6.0 | 342 | 0.6969 | 0.82 |
| 0.6178 | 7.0 | 399 | 0.6632 | 0.84 |
| 0.4232 | 8.0 | 456 | 0.5841 | 0.83 |
| 0.3135 | 9.0 | 513 | 0.5960 | 0.82 |
| 0.198 | 10.0 | 570 | 0.5557 | 0.83 |
| 0.1651 | 11.0 | 627 | 0.5957 | 0.84 |
| 0.1191 | 12.0 | 684 | 0.5640 | 0.85 |
| 0.1267 | 13.0 | 741 | 0.5604 | 0.84 |
| 0.0784 | 14.0 | 798 | 0.5233 | 0.85 |
| 0.1076 | 15.0 | 855 | 0.5229 | 0.87 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3