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: 0.81
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: 0.6173
- Accuracy: 0.81
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 1.9814 | 1.0 | 112 | 1.8342 | 0.53 |
| 1.3136 | 2.0 | 225 | 1.2448 | 0.66 |
| 1.023 | 3.0 | 337 | 0.9055 | 0.73 |
| 0.6619 | 4.0 | 450 | 0.8979 | 0.71 |
| 0.4521 | 5.0 | 562 | 0.7662 | 0.74 |
| 0.421 | 6.0 | 675 | 0.6843 | 0.78 |
| 0.2964 | 7.0 | 787 | 0.6774 | 0.79 |
| 0.1895 | 8.0 | 900 | 0.6137 | 0.82 |
| 0.187 | 9.0 | 1012 | 0.6087 | 0.82 |
| 0.1317 | 9.96 | 1120 | 0.6173 | 0.81 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2