metadata
license: apache-2.0
base_model: vpingale07/distilhubert-v2-v3
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: vpingale07/distilhubert-v2-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: 0.785
vpingale07/distilhubert-v2-finetuned-gtzan
This model is a fine-tuned version of vpingale07/distilhubert-v2-v3 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.0276
- Accuracy: 0.785
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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4443 | 1.0 | 100 | 0.7764 | 0.745 |
| 0.2265 | 2.0 | 200 | 0.8049 | 0.77 |
| 0.0928 | 3.0 | 300 | 0.9190 | 0.74 |
| 0.0661 | 4.0 | 400 | 0.9776 | 0.765 |
| 0.0095 | 5.0 | 500 | 1.0018 | 0.76 |
| 0.0069 | 6.0 | 600 | 0.9838 | 0.79 |
| 0.0046 | 7.0 | 700 | 1.0447 | 0.78 |
| 0.0041 | 8.0 | 800 | 1.0276 | 0.785 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2