metadata
base_model: yus988/pingpong-music_genres_classification-finetuned
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: pingpong-music_genres_classification-finetuned-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: 0.94
pingpong-music_genres_classification-finetuned-finetuned-gtzan
This model is a fine-tuned version of yus988/pingpong-music_genres_classification-finetuned on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.3171
- Accuracy: 0.94
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.817 | 1.0 | 56 | 1.5314 | 0.83 |
| 1.3804 | 1.99 | 112 | 1.2976 | 0.73 |
| 1.1139 | 2.99 | 168 | 0.7886 | 0.9 |
| 0.8946 | 3.99 | 224 | 0.6678 | 0.89 |
| 0.7045 | 4.98 | 280 | 0.8158 | 0.82 |
| 0.7178 | 6.0 | 337 | 0.7588 | 0.83 |
| 0.6513 | 6.99 | 393 | 0.4012 | 0.93 |
| 0.548 | 7.99 | 449 | 0.3258 | 0.93 |
| 0.3329 | 8.99 | 505 | 0.3477 | 0.93 |
| 0.2874 | 9.97 | 560 | 0.3171 | 0.94 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.2