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: 0.7866666666666666
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: 0.6895
- Accuracy: 0.7867
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0249 | 1.0 | 88 | 1.9523 | 0.4667 |
| 1.3937 | 2.0 | 176 | 1.4094 | 0.62 |
| 1.2571 | 3.0 | 264 | 1.2109 | 0.6567 |
| 0.9939 | 4.0 | 352 | 0.9954 | 0.7067 |
| 0.7253 | 5.0 | 440 | 0.8227 | 0.78 |
| 0.6612 | 6.0 | 528 | 0.8231 | 0.76 |
| 0.3185 | 7.0 | 616 | 0.7390 | 0.79 |
| 0.2263 | 8.0 | 704 | 0.7152 | 0.78 |
| 0.4796 | 9.0 | 792 | 0.6964 | 0.7833 |
| 0.3332 | 10.0 | 880 | 0.6895 | 0.7867 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3