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: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8
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: 0.6141
- Accuracy: 0.8
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: 14
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1976 | 0.99 | 56 | 2.1232 | 0.36 |
| 1.5738 | 2.0 | 113 | 1.4564 | 0.68 |
| 1.2321 | 2.99 | 169 | 1.1535 | 0.74 |
| 0.9847 | 4.0 | 226 | 0.9799 | 0.74 |
| 0.8254 | 4.99 | 282 | 0.8700 | 0.78 |
| 0.6017 | 6.0 | 339 | 0.8466 | 0.74 |
| 0.631 | 6.99 | 395 | 0.6828 | 0.8 |
| 0.4887 | 8.0 | 452 | 0.6360 | 0.81 |
| 0.3798 | 8.99 | 508 | 0.6158 | 0.82 |
| 0.2427 | 10.0 | 565 | 0.6163 | 0.78 |
| 0.2077 | 10.99 | 621 | 0.6197 | 0.8 |
| 0.1506 | 12.0 | 678 | 0.5992 | 0.8 |
| 0.1467 | 12.99 | 734 | 0.6003 | 0.8 |
| 0.1967 | 13.88 | 784 | 0.6141 | 0.8 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3