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: 0.73
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: 1.3004
- Accuracy: 0.73
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 2.3007 | 0.97 | 7 | 2.2260 | 0.34 |
| 2.2424 | 1.93 | 14 | 2.0328 | 0.39 |
| 1.9803 | 2.9 | 21 | 1.8298 | 0.41 |
| 1.8344 | 4.0 | 29 | 1.6637 | 0.52 |
| 1.608 | 4.97 | 36 | 1.5523 | 0.58 |
| 1.5644 | 5.93 | 43 | 1.4443 | 0.67 |
| 1.4354 | 6.9 | 50 | 1.3870 | 0.7 |
| 1.38 | 8.0 | 58 | 1.3434 | 0.69 |
| 1.3521 | 8.97 | 65 | 1.3051 | 0.76 |
| 1.3542 | 9.66 | 70 | 1.3004 | 0.73 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3